Merge branch 'merge' into next

We want the irq fixes from the "merge" branch.

67 files changed, 551 insertions, 285 deletions

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 56a4df952fb..22e58a99f38 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -477,7 +477,7 @@ config ALPHA_BROKEN_IRQ_MASK
 
 config VGA_HOSE
 	bool
-	depends on ALPHA_GENERIC || ALPHA_TITAN || ALPHA_MARVEL || ALPHA_TSUNAMI
+	depends on VGA_CONSOLE && (ALPHA_GENERIC || ALPHA_TITAN || ALPHA_MARVEL || ALPHA_TSUNAMI)
 	default y
 	help
 	  Support VGA on an arbitrary hose; needed for several platforms
diff --git a/arch/alpha/include/asm/rtc.h b/arch/alpha/include/asm/rtc.h
index 1f7fba671ae..d70408d3667 100644
--- a/arch/alpha/include/asm/rtc.h
+++ b/arch/alpha/include/asm/rtc.h
@@ -1,14 +1,10 @@
 #ifndef _ALPHA_RTC_H
 #define _ALPHA_RTC_H
 
-#if defined(CONFIG_ALPHA_GENERIC)
+#if defined(CONFIG_ALPHA_MARVEL) && defined(CONFIG_SMP) \
+ || defined(CONFIG_ALPHA_GENERIC)
 # define get_rtc_time		alpha_mv.rtc_get_time
 # define set_rtc_time		alpha_mv.rtc_set_time
-#else
-# if defined(CONFIG_ALPHA_MARVEL) && defined(CONFIG_SMP)
-#  define get_rtc_time		marvel_get_rtc_time
-#  define set_rtc_time		marvel_set_rtc_time
-# endif
 #endif
 
 #include <asm-generic/rtc.h>
diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c
index 5e7c28f92f1..61893d7bdda 100644
--- a/arch/alpha/kernel/core_tsunami.c
+++ b/arch/alpha/kernel/core_tsunami.c
@@ -11,6 +11,7 @@
 #include <asm/core_tsunami.h>
 #undef __EXTERN_INLINE
 
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/sched.h>
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index 14a4b6a7cf5..407accc8087 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -317,7 +317,7 @@ marvel_init_irq(void)
 }
 
 static int 
-marvel_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+marvel_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct pci_controller *hose = dev->sysdata;
 	struct io7_port *io7_port = hose->sysdata;
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index cf006d40342..36586dba6fa 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1186,6 +1186,15 @@ if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
 
+config ARM_ERRATA_326103
+	bool "ARM errata: FSR write bit incorrect on a SWP to read-only memory"
+	depends on CPU_V6
+	help
+	  Executing a SWP instruction to read-only memory does not set bit 11
+	  of the FSR on the ARM 1136 prior to r1p0. This causes the kernel to
+	  treat the access as a read, preventing a COW from occurring and
+	  causing the faulting task to livelock.
+
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
 	depends on CPU_V6 || CPU_V6K
diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts
index 0b32925f214..e2fe3195c0d 100644
--- a/arch/arm/boot/dts/versatile-ab.dts
+++ b/arch/arm/boot/dts/versatile-ab.dts
@@ -173,7 +173,7 @@
 			mmc@5000 {
 				compatible = "arm,primecell";
 				reg = < 0x5000 0x1000>;
-				interrupts = <22>;
+				interrupts = <22 34>;
 			};
 			kmi@6000 {
 				compatible = "arm,pl050", "arm,primecell";
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index 166461073b7..7e817526906 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -41,7 +41,7 @@
 			mmc@b000 {
 				compatible = "arm,primecell";
 				reg = <0xb000 0x1000>;
-				interrupts = <23>;
+				interrupts = <23 34>;
 			};
 		};
 	};
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index d4c24d412a8..0f04d84582e 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -118,6 +118,13 @@ extern void iwmmxt_task_switch(struct thread_info *);
 extern void vfp_sync_hwstate(struct thread_info *);
 extern void vfp_flush_hwstate(struct thread_info *);
 
+struct user_vfp;
+struct user_vfp_exc;
+
+extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
+					   struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp __user *,
+				    struct user_vfp_exc __user *);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 60843eb0f61..73409e6c025 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -7,6 +7,8 @@
 
 	.macro set_tls_v6k, tp, tmp1, tmp2
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
+	mov	\tmp1, #0
+	mcr	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	.endm
 
 	.macro set_tls_v6, tp, tmp1, tmp2
@@ -15,6 +17,8 @@
 	mov	\tmp2, #0xffff0fff
 	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
 	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	movne	\tmp1, #0
+	mcrne	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 71ccdbfed66..8349d4e97e2 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -155,10 +155,10 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	}
 
 	c = irq_data_get_irq_chip(d);
-	if (c->irq_set_affinity)
-		c->irq_set_affinity(d, affinity, true);
-	else
+	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 80abafb9bf3..9650c143afc 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -906,27 +906,14 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-#ifdef __ARMEB__
-#define AUDIT_ARCH_NR AUDIT_ARCH_ARMEB
-#else
-#define AUDIT_ARCH_NR AUDIT_ARCH_ARM
-#endif
-
 asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 {
 	unsigned long ip;
 
-	/*
-	 * Save IP.  IP is used to denote syscall entry/exit:
-	 *  IP = 0 -> entry, = 1 -> exit
-	 */
-	ip = regs->ARM_ip;
-	regs->ARM_ip = why;
-
-	if (!ip)
+	if (why)
 		audit_syscall_exit(regs);
 	else
-		audit_syscall_entry(AUDIT_ARCH_NR, scno, regs->ARM_r0,
+		audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0,
 				    regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
 
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
@@ -936,6 +923,13 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 
 	current_thread_info()->syscall = scno;
 
+	/*
+	 * IP is used to denote syscall entry/exit:
+	 * IP = 0 -> entry, =1 -> exit
+	 */
+	ip = regs->ARM_ip;
+	regs->ARM_ip = why;
+
 	/* the 0x80 provides a way for the tracing parent to distinguish
 	   between a syscall stop and SIGTRAP delivery */
 	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 7cb532fc8aa..d68d1b69468 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -180,44 +180,23 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	const unsigned long magic = VFP_MAGIC;
 	const unsigned long size = VFP_STORAGE_SIZE;
 	int err = 0;
 
-	vfp_sync_hwstate(thread);
 	__put_user_error(magic, &frame->magic, err);
 	__put_user_error(size, &frame->size, err);
 
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
-			      sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
-
-	/*
-	 * Copy the exception registers.
-	 */
-	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
-	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+	if (err)
+		return -EFAULT;
 
-	return err ? -EFAULT : 0;
+	return vfp_preserve_user_clear_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 static int restore_vfp_context(struct vfp_sigframe __user *frame)
 {
-	struct thread_info *thread = current_thread_info();
-	struct vfp_hard_struct *h = &thread->vfpstate.hard;
 	unsigned long magic;
 	unsigned long size;
-	unsigned long fpexc;
 	int err = 0;
 
 	__get_user_error(magic, &frame->magic, err);
@@ -228,33 +207,7 @@ static int restore_vfp_context(struct vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	vfp_flush_hwstate(thread);
-
-	/*
-	 * Copy the floating point registers. There can be unused
-	 * registers see asm/hwcap.h for details.
-	 */
-	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
-				sizeof(h->fpregs));
-	/*
-	 * Copy the status and control register.
-	 */
-	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
-
-	/*
-	 * Sanitise and restore the exception registers.
-	 */
-	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
-	/* Ensure the VFP is enabled. */
-	fpexc |= FPEXC_EN;
-	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
-	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
-	h->fpexc = fpexc;
-
-	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
-	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
-
-	return err ? -EFAULT : 0;
+	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
 }
 
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index addbbe8028c..8f464465977 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -251,8 +251,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu = smp_processor_id();
 
-	printk("CPU%u: Booted secondary processor\n", cpu);
-
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
@@ -264,6 +262,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
 
+	printk("CPU%u: Booted secondary processor\n", cpu);
+
 	cpu_init();
 	preempt_disable();
 	trace_hardirqs_off();
@@ -510,10 +510,6 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	platform_cpu_kill(cpu);
-#endif
-
 	while (1)
 		cpu_relax();
 }
@@ -576,17 +572,25 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static void smp_kill_cpus(cpumask_t *mask)
+{
+	unsigned int cpu;
+	for_each_cpu(cpu, mask)
+		platform_cpu_kill(cpu);
+}
+#else
+static void smp_kill_cpus(cpumask_t *mask) { }
+#endif
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
+	struct cpumask mask;
 
-	if (num_online_cpus() > 1) {
-		struct cpumask mask;
-		cpumask_copy(&mask, cpu_online_mask);
-		cpumask_clear_cpu(smp_processor_id(), &mask);
-
-		smp_cross_call(&mask, IPI_CPU_STOP);
-	}
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+	smp_cross_call(&mask, IPI_CPU_STOP);
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
@@ -595,6 +599,8 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
+
+	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index d2b177905cd..76cbb055dd0 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -115,7 +115,7 @@ int kernel_execve(const char *filename,
 		  "Ir" (THREAD_START_SP - sizeof(regs)),
 		  "r" (&regs),
 		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
+		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
 
  out:
 	return ret;
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 1c672d9e665..f7fe1b9f317 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/kexec.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <mach/bridge-regs.h>
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index fcce7ff3763..cfd98b186fc 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -48,7 +48,7 @@ static irqreturn_t deferred_fiq(int irq, void *dev_id)
 	struct irq_chip *irq_chip = NULL;
 	int gpio, irq_num, fiq_count;
 
-	irq_desc = irq_to_desc(IH_GPIO_BASE);
+	irq_desc = irq_to_desc(gpio_to_irq(AMS_DELTA_GPIO_PIN_KEYBRD_CLK));
 	if (irq_desc)
 		irq_chip = irq_desc->irq_data.chip;
 
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 930c0d38043..740cee9369b 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -641,7 +641,7 @@ static struct regulator_consumer_supply dummy_supplies[] = {
 
 static void __init igep_init(void)
 {
-	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+	regulator_register_fixed(1, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 
 	/* Get IGEP2 hardware revision */
diff --git a/arch/arm/mach-omap2/include/mach/ctrl_module_pad_core_44xx.h b/arch/arm/mach-omap2/include/mach/ctrl_module_pad_core_44xx.h
index 1e2d3322f33..c88420de115 100644
--- a/arch/arm/mach-omap2/include/mach/ctrl_module_pad_core_44xx.h
+++ b/arch/arm/mach-omap2/include/mach/ctrl_module_pad_core_44xx.h
@@ -941,10 +941,10 @@
 #define OMAP4_DSI2_LANEENABLE_MASK				(0x7 << 29)
 #define OMAP4_DSI1_LANEENABLE_SHIFT				24
 #define OMAP4_DSI1_LANEENABLE_MASK				(0x1f << 24)
-#define OMAP4_DSI2_PIPD_SHIFT					19
-#define OMAP4_DSI2_PIPD_MASK					(0x1f << 19)
-#define OMAP4_DSI1_PIPD_SHIFT					14
-#define OMAP4_DSI1_PIPD_MASK					(0x1f << 14)
+#define OMAP4_DSI1_PIPD_SHIFT					19
+#define OMAP4_DSI1_PIPD_MASK					(0x1f << 19)
+#define OMAP4_DSI2_PIPD_SHIFT					14
+#define OMAP4_DSI2_PIPD_MASK					(0x1f << 14)
 
 /* CONTROL_MCBSPLP */
 #define OMAP4_ALBCTRLRX_FSX_SHIFT				31
diff --git a/arch/arm/mach-orion5x/mpp.h b/arch/arm/mach-orion5x/mpp.h
index eac68978a2c..db70e79a119 100644
--- a/arch/arm/mach-orion5x/mpp.h
+++ b/arch/arm/mach-orion5x/mpp.h
@@ -65,8 +65,8 @@
 #define MPP8_GIGE               MPP(8,  0x1, 0, 0, 1,   1,   1)
 
 #define MPP9_UNUSED		MPP(9,  0x0, 0, 0, 1,   1,   1)
-#define MPP9_GPIO		MPP(9,  0x0, 0, 0, 1,   1,   1)
-#define MPP9_GIGE               MPP(9,  0x1, 1, 1, 1,   1,   1)
+#define MPP9_GPIO		MPP(9,  0x0, 1, 1, 1,   1,   1)
+#define MPP9_GIGE               MPP(9,  0x1, 0, 0, 1,   1,   1)
 
 #define MPP10_UNUSED		MPP(10, 0x0, 0, 0, 1,   1,   1)
 #define MPP10_GPIO		MPP(10, 0x0, 1, 1, 1,   1,   1)
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index ff1f7cc11f8..80741992a9f 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,18 +26,23 @@ ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
- * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR (erratum 326103).
- * The test below covers all the write situations, including Java bytecodes
+ * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR.
  */
-	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
+#ifdef CONFIG_ARM_ERRATA_326103
+	ldr	ip, =0x4107b36
+	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
+	teq	ip, r3, lsr #4			@ r0 ARM1136?
+	bne	do_DataAbort
 	tst	r5, #PSR_J_BIT			@ Java?
+	tsteq	r5, #PSR_T_BIT			@ Thumb?
 	bne	do_DataAbort
-	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
-	ldreq	r3, [r4]			@ read aborted ARM instruction
+	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
+	ldr	r3, [r4]			@ read aborted ARM instruction
 #ifdef CONFIG_CPU_ENDIAN_BE8
-	reveq	r3, r3
+	rev	r3, r3
 #endif
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
+#endif
 	b	do_DataAbort
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index a53fd2aaa2f..2a8e380501e 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -32,6 +32,7 @@ static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
+static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
 
 struct l2x0_regs l2x0_saved_regs;
 
@@ -61,12 +62,7 @@ static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
 
-#ifdef CONFIG_PL310_ERRATA_753970
-	/* write to an unmmapped register */
-	writel_relaxed(0, base + L2X0_DUMMY_REG);
-#else
-	writel_relaxed(0, base + L2X0_CACHE_SYNC);
-#endif
+	writel_relaxed(0, base + sync_reg_offset);
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -85,10 +81,13 @@ static inline void l2x0_inv_line(unsigned long addr)
 }
 
 #if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
+static inline void debug_writel(unsigned long val)
+{
+	if (outer_cache.set_debug)
+		outer_cache.set_debug(val);
+}
 
-#define debug_writel(val)	outer_cache.set_debug(val)
-
-static void l2x0_set_debug(unsigned long val)
+static void pl310_set_debug(unsigned long val)
 {
 	writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
 }
@@ -98,7 +97,7 @@ static inline void debug_writel(unsigned long val)
 {
 }
 
-#define l2x0_set_debug	NULL
+#define pl310_set_debug	NULL
 #endif
 
 #ifdef CONFIG_PL310_ERRATA_588369
@@ -331,6 +330,11 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		else
 			ways = 8;
 		type = "L310";
+#ifdef CONFIG_PL310_ERRATA_753970
+		/* Unmapped register. */
+		sync_reg_offset = L2X0_DUMMY_REG;
+#endif
+		outer_cache.set_debug = pl310_set_debug;
 		break;
 	case L2X0_CACHE_ID_PART_L210:
 		ways = (aux >> 13) & 0xf;
@@ -379,7 +383,6 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	outer_cache.flush_all = l2x0_flush_all;
 	outer_cache.inv_all = l2x0_inv_all;
 	outer_cache.disable = l2x0_disable;
-	outer_cache.set_debug = l2x0_set_debug;
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 595079fa9d1..8f5813bbffb 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -293,11 +293,11 @@ EXPORT_SYMBOL(pfn_valid);
 #endif
 
 #ifndef CONFIG_SPARSEMEM
-static void arm_memory_present(void)
+static void __init arm_memory_present(void)
 {
 }
 #else
-static void arm_memory_present(void)
+static void __init arm_memory_present(void)
 {
 	struct memblock_region *reg;
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index b86f8933ff9..2c7cf2f9c83 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -618,8 +618,8 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 	}
 }
 
-static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
-	unsigned long phys, const struct mem_type *type)
+static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
+	unsigned long end, unsigned long phys, const struct mem_type *type)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index ecdb3da0dea..c58d896cd5c 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -916,6 +916,13 @@ void omap_start_dma(int lch)
 			l |= OMAP_DMA_CCR_BUFFERING_DISABLE;
 	l |= OMAP_DMA_CCR_EN;
 
+	/*
+	 * As dma_write() uses IO accessors which are weakly ordered, there
+	 * is no guarantee that data in coherent DMA memory will be visible
+	 * to the DMA device.  Add a memory barrier here to ensure that any
+	 * such data is visible prior to enabling DMA.
+	 */
+	mb();
 	p->dma_write(l, CCR, lch);
 
 	dma_chan[lch].flags |= OMAP_DMA_ACTIVE;
@@ -965,6 +972,13 @@ void omap_stop_dma(int lch)
 		p->dma_write(l, CCR, lch);
 	}
 
+	/*
+	 * Ensure that data transferred by DMA is visible to any access
+	 * after DMA has been disabled.  This is important for coherent
+	 * DMA regions.
+	 */
+	mb();
+
 	if (!omap_dma_in_1510_mode() && dma_chan[lch].next_lch != -1) {
 		int next_lch, cur_lch = lch;
 		char dma_chan_link_map[dma_lch_count];
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 858748eaa14..bc683b8219b 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -17,6 +17,8 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/uaccess.h>
+#include <linux/user.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -529,6 +531,103 @@ void vfp_flush_hwstate(struct thread_info *thread)
 }
 
 /*
+ * Save the current VFP state into the provided structures and prepare
+ * for entry into a new function (signal handler).
+ */
+int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
+				    struct user_vfp_exc __user *ufp_exc)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
+	int err = 0;
+
+	/* Ensure that the saved hwstate is up-to-date. */
+	vfp_sync_hwstate(thread);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_to_user(&ufp->fpregs, &hwstate->fpregs,
+			      sizeof(hwstate->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__put_user_error(hwstate->fpscr, &ufp->fpscr, err);
+
+	/*
+	 * Copy the exception registers.
+	 */
+	__put_user_error(hwstate->fpexc, &ufp_exc->fpexc, err);
+	__put_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
+	__put_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Ensure that VFP is disabled. */
+	vfp_flush_hwstate(thread);
+
+	/*
+	 * As per the PCS, clear the length and stride bits for function
+	 * entry.
+	 */
+	hwstate->fpscr &= ~(FPSCR_LENGTH_MASK | FPSCR_STRIDE_MASK);
+
+	/*
+	 * Disable VFP in the hwstate so that we can detect if it gets
+	 * used.
+	 */
+	hwstate->fpexc &= ~FPEXC_EN;
+	return 0;
+}
+
+/* Sanitise and restore the current VFP state from the provided structures. */
+int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
+			     struct user_vfp_exc __user *ufp_exc)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
+	unsigned long fpexc;
+	int err = 0;
+
+	/*
+	 * If VFP has been used, then disable it to avoid corrupting
+	 * the new thread state.
+	 */
+	if (hwstate->fpexc & FPEXC_EN)
+		vfp_flush_hwstate(thread);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
+				sizeof(hwstate->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+
+	/*
+	 * Sanitise and restore the exception registers.
+	 */
+	__get_user_error(fpexc, &ufp_exc->fpexc, err);
+
+	/* Ensure the VFP is enabled. */
+	fpexc |= FPEXC_EN;
+
+	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
+	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
+	hwstate->fpexc = fpexc;
+
+	__get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
+	__get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+
+	return err ? -EFAULT : 0;
+}
+
+/*
  * VFP hardware can lose all context when a CPU goes offline.
  * As we will be running in SMP mode with CPU hotplug, we will save the
  * hardware state at every thread switch.  We clear our held state when
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index f5104b7c52c..463fb3bbe11 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1174,7 +1174,7 @@ out:
 
 bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 {
-	return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL);
+	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/m68k/platform/520x/config.c b/arch/m68k/platform/520x/config.c
index 235947844f2..09df4b89e8b 100644
--- a/arch/m68k/platform/520x/config.c
+++ b/arch/m68k/platform/520x/config.c
@@ -22,7 +22,7 @@
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m520x_qspi_init(void)
 {
@@ -35,7 +35,7 @@ static void __init m520x_qspi_init(void)
 	writew(par, MCF_GPIO_PAR_UART);
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -79,7 +79,7 @@ void __init config_BSP(char *commandp, int size)
 	mach_sched_init = hw_timer_init;
 	m520x_uarts_init();
 	m520x_fec_init();
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m520x_qspi_init();
 #endif
 }
diff --git a/arch/m68k/platform/523x/config.c b/arch/m68k/platform/523x/config.c
index c8b405d5a96..d47dfd8f50a 100644
--- a/arch/m68k/platform/523x/config.c
+++ b/arch/m68k/platform/523x/config.c
@@ -22,7 +22,7 @@
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m523x_qspi_init(void)
 {
@@ -36,7 +36,7 @@ static void __init m523x_qspi_init(void)
 	writew(par, MCFGPIO_PAR_TIMER);
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -58,7 +58,7 @@ void __init config_BSP(char *commandp, int size)
 {
 	mach_sched_init = hw_timer_init;
 	m523x_fec_init();
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m523x_qspi_init();
 #endif
 }
diff --git a/arch/m68k/platform/5249/config.c b/arch/m68k/platform/5249/config.c
index bbf05135bb9..300e729a58d 100644
--- a/arch/m68k/platform/5249/config.c
+++ b/arch/m68k/platform/5249/config.c
@@ -51,7 +51,7 @@ static struct platform_device *m5249_devices[] __initdata = {
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m5249_qspi_init(void)
 {
@@ -61,7 +61,7 @@ static void __init m5249_qspi_init(void)
 	mcf_mapirq2imr(MCF_IRQ_QSPI, MCFINTC_QSPI);
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -90,7 +90,7 @@ void __init config_BSP(char *commandp, int size)
 #ifdef CONFIG_M5249C3
 	m5249_smc91x_init();
 #endif
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m5249_qspi_init();
 #endif
 }
diff --git a/arch/m68k/platform/527x/config.c b/arch/m68k/platform/527x/config.c
index f91a53294c3..b3cb378c5e9 100644
--- a/arch/m68k/platform/527x/config.c
+++ b/arch/m68k/platform/527x/config.c
@@ -23,7 +23,7 @@
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m527x_qspi_init(void)
 {
@@ -42,7 +42,7 @@ static void __init m527x_qspi_init(void)
 #endif
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -90,7 +90,7 @@ void __init config_BSP(char *commandp, int size)
 	mach_sched_init = hw_timer_init;
 	m527x_uarts_init();
 	m527x_fec_init();
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m527x_qspi_init();
 #endif
 }
diff --git a/arch/m68k/platform/528x/config.c b/arch/m68k/platform/528x/config.c
index d4492926614..c5f11ba49be 100644
--- a/arch/m68k/platform/528x/config.c
+++ b/arch/m68k/platform/528x/config.c
@@ -24,7 +24,7 @@
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m528x_qspi_init(void)
 {
@@ -32,7 +32,7 @@ static void __init m528x_qspi_init(void)
 	__raw_writeb(0x07, MCFGPIO_PQSPAR);
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -98,7 +98,7 @@ void __init config_BSP(char *commandp, int size)
 	mach_sched_init = hw_timer_init;
 	m528x_uarts_init();
 	m528x_fec_init();
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m528x_qspi_init();
 #endif
 }
diff --git a/arch/m68k/platform/532x/config.c b/arch/m68k/platform/532x/config.c
index 2bec3477b73..37082d02f2b 100644
--- a/arch/m68k/platform/532x/config.c
+++ b/arch/m68k/platform/532x/config.c
@@ -30,7 +30,7 @@
 
 /***************************************************************************/
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 
 static void __init m532x_qspi_init(void)
 {
@@ -38,7 +38,7 @@ static void __init m532x_qspi_init(void)
 	writew(0x01f0, MCF_GPIO_PAR_QSPI);
 }
 
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 /***************************************************************************/
 
@@ -77,7 +77,7 @@ void __init config_BSP(char *commandp, int size)
 	mach_sched_init = hw_timer_init;
 	m532x_uarts_init();
 	m532x_fec_init();
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	m532x_qspi_init();
 #endif
 
diff --git a/arch/m68k/platform/coldfire/device.c b/arch/m68k/platform/coldfire/device.c
index 7af97362b95..3aa77ddea89 100644
--- a/arch/m68k/platform/coldfire/device.c
+++ b/arch/m68k/platform/coldfire/device.c
@@ -121,7 +121,7 @@ static struct platform_device mcf_fec1 = {
 #endif /* MCFFEC_BASE1 */
 #endif /* CONFIG_FEC */
 
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 /*
  *	The ColdFire QSPI module is an SPI protocol hardware block used
  *	on a number of different ColdFire CPUs.
@@ -274,7 +274,7 @@ static struct platform_device mcf_qspi = {
 	.resource		= mcf_qspi_resources,
 	.dev.platform_data	= &mcf_qspi_data,
 };
-#endif /* CONFIG_SPI_COLDFIRE_QSPI */
+#endif /* IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI) */
 
 static struct platform_device *mcf_devices[] __initdata = {
 	&mcf_uart,
@@ -284,7 +284,7 @@ static struct platform_device *mcf_devices[] __initdata = {
 	&mcf_fec1,
 #endif
 #endif
-#ifdef CONFIG_SPI_COLDFIRE_QSPI
+#if IS_ENABLED(CONFIG_SPI_COLDFIRE_QSPI)
 	&mcf_qspi,
 #endif
 };
diff --git a/arch/mips/ath79/dev-wmac.c b/arch/mips/ath79/dev-wmac.c
index e2150705206..9c717bf98ff 100644
--- a/arch/mips/ath79/dev-wmac.c
+++ b/arch/mips/ath79/dev-wmac.c
@@ -58,8 +58,8 @@ static void __init ar913x_wmac_setup(void)
 
 static int ar933x_wmac_reset(void)
 {
-	ath79_device_reset_clear(AR933X_RESET_WMAC);
 	ath79_device_reset_set(AR933X_RESET_WMAC);
+	ath79_device_reset_clear(AR933X_RESET_WMAC);
 
 	return 0;
 }
diff --git a/arch/mips/include/asm/mach-jz4740/irq.h b/arch/mips/include/asm/mach-jz4740/irq.h
index a865c983c70..5ad1a9c113c 100644
--- a/arch/mips/include/asm/mach-jz4740/irq.h
+++ b/arch/mips/include/asm/mach-jz4740/irq.h
@@ -45,7 +45,7 @@
 #define JZ4740_IRQ_LCD		JZ4740_IRQ(30)
 
 /* 2nd-level interrupts */
-#define JZ4740_IRQ_DMA(x)	(JZ4740_IRQ(32) + (X))
+#define JZ4740_IRQ_DMA(x)	(JZ4740_IRQ(32) + (x))
 
 #define JZ4740_IRQ_INTC_GPIO(x) (JZ4740_IRQ_GPIO0 - (x))
 #define JZ4740_IRQ_GPIO(x)	(JZ4740_IRQ(48) + (x))
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 73c0d45798d..9b02cfba744 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -37,12 +37,6 @@ extern void tlbmiss_handler_setup_pgd(unsigned long pgd);
 		write_c0_xcontext((unsigned long) smp_processor_id() << 51); \
 	} while (0)
 
-
-static inline unsigned long get_current_pgd(void)
-{
-	return PHYS_TO_XKSEG_CACHED((read_c0_context() >> 11) & ~0xfffUL);
-}
-
 #else /* CONFIG_MIPS_PGD_C0_CONTEXT: using  pgd_current*/
 
 /*
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 185ca00c4c8..d5a338a1739 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -257,11 +257,8 @@ asmlinkage int sys_sigsuspend(nabi_no_regargs struct pt_regs regs)
 		return -EFAULT;
 	sigdelsetmask(&newset, ~_BLOCKABLE);
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -286,11 +283,8 @@ asmlinkage int sys_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
 		return -EFAULT;
 	sigdelsetmask(&newset, ~_BLOCKABLE);
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -362,10 +356,7 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 		goto badframe;
 
 	sigdelsetmask(&blocked, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = blocked;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&blocked);
 
 	sig = restore_sigcontext(&regs, &frame->sf_sc);
 	if (sig < 0)
@@ -401,10 +392,7 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
@@ -580,12 +568,7 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 	if (ret)
 		return ret;
 
-	spin_lock_irq(&current->sighand->siglock);
-	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&current->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	block_sigmask(ka, sig);
 
 	return ret;
 }
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 06b5da392e2..ac3b8d89aae 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -290,11 +290,8 @@ asmlinkage int sys32_sigsuspend(nabi_no_regargs struct pt_regs regs)
 		return -EFAULT;
 	sigdelsetmask(&newset, ~_BLOCKABLE);
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -318,11 +315,8 @@ asmlinkage int sys32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
 		return -EFAULT;
 	sigdelsetmask(&newset, ~_BLOCKABLE);
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -488,10 +482,7 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 		goto badframe;
 
 	sigdelsetmask(&blocked, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = blocked;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&blocked);
 
 	sig = restore_sigcontext32(&regs, &frame->sf_sc);
 	if (sig < 0)
@@ -529,10 +520,7 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index ae29e894ab8..86eb4b04631 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -93,11 +93,8 @@ asmlinkage int sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
 	sigset_from_compat(&newset, &uset);
 	sigdelsetmask(&newset, ~_BLOCKABLE);
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
@@ -121,10 +118,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h
index 4e9626836ba..d1d864b81ba 100644
--- a/arch/parisc/include/asm/hardware.h
+++ b/arch/parisc/include/asm/hardware.h
@@ -2,7 +2,6 @@
 #define _PARISC_HARDWARE_H
 
 #include <linux/mod_devicetable.h>
-#include <asm/pdc.h>
 
 #define HWTYPE_ANY_ID		PA_HWTYPE_ANY_ID
 #define HVERSION_ANY_ID		PA_HVERSION_ANY_ID
@@ -95,12 +94,14 @@ struct bc_module {
 #define HPHW_MC	       15
 #define HPHW_FAULTY    31
 
+struct parisc_device_id;
 
 /* hardware.c: */
 extern const char *parisc_hardware_description(struct parisc_device_id *id);
 extern enum cpu_type parisc_get_cpu_type(unsigned long hversion);
 
 struct pci_dev;
+struct hardware_path;
 
 /* drivers.c: */
 extern struct parisc_device *alloc_pa_dev(unsigned long hpa,
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index a84cc1f925f..4e0e7dbf0f3 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -160,5 +160,11 @@ extern int npmem_ranges;
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
+#include <asm/pdc.h>
+
+#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
+
+/* DEFINITION OF THE ZERO-PAGE (PAG0) */
+/* based on work by Jason Eckhardt (jason@equator.com) */
 
 #endif /* _PARISC_PAGE_H */
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index 4ca510b3c6f..7f0f2d23059 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -343,8 +343,6 @@
 
 #ifdef __KERNEL__
 
-#include <asm/page.h> /* for __PAGE_OFFSET */
-
 extern int pdc_type;
 
 /* Values for pdc_type */
@@ -677,11 +675,6 @@ static inline char * os_id_to_string(u16 os_id) {
 
 #endif /* __KERNEL__ */
 
-#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
-
-/* DEFINITION OF THE ZERO-PAGE (PAG0) */
-/* based on work by Jason Eckhardt (jason@equator.com) */
-
 /* flags of the device_path */
 #define	PF_AUTOBOOT	0x80
 #define	PF_AUTOSEARCH	0x40
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 22dadeb5869..ee99f233935 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -44,6 +44,8 @@ struct vm_area_struct;
 
 #endif /* !__ASSEMBLY__ */
 
+#include <asm/page.h>
+
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 804aa28ab1d..3516e0b2704 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/ldcw.h>
 #include <asm/processor.h>
 #include <asm/spinlock_types.h>
 
diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c
index 4f004596a6e..47341aa208f 100644
--- a/arch/parisc/kernel/pdc_cons.c
+++ b/arch/parisc/kernel/pdc_cons.c
@@ -50,6 +50,7 @@
 #include <linux/init.h>
 #include <linux/major.h>
 #include <linux/tty.h>
+#include <asm/page.h>		/* for PAGE0 */
 #include <asm/pdc.h>		/* for iodc_call() proto and friends */
 
 static DEFINE_SPINLOCK(pdc_console_lock);
@@ -104,7 +105,7 @@ static int pdc_console_tty_open(struct tty_struct *tty, struct file *filp)
 
 static void pdc_console_tty_close(struct tty_struct *tty, struct file *filp)
 {
-	if (!tty->count) {
+	if (tty->count == 1) {
 		del_timer_sync(&pdc_console_timer);
 		tty_port_tty_set(&tty_port, NULL);
 	}
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 7c0774397b8..70e105d6242 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -29,6 +29,7 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
+#include <asm/page.h>
 #include <asm/param.h>
 #include <asm/pdc.h>
 #include <asm/led.h>
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 29f13570214..ed1718feb9d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -584,23 +584,19 @@ _GLOBAL(ret_from_except_lite)
 fast_exc_return_irq:
 restore:
 	/*
-	 * This is the main kernel exit path, we first check if we
-	 * have to change our interrupt state.
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
 	 */
 	ld	r5,SOFTE(r1)
 	lbz	r6,PACASOFTIRQEN(r13)
-	cmpwi	cr1,r5,0
-	cmpw	cr0,r5,r6
-	beq	cr0,4f
+	cmpwi	cr0,r5,0
+	beq	restore_irq_off
 
-	/* We do, handle disable first, which is easy */
-	bne	cr1,3f;
- 	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13);
-	TRACE_DISABLE_INTS
-	b	4f
+	/* We are enabling, were we already enabled ? Yes, just return */
+	cmpwi	cr0,r6,1
+	beq	cr0,do_restore
 
-3:	/*
+	/*
 	 * We are about to soft-enable interrupts (we are hard disabled
 	 * at this point). We check if there's anything that needs to
 	 * be replayed first.
@@ -622,7 +618,7 @@ restore_no_replay:
 	/*
 	 * Final return path. BookE is handled in a different file
 	 */
-4:
+do_restore:
 #ifdef CONFIG_PPC_BOOK3E
 	b	.exception_return_book3e
 #else
@@ -696,6 +692,25 @@ fast_exception_return:
 #endif /* CONFIG_PPC_BOOK3E */
 
 	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+restore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13);
+	TRACE_DISABLE_INTS
+	b	do_restore
+
+	/*
 	 * Something did happen, check if a re-emit is needed
 	 * (this also clears paca->irq_happened)
 	 */
@@ -744,6 +759,9 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 1:	b	.ret_from_except /* What else to do here ? */
  
+
+
+3:
 do_work:
 #ifdef CONFIG_PREEMPT
 	andi.	r0,r3,MSR_PR	/* Returning to user mode? */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c6c6f3b7f8c..641da9e868c 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAG
+	else {
+		/*
+		 * We should already be hard disabled here. We had bugs
+		 * where that wasn't the case so let's dbl check it and
+		 * warn if we are wrong. Only do that when IRQ tracing
+		 * is enabled as mfmsr() can be costly.
+		 */
+		if (WARN_ON(mfmsr() & MSR_EE))
+			__hard_irq_disable();
+	}
+#endif /* CONFIG_TRACE_IRQFLAG */
+
 	set_soft_enabled(0);
 
 	/*
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ddc485a529f..c3beaeef3f6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -258,6 +258,8 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 			    !(memslot->userspace_addr & (s - 1))) {
 				start &= ~(s - 1);
 				pgsize = s;
+				get_page(hpage);
+				put_page(page);
 				page = hpage;
 			}
 		}
@@ -281,11 +283,8 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	err = 0;
 
  out:
-	if (got) {
-		if (PageHuge(page))
-			page = compound_head(page);
+	if (got)
 		put_page(page);
-	}
 	return err;
 
  up_err:
@@ -678,8 +677,15 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		SetPageDirty(page);
 
  out_put:
-	if (page)
-		put_page(page);
+	if (page) {
+		/*
+		 * We drop pages[0] here, not page because page might
+		 * have been set to the head page of a compound, but
+		 * we have to drop the reference on the correct tail
+		 * page to match the get inside gup()
+		 */
+		put_page(pages[0]);
+	}
 	return ret;
 
  out_unlock:
@@ -979,6 +985,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 			pa = *physp;
 		}
 		page = pfn_to_page(pa >> PAGE_SHIFT);
+		get_page(page);
 	} else {
 		hva = gfn_to_hva_memslot(memslot, gfn);
 		npages = get_user_pages_fast(hva, 1, 1, pages);
@@ -991,8 +998,6 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 		page = compound_head(page);
 		psize <<= compound_order(page);
 	}
-	if (!kvm->arch.using_mmu_notifiers)
-		get_page(page);
 	offset = gpa & (psize - 1);
 	if (nb_ret)
 		*nb_ret = psize - offset;
@@ -1003,7 +1008,6 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 {
 	struct page *page = virt_to_page(va);
 
-	page = compound_head(page);
 	put_page(page);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 01294a5099d..108d1f58017 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1192,8 +1192,6 @@ static void unpin_slot(struct kvm *kvm, int slot_id)
 				continue;
 			pfn = physp[j] >> PAGE_SHIFT;
 			page = pfn_to_page(pfn);
-			if (PageHuge(page))
-				page = compound_head(page);
 			SetPageDirty(page);
 			put_page(page);
 		}
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af1ab5e9a69..5c3cf2d04e4 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -48,7 +48,13 @@
 /*
  * Assembly helpers from arch/powerpc/net/bpf_jit.S:
  */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+#define DECLARE_LOAD_FUNC(func)	\
+	extern u8 func[], func##_negative_offset[], func##_positive_offset[]
+
+DECLARE_LOAD_FUNC(sk_load_word);
+DECLARE_LOAD_FUNC(sk_load_half);
+DECLARE_LOAD_FUNC(sk_load_byte);
+DECLARE_LOAD_FUNC(sk_load_byte_msh);
 
 #define FUNCTION_DESCR_SIZE	24
 
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e85cc..55ba3855a97 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -31,14 +31,13 @@
  * then branch directly to slow_path_XXX if required.  (In fact, could
  * load a spare GPR with the address of slow_path_generic and pass size
  * as an argument, making the call site a mtlr, li and bllr.)
- *
- * Technically, the "is addr < 0" check is unnecessary & slowing down
- * the ABS path, as it's statically checked on generation.
  */
 	.globl	sk_load_word
 sk_load_word:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_word_neg
+	.globl	sk_load_word_positive_offset
+sk_load_word_positive_offset:
 	/* Are we accessing past headlen? */
 	subi	r_scratch1, r_HL, 4
 	cmpd	r_scratch1, r_addr
@@ -51,7 +50,9 @@ sk_load_word:
 	.globl	sk_load_half
 sk_load_half:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_half_neg
+	.globl	sk_load_half_positive_offset
+sk_load_half_positive_offset:
 	subi	r_scratch1, r_HL, 2
 	cmpd	r_scratch1, r_addr
 	blt	bpf_slow_path_half
@@ -61,7 +62,9 @@ sk_load_half:
 	.globl	sk_load_byte
 sk_load_byte:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_byte_neg
+	.globl	sk_load_byte_positive_offset
+sk_load_byte_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte
 	lbzx	r_A, r_D, r_addr
@@ -69,22 +72,20 @@ sk_load_byte:
 
 /*
  * BPF_S_LDX_B_MSH: ldxb  4*([offset]&0xf)
- * r_addr is the offset value, already known positive
+ * r_addr is the offset value
  */
 	.globl sk_load_byte_msh
 sk_load_byte_msh:
+	cmpdi	r_addr, 0
+	blt	bpf_slow_path_byte_msh_neg
+	.globl sk_load_byte_msh_positive_offset
+sk_load_byte_msh_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte_msh
 	lbzx	r_X, r_D, r_addr
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
 
-bpf_error:
-	/* Entered with cr0 = lt */
-	li	r3, 0
-	/* Generated code will 'blt epilogue', returning 0. */
-	blr
-
 /* Call out to skb_copy_bits:
  * We'll need to back up our volatile regs first; we have
  * local variable space at r1+(BPF_PPC_STACK_BASIC).
@@ -136,3 +137,84 @@ bpf_slow_path_byte_msh:
 	lbz	r_X, BPF_PPC_STACK_BASIC+(2*8)(r1)
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
+
+/* Call out to bpf_internal_load_pointer_neg_helper:
+ * We'll need to back up our volatile regs first; we have
+ * local variable space at r1+(BPF_PPC_STACK_BASIC).
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define sk_negative_common(SIZE)				\
+	mflr	r0;						\
+	std	r0, 16(r1);					\
+	/* R3 goes in parameter space of caller's frame */	\
+	std	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	std	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	std	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	stdu	r1, -BPF_PPC_SLOWPATH_FRAME(r1);		\
+	/* R3 = r_skb, as passed */				\
+	mr	r4, r_addr;					\
+	li	r5, SIZE;					\
+	bl	bpf_internal_load_pointer_neg_helper;		\
+	/* R3 != 0 on success */				\
+	addi	r1, r1, BPF_PPC_SLOWPATH_FRAME;			\
+	ld	r0, 16(r1);					\
+	ld	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	ld	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	mtlr	r0;						\
+	cmpldi	r3, 0;						\
+	beq	bpf_error_slow;	/* cr0 = EQ */			\
+	mr	r_addr, r3;					\
+	ld	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	/* Great success! */
+
+bpf_slow_path_word_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_word_negative_offset
+sk_load_word_negative_offset:
+	sk_negative_common(4)
+	lwz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_half_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_half_negative_offset
+sk_load_half_negative_offset:
+	sk_negative_common(2)
+	lhz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_negative_offset
+sk_load_byte_negative_offset:
+	sk_negative_common(1)
+	lbz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_msh_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_msh_negative_offset
+sk_load_byte_msh_negative_offset:
+	sk_negative_common(1)
+	lbz	r_X, 0(r_addr)
+	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
+	blr
+
+bpf_error_slow:
+	/* fabricate a cr0 = lt */
+	li	r_scratch1, -1
+	cmpdi	r_scratch1, 0
+bpf_error:
+	/* Entered with cr0 = lt */
+	li	r3, 0
+	/* Generated code will 'blt epilogue', returning 0. */
+	blr
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 73619d3aeb6..2dc8b148484 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -127,6 +127,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	PPC_BLR();
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
 /* Assemble the body code between the prologue & epilogue. */
 static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			      struct codegen_context *ctx,
@@ -391,21 +394,16 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 
 			/*** Absolute loads from packet header/data ***/
 		case BPF_S_LD_W_ABS:
-			func = sk_load_word;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 			goto common_load;
 		case BPF_S_LD_H_ABS:
-			func = sk_load_half;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 			goto common_load;
 		case BPF_S_LD_B_ABS:
-			func = sk_load_byte;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 		common_load:
-			/*
-			 * Load from [K].  Reference with the (negative)
-			 * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported.
-			 */
+			/* Load from [K]. */
 			ctx->seen |= SEEN_DATAREF;
-			if ((int)K < 0)
-				return -ENOTSUPP;
 			PPC_LI64(r_scratch1, func);
 			PPC_MTLR(r_scratch1);
 			PPC_LI32(r_addr, K);
@@ -429,7 +427,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		common_load_ind:
 			/*
 			 * Load from [X + K].  Negative offsets are tested for
-			 * in the helper functions, and result in a 'ret 0'.
+			 * in the helper functions.
 			 */
 			ctx->seen |= SEEN_DATAREF | SEEN_XREG;
 			PPC_LI64(r_scratch1, func);
@@ -443,13 +441,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 		case BPF_S_LDX_B_MSH:
-			/*
-			 * x86 version drops packet (RET 0) when K<0, whereas
-			 * interpreter does allow K<0 (__load_pointer, special
-			 * ancillary data).  common_load returns ENOTSUPP if K<0,
-			 * so we fall back to interpreter & filter works.
-			 */
-			func = sk_load_byte_msh;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 			goto common_load;
 			break;
 
diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c
index 38d48a59879..9708851a8b9 100644
--- a/arch/sparc/kernel/central.c
+++ b/arch/sparc/kernel/central.c
@@ -269,4 +269,4 @@ static int __init sunfire_init(void)
 	return 0;
 }
 
-subsys_initcall(sunfire_init);
+fs_initcall(sunfire_init);
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index b57a5942ba6..874162a11ce 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -495,11 +495,11 @@ xcall_fetch_glob_regs:
 	stx		%o7, [%g1 + GR_SNAP_O7]
 	stx		%i7, [%g1 + GR_SNAP_I7]
 	/* Don't try this at home kids... */
-	rdpr		%cwp, %g2
-	sub		%g2, 1, %g7
+	rdpr		%cwp, %g3
+	sub		%g3, 1, %g7
 	wrpr		%g7, %cwp
 	mov		%i7, %g7
-	wrpr		%g2, %cwp
+	wrpr		%g3, %cwp
 	stx		%g7, [%g1 + GR_SNAP_RPC]
 	sethi		%hi(trap_block), %g7
 	or		%g7, %lo(trap_block), %g7
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d14cc6b79a..c9866b0b77d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -81,7 +81,7 @@ config X86
 	select CLKEVT_I8253
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
-	select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
+	select DCACHE_WORD_ACCESS
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index d3c0b027766..fb7117a4ade 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -403,13 +403,11 @@ static void print_absolute_symbols(void)
 	for (i = 0; i < ehdr.e_shnum; i++) {
 		struct section *sec = &secs[i];
 		char *sym_strtab;
-		Elf32_Sym *sh_symtab;
 		int j;
 
 		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
 		}
-		sh_symtab = sec->symtab;
 		sym_strtab = sec->link->strtab;
 		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
 			Elf32_Sym *sym;
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 4824fb45560..07b3a68d2d2 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -294,8 +294,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	/* OK, This is the point of no return */
 	set_personality(PER_LINUX);
-	set_thread_flag(TIF_IA32);
-	current->mm->context.ia32_compat = 1;
+	set_personality_ia32(false);
 
 	setup_new_exec(bprm);
 
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 6fe6767b712..e58f03b206c 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -43,4 +43,37 @@ static inline unsigned long has_zero(unsigned long a)
 	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
 }
 
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, dummy;
+
+	asm(
+		"1:\tmov %2,%0\n"
+		"2:\n"
+		".section .fixup,\"ax\"\n"
+		"3:\t"
+		"lea %2,%1\n\t"
+		"and %3,%1\n\t"
+		"mov (%1),%0\n\t"
+		"leal %2,%%ecx\n\t"
+		"andl %4,%%ecx\n\t"
+		"shll $3,%%ecx\n\t"
+		"shr %%cl,%0\n\t"
+		"jmp 2b\n"
+		".previous\n"
+		_ASM_EXTABLE(1b, 3b)
+		:"=&r" (ret),"=&c" (dummy)
+		:"m" (*(unsigned long *)addr),
+		 "i" (-sizeof(unsigned long)),
+		 "i" (sizeof(unsigned long)-1));
+	return ret;
+}
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1c67ca100e4..146bb6218ee 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -580,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/* re-enable TopologyExtensions if switched off by BIOS */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		u64 val;
+
+		if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+			val |= 1ULL << 54;
+			wrmsrl_amd_safe(0xc0011005, val);
+			rdmsrl(0xc0011005, val);
+			if (val & (1ULL << 54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				printk(KERN_INFO FW_INFO "CPU: Re-enabling "
+				  "disabled Topology Extensions Support\n");
+			}
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ba6e4a27e..e554e5ad2fe 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -79,7 +79,6 @@ struct kvm_task_sleep_node {
 	u32 token;
 	int cpu;
 	bool halted;
-	struct mm_struct *mm;
 };
 
 static struct kvm_task_sleep_head {
@@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.mm = current->active_mm;
 	n.halted = idle || preempt_count() > 1;
-	atomic_inc(&n.mm->mm_count);
 	init_waitqueue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	spin_unlock(&b->lock);
@@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
 static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 {
 	hlist_del_init(&n->link);
-	if (!n->mm)
-		return;
-	mmdrop(n->mm);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (waitqueue_active(&n->wq))
@@ -207,7 +201,7 @@ again:
 		 * async PF was not yet handled.
 		 * Add dummy entry for the token.
 		 */
-		n = kmalloc(sizeof(*n), GFP_ATOMIC);
+		n = kzalloc(sizeof(*n), GFP_ATOMIC);
 		if (!n) {
 			/*
 			 * Allocation failed! Busy wait while other cpu
@@ -219,7 +213,6 @@ again:
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		n->mm = NULL;
 		init_waitqueue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 733ca39f367..43d8b48b23e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -423,6 +423,7 @@ void set_personality_ia32(bool x32)
 		current_thread_info()->status |= TS_COMPAT;
 	}
 }
+EXPORT_SYMBOL_GPL(set_personality_ia32);
 
 unsigned long get_wchan(struct task_struct *p)
 {
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da37..5a98aa27218 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+		size_t atom_size;
 
+		/*
+		 * On 64bit, use PMD_SIZE for atom_size so that embedded
+		 * percpu areas are aligned to PMD.  This, in the future,
+		 * can also allow using PMD mappings in vmalloc area.  Use
+		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
+		 * and large vmalloc area allocs can easily fail.
+		 */
+#ifdef CONFIG_X86_64
+		atom_size = PMD_SIZE;
+#else
+		atom_size = PAGE_SIZE;
+#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 91a5e989abc..185a2b823a2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6581,6 +6581,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 	vcpu->arch.apf.halted = false;
+	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 }
 
 bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c
index 66d377e334f..646e3b5b4bb 100644
--- a/arch/x86/platform/geode/net5501.c
+++ b/arch/x86/platform/geode/net5501.c
@@ -63,7 +63,7 @@ static struct gpio_led net5501_leds[] = {
 		.name = "net5501:1",
 		.gpio = 6,
 		.default_trigger = "default-on",
-		.active_low = 1,
+		.active_low = 0,
 	},
 };
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a8f8844b8d3..95dccce8e97 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -63,6 +63,7 @@
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
 #include <asm/mwait.h>
+#include <asm/pci_x86.h>
 
 #ifdef CONFIG_ACPI
 #include <linux/acpi.h>
@@ -809,9 +810,40 @@ static void xen_io_delay(void)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+	WARN_ON(1);
+	return x;
+}
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+	return ((x)>>24) & 0xFFu;
+}
 static u32 xen_apic_read(u32 reg)
 {
-	return 0;
+	struct xen_platform_op op = {
+		.cmd = XENPF_get_cpuinfo,
+		.interface_version = XENPF_INTERFACE_VERSION,
+		.u.pcpu_info.xen_cpuid = 0,
+	};
+	int ret = 0;
+
+	/* Shouldn't need this as APIC is turned off for PV, and we only
+	 * get called on the bootup processor. But just in case. */
+	if (!xen_initial_domain() || smp_processor_id())
+		return 0;
+
+	if (reg == APIC_LVR)
+		return 0x10;
+
+	if (reg != APIC_ID)
+		return 0;
+
+	ret = HYPERVISOR_dom0_op(&op);
+	if (ret)
+		return 0;
+
+	return op.u.pcpu_info.apic_id << 24;
 }
 
 static void xen_apic_write(u32 reg, u32 val)
@@ -849,6 +881,8 @@ static void set_xen_basic_apic_ops(void)
 	apic->icr_write = xen_apic_icr_write;
 	apic->wait_icr_idle = xen_apic_wait_icr_idle;
 	apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
+	apic->set_apic_id = xen_set_apic_id;
+	apic->get_apic_id = xen_get_apic_id;
 }
 
 #endif
@@ -1365,8 +1399,10 @@ asmlinkage void __init xen_start_kernel(void)
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
-		
-
+#ifdef CONFIG_PCI
+	/* PCI BIOS service won't work from a PV guest. */
+	pci_probe &= ~PCI_PROBE_BIOS;
+#endif
 	xen_raw_console_write("about to get started...\n");
 
 	xen_setup_runstate_info(0);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b8e279479a6..69f5857660a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
 	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long pfn = mfn_to_pfn(mfn);
+
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+		if (unlikely(pfn == ~0))
+			val = flags & ~_PAGE_PRESENT;
+		else
+			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
 	}
 
 	return val;