Merge branch 'memdup_user_nul' into work.misc

124 files changed, 864 insertions, 524 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 2c2ac3f3ff80..6312f607932f 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -445,6 +445,7 @@ config LINUX_LINK_BASE
 	  However some customers have peripherals mapped at this addr, so
 	  Linux needs to be scooted a bit.
 	  If you don't know what the above means, leave this setting alone.
+	  This needs to match memory start address specified in Device Tree
 
 config HIGHMEM
 	bool "High Memory Support"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index cf0cf34eeb24..aeb19021099e 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -81,7 +81,7 @@ endif
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
-KBUILD_CFLAGS_MODULE	+= -mlong-calls
+KBUILD_CFLAGS_MODULE	+= -mlong-calls -mno-millicode
 
 # Finally dump eveything into kernel build system
 KBUILD_CFLAGS	+= $(cflags-y)
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index f3db32154973..44a578c10732 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -46,6 +46,7 @@
 			snps,pbl = < 32 >;
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
+			max-speed = <100>;
 		};
 
 		ehci@0x40000 {
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index b0eb0e7fe21d..fc81879bc1f5 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -17,7 +17,8 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x0 0x80000000 0x0 0x40000000	/* 1 GB low mem */
+		/* CONFIG_LINUX_LINK_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MB low mem */
 		       0x1 0x00000000 0x0 0x40000000>;	/* 1 GB highmem */
 	};
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index abf06e81c929..210ef3e72332 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -62,9 +62,7 @@ extern int ioc_exists;
 #define ARC_REG_IC_IVIC		0x10
 #define ARC_REG_IC_CTRL		0x11
 #define ARC_REG_IC_IVIL		0x19
-#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4)
 #define ARC_REG_IC_PTAG		0x1E
-#endif
 #define ARC_REG_IC_PTAG_HI	0x1F
 
 /* Bit val in IC_CTRL */
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index 6ff657a904b6..c28e6c347b49 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -23,7 +23,7 @@
  * @dt_compat:		Array of device tree 'compatible' strings
  * 			(XXX: although only 1st entry is looked at)
  * @init_early:		Very early callback [called from setup_arch()]
- * @init_cpu_smp:	for each CPU as it is coming up (SMP as well as UP)
+ * @init_per_cpu:	for each CPU as it is coming up (SMP as well as UP)
  * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
  * @init_machine:	arch initcall level callback (e.g. populate static
  * 			platform devices or parse Devicetree)
@@ -35,7 +35,7 @@ struct machine_desc {
 	const char		**dt_compat;
 	void			(*init_early)(void);
 #ifdef CONFIG_SMP
-	void			(*init_cpu_smp)(unsigned int);
+	void			(*init_per_cpu)(unsigned int);
 #endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 133c867d15af..991380438d6b 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -48,7 +48,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
  * @init_early_smp:	A SMP specific h/w block can init itself
  * 			Could be common across platforms so not covered by
  * 			mach_desc->init_early()
- * @init_irq_cpu:	Called for each core so SMP h/w block driver can do
+ * @init_per_cpu:	Called for each core so SMP h/w block driver can do
  * 			any needed setup per cpu (e.g. IPI request)
  * @cpu_kick:		For Master to kickstart a cpu (optionally at a PC)
  * @ipi_send:		To send IPI to a @cpu
@@ -57,7 +57,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
 struct plat_smp_ops {
 	const char 	*info;
 	void		(*init_early_smp)(void);
-	void		(*init_irq_cpu)(int cpu);
+	void		(*init_per_cpu)(int cpu);
 	void		(*cpu_kick)(int cpu, unsigned long pc);
 	void		(*ipi_send)(int cpu);
 	void		(*ipi_clear)(int irq);
diff --git a/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h
index 7ca628b6ee2a..c11a25bb8158 100644
--- a/arch/arc/include/asm/unwind.h
+++ b/arch/arc/include/asm/unwind.h
@@ -112,7 +112,6 @@ struct unwind_frame_info {
 
 extern int arc_unwind(struct unwind_frame_info *frame);
 extern void arc_unwind_init(void);
-extern void arc_unwind_setup(void);
 extern void *unwind_add_table(struct module *module, const void *table_start,
 			      unsigned long table_size);
 extern void unwind_remove_table(void *handle, int init_only);
@@ -152,9 +151,6 @@ static inline void arc_unwind_init(void)
 {
 }
 
-static inline void arc_unwind_setup(void)
-{
-}
 #define unwind_add_table(a, b, c)
 #define unwind_remove_table(a, b)
 
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 26c156827479..0394f9f61b46 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = {
 static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
 			 irq_hw_number_t hw)
 {
-	if (irq == TIMER0_IRQ || irq == IPI_IRQ)
+	/*
+	 * core intc IRQs [16, 23]:
+	 * Statically assigned always private-per-core (Timers, WDT, IPI, PCT)
+	 */
+	if (hw < 24) {
+		/*
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 */
+		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
-	else
+	} else {
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+	}
 
 	return 0;
 }
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 2ee226546c6a..ba17f85285cf 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -29,11 +29,11 @@ void __init init_IRQ(void)
 
 #ifdef CONFIG_SMP
 	/* a SMP H/w block could do IPI IRQ request here */
-	if (plat_smp_ops.init_irq_cpu)
-		plat_smp_ops.init_irq_cpu(smp_processor_id());
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(smp_processor_id());
 
-	if (machine_desc->init_cpu_smp)
-		machine_desc->init_cpu_smp(smp_processor_id());
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(smp_processor_id());
 #endif
 }
 
@@ -51,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+/*
+ * API called for requesting percpu interrupts - called by each CPU
+ *  - For boot CPU, actually request the IRQ with genirq core + enables
+ *  - For subsequent callers only enable called locally
+ *
+ * Relies on being called by boot cpu first (i.e. request called ahead) of
+ * any enable as expected by genirq. Hence Suitable only for TIMER, IPI
+ * which are guaranteed to be setup on boot core first.
+ * Late probed peripherals such as perf can't use this as there no guarantee
+ * of being called on boot CPU first.
+ */
+
 void arc_request_percpu_irq(int irq, int cpu,
                             irqreturn_t (*isr)(int irq, void *dev),
                             const char *irq_nm,
@@ -60,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu,
 	if (!cpu) {
 		int rc;
 
+#ifdef CONFIG_ISA_ARCOMPACT
 		/*
-		 * These 2 calls are essential to making percpu IRQ APIs work
-		 * Ideally these details could be hidden in irq chip map function
-		 * but the issue is IPIs IRQs being static (non-DT) and platform
-		 * specific, so we can't identify them there.
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 *
+		 * For ARCv2, this is done in irq map function since we know
+		 * which irqs are strictly per cpu
 		 */
 		irq_set_percpu_devid(irq);
-		irq_modify_status(irq, IRQ_NOAUTOEN, 0);  /* @irq, @clr, @set */
+#endif
 
 		rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev);
 		if (rc)
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 74a9b074ac3e..bd237acdf4f2 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -132,7 +132,7 @@ static void mcip_probe_n_setup(void)
 struct plat_smp_ops plat_smp_ops = {
 	.info		= smp_cpuinfo_buf,
 	.init_early_smp	= mcip_probe_n_setup,
-	.init_irq_cpu	= mcip_setup_per_cpu,
+	.init_per_cpu	= mcip_setup_per_cpu,
 	.ipi_send	= mcip_ipi_send,
 	.ipi_clear	= mcip_ipi_clear,
 };
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 0c08bb1ce15a..8b134cfe5e1f 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -428,12 +428,11 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 
 #endif /* CONFIG_ISA_ARCV2 */
 
-void arc_cpu_pmu_irq_init(void)
+static void arc_cpu_pmu_irq_init(void *data)
 {
-	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	int irq = *(int *)data;
 
-	arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr,
-			       "ARC perf counters", pmu_cpu);
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
 
 	/* Clear all pending interrupt flags */
 	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
@@ -515,7 +514,6 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 	if (has_interrupts) {
 		int irq = platform_get_irq(pdev, 0);
-		unsigned long flags;
 
 		if (irq < 0) {
 			pr_err("Cannot get IRQ number for the platform\n");
@@ -524,24 +522,12 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 		arc_pmu->irq = irq;
 
-		/*
-		 * arc_cpu_pmu_irq_init() needs to be called on all cores for
-		 * their respective local PMU.
-		 * However we use opencoded on_each_cpu() to ensure it is called
-		 * on core0 first, so that arc_request_percpu_irq() sets up
-		 * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable
-		 * perf IRQ on non master cores.
-		 * see arc_request_percpu_irq()
-		 */
-		preempt_disable();
-		local_irq_save(flags);
-		arc_cpu_pmu_irq_init();
-		local_irq_restore(flags);
-		smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1);
-		preempt_enable();
-
-		/* Clean all pending interrupt flags */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
+		/* intc map function ensures irq_set_percpu_devid() called */
+		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
+				   this_cpu_ptr(&arc_pmu_cpu));
+
+		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+
 	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index c33e77c0ad3e..e1b87444ea9a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -429,7 +429,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	arc_unwind_init();
-	arc_unwind_setup();
 }
 
 static int __init customize_machine(void)
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 580587805fa3..ef6e9e15b82a 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -132,11 +132,11 @@ void start_kernel_secondary(void)
 	pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
 
 	/* Some SMP H/w setup - for each cpu */
-	if (plat_smp_ops.init_irq_cpu)
-		plat_smp_ops.init_irq_cpu(cpu);
+	if (plat_smp_ops.init_per_cpu)
+		plat_smp_ops.init_per_cpu(cpu);
 
-	if (machine_desc->init_cpu_smp)
-		machine_desc->init_cpu_smp(cpu);
+	if (machine_desc->init_per_cpu)
+		machine_desc->init_per_cpu(cpu);
 
 	arc_local_timer_setup();
 
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 7352475451f6..5eb707640e9c 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc)
 
 static unsigned long read_pointer(const u8 **pLoc,
 				  const void *end, signed ptrType);
+static void init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long));
+
+/*
+ * wrappers for header alloc (vs. calling one vs. other at call site)
+ * to elide section mismatches warnings
+ */
+static void *__init unw_hdr_alloc_early(unsigned long sz)
+{
+	return __alloc_bootmem_nopanic(sz, sizeof(unsigned int),
+				       MAX_DMA_ADDRESS);
+}
+
+static void *unw_hdr_alloc(unsigned long sz)
+{
+	return kmalloc(sz, GFP_KERNEL);
+}
 
 static void init_unwind_table(struct unwind_table *table, const char *name,
 			      const void *core_start, unsigned long core_size,
@@ -209,6 +226,8 @@ void __init arc_unwind_init(void)
 			  __start_unwind, __end_unwind - __start_unwind,
 			  NULL, 0);
 	  /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/
+
+	init_unwind_hdr(&root_table, unw_hdr_alloc_early);
 }
 
 static const u32 bad_cie, not_fde;
@@ -241,8 +260,8 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
 	e2->fde = v;
 }
 
-static void __init setup_unwind_table(struct unwind_table *table,
-				      void *(*alloc) (unsigned long))
+static void init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long))
 {
 	const u8 *ptr;
 	unsigned long tableSize = table->size, hdrSize;
@@ -277,10 +296,10 @@ static void __init setup_unwind_table(struct unwind_table *table,
 		if (cie == &not_fde)
 			continue;
 		if (cie == NULL || cie == &bad_cie)
-			return;
+			goto ret_err;
 		ptrType = fde_pointer_type(cie);
 		if (ptrType < 0)
-			return;
+			goto ret_err;
 
 		ptr = (const u8 *)(fde + 2);
 		if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde,
@@ -296,13 +315,15 @@ static void __init setup_unwind_table(struct unwind_table *table,
 	}
 
 	if (tableSize || !n)
-		return;
+		goto ret_err;
 
 	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
 	    + 2 * n * sizeof(unsigned long);
+
 	header = alloc(hdrSize);
 	if (!header)
-		return;
+		goto ret_err;
+
 	header->version = 1;
 	header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native;
 	header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4;
@@ -340,18 +361,10 @@ static void __init setup_unwind_table(struct unwind_table *table,
 	table->hdrsz = hdrSize;
 	smp_wmb();
 	table->header = (const void *)header;
-}
-
-static void *__init balloc(unsigned long sz)
-{
-	return __alloc_bootmem_nopanic(sz,
-				       sizeof(unsigned int),
-				       __pa(MAX_DMA_ADDRESS));
-}
+	return;
 
-void __init arc_unwind_setup(void)
-{
-	setup_unwind_table(&root_table, balloc);
+ret_err:
+	panic("Attention !!! Dwarf FDE parsing errors\n");;
 }
 
 #ifdef CONFIG_MODULES
@@ -377,6 +390,8 @@ void *unwind_add_table(struct module *module, const void *table_start,
 			  table_start, table_size,
 			  NULL, 0);
 
+	init_unwind_hdr(table, unw_hdr_alloc);
+
 #ifdef UNWIND_DEBUG
 	unw_debug("Table added for [%s] %lx %lx\n",
 		module->name, table->core.pc, table->core.range);
@@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only)
 	info.init_only = init_only;
 
 	unlink_table(&info); /* XXX: SMP */
+	kfree(table->header);
 	kfree(table);
 }
 
@@ -588,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie)
 	const u8 *ptr = (const u8 *)(cie + 2);
 	unsigned version = *ptr;
 
-	if (version != 1)
-		return -1;	/* unsupported */
-
 	if (*++ptr) {
 		const char *aug;
 		const u8 *end = (const u8 *)(cie + 1) + *cie;
@@ -1002,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame)
 		ptr = (const u8 *)(cie + 2);
 		end = (const u8 *)(cie + 1) + *cie;
 		frame->call_frame = 1;
-		if ((state.version = *ptr) != 1)
-			cie = NULL;	/* unsupported version */
-		else if (*++ptr) {
+		if (*++ptr) {
 			/* check if augmentation size is first (thus present) */
 			if (*ptr == 'z') {
 				while (++ptr < end && *ptr) {
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 065ee6bfa82a..92dd92cad7f9 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -111,7 +111,7 @@ void __kunmap_atomic(void *kv)
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
-noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr)
+static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
 	pgd_t *pgd_k;
 	pud_t *pud_k;
@@ -127,7 +127,7 @@ noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr)
 	return pte_k;
 }
 
-void kmap_init(void)
+void __init kmap_init(void)
 {
 	/* Due to recursive include hell, we can't do this in processor.h */
 	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index a9305b5a2cd4..7d2c4fbf4f22 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -51,7 +51,9 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	int in_use = 0;
 
 	if (!low_mem_sz) {
-		BUG_ON(base != low_mem_start);
+		if (base != low_mem_start)
+			panic("CONFIG_LINUX_LINK_BASE != DT memory { }");
+
 		low_mem_sz = size;
 		in_use = 1;
 	} else {
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index d83ff9c9701e..de8791a4d131 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -74,7 +74,7 @@
 		reg = <0x48240200 0x100>;
 		interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	local_timer: timer@48240600 {
@@ -82,7 +82,7 @@
 		reg = <0x48240600 0x100>;
 		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	l2-cache-controller@48242000 {
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index cc88728d751d..a38af2bfbfcf 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -259,6 +259,14 @@
 		ti,invert-autoidle-bit;
 	};
 
+	mpu_periphclk: mpu_periphclk {
+		#clock-cells = <0>;
+		compatible = "fixed-factor-clock";
+		clocks = <&dpll_mpu_m2_ck>;
+		clock-mult = <1>;
+		clock-div = <2>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,am3-dpll-clock";
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index ad6de73ed5a5..e74df327cdd3 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -184,6 +184,7 @@
 							regulator-name = "VDD_SDHC_1V8";
 							regulator-min-microvolt = <1800000>;
 							regulator-max-microvolt = <1800000>;
+							regulator-always-on;
 						};
 					};
 				};
diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi
index 8ea177f375dd..fb1da99996ea 100644
--- a/arch/arm/boot/dts/berlin2q.dtsi
+++ b/arch/arm/boot/dts/berlin2q.dtsi
@@ -118,7 +118,8 @@
 		sdhci0: sdhci@ab0000 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0000 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -126,7 +127,8 @@
 		sdhci1: sdhci@ab0800 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0800 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -135,7 +137,7 @@
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab1000 0x200>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>;
+			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>;
 			clock-names = "io", "core";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 3c99cfa1a876..eee636de4cd8 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -218,6 +218,7 @@
 			reg = <0x480c8000 0x2000>;
 			interrupts = <77>;
 			ti,hwmods = "mailbox";
+			#mbox-cells = <1>;
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <12>;
 			mbox_dsp: mbox_dsp {
@@ -279,8 +280,11 @@
 			ti,spi-num-cs = <4>;
 			ti,hwmods = "mcspi1";
 			dmas = <&edma 16 &edma 17
-				&edma 18 &edma 19>;
-			dma-names = "tx0", "rx0", "tx1", "rx1";
+				&edma 18 &edma 19
+				&edma 20 &edma 21
+				&edma 22 &edma 23>;
+			dma-names = "tx0", "rx0", "tx1", "rx1",
+				    "tx2", "rx2", "tx3", "rx3";
 		};
 
 		mmc1: mmc@48060000 {
diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts
index 58adf176425a..a51834e1dd27 100644
--- a/arch/arm/boot/dts/imx6q-gw5400-a.dts
+++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts
@@ -154,7 +154,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index 7b31fdb79ced..dc0cebfe22d7 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -94,7 +94,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
index 1b66328a8498..18cd4114a23e 100644
--- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
@@ -154,7 +154,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
index 7c51839ff934..eea90f37bbb8 100644
--- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
@@ -155,7 +155,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
index 929e0b37bd9e..6c11a2ae35ef 100644
--- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
@@ -145,7 +145,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 8263fc18a7d9..d354d406954d 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -113,14 +113,14 @@
 &clks {
 	assigned-clocks = <&clks IMX6QDL_PLL4_BYPASS_SRC>,
 			  <&clks IMX6QDL_PLL4_BYPASS>,
-			  <&clks IMX6QDL_CLK_PLL4_POST_DIV>,
 			  <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
+			  <&clks IMX6QDL_CLK_PLL4_POST_DIV>;
 	assigned-clock-parents = <&clks IMX6QDL_CLK_LVDS2_IN>,
 				 <&clks IMX6QDL_PLL4_BYPASS_SRC>,
 				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
 				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-	assigned-clock-rates = <0>, <0>, <24576000>;
+	assigned-clock-rates = <0>, <0>, <0>, <0>, <24576000>;
 };
 
 &ecspi1 {
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index 1a78f013f37a..b75f7b2b7c4a 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -189,3 +189,7 @@
 	};
 };
 
+&uart3 {
+	interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH
+			       &omap4_pmx_core OMAP4_UART3_RX>;
+};
diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
index 2d4250b1faf8..68b479b8772c 100644
--- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts
+++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts
@@ -83,6 +83,7 @@
 		reg = <0x5d>;
 		interrupt-parent = <&pio>;
 		interrupts = <0 3 IRQ_TYPE_LEVEL_HIGH>; /* PA3 */
+		touchscreen-swapped-x-y;
 	};
 };
 
diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi
index 40c23a0b7cfc..ec1aa64ded68 100644
--- a/arch/arm/boot/dts/tegra124-nyan.dtsi
+++ b/arch/arm/boot/dts/tegra124-nyan.dtsi
@@ -399,7 +399,7 @@
 
 	/* CPU DFLL clock */
 	clock@0,70110000 {
-		status = "okay";
+		status = "disabled";
 		vdd-cpu-supply = <&vdd_cpu>;
 		nvidia,i2c-fs-rate = <400000>;
 	};
diff --git a/arch/arm/boot/dts/vf610-colibri.dtsi b/arch/arm/boot/dts/vf610-colibri.dtsi
index 19fe045b8334..2d7eab755210 100644
--- a/arch/arm/boot/dts/vf610-colibri.dtsi
+++ b/arch/arm/boot/dts/vf610-colibri.dtsi
@@ -18,8 +18,3 @@
 		reg = <0x80000000 0x10000000>;
 	};
 };
-
-&L2 {
-	arm,data-latency = <2 1 2>;
-	arm,tag-latency = <3 2 3>;
-};
diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi
index 5f8eb1bd782b..58bc6e448be5 100644
--- a/arch/arm/boot/dts/vf610.dtsi
+++ b/arch/arm/boot/dts/vf610.dtsi
@@ -19,7 +19,7 @@
 		reg = <0x40006000 0x1000>;
 		cache-unified;
 		cache-level = <2>;
-		arm,data-latency = <1 1 1>;
+		arm,data-latency = <3 3 3>;
 		arm,tag-latency = <2 2 2>;
 	};
 };
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 0d5acc2cdc8e..3cd1b27f2697 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -178,8 +178,10 @@
 				compatible = "fsl,vf610-sai";
 				reg = <0x40031000 0x1000>;
 				interrupts = <86 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks VF610_CLK_SAI2>;
-				clock-names = "sai";
+				clocks = <&clks VF610_CLK_SAI2>,
+					<&clks VF610_CLK_SAI2_DIV>,
+					<&clks 0>, <&clks 0>;
+				clock-names = "bus", "mclk1", "mclk2", "mclk3";
 				dma-names = "tx", "rx";
 				dmas = <&edma0 0 21>,
 					<&edma0 0 20>;
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 6607d976e07d..7da5503c0591 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -21,6 +21,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <asm/barrier.h>
 
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
 #define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 8cc85a4ebec2..35c9db857ebe 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -510,10 +510,14 @@ __copy_to_user_std(void __user *to, const void *from, unsigned long n);
 static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+#ifndef CONFIG_UACCESS_WITH_MEMCPY
 	unsigned int __ua_flags = uaccess_save_and_enable();
 	n = arm_copy_to_user(to, from, n);
 	uaccess_restore(__ua_flags);
 	return n;
+#else
+	return arm_copy_to_user(to, from, n);
+#endif
 }
 
 extern unsigned long __must_check
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 7a7c4cea5523..4adfb46e3ee9 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -95,6 +95,22 @@ void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
 	char buf[64];
+#ifndef CONFIG_CPU_V7M
+	unsigned int domain;
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Get the domain register for the parent context. In user
+	 * mode, we don't save the DACR, so lets use what it should
+	 * be. For other modes, we place it after the pt_regs struct.
+	 */
+	if (user_mode(regs))
+		domain = DACR_UACCESS_ENABLE;
+	else
+		domain = *(unsigned int *)(regs + 1);
+#else
+	domain = get_domain();
+#endif
+#endif
 
 	show_regs_print_info(KERN_DEFAULT);
 
@@ -123,21 +139,8 @@ void __show_regs(struct pt_regs *regs)
 
 #ifndef CONFIG_CPU_V7M
 	{
-		unsigned int domain = get_domain();
 		const char *segment;
 
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-		/*
-		 * Get the domain register for the parent context. In user
-		 * mode, we don't save the DACR, so lets use what it should
-		 * be. For other modes, we place it after the pt_regs struct.
-		 */
-		if (user_mode(regs))
-			domain = DACR_UACCESS_ENABLE;
-		else
-			domain = *(unsigned int *)(regs + 1);
-#endif
-
 		if ((domain & domain_mask(DOMAIN_USER)) ==
 		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
 			segment = "none";
@@ -163,11 +166,11 @@ void __show_regs(struct pt_regs *regs)
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac = get_domain();
+			unsigned int transbase;
 			asm("mrc p15, 0, %0, c2, c0\n\t"
 			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
-			  	transbase, dac);
+				transbase, domain);
 		}
 #endif
 		asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl));
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 5b26e7efa9ea..c3fe769d7558 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -36,10 +36,10 @@
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
-	"	mov		%2, %1\n"			\
-	"0:	ldrex"B"	%1, [%3]\n"			\
-	"1:	strex"B"	%0, %2, [%3]\n"			\
+	"0:	ldrex"B"	%2, [%3]\n"			\
+	"1:	strex"B"	%0, %1, [%3]\n"			\
 	"	cmp		%0, #0\n"			\
+	"	moveq		%1, %2\n"			\
 	"	movne		%0, %4\n"			\
 	"2:\n"							\
 	"	.section	 .text.fixup,\"ax\"\n"		\
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index d72b90905132..588bbc288396 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 static unsigned long noinline
 __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 {
+	unsigned long ua_flags;
 	int atomic;
 
 	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
@@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 		if (tocopy > n)
 			tocopy = n;
 
+		ua_flags = uaccess_save_and_enable();
 		memcpy((void *)to, from, tocopy);
+		uaccess_restore(ua_flags);
 		to += tocopy;
 		from += tocopy;
 		n -= tocopy;
@@ -145,14 +148,21 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 	 * With frame pointer disabled, tail call optimization kicks in
 	 * as well making this test almost invisible.
 	 */
-	if (n < 64)
-		return __copy_to_user_std(to, from, n);
-	return __copy_to_user_memcpy(to, from, n);
+	if (n < 64) {
+		unsigned long ua_flags = uaccess_save_and_enable();
+		n = __copy_to_user_std(to, from, n);
+		uaccess_restore(ua_flags);
+	} else {
+		n = __copy_to_user_memcpy(to, from, n);
+	}
+	return n;
 }
 	
 static unsigned long noinline
 __clear_user_memset(void __user *addr, unsigned long n)
 {
+	unsigned long ua_flags;
+
 	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
 		memset((void *)addr, 0, n);
 		return 0;
@@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n)
 		if (tocopy > n)
 			tocopy = n;
 
+		ua_flags = uaccess_save_and_enable();
 		memset((void *)addr, 0, tocopy);
+		uaccess_restore(ua_flags);
 		addr += tocopy;
 		n -= tocopy;
 
@@ -193,9 +205,14 @@ out:
 unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
-	if (n < 64)
-		return __clear_user_std(addr, n);
-	return __clear_user_memset(addr, n);
+	if (n < 64) {
+		unsigned long ua_flags = uaccess_save_and_enable();
+		n = __clear_user_std(addr, n);
+		uaccess_restore(ua_flags);
+	} else {
+		n = __clear_user_memset(addr, n);
+	}
+	return n;
 }
 
 #if 0
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 92673006e55c..28656c2b54a0 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -4,7 +4,6 @@ menuconfig ARCH_AT91
 	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLK_AT91
 	select PINCTRL
-	select PINCTRL_AT91
 	select SOC_BUS
 
 if ARCH_AT91
@@ -17,6 +16,7 @@ config SOC_SAMA5D2
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
 	select HAVE_AT91_GENERATED_CLK
+	select PINCTRL_AT91PIO4
 	help
 	  Select this if ou are using one of Atmel's SAMA5D2 family SoC.
 
@@ -27,6 +27,7 @@ config SOC_SAMA5D3
 	select HAVE_AT91_UTMI
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D3 family SoC.
 	  This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36.
@@ -40,6 +41,7 @@ config SOC_SAMA5D4
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D4 family SoC.
 
@@ -50,6 +52,7 @@ config SOC_AT91RM9200
 	select CPU_ARM920T
 	select HAVE_AT91_USB_CLK
 	select MIGHT_HAVE_PCI
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help
@@ -65,6 +68,7 @@ config SOC_AT91SAM9
 	select HAVE_AT91_UTMI
 	select HAVE_FB_ATMEL
 	select MEMORY
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 80e277cfcc8b..23726fb31741 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -41,8 +41,10 @@
  * implementation should be moved down into the pinctrl driver and get
  * called as part of the generic suspend/resume path.
  */
+#ifdef CONFIG_PINCTRL_AT91
 extern void at91_pinctrl_gpio_suspend(void);
 extern void at91_pinctrl_gpio_resume(void);
+#endif
 
 static struct {
 	unsigned long uhp_udp_mask;
@@ -151,8 +153,9 @@ static void at91_pm_suspend(suspend_state_t state)
 
 static int at91_pm_enter(suspend_state_t state)
 {
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_suspend();
-
+#endif
 	switch (state) {
 	/*
 	 * Suspend-to-RAM is like STANDBY plus slow clock mode, so
@@ -192,7 +195,9 @@ static int at91_pm_enter(suspend_state_t state)
 error:
 	target_state = PM_SUSPEND_ON;
 
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_resume();
+#endif
 	return 0;
 }
 
diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c
index de68938ee6aa..c21e41dad19c 100644
--- a/arch/arm/mach-exynos/pmu.c
+++ b/arch/arm/mach-exynos/pmu.c
@@ -748,8 +748,12 @@ static void exynos5_powerdown_conf(enum sys_powerdown mode)
 void exynos_sys_powerdown_conf(enum sys_powerdown mode)
 {
 	unsigned int i;
+	const struct exynos_pmu_data *pmu_data;
+
+	if (!pmu_context)
+		return;
 
-	const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data;
+	pmu_data = pmu_context->pmu_data;
 
 	if (pmu_data->powerdown_conf)
 		pmu_data->powerdown_conf(mode);
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index b02439019963..7a0c13bf4269 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -143,7 +143,7 @@ static inline void __indirect_writesl(volatile void __iomem *bus_addr,
 		writel(*vaddr++, bus_addr);
 }
 
-static inline unsigned char __indirect_readb(const volatile void __iomem *p)
+static inline u8 __indirect_readb(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -166,7 +166,7 @@ static inline void __indirect_readsb(const volatile void __iomem *bus_addr,
 		*vaddr++ = readb(bus_addr);
 }
 
-static inline unsigned short __indirect_readw(const volatile void __iomem *p)
+static inline u16 __indirect_readw(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -189,7 +189,7 @@ static inline void __indirect_readsw(const volatile void __iomem *bus_addr,
 		*vaddr++ = readw(bus_addr);
 }
 
-static inline unsigned long __indirect_readl(const volatile void __iomem *p)
+static inline u32 __indirect_readl(const volatile void __iomem *p)
 {
 	u32 addr = (__force u32)p;
 	u32 data;
@@ -350,7 +350,7 @@ static inline void insl(u32 io_addr, void *p, u32 count)
 					((unsigned long)p <= (PIO_MASK + PIO_OFFSET)))
 
 #define	ioread8(p)			ioread8(p)
-static inline unsigned int ioread8(const void __iomem *addr)
+static inline u8 ioread8(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -378,7 +378,7 @@ static inline void ioread8_rep(const void __iomem *addr, void *vaddr, u32 count)
 }
 
 #define	ioread16(p)			ioread16(p)
-static inline unsigned int ioread16(const void __iomem *addr)
+static inline u16 ioread16(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -407,7 +407,7 @@ static inline void ioread16_rep(const void __iomem *addr, void *vaddr,
 }
 
 #define	ioread32(p)			ioread32(p)
-static inline unsigned int ioread32(const void __iomem *addr)
+static inline u32 ioread32(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 5076d3f334d2..0517f0c1581a 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -65,6 +65,8 @@ config SOC_AM43XX
 	select MACH_OMAP_GENERIC
 	select MIGHT_HAVE_CACHE_L2X0
 	select HAVE_ARM_SCU
+	select GENERIC_CLOCKEVENTS_BROADCAST
+	select HAVE_ARM_TWD
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
@@ -121,6 +123,7 @@ config ARCH_OMAP2PLUS_TYPICAL
 	select NEON if CPU_V7
 	select PM
 	select REGULATOR
+	select REGULATOR_FIXED_VOLTAGE
 	select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
 	select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
 	select VFP
@@ -201,7 +204,6 @@ config MACH_OMAP3_PANDORA
 	depends on ARCH_OMAP3
 	default y
 	select OMAP_PACKAGE_CBB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_NOKIA_N810
        bool
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index b18ebbefae09..f86692dbcfd5 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -320,6 +320,12 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 	return r;
 }
 
+#if !defined(CONFIG_SMP) && defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)
+void tick_broadcast(const struct cpumask *mask)
+{
+}
+#endif
+
 static void __init omap2_gp_clockevent_init(int gptimer_id,
 						const char *fck_source,
 						const char *property)
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index 9a9c15bfcd34..7c0d5618be5e 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -889,6 +889,7 @@ static void __init e680_init(void)
 
 	pxa_set_keypad_info(&e680_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e680_devices));
 }
@@ -956,6 +957,7 @@ static void __init a1200_init(void)
 
 	pxa_set_keypad_info(&a1200_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a1200_devices));
 }
@@ -1148,6 +1150,7 @@ static void __init a910_init(void)
 		platform_device_register(&a910_camera);
 	}
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a910_devices));
 }
@@ -1215,6 +1218,7 @@ static void __init e6_init(void)
 
 	pxa_set_keypad_info(&e6_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e6_devices));
 }
@@ -1256,6 +1260,7 @@ static void __init e2_init(void)
 
 	pxa_set_keypad_info(&e2_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e2_devices));
 }
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index a19460e6e7b0..b355fca6cc2e 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_12[] = {
 	{ .frequency = 75000000,	.driver_data = PLLVAL(0x75, 3, 3),  }, 	/* FVco 600.000000 */
 	{ .frequency = 80000000,	.driver_data = PLLVAL(0x98, 4, 3),  }, 	/* FVco 640.000000 */
 	{ .frequency = 90000000,	.driver_data = PLLVAL(0x70, 2, 3),  }, 	/* FVco 720.000000 */
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index 1191b2905625..be9a248b5ce9 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
 	{ .frequency = 78019200,	.driver_data = PLLVAL(121, 5, 3), 	}, 	/* FVco 624.153600 */
 	{ .frequency = 84067200,	.driver_data = PLLVAL(131, 5, 3), 	}, 	/* FVco 672.537600 */
 	{ .frequency = 90115200,	.driver_data = PLLVAL(141, 5, 3), 	}, 	/* FVco 720.921600 */
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 845769e41332..c8c8b9ed02e0 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu)
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
-		if (per_cpu(reserved_asids, cpu) == asid)
-			return 1;
-	return 0;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
-			return generation | (asid & ~ASID_MASK);
+		if (check_update_reserved_asid(asid, newasid))
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
 	cpumask_clear(mm_cpumask(mm));
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e62400e5fb99..534a60ae282e 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
-		phys_addr_t phys = sg_phys(s) & PAGE_MASK;
+		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!is_coherent &&
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 8a63b4cdc0f2..7f8cd1b3557f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -22,6 +22,7 @@
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
+#include <linux/stop_machine.h>
 
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
@@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = {
  * safe to be called with preemption disabled, as under stop_machine().
  */
 static inline void section_update(unsigned long addr, pmdval_t mask,
-				  pmdval_t prot)
+				  pmdval_t prot, struct mm_struct *mm)
 {
-	struct mm_struct *mm;
 	pmd_t *pmd;
 
-	mm = current->active_mm;
 	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
 
 #ifdef CONFIG_ARM_LPAE
@@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void)
 	return !!(get_cr() & CR_XP);
 }
 
-#define set_section_perms(perms, field)	{				\
-	size_t i;							\
-	unsigned long addr;						\
-									\
-	if (!arch_has_strict_perms())					\
-		return;							\
-									\
-	for (i = 0; i < ARRAY_SIZE(perms); i++) {			\
-		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||	\
-		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {		\
-			pr_err("BUG: section %lx-%lx not aligned to %lx\n", \
-				perms[i].start, perms[i].end,		\
-				SECTION_SIZE);				\
-			continue;					\
-		}							\
-									\
-		for (addr = perms[i].start;				\
-		     addr < perms[i].end;				\
-		     addr += SECTION_SIZE)				\
-			section_update(addr, perms[i].mask,		\
-				       perms[i].field);			\
-	}								\
+void set_section_perms(struct section_perm *perms, int n, bool set,
+			struct mm_struct *mm)
+{
+	size_t i;
+	unsigned long addr;
+
+	if (!arch_has_strict_perms())
+		return;
+
+	for (i = 0; i < n; i++) {
+		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||
+		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {
+			pr_err("BUG: section %lx-%lx not aligned to %lx\n",
+				perms[i].start, perms[i].end,
+				SECTION_SIZE);
+			continue;
+		}
+
+		for (addr = perms[i].start;
+		     addr < perms[i].end;
+		     addr += SECTION_SIZE)
+			section_update(addr, perms[i].mask,
+				set ? perms[i].prot : perms[i].clear, mm);
+	}
+
 }
 
-static inline void fix_kernmem_perms(void)
+static void update_sections_early(struct section_perm perms[], int n)
 {
-	set_section_perms(nx_perms, prot);
+	struct task_struct *t, *s;
+
+	read_lock(&tasklist_lock);
+	for_each_process(t) {
+		if (t->flags & PF_KTHREAD)
+			continue;
+		for_each_thread(t, s)
+			set_section_perms(perms, n, true, s->mm);
+	}
+	read_unlock(&tasklist_lock);
+	set_section_perms(perms, n, true, current->active_mm);
+	set_section_perms(perms, n, true, &init_mm);
+}
+
+int __fix_kernmem_perms(void *unused)
+{
+	update_sections_early(nx_perms, ARRAY_SIZE(nx_perms));
+	return 0;
+}
+
+void fix_kernmem_perms(void)
+{
+	stop_machine(__fix_kernmem_perms, NULL, NULL);
 }
 
 #ifdef CONFIG_DEBUG_RODATA
+int __mark_rodata_ro(void *unused)
+{
+	update_sections_early(ro_perms, ARRAY_SIZE(ro_perms));
+	return 0;
+}
+
 void mark_rodata_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	stop_machine(__mark_rodata_ro, NULL, NULL);
 }
 
 void set_kernel_text_rw(void)
 {
-	set_section_perms(ro_perms, clear);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
+				current->active_mm);
 }
 
 void set_kernel_text_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
+				current->active_mm);
 }
 #endif /* CONFIG_DEBUG_RODATA */
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index de2b246fed38..8e1ea433c3f1 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area)
 .equ	cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	stmia	r0!, {r4 - r5}
@@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	stmia	r0, {r5 - r11}
-	ldmfd	sp!, {r4 - r10, pc}
+	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
 ENTRY(cpu_v7_do_resume)
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index e81cd48d6245..925552e7b4f3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -269,6 +269,7 @@
 			clock-frequency = <0>;	/* Updated by bootloader */
 			voltage-ranges = <1800 1800 3300 3300>;
 			sdhci,auto-cmd12;
+			little-endian;
 			bus-width = <4>;
 		};
 
@@ -277,6 +278,7 @@
 			reg = <0x0 0x2300000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -287,6 +289,7 @@
 			reg = <0x0 0x2310000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -297,6 +300,7 @@
 			reg = <0x0 0x2320000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -307,6 +311,7 @@
 			reg = <0x0 0x2330000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 030cdcb46c6b..2731d3b25ed2 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e074f93f383..63f52b55defe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -276,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep)) {
-		BUG_ON(!pte_young(pte));
-		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep) && pte_valid(pte)) {
+		VM_WARN_ONCE(!pte_young(pte),
+			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
+		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 1ee2c3937d4e..71426a78db12 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@ SECTIONS
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
 
-	PERCPU_SECTION(64)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
@@ -158,7 +159,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	PECOFF_EDATA_PADDING
 	_edata = .;
 
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 1e9c8b0bf486..170d786807c4 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index db73390568c8..74c132d901bd 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			322 /* length of syscall table */
+#define NR_syscalls			323 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 9038726e7d26..762edce7572e 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -335,5 +335,6 @@
 #define __NR_userfaultfd		1343
 #define __NR_membarrier			1344
 #define __NR_kcmp			1345
+#define __NR_mlock2			1346
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index dcd97f84d065..534a74acb849 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1771,5 +1771,6 @@ sys_call_table:
 	data8 sys_userfaultfd
 	data8 sys_membarrier
 	data8 sys_kcmp				// 1345
+	data8 sys_mlock2
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index c89da6312954..bf4dec229437 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -61,7 +61,8 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	/* FIXME this part of code is untested */
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		__dma_sync(sg_phys(sg), sg->length, direction);
+		__dma_sync(page_to_phys(sg_page(sg)) + sg->offset,
+							sg->length, direction);
 	}
 
 	return nents;
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 5305d694ffe5..095ecafe6bd3 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -599,7 +599,7 @@ extern void __put_user_unknown(void);
  * On error, the variable @x is set to zero.
  */
 #define __get_user_unaligned(x,ptr) \
-	__get_user__unalignednocheck((x),(ptr),sizeof(*(ptr)))
+	__get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr)))
 
 /*
  * Yuck.  We need two variants, one for 64bit operation and one
@@ -620,8 +620,8 @@ extern void __get_user_unaligned_unknown(void);
 do {									\
 	switch (size) {							\
 	case 1: __get_data_asm(val, "lb", ptr); break;			\
-	case 2: __get_user_unaligned_asm(val, "ulh", ptr); break;	\
-	case 4: __get_user_unaligned_asm(val, "ulw", ptr); break;	\
+	case 2: __get_data_unaligned_asm(val, "ulh", ptr); break;	\
+	case 4: __get_data_unaligned_asm(val, "ulw", ptr); break;	\
 	case 8: __GET_USER_UNALIGNED_DW(val, ptr); break;		\
 	default: __get_user_unaligned_unknown(); break;			\
 	}								\
@@ -1122,9 +1122,15 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
 	__cu_to = (to);							\
 	__cu_from = (from);						\
 	__cu_len = (n);							\
-	might_fault();							\
-	__cu_len = __invoke_copy_from_user(__cu_to, __cu_from,		\
-					   __cu_len);			\
+	if (eva_kernel_access()) {					\
+		__cu_len = __invoke_copy_from_kernel(__cu_to,		\
+						     __cu_from,		\
+						     __cu_len);		\
+	} else {							\
+		might_fault();						\
+		__cu_len = __invoke_copy_from_user(__cu_to, __cu_from,	\
+						   __cu_len);		\
+	}								\
 	__cu_len;							\
 })
 
@@ -1229,16 +1235,28 @@ __clear_user(void __user *addr, __kernel_size_t size)
 {
 	__kernel_size_t res;
 
-	might_fault();
-	__asm__ __volatile__(
-		"move\t$4, %1\n\t"
-		"move\t$5, $0\n\t"
-		"move\t$6, %2\n\t"
-		__MODULE_JAL(__bzero)
-		"move\t%0, $6"
-		: "=r" (res)
-		: "r" (addr), "r" (size)
-		: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+	if (eva_kernel_access()) {
+		__asm__ __volatile__(
+			"move\t$4, %1\n\t"
+			"move\t$5, $0\n\t"
+			"move\t$6, %2\n\t"
+			__MODULE_JAL(__bzero_kernel)
+			"move\t%0, $6"
+			: "=r" (res)
+			: "r" (addr), "r" (size)
+			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+	} else {
+		might_fault();
+		__asm__ __volatile__(
+			"move\t$4, %1\n\t"
+			"move\t$5, $0\n\t"
+			"move\t$6, %2\n\t"
+			__MODULE_JAL(__bzero)
+			"move\t%0, $6"
+			: "=r" (res)
+			: "r" (addr), "r" (size)
+			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+	}
 
 	return res;
 }
@@ -1384,7 +1402,7 @@ static inline long strlen_user(const char __user *s)
 		might_fault();
 		__asm__ __volatile__(
 			"move\t$4, %1\n\t"
-			__MODULE_JAL(__strlen_kernel_asm)
+			__MODULE_JAL(__strlen_user_asm)
 			"move\t%0, $2"
 			: "=r" (res)
 			: "r" (s)
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 8fd5a276cad2..ac81edd44563 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -257,7 +257,6 @@ LEAF(mips_cps_core_init)
 	has_mt	t0, 3f
 
 	.set	push
-	.set	mips64r2
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -376,7 +375,6 @@ LEAF(mips_cps_boot_vpes)
 	 nop
 
 	.set	push
-	.set	mips64r2
 	.set	mt
 
 1:	/* Enter VPE configuration state */
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 291af0b5c482..e2b6ab74643d 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -17,6 +17,7 @@
 #include <asm/fpu.h>
 #include <asm/msa.h>
 
+extern void *__bzero_kernel(void *__s, size_t __count);
 extern void *__bzero(void *__s, size_t __count);
 extern long __strncpy_from_kernel_nocheck_asm(char *__to,
 					      const char *__from, long __len);
@@ -64,6 +65,7 @@ EXPORT_SYMBOL(__copy_from_user_eva);
 EXPORT_SYMBOL(__copy_in_user_eva);
 EXPORT_SYMBOL(__copy_to_user_eva);
 EXPORT_SYMBOL(__copy_user_inatomic_eva);
+EXPORT_SYMBOL(__bzero_kernel);
 #endif
 EXPORT_SYMBOL(__bzero);
 EXPORT_SYMBOL(__strncpy_from_kernel_nocheck_asm);
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index b8e63fd00375..8f0019a2e5c8 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -283,6 +283,8 @@ LEAF(memset)
 1:
 #ifndef CONFIG_EVA
 FEXPORT(__bzero)
+#else
+FEXPORT(__bzero_kernel)
 #endif
 	__BUILD_BZERO LEGACY_MODE
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index d8117be729a2..730d394ce5f0 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
 		page = dma_alloc_from_contiguous(dev,
 					count, get_order(size));
 	if (!page)
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index dbbeccc3d714..a245cad4372a 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -221,7 +221,6 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 static int rt288x_pci_probe(struct platform_device *pdev)
 {
 	void __iomem *io_map_base;
-	int i;
 
 	rt2880_pci_base = ioremap_nocache(RT2880_PCI_BASE, PAGE_SIZE);
 
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 78b2ef49dbc7..9d293b3e9130 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -39,7 +39,6 @@ extern void msp_serial_setup(void);
 void msp7120_reset(void)
 {
 	void *start, *end, *iptr;
-	register int i;
 
 	/* Diasble all interrupts */
 	local_irq_disable();
diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c
index db8f88b6a3af..6afa34346b81 100644
--- a/arch/mips/sni/reset.c
+++ b/arch/mips/sni/reset.c
@@ -26,7 +26,7 @@ static inline void kb_wait(void)
 /* XXX This ends up at the ARC firmware prompt ...  */
 void sni_machine_restart(char *command)
 {
-	int i, j;
+	int i;
 
 	/* This does a normal via the keyboard controller like a PC.
 	   We can do that easier ...  */
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index ef5f348f386a..018f8c7b94f2 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -26,8 +26,8 @@ aflags-vdso := $(ccflags-vdso) \
 # the comments on that file.
 #
 ifndef CONFIG_CPU_MIPSR6
-  ifeq ($(call ld-ifversion, -gt, 22400000, y),)
-    $(warning MIPS VDSO requires binutils > 2.24)
+  ifeq ($(call ld-ifversion, -lt, 22500000, y),)
+    $(warning MIPS VDSO requires binutils >= 2.25)
     obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y))
     ccflags-vdso += -DDISABLE_MIPS_VDSO
   endif
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index d8534f95915a..291cee28ccb6 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -372,7 +372,8 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
  */
 #ifdef CONFIG_HUGETLB_PAGE
 #define pte_huge(pte)           (pte_val(pte) & _PAGE_HUGE)
-#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_HUGE))
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | \
+				 (parisc_requires_coherency() ? 0 : _PAGE_HUGE)))
 #else
 #define pte_huge(pte)           (0)
 #define pte_mkhuge(pte)         (pte)
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 33170384d3ac..35bdccbb2036 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -360,8 +360,9 @@
 #define __NR_execveat		(__NR_Linux + 342)
 #define __NR_membarrier		(__NR_Linux + 343)
 #define __NR_userfaultfd	(__NR_Linux + 344)
+#define __NR_mlock2		(__NR_Linux + 345)
 
-#define __NR_Linux_syscalls	(__NR_userfaultfd + 1)
+#define __NR_Linux_syscalls	(__NR_mlock2 + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 64f2764a8cef..c99f3dde455c 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -171,24 +171,6 @@ void pcibios_set_master(struct pci_dev *dev)
 }
 
 
-void __init pcibios_init_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev = bus->self;
-	unsigned short bridge_ctl;
-
-	/* We deal only with pci controllers and pci-pci bridges. */
-	if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
-		return;
-
-	/* PCI-PCI bridge - set the cache line and default latency
-	   (32) for primary and secondary buses. */
-	pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32);
-
-	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl);
-	bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR;
-	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl);
-}
-
 /*
  * pcibios align resources() is called every time generic PCI code
  * wants to generate a new address. The process of looking for
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index dc1ea796fd60..2264f68f3c2f 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -435,6 +435,55 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs, int in_syscall)
 		regs->gr[28]);
 }
 
+/*
+ * Check how the syscall number gets loaded into %r20 within
+ * the delay branch in userspace and adjust as needed.
+ */
+
+static void check_syscallno_in_delay_branch(struct pt_regs *regs)
+{
+	u32 opcode, source_reg;
+	u32 __user *uaddr;
+	int err;
+
+	/* Usually we don't have to restore %r20 (the system call number)
+	 * because it gets loaded in the delay slot of the branch external
+	 * instruction via the ldi instruction.
+	 * In some cases a register-to-register copy instruction might have
+	 * been used instead, in which case we need to copy the syscall
+	 * number into the source register before returning to userspace.
+	 */
+
+	/* A syscall is just a branch, so all we have to do is fiddle the
+	 * return pointer so that the ble instruction gets executed again.
+	 */
+	regs->gr[31] -= 8; /* delayed branching */
+
+	/* Get assembler opcode of code in delay branch */
+	uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4);
+	err = get_user(opcode, uaddr);
+	if (err)
+		return;
+
+	/* Check if delay branch uses "ldi int,%r20" */
+	if ((opcode & 0xffff0000) == 0x34140000)
+		return;	/* everything ok, just return */
+
+	/* Check if delay branch uses "nop" */
+	if (opcode == INSN_NOP)
+		return;
+
+	/* Check if delay branch uses "copy %rX,%r20" */
+	if ((opcode & 0xffe0ffff) == 0x08000254) {
+		source_reg = (opcode >> 16) & 31;
+		regs->gr[source_reg] = regs->gr[20];
+		return;
+	}
+
+	pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n",
+		current->comm, task_pid_nr(current), opcode);
+}
+
 static inline void
 syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 {
@@ -457,10 +506,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 		}
 		/* fallthrough */
 	case -ERESTARTNOINTR:
-		/* A syscall is just a branch, so all
-		 * we have to do is fiddle the return pointer.
-		 */
-		regs->gr[31] -= 8; /* delayed branching */
+		check_syscallno_in_delay_branch(regs);
 		break;
 	}
 }
@@ -510,15 +556,9 @@ insert_restart_trampoline(struct pt_regs *regs)
 	}
 	case -ERESTARTNOHAND:
 	case -ERESTARTSYS:
-	case -ERESTARTNOINTR: {
-		/* Hooray for delayed branching.  We don't
-		 * have to restore %r20 (the system call
-		 * number) because it gets loaded in the delay
-		 * slot of the branch external instruction.
-		 */
-		regs->gr[31] -= 8;
+	case -ERESTARTNOINTR:
+		check_syscallno_in_delay_branch(regs);
 		return;
-	}
 	default:
 		break;
 	}
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 78c3ef8c348d..d4ffcfbc9885 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -440,6 +440,7 @@
 	ENTRY_COMP(execveat)
 	ENTRY_SAME(membarrier)
 	ENTRY_SAME(userfaultfd)
+	ENTRY_SAME(mlock2)		/* 345 */
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts
index 631ede72e226..68f0ed7626bd 100644
--- a/arch/powerpc/boot/dts/sbc8641d.dts
+++ b/arch/powerpc/boot/dts/sbc8641d.dts
@@ -227,23 +227,15 @@
 				reg = <0x520 0x20>;
 
 				phy0: ethernet-phy@1f {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0x1f>;
 				};
 				phy1: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0>;
 				};
 				phy2: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <1>;
 				};
 				phy3: ethernet-phy@2 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <2>;
 				};
 				tbi0: tbi-phy@11 {
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f2b0b1b0c72a..5654ece02c0d 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -370,16 +370,16 @@ COMPAT_SYS(execveat)
 PPC64ONLY(switch_endian)
 SYSCALL_SPU(userfaultfd)
 SYSCALL_SPU(membarrier)
-SYSCALL(semop)
-SYSCALL(semget)
-COMPAT_SYS(semctl)
-COMPAT_SYS(semtimedop)
-COMPAT_SYS(msgsnd)
-COMPAT_SYS(msgrcv)
-SYSCALL(msgget)
-COMPAT_SYS(msgctl)
-COMPAT_SYS(shmat)
-SYSCALL(shmdt)
-SYSCALL(shmget)
-COMPAT_SYS(shmctl)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
+SYSCALL(ni_syscall)
 SYSCALL(mlock2)
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 1effea5193d6..12a05652377a 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -388,18 +388,6 @@
 #define __NR_switch_endian	363
 #define __NR_userfaultfd	364
 #define __NR_membarrier		365
-#define __NR_semop		366
-#define __NR_semget		367
-#define __NR_semctl		368
-#define __NR_semtimedop		369
-#define __NR_msgsnd		370
-#define __NR_msgrcv		371
-#define __NR_msgget		372
-#define __NR_msgctl		373
-#define __NR_shmat		374
-#define __NR_shmdt		375
-#define __NR_shmget		376
-#define __NR_shmctl		377
 #define __NR_mlock2		378
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 80dfe8965df9..8d14feb40f12 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -590,16 +590,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
 
-	/*
-	 * If it's PHB PE, the frozen state on all available PEs should have
-	 * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its
-	 * child PEs because they might be in frozen state.
-	 */
-	if (!(pe->type & EEH_PE_PHB)) {
-		rc = eeh_clear_pe_frozen_state(pe, false);
-		if (rc)
-			return rc;
-	}
+	/* Clear frozen state */
+	rc = eeh_clear_pe_frozen_state(pe, false);
+	if (rc)
+		return rc;
 
 	/* Give the system 5 seconds to finish running the user-space
 	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 54b45b73195f..a7352b59e6f9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -224,6 +224,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
+	/*
+	 * Check for illegal transactional state bit combination
+	 * and if we find it, force the TS field to a safe state.
+	 */
+	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
+		msr &= ~MSR_TS_MASK;
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index 6ccfb6c1c707..e505223b4ec5 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -43,11 +43,34 @@ static unsigned int opal_irq_count;
 static unsigned int *opal_irqs;
 
 static void opal_handle_irq_work(struct irq_work *work);
-static __be64 last_outstanding_events;
+static u64 last_outstanding_events;
 static struct irq_work opal_event_irq_work = {
 	.func = opal_handle_irq_work,
 };
 
+void opal_handle_events(uint64_t events)
+{
+	int virq, hwirq = 0;
+	u64 mask = opal_event_irqchip.mask;
+
+	if (!in_irq() && (events & mask)) {
+		last_outstanding_events = events;
+		irq_work_queue(&opal_event_irq_work);
+		return;
+	}
+
+	while (events & mask) {
+		hwirq = fls64(events) - 1;
+		if (BIT_ULL(hwirq) & mask) {
+			virq = irq_find_mapping(opal_event_irqchip.domain,
+						hwirq);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+		events &= ~BIT_ULL(hwirq);
+	}
+}
+
 static void opal_event_mask(struct irq_data *d)
 {
 	clear_bit(d->hwirq, &opal_event_irqchip.mask);
@@ -55,9 +78,21 @@ static void opal_event_mask(struct irq_data *d)
 
 static void opal_event_unmask(struct irq_data *d)
 {
+	__be64 events;
+
 	set_bit(d->hwirq, &opal_event_irqchip.mask);
 
-	opal_poll_events(&last_outstanding_events);
+	opal_poll_events(&events);
+	last_outstanding_events = be64_to_cpu(events);
+
+	/*
+	 * We can't just handle the events now with opal_handle_events().
+	 * If we did we would deadlock when opal_event_unmask() is called from
+	 * handle_level_irq() with the irq descriptor lock held, because
+	 * calling opal_handle_events() would call generic_handle_irq() and
+	 * then handle_level_irq() which would try to take the descriptor lock
+	 * again. Instead queue the events for later.
+	 */
 	if (last_outstanding_events & opal_event_irqchip.mask)
 		/* Need to retrigger the interrupt */
 		irq_work_queue(&opal_event_irq_work);
@@ -96,29 +131,6 @@ static int opal_event_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-void opal_handle_events(uint64_t events)
-{
-	int virq, hwirq = 0;
-	u64 mask = opal_event_irqchip.mask;
-
-	if (!in_irq() && (events & mask)) {
-		last_outstanding_events = events;
-		irq_work_queue(&opal_event_irq_work);
-		return;
-	}
-
-	while (events & mask) {
-		hwirq = fls64(events) - 1;
-		if (BIT_ULL(hwirq) & mask) {
-			virq = irq_find_mapping(opal_event_irqchip.domain,
-						hwirq);
-			if (virq)
-				generic_handle_irq(virq);
-		}
-		events &= ~BIT_ULL(hwirq);
-	}
-}
-
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
 	__be64 events;
@@ -131,7 +143,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 
 static void opal_handle_irq_work(struct irq_work *work)
 {
-	opal_handle_events(be64_to_cpu(last_outstanding_events));
+	opal_handle_events(last_outstanding_events);
 }
 
 static int opal_event_match(struct irq_domain *h, struct device_node *node,
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 4296d55e88f3..57cffb80bc36 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -278,7 +278,7 @@ static void opal_handle_message(void)
 
 	/* Sanity check */
 	if (type >= OPAL_MSG_TYPE_MAX) {
-		pr_warning("%s: Unknown message type: %u\n", __func__, type);
+		pr_warn_once("%s: Unknown message type: %u\n", __func__, type);
 		return;
 	}
 	opal_message_do_notify(type, (void *)&msg);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 8140d10c6785..6e72961608f0 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 			}
 			if (separator)
 				ptr += sprintf(ptr, "%c", separator);
+			/*
+			 * Use four '%' characters below because of the
+			 * following two conversions:
+			 *
+			 *  1) sprintf: %%%%r -> %%r
+			 *  2) printk : %%r   -> %r
+			 */
 			if (operand->flags & OPERAND_GPR)
-				ptr += sprintf(ptr, "%%r%i", value);
+				ptr += sprintf(ptr, "%%%%r%i", value);
 			else if (operand->flags & OPERAND_FPR)
-				ptr += sprintf(ptr, "%%f%i", value);
+				ptr += sprintf(ptr, "%%%%f%i", value);
 			else if (operand->flags & OPERAND_AR)
-				ptr += sprintf(ptr, "%%a%i", value);
+				ptr += sprintf(ptr, "%%%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
-				ptr += sprintf(ptr, "%%c%i", value);
+				ptr += sprintf(ptr, "%%%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
-				ptr += sprintf(ptr, "%%v%i", value);
+				ptr += sprintf(ptr, "%%%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);
diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h
index e6820c86e8c7..47ebd5b5ed55 100644
--- a/arch/sh/include/uapi/asm/unistd_64.h
+++ b/arch/sh/include/uapi/asm/unistd_64.h
@@ -278,7 +278,7 @@
 #define __NR_fsetxattr		256
 #define __NR_getxattr		257
 #define __NR_lgetxattr		258
-#define __NR_fgetxattr		269
+#define __NR_fgetxattr		259
 #define __NR_listxattr		260
 #define __NR_llistxattr		261
 #define __NR_flistxattr		262
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7cfd7f153966..4dca18347ee9 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h
index 370ca1e71ffb..93310837c2df 100644
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@@ -95,6 +95,7 @@
  * really available.  So we simply advertise only "crypto" support.
  */
 #define HWCAP_SPARC_CRYPTO	0x04000000 /* CRYPTO insns available */
+#define HWCAP_SPARC_ADI		0x08000000 /* ADI available */
 
 #define CORE_DUMP_USE_REGSET
 
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index efe9479f837b..f31a124a8497 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -417,8 +417,9 @@
 #define __NR_bpf		349
 #define __NR_execveat		350
 #define __NR_membarrier		351
+#define __NR_userfaultfd	352
 
-#define NR_syscalls		352
+#define NR_syscalls		353
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 3d61fcae7ee3..f2d30cab5b3f 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -946,6 +946,12 @@ ENTRY(__retl_one)
 	 mov	1, %o0
 ENDPROC(__retl_one)
 
+ENTRY(__retl_one_fp)
+	VISExitHalf
+	retl
+	 mov	1, %o0
+ENDPROC(__retl_one_fp)
+
 ENTRY(__ret_one_asi)
 	wr	%g0, ASI_AIUS, %asi
 	ret
@@ -958,6 +964,13 @@ ENTRY(__retl_one_asi)
 	 mov	1, %o0
 ENDPROC(__retl_one_asi)
 
+ENTRY(__retl_one_asi_fp)
+	wr	%g0, ASI_AIUS, %asi
+	VISExitHalf
+	retl
+	 mov	1, %o0
+ENDPROC(__retl_one_asi_fp)
+
 ENTRY(__retl_o1)
 	retl
 	 mov	%o1, %o0
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b0da5aedb336..6596f66ce112 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>
@@ -1828,11 +1828,18 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 void
 perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
+	u64 saved_fault_address = current_thread_info()->fault_address;
+	u8 saved_fault_code = get_thread_fault_code();
+	mm_segment_t old_fs;
+
 	perf_callchain_store(entry, regs->tpc);
 
 	if (!current->mm)
 		return;
 
+	old_fs = get_fs();
+	set_fs(USER_DS);
+
 	flushw_user();
 
 	pagefault_disable();
@@ -1843,4 +1850,8 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		perf_callchain_user_64(entry, regs);
 
 	pagefault_enable();
+
+	set_fs(old_fs);
+	set_thread_fault_code(saved_fault_code);
+	current_thread_info()->fault_address = saved_fault_address;
 }
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 39f0c662f4c8..d08bdaffdbfc 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -73,7 +73,13 @@ rtrap_nmi:	ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
 		andn			%l1, %l4, %l1
 		srl			%l4, 20, %l4
 		ba,pt			%xcc, rtrap_no_irq_enable
-		 wrpr			%l4, %pil
+		nop
+		/* Do not actually set the %pil here.  We will do that
+		 * below after we clear PSTATE_IE in the %pstate register.
+		 * If we re-enable interrupts here, we can recurse down
+		 * the hardirq stack potentially endlessly, causing a
+		 * stack overflow.
+		 */
 
 		.align			64
 		.globl			rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index f7b261749383..f3185e2b028b 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -380,7 +380,8 @@ static const char *hwcaps[] = {
 	 */
 	"mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2",
 	"ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau",
-	"ima", "cspare", "pause", "cbcond",
+	"ima", "cspare", "pause", "cbcond", NULL /*reserved for crypto */,
+	"adp",
 };
 
 static const char *crypto_hwcaps[] = {
@@ -396,7 +397,7 @@ void cpucap_info(struct seq_file *m)
 	seq_puts(m, "cpucaps\t\t: ");
 	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 		unsigned long bit = 1UL << i;
-		if (caps & bit) {
+		if (hwcaps[i] && (caps & bit)) {
 			seq_printf(m, "%s%s",
 				   printed ? "," : "", hwcaps[i]);
 			printed++;
@@ -450,7 +451,7 @@ static void __init report_hwcaps(unsigned long caps)
 
 	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 		unsigned long bit = 1UL << i;
-		if (caps & bit)
+		if (hwcaps[i] && (caps & bit))
 			report_one_hwcap(&printed, hwcaps[i]);
 	}
 	if (caps & HWCAP_SPARC_CRYPTO)
@@ -485,7 +486,7 @@ static unsigned long __init mdesc_cpu_hwcap_list(void)
 		for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 			unsigned long bit = 1UL << i;
 
-			if (!strcmp(prop, hwcaps[i])) {
+			if (hwcaps[i] && !strcmp(prop, hwcaps[i])) {
 				caps |= bit;
 				break;
 			}
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index cc23b62b6e38..78e80293cb6d 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -87,4 +87,4 @@ sys_call_table:
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 /*345*/	.long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.long sys_execveat, sys_membarrier
+/*350*/	.long sys_execveat, sys_membarrier, sys_userfaultfd
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index f229468a7479..2549c2c3ec2f 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -88,7 +88,7 @@ sys_call_table32:
 	.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, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.word sys32_execveat, sys_membarrier
+/*350*/	.word sys32_execveat, sys_membarrier, sys_userfaultfd
 
 #endif /* CONFIG_COMPAT */
 
@@ -168,4 +168,4 @@ sys_call_table:
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.word sys64_execveat, sys_membarrier
+/*350*/	.word sys64_execveat, sys_membarrier, sys_userfaultfd
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index 119ccb9a54f4..d5242b8c4f94 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 7fe1ccefd9d0..4e962d993b10 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 30eee6e8a81b..d5f585df2f3f 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -34,10 +34,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -134,40 +140,40 @@
 	fsrc2		%x6, %f12; \
 	fsrc2		%x7, %f14;
 #define FREG_LOAD_1(base, x0) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0))
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
 #define FREG_LOAD_2(base, x0, x1) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
 #define FREG_LOAD_3(base, x0, x1, x2) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
 #define FREG_LOAD_4(base, x0, x1, x2, x3) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
 #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
 #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD(LOAD(ldd, base + 0x28, %x5));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
 #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD(LOAD(ldd, base + 0x28, %x5)); \
-	EX_LD(LOAD(ldd, base + 0x30, %x6));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
+	EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
@@ -275,11 +281,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	/* fall through for 0 < low bits < 8 */
 110:	sub		%o4, 64, %g2
-	EX_LD(LOAD_BLK(%g2, %f0))
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+	EX_LD_FP(LOAD_BLK(%g2, %f0))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -290,10 +296,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 120:	sub		%o4, 56, %g2
 	FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -304,10 +310,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 130:	sub		%o4, 48, %g2
 	FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -318,10 +324,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 140:	sub		%o4, 40, %g2
 	FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_5(f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -332,10 +338,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 150:	sub		%o4, 32, %g2
 	FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_4(f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -346,10 +352,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 160:	sub		%o4, 24, %g2
 	FREG_LOAD_3(%g2, f0, f2, f4)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_3(f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -360,10 +366,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 170:	sub		%o4, 16, %g2
 	FREG_LOAD_2(%g2, f0, f2)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_2(f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -374,10 +380,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 180:	sub		%o4, 8, %g2
 	FREG_LOAD_1(%g2, f0)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_1(f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -387,10 +393,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 
 190:
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
 	subcc		%g1, 64, %g1
-	EX_LD(LOAD_BLK(%o4, %f0))
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f0))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	add		%o4, 64, %o4
 	bne,pt		%xcc, 1b
 	 LOAD(prefetch, %o4 + 64, #one_read)
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index fd9f903ffa32..2e8ee7ad07a9 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index 9744c4540a8d..be0bf4590df8 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 83aeeb1dffdb..8e13ee1f4454 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -48,10 +48,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -210,17 +216,17 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%o2, %o4, %o2
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
-	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
-1:	EX_LD(LOAD(ldd, %g1 + 0x08, %f2))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
+1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
 	subcc		%o4, 0x40, %o4
-	EX_LD(LOAD(ldd, %g1 + 0x10, %f4))
-	EX_LD(LOAD(ldd, %g1 + 0x18, %f6))
-	EX_LD(LOAD(ldd, %g1 + 0x20, %f8))
-	EX_LD(LOAD(ldd, %g1 + 0x28, %f10))
-	EX_LD(LOAD(ldd, %g1 + 0x30, %f12))
-	EX_LD(LOAD(ldd, %g1 + 0x38, %f14))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %g1 + 0x40, %f0))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
 	faligndata	%f2, %f4, %f18
 	add		%g1, 0x40, %g1
 	faligndata	%f4, %f6, %f20
@@ -229,14 +235,14 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE(std, %f16, %o0 + 0x00))
-	EX_ST(STORE(std, %f18, %o0 + 0x08))
-	EX_ST(STORE(std, %f20, %o0 + 0x10))
-	EX_ST(STORE(std, %f22, %o0 + 0x18))
-	EX_ST(STORE(std, %f24, %o0 + 0x20))
-	EX_ST(STORE(std, %f26, %o0 + 0x28))
-	EX_ST(STORE(std, %f28, %o0 + 0x30))
-	EX_ST(STORE(std, %f30, %o0 + 0x38))
+	EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
+	EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
+	EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
+	EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
+	EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
+	EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
+	EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
+	EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index a6ae2ea04bf5..ecc5692fa2b4 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		___copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 #define LOAD_BLK(addr,dest)	ldda [addr] ASI_BLK_AIUS, dest
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index f4b970eeb485..9eea392e44d4 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		___copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_BLK(src,addr)	stda src, [addr] ASI_BLK_AIUS
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index b67142b7768e..3e6209ebb7d7 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -25,10 +25,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -73,8 +79,8 @@
 	faligndata		%f8, %f9, %f62;
 
 #define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt)	\
-	EX_LD(LOAD_BLK(%src, %fdest));				\
-	EX_ST(STORE_BLK(%fsrc, %dest));				\
+	EX_LD_FP(LOAD_BLK(%src, %fdest));				\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));				\
 	add			%src, 0x40, %src;		\
 	subcc			%len, 0x40, %len;		\
 	be,pn			%xcc, jmptgt;			\
@@ -89,12 +95,12 @@
 
 #define DO_SYNC			membar	#Sync;
 #define STORE_SYNC(dest, fsrc)				\
-	EX_ST(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
 	add			%dest, 0x40, %dest;	\
 	DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)			\
-	EX_ST(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
 	add			%dest, 0x40, %dest;	\
 	ba,pt			%xcc, target;		\
 	 nop;
@@ -103,7 +109,7 @@
 	subcc			%left, 8, %left;\
 	bl,pn			%xcc, 95f;	\
 	 faligndata		%f0, %f1, %f48;	\
-	EX_ST(STORE(std, %f48, %dest));		\
+	EX_ST_FP(STORE(std, %f48, %dest));		\
 	add			%dest, 8, %dest;
 
 #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
@@ -160,8 +166,8 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
+	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -172,20 +178,20 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD(LOAD(ldd, %o1, %f4))
-1:	EX_LD(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -208,13 +214,13 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	add		%g1, %GLOBAL_SPARE, %g1
 	subcc		%o2, %g3, %o2
 
-	EX_LD(LOAD_BLK(%o1, %f0))
+	EX_LD_FP(LOAD_BLK(%o1, %f0))
 	add		%o1, 0x40, %o1
 	add		%g1, %g3, %g1
-	EX_LD(LOAD_BLK(%o1, %f16))
+	EX_LD_FP(LOAD_BLK(%o1, %f16))
 	add		%o1, 0x40, %o1
 	sub		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
-	EX_LD(LOAD_BLK(%o1, %f32))
+	EX_LD_FP(LOAD_BLK(%o1, %f32))
 	add		%o1, 0x40, %o1
 
 	/* There are 8 instances of the unrolled loop,
@@ -426,28 +432,28 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 62:	FINISH_VISCHUNK(o0, f44, f46, g3)
 63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0,  g3)
 
-93:	EX_LD(LOAD(ldd, %o1, %f2))
+93:	EX_LD_FP(LOAD(ldd, %o1, %f2))
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f0, %f2, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bl,pn		%xcc, 95f
 	 add		%o0, 8, %o0
-	EX_LD(LOAD(ldd, %o1, %f0))
+	EX_LD_FP(LOAD(ldd, %o1, %f0))
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f2, %f0, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bge,pt		%xcc, 93b
 	 add		%o0, 8, %o0
 
 95:	brz,pt		%o2, 2f
 	 mov		%g1, %o1
 
-1:	EX_LD(LOAD(ldub, %o1, %o3))
+1:	EX_LD_FP(LOAD(ldub, %o1, %o3))
 	add		%o1, 1, %o1
 	subcc		%o2, 1, %o2
-	EX_ST(STORE(stb, %o3, %o0))
+	EX_ST_FP(STORE(stb, %o3, %o0))
 	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 
diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index b1acd1331c33..88ad73d86fe4 100644
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		U3copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 #define EX_RETVAL(x)		0
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index ef1e493afdfa..845139d75537 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		U3copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_BLK(src,addr)	stda src, [addr] ASI_BLK_AIUS
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 7cae9cc6a204..491ee69e4995 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -24,10 +24,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -120,8 +126,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
+	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -132,20 +138,20 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD(LOAD(ldd, %o1, %f4))
-1:	EX_LD(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f2
-	EX_ST(STORE(std, %f2, %o0))
+	EX_ST_FP(STORE(std, %f2, %o0))
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -155,25 +161,25 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	LOAD(prefetch, %o1 + 0x080, #one_read)
 	LOAD(prefetch, %o1 + 0x0c0, #one_read)
 	LOAD(prefetch, %o1 + 0x100, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x000, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
 	LOAD(prefetch, %o1 + 0x140, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	LOAD(prefetch, %o1 + 0x180, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f6, %f8, %f22
 
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	faligndata	%f8, %f10, %f24
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 	faligndata	%f10, %f12, %f26
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 
 	subcc		GLOBAL_SPARE, 0x80, GLOBAL_SPARE
 	add		%o1, 0x40, %o1
@@ -184,26 +190,26 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	.align		64
 1:
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	faligndata	%f12, %f14, %f28
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f0, %f2, %f16
 	add		%o0, 0x40, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	subcc		%o3, 0x01, %o3
 	faligndata	%f6, %f8, %f22
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 
 	faligndata	%f8, %f10, %f24
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f10, %f12, %f26
 	bg,pt		%XCC, 1b
@@ -211,29 +217,29 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	/* Finally we copy the last full 64-byte block. */
 2:
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	faligndata	%f12, %f14, %f28
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	faligndata	%f6, %f8, %f22
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 	faligndata	%f8, %f10, %f24
 	cmp		%g1, 0
 	be,pt		%XCC, 1f
 	 add		%o0, 0x40, %o0
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 1:	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
 	add		%o0, 0x40, %o0
 	add		%o1, 0x40, %o1
 	membar		#Sync
@@ -253,20 +259,20 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	sub		%o2, %g2, %o2
 	be,a,pt		%XCC, 1f
-	 EX_LD(LOAD(ldd, %o1 + 0x00, %f0))
+	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
 
-1:	EX_LD(LOAD(ldd, %o1 + 0x08, %f2))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f0, %f2, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	be,pn		%XCC, 2f
 	 add		%o0, 0x8, %o0
-	EX_LD(LOAD(ldd, %o1 + 0x08, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f2, %f0, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bne,pn		%XCC, 1b
 	 add		%o0, 0x8, %o0
 
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index bb509cee3b59..8767060d70fb 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 25ed4098640e..e3abe6f3156d 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT)
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
-LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt
+LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt))
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index e697a4136707..e9f8445861dc 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg)
 
 char *split_if_spec(char *str, ...)
 {
-	char **arg, *end;
+	char **arg, *end, *ret = NULL;
 	va_list ap;
 
 	va_start(ap, str);
 	while ((arg = va_arg(ap, char **)) != NULL) {
 		if (*str == '\0')
-			return NULL;
+			goto out;
 		end = strchr(str, ',');
 		if (end != str)
 			*arg = str;
 		if (end == NULL)
-			return NULL;
+			goto out;
 		*end++ = '\0';
 		str = end;
 	}
+	ret = str;
+out:
 	va_end(ap);
-	return str;
+	return ret;
 }
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 57acbd67d85d..fc8be0e3a4ff 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs)
 	struct ksignal ksig;
 	int handled_sig = 0;
 
-	while (get_signal(&ksig)) {
+	if (get_signal(&ksig)) {
 		handled_sig = 1;
 		/* Whee!  Actually deliver the signal.  */
 		handle_signal(&ksig, regs);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf070c27..2bf79d7c97df 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533dd3cc..d0e35ebb2adb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	int tos;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f63360be2238..e2a430021e46 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8ed391..a316ca96f1b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b717e944..659f01e165d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	}
 
 	mask = x86_pmu.lbr_nr - 1;
-	tos = intel_pmu_lbr_tos();
+	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
 
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a1e8d6..3512ba607361 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 06332cb7e7d1..3f5c48ddba45 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
 
+static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	return best && (best->edx & bit(X86_FEATURE_MTRR));
+}
+
 static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 9e8bf13572e6..3f8c732117ec 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
-static u8 mtrr_disabled_type(void)
+static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Intel SDM 11.11.2.2: all MTRRs are disabled when
 	 * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
 	 * memory type is applied to all of physical memory.
+	 *
+	 * However, virtual machines can be run with CPUID such that
+	 * there are no MTRRs.  In that case, the firmware will never
+	 * enable MTRRs and it is obviously undesirable to run the
+	 * guest entirely with UC memory and we use WB.
 	 */
-	return MTRR_TYPE_UNCACHABLE;
+	if (guest_cpuid_has_mtrr(vcpu))
+		return MTRR_TYPE_UNCACHABLE;
+	else
+		return MTRR_TYPE_WRBACK;
 }
 
 /*
@@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr)
 
 	for (seg = 0; seg < seg_num; seg++) {
 		mtrr_seg = &fixed_seg_table[seg];
-		if (mtrr_seg->start >= addr && addr < mtrr_seg->end)
+		if (mtrr_seg->start <= addr && addr < mtrr_seg->end)
 			return seg;
 	}
 
@@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
 	*start = range->base & PAGE_MASK;
 
 	mask = range->mask & PAGE_MASK;
-	mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
 
 	/* This cannot overflow because writing to the reserved bits of
 	 * variable MTRRs causes a #GP.
@@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	if (var_mtrr_range_is_valid(cur))
 		list_del(&mtrr_state->var_ranges[index].node);
 
+	/* Extend the mask with all 1 bits to the left, since those
+	 * bits must implicitly be 0.  The bits are then cleared
+	 * when reading them.
+	 */
 	if (!is_mtrr_mask)
 		cur->base = data;
 	else
-		cur->mask = data;
+		cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu));
 
 	/* add it to the list if it's enabled. */
 	if (var_mtrr_range_is_valid(cur)) {
@@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
 		else
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+
+		*pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1;
 	}
 
 	return 0;
@@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 	}
 
 	if (iter.mtrr_disabled)
-		return mtrr_disabled_type();
+		return mtrr_disabled_type(vcpu);
 
 	/* not contained in any MTRRs. */
 	if (type == -1)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 83a1c643f9a5..899c40f826dd 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3422,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
+	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
+
 	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)
@@ -3892,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM);
-
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_handle_nmi(&svm->vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index af823a388c19..44976a596fa6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2803,7 +2803,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.ia32_xss;
 		break;
 	case MSR_TSC_AUX:
-		if (!guest_cpuid_has_rdtscp(vcpu))
+		if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
 			return 1;
 		/* Otherwise falls through */
 	default:
@@ -2909,7 +2909,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
 	case MSR_TSC_AUX:
-		if (!guest_cpuid_has_rdtscp(vcpu))
+		if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
 			return 1;
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
@@ -8042,6 +8042,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	u32 exit_reason = vmx->exit_reason;
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
+	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
+
 	/*
 	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more
 	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
@@ -8668,7 +8670,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx->loaded_vmcs->launched = 1;
 
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
-	trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
 
 	/*
 	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eed32283d22c..7ffc224bbe41 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3572,9 +3572,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
+	int i;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
-	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3593,6 +3595,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
 	int start = 0;
+	int i;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3602,7 +3605,8 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
 	       sizeof(kvm->arch.vpit->pit_state.channels));
 	kvm->arch.vpit->pit_state.flags = ps->flags;
-	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -6515,6 +6519,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
+	trace_kvm_entry(vcpu->vcpu_id);
+	wait_lapic_expire(vcpu);
 	__kvm_guest_enter();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
@@ -6527,8 +6533,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
 	}
 
-	trace_kvm_entry(vcpu->vcpu_id);
-	wait_lapic_expire(vcpu);
 	kvm_x86_ops->run(vcpu);
 
 	/*
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index a035c2aa7801..0f1c6fc3ddd8 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -89,7 +89,7 @@ static struct addr_marker address_markers[] = {
 	{ 0/* VMALLOC_START */, "vmalloc() Area" },
 	{ 0/*VMALLOC_END*/,     "vmalloc() End" },
 # ifdef CONFIG_HIGHMEM
-	{ 0/*PKMAP_BASE*/,      "Persisent kmap() Area" },
+	{ 0/*PKMAP_BASE*/,      "Persistent kmap() Area" },
 # endif
 	{ 0/*FIXADDR_START*/,   "Fixmap Area" },
 #endif
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 06934a8a4872..14fcd01ed992 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 		if (err)
 			return 1;
 
-		err = convert_fxsr_from_user(&fpx, sc.fpstate);
+		err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate);
 		if (err)
 			return 1;
 
@@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 	{
 		struct user_i387_struct fp;
 
-		err = copy_from_user(&fp, sc.fpstate,
+		err = copy_from_user(&fp, (void *)sc.fpstate,
 				     sizeof(struct user_i387_struct));
 		if (err)
 			return 1;
@@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to,
 #endif
 #undef PUTREG
 	sc.oldmask = mask;
-	sc.fpstate = to_fp;
+	sc.fpstate = (unsigned long)to_fp;
 
 	err = copy_to_user(to, &sc, sizeof(struct sigcontext));
 	if (err)
@@ -468,12 +468,10 @@ long sys_sigreturn(void)
 	struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
 	sigset_t set;
 	struct sigcontext __user *sc = &frame->sc;
-	unsigned long __user *oldmask = &sc->oldmask;
-	unsigned long __user *extramask = frame->extramask;
 	int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long);
 
-	if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) ||
-	    copy_from_user(&set.sig[1], extramask, sig_size))
+	if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) ||
+	    copy_from_user(&set.sig[1], frame->extramask, sig_size))
 		goto segfault;
 
 	set_current_blocked(&set);
@@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 {
 	struct rt_sigframe __user *frame;
 	int err = 0, sig = ksig->sig;
+	unsigned long fp_to;
 
 	frame = (struct rt_sigframe __user *)
 		round_down(stack_top - sizeof(struct rt_sigframe), 16);
@@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 	err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs));
 	err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
 			       set->sig[0]);
-	err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
+
+	fp_to = (unsigned long)&frame->fpstate;
+
+	err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate);
 	if (sizeof(*set) == 16) {
 		err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
 		err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index ac161db63388..cb5e266a8bf7 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2495,14 +2495,9 @@ void __init xen_init_mmu_ops(void)
 {
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 
-	/* Optimization - we can use the HVM one but it has no idea which
-	 * VCPUs are descheduled - which means that it will needlessly IPI
-	 * them. Xen knows so let it do the job.
-	 */
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-		pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others;
+	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return;
-	}
+
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index feddabdab448..3705eabd7e22 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -68,26 +68,16 @@ static void xen_pv_post_suspend(int suspend_cancelled)
 
 void xen_arch_pre_suspend(void)
 {
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		xen_pmu_finish(cpu);
-
 	if (xen_pv_domain())
 		xen_pv_pre_suspend();
 }
 
 void xen_arch_post_suspend(int cancelled)
 {
-	int cpu;
-
 	if (xen_pv_domain())
 		xen_pv_post_suspend(cancelled);
 	else
 		xen_hvm_post_suspend(cancelled);
-
-	for_each_online_cpu(cpu)
-		xen_pmu_init(cpu);
 }
 
 static void xen_vcpu_notify_restore(void *data)
@@ -106,10 +96,20 @@ static void xen_vcpu_notify_suspend(void *data)
 
 void xen_arch_resume(void)
 {
+	int cpu;
+
 	on_each_cpu(xen_vcpu_notify_restore, NULL, 1);
+
+	for_each_online_cpu(cpu)
+		xen_pmu_init(cpu);
 }
 
 void xen_arch_suspend(void)
 {
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		xen_pmu_finish(cpu);
+
 	on_each_cpu(xen_vcpu_notify_suspend, NULL, 1);
 }