Merge branch 'tracing/urgent' into tracing/ftrace

Conflicts:
	kernel/trace/trace.c

44 files changed, 296 insertions, 196 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index e6ab550bceb..8977d99987c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -21,7 +21,7 @@ config OPROFILE_IBS
           Instruction-Based Sampling (IBS) is a new profiling
           technique that provides rich, precise program performance
           information. IBS is introduced by AMD Family10h processors
-          (AMD Opteron Quad-Core processor “Barcelona”) to overcome
+          (AMD Opteron Quad-Core processor "Barcelona") to overcome
           the limitations of conventional performance counter
           sampling.
 
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 809ff9ab853..77764301844 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -44,10 +44,10 @@
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 32MB of the kernel text.
  */
-#define MODULE_END		(PAGE_OFFSET)
-#define MODULE_START		(MODULE_END - 16*1048576)
+#define MODULES_END		(PAGE_OFFSET)
+#define MODULES_VADDR		(MODULES_END - 16*1048576)
 
-#if TASK_SIZE > MODULE_START
+#if TASK_SIZE > MODULES_VADDR
 #error Top of user space clashes with start of module space
 #endif
 
@@ -56,7 +56,7 @@
  * Since we use sections to map it, this macro replaces the physical address
  * with its virtual address while keeping offset from the base section.
  */
-#define XIP_VIRT_ADDR(physaddr)  (MODULE_START + ((physaddr) & 0x000fffff))
+#define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
 /*
  * Allow 16MB-aligned ioremap pages
@@ -94,8 +94,8 @@
 /*
  * The module can be at any place in ram in nommu mode.
  */
-#define MODULE_END		(END_MEM)
-#define MODULE_START		(PHYS_OFFSET)
+#define MODULES_END		(END_MEM)
+#define MODULES_VADDR		(PHYS_OFFSET)
 
 #endif /* !CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 7aad78420f1..568020b34e3 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -42,6 +42,10 @@
 #define CR_U	(1 << 22)	/* Unaligned access operation		*/
 #define CR_XP	(1 << 23)	/* Extended page tables			*/
 #define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
+#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
+#define CR_AFE	(1 << 29)	/* Access flag enable			*/
+#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
 
 /*
  * This is used to ensure the compiler did actually allocate the register we
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index 513f332f040..84849098c8e 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -21,12 +21,16 @@ int elf_check_arch(const struct elf32_hdr *x)
 
 	eflags = x->e_flags;
 	if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) {
+		unsigned int flt_fmt;
+
 		/* APCS26 is only allowed if the CPU supports it */
 		if ((eflags & EF_ARM_APCS_26) && !(elf_hwcap & HWCAP_26BIT))
 			return 0;
 
+		flt_fmt = eflags & (EF_ARM_VFP_FLOAT | EF_ARM_SOFT_FLOAT);
+
 		/* VFP requires the supporting code */
-		if ((eflags & EF_ARM_VFP_FLOAT) && !(elf_hwcap & HWCAP_VFP))
+		if (flt_fmt == EF_ARM_VFP_FLOAT && !(elf_hwcap & HWCAP_VFP))
 			return 0;
 	}
 	return 1;
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 9203ba7d58e..b8d965dcd6f 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -26,12 +26,12 @@
 /*
  * The XIP kernel text is mapped in the module area for modules and
  * some other stuff to work without any indirect relocations.
- * MODULE_START is redefined here and not in asm/memory.h to avoid
+ * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
 extern void _etext;
-#undef MODULE_START
-#define MODULE_START	(((unsigned long)&_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#undef MODULES_VADDR
+#define MODULES_VADDR	(((unsigned long)&_etext + ~PGDIR_MASK) & PGDIR_MASK)
 #endif
 
 #ifdef CONFIG_MMU
@@ -43,7 +43,7 @@ void *module_alloc(unsigned long size)
 	if (!size)
 		return NULL;
 
-	area = __get_vm_area(size, VM_ALLOC, MODULE_START, MODULE_END);
+	area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END);
 	if (!area)
 		return NULL;
 
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 763bdbeaf68..2249049c1d5 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -429,18 +429,16 @@ void __init gpmc_init(void)
 	gpmc_l3_clk = clk_get(NULL, ck);
 	if (IS_ERR(gpmc_l3_clk)) {
 		printk(KERN_ERR "Could not get GPMC clock %s\n", ck);
-		return -ENODEV;
+		BUG();
 	}
 
 	gpmc_base = ioremap(l, SZ_4K);
 	if (!gpmc_base) {
 		clk_put(gpmc_l3_clk);
 		printk(KERN_ERR "Could not get GPMC register memory\n");
-		return -ENOMEM;
+		BUG();
 	}
 
-	BUG_ON(IS_ERR(gpmc_l3_clk));
-
 	l = gpmc_read_reg(GPMC_REVISION);
 	printk(KERN_INFO "GPMC revision %d.%d\n", (l >> 4) & 0x0f, l & 0x0f);
 	/* Set smart idle mode and automatic L3 clock gating */
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index 10b1bae1a25..464de893a98 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -98,7 +98,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Clean and invalidate partial last cache line.
 	 */
-	if (end & (CACHE_LINE_SIZE - 1)) {
+	if (start < end && (end & (CACHE_LINE_SIZE - 1))) {
 		xsc3_l2_clean_pa(end & ~(CACHE_LINE_SIZE - 1));
 		xsc3_l2_inv_pa(end & ~(CACHE_LINE_SIZE - 1));
 		end &= ~(CACHE_LINE_SIZE - 1);
@@ -107,7 +107,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Invalidate all full cache lines between 'start' and 'end'.
 	 */
-	while (start != end) {
+	while (start < end) {
 		xsc3_l2_inv_pa(start);
 		start += CACHE_LINE_SIZE;
 	}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 8ba75406455..e63db11f16a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -180,20 +180,20 @@ void adjust_cr(unsigned long mask, unsigned long set)
 #endif
 
 #define PROT_PTE_DEVICE		L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_WRITE
-#define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_XN|PMD_SECT_AP_WRITE
+#define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_AP_WRITE
 
 static struct mem_type mem_types[] = {
 	[MT_DEVICE] = {		  /* Strongly ordered / ARMv6 shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
 				  L_PTE_SHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_UNCACHED,
+		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_S,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_DEVICE_NONSHARED] = { /* ARMv6 non-shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_NONSHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_TEX(2),
+		.prot_sect	= PROT_SECT_DEVICE,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_DEVICE_CACHED] = {	  /* ioremap_cached */
@@ -205,7 +205,7 @@ static struct mem_type mem_types[] = {
 	[MT_DEVICE_WC] = {	/* ioremap_wc */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_WC,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_BUFFERABLE,
+		.prot_sect	= PROT_SECT_DEVICE,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_CACHECLEAN] = {
@@ -273,22 +273,23 @@ static void __init build_mem_type_table(void)
 #endif
 
 	/*
-	 * On non-Xscale3 ARMv5-and-older systems, use CB=01
-	 * (Uncached/Buffered) for ioremap_wc() mappings.  On XScale3
-	 * and ARMv6+, use TEXCB=00100 mappings (Inner/Outer Uncacheable
-	 * in xsc3 parlance, Uncached Normal in ARMv6 parlance).
+	 * Strip out features not present on earlier architectures.
+	 * Pre-ARMv5 CPUs don't have TEX bits.  Pre-ARMv6 CPUs or those
+	 * without extended page tables don't have the 'Shared' bit.
 	 */
-	if (cpu_is_xsc3() || cpu_arch >= CPU_ARCH_ARMv6) {
-		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
-		mem_types[MT_DEVICE_WC].prot_sect &= ~PMD_SECT_BUFFERABLE;
-	}
+	if (cpu_arch < CPU_ARCH_ARMv5)
+		for (i = 0; i < ARRAY_SIZE(mem_types); i++)
+			mem_types[i].prot_sect &= ~PMD_SECT_TEX(7);
+	if ((cpu_arch < CPU_ARCH_ARMv6 || !(cr & CR_XP)) && !cpu_is_xsc3())
+		for (i = 0; i < ARRAY_SIZE(mem_types); i++)
+			mem_types[i].prot_sect &= ~PMD_SECT_S;
 
 	/*
-	 * ARMv5 and lower, bit 4 must be set for page tables.
-	 * (was: cache "update-able on write" bit on ARM610)
-	 * However, Xscale cores require this bit to be cleared.
+	 * ARMv5 and lower, bit 4 must be set for page tables (was: cache
+	 * "update-able on write" bit on ARM610).  However, Xscale and
+	 * Xscale3 require this bit to be cleared.
 	 */
-	if (cpu_is_xscale()) {
+	if (cpu_is_xscale() || cpu_is_xsc3()) {
 		for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
 			mem_types[i].prot_sect &= ~PMD_BIT4;
 			mem_types[i].prot_l1 &= ~PMD_BIT4;
@@ -302,6 +303,64 @@ static void __init build_mem_type_table(void)
 		}
 	}
 
+	/*
+	 * Mark the device areas according to the CPU/architecture.
+	 */
+	if (cpu_is_xsc3() || (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP))) {
+		if (!cpu_is_xsc3()) {
+			/*
+			 * Mark device regions on ARMv6+ as execute-never
+			 * to prevent speculative instruction fetches.
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN;
+		}
+		if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
+			/*
+			 * For ARMv7 with TEX remapping,
+			 * - shared device is SXCB=1100
+			 * - nonshared device is SXCB=0100
+			 * - write combine device mem is SXCB=0001
+			 * (Uncached Normal memory)
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1);
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(1);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
+		} else if (cpu_is_xsc3()) {
+			/*
+			 * For Xscale3,
+			 * - shared device is TEXCB=00101
+			 * - nonshared device is TEXCB=01000
+			 * - write combine device mem is TEXCB=00100
+			 * (Inner/Outer Uncacheable in xsc3 parlance)
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1) | PMD_SECT_BUFFERED;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
+		} else {
+			/*
+			 * For ARMv6 and ARMv7 without TEX remapping,
+			 * - shared device is TEXCB=00001
+			 * - nonshared device is TEXCB=01000
+			 * - write combine device mem is TEXCB=00100
+			 * (Uncached Normal in ARMv6 parlance).
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
+		}
+	} else {
+		/*
+		 * On others, write combining is "Uncached/Buffered"
+		 */
+		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
+	}
+
+	/*
+	 * Now deal with the memory-type mappings
+	 */
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
@@ -317,12 +376,8 @@ static void __init build_mem_type_table(void)
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
-	if (arch_is_coherent()) {
-		if (cpu_is_xsc3()) {
-			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
-		}
-	}
+	if (arch_is_coherent() && cpu_is_xsc3())
+		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 
 	/*
 	 * ARMv6 and above have extended page tables.
@@ -336,11 +391,6 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 
-		/*
-		 * Mark the device area as "shared device"
-		 */
-		mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED;
-
 #ifdef CONFIG_SMP
 		/*
 		 * Mark memory with the "shared" attribute for SMP systems
@@ -360,9 +410,6 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_LOW_VECTORS].prot_pte |= vecs_pgprot;
 	mem_types[MT_HIGH_VECTORS].prot_pte |= vecs_pgprot;
 
-	if (cpu_arch < CPU_ARCH_ARMv5)
-		mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1);
-
 	pgprot_user   = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot);
 	pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
 				 L_PTE_DIRTY | L_PTE_WRITE |
@@ -654,7 +701,7 @@ static inline void prepare_page_table(struct meminfo *mi)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
-	for (addr = 0; addr < MODULE_START; addr += PGDIR_SIZE)
+	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 #ifdef CONFIG_XIP_KERNEL
@@ -766,7 +813,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 #ifdef CONFIG_XIP_KERNEL
 	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
-	map.virtual = MODULE_START;
+	map.virtual = MODULES_VADDR;
 	map.length = ((unsigned long)&_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK;
 	map.type = MT_ROM;
 	create_mapping(&map);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 07f82db7094..4d3c0a73e7f 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -115,7 +115,7 @@ ENTRY(cpu_v7_set_pte_ext)
 	orr	r3, r3, r2
 	orr	r3, r3, #PTE_EXT_AP0 | 2
 
-	tst	r2, #1 << 4
+	tst	r1, #1 << 4
 	orrne	r3, r3, #PTE_EXT_TEX(1)
 
 	tst	r1, #L_PTE_WRITE
@@ -192,11 +192,11 @@ __v7_setup:
 	mov	pc, lr				@ return to head.S:__ret
 ENDPROC(__v7_setup)
 
-	/*
-	 *         V X F   I D LR
-	 * .... ...E PUI. .T.T 4RVI ZFRS BLDP WCAM
-	 * rrrr rrrx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *         0 110       0011 1.00 .111 1101 < we want
+	/*   AT
+	 *  TFR   EV X F   I D LR
+	 * .EEE ..EE PUI. .T.T 4RVI ZFRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *    1    0 110       0011 1.00 .111 1101 < we want
 	 */
 	.type	v7_crval, #object
 v7_crval:
diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c
index bf6a10c5fc4..be6aab9c683 100644
--- a/arch/arm/plat-omap/clock.c
+++ b/arch/arm/plat-omap/clock.c
@@ -428,23 +428,23 @@ static int clk_debugfs_register_one(struct clk *c)
 	if (c->id != 0)
 		sprintf(p, ":%d", c->id);
 	d = debugfs_create_dir(s, pa ? pa->dent : clk_debugfs_root);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
+	if (!d)
+		return -ENOMEM;
 	c->dent = d;
 
 	d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount);
-	if (IS_ERR(d)) {
-		err = PTR_ERR(d);
+	if (!d) {
+		err = -ENOMEM;
 		goto err_out;
 	}
 	d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate);
-	if (IS_ERR(d)) {
-		err = PTR_ERR(d);
+	if (!d) {
+		err = -ENOMEM;
 		goto err_out;
 	}
 	d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags);
-	if (IS_ERR(d)) {
-		err = PTR_ERR(d);
+	if (!d) {
+		err = -ENOMEM;
 		goto err_out;
 	}
 	return 0;
@@ -483,8 +483,8 @@ static int __init clk_debugfs_init(void)
 	int err;
 
 	d = debugfs_create_dir("clock", NULL);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
+	if (!d)
+		return -ENOMEM;
 	clk_debugfs_root = d;
 
 	list_for_each_entry(c, &clocks, node) {
diff --git a/arch/arm/plat-omap/include/mach/entry-macro.S b/arch/arm/plat-omap/include/mach/entry-macro.S
index 030118ee204..2276f89671d 100644
--- a/arch/arm/plat-omap/include/mach/entry-macro.S
+++ b/arch/arm/plat-omap/include/mach/entry-macro.S
@@ -65,7 +65,8 @@
 #include <mach/omap34xx.h>
 #endif
 
-#define INTCPS_SIR_IRQ_OFFSET	0x0040		/* Active interrupt number */
+#define INTCPS_SIR_IRQ_OFFSET	0x0040		/* Active interrupt offset */
+#define	ACTIVEIRQ_MASK		0x7f		/* Active interrupt bits */
 
 		.macro	disable_fiq
 		.endm
@@ -88,6 +89,7 @@
 		cmp	\irqnr, #0x0
 2222:
 		ldrne	\irqnr, [\base, #INTCPS_SIR_IRQ_OFFSET]
+		and	\irqnr, \irqnr, #ACTIVEIRQ_MASK /* Clear spurious bits */
 
 		.endm
 
diff --git a/arch/arm/plat-omap/include/mach/irqs.h b/arch/arm/plat-omap/include/mach/irqs.h
index a2929ac8c68..bed5274c910 100644
--- a/arch/arm/plat-omap/include/mach/irqs.h
+++ b/arch/arm/plat-omap/include/mach/irqs.h
@@ -372,7 +372,7 @@
 
 /* External TWL4030 gpio interrupts are optional */
 #define TWL4030_GPIO_IRQ_BASE	TWL4030_PWR_IRQ_END
-#ifdef	CONFIG_TWL4030_GPIO
+#ifdef	CONFIG_GPIO_TWL4030
 #define TWL4030_GPIO_NR_IRQS	18
 #else
 #define	TWL4030_GPIO_NR_IRQS	0
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 27eec71429b..6bd91ed7cd0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -148,6 +148,7 @@ config IA64_GENERIC
 	select ACPI_NUMA
 	select SWIOTLB
 	select PCI_MSI
+	select DMAR
 	help
 	  This selects the system type of your hardware.  A "generic" kernel
 	  will run on any supported IA-64 system.  However, if you configure
@@ -585,7 +586,7 @@ source "fs/Kconfig.binfmt"
 
 endmenu
 
-menu "Power management and ACPI"
+menu "Power management and ACPI options"
 
 source "kernel/power/Kconfig"
 
@@ -641,6 +642,8 @@ source "net/Kconfig"
 
 source "drivers/Kconfig"
 
+source "arch/ia64/hp/sim/Kconfig"
+
 config MSPEC
 	tristate "Memory special operations driver"
 	depends on IA64
@@ -652,6 +655,12 @@ config MSPEC
 
 source "fs/Kconfig"
 
+source "arch/ia64/Kconfig.debug"
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
 source "arch/ia64/kvm/Kconfig"
 
 source "lib/Kconfig"
@@ -678,11 +687,3 @@ config IRQ_PER_CPU
 
 config IOMMU_HELPER
 	def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
-
-source "arch/ia64/hp/sim/Kconfig"
-
-source "arch/ia64/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c
index 88b6e6f3fd8..2769dbfd03b 100644
--- a/arch/ia64/hp/common/hwsw_iommu.c
+++ b/arch/ia64/hp/common/hwsw_iommu.c
@@ -13,19 +13,12 @@
  */
 
 #include <linux/device.h>
+#include <linux/swiotlb.h>
 
 #include <asm/machvec.h>
 
 /* swiotlb declarations & definitions: */
 extern int swiotlb_late_init_with_default_size (size_t size);
-extern ia64_mv_dma_alloc_coherent	swiotlb_alloc_coherent;
-extern ia64_mv_dma_free_coherent	swiotlb_free_coherent;
-extern ia64_mv_dma_map_single_attrs	swiotlb_map_single_attrs;
-extern ia64_mv_dma_unmap_single_attrs	swiotlb_unmap_single_attrs;
-extern ia64_mv_dma_map_sg_attrs		swiotlb_map_sg_attrs;
-extern ia64_mv_dma_unmap_sg_attrs	swiotlb_unmap_sg_attrs;
-extern ia64_mv_dma_supported		swiotlb_dma_supported;
-extern ia64_mv_dma_mapping_error	swiotlb_dma_mapping_error;
 
 /* hwiommu declarations & definitions: */
 
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 7f257507cd8..0d9d16e2d94 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -434,28 +434,4 @@ extern void memset_io(volatile void __iomem *s, int c, long n);
 
 # endif /* __KERNEL__ */
 
-/*
- * Enabling BIO_VMERGE_BOUNDARY forces us to turn off I/O MMU bypassing.  It is said that
- * BIO-level virtual merging can give up to 4% performance boost (not verified for ia64).
- * On the other hand, we know that I/O MMU bypassing gives ~8% performance improvement on
- * SPECweb-like workloads on zx1-based machines.  Thus, for now we favor I/O MMU bypassing
- * over BIO-level virtual merging.
- */
-extern unsigned long ia64_max_iommu_merge_mask;
-#if 1
-#define BIO_VMERGE_BOUNDARY	0
-#else
-/*
- * It makes no sense at all to have this BIO_VMERGE_BOUNDARY macro here.  Should be
- * replaced by dma_merge_mask() or something of that sort.  Note: the only way
- * BIO_VMERGE_BOUNDARY is used is to mask off bits.  Effectively, our definition gets
- * expanded into:
- *
- *	addr & ((ia64_max_iommu_merge_mask + 1) - 1) == (addr & ia64_max_iommu_vmerge_mask)
- *
- * which is precisely what we want.
- */
-#define BIO_VMERGE_BOUNDARY	(ia64_max_iommu_merge_mask + 1)
-#endif
-
 #endif /* _ASM_IA64_IO_H */
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 1ea28bcee33..59c17e44668 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -11,6 +11,7 @@
 #define _ASM_IA64_MACHVEC_H
 
 #include <linux/types.h>
+#include <linux/swiotlb.h>
 
 /* forward declarations: */
 struct device;
@@ -298,27 +299,6 @@ extern void machvec_init_from_cmdline(const char *cmdline);
 # endif /* CONFIG_IA64_GENERIC */
 
 /*
- * Declare default routines which aren't declared anywhere else:
- */
-extern ia64_mv_dma_init			swiotlb_init;
-extern ia64_mv_dma_alloc_coherent	swiotlb_alloc_coherent;
-extern ia64_mv_dma_free_coherent	swiotlb_free_coherent;
-extern ia64_mv_dma_map_single		swiotlb_map_single;
-extern ia64_mv_dma_map_single_attrs	swiotlb_map_single_attrs;
-extern ia64_mv_dma_unmap_single		swiotlb_unmap_single;
-extern ia64_mv_dma_unmap_single_attrs	swiotlb_unmap_single_attrs;
-extern ia64_mv_dma_map_sg		swiotlb_map_sg;
-extern ia64_mv_dma_map_sg_attrs		swiotlb_map_sg_attrs;
-extern ia64_mv_dma_unmap_sg		swiotlb_unmap_sg;
-extern ia64_mv_dma_unmap_sg_attrs	swiotlb_unmap_sg_attrs;
-extern ia64_mv_dma_sync_single_for_cpu	swiotlb_sync_single_for_cpu;
-extern ia64_mv_dma_sync_sg_for_cpu	swiotlb_sync_sg_for_cpu;
-extern ia64_mv_dma_sync_single_for_device swiotlb_sync_single_for_device;
-extern ia64_mv_dma_sync_sg_for_device	swiotlb_sync_sg_for_device;
-extern ia64_mv_dma_mapping_error	swiotlb_dma_mapping_error;
-extern ia64_mv_dma_supported		swiotlb_dma_supported;
-
-/*
  * Define default versions so we can extend machvec for new platforms without having
  * to update the machvec files for all existing platforms.
  */
diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h
index 6bc96ee5432..c0cea375620 100644
--- a/arch/ia64/include/asm/meminit.h
+++ b/arch/ia64/include/asm/meminit.h
@@ -48,7 +48,6 @@ extern int reserve_elfcorehdr(unsigned long *start, unsigned long *end);
  */
 #define GRANULEROUNDDOWN(n)	((n) & ~(IA64_GRANULE_SIZE-1))
 #define GRANULEROUNDUP(n)	(((n)+IA64_GRANULE_SIZE-1) & ~(IA64_GRANULE_SIZE-1))
-#define ORDERROUNDDOWN(n)	((n) & ~((PAGE_SIZE<<MAX_ORDER)-1))
 
 #ifdef CONFIG_NUMA
   extern void call_pernode_memory (unsigned long start, unsigned long len, void *func);
diff --git a/arch/ia64/include/asm/sal.h b/arch/ia64/include/asm/sal.h
index ea310c0812a..966797a97c9 100644
--- a/arch/ia64/include/asm/sal.h
+++ b/arch/ia64/include/asm/sal.h
@@ -337,11 +337,24 @@ typedef struct sal_log_record_header {
 #define sal_log_severity_fatal		1
 #define sal_log_severity_corrected	2
 
+/*
+ * Error Recovery Info (ERI) bit decode.  From SAL Spec section B.2.2 Table B-3
+ * Error Section Error_Recovery_Info Field Definition.
+ */
+#define ERI_NOT_VALID		0x0	/* Error Recovery Field is not valid */
+#define ERI_NOT_ACCESSIBLE	0x30	/* Resource not accessible */
+#define ERI_CONTAINMENT_WARN	0x22	/* Corrupt data propagated */
+#define ERI_UNCORRECTED_ERROR	0x20	/* Uncorrected error */
+#define ERI_COMPONENT_RESET	0x24	/* Component must be reset */
+#define ERI_CORR_ERROR_LOG	0x21	/* Corrected error, needs logging */
+#define ERI_CORR_ERROR_THRESH	0x29	/* Corrected error threshold exceeded */
+
 /* Definition of log section header structures */
 typedef struct sal_log_sec_header {
     efi_guid_t guid;			/* Unique Section ID */
     sal_log_revision_t revision;	/* Major and Minor revision of Section */
-    u16 reserved;
+    u8 error_recovery_info;		/* Platform error recovery status */
+    u8 reserved;
     u32 len;				/* Section length */
 } sal_log_section_hdr_t;
 
diff --git a/arch/ia64/include/asm/sn/sn_sal.h b/arch/ia64/include/asm/sn/sn_sal.h
index 57e649d388b..e310fc0135d 100644
--- a/arch/ia64/include/asm/sn/sn_sal.h
+++ b/arch/ia64/include/asm/sn/sn_sal.h
@@ -90,6 +90,8 @@
 #define  SN_SAL_SET_CPU_NUMBER			   0x02000068
 
 #define  SN_SAL_KERNEL_LAUNCH_EVENT		   0x02000069
+#define  SN_SAL_WATCHLIST_ALLOC			   0x02000070
+#define  SN_SAL_WATCHLIST_FREE			   0x02000071
 
 /*
  * Service-specific constants
@@ -1185,4 +1187,47 @@ ia64_sn_kernel_launch_event(void)
 	SAL_CALL_NOLOCK(rv, SN_SAL_KERNEL_LAUNCH_EVENT, 0, 0, 0, 0, 0, 0, 0);
 	return rv.status;
 }
+
+union sn_watchlist_u {
+	u64     val;
+	struct {
+		u64	blade	: 16,
+			size	: 32,
+			filler	: 16;
+	};
+};
+
+static inline int
+sn_mq_watchlist_alloc(int blade, void *mq, unsigned int mq_size,
+				unsigned long *intr_mmr_offset)
+{
+	struct ia64_sal_retval rv;
+	unsigned long addr;
+	union sn_watchlist_u size_blade;
+	int watchlist;
+
+	addr = (unsigned long)mq;
+	size_blade.size = mq_size;
+	size_blade.blade = blade;
+
+	/*
+	 * bios returns watchlist number or negative error number.
+	 */
+	ia64_sal_oemcall_nolock(&rv, SN_SAL_WATCHLIST_ALLOC, addr,
+			size_blade.val, (u64)intr_mmr_offset,
+			(u64)&watchlist, 0, 0, 0);
+	if (rv.status < 0)
+		return rv.status;
+
+	return watchlist;
+}
+
+static inline int
+sn_mq_watchlist_free(int blade, int watchlist_num)
+{
+	struct ia64_sal_retval rv;
+	ia64_sal_oemcall_nolock(&rv, SN_SAL_WATCHLIST_FREE, blade,
+			watchlist_num, 0, 0, 0, 0, 0);
+	return rv.status;
+}
 #endif /* _ASM_IA64_SN_SN_SAL_H */
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 0635015d0aa..bd7acc71e8a 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -678,6 +678,30 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 	return 0;
 }
 
+int __init early_acpi_boot_init(void)
+{
+	int ret;
+
+	/*
+	 * do a partial walk of MADT to determine how many CPUs
+	 * we have including offline CPUs
+	 */
+	if (acpi_table_parse(ACPI_SIG_MADT, acpi_parse_madt)) {
+		printk(KERN_ERR PREFIX "Can't find MADT\n");
+		return 0;
+	}
+
+	ret = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
+		acpi_parse_lsapic, NR_CPUS);
+	if (ret < 1)
+		printk(KERN_ERR PREFIX
+		       "Error parsing MADT - no LAPIC entries\n");
+
+	return 0;
+}
+
+
+
 int __init acpi_boot_init(void)
 {
 
@@ -701,11 +725,6 @@ int __init acpi_boot_init(void)
 		printk(KERN_ERR PREFIX
 		       "Error parsing LAPIC address override entry\n");
 
-	if (acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, acpi_parse_lsapic, NR_CPUS)
-	    < 1)
-		printk(KERN_ERR PREFIX
-		       "Error parsing MADT - no LAPIC entries\n");
-
 	if (acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0)
 	    < 0)
 		printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index 031abbf9c87..dbdb778efa0 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -12,13 +12,11 @@
 #include <asm/machvec.h>
 #include <linux/dma-mapping.h>
 
-#include <asm/machvec.h>
 #include <asm/system.h>
 
 #ifdef CONFIG_DMAR
 
 #include <linux/kernel.h>
-#include <linux/string.h>
 
 #include <asm/page.h>
 #include <asm/iommu.h>
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index ae7911702bf..865af27c773 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -359,7 +359,7 @@ reserve_memory (void)
 	}
 #endif
 
-#ifdef CONFIG_CRASH_KERNEL
+#ifdef CONFIG_CRASH_DUMP
 	if (reserve_elfcorehdr(&rsvd_region[n].start,
 			       &rsvd_region[n].end) == 0)
 		n++;
@@ -561,8 +561,12 @@ setup_arch (char **cmdline_p)
 #ifdef CONFIG_ACPI
 	/* Initialize the ACPI boot-time table parser */
 	acpi_table_init();
+	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+	prefill_possible_map();
+#endif
 	per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
 		32 : cpus_weight(early_cpu_possible_map)),
 		additional_cpus > 0 ? additional_cpus : 0);
@@ -853,9 +857,6 @@ void __init
 setup_per_cpu_areas (void)
 {
 	/* start_kernel() requires this... */
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-	prefill_possible_map();
-#endif
 }
 
 /*
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index d8c5fcd89e5..d85ba98d900 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -635,7 +635,6 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 			(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
 #endif
 	start = GRANULEROUNDDOWN(start);
-	start = ORDERROUNDDOWN(start);
 	end = GRANULEROUNDUP(end);
 	mem_data[node].max_pfn = max(mem_data[node].max_pfn,
 				     end >> PAGE_SHIFT);
diff --git a/arch/ia64/uv/kernel/setup.c b/arch/ia64/uv/kernel/setup.c
index cf5f28ae96c..7a5ae633198 100644
--- a/arch/ia64/uv/kernel/setup.c
+++ b/arch/ia64/uv/kernel/setup.c
@@ -19,6 +19,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
 
 #ifdef CONFIG_IA64_SGI_UV
 int sn_prom_type;
+long sn_partition_id;
+EXPORT_SYMBOL(sn_partition_id);
+long sn_coherency_id;
+EXPORT_SYMBOL_GPL(sn_coherency_id);
+long sn_region_size;
+EXPORT_SYMBOL(sn_region_size);
 #endif
 
 struct redir_addr {
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index fdf088f2430..7b4cefa2199 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -16,6 +16,7 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 
+#include <asm/kexec.h>
 #include <asm/reg.h>
 #include <asm/io.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 31481dc485d..7190493e9bd 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -189,7 +189,6 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
 {
 	struct pci_controller *phb;
 	int primary;
-	struct pci_bus *b;
 
 	primary = list_empty(&hose_list);
 	phb = pcibios_alloc_controller(dn);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d03e91762f6..27b8a3a3991 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1495,7 +1495,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
 	def_bool X86_64
 	depends on NUMA
 
-menu "Power management options"
+menu "Power management and ACPI options"
 	depends on !X86_VOYAGER
 
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d843ed0e9b2..0005adb0f94 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -101,30 +101,22 @@
 #define LAST_VM86_IRQ		15
 #define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
 
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
 # else
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
 
-#elif !defined(CONFIG_X86_VOYAGER)
+#elif defined(CONFIG_X86_VOYAGER)
 
-# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
-
-#  define NR_IRQS		224
-
-# else /* IO_APIC || PARAVIRT */
-
-#  define NR_IRQS		16
-
-# endif
+# define NR_IRQS		224
 
-#else /* !VISWS && !VOYAGER */
+#else /* IO_APIC || VOYAGER */
 
-# define NR_IRQS		224
+# define NR_IRQS		16
 
-#endif /* VISWS */
+#endif
 
 /* Voyager specific defines */
 /* These define the CPIs we use in linux */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 46be2fa7ac2..c2a812ebde8 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -108,9 +108,7 @@ static __always_inline unsigned long long __native_read_tsc(void)
 {
 	DECLARE_ARGS(val, low, high);
 
-	rdtsc_barrier();
 	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
-	rdtsc_barrier();
 
 	return EAX_EDX_VAL(val, low, high);
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 90ac7718469..4850e4b02b6 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -154,7 +154,7 @@ extern unsigned long node_remap_size[];
 
 #endif
 
-/* sched_domains SD_NODE_INIT for NUMAQ machines */
+/* sched_domains SD_NODE_INIT for NUMA machines */
 #define SD_NODE_INIT (struct sched_domain) {		\
 	.min_interval		= 8,			\
 	.max_interval		= 32,			\
@@ -169,8 +169,9 @@ extern unsigned long node_remap_size[];
 	.flags			= SD_LOAD_BALANCE	\
 				| SD_BALANCE_EXEC	\
 				| SD_BALANCE_FORK	\
-				| SD_SERIALIZE		\
-				| SD_WAKE_BALANCE,	\
+				| SD_WAKE_AFFINE	\
+				| SD_WAKE_BALANCE	\
+				| SD_SERIALIZE,		\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 }
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 38ae163cc91..9cd83a8e40d 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,6 +34,8 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
+	cycles_t cycles;
+
 	/*
 	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
 	 * access boot_cpu_data (which is not VDSO-safe):
@@ -42,7 +44,11 @@ static __always_inline cycles_t vget_cycles(void)
 	if (!cpu_has_tsc)
 		return 0;
 #endif
-	return (cycles_t)__native_read_tsc();
+	rdtsc_barrier();
+	cycles = (cycles_t)__native_read_tsc();
+	rdtsc_barrier();
+
+	return cycles;
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
index 9c811d2e6f9..b3e64730762 100644
--- a/arch/x86/include/asm/voyager.h
+++ b/arch/x86/include/asm/voyager.h
@@ -520,6 +520,7 @@ extern void voyager_restart(void);
 extern void voyager_cat_power_off(void);
 extern void voyager_cat_do_common_interrupt(void);
 extern void voyager_handle_nmi(void);
+extern void voyager_smp_intr_init(void);
 /* Commands for the following are */
 #define	VOYAGER_PSI_READ	0
 #define VOYAGER_PSI_WRITE	1
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a8fd9ebdc8e..331b318304e 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -50,7 +50,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 /* returns !0 if the IOMMU is caching non-present entries in its TLB */
 static int iommu_has_npcache(struct amd_iommu *iommu)
 {
-	return iommu->cap & IOMMU_CAP_NPCACHE;
+	return iommu->cap & (1UL << IOMMU_CAP_NPCACHE);
 }
 
 /****************************************************************************
@@ -536,6 +536,9 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
 {
 	address >>= PAGE_SHIFT;
 	iommu_area_free(dom->bitmap, address, pages);
+
+	if (address + pages >= dom->next_bit)
+		dom->need_flush = true;
 }
 
 /****************************************************************************
@@ -992,8 +995,10 @@ static void __unmap_single(struct amd_iommu *iommu,
 
 	dma_ops_free_addresses(dma_dom, dma_addr, pages);
 
-	if (amd_iommu_unmap_flush)
+	if (amd_iommu_unmap_flush || dma_dom->need_flush) {
 		iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size);
+		dma_dom->need_flush = false;
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index b764d7429c6..7a3f2028e2e 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3611,6 +3611,8 @@ int __init probe_nr_irqs(void)
 	/* something wrong ? */
 	if (nr < nr_min)
 		nr = nr_min;
+	if (WARN_ON(nr > NR_IRQS))
+		nr = NR_IRQS;
 
 	return nr;
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f4c93f1cfc1..724adfc63cb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -29,11 +29,7 @@ EXPORT_SYMBOL(pm_power_off);
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-/*
- * Keyboard reset and triple fault may result in INIT, not RESET, which
- * doesn't work when we're in vmx root mode.  Try ACPI first.
- */
-enum reboot_type reboot_type = BOOT_ACPI;
+enum reboot_type reboot_type = BOOT_KBD;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index e00534b3353..f4049f3513b 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -154,6 +154,12 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
 	flush_mm = mm;
 	flush_va = va;
 	cpus_or(flush_cpumask, cpumask, flush_cpumask);
+
+	/*
+	 * Make the above memory operations globally visible before
+	 * sending the IPI.
+	 */
+	smp_mb();
 	/*
 	 * We have to send the IPI only to
 	 * CPUs affected.
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index dcbf7a1159e..8f919ca6949 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -183,6 +183,11 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
 	cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
 
 	/*
+	 * Make the above memory operations globally visible before
+	 * sending the IPI.
+	 */
+	smp_mb();
+	/*
 	 * We have to send the IPI only to
 	 * CPUs affected.
 	 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 62348e4fd8d..424093b157d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -55,7 +55,7 @@ u64 native_sched_clock(void)
 	rdtscll(this_offset);
 
 	/* return the value in ns */
-	return cycles_2_ns(this_offset);
+	return __cycles_2_ns(this_offset);
 }
 
 /* We need to define a real function for sched_clock, to override the
@@ -813,10 +813,6 @@ void __init tsc_init(void)
 		cpu_khz = calibrate_cpu();
 #endif
 
-	lpj = ((u64)tsc_khz * 1000);
-	do_div(lpj, HZ);
-	lpj_fine = lpj;
-
 	printk("Detected %lu.%03lu MHz processor.\n",
 			(unsigned long)cpu_khz / 1000,
 			(unsigned long)cpu_khz % 1000);
@@ -836,6 +832,10 @@ void __init tsc_init(void)
 	/* now allow native_sched_clock() to use rdtsc */
 	tsc_disabled = 0;
 
+	lpj = ((u64)tsc_khz * 1000);
+	do_div(lpj, HZ);
+	lpj_fine = lpj;
+
 	use_tsc_delay();
 	/* Check and install the TSC clocksource */
 	dmi_check_system(bad_tsc_dmi_table);
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index 6bbdd633864..a580b9562e7 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -27,7 +27,7 @@ static struct irqaction irq2 = {
 void __init intr_init_hook(void)
 {
 #ifdef CONFIG_SMP
-	smp_intr_init();
+	voyager_smp_intr_init();
 #endif
 
 	setup_irq(2, &irq2);
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 7f4c6af1435..0e331652681 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -1258,7 +1258,7 @@ static void handle_vic_irq(unsigned int irq, struct irq_desc *desc)
 #define QIC_SET_GATE(cpi, vector) \
 	set_intr_gate((cpi) + QIC_DEFAULT_CPI_BASE, (vector))
 
-void __init smp_intr_init(void)
+void __init voyager_smp_intr_init(void)
 {
 	int i;
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d16..e89d24815f2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
 
 void arch_report_meminfo(struct seq_file *m)
 {
-	seq_printf(m, "DirectMap4k:  %8lu kB\n",
+	seq_printf(m, "DirectMap4k:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_4K] << 2);
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-	seq_printf(m, "DirectMap2M:  %8lu kB\n",
+	seq_printf(m, "DirectMap2M:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 11);
 #else
-	seq_printf(m, "DirectMap4M:  %8lu kB\n",
+	seq_printf(m, "DirectMap4M:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 12);
 #endif
 #ifdef CONFIG_X86_64
 	if (direct_gbpages)
-		seq_printf(m, "DirectMap1G:  %8lu kB\n",
+		seq_printf(m, "DirectMap1G:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
 }
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 0620d6d45f7..3f1b81a83e2 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -27,8 +27,7 @@ static int num_counters = 2;
 static int counter_width = 32;
 
 #define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1))))
+#define CTR_OVERFLOWED(n) (!((n) & (1ULL<<(counter_width-1))))
 
 #define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
 #define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
@@ -124,14 +123,14 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 static int ppro_check_ctrs(struct pt_regs * const regs,
 			   struct op_msrs const * const msrs)
 {
-	unsigned int low, high;
+	u64 val;
 	int i;
 
 	for (i = 0 ; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
-		CTR_READ(low, high, msrs, i);
-		if (CTR_OVERFLOWED(low)) {
+		rdmsrl(msrs->counters[i].addr, val);
+		if (CTR_OVERFLOWED(val)) {
 			oprofile_add_sample(regs, i);
 			wrmsrl(msrs->counters[i].addr, -reset_value[i]);
 		}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b61534c7a4c..5e4686d70f6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -863,15 +863,16 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l
 	if (PagePinned(virt_to_page(mm->pgd))) {
 		SetPagePinned(page);
 
+		vm_unmap_aliases();
 		if (!PageHighMem(page)) {
 			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
 				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
-		} else
+		} else {
 			/* make sure there are no stray mappings of
 			   this page */
 			kmap_flush_unused();
-			vm_unmap_aliases();
+		}
 	}
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index aba77b2b7d1..688936044dc 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -850,13 +850,16 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
+	vm_unmap_aliases();
+
 	xen_mc_batch();
 
-	if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
-		/* re-enable interrupts for kmap_flush_unused */
+	 if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
+		/* re-enable interrupts for flushing */
 		xen_mc_issue(0);
+
 		kmap_flush_unused();
-		vm_unmap_aliases();
+
 		xen_mc_batch();
 	}
 
@@ -874,7 +877,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 #else /* CONFIG_X86_32 */
 #ifdef CONFIG_X86_PAE
 	/* Need to make sure unshared kernel PMD is pinnable */
-	xen_pin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
 		     PT_PMD);
 #endif
 	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
@@ -991,7 +994,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
 	/* Need to make sure unshared kernel PMD is unpinned */
-	xen_unpin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
 		       PT_PMD);
 #endif