Merge branch 'sched/urgent' into sched/core

32 files changed, 236 insertions, 114 deletions

diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 809ff9ab853a..77764301844b 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 7aad78420f18..568020b34e3e 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 513f332f040d..84849098c8e8 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 9203ba7d58ee..b8d965dcd6fd 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 763bdbeaf681..2249049c1d5a 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 10b1bae1a258..464de893a988 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 8ba754064559..e63db11f16a8 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 07f82db70945..4d3c0a73e7fb 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 bf6a10c5fc4f..be6aab9c6834 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 030118ee204a..2276f89671d8 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 a2929ac8c687..bed5274c910a 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/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index fdf088f2430e..7b4cefa2199b 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 31481dc485de..7190493e9bdc 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 488a4ecd0b59..1d5550d19b66 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1494,7 +1494,7 @@ 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
@@ -1894,6 +1894,10 @@ config SYSVIPC_COMPAT
 endmenu
 
 
+config HAVE_ATOMIC_IOMAP
+        def_bool y
+        depends on X86_32
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 8668a94f850e..23696d44a0af 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -9,6 +9,10 @@
 
 extern int fixmaps_set;
 
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
 void native_set_fixmap(enum fixed_addresses idx,
                        unsigned long phys, pgprot_t flags);
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
index 09f29ab5c139..c7115c1d7217 100644
--- a/arch/x86/include/asm/fixmap_32.h
+++ b/arch/x86/include/asm/fixmap_32.h
@@ -28,10 +28,8 @@ extern unsigned long __FIXADDR_TOP;
 #include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
-#endif
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -75,10 +73,8 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_CYCLONE_TIMER
         FIX_CYCLONE_TIMER, /*cyclone timer register*/
 #endif
-#ifdef CONFIG_HIGHMEM
         FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
         FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
 #ifdef CONFIG_PCI_MMCONFIG
         FIX_PCIE_MCFG,
 #endif
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index a3b3b7c3027b..bf9276bea660 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -25,14 +25,11 @@
 #include <asm/kmap_types.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
+#include <asm/fixmap.h>
 
 /* declarations for highmem.c */
 extern unsigned long highstart_pfn, highend_pfn;
 
-extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
-extern pte_t *pkmap_page_table;
-
 /*
  * Right now we initialize only a single pte table. It can be extended
  * easily, subsequent pte tables have to be allocated in one physical
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d843ed0e9b2e..0005adb0f941 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/topology.h b/arch/x86/include/asm/topology.h
index 90ac7718469a..4850e4b02b61 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/voyager.h b/arch/x86/include/asm/voyager.h
index 9c811d2e6f91..b3e647307625 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 a8fd9ebdc8e2..331b318304eb 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 b764d7429c61..7a3f2028e2eb 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 f4c93f1cfc19..724adfc63cb9 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 e00534b33534..f4049f3513b6 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 dcbf7a1159ea..8f919ca69494 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 62348e4fd8d1..2ef80e301925 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -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 6bbdd633864c..a580b9562e76 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 7f4c6af14351..0e331652681e 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/Makefile b/arch/x86/mm/Makefile
index 59f89b434b45..fea4565ff576 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
             pat.o pgtable.o gup.o
 
-obj-$(CONFIG_X86_32)            += pgtable_32.o
+obj-$(CONFIG_X86_32)            += pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP)        += dump_pagetables.o
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c5..c483f4242079 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -334,7 +334,6 @@ int devmem_is_allowed(unsigned long pagenr)
         return 0;
 }
 
-#ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 pgprot_t kmap_prot;
 
@@ -357,6 +356,7 @@ static void __init kmap_init(void)
         kmap_prot = PAGE_KERNEL;
 }
 
+#ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
         unsigned long vaddr;
@@ -436,7 +436,6 @@ static void __init set_highmem_pages_init(void)
 #endif /* !CONFIG_NUMA */
 
 #else
-# define kmap_init()                            do { } while (0)
 # define permanent_kmaps_init(pgd_base)         do { } while (0)
 # define set_highmem_pages_init()       do { } while (0)
 #endif /* CONFIG_HIGHMEM */
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 000000000000..d0151d8ce452
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+        enum fixed_addresses idx;
+        unsigned long vaddr;
+
+        pagefault_disable();
+
+        idx = type + KM_TYPE_NR*smp_processor_id();
+        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+        set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+        arch_flush_lazy_mmu_mode();
+
+        return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+        unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+        enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+        /*
+         * Force other mappings to Oops if they'll try to access this pte
+         * without first remap it.  Keeping stale mappings around is a bad idea
+         * also, in case the page changes cacheability attributes or becomes
+         * a protected page in a hypervisor.
+         */
+        if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+                kpte_clear_flush(kmap_pte-idx, vaddr);
+
+        arch_flush_lazy_mmu_mode();
+        pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d166..e89d24815f26 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
 }