12 files changed, 45 insertions, 38 deletions

diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 22fab6c4be15..7da00b799cda 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -12,11 +12,6 @@ ENTRY(_start)
 
 SECTIONS
 {
-        . = HEADER_OFFSET;
-        .header : {
-                 *(.header)
-        }
-
         . = 0;
         .text : {
                  *(.text*)
@@ -50,6 +45,11 @@ SECTIONS
                 __bss_end = .;
         }
 
+        . = HEADER_OFFSET;
+        .header : {
+                *(.header)
+        }
+
         . = ALIGN(16);
         _end = .;
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 0c37f16b6950..c5ef1af8e79d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -385,11 +385,13 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory))
                 return memory;
 
-        if (!dev)
+        if (!dev) {
                 dev = &fallback_dev;
+                gfp |= GFP_DMA;
+        }
         dma_mask = dev->coherent_dma_mask;
         if (dma_mask == 0)
-                dma_mask = DMA_32BIT_MASK;
+                dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
 
         /* Device not DMA able */
         if (dev->dma_mask == NULL)
@@ -403,7 +405,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
            larger than 16MB and in this case we have a chance of
            finding fitting memory in the next higher zone first. If
            not retry with true GFP_DMA. -AK */
-        if (dma_mask <= DMA_32BIT_MASK)
+        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
                 gfp |= GFP_DMA32;
 #endif
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index fb03ef380f0e..a7835f282936 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1303,6 +1303,9 @@ static const struct user_regset_view user_x86_64_view = {
 #define genregs32_get           genregs_get
 #define genregs32_set           genregs_set
 
+#define user_i387_ia32_struct   user_i387_struct
+#define user32_fxsr_struct      user_fxsr_struct
+
 #endif  /* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
@@ -1315,13 +1318,13 @@ static const struct user_regset x86_32_regsets[] = {
         },
         [REGSET_FP] = {
                 .core_note_type = NT_PRFPREG,
-                .n = sizeof(struct user_i387_struct) / sizeof(u32),
+                .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
                 .size = sizeof(u32), .align = sizeof(u32),
                 .active = fpregs_active, .get = fpregs_get, .set = fpregs_set
         },
         [REGSET_XFP] = {
                 .core_note_type = NT_PRXFPREG,
-                .n = sizeof(struct user_i387_struct) / sizeof(u32),
+                .n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
                 .size = sizeof(u32), .align = sizeof(u32),
                 .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
         },
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c0c68c18a788..6f80b852a196 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -12,6 +12,7 @@
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
 
+#ifdef CONFIG_X86_LOCAL_APIC
 unsigned int num_processors;
 unsigned disabled_cpus __cpuinitdata;
 /* Processor that is doing the boot up */
@@ -23,8 +24,9 @@ EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 
 /* Bitmask of physically existing CPUs */
 physid_mask_t phys_cpu_present_map;
+#endif
 
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_SMP)
+#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
 /*
  * Copy data used in early init routines from the initial arrays to the
  * per cpu data areas.  These arrays then become expendable and the
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index f2fc8feb727d..6dff1286ad8a 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -951,7 +951,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 {
         if (c->x86 == 0x6 && c->x86_model >= 0xf)
-                set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 }
 
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 8f75893a6467..0cb7aadc87cd 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -231,7 +231,8 @@ native_smp_call_function_mask(cpumask_t mask,
         wmb();
 
         /* Send a message to other CPUs */
-        if (cpus_equal(mask, allbutself))
+        if (cpus_equal(mask, allbutself) &&
+            cpus_equal(cpu_online_map, cpu_callout_map))
                 send_IPI_allbutself(CALL_FUNCTION_VECTOR);
         else
                 send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6b087ab6cd8f..38988491c622 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -86,6 +86,7 @@ void *x86_bios_cpu_apicid_early_ptr;
 
 #ifdef CONFIG_X86_32
 u8 apicid_2_node[MAX_APICID];
+static int low_mappings;
 #endif
 
 /* State of each CPU */
@@ -326,6 +327,12 @@ static void __cpuinit start_secondary(void *unused)
                 enable_8259A_irq(0);
         }
 
+#ifdef CONFIG_X86_32
+        while (low_mappings)
+                cpu_relax();
+        __flush_tlb_all();
+#endif
+
         /* This must be done before setting cpu_online_map */
         set_cpu_sibling_map(raw_smp_processor_id());
         wmb();
@@ -1040,14 +1047,20 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 #ifdef CONFIG_X86_32
         /* init low mem mapping */
         clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-                        min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+                min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
         flush_tlb_all();
-#endif
+        low_mappings = 1;
 
         err = do_boot_cpu(apicid, cpu);
-        if (err < 0) {
+
+        zap_low_mappings();
+        low_mappings = 0;
+#else
+        err = do_boot_cpu(apicid, cpu);
+#endif
+        if (err) {
                 Dprintk("do_boot_cpu failed %d\n", err);
-                return err;
+                return -EIO;
         }
 
         /*
@@ -1259,9 +1272,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
         setup_ioapic_dest();
 #endif
         check_nmi_watchdog();
-#ifdef CONFIG_X86_32
-        zap_low_mappings();
-#endif
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 58882f9f2637..f6c05d0410fb 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -2,6 +2,7 @@
    All C exports should go in the respective C files. */
 
 #include <linux/module.h>
+#include <net/checksum.h>
 #include <linux/smp.h>
 
 #include <asm/processor.h>
@@ -29,6 +30,8 @@ EXPORT_SYMBOL(__copy_from_user_inatomic);
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 
+EXPORT_SYMBOL(csum_partial);
+
 /*
  * Export string functions. We normally rely on gcc builtin for most of these,
  * but gcc sometimes decides not to inline them.
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index bc503f506903..bf51144d97e1 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -136,8 +136,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
                                                 (__force u32)sum);
 }
 
-EXPORT_SYMBOL(csum_partial);
-
 /*
  * this routine is used for miscellaneous IP-like checksums, mainly
  * in icmp.c
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index de236e419cb5..ec30d10154b6 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -438,8 +438,6 @@ void zap_low_mappings(void)
 {
         int i;
 
-        save_pg_dir();
-
         /*
          * Zap initial low-memory mappings.
          *
@@ -663,16 +661,8 @@ void __init mem_init(void)
                 test_wp_bit();
 
         cpa_init();
-
-        /*
-         * Subtle. SMP is doing it's boot stuff late (because it has to
-         * fork idle threads) - but it also needs low mappings for the
-         * protected-mode entry to work. We zap these entries only after
-         * the WP-bit has been tested.
-         */
-#ifndef CONFIG_SMP
+        save_pg_dir();
         zap_low_mappings();
-#endif
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 60adbe22efa0..bcb1a8e4b2db 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -555,7 +555,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                 "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
                         current->comm, current->pid,
                         cattr_name(flags),
-                        offset, offset + size);
+                        offset, (unsigned long long)(offset + size));
                 return 0;
         }
 
@@ -576,7 +576,7 @@ void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
                 "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
                         current->comm, current->pid,
                         cattr_name(want_flags),
-                        addr, addr + size,
+                        addr, (unsigned long long)(addr + size),
                         cattr_name(flags));
         }
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 8af0f0bae2af..10fb308fded8 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -301,15 +301,13 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
         prot = pgprot_val(vma->vm_page_prot);
         if (pat_wc_enabled && write_combine)
                 prot |= _PAGE_CACHE_WC;
-        else if (pat_wc_enabled)
+        else if (pat_wc_enabled || boot_cpu_data.x86 > 3)
                 /*
                  * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
                  * To avoid attribute conflicts, request UC MINUS here
                  * aswell.
                  */
                 prot |= _PAGE_CACHE_UC_MINUS;
-        else if (boot_cpu_data.x86 > 3)
-                prot |= _PAGE_CACHE_UC;
 
         vma->vm_page_prot = __pgprot(prot);