18 files changed, 84 insertions, 57 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/init_task.c b/arch/x86/kernel/init_task.c
index 3d01e47777db..a4f93b4120c1 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -11,7 +11,6 @@
 #include <asm/desc.h>
 
 static struct fs_struct init_fs = INIT_FS;
-static struct files_struct init_files = INIT_FILES;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
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/process.c b/arch/x86/kernel/process.c
index 67e9b4a1e89d..ba370dc8685b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -99,15 +99,6 @@ static void mwait_idle(void)
 		local_irq_enable();
 }
 
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
 /*
  * On SMP it's slightly faster (but much more power-consuming!)
  * to poll the ->work.need_resched flag instead of waiting for the
@@ -119,6 +110,33 @@ static void poll_idle(void)
 	cpu_relax();
 }
 
+/*
+ * mwait selection logic:
+ *
+ * It depends on the CPU. For AMD CPUs that support MWAIT this is
+ * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings
+ * then depend on a clock divisor and current Pstate of the core. If
+ * all cores of a processor are in halt state (C1) the processor can
+ * enter the C1E (C1 enhanced) state. If mwait is used this will never
+ * happen.
+ *
+ * idle=mwait overrides this decision and forces the usage of mwait.
+ */
+static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+{
+	if (force_mwait)
+		return 1;
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		switch(c->x86) {
+		case 0x10:
+		case 0x11:
+			return 0;
+		}
+	}
+	return 1;
+}
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 	static int selected;
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/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 3324d90038e4..7c077a9d9777 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -216,7 +216,7 @@ int pit_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
 
-	if (pit && vcpu->vcpu_id == 0)
+	if (pit && vcpu->vcpu_id == 0 && pit->pit_state.inject_pending)
 		return atomic_read(&pit->pit_state.pit_timer.pending);
 
 	return 0;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 36809d79788b..c297c50eba63 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -957,7 +957,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *lapic = vcpu->arch.apic;
 
-	if (lapic)
+	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
 		return atomic_read(&lapic->timer.pending);
 
 	return 0;
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index f2a696d6a243..8a96320ab071 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -677,8 +677,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	c->use_modrm_ea = 1;
 
 	if (c->modrm_mod == 3) {
-		c->modrm_val = *(unsigned long *)
-			decode_register(c->modrm_rm, c->regs, c->d & ByteOp);
+		c->modrm_ptr = decode_register(c->modrm_rm,
+					       c->regs, c->d & ByteOp);
+		c->modrm_val = *(unsigned long *)c->modrm_ptr;
 		return rc;
 	}
 
@@ -1005,6 +1006,7 @@ done_prefixes:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->src.type = OP_REG;
 			c->src.val = c->modrm_val;
+			c->src.ptr = c->modrm_ptr;
 			break;
 		}
 		c->src.type = OP_MEM;
@@ -1049,6 +1051,7 @@ done_prefixes:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->dst.type = OP_REG;
 			c->dst.val = c->dst.orig_val = c->modrm_val;
+			c->dst.ptr = c->modrm_ptr;
 			break;
 		}
 		c->dst.type = OP_MEM;
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..de3a99812450 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -28,7 +28,7 @@
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_wc_enabled = 1;
 
-void __init pat_disable(char *reason)
+void __cpuinit pat_disable(char *reason)
 {
 	pat_wc_enabled = 0;
 	printk(KERN_INFO "%s\n", reason);
@@ -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/common.c b/arch/x86/pci/common.c
index 8545c8a9d107..6e64aaf00d1d 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -302,18 +302,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 #ifdef __i386__
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);