[GIT PULL] x86 fixes

[Ingo Molnar <mingo@elte.hu>]

Linus,

Please pull the latest x86-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-fixes-for-linus


out-of-topic modifications in x86-fixes-for-linus:
--------------------------------------------------
drivers/char/nvram.c               # a01c780: nvram: Fix write beyond end condi
drivers/edac/amd64_edac.c          # 5054225: x86, msr: Add support for non-con
mm/migrate.c                       # b9255850: mm: Adjust do_pages_stat() so gc

 Thanks,

	Ingo

------------------>
Andy Isaacson (2):
      x86: Factor duplicated code out of __show_regs() into show_regs_common()
      x86: Print DMI_BOARD_NAME as well as DMI_PRODUCT_NAME from __show_regs()

Borislav Petkov (1):
      x86, msr: Add support for non-contiguous cpumasks

Cliff Wickman (1):
      x86: Fix duplicated UV BAU interrupt vector

Cyrill Gorcunov (1):
      x86, mce: Thermal monitoring depends on APIC being enabled

FUJITA Tomonori (2):
      x86: Remove usedac in feature-removal-schedule.txt
      x86: Move swiotlb initialization before dma32_free_bootmem

H. Peter Anvin (3):
      doc: Add documentation for bootloader_{type,version}
      mm: Adjust do_pages_stat() so gcc can see copy_from_user() is safe
      nvram: Fix write beyond end condition; prove to gcc copy is safe

Hidetoshi Seto (2):
      x86, mce: fix confusion between bank attributes and mce attributes
      x86, mce: Clean up thermal init by introducing intel_thermal_supported()

Jan Beulich (1):
      x86/mce: Set up timer unconditionally

Joe Perches (7):
      arch/x86/kernel/microcode*: Use pr_fmt() and remove duplicated KERN_ERR prefix
      x86: es7000_32.c: Use pr_<level> and add pr_fmt(fmt)
      x86: setup_percpu.c: Use pr_<level> and add pr_fmt(fmt)
      x86: i8254.c: Add pr_fmt(fmt)
      x86: kmmio.c: Add and use pr_fmt(fmt)
      x86: mmio-mod.c: Use pr_fmt
      x86: Fix build warning in arch/x86/mm/mmio-mod.c

Joerg Roedel (2):
      x86/amd-iommu: Fix passthrough mode
      x86/amd-iommu: Fix PCI hotplug with passthrough mode

Leann Ogasawara (1):
      x86: ASUS P4S800 reboot=bios quirk

Mike Travis (2):
      x86: Remove enabling x2apic message for every CPU
      x86: Limit the number of processor bootup messages

Prarit Bhargava (1):
      x86, AMD: Fix stale cpuid4_info shared_map data in shared_cpu_map cpumasks

Shaun Patterson (1):
      x86: Fix typo in arch/x86/mm/kmmio.c

Thomas Gleixner (1):
      x86: Fix bogus warning in apic_noop.apic_write()

Yinghai Lu (2):
      x86: Use find_e820() instead of hard coded trampoline address
      x86: Gart: fix breakage due to IOMMU initialization cleanup


 Documentation/feature-removal-schedule.txt |    7 ---
 Documentation/sysctl/kernel.txt            |   31 ++++++++++++
 arch/x86/include/asm/amd_iommu_proto.h     |    4 +-
 arch/x86/include/asm/irq_vectors.h         |    2 +-
 arch/x86/include/asm/msr.h                 |    3 +
 arch/x86/include/asm/system.h              |    1 +
 arch/x86/include/asm/trampoline.h          |    1 -
 arch/x86/kernel/amd_iommu.c                |   46 ++++++++++++++++--
 arch/x86/kernel/amd_iommu_init.c           |    9 ++++
 arch/x86/kernel/aperture_64.c              |   11 ++--
 arch/x86/kernel/apic/apic.c                |    2 +-
 arch/x86/kernel/apic/apic_noop.c           |    2 +-
 arch/x86/kernel/apic/es7000_32.c           |   12 +++--
 arch/x86/kernel/cpu/addon_cpuid_features.c |   15 ++++--
 arch/x86/kernel/cpu/amd.c                  |    2 -
 arch/x86/kernel/cpu/common.c               |    8 ++-
 arch/x86/kernel/cpu/intel.c                |    2 -
 arch/x86/kernel/cpu/intel_cacheinfo.c      |   13 +++--
 arch/x86/kernel/cpu/mcheck/mce.c           |    5 +-
 arch/x86/kernel/cpu/mcheck/therm_throt.c   |   20 ++++++--
 arch/x86/kernel/e820.c                     |   11 ++++-
 arch/x86/kernel/head32.c                   |    2 -
 arch/x86/kernel/head64.c                   |    2 -
 arch/x86/kernel/microcode_amd.c            |   40 +++++++--------
 arch/x86/kernel/microcode_core.c           |   26 ++++++-----
 arch/x86/kernel/microcode_intel.c          |   47 ++++++++-----------
 arch/x86/kernel/mpparse.c                  |    3 -
 arch/x86/kernel/pci-dma.c                  |    5 ++-
 arch/x86/kernel/pci-gart_64.c              |    3 +-
 arch/x86/kernel/process.c                  |   21 ++++++++
 arch/x86/kernel/process_32.c               |   14 +-----
 arch/x86/kernel/process_64.c               |   16 +------
 arch/x86/kernel/reboot.c                   |    8 +++
 arch/x86/kernel/setup.c                    |   13 +++--
 arch/x86/kernel/setup_percpu.c             |   13 +++--
 arch/x86/kernel/smpboot.c                  |   45 ++++++++++++------
 arch/x86/kernel/trampoline.c               |   20 ++++----
 arch/x86/kvm/i8254.c                       |   12 +++--
 arch/x86/lib/msr.c                         |   26 +++++++++--
 arch/x86/mm/kmmio.c                        |   42 ++++++++--------
 arch/x86/mm/mmio-mod.c                     |   71 ++++++++++++++--------------
 drivers/char/nvram.c                       |   14 ++++--
 drivers/edac/amd64_edac.c                  |   46 +++++++-----------
 mm/migrate.c                               |    2 +-
 44 files changed, 412 insertions(+), 286 deletions(-)

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 2a4d779..eb2c138 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -291,13 +291,6 @@ Who:	Michael Buesch <mb@bu3sch.de>
 
 ---------------------------
 
-What:	usedac i386 kernel parameter
-When:	2.6.27
-Why:	replaced by allowdac and no dac combination
-Who:	Glauber Costa <gcosta@redhat.com>
-
----------------------------
-
 What: print_fn_descriptor_symbol()
 When: October 2009
 Why:  The %pF vsprintf format provides the same functionality in a
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 8f7a0e7..3894eaa 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -19,6 +19,8 @@ Currently, these files might (depending on your configuration)
 show up in /proc/sys/kernel:
 - acpi_video_flags
 - acct
+- bootloader_type	     [ X86 only ]
+- bootloader_version	     [ X86 only ]
 - callhome		     [ S390 only ]
 - auto_msgmni
 - core_pattern
@@ -93,6 +95,35 @@ valid for 30 seconds.
 
 ==============================================================
 
+bootloader_type:
+
+x86 bootloader identification
+
+This gives the bootloader type number as indicated by the bootloader,
+shifted left by 4, and OR'd with the low four bits of the bootloader
+version.  The reason for this encoding is that this used to match the
+type_of_loader field in the kernel header; the encoding is kept for
+backwards compatibility.  That is, if the full bootloader type number
+is 0x15 and the full version number is 0x234, this file will contain
+the value 340 = 0x154.
+
+See the type_of_loader and ext_loader_type fields in
+Documentation/x86/boot.txt for additional information.
+
+==============================================================
+
+bootloader_version:
+
+x86 bootloader version
+
+The complete bootloader version number.  In the example above, this
+file will contain the value 564 = 0x234.
+
+See the type_of_loader and ext_loader_ver fields in
+Documentation/x86/boot.txt for additional information.
+
+==============================================================
+
 callhome:
 
 Controls the kernel's callhome behavior in case of a kernel panic.
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index 84786fb..4d817f9 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -28,7 +28,9 @@ extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_apply_erratum_63(u16 devid);
 extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
-
+extern int amd_iommu_init_devices(void);
+extern void amd_iommu_uninit_devices(void);
+extern void amd_iommu_init_notifier(void);
 #ifndef CONFIG_AMD_IOMMU_STATS
 
 static inline void amd_iommu_stats_init(void) { }
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6a635bd..4611f08 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -113,7 +113,7 @@
  */
 #define LOCAL_PENDING_VECTOR		0xec
 
-#define UV_BAU_MESSAGE			0xec
+#define UV_BAU_MESSAGE			0xea
 
 /*
  * Self IPI vector for machine checks
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 5bef931..2d228fc 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -244,6 +244,9 @@ do {                                                            \
 
 #define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
 
+struct msr *msrs_alloc(void);
+void msrs_free(struct msr *msrs);
+
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 022a843..ecb544e 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -23,6 +23,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 struct tss_struct;
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
+extern void show_regs_common(void);
 
 #ifdef CONFIG_X86_32
 
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 90f06c2..cb507bb 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -16,7 +16,6 @@ extern unsigned long initial_code;
 extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
-#define TRAMPOLINE_BASE 0x6000
 
 extern unsigned long setup_trampoline(void);
 extern void __init reserve_trampoline_memory(void);
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 1c0fb4d..b990b5c 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -166,6 +166,43 @@ static void iommu_uninit_device(struct device *dev)
 {
 	kfree(dev->archdata.iommu);
 }
+
+void __init amd_iommu_uninit_devices(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	for_each_pci_dev(pdev) {
+
+		if (!check_device(&pdev->dev))
+			continue;
+
+		iommu_uninit_device(&pdev->dev);
+	}
+}
+
+int __init amd_iommu_init_devices(void)
+{
+	struct pci_dev *pdev = NULL;
+	int ret = 0;
+
+	for_each_pci_dev(pdev) {
+
+		if (!check_device(&pdev->dev))
+			continue;
+
+		ret = iommu_init_device(&pdev->dev);
+		if (ret)
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+
+	amd_iommu_uninit_devices();
+
+	return ret;
+}
 #ifdef CONFIG_AMD_IOMMU_STATS
 
 /*
@@ -1587,6 +1624,11 @@ static struct notifier_block device_nb = {
 	.notifier_call = device_change_notifier,
 };
 
+void amd_iommu_init_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &device_nb);
+}
+
 /*****************************************************************************
  *
  * The next functions belong to the dma_ops mapping/unmapping code.
@@ -2145,8 +2187,6 @@ static void prealloc_protection_domains(void)
 		if (!check_device(&dev->dev))
 			continue;
 
-		iommu_init_device(&dev->dev);
-
 		/* Is there already any domain for it? */
 		if (domain_for_device(&dev->dev))
 			continue;
@@ -2215,8 +2255,6 @@ int __init amd_iommu_init_dma_ops(void)
 
 	register_iommu(&amd_iommu_ops);
 
-	bus_register_notifier(&pci_bus_type, &device_nb);
-
 	amd_iommu_stats_init();
 
 	return 0;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 7ffc399..309a52f 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1274,6 +1274,10 @@ static int __init amd_iommu_init(void)
 	if (ret)
 		goto free;
 
+	ret = amd_iommu_init_devices();
+	if (ret)
+		goto free;
+
 	if (iommu_pass_through)
 		ret = amd_iommu_init_passthrough();
 	else
@@ -1281,6 +1285,8 @@ static int __init amd_iommu_init(void)
 	if (ret)
 		goto free;
 
+	amd_iommu_init_notifier();
+
 	enable_iommus();
 
 	if (iommu_pass_through)
@@ -1296,6 +1302,9 @@ out:
 	return ret;
 
 free:
+
+	amd_iommu_uninit_devices();
+
 	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
 		   get_order(MAX_DOMAIN_ID/8));
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index e0dfb68..3704997 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -280,7 +280,8 @@ void __init early_gart_iommu_check(void)
 	 * or BIOS forget to put that in reserved.
 	 * try to update e820 to make that region as reserved.
 	 */
-	int i, fix, slot;
+	u32 agp_aper_base = 0, agp_aper_order = 0;
+	int i, fix, slot, valid_agp = 0;
 	u32 ctl;
 	u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
 	u64 aper_base = 0, last_aper_base = 0;
@@ -290,6 +291,8 @@ void __init early_gart_iommu_check(void)
 		return;
 
 	/* This is mostly duplicate of iommu_hole_init */
+	agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp);
+
 	fix = 0;
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
 		int bus;
@@ -342,10 +345,10 @@ void __init early_gart_iommu_check(void)
 		}
 	}
 
-	if (!fix)
+	if (valid_agp)
 		return;
 
-	/* different nodes have different setting, disable them all at first*/
+	/* disable them all at first */
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
 		int bus;
 		int dev_base, dev_limit;
@@ -458,8 +461,6 @@ out:
 
 	if (aper_alloc) {
 		/* Got the aperture from the AGP bridge */
-	} else if (!valid_agp) {
-		/* Do nothing */
 	} else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) ||
 		   force_iommu ||
 		   valid_agp ||
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index efb2b9c..aa57c07 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1341,7 +1341,7 @@ void enable_x2apic(void)
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
 	if (!(msr & X2APIC_ENABLE)) {
-		pr_info("Enabling x2apic\n");
+		printk_once(KERN_INFO "Enabling x2apic\n");
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index d9acc3b..e31b9ff 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -127,7 +127,7 @@ static u32 noop_apic_read(u32 reg)
 
 static void noop_apic_write(u32 reg, u32 v)
 {
-	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
 }
 
 struct apic apic_noop = {
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index e85f8fb..dd2b5f2 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -27,6 +27,9 @@
  *
  * http://www.unisys.com
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/cpumask.h>
@@ -223,9 +226,9 @@ static int parse_unisys_oem(char *oemptr)
 			mip_addr = val;
 			mip = (struct mip_reg *)val;
 			mip_reg = __va(mip);
-			pr_debug("es7000_mipcfg: host_reg = 0x%lx \n",
+			pr_debug("host_reg = 0x%lx\n",
 				 (unsigned long)host_reg);
-			pr_debug("es7000_mipcfg: mip_reg = 0x%lx \n",
+			pr_debug("mip_reg = 0x%lx\n",
 				 (unsigned long)mip_reg);
 			success++;
 			break;
@@ -401,7 +404,7 @@ static void es7000_enable_apic_mode(void)
 	if (!es7000_plat)
 		return;
 
-	printk(KERN_INFO "ES7000: Enabling APIC mode.\n");
+	pr_info("Enabling APIC mode.\n");
 	memset(&es7000_mip_reg, 0, sizeof(struct mip_reg));
 	es7000_mip_reg.off_0x00 = MIP_SW_APIC;
 	es7000_mip_reg.off_0x38 = MIP_VALID;
@@ -514,8 +517,7 @@ static void es7000_setup_apic_routing(void)
 {
 	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
 
-	printk(KERN_INFO
-	  "Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
+	pr_info("Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
 		(apic_version[apic] == 0x14) ?
 			"Physical Cluster" : "Logical Cluster",
 		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index c965e52..468489b 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -74,6 +74,7 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
 	unsigned int eax, ebx, ecx, edx, sub_index;
 	unsigned int ht_mask_width, core_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
+	static bool printed;
 
 	if (c->cpuid_level < 0xb)
 		return;
@@ -127,12 +128,14 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
 
-
-	printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
-	       c->phys_proc_id);
-	if (c->x86_max_cores > 1)
-		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
-		       c->cpu_core_id);
+	if (!printed) {
+		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+		       c->phys_proc_id);
+		if (c->x86_max_cores > 1)
+			printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+			       c->cpu_core_id);
+		printed = 1;
+	}
 	return;
 #endif
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7128b37..8dc3ea1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -375,8 +375,6 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 			node = nearby_node(apicid);
 	}
 	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1afa99..0ee9a32 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -427,6 +427,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_HT
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
+	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
 		return;
@@ -442,7 +443,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
 	if (smp_num_siblings == 1) {
-		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
+		printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n");
 		goto out;
 	}
 
@@ -469,11 +470,12 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 				       ((1 << core_bits) - 1);
 
 out:
-	if ((c->x86_max_cores * smp_num_siblings) > 1) {
+	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
 		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
 		       c->phys_proc_id);
 		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
 		       c->cpu_core_id);
+		printed = 1;
 	}
 #endif
 }
@@ -1115,7 +1117,7 @@ void __cpuinit cpu_init(void)
 	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
 		panic("CPU#%d already initialized!\n", cpu);
 
-	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+	pr_debug("Initializing CPU#%d\n", cpu);
 
 	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c900b73..9c31e8b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -270,8 +270,6 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 		node = cpu_to_node(cpu);
 	}
 	numa_set_node(cpu, node);
-
-	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6c40f6b..63ada17 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -507,18 +507,19 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 {
 	struct _cpuid4_info	*this_leaf, *sibling_leaf;
 	unsigned long num_threads_sharing;
-	int index_msb, i;
+	int index_msb, i, sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
-		struct cpuinfo_x86 *d;
-		for_each_online_cpu(i) {
+		for_each_cpu(i, c->llc_shared_map) {
 			if (!per_cpu(cpuid4_info, i))
 				continue;
-			d = &cpu_data(i);
 			this_leaf = CPUID4_INFO_IDX(i, index);
-			cpumask_copy(to_cpumask(this_leaf->shared_cpu_map),
-				     d->llc_shared_map);
+			for_each_cpu(sibling, c->llc_shared_map) {
+				if (!cpu_online(sibling))
+					continue;
+				set_bit(sibling, this_leaf->shared_cpu_map);
+			}
 		}
 		return;
 	}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d7ebf25..a8aacd4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1388,13 +1388,14 @@ static void __mcheck_cpu_init_timer(void)
 	struct timer_list *t = &__get_cpu_var(mce_timer);
 	int *n = &__get_cpu_var(mce_next_interval);
 
+	setup_timer(t, mce_start_timer, smp_processor_id());
+
 	if (mce_ignore_ce)
 		return;
 
 	*n = check_interval * HZ;
 	if (!*n)
 		return;
-	setup_timer(t, mce_start_timer, smp_processor_id());
 	t->expires = round_jiffies(jiffies + *n);
 	add_timer_on(t, smp_processor_id());
 }
@@ -1928,7 +1929,7 @@ error2:
 		sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[j].attr);
 error:
 	while (--i >= 0)
-		sysdev_remove_file(&per_cpu(mce_dev, cpu), &mce_banks[i].attr);
+		sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);
 
 	sysdev_unregister(&per_cpu(mce_dev, cpu));
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4fef985..81c499e 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -256,6 +256,16 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 	ack_APIC_irq();
 }
 
+/* Thermal monitoring depends on APIC, ACPI and clock modulation */
+static int intel_thermal_supported(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has_apic)
+		return 0;
+	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
+		return 0;
+	return 1;
+}
+
 void __init mcheck_intel_therm_init(void)
 {
 	/*
@@ -263,8 +273,7 @@ void __init mcheck_intel_therm_init(void)
 	 * LVT value on BSP and use that value to restore APs' thermal LVT
 	 * entry BIOS programmed later
 	 */
-	if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) &&
-		cpu_has(&boot_cpu_data, X86_FEATURE_ACC))
+	if (intel_thermal_supported(&boot_cpu_data))
 		lvtthmr_init = apic_read(APIC_LVTTHMR);
 }
 
@@ -274,8 +283,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	int tm2 = 0;
 	u32 l, h;
 
-	/* Thermal monitoring depends on ACPI and clock modulation*/
-	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
+	if (!intel_thermal_supported(c))
 		return;
 
 	/*
@@ -339,8 +347,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	l = apic_read(APIC_LVTTHMR);
 	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
 
-	printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n",
-	       cpu, tm2 ? "TM2" : "TM1");
+	printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n",
+		       tm2 ? "TM2" : "TM1");
 
 	/* enable thermal throttle processing */
 	atomic_set(&therm_throt_en, 1);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d17d482..f50447d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -732,7 +732,16 @@ struct early_res {
 	char overlap_ok;
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
-	{ 0, PAGE_SIZE, "BIOS data page" },	/* BIOS data page */
+	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
+#ifdef CONFIG_X86_32
+	/*
+	 * But first pinch a few for the stack/trampoline stuff
+	 * FIXME: Don't need the extra page at 4K, but need to fix
+	 * trampoline before removing it. (see the GDT stuff)
+	 */
+	{ PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 },
+#endif
+
 	{}
 };
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 4f8e250..5051b94 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,8 +29,6 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
-	reserve_trampoline_memory();
-
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0b06cd7..b5a9896 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -98,8 +98,6 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
 	copy_bootdata(__va(real_mode_data));
 
-	reserve_trampoline_memory();
-
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 63123d9..37542b6 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -13,6 +13,9 @@
  *  Licensed under the terms of the GNU General Public
  *  License version 2. See file COPYING for details.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/firmware.h>
 #include <linux/pci_ids.h>
 #include <linux/uaccess.h>
@@ -81,7 +84,7 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 
 	memset(csig, 0, sizeof(*csig));
 	rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
-	pr_info("microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev);
+	pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
 	return 0;
 }
 
@@ -111,8 +114,8 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 
 	/* ucode might be chipset specific -- currently we don't support this */
 	if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
-		pr_err(KERN_ERR "microcode: CPU%d: loading of chipset "
-		       "specific code not yet supported\n", cpu);
+		pr_err("CPU%d: loading of chipset specific code not yet supported\n",
+		       cpu);
 		return 0;
 	}
 
@@ -141,12 +144,12 @@ static int apply_microcode_amd(int cpu)
 
 	/* check current patch id and patch's id for match */
 	if (rev != mc_amd->hdr.patch_id) {
-		pr_err("microcode: CPU%d: update failed "
-		       "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
+		pr_err("CPU%d: update failed (for patch_level=0x%x)\n",
+		       cpu, mc_amd->hdr.patch_id);
 		return -1;
 	}
 
-	pr_info("microcode: CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
+	pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
 	uci->cpu_sig.rev = rev;
 
 	return 0;
@@ -169,15 +172,14 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 		return NULL;
 
 	if (section_hdr[0] != UCODE_UCODE_TYPE) {
-		pr_err("microcode: error: invalid type field in "
-		       "container file section header\n");
+		pr_err("error: invalid type field in container file section header\n");
 		return NULL;
 	}
 
 	total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
 
 	if (total_size > size || total_size > UCODE_MAX_SIZE) {
-		pr_err("microcode: error: size mismatch\n");
+		pr_err("error: size mismatch\n");
 		return NULL;
 	}
 
@@ -206,14 +208,13 @@ static int install_equiv_cpu_table(const u8 *buf)
 	size = buf_pos[2];
 
 	if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		pr_err("microcode: error: invalid type field in "
-		       "container file section header\n");
+		pr_err("error: invalid type field in container file section header\n");
 		return 0;
 	}
 
 	equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size);
 	if (!equiv_cpu_table) {
-		pr_err("microcode: failed to allocate equivalent CPU table\n");
+		pr_err("failed to allocate equivalent CPU table\n");
 		return 0;
 	}
 
@@ -246,7 +247,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 	offset = install_equiv_cpu_table(ucode_ptr);
 	if (!offset) {
-		pr_err("microcode: failed to create equivalent cpu table\n");
+		pr_err("failed to create equivalent cpu table\n");
 		return UCODE_ERROR;
 	}
 
@@ -277,8 +278,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 		if (!leftover) {
 			vfree(uci->mc);
 			uci->mc = new_mc;
-			pr_debug("microcode: CPU%d found a matching microcode "
-				 "update with version 0x%x (current=0x%x)\n",
+			pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 				 cpu, new_rev, uci->cpu_sig.rev);
 		} else {
 			vfree(new_mc);
@@ -300,7 +300,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 		return UCODE_NFOUND;
 
 	if (*(u32 *)firmware->data != UCODE_MAGIC) {
-		pr_err("microcode: invalid UCODE_MAGIC (0x%08x)\n",
+		pr_err("invalid UCODE_MAGIC (0x%08x)\n",
 		       *(u32 *)firmware->data);
 		return UCODE_ERROR;
 	}
@@ -313,8 +313,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	pr_info("microcode: AMD microcode update via "
-		"/dev/cpu/microcode not supported\n");
+	pr_info("AMD microcode update via /dev/cpu/microcode not supported\n");
 	return UCODE_ERROR;
 }
 
@@ -334,14 +333,13 @@ void init_microcode_amd(struct device *device)
 	WARN_ON(c->x86_vendor != X86_VENDOR_AMD);
 
 	if (c->x86 < 0x10) {
-		pr_warning("microcode: AMD CPU family 0x%x not supported\n",
-			   c->x86);
+		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
 		return;
 	}
 	supported_cpu = 1;
 
 	if (request_firmware(&firmware, fw_name, device))
-		pr_err("microcode: failed to load file %s\n", fw_name);
+		pr_err("failed to load file %s\n", fw_name);
 }
 
 void fini_microcode_amd(void)
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index e68aae3..844c02c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -70,6 +70,9 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/platform_device.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
@@ -209,7 +212,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	ssize_t ret = -EINVAL;
 
 	if ((len >> PAGE_SHIFT) > totalram_pages) {
-		pr_err("microcode: too much data (max %ld pages)\n", totalram_pages);
+		pr_err("too much data (max %ld pages)\n", totalram_pages);
 		return ret;
 	}
 
@@ -244,7 +247,7 @@ static int __init microcode_dev_init(void)
 
 	error = misc_register(&microcode_dev);
 	if (error) {
-		pr_err("microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR);
+		pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR);
 		return error;
 	}
 
@@ -359,7 +362,7 @@ static enum ucode_state microcode_resume_cpu(int cpu)
 	if (!uci->mc)
 		return UCODE_NFOUND;
 
-	pr_debug("microcode: CPU%d updated upon resume\n", cpu);
+	pr_debug("CPU%d updated upon resume\n", cpu);
 	apply_microcode_on_target(cpu);
 
 	return UCODE_OK;
@@ -379,7 +382,7 @@ static enum ucode_state microcode_init_cpu(int cpu)
 	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
 
 	if (ustate == UCODE_OK) {
-		pr_debug("microcode: CPU%d updated upon init\n", cpu);
+		pr_debug("CPU%d updated upon init\n", cpu);
 		apply_microcode_on_target(cpu);
 	}
 
@@ -406,7 +409,7 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 	if (!cpu_online(cpu))
 		return 0;
 
-	pr_debug("microcode: CPU%d added\n", cpu);
+	pr_debug("CPU%d added\n", cpu);
 
 	err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
 	if (err)
@@ -425,7 +428,7 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
 	if (!cpu_online(cpu))
 		return 0;
 
-	pr_debug("microcode: CPU%d removed\n", cpu);
+	pr_debug("CPU%d removed\n", cpu);
 	microcode_fini_cpu(cpu);
 	sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
 	return 0;
@@ -473,15 +476,15 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 		microcode_update_cpu(cpu);
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		pr_debug("microcode: CPU%d added\n", cpu);
+		pr_debug("CPU%d added\n", cpu);
 		if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group))
-			pr_err("microcode: Failed to create group for CPU%d\n", cpu);
+			pr_err("Failed to create group for CPU%d\n", cpu);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		/* Suspend is in progress, only remove the interface */
 		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
-		pr_debug("microcode: CPU%d removed\n", cpu);
+		pr_debug("CPU%d removed\n", cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_UP_CANCELED_FROZEN:
@@ -507,7 +510,7 @@ static int __init microcode_init(void)
 		microcode_ops = init_amd_microcode();
 
 	if (!microcode_ops) {
-		pr_err("microcode: no support for this CPU vendor\n");
+		pr_err("no support for this CPU vendor\n");
 		return -ENODEV;
 	}
 
@@ -541,8 +544,7 @@ static int __init microcode_init(void)
 	register_hotcpu_notifier(&mc_cpu_notifier);
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
-	       " <tigran@aivazian.fsnet.co.uk>,"
-	       " Peter Oruba\n");
+		" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
 
 	return 0;
 }
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 0d334dd..ebd193e 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -70,6 +70,9 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/firmware.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
@@ -146,8 +149,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 
 	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
 	    cpu_has(c, X86_FEATURE_IA64)) {
-		printk(KERN_ERR "microcode: CPU%d not a capable Intel "
-			"processor\n", cpu_num);
+		pr_err("CPU%d not a capable Intel processor\n", cpu_num);
 		return -1;
 	}
 
@@ -165,8 +167,8 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
 
-	printk(KERN_INFO "microcode: CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
-			cpu_num, csig->sig, csig->pf, csig->rev);
+	pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
+		cpu_num, csig->sig, csig->pf, csig->rev);
 
 	return 0;
 }
@@ -194,28 +196,24 @@ static int microcode_sanity_check(void *mc)
 	data_size = get_datasize(mc_header);
 
 	if (data_size + MC_HEADER_SIZE > total_size) {
-		printk(KERN_ERR "microcode: error! "
-				"Bad data size in microcode data file\n");
+		pr_err("error! Bad data size in microcode data file\n");
 		return -EINVAL;
 	}
 
 	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
-		printk(KERN_ERR "microcode: error! "
-				"Unknown microcode update format\n");
+		pr_err("error! Unknown microcode update format\n");
 		return -EINVAL;
 	}
 	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
 	if (ext_table_size) {
 		if ((ext_table_size < EXT_HEADER_SIZE)
 		 || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
-			printk(KERN_ERR "microcode: error! "
-				"Small exttable size in microcode data file\n");
+			pr_err("error! Small exttable size in microcode data file\n");
 			return -EINVAL;
 		}
 		ext_header = mc + MC_HEADER_SIZE + data_size;
 		if (ext_table_size != exttable_size(ext_header)) {
-			printk(KERN_ERR "microcode: error! "
-				"Bad exttable size in microcode data file\n");
+			pr_err("error! Bad exttable size in microcode data file\n");
 			return -EFAULT;
 		}
 		ext_sigcount = ext_header->count;
@@ -230,8 +228,7 @@ static int microcode_sanity_check(void *mc)
 		while (i--)
 			ext_table_sum += ext_tablep[i];
 		if (ext_table_sum) {
-			printk(KERN_WARNING "microcode: aborting, "
-				"bad extended signature table checksum\n");
+			pr_warning("aborting, bad extended signature table checksum\n");
 			return -EINVAL;
 		}
 	}
@@ -242,7 +239,7 @@ static int microcode_sanity_check(void *mc)
 	while (i--)
 		orig_sum += ((int *)mc)[i];
 	if (orig_sum) {
-		printk(KERN_ERR "microcode: aborting, bad checksum\n");
+		pr_err("aborting, bad checksum\n");
 		return -EINVAL;
 	}
 	if (!ext_table_size)
@@ -255,7 +252,7 @@ static int microcode_sanity_check(void *mc)
 			- (mc_header->sig + mc_header->pf + mc_header->cksum)
 			+ (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
 		if (sum) {
-			printk(KERN_ERR "microcode: aborting, bad checksum\n");
+			pr_err("aborting, bad checksum\n");
 			return -EINVAL;
 		}
 	}
@@ -327,13 +324,11 @@ static int apply_microcode(int cpu)
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
 
 	if (val[1] != mc_intel->hdr.rev) {
-		printk(KERN_ERR "microcode: CPU%d update "
-				"to revision 0x%x failed\n",
-			cpu_num, mc_intel->hdr.rev);
+		pr_err("CPU%d update to revision 0x%x failed\n",
+		       cpu_num, mc_intel->hdr.rev);
 		return -1;
 	}
-	printk(KERN_INFO "microcode: CPU%d updated to revision "
-			 "0x%x, date = %04x-%02x-%02x \n",
+	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x \n",
 		cpu_num, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
@@ -362,8 +357,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		mc_size = get_totalsize(&mc_header);
 		if (!mc_size || mc_size > leftover) {
-			printk(KERN_ERR "microcode: error!"
-					"Bad data in microcode data file\n");
+			pr_err("error! Bad data in microcode data file\n");
 			break;
 		}
 
@@ -405,9 +399,8 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		vfree(uci->mc);
 	uci->mc = (struct microcode_intel *)new_mc;
 
-	pr_debug("microcode: CPU%d found a matching microcode update with"
-		 " version 0x%x (current=0x%x)\n",
-			cpu, new_rev, uci->cpu_sig.rev);
+	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
+		 cpu, new_rev, uci->cpu_sig.rev);
 out:
 	return state;
 }
@@ -429,7 +422,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 		c->x86, c->x86_model, c->x86_mask);
 
 	if (request_firmware(&firmware, name, device)) {
-		pr_debug("microcode: data file %s load failed\n", name);
+		pr_debug("data file %s load failed\n", name);
 		return UCODE_NFOUND;
 	}
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 35a57c9..40b54ce 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -945,9 +945,6 @@ void __init early_reserve_e820_mpc_new(void)
 {
 	if (enable_update_mptable && alloc_mptable) {
 		u64 startt = 0;
-#ifdef CONFIG_X86_TRAMPOLINE
-		startt = TRAMPOLINE_BASE;
-#endif
 		mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4);
 	}
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index afcc58b..fcc2f2b 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -120,11 +120,14 @@ static void __init dma32_free_bootmem(void)
 
 void __init pci_iommu_alloc(void)
 {
+	int use_swiotlb;
+
+	use_swiotlb = pci_swiotlb_init();
 #ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 #endif
-	if (pci_swiotlb_init())
+	if (use_swiotlb)
 		return;
 
 	gart_iommu_hole_init();
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index e6a0d40..56c0e73 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -710,7 +710,8 @@ static void gart_iommu_shutdown(void)
 	struct pci_dev *dev;
 	int i;
 
-	if (no_agp)
+	/* don't shutdown it if there is AGP installed */
+	if (!no_agp)
 		return;
 
 	for (i = 0; i < num_k8_northbridges; i++) {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 5e2ba63..7a7bd4e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -10,6 +10,8 @@
 #include <linux/clockchips.h>
 #include <linux/random.h>
 #include <linux/user-return-notifier.h>
+#include <linux/dmi.h>
+#include <linux/utsname.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/system.h>
@@ -90,6 +92,25 @@ void exit_thread(void)
 	}
 }
 
+void show_regs_common(void)
+{
+	const char *board, *product;
+
+	board = dmi_get_system_info(DMI_BOARD_NAME);
+	if (!board)
+		board = "";
+	product = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (!product)
+		product = "";
+
+	printk("\n");
+	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+		current->pid, current->comm, print_tainted(),
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version, board, product);
+}
+
 void flush_thread(void)
 {
 	struct task_struct *tsk = current;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 075580b..120b887 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -23,7 +23,6 @@
 #include <linux/vmalloc.h>
 #include <linux/user.h>
 #include <linux/interrupt.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/init.h>
@@ -35,7 +34,6 @@
 #include <linux/tick.h>
 #include <linux/percpu.h>
 #include <linux/prctl.h>
-#include <linux/dmi.h>
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
@@ -128,7 +126,6 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned long sp;
 	unsigned short ss, gs;
-	const char *board;
 
 	if (user_mode_vm(regs)) {
 		sp = regs->sp;
@@ -140,16 +137,7 @@ void __show_regs(struct pt_regs *regs, int all)
 		savesegment(gs, gs);
 	}
 
-	printk("\n");
-
-	board = dmi_get_system_info(DMI_PRODUCT_NAME);
-	if (!board)
-		board = "";
-	printk("Pid: %d, comm: %s %s (%s %.*s) %s\n",
-			task_pid_nr(current), current->comm,
-			print_tainted(), init_utsname()->release,
-			(int)strcspn(init_utsname()->version, " "),
-			init_utsname()->version, board);
+	show_regs_common();
 
 	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
 			(u16)regs->cs, regs->ip, regs->flags,
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c95c8f4..e5ab0cd 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -26,7 +26,6 @@
 #include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/interrupt.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
@@ -38,7 +37,6 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
-#include <linux/dmi.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -163,18 +161,8 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
-	const char *board;
-
-	printk("\n");
-	print_modules();
-	board = dmi_get_system_info(DMI_PRODUCT_NAME);
-	if (!board)
-		board = "";
-	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n",
-		current->pid, current->comm, print_tainted(),
-		init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version, board);
+
+	show_regs_common();
 	printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
 	printk_address(regs->ip, 1);
 	printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2b97fc5..1545bc0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -259,6 +259,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"),
 		},
 	},
+	{       /* Handle problems with rebooting on ASUS P4S800 */
+		.callback = set_bios_reboot,
+		.ident = "ASUS P4S800",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 946a311..f7b8b98 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -73,6 +73,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/apic.h>
+#include <asm/trampoline.h>
 #include <asm/e820.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
@@ -875,6 +876,13 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_brk();
 
+	/*
+	 * Find and reserve possible boot-time SMP configuration:
+	 */
+	find_smp_config();
+
+	reserve_trampoline_memory();
+
 #ifdef CONFIG_ACPI_SLEEP
 	/*
 	 * Reserve low memory region for sleep support.
@@ -921,11 +929,6 @@ void __init setup_arch(char **cmdline_p)
 
 	early_acpi_boot_init();
 
-	/*
-	 * Find and reserve possible boot-time SMP configuration:
-	 */
-	find_smp_config();
-
 #ifdef CONFIG_ACPI_NUMA
 	/*
 	 * Parse SRAT to discover nodes.
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index d559af9..35abcb8 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -1,3 +1,5 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -20,9 +22,9 @@
 #include <asm/stackprotector.h>
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
+# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__)
 #else
-# define DBG(x...)
+# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0)
 #endif
 
 DEFINE_PER_CPU(int, cpu_number);
@@ -116,8 +118,8 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 	} else {
 		ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
 						   size, align, goal);
-		pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
-			 "%016lx\n", cpu, size, node, __pa(ptr));
+		pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n",
+			 cpu, size, node, __pa(ptr));
 	}
 	return ptr;
 #else
@@ -198,8 +200,7 @@ void __init setup_per_cpu_areas(void)
 					    pcpu_cpu_distance,
 					    pcpu_fc_alloc, pcpu_fc_free);
 		if (rc < 0)
-			pr_warning("PERCPU: %s allocator failed (%d), "
-				   "falling back to page size\n",
+			pr_warning("%s allocator failed (%d), falling back to page size\n",
 				   pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
 	if (rc < 0)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 29e6744..678d0b8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -671,6 +671,26 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
 	complete(&c_idle->done);
 }
 
+/* reduce the number of lines printed when booting a large cpu count system */
+static void __cpuinit announce_cpu(int cpu, int apicid)
+{
+	static int current_node = -1;
+	int node = cpu_to_node(cpu);
+
+	if (system_state == SYSTEM_BOOTING) {
+		if (node != current_node) {
+			if (current_node > (-1))
+				pr_cont(" Ok.\n");
+			current_node = node;
+			pr_info("Booting Node %3d, Processors ", node);
+		}
+		pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : "");
+		return;
+	} else
+		pr_info("Booting Node %d Processor %d APIC 0x%x\n",
+			node, cpu, apicid);
+}
+
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
  * (ie clustered apic addressing mode), this is a LOGICAL apic ID.
@@ -737,9 +757,8 @@ do_rest:
 	/* start_ip had better be page-aligned! */
 	start_ip = setup_trampoline();
 
-	/* So we see what's up   */
-	printk(KERN_INFO "Booting processor %d APIC 0x%x ip 0x%lx\n",
-			  cpu, apicid, start_ip);
+	/* So we see what's up */
+	announce_cpu(cpu, apicid);
 
 	/*
 	 * This grunge runs the startup process for
@@ -788,21 +807,17 @@ do_rest:
 			udelay(100);
 		}
 
-		if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
-			/* number CPUs logically, starting from 1 (BSP is 0) */
-			pr_debug("OK.\n");
-			printk(KERN_INFO "CPU%d: ", cpu);
-			print_cpu_info(&cpu_data(cpu));
-			pr_debug("CPU has booted.\n");
-		} else {
+		if (cpumask_test_cpu(cpu, cpu_callin_mask))
+			pr_debug("CPU%d: has booted.\n", cpu);
+		else {
 			boot_error = 1;
 			if (*((volatile unsigned char *)trampoline_base)
 					== 0xA5)
 				/* trampoline started but...? */
-				printk(KERN_ERR "Stuck ??\n");
+				pr_err("CPU%d: Stuck ??\n", cpu);
 			else
 				/* trampoline code not run */
-				printk(KERN_ERR "Not responding.\n");
+				pr_err("CPU%d: Not responding.\n", cpu);
 			if (apic->inquire_remote_apic)
 				apic->inquire_remote_apic(apicid);
 		}
@@ -1293,14 +1308,16 @@ void native_cpu_die(unsigned int cpu)
 	for (i = 0; i < 10; i++) {
 		/* They ack this in play_dead by setting CPU_DEAD */
 		if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
-			printk(KERN_INFO "CPU %d is now offline\n", cpu);
+			if (system_state == SYSTEM_RUNNING)
+				pr_info("CPU %u is now offline\n", cpu);
+
 			if (1 == num_online_cpus())
 				alternatives_smp_switch(0);
 			return;
 		}
 		msleep(100);
 	}
-	printk(KERN_ERR "CPU %u didn't die...\n", cpu);
+	pr_err("CPU %u didn't die...\n", cpu);
 }
 
 void play_dead_common(void)
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index cd02212..c652ef6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -12,21 +12,19 @@
 #endif
 
 /* ready for x86_64 and x86 */
-unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base;
 
 void __init reserve_trampoline_memory(void)
 {
-#ifdef CONFIG_X86_32
-	/*
-	 * But first pinch a few for the stack/trampoline stuff
-	 * FIXME: Don't need the extra page at 4K, but need to fix
-	 * trampoline before removing it. (see the GDT stuff)
-	 */
-	reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
-#endif
+	unsigned long mem;
+
 	/* Has to be in very low memory so we can execute real-mode AP code. */
-	reserve_early(TRAMPOLINE_BASE, TRAMPOLINE_BASE + TRAMPOLINE_SIZE,
-			"TRAMPOLINE");
+	mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+	if (mem == -1L)
+		panic("Cannot allocate trampoline\n");
+
+	trampoline_base = __va(mem);
+	reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index fab7440..296aba4 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -29,6 +29,8 @@
  *   Based on QEMU and Xen.
  */
 
+#define pr_fmt(fmt) "pit: " fmt
+
 #include <linux/kvm_host.h>
 
 #include "irq.h"
@@ -262,7 +264,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 
 static void destroy_pit_timer(struct kvm_timer *pt)
 {
-	pr_debug("pit: execute del timer!\n");
+	pr_debug("execute del timer!\n");
 	hrtimer_cancel(&pt->timer);
 }
 
@@ -284,7 +286,7 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
-	pr_debug("pit: create pit timer, interval is %llu nsec\n", interval);
+	pr_debug("create pit timer, interval is %llu nsec\n", interval);
 
 	/* TODO The new value only affected after the retriggered */
 	hrtimer_cancel(&pt->timer);
@@ -309,7 +311,7 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 
 	WARN_ON(!mutex_is_locked(&ps->lock));
 
-	pr_debug("pit: load_count val is %d, channel is %d\n", val, channel);
+	pr_debug("load_count val is %d, channel is %d\n", val, channel);
 
 	/*
 	 * The largest possible initial count is 0; this is equivalent
@@ -395,8 +397,8 @@ static int pit_ioport_write(struct kvm_io_device *this,
 	mutex_lock(&pit_state->lock);
 
 	if (val != 0)
-		pr_debug("pit: write addr is 0x%x, len is %d, val is 0x%x\n",
-			  (unsigned int)addr, len, val);
+		pr_debug("write addr is 0x%x, len is %d, val is 0x%x\n",
+			 (unsigned int)addr, len, val);
 
 	if (addr == 3) {
 		channel = val >> 6;
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 41628b1..8728341 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -7,7 +7,6 @@ struct msr_info {
 	u32 msr_no;
 	struct msr reg;
 	struct msr *msrs;
-	int off;
 	int err;
 };
 
@@ -18,7 +17,7 @@ static void __rdmsr_on_cpu(void *info)
 	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = &rv->msrs[this_cpu - rv->off];
+		reg = per_cpu_ptr(rv->msrs, this_cpu);
 	else
 		reg = &rv->reg;
 
@@ -32,7 +31,7 @@ static void __wrmsr_on_cpu(void *info)
 	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = &rv->msrs[this_cpu - rv->off];
+		reg = per_cpu_ptr(rv->msrs, this_cpu);
 	else
 		reg = &rv->reg;
 
@@ -80,7 +79,6 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
 
 	memset(&rv, 0, sizeof(rv));
 
-	rv.off    = cpumask_first(mask);
 	rv.msrs	  = msrs;
 	rv.msr_no = msr_no;
 
@@ -120,6 +118,26 @@ void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
 }
 EXPORT_SYMBOL(wrmsr_on_cpus);
 
+struct msr *msrs_alloc(void)
+{
+	struct msr *msrs = NULL;
+
+	msrs = alloc_percpu(struct msr);
+	if (!msrs) {
+		pr_warning("%s: error allocating msrs\n", __func__);
+		return NULL;
+	}
+
+	return msrs;
+}
+EXPORT_SYMBOL(msrs_alloc);
+
+void msrs_free(struct msr *msrs)
+{
+	free_percpu(msrs);
+}
+EXPORT_SYMBOL(msrs_free);
+
 /* These "safe" variants are slower and should be used when the target MSR
    may not actually exist. */
 static void __rdmsr_safe_on_cpu(void *info)
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 07bcc30..c0f6198 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -5,6 +5,8 @@
  *     2008 Pekka Paalanen <pq@iki.fi>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/list.h>
 #include <linux/rculist.h>
 #include <linux/spinlock.h>
@@ -136,7 +138,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 	pte_t *pte = lookup_address(f->page, &level);
 
 	if (!pte) {
-		pr_err("kmmio: no pte for page 0x%08lx\n", f->page);
+		pr_err("no pte for page 0x%08lx\n", f->page);
 		return -1;
 	}
 
@@ -148,7 +150,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 		clear_pte_presence(pte, clear, &f->old_presence);
 		break;
 	default:
-		pr_err("kmmio: unexpected page level 0x%x.\n", level);
+		pr_err("unexpected page level 0x%x.\n", level);
 		return -1;
 	}
 
@@ -170,13 +172,14 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
 	int ret;
-	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
+	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
-					f->page, f->count, !!f->old_presence);
+		pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n",
+			   f->page, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
-	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
+	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"),
+		  f->page);
 	f->armed = true;
 	return ret;
 }
@@ -240,24 +243,21 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 			 * condition needs handling by do_page_fault(), the
 			 * page really not being present is the most common.
 			 */
-			pr_debug("kmmio: secondary hit for 0x%08lx CPU %d.\n",
-					addr, smp_processor_id());
+			pr_debug("secondary hit for 0x%08lx CPU %d.\n",
+				 addr, smp_processor_id());
 
 			if (!faultpage->old_presence)
-				pr_info("kmmio: unexpected secondary hit for "
-					"address 0x%08lx on CPU %d.\n", addr,
-					smp_processor_id());
+				pr_info("unexpected secondary hit for address 0x%08lx on CPU %d.\n",
+					addr, smp_processor_id());
 		} else {
 			/*
 			 * Prevent overwriting already in-flight context.
 			 * This should not happen, let's hope disarming at
 			 * least prevents a panic.
 			 */
-			pr_emerg("kmmio: recursive probe hit on CPU %d, "
-					"for address 0x%08lx. Ignoring.\n",
-					smp_processor_id(), addr);
-			pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
-						ctx->addr);
+			pr_emerg("recursive probe hit on CPU %d, for address 0x%08lx. Ignoring.\n",
+				 smp_processor_id(), addr);
+			pr_emerg("previous hit was at 0x%08lx.\n", ctx->addr);
 			disarm_kmmio_fault_page(faultpage);
 		}
 		goto no_kmmio_ctx;
@@ -316,8 +316,8 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 		 * something external causing them (f.e. using a debugger while
 		 * mmio tracing enabled), or erroneous behaviour
 		 */
-		pr_warning("kmmio: unexpected debug trap on CPU %d.\n",
-							smp_processor_id());
+		pr_warning("unexpected debug trap on CPU %d.\n",
+			   smp_processor_id());
 		goto out;
 	}
 
@@ -425,7 +425,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
 		if (add_kmmio_fault_page(p->addr + size))
-			pr_err("kmmio: Unable to set page fault.\n");
+			pr_err("Unable to set page fault.\n");
 		size += PAGE_SIZE;
 	}
 out:
@@ -490,7 +490,7 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
  * 2. remove_kmmio_fault_pages()
  *    Remove the pages from kmmio_page_table.
  * 3. rcu_free_kmmio_fault_pages()
- *    Actally free the kmmio_fault_page structs as with RCU.
+ *    Actually free the kmmio_fault_page structs as with RCU.
  */
 void unregister_kmmio_probe(struct kmmio_probe *p)
 {
@@ -511,7 +511,7 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 
 	drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC);
 	if (!drelease) {
-		pr_crit("kmmio: leaking kmmio_fault_page objects.\n");
+		pr_crit("leaking kmmio_fault_page objects.\n");
 		return;
 	}
 	drelease->release_list = release_list;
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 132772a..34a3291 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -19,6 +19,9 @@
  *
  * Derived from the read-mod example from relay-examples by Tom Zanussi.
  */
+
+#define pr_fmt(fmt) "mmiotrace: " fmt
+
 #define DEBUG 1
 
 #include <linux/module.h>
@@ -36,8 +39,6 @@
 
 #include "pf_in.h"
 
-#define NAME "mmiotrace: "
-
 struct trap_reason {
 	unsigned long addr;
 	unsigned long ip;
@@ -96,17 +97,18 @@ static void print_pte(unsigned long address)
 	pte_t *pte = lookup_address(address, &level);
 
 	if (!pte) {
-		pr_err(NAME "Error in %s: no pte for page 0x%08lx\n",
-							__func__, address);
+		pr_err("Error in %s: no pte for page 0x%08lx\n",
+		       __func__, address);
 		return;
 	}
 
 	if (level == PG_LEVEL_2M) {
-		pr_emerg(NAME "4MB pages are not currently supported: "
-							"0x%08lx\n", address);
+		pr_emerg("4MB pages are not currently supported: 0x%08lx\n",
+			 address);
 		BUG();
 	}
-	pr_info(NAME "pte for 0x%lx: 0x%llx 0x%llx\n", address,
+	pr_info("pte for 0x%lx: 0x%llx 0x%llx\n",
+		address,
 		(unsigned long long)pte_val(*pte),
 		(unsigned long long)pte_val(*pte) & _PAGE_PRESENT);
 }
@@ -118,22 +120,21 @@ static void print_pte(unsigned long address)
 static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr)
 {
 	const struct trap_reason *my_reason = &get_cpu_var(pf_reason);
-	pr_emerg(NAME "unexpected fault for address: 0x%08lx, "
-					"last fault for address: 0x%08lx\n",
-					addr, my_reason->addr);
+	pr_emerg("unexpected fault for address: 0x%08lx, last fault for address: 0x%08lx\n",
+		 addr, my_reason->addr);
 	print_pte(addr);
 	print_symbol(KERN_EMERG "faulting IP is at %s\n", regs->ip);
 	print_symbol(KERN_EMERG "last faulting IP was at %s\n", my_reason->ip);
 #ifdef __i386__
 	pr_emerg("eax: %08lx   ebx: %08lx   ecx: %08lx   edx: %08lx\n",
-			regs->ax, regs->bx, regs->cx, regs->dx);
+		 regs->ax, regs->bx, regs->cx, regs->dx);
 	pr_emerg("esi: %08lx   edi: %08lx   ebp: %08lx   esp: %08lx\n",
-			regs->si, regs->di, regs->bp, regs->sp);
+		 regs->si, regs->di, regs->bp, regs->sp);
 #else
 	pr_emerg("rax: %016lx   rcx: %016lx   rdx: %016lx\n",
-					regs->ax, regs->cx, regs->dx);
+		 regs->ax, regs->cx, regs->dx);
 	pr_emerg("rsi: %016lx   rdi: %016lx   rbp: %016lx   rsp: %016lx\n",
-				regs->si, regs->di, regs->bp, regs->sp);
+		 regs->si, regs->di, regs->bp, regs->sp);
 #endif
 	put_cpu_var(pf_reason);
 	BUG();
@@ -213,7 +214,7 @@ static void post(struct kmmio_probe *p, unsigned long condition,
 	/* this should always return the active_trace count to 0 */
 	my_reason->active_traces--;
 	if (my_reason->active_traces) {
-		pr_emerg(NAME "unexpected post handler");
+		pr_emerg("unexpected post handler");
 		BUG();
 	}
 
@@ -244,7 +245,7 @@ static void ioremap_trace_core(resource_size_t offset, unsigned long size,
 	};
 
 	if (!trace) {
-		pr_err(NAME "kmalloc failed in ioremap\n");
+		pr_err("kmalloc failed in ioremap\n");
 		return;
 	}
 
@@ -282,8 +283,8 @@ void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
 	if (!is_enabled()) /* recheck and proper locking in *_core() */
 		return;
 
-	pr_debug(NAME "ioremap_*(0x%llx, 0x%lx) = %p\n",
-				(unsigned long long)offset, size, addr);
+	pr_debug("ioremap_*(0x%llx, 0x%lx) = %p\n",
+		 (unsigned long long)offset, size, addr);
 	if ((filter_offset) && (offset != filter_offset))
 		return;
 	ioremap_trace_core(offset, size, addr);
@@ -301,7 +302,7 @@ static void iounmap_trace_core(volatile void __iomem *addr)
 	struct remap_trace *tmp;
 	struct remap_trace *found_trace = NULL;
 
-	pr_debug(NAME "Unmapping %p.\n", addr);
+	pr_debug("Unmapping %p.\n", addr);
 
 	spin_lock_irq(&trace_lock);
 	if (!is_enabled())
@@ -363,9 +364,8 @@ static void clear_trace_list(void)
 	 * Caller also ensures is_enabled() cannot change.
 	 */
 	list_for_each_entry(trace, &trace_list, list) {
-		pr_notice(NAME "purging non-iounmapped "
-					"trace @0x%08lx, size 0x%lx.\n",
-					trace->probe.addr, trace->probe.len);
+		pr_notice("purging non-iounmapped trace @0x%08lx, size 0x%lx.\n",
+			  trace->probe.addr, trace->probe.len);
 		if (!nommiotrace)
 			unregister_kmmio_probe(&trace->probe);
 	}
@@ -387,7 +387,7 @@ static void enter_uniprocessor(void)
 
 	if (downed_cpus == NULL &&
 	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
-		pr_notice(NAME "Failed to allocate mask\n");
+		pr_notice("Failed to allocate mask\n");
 		goto out;
 	}
 
@@ -395,20 +395,19 @@ static void enter_uniprocessor(void)
 	cpumask_copy(downed_cpus, cpu_online_mask);
 	cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
 	if (num_online_cpus() > 1)
-		pr_notice(NAME "Disabling non-boot CPUs...\n");
+		pr_notice("Disabling non-boot CPUs...\n");
 	put_online_cpus();
 
 	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_down(cpu);
 		if (!err)
-			pr_info(NAME "CPU%d is down.\n", cpu);
+			pr_info("CPU%d is down.\n", cpu);
 		else
-			pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err);
+			pr_err("Error taking CPU%d down: %d\n", cpu, err);
 	}
 out:
 	if (num_online_cpus() > 1)
-		pr_warning(NAME "multiple CPUs still online, "
-						"may miss events.\n");
+		pr_warning("multiple CPUs still online, may miss events.\n");
 }
 
 /* __ref because leave_uniprocessor calls cpu_up which is __cpuinit,
@@ -420,13 +419,13 @@ static void __ref leave_uniprocessor(void)
 
 	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
 		return;
-	pr_notice(NAME "Re-enabling CPUs...\n");
+	pr_notice("Re-enabling CPUs...\n");
 	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_up(cpu);
 		if (!err)
-			pr_info(NAME "enabled CPU%d.\n", cpu);
+			pr_info("enabled CPU%d.\n", cpu);
 		else
-			pr_err(NAME "cannot re-enable CPU%d: %d\n", cpu, err);
+			pr_err("cannot re-enable CPU%d: %d\n", cpu, err);
 	}
 }
 
@@ -434,8 +433,8 @@ static void __ref leave_uniprocessor(void)
 static void enter_uniprocessor(void)
 {
 	if (num_online_cpus() > 1)
-		pr_warning(NAME "multiple CPUs are online, may miss events. "
-			"Suggest booting with maxcpus=1 kernel argument.\n");
+		pr_warning("multiple CPUs are online, may miss events. "
+			   "Suggest booting with maxcpus=1 kernel argument.\n");
 }
 
 static void leave_uniprocessor(void)
@@ -450,13 +449,13 @@ void enable_mmiotrace(void)
 		goto out;
 
 	if (nommiotrace)
-		pr_info(NAME "MMIO tracing disabled.\n");
+		pr_info("MMIO tracing disabled.\n");
 	kmmio_init();
 	enter_uniprocessor();
 	spin_lock_irq(&trace_lock);
 	atomic_inc(&mmiotrace_enabled);
 	spin_unlock_irq(&trace_lock);
-	pr_info(NAME "enabled.\n");
+	pr_info("enabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
 }
@@ -475,7 +474,7 @@ void disable_mmiotrace(void)
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
 	kmmio_cleanup();
-	pr_info(NAME "disabled.\n");
+	pr_info("disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
 }
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 4008e2c..fdbcc9f 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -264,10 +264,16 @@ static ssize_t nvram_write(struct file *file, const char __user *buf,
 	unsigned char contents[NVRAM_BYTES];
 	unsigned i = *ppos;
 	unsigned char *tmp;
-	int len;
 
-	len = (NVRAM_BYTES - i) < count ? (NVRAM_BYTES - i) : count;
-	if (copy_from_user(contents, buf, len))
+	if (i >= NVRAM_BYTES)
+		return 0;	/* Past EOF */
+
+	if (count > NVRAM_BYTES - i)
+		count = NVRAM_BYTES - i;
+	if (count > NVRAM_BYTES)
+		return -EFAULT;	/* Can't happen, but prove it to gcc */
+
+	if (copy_from_user(contents, buf, count))
 		return -EFAULT;
 
 	spin_lock_irq(&rtc_lock);
@@ -275,7 +281,7 @@ static ssize_t nvram_write(struct file *file, const char __user *buf,
 	if (!__nvram_check_checksum())
 		goto checksum_err;
 
-	for (tmp = contents; count-- > 0 && i < NVRAM_BYTES; ++i, ++tmp)
+	for (tmp = contents; count--; ++i, ++tmp)
 		__nvram_write_byte(*tmp, i);
 
 	__nvram_set_checksum();
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 5fdd6da..df5b684 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -13,6 +13,8 @@ module_param(report_gart_errors, int, 0644);
 static int ecc_enable_override;
 module_param(ecc_enable_override, int, 0644);
 
+static struct msr *msrs;
+
 /* Lookup table for all possible MC control instances */
 struct amd64_pvt;
 static struct mem_ctl_info *mci_lookup[EDAC_MAX_NUMNODES];
@@ -2495,8 +2497,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, int nid)
 static bool amd64_nb_mce_bank_enabled_on_node(int nid)
 {
 	cpumask_var_t mask;
-	struct msr *msrs;
-	int cpu, nbe, idx = 0;
+	int cpu, nbe;
 	bool ret = false;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
@@ -2507,32 +2508,22 @@ static bool amd64_nb_mce_bank_enabled_on_node(int nid)
 
 	get_cpus_on_this_dct_cpumask(mask, nid);
 
-	msrs = kzalloc(sizeof(struct msr) * cpumask_weight(mask), GFP_KERNEL);
-	if (!msrs) {
-		amd64_printk(KERN_WARNING, "%s: error allocating msrs\n",
-			      __func__);
-		free_cpumask_var(mask);
-		 return false;
-	}
-
 	rdmsr_on_cpus(mask, MSR_IA32_MCG_CTL, msrs);
 
 	for_each_cpu(cpu, mask) {
-		nbe = msrs[idx].l & K8_MSR_MCGCTL_NBE;
+		struct msr *reg = per_cpu_ptr(msrs, cpu);
+		nbe = reg->l & K8_MSR_MCGCTL_NBE;
 
 		debugf0("core: %u, MCG_CTL: 0x%llx, NB MSR is %s\n",
-			cpu, msrs[idx].q,
+			cpu, reg->q,
 			(nbe ? "enabled" : "disabled"));
 
 		if (!nbe)
 			goto out;
-
-		idx++;
 	}
 	ret = true;
 
 out:
-	kfree(msrs);
 	free_cpumask_var(mask);
 	return ret;
 }
@@ -2540,8 +2531,7 @@ out:
 static int amd64_toggle_ecc_err_reporting(struct amd64_pvt *pvt, bool on)
 {
 	cpumask_var_t cmask;
-	struct msr *msrs = NULL;
-	int cpu, idx = 0;
+	int cpu;
 
 	if (!zalloc_cpumask_var(&cmask, GFP_KERNEL)) {
 		amd64_printk(KERN_WARNING, "%s: error allocating mask\n",
@@ -2551,34 +2541,27 @@ static int amd64_toggle_ecc_err_reporting(struct amd64_pvt *pvt, bool on)
 
 	get_cpus_on_this_dct_cpumask(cmask, pvt->mc_node_id);
 
-	msrs = kzalloc(sizeof(struct msr) * cpumask_weight(cmask), GFP_KERNEL);
-	if (!msrs) {
-		amd64_printk(KERN_WARNING, "%s: error allocating msrs\n",
-			     __func__);
-		return -ENOMEM;
-	}
-
 	rdmsr_on_cpus(cmask, MSR_IA32_MCG_CTL, msrs);
 
 	for_each_cpu(cpu, cmask) {
 
+		struct msr *reg = per_cpu_ptr(msrs, cpu);
+
 		if (on) {
-			if (msrs[idx].l & K8_MSR_MCGCTL_NBE)
+			if (reg->l & K8_MSR_MCGCTL_NBE)
 				pvt->flags.ecc_report = 1;
 
-			msrs[idx].l |= K8_MSR_MCGCTL_NBE;
+			reg->l |= K8_MSR_MCGCTL_NBE;
 		} else {
 			/*
 			 * Turn off ECC reporting only when it was off before
 			 */
 			if (!pvt->flags.ecc_report)
-				msrs[idx].l &= ~K8_MSR_MCGCTL_NBE;
+				reg->l &= ~K8_MSR_MCGCTL_NBE;
 		}
-		idx++;
 	}
 	wrmsr_on_cpus(cmask, MSR_IA32_MCG_CTL, msrs);
 
-	kfree(msrs);
 	free_cpumask_var(cmask);
 
 	return 0;
@@ -3036,6 +3019,8 @@ static int __init amd64_edac_init(void)
 	if (cache_k8_northbridges() < 0)
 		return err;
 
+	msrs = msrs_alloc();
+
 	err = pci_register_driver(&amd64_pci_driver);
 	if (err)
 		return err;
@@ -3071,6 +3056,9 @@ static void __exit amd64_edac_exit(void)
 		edac_pci_release_generic_ctl(amd64_ctl_pci);
 
 	pci_unregister_driver(&amd64_pci_driver);
+
+	msrs_free(msrs);
+	msrs = NULL;
 }
 
 module_init(amd64_edac_init);
diff --git a/mm/migrate.c b/mm/migrate.c
index 7dbcb22..0bc640f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1044,7 +1044,7 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 	int err;
 
 	for (i = 0; i < nr_pages; i += chunk_nr) {
-		if (chunk_nr + i > nr_pages)
+		if (chunk_nr > nr_pages - i)
 			chunk_nr = nr_pages - i;
 
 		err = copy_from_user(chunk_pages, &pages[i],