47 files changed, 377 insertions, 195 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3d0f2b6a5a1..68d91c8233f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,7 +22,6 @@ config X86
         select HAVE_IDE
         select HAVE_OPROFILE
         select HAVE_IOREMAP_PROT
-        select HAVE_GET_USER_PAGES_FAST
         select HAVE_KPROBES
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select HAVE_KRETPROBES
@@ -952,9 +951,9 @@ config NUMA
           local memory controller of the CPU and add some more
           NUMA awareness to the kernel.
 
-          For i386 this is currently highly experimental and should be only
+          For 32-bit this is currently highly experimental and should be only
           used for kernel development. It might also cause boot failures.
-          For x86_64 this is recommended on all multiprocessor Opteron systems.
+          For 64-bit this is recommended on all multiprocessor Opteron systems.
           If the system is EM64T, you should say N unless your system is
           EM64T NUMA.
 
@@ -1264,7 +1263,7 @@ config KEXEC
           strongly in flux, so no good recommendation can be made.
 
 config CRASH_DUMP
-        bool "kernel crash dumps (EXPERIMENTAL)"
+        bool "kernel crash dumps"
         depends on X86_64 || (X86_32 && HIGHMEM)
         help
           Generate crash dump after being started by kexec.
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index a34b9982c7c..cc0ef13fba7 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -24,10 +24,14 @@
 #include <linux/edd.h>
 #include <asm/boot.h>
 #include <asm/setup.h>
+#include "bitops.h"
+#include <asm/cpufeature.h>
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
 
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
 extern struct setup_header hdr;
 extern struct boot_params boot_params;
 
@@ -242,6 +246,12 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
 
 /* cpu.c, cpucheck.c */
+struct cpu_features {
+        int level;              /* Family, or 64 for x86-64 */
+        int model;
+        u32 flags[NCAPINTS];
+};
+extern struct cpu_features cpu;
 int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
 int validate_cpu(void);
 
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 92d6fd73dc7..75298fe2edc 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -16,9 +16,6 @@
  */
 
 #include "boot.h"
-#include "bitops.h"
-#include <asm/cpufeature.h>
-
 #include "cpustr.h"
 
 static char *cpu_name(int level)
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 7804389ee00..4b9ae7c5674 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -22,21 +22,13 @@
 
 #ifdef _SETUP
 # include "boot.h"
-# include "bitops.h"
 #endif
 #include <linux/types.h>
-#include <asm/cpufeature.h>
 #include <asm/processor-flags.h>
 #include <asm/required-features.h>
 #include <asm/msr-index.h>
 
-struct cpu_features {
-        int level;              /* Family, or 64 for x86-64 */
-        int model;
-        u32 flags[NCAPINTS];
-};
-
-static struct cpu_features cpu;
+struct cpu_features cpu;
 static u32 cpu_vendor[3];
 static u32 err_flags[NCAPINTS];
 
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 2296164b54d..197421db1af 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -73,6 +73,11 @@ static void keyboard_set_repeat(void)
  */
 static void query_ist(void)
 {
+        /* Some older BIOSes apparently crash on this call, so filter
+           it from machines too old to have SpeedStep at all. */
+        if (cpu.level < 6)
+                return;
+
         asm("int $0x15"
             : "=a" (boot_params.ist_info.signature),
               "=b" (boot_params.ist_info.command),
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 53165c97336..8c3c25f3557 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -13,7 +13,6 @@
  */
 
 #include "boot.h"
-#include <linux/kernel.h>
 
 #define SMAP    0x534d4150      /* ASCII "SMAP" */
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d8d118935b0..f20470823d3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -96,6 +96,8 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #warning ACPI uses CMPXCHG, i486 and later hardware
 #endif
 
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -157,6 +159,14 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 struct acpi_mcfg_allocation *pci_mmcfg_config;
 int pci_mmcfg_config_num;
 
+static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
+{
+        if (!strcmp(mcfg->header.oem_id, "SGI"))
+                acpi_mcfg_64bit_base_addr = TRUE;
+
+        return 0;
+}
+
 int __init acpi_parse_mcfg(struct acpi_table_header *header)
 {
         struct acpi_table_mcfg *mcfg;
@@ -189,8 +199,12 @@ int __init acpi_parse_mcfg(struct acpi_table_header *header)
         }
 
         memcpy(pci_mmcfg_config, &mcfg[1], config_size);
+
+        acpi_mcfg_oem_check(mcfg);
+
         for (i = 0; i < pci_mmcfg_config_num; ++i) {
-                if (pci_mmcfg_config[i].address > 0xFFFFFFFF) {
+                if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) &&
+                    !acpi_mcfg_64bit_base_addr) {
                         printk(KERN_ERR PREFIX
                                "MMCONFIG not in low 4GB of memory\n");
                         kfree(pci_mmcfg_config);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index fa2161d5003..426e5d91b63 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -20,7 +20,7 @@ unsigned long acpi_realmode_flags;
 /* address in low memory of the wakeup routine. */
 static unsigned long acpi_realmode;
 
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
 static char temp_stack[10240];
 #endif
 
@@ -86,7 +86,7 @@ int acpi_save_state_mem(void)
 #endif /* !CONFIG_64BIT */
 
         header->pmode_cr0 = read_cr0();
-        header->pmode_cr4 = read_cr4();
+        header->pmode_cr4 = read_cr4_safe();
         header->realmode_flags = acpi_realmode_flags;
         header->real_magic = 0x12345678;
 
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 22d7d050905..de39e1f2ede 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -101,16 +101,13 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
  */
 static int iommu_completion_wait(struct amd_iommu *iommu)
 {
-        int ret;
+        int ret, ready = 0;
+        unsigned status = 0;
         struct iommu_cmd cmd;
-        volatile u64 ready = 0;
-        unsigned long ready_phys = virt_to_phys(&ready);
         unsigned long i = 0;
 
         memset(&cmd, 0, sizeof(cmd));
-        cmd.data[0] = LOW_U32(ready_phys) | CMD_COMPL_WAIT_STORE_MASK;
-        cmd.data[1] = upper_32_bits(ready_phys);
-        cmd.data[2] = 1; /* value written to 'ready' */
+        cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
         CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
 
         iommu->need_sync = 0;
@@ -122,9 +119,15 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
         while (!ready && (i < EXIT_LOOP_COUNT)) {
                 ++i;
-                cpu_relax();
+                /* wait for the bit to become one */
+                status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+                ready = status & MMIO_STATUS_COM_WAIT_INT_MASK;
         }
 
+        /* set bit back to zero */
+        status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
+        writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
         if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
                 printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
 
@@ -161,7 +164,7 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
         address &= PAGE_MASK;
         CMD_SET_TYPE(&cmd, CMD_INV_IOMMU_PAGES);
         cmd.data[1] |= domid;
-        cmd.data[2] = LOW_U32(address);
+        cmd.data[2] = lower_32_bits(address);
         cmd.data[3] = upper_32_bits(address);
         if (s) /* size bit - we flush more than one 4kb page */
                 cmd.data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index d9a9da597e7..a69cc0f5204 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -801,6 +801,21 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
 }
 
 /*
+ * Init the device table to not allow DMA access for devices and
+ * suppress all page faults
+ */
+static void init_device_table(void)
+{
+        u16 devid;
+
+        for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
+                set_dev_entry_bit(devid, DEV_ENTRY_VALID);
+                set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
+                set_dev_entry_bit(devid, DEV_ENTRY_NO_PAGE_FAULT);
+        }
+}
+
+/*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
  */
@@ -931,6 +946,9 @@ int __init amd_iommu_init(void)
         if (amd_iommu_pd_alloc_bitmap == NULL)
                 goto free;
 
+        /* init the device table */
+        init_device_table();
+
         /*
          * let all alias entries point to itself
          */
@@ -954,15 +972,15 @@ int __init amd_iommu_init(void)
         if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
                 goto free;
 
-        ret = amd_iommu_init_dma_ops();
+        ret = sysdev_class_register(&amd_iommu_sysdev_class);
         if (ret)
                 goto free;
 
-        ret = sysdev_class_register(&amd_iommu_sysdev_class);
+        ret = sysdev_register(&device_amd_iommu);
         if (ret)
                 goto free;
 
-        ret = sysdev_register(&device_amd_iommu);
+        ret = amd_iommu_init_dma_ops();
         if (ret)
                 goto free;
 
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index d6c89835837..f88bd0d982b 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1454,8 +1454,6 @@ void disconnect_bsp_APIC(int virt_wire_setup)
         }
 }
 
-unsigned int __cpuinitdata maxcpus = NR_CPUS;
-
 void __cpuinit generic_processor_info(int apicid, int version)
 {
         int cpu;
@@ -1482,12 +1480,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
                 return;
         }
 
-        if (num_processors >= maxcpus) {
-                printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
-                        " Processor ignored.\n", maxcpus);
-                return;
-        }
-
         num_processors++;
         cpus_complement(tmp_map, cpu_present_map);
         cpu = first_cpu(tmp_map);
@@ -1720,15 +1712,19 @@ static int __init parse_lapic_timer_c2_ok(char *arg)
 }
 early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
 
-static int __init apic_set_verbosity(char *str)
+static int __init apic_set_verbosity(char *arg)
 {
-        if (strcmp("debug", str) == 0)
+        if (!arg)
+                return -EINVAL;
+
+        if (strcmp(arg, "debug") == 0)
                 apic_verbosity = APIC_DEBUG;
-        else if (strcmp("verbose", str) == 0)
+        else if (strcmp(arg, "verbose") == 0)
                 apic_verbosity = APIC_VERBOSE;
-        return 1;
+
+        return 0;
 }
-__setup("apic=", apic_set_verbosity);
+early_param("apic", apic_set_verbosity);
 
 static int __init lapic_insert_resource(void)
 {
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 7f1f030da7e..446c062e831 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -90,7 +90,6 @@ static unsigned long apic_phys;
 
 unsigned long mp_lapic_addr;
 
-unsigned int __cpuinitdata maxcpus = NR_CPUS;
 /*
  * Get the LAPIC version
  */
@@ -1062,12 +1061,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
                 return;
         }
 
-        if (num_processors >= maxcpus) {
-                printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
-                       " Processor ignored.\n", maxcpus);
-                return;
-        }
-
         num_processors++;
         cpus_complement(tmp_map, cpu_present_map);
         cpu = first_cpu(tmp_map);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c9b58a806e8..c8e315f1aa8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -50,6 +50,8 @@ static double __initdata y = 3145727.0;
  */
 static void __init check_fpu(void)
 {
+        s32 fdiv_bug;
+
         if (!boot_cpu_data.hard_math) {
 #ifndef CONFIG_MATH_EMULATION
                 printk(KERN_EMERG "No coprocessor found and no math emulation present.\n");
@@ -74,8 +76,10 @@ static void __init check_fpu(void)
                 "fistpl %0\n\t"
                 "fwait\n\t"
                 "fninit"
-                : "=m" (*&boot_cpu_data.fdiv_bug)
+                : "=m" (*&fdiv_bug)
                 : "m" (*&x), "m" (*&y));
+
+        boot_cpu_data.fdiv_bug = fdiv_bug;
         if (boot_cpu_data.fdiv_bug)
                 printk("Hmm, FPU with FDIV bug.\n");
 }
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index de7439f82b9..05cc22dbd4f 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -478,7 +478,13 @@ static int setup_p4_watchdog(unsigned nmi_hz)
                 perfctr_msr = MSR_P4_IQ_PERFCTR1;
                 evntsel_msr = MSR_P4_CRU_ESCR0;
                 cccr_msr = MSR_P4_IQ_CCCR1;
-                cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
+
+                /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */
+                if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4)
+                        cccr_val = P4_CCCR_OVF_PMI0;
+                else
+                        cccr_val = P4_CCCR_OVF_PMI1;
+                cccr_val |= P4_CCCR_ESCR_SELECT(4);
         }
 
         evntsel = P4_ESCR_EVENT_SELECT(0x3F)
diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c
index 4b63c8e1f13..5cab48ee61a 100644
--- a/arch/x86/kernel/efi_32.c
+++ b/arch/x86/kernel/efi_32.c
@@ -53,7 +53,7 @@ void efi_call_phys_prelog(void)
          * directory. If I have PAE, I just need to duplicate one entry in
          * page directory.
          */
-        cr4 = read_cr4();
+        cr4 = read_cr4_safe();
 
         if (cr4 & X86_CR4_PAE) {
                 efi_bak_pg_dir_pointer[0].pgd =
@@ -91,7 +91,7 @@ void efi_call_phys_epilog(void)
         gdt_descr.size = GDT_SIZE - 1;
         load_gdt(&gdt_descr);
 
-        cr4 = read_cr4();
+        cr4 = read_cr4_safe();
 
         if (cr4 & X86_CR4_PAE) {
                 swapper_pg_dir[pgd_index(0)].pgd =
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 2cfcbded888..2d7e307c777 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -222,7 +222,7 @@ static __init void map_low_mmrs(void)
 
 enum map_type {map_wb, map_uc};
 
-static void map_high(char *id, unsigned long base, int shift, enum map_type map_type)
+static __init void map_high(char *id, unsigned long base, int shift, enum map_type map_type)
 {
         unsigned long bytes, paddr;
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 1b318e903bf..9bfc4d72fb2 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -88,6 +88,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
         BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
         BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
                                 (__START_KERNEL & PGDIR_MASK)));
+        BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
         /* clear bss before set_intr_gate with early_idt_handler */
         clear_bss();
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ad2b15a1334..59fd3b6b130 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -359,6 +359,7 @@ static int hpet_clocksource_register(void)
 int __init hpet_enable(void)
 {
         unsigned long id;
+        int i;
 
         if (!is_hpet_capable())
                 return 0;
@@ -369,6 +370,29 @@ int __init hpet_enable(void)
          * Read the period and check for a sane value:
          */
         hpet_period = hpet_readl(HPET_PERIOD);
+
+        /*
+         * AMD SB700 based systems with spread spectrum enabled use a
+         * SMM based HPET emulation to provide proper frequency
+         * setting. The SMM code is initialized with the first HPET
+         * register access and takes some time to complete. During
+         * this time the config register reads 0xffffffff. We check
+         * for max. 1000 loops whether the config register reads a non
+         * 0xffffffff value to make sure that HPET is up and running
+         * before we go further. A counting loop is safe, as the HPET
+         * access takes thousands of CPU cycles. On non SB700 based
+         * machines this check is only done once and has no side
+         * effects.
+         */
+        for (i = 0; hpet_readl(HPET_CFG) == 0xFFFFFFFF; i++) {
+                if (i == 1000) {
+                        printk(KERN_WARNING
+                               "HPET config register value = 0xFFFFFFFF. "
+                               "Disabling HPET\n");
+                        goto out_nohpet;
+                }
+        }
+
         if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
                 goto out_nohpet;
 
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index de9aa0e3a9c..09cddb57bec 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -57,7 +57,7 @@ atomic_t irq_mis_count;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-static DEFINE_SPINLOCK(vector_lock);
+DEFINE_SPINLOCK(vector_lock);
 
 int timer_through_8259 __initdata;
 
@@ -1209,10 +1209,6 @@ static int assign_irq_vector(int irq)
         return vector;
 }
 
-void setup_vector_irq(int cpu)
-{
-}
-
 static struct irq_chip ioapic_chip;
 
 #define IOAPIC_AUTO     -1
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8269434d170..61a83b70c18 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -101,7 +101,7 @@ int timer_through_8259 __initdata;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-DEFINE_SPINLOCK(vector_lock);
+static DEFINE_SPINLOCK(vector_lock);
 
 /*
  * # of IRQ routing registers
@@ -697,6 +697,19 @@ static int pin_2_irq(int idx, int apic, int pin)
         return irq;
 }
 
+void lock_vector_lock(void)
+{
+        /* Used to the online set of cpus does not change
+         * during assign_irq_vector.
+         */
+        spin_lock(&vector_lock);
+}
+
+void unlock_vector_lock(void)
+{
+        spin_unlock(&vector_lock);
+}
+
 static int __assign_irq_vector(int irq, cpumask_t mask)
 {
         /*
@@ -802,7 +815,7 @@ static void __clear_irq_vector(int irq)
         cpus_clear(cfg->domain);
 }
 
-static void __setup_vector_irq(int cpu)
+void __setup_vector_irq(int cpu)
 {
         /* Initialize vector_irq on a new cpu */
         /* This function must be called with vector_lock held */
@@ -825,14 +838,6 @@ static void __setup_vector_irq(int cpu)
         }
 }
 
-void setup_vector_irq(int cpu)
-{
-        spin_lock(&vector_lock);
-        __setup_vector_irq(smp_processor_id());
-        spin_unlock(&vector_lock);
-}
-
-
 static struct irq_chip ioapic_chip;
 
 static void ioapic_register_intr(int irq, unsigned long trigger)
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 9fe478d9840..0732adba05c 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/numa.h>
 #include <linux/ftrace.h>
+#include <linux/suspend.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -78,7 +79,7 @@ static void load_segments(void)
 /*
  * A architecture hook called to validate the
  * proposed image and prepare the control pages
- * as needed.  The pages for KEXEC_CONTROL_CODE_SIZE
+ * as needed.  The pages for KEXEC_CONTROL_PAGE_SIZE
  * have been allocated, but the segments have yet
  * been copied into the kernel.
  *
@@ -113,6 +114,7 @@ void machine_kexec(struct kimage *image)
 {
         unsigned long page_list[PAGES_NR];
         void *control_page;
+        int save_ftrace_enabled;
         asmlinkage unsigned long
                 (*relocate_kernel_ptr)(unsigned long indirection_page,
                                        unsigned long control_page,
@@ -120,7 +122,12 @@ void machine_kexec(struct kimage *image)
                                        unsigned int has_pae,
                                        unsigned int preserve_context);
 
-        tracer_disable();
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context)
+                save_processor_state();
+#endif
+
+        save_ftrace_enabled = __ftrace_enabled_save();
 
         /* Interrupts aren't acceptable while we reboot */
         local_irq_disable();
@@ -138,7 +145,7 @@ void machine_kexec(struct kimage *image)
         }
 
         control_page = page_address(image->control_code_page);
-        memcpy(control_page, relocate_kernel, PAGE_SIZE/2);
+        memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
 
         relocate_kernel_ptr = control_page;
         page_list[PA_CONTROL_PAGE] = __pa(control_page);
@@ -178,6 +185,13 @@ void machine_kexec(struct kimage *image)
                                            (unsigned long)page_list,
                                            image->start, cpu_has_pae,
                                            image->preserve_context);
+
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context)
+                restore_processor_state();
+#endif
+
+        __ftrace_enabled_restore(save_ftrace_enabled);
 }
 
 void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 07c0f828f48..3b599518c32 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -33,6 +33,8 @@
 #include <linux/module.h>
 #include <asm/geode.h>
 
+#define MFGPT_DEFAULT_IRQ       7
+
 static struct mfgpt_timer_t {
         unsigned int avail:1;
 } mfgpt_timers[MFGPT_MAX_TIMERS];
@@ -157,29 +159,48 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
 }
 EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event);
 
-int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
+int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable)
 {
-        u32 val, dummy;
-        int offset;
+        u32 zsel, lpc, dummy;
+        int shift;
 
         if (timer < 0 || timer >= MFGPT_MAX_TIMERS)
                 return -EIO;
 
-        if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable))
+        /*
+         * Unfortunately, MFGPTs come in pairs sharing their IRQ lines. If VSA
+         * is using the same CMP of the timer's Siamese twin, the IRQ is set to
+         * 2, and we mustn't use nor change it.
+         * XXX: Likewise, 2 Linux drivers might clash if the 2nd overwrites the
+         * IRQ of the 1st. This can only happen if forcing an IRQ, calling this
+         * with *irq==0 is safe. Currently there _are_ no 2 drivers.
+         */
+        rdmsr(MSR_PIC_ZSEL_LOW, zsel, dummy);
+        shift = ((cmp == MFGPT_CMP1 ? 0 : 4) + timer % 4) * 4;
+        if (((zsel >> shift) & 0xF) == 2)
                 return -EIO;
 
-        rdmsr(MSR_PIC_ZSEL_LOW, val, dummy);
+        /* Choose IRQ: if none supplied, keep IRQ already set or use default */
+        if (!*irq)
+                *irq = (zsel >> shift) & 0xF;
+        if (!*irq)
+                *irq = MFGPT_DEFAULT_IRQ;
 
-        offset = (timer % 4) * 4;
-
-        val &= ~((0xF << offset) | (0xF << (offset + 16)));
+        /* Can't use IRQ if it's 0 (=disabled), 2, or routed to LPC */
+        if (*irq < 1 || *irq == 2 || *irq > 15)
+                return -EIO;
+        rdmsr(MSR_PIC_IRQM_LPC, lpc, dummy);
+        if (lpc & (1 << *irq))
+                return -EIO;
 
+        /* All chosen and checked - go for it */
+        if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable))
+                return -EIO;
         if (enable) {
-                val |= (irq & 0x0F) << (offset);
-                val |= (irq & 0x0F) << (offset + 16);
+                zsel = (zsel & ~(0xF << shift)) | (*irq << shift);
+                wrmsr(MSR_PIC_ZSEL_LOW, zsel, dummy);
         }
 
-        wrmsr(MSR_PIC_ZSEL_LOW, val, dummy);
         return 0;
 }
 
@@ -242,7 +263,7 @@ EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer);
 static unsigned int mfgpt_tick_mode = CLOCK_EVT_MODE_SHUTDOWN;
 static u16 mfgpt_event_clock;
 
-static int irq = 7;
+static int irq;
 static int __init mfgpt_setup(char *str)
 {
         get_option(&str, &irq);
@@ -346,7 +367,7 @@ int __init mfgpt_timer_setup(void)
         mfgpt_event_clock = timer;
 
         /* Set up the IRQ on the MFGPT side */
-        if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, irq)) {
+        if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, &irq)) {
                 printk(KERN_ERR "mfgpt-timer:  Could not set up IRQ %d\n", irq);
                 return -EIO;
         }
@@ -374,13 +395,14 @@ int __init mfgpt_timer_setup(void)
                         &mfgpt_clockevent);
 
         printk(KERN_INFO
-               "mfgpt-timer:  registering the MFGPT timer as a clock event.\n");
+               "mfgpt-timer:  Registering MFGPT timer %d as a clock event, using IRQ %d\n",
+               timer, irq);
         clockevents_register_device(&mfgpt_clockevent);
 
         return 0;
 
 err:
-        geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, irq);
+        geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, &irq);
         printk(KERN_ERR
                "mfgpt-timer:  Unable to set up the MFGPT clock source\n");
         return -EIO;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 2c1963b3962..b3fb430725c 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -83,7 +83,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m)
         if (x86_quirks->mpc_oem_bus_info)
                 x86_quirks->mpc_oem_bus_info(m, str);
         else
-                printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str);
+                apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->mpc_busid, str);
 
 #if MAX_MP_BUSSES < 256
         if (m->mpc_busid >= MAX_MP_BUSSES) {
@@ -154,7 +154,7 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m)
 
 static void print_MP_intsrc_info(struct mpc_config_intsrc *m)
 {
-        printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC INT %02x\n",
                 m->mpc_irqtype, m->mpc_irqflag & 3,
                 (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
@@ -163,7 +163,7 @@ static void print_MP_intsrc_info(struct mpc_config_intsrc *m)
 
 static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
 {
-        printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC INT %02x\n",
                 mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
                 (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
@@ -235,7 +235,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m)
 
 static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m)
 {
-        printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC LINT %02x\n",
                 m->mpc_irqtype, m->mpc_irqflag & 3,
                 (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid,
@@ -695,7 +695,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
         unsigned int *bp = phys_to_virt(base);
         struct intel_mp_floating *mpf;
 
-        printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length);
+        apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
+                        bp, length);
         BUILD_BUG_ON(sizeof(*mpf) != 16);
 
         while (length > 0) {
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 9fd80955244..e4393808688 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -131,7 +131,7 @@ static int msr_open(struct inode *inode, struct file *file)
                 ret = -EIO;     /* MSR not supported */
 out:
         unlock_kernel();
-        return 0;
+        return ret;
 }
 
 /*
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ac6d51222e7..abb78a2cc4a 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -114,6 +114,23 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
+static void report_broken_nmi(int cpu, int *prev_nmi_count)
+{
+        printk(KERN_CONT "\n");
+
+        printk(KERN_WARNING
+                "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
+                        cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
+
+        printk(KERN_WARNING
+                "Please report this to bugzilla.kernel.org,\n");
+        printk(KERN_WARNING
+                "and attach the output of the 'dmesg' command.\n");
+
+        per_cpu(wd_enabled, cpu) = 0;
+        atomic_dec(&nmi_active);
+}
+
 int __init check_nmi_watchdog(void)
 {
         unsigned int *prev_nmi_count;
@@ -141,15 +158,8 @@ int __init check_nmi_watchdog(void)
         for_each_online_cpu(cpu) {
                 if (!per_cpu(wd_enabled, cpu))
                         continue;
-                if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
-                        printk(KERN_WARNING "WARNING: CPU#%d: NMI "
-                                "appears to be stuck (%d->%d)!\n",
-                                cpu,
-                                prev_nmi_count[cpu],
-                                get_nmi_count(cpu));
-                        per_cpu(wd_enabled, cpu) = 0;
-                        atomic_dec(&nmi_active);
-                }
+                if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
+                        report_broken_nmi(cpu, prev_nmi_count);
         }
         endflag = 1;
         if (!atomic_read(&nmi_active)) {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index b67a4b1d4ea..218d783ed7a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1350,7 +1350,7 @@ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
  * Function for kdump case. Get the tce tables from first kernel
  * by reading the contents of the base adress register of calgary iommu
  */
-static void get_tce_space_from_tar()
+static void __init get_tce_space_from_tar(void)
 {
         int bus;
         void __iomem *target;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 53bc653ed5c..3b7a1ddcc0b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -95,7 +95,6 @@ static inline void play_dead(void)
 {
         /* This must be done before dead CPU ack */
         cpu_exit_clear();
-        wbinvd();
         mb();
         /* Ack it */
         __get_cpu_var(cpu_state) = CPU_DEAD;
@@ -104,8 +103,8 @@ static inline void play_dead(void)
          * With physical CPU hotplug, we should halt the cpu
          */
         local_irq_disable();
-        while (1)
-                halt();
+        /* mask all interrupts, flush any and all caches, and halt */
+        wbinvd_halt();
 }
 #else
 static inline void play_dead(void)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3560d7f4d74..e04134a80c2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -93,14 +93,13 @@ DECLARE_PER_CPU(int, cpu_state);
 static inline void play_dead(void)
 {
         idle_task_exit();
-        wbinvd();
         mb();
         /* Ack it */
         __get_cpu_var(cpu_state) = CPU_DEAD;
 
         local_irq_disable();
-        while (1)
-                halt();
+        /* mask all interrupts, flush any and all caches, and halt */
+        wbinvd_halt();
 }
 #else
 static inline void play_dead(void)
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 703310a9902..6f50664b2ba 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -20,10 +20,11 @@
 #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define PAE_PGD_ATTR (_PAGE_PRESENT)
 
-/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are
- * used to save some data for jumping back
+/* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
+ * ~ control_page + PAGE_SIZE are used as data storage and stack for
+ * jumping back
  */
-#define DATA(offset)            (PAGE_SIZE/2+(offset))
+#define DATA(offset)            (KEXEC_CONTROL_CODE_MAX_SIZE+(offset))
 
 /* Minimal CPU state */
 #define ESP                     DATA(0x0)
@@ -376,3 +377,6 @@ swap_pages:
         popl    %ebx
         popl    %ebp
         ret
+
+        .globl kexec_control_code_size
+.set kexec_control_code_size, . - relocate_kernel
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2d888586385..a4656adab53 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -445,7 +445,7 @@ static void __init reserve_early_setup_data(void)
  * @size: Size of the crashkernel memory to reserve.
  * Returns the base address on success, and -1ULL on failure.
  */
-unsigned long long find_and_reserve_crashkernel(unsigned long long size)
+unsigned long long __init find_and_reserve_crashkernel(unsigned long long size)
 {
         const unsigned long long alignment = 16<<20;    /* 16M */
         unsigned long long start = 0LL;
@@ -604,6 +604,14 @@ void __init setup_arch(char **cmdline_p)
         early_cpu_init();
         early_ioremap_init();
 
+#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
+        /*
+         * Must be before kernel pagetables are setup
+         * or fixmap area is touched.
+         */
+        vmi_init();
+#endif
+
         ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
         screen_info = boot_params.screen_info;
         edid_info = boot_params.edid_info;
@@ -817,14 +825,6 @@ void __init setup_arch(char **cmdline_p)
         kvmclock_init();
 #endif
 
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
-        /*
-         * Must be after max_low_pfn is determined, and before kernel
-         * pagetables are setup.
-         */
-        vmi_init();
-#endif
-
         paravirt_pagetable_setup_start(swapper_pg_dir);
         paging_init();
         paravirt_pagetable_setup_done(swapper_pg_dir);
@@ -861,12 +861,6 @@ void __init setup_arch(char **cmdline_p)
         init_apic_mappings();
         ioapic_init_mappings();
 
-#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
-        if (def_to_bigsmp)
-                printk(KERN_WARNING "More than 8 CPUs detected and "
-                        "CONFIG_X86_PC cannot handle it.\nUse "
-                        "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
-#endif
         kvm_guest_init();
 
         e820_reserve_resources();
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 87a9c2f28d9..162da796a32 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -100,7 +100,16 @@ static inline int restore_i387(struct _fpstate __user *buf)
                 clts();
                 task_thread_info(current)->status |= TS_USEDFPU;
         }
-        return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+        err = restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+        if (unlikely(err)) {
+                /*
+                 * Encountered an error while doing the restore from the
+                 * user buffer, clear the fpu state.
+                 */
+                clear_fpu(tsk);
+                clear_used_math();
+        }
+        return err;
 }
 
 /*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index d5e19c36204..18a2350deac 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -326,12 +326,16 @@ static void __cpuinit start_secondary(void *unused)
          * for which cpus receive the IPI. Holding this
          * lock helps us to not include this cpu in a currently in progress
          * smp_call_function().
+         *
+         * We need to hold vector_lock so there the set of online cpus
+         * does not change while we are assigning vectors to cpus.  Holding
+         * this lock ensures we don't half assign or remove an irq from a cpu.
          */
         ipi_call_lock_irq();
-#ifdef CONFIG_X86_IO_APIC
-        setup_vector_irq(smp_processor_id());
-#endif
+        lock_vector_lock();
+        __setup_vector_irq(smp_processor_id());
         cpu_set(smp_processor_id(), cpu_online_map);
+        unlock_vector_lock();
         ipi_call_unlock_irq();
         per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 
@@ -752,6 +756,14 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
 }
 
 #ifdef CONFIG_X86_64
+
+/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */
+static void __ref free_bootmem_pda(struct x8664_pda *oldpda)
+{
+        if (!after_bootmem)
+                free_bootmem((unsigned long)oldpda, sizeof(*oldpda));
+}
+
 /*
  * Allocate node local memory for the AP pda.
  *
@@ -780,8 +792,7 @@ int __cpuinit get_local_pda(int cpu)
 
         if (oldpda) {
                 memcpy(newpda, oldpda, size);
-                if (!after_bootmem)
-                        free_bootmem((unsigned long)oldpda, size);
+                free_bootmem_pda(oldpda);
         }
 
         newpda->in_bootmem = 0;
@@ -1044,6 +1055,34 @@ static __init void disable_smp(void)
 static int __init smp_sanity_check(unsigned max_cpus)
 {
         preempt_disable();
+
+#if defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
+        if (def_to_bigsmp && nr_cpu_ids > 8) {
+                unsigned int cpu;
+                unsigned nr;
+
+                printk(KERN_WARNING
+                       "More than 8 CPUs detected - skipping them.\n"
+                       "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n");
+
+                nr = 0;
+                for_each_present_cpu(cpu) {
+                        if (nr >= 8)
+                                cpu_clear(cpu, cpu_present_map);
+                        nr++;
+                }
+
+                nr = 0;
+                for_each_possible_cpu(cpu) {
+                        if (nr >= 8)
+                                cpu_clear(cpu, cpu_possible_map);
+                        nr++;
+                }
+
+                nr_cpu_ids = 8;
+        }
+#endif
+
         if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
                 printk(KERN_WARNING "weird, boot CPU (#%d) not listed"
                                     "by the BIOS.\n", hard_smp_processor_id());
@@ -1333,7 +1372,9 @@ int __cpu_disable(void)
         remove_siblinginfo(cpu);
 
         /* It's now safe to remove this processor from the online map */
+        lock_vector_lock();
         remove_cpu_from_maps(cpu);
+        unlock_vector_lock();
         fixup_irqs(cpu_online_map);
         return 0;
 }
@@ -1367,17 +1408,3 @@ void __cpu_die(unsigned int cpu)
         BUG();
 }
 #endif
-
-/*
- * If the BIOS enumerates physical processors before logical,
- * maxcpus=N at enumeration-time can be used to disable HT.
- */
-static int __init parse_maxcpus(char *arg)
-{
-        extern unsigned int maxcpus;
-
-        if (arg)
-                maxcpus = simple_strtoul(arg, NULL, 0);
-        return 0;
-}
-early_param("maxcpus", parse_maxcpus);
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 99941b37eca..397e309839d 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -8,18 +8,21 @@
 DEFINE_PER_CPU(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-/* Initialize the CPU's GDT.  This is either the boot CPU doing itself
-   (still using the master per-cpu area), or a CPU doing it for a
-   secondary which will soon come up. */
+/*
+ * Initialize the CPU's GDT.  This is either the boot CPU doing itself
+ * (still using the master per-cpu area), or a CPU doing it for a
+ * secondary which will soon come up.
+ */
 __cpuinit void init_gdt(int cpu)
 {
-        struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+        struct desc_struct gdt;
 
-        pack_descriptor(&gdt[GDT_ENTRY_PERCPU],
-                        __per_cpu_offset[cpu], 0xFFFFF,
+        pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF,
                         0x2 | DESCTYPE_S, 0x8);
+        gdt.s = 1;
 
-        gdt[GDT_ENTRY_PERCPU].s = 1;
+        write_gdt_entry(get_cpu_gdt_table(cpu),
+                        GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
 
         per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
         per_cpu(cpu_number, cpu) = cpu;
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 5df5d2e97ec..d4fb6c15dc4 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -1136,7 +1136,14 @@ asmlinkage void math_state_restore(void)
         }
 
         clts();                         /* Allow maths ops (or we recurse) */
-        restore_fpu_checking(&me->thread.xstate->fxsave);
+        /*
+         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+         */
+        if (unlikely(restore_fpu_checking(&me->thread.xstate->fxsave))) {
+                stts();
+                force_sig(SIGSEGV, me);
+                return;
+        }
         task_thread_info(me)->status |= TS_USEDFPU;
         me->fpu_counter++;
 }
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 3059eb45a91..61a97e616f7 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -170,8 +170,6 @@ static int __init visws_get_smp_config(unsigned int early)
         return 1;
 }
 
-extern unsigned int __cpuinitdata maxcpus;
-
 /*
  * The Visual Workstation is Intel MP compliant in the hardware
  * sense, but it doesn't have a BIOS(-configuration table).
@@ -230,8 +228,8 @@ static int __init visws_find_smp_config(unsigned int reserve)
                 ncpus = CO_CPU_MAX;
         }
 
-        if (ncpus > maxcpus)
-                ncpus = maxcpus;
+        if (ncpus > setup_max_cpus)
+                ncpus = setup_max_cpus;
 
 #ifdef CONFIG_X86_LOCAL_APIC
         smp_found_config = 1;
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 0a1b1a9d922..6ca515d6db5 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -37,6 +37,7 @@
 #include <asm/timer.h>
 #include <asm/vmi_time.h>
 #include <asm/kmap_types.h>
+#include <asm/setup.h>
 
 /* Convenient for calling VMI functions indirectly in the ROM */
 typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
@@ -683,7 +684,7 @@ void vmi_bringup(void)
 {
         /* We must establish the lowmem mapping for MMU ops to work */
         if (vmi_ops.set_linear_mapping)
-                vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, max_low_pfn, 0);
+                vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0);
 }
 
 /*
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index cdb2363697d..af5bdad8460 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -209,3 +209,11 @@ SECTIONS
 
   DWARF_DEBUG
 }
+
+#ifdef CONFIG_KEXEC
+/* Link time checks */
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+       "kexec control code size is too big")
+#endif
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 2977ea37791..dfb932dcf13 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,6 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-            pat.o pgtable.o
+            pat.o pgtable.o gup.o
 
-obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o
 obj-$(CONFIG_X86_32)            += pgtable_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 08a20e6a15c..5f47fde5fa9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -60,7 +60,7 @@ static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-int direct_gbpages __meminitdata
+int direct_gbpages
 #ifdef CONFIG_DIRECT_GBPAGES
                                 = 1
 #endif
@@ -88,7 +88,11 @@ early_param("gbpages", parse_direct_gbpages_on);
 
 int after_bootmem;
 
-static __init void *spp_getpage(void)
+/*
+ * NOTE: This function is marked __ref because it calls __init function
+ * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
+ */
+static __ref void *spp_getpage(void)
 {
         void *ptr;
 
@@ -314,6 +318,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 {
         unsigned long pages = 0;
         unsigned long last_map_addr = end;
+        unsigned long start = address;
 
         int i = pmd_index(address);
 
@@ -334,6 +339,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                         if (!pmd_large(*pmd))
                                 last_map_addr = phys_pte_update(pmd, address,
                                                                  end);
+                        /* Count entries we're using from level2_ident_pgt */
+                        if (start == 0)
+                                pages++;
                         continue;
                 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 016f335bbee..6ba6f889c79 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -170,7 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
         phys_addr &= PAGE_MASK;
         size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
-        retval = reserve_memtype(phys_addr, phys_addr + size,
+        retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
                                                 prot_val, &new_prot_val);
         if (retval) {
                 pr_debug("Warning: reserve_memtype returned %d\n", retval);
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 0dcd42eb94e..d4aa503caaa 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -221,8 +221,7 @@ static int pageattr_test(void)
         failed += print_split(&sc);
 
         if (failed) {
-                printk(KERN_ERR "NOT PASSED. Please report.\n");
-                WARN_ON(1);
+                WARN(1, KERN_ERR "NOT PASSED. Please report.\n");
                 return -EINVAL;
         } else {
                 if (print)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 0d254adcc82..1b87b76e2d0 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -55,13 +55,19 @@ static void split_page_count(int level)
 
 int arch_report_meminfo(char *page)
 {
-        int n = sprintf(page, "DirectMap4k:  %8lu\n"
-                        "DirectMap2M:  %8lu\n",
-                        direct_pages_count[PG_LEVEL_4K],
-                        direct_pages_count[PG_LEVEL_2M]);
+        int n = sprintf(page, "DirectMap4k:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+        n += sprintf(page + n, "DirectMap2M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+        n += sprintf(page + n, "DirectMap4M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
 #ifdef CONFIG_X86_64
-        n += sprintf(page + n, "DirectMap1G:  %8lu\n",
-                     direct_pages_count[PG_LEVEL_1G]);
+        if (direct_gbpages)
+                n += sprintf(page + n, "DirectMap1G:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
         return n;
 }
@@ -592,10 +598,9 @@ repeat:
         if (!pte_val(old_pte)) {
                 if (!primary)
                         return 0;
-                printk(KERN_WARNING "CPA: called for zero pte. "
+                WARN(1, KERN_WARNING "CPA: called for zero pte. "
                        "vaddr = %lx cpa->vaddr = %lx\n", address,
                        cpa->vaddr);
-                WARN_ON(1);
                 return -EINVAL;
         }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 557b2abceef..d50302774fe 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
         unsigned long addr;
         int i;
 
+        if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
+                return;
+
         pud = pud_offset(pgd, 0);
 
         for (addr = i = 0; i < PREALLOCATED_PMDS;
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 1eb2973a301..16ae70fc57e 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -178,7 +178,7 @@ void acpi_numa_arch_fixup(void)
  * start of the node, and that the current "end" address is after
  * the previous one.
  */
-static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
+static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
 {
         /*
          * Only add present memory as told by the e820.
@@ -189,10 +189,10 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
         if (memory_chunk->start_pfn >= max_pfn) {
                 printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
                         memory_chunk->start_pfn, memory_chunk->end_pfn);
-                return;
+                return -1;
         }
         if (memory_chunk->nid != nid)
-                return;
+                return -1;
 
         if (!node_has_online_mem(nid))
                 node_start_pfn[nid] = memory_chunk->start_pfn;
@@ -202,6 +202,8 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
 
         if (node_end_pfn[nid] < memory_chunk->end_pfn)
                 node_end_pfn[nid] = memory_chunk->end_pfn;
+
+        return 0;
 }
 
 int __init get_memcfg_from_srat(void)
@@ -259,7 +261,9 @@ int __init get_memcfg_from_srat(void)
                 printk(KERN_DEBUG
                         "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
                        j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
-                node_read_chunk(chunk->nid, chunk);
+                if (node_read_chunk(chunk->nid, chunk))
+                        continue;
+
                 e820_register_active_regions(chunk->nid, chunk->start_pfn,
                                              min(chunk->end_pfn, max_pfn));
         }
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 23faaa890ff..2bd5c53f638 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -365,7 +365,7 @@ static void __init pci_mmcfg_reject_broken(int early)
         return;
 
 reject:
-        printk(KERN_ERR "PCI: Not using MMCONFIG.\n");
+        printk(KERN_INFO "PCI: Not using MMCONFIG.\n");
         pci_mmcfg_arch_free();
         kfree(pci_mmcfg_config);
         pci_mmcfg_config = NULL;
diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c
index 7dc5d5cf50a..d3e083dea72 100644
--- a/arch/x86/power/cpu_32.c
+++ b/arch/x86/power/cpu_32.c
@@ -45,7 +45,7 @@ static void __save_processor_state(struct saved_context *ctxt)
         ctxt->cr0 = read_cr0();
         ctxt->cr2 = read_cr2();
         ctxt->cr3 = read_cr3();
-        ctxt->cr4 = read_cr4();
+        ctxt->cr4 = read_cr4_safe();
 }
 
 /* Needed by apm.c */
@@ -98,7 +98,9 @@ static void __restore_processor_state(struct saved_context *ctxt)
         /*
          * control registers
          */
-        write_cr4(ctxt->cr4);
+        /* cr4 was introduced in the Pentium CPU */
+        if (ctxt->cr4)
+                write_cr4(ctxt->cr4);
         write_cr3(ctxt->cr3);
         write_cr2(ctxt->cr2);
         write_cr0(ctxt->cr0);
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index b95aa6cfe3c..4fc7e872c85 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -28,9 +28,9 @@ ENTRY(swsusp_arch_suspend)
         ret
 
 ENTRY(restore_image)
-        movl    resume_pg_dir, %ecx
-        subl    $__PAGE_OFFSET, %ecx
-        movl    %ecx, %cr3
+        movl    resume_pg_dir, %eax
+        subl    $__PAGE_OFFSET, %eax
+        movl    %eax, %cr3
 
         movl    restore_pblist, %edx
         .p2align 4,,7
@@ -52,17 +52,21 @@ copy_loop:
 
 done:
         /* go back to the original page tables */
-        movl    $swapper_pg_dir, %ecx
-        subl    $__PAGE_OFFSET, %ecx
-        movl    %ecx, %cr3
+        movl    $swapper_pg_dir, %eax
+        subl    $__PAGE_OFFSET, %eax
+        movl    %eax, %cr3
         /* Flush TLB, including "global" things (vmalloc) */
-        movl    mmu_cr4_features, %eax
-        movl    %eax, %edx
+        movl    mmu_cr4_features, %ecx
+        jecxz   1f      # cr4 Pentium and higher, skip if zero
+        movl    %ecx, %edx
         andl    $~(1<<7), %edx;  # PGE
         movl    %edx, %cr4;  # turn off PGE
-        movl    %cr3, %ecx;  # flush TLB
-        movl    %ecx, %cr3
-        movl    %eax, %cr4;  # turn PGE back on
+1:
+        movl    %cr3, %eax;  # flush TLB
+        movl    %eax, %cr3
+        jecxz   1f      # cr4 Pentium and higher, skip if zero
+        movl    %ecx, %cr4;  # turn PGE back on
+1:
 
         movl saved_context_esp, %esp
         movl saved_context_ebp, %ebp