37 files changed, 279 insertions, 323 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 743642f1a36c..7338ef2218bc 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)    += sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)    += syscall_64.o vsyscall_64.o
 obj-y                   += bootflag.o e820.o
-obj-y                   += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
+obj-y                   += pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y                   += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y                   += tsc.o io_delay.o rtc.o
 obj-y                   += pci-iommu_table.o
@@ -55,6 +55,7 @@ obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)    += tls.o
 obj-y                           += step.o
 obj-$(CONFIG_INTEL_TXT)         += tboot.o
+obj-$(CONFIG_ISA_DMA_API)       += i8237.o
 obj-$(CONFIG_STACKTRACE)        += stacktrace.o
 obj-y                           += cpu/
 obj-y                           += acpi/
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 4572c58e66d5..ff93bc1b09c3 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -25,12 +25,12 @@ static char temp_stack[4096];
 #endif
 
 /**
- * acpi_save_state_mem - save kernel state
+ * acpi_suspend_lowlevel - save kernel state
  *
  * Create an identity mapped page table and copy the wakeup routine to
  * low memory.
  */
-int acpi_save_state_mem(void)
+int acpi_suspend_lowlevel(void)
 {
         struct wakeup_header *header;
         /* address in low memory of the wakeup routine. */
@@ -96,16 +96,10 @@ int acpi_save_state_mem(void)
        saved_magic = 0x123456789abcdef0L;
 #endif /* CONFIG_64BIT */
 
+        do_suspend_lowlevel();
         return 0;
 }
 
-/*
- * acpi_restore_state - undo effects of acpi_save_state_mem
- */
-void acpi_restore_state_mem(void)
-{
-}
-
 static int __init acpi_sleep_setup(char *str)
 {
         while ((str != NULL) && (*str != '\0')) {
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 86ba1c87165b..416d4be13fef 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -11,3 +11,5 @@ extern int wakeup_pmode_return;
 
 extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 extern void wakeup_long64(void);
+
+extern void do_suspend_lowlevel(void);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 6e11c8134158..246d727b65b7 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -21,7 +21,7 @@
 #include <linux/acpi.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/msi.h>
 #include <asm/pci-direct.h>
@@ -1260,7 +1260,7 @@ static void disable_iommus(void)
  * disable suspend until real resume implemented
  */
 
-static int amd_iommu_resume(struct sys_device *dev)
+static void amd_iommu_resume(void)
 {
         struct amd_iommu *iommu;
 
@@ -1276,11 +1276,9 @@ static int amd_iommu_resume(struct sys_device *dev)
          */
         amd_iommu_flush_all_devices();
         amd_iommu_flush_all_domains();
-
-        return 0;
 }
 
-static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
+static int amd_iommu_suspend(void)
 {
         /* disable IOMMUs to go out of the way for BIOS */
         disable_iommus();
@@ -1288,17 +1286,11 @@ static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
         return 0;
 }
 
-static struct sysdev_class amd_iommu_sysdev_class = {
-        .name = "amd_iommu",
+static struct syscore_ops amd_iommu_syscore_ops = {
         .suspend = amd_iommu_suspend,
         .resume = amd_iommu_resume,
 };
 
-static struct sys_device device_amd_iommu = {
-        .id = 0,
-        .cls = &amd_iommu_sysdev_class,
-};
-
 /*
  * This is the core init function for AMD IOMMU hardware in the system.
  * This function is called from the generic x86 DMA layer initialization
@@ -1415,14 +1407,6 @@ static int __init amd_iommu_init(void)
                 goto free;
         }
 
-        ret = sysdev_class_register(&amd_iommu_sysdev_class);
-        if (ret)
-                goto free;
-
-        ret = sysdev_register(&device_amd_iommu);
-        if (ret)
-                goto free;
-
         ret = amd_iommu_init_devices();
         if (ret)
                 goto free;
@@ -1441,6 +1425,8 @@ static int __init amd_iommu_init(void)
 
         amd_iommu_init_notifier();
 
+        register_syscore_ops(&amd_iommu_syscore_ops);
+
         if (iommu_pass_through)
                 goto out;
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6801959a8b2a..4c39baa8facc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,7 +21,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 EXPORT_SYMBOL(amd_nb_misc_ids);
 
 static struct pci_device_id amd_nb_link_ids[] = {
-        { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_LINK) },
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
         {}
 };
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 1293c709ee85..cd1ffed4ee22 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -316,7 +316,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
         irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
         irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
         /* APB timer irqs are set up as mp_irqs, timer is edge type */
-        __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+        __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge");
 
         if (system_state == SYSTEM_BOOTING) {
                 if (request_irq(adev->irq, apbt_interrupt_handler,
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4962a7..73fb469908c6 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@ out:
                  * Don't enable translation yet but enable GART IO and CPU
                  * accesses and set DISTLBWALKPRB since GART table memory is UC.
                  */
-                u32 ctl = DISTLBWALKPRB | aper_order << 1;
+                u32 ctl = aper_order << 1;
 
                 bus = amd_nb_bus_dev_ranges[i].bus;
                 dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 966673f44141..fabf01eff771 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -24,7 +24,7 @@
 #include <linux/ftrace.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/timex.h>
 #include <linux/dmar.h>
@@ -2046,7 +2046,7 @@ static struct {
         unsigned int apic_thmr;
 } apic_pm_state;
 
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+static int lapic_suspend(void)
 {
         unsigned long flags;
         int maxlvt;
@@ -2084,23 +2084,21 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
         return 0;
 }
 
-static int lapic_resume(struct sys_device *dev)
+static void lapic_resume(void)
 {
         unsigned int l, h;
         unsigned long flags;
-        int maxlvt;
-        int ret = 0;
+        int maxlvt, ret;
         struct IO_APIC_route_entry **ioapic_entries = NULL;
 
         if (!apic_pm_state.active)
-                return 0;
+                return;
 
         local_irq_save(flags);
         if (intr_remapping_enabled) {
                 ioapic_entries = alloc_ioapic_entries();
                 if (!ioapic_entries) {
                         WARN(1, "Alloc ioapic_entries in lapic resume failed.");
-                        ret = -ENOMEM;
                         goto restore;
                 }
 
@@ -2162,8 +2160,6 @@ static int lapic_resume(struct sys_device *dev)
         }
 restore:
         local_irq_restore(flags);
-
-        return ret;
 }
 
 /*
@@ -2171,17 +2167,11 @@ restore:
  * are needed on every CPU up until machine_halt/restart/poweroff.
  */
 
-static struct sysdev_class lapic_sysclass = {
-        .name           = "lapic",
+static struct syscore_ops lapic_syscore_ops = {
         .resume         = lapic_resume,
         .suspend        = lapic_suspend,
 };
 
-static struct sys_device device_lapic = {
-        .id     = 0,
-        .cls    = &lapic_sysclass,
-};
-
 static void __cpuinit apic_pm_activate(void)
 {
         apic_pm_state.active = 1;
@@ -2189,16 +2179,11 @@ static void __cpuinit apic_pm_activate(void)
 
 static int __init init_lapic_sysfs(void)
 {
-        int error;
-
-        if (!cpu_has_apic)
-                return 0;
         /* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+        if (cpu_has_apic)
+                register_syscore_ops(&lapic_syscore_ops);
 
-        error = sysdev_class_register(&lapic_sysclass);
-        if (!error)
-                error = sysdev_register(&device_lapic);
-        return error;
+        return 0;
 }
 
 /* local apic needs to resume before other devices access its registers. */
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c4e557a1ebb6..5260fe91bcb6 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -16,6 +16,7 @@
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
 #include <linux/module.h>
+#include <linux/delay.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 180ca240e03c..68df09bba92e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -30,7 +30,7 @@
 #include <linux/compiler.h>
 #include <linux/acpi.h>
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/msi.h>
 #include <linux/htirq.h>
 #include <linux/freezer.h>
@@ -2918,89 +2918,84 @@ static int __init io_apic_bug_finalize(void)
 
 late_initcall(io_apic_bug_finalize);
 
-struct sysfs_ioapic_data {
-        struct sys_device dev;
-        struct IO_APIC_route_entry entry[0];
-};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct IO_APIC_route_entry *ioapic_saved_data[MAX_IO_APICS];
 
-static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
+static void suspend_ioapic(int ioapic_id)
 {
-        struct IO_APIC_route_entry *entry;
-        struct sysfs_ioapic_data *data;
+        struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
         int i;
 
-        data = container_of(dev, struct sysfs_ioapic_data, dev);
-        entry = data->entry;
-        for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
-                *entry = ioapic_read_entry(dev->id, i);
+        if (!saved_data)
+                return;
+
+        for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+                saved_data[i] = ioapic_read_entry(ioapic_id, i);
+}
+
+static int ioapic_suspend(void)
+{
+        int ioapic_id;
+
+        for (ioapic_id = 0; ioapic_id < nr_ioapics; ioapic_id++)
+                suspend_ioapic(ioapic_id);
 
         return 0;
 }
 
-static int ioapic_resume(struct sys_device *dev)
+static void resume_ioapic(int ioapic_id)
 {
-        struct IO_APIC_route_entry *entry;
-        struct sysfs_ioapic_data *data;
+        struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
         unsigned long flags;
         union IO_APIC_reg_00 reg_00;
         int i;
 
-        data = container_of(dev, struct sysfs_ioapic_data, dev);
-        entry = data->entry;
+        if (!saved_data)
+                return;
 
         raw_spin_lock_irqsave(&ioapic_lock, flags);
-        reg_00.raw = io_apic_read(dev->id, 0);
-        if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
-                reg_00.bits.ID = mp_ioapics[dev->id].apicid;
-                io_apic_write(dev->id, 0, reg_00.raw);
+        reg_00.raw = io_apic_read(ioapic_id, 0);
+        if (reg_00.bits.ID != mp_ioapics[ioapic_id].apicid) {
+                reg_00.bits.ID = mp_ioapics[ioapic_id].apicid;
+                io_apic_write(ioapic_id, 0, reg_00.raw);
         }
         raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-        for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
-                ioapic_write_entry(dev->id, i, entry[i]);
+        for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+                ioapic_write_entry(ioapic_id, i, saved_data[i]);
+}
 
-        return 0;
+static void ioapic_resume(void)
+{
+        int ioapic_id;
+
+        for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--)
+                resume_ioapic(ioapic_id);
 }
 
-static struct sysdev_class ioapic_sysdev_class = {
-        .name = "ioapic",
+static struct syscore_ops ioapic_syscore_ops = {
         .suspend = ioapic_suspend,
         .resume = ioapic_resume,
 };
 
-static int __init ioapic_init_sysfs(void)
+static int __init ioapic_init_ops(void)
 {
-        struct sys_device * dev;
-        int i, size, error;
+        int i;
 
-        error = sysdev_class_register(&ioapic_sysdev_class);
-        if (error)
-                return error;
+        for (i = 0; i < nr_ioapics; i++) {
+                unsigned int size;
 
-        for (i = 0; i < nr_ioapics; i++ ) {
-                size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+                size = nr_ioapic_registers[i]
                         * sizeof(struct IO_APIC_route_entry);
-                mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
-                if (!mp_ioapic_data[i]) {
-                        printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
-                        continue;
-                }
-                dev = &mp_ioapic_data[i]->dev;
-                dev->id = i;
-                dev->cls = &ioapic_sysdev_class;
-                error = sysdev_register(dev);
-                if (error) {
-                        kfree(mp_ioapic_data[i]);
-                        mp_ioapic_data[i] = NULL;
-                        printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
-                        continue;
-                }
+                ioapic_saved_data[i] = kzalloc(size, GFP_KERNEL);
+                if (!ioapic_saved_data[i])
+                        pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
         }
 
+        register_syscore_ops(&ioapic_syscore_ops);
+
         return 0;
 }
 
-device_initcall(ioapic_init_sysfs);
+device_initcall(ioapic_init_ops);
 
 /*
  * Dynamic irq allocate and deallocation
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 3c289281394c..33b10a0fc095 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -23,6 +23,8 @@
 #include <linux/io.h>
 #include <linux/pci.h>
 #include <linux/kdebug.h>
+#include <linux/delay.h>
+#include <linux/crash_dump.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,6 +36,7 @@
 #include <asm/ipi.h>
 #include <asm/smp.h>
 #include <asm/x86_init.h>
+#include <asm/emergency-restart.h>
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
@@ -810,4 +813,11 @@ void __init uv_system_init(void)
 
         /* register Legacy VGA I/O redirection handler */
         pci_register_set_vga_state(uv_set_vga_state);
+
+        /*
+         * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
+         * EFI is not enabled in the kdump kernel.
+         */
+        if (is_kdump_kernel())
+                reboot_type = BOOT_ACPI;
 }
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0b4be431c620..adee12e0da1f 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
 #include <linux/acpi.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -1238,6 +1239,7 @@ static int suspend(int vetoable)
 
         local_irq_disable();
         sysdev_suspend(PMSG_SUSPEND);
+        syscore_suspend();
 
         local_irq_enable();
 
@@ -1255,6 +1257,7 @@ static int suspend(int vetoable)
                 apm_error("suspend", err);
         err = (err == APM_SUCCESS) ? 0 : -EIO;
 
+        syscore_resume();
         sysdev_resume();
         local_irq_enable();
 
@@ -1280,6 +1283,7 @@ static void standby(void)
 
         local_irq_disable();
         sysdev_suspend(PMSG_SUSPEND);
+        syscore_suspend();
         local_irq_enable();
 
         err = set_system_power_state(APM_STATE_STANDBY);
@@ -1287,6 +1291,7 @@ static void standby(void)
                 apm_error("standby", err);
 
         local_irq_disable();
+        syscore_resume();
         sysdev_resume();
         local_irq_enable();
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3ecece0217ef..3532d3bf8105 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         /* As a rule processors have APIC timer running in deep C states */
         if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
                 set_cpu_cap(c, X86_FEATURE_ARAT);
+
+        /*
+         * Disable GART TLB Walk Errors on Fam10h. We do this here
+         * because this is always needed when GART is enabled, even in a
+         * kernel which has no MCE support built in.
+         */
+        if (c->x86 == 0x10) {
+                /*
+                 * BIOS should disable GartTlbWlk Errors themself. If
+                 * it doesn't do it here as suggested by the BKDG.
+                 *
+                 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+                 */
+                u64 mask;
+
+                rdmsrl(MSR_AMD64_MCx_MASK(4), mask);
+                mask |= (1 << 10);
+                wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+        }
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 8209472b27a5..83930deec3c6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m)
 ssize_t apei_read_mce(struct mce *m, u64 *record_id)
 {
         struct cper_mce_record rcd;
-        ssize_t len;
-
-        len = erst_read_next(&rcd.hdr, sizeof(rcd));
-        if (len <= 0)
-                return len;
-        /* Can not skip other records in storage via ERST unless clear them */
-        else if (len != sizeof(rcd) ||
-                 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
-                if (printk_ratelimit())
-                        pr_warning(
-                        "MCE-APEI: Can not skip the unknown record in ERST");
-                return -EIO;
-        }
-
+        int rc, pos;
+
+        rc = erst_get_record_id_begin(&pos);
+        if (rc)
+                return rc;
+retry:
+        rc = erst_get_record_id_next(&pos, record_id);
+        if (rc)
+                goto out;
+        /* no more record */
+        if (*record_id == APEI_ERST_INVALID_RECORD_ID)
+                goto out;
+        rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd));
+        /* someone else has cleared the record, try next one */
+        if (rc == -ENOENT)
+                goto retry;
+        else if (rc < 0)
+                goto out;
+        /* try to skip other type records in storage */
+        else if (rc != sizeof(rcd) ||
+                 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+                goto retry;
         memcpy(m, &rcd.mce, sizeof(*m));
-        *record_id = rcd.hdr.record_id;
+        rc = sizeof(*m);
+out:
+        erst_get_record_id_end();
 
-        return sizeof(*m);
+        return rc;
 }
 
 /* Check whether there is record in ERST */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ab1122998dba..3385ea26f684 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -21,6 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/string.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
@@ -1625,7 +1626,7 @@ out:
 static unsigned int mce_poll(struct file *file, poll_table *wait)
 {
         poll_wait(file, &mce_wait, wait);
-        if (rcu_dereference_check_mce(mcelog.next))
+        if (rcu_access_index(mcelog.next))
                 return POLLIN | POLLRDNORM;
         if (!mce_apei_read_done && apei_check_mce())
                 return POLLIN | POLLRDNORM;
@@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void)
         return 0;
 }
 
-static int mce_suspend(struct sys_device *dev, pm_message_t state)
+static int mce_suspend(void)
 {
         return mce_disable_error_reporting();
 }
 
-static int mce_shutdown(struct sys_device *dev)
+static void mce_shutdown(void)
 {
-        return mce_disable_error_reporting();
+        mce_disable_error_reporting();
 }
 
 /*
@@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev)
  * Only one CPU is active at this time, the others get re-added later using
  * CPU hotplug:
  */
-static int mce_resume(struct sys_device *dev)
+static void mce_resume(void)
 {
         __mcheck_cpu_init_generic();
         __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
-
-        return 0;
 }
 
+static struct syscore_ops mce_syscore_ops = {
+        .suspend        = mce_suspend,
+        .shutdown       = mce_shutdown,
+        .resume         = mce_resume,
+};
+
 static void mce_cpu_restart(void *data)
 {
         del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all)
 }
 
 static struct sysdev_class mce_sysclass = {
-        .suspend        = mce_suspend,
-        .shutdown       = mce_shutdown,
-        .resume         = mce_resume,
         .name           = "machinecheck",
 };
 
@@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void)
                         return err;
         }
 
+        register_syscore_ops(&mce_syscore_ops);
         register_hotcpu_notifier(&mce_cpu_notifier);
         misc_register(&mce_log_device);
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index bebabec5b448..929739a653d1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -45,6 +45,7 @@
 #include <linux/cpu.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
@@ -292,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
         /*
          * HACK!
-         * We use this same function to initialize the mtrrs on boot.
-         * The state of the boot cpu's mtrrs has been saved, and we want
-         * to replicate across all the APs.
-         * If we're doing that @reg is set to something special...
+         *
+         * We use this same function to initialize the mtrrs during boot,
+         * resume, runtime cpu online and on an explicit request to set a
+         * specific MTRR.
+         *
+         * During boot or suspend, the state of the boot cpu's mtrrs has been
+         * saved, and we want to replicate that across all the cpus that come
+         * online (either at the end of boot or resume or during a runtime cpu
+         * online). If we're doing that, @reg is set to something special and on
+         * this cpu we still do mtrr_if->set_all(). During boot/resume, this
+         * is unnecessary if at this point we are still on the cpu that started
+         * the boot/resume sequence. But there is no guarantee that we are still
+         * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be
+         * sure that we are in sync with everyone else.
          */
         if (reg != ~0U)
                 mtrr_if->set(reg, base, size, type);
-        else if (!mtrr_aps_delayed_init)
+        else
                 mtrr_if->set_all();
 
         /* Wait for the others */
@@ -630,7 +641,7 @@ struct mtrr_value {
 
 static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES];
 
-static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
+static int mtrr_save(void)
 {
         int i;
 
@@ -642,7 +653,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
         return 0;
 }
 
-static int mtrr_restore(struct sys_device *sysdev)
+static void mtrr_restore(void)
 {
         int i;
 
@@ -653,12 +664,11 @@ static int mtrr_restore(struct sys_device *sysdev)
                                     mtrr_value[i].ltype);
                 }
         }
-        return 0;
 }
 
 
 
-static struct sysdev_driver mtrr_sysdev_driver = {
+static struct syscore_ops mtrr_syscore_ops = {
         .suspend        = mtrr_save,
         .resume         = mtrr_restore,
 };
@@ -839,7 +849,7 @@ static int __init mtrr_init_finialize(void)
          * TBD: is there any system with such CPU which supports
          * suspend/resume? If no, we should remove the code.
          */
-        sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver);
+        register_syscore_ops(&mtrr_syscore_ops);
 
         return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87eab4a27dfc..632e5dc9c9c0 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -500,12 +500,17 @@ static bool check_hw_exists(void)
         return true;
 
 bios_fail:
-        printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+        /*
+         * We still allow the PMU driver to operate:
+         */
+        printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
         printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
-        return false;
+
+        return true;
 
 msr_fail:
         printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+
         return false;
 }
 
@@ -581,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
                         return -EOPNOTSUPP;
         }
 
+        /*
+         * Do not allow config1 (extended registers) to propagate,
+         * there's no sane user-space generalization yet:
+         */
         if (attr->type == PERF_TYPE_RAW)
-                return x86_pmu_extra_regs(event->attr.config, event);
+                return 0;
 
         if (attr->type == PERF_TYPE_HW_CACHE)
                 return set_ext_hw_attr(hwc, event);
@@ -912,7 +921,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
                 hwc->event_base = 0;
         } else if (hwc->idx >= X86_PMC_IDX_FIXED) {
                 hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-                hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
+                hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
         } else {
                 hwc->config_base = x86_pmu_config_addr(hwc->idx);
                 hwc->event_base  = x86_pmu_event_addr(hwc->idx);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62bbd774..cf4e369cea67 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(L1D) ] = {
         [ C(OP_READ) ] = {
                 [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-                [ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+                [ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
         },
         [ C(OP_WRITE) ] = {
                 [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
  *
  * Exceptions:
  *
+ * 0x000        FP      PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x003        FP      PERF_CTL[3]
+ * 0x004        FP      PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x00B        FP      PERF_CTL[3]
  * 0x00D        FP      PERF_CTL[3]
  * 0x023        DE      PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x0DF        LS      PERF_CTL[5:0]
  * 0x1D6        EX      PERF_CTL[5:0]
  * 0x1D8        EX      PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
-        unsigned int event_code = amd_get_event_code(&event->hw);
+        struct hw_perf_event *hwc = &event->hw;
+        unsigned int event_code = amd_get_event_code(hwc);
 
         switch (event_code & AMD_EVENT_TYPE_MASK) {
         case AMD_EVENT_FP:
                 switch (event_code) {
+                case 0x000:
+                        if (!(hwc->config & 0x0000F000ULL))
+                                break;
+                        if (!(hwc->config & 0x00000F00ULL))
+                                break;
+                        return &amd_f15_PMC3;
+                case 0x004:
+                        if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+                                break;
+                        return &amd_f15_PMC3;
                 case 0x003:
                 case 0x00B:
                 case 0x00D:
                         return &amd_f15_PMC3;
-                default:
-                        return &amd_f15_PMC53;
                 }
+                return &amd_f15_PMC53;
         case AMD_EVENT_LS:
         case AMD_EVENT_DC:
         case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2cee1da..43fa20b13817 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 {
  [ C(L1D) ] = {
         [ C(OP_READ) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-                [ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+                [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+                [ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
         },
         [ C(OP_WRITE) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-                [ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+                [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+                [ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
         },
         [ C(OP_PREFETCH) ] = {
                 [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
@@ -1425,6 +1425,7 @@ static __init int intel_pmu_init(void)
 
         case 37: /* 32 nm nehalem, "Clarkdale" */
         case 44: /* 32 nm nehalem, "Gulftown" */
+        case 47: /* 32 nm Xeon E7 */
                 memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
                        sizeof(hw_cache_event_ids));
                 memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 0811f5ebfba6..d1f77e2934a1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -777,6 +777,7 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
          * the counter has reached zero value and continued counting before
          * real NMI signal was received:
          */
+        rdmsrl(hwc->event_base, v);
         if (!(v & ARCH_P4_UNFLAGGED_BIT))
                 return 1;
 
@@ -946,7 +947,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
                 if (!x86_perf_event_set_period(event))
                         continue;
                 if (perf_event_overflow(event, 1, &data, regs))
-                        p4_pmu_disable_event(event);
+                        x86_pmu_stop(event, 0);
         }
 
         if (handled) {
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index d5cd13945d5a..642f75a68cd5 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -14,9 +14,6 @@
 
 static void *kdump_buf_page;
 
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
 static inline bool is_crashed_pfn_valid(unsigned long pfn)
 {
 #ifndef CONFIG_X86_PAE
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 994828899e09..afa64adb75ee 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -10,9 +10,6 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 7a8cebc9ff29..706a9fb46a58 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -65,12 +65,10 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
                 return 0;
         ret = ih->xlate(ih, intspec, intsize, &virq, &type);
         if (ret)
-                return ret;
+                return 0;
         if (type == IRQ_TYPE_NONE)
                 return virq;
-        /* set the mask if it is different from current */
-        if (type == (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
-                set_irq_type(virq, type);
+        irq_set_irq_type(virq, type);
         return virq;
 }
 EXPORT_SYMBOL_GPL(irq_create_of_mapping);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 999e2793590b..e2a3f0606da4 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -27,7 +27,7 @@ static int die_counter;
 
 void printk_address(unsigned long address, int reliable)
 {
-        printk(" [<%p>] %s%pS\n", (void *) address,
+        printk(" [<%p>] %s%pB\n", (void *) address,
                         reliable ? "" : "? ", (void *) address);
 }
 
@@ -322,16 +322,6 @@ void die(const char *str, struct pt_regs *regs, long err)
         oops_end(flags, regs, sig);
 }
 
-static int __init oops_setup(char *s)
-{
-        if (!s)
-                return -EINVAL;
-        if (!strcmp(s, "panic"))
-                panic_on_oops = 1;
-        return 0;
-}
-early_param("oops", oops_setup);
-
 static int __init kstack_setup(char *s)
 {
         if (!s)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index cdf5bfd9d4d5..3e2ef8425316 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/init.h>
+#include <linux/crash_dump.h>
 #include <linux/bootmem.h>
 #include <linux/pfn.h>
 #include <linux/suspend.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2d2673c28aff..5655c2272adb 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -77,9 +77,6 @@ void __init x86_64_start_kernel(char * real_mode_data)
         /* Make NULL pointers segfault */
         zap_identity_mappings();
 
-        /* Cleanup the over mapped high alias */
-        cleanup_highmap();
-
         max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 
         for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c
index b42ca694dc68..8eeaa81de066 100644
--- a/arch/x86/kernel/i8237.c
+++ b/arch/x86/kernel/i8237.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/dma.h>
 
@@ -21,7 +21,7 @@
  * in asm/dma.h.
  */
 
-static int i8237A_resume(struct sys_device *dev)
+static void i8237A_resume(void)
 {
         unsigned long flags;
         int i;
@@ -41,31 +41,15 @@ static int i8237A_resume(struct sys_device *dev)
         enable_dma(4);
 
         release_dma_lock(flags);
-
-        return 0;
 }
 
-static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
-{
-        return 0;
-}
-
-static struct sysdev_class i8237_sysdev_class = {
-        .name           = "i8237",
-        .suspend        = i8237A_suspend,
+static struct syscore_ops i8237_syscore_ops = {
         .resume         = i8237A_resume,
 };
 
-static struct sys_device device_i8237A = {
-        .id             = 0,
-        .cls            = &i8237_sysdev_class,
-};
-
-static int __init i8237A_init_sysfs(void)
+static int __init i8237A_init_ops(void)
 {
-        int error = sysdev_class_register(&i8237_sysdev_class);
-        if (!error)
-                error = sysdev_register(&device_i8237A);
-        return error;
+        register_syscore_ops(&i8237_syscore_ops);
+        return 0;
 }
-device_initcall(i8237A_init_sysfs);
+device_initcall(i8237A_init_ops);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index d9ca749c123b..65b8f5c2eebf 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -8,7 +8,7 @@
 #include <linux/random.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/bitops.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
@@ -245,20 +245,19 @@ static void save_ELCR(char *trigger)
         trigger[1] = inb(0x4d1) & 0xDE;
 }
 
-static int i8259A_resume(struct sys_device *dev)
+static void i8259A_resume(void)
 {
         init_8259A(i8259A_auto_eoi);
         restore_ELCR(irq_trigger);
-        return 0;
 }
 
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
+static int i8259A_suspend(void)
 {
         save_ELCR(irq_trigger);
         return 0;
 }
 
-static int i8259A_shutdown(struct sys_device *dev)
+static void i8259A_shutdown(void)
 {
         /* Put the i8259A into a quiescent state that
          * the kernel initialization code can get it
@@ -266,21 +265,14 @@ static int i8259A_shutdown(struct sys_device *dev)
          */
         outb(0xff, PIC_MASTER_IMR);     /* mask all of 8259A-1 */
         outb(0xff, PIC_SLAVE_IMR);      /* mask all of 8259A-1 */
-        return 0;
 }
 
-static struct sysdev_class i8259_sysdev_class = {
-        .name = "i8259",
+static struct syscore_ops i8259_syscore_ops = {
         .suspend = i8259A_suspend,
         .resume = i8259A_resume,
         .shutdown = i8259A_shutdown,
 };
 
-static struct sys_device device_i8259A = {
-        .id     = 0,
-        .cls    = &i8259_sysdev_class,
-};
-
 static void mask_8259A(void)
 {
         unsigned long flags;
@@ -399,17 +391,12 @@ struct legacy_pic default_legacy_pic = {
 
 struct legacy_pic *legacy_pic = &default_legacy_pic;
 
-static int __init i8259A_init_sysfs(void)
+static int __init i8259A_init_ops(void)
 {
-        int error;
-
-        if (legacy_pic != &default_legacy_pic)
-                return 0;
+        if (legacy_pic == &default_legacy_pic)
+                register_syscore_ops(&i8259_syscore_ops);
 
-        error = sysdev_class_register(&i8259_sysdev_class);
-        if (!error)
-                error = sysdev_register(&device_i8259A);
-        return error;
+        return 0;
 }
 
-device_initcall(i8259A_init_sysfs);
+device_initcall(i8259A_init_ops);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 948a31eae75f..1cb0b9fc78dc 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -8,6 +8,7 @@
 #include <linux/seq_file.h>
 #include <linux/smp.h>
 #include <linux/ftrace.h>
+#include <linux/delay.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index dba0b36941a5..5f9ecff328b5 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -121,8 +121,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
                 memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
                        dbg_reg_def[regno].size);
 
-        switch (regno) {
 #ifdef CONFIG_X86_32
+        switch (regno) {
         case GDB_SS:
                 if (!user_mode_vm(regs))
                         *(unsigned long *)mem = __KERNEL_DS;
@@ -135,8 +135,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
         case GDB_FS:
                 *(unsigned long *)mem = 0xFFFF;
                 break;
-#endif
         }
+#endif
         return dbg_reg_def[regno].name;
 }
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 87af68e0e1e1..f9242800bc84 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -82,6 +82,7 @@
 #include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -438,33 +439,25 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
         return 0;
 }
 
-static int mc_sysdev_resume(struct sys_device *dev)
+static struct sysdev_driver mc_sysdev_driver = {
+        .add                    = mc_sysdev_add,
+        .remove                 = mc_sysdev_remove,
+};
+
+/**
+ * mc_bp_resume - Update boot CPU microcode during resume.
+ */
+static void mc_bp_resume(void)
 {
-        int cpu = dev->id;
+        int cpu = smp_processor_id();
         struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-        if (!cpu_online(cpu))
-                return 0;
-
-        /*
-         * All non-bootup cpus are still disabled,
-         * so only CPU 0 will apply ucode here.
-         *
-         * Moreover, there can be no concurrent
-         * updates from any other places at this point.
-         */
-        WARN_ON(cpu != 0);
-
         if (uci->valid && uci->mc)
                 microcode_ops->apply_microcode(cpu);
-
-        return 0;
 }
 
-static struct sysdev_driver mc_sysdev_driver = {
-        .add                    = mc_sysdev_add,
-        .remove                 = mc_sysdev_remove,
-        .resume                 = mc_sysdev_resume,
+static struct syscore_ops mc_syscore_ops = {
+        .resume                 = mc_bp_resume,
 };
 
 static __cpuinit int
@@ -542,6 +535,7 @@ static int __init microcode_init(void)
         if (error)
                 return error;
 
+        register_syscore_ops(&mc_syscore_ops);
         register_hotcpu_notifier(&mc_cpu_notifier);
 
         pr_info("Microcode Update Driver: v" MICROCODE_VERSION
@@ -556,6 +550,7 @@ static void __exit microcode_exit(void)
         microcode_dev_exit();
 
         unregister_hotcpu_notifier(&mc_cpu_notifier);
+        unregister_syscore_ops(&mc_syscore_ops);
 
         get_online_cpus();
         mutex_lock(&microcode_mutex);
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 6f789a887c06..5a532ce646bf 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -714,10 +714,6 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
                 *nr_m_spare += 1;
         }
 }
-#else /* CONFIG_X86_IO_APIC */
-static
-inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
-#endif /* CONFIG_X86_IO_APIC */
 
 static int
 check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
@@ -731,6 +727,10 @@ check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
 
         return ret;
 }
+#else /* CONFIG_X86_IO_APIC */
+static
+inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
+#endif /* CONFIG_X86_IO_APIC */
 
 static int  __init replace_intsrc_all(struct mpc_table *mpc,
                                         unsigned long mpc_new_phys,
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c01ffa5b9b87..b117efd24f71 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -27,7 +27,7 @@
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
 #include <asm/atomic.h>
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
 #define AGPEXTERN
 #endif
 
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR      (1ULL << 40)
+
 /* backdoor interface to AGP driver */
 AGPEXTERN int agp_memory_reserved;
 AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
                                 size_t size, int dir, unsigned long align_mask)
 {
         unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
-        unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+        unsigned long iommu_page;
         int i;
 
+        if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+                return bad_dma_addr;
+
+        iommu_page = alloc_iommu(dev, npages, align_mask);
         if (iommu_page == -1) {
                 if (!nonforced_iommu(dev, phys_mem, size))
                         return phys_mem;
@@ -589,7 +596,7 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
         aperture_alloc = aper_alloc;
 }
 
-static void gart_fixup_northbridges(struct sys_device *dev)
+static void gart_fixup_northbridges(void)
 {
         int i;
 
@@ -613,33 +620,20 @@ static void gart_fixup_northbridges(struct sys_device *dev)
         }
 }
 
-static int gart_resume(struct sys_device *dev)
+static void gart_resume(void)
 {
         pr_info("PCI-DMA: Resuming GART IOMMU\n");
 
-        gart_fixup_northbridges(dev);
+        gart_fixup_northbridges();
 
         enable_gart_translations();
-
-        return 0;
 }
 
-static int gart_suspend(struct sys_device *dev, pm_message_t state)
-{
-        return 0;
-}
-
-static struct sysdev_class gart_sysdev_class = {
-        .name           = "gart",
-        .suspend        = gart_suspend,
+static struct syscore_ops gart_syscore_ops = {
         .resume         = gart_resume,
 
 };
 
-static struct sys_device device_gart = {
-        .cls            = &gart_sysdev_class,
-};
-
 /*
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
@@ -650,7 +644,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
         unsigned aper_base, new_aper_base;
         struct pci_dev *dev;
         void *gatt;
-        int i, error;
+        int i;
 
         pr_info("PCI-DMA: Disabling AGP.\n");
 
@@ -685,12 +679,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 
         agp_gatt_table = gatt;
 
-        error = sysdev_class_register(&gart_sysdev_class);
-        if (!error)
-                error = sysdev_register(&device_gart);
-        if (error)
-                panic("Could not register gart_sysdev -- "
-                      "would corrupt data on next suspend");
+        register_syscore_ops(&gart_syscore_ops);
 
         flush_gart();
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bd387e8f73b4..6c9dd922ac0d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -501,6 +501,10 @@ void set_personality_64bit(void)
         /* Make sure to be in 64bit mode */
         clear_thread_flag(TIF_IA32);
 
+        /* Ensure the corresponding mm is not marked. */
+        if (current->mm)
+                current->mm->context.ia32_compat = 0;
+
         /* TBD: overwrites user setup. Should have two bits.
            But 64bit processes have always behaved this way,
            so it's not too bad. The main problem is just that
@@ -516,6 +520,10 @@ void set_personality_ia32(void)
         set_thread_flag(TIF_IA32);
         current->personality |= force_personality32;
 
+        /* Mark the associated mm as containing 32-bit tasks. */
+        if (current->mm)
+                current->mm->context.ia32_compat = 1;
+
         /* Prepare the first "return" to user space */
         current_thread_info()->status |= TS_COMPAT;
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d3ce37edb54d..08c44b08bf5b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -6,6 +6,7 @@
 #include <linux/dmi.h>
 #include <linux/sched.h>
 #include <linux/tboot.h>
+#include <linux/delay.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d43b28e0728..4be9b398470e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -294,30 +294,11 @@ static void __init init_gbpages(void)
         else
                 direct_gbpages = 0;
 }
-
-static void __init cleanup_highmap_brk_end(void)
-{
-        pud_t *pud;
-        pmd_t *pmd;
-
-        mmu_cr4_features = read_cr4();
-
-        /*
-         * _brk_end cannot change anymore, but it and _end may be
-         * located on different 2M pages. cleanup_highmap(), however,
-         * can only consider _end when it runs, so destroy any
-         * mappings beyond _brk_end here.
-         */
-        pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
-        pmd = pmd_offset(pud, _brk_end - 1);
-        while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
-                pmd_clear(pmd);
-}
 #else
 static inline void init_gbpages(void)
 {
 }
-static inline void cleanup_highmap_brk_end(void)
+static void __init cleanup_highmap(void)
 {
 }
 #endif
@@ -330,8 +311,6 @@ static void __init reserve_brk(void)
         /* Mark brk area as locked down and no longer taking any
            new allocations */
         _brk_start = 0;
-
-        cleanup_highmap_brk_end();
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -640,28 +619,6 @@ void __init reserve_standard_io_resources(void)
 
 }
 
-/*
- * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
- * is_kdump_kernel() to determine if we are booting after a panic. Hence
- * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
- */
-
-#ifdef CONFIG_CRASH_DUMP
-/* elfcorehdr= specifies the location of elf core header
- * stored by the crashed kernel. This option will be passed
- * by kexec loader to the capture kernel.
- */
-static int __init setup_elfcorehdr(char *arg)
-{
-        char *end;
-        if (!arg)
-                return -EINVAL;
-        elfcorehdr_addr = memparse(arg, &end);
-        return end > arg ? 0 : -EINVAL;
-}
-early_param("elfcorehdr", setup_elfcorehdr);
-#endif
-
 static __init void reserve_ibft_region(void)
 {
         unsigned long addr, size = 0;
@@ -950,6 +907,8 @@ void __init setup_arch(char **cmdline_p)
          */
         reserve_brk();
 
+        cleanup_highmap();
+
         memblock.current_limit = get_max_mapped();
         memblock_x86_fill();
 
@@ -1017,6 +976,11 @@ void __init setup_arch(char **cmdline_p)
         paging_init();
         x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
+        if (boot_cpu_data.cpuid_level >= 0) {
+                /* A CPU has %cr4 if and only if it has CPUID */
+                mmu_cr4_features = read_cr4();
+        }
+
 #ifdef CONFIG_X86_32
         /* sync back kernel address range */
         clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 5f181742e8f9..abce34d5c79d 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -343,3 +343,4 @@ ENTRY(sys_call_table)
         .long sys_name_to_handle_at
         .long sys_open_by_handle_at
         .long sys_clock_adjtime
+        .long sys_syncfs