20 files changed, 85 insertions, 36 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a279d98ea95e..2b7d573be549 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
-#include <linux/delay.h>
 #include <linux/pm.h>
 
 #include <asm/alternative.h>
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 97b6d8114a43..057099e5faba 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -10,7 +10,6 @@
 
 #include <linux/spinlock.h>     /* And spinlocks */
 #include <asm/io.h>             /* need byte IO */
-#include <linux/delay.h>
 
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
 #define dma_outb        outb_p
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index ef328901c802..c9e09ea05644 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -237,7 +237,7 @@ static inline void fpu_save_init(struct fpu *fpu)
         } else if (use_fxsr()) {
                 fpu_fxsave(fpu);
         } else {
-                asm volatile("fsave %[fx]; fwait"
+                asm volatile("fnsave %[fx]; fwait"
                              : [fx] "=m" (fpu->state->fsave));
                 return;
         }
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/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/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/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5a05ef63eb4a..3385ea26f684 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1626,7 +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;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 307dfbbf4a8e..929739a653d1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -293,14 +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 */
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/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 5ed0ab549eb8..f9242800bc84 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -550,6 +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/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 5a0484a95ad6..4be9b398470e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -976,6 +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/kvm/x86.c b/arch/x86/kvm/x86.c
index 58f517b59645..934b4c6b0bf9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2395,9 +2395,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
                 int i;
 
                 entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-                for (i = 1; *nent < maxnent; ++i) {
-                        if (entry[i - 1].eax == 0 && i != 2)
-                                break;
+                for (i = 1; *nent < maxnent && i < 64; ++i) {
+                        if (entry[i].eax == 0)
+                                continue;
                         do_cpuid_1_ent(&entry[i], function, i);
                         entry[i].flags |=
                                KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -4958,12 +4958,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
                         best = e;
                         break;
                 }
-                /*
-                 * Both basic or both extended?
-                 */
-                if (((e->function ^ function) & 0x80000000) == 0)
-                        if (!best || e->function > best->function)
-                                best = e;
         }
         return best;
 }
@@ -4983,6 +4977,27 @@ not_found:
         return 36;
 }
 
+/*
+ * If no match is found, check whether we exceed the vCPU's limit
+ * and return the content of the highest valid _standard_ leaf instead.
+ * This is to satisfy the CPUID specification.
+ */
+static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
+                                                  u32 function, u32 index)
+{
+        struct kvm_cpuid_entry2 *maxlevel;
+
+        maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+        if (!maxlevel || maxlevel->eax >= function)
+                return NULL;
+        if (function & 0x80000000) {
+                maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
+                if (!maxlevel)
+                        return NULL;
+        }
+        return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+}
+
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
         u32 function, index;
@@ -4995,6 +5010,10 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
         kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
         kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
         best = kvm_find_cpuid_entry(vcpu, function, index);
+
+        if (!best)
+                best = check_cpuid_limit(vcpu, function, index);
+
         if (best) {
                 kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
                 kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 48651c6f657d..364f36bdfad8 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -211,10 +211,12 @@ int __init get_memcfg_from_srat(void)
 {
         int i, j, nid;
 
-
         if (srat_disabled())
                 goto out_fail;
 
+        if (acpi_numa_init() < 0)
+                goto out_fail;
+
         if (num_memory_chunks == 0) {
                 printk(KERN_DEBUG
                          "could not find any ACPI SRAT memory areas.\n");
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 8dace181c88e..cf9750004a08 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -49,6 +49,10 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
         val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
         val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
         val |= (counter_config->unit_mask & 0xFF) << 8;
+        counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV |
+                                  ARCH_PERFMON_EVENTSEL_EDGE |
+                                  ARCH_PERFMON_EVENTSEL_CMASK);
+        val |= counter_config->extra;
         event &= model->event_mask ? model->event_mask : 0xFF;
         val |= event & 0xFF;
         val |= (event & 0x0F00) << 24;
@@ -440,6 +444,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
                 oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
                 oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
                 oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+                oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
         }
 
         return 0;
diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h
index e28398df0df2..0b7b7b179cbe 100644
--- a/arch/x86/oprofile/op_counter.h
+++ b/arch/x86/oprofile/op_counter.h
@@ -22,6 +22,7 @@ struct op_counter_config {
         unsigned long kernel;
         unsigned long user;
         unsigned long unit_mask;
+        unsigned long extra;
 };
 
 extern struct op_counter_config counter_config[];
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 04cf645feb92..73d70d65e76e 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -100,9 +100,11 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 void __init mrst_rtc_init(void)
 {
-        unsigned long vrtc_paddr = sfi_mrtc_array[0].phys_addr;
+        unsigned long vrtc_paddr;
 
         sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+
+        vrtc_paddr = sfi_mrtc_array[0].phys_addr;
         if (!sfi_mrtc_num || !vrtc_paddr)
                 return;
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index a7b38d35c29a..7cb6424317f6 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -11,6 +11,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #include <asm/mmu_context.h>
 #include <asm/uv/uv.h>
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index fe4cf8294878..c7abf13a213f 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -471,15 +471,7 @@ static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
         legacy_pic->init(0);
         enable_cobalt_irq(data);
-}
-
-static void end_piix4_master_irq(struct irq_data *data)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&cobalt_lock, flags);
-        enable_cobalt_irq(data);
-        spin_unlock_irqrestore(&cobalt_lock, flags);
+        return 0;
 }
 
 static struct irq_chip piix4_master_irq_type = {
@@ -492,7 +484,7 @@ static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
         .name           = "PIIX4-virtual",
-        .mask           = pii4_mask,
+        .irq_mask       = pii4_mask,
 };
 
 /*
@@ -580,9 +572,9 @@ static struct irqaction cascade_action = {
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-        piix4_virtual_irq_type.enable = i8259A_chip.unmask;
-        piix4_virtual_irq_type.disable = i8259A_chip.mask;
-        piix4_virtual_irq_type.unmask = i8259A_chip.unmask;
+        piix4_virtual_irq_type.irq_enable = i8259A_chip.irq_unmask;
+        piix4_virtual_irq_type.irq_disable = i8259A_chip.irq_mask;
+        piix4_virtual_irq_type.irq_unmask = i8259A_chip.irq_unmask;
 }
 
 static void __init visws_pre_intr_init(void)
@@ -599,7 +591,7 @@ static void __init visws_pre_intr_init(void)
                 else if (i == CO_IRQ_IDE0)
                         chip = &cobalt_irq_type;
                 else if (i == CO_IRQ_IDE1)
-                        >chip = &cobalt_irq_type;
+                        chip = &cobalt_irq_type;
                 else if (i == CO_IRQ_8259)
                         chip = &piix4_master_irq_type;
                 else if (i < CO_IRQ_APIC0)