12 files changed, 79 insertions, 8 deletions

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/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.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/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2871d3c71b6..8ed8908cc9f7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -312,6 +312,26 @@ void __cpuinit smp_store_cpu_info(int id)
                 identify_secondary_cpu(c);
 }
 
+static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2)
+{
+        int node1 = early_cpu_to_node(cpu1);
+        int node2 = early_cpu_to_node(cpu2);
+
+        /*
+         * Our CPU scheduler assumes all logical cpus in the same physical cpu
+         * share the same node. But, buggy ACPI or NUMA emulation might assign
+         * them to different node. Fix it.
+         */
+        if (node1 != node2) {
+                pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n",
+                           cpu1, node1, cpu2, node2, node2);
+
+                numa_remove_cpu(cpu1);
+                numa_set_node(cpu1, node2);
+                numa_add_cpu(cpu1);
+        }
+}
+
 static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
 {
         cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
@@ -320,6 +340,7 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
         cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
         cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
         cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
+        check_cpu_siblings_on_same_node(cpu1, cpu2);
 }
 
 
@@ -361,10 +382,12 @@ void __cpuinit set_cpu_sibling_map(int cpu)
                     per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
                         cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
                         cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
+                        check_cpu_siblings_on_same_node(cpu, i);
                 }
                 if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
                         cpumask_set_cpu(i, cpu_core_mask(cpu));
                         cpumask_set_cpu(cpu, cpu_core_mask(i));
+                        check_cpu_siblings_on_same_node(cpu, i);
                         /*
                          *  Does this new cpu bringup a new core?
                          */