30 files changed, 433 insertions, 203 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 55d106b5e31b..211ca3f7fd16 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -185,17 +185,16 @@ struct bootnode;
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
-extern int acpi_get_nodes(struct bootnode *physnodes);
+extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+                                unsigned long end);
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
 #define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
+#ifdef CONFIG_NUMA_EMU
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
                                    int num_nodes);
-#else
-static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
-                                   int num_nodes)
-{
-}
 #endif
+#endif /* CONFIG_ACPI_NUMA */
 
 #define acpi_unlazy_tlb(x)      leave_mm(x)
 
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 6aee50d655d1..64dc82ee19f0 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -3,16 +3,27 @@
 
 #include <linux/pci.h>
 
+struct amd_nb_bus_dev_range {
+        u8 bus;
+        u8 dev_base;
+        u8 dev_limit;
+};
+
 extern struct pci_device_id amd_nb_misc_ids[];
+extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
 struct bootnode;
 
 extern int early_is_amd_nb(u32 value);
 extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
-extern int amd_get_nodes(struct bootnode *nodes);
 extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
 extern int amd_scan_nodes(void);
 
+#ifdef CONFIG_NUMA_EMU
+extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes);
+extern void amd_get_nodes(struct bootnode *nodes);
+#endif
+
 struct amd_northbridge {
         struct pci_dev *misc;
 };
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0141b234406f..4729b2b63117 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -116,11 +116,11 @@ enum fixed_addresses {
 #endif
         FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
         FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
-        __end_of_permanent_fixed_addresses,
-
 #ifdef  CONFIG_X86_MRST
         FIX_LNW_VRTC,
 #endif
+        __end_of_permanent_fixed_addresses,
+
         /*
          * 256 temporary boot-time mappings, used by early_ioremap(),
          * before ioremap() is functional.
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
index 49dbfdfa50f9..91d915a65259 100644
--- a/arch/x86/include/asm/gpio.h
+++ b/arch/x86/include/asm/gpio.h
@@ -38,12 +38,9 @@ static inline int gpio_cansleep(unsigned int gpio)
         return __gpio_cansleep(gpio);
 }
 
-/*
- * Not implemented, yet.
- */
 static inline int gpio_to_irq(unsigned int gpio)
 {
-        return -ENOSYS;
+        return __gpio_to_irq(gpio);
 }
 
 static inline int irq_to_gpio(unsigned int irq)
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f23eb2528464..ca242d35e873 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -18,7 +18,6 @@ enum die_val {
         DIE_TRAP,
         DIE_GPF,
         DIE_CALL,
-        DIE_NMI_IPI,
         DIE_PAGE_FAULT,
         DIE_NMIUNKNOWN,
 };
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index f7920601e472..72a8b52e7dfd 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -7,9 +7,19 @@
 
 #include <asm/mc146818rtc.h>
 
+#define NMI_REASON_PORT         0x61
+
+#define NMI_REASON_SERR         0x80
+#define NMI_REASON_IOCHK        0x40
+#define NMI_REASON_MASK         (NMI_REASON_SERR | NMI_REASON_IOCHK)
+
+#define NMI_REASON_CLEAR_SERR   0x04
+#define NMI_REASON_CLEAR_IOCHK  0x08
+#define NMI_REASON_CLEAR_MASK   0x0f
+
 static inline unsigned char get_nmi_reason(void)
 {
-        return inb(0x61);
+        return inb(NMI_REASON_PORT);
 }
 
 static inline void reassert_nmi(void)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c4021b953510..c76f5b92b840 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -23,6 +23,26 @@ void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
+/*
+ * Define some priorities for the nmi notifier call chain.
+ *
+ * Create a local nmi bit that has a higher priority than
+ * external nmis, because the local ones are more frequent.
+ *
+ * Also setup some default high/normal/low settings for
+ * subsystems to registers with.  Using 4 bits to seperate
+ * the priorities.  This can go alot higher if needed be.
+ */
+
+#define NMI_LOCAL_SHIFT         16      /* randomly picked */
+#define NMI_LOCAL_BIT           (1ULL << NMI_LOCAL_SHIFT)
+#define NMI_HIGH_PRIOR          (1ULL << 8)
+#define NMI_NORMAL_PRIOR        (1ULL << 4)
+#define NMI_LOW_PRIOR           (1ULL << 0)
+#define NMI_LOCAL_HIGH_PRIOR    (NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
+#define NMI_LOCAL_NORMAL_PRIOR  (NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
+#define NMI_LOCAL_LOW_PRIOR     (NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+
 void stop_nmi(void);
 void restart_nmi(void);
 
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 823e070e7c26..5ae87285a502 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -38,7 +38,7 @@ extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
 
 #ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE      ((u64)64 << 20)
+#define FAKE_NODE_MIN_SIZE      ((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
 #endif /* CONFIG_NUMA_EMU */
 #else
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 295e2ff18a6a..e2f6a99f14ab 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -20,6 +20,9 @@
 #define ARCH_P4_MAX_ESCR        (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
 #define ARCH_P4_MAX_CCCR        (18)
 
+#define ARCH_P4_CNTRVAL_BITS    (40)
+#define ARCH_P4_CNTRVAL_MASK    ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+
 #define P4_ESCR_EVENT_MASK      0x7e000000U
 #define P4_ESCR_EVENT_SHIFT     25
 #define P4_ESCR_EVENTMASK_MASK  0x01fffe00U
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index affacb5e0065..0a99f7198bc3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,13 @@ struct pci_device_id amd_nb_misc_ids[] = {
 };
 EXPORT_SYMBOL(amd_nb_misc_ids);
 
+const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
+        { 0x00, 0x18, 0x20 },
+        { 0xff, 0x00, 0x20 },
+        { 0xfe, 0x00, 0x20 },
+        { }
+};
+
 struct amd_northbridge_info amd_northbridges;
 EXPORT_SYMBOL(amd_northbridges);
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index dcd7c83e1659..5955a7800a96 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -39,18 +39,6 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
-struct bus_dev_range {
-        int bus;
-        int dev_base;
-        int dev_limit;
-};
-
-static struct bus_dev_range bus_dev_ranges[] __initdata = {
-        { 0x00, 0x18, 0x20},
-        { 0xff, 0x00, 0x20},
-        { 0xfe, 0x00, 0x20}
-};
-
 static struct resource gart_resource = {
         .name   = "GART",
         .flags  = IORESOURCE_MEM,
@@ -294,13 +282,13 @@ void __init early_gart_iommu_check(void)
         search_agp_bridge(&agp_aper_order, &valid_agp);
 
         fix = 0;
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
                         if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
@@ -349,13 +337,13 @@ void __init early_gart_iommu_check(void)
                 return;
 
         /* disable them all at first */
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
                         if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
@@ -390,14 +378,14 @@ int __init gart_iommu_hole_init(void)
 
         fix = 0;
         node = 0;
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus;
                 int dev_base, dev_limit;
                 u32 ctl;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
 
                 for (slot = dev_base; slot < dev_limit; slot++) {
                         if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
@@ -505,7 +493,7 @@ out:
         }
 
         /* Fix up the north bridges */
-        for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
                 int bus, dev_base, dev_limit;
 
                 /*
@@ -514,9 +502,9 @@ out:
                  */
                 u32 ctl = DISTLBWALKPRB | aper_order << 1;
 
-                bus = bus_dev_ranges[i].bus;
-                dev_base = bus_dev_ranges[i].dev_base;
-                dev_limit = bus_dev_ranges[i].dev_limit;
+                bus = amd_nb_bus_dev_ranges[i].bus;
+                dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+                dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
                 for (slot = dev_base; slot < dev_limit; slot++) {
                         if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a51345ba449e..06c196d7e59c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -684,7 +684,7 @@ static int __init calibrate_APIC_clock(void)
         lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
                                        lapic_clockevent.shift);
         lapic_clockevent.max_delta_ns =
-                clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+                clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
         lapic_clockevent.min_delta_ns =
                 clockevent_delta2ns(0xF, &lapic_clockevent);
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 72ec29e1ae06..79fd43ca6f96 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -68,7 +68,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 
         switch (cmd) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 break;
 
         default:
@@ -96,7 +95,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block backtrace_notifier = {
         .notifier_call          = arch_trigger_all_cpu_backtrace_handler,
         .next                   = NULL,
-        .priority               = 1
+        .priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static int __init register_trigger_all_cpu_backtrace(void)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ecca5f41ad2c..bd16b58b8850 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -378,7 +378,7 @@ struct apic __refdata apic_x2apic_uv_x = {
 
 static __cpuinit void set_x2apic_extra_bits(int pnode)
 {
-        __this_cpu_write(x2apic_extra_bits, (pnode << 6));
+        __this_cpu_write(x2apic_extra_bits, pnode << uvh_apicid.s.pnode_shift);
 }
 
 /*
@@ -641,7 +641,7 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
-        if (reason != DIE_NMI_IPI)
+        if (reason != DIE_NMIUNKNOWN)
                 return NOTIFY_OK;
 
         if (in_crash_kexec)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7bfedb..a77971979564 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
         struct die_args *args = (struct die_args *)data;
         int cpu = smp_processor_id();
         struct mce *m = &__get_cpu_var(injectm);
-        if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+        if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
                 return NOTIFY_DONE;
         cpumask_clear_cpu(cpu, mce_inject_cpumask);
         if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
         .notifier_call = mce_raise_notify,
-        .priority = 1000,
+        .priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 04921017abe0..9d977a2ea693 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1267,7 +1267,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 
         switch (cmd) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 break;
         case DIE_NMIUNKNOWN:
                 this_nmi = percpu_read(irq_stat.__nmi_count);
@@ -1317,7 +1316,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
         .notifier_call          = perf_event_nmi_handler,
         .next                   = NULL,
-        .priority               = 1
+        .priority               = NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b93e694..e56b9bfbabd1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-        int overflow = 0;
-        u32 low, high;
+        u64 v;
 
-        rdmsr(hwc->config_base + hwc->idx, low, high);
-
-        /* we need to check high bit for unflagged overflows */
-        if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-                overflow = 1;
-                (void)checking_wrmsrl(hwc->config_base + hwc->idx,
-                        ((u64)low) & ~P4_CCCR_OVF);
+        /* an official way for overflow indication */
+        rdmsrl(hwc->config_base + hwc->idx, v);
+        if (v & P4_CCCR_OVF) {
+                wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+                return 1;
         }
 
-        return overflow;
+        /* it might be unflagged overflow */
+        rdmsrl(hwc->event_base + hwc->idx, v);
+        if (!(v & ARCH_P4_CNTRVAL_MASK))
+                return 1;
+
+        return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
          */
         .num_counters           = ARCH_P4_MAX_CCCR,
         .apic                   = 1,
-        .cntval_bits            = 40,
-        .cntval_mask            = (1ULL << 40) - 1,
-        .max_period             = (1ULL << 39) - 1,
+        .cntval_bits            = ARCH_P4_CNTRVAL_BITS,
+        .cntval_mask            = ARCH_P4_CNTRVAL_MASK,
+        .max_period             = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
         /*
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 8474c998cbd4..d6fb146c0d8b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -197,14 +197,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
-        unsigned long bp = 0;
         unsigned long stack;
 
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp)
-                get_bp(bp);
-#endif
-
         printk("Pid: %d, comm: %.20s %s %s %.*s\n",
                 current->pid, current->comm, print_tainted(),
                 init_utsname()->release,
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e3ba417e8697..d3b895f375d3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -299,17 +299,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_args)
         XCPT_FRAME
         cld
-        movq_cfi rdi, RDI+16-ARGOFFSET
-        movq_cfi rsi, RSI+16-ARGOFFSET
-        movq_cfi rdx, RDX+16-ARGOFFSET
-        movq_cfi rcx, RCX+16-ARGOFFSET
-        movq_cfi rax, RAX+16-ARGOFFSET
-        movq_cfi  r8,  R8+16-ARGOFFSET
-        movq_cfi  r9,  R9+16-ARGOFFSET
-        movq_cfi r10, R10+16-ARGOFFSET
-        movq_cfi r11, R11+16-ARGOFFSET
-
-        leaq -ARGOFFSET+16(%rsp),%rdi   /* arg1 for handler */
+        /*
+         * start from rbp in pt_regs and jump over
+         * return address.
+         */
+        movq_cfi rdi, RDI+8-RBP
+        movq_cfi rsi, RSI+8-RBP
+        movq_cfi rdx, RDX+8-RBP
+        movq_cfi rcx, RCX+8-RBP
+        movq_cfi rax, RAX+8-RBP
+        movq_cfi  r8,  R8+8-RBP
+        movq_cfi  r9,  R9+8-RBP
+        movq_cfi r10, R10+8-RBP
+        movq_cfi r11, R11+8-RBP
+
+        leaq -RBP+8(%rsp),%rdi  /* arg1 for handler */
         movq_cfi rbp, 8         /* push %rbp */
         leaq 8(%rsp), %rbp              /* mov %rsp, %ebp */
         testl $3, CS(%rdi)
@@ -782,8 +786,9 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
         .macro interrupt func
-        subq $ORIG_RAX-ARGOFFSET+8, %rsp
-        CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
+        /* reserve pt_regs for scratch regs and rbp */
+        subq $ORIG_RAX-RBP, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
         call save_args
         PARTIAL_FRAME 0
         call \func
@@ -808,9 +813,14 @@ ret_from_intr:
         TRACE_IRQS_OFF
         decl PER_CPU_VAR(irq_count)
         leaveq
+
         CFI_RESTORE             rbp
         CFI_DEF_CFA_REGISTER    rsp
         CFI_ADJUST_CFA_OFFSET   -8
+
+        /* we did not save rbx, restore only from ARGOFFSET */
+        addq $8, %rsp
+        CFI_ADJUST_CFA_OFFSET   -8
 exit_intr:
         GET_THREAD_INFO(%rcx)
         testl $3,CS-ARGOFFSET(%rsp)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index cd21b654dec6..a4130005028a 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -48,6 +48,7 @@
 #include <asm/apicdef.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 {
@@ -525,10 +526,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
                 }
                 return NOTIFY_DONE;
 
-        case DIE_NMI_IPI:
-                /* Just ignore, we will handle the roundup on DIE_NMI. */
-                return NOTIFY_DONE;
-
         case DIE_NMIUNKNOWN:
                 if (was_in_debug_nmi[raw_smp_processor_id()]) {
                         was_in_debug_nmi[raw_smp_processor_id()] = 0;
@@ -606,7 +603,7 @@ static struct notifier_block kgdb_notifier = {
         /*
          * Lowest-prio notifier priority, we want to be notified last:
          */
-        .priority       = -INT_MAX,
+        .priority       = NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c495aa8d4815..fc7aae1e2bc7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -18,6 +18,7 @@
 #include <asm/pci_x86.h>
 #include <asm/virtext.h>
 #include <asm/cpu.h>
+#include <asm/nmi.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/ctype.h>
@@ -747,7 +748,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 {
         int cpu;
 
-        if (val != DIE_NMI_IPI)
+        if (val != DIE_NMI)
                 return NOTIFY_OK;
 
         cpu = raw_smp_processor_id();
@@ -778,6 +779,8 @@ static void smp_send_nmi_allbutself(void)
 
 static struct notifier_block crash_nmi_nb = {
         .notifier_call = crash_nmi_callback,
+        /* we want to be the first one called */
+        .priority = NMI_LOCAL_HIGH_PRIOR+1,
 };
 
 /* Halt all other CPUs, calling the specified function on each of them
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c7149c96d079..763df77343dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -97,12 +97,12 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
  */
 static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
 
-void cpu_hotplug_driver_lock()
+void cpu_hotplug_driver_lock(void)
 {
         mutex_lock(&x86_cpu_hotplug_driver_mutex);
 }
 
-void cpu_hotplug_driver_unlock()
+void cpu_hotplug_driver_unlock(void)
 {
         mutex_unlock(&x86_cpu_hotplug_driver_mutex);
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c76aaca5694d..b9b67166f9de 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,6 +84,11 @@ EXPORT_SYMBOL_GPL(used_vectors);
 static int ignore_nmis;
 
 int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
 
 static inline void conditional_sti(struct pt_regs *regs)
 {
@@ -310,15 +315,15 @@ static int __init setup_unknown_nmi_panic(char *str)
 __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 static notrace __kprobes void
-mem_parity_error(unsigned char reason, struct pt_regs *regs)
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
-        printk(KERN_EMERG
-                "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-                        reason, smp_processor_id());
-
-        printk(KERN_EMERG
-                "You have some hardware problem, likely on the PCI bus.\n");
+        pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
 
+        /*
+         * On some machines, PCI SERR line is used to report memory
+         * errors. EDAC makes use of it.
+         */
 #if defined(CONFIG_EDAC)
         if (edac_handler_set()) {
                 edac_atomic_assert_error();
@@ -329,11 +334,11 @@ mem_parity_error(unsigned char reason, struct pt_regs *regs)
         if (panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
-        printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+        pr_emerg("Dazed and confused, but trying to continue\n");
 
-        /* Clear and disable the memory parity error line. */
-        reason = (reason & 0xf) | 4;
-        outb(reason, 0x61);
+        /* Clear and disable the PCI SERR error line. */
+        reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+        outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -341,15 +346,17 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 {
         unsigned long i;
 
-        printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
+        pr_emerg(
+        "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
         show_registers(regs);
 
         if (panic_on_io_nmi)
                 panic("NMI IOCK error: Not continuing");
 
         /* Re-enable the IOCK line, wait for a few seconds */
-        reason = (reason & 0xf) | 8;
-        outb(reason, 0x61);
+        reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+        outb(reason, NMI_REASON_PORT);
 
         i = 20000;
         while (--i) {
@@ -357,8 +364,8 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
                 udelay(100);
         }
 
-        reason &= ~8;
-        outb(reason, 0x61);
+        reason &= ~NMI_REASON_CLEAR_IOCHK;
+        outb(reason, NMI_REASON_PORT);
 }
 
 static notrace __kprobes void
@@ -377,57 +384,50 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
                 return;
         }
 #endif
-        printk(KERN_EMERG
-                "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-                        reason, smp_processor_id());
+        pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+                 reason, smp_processor_id());
 
-        printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
+        pr_emerg("Do you have a strange power saving mode enabled?\n");
         if (unknown_nmi_panic || panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
-        printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+        pr_emerg("Dazed and confused, but trying to continue\n");
 }
 
 static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 {
         unsigned char reason = 0;
-        int cpu;
 
-        cpu = smp_processor_id();
-
-        /* Only the BSP gets external NMIs from the system. */
-        if (!cpu)
-                reason = get_nmi_reason();
+        /*
+         * CPU-specific NMI must be processed before non-CPU-specific
+         * NMI, otherwise we may lose it, because the CPU-specific
+         * NMI can not be detected/processed on other CPUs.
+         */
+        if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
+                return;
 
-        if (!(reason & 0xc0)) {
-                if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
-                                                                == NOTIFY_STOP)
-                        return;
+        /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+        raw_spin_lock(&nmi_reason_lock);
+        reason = get_nmi_reason();
 
-#ifdef CONFIG_X86_LOCAL_APIC
-                if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-                                                        == NOTIFY_STOP)
-                        return;
+        if (reason & NMI_REASON_MASK) {
+                if (reason & NMI_REASON_SERR)
+                        pci_serr_error(reason, regs);
+                else if (reason & NMI_REASON_IOCHK)
+                        io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+                /*
+                 * Reassert NMI in case it became active
+                 * meanwhile as it's edge-triggered:
+                 */
+                reassert_nmi();
 #endif
-                unknown_nmi_error(reason, regs);
-
+                raw_spin_unlock(&nmi_reason_lock);
                 return;
         }
-        if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
-                return;
+        raw_spin_unlock(&nmi_reason_lock);
 
-        /* AK: following checks seem to be broken on modern chipsets. FIXME */
-        if (reason & 0x80)
-                mem_parity_error(reason, regs);
-        if (reason & 0x40)
-                io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-        /*
-         * Reassert NMI in case it became active meanwhile
-         * as it's edge-triggered:
-         */
-        reassert_nmi();
-#endif
+        unknown_nmi_error(reason, regs);
 }
 
 dotraplinkage notrace __kprobes void
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 03d2ea82f35a..823f79a17ad1 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -965,7 +965,7 @@ out:
 
 static int __init init_tsc_clocksource(void)
 {
-        if (!cpu_has_tsc || tsc_disabled > 0)
+        if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz)
                 return 0;
 
         if (tsc_clocksource_reliable)
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index 08a0069b87a5..f21962c435ed 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -27,6 +27,7 @@
 #include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
+static unsigned char __initdata nodeids[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
 
 static __init int find_northbridge(void)
@@ -68,19 +69,6 @@ static __init void early_get_boot_cpu_id(void)
 #endif
 }
 
-int __init amd_get_nodes(struct bootnode *physnodes)
-{
-        int i;
-        int ret = 0;
-
-        for_each_node_mask(i, nodes_parsed) {
-                physnodes[ret].start = nodes[i].start;
-                physnodes[ret].end = nodes[i].end;
-                ret++;
-        }
-        return ret;
-}
-
 int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 {
         unsigned long start = PFN_PHYS(start_pfn);
@@ -113,7 +101,7 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
                 base = read_pci_config(0, nb, 1, 0x40 + i*8);
                 limit = read_pci_config(0, nb, 1, 0x44 + i*8);
 
-                nodeid = limit & 7;
+                nodeids[i] = nodeid = limit & 7;
                 if ((base & 3) == 0) {
                         if (i < numnodes)
                                 pr_info("Skipping disabled node %d\n", i);
@@ -193,6 +181,76 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
         return 0;
 }
 
+#ifdef CONFIG_NUMA_EMU
+static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
+        [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
+void __init amd_get_nodes(struct bootnode *physnodes)
+{
+        int i;
+
+        for_each_node_mask(i, nodes_parsed) {
+                physnodes[i].start = nodes[i].start;
+                physnodes[i].end = nodes[i].end;
+        }
+}
+
+static int __init find_node_by_addr(unsigned long addr)
+{
+        int ret = NUMA_NO_NODE;
+        int i;
+
+        for (i = 0; i < 8; i++)
+                if (addr >= nodes[i].start && addr < nodes[i].end) {
+                        ret = i;
+                        break;
+                }
+        return ret;
+}
+
+/*
+ * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be
+ * setup to represent the physical topology but reflect the emulated
+ * environment.  For each emulated node, the real node which it appears on is
+ * found and a fake pxm to nid mapping is created which mirrors the actual
+ * locality.  node_distance() then represents the correct distances between
+ * emulated nodes by using the fake acpi mappings to pxms.
+ */
+void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
+{
+        unsigned int bits;
+        unsigned int cores;
+        unsigned int apicid_base = 0;
+        int i;
+
+        bits = boot_cpu_data.x86_coreid_bits;
+        cores = 1 << bits;
+        early_get_boot_cpu_id();
+        if (boot_cpu_physical_apicid > 0)
+                apicid_base = boot_cpu_physical_apicid;
+
+        for (i = 0; i < nr_nodes; i++) {
+                int index;
+                int nid;
+                int j;
+
+                nid = find_node_by_addr(nodes[i].start);
+                if (nid == NUMA_NO_NODE)
+                        continue;
+
+                index = nodeids[nid] << bits;
+                if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE)
+                        for (j = apicid_base; j < cores + apicid_base; j++)
+                                fake_apicid_to_node[index + j] = i;
+#ifdef CONFIG_ACPI_NUMA
+                __acpi_map_pxm_to_node(nid, i);
+#endif
+        }
+        memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+}
+#endif /* CONFIG_NUMA_EMU */
+
 int __init amd_scan_nodes(void)
 {
         unsigned int bits;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 7762a517d69d..1e72102e80c9 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -260,30 +260,30 @@ void __init numa_init_array(void)
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
-static struct bootnode physnodes[MAX_NUMNODES] __initdata;
+static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata;
 static char *cmdline __initdata;
 
 static int __init setup_physnodes(unsigned long start, unsigned long end,
                                         int acpi, int amd)
 {
-        int nr_nodes = 0;
         int ret = 0;
         int i;
 
+        memset(physnodes, 0, sizeof(physnodes));
 #ifdef CONFIG_ACPI_NUMA
         if (acpi)
-                nr_nodes = acpi_get_nodes(physnodes);
+                acpi_get_nodes(physnodes, start, end);
 #endif
 #ifdef CONFIG_AMD_NUMA
         if (amd)
-                nr_nodes = amd_get_nodes(physnodes);
+                amd_get_nodes(physnodes);
 #endif
         /*
          * Basic sanity checking on the physical node map: there may be errors
          * if the SRAT or AMD code incorrectly reported the topology or the mem=
          * kernel parameter is used.
          */
-        for (i = 0; i < nr_nodes; i++) {
+        for (i = 0; i < MAX_NUMNODES; i++) {
                 if (physnodes[i].start == physnodes[i].end)
                         continue;
                 if (physnodes[i].start > end) {
@@ -298,17 +298,6 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
                         physnodes[i].start = start;
                 if (physnodes[i].end > end)
                         physnodes[i].end = end;
-        }
-
-        /*
-         * Remove all nodes that have no memory or were truncated because of the
-         * limited address range.
-         */
-        for (i = 0; i < nr_nodes; i++) {
-                if (physnodes[i].start == physnodes[i].end)
-                        continue;
-                physnodes[ret].start = physnodes[i].start;
-                physnodes[ret].end = physnodes[i].end;
                 ret++;
         }
 
@@ -324,6 +313,24 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
         return ret;
 }
 
+static void __init fake_physnodes(int acpi, int amd, int nr_nodes)
+{
+        int i;
+
+        BUG_ON(acpi && amd);
+#ifdef CONFIG_ACPI_NUMA
+        if (acpi)
+                acpi_fake_nodes(nodes, nr_nodes);
+#endif
+#ifdef CONFIG_AMD_NUMA
+        if (amd)
+                amd_fake_nodes(nodes, nr_nodes);
+#endif
+        if (!acpi && !amd)
+                for (i = 0; i < nr_cpu_ids; i++)
+                        numa_set_node(i, 0);
+}
+
 /*
  * Setups up nid to range from addr to addr + size.  If the end
  * boundary is greater than max_addr, then max_addr is used instead.
@@ -352,8 +359,7 @@ static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr)
  * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
  * to max_addr.  The return value is the number of nodes allocated.
  */
-static int __init split_nodes_interleave(u64 addr, u64 max_addr,
-                                                int nr_phys_nodes, int nr_nodes)
+static int __init split_nodes_interleave(u64 addr, u64 max_addr, int nr_nodes)
 {
         nodemask_t physnode_mask = NODE_MASK_NONE;
         u64 size;
@@ -384,7 +390,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
                 return -1;
         }
 
-        for (i = 0; i < nr_phys_nodes; i++)
+        for (i = 0; i < MAX_NUMNODES; i++)
                 if (physnodes[i].start != physnodes[i].end)
                         node_set(i, physnode_mask);
 
@@ -553,11 +559,9 @@ static int __init numa_emulation(unsigned long start_pfn,
 {
         u64 addr = start_pfn << PAGE_SHIFT;
         u64 max_addr = last_pfn << PAGE_SHIFT;
-        int num_phys_nodes;
         int num_nodes;
         int i;
 
-        num_phys_nodes = setup_physnodes(addr, max_addr, acpi, amd);
         /*
          * If the numa=fake command-line contains a 'M' or 'G', it represents
          * the fixed node size.  Otherwise, if it is just a single number N,
@@ -572,7 +576,7 @@ static int __init numa_emulation(unsigned long start_pfn,
                 unsigned long n;
 
                 n = simple_strtoul(cmdline, NULL, 0);
-                num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n);
+                num_nodes = split_nodes_interleave(addr, max_addr, n);
         }
 
         if (num_nodes < 0)
@@ -595,7 +599,8 @@ static int __init numa_emulation(unsigned long start_pfn,
                                                 nodes[i].end >> PAGE_SHIFT);
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
         }
-        acpi_fake_nodes(nodes, num_nodes);
+        setup_physnodes(addr, max_addr, acpi, amd);
+        fake_physnodes(acpi, amd, num_nodes);
         numa_init_array();
         return 0;
 }
@@ -610,8 +615,12 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
         nodes_clear(node_online_map);
 
 #ifdef CONFIG_NUMA_EMU
+        setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+                        acpi, amd);
         if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd))
                 return;
+        setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT,
+                        acpi, amd);
         nodes_clear(node_possible_map);
         nodes_clear(node_online_map);
 #endif
@@ -767,6 +776,7 @@ void __cpuinit numa_clear_node(int cpu)
 
 #ifndef CONFIG_DEBUG_PER_CPU_MAPS
 
+#ifndef CONFIG_NUMA_EMU
 void __cpuinit numa_add_cpu(int cpu)
 {
         cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
@@ -776,34 +786,115 @@ void __cpuinit numa_remove_cpu(int cpu)
 {
         cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
+#else
+void __cpuinit numa_add_cpu(int cpu)
+{
+        unsigned long addr;
+        u16 apicid;
+        int physnid;
+        int nid = NUMA_NO_NODE;
+
+        apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+        if (apicid != BAD_APICID)
+                nid = apicid_to_node[apicid];
+        if (nid == NUMA_NO_NODE)
+                nid = early_cpu_to_node(cpu);
+        BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+
+        /*
+         * Use the starting address of the emulated node to find which physical
+         * node it is allocated on.
+         */
+        addr = node_start_pfn(nid) << PAGE_SHIFT;
+        for (physnid = 0; physnid < MAX_NUMNODES; physnid++)
+                if (addr >= physnodes[physnid].start &&
+                    addr < physnodes[physnid].end)
+                        break;
+
+        /*
+         * Map the cpu to each emulated node that is allocated on the physical
+         * node of the cpu's apic id.
+         */
+        for_each_online_node(nid) {
+                addr = node_start_pfn(nid) << PAGE_SHIFT;
+                if (addr >= physnodes[physnid].start &&
+                    addr < physnodes[physnid].end)
+                        cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+        }
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+        int i;
+
+        for_each_online_node(i)
+                cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
+}
+#endif /* !CONFIG_NUMA_EMU */
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
+static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+{
+        int node = early_cpu_to_node(cpu);
+        struct cpumask *mask;
+        char buf[64];
+
+        mask = node_to_cpumask_map[node];
+        if (!mask) {
+                pr_err("node_to_cpumask_map[%i] NULL\n", node);
+                dump_stack();
+                return NULL;
+        }
+
+        cpulist_scnprintf(buf, sizeof(buf), mask);
+        printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+                enable ? "numa_add_cpu" : "numa_remove_cpu",
+                cpu, node, buf);
+        return mask;
+}
 
 /*
  * --------- debug versions of the numa functions ---------
  */
+#ifndef CONFIG_NUMA_EMU
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
-        int node = early_cpu_to_node(cpu);
         struct cpumask *mask;
-        char buf[64];
 
-        mask = node_to_cpumask_map[node];
-        if (mask == NULL) {
-                printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
-                dump_stack();
+        mask = debug_cpumask_set_cpu(cpu, enable);
+        if (!mask)
                 return;
-        }
 
         if (enable)
                 cpumask_set_cpu(cpu, mask);
         else
                 cpumask_clear_cpu(cpu, mask);
+}
+#else
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+        int node = early_cpu_to_node(cpu);
+        struct cpumask *mask;
+        int i;
 
-        cpulist_scnprintf(buf, sizeof(buf), mask);
-        printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-                enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
+        for_each_online_node(i) {
+                unsigned long addr;
+
+                addr = node_start_pfn(i) << PAGE_SHIFT;
+                if (addr < physnodes[node].start ||
+                                        addr >= physnodes[node].end)
+                        continue;
+                mask = debug_cpumask_set_cpu(cpu, enable);
+                if (!mask)
+                        return;
+
+                if (enable)
+                        cpumask_set_cpu(cpu, mask);
+                else
+                        cpumask_clear_cpu(cpu, mask);
+        }
 }
+#endif /* CONFIG_NUMA_EMU */
 
 void __cpuinit numa_add_cpu(int cpu)
 {
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 171a0aacb99a..603d285d1daa 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -349,18 +349,19 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 
 void __init acpi_numa_arch_fixup(void) {}
 
-int __init acpi_get_nodes(struct bootnode *physnodes)
+#ifdef CONFIG_NUMA_EMU
+void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
+                                unsigned long end)
 {
         int i;
-        int ret = 0;
 
         for_each_node_mask(i, nodes_parsed) {
-                physnodes[ret].start = nodes[i].start;
-                physnodes[ret].end = nodes[i].end;
-                ret++;
+                cutoff_node(i, start, end);
+                physnodes[i].start = nodes[i].start;
+                physnodes[i].end = nodes[i].end;
         }
-        return ret;
 }
+#endif /* CONFIG_NUMA_EMU */
 
 /* Use the information discovered above to actually set up the nodes. */
 int __init acpi_scan_nodes(unsigned long start, unsigned long end)
@@ -505,8 +506,6 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 {
         int i, j;
 
-        printk(KERN_INFO "Faking PXM affinity for fake nodes on real "
-                         "topology.\n");
         for (i = 0; i < num_nodes; i++) {
                 int nid, pxm;
 
@@ -526,6 +525,17 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
                             fake_apicid_to_node[j] == NUMA_NO_NODE)
                                 fake_apicid_to_node[j] = i;
         }
+
+        /*
+         * If there are apicid-to-node mappings for physical nodes that do not
+         * have a corresponding emulated node, it should default to a guaranteed
+         * value.
+         */
+        for (i = 0; i < MAX_LOCAL_APIC; i++)
+                if (apicid_to_node[i] != NUMA_NO_NODE &&
+                    fake_apicid_to_node[i] == NUMA_NO_NODE)
+                        fake_apicid_to_node[i] = 0;
+
         for (i = 0; i < num_nodes; i++)
                 __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
         memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index f24a8533bcdf..e2b7b0c06cdf 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -65,7 +65,6 @@ static int profile_exceptions_notify(struct notifier_block *self,
 
         switch (val) {
         case DIE_NMI:
-        case DIE_NMI_IPI:
                 if (ctr_running)
                         model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
                 else if (!nmi_enabled)
@@ -361,7 +360,7 @@ static void nmi_cpu_setup(void *dummy)
 static struct notifier_block profile_exceptions_nb = {
         .notifier_call = profile_exceptions_notify,
         .next = NULL,
-        .priority = 2
+        .priority = NMI_LOCAL_LOW_PRIOR,
 };
 
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index 0636dd93cef8..720bf5a53c51 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -38,7 +38,7 @@ static int profile_timer_exceptions_notify(struct notifier_block *self,
 static struct notifier_block profile_timer_exceptions_nb = {
         .notifier_call = profile_timer_exceptions_notify,
         .next = NULL,
-        .priority = 0
+        .priority = NMI_LOW_PRIOR,
 };
 
 static int timer_start(void)
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index fc1e8fe07e5c..e27dffbbb1a7 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -4,6 +4,7 @@
 #include <linux/cpu.h>
 #include <linux/range.h>
 
+#include <asm/amd_nb.h>
 #include <asm/pci_x86.h>
 
 #include <asm/pci-direct.h>
@@ -378,6 +379,34 @@ static struct notifier_block __cpuinitdata amd_cpu_notifier = {
         .notifier_call  = amd_cpu_notify,
 };
 
+static void __init pci_enable_pci_io_ecs(void)
+{
+#ifdef CONFIG_AMD_NB
+        unsigned int i, n;
+
+        for (n = i = 0; !n && amd_nb_bus_dev_ranges[i].dev_limit; ++i) {
+                u8 bus = amd_nb_bus_dev_ranges[i].bus;
+                u8 slot = amd_nb_bus_dev_ranges[i].dev_base;
+                u8 limit = amd_nb_bus_dev_ranges[i].dev_limit;
+
+                for (; slot < limit; ++slot) {
+                        u32 val = read_pci_config(bus, slot, 3, 0);
+
+                        if (!early_is_amd_nb(val))
+                                continue;
+
+                        val = read_pci_config(bus, slot, 3, 0x8c);
+                        if (!(val & (ENABLE_CF8_EXT_CFG >> 32))) {
+                                val |= ENABLE_CF8_EXT_CFG >> 32;
+                                write_pci_config(bus, slot, 3, 0x8c, val);
+                        }
+                        ++n;
+                }
+        }
+        pr_info("Extended Config Space enabled on %u nodes\n", n);
+#endif
+}
+
 static int __init pci_io_ecs_init(void)
 {
         int cpu;
@@ -386,6 +415,10 @@ static int __init pci_io_ecs_init(void)
         if (boot_cpu_data.x86 < 0x10)
                 return 0;
 
+        /* Try the PCI method first. */
+        if (early_pci_allowed())
+                pci_enable_pci_io_ecs();
+
         register_cpu_notifier(&amd_cpu_notifier);
         for_each_online_cpu(cpu)
                 amd_cpu_notify(&amd_cpu_notifier, (unsigned long)CPU_ONLINE,