21 files changed, 190 insertions, 153 deletions

diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index ffd01e5dcb52..2ca43ba32bc0 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -595,7 +595,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
         dmi_check_system(sw_any_bug_dmi_table);
         if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) {
                 policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-                policy->cpus = cpu_core_map[cpu];
+                policy->cpus = per_cpu(cpu_core_map, cpu);
         }
 #endif
 
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 8eb414b906d2..793eae854f4f 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -200,7 +200,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
         unsigned int i;
 
 #ifdef CONFIG_SMP
-        policy->cpus = cpu_sibling_map[policy->cpu];
+        policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
 #endif
 
         /* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index b273b69cfddf..c06ac680c9ca 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -57,7 +57,7 @@ static struct powernow_k8_data *powernow_data[NR_CPUS];
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-static cpumask_t cpu_core_map[1];
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -667,7 +667,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst,
 
         dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
         data->powernow_table = powernow_table;
-        if (first_cpu(cpu_core_map[data->cpu]) == data->cpu)
+        if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
                 print_basics(data);
 
         for (j = 0; j < data->numps; j++)
@@ -821,7 +821,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
         /* fill in data */
         data->numps = data->acpi_data.state_count;
-        if (first_cpu(cpu_core_map[data->cpu]) == data->cpu)
+        if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
                 print_basics(data);
         powernow_k8_acpi_pst_values(data, 0);
 
@@ -1214,7 +1214,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
         if (cpu_family == CPU_HW_PSTATE)
                 pol->cpus = cpumask_of_cpu(pol->cpu);
         else
-                pol->cpus = cpu_core_map[pol->cpu];
+                pol->cpus = per_cpu(cpu_core_map, pol->cpu);
         data->available_cores = &(pol->cpus);
 
         /* Take a crude guess here.
@@ -1281,7 +1281,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
         cpumask_t oldmask = current->cpus_allowed;
         unsigned int khz = 0;
 
-        data = powernow_data[first_cpu(cpu_core_map[cpu])];
+        data = powernow_data[first_cpu(per_cpu(cpu_core_map, cpu))];
 
         if (!data)
                 return -EINVAL;
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 36685e8f7be1..14d68aa301ee 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -322,7 +322,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
         /* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-        policy->cpus = cpu_sibling_map[policy->cpu];
+        policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
 #endif
 
         cpus_allowed = current->cpus_allowed;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 1e31b6caffb1..879a0f789b1e 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -122,7 +122,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #ifdef CONFIG_X86_HT
         if (c->x86_max_cores * smp_num_siblings > 1) {
                 seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-                seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[n]));
+                seq_printf(m, "siblings\t: %d\n",
+                                cpus_weight(per_cpu(cpu_core_map, n)));
                 seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
                 seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
         }
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index e2f4a1c68547..4ee1e5ee9b57 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -378,7 +378,7 @@ static struct irq_cpu_info {
 
 #define IRQ_ALLOWED(cpu, allowed_mask)  cpu_isset(cpu, allowed_mask)
 
-#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i]))
+#define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i)))
 
 static cpumask_t balance_irq_affinity[NR_IRQS] = {
         [0 ... NR_IRQS-1] = CPU_MASK_ALL
@@ -598,7 +598,7 @@ tryanotherirq:
          * (A+B)/2 vs B
          */
         load = CPU_IRQ(min_loaded) >> 1;
-        for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) {
+        for_each_cpu_mask(j, per_cpu(cpu_sibling_map, min_loaded)) {
                 if (load > CPU_IRQ(j)) {
                         /* This won't change cpu_sibling_map[min_loaded] */
                         load = CPU_IRQ(j);
diff --git a/arch/x86/kernel/kprobes_32.c b/arch/x86/kernel/kprobes_32.c
index e7d0d3c2ef64..90f778c04b3f 100644
--- a/arch/x86/kernel/kprobes_32.c
+++ b/arch/x86/kernel/kprobes_32.c
@@ -41,6 +41,13 @@ void jprobe_return_end(void);
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
+struct kretprobe_blackpoint kretprobe_blacklist[] = {
+        {"__switch_to", }, /* This function switches only current task, but
+                             doesn't switch kernel stack.*/
+        {NULL, NULL}    /* Terminator */
+};
+const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
+
 /* insert a jmp code */
 static __always_inline void set_jmp_op(void *from, void *to)
 {
@@ -584,7 +591,7 @@ out:
         return 1;
 }
 
-static int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
         struct kprobe *cur = kprobe_running();
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -666,7 +673,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
                         ret = NOTIFY_STOP;
                 break;
         case DIE_GPF:
-        case DIE_PAGE_FAULT:
                 /* kprobe_running() needs smp_processor_id() */
                 preempt_disable();
                 if (kprobe_running() &&
diff --git a/arch/x86/kernel/kprobes_64.c b/arch/x86/kernel/kprobes_64.c
index 62e28e52d784..681b801c5e26 100644
--- a/arch/x86/kernel/kprobes_64.c
+++ b/arch/x86/kernel/kprobes_64.c
@@ -48,6 +48,13 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p);
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
+struct kretprobe_blackpoint kretprobe_blacklist[] = {
+        {"__switch_to", }, /* This function switches only current task, but
+                              doesn't switch kernel stack.*/
+        {NULL, NULL}    /* Terminator */
+};
+const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
+
 /*
  * returns non-zero if opcode modifies the interrupt flag.
  */
@@ -657,7 +664,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
                         ret = NOTIFY_STOP;
                 break;
         case DIE_GPF:
-        case DIE_PAGE_FAULT:
                 /* kprobe_running() needs smp_processor_id() */
                 preempt_disable();
                 if (kprobe_running() &&
diff --git a/arch/x86/kernel/mce_amd_64.c b/arch/x86/kernel/mce_amd_64.c
index 2f8a7f18b0fe..805b62b1e0df 100644
--- a/arch/x86/kernel/mce_amd_64.c
+++ b/arch/x86/kernel/mce_amd_64.c
@@ -472,7 +472,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 #ifdef CONFIG_SMP
         if (cpu_data[cpu].cpu_core_id && shared_bank[bank]) {   /* symlink */
-                i = first_cpu(cpu_core_map[cpu]);
+                i = first_cpu(per_cpu(cpu_core_map, cpu));
 
                 /* first core not up yet */
                 if (cpu_data[i].cpu_core_id)
@@ -492,7 +492,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
                 if (err)
                         goto out;
 
-                b->cpus = cpu_core_map[cpu];
+                b->cpus = per_cpu(cpu_core_map, cpu);
                 per_cpu(threshold_banks, cpu)[bank] = b;
                 goto out;
         }
@@ -509,7 +509,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
         b->cpus = CPU_MASK_ALL;
 #else
-        b->cpus = cpu_core_map[cpu];
+        b->cpus = per_cpu(cpu_core_map, cpu);
 #endif
         err = kobject_register(&b->kobj);
         if (err)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 7352d4b377e6..6309b275cb9c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -581,7 +581,7 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
  *
  * Kprobes not supported here. Set the probe on schedule instead.
  */
-__kprobes struct task_struct *
+struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
         struct thread_struct *prev = &prev_p->thread,
diff --git a/arch/x86/kernel/ptrace_32.c b/arch/x86/kernel/ptrace_32.c
index 0cecd7513c97..8622b9cd3e38 100644
--- a/arch/x86/kernel/ptrace_32.c
+++ b/arch/x86/kernel/ptrace_32.c
@@ -524,11 +524,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                 ret = 0;
                 break;
 
-        case PTRACE_DETACH:
-                /* detach a process that was attached. */
-                ret = ptrace_detach(child, data);
-                break;
-
         case PTRACE_GETREGS: { /* Get all gp regs from the child. */
                 if (!access_ok(VERIFY_WRITE, datap, FRAME_SIZE*sizeof(long))) {
                         ret = -EIO;
diff --git a/arch/x86/kernel/ptrace_64.c b/arch/x86/kernel/ptrace_64.c
index c0cac42df3b6..86321ee6da93 100644
--- a/arch/x86/kernel/ptrace_64.c
+++ b/arch/x86/kernel/ptrace_64.c
@@ -500,11 +500,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                 ret = 0;
                 break;
 
-        case PTRACE_DETACH:
-                /* detach a process that was attached. */
-                ret = ptrace_detach(child, data);
-                break;
-
         case PTRACE_GETREGS: { /* Get all gp regs from the child. */
                 if (!access_ok(VERIFY_WRITE, (unsigned __user *)data,
                                sizeof(struct user_regs_struct))) {
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index b7da90e79c78..85b5b6310acc 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -1070,7 +1070,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
         if (smp_num_siblings * c->x86_max_cores > 1) {
                 int cpu = c - cpu_data;
                 seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-                seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[cpu]));
+                seq_printf(m, "siblings\t: %d\n",
+                               cpus_weight(per_cpu(cpu_core_map, cpu)));
                 seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
                 seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
         }
diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c
index e4f61d1c6248..31fc08bd15ef 100644
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -70,12 +70,12 @@ EXPORT_SYMBOL(smp_num_siblings);
 int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID};
 
 /* representing HT siblings of each logical CPU */
-cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* bitmap of online cpus */
 cpumask_t cpu_online_map __read_mostly;
@@ -300,7 +300,7 @@ cpumask_t cpu_coregroup_map(int cpu)
          * And for power savings, we return cpu_core_map
          */
         if (sched_mc_power_savings || sched_smt_power_savings)
-                return cpu_core_map[cpu];
+                return per_cpu(cpu_core_map, cpu);
         else
                 return c->llc_shared_map;
 }
@@ -319,22 +319,22 @@ void __cpuinit set_cpu_sibling_map(int cpu)
                 for_each_cpu_mask(i, cpu_sibling_setup_map) {
                         if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
                             c[cpu].cpu_core_id == c[i].cpu_core_id) {
-                                cpu_set(i, cpu_sibling_map[cpu]);
-                                cpu_set(cpu, cpu_sibling_map[i]);
-                                cpu_set(i, cpu_core_map[cpu]);
-                                cpu_set(cpu, cpu_core_map[i]);
+                                cpu_set(i, per_cpu(cpu_sibling_map, cpu));
+                                cpu_set(cpu, per_cpu(cpu_sibling_map, i));
+                                cpu_set(i, per_cpu(cpu_core_map, cpu));
+                                cpu_set(cpu, per_cpu(cpu_core_map, i));
                                 cpu_set(i, c[cpu].llc_shared_map);
                                 cpu_set(cpu, c[i].llc_shared_map);
                         }
                 }
         } else {
-                cpu_set(cpu, cpu_sibling_map[cpu]);
+                cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
         }
 
         cpu_set(cpu, c[cpu].llc_shared_map);
 
         if (current_cpu_data.x86_max_cores == 1) {
-                cpu_core_map[cpu] = cpu_sibling_map[cpu];
+                per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
                 c[cpu].booted_cores = 1;
                 return;
         }
@@ -346,17 +346,17 @@ void __cpuinit set_cpu_sibling_map(int cpu)
                         cpu_set(cpu, c[i].llc_shared_map);
                 }
                 if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
-                        cpu_set(i, cpu_core_map[cpu]);
-                        cpu_set(cpu, cpu_core_map[i]);
+                        cpu_set(i, per_cpu(cpu_core_map, cpu));
+                        cpu_set(cpu, per_cpu(cpu_core_map, i));
                         /*
                          *  Does this new cpu bringup a new core?
                          */
-                        if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+                        if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
                                 /*
                                  * for each core in package, increment
                                  * the booted_cores for this new cpu
                                  */
-                                if (first_cpu(cpu_sibling_map[i]) == i)
+                                if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
                                         c[cpu].booted_cores++;
                                 /*
                                  * increment the core count for all
@@ -983,8 +983,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
                         printk(KERN_NOTICE "Local APIC not detected."
                                            " Using dummy APIC emulation.\n");
                 map_cpu_to_logical_apicid();
-                cpu_set(0, cpu_sibling_map[0]);
-                cpu_set(0, cpu_core_map[0]);
+                cpu_set(0, per_cpu(cpu_sibling_map, 0));
+                cpu_set(0, per_cpu(cpu_core_map, 0));
                 return;
         }
 
@@ -1008,8 +1008,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
                 printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n");
                 smpboot_clear_io_apic_irqs();
                 phys_cpu_present_map = physid_mask_of_physid(0);
-                cpu_set(0, cpu_sibling_map[0]);
-                cpu_set(0, cpu_core_map[0]);
+                cpu_set(0, per_cpu(cpu_sibling_map, 0));
+                cpu_set(0, per_cpu(cpu_core_map, 0));
                 return;
         }
 
@@ -1023,8 +1023,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
                 printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
                 smpboot_clear_io_apic_irqs();
                 phys_cpu_present_map = physid_mask_of_physid(0);
-                cpu_set(0, cpu_sibling_map[0]);
-                cpu_set(0, cpu_core_map[0]);
+                cpu_set(0, per_cpu(cpu_sibling_map, 0));
+                cpu_set(0, per_cpu(cpu_core_map, 0));
                 return;
         }
 
@@ -1102,16 +1102,16 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
         Dprintk("Boot done.\n");
 
         /*
-         * construct cpu_sibling_map[], so that we can tell sibling CPUs
+         * construct cpu_sibling_map, so that we can tell sibling CPUs
          * efficiently.
          */
         for (cpu = 0; cpu < NR_CPUS; cpu++) {
-                cpus_clear(cpu_sibling_map[cpu]);
-                cpus_clear(cpu_core_map[cpu]);
+                cpus_clear(per_cpu(cpu_sibling_map, cpu));
+                cpus_clear(per_cpu(cpu_core_map, cpu));
         }
 
-        cpu_set(0, cpu_sibling_map[0]);
-        cpu_set(0, cpu_core_map[0]);
+        cpu_set(0, per_cpu(cpu_sibling_map, 0));
+        cpu_set(0, per_cpu(cpu_core_map, 0));
 
         smpboot_setup_io_apic();
 
@@ -1148,19 +1148,19 @@ void remove_siblinginfo(int cpu)
         int sibling;
         struct cpuinfo_x86 *c = cpu_data;
 
-        for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
-                cpu_clear(cpu, cpu_core_map[sibling]);
-                /*
+        for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
+                cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
+                /*/
                  * last thread sibling in this cpu core going down
                  */
-                if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+                if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
                         c[sibling].booted_cores--;
         }
                         
-        for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
-                cpu_clear(cpu, cpu_sibling_map[sibling]);
-        cpus_clear(cpu_sibling_map[cpu]);
-        cpus_clear(cpu_core_map[cpu]);
+        for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
+                cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
+        cpus_clear(per_cpu(cpu_sibling_map, cpu));
+        cpus_clear(per_cpu(cpu_core_map, cpu));
         c[cpu].phys_proc_id = 0;
         c[cpu].cpu_core_id = 0;
         cpu_clear(cpu, cpu_sibling_setup_map);
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 720a7d1f8862..0faa0a0af272 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -91,12 +91,12 @@ EXPORT_SYMBOL(cpu_data);
 int smp_threads_ready;
 
 /* representing HT siblings of each logical CPU */
-cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /*
  * Trampoline 80x86 program as an array.
@@ -243,7 +243,7 @@ cpumask_t cpu_coregroup_map(int cpu)
          * And for power savings, we return cpu_core_map
          */
         if (sched_mc_power_savings || sched_smt_power_savings)
-                return cpu_core_map[cpu];
+                return per_cpu(cpu_core_map, cpu);
         else
                 return c->llc_shared_map;
 }
@@ -262,22 +262,22 @@ static inline void set_cpu_sibling_map(int cpu)
                 for_each_cpu_mask(i, cpu_sibling_setup_map) {
                         if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
                             c[cpu].cpu_core_id == c[i].cpu_core_id) {
-                                cpu_set(i, cpu_sibling_map[cpu]);
-                                cpu_set(cpu, cpu_sibling_map[i]);
-                                cpu_set(i, cpu_core_map[cpu]);
-                                cpu_set(cpu, cpu_core_map[i]);
+                                cpu_set(i, per_cpu(cpu_sibling_map, cpu));
+                                cpu_set(cpu, per_cpu(cpu_sibling_map, i));
+                                cpu_set(i, per_cpu(cpu_core_map, cpu));
+                                cpu_set(cpu, per_cpu(cpu_core_map, i));
                                 cpu_set(i, c[cpu].llc_shared_map);
                                 cpu_set(cpu, c[i].llc_shared_map);
                         }
                 }
         } else {
-                cpu_set(cpu, cpu_sibling_map[cpu]);
+                cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
         }
 
         cpu_set(cpu, c[cpu].llc_shared_map);
 
         if (current_cpu_data.x86_max_cores == 1) {
-                cpu_core_map[cpu] = cpu_sibling_map[cpu];
+                per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
                 c[cpu].booted_cores = 1;
                 return;
         }
@@ -289,17 +289,17 @@ static inline void set_cpu_sibling_map(int cpu)
                         cpu_set(cpu, c[i].llc_shared_map);
                 }
                 if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
-                        cpu_set(i, cpu_core_map[cpu]);
-                        cpu_set(cpu, cpu_core_map[i]);
+                        cpu_set(i, per_cpu(cpu_core_map, cpu));
+                        cpu_set(cpu, per_cpu(cpu_core_map, i));
                         /*
                          *  Does this new cpu bringup a new core?
                          */
-                        if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+                        if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
                                 /*
                                  * for each core in package, increment
                                  * the booted_cores for this new cpu
                                  */
-                                if (first_cpu(cpu_sibling_map[i]) == i)
+                                if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
                                         c[cpu].booted_cores++;
                                 /*
                                  * increment the core count for all
@@ -735,8 +735,8 @@ static __init void disable_smp(void)
                 phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
         else
                 phys_cpu_present_map = physid_mask_of_physid(0);
-        cpu_set(0, cpu_sibling_map[0]);
-        cpu_set(0, cpu_core_map[0]);
+        cpu_set(0, per_cpu(cpu_sibling_map, 0));
+        cpu_set(0, per_cpu(cpu_core_map, 0));
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -971,19 +971,19 @@ static void remove_siblinginfo(int cpu)
         int sibling;
         struct cpuinfo_x86 *c = cpu_data;
 
-        for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
-                cpu_clear(cpu, cpu_core_map[sibling]);
+        for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
+                cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
                 /*
                  * last thread sibling in this cpu core going down
                  */
-                if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+                if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
                         c[sibling].booted_cores--;
         }
                         
-        for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
-                cpu_clear(cpu, cpu_sibling_map[sibling]);
-        cpus_clear(cpu_sibling_map[cpu]);
-        cpus_clear(cpu_core_map[cpu]);
+        for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
+                cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
+        cpus_clear(per_cpu(cpu_sibling_map, cpu));
+        cpus_clear(per_cpu(cpu_core_map, cpu));
         c[cpu].phys_proc_id = 0;
         c[cpu].cpu_core_id = 0;
         cpu_clear(cpu, cpu_sibling_setup_map);
diff --git a/arch/x86/mm/fault_32.c b/arch/x86/mm/fault_32.c
index fcb38e7f3543..c686ae20fd6b 100644
--- a/arch/x86/mm/fault_32.c
+++ b/arch/x86/mm/fault_32.c
@@ -25,6 +25,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/desc.h>
@@ -32,33 +33,27 @@
 
 extern void die(const char *,struct pt_regs *,long);
 
-static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
-
-int register_page_fault_notifier(struct notifier_block *nb)
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs)
 {
-        vmalloc_sync_all();
-        return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
-}
-EXPORT_SYMBOL_GPL(register_page_fault_notifier);
+        int ret = 0;
+
+        /* kprobe_running() needs smp_processor_id() */
+        if (!user_mode_vm(regs)) {
+                preempt_disable();
+                if (kprobe_running() && kprobe_fault_handler(regs, 14))
+                        ret = 1;
+                preempt_enable();
+        }
 
-int unregister_page_fault_notifier(struct notifier_block *nb)
-{
-        return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+        return ret;
 }
-EXPORT_SYMBOL_GPL(unregister_page_fault_notifier);
-
-static inline int notify_page_fault(struct pt_regs *regs, long err)
+#else
+static inline int notify_page_fault(struct pt_regs *regs)
 {
-        struct die_args args = {
-                .regs = regs,
-                .str = "page fault",
-                .err = err,
-                .trapnr = 14,
-                .signr = SIGSEGV
-        };
-        return atomic_notifier_call_chain(&notify_page_fault_chain,
-                                          DIE_PAGE_FAULT, &args);
+        return 0;
 }
+#endif
 
 /*
  * Return EIP plus the CS segment base.  The segment limit is also
@@ -331,7 +326,7 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
         if (unlikely(address >= TASK_SIZE)) {
                 if (!(error_code & 0x0000000d) && vmalloc_fault(address) >= 0)
                         return;
-                if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+                if (notify_page_fault(regs))
                         return;
                 /*
                  * Don't take the mm semaphore here. If we fixup a prefetch
@@ -340,7 +335,7 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
                 goto bad_area_nosemaphore;
         }
 
-        if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+        if (notify_page_fault(regs))
                 return;
 
         /* It's safe to allow irq's after cr2 has been saved and the vmalloc
@@ -598,7 +593,7 @@ out_of_memory:
         }
         printk("VM: killing process %s\n", tsk->comm);
         if (error_code & 4)
-                do_exit(SIGKILL);
+                do_group_exit(SIGKILL);
         goto no_context;
 
 do_sigbus:
diff --git a/arch/x86/mm/fault_64.c b/arch/x86/mm/fault_64.c
index 54816adb8e93..5e0e54906c48 100644
--- a/arch/x86/mm/fault_64.c
+++ b/arch/x86/mm/fault_64.c
@@ -25,6 +25,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/pgalloc.h>
@@ -40,34 +41,27 @@
 #define PF_RSVD (1<<3)
 #define PF_INSTR        (1<<4)
 
-static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
-
-/* Hook to register for page fault notifications */
-int register_page_fault_notifier(struct notifier_block *nb)
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs)
 {
-        vmalloc_sync_all();
-        return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
-}
-EXPORT_SYMBOL_GPL(register_page_fault_notifier);
+        int ret = 0;
+
+        /* kprobe_running() needs smp_processor_id() */
+        if (!user_mode(regs)) {
+                preempt_disable();
+                if (kprobe_running() && kprobe_fault_handler(regs, 14))
+                        ret = 1;
+                preempt_enable();
+        }
 
-int unregister_page_fault_notifier(struct notifier_block *nb)
-{
-        return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+        return ret;
 }
-EXPORT_SYMBOL_GPL(unregister_page_fault_notifier);
-
-static inline int notify_page_fault(struct pt_regs *regs, long err)
+#else
+static inline int notify_page_fault(struct pt_regs *regs)
 {
-        struct die_args args = {
-                .regs = regs,
-                .str = "page fault",
-                .err = err,
-                .trapnr = 14,
-                .signr = SIGSEGV
-        };
-        return atomic_notifier_call_chain(&notify_page_fault_chain,
-                                          DIE_PAGE_FAULT, &args);
+        return 0;
 }
+#endif
 
 /* Sometimes the CPU reports invalid exceptions on prefetch.
    Check that here and ignore.
@@ -345,7 +339,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                         if (vmalloc_fault(address) >= 0)
                                 return;
                 }
-                if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+                if (notify_page_fault(regs))
                         return;
                 /*
                  * Don't take the mm semaphore here. If we fixup a prefetch
@@ -354,7 +348,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                 goto bad_area_nosemaphore;
         }
 
-        if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+        if (notify_page_fault(regs))
                 return;
 
         if (likely(regs->eflags & X86_EFLAGS_IF))
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 730a5b177b1f..dda4e83649a0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -735,11 +735,6 @@ int arch_add_memory(int nid, u64 start, u64 size)
         return __add_pages(zone, start_pfn, nr_pages);
 }
 
-int remove_memory(u64 start, u64 size)
-{
-        return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(remove_memory);
 #endif
 
 struct kmem_cache *pmd_cache;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 458893b376f8..1e3862e41065 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -474,12 +474,6 @@ error:
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
-int remove_memory(u64 start, u64 size)
-{
-        return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(remove_memory);
-
 #if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
 int memory_add_physaddr_to_nid(u64 start)
 {
@@ -748,3 +742,48 @@ const char *arch_vma_name(struct vm_area_struct *vma)
                 return "[vsyscall]";
         return NULL;
 }
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/*
+ * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
+ */
+int __meminit vmemmap_populate(struct page *start_page,
+                                                unsigned long size, int node)
+{
+        unsigned long addr = (unsigned long)start_page;
+        unsigned long end = (unsigned long)(start_page + size);
+        unsigned long next;
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+
+        for (; addr < end; addr = next) {
+                next = pmd_addr_end(addr, end);
+
+                pgd = vmemmap_pgd_populate(addr, node);
+                if (!pgd)
+                        return -ENOMEM;
+                pud = vmemmap_pud_populate(pgd, addr, node);
+                if (!pud)
+                        return -ENOMEM;
+
+                pmd = pmd_offset(pud, addr);
+                if (pmd_none(*pmd)) {
+                        pte_t entry;
+                        void *p = vmemmap_alloc_block(PMD_SIZE, node);
+                        if (!p)
+                                return -ENOMEM;
+
+                        entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+                        mk_pte_huge(entry);
+                        set_pmd(pmd, __pmd(pte_val(entry)));
+
+                        printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
+                                addr, addr + PMD_SIZE - 1, p, node);
+                } else
+                        vmemmap_verify((pte_t *)pmd, node, addr, next);
+        }
+
+        return 0;
+}
+#endif
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 47925927b12f..56b4757a1f47 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -379,7 +379,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
         int cpu = smp_processor_id();
-        return (cpu != first_cpu(cpu_sibling_map[cpu]));
+        return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
 #endif  
         return 0;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 557b8e24706a..4fa33c27ccb6 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -147,8 +147,13 @@ void __init xen_smp_prepare_boot_cpu(void)
         make_lowmem_page_readwrite(&per_cpu__gdt_page);
 
         for (cpu = 0; cpu < NR_CPUS; cpu++) {
-                cpus_clear(cpu_sibling_map[cpu]);
-                cpus_clear(cpu_core_map[cpu]);
+                cpus_clear(per_cpu(cpu_sibling_map, cpu));
+                /*
+                 * cpu_core_map lives in a per cpu area that is cleared
+                 * when the per cpu array is allocated.
+                 *
+                 * cpus_clear(per_cpu(cpu_core_map, cpu));
+                 */
         }
 
         xen_setup_vcpu_info_placement();
@@ -159,8 +164,13 @@ void __init xen_smp_prepare_cpus(unsigned int max_cpus)
         unsigned cpu;
 
         for (cpu = 0; cpu < NR_CPUS; cpu++) {
-                cpus_clear(cpu_sibling_map[cpu]);
-                cpus_clear(cpu_core_map[cpu]);
+                cpus_clear(per_cpu(cpu_sibling_map, cpu));
+                /*
+                 * cpu_core_ map will be zeroed when the per
+                 * cpu area is allocated.
+                 *
+                 * cpus_clear(per_cpu(cpu_core_map, cpu));
+                 */
         }
 
         smp_store_cpu_info(0);