16 files changed, 189 insertions, 103 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index efd30ccf3858..167e1e3ad7c6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -980,12 +980,9 @@ static void check_stack_usage(void)
 {
         static DEFINE_SPINLOCK(low_water_lock);
         static int lowest_to_date = THREAD_SIZE;
-        unsigned long *n = end_of_stack(current);
         unsigned long free;
 
-        while (*n == 0)
-                n++;
-        free = (unsigned long)n - (unsigned long)end_of_stack(current);
+        free = stack_not_used(current);
 
         if (free >= lowest_to_date)
                 return;
diff --git a/kernel/fork.c b/kernel/fork.c
index 4854c2c4a82e..6715ebc3761d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,6 +61,7 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <trace/sched.h>
+#include <linux/magic.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -212,6 +213,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
         struct task_struct *tsk;
         struct thread_info *ti;
+        unsigned long *stackend;
+
         int err;
 
         prepare_to_copy(orig);
@@ -237,6 +240,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
                 goto out;
 
         setup_thread_stack(tsk, orig);
+        stackend = end_of_stack(tsk);
+        *stackend = STACK_END_MAGIC;    /* for overflow detection */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
         tsk->stack_canary = get_random_int();
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 03d0bed2b8d9..c687ba4363f2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq)
         desc->irq_count = 0;
         desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-        cpumask_setall(&desc->affinity);
+        cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        cpumask_clear(desc->pending_mask);
+#endif
 #endif
         spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f6cdda68e5c6..9ebf77968871 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
+#include <linux/bootmem.h>
 
 #include "internals.h"
 
@@ -69,6 +70,7 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
+
 static struct irq_desc irq_desc_init = {
         .irq        = -1,
         .status     = IRQ_DISABLED,
@@ -76,9 +78,6 @@ static struct irq_desc irq_desc_init = {
         .handle_irq = handle_bad_irq,
         .depth      = 1,
         .lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-        .affinity   = CPU_MASK_ALL
-#endif
 };
 
 void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
@@ -115,6 +114,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
                 printk(KERN_ERR "can not alloc kstat_irqs\n");
                 BUG_ON(1);
         }
+        if (!init_alloc_desc_masks(desc, cpu, false)) {
+                printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+                BUG_ON(1);
+        }
         arch_init_chip_data(desc, cpu);
 }
 
@@ -123,7 +126,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
  */
 DEFINE_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+struct irq_desc **irq_desc_ptrs __read_mostly;
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
         [0 ... NR_IRQS_LEGACY-1] = {
@@ -133,14 +136,10 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
                 .handle_irq = handle_bad_irq,
                 .depth      = 1,
                 .lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-                .affinity   = CPU_MASK_ALL
-#endif
         }
 };
 
-/* FIXME: use bootmem alloc ...*/
-static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+static unsigned int *kstat_irqs_legacy;
 
 int __init early_irq_init(void)
 {
@@ -150,18 +149,30 @@ int __init early_irq_init(void)
 
         init_irq_default_affinity();
 
+         /* initialize nr_irqs based on nr_cpu_ids */
+        arch_probe_nr_irqs();
+        printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
+
         desc = irq_desc_legacy;
         legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
+        /* allocate irq_desc_ptrs array based on nr_irqs */
+        irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+
+        /* allocate based on nr_cpu_ids */
+        /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
+        kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
+                                          sizeof(int));
+
         for (i = 0; i < legacy_count; i++) {
                 desc[i].irq = i;
-                desc[i].kstat_irqs = kstat_irqs_legacy[i];
+                desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
                 lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-
+                init_alloc_desc_masks(&desc[i], 0, true);
                 irq_desc_ptrs[i] = desc + i;
         }
 
-        for (i = legacy_count; i < NR_IRQS; i++)
+        for (i = legacy_count; i < nr_irqs; i++)
                 irq_desc_ptrs[i] = NULL;
 
         return arch_early_irq_init();
@@ -169,7 +180,10 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-        return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+        if (irq_desc_ptrs && irq < nr_irqs)
+                return irq_desc_ptrs[irq];
+
+        return NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
@@ -178,10 +192,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
         unsigned long flags;
         int node;
 
-        if (irq >= NR_IRQS) {
-                printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
-                                irq, NR_IRQS);
-                WARN_ON(1);
+        if (irq >= nr_irqs) {
+                WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
+                        irq, nr_irqs);
                 return NULL;
         }
 
@@ -223,9 +236,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
                 .handle_irq = handle_bad_irq,
                 .depth = 1,
                 .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
-                .affinity = CPU_MASK_ALL
-#endif
         }
 };
 
@@ -238,14 +248,16 @@ int __init early_irq_init(void)
 
         init_irq_default_affinity();
 
+        printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
         desc = irq_desc;
         count = ARRAY_SIZE(irq_desc);
 
         for (i = 0; i < count; i++) {
                 desc[i].irq = i;
+                init_alloc_desc_masks(&desc[i], 0, true);
                 desc[i].kstat_irqs = kstat_irqs_all[i];
         }
-
         return arch_early_irq_init();
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b60950bf5a16..ee1aa9f8e8b9 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -17,7 +17,14 @@ extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
 extern void clear_kstat_irqs(struct irq_desc *desc);
 extern spinlock_t sparse_irq_lock;
+
+#ifdef CONFIG_SPARSE_IRQ
+/* irq_desc_ptrs allocated at boot time */
+extern struct irq_desc **irq_desc_ptrs;
+#else
+/* irq_desc_ptrs is a fixed size array */
 extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+#endif
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ea119effe096..6458e99984c0 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -90,14 +90,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-                cpumask_copy(&desc->affinity, cpumask);
+                cpumask_copy(desc->affinity, cpumask);
                 desc->chip->set_affinity(irq, cpumask);
         } else {
                 desc->status |= IRQ_MOVE_PENDING;
-                cpumask_copy(&desc->pending_mask, cpumask);
+                cpumask_copy(desc->pending_mask, cpumask);
         }
 #else
-        cpumask_copy(&desc->affinity, cpumask);
+        cpumask_copy(desc->affinity, cpumask);
         desc->chip->set_affinity(irq, cpumask);
 #endif
         desc->status |= IRQ_AFFINITY_SET;
@@ -119,16 +119,16 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
          * one of the targets is online.
          */
         if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-                if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+                if (cpumask_any_and(desc->affinity, cpu_online_mask)
                     < nr_cpu_ids)
                         goto set_affinity;
                 else
                         desc->status &= ~IRQ_AFFINITY_SET;
         }
 
-        cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+        cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-        desc->chip->set_affinity(irq, &desc->affinity);
+        desc->chip->set_affinity(irq, desc->affinity);
 
         return 0;
 }
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index bd72329e630c..e05ad9be43b7 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@ void move_masked_irq(int irq)
 
         desc->status &= ~IRQ_MOVE_PENDING;
 
-        if (unlikely(cpumask_empty(&desc->pending_mask)))
+        if (unlikely(cpumask_empty(desc->pending_mask)))
                 return;
 
         if (!desc->chip->set_affinity)
@@ -38,13 +38,13 @@ void move_masked_irq(int irq)
          * For correct operation this depends on the caller
          * masking the irqs.
          */
-        if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+        if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
                    < nr_cpu_ids)) {
-                cpumask_and(&desc->affinity,
-                            &desc->pending_mask, cpu_online_mask);
-                desc->chip->set_affinity(irq, &desc->affinity);
+                cpumask_and(desc->affinity,
+                            desc->pending_mask, cpu_online_mask);
+                desc->chip->set_affinity(irq, desc->affinity);
         }
-        cpumask_clear(&desc->pending_mask);
+        cpumask_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index aef18ab6b75b..243d6121e50e 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -33,15 +33,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
         old_desc->kstat_irqs = NULL;
 }
 
-static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
                  struct irq_desc *desc, int cpu)
 {
         memcpy(desc, old_desc, sizeof(struct irq_desc));
+        if (!init_alloc_desc_masks(desc, cpu, false)) {
+                printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+                                "for migration.\n", irq);
+                return false;
+        }
         spin_lock_init(&desc->lock);
         desc->cpu = cpu;
         lockdep_set_class(&desc->lock, &irq_desc_lock_class);
         init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+        init_copy_desc_masks(old_desc, desc);
         arch_init_copy_chip_data(old_desc, desc, cpu);
+        return true;
 }
 
 static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
@@ -71,12 +78,18 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
         node = cpu_to_node(cpu);
         desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
         if (!desc) {
-                printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+                printk(KERN_ERR "irq %d: can not get new irq_desc "
+                                "for migration.\n", irq);
+                /* still use old one */
+                desc = old_desc;
+                goto out_unlock;
+        }
+        if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
                 /* still use old one */
+                kfree(desc);
                 desc = old_desc;
                 goto out_unlock;
         }
-        init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
         irq_desc_ptrs[irq] = desc;
         spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index aae3f742bcec..692363dd591f 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
         struct irq_desc *desc = irq_to_desc((long)m->private);
-        const struct cpumask *mask = &desc->affinity;
+        const struct cpumask *mask = desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PENDING)
-                mask = &desc->pending_mask;
+                mask = desc->pending_mask;
 #endif
         seq_cpumask(m, mask);
         seq_putc(m, '\n');
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 483899578259..c7fd6692939d 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1130,7 +1130,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
                 return;
         memset(&prstatus, 0, sizeof(prstatus));
         prstatus.pr_pid = current->pid;
-        elf_core_copy_regs(&prstatus.pr_reg, regs);
+        elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
         buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
                               &prstatus, sizeof(prstatus));
         final_note(buf);
diff --git a/kernel/module.c b/kernel/module.c
index 1196f5d11700..29f2d7b33dd4 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -51,6 +51,7 @@
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/percpu.h>
 
 #if 0
 #define DEBUGP printk
@@ -366,6 +367,34 @@ static struct module *find_module(const char *name)
 }
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+static void *percpu_modalloc(unsigned long size, unsigned long align,
+                             const char *name)
+{
+        void *ptr;
+
+        if (align > PAGE_SIZE) {
+                printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
+                       name, align, PAGE_SIZE);
+                align = PAGE_SIZE;
+        }
+
+        ptr = __alloc_reserved_percpu(size, align);
+        if (!ptr)
+                printk(KERN_WARNING
+                       "Could not allocate %lu bytes percpu data\n", size);
+        return ptr;
+}
+
+static void percpu_modfree(void *freeme)
+{
+        free_percpu(freeme);
+}
+
+#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
 /* Number of blocks used and allocated. */
 static unsigned int pcpu_num_used, pcpu_num_allocated;
 /* Size of each block.  -ve means used. */
@@ -480,21 +509,6 @@ static void percpu_modfree(void *freeme)
         }
 }
 
-static unsigned int find_pcpusec(Elf_Ehdr *hdr,
-                                 Elf_Shdr *sechdrs,
-                                 const char *secstrings)
-{
-        return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
-}
-
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
-{
-        int cpu;
-
-        for_each_possible_cpu(cpu)
-                memcpy(pcpudest + per_cpu_offset(cpu), from, size);
-}
-
 static int percpu_modinit(void)
 {
         pcpu_num_used = 2;
@@ -513,7 +527,26 @@ static int percpu_modinit(void)
         return 0;
 }
 __initcall(percpu_modinit);
+
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
+static unsigned int find_pcpusec(Elf_Ehdr *hdr,
+                                 Elf_Shdr *sechdrs,
+                                 const char *secstrings)
+{
+        return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
+}
+
+static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+}
+
 #else /* ... !CONFIG_SMP */
+
 static inline void *percpu_modalloc(unsigned long size, unsigned long align,
                                     const char *name)
 {
@@ -535,6 +568,7 @@ static inline void percpu_modcopy(void *pcpudst, const void *src,
         /* pcpusec should be 0, and size of that section should be 0. */
         BUG_ON(size != 0);
 }
+
 #endif /* CONFIG_SMP */
 
 #define MODINFO_ATTR(field)     \
diff --git a/kernel/panic.c b/kernel/panic.c
index 2a2ff36ff44d..32fe4eff1b89 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -74,6 +74,9 @@ NORET_TYPE void panic(const char * fmt, ...)
         vsnprintf(buf, sizeof(buf), fmt, args);
         va_end(args);
         printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+        dump_stack();
+#endif
         bust_spinlocks(0);
 
         /*
@@ -355,15 +358,18 @@ EXPORT_SYMBOL(warn_slowpath);
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
+
 /*
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
 void __stack_chk_fail(void)
 {
-        panic("stack-protector: Kernel stack is corrupted");
+        panic("stack-protector: Kernel stack is corrupted in: %p\n",
+                __builtin_return_address(0));
 }
 EXPORT_SYMBOL(__stack_chk_fail);
+
 #endif
 
 core_param(panic, panic_timeout, int, 0644);
diff --git a/kernel/sched.c b/kernel/sched.c
index 8e2558c2ba67..11dd52780adb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3448,19 +3448,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 #define MAX_PINNED_INTERVAL     512
 
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
                         struct sched_domain *sd, enum cpu_idle_type idle,
-                        int *balance, struct cpumask *cpus)
+                        int *balance)
 {
         int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
         struct sched_group *group;
         unsigned long imbalance;
         struct rq *busiest;
         unsigned long flags;
+        struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
         cpumask_setall(cpus);
 
@@ -3615,8 +3619,7 @@ out:
  * this_rq is locked.
  */
 static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-                        struct cpumask *cpus)
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 {
         struct sched_group *group;
         struct rq *busiest = NULL;
@@ -3624,6 +3627,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
         int ld_moved = 0;
         int sd_idle = 0;
         int all_pinned = 0;
+        struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
         cpumask_setall(cpus);
 
@@ -3764,10 +3768,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
         struct sched_domain *sd;
         int pulled_task = 0;
         unsigned long next_balance = jiffies + HZ;
-        cpumask_var_t tmpmask;
-
-        if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-                return;
 
         for_each_domain(this_cpu, sd) {
                 unsigned long interval;
@@ -3778,7 +3778,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                 if (sd->flags & SD_BALANCE_NEWIDLE)
                         /* If we've pulled tasks over stop searching: */
                         pulled_task = load_balance_newidle(this_cpu, this_rq,
-                                                           sd, tmpmask);
+                                                           sd);
 
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
@@ -3793,7 +3793,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                  */
                 this_rq->next_balance = next_balance;
         }
-        free_cpumask_var(tmpmask);
 }
 
 /*
@@ -3943,11 +3942,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
         unsigned long next_balance = jiffies + 60*HZ;
         int update_next_balance = 0;
         int need_serialize;
-        cpumask_var_t tmp;
-
-        /* Fails alloc?  Rebalancing probably not a priority right now. */
-        if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
-                return;
 
         for_each_domain(cpu, sd) {
                 if (!(sd->flags & SD_LOAD_BALANCE))
@@ -3972,7 +3966,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
                 }
 
                 if (time_after_eq(jiffies, sd->last_balance + interval)) {
-                        if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+                        if (load_balance(cpu, rq, sd, idle, &balance)) {
                                 /*
                                  * We've pulled tasks over so either we're no
                                  * longer idle, or one of our SMT siblings is
@@ -4006,8 +4000,6 @@ out:
          */
         if (likely(update_next_balance))
                 rq->next_balance = next_balance;
-
-        free_cpumask_var(tmp);
 }
 
 /*
@@ -5944,12 +5936,7 @@ void sched_show_task(struct task_struct *p)
                 printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-        {
-                unsigned long *n = end_of_stack(p);
-                while (!*n)
-                        n++;
-                free = (unsigned long)n - (unsigned long)end_of_stack(p);
-        }
+        free = stack_not_used(p);
 #endif
         printk(KERN_CONT "%5lu %5d %6d\n", free,
                 task_pid_nr(p), task_pid_nr(p->real_parent));
@@ -7254,7 +7241,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
         int group;
 
-        cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+        cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
         group = cpumask_first(mask);
         if (sg)
                 *sg = &per_cpu(sched_group_core, group).sg;
@@ -7283,7 +7270,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
         cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
         group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-        cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+        cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
         group = cpumask_first(mask);
 #else
         group = cpu;
@@ -7626,7 +7613,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 SD_INIT(sd, SIBLING);
                 set_domain_attribute(sd, attr);
                 cpumask_and(sched_domain_span(sd),
-                            &per_cpu(cpu_sibling_map, i), cpu_map);
+                            topology_thread_cpumask(i), cpu_map);
                 sd->parent = p;
                 p->child = sd;
                 cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7637,7 +7624,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
         /* Set up CPU (sibling) groups */
         for_each_cpu(i, cpu_map) {
                 cpumask_and(this_sibling_map,
-                            &per_cpu(cpu_sibling_map, i), cpu_map);
+                            topology_thread_cpumask(i), cpu_map);
                 if (i != cpumask_first(this_sibling_map))
                         continue;
 
@@ -8309,6 +8296,9 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
         alloc_size *= 2;
 #endif
+#ifdef CONFIG_CPUMASK_OFFSTACK
+        alloc_size += num_possible_cpus() * cpumask_size();
+#endif
         /*
          * As sched_init() is called before page_alloc is setup,
          * we use alloc_bootmem().
@@ -8346,6 +8336,12 @@ void __init sched_init(void)
                 ptr += nr_cpu_ids * sizeof(void **);
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+                for_each_possible_cpu(i) {
+                        per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+                        ptr += cpumask_size();
+                }
+#endif /* CONFIG_CPUMASK_OFFSTACK */
         }
 
 #ifdef CONFIG_SMP
@@ -9490,7 +9486,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
 static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 {
-        u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+        u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
         u64 data;
 
 #ifndef CONFIG_64BIT
@@ -9509,7 +9505,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 
 static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
 {
-        u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+        u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 
 #ifndef CONFIG_64BIT
         /*
@@ -9605,7 +9601,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
         ca = task_ca(tsk);
 
         for (; ca; ca = ca->parent) {
-                u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+                u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
                 *cpuusage += cputime;
         }
 }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index bac1061cea2f..da932f4c8524 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -960,12 +960,13 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
+static inline int pick_optimal_cpu(int this_cpu,
+                                   const struct cpumask *mask)
 {
         int first;
 
         /* "this_cpu" is cheaper to preempt than a remote processor */
-        if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
+        if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
                 return this_cpu;
 
         first = cpumask_first(mask);
@@ -981,6 +982,7 @@ static int find_lowest_rq(struct task_struct *task)
         struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
         int this_cpu = smp_processor_id();
         int cpu      = task_cpu(task);
+        cpumask_var_t domain_mask;
 
         if (task->rt.nr_cpus_allowed == 1)
                 return -1; /* No other targets possible */
@@ -1013,19 +1015,25 @@ static int find_lowest_rq(struct task_struct *task)
         if (this_cpu == cpu)
                 this_cpu = -1; /* Skip this_cpu opt if the same */
 
-        for_each_domain(cpu, sd) {
-                if (sd->flags & SD_WAKE_AFFINE) {
-                        cpumask_t domain_mask;
-                        int       best_cpu;
+        if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
+                for_each_domain(cpu, sd) {
+                        if (sd->flags & SD_WAKE_AFFINE) {
+                                int best_cpu;
 
-                        cpumask_and(&domain_mask, sched_domain_span(sd),
-                                    lowest_mask);
+                                cpumask_and(domain_mask,
+                                            sched_domain_span(sd),
+                                            lowest_mask);
 
-                        best_cpu = pick_optimal_cpu(this_cpu,
-                                                    &domain_mask);
-                        if (best_cpu != -1)
-                                return best_cpu;
+                                best_cpu = pick_optimal_cpu(this_cpu,
+                                                            domain_mask);
+
+                                if (best_cpu != -1) {
+                                        free_cpumask_var(domain_mask);
+                                        return best_cpu;
+                                }
+                        }
                 }
+                free_cpumask_var(domain_mask);
         }
 
         /*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9041ea7948fe..57d3f67f6f38 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -796,6 +796,11 @@ int __init __weak early_irq_init(void)
         return 0;
 }
 
+int __init __weak arch_probe_nr_irqs(void)
+{
+        return 0;
+}
+
 int __init __weak arch_early_irq_init(void)
 {
         return 0;
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 0cd415ee62a2..74541ca49536 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -170,7 +170,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
          * doesn't hit this CPU until we're ready. */
         get_cpu();
         for_each_online_cpu(i) {
-                sm_work = percpu_ptr(stop_machine_work, i);
+                sm_work = per_cpu_ptr(stop_machine_work, i);
                 INIT_WORK(sm_work, stop_cpu);
                 queue_work_on(i, stop_machine_wq, sm_work);
         }