15 files changed, 89 insertions, 51 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4349935c2ad8..e92e98189032 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
                 return -ENODEV;
 
         trialcs = alloc_trial_cpuset(cs);
-        if (!trialcs)
-                return -ENOMEM;
+        if (!trialcs) {
+                retval = -ENOMEM;
+                goto out;
+        }
 
         switch (cft->private) {
         case FILE_CPULIST:
@@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
         }
 
         free_trial_cpuset(trialcs);
+out:
         cgroup_unlock();
         return retval;
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4571ae7e085a..99c3bc8a6fb4 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -3,6 +3,12 @@
  */
 #include <linux/irqdesc.h>
 
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS        (NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS        NR_IRQS
+#endif
+
 extern int noirqdebug;
 
 #define irq_data_to_desc(data)  container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 282f20230e67..2039bea31bdf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
@@ -217,6 +217,15 @@ int __init early_irq_init(void)
         initcnt = arch_probe_nr_irqs();
         printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
 
+        if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+                nr_irqs = IRQ_BITMAP_BITS;
+
+        if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+                initcnt = IRQ_BITMAP_BITS;
+
+        if (initcnt > nr_irqs)
+                nr_irqs = initcnt;
+
         for (i = 0; i < initcnt; i++) {
                 desc = alloc_desc(i, node);
                 set_bit(i, allocated_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..9033c1c70828 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1100,7 +1100,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
         if (retval)
                 kfree(action);
 
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
         if (!retval && (irqflags & IRQF_SHARED)) {
                 /*
                  * It's a shared IRQ -- the driver ought to be prepared for it
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 891115a929aa..dc49358b73fa 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -23,7 +23,7 @@
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 
 /* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
 
 /*
  * Run software resends of IRQ's
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 999835b6112b..656222fcf767 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -782,6 +782,10 @@ retry:
         raw_spin_unlock_irq(&ctx->lock);
 }
 
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
                  struct perf_cpu_context *cpuctx,
@@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event,
 
         event->state = PERF_EVENT_STATE_ACTIVE;
         event->oncpu = smp_processor_id();
+
+        /*
+         * Unthrottle events, since we scheduled we might have missed several
+         * ticks already, also for a heavily scheduling task there is little
+         * guarantee it'll get a tick in a timely manner.
+         */
+        if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+                perf_log_throttle(event, 1);
+                event->hw.interrupts = 0;
+        }
+
         /*
          * The new state must be visible before we turn it on in the hardware:
          */
@@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task)
         }
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
         u64 frequency = event->attr.sample_freq;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561e..701853042c28 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
 
 static int __init pm_start_workqueue(void)
 {
-        pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+        pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
 
         return pm_wq ? 0 : -ENOMEM;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e0..0cf3a27a6c9d 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
  */
 #define TIMEOUT (20 * HZ)
 
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
 {
         if ((p == current) ||
             (p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
                 todo = 0;
                 read_lock(&tasklist_lock);
                 do_each_thread(g, p) {
-                        if (frozen(p) || !freezeable(p))
+                        if (frozen(p) || !freezable(p))
                                 continue;
 
                         if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
 
         read_lock(&tasklist_lock);
         do_each_thread(g, p) {
-                if (!freezeable(p))
+                if (!freezable(p))
                         continue;
 
                 if (nosig_only && should_send_signal(p))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0dac75ea4456..64db648ff911 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1519,11 +1519,8 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
                 unsigned int nr_pages, unsigned int nr_highmem)
 {
-        int error = 0;
-
         if (nr_highmem > 0) {
-                error = get_highmem_buffer(PG_ANY);
-                if (error)
+                if (get_highmem_buffer(PG_ANY))
                         goto err_out;
                 if (nr_highmem > alloc_highmem) {
                         nr_highmem -= alloc_highmem;
@@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 
  err_out:
         swsusp_free();
-        return error;
+        return -ENOMEM;
 }
 
 asmlinkage int swsusp_save(void)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1708b1e2972d..e2302e40b360 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
         return !err;
 }
 
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
 {
         int retval;
 
@@ -219,7 +219,7 @@ out:
  * Performs checks and sets PT_PTRACED.
  * Should be used by all ptrace implementations for PTRACE_TRACEME.
  */
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
 {
         int ret = -EPERM;
 
@@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
         return false;
 }
 
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
         bool dead = false;
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 48b2761b5668..a3b5aff62606 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -600,4 +600,14 @@ int tick_broadcast_oneshot_active(void)
         return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
 }
 
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+        struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+        return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 051bc80a0c43..ed228ef6f6b8 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -51,7 +51,11 @@ int tick_is_oneshot_available(void)
 {
         struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-        return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+        if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+                return 0;
+        if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+                return 1;
+        return tick_broadcast_oneshot_available();
 }
 
 /*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 290eefbc1f60..f65d3a723a64 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -36,6 +36,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -46,6 +47,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -76,6 +78,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
         return 0;
 }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
 /*
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d95721f33702..cbafed7d4f38 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
         rwbs[i] = '\0';
 }
 
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
-        int rw = rq->cmd_flags & 0x03;
-        int bytes;
-
-        if (rq->cmd_flags & REQ_DISCARD)
-                rw |= REQ_DISCARD;
-
-        if (rq->cmd_flags & REQ_SECURE)
-                rw |= REQ_SECURE;
-
-        bytes = blk_rq_bytes(rq);
-
-        blk_fill_rwbs(rwbs, rw, bytes);
-}
-
 #endif /* CONFIG_EVENT_TRACING */
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa6819..ee6578b578ad 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -79,7 +79,9 @@ enum {
         MAX_IDLE_WORKERS_RATIO  = 4,            /* 1/4 of busy can be idle */
         IDLE_WORKER_TIMEOUT     = 300 * HZ,     /* keep idle ones for 5 mins */
 
-        MAYDAY_INITIAL_TIMEOUT  = HZ / 100,     /* call for help after 10ms */
+        MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
+                                                /* call for help after 10ms
+                                                   (min two ticks) */
         MAYDAY_INTERVAL         = HZ / 10,      /* and then every 100ms */
         CREATE_COOLDOWN         = HZ,           /* time to breath after fail */
         TRUSTEE_COOLDOWN        = HZ / 10,      /* for trustee draining */
@@ -2047,6 +2049,15 @@ repeat:
                                 move_linked_works(work, scheduled, &n);
 
                 process_scheduled_works(rescuer);
+
+                /*
+                 * Leave this gcwq.  If keep_working() is %true, notify a
+                 * regular worker; otherwise, we end up with 0 concurrency
+                 * and stalling the execution.
+                 */
+                if (keep_working(gcwq))
+                        wake_up_worker(gcwq);
+
                 spin_unlock_irq(&gcwq->lock);
         }
 
@@ -2956,7 +2967,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
          */
         spin_lock(&workqueue_lock);
 
-        if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+        if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
                 for_each_cwq_cpu(cpu, wq)
                         get_cwq(cpu, wq)->max_active = 0;
 
@@ -3068,7 +3079,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 
                 spin_lock_irq(&gcwq->lock);
 
-                if (!(wq->flags & WQ_FREEZEABLE) ||
+                if (!(wq->flags & WQ_FREEZABLE) ||
                     !(gcwq->flags & GCWQ_FREEZING))
                         get_cwq(gcwq->cpu, wq)->max_active = max_active;
 
@@ -3318,7 +3329,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
          * want to get it over with ASAP - spam rescuers, wake up as
          * many idlers as necessary and create new ones till the
          * worklist is empty.  Note that if the gcwq is frozen, there
-         * may be frozen works in freezeable cwqs.  Don't declare
+         * may be frozen works in freezable cwqs.  Don't declare
          * completion while frozen.
          */
         while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3576,9 +3587,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 /**
  * freeze_workqueues_begin - begin freezing workqueues
  *
- * Start freezing workqueues.  After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues.  After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
  *
  * CONTEXT:
  * Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3604,7 +3615,7 @@ void freeze_workqueues_begin(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (cwq && wq->flags & WQ_FREEZEABLE)
+                        if (cwq && wq->flags & WQ_FREEZABLE)
                                 cwq->max_active = 0;
                 }
 
@@ -3615,7 +3626,7 @@ void freeze_workqueues_begin(void)
 }
 
 /**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
  *
  * Check whether freezing is complete.  This function must be called
  * between freeze_workqueues_begin() and thaw_workqueues().
@@ -3624,8 +3635,8 @@ void freeze_workqueues_begin(void)
  * Grabs and releases workqueue_lock.
  *
  * RETURNS:
- * %true if some freezeable workqueues are still busy.  %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy.  %false if freezing
+ * is complete.
  */
 bool freeze_workqueues_busy(void)
 {
@@ -3645,7 +3656,7 @@ bool freeze_workqueues_busy(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+                        if (!cwq || !(wq->flags & WQ_FREEZABLE))
                                 continue;
 
                         BUG_ON(cwq->nr_active < 0);
@@ -3690,7 +3701,7 @@ void thaw_workqueues(void)
                 list_for_each_entry(wq, &workqueues, list) {
                         struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-                        if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+                        if (!cwq || !(wq->flags & WQ_FREEZABLE))
                                 continue;
 
                         /* restore max_active and repopulate worklist */