Merge commit 'v2.6.37-rc2' into upstream/xenfs

* commit 'v2.6.37-rc2': (10093 commits)
  Linux 2.6.37-rc2
  capabilities/syslog: open code cap_syslog logic to fix build failure
  i2c: Sanity checks on adapter registration
  i2c: Mark i2c_adapter.id as deprecated
  i2c: Drivers shouldn't include <linux/i2c-id.h>
  i2c: Delete unused adapter IDs
  i2c: Remove obsolete cleanup for clientdata
  include/linux/kernel.h: Move logging bits to include/linux/printk.h
  Fix gcc 4.5.1 miscompiling drivers/char/i8k.c (again)
  hwmon: (w83795) Check for BEEP pin availability
  hwmon: (w83795) Clear intrusion alarm immediately
  hwmon: (w83795) Read the intrusion state properly
  hwmon: (w83795) Print the actual temperature channels as sources
  hwmon: (w83795) List all usable temperature sources
  hwmon: (w83795) Expose fan control method
  hwmon: (w83795) Fix fan control mode attributes
  hwmon: (lm95241) Check validity of input values
  hwmon: Change mail address of Hans J. Koch
  PCI: sysfs: fix printk warnings
  GFS2: Fix inode deallocation race
  ...

1 files changed, 198 insertions, 118 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f77afd939229..90db1bd1a978 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -42,9 +42,6 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
-
 #include "workqueue_sched.h"
 
 enum {
@@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #define for_each_busy_worker(worker, i, pos, gcwq)                      \
         for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)                     \
                 hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
@@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
              (cpu) < WORK_CPU_NONE;                                     \
              (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
 
-#ifdef CONFIG_LOCKDEP
-/**
- * in_workqueue_context() - in context of specified workqueue?
- * @wq: the workqueue of interest
- *
- * Checks lockdep state to see if the current task is executing from
- * within a workqueue item.  This function exists only if lockdep is
- * enabled.
- */
-int in_workqueue_context(struct workqueue_struct *wq)
-{
-        return lock_is_held(&wq->lockdep_map);
-}
-#endif
-
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
 static struct debug_obj_descr work_debug_descr;
@@ -604,7 +589,9 @@ static bool keep_working(struct global_cwq *gcwq)
 {
         atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
 
-        return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1;
+        return !list_empty(&gcwq->worklist) &&
+                (atomic_read(nr_running) <= 1 ||
+                 gcwq->flags & GCWQ_HIGHPRI_PENDING);
 }
 
 /* Do we need a new worker?  Called from manager. */
@@ -997,6 +984,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
 
         /* gcwq determined, get cwq and queue */
         cwq = get_cwq(gcwq->cpu, wq);
+        trace_workqueue_queue_work(cpu, cwq, work);
 
         BUG_ON(!list_empty(&work->entry));
 
@@ -1004,6 +992,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
         work_flags = work_color_to_flags(cwq->work_color);
 
         if (likely(cwq->nr_active < cwq->max_active)) {
+                trace_workqueue_activate_work(work);
                 cwq->nr_active++;
                 worklist = gcwq_determine_ins_pos(gcwq, cwq);
         } else {
@@ -1679,6 +1668,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
                                                     struct work_struct, entry);
         struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
 
+        trace_workqueue_activate_work(work);
         move_linked_works(work, pos, NULL);
         __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
         cwq->nr_active++;
@@ -2074,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
          * checks and call back into the fixup functions where we
          * might deadlock.
          */
-        INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
+        INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
         __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
         init_completion(&barr->done);
 
@@ -2326,27 +2316,17 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
-/**
- * flush_work - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns false if @work has already terminated.
- *
- * It is expected that, prior to calling flush_work(), the caller has
- * arranged for the work to not be requeued, otherwise it doesn't make
- * sense to use this function.
- */
-int flush_work(struct work_struct *work)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+                             bool wait_executing)
 {
         struct worker *worker = NULL;
         struct global_cwq *gcwq;
         struct cpu_workqueue_struct *cwq;
-        struct wq_barrier barr;
 
         might_sleep();
         gcwq = get_work_gcwq(work);
         if (!gcwq)
-                return 0;
+                return false;
 
         spin_lock_irq(&gcwq->lock);
         if (!list_empty(&work->entry)) {
@@ -2359,28 +2339,127 @@ int flush_work(struct work_struct *work)
                 cwq = get_work_cwq(work);
                 if (unlikely(!cwq || gcwq != cwq->gcwq))
                         goto already_gone;
-        } else {
+        } else if (wait_executing) {
                 worker = find_worker_executing_work(gcwq, work);
                 if (!worker)
                         goto already_gone;
                 cwq = worker->current_cwq;
-        }
+        } else
+                goto already_gone;
 
-        insert_wq_barrier(cwq, &barr, work, worker);
+        insert_wq_barrier(cwq, barr, work, worker);
         spin_unlock_irq(&gcwq->lock);
 
         lock_map_acquire(&cwq->wq->lockdep_map);
         lock_map_release(&cwq->wq->lockdep_map);
-
-        wait_for_completion(&barr.done);
-        destroy_work_on_stack(&barr.work);
-        return 1;
+        return true;
 already_gone:
         spin_unlock_irq(&gcwq->lock);
-        return 0;
+        return false;
+}
+
+/**
+ * flush_work - wait for a work to finish executing the last queueing instance
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  This function considers
+ * only the last queueing instance of @work.  If @work has been
+ * enqueued across different CPUs on a non-reentrant workqueue or on
+ * multiple workqueues, @work might still be executing on return on
+ * some of the CPUs from earlier queueing.
+ *
+ * If @work was queued only on a non-reentrant, ordered or unbound
+ * workqueue, @work is guaranteed to be idle on return if it hasn't
+ * been requeued since flush started.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work(struct work_struct *work)
+{
+        struct wq_barrier barr;
+
+        if (start_flush_work(work, &barr, true)) {
+                wait_for_completion(&barr.done);
+                destroy_work_on_stack(&barr.work);
+                return true;
+        } else
+                return false;
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
+static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
+{
+        struct wq_barrier barr;
+        struct worker *worker;
+
+        spin_lock_irq(&gcwq->lock);
+
+        worker = find_worker_executing_work(gcwq, work);
+        if (unlikely(worker))
+                insert_wq_barrier(worker->current_cwq, &barr, work, worker);
+
+        spin_unlock_irq(&gcwq->lock);
+
+        if (unlikely(worker)) {
+                wait_for_completion(&barr.done);
+                destroy_work_on_stack(&barr.work);
+                return true;
+        } else
+                return false;
+}
+
+static bool wait_on_work(struct work_struct *work)
+{
+        bool ret = false;
+        int cpu;
+
+        might_sleep();
+
+        lock_map_acquire(&work->lockdep_map);
+        lock_map_release(&work->lockdep_map);
+
+        for_each_gcwq_cpu(cpu)
+                ret |= wait_on_cpu_work(get_gcwq(cpu), work);
+        return ret;
+}
+
+/**
+ * flush_work_sync - wait until a work has finished execution
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  On return, it's
+ * guaranteed that all queueing instances of @work which happened
+ * before this function is called are finished.  In other words, if
+ * @work hasn't been requeued since this function was called, @work is
+ * guaranteed to be idle on return.
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work_sync(struct work_struct *work)
+{
+        struct wq_barrier barr;
+        bool pending, waited;
+
+        /* we'll wait for executions separately, queue barr only if pending */
+        pending = start_flush_work(work, &barr, false);
+
+        /* wait for executions to finish */
+        waited = wait_on_work(work);
+
+        /* wait for the pending one */
+        if (pending) {
+                wait_for_completion(&barr.done);
+                destroy_work_on_stack(&barr.work);
+        }
+
+        return pending || waited;
+}
+EXPORT_SYMBOL_GPL(flush_work_sync);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.
@@ -2423,39 +2502,7 @@ static int try_to_grab_pending(struct work_struct *work)
         return ret;
 }
 
-static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
-{
-        struct wq_barrier barr;
-        struct worker *worker;
-
-        spin_lock_irq(&gcwq->lock);
-
-        worker = find_worker_executing_work(gcwq, work);
-        if (unlikely(worker))
-                insert_wq_barrier(worker->current_cwq, &barr, work, worker);
-
-        spin_unlock_irq(&gcwq->lock);
-
-        if (unlikely(worker)) {
-                wait_for_completion(&barr.done);
-                destroy_work_on_stack(&barr.work);
-        }
-}
-
-static void wait_on_work(struct work_struct *work)
-{
-        int cpu;
-
-        might_sleep();
-
-        lock_map_acquire(&work->lockdep_map);
-        lock_map_release(&work->lockdep_map);
-
-        for_each_gcwq_cpu(cpu)
-                wait_on_cpu_work(get_gcwq(cpu), work);
-}
-
-static int __cancel_work_timer(struct work_struct *work,
+static bool __cancel_work_timer(struct work_struct *work,
                                 struct timer_list* timer)
 {
         int ret;
@@ -2472,42 +2519,81 @@ static int __cancel_work_timer(struct work_struct *work,
 }
 
 /**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns true if @work was pending.
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
  *
- * cancel_work_sync() will cancel the work if it is queued. If the work's
- * callback appears to be running, cancel_work_sync() will block until it
- * has completed.
+ * Cancel @work and wait for its execution to finish.  This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue.  On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
  *
- * It is possible to use this function if the work re-queues itself. It can
- * cancel the work even if it migrates to another workqueue, however in that
- * case it only guarantees that work->func() has completed on the last queued
- * workqueue.
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's.  Use cancel_delayed_work_sync() instead.
  *
- * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
- * pending, otherwise it goes into a busy-wait loop until the timer expires.
- *
- * The caller must ensure that workqueue_struct on which this work was last
+ * The caller must ensure that the workqueue on which @work was last
  * queued can't be destroyed before this function returns.
+ *
+ * RETURNS:
+ * %true if @work was pending, %false otherwise.
  */
-int cancel_work_sync(struct work_struct *work)
+bool cancel_work_sync(struct work_struct *work)
 {
         return __cancel_work_timer(work, NULL);
 }
 EXPORT_SYMBOL_GPL(cancel_work_sync);
 
 /**
- * cancel_delayed_work_sync - reliably kill off a delayed work.
- * @dwork: the delayed work struct
+ * flush_delayed_work - wait for a dwork to finish executing the last queueing
+ * @dwork: the delayed work to flush
+ *
+ * Delayed timer is cancelled and the pending work is queued for
+ * immediate execution.  Like flush_work(), this function only
+ * considers the last queueing instance of @dwork.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_delayed_work(struct delayed_work *dwork)
+{
+        if (del_timer_sync(&dwork->timer))
+                __queue_work(raw_smp_processor_id(),
+                             get_work_cwq(&dwork->work)->wq, &dwork->work);
+        return flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
+ * flush_delayed_work_sync - wait for a dwork to finish
+ * @dwork: the delayed work to flush
  *
- * Returns true if @dwork was pending.
+ * Delayed timer is cancelled and the pending work is queued for
+ * execution immediately.  Other than timer handling, its behavior
+ * is identical to flush_work_sync().
  *
- * It is possible to use this function if @dwork rearms itself via queue_work()
- * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
  */
-int cancel_delayed_work_sync(struct delayed_work *dwork)
+bool flush_delayed_work_sync(struct delayed_work *dwork)
+{
+        if (del_timer_sync(&dwork->timer))
+                __queue_work(raw_smp_processor_id(),
+                             get_work_cwq(&dwork->work)->wq, &dwork->work);
+        return flush_work_sync(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work_sync);
+
+/**
+ * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
+ * @dwork: the delayed work cancel
+ *
+ * This is cancel_work_sync() for delayed works.
+ *
+ * RETURNS:
+ * %true if @dwork was pending, %false otherwise.
+ */
+bool cancel_delayed_work_sync(struct delayed_work *dwork)
 {
         return __cancel_work_timer(&dwork->work, &dwork->timer);
 }
@@ -2559,23 +2645,6 @@ int schedule_delayed_work(struct delayed_work *dwork,
 EXPORT_SYMBOL(schedule_delayed_work);
 
 /**
- * flush_delayed_work - block until a dwork_struct's callback has terminated
- * @dwork: the delayed work which is to be flushed
- *
- * Any timeout is cancelled, and any pending work is run immediately.
- */
-void flush_delayed_work(struct delayed_work *dwork)
-{
-        if (del_timer_sync(&dwork->timer)) {
-                __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
-                             &dwork->work);
-                put_cpu();
-        }
-        flush_work(&dwork->work);
-}
-EXPORT_SYMBOL(flush_delayed_work);
-
-/**
  * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
  * @cpu: cpu to use
  * @dwork: job to be done
@@ -2592,13 +2661,15 @@ int schedule_delayed_work_on(int cpu,
 EXPORT_SYMBOL(schedule_delayed_work_on);
 
 /**
- * schedule_on_each_cpu - call a function on each online CPU from keventd
+ * schedule_on_each_cpu - execute a function synchronously on each online CPU
  * @func: the function to call
  *
- * Returns zero on success.
- * Returns -ve errno on failure.
- *
+ * schedule_on_each_cpu() executes @func on each online CPU using the
+ * system workqueue and blocks until all CPUs have completed.
  * schedule_on_each_cpu() is very slow.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
  */
 int schedule_on_each_cpu(work_func_t func)
 {
@@ -2720,7 +2791,9 @@ static int alloc_cwqs(struct workqueue_struct *wq)
                 }
         }
 
-        /* just in case, make sure it's actually aligned */
+        /* just in case, make sure it's actually aligned
+         * - this is affected by PERCPU() alignment in vmlinux.lds.S
+         */
         BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align));
         return wq->cpu_wq.v ? 0 : -ENOMEM;
 }
@@ -2764,6 +2837,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
         unsigned int cpu;
 
         /*
+         * Workqueues which may be used during memory reclaim should
+         * have a rescuer to guarantee forward progress.
+         */
+        if (flags & WQ_MEM_RECLAIM)
+                flags |= WQ_RESCUER;
+
+        /*
          * Unbound workqueues aren't concurrency managed and should be
          * dispatched to workers immediately.
          */