Merge branch 'for-3.9/core' of git://git.kernel.dk/linux-block

Pull block IO core bits from Jens Axboe:
 "Below are the core block IO bits for 3.9.  It was delayed a few days
  since my workstation kept crashing every 2-8h after pulling it into
  current -git, but turns out it is a bug in the new pstate code (divide
  by zero, will report separately).  In any case, it contains:

   - The big cfq/blkcg update from Tejun and and Vivek.

   - Additional block and writeback tracepoints from Tejun.

   - Improvement of the should sort (based on queues) logic in the plug
     flushing.

   - _io() variants of the wait_for_completion() interface, using
     io_schedule() instead of schedule() to contribute to io wait
     properly.

   - Various little fixes.

  You'll get two trivial merge conflicts, which should be easy enough to
  fix up"

Fix up the trivial conflicts due to hlist traversal cleanups (commit
b67bfe0d42ca: "hlist: drop the node parameter from iterators").

* 'for-3.9/core' of git://git.kernel.dk/linux-block: (39 commits)
  block: remove redundant check to bd_openers()
  block: use i_size_write() in bd_set_size()
  cfq: fix lock imbalance with failed allocations
  drivers/block/swim3.c: fix null pointer dereference
  block: don't select PERCPU_RWSEM
  block: account iowait time when waiting for completion of IO request
  sched: add wait_for_completion_io[_timeout]
  writeback: add more tracepoints
  block: add block_{touch|dirty}_buffer tracepoint
  buffer: make touch_buffer() an exported function
  block: add @req to bio_{front|back}_merge tracepoints
  block: add missing block_bio_complete() tracepoint
  block: Remove should_sort judgement when flush blk_plug
  block,elevator: use new hashtable implementation
  cfq-iosched: add hierarchical cfq_group statistics
  cfq-iosched: collect stats from dead cfqgs
  cfq-iosched: separate out cfqg_stats_reset() from cfq_pd_reset_stats()
  blkcg: make blkcg_print_blkgs() grab q locks instead of blkcg lock
  block: RCU free request_queue
  blkcg: implement blkg_[rw]stat_recursive_sum() and blkg_[rw]stat_merge()
  ...

2 files changed, 77 insertions, 8 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 12af4270c9c1..7f12624a393c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3258,7 +3258,8 @@ void complete_all(struct completion *x)
 EXPORT_SYMBOL(complete_all);
 
 static inline long __sched
-do_wait_for_common(struct completion *x, long timeout, int state)
+do_wait_for_common(struct completion *x,
+                   long (*action)(long), long timeout, int state)
 {
         if (!x->done) {
                 DECLARE_WAITQUEUE(wait, current);
@@ -3271,7 +3272,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                         }
                         __set_current_state(state);
                         spin_unlock_irq(&x->wait.lock);
-                        timeout = schedule_timeout(timeout);
+                        timeout = action(timeout);
                         spin_lock_irq(&x->wait.lock);
                 } while (!x->done && timeout);
                 __remove_wait_queue(&x->wait, &wait);
@@ -3282,17 +3283,30 @@ do_wait_for_common(struct completion *x, long timeout, int state)
         return timeout ?: 1;
 }
 
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
+static inline long __sched
+__wait_for_common(struct completion *x,
+                  long (*action)(long), long timeout, int state)
 {
         might_sleep();
 
         spin_lock_irq(&x->wait.lock);
-        timeout = do_wait_for_common(x, timeout, state);
+        timeout = do_wait_for_common(x, action, timeout, state);
         spin_unlock_irq(&x->wait.lock);
         return timeout;
 }
 
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+        return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+        return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
 /**
  * wait_for_completion: - waits for completion of a task
  * @x:  holds the state of this particular completion
@@ -3329,6 +3343,39 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 EXPORT_SYMBOL(wait_for_completion_timeout);
 
 /**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+        wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+        return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
  * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
  * @x:  holds the state of this particular completion
  *
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 71259e2b6b61..9e5b8c272eec 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -739,6 +739,12 @@ static void blk_add_trace_rq_complete(void *ignore,
                                       struct request_queue *q,
                                       struct request *rq)
 {
+        struct blk_trace *bt = q->blk_trace;
+
+        /* if control ever passes through here, it's a request based driver */
+        if (unlikely(bt && !bt->rq_based))
+                bt->rq_based = true;
+
         blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
 }
 
@@ -774,15 +780,30 @@ static void blk_add_trace_bio_bounce(void *ignore,
         blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
 }
 
-static void blk_add_trace_bio_complete(void *ignore,
-                                       struct request_queue *q, struct bio *bio,
-                                       int error)
+static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
 {
+        struct request_queue *q;
+        struct blk_trace *bt;
+
+        if (!bio->bi_bdev)
+                return;
+
+        q = bdev_get_queue(bio->bi_bdev);
+        bt = q->blk_trace;
+
+        /*
+         * Request based drivers will generate both rq and bio completions.
+         * Ignore bio ones.
+         */
+        if (likely(!bt) || bt->rq_based)
+                return;
+
         blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
 }
 
 static void blk_add_trace_bio_backmerge(void *ignore,
                                         struct request_queue *q,
+                                        struct request *rq,
                                         struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
@@ -790,6 +811,7 @@ static void blk_add_trace_bio_backmerge(void *ignore,
 
 static void blk_add_trace_bio_frontmerge(void *ignore,
                                          struct request_queue *q,
+                                         struct request *rq,
                                          struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);