Merge branch 'for-3.2/core' of git://git.kernel.dk/linux-block

* 'for-3.2/core' of git://git.kernel.dk/linux-block: (29 commits)
  block: don't call blk_drain_queue() if elevator is not up
  blk-throttle: use queue_is_locked() instead of lockdep_is_held()
  blk-throttle: Take blkcg->lock while traversing blkcg->policy_list
  blk-throttle: Free up policy node associated with deleted rule
  block: warn if tag is greater than real_max_depth.
  block: make gendisk hold a reference to its queue
  blk-flush: move the queue kick into
  blk-flush: fix invalid BUG_ON in blk_insert_flush
  block: Remove the control of complete cpu from bio.
  block: fix a typo in the blk-cgroup.h file
  block: initialize the bounce pool if high memory may be added later
  block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown
  block: drop @tsk from attempt_plug_merge() and explain sync rules
  block: make get_request[_wait]() fail if queue is dead
  block: reorganize throtl_get_tg() and blk_throtl_bio()
  block: reorganize queue draining
  block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg()
  block: pass around REQ_* flags instead of broken down booleans during request alloc/free
  block: move blk_throtl prototypes to block/blk.h
  block: fix genhd refcounting in blkio_policy_parse_and_set()
  ...

Fix up trivial conflicts due to "mddev_t" -> "struct mddev" conversion
and making the request functions be of type "void" instead of "int" in
 - drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c}
 - drivers/staging/zram/zram_drv.c

1 files changed, 62 insertions, 44 deletions

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a19f58c6fc3a..4553245d9317 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -10,6 +10,7 @@
 #include <linux/bio.h>
 #include <linux/blktrace_api.h>
 #include "blk-cgroup.h"
+#include "blk.h"
 
 /* Max dispatch from a group in 1 round */
 static int throtl_grp_quantum = 8;
@@ -302,16 +303,16 @@ throtl_grp *throtl_find_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
 	return tg;
 }
 
-/*
- * This function returns with queue lock unlocked in case of error, like
- * request queue is no more
- */
 static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 {
 	struct throtl_grp *tg = NULL, *__tg = NULL;
 	struct blkio_cgroup *blkcg;
 	struct request_queue *q = td->queue;
 
+	/* no throttling for dead queue */
+	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
+		return NULL;
+
 	rcu_read_lock();
 	blkcg = task_blkio_cgroup(current);
 	tg = throtl_find_tg(td, blkcg);
@@ -323,32 +324,22 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	/*
 	 * Need to allocate a group. Allocation of group also needs allocation
 	 * of per cpu stats which in-turn takes a mutex() and can block. Hence
-	 * we need to drop rcu lock and queue_lock before we call alloc
-	 *
-	 * Take the request queue reference to make sure queue does not
-	 * go away once we return from allocation.
+	 * we need to drop rcu lock and queue_lock before we call alloc.
 	 */
-	blk_get_queue(q);
 	rcu_read_unlock();
 	spin_unlock_irq(q->queue_lock);
 
 	tg = throtl_alloc_tg(td);
-	/*
-	 * We might have slept in group allocation. Make sure queue is not
-	 * dead
-	 */
-	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
-		blk_put_queue(q);
-		if (tg)
-			kfree(tg);
-
-		return ERR_PTR(-ENODEV);
-	}
-	blk_put_queue(q);
 
 	/* Group allocated and queue is still alive. take the lock */
 	spin_lock_irq(q->queue_lock);
 
+	/* Make sure @q is still alive */
+	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+		kfree(tg);
+		return NULL;
+	}
+
 	/*
 	 * Initialize the new group. After sleeping, read the blkcg again.
 	 */
@@ -1014,11 +1005,6 @@ static void throtl_release_tgs(struct throtl_data *td)
 	}
 }
 
-static void throtl_td_free(struct throtl_data *td)
-{
-	kfree(td);
-}
-
 /*
  * Blk cgroup controller notification saying that blkio_group object is being
  * delinked as associated cgroup object is going away. That also means that
@@ -1123,17 +1109,17 @@ static struct blkio_policy_type blkio_policy_throtl = {
 	.plid = BLKIO_POLICY_THROTL,
 };
 
-int blk_throtl_bio(struct request_queue *q, struct bio **biop)
+bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 {
 	struct throtl_data *td = q->td;
 	struct throtl_grp *tg;
-	struct bio *bio = *biop;
 	bool rw = bio_data_dir(bio), update_disptime = true;
 	struct blkio_cgroup *blkcg;
+	bool throttled = false;
 
 	if (bio->bi_rw & REQ_THROTTLED) {
 		bio->bi_rw &= ~REQ_THROTTLED;
-		return 0;
+		goto out;
 	}
 
 	/*
@@ -1152,7 +1138,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 			blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
 					rw, rw_is_sync(bio->bi_rw));
 			rcu_read_unlock();
-			return 0;
+			goto out;
 		}
 	}
 	rcu_read_unlock();
@@ -1161,18 +1147,10 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 	 * Either group has not been allocated yet or it is not an unlimited
 	 * IO group
 	 */
-
 	spin_lock_irq(q->queue_lock);
 	tg = throtl_get_tg(td);
-
-	if (IS_ERR(tg)) {
-		if (PTR_ERR(tg)	== -ENODEV) {
-			/*
-			 * Queue is gone. No queue lock held here.
-			 */
-			return -ENODEV;
-		}
-	}
+	if (unlikely(!tg))
+		goto out_unlock;
 
 	if (tg->nr_queued[rw]) {
 		/*
@@ -1200,7 +1178,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 		 * So keep on trimming slice even if bio is not queued.
 		 */
 		throtl_trim_slice(td, tg, rw);
-		goto out;
+		goto out_unlock;
 	}
 
 queue_bio:
@@ -1212,16 +1190,52 @@ queue_bio:
 			tg->nr_queued[READ], tg->nr_queued[WRITE]);
 
 	throtl_add_bio_tg(q->td, tg, bio);
-	*biop = NULL;
+	throttled = true;
 
 	if (update_disptime) {
 		tg_update_disptime(td, tg);
 		throtl_schedule_next_dispatch(td);
 	}
 
+out_unlock:
+	spin_unlock_irq(q->queue_lock);
 out:
+	return throttled;
+}
+
+/**
+ * blk_throtl_drain - drain throttled bios
+ * @q: request_queue to drain throttled bios for
+ *
+ * Dispatch all currently throttled bios on @q through ->make_request_fn().
+ */
+void blk_throtl_drain(struct request_queue *q)
+	__releases(q->queue_lock) __acquires(q->queue_lock)
+{
+	struct throtl_data *td = q->td;
+	struct throtl_rb_root *st = &td->tg_service_tree;
+	struct throtl_grp *tg;
+	struct bio_list bl;
+	struct bio *bio;
+
+	WARN_ON_ONCE(!queue_is_locked(q));
+
+	bio_list_init(&bl);
+
+	while ((tg = throtl_rb_first(st))) {
+		throtl_dequeue_tg(td, tg);
+
+		while ((bio = bio_list_peek(&tg->bio_lists[READ])))
+			tg_dispatch_one_bio(td, tg, bio_data_dir(bio), &bl);
+		while ((bio = bio_list_peek(&tg->bio_lists[WRITE])))
+			tg_dispatch_one_bio(td, tg, bio_data_dir(bio), &bl);
+	}
 	spin_unlock_irq(q->queue_lock);
-	return 0;
+
+	while ((bio = bio_list_pop(&bl)))
+		generic_make_request(bio);
+
+	spin_lock_irq(q->queue_lock);
 }
 
 int blk_throtl_init(struct request_queue *q)
@@ -1296,7 +1310,11 @@ void blk_throtl_exit(struct request_queue *q)
 	 * it.
 	 */
 	throtl_shutdown_wq(q);
-	throtl_td_free(td);
+}
+
+void blk_throtl_release(struct request_queue *q)
+{
+	kfree(q->td);
 }
 
 static int __init throtl_init(void)