---

yaml
---
r: 142051
b: refs/heads/master
c: 3cd6927
h: refs/heads/master
i:
  142049: 8af4f70
  142047: 5f727cf
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 67a32ec750109fdfc7cba311145a18d543521822
+refs/heads/master: 3cd69271f86770499425c7cea2902512ba936a75

trunk/block/blk-core.c

@@ -484,11 +484,11 @@ static int blk_init_free_list(struct request_queue *q)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[READ] = rl->count[WRITE] = 0;
-	rl->starved[READ] = rl->starved[WRITE] = 0;
+	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
+	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
 	rl->elvpriv = 0;
-	init_waitqueue_head(&rl->wait[READ]);
-	init_waitqueue_head(&rl->wait[WRITE]);
+	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
+	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
 	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
 				mempool_free_slab, request_cachep, q->node);
@@ -699,37 +699,37 @@ static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
 	ioc->last_waited = jiffies;
 }
 
-static void __freed_request(struct request_queue *q, int rw)
+static void __freed_request(struct request_queue *q, int sync)
 {
 	struct request_list *rl = &q->rq;
 
-	if (rl->count[rw] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, rw);
+	if (rl->count[sync] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, sync);
 
-	if (rl->count[rw] + 1 <= q->nr_requests) {
-		if (waitqueue_active(&rl->wait[rw]))
-			wake_up(&rl->wait[rw]);
+	if (rl->count[sync] + 1 <= q->nr_requests) {
+		if (waitqueue_active(&rl->wait[sync]))
+			wake_up(&rl->wait[sync]);
 
-		blk_clear_queue_full(q, rw);
+		blk_clear_queue_full(q, sync);
 	}
 }
 
 /*
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_queue *q, int rw, int priv)
+static void freed_request(struct request_queue *q, int sync, int priv)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[rw]--;
+	rl->count[sync]--;
 	if (priv)
 		rl->elvpriv--;
 
-	__freed_request(q, rw);
+	__freed_request(q, sync);
 
-	if (unlikely(rl->starved[rw ^ 1]))
-		__freed_request(q, rw ^ 1);
+	if (unlikely(rl->starved[sync ^ 1]))
+		__freed_request(q, sync ^ 1);
 }
 
 /*
@@ -743,25 +743,25 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	struct request *rq = NULL;
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	int may_queue, priv;
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
-	if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
-		if (rl->count[rw]+1 >= q->nr_requests) {
+	if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
+		if (rl->count[is_sync]+1 >= q->nr_requests) {
 			ioc = current_io_context(GFP_ATOMIC, q->node);
 			/*
 			 * The queue will fill after this allocation, so set
 			 * it as full, and mark this process as "batching".
 			 * This process will be allowed to complete a batch of
 			 * requests, others will be blocked.
 			 */
-			if (!blk_queue_full(q, rw)) {
+			if (!blk_queue_full(q, is_sync)) {
 				ioc_set_batching(q, ioc);
-				blk_set_queue_full(q, rw);
+				blk_set_queue_full(q, is_sync);
 			} else {
 				if (may_queue != ELV_MQUEUE_MUST
 						&& !ioc_batching(q, ioc)) {
@@ -774,19 +774,19 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 				}
 			}
 		}
-		blk_set_queue_congested(q, rw);
+		blk_set_queue_congested(q, is_sync);
 	}
 
 	/*
 	 * Only allow batching queuers to allocate up to 50% over the defined
 	 * limit of requests, otherwise we could have thousands of requests
 	 * allocated with any setting of ->nr_requests
 	 */
-	if (rl->count[rw] >= (3 * q->nr_requests / 2))
+	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
 		goto out;
 
-	rl->count[rw]++;
-	rl->starved[rw] = 0;
+	rl->count[is_sync]++;
+	rl->starved[is_sync] = 0;
 
 	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	if (priv)
@@ -804,7 +804,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * wait queue, but this is pretty rare.
 		 */
 		spin_lock_irq(q->queue_lock);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 
 		/*
 		 * in the very unlikely event that allocation failed and no
@@ -814,8 +814,8 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * rq mempool into READ and WRITE
 		 */
 rq_starved:
-		if (unlikely(rl->count[rw] == 0))
-			rl->starved[rw] = 1;
+		if (unlikely(rl->count[is_sync] == 0))
+			rl->starved[is_sync] = 1;
 
 		goto out;
 	}
@@ -829,7 +829,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, rw_flags & 1);
 out:
 	return rq;
 }
@@ -843,7 +843,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 					struct bio *bio)
 {
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	struct request *rq;
 
 	rq = get_request(q, rw_flags, bio, GFP_NOIO);
@@ -852,10 +852,10 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		struct io_context *ioc;
 		struct request_list *rl = &q->rq;
 
-		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
+		prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, rw_flags & 1);
 
 		__generic_unplug_device(q);
 		spin_unlock_irq(q->queue_lock);
@@ -871,7 +871,7 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		ioc_set_batching(q, ioc);
 
 		spin_lock_irq(q->queue_lock);
-		finish_wait(&rl->wait[rw], &wait);
+		finish_wait(&rl->wait[is_sync], &wait);
 
 		rq = get_request(q, rw_flags, bio, GFP_NOIO);
 	};
@@ -1070,14 +1070,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 * it didn't come out of our reserved rq pools
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
-		int rw = rq_data_dir(req);
+		int is_sync = rq_is_sync(req) != 0;
 		int priv = req->cmd_flags & REQ_ELVPRIV;
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(!hlist_unhashed(&req->hash));
 
 		blk_free_request(q, req);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 	}
 }
 EXPORT_SYMBOL_GPL(__blk_put_request);
@@ -1128,6 +1128,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
+	if (bio_noidle(bio))
+		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
 	req->hard_sector = req->sector = bio->bi_sector;
@@ -1136,6 +1138,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
+/*
+ * Only disabling plugging for non-rotational devices if it does tagging
+ * as well, otherwise we do need the proper merging
+ */
+static inline bool queue_should_plug(struct request_queue *q)
+{
+	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+}
+
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
 	struct request *req;
@@ -1242,11 +1253,11 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
 	    bio_flagged(bio, BIO_CPU_AFFINE))
 		req->cpu = blk_cpu_to_group(smp_processor_id());
-	if (!blk_queue_nonrot(q) && elv_queue_empty(q))
+	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (unplug || blk_queue_nonrot(q))
+	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;

trunk/block/blk-sysfs.c

@@ -48,28 +48,28 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	q->nr_requests = nr;
 	blk_queue_congestion_threshold(q);
 
-	if (rl->count[READ] >= queue_congestion_on_threshold(q))
-		blk_set_queue_congested(q, READ);
-	else if (rl->count[READ] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, READ);
-
-	if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
-		blk_set_queue_congested(q, WRITE);
-	else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, WRITE);
-
-	if (rl->count[READ] >= q->nr_requests) {
-		blk_set_queue_full(q, READ);
-	} else if (rl->count[READ]+1 <= q->nr_requests) {
-		blk_clear_queue_full(q, READ);
-		wake_up(&rl->wait[READ]);
+	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_SYNC);
+	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_SYNC);
+
+	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_ASYNC);
+	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_ASYNC);
+
+	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_SYNC);
+	} else if (rl->count[BLK_RW_SYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_SYNC);
+		wake_up(&rl->wait[BLK_RW_SYNC]);
 	}
 
-	if (rl->count[WRITE] >= q->nr_requests) {
-		blk_set_queue_full(q, WRITE);
-	} else if (rl->count[WRITE]+1 <= q->nr_requests) {
-		blk_clear_queue_full(q, WRITE);
-		wake_up(&rl->wait[WRITE]);
+	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_ASYNC);
+	} else if (rl->count[BLK_RW_ASYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_ASYNC);
+		wake_up(&rl->wait[BLK_RW_ASYNC]);
 	}
 	spin_unlock_irq(q->queue_lock);
 	return ret;

trunk/block/cfq-iosched.c

@@ -1992,8 +1992,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		}
 		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
 			cfq_slice_expired(cfqd, 1);
-		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
+		else if (sync && !rq_noidle(rq) &&
+			 RB_EMPTY_ROOT(&cfqq->sort_list)) {
 			cfq_arm_slice_timer(cfqd);
+		}
 	}
 
 	if (!cfqd->rq_in_driver)

trunk/block/elevator.c

@@ -677,7 +677,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 	}
 
 	if (unplug_it && blk_queue_plugged(q)) {
-		int nrq = q->rq.count[READ] + q->rq.count[WRITE]
+		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
 			- q->in_flight;
 
 		if (nrq >= q->unplug_thresh)

trunk/fs/buffer.c

@@ -737,7 +737,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
 	struct buffer_head *bh;
 	struct list_head tmp;
-	struct address_space *mapping;
+	struct address_space *mapping, *prev_mapping = NULL;
 	int err = 0, err2;
 
 	INIT_LIST_HEAD(&tmp);
@@ -762,7 +762,18 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * contents - it is a noop if I/O is still in
 				 * flight on potentially older contents.
 				 */
-				ll_rw_block(SWRITE_SYNC, 1, &bh);
+				ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+
+				/*
+				 * Kick off IO for the previous mapping. Note
+				 * that we will not run the very last mapping,
+				 * wait_on_buffer() will do that for us
+				 * through sync_buffer().
+				 */
+				if (prev_mapping && prev_mapping != mapping)
+					blk_run_address_space(prev_mapping);
+				prev_mapping = mapping;
+
 				brelse(bh);
 				spin_lock(lock);
 			}
@@ -2957,12 +2968,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 	for (i = 0; i < nr; i++) {
 		struct buffer_head *bh = bhs[i];
 
-		if (rw == SWRITE || rw == SWRITE_SYNC)
+		if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
 			lock_buffer(bh);
 		else if (!trylock_buffer(bh))
 			continue;
 
-		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
+		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
+		    rw == SWRITE_SYNC_PLUG) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
@@ -2998,7 +3010,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(WRITE, bh);
+		ret = submit_bh(WRITE_SYNC, bh);
 		wait_on_buffer(bh);
 		if (buffer_eopnotsupp(bh)) {
 			clear_buffer_eopnotsupp(bh);

trunk/fs/direct-io.c

@@ -1126,7 +1126,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	int acquire_i_mutex = 0;
 
 	if (rw & WRITE)
-		rw = WRITE_SYNC;
+		rw = WRITE_ODIRECT;
 
 	if (bdev)
 		bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev));

trunk/fs/jbd/commit.c

@@ -351,8 +351,13 @@ void journal_commit_transaction(journal_t *journal)
 	spin_lock(&journal->j_state_lock);
 	commit_transaction->t_state = T_LOCKED;
 
+	/*
+	 * Use plugged writes here, since we want to submit several before
+	 * we unplug the device. We don't do explicit unplugging in here,
+	 * instead we rely on sync_buffer() doing the unplug for us.
+	 */
 	if (commit_transaction->t_synchronous_commit)
-		write_op = WRITE_SYNC;
+		write_op = WRITE_SYNC_PLUG;
 	spin_lock(&commit_transaction->t_handle_lock);
 	while (commit_transaction->t_updates) {
 		DEFINE_WAIT(wait);