Merge branch 'writeback-workqueue' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq into for-3.10/core

Tejun writes:

-----

This is the pull request for the earlier patchset[1] with the same
name.  It's only three patches (the first one was committed to
workqueue tree) but the merge strategy is a bit involved due to the
dependencies.

* Because the conversion needs features from wq/for-3.10,
  block/for-3.10/core is based on rc3, and wq/for-3.10 has conflicts
  with rc3, I pulled mainline (rc5) into wq/for-3.10 to prevent those
  workqueue conflicts from flaring up in block tree.

* Resolving the issue that Jan and Dave raised about debugging
  requires arch-wide changes.  The patchset is being worked on[2] but
  it'll have to go through -mm after these changes show up in -next,
  and not included in this pull request.

The three commits are located in the following git branch.

  git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git writeback-workqueue

Pulling it into block/for-3.10/core produces a conflict in
drivers/md/raid5.c between the following two commits.

  e3620a3ad5 ("MD RAID5: Avoid accessing gendisk or queue structs when not available")
  2f6db2a707 ("raid5: use bio_reset()")

The conflict is trivial - one removes an "if ()" conditional while the
other removes "rbi->bi_next = NULL" right above it.  We just need to
remove both.  The merged branch is available at

  git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git block-test-merge

so that you can use it for verification.  The test merge commit has
proper merge description.

While these changes are a bit of pain to route, they make code simpler
and even have, while minute, measureable performance gain[3] even on a
workload which isn't particularly favorable to showing the benefits of
this conversion.

----

Fixed up the conflict.

Conflicts:
	drivers/md/raid5.c

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 81 insertions, 35 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7bbd2854621..2fefb9f2198 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -667,9 +667,11 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_size = STRIPE_SIZE;
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
-			trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
-					      bi, disk_devt(conf->mddev->gendisk),
-					      sh->dev[i].sector);
+
+			if (conf->mddev->gendisk)
+				trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
+						      bi, disk_devt(conf->mddev->gendisk),
+						      sh->dev[i].sector);
 			generic_make_request(bi);
 		}
 		if (rrdev) {
@@ -700,9 +702,10 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_size = STRIPE_SIZE;
-			trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
-					      rbi, disk_devt(conf->mddev->gendisk),
-					      sh->dev[i].sector);
+			if (conf->mddev->gendisk)
+				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
+						      rbi, disk_devt(conf->mddev->gendisk),
+						      sh->dev[i].sector);
 			generic_make_request(rbi);
 		}
 		if (!rdev && !rrdev) {
@@ -2279,17 +2282,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 	int level = conf->level;
 
 	if (rcw) {
-		/* if we are not expanding this is a proper write request, and
-		 * there will be bios with new data to be drained into the
-		 * stripe cache
-		 */
-		if (!expand) {
-			sh->reconstruct_state = reconstruct_state_drain_run;
-			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
-		} else
-			sh->reconstruct_state = reconstruct_state_run;
-
-		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -2302,6 +2294,21 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 				s->locked++;
 			}
 		}
+		/* if we are not expanding this is a proper write request, and
+		 * there will be bios with new data to be drained into the
+		 * stripe cache
+		 */
+		if (!expand) {
+			if (!s->locked)
+				/* False alarm, nothing to do */
+				return;
+			sh->reconstruct_state = reconstruct_state_drain_run;
+			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		} else
+			sh->reconstruct_state = reconstruct_state_run;
+
+		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
+
 		if (s->locked + conf->max_degraded == disks)
 			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
 				atomic_inc(&conf->pending_full_writes);
@@ -2310,11 +2317,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
-		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
-		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
-		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
-
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (i == pd_idx)
@@ -2329,6 +2331,13 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 				s->locked++;
 			}
 		}
+		if (!s->locked)
+			/* False alarm - nothing to do */
+			return;
+		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
 	}
 
 	/* keep the parity disk(s) locked while asynchronous operations
@@ -2563,6 +2572,8 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 	int i;
 
 	clear_bit(STRIPE_SYNCING, &sh->state);
+	if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+		wake_up(&conf->wait_for_overlap);
 	s->syncing = 0;
 	s->replacing = 0;
 	/* There is nothing more to do for sync/check/repair.
@@ -2736,6 +2747,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 {
 	int i;
 	struct r5dev *dev;
+	int discard_pending = 0;
 
 	for (i = disks; i--; )
 		if (sh->dev[i].written) {
@@ -2764,9 +2776,23 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 						STRIPE_SECTORS,
 					 !test_bit(STRIPE_DEGRADED, &sh->state),
 						0);
-			}
-		} else if (test_bit(R5_Discard, &sh->dev[i].flags))
-			clear_bit(R5_Discard, &sh->dev[i].flags);
+			} else if (test_bit(R5_Discard, &dev->flags))
+				discard_pending = 1;
+		}
+	if (!discard_pending &&
+	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
+		clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
+		clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+		if (sh->qd_idx >= 0) {
+			clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
+			clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags);
+		}
+		/* now that discard is done we can proceed with any sync */
+		clear_bit(STRIPE_DISCARD, &sh->state);
+		if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+			set_bit(STRIPE_HANDLE, &sh->state);
+
+	}
 
 	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
 		if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -2825,8 +2851,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 	set_bit(STRIPE_HANDLE, &sh->state);
 	if (rmw < rcw && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
-		blk_add_trace_msg(conf->mddev->queue, "raid5 rmw %llu %d",
-				  (unsigned long long)sh->sector, rmw);
+		if (conf->mddev->queue)
+			blk_add_trace_msg(conf->mddev->queue,
+					  "raid5 rmw %llu %d",
+					  (unsigned long long)sh->sector, rmw);
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if ((dev->towrite || i == sh->pd_idx) &&
@@ -2876,7 +2904,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 				}
 			}
 		}
-		if (rcw)
+		if (rcw && conf->mddev->queue)
 			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
 					  (unsigned long long)sh->sector,
 					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
@@ -3416,9 +3444,15 @@ static void handle_stripe(struct stripe_head *sh)
 		return;
 	}
 
-	if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
-		set_bit(STRIPE_SYNCING, &sh->state);
-		clear_bit(STRIPE_INSYNC, &sh->state);
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+		spin_lock(&sh->stripe_lock);
+		/* Cannot process 'sync' concurrently with 'discard' */
+		if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+			set_bit(STRIPE_SYNCING, &sh->state);
+			clear_bit(STRIPE_INSYNC, &sh->state);
+		}
+		spin_unlock(&sh->stripe_lock);
 	}
 	clear_bit(STRIPE_DELAYED, &sh->state);
 
@@ -3578,6 +3612,8 @@ static void handle_stripe(struct stripe_head *sh)
 	    test_bit(STRIPE_INSYNC, &sh->state)) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
 		clear_bit(STRIPE_SYNCING, &sh->state);
+		if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+			wake_up(&conf->wait_for_overlap);
 	}
 
 	/* If the failed drives are just a ReadError, then we might need
@@ -3981,9 +4017,10 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		atomic_inc(&conf->active_aligned_reads);
 		spin_unlock_irq(&conf->device_lock);
 
-		trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
-				      align_bi, disk_devt(mddev->gendisk),
-				      raid_bio->bi_sector);
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
+					      align_bi, disk_devt(mddev->gendisk),
+					      raid_bio->bi_sector);
 		generic_make_request(align_bi);
 		return 1;
 	} else {
@@ -4077,7 +4114,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 		}
 		spin_unlock_irq(&conf->device_lock);
 	}
-	trace_block_unplug(mddev->queue, cnt, !from_schedule);
+	if (mddev->queue)
+		trace_block_unplug(mddev->queue, cnt, !from_schedule);
 	kfree(cb);
 }
 
@@ -4140,6 +4178,13 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
 		prepare_to_wait(&conf->wait_for_overlap, &w,
 				TASK_UNINTERRUPTIBLE);
+		set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
+		if (test_bit(STRIPE_SYNCING, &sh->state)) {
+			release_stripe(sh);
+			schedule();
+			goto again;
+		}
+		clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
 		spin_lock_irq(&sh->stripe_lock);
 		for (d = 0; d < conf->raid_disks; d++) {
 			if (d == sh->pd_idx || d == sh->qd_idx)
@@ -4152,6 +4197,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 				goto again;
 			}
 		}
+		set_bit(STRIPE_DISCARD, &sh->state);
 		finish_wait(&conf->wait_for_overlap, &w);
 		for (d = 0; d < conf->raid_disks; d++) {
 			if (d == sh->pd_idx || d == sh->qd_idx)