1 files changed, 127 insertions, 65 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3ee2912889e..9359828ffe2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -90,7 +90,7 @@ static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
  */
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
-	int sectors = bio->bi_size >> 9;
+	int sectors = bio_sectors(bio);
 	if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
@@ -184,6 +184,8 @@ static void return_io(struct bio *return_bi)
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
 		bi->bi_size = 0;
+		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+					 bi, 0);
 		bio_endio(bi, 0);
 		bi = return_bi;
 	}
@@ -567,14 +569,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		bi = &sh->dev[i].req;
 		rbi = &sh->dev[i].rreq; /* For writing to replacement */
 
-		bi->bi_rw = rw;
-		rbi->bi_rw = rw;
-		if (rw & WRITE) {
-			bi->bi_end_io = raid5_end_write_request;
-			rbi->bi_end_io = raid5_end_write_request;
-		} else
-			bi->bi_end_io = raid5_end_read_request;
-
 		rcu_read_lock();
 		rrdev = rcu_dereference(conf->disks[i].replacement);
 		smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
@@ -649,7 +643,14 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
+			bio_reset(bi);
 			bi->bi_bdev = rdev->bdev;
+			bi->bi_rw = rw;
+			bi->bi_end_io = (rw & WRITE)
+				? raid5_end_write_request
+				: raid5_end_read_request;
+			bi->bi_private = sh;
+
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
 				__func__, (unsigned long long)sh->sector,
 				bi->bi_rw, i);
@@ -663,17 +664,16 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 				bi->bi_rw |= REQ_FLUSH;
 
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_idx = 0;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
 			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
 			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) {
@@ -683,7 +683,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
+			bio_reset(rbi);
 			rbi->bi_bdev = rrdev->bdev;
+			rbi->bi_rw = rw;
+			BUG_ON(!(rw & WRITE));
+			rbi->bi_end_io = raid5_end_write_request;
+			rbi->bi_private = sh;
+
 			pr_debug("%s: for %llu schedule op %ld on "
 				 "replacement disc %d\n",
 				__func__, (unsigned long long)sh->sector,
@@ -695,15 +701,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			else
 				rbi->bi_sector = (sh->sector
 						  + rrdev->data_offset);
-			rbi->bi_flags = 1 << BIO_UPTODATE;
-			rbi->bi_idx = 0;
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_size = STRIPE_SIZE;
-			rbi->bi_next = NULL;
-			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) {
@@ -1882,8 +1886,15 @@ static void raid5_end_write_request(struct bio *bi, int error)
 					&rdev->mddev->recovery);
 		} else if (is_badblock(rdev, sh->sector,
 				       STRIPE_SECTORS,
-				       &first_bad, &bad_sectors))
+				       &first_bad, &bad_sectors)) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
+			if (test_bit(R5_ReadError, &sh->dev[i].flags))
+				/* That was a successful write so make
+				 * sure it looks like we already did
+				 * a re-write.
+				 */
+				set_bit(R5_ReWrite, &sh->dev[i].flags);
+		}
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
@@ -2280,17 +2291,6 @@ 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];
@@ -2303,6 +2303,21 @@ 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);
@@ -2311,11 +2326,6 @@ 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)
@@ -2330,6 +2340,13 @@ 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
@@ -2384,11 +2401,11 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 	} else
 		bip = &sh->dev[dd_idx].toread;
 	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
-		if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
+		if (bio_end_sector(*bip) > bi->bi_sector)
 			goto overlap;
 		bip = & (*bip)->bi_next;
 	}
-	if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
+	if (*bip && (*bip)->bi_sector < bio_end_sector(bi))
 		goto overlap;
 
 	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
@@ -2404,8 +2421,8 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
 			     bi && bi->bi_sector <= sector;
 		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
-			if (bi->bi_sector + (bi->bi_size>>9) >= sector)
-				sector = bi->bi_sector + (bi->bi_size>>9);
+			if (bio_end_sector(bi) >= sector)
+				sector = bio_end_sector(bi);
 		}
 		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
 			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
@@ -2564,6 +2581,8 @@ 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.
@@ -2737,6 +2756,7 @@ 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) {
@@ -2765,9 +2785,23 @@ 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))
@@ -2826,8 +2860,10 @@ 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) &&
@@ -2877,7 +2913,7 @@ 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));
@@ -3417,9 +3453,15 @@ 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);
 
@@ -3579,6 +3621,8 @@ 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
@@ -3804,7 +3848,7 @@ static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
 	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bio_sectors(bio);
 
 	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
 		chunk_sectors = mddev->new_chunk_sectors;
@@ -3878,6 +3922,8 @@ static void raid5_align_endio(struct bio *bi, int error)
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error && uptodate) {
+		trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
+					 raid_bi, 0);
 		bio_endio(raid_bi, 0);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_stripe);
@@ -3894,7 +3940,7 @@ static int bio_fits_rdev(struct bio *bi)
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > queue_max_sectors(q))
+	if (bio_sectors(bi) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
 	if (bi->bi_phys_segments > queue_max_segments(q))
@@ -3941,7 +3987,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 						    0,
 						    &dd_idx, NULL);
 
-	end_sector = align_bi->bi_sector + (align_bi->bi_size >> 9);
+	end_sector = bio_end_sector(align_bi);
 	rcu_read_lock();
 	rdev = rcu_dereference(conf->disks[dd_idx].replacement);
 	if (!rdev || test_bit(Faulty, &rdev->flags) ||
@@ -3964,7 +4010,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
+		    is_badblock(rdev, align_bi->bi_sector, bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
 			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
@@ -3982,9 +4028,10 @@ 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 {
@@ -4078,7 +4125,8 @@ 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);
 }
 
@@ -4141,6 +4189,13 @@ 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)
@@ -4153,6 +4208,7 @@ 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)
@@ -4216,7 +4272,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 	}
 
 	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_sector + (bi->bi_size>>9);
+	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
 
@@ -4336,6 +4392,8 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		if ( rw == WRITE )
 			md_write_end(mddev);
 
+		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+					 bi, 0);
 		bio_endio(bi, 0);
 	}
 }
@@ -4620,9 +4678,10 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
 		*skipped = 1;
 		return rv;
 	}
-	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
-	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
-	    !conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
+	if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    !conf->fullsync &&
+	    !bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	    sync_blocks >= STRIPE_SECTORS) {
 		/* we can skip this block, and probably more */
 		sync_blocks /= STRIPE_SECTORS;
 		*skipped = 1;
@@ -4679,7 +4738,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	sector = raid5_compute_sector(conf, logical_sector,
 				      0, &dd_idx, NULL);
-	last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
+	last_sector = bio_end_sector(raid_bio);
 
 	for (; logical_sector < last_sector;
 	     logical_sector += STRIPE_SECTORS,
@@ -4712,8 +4771,11 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		handled++;
 	}
 	remaining = raid5_dec_bi_active_stripes(raid_bio);
-	if (remaining == 0)
+	if (remaining == 0) {
+		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
+					 raid_bio, 0);
 		bio_endio(raid_bio, 0);
+	}
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_stripe);
 	return handled;