1 files changed, 80 insertions, 59 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index deddabfb07d7..3983d5c8b5cd 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -751,8 +751,16 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
+		    r10_bio->devs[slot].addr + sectors >
+		    rdev->recovery_offset) {
+			/*
+			 * Read replacement first to prevent reading both rdev
+			 * and replacement as NULL during replacement replace
+			 * rdev.
+			 */
+			smp_mb();
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		}
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags))
 			continue;
@@ -919,6 +927,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			else
 				generic_make_request(bio);
 			bio = next;
+			cond_resched();
 		}
 		blk_finish_plug(&plug);
 	} else
@@ -1104,6 +1113,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		else
 			generic_make_request(bio);
 		bio = next;
+		cond_resched();
 	}
 	kfree(plug);
 }
@@ -1363,9 +1373,15 @@ retry_write:
 
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[d].replacement);
+		struct md_rdev *rdev, *rrdev;
+
+		rrdev = rcu_dereference(conf->mirrors[d].replacement);
+		/*
+		 * Read replacement first to prevent reading both rdev and
+		 * replacement as NULL during replacement replace rdev.
+		 */
+		smp_mb();
+		rdev = rcu_dereference(conf->mirrors[d].rdev);
 		if (rdev == rrdev)
 			rrdev = NULL;
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
@@ -1826,9 +1842,12 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int err = 0;
 	int number = rdev->raid_disk;
 	struct md_rdev **rdevp;
-	struct raid10_info *p = conf->mirrors + number;
+	struct raid10_info *p;
 
 	print_conf(conf);
+	if (unlikely(number >= mddev->raid_disks))
+		return 0;
+	p = conf->mirrors + number;
 	if (rdev == p->rdev)
 		rdevp = &p->rdev;
 	else if (rdev == p->replacement)
@@ -2226,11 +2245,22 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
 	int d;
-	struct bio *wbio, *wbio2;
+	struct bio *wbio = r10_bio->devs[1].bio;
+	struct bio *wbio2 = r10_bio->devs[1].repl_bio;
+
+	/* Need to test wbio2->bi_end_io before we call
+	 * generic_make_request as if the former is NULL,
+	 * the latter is free to free wbio2.
+	 */
+	if (wbio2 && !wbio2->bi_end_io)
+		wbio2 = NULL;
 
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) {
 		fix_recovery_read_error(r10_bio);
-		end_sync_request(r10_bio);
+		if (wbio->bi_end_io)
+			end_sync_request(r10_bio);
+		if (wbio2)
+			end_sync_request(r10_bio);
 		return;
 	}
 
@@ -2239,14 +2269,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	 * and submit the write request
 	 */
 	d = r10_bio->devs[1].devnum;
-	wbio = r10_bio->devs[1].bio;
-	wbio2 = r10_bio->devs[1].repl_bio;
-	/* Need to test wbio2->bi_end_io before we call
-	 * generic_make_request as if the former is NULL,
-	 * the latter is free to free wbio2.
-	 */
-	if (wbio2 && !wbio2->bi_end_io)
-		wbio2 = NULL;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
@@ -2914,10 +2936,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 	sector_t chunk_mask = conf->geo.chunk_mask;
 	int page_idx = 0;
 
-	if (!mempool_initialized(&conf->r10buf_pool))
-		if (init_resync(conf))
-			return 0;
-
 	/*
 	 * Allow skipping a full rebuild for incremental assembly
 	 * of a clean array, like RAID1 does.
@@ -2933,6 +2951,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		return mddev->dev_sectors - sector_nr;
 	}
 
+	if (!mempool_initialized(&conf->r10buf_pool))
+		if (init_resync(conf))
+			return 0;
+
  skipped:
 	max_sector = mddev->dev_sectors;
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -3048,7 +3070,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			int must_sync;
 			int any_working;
 			int need_recover = 0;
-			int need_replace = 0;
 			struct raid10_info *mirror = &conf->mirrors[i];
 			struct md_rdev *mrdev, *mreplace;
 
@@ -3060,11 +3081,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			    !test_bit(Faulty, &mrdev->flags) &&
 			    !test_bit(In_sync, &mrdev->flags))
 				need_recover = 1;
-			if (mreplace != NULL &&
-			    !test_bit(Faulty, &mreplace->flags))
-				need_replace = 1;
+			if (mreplace && test_bit(Faulty, &mreplace->flags))
+				mreplace = NULL;
 
-			if (!need_recover && !need_replace) {
+			if (!need_recover && !mreplace) {
 				rcu_read_unlock();
 				continue;
 			}
@@ -3080,8 +3100,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				rcu_read_unlock();
 				continue;
 			}
-			if (mreplace && test_bit(Faulty, &mreplace->flags))
-				mreplace = NULL;
 			/* Unless we are doing a full sync, or a replacement
 			 * we only need to recover the block if it is set in
 			 * the bitmap
@@ -3204,11 +3222,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				bio = r10_bio->devs[1].repl_bio;
 				if (bio)
 					bio->bi_end_io = NULL;
-				/* Note: if need_replace, then bio
+				/* Note: if replace is not NULL, then bio
 				 * cannot be NULL as r10buf_pool_alloc will
 				 * have allocated it.
 				 */
-				if (!need_replace)
+				if (!mreplace)
 					break;
 				bio->bi_next = biolist;
 				biolist = bio;
@@ -3629,6 +3647,20 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
 	return nc*fc;
 }
 
+static void raid10_free_conf(struct r10conf *conf)
+{
+	if (!conf)
+		return;
+
+	mempool_exit(&conf->r10bio_pool);
+	kfree(conf->mirrors);
+	kfree(conf->mirrors_old);
+	kfree(conf->mirrors_new);
+	safe_put_page(conf->tmppage);
+	bioset_exit(&conf->bio_split);
+	kfree(conf);
+}
+
 static struct r10conf *setup_conf(struct mddev *mddev)
 {
 	struct r10conf *conf = NULL;
@@ -3711,20 +3743,24 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return conf;
 
  out:
-	if (conf) {
-		mempool_exit(&conf->r10bio_pool);
-		kfree(conf->mirrors);
-		safe_put_page(conf->tmppage);
-		bioset_exit(&conf->bio_split);
-		kfree(conf);
-	}
+	raid10_free_conf(conf);
 	return ERR_PTR(err);
 }
 
+static void raid10_set_io_opt(struct r10conf *conf)
+{
+	int raid_disks = conf->geo.raid_disks;
+
+	if (!(conf->geo.raid_disks % conf->geo.near_copies))
+		raid_disks /= conf->geo.near_copies;
+	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
+			 raid_disks);
+}
+
 static int raid10_run(struct mddev *mddev)
 {
 	struct r10conf *conf;
-	int i, disk_idx, chunk_size;
+	int i, disk_idx;
 	struct raid10_info *disk;
 	struct md_rdev *rdev;
 	sector_t size;
@@ -3745,6 +3781,9 @@ static int raid10_run(struct mddev *mddev)
 	if (!conf)
 		goto out;
 
+	mddev->thread = conf->thread;
+	conf->thread = NULL;
+
 	if (mddev_is_clustered(conf->mddev)) {
 		int fc, fo;
 
@@ -3757,21 +3796,13 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	mddev->thread = conf->thread;
-	conf->thread = NULL;
-
-	chunk_size = mddev->chunk_sectors << 9;
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
 					      mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, chunk_size);
-		if (conf->geo.raid_disks % conf->geo.near_copies)
-			blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
-		else
-			blk_queue_io_opt(mddev->queue, chunk_size *
-					 (conf->geo.raid_disks / conf->geo.near_copies));
+		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
+		raid10_set_io_opt(conf);
 	}
 
 	rdev_for_each(rdev, mddev) {
@@ -3931,10 +3962,7 @@ static int raid10_run(struct mddev *mddev)
 
 out_free_conf:
 	md_unregister_thread(&mddev->thread);
-	mempool_exit(&conf->r10bio_pool);
-	safe_put_page(conf->tmppage);
-	kfree(conf->mirrors);
-	kfree(conf);
+	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
 	return -EIO;
@@ -3942,15 +3970,7 @@ out:
 
 static void raid10_free(struct mddev *mddev, void *priv)
 {
-	struct r10conf *conf = priv;
-
-	mempool_exit(&conf->r10bio_pool);
-	safe_put_page(conf->tmppage);
-	kfree(conf->mirrors);
-	kfree(conf->mirrors_old);
-	kfree(conf->mirrors_new);
-	bioset_exit(&conf->bio_split);
-	kfree(conf);
+	raid10_free_conf(priv);
 }
 
 static void raid10_quiesce(struct mddev *mddev, int quiesce)
@@ -4745,6 +4765,7 @@ static void end_reshape(struct r10conf *conf)
 		stripe /= conf->geo.near_copies;
 		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
 			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+		raid10_set_io_opt(conf);
 	}
 	conf->fullsync = 0;
 }