Merge tag 'md-3.7-fixes' of git://neil.brown.name/md

Pull md fixes from NeilBrown:
 "Several bug fixes for md in 3.7:

   - raid5 discard has problems
   - raid10 replacement devices have problems
   - bad block lock seqlock usage has problems
   - dm-raid doesn't free everything"

* tag 'md-3.7-fixes' of git://neil.brown.name/md:
  md/raid10: decrement correct pending counter when writing to replacement.
  md/raid10: close race that lose writes lost when replacement completes.
  md/raid5: Make sure we clear R5_Discard when discard is finished.
  md/raid5: move resolving of reconstruct_state earlier in stripe_handle.
  md/raid5: round discard alignment up to power of 2.
  md: make sure everything is freed when dm-raid stops an array.
  md: Avoid write invalid address if read_seqretry returned true.
  md: Reassigned the parameters if read_seqretry returned true in func md_is_badblock.

3 files changed, 132 insertions, 105 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9ab768acfb6..61200717687 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1817,10 +1817,10 @@ retry:
 			memset(bbp, 0xff, PAGE_SIZE);
 
 			for (i = 0 ; i < bb->count ; i++) {
-				u64 internal_bb = *p++;
+				u64 internal_bb = p[i];
 				u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
 						| BB_LEN(internal_bb));
-				*bbp++ = cpu_to_le64(store_bb);
+				bbp[i] = cpu_to_le64(store_bb);
 			}
 			bb->changed = 0;
 			if (read_seqretry(&bb->lock, seq))
@@ -5294,7 +5294,7 @@ void md_stop_writes(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_stop_writes);
 
-void md_stop(struct mddev *mddev)
+static void __md_stop(struct mddev *mddev)
 {
 	mddev->ready = 0;
 	mddev->pers->stop(mddev);
@@ -5304,6 +5304,18 @@ void md_stop(struct mddev *mddev)
 	mddev->pers = NULL;
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 }
+
+void md_stop(struct mddev *mddev)
+{
+	/* stop the array and free an attached data structures.
+	 * This is called from dm-raid
+	 */
+	__md_stop(mddev);
+	bitmap_destroy(mddev);
+	if (mddev->bio_set)
+		bioset_free(mddev->bio_set);
+}
+
 EXPORT_SYMBOL_GPL(md_stop);
 
 static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
@@ -5364,7 +5376,7 @@ static int do_md_stop(struct mddev * mddev, int mode,
 			set_disk_ro(disk, 0);
 
 		__md_stop_writes(mddev);
-		md_stop(mddev);
+		__md_stop(mddev);
 		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
@@ -7936,9 +7948,9 @@ int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
 		   sector_t *first_bad, int *bad_sectors)
 {
 	int hi;
-	int lo = 0;
+	int lo;
 	u64 *p = bb->page;
-	int rv = 0;
+	int rv;
 	sector_t target = s + sectors;
 	unsigned seq;
 
@@ -7953,7 +7965,8 @@ int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
 
 retry:
 	seq = read_seqbegin(&bb->lock);
-
+	lo = 0;
+	rv = 0;
 	hi = bb->count;
 
 	/* Binary search between lo and hi for 'target'
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d1295aff417..0d5d0ff2c0f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -499,7 +499,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
 	 */
 	one_write_done(r10_bio);
 	if (dec_rdev)
-		rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
+		rdev_dec_pending(rdev, conf->mddev);
 }
 
 /*
@@ -1334,18 +1334,21 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
+		if (rdev && (test_bit(Faulty, &rdev->flags)
+			     || test_bit(Unmerged, &rdev->flags)))
+			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)
 			      || test_bit(Unmerged, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags)) {
+
+		if (!rdev && !rrdev) {
 			set_bit(R10BIO_Degraded, &r10_bio->state);
 			continue;
 		}
-		if (test_bit(WriteErrorSeen, &rdev->flags)) {
+		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
 			int bad_sectors;
@@ -1387,8 +1390,10 @@ retry_write:
 					max_sectors = good_sectors;
 			}
 		}
-		r10_bio->devs[i].bio = bio;
-		atomic_inc(&rdev->nr_pending);
+		if (rdev) {
+			r10_bio->devs[i].bio = bio;
+			atomic_inc(&rdev->nr_pending);
+		}
 		if (rrdev) {
 			r10_bio->devs[i].repl_bio = bio;
 			atomic_inc(&rrdev->nr_pending);
@@ -1444,69 +1449,71 @@ retry_write:
 	for (i = 0; i < conf->copies; i++) {
 		struct bio *mbio;
 		int d = r10_bio->devs[i].devnum;
-		if (!r10_bio->devs[i].bio)
-			continue;
+		if (r10_bio->devs[i].bio) {
+			struct md_rdev *rdev = conf->mirrors[d].rdev;
+			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+				    max_sectors);
+			r10_bio->devs[i].bio = mbio;
+
+			mbio->bi_sector	= (r10_bio->devs[i].addr+
+					   choose_data_offset(r10_bio,
+							      rdev));
+			mbio->bi_bdev = rdev->bdev;
+			mbio->bi_end_io	= raid10_end_write_request;
+			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_private = r10_bio;
 
-		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
-		r10_bio->devs[i].bio = mbio;
+			atomic_inc(&r10_bio->remaining);
 
-		mbio->bi_sector	= (r10_bio->devs[i].addr+
-				   choose_data_offset(r10_bio,
-						      conf->mirrors[d].rdev));
-		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
-		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
-		mbio->bi_private = r10_bio;
+			cb = blk_check_plugged(raid10_unplug, mddev,
+					       sizeof(*plug));
+			if (cb)
+				plug = container_of(cb, struct raid10_plug_cb,
+						    cb);
+			else
+				plug = NULL;
+			spin_lock_irqsave(&conf->device_lock, flags);
+			if (plug) {
+				bio_list_add(&plug->pending, mbio);
+				plug->pending_cnt++;
+			} else {
+				bio_list_add(&conf->pending_bio_list, mbio);
+				conf->pending_count++;
+			}
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			if (!plug)
+				md_wakeup_thread(mddev->thread);
+		}
 
-		atomic_inc(&r10_bio->remaining);
+		if (r10_bio->devs[i].repl_bio) {
+			struct md_rdev *rdev = conf->mirrors[d].replacement;
+			if (rdev == NULL) {
+				/* Replacement just got moved to main 'rdev' */
+				smp_mb();
+				rdev = conf->mirrors[d].rdev;
+			}
+			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+				    max_sectors);
+			r10_bio->devs[i].repl_bio = mbio;
+
+			mbio->bi_sector	= (r10_bio->devs[i].addr +
+					   choose_data_offset(
+						   r10_bio, rdev));
+			mbio->bi_bdev = rdev->bdev;
+			mbio->bi_end_io	= raid10_end_write_request;
+			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_private = r10_bio;
 
-		cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
-		if (cb)
-			plug = container_of(cb, struct raid10_plug_cb, cb);
-		else
-			plug = NULL;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		if (plug) {
-			bio_list_add(&plug->pending, mbio);
-			plug->pending_cnt++;
-		} else {
+			atomic_inc(&r10_bio->remaining);
+			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			conf->pending_count++;
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			if (!mddev_check_plugged(mddev))
+				md_wakeup_thread(mddev->thread);
 		}
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!plug)
-			md_wakeup_thread(mddev->thread);
-
-		if (!r10_bio->devs[i].repl_bio)
-			continue;
-
-		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
-		r10_bio->devs[i].repl_bio = mbio;
-
-		/* We are actively writing to the original device
-		 * so it cannot disappear, so the replacement cannot
-		 * become NULL here
-		 */
-		mbio->bi_sector	= (r10_bio->devs[i].addr +
-				   choose_data_offset(
-					   r10_bio,
-					   conf->mirrors[d].replacement));
-		mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
-		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
-		mbio->bi_private = r10_bio;
-
-		atomic_inc(&r10_bio->remaining);
-		spin_lock_irqsave(&conf->device_lock, flags);
-		bio_list_add(&conf->pending_bio_list, mbio);
-		conf->pending_count++;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!mddev_check_plugged(mddev))
-			md_wakeup_thread(mddev->thread);
 	}
 
 	/* Don't remove the bias on 'remaining' (one_write_done) until
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c5439dce029..a4502686e7a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2774,10 +2774,12 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 			dev = &sh->dev[i];
 			if (!test_bit(R5_LOCKED, &dev->flags) &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			     test_and_clear_bit(R5_Discard, &dev->flags))) {
+			     test_bit(R5_Discard, &dev->flags))) {
 				/* We can return any write requests */
 				struct bio *wbi, *wbi2;
 				pr_debug("Return write for disc %d\n", i);
+				if (test_and_clear_bit(R5_Discard, &dev->flags))
+					clear_bit(R5_UPTODATE, &dev->flags);
 				wbi = dev->written;
 				dev->written = NULL;
 				while (wbi && wbi->bi_sector <
@@ -2795,7 +2797,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 					 !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);
 
 	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
 		if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -3490,40 +3493,6 @@ static void handle_stripe(struct stripe_head *sh)
 			handle_failed_sync(conf, sh, &s);
 	}
 
-	/*
-	 * might be able to return some write requests if the parity blocks
-	 * are safe, or on a failed drive
-	 */
-	pdev = &sh->dev[sh->pd_idx];
-	s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
-		|| (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
-	qdev = &sh->dev[sh->qd_idx];
-	s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
-		|| (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
-		|| conf->level < 6;
-
-	if (s.written &&
-	    (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
-			     && !test_bit(R5_LOCKED, &pdev->flags)
-			     && (test_bit(R5_UPTODATE, &pdev->flags) ||
-				 test_bit(R5_Discard, &pdev->flags))))) &&
-	    (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
-			     && !test_bit(R5_LOCKED, &qdev->flags)
-			     && (test_bit(R5_UPTODATE, &qdev->flags) ||
-				 test_bit(R5_Discard, &qdev->flags))))))
-		handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
-
-	/* Now we might consider reading some blocks, either to check/generate
-	 * parity, or to satisfy requests
-	 * or to load a block that is being partially written.
-	 */
-	if (s.to_read || s.non_overwrite
-	    || (conf->level == 6 && s.to_write && s.failed)
-	    || (s.syncing && (s.uptodate + s.compute < disks))
-	    || s.replacing
-	    || s.expanding)
-		handle_stripe_fill(sh, &s, disks);
-
 	/* Now we check to see if any write operations have recently
 	 * completed
 	 */
@@ -3561,6 +3530,40 @@ static void handle_stripe(struct stripe_head *sh)
 			s.dec_preread_active = 1;
 	}
 
+	/*
+	 * might be able to return some write requests if the parity blocks
+	 * are safe, or on a failed drive
+	 */
+	pdev = &sh->dev[sh->pd_idx];
+	s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
+		|| (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
+	qdev = &sh->dev[sh->qd_idx];
+	s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
+		|| (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
+		|| conf->level < 6;
+
+	if (s.written &&
+	    (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
+			     && !test_bit(R5_LOCKED, &pdev->flags)
+			     && (test_bit(R5_UPTODATE, &pdev->flags) ||
+				 test_bit(R5_Discard, &pdev->flags))))) &&
+	    (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
+			     && !test_bit(R5_LOCKED, &qdev->flags)
+			     && (test_bit(R5_UPTODATE, &qdev->flags) ||
+				 test_bit(R5_Discard, &qdev->flags))))))
+		handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
+
+	/* Now we might consider reading some blocks, either to check/generate
+	 * parity, or to satisfy requests
+	 * or to load a block that is being partially written.
+	 */
+	if (s.to_read || s.non_overwrite
+	    || (conf->level == 6 && s.to_write && s.failed)
+	    || (s.syncing && (s.uptodate + s.compute < disks))
+	    || s.replacing
+	    || s.expanding)
+		handle_stripe_fill(sh, &s, disks);
+
 	/* Now to consider new write requests and what else, if anything
 	 * should be read.  We do not handle new writes when:
 	 * 1/ A 'write' operation (copy+xor) is already in flight.
@@ -5529,6 +5532,10 @@ static int run(struct mddev *mddev)
 		 * discard data disk but write parity disk
 		 */
 		stripe = stripe * PAGE_SIZE;
+		/* Round up to power of 2, as discard handling
+		 * currently assumes that */
+		while ((stripe-1) & stripe)
+			stripe = (stripe | (stripe-1)) + 1;
 		mddev->queue->limits.discard_alignment = stripe;
 		mddev->queue->limits.discard_granularity = stripe;
 		/*