Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:
 - A bunch of patches from Neil Brown to fix RCU usage
 - Two performance improvement patches from Tomasz Majchrzak
 - Alexey Obitotskiy fixes module refcount issue
 - Arnd Bergmann fixes time granularity
 - Cong Wang fixes a list corruption issue
 - Guoqing Jiang fixes a deadlock in md-cluster
 - A null pointer deference fix from me
 - Song Liu fixes misuse of raid6 rmw
 - Other trival/cleanup fixes from Guoqing Jiang and Xiao Ni

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (28 commits)
  MD: fix null pointer deference
  raid10: improve random reads performance
  md: add missing sysfs_notify on array_state update
  Fix kernel module refcount handling
  md: use seconds granularity for error logging
  md: reduce the number of synchronize_rcu() calls when multiple devices fail.
  md: be extra careful not to take a reference to a Faulty device.
  md/multipath: add rcu protection to rdev access in multipath_status.
  md/raid5: add rcu protection to rdev accesses in raid5_status.
  md/raid5: add rcu protection to rdev accesses in want_replace
  md/raid5: add rcu protection to rdev accesses in handle_failed_sync.
  md/raid1: add rcu protection to rdev in fix_read_error
  md/raid1: small code cleanup in end_sync_write
  md/raid1: small cleanup in raid1_end_read/write_request
  md/raid10: simplify print_conf a little.
  md/raid10: minor code improvement in fix_read_error()
  md/raid10: add rcu protection to rdev access during reshape.
  md/raid10: add rcu protection to rdev access in raid10_sync_request.
  md/raid10: add rcu protection in raid10_status.
  md/raid10: fix refounct imbalance when resyncing an array with a replacement device.
  ...

drivers/md/md.c

@@ -2482,8 +2482,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		if (add_journal)
 			mddev_resume(mddev);
 		if (err) {
-			unbind_rdev_from_array(rdev);
-			export_rdev(rdev);
+			md_kick_rdev_from_array(rdev);
 			return err;
 		}
 	}
@@ -2600,6 +2599,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		else
 			err = -EBUSY;
 	} else if (cmd_match(buf, "remove")) {
+		if (rdev->mddev->pers) {
+			clear_bit(Blocked, &rdev->flags);
+			remove_and_add_spares(rdev->mddev, rdev);
+		}
 		if (rdev->raid_disk >= 0)
 			err = -EBUSY;
 		else {
@@ -3176,8 +3179,7 @@ int md_rdev_init(struct md_rdev *rdev)
 	rdev->data_offset = 0;
 	rdev->new_data_offset = 0;
 	rdev->sb_events = 0;
-	rdev->last_read_error.tv_sec  = 0;
-	rdev->last_read_error.tv_nsec = 0;
+	rdev->last_read_error = 0;
 	rdev->sb_loaded = 0;
 	rdev->bb_page = NULL;
 	atomic_set(&rdev->nr_pending, 0);
@@ -3583,6 +3585,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			mddev->to_remove = &md_redundancy_group;
 	}
 
+	module_put(oldpers->owner);
+
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
@@ -3940,6 +3944,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 			} else
 				err = -EBUSY;
 		}
+		if (!err)
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 		spin_unlock(&mddev->lock);
 		return err ?: len;
 	}
@@ -4191,6 +4197,7 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
 		return err;
 	if (mddev->pers) {
 		err = update_size(mddev, sectors);
+		if (err == 0)
 			md_update_sb(mddev, 1);
 	} else {
 		if (mddev->dev_sectors == 0 ||
@@ -7813,6 +7820,7 @@ void md_do_sync(struct md_thread *thread)
 		if (ret)
 			goto skip;
 
+		set_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags);
 		if (!(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
 			test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ||
 			test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
@@ -8151,18 +8159,11 @@ void md_do_sync(struct md_thread *thread)
 		}
 	}
  skip:
-	if (mddev_is_clustered(mddev) &&
-	    ret == 0) {
-		/* set CHANGE_PENDING here since maybe another
-		 * update is needed, so other nodes are informed */
+	/* set CHANGE_PENDING here since maybe another update is needed,
+	 * so other nodes are informed. It should be harmless for normal
+	 * raid */
 	set_mask_bits(&mddev->flags, 0,
 		      BIT(MD_CHANGE_PENDING) | BIT(MD_CHANGE_DEVS));
-		md_wakeup_thread(mddev->thread);
-		wait_event(mddev->sb_wait,
-			   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
-		md_cluster_ops->resync_finish(mddev);
-	} else
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
 	spin_lock(&mddev->lock);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
@@ -8188,15 +8189,34 @@ static int remove_and_add_spares(struct mddev *mddev,
 	struct md_rdev *rdev;
 	int spares = 0;
 	int removed = 0;
+	bool remove_some = false;
 
-	rdev_for_each(rdev, mddev)
+	rdev_for_each(rdev, mddev) {
+		if ((this == NULL || rdev == this) &&
+		    rdev->raid_disk >= 0 &&
+		    !test_bit(Blocked, &rdev->flags) &&
+		    test_bit(Faulty, &rdev->flags) &&
+		    atomic_read(&rdev->nr_pending)==0) {
+			/* Faulty non-Blocked devices with nr_pending == 0
+			 * never get nr_pending incremented,
+			 * never get Faulty cleared, and never get Blocked set.
+			 * So we can synchronize_rcu now rather than once per device
+			 */
+			remove_some = true;
+			set_bit(RemoveSynchronized, &rdev->flags);
+		}
+	}
+
+	if (remove_some)
+		synchronize_rcu();
+	rdev_for_each(rdev, mddev) {
 		if ((this == NULL || rdev == this) &&
 		    rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
-		    (test_bit(Faulty, &rdev->flags) ||
+		    ((test_bit(RemoveSynchronized, &rdev->flags) ||
 		     (!test_bit(In_sync, &rdev->flags) &&
 		      !test_bit(Journal, &rdev->flags))) &&
-		    atomic_read(&rdev->nr_pending)==0) {
+		    atomic_read(&rdev->nr_pending)==0)) {
 			if (mddev->pers->hot_remove_disk(
 				    mddev, rdev) == 0) {
 				sysfs_unlink_rdev(mddev, rdev);
@@ -8204,6 +8224,10 @@ static int remove_and_add_spares(struct mddev *mddev,
 				removed++;
 			}
 		}
+		if (remove_some && test_bit(RemoveSynchronized, &rdev->flags))
+			clear_bit(RemoveSynchronized, &rdev->flags);
+	}
+
 	if (removed && mddev->kobj.sd)
 		sysfs_notify(&mddev->kobj, NULL, "degraded");
 
@@ -8506,6 +8530,11 @@ void md_reap_sync_thread(struct mddev *mddev)
 			rdev->saved_raid_disk = -1;
 
 	md_update_sb(mddev, 1);
+	/* MD_CHANGE_PENDING should be cleared by md_update_sb, so we can
+	 * call resync_finish here if MD_CLUSTER_RESYNC_LOCKED is set by
+	 * clustered raid */
+	if (test_and_clear_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags))
+		md_cluster_ops->resync_finish(mddev);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -8803,6 +8832,7 @@ EXPORT_SYMBOL(md_reload_sb);
  * at boot time.
  */
 
+static DEFINE_MUTEX(detected_devices_mutex);
 static LIST_HEAD(all_detected_devices);
 struct detected_devices_node {
 	struct list_head list;
@@ -8816,7 +8846,9 @@ void md_autodetect_dev(dev_t dev)
 	node_detected_dev = kzalloc(sizeof(*node_detected_dev), GFP_KERNEL);
 	if (node_detected_dev) {
 		node_detected_dev->dev = dev;
+		mutex_lock(&detected_devices_mutex);
 		list_add_tail(&node_detected_dev->list, &all_detected_devices);
+		mutex_unlock(&detected_devices_mutex);
 	} else {
 		printk(KERN_CRIT "md: md_autodetect_dev: kzalloc failed"
 			", skipping dev(%d,%d)\n", MAJOR(dev), MINOR(dev));
@@ -8835,6 +8867,7 @@ static void autostart_arrays(int part)
 
 	printk(KERN_INFO "md: Autodetecting RAID arrays.\n");
 
+	mutex_lock(&detected_devices_mutex);
 	while (!list_empty(&all_detected_devices) && i_scanned < INT_MAX) {
 		i_scanned++;
 		node_detected_dev = list_entry(all_detected_devices.next,
@@ -8853,6 +8886,7 @@ static void autostart_arrays(int part)
 		list_add(&rdev->same_set, &pending_raid_disks);
 		i_passed++;
 	}
+	mutex_unlock(&detected_devices_mutex);
 
 	printk(KERN_INFO "md: Scanned %d and added %d devices.\n",
 						i_scanned, i_passed);

drivers/md/md.h

@@ -99,7 +99,7 @@ struct md_rdev {
 	atomic_t	read_errors;	/* number of consecutive read errors that
 					 * we have tried to ignore.
 					 */
-	struct timespec last_read_error;	/* monotonic time since our
+	time64_t	last_read_error;	/* monotonic time since our
 						 * last read error
 						 */
 	atomic_t	corrected_errors; /* number of corrected read errors,
@@ -163,6 +163,11 @@ enum flag_bits {
 				 * than other devices in the array
 				 */
 	ClusterRemove,
+	RemoveSynchronized,	/* synchronize_rcu() was called after
+				 * this device was known to be faulty,
+				 * so it is safe to remove without
+				 * another synchronize_rcu() call.
+				 */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -204,6 +209,9 @@ struct mddev {
 #define MD_RELOAD_SB	7	/* Reload the superblock because another node
 				 * updated it.
 				 */
+#define MD_CLUSTER_RESYNC_LOCKED 8 /* cluster raid only, which means node
+				    * already took resync lock, need to
+				    * release the lock */
 
 	int				suspended;
 	atomic_t			active_io;

drivers/md/multipath.c

@@ -43,7 +43,8 @@ static int multipath_map (struct mpconf *conf)
 	rcu_read_lock();
 	for (i = 0; i < disks; i++) {
 		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		if (rdev && test_bit(In_sync, &rdev->flags)) {
+		if (rdev && test_bit(In_sync, &rdev->flags) &&
+		    !test_bit(Faulty, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 			return i;
@@ -141,17 +142,19 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	return;
 }
 
-static void multipath_status (struct seq_file *seq, struct mddev *mddev)
+static void multipath_status(struct seq_file *seq, struct mddev *mddev)
 {
 	struct mpconf *conf = mddev->private;
 	int i;
 
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
 		    conf->raid_disks - mddev->degraded);
-	for (i = 0; i < conf->raid_disks; i++)
-		seq_printf (seq, "%s",
-			       conf->multipaths[i].rdev &&
-			       test_bit(In_sync, &conf->multipaths[i].rdev->flags) ? "U" : "_");
+	rcu_read_lock();
+	for (i = 0; i < conf->raid_disks; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
+		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+	}
+	rcu_read_unlock();
 	seq_printf (seq, "]");
 }
 
@@ -295,6 +298,7 @@ static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			goto abort;
 		}
 		p->rdev = NULL;
+		if (!test_bit(RemoveSynchronized, &rdev->flags)) {
 			synchronize_rcu();
 			if (atomic_read(&rdev->nr_pending)) {
 				/* lost the race, try later */
@@ -302,6 +306,7 @@ static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 				p->rdev = rdev;
 				goto abort;
 			}
+		}
 		err = md_integrity_register(mddev);
 	}
 abort:

drivers/md/raid1.c

@@ -319,14 +319,13 @@ static void raid1_end_read_request(struct bio *bio)
 {
 	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
-	int mirror;
 	struct r1conf *conf = r1_bio->mddev->private;
+	struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
 
-	mirror = r1_bio->read_disk;
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	update_head_pos(mirror, r1_bio);
+	update_head_pos(r1_bio->read_disk, r1_bio);
 
 	if (uptodate)
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
@@ -339,14 +338,14 @@ static void raid1_end_read_request(struct bio *bio)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 
 	if (uptodate) {
 		raid_end_bio_io(r1_bio);
-		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+		rdev_dec_pending(rdev, conf->mddev);
 	} else {
 		/*
 		 * oops, read error:
@@ -356,7 +355,7 @@ static void raid1_end_read_request(struct bio *bio)
 			KERN_ERR "md/raid1:%s: %s: "
 			"rescheduling sector %llu\n",
 			mdname(conf->mddev),
-			bdevname(conf->mirrors[mirror].rdev->bdev,
+			bdevname(rdev->bdev,
 				 b),
 			(unsigned long long)r1_bio->sector);
 		set_bit(R1BIO_ReadError, &r1_bio->state);
@@ -403,20 +402,18 @@ static void r1_bio_write_done(struct r1bio *r1_bio)
 static void raid1_end_write_request(struct bio *bio)
 {
 	struct r1bio *r1_bio = bio->bi_private;
-	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
+	int behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	struct r1conf *conf = r1_bio->mddev->private;
 	struct bio *to_put = NULL;
-
-	mirror = find_bio_disk(r1_bio, bio);
+	int mirror = find_bio_disk(r1_bio, bio);
+	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
 	if (bio->bi_error) {
-		set_bit(WriteErrorSeen,
-			&conf->mirrors[mirror].rdev->flags);
-		if (!test_and_set_bit(WantReplacement,
-				      &conf->mirrors[mirror].rdev->flags))
+		set_bit(WriteErrorSeen,	&rdev->flags);
+		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
 				conf->mddev->recovery);
 
@@ -445,13 +442,12 @@ static void raid1_end_write_request(struct bio *bio)
 		 * before rdev->recovery_offset, but for simplicity we don't
 		 * check this here.
 		 */
-		if (test_bit(In_sync, &conf->mirrors[mirror].rdev->flags) &&
-		    !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))
+		if (test_bit(In_sync, &rdev->flags) &&
+		    !test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(conf->mirrors[mirror].rdev,
-				r1_bio->sector, r1_bio->sectors,
+		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
 				&first_bad, &bad_sectors)) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
@@ -459,7 +455,7 @@ static void raid1_end_write_request(struct bio *bio)
 	}
 
 	if (behind) {
-		if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+		if (test_bit(WriteMostly, &rdev->flags))
 			atomic_dec(&r1_bio->behind_remaining);
 
 		/*
@@ -483,8 +479,7 @@ static void raid1_end_write_request(struct bio *bio)
 		}
 	}
 	if (r1_bio->bios[mirror] == NULL)
-		rdev_dec_pending(conf->mirrors[mirror].rdev,
-				 conf->mddev);
+		rdev_dec_pending(rdev, conf->mddev);
 
 	/*
 	 * Let's see if all mirrored write operations have finished
@@ -689,13 +684,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		if (!rdev)
 			goto retry;
 		atomic_inc(&rdev->nr_pending);
-		if (test_bit(Faulty, &rdev->flags)) {
-			/* cannot risk returning a device that failed
-			 * before we inc'ed nr_pending
-			 */
-			rdev_dec_pending(rdev, conf->mddev);
-			goto retry;
-		}
 		sectors = best_good_sectors;
 
 		if (conf->mirrors[best_disk].next_seq_sect != this_sector)
@@ -1666,13 +1654,16 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			goto abort;
 		}
 		p->rdev = NULL;
+		if (!test_bit(RemoveSynchronized, &rdev->flags)) {
 			synchronize_rcu();
 			if (atomic_read(&rdev->nr_pending)) {
 				/* lost the race, try later */
 				err = -EBUSY;
 				p->rdev = rdev;
 				goto abort;
-		} else if (conf->mirrors[conf->raid_disks + number].rdev) {
+			}
+		}
+		if (conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
 			 * doing this to avoid confusion.
@@ -1719,11 +1710,9 @@ static void end_sync_write(struct bio *bio)
 	struct r1bio *r1_bio = bio->bi_private;
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
-	int mirror=0;
 	sector_t first_bad;
 	int bad_sectors;
-
-	mirror = find_bio_disk(r1_bio, bio);
+	struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
 
 	if (!uptodate) {
 		sector_t sync_blocks = 0;
@@ -1736,16 +1725,12 @@ static void end_sync_write(struct bio *bio)
 			s += sync_blocks;
 			sectors_to_go -= sync_blocks;
 		} while (sectors_to_go > 0);
-		set_bit(WriteErrorSeen,
-			&conf->mirrors[mirror].rdev->flags);
-		if (!test_and_set_bit(WantReplacement,
-				      &conf->mirrors[mirror].rdev->flags))
+		set_bit(WriteErrorSeen, &rdev->flags);
+		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
 				mddev->recovery);
 		set_bit(R1BIO_WriteError, &r1_bio->state);
-	} else if (is_badblock(conf->mirrors[mirror].rdev,
-			       r1_bio->sector,
-			       r1_bio->sectors,
+	} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
 			       &first_bad, &bad_sectors) &&
 		   !is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
 				r1_bio->sector,
@@ -2072,29 +2057,30 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			s = PAGE_SIZE >> 9;
 
 		do {
-			/* Note: no rcu protection needed here
-			 * as this is synchronous in the raid1d thread
-			 * which is the thread that might remove
-			 * a device.  If raid1d ever becomes multi-threaded....
-			 */
 			sector_t first_bad;
 			int bad_sectors;
 
-			rdev = conf->mirrors[d].rdev;
+			rcu_read_lock();
+			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
 			      rdev->recovery_offset >= sect + s)) &&
 			    is_badblock(rdev, sect, s,
-					&first_bad, &bad_sectors) == 0 &&
-			    sync_page_io(rdev, sect, s<<9,
+					&first_bad, &bad_sectors) == 0) {
+				atomic_inc(&rdev->nr_pending);
+				rcu_read_unlock();
+				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, 0, false))
 					success = 1;
-			else {
+				rdev_dec_pending(rdev, mddev);
+				if (success)
+					break;
+			} else
+				rcu_read_unlock();
 			d++;
 			if (d == conf->raid_disks * 2)
 				d = 0;
-			}
 		} while (!success && d != read_disk);
 
 		if (!success) {
@@ -2110,11 +2096,17 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			if (d==0)
 				d = conf->raid_disks * 2;
 			d--;
-			rdev = conf->mirrors[d].rdev;
+			rcu_read_lock();
+			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
-			    !test_bit(Faulty, &rdev->flags))
+			    !test_bit(Faulty, &rdev->flags)) {
+				atomic_inc(&rdev->nr_pending);
+				rcu_read_unlock();
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
+				rdev_dec_pending(rdev, mddev);
+			} else
+				rcu_read_unlock();
 		}
 		d = start;
 		while (d != read_disk) {
@@ -2122,9 +2114,12 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			if (d==0)
 				d = conf->raid_disks * 2;
 			d--;
-			rdev = conf->mirrors[d].rdev;
+			rcu_read_lock();
+			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
 			    !test_bit(Faulty, &rdev->flags)) {
+				atomic_inc(&rdev->nr_pending);
+				rcu_read_unlock();
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
@@ -2136,7 +2131,9 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 								    rdev->data_offset),
 					       bdevname(rdev->bdev, b));
 				}
-			}
+				rdev_dec_pending(rdev, mddev);
+			} else
+				rcu_read_unlock();
 		}
 		sectors -= s;
 		sect += s;
@@ -2534,6 +2531,13 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		return sync_blocks;
 	}
 
+	/*
+	 * If there is non-resync activity waiting for a turn, then let it
+	 * though before starting on this new sync request.
+	 */
+	if (conf->nr_waiting)
+		schedule_timeout_uninterruptible(1);
+
 	/* we are incrementing sector_nr below. To be safe, we check against
 	 * sector_nr + two times RESYNC_SECTORS
 	 */

drivers/md/raid10.c

@@ -707,7 +707,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 
 	raid10_find_phys(conf, r10_bio);
 	rcu_read_lock();
-retry:
 	sectors = r10_bio->sectors;
 	best_slot = -1;
 	best_rdev = NULL;
@@ -804,13 +803,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 
 	if (slot >= 0) {
 		atomic_inc(&rdev->nr_pending);
-		if (test_bit(Faulty, &rdev->flags)) {
-			/* Cannot risk returning a device that failed
-			 * before we inc'ed nr_pending
-			 */
-			rdev_dec_pending(rdev, conf->mddev);
-			goto retry;
-		}
 		r10_bio->read_slot = slot;
 	} else
 		rdev = NULL;
@@ -913,7 +905,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 
 	/* Now wait for all pending IO to complete */
 	wait_event_lock_irq(conf->wait_barrier,
-			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
+			    !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH,
 			    conf->resync_lock);
 
 	spin_unlock_irq(&conf->resync_lock);
@@ -944,22 +936,22 @@ static void wait_barrier(struct r10conf *conf)
 		 */
 		wait_event_lock_irq(conf->wait_barrier,
 				    !conf->barrier ||
-				    (conf->nr_pending &&
+				    (atomic_read(&conf->nr_pending) &&
 				     current->bio_list &&
 				     !bio_list_empty(current->bio_list)),
 				    conf->resync_lock);
 		conf->nr_waiting--;
+		if (!conf->nr_waiting)
+			wake_up(&conf->wait_barrier);
 	}
-	conf->nr_pending++;
+	atomic_inc(&conf->nr_pending);
 	spin_unlock_irq(&conf->resync_lock);
 }
 
 static void allow_barrier(struct r10conf *conf)
 {
-	unsigned long flags;
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	conf->nr_pending--;
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	if ((atomic_dec_and_test(&conf->nr_pending)) ||
+			(conf->array_freeze_pending))
 		wake_up(&conf->wait_barrier);
 }
 
@@ -978,13 +970,15 @@ static void freeze_array(struct r10conf *conf, int extra)
 	 * we continue.
 	 */
 	spin_lock_irq(&conf->resync_lock);
+	conf->array_freeze_pending++;
 	conf->barrier++;
 	conf->nr_waiting++;
 	wait_event_lock_irq_cmd(conf->wait_barrier,
-				conf->nr_pending == conf->nr_queued+extra,
+				atomic_read(&conf->nr_pending) == conf->nr_queued+extra,
 				conf->resync_lock,
 				flush_pending_writes(conf));
 
+	conf->array_freeze_pending--;
 	spin_unlock_irq(&conf->resync_lock);
 }
 
@@ -1499,10 +1493,12 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev)
 	}
 	seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
 					conf->geo.raid_disks - mddev->degraded);
-	for (i = 0; i < conf->geo.raid_disks; i++)
-		seq_printf(seq, "%s",
-			      conf->mirrors[i].rdev &&
-			      test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
+	rcu_read_lock();
+	for (i = 0; i < conf->geo.raid_disks; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+	}
+	rcu_read_unlock();
 	seq_printf(seq, "]");
 }
 
@@ -1600,7 +1596,7 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 static void print_conf(struct r10conf *conf)
 {
 	int i;
-	struct raid10_info *tmp;
+	struct md_rdev *rdev;
 
 	printk(KERN_DEBUG "RAID10 conf printout:\n");
 	if (!conf) {
@@ -1610,14 +1606,16 @@ static void print_conf(struct r10conf *conf)
 	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded,
 		conf->geo.raid_disks);
 
+	/* This is only called with ->reconfix_mutex held, so
+	 * rcu protection of rdev is not needed */
 	for (i = 0; i < conf->geo.raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
-		tmp = conf->mirrors + i;
-		if (tmp->rdev)
+		rdev = conf->mirrors[i].rdev;
+		if (rdev)
 			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
-				i, !test_bit(In_sync, &tmp->rdev->flags),
-			        !test_bit(Faulty, &tmp->rdev->flags),
-				bdevname(tmp->rdev->bdev,b));
+				i, !test_bit(In_sync, &rdev->flags),
+			        !test_bit(Faulty, &rdev->flags),
+				bdevname(rdev->bdev,b));
 	}
 }
 
@@ -1766,7 +1764,7 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		err = -EBUSY;
 		goto abort;
 	}
-	/* Only remove faulty devices if recovery
+	/* Only remove non-faulty devices if recovery
 	 * is not possible.
 	 */
 	if (!test_bit(Faulty, &rdev->flags) &&
@@ -1778,13 +1776,16 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		goto abort;
 	}
 	*rdevp = NULL;
+	if (!test_bit(RemoveSynchronized, &rdev->flags)) {
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
 			/* lost the race, try later */
 			err = -EBUSY;
 			*rdevp = rdev;
 			goto abort;
-	} else if (p->replacement) {
+		}
+	}
+	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
 		p->rdev = p->replacement;
 		clear_bit(Replacement, &p->replacement->flags);
@@ -2171,21 +2172,20 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
  */
 static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 {
-	struct timespec cur_time_mon;
+	long cur_time_mon;
 	unsigned long hours_since_last;
 	unsigned int read_errors = atomic_read(&rdev->read_errors);
 
-	ktime_get_ts(&cur_time_mon);
+	cur_time_mon = ktime_get_seconds();
 
-	if (rdev->last_read_error.tv_sec == 0 &&
-	    rdev->last_read_error.tv_nsec == 0) {
+	if (rdev->last_read_error == 0) {
 		/* first time we've seen a read error */
 		rdev->last_read_error = cur_time_mon;
 		return;
 	}
 
-	hours_since_last = (cur_time_mon.tv_sec -
-			    rdev->last_read_error.tv_sec) / 3600;
+	hours_since_last = (long)(cur_time_mon -
+			    rdev->last_read_error) / 3600;
 
 	rdev->last_read_error = cur_time_mon;
 
@@ -2264,7 +2264,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		printk(KERN_NOTICE
 		       "md/raid10:%s: %s: Failing raid device\n",
 		       mdname(mddev), b);
-		md_error(mddev, conf->mirrors[d].rdev);
+		md_error(mddev, rdev);
 		r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED;
 		return;
 	}
@@ -2287,6 +2287,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
 				atomic_inc(&rdev->nr_pending);
@@ -2340,6 +2341,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
+			    test_bit(Faulty, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -2379,6 +2381,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
+			    test_bit(Faulty, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -2876,11 +2879,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* Completed a full sync so the replacements
 				 * are now fully recovered.
 				 */
-				for (i = 0; i < conf->geo.raid_disks; i++)
-					if (conf->mirrors[i].replacement)
-						conf->mirrors[i].replacement
-							->recovery_offset
-							= MaxSector;
+				rcu_read_lock();
+				for (i = 0; i < conf->geo.raid_disks; i++) {
+					struct md_rdev *rdev =
+						rcu_dereference(conf->mirrors[i].replacement);
+					if (rdev)
+						rdev->recovery_offset = MaxSector;
+				}
+				rcu_read_unlock();
 			}
 			conf->fullsync = 0;
 		}
@@ -2911,6 +2917,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 	    max_sector > (sector_nr | chunk_mask))
 		max_sector = (sector_nr | chunk_mask) + 1;
 
+	/*
+	 * If there is non-resync activity waiting for a turn, then let it
+	 * though before starting on this new sync request.
+	 */
+	if (conf->nr_waiting)
+		schedule_timeout_uninterruptible(1);
+
 	/* Again, very different code for resync and recovery.
 	 * Both must result in an r10bio with a list of bios that
 	 * have bi_end_io, bi_sector, bi_bdev set,
@@ -2939,14 +2952,20 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			int must_sync;
 			int any_working;
 			struct raid10_info *mirror = &conf->mirrors[i];
+			struct md_rdev *mrdev, *mreplace;
 
-			if ((mirror->rdev == NULL ||
-			     test_bit(In_sync, &mirror->rdev->flags))
-			    &&
-			    (mirror->replacement == NULL ||
-			     test_bit(Faulty,
-				      &mirror->replacement->flags)))
+			rcu_read_lock();
+			mrdev = rcu_dereference(mirror->rdev);
+			mreplace = rcu_dereference(mirror->replacement);
+
+			if ((mrdev == NULL ||
+			     test_bit(Faulty, &mrdev->flags) ||
+			     test_bit(In_sync, &mrdev->flags)) &&
+			    (mreplace == NULL ||
+			     test_bit(Faulty, &mreplace->flags))) {
+				rcu_read_unlock();
 				continue;
+			}
 
 			still_degraded = 0;
 			/* want to reconstruct this device */
@@ -2956,8 +2975,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* last stripe is not complete - don't
 				 * try to recover this sector.
 				 */
+				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
@@ -2967,14 +2989,19 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (sync_blocks < max_sync)
 				max_sync = sync_blocks;
 			if (!must_sync &&
-			    mirror->replacement == NULL &&
+			    mreplace == NULL &&
 			    !conf->fullsync) {
 				/* yep, skip the sync_blocks here, but don't assume
 				 * that there will never be anything to do here
 				 */
 				chunks_skipped = -1;
+				rcu_read_unlock();
 				continue;
 			}
+			atomic_inc(&mrdev->nr_pending);
+			if (mreplace)
+				atomic_inc(&mreplace->nr_pending);
+			rcu_read_unlock();
 
 			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
 			r10_bio->state = 0;
@@ -2993,12 +3020,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			/* Need to check if the array will still be
 			 * degraded
 			 */
-			for (j = 0; j < conf->geo.raid_disks; j++)
-				if (conf->mirrors[j].rdev == NULL ||
-				    test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
+			rcu_read_lock();
+			for (j = 0; j < conf->geo.raid_disks; j++) {
+				struct md_rdev *rdev = rcu_dereference(
+					conf->mirrors[j].rdev);
+				if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
 					still_degraded = 1;
 					break;
 				}
+			}
 
 			must_sync = bitmap_start_sync(mddev->bitmap, sect,
 						      &sync_blocks, still_degraded);
@@ -3008,15 +3038,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				int k;
 				int d = r10_bio->devs[j].devnum;
 				sector_t from_addr, to_addr;
-				struct md_rdev *rdev;
+				struct md_rdev *rdev =
+					rcu_dereference(conf->mirrors[d].rdev);
 				sector_t sector, first_bad;
 				int bad_sectors;
-				if (!conf->mirrors[d].rdev ||
-				    !test_bit(In_sync, &conf->mirrors[d].rdev->flags))
+				if (!rdev ||
+				    !test_bit(In_sync, &rdev->flags))
 					continue;
 				/* This is where we read from */
 				any_working = 1;
-				rdev = conf->mirrors[d].rdev;
 				sector = r10_bio->devs[j].addr;
 
 				if (is_badblock(rdev, sector, max_sync,
@@ -3055,8 +3085,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				r10_bio->devs[1].devnum = i;
 				r10_bio->devs[1].addr = to_addr;
 
-				rdev = mirror->rdev;
-				if (!test_bit(In_sync, &rdev->flags)) {
+				if (!test_bit(In_sync, &mrdev->flags)) {
 					bio = r10_bio->devs[1].bio;
 					bio_reset(bio);
 					bio->bi_next = biolist;
@@ -3065,8 +3094,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					bio->bi_end_io = end_sync_write;
 					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 					bio->bi_iter.bi_sector = to_addr
-						+ rdev->data_offset;
-					bio->bi_bdev = rdev->bdev;
+						+ mrdev->data_offset;
+					bio->bi_bdev = mrdev->bdev;
 					atomic_inc(&r10_bio->remaining);
 				} else
 					r10_bio->devs[1].bio->bi_end_io = NULL;
@@ -3075,8 +3104,7 @@ 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;
-				rdev = mirror->replacement;
-				/* Note: if rdev != NULL, then bio
+				/* Note: if mreplace != NULL, then bio
 				 * cannot be NULL as r10buf_pool_alloc will
 				 * have allocated it.
 				 * So the second test here is pointless.
@@ -3084,8 +3112,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				 * this comment keeps human reviewers
 				 * happy.
 				 */
-				if (rdev == NULL || bio == NULL ||
-				    test_bit(Faulty, &rdev->flags))
+				if (mreplace == NULL || bio == NULL ||
+				    test_bit(Faulty, &mreplace->flags))
 					break;
 				bio_reset(bio);
 				bio->bi_next = biolist;
@@ -3094,11 +3122,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				bio->bi_end_io = end_sync_write;
 				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 				bio->bi_iter.bi_sector = to_addr +
-					rdev->data_offset;
-				bio->bi_bdev = rdev->bdev;
+					mreplace->data_offset;
+				bio->bi_bdev = mreplace->bdev;
 				atomic_inc(&r10_bio->remaining);
 				break;
 			}
+			rcu_read_unlock();
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
@@ -3111,15 +3140,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 						if (r10_bio->devs[k].devnum == i)
 							break;
 					if (!test_bit(In_sync,
-						      &mirror->rdev->flags)
+						      &mrdev->flags)
 					    && !rdev_set_badblocks(
-						    mirror->rdev,
+						    mrdev,
 						    r10_bio->devs[k].addr,
 						    max_sync, 0))
 						any_working = 0;
-					if (mirror->replacement &&
+					if (mreplace &&
 					    !rdev_set_badblocks(
-						    mirror->replacement,
+						    mreplace,
 						    r10_bio->devs[k].addr,
 						    max_sync, 0))
 						any_working = 0;
@@ -3137,8 +3166,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				if (rb2)
 					atomic_dec(&rb2->remaining);
 				r10_bio = rb2;
+				rdev_dec_pending(mrdev, mddev);
+				if (mreplace)
+					rdev_dec_pending(mreplace, mddev);
 				break;
 			}
+			rdev_dec_pending(mrdev, mddev);
+			if (mreplace)
+				rdev_dec_pending(mreplace, mddev);
 		}
 		if (biolist == NULL) {
 			while (r10_bio) {
@@ -3183,6 +3218,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			int d = r10_bio->devs[i].devnum;
 			sector_t first_bad, sector;
 			int bad_sectors;
+			struct md_rdev *rdev;
 
 			if (r10_bio->devs[i].repl_bio)
 				r10_bio->devs[i].repl_bio->bi_end_io = NULL;
@@ -3190,12 +3226,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio = r10_bio->devs[i].bio;
 			bio_reset(bio);
 			bio->bi_error = -EIO;
-			if (conf->mirrors[d].rdev == NULL ||
-			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
+			rcu_read_lock();
+			rdev = rcu_dereference(conf->mirrors[d].rdev);
+			if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
+				rcu_read_unlock();
 				continue;
+			}
 			sector = r10_bio->devs[i].addr;
-			if (is_badblock(conf->mirrors[d].rdev,
-					sector, max_sync,
+			if (is_badblock(rdev, sector, max_sync,
 					&first_bad, &bad_sectors)) {
 				if (first_bad > sector)
 					max_sync = first_bad - sector;
@@ -3203,25 +3241,28 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					bad_sectors -= (sector - first_bad);
 					if (max_sync > bad_sectors)
 						max_sync = bad_sectors;
+					rcu_read_unlock();
 					continue;
 				}
 			}
-			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
+			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&r10_bio->remaining);
 			bio->bi_next = biolist;
 			biolist = bio;
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_read;
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
-			bio->bi_iter.bi_sector = sector +
-				conf->mirrors[d].rdev->data_offset;
-			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
+			bio->bi_iter.bi_sector = sector + rdev->data_offset;
+			bio->bi_bdev = rdev->bdev;
 			count++;
 
-			if (conf->mirrors[d].replacement == NULL ||
-			    test_bit(Faulty,
-				     &conf->mirrors[d].replacement->flags))
+			rdev = rcu_dereference(conf->mirrors[d].replacement);
+			if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
+				rcu_read_unlock();
 				continue;
+			}
+			atomic_inc(&rdev->nr_pending);
+			rcu_read_unlock();
 
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
@@ -3229,15 +3270,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
-			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 			bio->bi_next = biolist;
 			biolist = bio;
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_write;
 			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-			bio->bi_iter.bi_sector = sector +
-				conf->mirrors[d].replacement->data_offset;
-			bio->bi_bdev = conf->mirrors[d].replacement->bdev;
+			bio->bi_iter.bi_sector = sector + rdev->data_offset;
+			bio->bi_bdev = rdev->bdev;
 			count++;
 		}
 
@@ -3504,6 +3543,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 
 	spin_lock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
+	atomic_set(&conf->nr_pending, 0);
 
 	conf->thread = md_register_thread(raid10d, mddev, "raid10");
 	if (!conf->thread)
@@ -4333,15 +4373,16 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 	blist = read_bio;
 	read_bio->bi_next = NULL;
 
+	rcu_read_lock();
 	for (s = 0; s < conf->copies*2; s++) {
 		struct bio *b;
 		int d = r10_bio->devs[s/2].devnum;
 		struct md_rdev *rdev2;
 		if (s&1) {
-			rdev2 = conf->mirrors[d].replacement;
+			rdev2 = rcu_dereference(conf->mirrors[d].replacement);
 			b = r10_bio->devs[s/2].repl_bio;
 		} else {
-			rdev2 = conf->mirrors[d].rdev;
+			rdev2 = rcu_dereference(conf->mirrors[d].rdev);
 			b = r10_bio->devs[s/2].bio;
 		}
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
@@ -4386,6 +4427,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		nr_sectors += len >> 9;
 	}
 bio_full:
+	rcu_read_unlock();
 	r10_bio->sectors = nr_sectors;
 
 	/* Now submit the read */
@@ -4437,16 +4479,20 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		struct bio *b;
 		int d = r10_bio->devs[s/2].devnum;
 		struct md_rdev *rdev;
+		rcu_read_lock();
 		if (s&1) {
-			rdev = conf->mirrors[d].replacement;
+			rdev = rcu_dereference(conf->mirrors[d].replacement);
 			b = r10_bio->devs[s/2].repl_bio;
 		} else {
-			rdev = conf->mirrors[d].rdev;
+			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			b = r10_bio->devs[s/2].bio;
 		}
-		if (!rdev || test_bit(Faulty, &rdev->flags))
+		if (!rdev || test_bit(Faulty, &rdev->flags)) {
+			rcu_read_unlock();
 			continue;
+		}
 		atomic_inc(&rdev->nr_pending);
+		rcu_read_unlock();
 		md_sync_acct(b->bi_bdev, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
@@ -4507,9 +4553,10 @@ static int handle_reshape_read_error(struct mddev *mddev,
 		if (s > (PAGE_SIZE >> 9))
 			s = PAGE_SIZE >> 9;
 
+		rcu_read_lock();
 		while (!success) {
 			int d = r10b->devs[slot].devnum;
-			struct md_rdev *rdev = conf->mirrors[d].rdev;
+			struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
 			sector_t addr;
 			if (rdev == NULL ||
 			    test_bit(Faulty, &rdev->flags) ||
@@ -4517,11 +4564,15 @@ static int handle_reshape_read_error(struct mddev *mddev,
 				goto failed;
 
 			addr = r10b->devs[slot].addr + idx * PAGE_SIZE;
+			atomic_inc(&rdev->nr_pending);
+			rcu_read_unlock();
 			success = sync_page_io(rdev,
 					       addr,
 					       s << 9,
 					       bvec[idx].bv_page,
 					       REQ_OP_READ, 0, false);
+			rdev_dec_pending(rdev, mddev);
+			rcu_read_lock();
 			if (success)
 				break;
 		failed:
@@ -4531,6 +4582,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
 			if (slot == first_slot)
 				break;
 		}
+		rcu_read_unlock();
 		if (!success) {
 			/* couldn't read this block, must give up */
 			set_bit(MD_RECOVERY_INTR,
@@ -4600,16 +4652,18 @@ static void raid10_finish_reshape(struct mddev *mddev)
 		}
 	} else {
 		int d;
+		rcu_read_lock();
 		for (d = conf->geo.raid_disks ;
 		     d < conf->geo.raid_disks - mddev->delta_disks;
 		     d++) {
-			struct md_rdev *rdev = conf->mirrors[d].rdev;
+			struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev)
 				clear_bit(In_sync, &rdev->flags);
-			rdev = conf->mirrors[d].replacement;
+			rdev = rcu_dereference(conf->mirrors[d].replacement);
 			if (rdev)
 				clear_bit(In_sync, &rdev->flags);
 		}
+		rcu_read_unlock();
 	}
 	mddev->layout = mddev->new_layout;
 	mddev->chunk_sectors = 1 << conf->geo.chunk_shift;

drivers/md/raid10.h

@@ -64,10 +64,11 @@ struct r10conf {
 	int			pending_count;
 
 	spinlock_t		resync_lock;
-	int			nr_pending;
+	atomic_t		nr_pending;
 	int			nr_waiting;
 	int			nr_queued;
 	int			barrier;
+	int			array_freeze_pending;
 	sector_t		next_resync;
 	int			fullsync;  /* set to 1 if a full sync is needed,
 					    * (fresh device added).

drivers/md/raid5.c

@@ -3080,7 +3080,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct md_rdev *rdev;
 			rcu_read_lock();
 			rdev = rcu_dereference(conf->disks[i].rdev);
-			if (rdev && test_bit(In_sync, &rdev->flags))
+			if (rdev && test_bit(In_sync, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags))
 				atomic_inc(&rdev->nr_pending);
 			else
 				rdev = NULL;
@@ -3210,15 +3211,16 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 		/* During recovery devices cannot be removed, so
 		 * locking and refcounting of rdevs is not needed
 		 */
+		rcu_read_lock();
 		for (i = 0; i < conf->raid_disks; i++) {
-			struct md_rdev *rdev = conf->disks[i].rdev;
+			struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
 			    && !rdev_set_badblocks(rdev, sh->sector,
 						   STRIPE_SECTORS, 0))
 				abort = 1;
-			rdev = conf->disks[i].replacement;
+			rdev = rcu_dereference(conf->disks[i].replacement);
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
@@ -3226,6 +3228,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 						   STRIPE_SECTORS, 0))
 				abort = 1;
 		}
+		rcu_read_unlock();
 		if (abort)
 			conf->recovery_disabled =
 				conf->mddev->recovery_disabled;
@@ -3237,15 +3240,16 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
 {
 	struct md_rdev *rdev;
 	int rv = 0;
-	/* Doing recovery so rcu locking not required */
-	rdev = sh->raid_conf->disks[disk_idx].replacement;
+
+	rcu_read_lock();
+	rdev = rcu_dereference(sh->raid_conf->disks[disk_idx].replacement);
 	if (rdev
 	    && !test_bit(Faulty, &rdev->flags)
 	    && !test_bit(In_sync, &rdev->flags)
 	    && (rdev->recovery_offset <= sh->sector
 		|| rdev->mddev->recovery_cp <= sh->sector))
 		rv = 1;
-
+	rcu_read_unlock();
 	return rv;
 }
 
@@ -3600,7 +3604,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 	pr_debug("for sector %llu, rmw=%d rcw=%d\n",
 		(unsigned long long)sh->sector, rmw, rcw);
 	set_bit(STRIPE_HANDLE, &sh->state);
-	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) {
+	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
 		if (conf->mddev->queue)
 			blk_add_trace_msg(conf->mddev->queue,
@@ -3627,7 +3631,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			}
 		}
 	}
-	if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) {
+	if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_PREFER_RMW)) && rcw > 0) {
 		/* want reconstruct write, but need to get some data */
 		int qread =0;
 		rcw = 0;
@@ -7066,10 +7070,12 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
 		conf->chunk_sectors / 2, mddev->layout);
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
-	for (i = 0; i < conf->raid_disks; i++)
-		seq_printf (seq, "%s",
-			       conf->disks[i].rdev &&
-			       test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
+	rcu_read_lock();
+	for (i = 0; i < conf->raid_disks; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+	}
+	rcu_read_unlock();
 	seq_printf (seq, "]");
 }
 
@@ -7191,12 +7197,15 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		goto abort;
 	}
 	*rdevp = NULL;
+	if (!test_bit(RemoveSynchronized, &rdev->flags)) {
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
 			/* lost the race, try later */
 			err = -EBUSY;
 			*rdevp = rdev;
-	} else if (p->replacement) {
+		}
+	}
+	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
 		p->rdev = p->replacement;
 		clear_bit(Replacement, &p->replacement->flags);