Merge branch 'md-next' of...

Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.19/drivers

Pull MD updates from Song:

"1. Improve annotation in raid5 code, by Logan Gunthorpe.
 2. Support MD_BROKEN flag in raid-1/5/10, by Mariusz Tkaczyk.
 3. Other small fixes/cleanups."

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: Replace role magic numbers with defined constants
  md/raid0: Ignore RAID0 layout if the second zone has only one device
  md/raid5: Annotate functions that hold device_lock with __must_hold
  md/raid5-ppl: Annotate with rcu_dereference_protected()
  md/raid5: Annotate rdev/replacement access when mddev_lock is held
  md/raid5: Annotate rdev/replacement accesses when nr_pending is elevated
  md/raid5: Add __rcu annotation to struct disk_info
  md/raid5: Un-nest struct raid5_percpu definition
  md/raid5: Cleanup setup_conf() error returns
  md: replace deprecated strlcpy & remove duplicated line
  md/bitmap: don't set sb values if can't pass sanity check
  md: fix an incorrect NULL check in md_reload_sb
  md: fix an incorrect NULL check in does_sb_need_changing
  raid5: introduce MD_BROKEN
  md: Set MD_BROKEN for RAID1 and RAID10

drivers/md/md-bitmap.c

@@ -639,14 +639,6 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	/* Setup nodes/clustername only if bitmap version is
-	 * cluster-compatible
-	 */
-	if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
-		nodes = le32_to_cpu(sb->nodes);
-		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
-				sb->cluster_name, 64);
-	}
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -668,6 +660,16 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 		goto out;
 	}
 
+	/*
+	 * Setup nodes/clustername only if bitmap version is
+	 * cluster-compatible
+	 */
+	if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
+		nodes = le32_to_cpu(sb->nodes);
+		strscpy(bitmap->mddev->bitmap_info.cluster_name,
+				sb->cluster_name, 64);
+	}
+
 	/* keep the array size field of the bitmap superblock up to date */
 	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
 
@@ -695,14 +697,13 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
 		set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
 	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
-	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
 	err = 0;
 
 out:
 	kunmap_atomic(sb);
-	/* Assigning chunksize is required for "re_read" */
-	bitmap->mddev->bitmap_info.chunksize = chunksize;
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
+		/* Assigning chunksize is required for "re_read" */
+		bitmap->mddev->bitmap_info.chunksize = chunksize;
 		err = md_setup_cluster(bitmap->mddev, nodes);
 		if (err) {
 			pr_warn("%s: Could not setup cluster service (%d)\n",
@@ -713,18 +714,18 @@ static int md_bitmap_read_sb(struct bitmap *bitmap)
 		goto re_read;
 	}
 
-
 out_no_sb:
-	if (test_bit(BITMAP_STALE, &bitmap->flags))
-		bitmap->events_cleared = bitmap->mddev->events;
-	bitmap->mddev->bitmap_info.chunksize = chunksize;
-	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
-	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
-	bitmap->mddev->bitmap_info.nodes = nodes;
-	if (bitmap->mddev->bitmap_info.space == 0 ||
-	    bitmap->mddev->bitmap_info.space > sectors_reserved)
-		bitmap->mddev->bitmap_info.space = sectors_reserved;
-	if (err) {
+	if (err == 0) {
+		if (test_bit(BITMAP_STALE, &bitmap->flags))
+			bitmap->events_cleared = bitmap->mddev->events;
+		bitmap->mddev->bitmap_info.chunksize = chunksize;
+		bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+		bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+		bitmap->mddev->bitmap_info.nodes = nodes;
+		if (bitmap->mddev->bitmap_info.space == 0 ||
+			bitmap->mddev->bitmap_info.space > sectors_reserved)
+			bitmap->mddev->bitmap_info.space = sectors_reserved;
+	} else {
 		md_bitmap_print_sb(bitmap);
 		if (bitmap->cluster_slot < 0)
 			md_cluster_stop(bitmap->mddev);

drivers/md/md-cluster.c

@@ -201,7 +201,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 		pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
 		goto out_err;
 	}
-	strlcpy(res->name, name, namelen + 1);
+	strscpy(res->name, name, namelen + 1);
 	if (with_lvb) {
 		res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
 		if (!res->lksb.sb_lvbptr) {

drivers/md/md.c

@@ -2627,14 +2627,16 @@ static void sync_sbs(struct mddev *mddev, int nospares)
 
 static bool does_sb_need_changing(struct mddev *mddev)
 {
-	struct md_rdev *rdev;
+	struct md_rdev *rdev = NULL, *iter;
 	struct mdp_superblock_1 *sb;
 	int role;
 
 	/* Find a good rdev */
-	rdev_for_each(rdev, mddev)
-		if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags))
+	rdev_for_each(iter, mddev)
+		if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) {
+			rdev = iter;
 			break;
+		}
 
 	/* No good device found. */
 	if (!rdev)
@@ -2645,11 +2647,11 @@ static bool does_sb_need_changing(struct mddev *mddev)
 	rdev_for_each(rdev, mddev) {
 		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
 		/* Device activated? */
-		if (role == 0xffff && rdev->raid_disk >=0 &&
+		if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags))
 			return true;
 		/* Device turned faulty? */
-		if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd))
+		if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX))
 			return true;
 	}
 
@@ -2984,10 +2986,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
 		md_error(rdev->mddev, rdev);
-		if (test_bit(Faulty, &rdev->flags))
-			err = 0;
-		else
+
+		if (test_bit(MD_BROKEN, &rdev->mddev->flags))
 			err = -EBUSY;
+		else
+			err = 0;
 	} else if (cmd_match(buf, "remove")) {
 		if (rdev->mddev->pers) {
 			clear_bit(Blocked, &rdev->flags);
@@ -4028,7 +4031,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	oldpriv = mddev->private;
 	mddev->pers = pers;
 	mddev->private = priv;
-	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 	mddev->level = mddev->new_level;
 	mddev->layout = mddev->new_layout;
 	mddev->chunk_sectors = mddev->new_chunk_sectors;
@@ -4353,10 +4356,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
  *     like active, but no writes have been seen for a while (100msec).
  *
  * broken
- *     RAID0/LINEAR-only: same as clean, but array is missing a member.
- *     It's useful because RAID0/LINEAR mounted-arrays aren't stopped
- *     when a member is gone, so this state will at least alert the
- *     user that something is wrong.
+*     Array is failed. It's useful because mounted-arrays aren't stopped
+*     when array is failed, so this state will at least alert the user that
+*     something is wrong.
  */
 enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
 		   write_pending, active_idle, broken, bad_word};
@@ -5763,7 +5765,7 @@ static int add_named_array(const char *val, const struct kernel_param *kp)
 		len--;
 	if (len >= DISK_NAME_LEN)
 		return -E2BIG;
-	strlcpy(buf, val, len+1);
+	strscpy(buf, val, len+1);
 	if (strncmp(buf, "md_", 3) == 0)
 		return md_alloc(0, buf);
 	if (strncmp(buf, "md", 2) == 0 &&
@@ -5896,7 +5898,7 @@ int md_run(struct mddev *mddev)
 		mddev->level = pers->level;
 		mddev->new_level = pers->level;
 	}
-	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 
 	if (mddev->reshape_position != MaxSector &&
 	    pers->start_reshape == NULL) {
@@ -7443,7 +7445,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev)
 		err =  -ENODEV;
 	else {
 		md_error(mddev, rdev);
-		if (!test_bit(Faulty, &rdev->flags))
+		if (test_bit(MD_BROKEN, &mddev->flags))
 			err = -EBUSY;
 	}
 	rcu_read_unlock();
@@ -7984,13 +7986,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (!mddev->pers || !mddev->pers->error_handler)
 		return;
-	mddev->pers->error_handler(mddev,rdev);
-	if (mddev->degraded)
+	mddev->pers->error_handler(mddev, rdev);
+
+	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
+	if (!test_bit(MD_BROKEN, &mddev->flags)) {
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
+	}
 	if (mddev->event_work.func)
 		queue_work(md_misc_wq, &mddev->event_work);
 	md_new_event();
@@ -9670,7 +9675,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 		role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);
 
 		if (test_bit(Candidate, &rdev2->flags)) {
-			if (role == 0xfffe) {
+			if (role == MD_DISK_ROLE_FAULTY) {
 				pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b));
 				md_kick_rdev_from_array(rdev2);
 				continue;
@@ -9683,7 +9688,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 			/*
 			 * got activated except reshape is happening.
 			 */
-			if (rdev2->raid_disk == -1 && role != 0xffff &&
+			if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE &&
 			    !(le32_to_cpu(sb->feature_map) &
 			      MD_FEATURE_RESHAPE_ACTIVE)) {
 				rdev2->saved_raid_disk = role;
@@ -9700,7 +9705,8 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 			 * as faulty. The recovery is performed by the
 			 * one who initiated the error.
 			 */
-			if ((role == 0xfffe) || (role == 0xfffd)) {
+			if (role == MD_DISK_ROLE_FAULTY ||
+			    role == MD_DISK_ROLE_JOURNAL) {
 				md_error(mddev, rdev2);
 				clear_bit(Blocked, &rdev2->flags);
 			}
@@ -9790,16 +9796,18 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
 
 void md_reload_sb(struct mddev *mddev, int nr)
 {
-	struct md_rdev *rdev;
+	struct md_rdev *rdev = NULL, *iter;
 	int err;
 
 	/* Find the rdev */
-	rdev_for_each_rcu(rdev, mddev) {
-		if (rdev->desc_nr == nr)
+	rdev_for_each_rcu(iter, mddev) {
+		if (iter->desc_nr == nr) {
+			rdev = iter;
 			break;
+		}
 	}
 
-	if (!rdev || rdev->desc_nr != nr) {
+	if (!rdev) {
 		pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr);
 		return;
 	}

drivers/md/md.h

@@ -234,34 +234,42 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				int is_new);
 struct md_cluster_info;
 
-/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
+/**
+ * enum mddev_flags - md device flags.
+ * @MD_ARRAY_FIRST_USE: First use of array, needs initialization.
+ * @MD_CLOSING: If set, we are closing the array, do not open it then.
+ * @MD_JOURNAL_CLEAN: A raid with journal is already clean.
+ * @MD_HAS_JOURNAL: The raid array has journal feature set.
+ * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took
+ *			       resync lock, need to release the lock.
+ * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as
+ *			    calls to md_error() will never cause the array to
+ *			    become failed.
+ * @MD_HAS_PPL:  The raid array has PPL feature set.
+ * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
+ * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
+ *			 without taking reconfig_mutex.
+ * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
+ *		     explicitly holding reconfig_mutex.
+ * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
+ *		   array is ready yet.
+ * @MD_BROKEN: This is used to stop writes and mark array as failed.
+ *
+ * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
+ */
 enum mddev_flags {
-	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */
-	MD_CLOSING,		/* If set, we are closing the array, do not open
-				 * it then */
-	MD_JOURNAL_CLEAN,	/* A raid with journal is already clean */
-	MD_HAS_JOURNAL,		/* The raid array has journal feature set */
-	MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node
-				   * already took resync lock, need to
-				   * release the lock */
-	MD_FAILFAST_SUPPORTED,	/* Using MD_FAILFAST on metadata writes is
-				 * supported as calls to md_error() will
-				 * never cause the array to become failed.
-				 */
-	MD_HAS_PPL,		/* The raid array has PPL feature set */
-	MD_HAS_MULTIPLE_PPLS,	/* The raid array has multiple PPLs feature set */
-	MD_ALLOW_SB_UPDATE,	/* md_check_recovery is allowed to update
-				 * the metadata without taking reconfig_mutex.
-				 */
-	MD_UPDATING_SB,		/* md_check_recovery is updating the metadata
-				 * without explicitly holding reconfig_mutex.
-				 */
-	MD_NOT_READY,		/* do_md_run() is active, so 'array_state'
-				 * must not report that array is ready yet
-				 */
-	MD_BROKEN,              /* This is used in RAID-0/LINEAR only, to stop
-				 * I/O in case an array member is gone/failed.
-				 */
+	MD_ARRAY_FIRST_USE,
+	MD_CLOSING,
+	MD_JOURNAL_CLEAN,
+	MD_HAS_JOURNAL,
+	MD_CLUSTER_RESYNC_LOCKED,
+	MD_FAILFAST_SUPPORTED,
+	MD_HAS_PPL,
+	MD_HAS_MULTIPLE_PPLS,
+	MD_ALLOW_SB_UPDATE,
+	MD_UPDATING_SB,
+	MD_NOT_READY,
+	MD_BROKEN,
 };
 
 enum mddev_sb_flags {

drivers/md/raid0.c

@@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
 
-	if (conf->nr_strip_zones == 1) {
-		conf->layout = RAID0_ORIG_LAYOUT;
-	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
-		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = mddev->layout;
-	} else if (default_layout == RAID0_ORIG_LAYOUT ||
-		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = default_layout;
-	} else {
-		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
-		       mdname(mddev));
-		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
-		err = -ENOTSUPP;
-		goto abort;
-	}
 	/*
 	 * now since we have the hard sector sizes, we can make sure
 	 * chunk size is a multiple of that sector size
@@ -273,6 +258,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			 (unsigned long long)smallest->sectors);
 	}
 
+	if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) {
+		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
+	} else if (default_layout == RAID0_ORIG_LAYOUT ||
+		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = default_layout;
+	} else {
+		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+		       mdname(mddev));
+		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
+		err = -EOPNOTSUPP;
+		goto abort;
+	}
+
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 

drivers/md/raid1.c

@@ -1641,30 +1641,39 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, "]");
 }
 
+/**
+ * raid1_error() - RAID1 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ *	- &MD_BROKEN flag is set in &mddev->flags.
+ *	- recovery is disabled.
+ * Otherwise, it must be degraded:
+ *	- recovery is interrupted.
+ *	- &mddev->degraded is bumped.
+ *
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
 static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
 	unsigned long flags;
 
-	/*
-	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks with "fail_last_dev == false",
-	 * ignore the error, let the next level up know.
-	 * else mark the drive as failed
-	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
-	    && (conf->raid_disks - mddev->degraded) == 1) {
-		/*
-		 * Don't fail the drive, act as though we were just a
-		 * normal single drive.
-		 * However don't try a recovery from this drive as
-		 * it is very likely to fail.
-		 */
-		conf->recovery_disabled = mddev->recovery_disabled;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+	if (test_bit(In_sync, &rdev->flags) &&
+	    (conf->raid_disks - mddev->degraded) == 1) {
+		set_bit(MD_BROKEN, &mddev->flags);
+
+		if (!mddev->fail_last_dev) {
+			conf->recovery_disabled = mddev->recovery_disabled;
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			return;
+		}
 	}
 	set_bit(Blocked, &rdev->flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags))

drivers/md/raid10.c

@@ -1970,32 +1970,40 @@ static int enough(struct r10conf *conf, int ignore)
 		_enough(conf, 1, ignore);
 }
 
+/**
+ * raid10_error() - RAID10 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ *	- &MD_BROKEN flag is set in &mddev->flags.
+ * Otherwise, it must be degraded:
+ *	- recovery is interrupted.
+ *	- &mddev->degraded is bumped.
+
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
 static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r10conf *conf = mddev->private;
 	unsigned long flags;
 
-	/*
-	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks with "fail_last_dev == false",
-	 * ignore the error, let the next level up know.
-	 * else mark the drive as failed
-	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
-	    && !enough(conf, rdev->raid_disk)) {
-		/*
-		 * Don't fail the drive, just return an IO error.
-		 */
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+	if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) {
+		set_bit(MD_BROKEN, &mddev->flags);
+
+		if (!mddev->fail_last_dev) {
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			return;
+		}
 	}
 	if (test_and_clear_bit(In_sync, &rdev->flags))
 		mddev->degraded++;
-	/*
-	 * If recovery is running, make sure it aborts.
-	 */
+
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);

drivers/md/raid5-ppl.c

@@ -883,7 +883,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 				 (unsigned long long)r_sector, dd_idx,
 				 (unsigned long long)sector);
 
-			rdev = conf->disks[dd_idx].rdev;
+			/* Array has not started so rcu dereference is safe */
+			rdev = rcu_dereference_protected(
+					conf->disks[dd_idx].rdev, 1);
 			if (!rdev || (!test_bit(In_sync, &rdev->flags) &&
 				      sector >= rdev->recovery_offset)) {
 				pr_debug("%s:%*s data member disk %d missing\n",
@@ -934,7 +936,10 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 		parity_sector = raid5_compute_sector(conf, r_sector_first + i,
 				0, &disk, &sh);
 		BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
-		parity_rdev = conf->disks[sh.pd_idx].rdev;
+
+		/* Array has not started so rcu dereference is safe */
+		parity_rdev = rcu_dereference_protected(
+					conf->disks[sh.pd_idx].rdev, 1);
 
 		BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
 		pr_debug("%s:%*s write parity at sector %llu, disk %s\n",
@@ -1404,7 +1409,9 @@ int ppl_init_log(struct r5conf *conf)
 
 	for (i = 0; i < ppl_conf->count; i++) {
 		struct ppl_log *log = &ppl_conf->child_logs[i];
-		struct md_rdev *rdev = conf->disks[i].rdev;
+		/* Array has not started so rcu dereference is safe */
+		struct md_rdev *rdev =
+			rcu_dereference_protected(conf->disks[i].rdev, 1);
 
 		mutex_init(&log->io_mutex);
 		spin_lock_init(&log->io_list_lock);

drivers/md/raid5.h

@@ -473,7 +473,8 @@ enum {
  */
 
 struct disk_info {
-	struct md_rdev	*rdev, *replacement;
+	struct md_rdev	__rcu *rdev;
+	struct md_rdev  __rcu *replacement;
 	struct page	*extra_page; /* extra page to use in prexor */
 };
 
@@ -560,6 +561,16 @@ struct r5pending_data {
 	struct bio_list bios;
 };
 
+struct raid5_percpu {
+	struct page	*spare_page; /* Used when checking P/Q in raid6 */
+	void		*scribble;  /* space for constructing buffer
+				     * lists and performing address
+				     * conversions
+				     */
+	int             scribble_obj_size;
+	local_lock_t    lock;
+};
+
 struct r5conf {
 	struct hlist_head	*stripe_hashtbl;
 	/* only protect corresponding hash list and inactive_list */
@@ -635,15 +646,7 @@ struct r5conf {
 					    */
 	int			recovery_disabled;
 	/* per cpu variables */
-	struct raid5_percpu {
-		struct page	*spare_page; /* Used when checking P/Q in raid6 */
-		void		*scribble;  /* space for constructing buffer
-					     * lists and performing address
-					     * conversions
-					     */
-		int             scribble_obj_size;
-		local_lock_t    lock;
-	} __percpu *percpu;
+	struct raid5_percpu __percpu *percpu;
 	int scribble_disks;
 	int scribble_sectors;
 	struct hlist_node node;