Merge tag 'md-3.4' of git://neil.brown.name/md

Pull md updates for 3.4 from Neil Brown:
 "Mostly tidying up code in preparation for some bigger changes next
  time.

  A few bug fixes tagged for -stable.

  Main functionality change is that some RAID10 arrays can now grow to
  use extra space that may have been made available on the individual
  devices."

Fixed up trivial conflicts with the k[un]map_atomic() cleanups in
drivers/md/bitmap.c.

* tag 'md-3.4' of git://neil.brown.name/md: (22 commits)
  md: Add judgement bb->unacked_exist in function md_ack_all_badblocks().
  md: fix clearing of the 'changed' flags for the bad blocks list.
  md/bitmap: discard CHUNK_BLOCK_SHIFT macro
  md/bitmap: remove unnecessary indirection when allocating.
  md/bitmap: remove some pointless locking.
  md/bitmap: change a 'goto' to a normal 'if' construct.
  md/bitmap: move printing of bitmap status to bitmap.c
  md/bitmap: remove some unused noise from bitmap.h
  md/raid10 - support resizing some RAID10 arrays.
  md/raid1: handle merge_bvec_fn in member devices.
  md/raid10: handle merge_bvec_fn in member devices.
  md: add proper merge_bvec handling to RAID0 and Linear.
  md: tidy up rdev_for_each usage.
  md/raid1,raid10: avoid deadlock during resync/recovery.
  md/bitmap: ensure to load bitmap when creating via sysfs.
  md: don't set md arrays to readonly on shutdown.
  md: allow re-add to failed arrays.
  md/raid5: use atomic_dec_return() instead of atomic_dec() and atomic_read().
  md: Use existed macros instead of numbers
  md/raid5: removed unused 'added_devices' variable.
  ...

1 files changed, 57 insertions, 83 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index ce88755baf4a..b572e1e386ce 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -439,7 +439,7 @@ static void submit_flushes(struct work_struct *ws)
 	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
 	atomic_set(&mddev->flush_pending, 1);
 	rcu_read_lock();
-	list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+	rdev_for_each_rcu(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
 			/* Take two references, one is dropped
@@ -749,7 +749,7 @@ static struct md_rdev * find_rdev_nr(struct mddev *mddev, int nr)
 {
 	struct md_rdev *rdev;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->desc_nr == nr)
 			return rdev;
 
@@ -760,7 +760,7 @@ static struct md_rdev * find_rdev(struct mddev * mddev, dev_t dev)
 {
 	struct md_rdev *rdev;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->bdev->bd_dev == dev)
 			return rdev;
 
@@ -1342,7 +1342,7 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 		sb->state |= (1<<MD_SB_BITMAP_PRESENT);
 
 	sb->disks[0].state = (1<<MD_DISK_REMOVED);
-	list_for_each_entry(rdev2, &mddev->disks, same_set) {
+	rdev_for_each(rdev2, mddev) {
 		mdp_disk_t *d;
 		int desc_nr;
 		int is_active = test_bit(In_sync, &rdev2->flags);
@@ -1805,18 +1805,18 @@ retry:
 						| BB_LEN(internal_bb));
 				*bbp++ = cpu_to_le64(store_bb);
 			}
+			bb->changed = 0;
 			if (read_seqretry(&bb->lock, seq))
 				goto retry;
 
 			bb->sector = (rdev->sb_start +
 				      (int)le32_to_cpu(sb->bblog_offset));
 			bb->size = le16_to_cpu(sb->bblog_size);
-			bb->changed = 0;
 		}
 	}
 
 	max_dev = 0;
-	list_for_each_entry(rdev2, &mddev->disks, same_set)
+	rdev_for_each(rdev2, mddev)
 		if (rdev2->desc_nr+1 > max_dev)
 			max_dev = rdev2->desc_nr+1;
 
@@ -1833,7 +1833,7 @@ retry:
 	for (i=0; i<max_dev;i++)
 		sb->dev_roles[i] = cpu_to_le16(0xfffe);
 	
-	list_for_each_entry(rdev2, &mddev->disks, same_set) {
+	rdev_for_each(rdev2, mddev) {
 		i = rdev2->desc_nr;
 		if (test_bit(Faulty, &rdev2->flags))
 			sb->dev_roles[i] = cpu_to_le16(0xfffe);
@@ -1948,7 +1948,7 @@ int md_integrity_register(struct mddev *mddev)
 		return 0; /* nothing to do */
 	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
@@ -2175,7 +2175,7 @@ static void export_array(struct mddev *mddev)
 {
 	struct md_rdev *rdev, *tmp;
 
-	rdev_for_each(rdev, tmp, mddev) {
+	rdev_for_each_safe(rdev, tmp, mddev) {
 		if (!rdev->mddev) {
 			MD_BUG();
 			continue;
@@ -2307,11 +2307,11 @@ static void md_print_devices(void)
 			bitmap_print_sb(mddev->bitmap);
 		else
 			printk("%s: ", mdname(mddev));
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			printk("<%s>", bdevname(rdev->bdev,b));
 		printk("\n");
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			print_rdev(rdev, mddev->major_version);
 	}
 	printk("md:	**********************************\n");
@@ -2328,7 +2328,7 @@ static void sync_sbs(struct mddev * mddev, int nospares)
 	 * with the rest of the array)
 	 */
 	struct md_rdev *rdev;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->sb_events == mddev->events ||
 		    (nospares &&
 		     rdev->raid_disk < 0 &&
@@ -2351,7 +2351,7 @@ static void md_update_sb(struct mddev * mddev, int force_change)
 
 repeat:
 	/* First make sure individual recovery_offsets are correct */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    mddev->delta_disks >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
@@ -2364,8 +2364,9 @@ repeat:
 		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
 		if (!mddev->external) {
 			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
-			list_for_each_entry(rdev, &mddev->disks, same_set) {
+			rdev_for_each(rdev, mddev) {
 				if (rdev->badblocks.changed) {
+					rdev->badblocks.changed = 0;
 					md_ack_all_badblocks(&rdev->badblocks);
 					md_error(mddev, rdev);
 				}
@@ -2430,7 +2431,7 @@ repeat:
 		mddev->events --;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->badblocks.changed)
 			any_badblocks_changed++;
 		if (test_bit(Faulty, &rdev->flags))
@@ -2444,7 +2445,7 @@ repeat:
 		 mdname(mddev), mddev->in_sync);
 
 	bitmap_update_sb(mddev->bitmap);
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		char b[BDEVNAME_SIZE];
 
 		if (rdev->sb_loaded != 1)
@@ -2493,7 +2494,7 @@ repeat:
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (test_and_clear_bit(FaultRecorded, &rdev->flags))
 			clear_bit(Blocked, &rdev->flags);
 
@@ -2896,7 +2897,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
 			struct md_rdev *rdev2;
 
 			mddev_lock(mddev);
-			list_for_each_entry(rdev2, &mddev->disks, same_set)
+			rdev_for_each(rdev2, mddev)
 				if (rdev->bdev == rdev2->bdev &&
 				    rdev != rdev2 &&
 				    overlaps(rdev->data_offset, rdev->sectors,
@@ -3193,7 +3194,7 @@ static void analyze_sbs(struct mddev * mddev)
 	char b[BDEVNAME_SIZE];
 
 	freshest = NULL;
-	rdev_for_each(rdev, tmp, mddev)
+	rdev_for_each_safe(rdev, tmp, mddev)
 		switch (super_types[mddev->major_version].
 			load_super(rdev, freshest, mddev->minor_version)) {
 		case 1:
@@ -3214,7 +3215,7 @@ static void analyze_sbs(struct mddev * mddev)
 		validate_super(mddev, freshest);
 
 	i = 0;
-	rdev_for_each(rdev, tmp, mddev) {
+	rdev_for_each_safe(rdev, tmp, mddev) {
 		if (mddev->max_disks &&
 		    (rdev->desc_nr >= mddev->max_disks ||
 		     i > mddev->max_disks)) {
@@ -3403,7 +3404,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		return -EINVAL;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		rdev->new_raid_disk = rdev->raid_disk;
 
 	/* ->takeover must set new_* and/or delta_disks
@@ -3456,7 +3457,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->safemode = 0;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
 		if (rdev->new_raid_disk >= mddev->raid_disks)
@@ -3465,7 +3466,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			continue;
 		sysfs_unlink_rdev(mddev, rdev);
 	}
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
 		if (rdev->new_raid_disk == rdev->raid_disk)
@@ -4796,7 +4797,7 @@ int md_run(struct mddev *mddev)
 	 * the only valid external interface is through the md
 	 * device.
 	 */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
 		sync_blockdev(rdev->bdev);
@@ -4867,8 +4868,8 @@ int md_run(struct mddev *mddev)
 		struct md_rdev *rdev2;
 		int warned = 0;
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
-			list_for_each_entry(rdev2, &mddev->disks, same_set) {
+		rdev_for_each(rdev, mddev)
+			rdev_for_each(rdev2, mddev) {
 				if (rdev < rdev2 &&
 				    rdev->bdev->bd_contains ==
 				    rdev2->bdev->bd_contains) {
@@ -4945,7 +4946,7 @@ int md_run(struct mddev *mddev)
 	mddev->in_sync = 1;
 	smp_wmb();
 	mddev->ready = 1;
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->raid_disk >= 0)
 			if (sysfs_link_rdev(mddev, rdev))
 				/* failure here is OK */;
@@ -5073,6 +5074,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->changed = 0;
 	mddev->degraded = 0;
 	mddev->safemode = 0;
+	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.chunksize = 0;
@@ -5175,7 +5177,7 @@ static int do_md_stop(struct mddev * mddev, int mode, int is_open)
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			if (rdev->raid_disk >= 0)
 				sysfs_unlink_rdev(mddev, rdev);
 
@@ -5226,7 +5228,7 @@ static void autorun_array(struct mddev *mddev)
 
 	printk(KERN_INFO "md: running: ");
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		char b[BDEVNAME_SIZE];
 		printk("<%s>", bdevname(rdev->bdev,b));
 	}
@@ -5356,7 +5358,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
 	struct md_rdev *rdev;
 
 	nr=working=insync=failed=spare=0;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		nr++;
 		if (test_bit(Faulty, &rdev->flags))
 			failed++;
@@ -5923,7 +5925,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 		 * grow, and re-add.
 		 */
 		return -EBUSY;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		sector_t avail = rdev->sectors;
 
 		if (fit && (num_sectors == 0 || num_sectors > avail))
@@ -6724,7 +6726,6 @@ static int md_seq_show(struct seq_file *seq, void *v)
 	struct mddev *mddev = v;
 	sector_t sectors;
 	struct md_rdev *rdev;
-	struct bitmap *bitmap;
 
 	if (v == (void*)1) {
 		struct md_personality *pers;
@@ -6758,7 +6759,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		}
 
 		sectors = 0;
-		list_for_each_entry(rdev, &mddev->disks, same_set) {
+		rdev_for_each(rdev, mddev) {
 			char b[BDEVNAME_SIZE];
 			seq_printf(seq, " %s[%d]",
 				bdevname(rdev->bdev,b), rdev->desc_nr);
@@ -6812,27 +6813,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		} else
 			seq_printf(seq, "\n       ");
 
-		if ((bitmap = mddev->bitmap)) {
-			unsigned long chunk_kb;
-			unsigned long flags;
-			spin_lock_irqsave(&bitmap->lock, flags);
-			chunk_kb = mddev->bitmap_info.chunksize >> 10;
-			seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
-				"%lu%s chunk",
-				bitmap->pages - bitmap->missing_pages,
-				bitmap->pages,
-				(bitmap->pages - bitmap->missing_pages)
-					<< (PAGE_SHIFT - 10),
-				chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize,
-				chunk_kb ? "KB" : "B");
-			if (bitmap->file) {
-				seq_printf(seq, ", file: ");
-				seq_path(seq, &bitmap->file->f_path, " \t\n");
-			}
-
-			seq_printf(seq, "\n");
-			spin_unlock_irqrestore(&bitmap->lock, flags);
-		}
+		bitmap_status(seq, mddev->bitmap);
 
 		seq_printf(seq, "\n");
 	}
@@ -7170,7 +7151,7 @@ void md_do_sync(struct mddev *mddev)
 		max_sectors = mddev->dev_sectors;
 		j = MaxSector;
 		rcu_read_lock();
-		list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+		rdev_for_each_rcu(rdev, mddev)
 			if (rdev->raid_disk >= 0 &&
 			    !test_bit(Faulty, &rdev->flags) &&
 			    !test_bit(In_sync, &rdev->flags) &&
@@ -7342,7 +7323,7 @@ void md_do_sync(struct mddev *mddev)
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 				mddev->curr_resync = MaxSector;
 			rcu_read_lock();
-			list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+			rdev_for_each_rcu(rdev, mddev)
 				if (rdev->raid_disk >= 0 &&
 				    mddev->delta_disks >= 0 &&
 				    !test_bit(Faulty, &rdev->flags) &&
@@ -7388,7 +7369,7 @@ static int remove_and_add_spares(struct mddev *mddev)
 
 	mddev->curr_resync_completed = 0;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
@@ -7406,7 +7387,7 @@ static int remove_and_add_spares(struct mddev *mddev)
 			     "degraded");
 
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
@@ -7451,7 +7432,7 @@ static void reap_sync_thread(struct mddev *mddev)
 	 * do the superblock for an incrementally recovered device
 	 * written out.
 	 */
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (!mddev->degraded ||
 		    test_bit(In_sync, &rdev->flags))
 			rdev->saved_raid_disk = -1;
@@ -7529,7 +7510,7 @@ void md_check_recovery(struct mddev *mddev)
 			 * failed devices.
 			 */
 			struct md_rdev *rdev;
-			list_for_each_entry(rdev, &mddev->disks, same_set)
+			rdev_for_each(rdev, mddev)
 				if (rdev->raid_disk >= 0 &&
 				    !test_bit(Blocked, &rdev->flags) &&
 				    test_bit(Faulty, &rdev->flags) &&
@@ -8040,7 +8021,7 @@ void md_ack_all_badblocks(struct badblocks *bb)
 		return;
 	write_seqlock_irq(&bb->lock);
 
-	if (bb->changed == 0) {
+	if (bb->changed == 0 && bb->unacked_exist) {
 		u64 *p = bb->page;
 		int i;
 		for (i = 0; i < bb->count ; i++) {
@@ -8157,30 +8138,23 @@ static int md_notify_reboot(struct notifier_block *this,
 	struct mddev *mddev;
 	int need_delay = 0;
 
-	if ((code == SYS_DOWN) || (code == SYS_HALT) || (code == SYS_POWER_OFF)) {
-
-		printk(KERN_INFO "md: stopping all md devices.\n");
-
-		for_each_mddev(mddev, tmp) {
-			if (mddev_trylock(mddev)) {
-				/* Force a switch to readonly even array
-				 * appears to still be in use.  Hence
-				 * the '100'.
-				 */
-				md_set_readonly(mddev, 100);
-				mddev_unlock(mddev);
-			}
-			need_delay = 1;
+	for_each_mddev(mddev, tmp) {
+		if (mddev_trylock(mddev)) {
+			__md_stop_writes(mddev);
+			mddev->safemode = 2;
+			mddev_unlock(mddev);
 		}
-		/*
-		 * certain more exotic SCSI devices are known to be
-		 * volatile wrt too early system reboots. While the
-		 * right place to handle this issue is the given
-		 * driver, we do want to have a safe RAID driver ...
-		 */
-		if (need_delay)
-			mdelay(1000*1);
+		need_delay = 1;
 	}
+	/*
+	 * certain more exotic SCSI devices are known to be
+	 * volatile wrt too early system reboots. While the
+	 * right place to handle this issue is the given
+	 * driver, we do want to have a safe RAID driver ...
+	 */
+	if (need_delay)
+		mdelay(1000*1);
+
 	return NOTIFY_DONE;
 }