md: don't return -EAGAIN in md_allow_write for external metadata arrays

This essentially reverts commit b5470dc5fc18 ("md: resolve external
metadata handling deadlock in md_allow_write") with some adjustments.

Since commit 6791875e2e53 ("md: make reconfig_mutex optional for writes
to md sysfs files.") changing array_state to 'active' does not use
mddev_lock() and will not cause a deadlock with md_allow_write(). This
revert simplifies userspace tools that write to sysfs attributes like
"stripe_cache_size" or "consistency_policy" because it removes the need
for special handling for external metadata arrays, checking for EAGAIN
and retrying the write.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 82f798be964fc51d8c1d2d5b8cf5fc88392814ee..10367ffe92e3e37704f5e32793ea97175c8b15e6 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8022,18 +8022,15 @@ EXPORT_SYMBOL(md_write_end);
  * may proceed without blocking.  It is important to call this before
  * attempting a GFP_KERNEL allocation while holding the mddev lock.
  * Must be called with mddev_lock held.
- *
- * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock
- * is dropped, so return -EAGAIN after notifying userspace.
  */
-int md_allow_write(struct mddev *mddev)
+void md_allow_write(struct mddev *mddev)
 {
        if (!mddev->pers)
-               return 0;
+               return;
        if (mddev->ro)
-               return 0;
+               return;
        if (!mddev->pers->sync_request)
-               return 0;
+               return;
 
        spin_lock(&mddev->lock);
        if (mddev->in_sync) {
@@ -8046,13 +8043,12 @@ int md_allow_write(struct mddev *mddev)
                spin_unlock(&mddev->lock);
                md_update_sb(mddev, 0);
                sysfs_notify_dirent_safe(mddev->sysfs_state);
+               /* wait for the dirty state to be recorded in the metadata */
+               wait_event(mddev->sb_wait,
+                          !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
+                          !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
        } else
                spin_unlock(&mddev->lock);
-
-       if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-               return -EAGAIN;
-       else
-               return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 4e75d121bfcc5671640421769476c85d2843e7c9..11f15146ce5177de0468c706a5f82a037b42c132 100644 (file)
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -665,7 +665,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
                        bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
-extern int md_allow_write(struct mddev *mddev);
+extern void md_allow_write(struct mddev *mddev);
 extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7ed59351fe972d60a8bf2bb22d20f4abaa718710..7c1f733988001c3dee5504846099c4da9cc37382 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3197,7 +3197,7 @@ static int raid1_reshape(struct mddev *mddev)
        struct r1conf *conf = mddev->private;
        int cnt, raid_disks;
        unsigned long flags;
-       int d, d2, err;
+       int d, d2;
 
        /* Cannot change chunk_size, layout, or level */
        if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3209,11 +3209,8 @@ static int raid1_reshape(struct mddev *mddev)
                return -EINVAL;
        }
 
-       if (!mddev_is_clustered(mddev)) {
-               err = md_allow_write(mddev);
-               if (err)
-                       return err;
-       }
+       if (!mddev_is_clustered(mddev))
+               md_allow_write(mddev);
 
        raid_disks = mddev->raid_disks + mddev->delta_disks;
 

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3809a2192132959f39e1b19c426f178f43543225..f8055a7abb4b053fd74f5502e648cecdf105349e 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2309,14 +2309,12 @@ static int resize_stripes(struct r5conf *conf, int newsize)
        struct stripe_head *osh, *nsh;
        LIST_HEAD(newstripes);
        struct disk_info *ndisks;
-       int err;
+       int err = 0;
        struct kmem_cache *sc;
        int i;
        int hash, cnt;
 
-       err = md_allow_write(conf->mddev);
-       if (err)
-               return err;
+       md_allow_write(conf->mddev);
 
        /* Step 1 */
        sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
@@ -6310,7 +6308,6 @@ int
 raid5_set_cache_size(struct mddev *mddev, int size)
 {
        struct r5conf *conf = mddev->private;
-       int err;
 
        if (size <= 16 || size > 32768)
                return -EINVAL;
@@ -6322,10 +6319,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
                ;
        mutex_unlock(&conf->cache_size_mutex);
 
-
-       err = md_allow_write(mddev);
-       if (err)
-               return err;
+       md_allow_write(mddev);
 
        mutex_lock(&conf->cache_size_mutex);
        while (size > conf->max_nr_stripes)