[7/8] btrfs: be more explicit about allowed flush states
diff mbox series

Message ID 20181203152459.21630-8-josef@toxicpanda.com
State New
Headers show
Series
  • Enospc cleanups and fixeS
Related show

Commit Message

Josef Bacik Dec. 3, 2018, 3:24 p.m. UTC
For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when
running delalloc because we may be holding a tree lock.  We can also
deadlock with delayed refs rsv's that are running via the committing
mechanism.  The only safe operations for FLUSH_LIMIT is to run the
delayed operations and to allocate chunks, everything else has the
potential to deadlock.  Future proof this by explicitly specifying the
states that FLUSH_LIMIT is allowed to use.  This will keep us from
introducing bugs later on when adding new flush states.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/extent-tree.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

Comments

David Sterba Dec. 11, 2018, 6:28 p.m. UTC | #1
On Mon, Dec 03, 2018 at 10:24:58AM -0500, Josef Bacik wrote:
> For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when
> running delalloc because we may be holding a tree lock.  We can also
> deadlock with delayed refs rsv's that are running via the committing
> mechanism.  The only safe operations for FLUSH_LIMIT is to run the
> delayed operations and to allocate chunks, everything else has the
> potential to deadlock.  Future proof this by explicitly specifying the
> states that FLUSH_LIMIT is allowed to use.  This will keep us from
> introducing bugs later on when adding new flush states.
> 
> Signed-off-by: Josef Bacik <josef@toxicpanda.com>

Reviewed-by: David Sterba <dsterba@suse.com>
Nikolay Borisov Dec. 12, 2018, 8:40 a.m. UTC | #2
On 3.12.18 г. 17:24 ч., Josef Bacik wrote:
> For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when
> running delalloc because we may be holding a tree lock.  We can also
> deadlock with delayed refs rsv's that are running via the committing
> mechanism.  The only safe operations for FLUSH_LIMIT is to run the
> delayed operations and to allocate chunks, everything else has the
> potential to deadlock.  Future proof this by explicitly specifying the
> states that FLUSH_LIMIT is allowed to use.  This will keep us from
> introducing bugs later on when adding new flush states.
> 
> Signed-off-by: Josef Bacik <josef@toxicpanda.com>

Reviewed-by: Nikolay Borisov <nborisov@suse.com>

> ---
>  fs/btrfs/extent-tree.c | 21 ++++++++++-----------
>  1 file changed, 10 insertions(+), 11 deletions(-)
> 
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 0e1a499035ac..ab9d915d9289 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -5123,12 +5123,18 @@ void btrfs_init_async_reclaim_work(struct work_struct *work)
>  	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
>  }
>  
> +static const enum btrfs_flush_state priority_flush_states[] = {
> +	FLUSH_DELAYED_ITEMS_NR,
> +	FLUSH_DELAYED_ITEMS,
> +	ALLOC_CHUNK,
> +};
> +
>  static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
>  					    struct btrfs_space_info *space_info,
>  					    struct reserve_ticket *ticket)
>  {
>  	u64 to_reclaim;
> -	int flush_state = FLUSH_DELAYED_ITEMS_NR;
> +	int flush_state = 0;
>  
>  	spin_lock(&space_info->lock);
>  	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
> @@ -5140,7 +5146,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
>  	spin_unlock(&space_info->lock);
>  
>  	do {
> -		flush_space(fs_info, space_info, to_reclaim, flush_state);
> +		flush_space(fs_info, space_info, to_reclaim,
> +			    priority_flush_states[flush_state]);
>  		flush_state++;
>  		spin_lock(&space_info->lock);
>  		if (ticket->bytes == 0) {
> @@ -5148,15 +5155,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
>  			return;
>  		}
>  		spin_unlock(&space_info->lock);
> -
> -		/*
> -		 * Priority flushers can't wait on delalloc without
> -		 * deadlocking.
> -		 */
> -		if (flush_state == FLUSH_DELALLOC ||
> -		    flush_state == FLUSH_DELALLOC_WAIT)
> -			flush_state = ALLOC_CHUNK;
> -	} while (flush_state < COMMIT_TRANS);
> +	} while (flush_state < ARRAY_SIZE(priority_flush_states));
>  }
>  
>  static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
>

Patch
diff mbox series

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0e1a499035ac..ab9d915d9289 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5123,12 +5123,18 @@  void btrfs_init_async_reclaim_work(struct work_struct *work)
 	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
 }
 
+static const enum btrfs_flush_state priority_flush_states[] = {
+	FLUSH_DELAYED_ITEMS_NR,
+	FLUSH_DELAYED_ITEMS,
+	ALLOC_CHUNK,
+};
+
 static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 					    struct btrfs_space_info *space_info,
 					    struct reserve_ticket *ticket)
 {
 	u64 to_reclaim;
-	int flush_state = FLUSH_DELAYED_ITEMS_NR;
+	int flush_state = 0;
 
 	spin_lock(&space_info->lock);
 	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
@@ -5140,7 +5146,8 @@  static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	spin_unlock(&space_info->lock);
 
 	do {
-		flush_space(fs_info, space_info, to_reclaim, flush_state);
+		flush_space(fs_info, space_info, to_reclaim,
+			    priority_flush_states[flush_state]);
 		flush_state++;
 		spin_lock(&space_info->lock);
 		if (ticket->bytes == 0) {
@@ -5148,15 +5155,7 @@  static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 			return;
 		}
 		spin_unlock(&space_info->lock);
-
-		/*
-		 * Priority flushers can't wait on delalloc without
-		 * deadlocking.
-		 */
-		if (flush_state == FLUSH_DELALLOC ||
-		    flush_state == FLUSH_DELALLOC_WAIT)
-			flush_state = ALLOC_CHUNK;
-	} while (flush_state < COMMIT_TRANS);
+	} while (flush_state < ARRAY_SIZE(priority_flush_states));
 }
 
 static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,