btrfs: autodefrag: only scan one inode once

Although we have btrfs_requeue_inode_defrag(), for autodefrag we are
still just exhausting all inode_defrag items in the tree.

This means, it doesn't make much difference to requeue an inode_defrag,
other than scan the inode from the beginning till its end.

Change the behaviour to always scan from offset 0 of an inode, and till
the end.

By this we get the following benefit:

- Straight-forward code

- No more re-queue related check

- Fewer members in inode_defrag

We still keep the same btrfs_get_fs_root() and btrfs_iget() check for
each loop, and added extra should_auto_defrag() check per-loop.

Note: the patch needs to be backported and is intentionally written
to minimize the diff size, code will be cleaned up later.

CC: stable@vger.kernel.org # 5.16
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 11204db..36a8136 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -49,12 +49,6 @@ struct inode_defrag {
 
        /* root objectid */
        u64 root;
-
-       /* last offset we were able to defrag */
-       u64 last_offset;
-
-       /* if we've wrapped around back to zero once already */
-       int cycled;
 };
 
 static int __compare_inode_defrag(struct inode_defrag *defrag1,
@@ -107,8 +101,6 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
                         */
                        if (defrag->transid < entry->transid)
                                entry->transid = defrag->transid;
-                       if (defrag->last_offset > entry->last_offset)
-                               entry->last_offset = defrag->last_offset;
                        return -EEXIST;
                }
        }
@@ -179,34 +171,6 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 }
 
 /*
- * Requeue the defrag object. If there is a defrag object that points to
- * the same inode in the tree, we will merge them together (by
- * __btrfs_add_inode_defrag()) and free the one that we want to requeue.
- */
-static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
-                                      struct inode_defrag *defrag)
-{
-       struct btrfs_fs_info *fs_info = inode->root->fs_info;
-       int ret;
-
-       if (!__need_auto_defrag(fs_info))
-               goto out;
-
-       /*
-        * Here we don't check the IN_DEFRAG flag, because we need merge
-        * them together.
-        */
-       spin_lock(&fs_info->defrag_inodes_lock);
-       ret = __btrfs_add_inode_defrag(inode, defrag);
-       spin_unlock(&fs_info->defrag_inodes_lock);
-       if (ret)
-               goto out;
-       return;
-out:
-       kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-}
-
-/*
  * pick the defragable inode that we want, if it doesn't exist, we will get
  * the next one.
  */
@@ -278,8 +242,14 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
        struct btrfs_root *inode_root;
        struct inode *inode;
        struct btrfs_ioctl_defrag_range_args range;
-       int num_defrag;
-       int ret;
+       int ret = 0;
+       u64 cur = 0;
+
+again:
+       if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
+               goto cleanup;
+       if (!__need_auto_defrag(fs_info))
+               goto cleanup;
 
        /* get the inode */
        inode_root = btrfs_get_fs_root(fs_info, defrag->root, true);
@@ -295,39 +265,29 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
                goto cleanup;
        }
 
+       if (cur >= i_size_read(inode)) {
+               iput(inode);
+               goto cleanup;
+       }
+
        /* do a chunk of defrag */
        clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
        memset(&range, 0, sizeof(range));
        range.len = (u64)-1;
-       range.start = defrag->last_offset;
+       range.start = cur;
 
        sb_start_write(fs_info->sb);
-       num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
+       ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
                                       BTRFS_DEFRAG_BATCH);
        sb_end_write(fs_info->sb);
-       /*
-        * if we filled the whole defrag batch, there
-        * must be more work to do.  Queue this defrag
-        * again
-        */
-       if (num_defrag == BTRFS_DEFRAG_BATCH) {
-               defrag->last_offset = range.start;
-               btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
-       } else if (defrag->last_offset && !defrag->cycled) {
-               /*
-                * we didn't fill our defrag batch, but
-                * we didn't start at zero.  Make sure we loop
-                * around to the start of the file.
-                */
-               defrag->last_offset = 0;
-               defrag->cycled = 1;
-               btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
-       } else {
-               kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-       }
-
        iput(inode);
-       return 0;
+
+       if (ret < 0)
+               goto cleanup;
+
+       cur = max(cur + fs_info->sectorsize, range.start);
+       goto again;
+
 cleanup:
        kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
        return ret;