btrfs: refactor the zoned device handling in cow_file_range

Handling of the done_offset to cow_file_range is a bit confusing, as
it is not updated at all when the function succeeds, and the -EAGAIN
status is used bother for the case where we need to wait for a zone
finish and the one where the allocation was partially successful.

Change the calling convention so that done_offset is always updated,
and 0 is returned if some allocation was successful (partial allocation
can still only happen for zoned devices), and waiting for a zone
finish is done internally in cow_file_range instead of the caller.

Also write a comment explaining the logic.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7447f3b..0617e47 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1363,7 +1363,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
                         * compressed extent.
                         */
                        unlock_page(locked_page);
-                       return 1;
+                       ret = 1;
+                       goto done;
                } else if (ret < 0) {
                        goto out_unlock;
                }
@@ -1394,6 +1395,31 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
                ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
                                           min_alloc_size, 0, alloc_hint,
                                           &ins, 1, 1);
+               if (ret == -EAGAIN) {
+                       /*
+                        * btrfs_reserve_extent only returns -EAGAIN for zoned
+                        * file systems, which is an indication that there are
+                        * no active zones to allocate from at the moment.
+                        *
+                        * If this is the first loop iteration, wait for at
+                        * least one zone to finish before retrying the
+                        * allocation.  Otherwise ask the caller to write out
+                        * the already allocated blocks before coming back to
+                        * us, or return -ENOSPC if it can't handle retries.
+                        */
+                       ASSERT(btrfs_is_zoned(fs_info));
+                       if (start == orig_start) {
+                               wait_on_bit_io(&inode->root->fs_info->flags,
+                                              BTRFS_FS_NEED_ZONE_FINISH,
+                                              TASK_UNINTERRUPTIBLE);
+                               continue;
+                       }
+                       if (done_offset) {
+                               *done_offset = start - 1;
+                               return 0;
+                       }
+                       ret = -ENOSPC;
+               }
                if (ret < 0)
                        goto out_unlock;
                cur_alloc_size = ins.offset;
@@ -1477,6 +1503,9 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
                if (ret)
                        goto out_unlock;
        }
+done:
+       if (done_offset)
+               *done_offset = end;
        return ret;
 
 out_drop_extent_cache:
@@ -1486,21 +1515,6 @@ out_reserve:
        btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
 out_unlock:
        /*
-        * If done_offset is non-NULL and ret == -EAGAIN, we expect the
-        * caller to write out the successfully allocated region and retry.
-        */
-       if (done_offset && ret == -EAGAIN) {
-               if (orig_start < start)
-                       *done_offset = start - 1;
-               else
-                       *done_offset = start;
-               return ret;
-       } else if (ret == -EAGAIN) {
-               /* Convert to -ENOSPC since the caller cannot retry. */
-               ret = -ENOSPC;
-       }
-
-       /*
         * Now, we have three regions to clean up:
         *
         * |-------(1)----|---(2)---|-------------(3)----------|
@@ -1710,19 +1724,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
        while (start <= end) {
                ret = cow_file_range(inode, locked_page, start, end, &done_offset,
                                     true, false);
-               if (ret && ret != -EAGAIN)
+               if (ret)
                        return ret;
 
-               if (ret == 0)
-                       done_offset = end;
-
-               if (done_offset == start) {
-                       wait_on_bit_io(&inode->root->fs_info->flags,
-                                      BTRFS_FS_NEED_ZONE_FINISH,
-                                      TASK_UNINTERRUPTIBLE);
-                       continue;
-               }
-
                if (!locked_page_done) {
                        __set_page_dirty_nobuffers(locked_page);
                        account_page_redirty(locked_page);