btrfs: qgroup: Use separate meta reservation type for delalloc
Before this patch, btrfs qgroup is mixing per-transcation meta rsv with
preallocated meta rsv, making it quite easy to underflow qgroup meta
reservation.
Since we have the new qgroup meta rsv types, apply it to delalloc
reservation.
Now for delalloc, most of its reserved space will use META_PREALLOC qgroup
rsv type.
And for callers reducing outstanding extent like btrfs_finish_ordered_io(),
they will convert corresponding META_PREALLOC reservation to
META_PERTRANS.
This is mainly due to the fact that current qgroup numbers will only be
updated in btrfs_commit_transaction(), that's to say if we don't keep
such placeholder reservation, we can exceed qgroup limitation.
And for callers freeing outstanding extent in error handler, we will
just free META_PREALLOC bytes.
This behavior makes callers of btrfs_qgroup_release_meta() or
btrfs_qgroup_convert_meta() to be aware of which type they are.
So in this patch, btrfs_delalloc_release_metadata() and its callers get
an extra parameter to info qgroup to do correct meta convert/release.
The good news is, even we use the wrong type (convert or free), it won't
cause obvious bug, as prealloc type is always in good shape, and the
type only affects how per-trans meta is increased or not.
So the worst case will be at most metadata limitation can be sometimes
exceeded (no convert at all) or metadata limitation is reached too soon
(no free at all).
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a9a4738..1f091c2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1867,7 +1867,7 @@ static void btrfs_clear_bit_hook(void *private_data,
*/
if (*bits & EXTENT_CLEAR_META_RESV &&
root != fs_info->tree_root)
- btrfs_delalloc_release_metadata(inode, len);
+ btrfs_delalloc_release_metadata(inode, len, false);
/* For sanity tests. */
if (btrfs_is_testing(fs_info))
@@ -2152,7 +2152,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
ClearPageChecked(page);
set_page_dirty(page);
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false);
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state);
@@ -4802,8 +4802,8 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
page = find_or_create_page(mapping, index, mask);
if (!page) {
btrfs_delalloc_release_space(inode, data_reserved,
- block_start, blocksize);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
+ block_start, blocksize, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true);
ret = -ENOMEM;
goto out;
}
@@ -4870,8 +4870,8 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
out_unlock:
if (ret)
btrfs_delalloc_release_space(inode, data_reserved, block_start,
- blocksize);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
+ blocksize, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0));
unlock_page(page);
put_page(page);
out:
@@ -8636,7 +8636,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (ret < 0 && ret != -EIOCBQUEUED) {
if (dio_data.reserve)
btrfs_delalloc_release_space(inode, data_reserved,
- offset, dio_data.reserve);
+ offset, dio_data.reserve, true);
/*
* On error we might have left some ordered extents
* without submitting corresponding bios for them, so
@@ -8652,8 +8652,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
false);
} else if (ret >= 0 && (size_t)ret < count)
btrfs_delalloc_release_space(inode, data_reserved,
- offset, count - (size_t)ret);
- btrfs_delalloc_release_extents(BTRFS_I(inode), count);
+ offset, count - (size_t)ret, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), count, false);
}
out:
if (wakeup)
@@ -8968,7 +8968,8 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
if (reserved_space < PAGE_SIZE) {
end = page_start + reserved_space - 1;
btrfs_delalloc_release_space(inode, data_reserved,
- page_start, PAGE_SIZE - reserved_space);
+ page_start, PAGE_SIZE - reserved_space,
+ true);
}
}
@@ -9018,16 +9019,16 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
out_unlock:
if (!ret) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
}
unlock_page(page);
out:
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
btrfs_delalloc_release_space(inode, data_reserved, page_start,
- reserved_space);
+ reserved_space, (ret != 0));
out_noreserve:
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);