btrfs: make the delalloc block rsv per inode

The way we handle delalloc metadata reservations has gotten
progressively more complicated over the years.  There is so much cruft
and weirdness around keeping the reserved count and outstanding counters
consistent and handling the error cases that it's impossible to
understand.

Fix this by making the delalloc block rsv per-inode.  This way we can
calculate the actual size of the outstanding metadata reservations every
time we make a change, and then reserve the delta based on that amount.
This greatly simplifies the code everywhere, and makes the error
handling in btrfs_delalloc_reserve_metadata far less terrifying.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 11 insertions, 7 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5b0de1e120d1..b71731ef28c4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -42,6 +42,7 @@
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/uio.h>
+#include <linux/magic.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -315,7 +316,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 		btrfs_free_path(path);
 		return PTR_ERR(trans);
 	}
-	trans->block_rsv = &fs_info->delalloc_block_rsv;
+	trans->block_rsv = &BTRFS_I(inode)->block_rsv;
 
 	if (compressed_size && compressed_pages)
 		extent_item_size = btrfs_file_extent_calc_inline_size(
@@ -2954,7 +2955,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			trans = NULL;
 			goto out;
 		}
-		trans->block_rsv = &fs_info->delalloc_block_rsv;
+		trans->block_rsv = &BTRFS_I(inode)->block_rsv;
 		ret = btrfs_update_inode_fallback(trans, root, inode);
 		if (ret) /* -ENOMEM or corruption */
 			btrfs_abort_transaction(trans, ret);
@@ -2990,7 +2991,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	trans->block_rsv = &fs_info->delalloc_block_rsv;
+	trans->block_rsv = &BTRFS_I(inode)->block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
 		compress_type = ordered_extent->compress_type;
@@ -8845,7 +8846,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (iov_iter_rw(iter) == WRITE) {
 		up_read(&BTRFS_I(inode)->dio_sem);
 		current->journal_info = NULL;
-		btrfs_delalloc_release_extents(BTRFS_I(inode), count);
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
 				btrfs_delalloc_release_space(inode, data_reserved,
@@ -8866,6 +8866,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		} 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);
 	}
 out:
 	if (wakeup)
@@ -9430,6 +9431,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 
 struct inode *btrfs_alloc_inode(struct super_block *sb)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_inode *ei;
 	struct inode *inode;
 
@@ -9456,8 +9458,9 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	spin_lock_init(&ei->lock);
 	ei->outstanding_extents = 0;
-	ei->reserved_extents = 0;
-
+	if (sb->s_magic != BTRFS_TEST_MAGIC)
+		btrfs_init_metadata_block_rsv(fs_info, &ei->block_rsv,
+					      BTRFS_BLOCK_RSV_DELALLOC);
 	ei->runtime_flags = 0;
 	ei->prop_compress = BTRFS_COMPRESS_NONE;
 	ei->defrag_compress = BTRFS_COMPRESS_NONE;
@@ -9507,8 +9510,9 @@ void btrfs_destroy_inode(struct inode *inode)
 
 	WARN_ON(!hlist_empty(&inode->i_dentry));
 	WARN_ON(inode->i_data.nrpages);
+	WARN_ON(BTRFS_I(inode)->block_rsv.reserved);
+	WARN_ON(BTRFS_I(inode)->block_rsv.size);
 	WARN_ON(BTRFS_I(inode)->outstanding_extents);
-	WARN_ON(BTRFS_I(inode)->reserved_extents);
 	WARN_ON(BTRFS_I(inode)->delalloc_bytes);
 	WARN_ON(BTRFS_I(inode)->new_delalloc_bytes);
 	WARN_ON(BTRFS_I(inode)->csum_bytes);