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>

fs/btrfs/btrfs_inode.h

@@ -36,14 +36,13 @@
 #define BTRFS_INODE_ORPHAN_META_RESERVED	1
 #define BTRFS_INODE_DUMMY			2
 #define BTRFS_INODE_IN_DEFRAG			3
-#define BTRFS_INODE_DELALLOC_META_RESERVED	4
-#define BTRFS_INODE_HAS_ORPHAN_ITEM		5
-#define BTRFS_INODE_HAS_ASYNC_EXTENT		6
-#define BTRFS_INODE_NEEDS_FULL_SYNC		7
-#define BTRFS_INODE_COPY_EVERYTHING		8
-#define BTRFS_INODE_IN_DELALLOC_LIST		9
-#define BTRFS_INODE_READDIO_NEED_LOCK		10
-#define BTRFS_INODE_HAS_PROPS		        11
+#define BTRFS_INODE_HAS_ORPHAN_ITEM		4
+#define BTRFS_INODE_HAS_ASYNC_EXTENT		5
+#define BTRFS_INODE_NEEDS_FULL_SYNC		6
+#define BTRFS_INODE_COPY_EVERYTHING		7
+#define BTRFS_INODE_IN_DELALLOC_LIST		8
+#define BTRFS_INODE_READDIO_NEED_LOCK		9
+#define BTRFS_INODE_HAS_PROPS		        10
 
 /* in memory btrfs inode */
 struct btrfs_inode {
@@ -176,7 +175,8 @@ struct btrfs_inode {
 	 * of extent items we've reserved metadata for.
 	 */
 	unsigned outstanding_extents;
-	unsigned reserved_extents;
+
+	struct btrfs_block_rsv block_rsv;
 
 	/*
 	 * Cached values of inode properties
@@ -278,14 +278,6 @@ static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode,
 						  mod);
 }
 
-static inline void btrfs_mod_reserved_extents(struct btrfs_inode *inode, int mod)
-{
-	lockdep_assert_held(&inode->lock);
-	inode->reserved_extents += mod;
-	if (btrfs_is_free_space_inode(inode))
-		return;
-}
-
 static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
 {
 	int ret = 0;

fs/btrfs/ctree.h

@@ -763,8 +763,6 @@ struct btrfs_fs_info {
 	 * delayed dir index item
 	 */
 	struct btrfs_block_rsv global_block_rsv;
-	/* block reservation for delay allocation */
-	struct btrfs_block_rsv delalloc_block_rsv;
 	/* block reservation for metadata operations */
 	struct btrfs_block_rsv trans_block_rsv;
 	/* block reservation for chunk tree */
@@ -2757,6 +2755,9 @@ int btrfs_delalloc_reserve_space(struct inode *inode,
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
 struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
 					      unsigned short type);
+void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
+				   struct btrfs_block_rsv *rsv,
+				   unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_rsv *rsv);
 void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);

fs/btrfs/delayed-inode.c

@@ -581,36 +581,12 @@ static int btrfs_delayed_inode_reserve_metadata(
 	struct btrfs_block_rsv *dst_rsv;
 	u64 num_bytes;
 	int ret;
-	bool release = false;
 
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	/*
-	 * If our block_rsv is the delalloc block reserve then check and see if
-	 * we have our extra reservation for updating the inode.  If not fall
-	 * through and try to reserve space quickly.
-	 *
-	 * We used to try and steal from the delalloc block rsv or the global
-	 * reserve, but we'd steal a full reservation, which isn't kind.  We are
-	 * here through delalloc which means we've likely just cowed down close
-	 * to the leaf that contains the inode, so we would steal less just
-	 * doing the fallback inode update, so if we do end up having to steal
-	 * from the global block rsv we hopefully only steal one or two blocks
-	 * worth which is less likely to hurt us.
-	 */
-	if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&inode->lock);
-		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &inode->runtime_flags))
-			release = true;
-		else
-			src_rsv = NULL;
-		spin_unlock(&inode->lock);
-	}
-
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
@@ -618,7 +594,7 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 * space.
 	 *
 	 * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
-	 * we're accounted for.
+	 * we always reserve enough to update the inode item.
 	 */
 	if (!src_rsv || (!trans->bytes_reserved &&
 			 src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
@@ -643,32 +619,12 @@ static int btrfs_delayed_inode_reserve_metadata(
 	}
 
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
-
-	/*
-	 * Migrate only takes a reservation, it doesn't touch the size of the
-	 * block_rsv.  This is to simplify people who don't normally have things
-	 * migrated from their block rsv.  If they go to release their
-	 * reservation, that will decrease the size as well, so if migrate
-	 * reduced size we'd end up with a negative size.  But for the
-	 * delalloc_meta_reserved stuff we will only know to drop 1 reservation,
-	 * but we could in fact do this reserve/migrate dance several times
-	 * between the time we did the original reservation and we'd clean it
-	 * up.  So to take care of this, release the space for the meta
-	 * reservation here.  I think it may be time for a documentation page on
-	 * how block rsvs. work.
-	 */
 	if (!ret) {
 		trace_btrfs_space_reservation(fs_info, "delayed_inode",
 					      btrfs_ino(inode), num_bytes, 1);
 		node->bytes_reserved = num_bytes;
 	}
 
-	if (release) {
-		trace_btrfs_space_reservation(fs_info, "delalloc",
-					      btrfs_ino(inode), num_bytes, 0);
-		btrfs_block_rsv_release(fs_info, src_rsv, num_bytes);
-	}
-
 	return ret;
 }
 

fs/btrfs/disk-io.c

@@ -2447,14 +2447,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_delalloc_bytes;
 	}
 
-	fs_info->btree_inode = new_inode(sb);
-	if (!fs_info->btree_inode) {
-		err = -ENOMEM;
-		goto fail_bio_counter;
-	}
-
-	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
-
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
 	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
 	INIT_LIST_HEAD(&fs_info->trans_list);
@@ -2487,8 +2479,6 @@ int open_ctree(struct super_block *sb,
 	btrfs_mapping_init(&fs_info->mapping_tree);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
-	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv,
-			     BTRFS_BLOCK_RSV_DELALLOC);
 	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
 	btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
 	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
@@ -2517,6 +2507,14 @@ int open_ctree(struct super_block *sb,
 
 	INIT_LIST_HEAD(&fs_info->ordered_roots);
 	spin_lock_init(&fs_info->ordered_root_lock);
+
+	fs_info->btree_inode = new_inode(sb);
+	if (!fs_info->btree_inode) {
+		err = -ENOMEM;
+		goto fail_bio_counter;
+	}
+	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
+
 	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
 					GFP_KERNEL);
 	if (!fs_info->delayed_root) {

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);