btrfs: qgroup: Move reserved data accounting from btrfs_delayed_ref_head to...

btrfs: qgroup: Move reserved data accounting from btrfs_delayed_ref_head to btrfs_qgroup_extent_record

[BUG]
Btrfs/139 will fail with a high probability if the testing machine (VM)
has only 2G RAM.

Resulting the final write success while it should fail due to EDQUOT,
and the fs will have quota exceeding the limit by 16K.

The simplified reproducer will be: (needs a 2G ram VM)

  $ mkfs.btrfs -f $dev
  $ mount $dev $mnt

  $ btrfs subv create $mnt/subv
  $ btrfs quota enable $mnt
  $ btrfs quota rescan -w $mnt
  $ btrfs qgroup limit -e 1G $mnt/subv

  $ for i in $(seq -w  1 8); do
  	xfs_io -f -c "pwrite 0 128M" $mnt/subv/file_$i > /dev/null
  	echo "file $i written" > /dev/kmsg
    done
  $ sync
  $ btrfs qgroup show -pcre --raw $mnt

The last pwrite will not trigger EDQUOT and final 'qgroup show' will
show something like:

  qgroupid         rfer         excl     max_rfer     max_excl parent  child
  --------         ----         ----     --------     -------- ------  -----
  0/5             16384        16384         none         none ---     ---
  0/256      1073758208   1073758208         none   1073741824 ---     ---

And 1073758208 is larger than
  > 1073741824.

[CAUSE]
It's a bug in btrfs qgroup data reserved space management.

For quota limit, we must ensure that:
  reserved (data + metadata) + rfer/excl <= limit

Since rfer/excl is only updated at transaction commmit time, reserved
space needs to be taken special care.

One important part of reserved space is data, and for a new data extent
written to disk, we still need to take the reserved space until
rfer/excl numbers get updated.

Originally when an ordered extent finishes, we migrate the reserved
qgroup data space from extent_io tree to delayed ref head of the data
extent, expecting delayed ref will only be cleaned up at commit
transaction time.

However for small RAM machine, due to memory pressure dirty pages can be
flushed back to disk without committing a transaction.

The related events will be something like:

  file 1 written
  btrfs_finish_ordered_io: ino=258 ordered offset=0 len=54947840
  btrfs_finish_ordered_io: ino=258 ordered offset=54947840 len=5636096
  btrfs_finish_ordered_io: ino=258 ordered offset=61153280 len=57344
  btrfs_finish_ordered_io: ino=258 ordered offset=61210624 len=8192
  btrfs_finish_ordered_io: ino=258 ordered offset=60583936 len=569344
  cleanup_ref_head: num_bytes=54947840
  cleanup_ref_head: num_bytes=5636096
  cleanup_ref_head: num_bytes=569344
  cleanup_ref_head: num_bytes=57344
  cleanup_ref_head: num_bytes=8192
  ^^^^^^^^^^^^^^^^ This will free qgroup data reserved space
  file 2 written
  ...
  file 8 written
  cleanup_ref_head: num_bytes=8192
  ...
  btrfs_commit_transaction  <<< the only transaction committed during
				the test

When file 2 is written, we have already freed 128M reserved qgroup data
space for ino 258. Thus later write won't trigger EDQUOT.

This allows us to write more data beyond qgroup limit.

In my 2G ram VM, it could reach about 1.2G before hitting EDQUOT.

[FIX]
By moving reserved qgroup data space from btrfs_delayed_ref_head to
btrfs_qgroup_extent_record, we can ensure that reserved qgroup data
space won't be freed half way before commit transaction, thus fix the
problem.

Fixes: f64d5ca8 ("btrfs: delayed_ref: Add new function to record reserved space into delayed ref")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/delayed-ref.c

@@ -602,17 +602,14 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 	RB_CLEAR_NODE(&head_ref->href_node);
 	head_ref->processing = 0;
 	head_ref->total_ref_mod = count_mod;
-	head_ref->qgroup_reserved = 0;
-	head_ref->qgroup_ref_root = 0;
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
 
 	if (qrecord) {
 		if (ref_root && reserved) {
-			head_ref->qgroup_ref_root = ref_root;
-			head_ref->qgroup_reserved = reserved;
+			qrecord->data_rsv = reserved;
+			qrecord->data_rsv_refroot = ref_root;
 		}
-
 		qrecord->bytenr = bytenr;
 		qrecord->num_bytes = num_bytes;
 		qrecord->old_roots = NULL;
@@ -651,10 +648,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		WARN_ON(qrecord && head_ref->qgroup_ref_root
-			&& head_ref->qgroup_reserved
-			&& existing->qgroup_ref_root
-			&& existing->qgroup_reserved);
 		update_existing_head_ref(trans, existing, head_ref,
 					 old_ref_mod);
 		/*
@@ -770,7 +763,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
 	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
+		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
 			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
@@ -867,7 +860,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
 	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
+		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
 			kmem_cache_free(btrfs_delayed_ref_head_cachep,

fs/btrfs/delayed-ref.h

@@ -102,17 +102,6 @@ struct btrfs_delayed_ref_head {
 	 */
 	int ref_mod;
 
-	/*
-	 * For qgroup reserved space freeing.
-	 *
-	 * ref_root and reserved will be recorded after
-	 * BTRFS_ADD_DELAYED_EXTENT is called.
-	 * And will be used to free reserved qgroup space at
-	 * run_delayed_refs() time.
-	 */
-	u64 qgroup_ref_root;
-	u64 qgroup_reserved;
-
 	/*
 	 * when a new extent is allocated, it is just reserved in memory
 	 * The actual extent isn't inserted into the extent allocation tree

fs/btrfs/extent-tree.c

@@ -2492,9 +2492,6 @@ void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	/* Also free its reserved qgroup space */
-	btrfs_qgroup_free_delayed_ref(fs_info, head->qgroup_ref_root,
-				      head->qgroup_reserved);
 	btrfs_delayed_refs_rsv_release(fs_info, nr_items);
 }
 

fs/btrfs/qgroup.c

@@ -1546,12 +1546,18 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 		parent_node = *p;
 		entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
 				 node);
-		if (bytenr < entry->bytenr)
+		if (bytenr < entry->bytenr) {
 			p = &(*p)->rb_left;
-		else if (bytenr > entry->bytenr)
+		} else if (bytenr > entry->bytenr) {
 			p = &(*p)->rb_right;
-		else
+		} else {
+			if (record->data_rsv && !entry->data_rsv) {
+				entry->data_rsv = record->data_rsv;
+				entry->data_rsv_refroot =
+					record->data_rsv_refroot;
+			}
 			return 1;
+		}
 	}
 
 	rb_link_node(&record->node, parent_node, p);
@@ -1597,7 +1603,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
 	    || bytenr == 0 || num_bytes == 0)
 		return 0;
-	record = kmalloc(sizeof(*record), gfp_flag);
+	record = kzalloc(sizeof(*record), gfp_flag);
 	if (!record)
 		return -ENOMEM;
 
@@ -2517,6 +2523,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 					goto cleanup;
 			}
 
+			/* Free the reserved data space */
+			btrfs_qgroup_free_refroot(fs_info,
+					record->data_rsv_refroot,
+					record->data_rsv,
+					BTRFS_QGROUP_RSV_DATA);
 			/*
 			 * Use SEQ_LAST as time_seq to do special search, which
 			 * doesn't lock tree or delayed_refs and search current

fs/btrfs/qgroup.h

@@ -107,6 +107,17 @@ struct btrfs_qgroup_extent_record {
 	struct rb_node node;
 	u64 bytenr;
 	u64 num_bytes;
+
+	/*
+	 * For qgroup reserved data space freeing.
+	 *
+	 * @data_rsv_refroot and @data_rsv will be recorded after
+	 * BTRFS_ADD_DELAYED_EXTENT is called.
+	 * And will be used to free reserved qgroup space at
+	 * transaction commit time.
+	 */
+	u32 data_rsv;		/* reserved data space needs to be freed */
+	u64 data_rsv_refroot;	/* which root the reserved data belongs to */
 	struct ulist *old_roots;
 };
 
@@ -326,15 +337,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
-static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
-						 u64 ref_root, u64 num_bytes)
-{
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
-		return;
-	trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
-	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes,
-				  BTRFS_QGROUP_RSV_DATA);
-}
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,

include/trace/events/btrfs.h

@@ -1513,35 +1513,6 @@ DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data,
 	TP_ARGS(inode, start, len, reserved, op)
 );
 
-DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref,
-
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 u64 ref_root, u64 reserved),
-
-	TP_ARGS(fs_info, ref_root, reserved),
-
-	TP_STRUCT__entry_btrfs(
-		__field(	u64,		ref_root	)
-		__field(	u64,		reserved	)
-	),
-
-	TP_fast_assign_btrfs(fs_info,
-		__entry->ref_root	= ref_root;
-		__entry->reserved	= reserved;
-	),
-
-	TP_printk_btrfs("root=%llu reserved=%llu op=free",
-		  __entry->ref_root, __entry->reserved)
-);
-
-DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref,
-
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 u64 ref_root, u64 reserved),
-
-	TP_ARGS(fs_info, ref_root, reserved)
-);
-
 DECLARE_EVENT_CLASS(btrfs_qgroup_extent,
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
 		 const struct btrfs_qgroup_extent_record *rec),