btrfs: qgroup: check generation when recording simple quota delta

Simple quotas count extents only from the moment the feature is enabled.
Therefore, if we do something like:

1. create subvol S
2. write F in S
3. enable quotas
4. remove F
5. write G in S

then after 3. and 4. we would expect the simple quota usage of S to be 0
(putting aside some metadata extents that might be written) and after
5., it should be the size of G plus metadata. Therefore, we need to be
able to determine whether a particular quota delta we are processing
predates simple quota enablement.

To do this, store the transaction id when quotas were enabled. In
fs_info for immediate use and in the quota status item to make it
recoverable on mount. When we see a delta, check if the generation of
the extent item is less than that of quota enablement. If so, we should
ignore the delta from this extent.

Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>

6 files changed, 40 insertions, 6 deletions

diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index fb1c1a1983f2..aa0844535644 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -980,6 +980,8 @@ BTRFS_SETGET_FUNCS(qgroup_status_flags, struct btrfs_qgroup_status_item,
 		   flags, 64);
 BTRFS_SETGET_FUNCS(qgroup_status_rescan, struct btrfs_qgroup_status_item,
 		   rescan, 64);
+BTRFS_SETGET_FUNCS(qgroup_status_enable_gen, struct btrfs_qgroup_status_item,
+		   enable_gen, 64);
 
 /* btrfs_qgroup_info_item */
 BTRFS_SETGET_FUNCS(qgroup_info_generation, struct btrfs_qgroup_info_item,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 865c74dffe82..8372d065aef4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1566,6 +1566,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 			.rsv_bytes = href->reserved_bytes,
 			.is_data = true,
 			.is_inc	= true,
+			.generation = trans->transid,
 		};
 
 		if (extent_op)
@@ -1738,6 +1739,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			.rsv_bytes = 0,
 			.is_data = false,
 			.is_inc = true,
+			.generation = trans->transid,
 		};
 
 		BUG_ON(!extent_op || !extent_op->update_flags);
@@ -3287,6 +3289,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			.rsv_bytes = 0,
 			.is_data = is_data,
 			.is_inc = false,
+			.generation = btrfs_extent_generation(leaf, ei),
 		};
 
 		/* In this branch refs == 1 */
@@ -4924,6 +4927,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_squota_delta delta = {
 		.root = root_objectid,
 		.num_bytes = ins->offset,
+		.generation = trans->transid,
 		.rsv_bytes = 0,
 		.is_data = true,
 		.is_inc = true,
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index e8fcf34f208a..2bd9bedc7095 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -687,6 +687,7 @@ struct btrfs_fs_info {
 	/* Protected by qgroup_rescan_lock */
 	bool qgroup_rescan_running;
 	u8 qgroup_drop_subtree_thres;
+	u64 qgroup_enable_gen;
 
 	/*
 	 * If this is not 0, then it indicates a serious filesystem error has
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5b3ad2f15039..f11f0fc8a9ff 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -369,6 +369,15 @@ static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info)
 				  BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING);
 }
 
+static void qgroup_read_enable_gen(struct btrfs_fs_info *fs_info,
+				   struct extent_buffer *leaf, int slot,
+				   struct btrfs_qgroup_status_item *ptr)
+{
+	ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA));
+	ASSERT(btrfs_item_size(leaf, slot) >= sizeof(*ptr));
+	fs_info->qgroup_enable_gen = btrfs_qgroup_status_enable_gen(leaf, ptr);
+}
+
 /*
  * The full config is read in one go, only called from open_ctree()
  * It doesn't use any locking, as at this point we're still single-threaded
@@ -384,7 +393,6 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 	int ret = 0;
 	u64 flags = 0;
 	u64 rescan_progress = 0;
-	bool simple;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED)
 		return 0;
@@ -437,9 +445,9 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				goto out;
 			}
 			fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr);
-			simple = (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE);
-			if (btrfs_qgroup_status_generation(l, ptr) !=
-			    fs_info->generation && !simple) {
+			if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) {
+				qgroup_read_enable_gen(fs_info, l, slot, ptr);
+			} else if (btrfs_qgroup_status_generation(l, ptr) != fs_info->generation) {
 				qgroup_mark_inconsistent(fs_info);
 				btrfs_err(fs_info,
 					"qgroup generation mismatch, marked as inconsistent");
@@ -1103,10 +1111,12 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
 	btrfs_set_qgroup_status_generation(leaf, ptr, trans->transid);
 	btrfs_set_qgroup_status_version(leaf, ptr, BTRFS_QGROUP_STATUS_VERSION);
 	fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON;
-	if (simple)
+	if (simple) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
-	else
+		btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid);
+	} else {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+	}
 	btrfs_set_qgroup_status_flags(leaf, ptr, fs_info->qgroup_flags &
 				      BTRFS_QGROUP_STATUS_FLAGS_MASK);
 	btrfs_set_qgroup_status_rescan(leaf, ptr, 0);
@@ -1210,6 +1220,8 @@ out_add_root:
 		goto out_free_path;
 	}
 
+	fs_info->qgroup_enable_gen = trans->transid;
+
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	/*
 	 * Commit the transaction while not holding qgroup_ioctl_lock, to avoid
@@ -4655,6 +4667,10 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 	if (!is_fstree(root))
 		return 0;
 
+	/* If the extent predates enabling quotas, don't count it. */
+	if (delta->generation < fs_info->qgroup_enable_gen)
+		return 0;
+
 	spin_lock(&fs_info->qgroup_lock);
 	qgroup = find_qgroup_rb(fs_info, root);
 	if (!qgroup) {
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 9858244eef20..855a4f978761 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -276,6 +276,8 @@ struct btrfs_squota_delta {
 	u64 num_bytes;
 	/* The number of bytes reserved for this extent. */
 	u64 rsv_bytes;
+	/* The generation the extent was created in. */
+	u64 generation;
 	/* Whether we are using or freeing the extent. */
 	bool is_inc;
 	/* Whether the extent is data or metadata. */
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 8b4def6aee52..c25fc9614594 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -1277,6 +1277,15 @@ struct btrfs_qgroup_status_item {
 	 * of the scan. It contains a logical address
 	 */
 	__le64 rescan;
+
+	/*
+	 * The generation when quotas were last enabled. Used by simple quotas to
+	 * avoid decrementing when freeing an extent that was written before
+	 * enable.
+	 *
+	 * Set only if flags contain BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE.
+	 */
+	__le64 enable_gen;
 } __attribute__ ((__packed__));
 
 struct btrfs_qgroup_info_item {