mkfs: Quota support through -R|--runtime quota

index fa861ba0b4c3..cf99df1c90a8 100644
@@ -1012,6 +1012,7 @@ struct btrfs_qgroup_status_item {
 	__le64 rescan;		/* progress during scanning */
 } __attribute__ ((__packed__));
 
+#define BTRFS_QGROUP_STATUS_VERSION		1
 struct btrfs_block_group_item {
 	__le64 used;
 	__le64 chunk_objectid;

index 571b4d4f7171..58c735788977 100644
@@ -1563,6 +1563,8 @@ static int repair_qgroup_status(struct btrfs_fs_info *info)
 	btrfs_set_qgroup_status_rescan(path.nodes[0], status_item, 0);
 	btrfs_set_qgroup_status_generation(path.nodes[0], status_item,
 					   trans->transid);
+	btrfs_set_qgroup_status_version(path.nodes[0], status_item,
+					BTRFS_QGROUP_STATUS_VERSION);
 
 	btrfs_mark_buffer_dirty(path.nodes[0]);
 

index 58c735788977..f509cdb9317a 100644
@@ -1582,7 +1582,7 @@ int repair_qgroups(struct btrfs_fs_info *info, int *repaired)
 
 	*repaired = 0;
 
-	if (!repair)
+	if (info->readonly)
 		return 0;
 
 	list_for_each_entry_safe(count, tmpcount, &bad_qgroups, bad_list) {

index f509cdb9317a..67bd8b96ddd3 100644
@@ -1319,8 +1319,7 @@ void report_qgroups(int all)
 	while (node) {
 		c = rb_entry(node, struct qgroup_count, rb_node);
 
-		if (report_qgroup_difference(c, all))
-			list_add_tail(&c->bad_list, &bad_qgroups);
+		report_qgroup_difference(c, all);
 
 		node = rb_next(node);
 	}

@@ -1358,9 +1357,20 @@ void free_qgroup_counts(void)
 	}
 }
 
+static bool is_bad_qgroup(struct qgroup_count *count)
+{
+	struct qgroup_info *info = &count->info;
+	struct qgroup_info *disk = &count->diskinfo;
+	s64 excl_diff = info->exclusive - disk->exclusive;
+	s64 ref_diff = info->referenced - disk->referenced;
+
+	return (excl_diff || ref_diff);
+}
+
 int qgroup_verify_all(struct btrfs_fs_info *info)
 {
 	int ret;
+	struct rb_node *node;
 
 	if (!info->quota_enabled)
 		return 0;

@@ -1395,6 +1405,20 @@ int qgroup_verify_all(struct btrfs_fs_info *info)
 
 	ret = account_all_refs(1, 0);
 
+	/*
+	 * Do the correctness check here, so for callers who don't want
+	 * verbose report can skip calling report_qgroups()
+	 */
+	node = rb_first(&counts.root);
+	while (node) {
+		struct qgroup_count *c;
+
+		c = rb_entry(node, struct qgroup_count, rb_node);
+		if (is_bad_qgroup(c))
+			list_add_tail(&c->bad_list, &bad_qgroups);
+		node = rb_next(node);
+	}
+
 out:
 	/*
 	 * Don't free the qgroup count records as they will be walked

index 891a6d797756..84b298af8ee4 100644
@@ -9884,7 +9884,7 @@ int cmd_check(int argc, char **argv)
 			goto out;
 		}
 		report_qgroups(0);
-		ret = repair_qgroups(info, &qgroups_repaired);
+		ret = repair_qgroups(info, &qgroups_repaired, false);
 		err |= !!ret;
 		if (err) {
 			error("failed to repair quota groups");

index 67bd8b96ddd3..bb77eac139aa 100644
@@ -1498,7 +1498,7 @@ out:
 }
 
 static int repair_qgroup_info(struct btrfs_fs_info *info,
-			      struct qgroup_count *count)
+			      struct qgroup_count *count, bool silent)
 {
 	int ret;
 	struct btrfs_root *root = info->quota_root;

@@ -1507,8 +1507,10 @@ static int repair_qgroup_info(struct btrfs_fs_info *info,
 	struct btrfs_qgroup_info_item *info_item;
 	struct btrfs_key key;
 
-	printf("Repair qgroup %llu/%llu\n", btrfs_qgroup_level(count->qgroupid),
-	       btrfs_qgroup_subvid(count->qgroupid));
+	if (!silent)
+		printf("Repair qgroup %llu/%llu\n",
+			btrfs_qgroup_level(count->qgroupid),
+			btrfs_qgroup_subvid(count->qgroupid));
 
 	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans))

@@ -1553,7 +1555,7 @@ out:
 	return ret;
 }
 
-static int repair_qgroup_status(struct btrfs_fs_info *info)
+static int repair_qgroup_status(struct btrfs_fs_info *info, bool silent)
 {
 	int ret;
 	struct btrfs_root *root = info->quota_root;

@@ -1562,7 +1564,8 @@ static int repair_qgroup_status(struct btrfs_fs_info *info)
 	struct btrfs_key key;
 	struct btrfs_qgroup_status_item *status_item;
 
-	printf("Repair qgroup status item\n");
+	if (!silent)
+		printf("Repair qgroup status item\n");
 
 	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans))

@@ -1599,7 +1602,7 @@ out:
 	return ret;
 }
 
-int repair_qgroups(struct btrfs_fs_info *info, int *repaired)
+int repair_qgroups(struct btrfs_fs_info *info, int *repaired, bool silent)
 {
 	int ret = 0;
 	struct qgroup_count *count, *tmpcount;

@@ -1610,7 +1613,7 @@ int repair_qgroups(struct btrfs_fs_info *info, int *repaired)
 		return 0;
 
 	list_for_each_entry_safe(count, tmpcount, &bad_qgroups, bad_list) {
-		ret = repair_qgroup_info(info, count);
+		ret = repair_qgroup_info(info, count, silent);
 		if (ret) {
 			goto out;
 		}

@@ -1626,7 +1629,7 @@ int repair_qgroups(struct btrfs_fs_info *info, int *repaired)
 	 * mount.
 	 */
 	if (*repaired || counts.qgroup_inconsist || counts.rescan_running) {
-		ret = repair_qgroup_status(info);
+		ret = repair_qgroup_status(info, silent);
 		if (ret)
 			goto out;
 

index d7d83a46ed5a..7e5697024f31 100644
@@ -24,7 +24,7 @@
 
 int qgroup_verify_all(struct btrfs_fs_info *info);
 void report_qgroups(int all);
-int repair_qgroups(struct btrfs_fs_info *info, int *repaired);
+int repair_qgroups(struct btrfs_fs_info *info, int *repaired, bool silent);
 
 int print_extent_state(struct btrfs_fs_info *info, u64 subvol);
 

index e26a1c29bb75..4ff1e1d22e0e 100644
@@ -23,6 +23,7 @@
 #include "internal.h"
 #include "sizes.h"
 #include "messages.h"
+#include "utils.h"
 
 static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_path *path, int level);

@@ -137,6 +138,114 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+/*
+ * Create a new tree root, with root objectid set to @objectid.
+ *
+ * NOTE: Doesn't support tree with non-zero offset, like tree reloc tree.
+ */
+int btrfs_create_root(struct btrfs_trans_handle *trans,
+		      struct btrfs_fs_info *fs_info, u64 objectid)
+{
+	struct extent_buffer *node;
+	struct btrfs_root *new_root;
+	struct btrfs_disk_key disk_key;
+	struct btrfs_key location;
+	struct btrfs_root_item root_item = { 0 };
+	int ret;
+
+	new_root = malloc(sizeof(*new_root));
+	if (!new_root)
+		return -ENOMEM;
+
+	btrfs_setup_root(new_root, fs_info, objectid);
+	if (!is_fstree(objectid))
+		new_root->track_dirty = 1;
+	add_root_to_dirty_list(new_root);
+
+	new_root->objectid = objectid;
+	new_root->root_key.objectid = objectid;
+	new_root->root_key.type = BTRFS_ROOT_ITEM_KEY;
+	new_root->root_key.offset = 0;
+
+	node = btrfs_alloc_free_block(trans, new_root, fs_info->nodesize,
+				      objectid, &disk_key, 0, 0, 0);
+	if (IS_ERR(node)) {
+		ret = PTR_ERR(node);
+		error("failed to create root node for tree %llu: %d (%s)",
+		      objectid, ret, strerror(-ret));
+		return ret;
+	}
+	new_root->node = node;
+
+	btrfs_set_header_generation(node, trans->transid);
+	btrfs_set_header_backref_rev(node, BTRFS_MIXED_BACKREF_REV);
+	btrfs_clear_header_flag(node, BTRFS_HEADER_FLAG_RELOC |
+				      BTRFS_HEADER_FLAG_WRITTEN);
+	btrfs_set_header_owner(node, objectid);
+	btrfs_set_header_nritems(node, 0);
+	btrfs_set_header_level(node, 0);
+	write_extent_buffer(node, fs_info->fsid, btrfs_header_fsid(),
+			    BTRFS_FSID_SIZE);
+	ret = btrfs_inc_ref(trans, new_root, node, 0);
+	if (ret < 0)
+		goto free;
+
+	/*
+	 * Special tree roots may need to modify pointers in @fs_info
+	 * Only quota is supported yet.
+	 */
+	switch (objectid) {
+	case BTRFS_QUOTA_TREE_OBJECTID:
+		if (fs_info->quota_root) {
+			error("quota root already exists");
+			ret = -EEXIST;
+			goto free;
+		}
+		fs_info->quota_root = new_root;
+		fs_info->quota_enabled = 1;
+		break;
+	/*
+	 * Essential trees can't be created by this function, yet.
+	 * As we expect such skeleton exists, or a lot of functions like
+	 * btrfs_alloc_free_block() doesn't work at all
+	 */
+	case BTRFS_ROOT_TREE_OBJECTID:
+	case BTRFS_EXTENT_TREE_OBJECTID:
+	case BTRFS_CHUNK_TREE_OBJECTID:
+	case BTRFS_FS_TREE_OBJECTID:
+		ret = -EEXIST;
+		goto free;
+	default:
+		/* Subvolume trees don't need special handles */
+		if (is_fstree(objectid))
+			break;
+		/* Other special trees are not supported yet */
+		ret = -ENOTTY;
+		goto free;
+	}
+	btrfs_mark_buffer_dirty(node);
+	btrfs_set_root_bytenr(&root_item, btrfs_header_bytenr(node));
+	btrfs_set_root_level(&root_item, 0);
+	btrfs_set_root_generation(&root_item, trans->transid);
+	btrfs_set_root_dirid(&root_item, 0);
+	btrfs_set_root_refs(&root_item, 1);
+	btrfs_set_root_used(&root_item, fs_info->nodesize);
+	location.objectid = objectid;
+	location.type = BTRFS_ROOT_ITEM_KEY;
+	location.offset = 0;
+
+	ret = btrfs_insert_root(trans, fs_info->tree_root, &location,
+				&root_item);
+	if (ret < 0)
+		goto free;
+	return ret;
+
+free:
+	free_extent_buffer(node);
+	free(new_root);
+	return ret;
+}
+
 /*
  * check if the tree block can be shared by multiple trees
  */

index cf99df1c90a8..b80771762575 100644
@@ -2606,6 +2606,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      struct extent_buffer *buf,
 		      struct extent_buffer **cow_ret, u64 new_root_objectid);
+int btrfs_create_root(struct btrfs_trans_handle *trans,
+		      struct btrfs_fs_info *fs_info, u64 objectid);
 int btrfs_extend_item(struct btrfs_root *root, struct btrfs_path *path,
 		u32 data_size);
 int btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path,

index b65b18ddf2f3..67b193960aec 100644
@@ -709,6 +709,40 @@ static void update_chunk_allocation(struct btrfs_fs_info *fs_info,
 	}
 }
 
+static int insert_qgroup_items(struct btrfs_trans_handle *trans,
+			       struct btrfs_fs_info *fs_info,
+			       u64 qgroupid)
+{
+	struct btrfs_path path;
+	struct btrfs_root *quota_root = fs_info->quota_root;
+	struct btrfs_key key;
+	int ret;
+
+	if (qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT) {
+		error("qgroup level other than 0 is not supported yet");
+		return -ENOTTY;
+	}
+
+	key.objectid = 0;
+	key.type = BTRFS_QGROUP_INFO_KEY;
+	key.offset = qgroupid;
+
+	btrfs_init_path(&path);
+	ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
+				      sizeof(struct btrfs_qgroup_info_item));
+	btrfs_release_path(&path);
+	if (ret < 0)
+		return ret;
+
+	key.objectid = 0;
+	key.type = BTRFS_QGROUP_LIMIT_KEY;
+	key.offset = qgroupid;
+	ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
+				      sizeof(struct btrfs_qgroup_limit_item));
+	btrfs_release_path(&path);
+	return ret;
+}
+
 int main(int argc, char **argv)
 {
 	char *file;

index 67b193960aec..6a5d14727388 100644
@@ -42,6 +42,7 @@
 #include "mkfs/common.h"
 #include "mkfs/rootdir.h"
 #include "fsfeatures.h"
+#include "qgroup-verify.h"
 
 static int verbose = 1;
 

@@ -743,6 +744,91 @@ static int insert_qgroup_items(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static int setup_quota_root(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_qgroup_status_item *qsi;
+	struct btrfs_root *quota_root;
+	struct btrfs_path path;
+	struct btrfs_key key;
+	int qgroup_repaired = 0;
+	int ret;
+
+	/* One to modify tree root, one for quota root */
+	trans = btrfs_start_transaction(fs_info->tree_root, 2);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		error("failed to start transaction: %d (%s)",
+			ret, strerror(-ret));
+		return ret;
+	}
+	ret = btrfs_create_root(trans, fs_info, BTRFS_QUOTA_TREE_OBJECTID);
+	if (ret < 0) {
+		error("failed to create quota root: %d (%s)",
+			ret, strerror(-ret));
+		goto fail;
+	}
+	quota_root = fs_info->quota_root;
+
+	key.objectid = 0;
+	key.type = BTRFS_QGROUP_STATUS_KEY;
+	key.offset = 0;
+
+	btrfs_init_path(&path);
+	ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
+				      sizeof(*qsi));
+	if (ret < 0) {
+		error("failed to insert qgroup status item: %d (%s)",
+			ret, strerror(-ret));
+		goto fail;
+	}
+
+	qsi = btrfs_item_ptr(path.nodes[0], path.slots[0],
+			     struct btrfs_qgroup_status_item);
+	btrfs_set_qgroup_status_generation(path.nodes[0], qsi, 0);
+	btrfs_set_qgroup_status_rescan(path.nodes[0], qsi, 0);
+
+	/* Mark current status info inconsistent, and fix it later */
+	btrfs_set_qgroup_status_flags(path.nodes[0], qsi,
+			BTRFS_QGROUP_STATUS_FLAG_ON |
+			BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT);
+	btrfs_release_path(&path);
+
+	/* Currently mkfs will only create one subvolume */
+	ret = insert_qgroup_items(trans, fs_info, BTRFS_FS_TREE_OBJECTID);
+	if (ret < 0) {
+		error("failed to insert qgroup items: %d (%s)",
+			ret, strerror(-ret));
+		goto fail;
+	}
+
+	ret = btrfs_commit_transaction(trans, fs_info->tree_root);
+	if (ret < 0) {
+		error("failed to commit current transaction: %d (%s)",
+			ret, strerror(-ret));
+		return ret;
+	}
+
+	/*
+	 * Qgroup is setup but with wrong info, use qgroup-verify
+	 * infrastructure to repair them.
+	 * (Just acts as offline rescan)
+	 */
+	ret = qgroup_verify_all(fs_info);
+	if (ret < 0) {
+		error("qgroup rescan failed: %d (%s)", ret, strerror(-ret));
+		return ret;
+	}
+	ret = repair_qgroups(fs_info, &qgroup_repaired, true);
+	if (ret < 0)
+		error("failed to fill qgroup info: %d (%s)", ret,
+			strerror(-ret));
+	return ret;
+fail:
+	btrfs_commit_transaction(trans, fs_info->tree_root);
+	return ret;
+}
+
 int main(int argc, char **argv)
 {
 	char *file;

index 6bdfab40d0b0..099cb537ef0d 100644
@@ -1116,7 +1116,7 @@ static int do_convert(const char *devname, u32 convert_flags, u32 nodesize,
 		error("unable to open %s: %m", devname);
 		goto fail;
 	}
-	btrfs_parse_features_to_string(features_buf, features);
+	btrfs_parse_fs_features_to_string(features_buf, features);
 	if (features == BTRFS_MKFS_DEFAULT_FEATURES)
 		strcat(features_buf, " (default)");
 

@@ -1767,7 +1767,7 @@ int main(int argc, char *argv[])
 				if (features & ~BTRFS_CONVERT_ALLOWED_FEATURES) {
 					char buf[64];
 
-					btrfs_parse_features_to_string(buf,
+					btrfs_parse_fs_features_to_string(buf,
 						features & ~BTRFS_CONVERT_ALLOWED_FEATURES);
 					error("features not allowed for convert: %s",
 						buf);

205 lines not on this page · raw message

index 3cc9452a3327..7ea4a2b47740 100644
@@ -40,9 +40,13 @@
 #define BTRFS_FEATURE_LIST_ALL		(1ULL << 63)
 
 void btrfs_list_all_fs_features(u64 mask_disallowed);
-char* btrfs_parse_fs_features(char *namelist, u64 *flags);
+void btrfs_list_all_runtime_features(u64 mask_disallowed);
+char *btrfs_parse_fs_features(char *namelist, u64 *flags);
+char *btrfs_parse_runtime_features(char *namelist, u64 *flags);
 void btrfs_process_fs_features(u64 flags);
-void btrfs_parse_features_to_string(char *buf, u64 flags);
+void btrfs_process_runtime_features(u64 flags);
+void btrfs_parse_fs_features_to_string(char *buf, u64 flags);
+void btrfs_parse_runtime_features_to_string(char *buf, u64 flags);
 void print_kernel_version(FILE *stream, u32 version);
 u32 get_running_kernel_version(void);
 int btrfs_check_nodesize(u32 nodesize, u32 sectorsize, u64 features);

index 6a5d14727388..388349f87319 100644
@@ -1390,7 +1390,7 @@ raid_groups:
 			btrfs_group_profile_str(metadata_profile),
 			pretty_size(allocation.system));
 		printf("SSD detected:       %s\n", ssd ? "yes" : "no");
-		btrfs_parse_features_to_string(features_buf, features);
+		btrfs_parse_fs_features_to_string(features_buf, features);
 		printf("Incompat features:  %s", features_buf);
 		printf("\n");
 

100 lines not on this page · raw message

index 02205dcec32d..c76043be73a2 100644
@@ -98,6 +98,9 @@ static const struct btrfs_feature mkfs_features[] = {
 };
 
 static const struct btrfs_feature runtime_features[] = {
+	{ "quota", BTRFS_RUNTIME_FEATURE_QUOTA, NULL,
+		VERSION_TO_STRING2(3, 4), NULL, 0, NULL, 0,
+		"enable btrfs quota support" },
 	/* Keep this one last */
 	{ "list-all", BTRFS_FEATURE_LIST_ALL, NULL }
 };

index 7ea4a2b47740..131412540c75 100644
@@ -39,6 +39,8 @@
 
 #define BTRFS_FEATURE_LIST_ALL		(1ULL << 63)
 
+#define BTRFS_RUNTIME_FEATURE_QUOTA	(1ULL << 0)
+
 void btrfs_list_all_fs_features(u64 mask_disallowed);
 void btrfs_list_all_runtime_features(u64 mask_disallowed);
 char *btrfs_parse_fs_features(char *namelist, u64 *flags);

index f9b3599447ef..6246651247df 100644
@@ -1385,6 +1385,14 @@ raid_groups:
 		}
 	}
 
+	if (runtime_features & BTRFS_RUNTIME_FEATURE_QUOTA) {
+		ret = setup_quota_root(fs_info);
+		if (ret < 0) {
+			error("failed to initialize quota: %d (%s)", ret,
+				strerror(-ret));
+			goto out;
+		}
+	}
 	if (verbose) {
 		char features_buf[64];