btrfs: qgroup: add new quota mode for simple quotas

Add a new quota mode called "simple quotas". It can be enabled by the
existing quota enable ioctl via a new command, and sets an incompat
bit, as the implementation of simple quotas will make backwards
incompatible changes to the disk format of the extent tree.

Signed-off-by: Boris Burkov <[email protected]>
Signed-off-by: David Sterba <[email protected]>

Author: boryas

fs/btrfs/delayed-ref.c

@@ -959,8 +959,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
-	    !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
@@ -1063,8 +1062,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
-	    !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);

fs/btrfs/fs.h

@@ -220,7 +220,8 @@ enum {
 	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
 	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID	|	\
 	 BTRFS_FEATURE_INCOMPAT_RAID1C34	|	\
-	 BTRFS_FEATURE_INCOMPAT_ZONED)
+	 BTRFS_FEATURE_INCOMPAT_ZONED		|	\
+	 BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA)
 
 #ifdef CONFIG_BTRFS_DEBUG
 	/*

fs/btrfs/ioctl.c

@@ -3697,7 +3697,8 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 
 	switch (sa->cmd) {
 	case BTRFS_QUOTA_CTL_ENABLE:
-		ret = btrfs_quota_enable(fs_info);
+	case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA:
+		ret = btrfs_quota_enable(fs_info, sa);
 		break;
 	case BTRFS_QUOTA_CTL_DISABLE:
 		ret = btrfs_quota_disable(fs_info);

fs/btrfs/qgroup.c

@@ -34,9 +34,21 @@ enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info)
 {
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
 		return BTRFS_QGROUP_MODE_DISABLED;
+	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE)
+		return BTRFS_QGROUP_MODE_SIMPLE;
 	return BTRFS_QGROUP_MODE_FULL;
 }
 
+bool btrfs_qgroup_enabled(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_DISABLED;
+}
+
+bool btrfs_qgroup_full_accounting(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL;
+}
+
 /*
  * Helpers to access qgroup reservation
  *
@@ -350,6 +362,8 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 
 static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info)
 {
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		return;
 	fs_info->qgroup_flags |= (BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT |
 				  BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN |
 				  BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING);
@@ -370,8 +384,9 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 	int ret = 0;
 	u64 flags = 0;
 	u64 rescan_progress = 0;
+	bool simple;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED)
 		return 0;
 
 	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
@@ -421,14 +436,14 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				 "old qgroup version, quota disabled");
 				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) {
+			    fs_info->generation && !simple) {
 				qgroup_mark_inconsistent(fs_info);
 				btrfs_err(fs_info,
 					"qgroup generation mismatch, marked as inconsistent");
 			}
-			fs_info->qgroup_flags = btrfs_qgroup_status_flags(l,
-									  ptr);
 			rescan_progress = btrfs_qgroup_status_rescan(l, ptr);
 			goto next1;
 		}
@@ -571,7 +586,7 @@ bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info)
 	struct rb_node *node;
 	bool ret = false;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED)
 		return ret;
 	/*
 	 * Since we're unmounting, there is no race and no need to grab qgroup
@@ -970,7 +985,8 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
+		       struct btrfs_ioctl_quota_ctl_args *quota_ctl_args)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_root *tree_root = fs_info->tree_root;
@@ -983,6 +999,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	struct btrfs_qgroup *prealloc = NULL;
 	struct btrfs_trans_handle *trans = NULL;
 	struct ulist *ulist = NULL;
+	const bool simple = (quota_ctl_args->cmd == BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA);
 	int ret = 0;
 	int slot;
 
@@ -1085,8 +1102,11 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 				 struct btrfs_qgroup_status_item);
 	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 |
-				BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+	fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON;
+	if (simple)
+		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
+	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);
@@ -1214,8 +1234,14 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_root = quota_root;
 	set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+	if (simple)
+		btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA);
 	spin_unlock(&fs_info->qgroup_lock);
 
+	/* Skip rescan for simple qgroups. */
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		goto out_free_path;
+
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (!ret) {
 	        qgroup_rescan_zero_tracking(fs_info);
@@ -1330,6 +1356,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	quota_root = fs_info->quota_root;
 	fs_info->quota_root = NULL;
 	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
+	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
 	fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
 	spin_unlock(&fs_info->qgroup_lock);
 
@@ -1810,6 +1837,9 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	struct btrfs_qgroup_extent_record *entry;
 	u64 bytenr = record->bytenr;
 
+	if (!btrfs_qgroup_full_accounting(fs_info))
+		return 0;
+
 	lockdep_assert_held(&delayed_refs->lock);
 	trace_btrfs_qgroup_trace_extent(fs_info, record);
 
@@ -1863,6 +1893,8 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans,
 	struct btrfs_backref_walk_ctx ctx = { 0 };
 	int ret;
 
+	if (!btrfs_qgroup_full_accounting(trans->fs_info))
+		return 0;
 	/*
 	 * We are always called in a context where we are already holding a
 	 * transaction handle. Often we are called when adding a data delayed
@@ -1931,8 +1963,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
-	    || bytenr == 0 || num_bytes == 0)
+	if (!btrfs_qgroup_full_accounting(fs_info) || bytenr == 0 || num_bytes == 0)
 		return 0;
 	record = kzalloc(sizeof(*record), GFP_NOFS);
 	if (!record)
@@ -1970,7 +2001,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 	u64 bytenr, num_bytes;
 
 	/* We can be called directly from walk_up_proc() */
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
 
 	for (i = 0; i < nr; i++) {
@@ -2346,7 +2377,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 	int level;
 	int ret;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
 
 	/* Wrong parameter order */
@@ -2413,7 +2444,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL);
 	BUG_ON(root_eb == NULL);
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
 
 	spin_lock(&fs_info->qgroup_lock);
@@ -2747,7 +2778,7 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	 * If quotas get disabled meanwhile, the resources need to be freed and
 	 * we can't just exit here.
 	 */
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+	if (!btrfs_qgroup_full_accounting(fs_info) ||
 	    fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING)
 		goto out_free;
 
@@ -2816,6 +2847,9 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 	u64 qgroup_to_skip;
 	int ret = 0;
 
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		return 0;
+
 	delayed_refs = &trans->transaction->delayed_refs;
 	qgroup_to_skip = delayed_refs->qgroup_to_skip;
 	while ((node = rb_first(&delayed_refs->dirty_extent_root))) {
@@ -2931,7 +2965,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 			qgroup_mark_inconsistent(fs_info);
 		spin_lock(&fs_info->qgroup_lock);
 	}
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (btrfs_qgroup_enabled(fs_info))
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_ON;
 	else
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
@@ -2990,7 +3024,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 	if (!committing)
 		mutex_lock(&fs_info->qgroup_ioctl_lock);
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_enabled(fs_info))
 		goto out;
 
 	quota_root = fs_info->quota_root;
@@ -3076,7 +3110,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		qgroup_dirty(fs_info, dstgroup);
 	}
 
-	if (srcid) {
+	if (srcid && btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL) {
 		srcgroup = find_qgroup_rb(fs_info, srcid);
 		if (!srcgroup)
 			goto unlock;
@@ -3339,6 +3373,9 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
 	int slot;
 	int ret;
 
+	if (!btrfs_qgroup_full_accounting(fs_info))
+		return 1;
+
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	extent_root = btrfs_extent_root(fs_info,
 				fs_info->qgroup_rescan_progress.objectid);
@@ -3419,10 +3456,15 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
 
 static bool rescan_should_stop(struct btrfs_fs_info *fs_info)
 {
-	return btrfs_fs_closing(fs_info) ||
-		test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state) ||
-		!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
-			  fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN;
+	if (btrfs_fs_closing(fs_info))
+		return true;
+	if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
+		return true;
+	if (!btrfs_qgroup_enabled(fs_info))
+		return true;
+	if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN)
+		return true;
+	return false;
 }
 
 static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
@@ -3436,6 +3478,9 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	bool stopped = false;
 	bool did_leaf_rescans = false;
 
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		return;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
@@ -3539,6 +3584,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 {
 	int ret = 0;
 
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) {
+		btrfs_warn(fs_info, "qgroup rescan init failed, running in simple mode");
+		return -EINVAL;
+	}
+
 	if (!init_flags) {
 		/* we're resuming qgroup rescan at mount time */
 		if (!(fs_info->qgroup_flags &
@@ -3569,7 +3619,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 			btrfs_warn(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
 			ret = -EINVAL;
-		} else if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
+		} else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
 			/* Quota disable is in progress */
 			ret = -EBUSY;
 		}
@@ -3828,7 +3878,7 @@ static int qgroup_reserve_data(struct btrfs_inode *inode,
 	u64 to_reserve;
 	int ret;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) ||
+	if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
 	    !is_fstree(root->root_key.objectid) || len == 0)
 		return 0;
 
@@ -3960,7 +4010,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 	int trace_op = QGROUP_RELEASE;
 	int ret;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &inode->root->fs_info->flags))
+	if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED)
 		return 0;
 
 	/* In release case, we shouldn't have @reserved */
@@ -4071,7 +4121,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
 	    !is_fstree(root->root_key.objectid) || num_bytes == 0)
 		return 0;
 
@@ -4116,7 +4166,7 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
 	    !is_fstree(root->root_key.objectid))
 		return;
 
@@ -4132,7 +4182,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
 	    !is_fstree(root->root_key.objectid))
 		return;
 
@@ -4191,7 +4241,7 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
 	    !is_fstree(root->root_key.objectid))
 		return;
 	/* Same as btrfs_qgroup_free_meta_prealloc() */
@@ -4299,7 +4349,7 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 	int level = btrfs_header_level(subvol_parent) - 1;
 	int ret = 0;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
 
 	if (btrfs_node_ptr_generation(subvol_parent, subvol_slot) >
@@ -4409,7 +4459,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	int i;
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
 	if (!is_fstree(root->root_key.objectid) || !root->reloc_root)
 		return 0;