btrfs: qgroup: Introduce extent changeset for qgroup reserve functions

Introduce a new parameter, struct extent_changeset for
btrfs_qgroup_reserved_data() and its callers.

Such extent_changeset was used in btrfs_qgroup_reserve_data() to record
which range it reserved in current reserve, so it can free it in error
paths.

The reason we need to export it to callers is, at buffered write error
path, without knowing what exactly which range we reserved in current
allocation, we can free space which is not reserved by us.

This will lead to qgroup reserved space underflow.

Reviewed-by: Chandan Rajendra <[email protected]>
Signed-off-by: Qu Wenruo <[email protected]>
Signed-off-by: David Sterba <[email protected]>

Author: Qu Wenruo

fs/btrfs/ctree.h

@@ -2708,8 +2708,9 @@ enum btrfs_flush_state {
 	COMMIT_TRANS		=	6,
 };
 
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
@@ -2727,7 +2728,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
 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,

fs/btrfs/extent-tree.c

@@ -3402,6 +3402,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_root *root = fs_info->tree_root;
 	struct inode *inode = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 alloc_hint = 0;
 	int dcs = BTRFS_DC_ERROR;
 	u64 num_pages = 0;
@@ -3521,7 +3522,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	num_pages *= 16;
 	num_pages *= PAGE_SIZE;
 
-	ret = btrfs_check_data_free_space(inode, 0, num_pages);
+	ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages);
 	if (ret)
 		goto out_put;
 
@@ -3552,6 +3553,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	block_group->disk_cache_state = dcs;
 	spin_unlock(&block_group->lock);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -4326,12 +4328,8 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 	return ret;
 }
 
-/*
- * New check_data_free_space() with ability for precious data reservation
- * Will replace old btrfs_check_data_free_space(), but for patch split,
- * add a new function first and then replace it.
- */
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int ret;
@@ -4346,9 +4344,11 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
 		return ret;
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
-	ret = btrfs_qgroup_reserve_data(inode, start, len);
+	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
 	if (ret < 0)
 		btrfs_free_reserved_data_space_noquota(inode, start, len);
+	else
+		ret = 0;
 	return ret;
 }
 
@@ -6175,6 +6175,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes)
  * @inode: inode we're writing to
  * @start: start range we are writing to
  * @len: how long the range we are writing to
+ * @reserved: mandatory parameter, record actually reserved qgroup ranges of
+ * 	      current reservation.
  *
  * This will do the following things
  *
@@ -6192,11 +6194,12 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes)
  * Return 0 for success
  * Return <0 for error(-ENOSPC or -EQUOT)
  */
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	int ret;
 
-	ret = btrfs_check_data_free_space(inode, start, len);
+	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
 	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);

fs/btrfs/extent_io.h

@@ -215,6 +215,40 @@ struct extent_changeset {
 	struct ulist range_changed;
 };
 
+static inline void extent_changeset_init(struct extent_changeset *changeset)
+{
+	changeset->bytes_changed = 0;
+	ulist_init(&changeset->range_changed);
+}
+
+static inline struct extent_changeset *extent_changeset_alloc(void)
+{
+	struct extent_changeset *ret;
+
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	extent_changeset_init(ret);
+	return ret;
+}
+
+static inline void extent_changeset_release(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	changeset->bytes_changed = 0;
+	ulist_release(&changeset->range_changed);
+}
+
+static inline void extent_changeset_free(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	extent_changeset_release(changeset);
+	kfree(changeset);
+}
+
 static inline void extent_set_compress_type(unsigned long *bio_flags,
 					    int compress_type)
 {

fs/btrfs/file.c

@@ -1581,6 +1581,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct page **pages = NULL;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 release_bytes = 0;
 	u64 lockstart;
 	u64 lockend;
@@ -1628,7 +1629,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
 
-		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
+		extent_changeset_release(data_reserved);
+		ret = btrfs_check_data_free_space(inode, &data_reserved, pos,
+						  write_bytes);
 		if (ret < 0) {
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
@@ -1802,6 +1805,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		}
 	}
 
+	extent_changeset_free(data_reserved);
 	return num_written ? num_written : ret;
 }
 
@@ -2772,6 +2776,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct falloc_range *range;
 	struct falloc_range *tmp;
 	struct list_head reserve_list;
@@ -2901,8 +2906,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 				free_extent_map(em);
 				break;
 			}
-			ret = btrfs_qgroup_reserve_data(inode, cur_offset,
-					last_byte - cur_offset);
+			ret = btrfs_qgroup_reserve_data(inode, &data_reserved,
+					cur_offset, last_byte - cur_offset);
 			if (ret < 0) {
 				free_extent_map(em);
 				break;
@@ -2974,6 +2979,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	if (ret != 0)
 		btrfs_free_reserved_data_space(inode, alloc_start,
 				       alloc_end - cur_offset);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 

fs/btrfs/inode-map.c

@@ -400,6 +400,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	struct btrfs_path *path;
 	struct inode *inode;
 	struct btrfs_block_rsv *rsv;
+	struct extent_changeset *data_reserved = NULL;
 	u64 num_bytes;
 	u64 alloc_hint = 0;
 	int ret;
@@ -492,7 +493,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_SIZE;
 
-	ret = btrfs_delalloc_reserve_space(inode, 0, prealloc);
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc);
 	if (ret)
 		goto out_put;
 
@@ -516,6 +517,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	trans->bytes_reserved = num_bytes;
 
 	btrfs_free_path(path);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 

fs/btrfs/inode.c

@@ -2037,6 +2037,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	struct btrfs_writepage_fixup *fixup;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct page *page;
 	struct inode *inode;
 	u64 page_start;
@@ -2074,7 +2075,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 		goto again;
 	}
 
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   PAGE_SIZE);
 	if (ret) {
 		mapping_set_error(page->mapping, ret);
@@ -2094,6 +2095,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
+	extent_changeset_free(data_reserved);
 }
 
 /*
@@ -4769,6 +4771,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
@@ -4783,7 +4786,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	    (!len || ((len & (blocksize - 1)) == 0)))
 		goto out;
 
-	ret = btrfs_delalloc_reserve_space(inode,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			round_down(from, blocksize), blocksize);
 	if (ret)
 		goto out;
@@ -4868,6 +4871,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	unlock_page(page);
 	put_page(page);
 out:
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -8718,6 +8722,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_data dio_data = { 0 };
+	struct extent_changeset *data_reserved = NULL;
 	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
 	int flags = 0;
@@ -8754,7 +8759,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			inode_unlock(inode);
 			relock = true;
 		}
-		ret = btrfs_delalloc_reserve_space(inode, offset, count);
+		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+						   offset, count);
 		if (ret)
 			goto out;
 		dio_data.outstanding_extents = count_max_extents(count);
@@ -8811,6 +8817,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (relock)
 		inode_lock(inode);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -9043,6 +9050,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	unsigned long zero_start;
 	loff_t size;
@@ -9068,7 +9076,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
 	 * end up waiting indefinitely to get a lock on the page currently
 	 * being processed by btrfs_page_mkwrite() function.
 	 */
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   reserved_space);
 	if (!ret) {
 		ret = file_update_time(vmf->vma->vm_file);
@@ -9174,13 +9182,15 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
 out_unlock:
 	if (!ret) {
 		sb_end_pagefault(inode->i_sb);
+		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
 	}
 	unlock_page(page);
 out:
 	btrfs_delalloc_release_space(inode, page_start, reserved_space);
 out_noreserve:
 	sb_end_pagefault(inode->i_sb);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 

fs/btrfs/ioctl.c

@@ -1127,6 +1127,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_io_tree *tree;
+	struct extent_changeset *data_reserved = NULL;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 
 	file_end = (isize - 1) >> PAGE_SHIFT;
@@ -1135,7 +1136,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
-	ret = btrfs_delalloc_reserve_space(inode,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
 	if (ret)
@@ -1247,6 +1248,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
+	extent_changeset_free(data_reserved);
 	return i_done;
 out:
 	for (i = 0; i < i_done; i++) {
@@ -1256,6 +1258,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	btrfs_delalloc_release_space(inode,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
+	extent_changeset_free(data_reserved);
 	return ret;
 
 }