Btrfs: use REQ_CGROUP_PUNT for worker thread submitted bios

Async CRCs and compression submit IO through helper threads, which means
they have IO priority inversions when cgroup IO controllers are in use.

This flags all of the writes submitted by btrfs helper threads as
REQ_CGROUP_PUNT.  submit_bio() will punt these to dedicated per-blkcg
work items to avoid the priority inversion.

For the compression code, we take a reference on the wbc's blkg css and
pass it down to the async workers.

For the async CRCs, the bio already has the correct css, we just need to
tell the block layer to use REQ_CGROUP_PUNT.

Reviewed-by: Josef Bacik <[email protected]>
Signed-off-by: Chris Mason <[email protected]>
Modified-and-reviewed-by: Tejun Heo <[email protected]>
Signed-off-by: David Sterba <[email protected]>

fs/btrfs/compression.c

@@ -311,7 +311,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				 unsigned long compressed_len,
 				 struct page **compressed_pages,
 				 unsigned long nr_pages,
-				 unsigned int write_flags)
+				 unsigned int write_flags,
+				 struct cgroup_subsys_state *blkcg_css)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct bio *bio = NULL;
@@ -346,6 +347,11 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	bio->bi_opf = REQ_OP_WRITE | write_flags;
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
+
+	if (blkcg_css) {
+		bio->bi_opf |= REQ_CGROUP_PUNT;
+		bio_associate_blkg_from_css(bio, blkcg_css);
+	}
 	refcount_set(&cb->pending_bios, 1);
 
 	/* create and submit bios for the compressed pages */

fs/btrfs/compression.h

@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,
 				  unsigned long nr_pages,
-				  unsigned int write_flags);
+				  unsigned int write_flags,
+				  struct cgroup_subsys_state *blkcg_css);
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 

fs/btrfs/disk-io.c

@@ -791,6 +791,12 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
+	/*
+	 * All of the bios that pass through here are from async helpers.
+	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+	 * This changes nothing when cgroups aren't in use.
+	 */
+	async->bio->bi_opf |= REQ_CGROUP_PUNT;
 	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
 	if (ret) {
 		async->bio->bi_status = ret;

fs/btrfs/extent_io.c

@@ -4250,6 +4250,9 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,
+		/* We're called from an async helper function */
+		.punt_to_cgroup	= 1,
+		.no_cgroup_owner = 1,
 	};
 
 	while (start <= end) {

fs/btrfs/inode.c

@@ -368,6 +368,7 @@ struct async_chunk {
 	u64 end;
 	unsigned int write_flags;
 	struct list_head extents;
+	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
 	atomic_t *pending;
 };
@@ -880,7 +881,8 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages,
-				    async_chunk->write_flags)) {
+				    async_chunk->write_flags,
+				    async_chunk->blkcg_css)) {
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
 			const u64 end = start + async_extent->ram_size - 1;
@@ -1198,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
 	async_chunk = container_of(work, struct async_chunk, work);
 	if (async_chunk->inode)
 		btrfs_add_delayed_iput(async_chunk->inode);
+	if (async_chunk->blkcg_css)
+		css_put(async_chunk->blkcg_css);
 	/*
 	 * Since the pointer to 'pending' is at the beginning of the array of
 	 * async_chunk's, freeing it ensures the whole array has been freed.
@@ -1206,12 +1210,15 @@ static noinline void async_cow_free(struct btrfs_work *work)
 		kvfree(async_chunk->pending);
 }
 
-static int cow_file_range_async(struct inode *inode, struct page *locked_page,
+static int cow_file_range_async(struct inode *inode,
+				struct writeback_control *wbc,
+				struct page *locked_page,
 				u64 start, u64 end, int *page_started,
 				unsigned long *nr_written,
 				unsigned int write_flags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
 	struct async_cow *ctx;
 	struct async_chunk *async_chunk;
 	unsigned long nr_pages;
@@ -1279,12 +1286,30 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		 * to unlock it.
 		 */
 		if (locked_page) {
+			/*
+			 * Depending on the compressibility, the pages might or
+			 * might not go through async.  We want all of them to
+			 * be accounted against wbc once.  Let's do it here
+			 * before the paths diverge.  wbc accounting is used
+			 * only for foreign writeback detection and doesn't
+			 * need full accuracy.  Just account the whole thing
+			 * against the first page.
+			 */
+			wbc_account_cgroup_owner(wbc, locked_page,
+						 cur_end - start);
 			async_chunk[i].locked_page = locked_page;
 			locked_page = NULL;
 		} else {
 			async_chunk[i].locked_page = NULL;
 		}
 
+		if (blkcg_css != blkcg_root_css) {
+			css_get(blkcg_css);
+			async_chunk[i].blkcg_css = blkcg_css;
+		} else {
+			async_chunk[i].blkcg_css = NULL;
+		}
+
 		btrfs_init_work(&async_chunk[i].work, async_cow_start,
 				async_cow_submit, async_cow_free);
 
@@ -1727,7 +1752,7 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 	} else {
 		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 			&BTRFS_I(inode)->runtime_flags);
-		ret = cow_file_range_async(inode, locked_page, start, end,
+		ret = cow_file_range_async(inode, wbc, locked_page, start, end,
 					   page_started, nr_written,
 					   write_flags);
 	}