Issuing metdata or otherwise shared IOs from !root cgroup can lead to
priority inversion. This patch ensures that those IOs are always
issued from the root cgroup.
v3: Dropped unnecessary btree_inode handling as suggested by David
Sterba.
v2: Fixed missing @bh in submit_bh_blkcg_css() call.
Signed-off-by: Tejun Heo <[email protected]>
Reviewed-by: Liu Bo <[email protected]>
Cc: David Sterba <[email protected]>
Cc: Chris Mason <[email protected]>
Cc: Josef Bacik <[email protected]>
---
fs/btrfs/check-integrity.c | 2 +-
fs/btrfs/disk-io.c | 4 ++++
fs/btrfs/ioctl.c | 4 ++++
3 files changed, 9 insertions(+), 1 deletion(-)
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2741,7 +2741,7 @@ int btrfsic_submit_bh(int op, int op_fla
struct btrfsic_dev_state *dev_state;
if (!btrfsic_is_initialized)
- return submit_bh(op, op_flags, bh);
+ return submit_bh_blkcg_css(op, op_flags, bh, blkcg_root_css);
mutex_lock(&btrfsic_mutex);
/* since btrfsic_submit_bh() might also be called before
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1025,6 +1025,8 @@ static blk_status_t btree_submit_bio_hoo
int async = check_async_write(bio_flags);
blk_status_t ret;
+ bio_associate_blkcg(bio, blkcg_root_css);
+
if (bio_op(bio) != REQ_OP_WRITE) {
/*
* called for a read, do the setup so that checksum validation
@@ -3512,6 +3514,8 @@ static void write_dev_flush(struct btrfs
return;
bio_reset(bio);
+ bio_associate_blkcg(bio, blkcg_root_css);
+
bio->bi_end_io = btrfs_end_empty_barrier;
bio_set_dev(bio, device->bdev);
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -150,6 +150,10 @@ void btrfs_update_iflags(struct inode *i
new_fl |= S_NOATIME;
if (ip->flags & BTRFS_INODE_DIRSYNC)
new_fl |= S_DIRSYNC;
+ /*
+ * The btree_inode will be always in the root cgroup. The cgroup
+ * writeback can be enabled on regular inodes selectively.
+ */
new_fl |= S_CGROUPWB;
set_mask_bits(&inode->i_flags,
