--- /dev/null
+From 09f871868080c33992cd6a9b72a5ca49582578fa Mon Sep 17 00:00:00 2001
+From: Jan Kara <jack@suse.cz>
+Date: Fri, 1 Apr 2022 12:27:48 +0200
+Subject: bfq: Track whether bfq_group is still online
+
+From: Jan Kara <jack@suse.cz>
+
+commit 09f871868080c33992cd6a9b72a5ca49582578fa upstream.
+
+Track whether bfq_group is still online. We cannot rely on
+blkcg_gq->online because that gets cleared only after all policies are
+offlined and we need something that gets updated already under
+bfqd->lock when we are cleaning up our bfq_group to be able to guarantee
+that when we see online bfq_group, it will stay online while we are
+holding bfqd->lock lock.
+
+CC: stable@vger.kernel.org
+Tested-by: "yukuai (C)" <yukuai3@huawei.com>
+Signed-off-by: Jan Kara <jack@suse.cz>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Link: https://lore.kernel.org/r/20220401102752.8599-7-jack@suse.cz
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/bfq-cgroup.c | 3 ++-
+ block/bfq-iosched.h | 2 ++
+ 2 files changed, 4 insertions(+), 1 deletion(-)
+
+--- a/block/bfq-cgroup.c
++++ b/block/bfq-cgroup.c
+@@ -442,6 +442,7 @@ static void bfq_pd_init(struct blkg_poli
+ */
+ bfqg->bfqd = bfqd;
+ bfqg->active_entities = 0;
++ bfqg->online = true;
+ bfqg->rq_pos_tree = RB_ROOT;
+ }
+
+@@ -488,7 +489,6 @@ struct bfq_group *bfq_find_set_group(str
+ struct bfq_entity *entity;
+
+ bfqg = bfq_lookup_bfqg(bfqd, blkcg);
+-
+ if (unlikely(!bfqg))
+ return NULL;
+
+@@ -788,6 +788,7 @@ static void bfq_pd_offline(struct blkg_p
+
+ put_async_queues:
+ bfq_put_async_queues(bfqd, bfqg);
++ bfqg->online = false;
+
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ /*
+--- a/block/bfq-iosched.h
++++ b/block/bfq-iosched.h
+@@ -776,6 +776,8 @@ struct bfq_group {
+
+ /* reference counter (see comments in bfq_bic_update_cgroup) */
+ int ref;
++ /* Is bfq_group still online? */
++ bool online;
+
+ struct bfq_entity entity;
+ struct bfq_sched_data sched_data;
--- /dev/null
+From ea591cd4eb270393810e7be01feb8fde6a34fbbe Mon Sep 17 00:00:00 2001
+From: Jan Kara <jack@suse.cz>
+Date: Fri, 1 Apr 2022 12:27:45 +0200
+Subject: bfq: Update cgroup information before merging bio
+
+From: Jan Kara <jack@suse.cz>
+
+commit ea591cd4eb270393810e7be01feb8fde6a34fbbe upstream.
+
+When the process is migrated to a different cgroup (or in case of
+writeback just starts submitting bios associated with a different
+cgroup) bfq_merge_bio() can operate with stale cgroup information in
+bic. Thus the bio can be merged to a request from a different cgroup or
+it can result in merging of bfqqs for different cgroups or bfqqs of
+already dead cgroups and causing possible use-after-free issues. Fix the
+problem by updating cgroup information in bfq_merge_bio().
+
+CC: stable@vger.kernel.org
+Fixes: e21b7a0b9887 ("block, bfq: add full hierarchical scheduling and cgroups support")
+Tested-by: "yukuai (C)" <yukuai3@huawei.com>
+Signed-off-by: Jan Kara <jack@suse.cz>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Link: https://lore.kernel.org/r/20220401102752.8599-4-jack@suse.cz
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/bfq-iosched.c | 11 +++++++++--
+ 1 file changed, 9 insertions(+), 2 deletions(-)
+
+--- a/block/bfq-iosched.c
++++ b/block/bfq-iosched.c
+@@ -1638,10 +1638,17 @@ static bool bfq_bio_merge(struct blk_mq_
+
+ spin_lock_irq(&bfqd->lock);
+
+- if (bic)
++ if (bic) {
++ /*
++ * Make sure cgroup info is uptodate for current process before
++ * considering the merge.
++ */
++ bfq_bic_update_cgroup(bic, bio);
++
+ bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+- else
++ } else {
+ bfqd->bio_bfqq = NULL;
++ }
+ bfqd->bio_bic = bic;
+
+ ret = blk_mq_sched_try_merge(q, bio, &free);
--- /dev/null
+From 68f4c6eba70df70a720188bce95c85570ddfcc87 Mon Sep 17 00:00:00 2001
+From: Zhihao Cheng <chengzhihao1@huawei.com>
+Date: Tue, 10 May 2022 21:38:05 +0800
+Subject: fs-writeback: writeback_sb_inodes：Recalculate 'wrote' according skipped pages
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Zhihao Cheng <chengzhihao1@huawei.com>
+
+commit 68f4c6eba70df70a720188bce95c85570ddfcc87 upstream.
+
+Commit 505a666ee3fc ("writeback: plug writeback in wb_writeback() and
+writeback_inodes_wb()") has us holding a plug during wb_writeback, which
+may cause a potential ABBA dead lock:
+
+ wb_writeback fat_file_fsync
+blk_start_plug(&plug)
+for (;;) {
+ iter i-1: some reqs have been added into plug->mq_list // LOCK A
+ iter i:
+ progress = __writeback_inodes_wb(wb, work)
+ . writeback_sb_inodes // fat's bdev
+ . __writeback_single_inode
+ . . generic_writepages
+ . . __block_write_full_page
+ . . . . __generic_file_fsync
+ . . . . sync_inode_metadata
+ . . . . writeback_single_inode
+ . . . . __writeback_single_inode
+ . . . . fat_write_inode
+ . . . . __fat_write_inode
+ . . . . sync_dirty_buffer // fat's bdev
+ . . . . lock_buffer(bh) // LOCK B
+ . . . . submit_bh
+ . . . . blk_mq_get_tag // LOCK A
+ . . . trylock_buffer(bh) // LOCK B
+ . . . redirty_page_for_writepage
+ . . . wbc->pages_skipped++
+ . . --wbc->nr_to_write
+ . wrote += write_chunk - wbc.nr_to_write // wrote > 0
+ . requeue_inode
+ . redirty_tail_locked
+ if (progress) // progress > 0
+ continue;
+ iter i+1:
+ queue_io
+ // similar process with iter i, infinite for-loop !
+}
+blk_finish_plug(&plug) // flush plug won't be called
+
+Above process triggers a hungtask like:
+[ 399.044861] INFO: task bb:2607 blocked for more than 30 seconds.
+[ 399.046824] Not tainted 5.18.0-rc1-00005-gefae4d9eb6a2-dirty
+[ 399.051539] task:bb state:D stack: 0 pid: 2607 ppid:
+2426 flags:0x00004000
+[ 399.051556] Call Trace:
+[ 399.051570] __schedule+0x480/0x1050
+[ 399.051592] schedule+0x92/0x1a0
+[ 399.051602] io_schedule+0x22/0x50
+[ 399.051613] blk_mq_get_tag+0x1d3/0x3c0
+[ 399.051640] __blk_mq_alloc_requests+0x21d/0x3f0
+[ 399.051657] blk_mq_submit_bio+0x68d/0xca0
+[ 399.051674] __submit_bio+0x1b5/0x2d0
+[ 399.051708] submit_bio_noacct+0x34e/0x720
+[ 399.051718] submit_bio+0x3b/0x150
+[ 399.051725] submit_bh_wbc+0x161/0x230
+[ 399.051734] __sync_dirty_buffer+0xd1/0x420
+[ 399.051744] sync_dirty_buffer+0x17/0x20
+[ 399.051750] __fat_write_inode+0x289/0x310
+[ 399.051766] fat_write_inode+0x2a/0xa0
+[ 399.051783] __writeback_single_inode+0x53c/0x6f0
+[ 399.051795] writeback_single_inode+0x145/0x200
+[ 399.051803] sync_inode_metadata+0x45/0x70
+[ 399.051856] __generic_file_fsync+0xa3/0x150
+[ 399.051880] fat_file_fsync+0x1d/0x80
+[ 399.051895] vfs_fsync_range+0x40/0xb0
+[ 399.051929] __x64_sys_fsync+0x18/0x30
+
+In my test, 'need_resched()' (which is imported by 590dca3a71 "fs-writeback:
+unplug before cond_resched in writeback_sb_inodes") in function
+'writeback_sb_inodes()' seldom comes true, unless cond_resched() is deleted
+from write_cache_pages().
+
+Fix it by correcting wrote number according number of skipped pages
+in writeback_sb_inodes().
+
+Goto Link to find a reproducer.
+
+Link: https://bugzilla.kernel.org/show_bug.cgi?id=215837
+Cc: stable@vger.kernel.org # v4.3
+Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
+Reviewed-by: Jan Kara <jack@suse.cz>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Link: https://lore.kernel.org/r/20220510133805.1988292-1-chengzhihao1@huawei.com
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/fs-writeback.c | 13 ++++++++-----
+ 1 file changed, 8 insertions(+), 5 deletions(-)
+
+--- a/fs/fs-writeback.c
++++ b/fs/fs-writeback.c
+@@ -1565,11 +1565,12 @@ static long writeback_sb_inodes(struct s
+ };
+ unsigned long start_time = jiffies;
+ long write_chunk;
+- long wrote = 0; /* count both pages and inodes */
++ long total_wrote = 0; /* count both pages and inodes */
+
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = wb_inode(wb->b_io.prev);
+ struct bdi_writeback *tmp_wb;
++ long wrote;
+
+ if (inode->i_sb != sb) {
+ if (work->sb) {
+@@ -1645,7 +1646,9 @@ static long writeback_sb_inodes(struct s
+
+ wbc_detach_inode(&wbc);
+ work->nr_pages -= write_chunk - wbc.nr_to_write;
+- wrote += write_chunk - wbc.nr_to_write;
++ wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped;
++ wrote = wrote < 0 ? 0 : wrote;
++ total_wrote += wrote;
+
+ if (need_resched()) {
+ /*
+@@ -1667,7 +1670,7 @@ static long writeback_sb_inodes(struct s
+ tmp_wb = inode_to_wb_and_lock_list(inode);
+ spin_lock(&inode->i_lock);
+ if (!(inode->i_state & I_DIRTY_ALL))
+- wrote++;
++ total_wrote++;
+ requeue_inode(inode, tmp_wb, &wbc);
+ inode_sync_complete(inode);
+ spin_unlock(&inode->i_lock);
+@@ -1681,14 +1684,14 @@ static long writeback_sb_inodes(struct s
+ * bail out to wb_writeback() often enough to check
+ * background threshold and other termination conditions.
+ */
+- if (wrote) {
++ if (total_wrote) {
+ if (time_is_before_jiffies(start_time + HZ / 10UL))
+ break;
+ if (work->nr_pages <= 0)
+ break;
+ }
+ }
+- return wrote;
++ return total_wrote;
+ }
+
+ static long __writeback_inodes_wb(struct bdi_writeback *wb,
projects / thirdparty / kernel / stable-queue.git / commitdiff
