6.16-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nilay Shroff nilay@linux.ibm.com
[ Upstream commit 370ac285f23aecae40600851fb4a1a9e75e50973 ]
A recent lockdep[1] splat observed while running blktest block/005 reveals a potential deadlock caused by the cpu_hotplug_lock dependency on ->freeze_lock. This dependency was introduced by commit 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key").
That change added a static key to avoid fetching q->rq_qos when neither blk-wbt nor blk-iolatency is configured. The static key dynamically patches kernel text to a NOP when disabled, eliminating overhead of fetching q->rq_qos in the I/O hot path. However, enabling a static key at runtime requires acquiring both cpu_hotplug_lock and jump_label_mutex. When this happens after the queue has already been frozen (i.e., while holding ->freeze_lock), it creates a locking dependency from cpu_hotplug_lock to ->freeze_lock, which leads to a potential deadlock reported by lockdep [1].
To resolve this, replace the static key mechanism with q->queue_flags: QUEUE_FLAG_QOS_ENABLED. This flag is evaluated in the fast path before accessing q->rq_qos. If the flag is set, we proceed to fetch q->rq_qos; otherwise, the access is skipped.
Since q->queue_flags is commonly accessed in IO hotpath and resides in the first cacheline of struct request_queue, checking it imposes minimal overhead while eliminating the deadlock risk.
This change avoids the lockdep splat without introducing performance regressions.
[1] https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vp...
Reported-by: Shinichiro Kawasaki shinichiro.kawasaki@wdc.com Closes: https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vp... Fixes: 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key") Tested-by: Shin'ichiro Kawasaki shinichiro.kawasaki@wdc.com Signed-off-by: Nilay Shroff nilay@linux.ibm.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20250814082612.500845-4-nilay@linux.ibm.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq-debugfs.c | 1 + block/blk-rq-qos.c | 9 ++++--- block/blk-rq-qos.h | 54 ++++++++++++++++++++++++------------------ include/linux/blkdev.h | 1 + 4 files changed, 37 insertions(+), 28 deletions(-)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 29b3540dd180..bdcb27ab5606 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(SQ_SCHED), QUEUE_FLAG_NAME(DISABLE_WBT_DEF), QUEUE_FLAG_NAME(NO_ELV_SWITCH), + QUEUE_FLAG_NAME(QOS_ENABLED), }; #undef QUEUE_FLAG_NAME
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index b1e24bb85ad2..654478dfbc20 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -2,8 +2,6 @@
#include "blk-rq-qos.h"
-__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos); - /* * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, * false if 'v' + 1 would be bigger than 'below'. @@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q) struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); - static_branch_dec(&block_rq_qos); } + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); mutex_unlock(&q->rq_qos_mutex); }
@@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - static_branch_inc(&block_rq_qos); + blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q);
blk_mq_unfreeze_queue(q, memflags);
@@ -374,10 +372,11 @@ void rq_qos_del(struct rq_qos *rqos) for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; - static_branch_dec(&block_rq_qos); break; } } + if (!q->rq_qos) + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags);
mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 28125fc49eff..1fe22000a379 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -12,7 +12,6 @@ #include "blk-mq-debugfs.h"
struct blk_mq_debugfs_attr; -extern struct static_key_false block_rq_qos;
enum rq_qos_id { RQ_QOS_WBT, @@ -113,49 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); }
static inline void rq_qos_done(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos && - !blk_rq_is_passthrough(rq)) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); }
static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_issue(q->rq_qos, rq); }
static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); }
static inline void rq_qos_done_bio(struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && - bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) || - bio_flagged(bio, BIO_QOS_MERGED))) { - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - - /* - * If a bio has BIO_QOS_xxx set, it implicitly implies that - * q->rq_qos is present. So, we skip re-checking q->rq_qos - * here as an extra optimization and directly call - * __rq_qos_done_bio(). - */ - __rq_qos_done_bio(q->rq_qos, bio); - } + struct request_queue *q; + + if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) && + !bio_flagged(bio, BIO_QOS_MERGED))) + return; + + q = bdev_get_queue(bio->bi_bdev); + + /* + * If a bio has BIO_QOS_xxx set, it implicitly implies that + * q->rq_qos is present. So, we skip re-checking q->rq_qos + * here as an extra optimization and directly call + * __rq_qos_done_bio(). + */ + __rq_qos_done_bio(q->rq_qos, bio); }
static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } @@ -164,14 +169,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); }
static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } @@ -179,7 +186,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
static inline void rq_qos_queue_depth_changed(struct request_queue *q) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 620345ce3aaa..3921188c9e13 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -652,6 +652,7 @@ enum { QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ + QUEUE_FLAG_QOS_ENABLED, /* qos is enabled */ QUEUE_FLAG_MAX };