From: Yang Yang yang.yang@vivo.com
mainline inclusion from mainline-5.12-rc1 commit ffa772cfe9356ce94d3061335c2681f60e7c1c5b category: bugfix bugzilla: 182133 CVE: NA
-------------------------------------------------
Hang occurs when user changes the scheduler queue depth, by writing to the 'nr_requests' sysfs file of that device.
The details of the environment that we found the problem are as follows: an eMMC block device total driver tags: 16 default queue_depth: 32 kqd->async_depth initialized in kyber_init_sched() with queue_depth=32
Then we change queue_depth to 256, by writing to the 'nr_requests' sysfs file. But kqd->async_depth don't be updated after queue_depth changes. Now the value of async depth is too small for queue_depth=256, this may cause hang.
This patch introduces kyber_depth_updated(), so that kyber can update async depth when queue depth changes.
Signed-off-by: Yang Yang yang.yang@vivo.com Reviewed-by: Omar Sandoval osandov@fb.com Signed-off-by: Jens Axboe axboe@kernel.dk
Conflict: block/kyber-iosched.c Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/kyber-iosched.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index a1660bafc9124..9eeb60d97f0ca 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -288,15 +288,6 @@ static void kyber_stat_timer_fn(struct blk_stat_callback *cb) blk_stat_activate_msecs(kqd->cb, 100); }
-static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd) -{ - /* - * All of the hardware queues have the same depth, so we can just grab - * the shift of the first one. - */ - return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift; -} - static int kyber_bucket_fn(const struct request *rq) { return kyber_sched_domain(rq->cmd_flags); @@ -306,7 +297,6 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) { struct kyber_queue_data *kqd; unsigned int max_tokens; - unsigned int shift; int ret = -ENOMEM; int i;
@@ -341,9 +331,6 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) sbitmap_queue_resize(&kqd->domain_tokens[i], kyber_depth[i]); }
- shift = kyber_sched_tags_shift(kqd); - kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; - kqd->read_lat_nsec = 2000000ULL; kqd->write_lat_nsec = 10000000ULL;
@@ -403,9 +390,19 @@ static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq) INIT_LIST_HEAD(&kcq->rq_list[i]); }
-static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx) { struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + unsigned int shift = tags->bitmap_tags.sb.shift; + + kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; + + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth); +} + +static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +{ struct kyber_hctx_data *khd; int i;
@@ -446,8 +443,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) khd->batching = 0;
hctx->sched_data = khd; - sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags, - kqd->async_depth); + kyber_depth_updated(hctx);
return 0;
@@ -966,6 +962,7 @@ static struct elevator_type kyber_sched = { .completed_request = kyber_completed_request, .dispatch_request = kyber_dispatch_request, .has_work = kyber_has_work, + .depth_updated = kyber_depth_updated, }, .uses_mq = true, #ifdef CONFIG_BLK_DEBUG_FS
From: Yu Kuai yukuai3@huawei.com
hulk inclusion category: bugfix bugzilla: 182133 CVE: NA
-------------------------------------------------
After introducing kyber_depth_updated(), the intialization of 'async_depth' is moved from kyber_init_sched() to kyber_init_hctx(), which leave a window for user to read uninitilized 'async_depth' through debugfs.
Thus initialize 'async_depth' to zero in kyber_queue_data_alloc() to fix the problem.
Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Hou Tao houtao1@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/kyber-iosched.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 9eeb60d97f0ca..d8f3cb1bffa61 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -333,6 +333,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
kqd->read_lat_nsec = 2000000ULL; kqd->write_lat_nsec = 10000000ULL; + kqd->async_depth = 0;
return kqd;