From: Ming Lei ming.lei@redhat.com
mainline inclusion from mainline-5.6-rc4 commit 01e99aeca3979600302913cef3f89076786f32c8 category: bugfix bugzilla: 42777 CVE: NA
---------------------------
For some reason, device may be in one situation which can't handle FS request, so STS_RESOURCE is always returned and the FS request will be added to hctx->dispatch. However passthrough request may be required at that time for fixing the problem. If passthrough request is added to scheduler queue, there isn't any chance for blk-mq to dispatch it given we prioritize requests in hctx->dispatch. Then the FS IO request may never be completed, and IO hang is caused.
So passthrough request has to be added to hctx->dispatch directly for fixing the IO hang.
Fix this issue by inserting passthrough request into hctx->dispatch directly together withing adding FS request to the tail of hctx->dispatch in blk_mq_dispatch_rq_list(). Actually we add FS request to tail of hctx->dispatch at default, see blk_mq_request_bypass_insert().
Then it becomes consistent with original legacy IO request path, in which passthrough request is always added to q->queue_head.
Cc: Dongli Zhang dongli.zhang@oracle.com Cc: Christoph Hellwig hch@infradead.org Cc: Ewan D. Milne emilne@redhat.com Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk
Conflicts: block/blk-flush.c block/blk-mq.c block/blk-mq-sched.c Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-flush.c | 2 +- block/blk-mq-sched.c | 22 +++++++++++++++------- block/blk-mq.c | 18 +++++++++++------- block/blk-mq.h | 3 ++- 4 files changed, 29 insertions(+), 16 deletions(-)
diff --git a/block/blk-flush.c b/block/blk-flush.c index 256fa1ccc2bd..2a8369eb6c1c 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -495,7 +495,7 @@ void blk_insert_flush(struct request *rq) if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { if (q->mq_ops) - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); else list_add_tail(&rq->queuelist, &q->queue_head); return; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index e98f51b86342..623c258d0b34 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -357,13 +357,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, bool has_sched, struct request *rq) { - /* dispatch flush rq directly */ - if (rq->rq_flags & RQF_FLUSH_SEQ) { - spin_lock(&hctx->lock); - list_add(&rq->queuelist, &hctx->dispatch); - spin_unlock(&hctx->lock); + /* + * dispatch flush and passthrough rq directly + * + * passthrough request has to be added to hctx->dispatch directly. + * For some reason, device may be in one situation which can't + * handle FS request, so STS_RESOURCE is always returned and the + * FS request will be added to hctx->dispatch. However passthrough + * request may be required at that time for fixing the problem. If + * passthrough request is added to scheduler queue, there isn't any + * chance to dispatch it given we prioritize requests in hctx->dispatch. + */ + if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq)) return true; - }
if (has_sched) rq->rq_flags |= RQF_SORTED; @@ -387,8 +393,10 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
WARN_ON(e && (rq->tag != -1));
- if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) + if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { + blk_mq_request_bypass_insert(rq, at_head, false); goto run; + }
if (e && e->type->ops.mq.insert_requests) { LIST_HEAD(list); diff --git a/block/blk-mq.c b/block/blk-mq.c index 59c92961cc20..a9138235b870 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -721,7 +721,7 @@ static void blk_mq_requeue_work(struct work_struct *work) * merge. */ if (rq->rq_flags & RQF_DONTPREP) - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); else blk_mq_sched_insert_request(rq, true, false, false); } @@ -1227,7 +1227,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bool needs_restart;
spin_lock(&hctx->lock); - list_splice_init(list, &hctx->dispatch); + list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock);
/* @@ -1590,13 +1590,17 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue) +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue) { struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
spin_lock(&hctx->lock); - list_add_tail(&rq->queuelist, &hctx->dispatch); + if (at_head) + list_add(&rq->queuelist, &hctx->dispatch); + else + list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock);
if (run_queue) @@ -1776,7 +1780,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (bypass_insert) return BLK_STS_RESOURCE;
- blk_mq_request_bypass_insert(rq, run_queue); + blk_mq_request_bypass_insert(rq, false, run_queue); return BLK_STS_OK; }
@@ -1792,7 +1796,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) - blk_mq_request_bypass_insert(rq, true); + blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) blk_mq_end_request(rq, ret);
@@ -1827,7 +1831,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, if (ret != BLK_STS_OK) { if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { - blk_mq_request_bypass_insert(rq, + blk_mq_request_bypass_insert(rq, false, list_empty(list)); break; } diff --git a/block/blk-mq.h b/block/blk-mq.h index a6094c27b827..debc646e1bed 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -64,7 +64,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue); +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list);
From: John Garry john.garry@huawei.com
mainline inclusion from mainline-5.7-rc2 commit 5fe56de799ad03e92d794c7936bf363922b571df category: bugfix bugzilla: 42779 CVE: NA
---------------------------
If in blk_mq_dispatch_rq_list() we find no budget, then we break of the dispatch loop, but the request may keep the driver tag, evaulated in 'nxt' in the previous loop iteration.
Fix by putting the driver tag for that request.
Reviewed-by: Ming Lei ming.lei@redhat.com Signed-off-by: John Garry john.garry@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk
Conflict: block/blk-mq.c Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-mq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c index a9138235b870..fa77ce3ff692 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1154,8 +1154,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, rq = list_first_entry(list, struct request, queuelist);
hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu); - if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) + if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { + blk_mq_put_driver_tag(rq); break; + }
if (!blk_mq_get_driver_tag(rq)) { /*
From: Douglas Anderson dianders@chromium.org
mainline inclusion from mainline-5.8-rc1 commit ab3cee3762e5e69f27c302c43691289fdfc12316 category: bugfix bugzilla: 42780 CVE: NA
---------------------------
In blk_mq_dispatch_rq_list(), if blk_mq_sched_needs_restart() returns true and the driver returns BLK_STS_RESOURCE then we'll kick the queue. However, there's another case where we might need to kick it. If we were unable to get budget we can be in much the same state as when the driver returns BLK_STS_RESOURCE, so we should treat it the same.
It should be noted that even if we add a whole bunch of extra kicking to the queue in other patches this patch is still important. Specifically any kicking that happened before we re-spliced leftover requests into 'hctx->dispatch' wouldn't have found any work, so we really need to make sure we kick ourselves after we've done the splicing.
Signed-off-by: Douglas Anderson dianders@chromium.org Reviewed-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-mq.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c index fa77ce3ff692..99806b1da1de 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1138,6 +1138,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bool no_tag = false; int errors, queued; blk_status_t ret = BLK_STS_OK; + bool no_budget_avail = false;
if (list_empty(list)) return false; @@ -1156,6 +1157,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu); if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { blk_mq_put_driver_tag(rq); + no_budget_avail = true; break; }
@@ -1263,13 +1265,15 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls - * that could otherwise occur if the queue is idle. + * that could otherwise occur if the queue is idle. We'll do + * similar if we couldn't get budget and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); - else if (needs_restart && (ret == BLK_STS_RESOURCE)) + else if (needs_restart && (ret == BLK_STS_RESOURCE || + no_budget_avail)) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
From: Douglas Anderson dianders@chromium.org
mainline inclusion from mainline-5.8-rc1 commit b9151e7bca82a17ff7aa442a168e0f924a07443c category: bugfix bugzilla: 42781 CVE: NA
---------------------------
We have: * blk_mq_run_hw_queue() * blk_mq_delay_run_hw_queue() * blk_mq_run_hw_queues()
...but not blk_mq_delay_run_hw_queues(), presumably because nobody needed it before now. Since we need it for a later patch in this series, add it.
Signed-off-by: Douglas Anderson dianders@chromium.org Reviewed-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-mq.c | 19 +++++++++++++++++++ include/linux/blk-mq.h | 1 + 2 files changed, 20 insertions(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c index 99806b1da1de..7f5360949509 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1456,6 +1456,25 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async) } EXPORT_SYMBOL(blk_mq_run_hw_queues);
+/** + * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. + * @q: Pointer to the request queue to run. + * @msecs: Microseconds of delay to wait before running the queues. + */ +void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) +{ + struct blk_mq_hw_ctx *hctx; + int i; + + queue_for_each_hw_ctx(q, hctx, i) { + if (blk_mq_hctx_stopped(hctx)) + continue; + + blk_mq_delay_run_hw_queue(hctx, msecs); + } +} +EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); + /** * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped * @q: request queue. diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 149d4113e5d6..4878d8ed4914 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -312,6 +312,7 @@ void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); +void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q);
From: Douglas Anderson dianders@chromium.org
mainline inclusion from mainline-5.8-rc1 commit a0823421a4d7264fc91c7b3769612331493cec1b category: bugfix bugzilla: 42781 CVE: NA
---------------------------
If ever a thread running blk-mq code tries to get budget and fails it immediately stops doing work and assumes that whenever budget is freed up that queues will be kicked and whatever work the thread was trying to do will be tried again.
One path where budget is freed and queues are kicked in the normal case can be seen in scsi_finish_command(). Specifically: - scsi_finish_command() - scsi_device_unbusy() - # Decrement "device_busy", AKA release budget - scsi_io_completion() - scsi_end_request() - blk_mq_run_hw_queues()
The above is all well and good. The problem comes up when a thread claims the budget but then releases it without actually dispatching any work. Since we didn't schedule any work we'll never run the path of finishing work / kicking the queues.
This isn't often actually a problem which is why this issue has existed for a while and nobody noticed. Specifically we only get into this situation when we unexpectedly found that we weren't going to do any work. Code that later receives new work kicks the queues. All good, right?
The problem shows up, however, if timing is just wrong and we hit a race. To see this race let's think about the case where we only have a budget of 1 (only one thread can hold budget). Now imagine that a thread got budget and then decided not to dispatch work. It's about to call put_budget() but then the thread gets context switched out for a long, long time. While in this state, any and all kicks of the queue (like the when we received new work) will be no-ops because nobody can get budget. Finally the thread holding budget gets to run again and returns. All the normal kicks will have been no-ops and we have an I/O stall.
As you can see from the above, you need just the right timing to see the race. To start with, the only case it happens if we thought we had work, actually managed to get the budget, but then actually didn't have work. That's pretty rare to start with. Even then, there's usually a very small amount of time between realizing that there's no work and putting the budget. During this small amount of time new work has to come in and the queue kick has to make it all the way to trying to get the budget and fail. It's pretty unlikely.
One case where this could have failed is illustrated by an example of threads running blk_mq_do_dispatch_sched():
* Threads A and B both run has_work() at the same time with the same "hctx". Imagine has_work() is exact. There's no lock, so it's OK if Thread A and B both get back true. * Thread B gets interrupted for a long time right after it decides that there is work. Maybe its CPU gets an interrupt and the interrupt handler is slow. * Thread A runs, get budget, dispatches work. * Thread A's work finishes and budget is released. * Thread B finally runs again and gets budget. * Since Thread A already took care of the work and no new work has come in, Thread B will get NULL from dispatch_request(). I believe this is specifically why dispatch_request() is allowed to return NULL in the first place if has_work() must be exact. * Thread B will now be holding the budget and is about to call put_budget(), but hasn't called it yet. * Thread B gets interrupted for a long time (again). Dang interrupts. * Now Thread C (maybe with a different "hctx" but the same queue) comes along and runs blk_mq_do_dispatch_sched(). * Thread C won't do anything because it can't get budget. * Finally Thread B will run again and put the budget without kicking any queues.
Even though the example above is with blk_mq_do_dispatch_sched() I believe the race is possible any time someone is holding budget but doesn't do work.
Unfortunately, the unlikely has become more likely if you happen to be using the BFQ I/O scheduler. BFQ, by design, sometimes returns "true" for has_work() but then NULL for dispatch_request() and stays in this state for a while (currently up to 9 ms). Suddenly you only need one race to hit, not two races in a row. With my current setup this is easy to reproduce in reboot tests and traces have actually shown that we hit a race similar to the one described above.
Note that we only need to fix blk_mq_do_dispatch_sched() and blk_mq_do_dispatch_ctx() and not the other places that put budget. In other cases we know that we have work to do on at least one "hctx" and code already exists to kick that "hctx"'s queue. When that work finally finishes all the queues will be kicked using the normal flow.
One last note is that (at least in the SCSI case) budget is shared by all "hctx"s that have the same queue. Thus we need to make sure to kick the whole queue, not just re-run dispatching on a single "hctx".
Signed-off-by: Douglas Anderson dianders@chromium.org Reviewed-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-mq-sched.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 623c258d0b34..56368f1934aa 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -81,6 +81,8 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) blk_mq_run_hw_queue(hctx, true); }
+#define BLK_MQ_BUDGET_DELAY 3 /* ms units */ + /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to @@ -105,6 +107,14 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) rq = e->type->ops.mq.dispatch_request(hctx); if (!rq) { blk_mq_put_dispatch_budget(hctx); + /* + * We're releasing without dispatching. Holding the + * budget could have blocked any "hctx"s with the + * same queue and if we didn't dispatch then there's + * no guarantee anyone will kick the queue. Kick it + * ourselves. + */ + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; }
@@ -151,6 +161,14 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { blk_mq_put_dispatch_budget(hctx); + /* + * We're releasing without dispatching. Holding the + * budget could have blocked any "hctx"s with the + * same queue and if we didn't dispatch then there's + * no guarantee anyone will kick the queue. Kick it + * ourselves. + */ + blk_mq_delay_run_hw_queues(q, BLK_MQ_BUDGET_DELAY); break; }
From: Ming Lei ming.lei@redhat.com
mainline inclusion from mainline-5.6-rc6 commit cc3200eac4c5eb11c3f34848a014d1f286316310 category: bugfix bugzilla: 42777 CVE: NA
---------------------------
commit 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly") may change to add flush request to the tail of dispatch by applying the 'add_head' parameter of blk_mq_sched_insert_request.
Turns out this way causes performance regression on NCQ controller because flush is non-NCQ command, which can't be queued when there is any in-flight NCQ command. When adding flush rq to the front of hctx->dispatch, it is easier to introduce extra time to flush rq's latency compared with adding to the tail of dispatch queue because of S_SCHED_RESTART, then chance of flush merge is increased, and less flush requests may be issued to controller.
So always insert flush request to the front of dispatch queue just like before applying commit 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly").
Cc: Damien Le Moal Damien.LeMoal@wdc.com Cc: Shinichiro Kawasaki shinichiro.kawasaki@wdc.com Reported-by: Shinichiro Kawasaki shinichiro.kawasaki@wdc.com Fixes: 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly") Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Yufen Yu yuyufen@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- block/blk-mq-sched.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 56368f1934aa..ce4b2ac6d697 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -412,6 +412,28 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, WARN_ON(e && (rq->tag != -1));
if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { + /* + * Firstly normal IO request is inserted to scheduler queue or + * sw queue, meantime we add flush request to dispatch queue( + * hctx->dispatch) directly and there is at most one in-flight + * flush request for each hw queue, so it doesn't matter to add + * flush request to tail or front of the dispatch queue. + * + * Secondly in case of NCQ, flush request belongs to non-NCQ + * command, and queueing it will fail when there is any + * in-flight normal IO request(NCQ command). When adding flush + * rq to the front of hctx->dispatch, it is easier to introduce + * extra time to flush rq's latency because of S_SCHED_RESTART + * compared with adding to the tail of dispatch queue, then + * chance of flush merge is increased, and less flush requests + * will be issued to controller. It is observed that ~10% time + * is saved in blktests block/004 on disk attached to AHCI/NCQ + * drive when adding flush rq to the front of hctx->dispatch. + * + * Simply queue flush rq to the front of hctx->dispatch so that + * intensive flush workloads can benefit in case of NCQ HW. + */ + at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head; blk_mq_request_bypass_insert(rq, at_head, false); goto run; }