From 7f90d45e57cb2ef1f0adcaf925ddffdfc5e680ca Mon Sep 17 00:00:00 2001 From: Justin Sanders Date: Tue, 10 Jun 2025 17:05:59 +0000 Subject: [PATCH 1/3] aoe: clean device rq_list in aoedev_downdev() An aoe device's rq_list contains accepted block requests that are waiting to be transmitted to the aoe target. This queue was added as part of the conversion to blk_mq. However, the queue was not cleaned out when an aoe device is downed which caused blk_mq_freeze_queue() to sleep indefinitely waiting for those requests to complete, causing a hang. This fix cleans out the queue before calling blk_mq_freeze_queue(). Link: https://bugzilla.kernel.org/show_bug.cgi?id=212665 Fixes: 3582dd291788 ("aoe: convert aoeblk to blk-mq") Signed-off-by: Justin Sanders Link: https://lore.kernel.org/r/20250610170600.869-1-jsanders.devel@gmail.com Tested-By: Valentin Kleibel Signed-off-by: Jens Axboe --- drivers/block/aoe/aoedev.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index 141b2a0e03f2..8c18034cb3d6 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -198,6 +198,7 @@ aoedev_downdev(struct aoedev *d) { struct aoetgt *t, **tt, **te; struct list_head *head, *pos, *nx; + struct request *rq, *rqnext; int i; d->flags &= ~DEVFL_UP; @@ -223,6 +224,13 @@ aoedev_downdev(struct aoedev *d) /* clean out the in-process request (if any) */ aoe_failip(d); + /* clean out any queued block requests */ + list_for_each_entry_safe(rq, rqnext, &d->rq_list, queuelist) { + list_del_init(&rq->queuelist); + blk_mq_start_request(rq); + blk_mq_end_request(rq, BLK_STS_IOERR); + } + /* fast fail all pending I/O */ if (d->blkq) { /* UP is cleared, freeze+quiesce to insure all are errored */ From cffc873d68ab09a0432b8212008c5613f8a70a2c Mon Sep 17 00:00:00 2001 From: Justin Sanders Date: Tue, 10 Jun 2025 17:06:00 +0000 Subject: [PATCH 2/3] aoe: defer rexmit timer downdev work to workqueue When aoe's rexmit_timer() notices that an aoe target fails to respond to commands for more than aoe_deadsecs, it calls aoedev_downdev() which cleans the outstanding aoe and block queues. This can involve sleeping, such as in blk_mq_freeze_queue(), which should not occur in irq context. This patch defers that aoedev_downdev() call to the aoe device's workqueue. Link: https://bugzilla.kernel.org/show_bug.cgi?id=212665 Signed-off-by: Justin Sanders Link: https://lore.kernel.org/r/20250610170600.869-2-jsanders.devel@gmail.com Tested-By: Valentin Kleibel Signed-off-by: Jens Axboe --- drivers/block/aoe/aoe.h | 1 + drivers/block/aoe/aoecmd.c | 8 ++++++-- drivers/block/aoe/aoedev.c | 5 ++++- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h index 749ae1246f4c..d35caa3c69e1 100644 --- a/drivers/block/aoe/aoe.h +++ b/drivers/block/aoe/aoe.h @@ -80,6 +80,7 @@ enum { DEVFL_NEWSIZE = (1<<6), /* need to update dev size in block layer */ DEVFL_FREEING = (1<<7), /* set when device is being cleaned up */ DEVFL_FREED = (1<<8), /* device has been cleaned up */ + DEVFL_DEAD = (1<<9), /* device has timed out of aoe_deadsecs */ }; enum { diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 92b06d1de4cc..6c94cfd1c480 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -754,7 +754,7 @@ rexmit_timer(struct timer_list *timer) utgts = count_targets(d, NULL); - if (d->flags & DEVFL_TKILL) { + if (d->flags & (DEVFL_TKILL | DEVFL_DEAD)) { spin_unlock_irqrestore(&d->lock, flags); return; } @@ -786,7 +786,8 @@ rexmit_timer(struct timer_list *timer) * to clean up. */ list_splice(&flist, &d->factive[0]); - aoedev_downdev(d); + d->flags |= DEVFL_DEAD; + queue_work(aoe_wq, &d->work); goto out; } @@ -898,6 +899,9 @@ aoecmd_sleepwork(struct work_struct *work) { struct aoedev *d = container_of(work, struct aoedev, work); + if (d->flags & DEVFL_DEAD) + aoedev_downdev(d); + if (d->flags & DEVFL_GDALLOC) aoeblk_gdalloc(d); diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index 8c18034cb3d6..9b66f8ebce50 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -200,8 +200,11 @@ aoedev_downdev(struct aoedev *d) struct list_head *head, *pos, *nx; struct request *rq, *rqnext; int i; + unsigned long flags; - d->flags &= ~DEVFL_UP; + spin_lock_irqsave(&d->lock, flags); + d->flags &= ~(DEVFL_UP | DEVFL_DEAD); + spin_unlock_irqrestore(&d->lock, flags); /* clean out active and to-be-retransmitted buffers */ for (i = 0; i < NFACTIVE; i++) { From 8c8472855884355caf3d8e0c50adf825f83454b2 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Thu, 19 Jun 2025 12:10:31 +1000 Subject: [PATCH 3/3] ublk: santizize the arguments from userspace when adding a device Sanity check the values for queue depth and number of queues we get from userspace when adding a device. Signed-off-by: Ronnie Sahlberg Reviewed-by: Ming Lei Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver") Fixes: 62fe99cef94a ("ublk: add read()/write() support for ublk char device") Link: https://lore.kernel.org/r/20250619021031.181340-1-ronniesahlberg@gmail.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c637ea010d34..d36f44f5ee80 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2825,6 +2825,9 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; + if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES) + return -EINVAL; + if (capable(CAP_SYS_ADMIN)) info.flags &= ~UBLK_F_UNPRIVILEGED_DEV; else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))