On Wed, 13 Apr 2022 at 10:07, Rokudo Yan <wu-yan@xxxxxxx> wrote:
>
> There is a potential livelock when mmc_sd_detect is invoked by
> pm_suspend, as below:
>
> [thread do suspend]
> state_store
> -pm_suspend
> -__pm_notifier_call_chain
> -mmc_pm_notify
> -cancel_delayed_work_sync(&host->detect)
> -__cancel_work_timer
> -__flush_work
> -wait_for_completion
> wait for detect work current running to complete
>
> [kworker run detect work]
> process_one_work
> -mmc_rescan
> -mmc_sd_detect
> -mmc_get_card
> -__mmc_claim_host
> -schedule
> wait for current host claimer release
>
> [kworker dispatch io (current host claimer)]
> process_one_work
> -blk_mq_run_work_fn
> -__blk_mq_run_hw_queue
> -blk_mq_sched_dispatch_requests
> -blk_mq_do_dispatch_sched
> -blk_mq_dispatch_rq_list
> -mmc_mq_queue_rq
> -mmc_get_card -- claim mmc host if inflight=1 (the first io)
> and only release when all ios complete
> -mmc_blk_mq_issue_rq
>
> if there are continous io requests in the system to keep queue busy
> (inflight !=0 all the time), the supsend process will blocked and
> hang the system.
>
> This issue can reproduced by steps below:
> 1. prepare 1 SD card
> 2. run fio to keep the card io busy
> fio --size=1m --bs=32k --ioengine=libaio --iodepth=64 \
> --direct=1 --rw=read --time_based --runtime=60000 \
> --name=test --filename=<path under sd card>
> 3. suspend the system (echo mem > /sys/power/state)
> 4. resume the system
> 5. suspend the system again & device hang
>
> Signed-off-by: Rokudo Yan <wu-yan@xxxxxxx>
I believe you are running some vendor/old kernel, because I think this
problem has been fixed.
You may have a look at commit 17a17bf50612 ("mmc: core: Fix hanging on
I/O during system suspend for removable cards")
Kind regards
Uffe
> ---
> drivers/mmc/core/queue.c | 8 ++++++++
> drivers/mmc/core/sd.c | 2 ++
> include/linux/mmc/host.h | 3 +++
> 3 files changed, 13 insertions(+)
>
> diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
> index c69b2d9df6f1..f00fc45a4fd5 100644
> --- a/drivers/mmc/core/queue.c
> +++ b/drivers/mmc/core/queue.c
> @@ -241,6 +241,14 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
> return BLK_STS_IOERR;
> }
>
> + /*
> + * requeue the io if sd detect is on-going to avoid livelock
> + * when mmc_sd_detect is invoked by pm_suspend and there are
> + * continous io requests simultaneously.
> + */
> + if (host->doing_sd_detect)
> + return BLK_STS_RESOURCE;
> +
> issue_type = mmc_issue_type(mq, req);
>
> spin_lock_irq(&mq->lock);
> diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
> index 68df6b2f49cc..460ea6ab9aba 100644
> --- a/drivers/mmc/core/sd.c
> +++ b/drivers/mmc/core/sd.c
> @@ -1594,6 +1594,7 @@ static void mmc_sd_detect(struct mmc_host *host)
> {
> int err;
>
> + host->doing_sd_detect = true;
> mmc_get_card(host->card, NULL);
>
> /*
> @@ -1611,6 +1612,7 @@ static void mmc_sd_detect(struct mmc_host *host)
> mmc_power_off(host);
> mmc_release_host(host);
> }
> + host->doing_sd_detect = false;
> }
>
> static int sd_can_poweroff_notify(struct mmc_card *card)
> diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
> index 7afb57cab00b..4abfc5d7ef20 100644
> --- a/include/linux/mmc/host.h
> +++ b/include/linux/mmc/host.h
> @@ -501,6 +501,9 @@ struct mmc_host {
> /* Host Software Queue support */
> bool hsq_enabled;
>
> + /* indicate SD detect on-going */
> + bool doing_sd_detect;
> +
> unsigned long private[] ____cacheline_aligned;
> };
>
> --
> 2.25.1
>
