[PATCH] mmc: core: clear MQRQ_XFER_SINGLE_BLOCK for new requests

[PATCH] mmc: core: clear MQRQ_XFER_SINGLE_BLOCK for new requests

[Fexiven]

mmc_blk_mq_complete_rq() and mmc_blk_cqe_complete_rq() set
MQRQ_XFER_SINGLE_BLOCK in the request PDU when a transfer fails, so the
retry is done one block at a time. Nothing ever clears the flag again.

The PDU belongs to the blk-mq tag and is reused for later requests, while
mmc_mq_queue_rq() only resets ->retries for a new request. Every tag that
has seen a single transfer error therefore keeps issuing single-block
transfers (CMD17/CMD24) for the rest of the uptime.

On an RK3576 board (HS400ES eMMC) with occasional data CRC errors, which
are recovered correctly, sequential direct reads dropped from ~200 MB/s
after boot to 3-10 MB/s within minutes and never recovered. The host
registers showed only CMD17 with a 512 byte block size. With this change
the read throughput stays at ~200 MB/s and writes at 60-90 MB/s while the
data CRC errors continue to be retried.

Reset the flags together with the retry counter when a request is
prepared for the first time. Requeued requests keep RQF_DONTPREP, so the
single-block retry of the failing request itself is unchanged.

Fixes: d34124edffdb ("mmc: block: Use MQRQ_XFER_SINGLE_BLOCK for both read and write recovery")
Cc: stable@vger.kernel.org
Signed-off-by: Fexiven <kernel@picomail.one>
---
 drivers/mmc/core/queue.c | 2 ++
 1 file changed, 2 insertions(+)

--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -301,6 +301,8 @@

 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		req_to_mmc_queue_req(req)->retries = 0;
+		/* the request PDU is reused: don't inherit single-block recovery */
+		req_to_mmc_queue_req(req)->flags = 0;
 		req->rq_flags |= RQF_DONTPREP;
 	}

Re: [PATCH] mmc: core: clear MQRQ_XFER_SINGLE_BLOCK for new requests

[Greg KH]

On Tue, Nov 03, 2026 at 08:23:45PM +0100, Fexiven wrote:
> mmc_blk_mq_complete_rq() and mmc_blk_cqe_complete_rq() set
> MQRQ_XFER_SINGLE_BLOCK in the request PDU when a transfer fails, so the
> retry is done one block at a time. Nothing ever clears the flag again.
> 
> The PDU belongs to the blk-mq tag and is reused for later requests, while
> mmc_mq_queue_rq() only resets ->retries for a new request. Every tag that
> has seen a single transfer error therefore keeps issuing single-block
> transfers (CMD17/CMD24) for the rest of the uptime.
> 
> On an RK3576 board (HS400ES eMMC) with occasional data CRC errors, which
> are recovered correctly, sequential direct reads dropped from ~200 MB/s
> after boot to 3-10 MB/s within minutes and never recovered. The host
> registers showed only CMD17 with a 512 byte block size. With this change
> the read throughput stays at ~200 MB/s and writes at 60-90 MB/s while the
> data CRC errors continue to be retried.
> 
> Reset the flags together with the retry counter when a request is
> prepared for the first time. Requeued requests keep RQF_DONTPREP, so the
> single-block retry of the failing request itself is unchanged.
> 
> Fixes: d34124edffdb ("mmc: block: Use MQRQ_XFER_SINGLE_BLOCK for both read and write recovery")
> Cc: stable@vger.kernel.org
> Signed-off-by: Fexiven <kernel@picomail.one>

Real name please.

thanks,

greg k-h

Re: [PATCH] mmc: core: clear MQRQ_XFER_SINGLE_BLOCK for new requests

[Shawn Lin]

Hi Fexiven

在 2026/11/04 星期三 3:23, Fexiven 写道:
> mmc_blk_mq_complete_rq() and mmc_blk_cqe_complete_rq() set
> MQRQ_XFER_SINGLE_BLOCK in the request PDU when a transfer fails, so the
> retry is done one block at a time. Nothing ever clears the flag again.
> 
> The PDU belongs to the blk-mq tag and is reused for later requests, while
> mmc_mq_queue_rq() only resets ->retries for a new request. Every tag that
> has seen a single transfer error therefore keeps issuing single-block
> transfers (CMD17/CMD24) for the rest of the uptime.
> 
> On an RK3576 board (HS400ES eMMC) with occasional data CRC errors, which
> are recovered correctly, sequential direct reads dropped from ~200 MB/s
> after boot to 3-10 MB/s within minutes and never recovered. The host
> registers showed only CMD17 with a 512 byte block size. With this change
> the read throughput stays at ~200 MB/s and writes at 60-90 MB/s while the
> data CRC errors continue to be retried.
> 
> Reset the flags together with the retry counter when a request is
> prepared for the first time. Requeued requests keep RQF_DONTPREP, so the
> single-block retry of the failing request itself is unchanged.
> 

Sorry for not catching this in the first place. I was preparing a patch
to fix it but forgot to send out immediately :(

Except for your DCO name , the change itself looks good.
With that improved, feel free to add,

Reviewed-by: Shawn Lin <shawn.lin@rock-chips.com>


> Fixes: d34124edffdb ("mmc: block: Use MQRQ_XFER_SINGLE_BLOCK for both read and write recovery")
> Cc: stable@vger.kernel.org
> Signed-off-by: Fexiven <kernel@picomail.one>
> ---
>   drivers/mmc/core/queue.c | 2 ++
>   1 file changed, 2 insertions(+)
> 
> --- a/drivers/mmc/core/queue.c
> +++ b/drivers/mmc/core/queue.c
> @@ -301,6 +301,8 @@
> 
>   	if (!(req->rq_flags & RQF_DONTPREP)) {
>   		req_to_mmc_queue_req(req)->retries = 0;
> +		/* the request PDU is reused: don't inherit single-block recovery */
> +		req_to_mmc_queue_req(req)->flags = 0;
>   		req->rq_flags |= RQF_DONTPREP;
>   	}
> 
> 
> 

[PATCH v2] mmc: core: clear MQRQ_XFER_SINGLE_BLOCK for new requests

[Jonathan Schmid]

mmc_blk_mq_complete_rq() and mmc_blk_cqe_complete_rq() set
MQRQ_XFER_SINGLE_BLOCK in the request PDU when a transfer fails, so the
retry is done one block at a time. Nothing ever clears the flag again.

The PDU belongs to the blk-mq tag and is reused for later requests, while
mmc_mq_queue_rq() only resets ->retries for a new request. Every tag that
has seen a single transfer error therefore keeps issuing single-block
transfers (CMD17/CMD24) for the rest of the uptime.

On an RK3576 board (HS400ES eMMC) with occasional data CRC errors, which
are recovered correctly, sequential direct reads dropped from ~200 MB/s
after boot to 3-10 MB/s within minutes and never recovered. The host
registers showed only CMD17 with a 512 byte block size. With this change
the read throughput stays at ~200 MB/s and writes at 60-90 MB/s while the
data CRC errors continue to be retried.

Reset the flags together with the retry counter when a request is
prepared for the first time. Requeued requests keep RQF_DONTPREP, so the
single-block retry of the failing request itself is unchanged.

Fixes: d34124edffdb ("mmc: block: Use MQRQ_XFER_SINGLE_BLOCK for both read and write recovery")
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Schmid <kernel@picomail.one>
---
v2: use my real name in From and Signed-off-by (Greg)

 drivers/mmc/core/queue.c | 2 ++
 1 file changed, 2 insertions(+)

--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -301,6 +301,8 @@

 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		req_to_mmc_queue_req(req)->retries = 0;
+		/* the request PDU is reused: don't inherit single-block recovery */
+		req_to_mmc_queue_req(req)->flags = 0;
 		req->rq_flags |= RQF_DONTPREP;
 	}