diff mbox series

[V16,08/23] mmc: core: Support UHS-II Auto Command Error Recovery

Message ID 20240522110909.10060-9-victorshihgli@gmail.com (mailing list archive)
State New
Headers show
Series Add support UHS-II for GL9755 and GL9767 | expand

Commit Message

Victor Shih May 22, 2024, 11:08 a.m. UTC
From: Victor Shih <victor.shih@genesyslogic.com.tw>

Add UHS-II Auto Command Error Recovery functionality
into the MMC request processing flow.

Signed-off-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
---

Updates in V16:
 - Separate the Error Recovery mechanism from patch#7 to patch#8.

---

 drivers/mmc/core/core.c    |  4 ++
 drivers/mmc/core/core.h    |  1 +
 drivers/mmc/core/sd_uhs2.c | 80 ++++++++++++++++++++++++++++++++++++++
 include/linux/mmc/host.h   |  6 +++
 4 files changed, 91 insertions(+)

Comments

Adrian Hunter May 24, 2024, 6:54 a.m. UTC | #1
On 22/05/24 14:08, Victor Shih wrote:
> From: Victor Shih <victor.shih@genesyslogic.com.tw>
> 
> Add UHS-II Auto Command Error Recovery functionality
> into the MMC request processing flow.

Not sure what "auto" means here, but the commit message
should outline what the spec. requires for error recovery.

> 
> Signed-off-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
> Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
> ---
> 
> Updates in V16:
>  - Separate the Error Recovery mechanism from patch#7 to patch#8.
> 
> ---
> 
>  drivers/mmc/core/core.c    |  4 ++
>  drivers/mmc/core/core.h    |  1 +
>  drivers/mmc/core/sd_uhs2.c | 80 ++++++++++++++++++++++++++++++++++++++
>  include/linux/mmc/host.h   |  6 +++
>  4 files changed, 91 insertions(+)
> 
> diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
> index 68496c51a521..18642afc405f 100644
> --- a/drivers/mmc/core/core.c
> +++ b/drivers/mmc/core/core.c
> @@ -403,6 +403,10 @@ void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
>  	while (1) {
>  		wait_for_completion(&mrq->completion);
>  
> +		if (host->ops->get_cd(host))
> +			if (mrq->cmd->error || (mrq->data && mrq->data->error))
> +				mmc_sd_uhs2_error_recovery(host, mrq);

There are several issues with this:

1. It is not OK to start a request from within the request path
because it is recursive:

   mmc_wait_for_req_done()			<--
      mmc_sd_uhs2_error_recovery()
         sd_uhs2_abort_trans()
            mmc_wait_for_cmd()
               mmc_wait_for_req()
                  mmc_wait_for_req_done()	<--

2. The mmc block driver does not use this path

3. No need to always call ->get_cd() if there is no error

It is worth considering whether the host controller could
send the abort command as part of the original request, as
is done with the stop command.

> +
>  		cmd = mrq->cmd;
>  
>  		if (!cmd->error || !cmd->retries ||
> diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
> index 920323faa834..259d47c8bb19 100644
> --- a/drivers/mmc/core/core.h
> +++ b/drivers/mmc/core/core.h
> @@ -82,6 +82,7 @@ int mmc_attach_mmc(struct mmc_host *host);
>  int mmc_attach_sd(struct mmc_host *host);
>  int mmc_attach_sdio(struct mmc_host *host);
>  int mmc_attach_sd_uhs2(struct mmc_host *host);
> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq);
>  
>  /* Module parameters */
>  extern bool use_spi_crc;
> diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
> index 85939a2582dc..d5acb4e6ccac 100644
> --- a/drivers/mmc/core/sd_uhs2.c
> +++ b/drivers/mmc/core/sd_uhs2.c
> @@ -1324,3 +1324,83 @@ int mmc_attach_sd_uhs2(struct mmc_host *host)
>  
>  	return err;
>  }
> +
> +static void sd_uhs2_abort_trans(struct mmc_host *mmc)
> +{
> +	struct mmc_request mrq = {};
> +	struct mmc_command cmd = {0};
> +	struct uhs2_command uhs2_cmd = {};
> +	int err;
> +
> +	mrq.cmd = &cmd;
> +	mmc->ongoing_mrq = &mrq;
> +
> +	uhs2_cmd.header = UHS2_NATIVE_PACKET | UHS2_PACKET_TYPE_CCMD |
> +			  mmc->card->uhs2_config.node_id;
> +	uhs2_cmd.arg = ((UHS2_DEV_CMD_TRANS_ABORT & 0xFF) << 8) |
> +			UHS2_NATIVE_CMD_WRITE |
> +			(UHS2_DEV_CMD_TRANS_ABORT >> 8);
> +
> +	sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> +	err = mmc_wait_for_cmd(mmc, &cmd, 0);
> +
> +	if (err)
> +		pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> +		       mmc_hostname(mmc), __func__, err);
> +}
> +
> +static void sd_uhs2_abort_status_read(struct mmc_host *mmc)
> +{
> +	struct mmc_request mrq = {};
> +	struct mmc_command cmd = {0};
> +	struct uhs2_command uhs2_cmd = {};
> +	int err;
> +
> +	mrq.cmd = &cmd;
> +	mmc->ongoing_mrq = &mrq;
> +
> +	uhs2_cmd.header = UHS2_NATIVE_PACKET |
> +			  UHS2_PACKET_TYPE_CCMD |
> +			  mmc->card->uhs2_config.node_id;
> +	uhs2_cmd.arg = ((UHS2_DEV_STATUS_REG & 0xFF) << 8) |
> +			UHS2_NATIVE_CMD_READ |
> +			UHS2_NATIVE_CMD_PLEN_4B |
> +			(UHS2_DEV_STATUS_REG >> 8);
> +
> +	sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> +	err = mmc_wait_for_cmd(mmc, &cmd, 0);
> +
> +	if (err)
> +		pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> +		       mmc_hostname(mmc), __func__, err);
> +}
> +
> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq)
> +{
> +	mmc->ops->uhs2_reset_cmd_data(mmc);

The host controller should already have done any resets needed.
sdhci already has support for doing that - see host->pending_reset

> +
> +	if (mrq->data) {
> +		if (mrq->data->error && mmc_card_uhs2(mmc)) {
> +			if (mrq->cmd) {
> +				switch (mrq->cmd->error) {
> +				case ETIMEDOUT:
> +				case EILSEQ:
> +				case EIO:
> +					sd_uhs2_abort_trans(mmc);
> +					sd_uhs2_abort_status_read(mmc);

What is the purpose of sd_uhs2_abort_status_read() here?
It is not obvious it does anything.

> +					break;
> +				default:
> +					break;
> +				}
> +			}
> +		}
> +	} else {
> +		if (mrq->cmd) {
> +			switch (mrq->cmd->error) {
> +			case ETIMEDOUT:
> +				sd_uhs2_abort_trans(mmc);
> +				break;
> +			}
> +		}
> +	}
> +}
> diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
> index fc9520b3bfa4..c914a58f7e1e 100644
> --- a/include/linux/mmc/host.h
> +++ b/include/linux/mmc/host.h
> @@ -271,6 +271,12 @@ struct mmc_host_ops {
>  	 * negative errno in case of a failure or zero for success.
>  	 */
>  	int	(*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
> +
> +	/*
> +	 * The uhs2_reset_cmd_data callback is used to excute reset
> +	 * when a auto command error occurs.
> +	 */
> +	void 	(*uhs2_reset_cmd_data)(struct mmc_host *host);
>  };
>  
>  struct mmc_cqe_ops {
Victor Shih May 31, 2024, 10:31 a.m. UTC | #2
On Fri, May 24, 2024 at 2:54 PM Adrian Hunter <adrian.hunter@intel.com> wrote:
>
> On 22/05/24 14:08, Victor Shih wrote:
> > From: Victor Shih <victor.shih@genesyslogic.com.tw>
> >
> > Add UHS-II Auto Command Error Recovery functionality
> > into the MMC request processing flow.
>
> Not sure what "auto" means here, but the commit message
> should outline what the spec. requires for error recovery.
>

Hi, Adrian

     I will add instructions in the v17 version.

Thanks, Victor Shih

> >
> > Signed-off-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
> > Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
> > ---
> >
> > Updates in V16:
> >  - Separate the Error Recovery mechanism from patch#7 to patch#8.
> >
> > ---
> >
> >  drivers/mmc/core/core.c    |  4 ++
> >  drivers/mmc/core/core.h    |  1 +
> >  drivers/mmc/core/sd_uhs2.c | 80 ++++++++++++++++++++++++++++++++++++++
> >  include/linux/mmc/host.h   |  6 +++
> >  4 files changed, 91 insertions(+)
> >
> > diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
> > index 68496c51a521..18642afc405f 100644
> > --- a/drivers/mmc/core/core.c
> > +++ b/drivers/mmc/core/core.c
> > @@ -403,6 +403,10 @@ void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
> >       while (1) {
> >               wait_for_completion(&mrq->completion);
> >
> > +             if (host->ops->get_cd(host))
> > +                     if (mrq->cmd->error || (mrq->data && mrq->data->error))
> > +                             mmc_sd_uhs2_error_recovery(host, mrq);
>
> There are several issues with this:
>
> 1. It is not OK to start a request from within the request path
> because it is recursive:
>
>    mmc_wait_for_req_done()                      <--
>       mmc_sd_uhs2_error_recovery()
>          sd_uhs2_abort_trans()
>             mmc_wait_for_cmd()
>                mmc_wait_for_req()
>                   mmc_wait_for_req_done()       <--
>
> 2. The mmc block driver does not use this path
>
> 3. No need to always call ->get_cd() if there is no error
>
> It is worth considering whether the host controller could
> send the abort command as part of the original request, as
> is done with the stop command.
>

Hi, Adrian

     1. It looks like just issuing a command in
mmc_wait_for_req_done() will cause a recursion.
         I will drop sd_uhs2_abort_trans() and
sd_uhs2_abort_status_read() in the v17 version.
     2. I have no idea about this part, could you please give me some advice?
     3. I will try to modify this part in the v17 version.

Thanks, Victor Shih

> > +
> >               cmd = mrq->cmd;
> >
> >               if (!cmd->error || !cmd->retries ||
> > diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
> > index 920323faa834..259d47c8bb19 100644
> > --- a/drivers/mmc/core/core.h
> > +++ b/drivers/mmc/core/core.h
> > @@ -82,6 +82,7 @@ int mmc_attach_mmc(struct mmc_host *host);
> >  int mmc_attach_sd(struct mmc_host *host);
> >  int mmc_attach_sdio(struct mmc_host *host);
> >  int mmc_attach_sd_uhs2(struct mmc_host *host);
> > +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq);
> >
> >  /* Module parameters */
> >  extern bool use_spi_crc;
> > diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
> > index 85939a2582dc..d5acb4e6ccac 100644
> > --- a/drivers/mmc/core/sd_uhs2.c
> > +++ b/drivers/mmc/core/sd_uhs2.c
> > @@ -1324,3 +1324,83 @@ int mmc_attach_sd_uhs2(struct mmc_host *host)
> >
> >       return err;
> >  }
> > +
> > +static void sd_uhs2_abort_trans(struct mmc_host *mmc)
> > +{
> > +     struct mmc_request mrq = {};
> > +     struct mmc_command cmd = {0};
> > +     struct uhs2_command uhs2_cmd = {};
> > +     int err;
> > +
> > +     mrq.cmd = &cmd;
> > +     mmc->ongoing_mrq = &mrq;
> > +
> > +     uhs2_cmd.header = UHS2_NATIVE_PACKET | UHS2_PACKET_TYPE_CCMD |
> > +                       mmc->card->uhs2_config.node_id;
> > +     uhs2_cmd.arg = ((UHS2_DEV_CMD_TRANS_ABORT & 0xFF) << 8) |
> > +                     UHS2_NATIVE_CMD_WRITE |
> > +                     (UHS2_DEV_CMD_TRANS_ABORT >> 8);
> > +
> > +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> > +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
> > +
> > +     if (err)
> > +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> > +                    mmc_hostname(mmc), __func__, err);
> > +}
> > +
> > +static void sd_uhs2_abort_status_read(struct mmc_host *mmc)
> > +{
> > +     struct mmc_request mrq = {};
> > +     struct mmc_command cmd = {0};
> > +     struct uhs2_command uhs2_cmd = {};
> > +     int err;
> > +
> > +     mrq.cmd = &cmd;
> > +     mmc->ongoing_mrq = &mrq;
> > +
> > +     uhs2_cmd.header = UHS2_NATIVE_PACKET |
> > +                       UHS2_PACKET_TYPE_CCMD |
> > +                       mmc->card->uhs2_config.node_id;
> > +     uhs2_cmd.arg = ((UHS2_DEV_STATUS_REG & 0xFF) << 8) |
> > +                     UHS2_NATIVE_CMD_READ |
> > +                     UHS2_NATIVE_CMD_PLEN_4B |
> > +                     (UHS2_DEV_STATUS_REG >> 8);
> > +
> > +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> > +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
> > +
> > +     if (err)
> > +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> > +                    mmc_hostname(mmc), __func__, err);
> > +}
> > +
> > +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq)
> > +{
> > +     mmc->ops->uhs2_reset_cmd_data(mmc);
>
> The host controller should already have done any resets needed.
> sdhci already has support for doing that - see host->pending_reset
>

Hi, Adrian

     I'm not sure what this means. Could you please give me more information?

Thanks, Victor Shih

> > +
> > +     if (mrq->data) {
> > +             if (mrq->data->error && mmc_card_uhs2(mmc)) {
> > +                     if (mrq->cmd) {
> > +                             switch (mrq->cmd->error) {
> > +                             case ETIMEDOUT:
> > +                             case EILSEQ:
> > +                             case EIO:
> > +                                     sd_uhs2_abort_trans(mmc);
> > +                                     sd_uhs2_abort_status_read(mmc);
>
> What is the purpose of sd_uhs2_abort_status_read() here?
> It is not obvious it does anything.
>

Hi, Adrian

     sd_uhs2_abort_status_read() seems to only have read status,
     I will drop this in the v17 version.

Thanks, Victor Shih

> > +                                     break;
> > +                             default:
> > +                                     break;
> > +                             }
> > +                     }
> > +             }
> > +     } else {
> > +             if (mrq->cmd) {
> > +                     switch (mrq->cmd->error) {
> > +                     case ETIMEDOUT:
> > +                             sd_uhs2_abort_trans(mmc);
> > +                             break;
> > +                     }
> > +             }
> > +     }
> > +}
> > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
> > index fc9520b3bfa4..c914a58f7e1e 100644
> > --- a/include/linux/mmc/host.h
> > +++ b/include/linux/mmc/host.h
> > @@ -271,6 +271,12 @@ struct mmc_host_ops {
> >        * negative errno in case of a failure or zero for success.
> >        */
> >       int     (*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
> > +
> > +     /*
> > +      * The uhs2_reset_cmd_data callback is used to excute reset
> > +      * when a auto command error occurs.
> > +      */
> > +     void    (*uhs2_reset_cmd_data)(struct mmc_host *host);
> >  };
> >
> >  struct mmc_cqe_ops {
>
Adrian Hunter May 31, 2024, 11:23 a.m. UTC | #3
On 31/05/24 13:31, Victor Shih wrote:
> On Fri, May 24, 2024 at 2:54 PM Adrian Hunter <adrian.hunter@intel.com> wrote:
>>
>> On 22/05/24 14:08, Victor Shih wrote:
>>> From: Victor Shih <victor.shih@genesyslogic.com.tw>
>>>
>>> Add UHS-II Auto Command Error Recovery functionality
>>> into the MMC request processing flow.
>>
>> Not sure what "auto" means here, but the commit message
>> should outline what the spec. requires for error recovery.
>>
> 
> Hi, Adrian
> 
>      I will add instructions in the v17 version.
> 
> Thanks, Victor Shih
> 
>>>
>>> Signed-off-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
>>> Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
>>> ---
>>>
>>> Updates in V16:
>>>  - Separate the Error Recovery mechanism from patch#7 to patch#8.
>>>
>>> ---
>>>
>>>  drivers/mmc/core/core.c    |  4 ++
>>>  drivers/mmc/core/core.h    |  1 +
>>>  drivers/mmc/core/sd_uhs2.c | 80 ++++++++++++++++++++++++++++++++++++++
>>>  include/linux/mmc/host.h   |  6 +++
>>>  4 files changed, 91 insertions(+)
>>>
>>> diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
>>> index 68496c51a521..18642afc405f 100644
>>> --- a/drivers/mmc/core/core.c
>>> +++ b/drivers/mmc/core/core.c
>>> @@ -403,6 +403,10 @@ void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
>>>       while (1) {
>>>               wait_for_completion(&mrq->completion);
>>>
>>> +             if (host->ops->get_cd(host))
>>> +                     if (mrq->cmd->error || (mrq->data && mrq->data->error))
>>> +                             mmc_sd_uhs2_error_recovery(host, mrq);
>>
>> There are several issues with this:
>>
>> 1. It is not OK to start a request from within the request path
>> because it is recursive:
>>
>>    mmc_wait_for_req_done()                      <--
>>       mmc_sd_uhs2_error_recovery()
>>          sd_uhs2_abort_trans()
>>             mmc_wait_for_cmd()
>>                mmc_wait_for_req()
>>                   mmc_wait_for_req_done()       <--
>>
>> 2. The mmc block driver does not use this path
>>
>> 3. No need to always call ->get_cd() if there is no error
>>
>> It is worth considering whether the host controller could
>> send the abort command as part of the original request, as
>> is done with the stop command.
>>
> 
> Hi, Adrian
> 
>      1. It looks like just issuing a command in
> mmc_wait_for_req_done() will cause a recursion.
>          I will drop sd_uhs2_abort_trans() and
> sd_uhs2_abort_status_read() in the v17 version.
>      2. I have no idea about this part, could you please give me some advice?

The mmc block driver sets the ->done() callback and so
mmc_wait_for_req_done() is never called for data transfers.

That won't matter if the host controller handles doing
the abort command, as was suggested elsewhere.

>      3. I will try to modify this part in the v17 version.
> 
> Thanks, Victor Shih
> 
>>> +
>>>               cmd = mrq->cmd;
>>>
>>>               if (!cmd->error || !cmd->retries ||
>>> diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
>>> index 920323faa834..259d47c8bb19 100644
>>> --- a/drivers/mmc/core/core.h
>>> +++ b/drivers/mmc/core/core.h
>>> @@ -82,6 +82,7 @@ int mmc_attach_mmc(struct mmc_host *host);
>>>  int mmc_attach_sd(struct mmc_host *host);
>>>  int mmc_attach_sdio(struct mmc_host *host);
>>>  int mmc_attach_sd_uhs2(struct mmc_host *host);
>>> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq);
>>>
>>>  /* Module parameters */
>>>  extern bool use_spi_crc;
>>> diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
>>> index 85939a2582dc..d5acb4e6ccac 100644
>>> --- a/drivers/mmc/core/sd_uhs2.c
>>> +++ b/drivers/mmc/core/sd_uhs2.c
>>> @@ -1324,3 +1324,83 @@ int mmc_attach_sd_uhs2(struct mmc_host *host)
>>>
>>>       return err;
>>>  }
>>> +
>>> +static void sd_uhs2_abort_trans(struct mmc_host *mmc)
>>> +{
>>> +     struct mmc_request mrq = {};
>>> +     struct mmc_command cmd = {0};
>>> +     struct uhs2_command uhs2_cmd = {};
>>> +     int err;
>>> +
>>> +     mrq.cmd = &cmd;
>>> +     mmc->ongoing_mrq = &mrq;
>>> +
>>> +     uhs2_cmd.header = UHS2_NATIVE_PACKET | UHS2_PACKET_TYPE_CCMD |
>>> +                       mmc->card->uhs2_config.node_id;
>>> +     uhs2_cmd.arg = ((UHS2_DEV_CMD_TRANS_ABORT & 0xFF) << 8) |
>>> +                     UHS2_NATIVE_CMD_WRITE |
>>> +                     (UHS2_DEV_CMD_TRANS_ABORT >> 8);
>>> +
>>> +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
>>> +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
>>> +
>>> +     if (err)
>>> +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
>>> +                    mmc_hostname(mmc), __func__, err);
>>> +}
>>> +
>>> +static void sd_uhs2_abort_status_read(struct mmc_host *mmc)
>>> +{
>>> +     struct mmc_request mrq = {};
>>> +     struct mmc_command cmd = {0};
>>> +     struct uhs2_command uhs2_cmd = {};
>>> +     int err;
>>> +
>>> +     mrq.cmd = &cmd;
>>> +     mmc->ongoing_mrq = &mrq;
>>> +
>>> +     uhs2_cmd.header = UHS2_NATIVE_PACKET |
>>> +                       UHS2_PACKET_TYPE_CCMD |
>>> +                       mmc->card->uhs2_config.node_id;
>>> +     uhs2_cmd.arg = ((UHS2_DEV_STATUS_REG & 0xFF) << 8) |
>>> +                     UHS2_NATIVE_CMD_READ |
>>> +                     UHS2_NATIVE_CMD_PLEN_4B |
>>> +                     (UHS2_DEV_STATUS_REG >> 8);
>>> +
>>> +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
>>> +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
>>> +
>>> +     if (err)
>>> +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
>>> +                    mmc_hostname(mmc), __func__, err);
>>> +}
>>> +
>>> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq)
>>> +{
>>> +     mmc->ops->uhs2_reset_cmd_data(mmc);
>>
>> The host controller should already have done any resets needed.
>> sdhci already has support for doing that - see host->pending_reset
>>
> 
> Hi, Adrian
> 
>      I'm not sure what this means. Could you please give me more information?

sdhci_uhs2_request_done() checks sdhci_needs_reset() and does
sdhci_uhs2_reset().

sdhci_needs_reset() does not cater for data errors because
the reset for data errors is done directly in what becomes
__sdhci_finish_data_common().

You may need to:
 1. add a parameter to __sdhci_finish_data_common() to
 skip doing the sdhci reset and instead set
 host->pending_reset
 2. amend sdhci_uhs2_request_done() to check for data error
 also to decide if a reset is needed

> 
> Thanks, Victor Shih
> 
>>> +
>>> +     if (mrq->data) {
>>> +             if (mrq->data->error && mmc_card_uhs2(mmc)) {
>>> +                     if (mrq->cmd) {
>>> +                             switch (mrq->cmd->error) {
>>> +                             case ETIMEDOUT:
>>> +                             case EILSEQ:
>>> +                             case EIO:
>>> +                                     sd_uhs2_abort_trans(mmc);
>>> +                                     sd_uhs2_abort_status_read(mmc);
>>
>> What is the purpose of sd_uhs2_abort_status_read() here?
>> It is not obvious it does anything.
>>
> 
> Hi, Adrian
> 
>      sd_uhs2_abort_status_read() seems to only have read status,
>      I will drop this in the v17 version.
> 
> Thanks, Victor Shih
> 
>>> +                                     break;
>>> +                             default:
>>> +                                     break;
>>> +                             }
>>> +                     }
>>> +             }
>>> +     } else {
>>> +             if (mrq->cmd) {
>>> +                     switch (mrq->cmd->error) {
>>> +                     case ETIMEDOUT:
>>> +                             sd_uhs2_abort_trans(mmc);
>>> +                             break;
>>> +                     }
>>> +             }
>>> +     }
>>> +}
>>> diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
>>> index fc9520b3bfa4..c914a58f7e1e 100644
>>> --- a/include/linux/mmc/host.h
>>> +++ b/include/linux/mmc/host.h
>>> @@ -271,6 +271,12 @@ struct mmc_host_ops {
>>>        * negative errno in case of a failure or zero for success.
>>>        */
>>>       int     (*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
>>> +
>>> +     /*
>>> +      * The uhs2_reset_cmd_data callback is used to excute reset
>>> +      * when a auto command error occurs.
>>> +      */
>>> +     void    (*uhs2_reset_cmd_data)(struct mmc_host *host);
>>>  };
>>>
>>>  struct mmc_cqe_ops {
>>
Victor Shih June 9, 2024, 6:40 p.m. UTC | #4
On Fri, May 31, 2024 at 7:23 PM Adrian Hunter <adrian.hunter@intel.com> wrote:
>
> On 31/05/24 13:31, Victor Shih wrote:
> > On Fri, May 24, 2024 at 2:54 PM Adrian Hunter <adrian.hunter@intel.com> wrote:
> >>
> >> On 22/05/24 14:08, Victor Shih wrote:
> >>> From: Victor Shih <victor.shih@genesyslogic.com.tw>
> >>>
> >>> Add UHS-II Auto Command Error Recovery functionality
> >>> into the MMC request processing flow.
> >>
> >> Not sure what "auto" means here, but the commit message
> >> should outline what the spec. requires for error recovery.
> >>
> >
> > Hi, Adrian
> >
> >      I will add instructions in the v17 version.
> >
> > Thanks, Victor Shih
> >
> >>>
> >>> Signed-off-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
> >>> Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
> >>> ---
> >>>
> >>> Updates in V16:
> >>>  - Separate the Error Recovery mechanism from patch#7 to patch#8.
> >>>
> >>> ---
> >>>
> >>>  drivers/mmc/core/core.c    |  4 ++
> >>>  drivers/mmc/core/core.h    |  1 +
> >>>  drivers/mmc/core/sd_uhs2.c | 80 ++++++++++++++++++++++++++++++++++++++
> >>>  include/linux/mmc/host.h   |  6 +++
> >>>  4 files changed, 91 insertions(+)
> >>>
> >>> diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
> >>> index 68496c51a521..18642afc405f 100644
> >>> --- a/drivers/mmc/core/core.c
> >>> +++ b/drivers/mmc/core/core.c
> >>> @@ -403,6 +403,10 @@ void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
> >>>       while (1) {
> >>>               wait_for_completion(&mrq->completion);
> >>>
> >>> +             if (host->ops->get_cd(host))
> >>> +                     if (mrq->cmd->error || (mrq->data && mrq->data->error))
> >>> +                             mmc_sd_uhs2_error_recovery(host, mrq);
> >>
> >> There are several issues with this:
> >>
> >> 1. It is not OK to start a request from within the request path
> >> because it is recursive:
> >>
> >>    mmc_wait_for_req_done()                      <--
> >>       mmc_sd_uhs2_error_recovery()
> >>          sd_uhs2_abort_trans()
> >>             mmc_wait_for_cmd()
> >>                mmc_wait_for_req()
> >>                   mmc_wait_for_req_done()       <--
> >>
> >> 2. The mmc block driver does not use this path
> >>
> >> 3. No need to always call ->get_cd() if there is no error
> >>
> >> It is worth considering whether the host controller could
> >> send the abort command as part of the original request, as
> >> is done with the stop command.
> >>
> >
> > Hi, Adrian
> >
> >      1. It looks like just issuing a command in
> > mmc_wait_for_req_done() will cause a recursion.
> >          I will drop sd_uhs2_abort_trans() and
> > sd_uhs2_abort_status_read() in the v17 version.
> >      2. I have no idea about this part, could you please give me some advice?
>
> The mmc block driver sets the ->done() callback and so
> mmc_wait_for_req_done() is never called for data transfers.
>
> That won't matter if the host controller handles doing
> the abort command, as was suggested elsewhere.
>
> >      3. I will try to modify this part in the v17 version.
> >
> > Thanks, Victor Shih
> >
> >>> +
> >>>               cmd = mrq->cmd;
> >>>
> >>>               if (!cmd->error || !cmd->retries ||
> >>> diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
> >>> index 920323faa834..259d47c8bb19 100644
> >>> --- a/drivers/mmc/core/core.h
> >>> +++ b/drivers/mmc/core/core.h
> >>> @@ -82,6 +82,7 @@ int mmc_attach_mmc(struct mmc_host *host);
> >>>  int mmc_attach_sd(struct mmc_host *host);
> >>>  int mmc_attach_sdio(struct mmc_host *host);
> >>>  int mmc_attach_sd_uhs2(struct mmc_host *host);
> >>> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq);
> >>>
> >>>  /* Module parameters */
> >>>  extern bool use_spi_crc;
> >>> diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
> >>> index 85939a2582dc..d5acb4e6ccac 100644
> >>> --- a/drivers/mmc/core/sd_uhs2.c
> >>> +++ b/drivers/mmc/core/sd_uhs2.c
> >>> @@ -1324,3 +1324,83 @@ int mmc_attach_sd_uhs2(struct mmc_host *host)
> >>>
> >>>       return err;
> >>>  }
> >>> +
> >>> +static void sd_uhs2_abort_trans(struct mmc_host *mmc)
> >>> +{
> >>> +     struct mmc_request mrq = {};
> >>> +     struct mmc_command cmd = {0};
> >>> +     struct uhs2_command uhs2_cmd = {};
> >>> +     int err;
> >>> +
> >>> +     mrq.cmd = &cmd;
> >>> +     mmc->ongoing_mrq = &mrq;
> >>> +
> >>> +     uhs2_cmd.header = UHS2_NATIVE_PACKET | UHS2_PACKET_TYPE_CCMD |
> >>> +                       mmc->card->uhs2_config.node_id;
> >>> +     uhs2_cmd.arg = ((UHS2_DEV_CMD_TRANS_ABORT & 0xFF) << 8) |
> >>> +                     UHS2_NATIVE_CMD_WRITE |
> >>> +                     (UHS2_DEV_CMD_TRANS_ABORT >> 8);
> >>> +
> >>> +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> >>> +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
> >>> +
> >>> +     if (err)
> >>> +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> >>> +                    mmc_hostname(mmc), __func__, err);
> >>> +}
> >>> +
> >>> +static void sd_uhs2_abort_status_read(struct mmc_host *mmc)
> >>> +{
> >>> +     struct mmc_request mrq = {};
> >>> +     struct mmc_command cmd = {0};
> >>> +     struct uhs2_command uhs2_cmd = {};
> >>> +     int err;
> >>> +
> >>> +     mrq.cmd = &cmd;
> >>> +     mmc->ongoing_mrq = &mrq;
> >>> +
> >>> +     uhs2_cmd.header = UHS2_NATIVE_PACKET |
> >>> +                       UHS2_PACKET_TYPE_CCMD |
> >>> +                       mmc->card->uhs2_config.node_id;
> >>> +     uhs2_cmd.arg = ((UHS2_DEV_STATUS_REG & 0xFF) << 8) |
> >>> +                     UHS2_NATIVE_CMD_READ |
> >>> +                     UHS2_NATIVE_CMD_PLEN_4B |
> >>> +                     (UHS2_DEV_STATUS_REG >> 8);
> >>> +
> >>> +     sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
> >>> +     err = mmc_wait_for_cmd(mmc, &cmd, 0);
> >>> +
> >>> +     if (err)
> >>> +             pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
> >>> +                    mmc_hostname(mmc), __func__, err);
> >>> +}
> >>> +
> >>> +void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq)
> >>> +{
> >>> +     mmc->ops->uhs2_reset_cmd_data(mmc);
> >>
> >> The host controller should already have done any resets needed.
> >> sdhci already has support for doing that - see host->pending_reset
> >>
> >
> > Hi, Adrian
> >
> >      I'm not sure what this means. Could you please give me more information?
>
> sdhci_uhs2_request_done() checks sdhci_needs_reset() and does
> sdhci_uhs2_reset().
>
> sdhci_needs_reset() does not cater for data errors because
> the reset for data errors is done directly in what becomes
> __sdhci_finish_data_common().
>
> You may need to:
>  1. add a parameter to __sdhci_finish_data_common() to
>  skip doing the sdhci reset and instead set
>  host->pending_reset
>  2. amend sdhci_uhs2_request_done() to check for data error
>  also to decide if a reset is needed
>

Hi, Adrian

If there is any mistake in my understanding, please help me correct it.
My understanding is as follows:

static bool sdhci_uhs2_request_done(struct sdhci_host *host)
{
      ...
      if (sdhci_needs_reset(host, mrq)) {
            ...
            if (mrq->cmd->error || (mrq->data && mrq->data->error))
                  sdhci_uhs2_reset_cmd_data(host->mmc);
            ...
      }
      ...
}

I have another question. the sdhci_uhs2_request_done() belongs to the patch#18.
Can the above content be modified directly in the patch#18?
Or does it need to be separated into another patch?

Thanks, Victor Shih

> >
> > Thanks, Victor Shih
> >
> >>> +
> >>> +     if (mrq->data) {
> >>> +             if (mrq->data->error && mmc_card_uhs2(mmc)) {
> >>> +                     if (mrq->cmd) {
> >>> +                             switch (mrq->cmd->error) {
> >>> +                             case ETIMEDOUT:
> >>> +                             case EILSEQ:
> >>> +                             case EIO:
> >>> +                                     sd_uhs2_abort_trans(mmc);
> >>> +                                     sd_uhs2_abort_status_read(mmc);
> >>
> >> What is the purpose of sd_uhs2_abort_status_read() here?
> >> It is not obvious it does anything.
> >>
> >
> > Hi, Adrian
> >
> >      sd_uhs2_abort_status_read() seems to only have read status,
> >      I will drop this in the v17 version.
> >
> > Thanks, Victor Shih
> >
> >>> +                                     break;
> >>> +                             default:
> >>> +                                     break;
> >>> +                             }
> >>> +                     }
> >>> +             }
> >>> +     } else {
> >>> +             if (mrq->cmd) {
> >>> +                     switch (mrq->cmd->error) {
> >>> +                     case ETIMEDOUT:
> >>> +                             sd_uhs2_abort_trans(mmc);
> >>> +                             break;
> >>> +                     }
> >>> +             }
> >>> +     }
> >>> +}
> >>> diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
> >>> index fc9520b3bfa4..c914a58f7e1e 100644
> >>> --- a/include/linux/mmc/host.h
> >>> +++ b/include/linux/mmc/host.h
> >>> @@ -271,6 +271,12 @@ struct mmc_host_ops {
> >>>        * negative errno in case of a failure or zero for success.
> >>>        */
> >>>       int     (*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
> >>> +
> >>> +     /*
> >>> +      * The uhs2_reset_cmd_data callback is used to excute reset
> >>> +      * when a auto command error occurs.
> >>> +      */
> >>> +     void    (*uhs2_reset_cmd_data)(struct mmc_host *host);
> >>>  };
> >>>
> >>>  struct mmc_cqe_ops {
> >>
>
diff mbox series

Patch

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 68496c51a521..18642afc405f 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -403,6 +403,10 @@  void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq)
 	while (1) {
 		wait_for_completion(&mrq->completion);
 
+		if (host->ops->get_cd(host))
+			if (mrq->cmd->error || (mrq->data && mrq->data->error))
+				mmc_sd_uhs2_error_recovery(host, mrq);
+
 		cmd = mrq->cmd;
 
 		if (!cmd->error || !cmd->retries ||
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 920323faa834..259d47c8bb19 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -82,6 +82,7 @@  int mmc_attach_mmc(struct mmc_host *host);
 int mmc_attach_sd(struct mmc_host *host);
 int mmc_attach_sdio(struct mmc_host *host);
 int mmc_attach_sd_uhs2(struct mmc_host *host);
+void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq);
 
 /* Module parameters */
 extern bool use_spi_crc;
diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
index 85939a2582dc..d5acb4e6ccac 100644
--- a/drivers/mmc/core/sd_uhs2.c
+++ b/drivers/mmc/core/sd_uhs2.c
@@ -1324,3 +1324,83 @@  int mmc_attach_sd_uhs2(struct mmc_host *host)
 
 	return err;
 }
+
+static void sd_uhs2_abort_trans(struct mmc_host *mmc)
+{
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {0};
+	struct uhs2_command uhs2_cmd = {};
+	int err;
+
+	mrq.cmd = &cmd;
+	mmc->ongoing_mrq = &mrq;
+
+	uhs2_cmd.header = UHS2_NATIVE_PACKET | UHS2_PACKET_TYPE_CCMD |
+			  mmc->card->uhs2_config.node_id;
+	uhs2_cmd.arg = ((UHS2_DEV_CMD_TRANS_ABORT & 0xFF) << 8) |
+			UHS2_NATIVE_CMD_WRITE |
+			(UHS2_DEV_CMD_TRANS_ABORT >> 8);
+
+	sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
+	err = mmc_wait_for_cmd(mmc, &cmd, 0);
+
+	if (err)
+		pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
+		       mmc_hostname(mmc), __func__, err);
+}
+
+static void sd_uhs2_abort_status_read(struct mmc_host *mmc)
+{
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {0};
+	struct uhs2_command uhs2_cmd = {};
+	int err;
+
+	mrq.cmd = &cmd;
+	mmc->ongoing_mrq = &mrq;
+
+	uhs2_cmd.header = UHS2_NATIVE_PACKET |
+			  UHS2_PACKET_TYPE_CCMD |
+			  mmc->card->uhs2_config.node_id;
+	uhs2_cmd.arg = ((UHS2_DEV_STATUS_REG & 0xFF) << 8) |
+			UHS2_NATIVE_CMD_READ |
+			UHS2_NATIVE_CMD_PLEN_4B |
+			(UHS2_DEV_STATUS_REG >> 8);
+
+	sd_uhs2_cmd_assemble(&cmd, &uhs2_cmd, 0, 0);
+	err = mmc_wait_for_cmd(mmc, &cmd, 0);
+
+	if (err)
+		pr_err("%s: %s: UHS2 CMD send fail, err= 0x%x!\n",
+		       mmc_hostname(mmc), __func__, err);
+}
+
+void mmc_sd_uhs2_error_recovery(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	mmc->ops->uhs2_reset_cmd_data(mmc);
+
+	if (mrq->data) {
+		if (mrq->data->error && mmc_card_uhs2(mmc)) {
+			if (mrq->cmd) {
+				switch (mrq->cmd->error) {
+				case ETIMEDOUT:
+				case EILSEQ:
+				case EIO:
+					sd_uhs2_abort_trans(mmc);
+					sd_uhs2_abort_status_read(mmc);
+					break;
+				default:
+					break;
+				}
+			}
+		}
+	} else {
+		if (mrq->cmd) {
+			switch (mrq->cmd->error) {
+			case ETIMEDOUT:
+				sd_uhs2_abort_trans(mmc);
+				break;
+			}
+		}
+	}
+}
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index fc9520b3bfa4..c914a58f7e1e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -271,6 +271,12 @@  struct mmc_host_ops {
 	 * negative errno in case of a failure or zero for success.
 	 */
 	int	(*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
+
+	/*
+	 * The uhs2_reset_cmd_data callback is used to excute reset
+	 * when a auto command error occurs.
+	 */
+	void 	(*uhs2_reset_cmd_data)(struct mmc_host *host);
 };
 
 struct mmc_cqe_ops {