| Message ID | 20230803054544.22007-1-wenchao.chen@unisoc.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | mmc: queue: replace immediate with hsq->depth | expand |
On Thu, 3 Aug 2023 at 07:46, Wenchao Chen <wenchao.chen@unisoc.com> wrote: > > Hsq is similar to cqe, using hsq->depth to represent > the maximum processing capacity of hsq. We can adjust > hsq->depth according to the actual situation. Sorry, but I don't quite follow here. Are you planning to update the host->hsq_depth dynamically from somewhere? Kind regards Uffe > > Signed-off-by: Wenchao Chen <wenchao.chen@unisoc.com> > --- > drivers/mmc/core/queue.c | 6 +----- > drivers/mmc/host/mmc_hsq.c | 1 + > drivers/mmc/host/mmc_hsq.h | 7 +++++++ > include/linux/mmc/host.h | 1 + > 4 files changed, 10 insertions(+), 5 deletions(-) > > diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c > index b396e3900717..a0a2412f62a7 100644 > --- a/drivers/mmc/core/queue.c > +++ b/drivers/mmc/core/queue.c > @@ -260,11 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, > } > break; > case MMC_ISSUE_ASYNC: > - /* > - * For MMC host software queue, we only allow 2 requests in > - * flight to avoid a long latency. > - */ > - if (host->hsq_enabled && mq->in_flight[issue_type] > 2) { > + if (host->hsq_enabled && mq->in_flight[issue_type] > host->hsq_depth) { > spin_unlock_irq(&mq->lock); > return BLK_STS_RESOURCE; > } > diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c > index 424dc7b07858..7b3952721c17 100644 > --- a/drivers/mmc/host/mmc_hsq.c > +++ b/drivers/mmc/host/mmc_hsq.c > @@ -337,6 +337,7 @@ int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc) > hsq->mmc = mmc; > hsq->mmc->cqe_private = hsq; > mmc->cqe_ops = &mmc_hsq_ops; > + mmc->hsq_depth = HSQ_MAX_DEPTH; > > for (i = 0; i < HSQ_NUM_SLOTS; i++) > hsq->tag_slot[i] = HSQ_INVALID_TAG; > diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h > index 1808024fc6c5..795f6b9421d7 100644 > --- a/drivers/mmc/host/mmc_hsq.h > +++ b/drivers/mmc/host/mmc_hsq.h > @@ -5,6 +5,13 @@ > #define HSQ_NUM_SLOTS 64 > #define HSQ_INVALID_TAG HSQ_NUM_SLOTS > > +/* > + * For MMC host software queue, we usually allow 2 requests in > + * flight to avoid a long latency. But we can adjust hsq->depth > + * according to the actual situation. > + */ > +#define HSQ_MAX_DEPTH 2 > + > struct hsq_slot { > struct mmc_request *mrq; > }; > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h > index 461d1543893b..1fd8b1dd8698 100644 > --- a/include/linux/mmc/host.h > +++ b/include/linux/mmc/host.h > @@ -520,6 +520,7 @@ struct mmc_host { > > /* Host Software Queue support */ > bool hsq_enabled; > + int hsq_depth; > > u32 err_stats[MMC_ERR_MAX]; > unsigned long private[] ____cacheline_aligned; > -- > 2.17.1 >
On Tue, Aug 8, 2023 at 5:28 PM Ulf Hansson <ulf.hansson@linaro.org> wrote: > > On Thu, 3 Aug 2023 at 07:46, Wenchao Chen <wenchao.chen@unisoc.com> wrote: > > > > Hsq is similar to cqe, using hsq->depth to represent > > the maximum processing capacity of hsq. We can adjust > > hsq->depth according to the actual situation. > > Sorry, but I don't quite follow here. > > Are you planning to update the host->hsq_depth dynamically from somewhere? > > Kind regards > Uffe > Hi Uffe, Depending on the mmc device, some devices allow host to send more reqs to the device. Also, we use hsq->hsq_depth instead of immediate number "2" to make the code easier to understand. Thanks Wenchao.Chen > > > > Signed-off-by: Wenchao Chen <wenchao.chen@unisoc.com> > > --- > > drivers/mmc/core/queue.c | 6 +----- > > drivers/mmc/host/mmc_hsq.c | 1 + > > drivers/mmc/host/mmc_hsq.h | 7 +++++++ > > include/linux/mmc/host.h | 1 + > > 4 files changed, 10 insertions(+), 5 deletions(-) > > > > diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c > > index b396e3900717..a0a2412f62a7 100644 > > --- a/drivers/mmc/core/queue.c > > +++ b/drivers/mmc/core/queue.c > > @@ -260,11 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, > > } > > break; > > case MMC_ISSUE_ASYNC: > > - /* > > - * For MMC host software queue, we only allow 2 requests in > > - * flight to avoid a long latency. > > - */ > > - if (host->hsq_enabled && mq->in_flight[issue_type] > 2) { > > + if (host->hsq_enabled && mq->in_flight[issue_type] > host->hsq_depth) { > > spin_unlock_irq(&mq->lock); > > return BLK_STS_RESOURCE; > > } > > diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c > > index 424dc7b07858..7b3952721c17 100644 > > --- a/drivers/mmc/host/mmc_hsq.c > > +++ b/drivers/mmc/host/mmc_hsq.c > > @@ -337,6 +337,7 @@ int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc) > > hsq->mmc = mmc; > > hsq->mmc->cqe_private = hsq; > > mmc->cqe_ops = &mmc_hsq_ops; > > + mmc->hsq_depth = HSQ_MAX_DEPTH; > > > > for (i = 0; i < HSQ_NUM_SLOTS; i++) > > hsq->tag_slot[i] = HSQ_INVALID_TAG; > > diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h > > index 1808024fc6c5..795f6b9421d7 100644 > > --- a/drivers/mmc/host/mmc_hsq.h > > +++ b/drivers/mmc/host/mmc_hsq.h > > @@ -5,6 +5,13 @@ > > #define HSQ_NUM_SLOTS 64 > > #define HSQ_INVALID_TAG HSQ_NUM_SLOTS > > > > +/* > > + * For MMC host software queue, we usually allow 2 requests in > > + * flight to avoid a long latency. But we can adjust hsq->depth > > + * according to the actual situation. > > + */ > > +#define HSQ_MAX_DEPTH 2 > > + > > struct hsq_slot { > > struct mmc_request *mrq; > > }; > > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h > > index 461d1543893b..1fd8b1dd8698 100644 > > --- a/include/linux/mmc/host.h > > +++ b/include/linux/mmc/host.h > > @@ -520,6 +520,7 @@ struct mmc_host { > > > > /* Host Software Queue support */ > > bool hsq_enabled; > > + int hsq_depth; > > > > u32 err_stats[MMC_ERR_MAX]; > > unsigned long private[] ____cacheline_aligned; > > -- > > 2.17.1 > >
On Tue, 8 Aug 2023 at 12:41, Wenchao Chen <wenchao.chen666@gmail.com> wrote: > > On Tue, Aug 8, 2023 at 5:28 PM Ulf Hansson <ulf.hansson@linaro.org> wrote: > > > > On Thu, 3 Aug 2023 at 07:46, Wenchao Chen <wenchao.chen@unisoc.com> wrote: > > > > > > Hsq is similar to cqe, using hsq->depth to represent > > > the maximum processing capacity of hsq. We can adjust > > > hsq->depth according to the actual situation. > > > > Sorry, but I don't quite follow here. > > > > Are you planning to update the host->hsq_depth dynamically from somewhere? > > > > Kind regards > > Uffe > > > Hi Uffe, > Depending on the mmc device, some devices allow host to send more reqs > to the device. In that case, please add a patch for that too, to show how this is going to be useful. > Also, we use hsq->hsq_depth instead of immediate number "2" to make > the code easier to understand. Right, but we don't need a new member in struct mmc_host for that. We could just be checking HSQ_MAX_DEPTH instead. Kind regards Uffe > > Thanks > Wenchao.Chen > > > > > > Signed-off-by: Wenchao Chen <wenchao.chen@unisoc.com> > > > --- > > > drivers/mmc/core/queue.c | 6 +----- > > > drivers/mmc/host/mmc_hsq.c | 1 + > > > drivers/mmc/host/mmc_hsq.h | 7 +++++++ > > > include/linux/mmc/host.h | 1 + > > > 4 files changed, 10 insertions(+), 5 deletions(-) > > > > > > diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c > > > index b396e3900717..a0a2412f62a7 100644 > > > --- a/drivers/mmc/core/queue.c > > > +++ b/drivers/mmc/core/queue.c > > > @@ -260,11 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, > > > } > > > break; > > > case MMC_ISSUE_ASYNC: > > > - /* > > > - * For MMC host software queue, we only allow 2 requests in > > > - * flight to avoid a long latency. > > > - */ > > > - if (host->hsq_enabled && mq->in_flight[issue_type] > 2) { > > > + if (host->hsq_enabled && mq->in_flight[issue_type] > host->hsq_depth) { > > > spin_unlock_irq(&mq->lock); > > > return BLK_STS_RESOURCE; > > > } > > > diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c > > > index 424dc7b07858..7b3952721c17 100644 > > > --- a/drivers/mmc/host/mmc_hsq.c > > > +++ b/drivers/mmc/host/mmc_hsq.c > > > @@ -337,6 +337,7 @@ int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc) > > > hsq->mmc = mmc; > > > hsq->mmc->cqe_private = hsq; > > > mmc->cqe_ops = &mmc_hsq_ops; > > > + mmc->hsq_depth = HSQ_MAX_DEPTH; > > > > > > for (i = 0; i < HSQ_NUM_SLOTS; i++) > > > hsq->tag_slot[i] = HSQ_INVALID_TAG; > > > diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h > > > index 1808024fc6c5..795f6b9421d7 100644 > > > --- a/drivers/mmc/host/mmc_hsq.h > > > +++ b/drivers/mmc/host/mmc_hsq.h > > > @@ -5,6 +5,13 @@ > > > #define HSQ_NUM_SLOTS 64 > > > #define HSQ_INVALID_TAG HSQ_NUM_SLOTS > > > > > > +/* > > > + * For MMC host software queue, we usually allow 2 requests in > > > + * flight to avoid a long latency. But we can adjust hsq->depth > > > + * according to the actual situation. > > > + */ > > > +#define HSQ_MAX_DEPTH 2 > > > + > > > struct hsq_slot { > > > struct mmc_request *mrq; > > > }; > > > diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h > > > index 461d1543893b..1fd8b1dd8698 100644 > > > --- a/include/linux/mmc/host.h > > > +++ b/include/linux/mmc/host.h > > > @@ -520,6 +520,7 @@ struct mmc_host { > > > > > > /* Host Software Queue support */ > > > bool hsq_enabled; > > > + int hsq_depth; > > > > > > u32 err_stats[MMC_ERR_MAX]; > > > unsigned long private[] ____cacheline_aligned; > > > -- > > > 2.17.1 > > >
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index b396e3900717..a0a2412f62a7 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -260,11 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, } break; case MMC_ISSUE_ASYNC: - /* - * For MMC host software queue, we only allow 2 requests in - * flight to avoid a long latency. - */ - if (host->hsq_enabled && mq->in_flight[issue_type] > 2) { + if (host->hsq_enabled && mq->in_flight[issue_type] > host->hsq_depth) { spin_unlock_irq(&mq->lock); return BLK_STS_RESOURCE; } diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c index 424dc7b07858..7b3952721c17 100644 --- a/drivers/mmc/host/mmc_hsq.c +++ b/drivers/mmc/host/mmc_hsq.c @@ -337,6 +337,7 @@ int mmc_hsq_init(struct mmc_hsq *hsq, struct mmc_host *mmc) hsq->mmc = mmc; hsq->mmc->cqe_private = hsq; mmc->cqe_ops = &mmc_hsq_ops; + mmc->hsq_depth = HSQ_MAX_DEPTH; for (i = 0; i < HSQ_NUM_SLOTS; i++) hsq->tag_slot[i] = HSQ_INVALID_TAG; diff --git a/drivers/mmc/host/mmc_hsq.h b/drivers/mmc/host/mmc_hsq.h index 1808024fc6c5..795f6b9421d7 100644 --- a/drivers/mmc/host/mmc_hsq.h +++ b/drivers/mmc/host/mmc_hsq.h @@ -5,6 +5,13 @@ #define HSQ_NUM_SLOTS 64 #define HSQ_INVALID_TAG HSQ_NUM_SLOTS +/* + * For MMC host software queue, we usually allow 2 requests in + * flight to avoid a long latency. But we can adjust hsq->depth + * according to the actual situation. + */ +#define HSQ_MAX_DEPTH 2 + struct hsq_slot { struct mmc_request *mrq; }; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 461d1543893b..1fd8b1dd8698 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -520,6 +520,7 @@ struct mmc_host { /* Host Software Queue support */ bool hsq_enabled; + int hsq_depth; u32 err_stats[MMC_ERR_MAX]; unsigned long private[] ____cacheline_aligned;
Hsq is similar to cqe, using hsq->depth to represent the maximum processing capacity of hsq. We can adjust hsq->depth according to the actual situation. Signed-off-by: Wenchao Chen <wenchao.chen@unisoc.com> --- drivers/mmc/core/queue.c | 6 +----- drivers/mmc/host/mmc_hsq.c | 1 + drivers/mmc/host/mmc_hsq.h | 7 +++++++ include/linux/mmc/host.h | 1 + 4 files changed, 10 insertions(+), 5 deletions(-)