[v5,03/10] scsi: ufshpb: Add region's reads counter
diff mbox series

Message ID 20210302132503.224670-4-avri.altman@wdc.com
State New, archived
Headers show
Series
  • Add Host control mode to HPB
Related show

Commit Message

Avri Altman March 2, 2021, 1:24 p.m. UTC
In host control mode, reads are the major source of activation trials.
Keep track of those reads counters, for both active as well inactive
regions.

We reset the read counter upon write - we are only interested in "clean"
reads.  less intuitive however, is that we also reset it upon region's
deactivation.  Region deactivation is often due to the fact that
eviction took place: a region become active on the expense of another.
This is happening when the max-active-regions limit has crossed. If we
don’t reset the counter, we will trigger a lot of trashing of the HPB
database, since few reads (or even one) to the region that was
deactivated, will trigger a re-activation trial.

Keep those counters normalized, as we are using those reads as a
comparative score, to make various decisions.
If during consecutive normalizations an active region has exhaust its
reads - inactivate it.

Signed-off-by: Avri Altman <avri.altman@wdc.com>
---
 drivers/scsi/ufs/ufshpb.c | 102 ++++++++++++++++++++++++++++++++------
 drivers/scsi/ufs/ufshpb.h |   5 ++
 2 files changed, 92 insertions(+), 15 deletions(-)

Comments

Can Guo March 11, 2021, 7:52 a.m. UTC | #1
Hi Avri,

On 2021-03-02 21:24, Avri Altman wrote:
> In host control mode, reads are the major source of activation trials.
> Keep track of those reads counters, for both active as well inactive
> regions.
> 
> We reset the read counter upon write - we are only interested in 
> "clean"
> reads.  less intuitive however, is that we also reset it upon region's
> deactivation.  Region deactivation is often due to the fact that
> eviction took place: a region become active on the expense of another.
> This is happening when the max-active-regions limit has crossed. If we
> don’t reset the counter, we will trigger a lot of trashing of the HPB
> database, since few reads (or even one) to the region that was
> deactivated, will trigger a re-activation trial.
> 
> Keep those counters normalized, as we are using those reads as a
> comparative score, to make various decisions.
> If during consecutive normalizations an active region has exhaust its
> reads - inactivate it.
> 
> Signed-off-by: Avri Altman <avri.altman@wdc.com>
> ---
>  drivers/scsi/ufs/ufshpb.c | 102 ++++++++++++++++++++++++++++++++------
>  drivers/scsi/ufs/ufshpb.h |   5 ++
>  2 files changed, 92 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
> index 044fec9854a0..a8f8d13af21a 100644
> --- a/drivers/scsi/ufs/ufshpb.c
> +++ b/drivers/scsi/ufs/ufshpb.c
> @@ -16,6 +16,8 @@
>  #include "ufshpb.h"
>  #include "../sd.h"
> 
> +#define ACTIVATION_THRESHOLD 4 /* 4 IOs */

Can this param be added as a sysfs entry?

Thanks,
Can Guo

> +
>  /* memory management */
>  static struct kmem_cache *ufshpb_mctx_cache;
>  static mempool_t *ufshpb_mctx_pool;
> @@ -554,6 +556,21 @@ static int ufshpb_issue_pre_req(struct ufshpb_lu
> *hpb, struct scsi_cmnd *cmd,
>  	return ret;
>  }
> 
> +static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> +				      int srgn_idx)
> +{
> +	struct ufshpb_region *rgn;
> +	struct ufshpb_subregion *srgn;
> +
> +	rgn = hpb->rgn_tbl + rgn_idx;
> +	srgn = rgn->srgn_tbl + srgn_idx;
> +
> +	list_del_init(&rgn->list_inact_rgn);
> +
> +	if (list_empty(&srgn->list_act_srgn))
> +		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> +}
> +
>  /*
>   * This function will set up HPB read command using host-side L2P map 
> data.
>   */
> @@ -600,12 +617,44 @@ int ufshpb_prep(struct ufs_hba *hba, struct
> ufshcd_lrb *lrbp)
>  		ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				 transfer_len);
>  		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
> +
> +		if (hpb->is_hcm) {
> +			spin_lock_irqsave(&rgn->rgn_lock, flags);
> +			rgn->reads = 0;
> +			spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		}
> +
>  		return 0;
>  	}
> 
>  	if (!ufshpb_is_support_chunk(hpb, transfer_len))
>  		return 0;
> 
> +	if (hpb->is_hcm) {
> +		bool activate = false;
> +		/*
> +		 * in host control mode, reads are the main source for
> +		 * activation trials.
> +		 */
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads++;
> +		if (rgn->reads == ACTIVATION_THRESHOLD)
> +			activate = true;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		if (activate) {
> +			spin_lock_irqsave(&hpb->rsp_list_lock, flags);
> +			ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
> +			hpb->stats.rb_active_cnt++;
> +			spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
> +			dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
> +				"activate region %d-%d\n", rgn_idx, srgn_idx);
> +		}
> +
> +		/* keep those counters normalized */
> +		if (rgn->reads > hpb->entries_per_srgn)
> +			schedule_work(&hpb->ufshpb_normalization_work);
> +	}
> +
>  	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
>  	if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				   transfer_len)) {
> @@ -745,21 +794,6 @@ static int ufshpb_clear_dirty_bitmap(struct 
> ufshpb_lu *hpb,
>  	return 0;
>  }
> 
> -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> -				      int srgn_idx)
> -{
> -	struct ufshpb_region *rgn;
> -	struct ufshpb_subregion *srgn;
> -
> -	rgn = hpb->rgn_tbl + rgn_idx;
> -	srgn = rgn->srgn_tbl + srgn_idx;
> -
> -	list_del_init(&rgn->list_inact_rgn);
> -
> -	if (list_empty(&srgn->list_act_srgn))
> -		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> -}
> -
>  static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int 
> rgn_idx)
>  {
>  	struct ufshpb_region *rgn;
> @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct 
> ufshpb_lu *hpb,
> 
>  	ufshpb_cleanup_lru_info(lru_info, rgn);
> 
> +	if (hpb->is_hcm) {
> +		unsigned long flags;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = 0;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +	}
> +
>  	for_each_sub_region(rgn, srgn_idx, srgn)
>  		ufshpb_purge_active_subregion(hpb, srgn);
>  }
> @@ -1523,6 +1565,31 @@ static void
> ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
>  	spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>  }
> 
> +static void ufshpb_normalization_work_handler(struct work_struct 
> *work)
> +{
> +	struct ufshpb_lu *hpb;
> +	int rgn_idx;
> +	unsigned long flags;
> +
> +	hpb = container_of(work, struct ufshpb_lu, 
> ufshpb_normalization_work);
> +
> +	for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
> +		struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = (rgn->reads >> 1);
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +
> +		if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
> +			continue;
> +
> +		/* if region is active but has no reads - inactivate it */
> +		spin_lock(&hpb->rsp_list_lock);
> +		ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
> +		spin_unlock(&hpb->rsp_list_lock);
> +	}
> +}
> +
>  static void ufshpb_map_work_handler(struct work_struct *work)
>  {
>  	struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, 
> map_work);
> @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
> *hba, struct ufshpb_lu *hpb)
>  	INIT_LIST_HEAD(&hpb->list_hpb_lu);
> 
>  	INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
> +	if (hpb->is_hcm)
> +		INIT_WORK(&hpb->ufshpb_normalization_work,
> +			  ufshpb_normalization_work_handler);
> 
>  	hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
>  			  sizeof(struct ufshpb_req), 0, 0, NULL);
> @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
> ufshpb_lu *hpb)
> 
>  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
>  {
> +	if (hpb->is_hcm)
> +		cancel_work_sync(&hpb->ufshpb_normalization_work);
>  	cancel_work_sync(&hpb->map_work);
>  }
> 
> diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
> index 8119b1a3d1e5..bd4308010466 100644
> --- a/drivers/scsi/ufs/ufshpb.h
> +++ b/drivers/scsi/ufs/ufshpb.h
> @@ -121,6 +121,10 @@ struct ufshpb_region {
>  	struct list_head list_lru_rgn;
>  	unsigned long rgn_flags;
>  #define RGN_FLAG_DIRTY 0
> +
> +	/* region reads - for host mode */
> +	spinlock_t rgn_lock;
> +	unsigned int reads;
>  };
> 
>  #define for_each_sub_region(rgn, i, srgn)				\
> @@ -211,6 +215,7 @@ struct ufshpb_lu {
> 
>  	/* for selecting victim */
>  	struct victim_select_info lru_info;
> +	struct work_struct ufshpb_normalization_work;
> 
>  	/* pinned region information */
>  	u32 lu_pinned_start;
Avri Altman March 11, 2021, 8:04 a.m. UTC | #2
> > diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
> > index 044fec9854a0..a8f8d13af21a 100644
> > --- a/drivers/scsi/ufs/ufshpb.c
> > +++ b/drivers/scsi/ufs/ufshpb.c
> > @@ -16,6 +16,8 @@
> >  #include "ufshpb.h"
> >  #include "../sd.h"
> >
> > +#define ACTIVATION_THRESHOLD 4 /* 4 IOs */
> 
> Can this param be added as a sysfs entry?
Yes.
Daejun asked me that as well, so the last patch makes all logic parameter configurable.

Thanks,
Avri

> 
> Thanks,
> Can Guo
Can Guo March 11, 2021, 8:07 a.m. UTC | #3
On 2021-03-11 16:04, Avri Altman wrote:
>> > diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
>> > index 044fec9854a0..a8f8d13af21a 100644
>> > --- a/drivers/scsi/ufs/ufshpb.c
>> > +++ b/drivers/scsi/ufs/ufshpb.c
>> > @@ -16,6 +16,8 @@
>> >  #include "ufshpb.h"
>> >  #include "../sd.h"
>> >
>> > +#define ACTIVATION_THRESHOLD 4 /* 4 IOs */
>> 
>> Can this param be added as a sysfs entry?
> Yes.
> Daejun asked me that as well, so the last patch makes all logic
> parameter configurable.
> 
> Thanks,
> Avri
> 

Ok, thanks. I haven't reach the last one, absorbing them one by one.

Can Guo.

>> 
>> Thanks,
>> Can Guo
Can Guo March 15, 2021, 3:16 a.m. UTC | #4
Hi Avri,

On 2021-03-02 21:24, Avri Altman wrote:
> In host control mode, reads are the major source of activation trials.
> Keep track of those reads counters, for both active as well inactive
> regions.
> 
> We reset the read counter upon write - we are only interested in 
> "clean"
> reads.  less intuitive however, is that we also reset it upon region's
> deactivation.  Region deactivation is often due to the fact that
> eviction took place: a region become active on the expense of another.
> This is happening when the max-active-regions limit has crossed. If we
> don’t reset the counter, we will trigger a lot of trashing of the HPB
> database, since few reads (or even one) to the region that was
> deactivated, will trigger a re-activation trial.
> 
> Keep those counters normalized, as we are using those reads as a
> comparative score, to make various decisions.
> If during consecutive normalizations an active region has exhaust its
> reads - inactivate it.
> 
> Signed-off-by: Avri Altman <avri.altman@wdc.com>
> ---
>  drivers/scsi/ufs/ufshpb.c | 102 ++++++++++++++++++++++++++++++++------
>  drivers/scsi/ufs/ufshpb.h |   5 ++
>  2 files changed, 92 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
> index 044fec9854a0..a8f8d13af21a 100644
> --- a/drivers/scsi/ufs/ufshpb.c
> +++ b/drivers/scsi/ufs/ufshpb.c
> @@ -16,6 +16,8 @@
>  #include "ufshpb.h"
>  #include "../sd.h"
> 
> +#define ACTIVATION_THRESHOLD 4 /* 4 IOs */
> +
>  /* memory management */
>  static struct kmem_cache *ufshpb_mctx_cache;
>  static mempool_t *ufshpb_mctx_pool;
> @@ -554,6 +556,21 @@ static int ufshpb_issue_pre_req(struct ufshpb_lu
> *hpb, struct scsi_cmnd *cmd,
>  	return ret;
>  }
> 
> +static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> +				      int srgn_idx)
> +{
> +	struct ufshpb_region *rgn;
> +	struct ufshpb_subregion *srgn;
> +
> +	rgn = hpb->rgn_tbl + rgn_idx;
> +	srgn = rgn->srgn_tbl + srgn_idx;
> +
> +	list_del_init(&rgn->list_inact_rgn);
> +
> +	if (list_empty(&srgn->list_act_srgn))
> +		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> +}
> +
>  /*
>   * This function will set up HPB read command using host-side L2P map 
> data.
>   */
> @@ -600,12 +617,44 @@ int ufshpb_prep(struct ufs_hba *hba, struct
> ufshcd_lrb *lrbp)
>  		ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				 transfer_len);
>  		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
> +
> +		if (hpb->is_hcm) {
> +			spin_lock_irqsave(&rgn->rgn_lock, flags);

rgn_lock is never used in IRQ contexts, so no need of irqsave and
irqrestore everywhere, which can impact performance. Please correct
me if I am wrong.

Meanwhile, have you ever initialized the rgn_lock before use it???

Thanks,
Can Guo.

> +			rgn->reads = 0;
> +			spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		}
> +
>  		return 0;
>  	}
> 
>  	if (!ufshpb_is_support_chunk(hpb, transfer_len))
>  		return 0;
> 
> +	if (hpb->is_hcm) {
> +		bool activate = false;
> +		/*
> +		 * in host control mode, reads are the main source for
> +		 * activation trials.
> +		 */
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads++;
> +		if (rgn->reads == ACTIVATION_THRESHOLD)
> +			activate = true;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		if (activate) {
> +			spin_lock_irqsave(&hpb->rsp_list_lock, flags);
> +			ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
> +			hpb->stats.rb_active_cnt++;
> +			spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
> +			dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
> +				"activate region %d-%d\n", rgn_idx, srgn_idx);
> +		}
> +
> +		/* keep those counters normalized */
> +		if (rgn->reads > hpb->entries_per_srgn)
> +			schedule_work(&hpb->ufshpb_normalization_work);
> +	}
> +
>  	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
>  	if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				   transfer_len)) {
> @@ -745,21 +794,6 @@ static int ufshpb_clear_dirty_bitmap(struct 
> ufshpb_lu *hpb,
>  	return 0;
>  }
> 
> -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> -				      int srgn_idx)
> -{
> -	struct ufshpb_region *rgn;
> -	struct ufshpb_subregion *srgn;
> -
> -	rgn = hpb->rgn_tbl + rgn_idx;
> -	srgn = rgn->srgn_tbl + srgn_idx;
> -
> -	list_del_init(&rgn->list_inact_rgn);
> -
> -	if (list_empty(&srgn->list_act_srgn))
> -		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> -}
> -
>  static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int 
> rgn_idx)
>  {
>  	struct ufshpb_region *rgn;
> @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct 
> ufshpb_lu *hpb,
> 
>  	ufshpb_cleanup_lru_info(lru_info, rgn);
> 
> +	if (hpb->is_hcm) {
> +		unsigned long flags;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = 0;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +	}
> +
>  	for_each_sub_region(rgn, srgn_idx, srgn)
>  		ufshpb_purge_active_subregion(hpb, srgn);
>  }
> @@ -1523,6 +1565,31 @@ static void
> ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
>  	spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>  }
> 
> +static void ufshpb_normalization_work_handler(struct work_struct 
> *work)
> +{
> +	struct ufshpb_lu *hpb;
> +	int rgn_idx;
> +	unsigned long flags;
> +
> +	hpb = container_of(work, struct ufshpb_lu, 
> ufshpb_normalization_work);
> +
> +	for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
> +		struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = (rgn->reads >> 1);
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +
> +		if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
> +			continue;
> +
> +		/* if region is active but has no reads - inactivate it */
> +		spin_lock(&hpb->rsp_list_lock);
> +		ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
> +		spin_unlock(&hpb->rsp_list_lock);
> +	}
> +}
> +
>  static void ufshpb_map_work_handler(struct work_struct *work)
>  {
>  	struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, 
> map_work);
> @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
> *hba, struct ufshpb_lu *hpb)
>  	INIT_LIST_HEAD(&hpb->list_hpb_lu);
> 
>  	INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
> +	if (hpb->is_hcm)
> +		INIT_WORK(&hpb->ufshpb_normalization_work,
> +			  ufshpb_normalization_work_handler);
> 
>  	hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
>  			  sizeof(struct ufshpb_req), 0, 0, NULL);
> @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
> ufshpb_lu *hpb)
> 
>  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
>  {
> +	if (hpb->is_hcm)
> +		cancel_work_sync(&hpb->ufshpb_normalization_work);
>  	cancel_work_sync(&hpb->map_work);
>  }
> 
> diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
> index 8119b1a3d1e5..bd4308010466 100644
> --- a/drivers/scsi/ufs/ufshpb.h
> +++ b/drivers/scsi/ufs/ufshpb.h
> @@ -121,6 +121,10 @@ struct ufshpb_region {
>  	struct list_head list_lru_rgn;
>  	unsigned long rgn_flags;
>  #define RGN_FLAG_DIRTY 0
> +
> +	/* region reads - for host mode */
> +	spinlock_t rgn_lock;
> +	unsigned int reads;
>  };
> 
>  #define for_each_sub_region(rgn, i, srgn)				\
> @@ -211,6 +215,7 @@ struct ufshpb_lu {
> 
>  	/* for selecting victim */
>  	struct victim_select_info lru_info;
> +	struct work_struct ufshpb_normalization_work;
> 
>  	/* pinned region information */
>  	u32 lu_pinned_start;
Can Guo March 15, 2021, 8:40 a.m. UTC | #5
On 2021-03-02 21:24, Avri Altman wrote:
> In host control mode, reads are the major source of activation trials.
> Keep track of those reads counters, for both active as well inactive
> regions.
> 
> We reset the read counter upon write - we are only interested in 
> "clean"
> reads.  less intuitive however, is that we also reset it upon region's
> deactivation.  Region deactivation is often due to the fact that
> eviction took place: a region become active on the expense of another.
> This is happening when the max-active-regions limit has crossed. If we
> don’t reset the counter, we will trigger a lot of trashing of the HPB
> database, since few reads (or even one) to the region that was
> deactivated, will trigger a re-activation trial.
> 
> Keep those counters normalized, as we are using those reads as a
> comparative score, to make various decisions.
> If during consecutive normalizations an active region has exhaust its
> reads - inactivate it.
> 
> Signed-off-by: Avri Altman <avri.altman@wdc.com>
> ---
>  drivers/scsi/ufs/ufshpb.c | 102 ++++++++++++++++++++++++++++++++------
>  drivers/scsi/ufs/ufshpb.h |   5 ++
>  2 files changed, 92 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
> index 044fec9854a0..a8f8d13af21a 100644
> --- a/drivers/scsi/ufs/ufshpb.c
> +++ b/drivers/scsi/ufs/ufshpb.c
> @@ -16,6 +16,8 @@
>  #include "ufshpb.h"
>  #include "../sd.h"
> 
> +#define ACTIVATION_THRESHOLD 4 /* 4 IOs */
> +
>  /* memory management */
>  static struct kmem_cache *ufshpb_mctx_cache;
>  static mempool_t *ufshpb_mctx_pool;
> @@ -554,6 +556,21 @@ static int ufshpb_issue_pre_req(struct ufshpb_lu
> *hpb, struct scsi_cmnd *cmd,
>  	return ret;
>  }
> 
> +static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> +				      int srgn_idx)
> +{
> +	struct ufshpb_region *rgn;
> +	struct ufshpb_subregion *srgn;
> +
> +	rgn = hpb->rgn_tbl + rgn_idx;
> +	srgn = rgn->srgn_tbl + srgn_idx;
> +
> +	list_del_init(&rgn->list_inact_rgn);
> +
> +	if (list_empty(&srgn->list_act_srgn))
> +		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> +}
> +
>  /*
>   * This function will set up HPB read command using host-side L2P map 
> data.
>   */
> @@ -600,12 +617,44 @@ int ufshpb_prep(struct ufs_hba *hba, struct
> ufshcd_lrb *lrbp)
>  		ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				 transfer_len);
>  		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
> +
> +		if (hpb->is_hcm) {
> +			spin_lock_irqsave(&rgn->rgn_lock, flags);
> +			rgn->reads = 0;
> +			spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		}
> +
>  		return 0;
>  	}
> 
>  	if (!ufshpb_is_support_chunk(hpb, transfer_len))
>  		return 0;
> 
> +	if (hpb->is_hcm) {
> +		bool activate = false;
> +		/*
> +		 * in host control mode, reads are the main source for
> +		 * activation trials.
> +		 */
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads++;
> +		if (rgn->reads == ACTIVATION_THRESHOLD)
> +			activate = true;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +		if (activate) {
> +			spin_lock_irqsave(&hpb->rsp_list_lock, flags);
> +			ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
> +			hpb->stats.rb_active_cnt++;
> +			spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
> +			dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
> +				"activate region %d-%d\n", rgn_idx, srgn_idx);
> +		}
> +
> +		/* keep those counters normalized */
> +		if (rgn->reads > hpb->entries_per_srgn)
> +			schedule_work(&hpb->ufshpb_normalization_work);
> +	}
> +
>  	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
>  	if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>  				   transfer_len)) {
> @@ -745,21 +794,6 @@ static int ufshpb_clear_dirty_bitmap(struct 
> ufshpb_lu *hpb,
>  	return 0;
>  }
> 
> -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int 
> rgn_idx,
> -				      int srgn_idx)
> -{
> -	struct ufshpb_region *rgn;
> -	struct ufshpb_subregion *srgn;
> -
> -	rgn = hpb->rgn_tbl + rgn_idx;
> -	srgn = rgn->srgn_tbl + srgn_idx;
> -
> -	list_del_init(&rgn->list_inact_rgn);
> -
> -	if (list_empty(&srgn->list_act_srgn))
> -		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> -}
> -
>  static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int 
> rgn_idx)
>  {
>  	struct ufshpb_region *rgn;
> @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct 
> ufshpb_lu *hpb,
> 
>  	ufshpb_cleanup_lru_info(lru_info, rgn);
> 
> +	if (hpb->is_hcm) {
> +		unsigned long flags;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = 0;
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +	}
> +
>  	for_each_sub_region(rgn, srgn_idx, srgn)
>  		ufshpb_purge_active_subregion(hpb, srgn);
>  }
> @@ -1523,6 +1565,31 @@ static void
> ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
>  	spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>  }
> 
> +static void ufshpb_normalization_work_handler(struct work_struct 
> *work)
> +{
> +	struct ufshpb_lu *hpb;
> +	int rgn_idx;
> +	unsigned long flags;
> +
> +	hpb = container_of(work, struct ufshpb_lu, 
> ufshpb_normalization_work);
> +
> +	for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
> +		struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
> +
> +		spin_lock_irqsave(&rgn->rgn_lock, flags);
> +		rgn->reads = (rgn->reads >> 1);
> +		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> +
> +		if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
> +			continue;
> +
> +		/* if region is active but has no reads - inactivate it */
> +		spin_lock(&hpb->rsp_list_lock);
> +		ufshpb_update_inactive_info(hpb, rgn->rgn_idx);

Miss a hpb->stats.rb_inactive_cnt++ here?

Thanks,
Can Guo.

> +		spin_unlock(&hpb->rsp_list_lock);
> +	}
> +}
> +
>  static void ufshpb_map_work_handler(struct work_struct *work)
>  {
>  	struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, 
> map_work);
> @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
> *hba, struct ufshpb_lu *hpb)
>  	INIT_LIST_HEAD(&hpb->list_hpb_lu);
> 
>  	INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
> +	if (hpb->is_hcm)
> +		INIT_WORK(&hpb->ufshpb_normalization_work,
> +			  ufshpb_normalization_work_handler);
> 
>  	hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
>  			  sizeof(struct ufshpb_req), 0, 0, NULL);
> @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
> ufshpb_lu *hpb)
> 
>  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
>  {
> +	if (hpb->is_hcm)
> +		cancel_work_sync(&hpb->ufshpb_normalization_work);
>  	cancel_work_sync(&hpb->map_work);
>  }
> 
> diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
> index 8119b1a3d1e5..bd4308010466 100644
> --- a/drivers/scsi/ufs/ufshpb.h
> +++ b/drivers/scsi/ufs/ufshpb.h
> @@ -121,6 +121,10 @@ struct ufshpb_region {
>  	struct list_head list_lru_rgn;
>  	unsigned long rgn_flags;
>  #define RGN_FLAG_DIRTY 0
> +
> +	/* region reads - for host mode */
> +	spinlock_t rgn_lock;
> +	unsigned int reads;
>  };
> 
>  #define for_each_sub_region(rgn, i, srgn)				\
> @@ -211,6 +215,7 @@ struct ufshpb_lu {
> 
>  	/* for selecting victim */
>  	struct victim_select_info lru_info;
> +	struct work_struct ufshpb_normalization_work;
> 
>  	/* pinned region information */
>  	u32 lu_pinned_start;
Avri Altman March 15, 2021, 9:20 a.m. UTC | #6
> > +
> > +             if (hpb->is_hcm) {
> > +                     spin_lock_irqsave(&rgn->rgn_lock, flags);
> 
> rgn_lock is never used in IRQ contexts, so no need of irqsave and
> irqrestore everywhere, which can impact performance. Please correct
> me if I am wrong.
Thanks.  Will do.

> 
> Meanwhile, have you ever initialized the rgn_lock before use it???
Yep - forgot to do that here (but not in gs20 and mi10).  Thanks.

Thanks,
Avri

> 
> Thanks,
> Can Guo.
> 
> > +                     rgn->reads = 0;
> > +                     spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> > +             }
> > +
> >               return 0;
> >       }
> >
> >       if (!ufshpb_is_support_chunk(hpb, transfer_len))
> >               return 0;
> >
> > +     if (hpb->is_hcm) {
> > +             bool activate = false;
> > +             /*
> > +              * in host control mode, reads are the main source for
> > +              * activation trials.
> > +              */
> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
> > +             rgn->reads++;
> > +             if (rgn->reads == ACTIVATION_THRESHOLD)
> > +                     activate = true;
> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> > +             if (activate) {
> > +                     spin_lock_irqsave(&hpb->rsp_list_lock, flags);
> > +                     ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
> > +                     hpb->stats.rb_active_cnt++;
> > +                     spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
> > +                     dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
> > +                             "activate region %d-%d\n", rgn_idx, srgn_idx);
> > +             }
> > +
> > +             /* keep those counters normalized */
> > +             if (rgn->reads > hpb->entries_per_srgn)
> > +                     schedule_work(&hpb->ufshpb_normalization_work);
> > +     }
> > +
> >       spin_lock_irqsave(&hpb->rgn_state_lock, flags);
> >       if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
> >                                  transfer_len)) {
> > @@ -745,21 +794,6 @@ static int ufshpb_clear_dirty_bitmap(struct
> > ufshpb_lu *hpb,
> >       return 0;
> >  }
> >
> > -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int
> > rgn_idx,
> > -                                   int srgn_idx)
> > -{
> > -     struct ufshpb_region *rgn;
> > -     struct ufshpb_subregion *srgn;
> > -
> > -     rgn = hpb->rgn_tbl + rgn_idx;
> > -     srgn = rgn->srgn_tbl + srgn_idx;
> > -
> > -     list_del_init(&rgn->list_inact_rgn);
> > -
> > -     if (list_empty(&srgn->list_act_srgn))
> > -             list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
> > -}
> > -
> >  static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int
> > rgn_idx)
> >  {
> >       struct ufshpb_region *rgn;
> > @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct
> > ufshpb_lu *hpb,
> >
> >       ufshpb_cleanup_lru_info(lru_info, rgn);
> >
> > +     if (hpb->is_hcm) {
> > +             unsigned long flags;
> > +
> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
> > +             rgn->reads = 0;
> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> > +     }
> > +
> >       for_each_sub_region(rgn, srgn_idx, srgn)
> >               ufshpb_purge_active_subregion(hpb, srgn);
> >  }
> > @@ -1523,6 +1565,31 @@ static void
> > ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
> >       spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
> >  }
> >
> > +static void ufshpb_normalization_work_handler(struct work_struct
> > *work)
> > +{
> > +     struct ufshpb_lu *hpb;
> > +     int rgn_idx;
> > +     unsigned long flags;
> > +
> > +     hpb = container_of(work, struct ufshpb_lu,
> > ufshpb_normalization_work);
> > +
> > +     for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
> > +             struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
> > +
> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
> > +             rgn->reads = (rgn->reads >> 1);
> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> > +
> > +             if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
> > +                     continue;
> > +
> > +             /* if region is active but has no reads - inactivate it */
> > +             spin_lock(&hpb->rsp_list_lock);
> > +             ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
> > +             spin_unlock(&hpb->rsp_list_lock);
> > +     }
> > +}
> > +
> >  static void ufshpb_map_work_handler(struct work_struct *work)
> >  {
> >       struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu,
> > map_work);
> > @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
> > *hba, struct ufshpb_lu *hpb)
> >       INIT_LIST_HEAD(&hpb->list_hpb_lu);
> >
> >       INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
> > +     if (hpb->is_hcm)
> > +             INIT_WORK(&hpb->ufshpb_normalization_work,
> > +                       ufshpb_normalization_work_handler);
> >
> >       hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
> >                         sizeof(struct ufshpb_req), 0, 0, NULL);
> > @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
> > ufshpb_lu *hpb)
> >
> >  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
> >  {
> > +     if (hpb->is_hcm)
> > +             cancel_work_sync(&hpb->ufshpb_normalization_work);
> >       cancel_work_sync(&hpb->map_work);
> >  }
> >
> > diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
> > index 8119b1a3d1e5..bd4308010466 100644
> > --- a/drivers/scsi/ufs/ufshpb.h
> > +++ b/drivers/scsi/ufs/ufshpb.h
> > @@ -121,6 +121,10 @@ struct ufshpb_region {
> >       struct list_head list_lru_rgn;
> >       unsigned long rgn_flags;
> >  #define RGN_FLAG_DIRTY 0
> > +
> > +     /* region reads - for host mode */
> > +     spinlock_t rgn_lock;
> > +     unsigned int reads;
> >  };
> >
> >  #define for_each_sub_region(rgn, i, srgn)                            \
> > @@ -211,6 +215,7 @@ struct ufshpb_lu {
> >
> >       /* for selecting victim */
> >       struct victim_select_info lru_info;
> > +     struct work_struct ufshpb_normalization_work;
> >
> >       /* pinned region information */
> >       u32 lu_pinned_start;
Avri Altman March 15, 2021, 9:22 a.m. UTC | #7
> > +             /* if region is active but has no reads - inactivate it */
> > +             spin_lock(&hpb->rsp_list_lock);
> > +             ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
> 
> Miss a hpb->stats.rb_inactive_cnt++ here?
Thanks.
Also noticed that since rb_inactive_cnt and rb_active_cnt are incremented now in more than one place - 
Need to protect that.

Thanks,
Avri

> 
> Thanks,
> Can Guo.
> 
> > +             spin_unlock(&hpb->rsp_list_lock);
> > +     }
> > +}
> > +
> >  static void ufshpb_map_work_handler(struct work_struct *work)
> >  {
> >       struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu,
> > map_work);
> > @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
> > *hba, struct ufshpb_lu *hpb)
> >       INIT_LIST_HEAD(&hpb->list_hpb_lu);
> >
> >       INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
> > +     if (hpb->is_hcm)
> > +             INIT_WORK(&hpb->ufshpb_normalization_work,
> > +                       ufshpb_normalization_work_handler);
> >
> >       hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
> >                         sizeof(struct ufshpb_req), 0, 0, NULL);
> > @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
> > ufshpb_lu *hpb)
> >
> >  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
> >  {
> > +     if (hpb->is_hcm)
> > +             cancel_work_sync(&hpb->ufshpb_normalization_work);
> >       cancel_work_sync(&hpb->map_work);
> >  }
> >
> > diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
> > index 8119b1a3d1e5..bd4308010466 100644
> > --- a/drivers/scsi/ufs/ufshpb.h
> > +++ b/drivers/scsi/ufs/ufshpb.h
> > @@ -121,6 +121,10 @@ struct ufshpb_region {
> >       struct list_head list_lru_rgn;
> >       unsigned long rgn_flags;
> >  #define RGN_FLAG_DIRTY 0
> > +
> > +     /* region reads - for host mode */
> > +     spinlock_t rgn_lock;
> > +     unsigned int reads;
> >  };
> >
> >  #define for_each_sub_region(rgn, i, srgn)                            \
> > @@ -211,6 +215,7 @@ struct ufshpb_lu {
> >
> >       /* for selecting victim */
> >       struct victim_select_info lru_info;
> > +     struct work_struct ufshpb_normalization_work;
> >
> >       /* pinned region information */
> >       u32 lu_pinned_start;
Can Guo March 15, 2021, 9:31 a.m. UTC | #8
On 2021-03-15 17:20, Avri Altman wrote:
>> > +
>> > +             if (hpb->is_hcm) {
>> > +                     spin_lock_irqsave(&rgn->rgn_lock, flags);
>> 
>> rgn_lock is never used in IRQ contexts, so no need of irqsave and
>> irqrestore everywhere, which can impact performance. Please correct
>> me if I am wrong.
> Thanks.  Will do.
> 
>> 
>> Meanwhile, have you ever initialized the rgn_lock before use it???
> Yep - forgot to do that here (but not in gs20 and mi10).  Thanks.

You mean you didn't test this specific series before upload?
I haven't moved to the test stage, but this will definitely
cause you error...

Can Guo.

> 
> Thanks,
> Avri
> 
>> 
>> Thanks,
>> Can Guo.
>> 
>> > +                     rgn->reads = 0;
>> > +                     spin_unlock_irqrestore(&rgn->rgn_lock, flags);
>> > +             }
>> > +
>> >               return 0;
>> >       }
>> >
>> >       if (!ufshpb_is_support_chunk(hpb, transfer_len))
>> >               return 0;
>> >
>> > +     if (hpb->is_hcm) {
>> > +             bool activate = false;
>> > +             /*
>> > +              * in host control mode, reads are the main source for
>> > +              * activation trials.
>> > +              */
>> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
>> > +             rgn->reads++;
>> > +             if (rgn->reads == ACTIVATION_THRESHOLD)
>> > +                     activate = true;
>> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
>> > +             if (activate) {
>> > +                     spin_lock_irqsave(&hpb->rsp_list_lock, flags);
>> > +                     ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
>> > +                     hpb->stats.rb_active_cnt++;
>> > +                     spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>> > +                     dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
>> > +                             "activate region %d-%d\n", rgn_idx, srgn_idx);
>> > +             }
>> > +
>> > +             /* keep those counters normalized */
>> > +             if (rgn->reads > hpb->entries_per_srgn)
>> > +                     schedule_work(&hpb->ufshpb_normalization_work);
>> > +     }
>> > +
>> >       spin_lock_irqsave(&hpb->rgn_state_lock, flags);
>> >       if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
>> >                                  transfer_len)) {
>> > @@ -745,21 +794,6 @@ static int ufshpb_clear_dirty_bitmap(struct
>> > ufshpb_lu *hpb,
>> >       return 0;
>> >  }
>> >
>> > -static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int
>> > rgn_idx,
>> > -                                   int srgn_idx)
>> > -{
>> > -     struct ufshpb_region *rgn;
>> > -     struct ufshpb_subregion *srgn;
>> > -
>> > -     rgn = hpb->rgn_tbl + rgn_idx;
>> > -     srgn = rgn->srgn_tbl + srgn_idx;
>> > -
>> > -     list_del_init(&rgn->list_inact_rgn);
>> > -
>> > -     if (list_empty(&srgn->list_act_srgn))
>> > -             list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
>> > -}
>> > -
>> >  static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int
>> > rgn_idx)
>> >  {
>> >       struct ufshpb_region *rgn;
>> > @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct
>> > ufshpb_lu *hpb,
>> >
>> >       ufshpb_cleanup_lru_info(lru_info, rgn);
>> >
>> > +     if (hpb->is_hcm) {
>> > +             unsigned long flags;
>> > +
>> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
>> > +             rgn->reads = 0;
>> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
>> > +     }
>> > +
>> >       for_each_sub_region(rgn, srgn_idx, srgn)
>> >               ufshpb_purge_active_subregion(hpb, srgn);
>> >  }
>> > @@ -1523,6 +1565,31 @@ static void
>> > ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
>> >       spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>> >  }
>> >
>> > +static void ufshpb_normalization_work_handler(struct work_struct
>> > *work)
>> > +{
>> > +     struct ufshpb_lu *hpb;
>> > +     int rgn_idx;
>> > +     unsigned long flags;
>> > +
>> > +     hpb = container_of(work, struct ufshpb_lu,
>> > ufshpb_normalization_work);
>> > +
>> > +     for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
>> > +             struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
>> > +
>> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
>> > +             rgn->reads = (rgn->reads >> 1);
>> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
>> > +
>> > +             if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
>> > +                     continue;
>> > +
>> > +             /* if region is active but has no reads - inactivate it */
>> > +             spin_lock(&hpb->rsp_list_lock);
>> > +             ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
>> > +             spin_unlock(&hpb->rsp_list_lock);
>> > +     }
>> > +}
>> > +
>> >  static void ufshpb_map_work_handler(struct work_struct *work)
>> >  {
>> >       struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu,
>> > map_work);
>> > @@ -1913,6 +1980,9 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
>> > *hba, struct ufshpb_lu *hpb)
>> >       INIT_LIST_HEAD(&hpb->list_hpb_lu);
>> >
>> >       INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
>> > +     if (hpb->is_hcm)
>> > +             INIT_WORK(&hpb->ufshpb_normalization_work,
>> > +                       ufshpb_normalization_work_handler);
>> >
>> >       hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
>> >                         sizeof(struct ufshpb_req), 0, 0, NULL);
>> > @@ -2012,6 +2082,8 @@ static void ufshpb_discard_rsp_lists(struct
>> > ufshpb_lu *hpb)
>> >
>> >  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
>> >  {
>> > +     if (hpb->is_hcm)
>> > +             cancel_work_sync(&hpb->ufshpb_normalization_work);
>> >       cancel_work_sync(&hpb->map_work);
>> >  }
>> >
>> > diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
>> > index 8119b1a3d1e5..bd4308010466 100644
>> > --- a/drivers/scsi/ufs/ufshpb.h
>> > +++ b/drivers/scsi/ufs/ufshpb.h
>> > @@ -121,6 +121,10 @@ struct ufshpb_region {
>> >       struct list_head list_lru_rgn;
>> >       unsigned long rgn_flags;
>> >  #define RGN_FLAG_DIRTY 0
>> > +
>> > +     /* region reads - for host mode */
>> > +     spinlock_t rgn_lock;
>> > +     unsigned int reads;
>> >  };
>> >
>> >  #define for_each_sub_region(rgn, i, srgn)                            \
>> > @@ -211,6 +215,7 @@ struct ufshpb_lu {
>> >
>> >       /* for selecting victim */
>> >       struct victim_select_info lru_info;
>> > +     struct work_struct ufshpb_normalization_work;
>> >
>> >       /* pinned region information */
>> >       u32 lu_pinned_start;
Avri Altman March 17, 2021, 9:19 a.m. UTC | #9
> >> > @@ -1079,6 +1113,14 @@ static void __ufshpb_evict_region(struct
> >> > ufshpb_lu *hpb,
> >> >
> >> >       ufshpb_cleanup_lru_info(lru_info, rgn);
> >> >
> >> > +     if (hpb->is_hcm) {
> >> > +             unsigned long flags;
> >> > +
> >> > +             spin_lock_irqsave(&rgn->rgn_lock, flags);
> >> > +             rgn->reads = 0;
> >> > +             spin_unlock_irqrestore(&rgn->rgn_lock, flags);
> >> > +     }
> >> > +
While at it, Following your comments concerning the unmap request,
Better move this as well outside of __ufshpb_evict_region while rgn_state_lock is not held.

Thanks,
Avri

Patch
diff mbox series

diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 044fec9854a0..a8f8d13af21a 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -16,6 +16,8 @@ 
 #include "ufshpb.h"
 #include "../sd.h"
 
+#define ACTIVATION_THRESHOLD 4 /* 4 IOs */
+
 /* memory management */
 static struct kmem_cache *ufshpb_mctx_cache;
 static mempool_t *ufshpb_mctx_pool;
@@ -554,6 +556,21 @@  static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
 	return ret;
 }
 
+static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int rgn_idx,
+				      int srgn_idx)
+{
+	struct ufshpb_region *rgn;
+	struct ufshpb_subregion *srgn;
+
+	rgn = hpb->rgn_tbl + rgn_idx;
+	srgn = rgn->srgn_tbl + srgn_idx;
+
+	list_del_init(&rgn->list_inact_rgn);
+
+	if (list_empty(&srgn->list_act_srgn))
+		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
+}
+
 /*
  * This function will set up HPB read command using host-side L2P map data.
  */
@@ -600,12 +617,44 @@  int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 		ufshpb_set_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
 				 transfer_len);
 		spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
+
+		if (hpb->is_hcm) {
+			spin_lock_irqsave(&rgn->rgn_lock, flags);
+			rgn->reads = 0;
+			spin_unlock_irqrestore(&rgn->rgn_lock, flags);
+		}
+
 		return 0;
 	}
 
 	if (!ufshpb_is_support_chunk(hpb, transfer_len))
 		return 0;
 
+	if (hpb->is_hcm) {
+		bool activate = false;
+		/*
+		 * in host control mode, reads are the main source for
+		 * activation trials.
+		 */
+		spin_lock_irqsave(&rgn->rgn_lock, flags);
+		rgn->reads++;
+		if (rgn->reads == ACTIVATION_THRESHOLD)
+			activate = true;
+		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
+		if (activate) {
+			spin_lock_irqsave(&hpb->rsp_list_lock, flags);
+			ufshpb_update_active_info(hpb, rgn_idx, srgn_idx);
+			hpb->stats.rb_active_cnt++;
+			spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
+			dev_dbg(&hpb->sdev_ufs_lu->sdev_dev,
+				"activate region %d-%d\n", rgn_idx, srgn_idx);
+		}
+
+		/* keep those counters normalized */
+		if (rgn->reads > hpb->entries_per_srgn)
+			schedule_work(&hpb->ufshpb_normalization_work);
+	}
+
 	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
 	if (ufshpb_test_ppn_dirty(hpb, rgn_idx, srgn_idx, srgn_offset,
 				   transfer_len)) {
@@ -745,21 +794,6 @@  static int ufshpb_clear_dirty_bitmap(struct ufshpb_lu *hpb,
 	return 0;
 }
 
-static void ufshpb_update_active_info(struct ufshpb_lu *hpb, int rgn_idx,
-				      int srgn_idx)
-{
-	struct ufshpb_region *rgn;
-	struct ufshpb_subregion *srgn;
-
-	rgn = hpb->rgn_tbl + rgn_idx;
-	srgn = rgn->srgn_tbl + srgn_idx;
-
-	list_del_init(&rgn->list_inact_rgn);
-
-	if (list_empty(&srgn->list_act_srgn))
-		list_add_tail(&srgn->list_act_srgn, &hpb->lh_act_srgn);
-}
-
 static void ufshpb_update_inactive_info(struct ufshpb_lu *hpb, int rgn_idx)
 {
 	struct ufshpb_region *rgn;
@@ -1079,6 +1113,14 @@  static void __ufshpb_evict_region(struct ufshpb_lu *hpb,
 
 	ufshpb_cleanup_lru_info(lru_info, rgn);
 
+	if (hpb->is_hcm) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&rgn->rgn_lock, flags);
+		rgn->reads = 0;
+		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
+	}
+
 	for_each_sub_region(rgn, srgn_idx, srgn)
 		ufshpb_purge_active_subregion(hpb, srgn);
 }
@@ -1523,6 +1565,31 @@  static void ufshpb_run_inactive_region_list(struct ufshpb_lu *hpb)
 	spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
 }
 
+static void ufshpb_normalization_work_handler(struct work_struct *work)
+{
+	struct ufshpb_lu *hpb;
+	int rgn_idx;
+	unsigned long flags;
+
+	hpb = container_of(work, struct ufshpb_lu, ufshpb_normalization_work);
+
+	for (rgn_idx = 0; rgn_idx < hpb->rgns_per_lu; rgn_idx++) {
+		struct ufshpb_region *rgn = hpb->rgn_tbl + rgn_idx;
+
+		spin_lock_irqsave(&rgn->rgn_lock, flags);
+		rgn->reads = (rgn->reads >> 1);
+		spin_unlock_irqrestore(&rgn->rgn_lock, flags);
+
+		if (rgn->rgn_state != HPB_RGN_ACTIVE || rgn->reads)
+			continue;
+
+		/* if region is active but has no reads - inactivate it */
+		spin_lock(&hpb->rsp_list_lock);
+		ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
+		spin_unlock(&hpb->rsp_list_lock);
+	}
+}
+
 static void ufshpb_map_work_handler(struct work_struct *work)
 {
 	struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu, map_work);
@@ -1913,6 +1980,9 @@  static int ufshpb_lu_hpb_init(struct ufs_hba *hba, struct ufshpb_lu *hpb)
 	INIT_LIST_HEAD(&hpb->list_hpb_lu);
 
 	INIT_WORK(&hpb->map_work, ufshpb_map_work_handler);
+	if (hpb->is_hcm)
+		INIT_WORK(&hpb->ufshpb_normalization_work,
+			  ufshpb_normalization_work_handler);
 
 	hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
 			  sizeof(struct ufshpb_req), 0, 0, NULL);
@@ -2012,6 +2082,8 @@  static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb)
 
 static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
 {
+	if (hpb->is_hcm)
+		cancel_work_sync(&hpb->ufshpb_normalization_work);
 	cancel_work_sync(&hpb->map_work);
 }
 
diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
index 8119b1a3d1e5..bd4308010466 100644
--- a/drivers/scsi/ufs/ufshpb.h
+++ b/drivers/scsi/ufs/ufshpb.h
@@ -121,6 +121,10 @@  struct ufshpb_region {
 	struct list_head list_lru_rgn;
 	unsigned long rgn_flags;
 #define RGN_FLAG_DIRTY 0
+
+	/* region reads - for host mode */
+	spinlock_t rgn_lock;
+	unsigned int reads;
 };
 
 #define for_each_sub_region(rgn, i, srgn)				\
@@ -211,6 +215,7 @@  struct ufshpb_lu {
 
 	/* for selecting victim */
 	struct victim_select_info lru_info;
+	struct work_struct ufshpb_normalization_work;
 
 	/* pinned region information */
 	u32 lu_pinned_start;