Re: [PATCH v5 07/10] scsi: ufshpb: Add "Cold" regions timer

[Can Guo <cang@codeaurora.org>]

On 2021-03-16 17:21, Avri Altman wrote:
>> > +static void ufshpb_read_to_handler(struct work_struct *work)
>> > +{
>> > +     struct delayed_work *dwork = to_delayed_work(work);
>> > +     struct ufshpb_lu *hpb;
>> > +     struct victim_select_info *lru_info;
>> > +     struct ufshpb_region *rgn;
>> > +     unsigned long flags;
>> > +     LIST_HEAD(expired_list);
>> > +
>> > +     hpb = container_of(dwork, struct ufshpb_lu, ufshpb_read_to_work);
>> > +
>> > +     spin_lock_irqsave(&hpb->rgn_state_lock, flags);
>> > +
>> > +     lru_info = &hpb->lru_info;
>> > +
>> > +     list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) {
>> > +             bool timedout = ktime_after(ktime_get(), rgn->read_timeout);
>> > +
>> > +             if (timedout) {
>> > +                     rgn->read_timeout_expiries--;
>> > +                     if (is_rgn_dirty(rgn) ||
>> > +                         rgn->read_timeout_expiries == 0)
>> > +                             list_add(&rgn->list_expired_rgn, &expired_list);
>> > +                     else
>> > +                             rgn->read_timeout = ktime_add_ms(ktime_get(),
>> > +                                                      READ_TO_MS);
>> > +             }
>> > +     }
>> > +
>> > +     spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
>> > +
>> > +     list_for_each_entry(rgn, &expired_list, list_expired_rgn) {
>> 
>> Here can be problematic - since you don't have the native expired_list
>> initialized
>> before use, if above loop did not insert anything to expired_list, it
>> shall become
>> a dead loop here.
> Not sure what you meant by native initialization.
> LIST_HEAD is statically initializing an empty list, resulting the same
> outcome as INIT_LIST_HEAD.
> 

Sorry for making you confused, you should use list_for_each_entry_safe()
instead of list_for_each_entry() as you are deleting entries within the 
loop,
otherwise, this can become an infinite loop. Again, have you tested this 
patch
before upload? I am sure this is problematic - when it becomes an 
inifinite
loop, below path will hang...

ufshcd_suspend()->ufshpb_suspend()->cancel_jobs()->cancel_delayed_work()

>> 
>> And, which lock is protecting rgn->list_expired_rgn? If two
>> read_to_handler works
>> are running in parallel, one can be inserting it to its expired_list
>> while another
>> can be deleting it.
> The timeout handler, being a delayed work, is meant to run every 
> polling period.
> Originally, I had it protected from 2 handlers running concurrently,
> But I removed it following Daejun's comment, which I accepted,
> Since it is always scheduled using the same polling period.

But one can set the delay to 0 through sysfs, right?

Thanks,
Can Guo.

> 
> Thanks,
> Avri
> 
>> 
>> Can Guo.
>> 
>> > +             list_del_init(&rgn->list_expired_rgn);
>> > +             spin_lock_irqsave(&hpb->rsp_list_lock, flags);
>> > +             ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
>> > +             hpb->stats.rb_inactive_cnt++;
>> > +             spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
>> > +     }
>> > +
>> > +     ufshpb_kick_map_work(hpb);
>> > +
>> > +     schedule_delayed_work(&hpb->ufshpb_read_to_work,
>> > +                           msecs_to_jiffies(POLLING_INTERVAL_MS));
>> > +}
>> > +
>> >  static void ufshpb_add_lru_info(struct victim_select_info *lru_info,
>> >                               struct ufshpb_region *rgn)
>> >  {
>> >       rgn->rgn_state = HPB_RGN_ACTIVE;
>> >       list_add_tail(&rgn->list_lru_rgn, &lru_info->lh_lru_rgn);
>> >       atomic_inc(&lru_info->active_cnt);
>> > +     if (rgn->hpb->is_hcm) {
>> > +             rgn->read_timeout = ktime_add_ms(ktime_get(), READ_TO_MS);
>> > +             rgn->read_timeout_expiries = READ_TO_EXPIRIES;
>> > +     }
>> >  }
>> >
>> >  static void ufshpb_hit_lru_info(struct victim_select_info *lru_info,
>> > @@ -1813,6 +1865,7 @@ static int ufshpb_alloc_region_tbl(struct
>> > ufs_hba *hba, struct ufshpb_lu *hpb)
>> >
>> >               INIT_LIST_HEAD(&rgn->list_inact_rgn);
>> >               INIT_LIST_HEAD(&rgn->list_lru_rgn);
>> > +             INIT_LIST_HEAD(&rgn->list_expired_rgn);
>> >
>> >               if (rgn_idx == hpb->rgns_per_lu - 1) {
>> >                       srgn_cnt = ((hpb->srgns_per_lu - 1) %
>> > @@ -1834,6 +1887,7 @@ static int ufshpb_alloc_region_tbl(struct
>> > ufs_hba *hba, struct ufshpb_lu *hpb)
>> >               }
>> >
>> >               rgn->rgn_flags = 0;
>> > +             rgn->hpb = hpb;
>> >       }
>> >
>> >       return 0;
>> > @@ -2053,6 +2107,8 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
>> > *hba, struct ufshpb_lu *hpb)
>> >                         ufshpb_normalization_work_handler);
>> >               INIT_WORK(&hpb->ufshpb_lun_reset_work,
>> >                         ufshpb_reset_work_handler);
>> > +             INIT_DELAYED_WORK(&hpb->ufshpb_read_to_work,
>> > +                               ufshpb_read_to_handler);
>> >       }
>> >
>> >       hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
>> > @@ -2087,6 +2143,10 @@ static int ufshpb_lu_hpb_init(struct ufs_hba
>> > *hba, struct ufshpb_lu *hpb)
>> >       ufshpb_stat_init(hpb);
>> >       ufshpb_param_init(hpb);
>> >
>> > +     if (hpb->is_hcm)
>> > +             schedule_delayed_work(&hpb->ufshpb_read_to_work,
>> > +                                   msecs_to_jiffies(POLLING_INTERVAL_MS));
>> > +
>> >       return 0;
>> >
>> >  release_pre_req_mempool:
>> > @@ -2154,6 +2214,7 @@ static void ufshpb_discard_rsp_lists(struct
>> > ufshpb_lu *hpb)
>> >  static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
>> >  {
>> >       if (hpb->is_hcm) {
>> > +             cancel_delayed_work_sync(&hpb->ufshpb_read_to_work);
>> >               cancel_work_sync(&hpb->ufshpb_lun_reset_work);
>> >               cancel_work_sync(&hpb->ufshpb_normalization_work);
>> >       }
>> > @@ -2264,6 +2325,10 @@ void ufshpb_resume(struct ufs_hba *hba)
>> >                       continue;
>> >               ufshpb_set_state(hpb, HPB_PRESENT);
>> >               ufshpb_kick_map_work(hpb);
>> > +             if (hpb->is_hcm)
>> > +                     schedule_delayed_work(&hpb->ufshpb_read_to_work,
>> > +                             msecs_to_jiffies(POLLING_INTERVAL_MS));
>> > +
>> >       }
>> >  }
>> >
>> > diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
>> > index 37c1b0ea0c0a..b49e9a34267f 100644
>> > --- a/drivers/scsi/ufs/ufshpb.h
>> > +++ b/drivers/scsi/ufs/ufshpb.h
>> > @@ -109,6 +109,7 @@ struct ufshpb_subregion {
>> >  };
>> >
>> >  struct ufshpb_region {
>> > +     struct ufshpb_lu *hpb;
>> >       struct ufshpb_subregion *srgn_tbl;
>> >       enum HPB_RGN_STATE rgn_state;
>> >       int rgn_idx;
>> > @@ -126,6 +127,10 @@ struct ufshpb_region {
>> >       /* region reads - for host mode */
>> >       spinlock_t rgn_lock;
>> >       unsigned int reads;
>> > +     /* region "cold" timer - for host mode */
>> > +     ktime_t read_timeout;
>> > +     unsigned int read_timeout_expiries;
>> > +     struct list_head list_expired_rgn;
>> >  };
>> >
>> >  #define for_each_sub_region(rgn, i, srgn)                            \
>> > @@ -219,6 +224,7 @@ struct ufshpb_lu {
>> >       struct victim_select_info lru_info;
>> >       struct work_struct ufshpb_normalization_work;
>> >       struct work_struct ufshpb_lun_reset_work;
>> > +     struct delayed_work ufshpb_read_to_work;
>> >
>> >       /* pinned region information */
>> >       u32 lu_pinned_start;