scsi: ufs: ufshpb: Add "cold" regions timer

In order not to hang on to "cold" regions, we inactivate a region that has
had no READ access for a predefined amount of time - READ_TO_MS. For that
purpose monitor the active regions list, polling it on every
POLLING_INTERVAL_MS. On timeout expiry add the region to the
"to-be-inactivated" list unless it is clean and did not exhaust its
READ_TO_EXPIRIES - another parameter.

None of this applies to pinned regions.

Link: https://lore.kernel.org/r/20210712095039.8093-9-avri.altman@wdc.comReviewed-by: Daejun Park <daejun7.park@samsung.com>
Signed-off-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/ufs/ufshpb.c

@@ -18,6 +18,9 @@
 
 #define ACTIVATION_THRESHOLD 8 /* 8 IOs */
 #define EVICTION_THRESHOLD (ACTIVATION_THRESHOLD << 5) /* 256 IOs */
+#define READ_TO_MS 1000
+#define READ_TO_EXPIRIES 100
+#define POLLING_INTERVAL_MS 200
 
 /* memory management */
 static struct kmem_cache *ufshpb_mctx_cache;
@@ -1032,12 +1035,63 @@ static int ufshpb_check_srgns_issue_state(struct ufshpb_lu *hpb,
 	return 0;
 }
 
+static void ufshpb_read_to_handler(struct work_struct *work)
+{
+	struct ufshpb_lu *hpb = container_of(work, struct ufshpb_lu,
+					     ufshpb_read_to_work.work);
+	struct victim_select_info *lru_info = &hpb->lru_info;
+	struct ufshpb_region *rgn, *next_rgn;
+	unsigned long flags;
+	LIST_HEAD(expired_list);
+
+	if (test_and_set_bit(TIMEOUT_WORK_RUNNING, &hpb->work_data_bits))
+		return;
+
+	spin_lock_irqsave(&hpb->rgn_state_lock, flags);
+
+	list_for_each_entry_safe(rgn, next_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_safe(rgn, next_rgn, &expired_list,
+				 list_expired_rgn) {
+		list_del_init(&rgn->list_expired_rgn);
+		spin_lock_irqsave(&hpb->rsp_list_lock, flags);
+		ufshpb_update_inactive_info(hpb, rgn->rgn_idx);
+		spin_unlock_irqrestore(&hpb->rsp_list_lock, flags);
+	}
+
+	ufshpb_kick_map_work(hpb);
+
+	clear_bit(TIMEOUT_WORK_RUNNING, &hpb->work_data_bits);
+
+	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,
@@ -1819,6 +1873,7 @@ 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) %
@@ -1840,6 +1895,7 @@ static int ufshpb_alloc_region_tbl(struct ufs_hba *hba, struct ufshpb_lu *hpb)
 		}
 
 		rgn->rgn_flags = 0;
+		rgn->hpb = hpb;
 	}
 
 	return 0;
@@ -2063,9 +2119,12 @@ 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)
+	if (hpb->is_hcm) {
 		INIT_WORK(&hpb->ufshpb_normalization_work,
 			  ufshpb_normalization_work_handler);
+		INIT_DELAYED_WORK(&hpb->ufshpb_read_to_work,
+				  ufshpb_read_to_handler);
+	}
 
 	hpb->map_req_cache = kmem_cache_create("ufshpb_req_cache",
 			  sizeof(struct ufshpb_req), 0, 0, NULL);
@@ -2099,6 +2158,10 @@ 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:
@@ -2165,9 +2228,10 @@ static void ufshpb_discard_rsp_lists(struct ufshpb_lu *hpb)
 
 static void ufshpb_cancel_jobs(struct ufshpb_lu *hpb)
 {
-	if (hpb->is_hcm)
+	if (hpb->is_hcm) {
+		cancel_delayed_work_sync(&hpb->ufshpb_read_to_work);
 		cancel_work_sync(&hpb->ufshpb_normalization_work);
-
+	}
 	cancel_work_sync(&hpb->map_work);
 }
 
@@ -2275,6 +2339,10 @@ 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));
+
 	}
 }
 

drivers/scsi/ufs/ufshpb.h

@@ -115,6 +115,7 @@ struct ufshpb_subregion {
 };
 
 struct ufshpb_region {
+	struct ufshpb_lu *hpb;
 	struct ufshpb_subregion *srgn_tbl;
 	enum HPB_RGN_STATE rgn_state;
 	int rgn_idx;
@@ -132,6 +133,10 @@ 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)				\
@@ -223,6 +228,9 @@ struct ufshpb_lu {
 	/* for selecting victim */
 	struct victim_select_info lru_info;
 	struct work_struct ufshpb_normalization_work;
+	struct delayed_work ufshpb_read_to_work;
+	unsigned long work_data_bits;
+#define TIMEOUT_WORK_RUNNING 0
 
 	/* pinned region information */
 	u32 lu_pinned_start;