1 files changed, 132 insertions, 78 deletions

diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index e7ace908a9b7..2261b4dd60b7 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -13,7 +13,6 @@
 
 struct dmz_reclaim {
 	struct dmz_metadata     *metadata;
-	struct dmz_dev		*dev;
 
 	struct delayed_work	work;
 	struct workqueue_struct *wq;
@@ -22,6 +21,8 @@ struct dmz_reclaim {
 	struct dm_kcopyd_throttle kc_throttle;
 	int			kc_err;
 
+	int			dev_idx;
+
 	unsigned long		flags;
 
 	/* Last target access time */
@@ -44,13 +45,13 @@ enum {
  * Percentage of unmapped (free) random zones below which reclaim starts
  * even if the target is busy.
  */
-#define DMZ_RECLAIM_LOW_UNMAP_RND	30
+#define DMZ_RECLAIM_LOW_UNMAP_ZONES	30
 
 /*
  * Percentage of unmapped (free) random zones above which reclaim will
  * stop if the target is busy.
  */
-#define DMZ_RECLAIM_HIGH_UNMAP_RND	50
+#define DMZ_RECLAIM_HIGH_UNMAP_ZONES	50
 
 /*
  * Align a sequential zone write pointer to chunk_block.
@@ -59,6 +60,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
 				sector_t block)
 {
 	struct dmz_metadata *zmd = zrc->metadata;
+	struct dmz_dev *dev = zone->dev;
 	sector_t wp_block = zone->wp_block;
 	unsigned int nr_blocks;
 	int ret;
@@ -74,15 +76,15 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
 	 * pointer and the requested position.
 	 */
 	nr_blocks = block - wp_block;
-	ret = blkdev_issue_zeroout(zrc->dev->bdev,
+	ret = blkdev_issue_zeroout(dev->bdev,
 				   dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block),
 				   dmz_blk2sect(nr_blocks), GFP_NOIO, 0);
 	if (ret) {
-		dmz_dev_err(zrc->dev,
+		dmz_dev_err(dev,
 			    "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
-			    dmz_id(zmd, zone), (unsigned long long)wp_block,
+			    zone->id, (unsigned long long)wp_block,
 			    (unsigned long long)block, nr_blocks, ret);
-		dmz_check_bdev(zrc->dev);
+		dmz_check_bdev(dev);
 		return ret;
 	}
 
@@ -116,7 +118,6 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
 			    struct dm_zone *src_zone, struct dm_zone *dst_zone)
 {
 	struct dmz_metadata *zmd = zrc->metadata;
-	struct dmz_dev *dev = zrc->dev;
 	struct dm_io_region src, dst;
 	sector_t block = 0, end_block;
 	sector_t nr_blocks;
@@ -128,7 +129,7 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
 	if (dmz_is_seq(src_zone))
 		end_block = src_zone->wp_block;
 	else
-		end_block = dev->zone_nr_blocks;
+		end_block = dmz_zone_nr_blocks(zmd);
 	src_zone_block = dmz_start_block(zmd, src_zone);
 	dst_zone_block = dmz_start_block(zmd, dst_zone);
 
@@ -136,9 +137,14 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
 		set_bit(DM_KCOPYD_WRITE_SEQ, &flags);
 
 	while (block < end_block) {
-		if (dev->flags & DMZ_BDEV_DYING)
+		if (src_zone->dev->flags & DMZ_BDEV_DYING)
+			return -EIO;
+		if (dst_zone->dev->flags & DMZ_BDEV_DYING)
 			return -EIO;
 
+		if (dmz_reclaim_should_terminate(src_zone))
+			return -EINTR;
+
 		/* Get a valid region from the source zone */
 		ret = dmz_first_valid_block(zmd, src_zone, &block);
 		if (ret <= 0)
@@ -156,11 +162,11 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
 				return ret;
 		}
 
-		src.bdev = dev->bdev;
+		src.bdev = src_zone->dev->bdev;
 		src.sector = dmz_blk2sect(src_zone_block + block);
 		src.count = dmz_blk2sect(nr_blocks);
 
-		dst.bdev = dev->bdev;
+		dst.bdev = dst_zone->dev->bdev;
 		dst.sector = dmz_blk2sect(dst_zone_block + block);
 		dst.count = src.count;
 
@@ -194,10 +200,10 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 	struct dmz_metadata *zmd = zrc->metadata;
 	int ret;
 
-	dmz_dev_debug(zrc->dev,
-		      "Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)",
-		      dzone->chunk, dmz_id(zmd, bzone), dmz_weight(bzone),
-		      dmz_id(zmd, dzone), dmz_weight(dzone));
+	DMDEBUG("(%s/%u): Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)",
+		dmz_metadata_label(zmd), zrc->dev_idx,
+		dzone->chunk, bzone->id, dmz_weight(bzone),
+		dzone->id, dmz_weight(dzone));
 
 	/* Flush data zone into the buffer zone */
 	ret = dmz_reclaim_copy(zrc, bzone, dzone);
@@ -210,7 +216,7 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 	ret = dmz_merge_valid_blocks(zmd, bzone, dzone, chunk_block);
 	if (ret == 0) {
 		/* Free the buffer zone */
-		dmz_invalidate_blocks(zmd, bzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_invalidate_blocks(zmd, bzone, 0, dmz_zone_nr_blocks(zmd));
 		dmz_lock_map(zmd);
 		dmz_unmap_zone(zmd, bzone);
 		dmz_unlock_zone_reclaim(dzone);
@@ -233,10 +239,10 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 	struct dmz_metadata *zmd = zrc->metadata;
 	int ret = 0;
 
-	dmz_dev_debug(zrc->dev,
-		      "Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)",
-		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
-		      dmz_id(zmd, bzone), dmz_weight(bzone));
+	DMDEBUG("(%s/%u): Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)",
+		dmz_metadata_label(zmd), zrc->dev_idx,
+		chunk, dzone->id, dmz_weight(dzone),
+		bzone->id, dmz_weight(bzone));
 
 	/* Flush data zone into the buffer zone */
 	ret = dmz_reclaim_copy(zrc, dzone, bzone);
@@ -252,7 +258,7 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 		 * Free the data zone and remap the chunk to
 		 * the buffer zone.
 		 */
-		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd));
 		dmz_lock_map(zmd);
 		dmz_unmap_zone(zmd, bzone);
 		dmz_unmap_zone(zmd, dzone);
@@ -277,18 +283,26 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 	struct dm_zone *szone = NULL;
 	struct dmz_metadata *zmd = zrc->metadata;
 	int ret;
+	int alloc_flags = DMZ_ALLOC_SEQ;
 
-	/* Get a free sequential zone */
+	/* Get a free random or sequential zone */
 	dmz_lock_map(zmd);
-	szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM);
+again:
+	szone = dmz_alloc_zone(zmd, zrc->dev_idx,
+			       alloc_flags | DMZ_ALLOC_RECLAIM);
+	if (!szone && alloc_flags == DMZ_ALLOC_SEQ && dmz_nr_cache_zones(zmd)) {
+		alloc_flags = DMZ_ALLOC_RND;
+		goto again;
+	}
 	dmz_unlock_map(zmd);
 	if (!szone)
 		return -ENOSPC;
 
-	dmz_dev_debug(zrc->dev,
-		      "Chunk %u, move rnd zone %u (weight %u) to seq zone %u",
-		      chunk, dmz_id(zmd, dzone), dmz_weight(dzone),
-		      dmz_id(zmd, szone));
+	DMDEBUG("(%s/%u): Chunk %u, move %s zone %u (weight %u) to %s zone %u",
+		dmz_metadata_label(zmd), zrc->dev_idx, chunk,
+		dmz_is_cache(dzone) ? "cache" : "rnd",
+		dzone->id, dmz_weight(dzone),
+		dmz_is_rnd(szone) ? "rnd" : "seq", szone->id);
 
 	/* Flush the random data zone into the sequential zone */
 	ret = dmz_reclaim_copy(zrc, dzone, szone);
@@ -306,7 +320,7 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 		dmz_unlock_map(zmd);
 	} else {
 		/* Free the data zone and remap the chunk */
-		dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks);
+		dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd));
 		dmz_lock_map(zmd);
 		dmz_unmap_zone(zmd, dzone);
 		dmz_unlock_zone_reclaim(dzone);
@@ -337,6 +351,14 @@ static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone)
 }
 
 /*
+ * Test if the target device is idle.
+ */
+static inline int dmz_target_idle(struct dmz_reclaim *zrc)
+{
+	return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
+}
+
+/*
  * Find a candidate zone for reclaim and process it.
  */
 static int dmz_do_reclaim(struct dmz_reclaim *zrc)
@@ -348,13 +370,16 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 	int ret;
 
 	/* Get a data zone */
-	dzone = dmz_get_zone_for_reclaim(zmd);
-	if (IS_ERR(dzone))
-		return PTR_ERR(dzone);
+	dzone = dmz_get_zone_for_reclaim(zmd, zrc->dev_idx,
+					 dmz_target_idle(zrc));
+	if (!dzone) {
+		DMDEBUG("(%s/%u): No zone found to reclaim",
+			dmz_metadata_label(zmd), zrc->dev_idx);
+		return -EBUSY;
+	}
 
 	start = jiffies;
-
-	if (dmz_is_rnd(dzone)) {
+	if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) {
 		if (!dmz_weight(dzone)) {
 			/* Empty zone */
 			dmz_reclaim_empty(zrc, dzone);
@@ -395,54 +420,80 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 	}
 out:
 	if (ret) {
+		if (ret == -EINTR)
+			DMDEBUG("(%s/%u): reclaim zone %u interrupted",
+				dmz_metadata_label(zmd), zrc->dev_idx,
+				rzone->id);
+		else
+			DMDEBUG("(%s/%u): Failed to reclaim zone %u, err %d",
+				dmz_metadata_label(zmd), zrc->dev_idx,
+				rzone->id, ret);
 		dmz_unlock_zone_reclaim(dzone);
 		return ret;
 	}
 
 	ret = dmz_flush_metadata(zrc->metadata);
 	if (ret) {
-		dmz_dev_debug(zrc->dev,
-			      "Metadata flush for zone %u failed, err %d\n",
-			      dmz_id(zmd, rzone), ret);
+		DMDEBUG("(%s/%u): Metadata flush for zone %u failed, err %d",
+			dmz_metadata_label(zmd), zrc->dev_idx, rzone->id, ret);
 		return ret;
 	}
 
-	dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms",
-		      dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start));
+	DMDEBUG("(%s/%u): Reclaimed zone %u in %u ms",
+		dmz_metadata_label(zmd), zrc->dev_idx,
+		rzone->id, jiffies_to_msecs(jiffies - start));
 	return 0;
 }
 
-/*
- * Test if the target device is idle.
- */
-static inline int dmz_target_idle(struct dmz_reclaim *zrc)
+static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc)
 {
-	return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
+	struct dmz_metadata *zmd = zrc->metadata;
+	unsigned int nr_cache = dmz_nr_cache_zones(zmd);
+	unsigned int nr_unmap, nr_zones;
+
+	if (nr_cache) {
+		nr_zones = nr_cache;
+		nr_unmap = dmz_nr_unmap_cache_zones(zmd);
+	} else {
+		nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
+		nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
+	}
+	return nr_unmap * 100 / nr_zones;
 }
 
 /*
  * Test if reclaim is necessary.
  */
-static bool dmz_should_reclaim(struct dmz_reclaim *zrc)
+static bool dmz_should_reclaim(struct dmz_reclaim *zrc, unsigned int p_unmap)
 {
-	struct dmz_metadata *zmd = zrc->metadata;
-	unsigned int nr_rnd = dmz_nr_rnd_zones(zmd);
-	unsigned int nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
-	unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
+	unsigned int nr_reclaim;
+
+	nr_reclaim = dmz_nr_rnd_zones(zrc->metadata, zrc->dev_idx);
+
+	if (dmz_nr_cache_zones(zrc->metadata)) {
+		/*
+		 * The first device in a multi-device
+		 * setup only contains cache zones, so
+		 * never start reclaim there.
+		 */
+		if (zrc->dev_idx == 0)
+			return false;
+		nr_reclaim += dmz_nr_cache_zones(zrc->metadata);
+	}
 
 	/* Reclaim when idle */
-	if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd)
+	if (dmz_target_idle(zrc) && nr_reclaim)
 		return true;
 
-	/* If there are still plenty of random zones, do not reclaim */
-	if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND)
+	/* If there are still plenty of cache zones, do not reclaim */
+	if (p_unmap >= DMZ_RECLAIM_HIGH_UNMAP_ZONES)
 		return false;
 
 	/*
-	 * If the percentage of unmapped random zones is low,
+	 * If the percentage of unmapped cache zones is low,
 	 * reclaim even if the target is busy.
 	 */
-	return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
+	return p_unmap <= DMZ_RECLAIM_LOW_UNMAP_ZONES;
 }
 
 /*
@@ -452,14 +503,14 @@ static void dmz_reclaim_work(struct work_struct *work)
 {
 	struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
 	struct dmz_metadata *zmd = zrc->metadata;
-	unsigned int nr_rnd, nr_unmap_rnd;
-	unsigned int p_unmap_rnd;
+	unsigned int p_unmap, nr_unmap_rnd = 0, nr_rnd = 0;
 	int ret;
 
-	if (dmz_bdev_is_dying(zrc->dev))
+	if (dmz_dev_is_dying(zmd))
 		return;
 
-	if (!dmz_should_reclaim(zrc)) {
+	p_unmap = dmz_reclaim_percentage(zrc);
+	if (!dmz_should_reclaim(zrc, p_unmap)) {
 		mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
 		return;
 	}
@@ -470,27 +521,29 @@ static void dmz_reclaim_work(struct work_struct *work)
 	 * and slower if there are still some free random zones to avoid
 	 * as much as possible to negatively impact the user workload.
 	 */
-	nr_rnd = dmz_nr_rnd_zones(zmd);
-	nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
-	p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
-	if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) {
+	if (dmz_target_idle(zrc) || p_unmap < DMZ_RECLAIM_LOW_UNMAP_ZONES / 2) {
 		/* Idle or very low percentage: go fast */
 		zrc->kc_throttle.throttle = 100;
 	} else {
 		/* Busy but we still have some random zone: throttle */
-		zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2);
+		zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2);
 	}
 
-	dmz_dev_debug(zrc->dev,
-		      "Reclaim (%u): %s, %u%% free rnd zones (%u/%u)",
-		      zrc->kc_throttle.throttle,
-		      (dmz_target_idle(zrc) ? "Idle" : "Busy"),
-		      p_unmap_rnd, nr_unmap_rnd, nr_rnd);
+	nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
+	nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
+
+	DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)",
+		dmz_metadata_label(zmd), zrc->dev_idx,
+		zrc->kc_throttle.throttle,
+		(dmz_target_idle(zrc) ? "Idle" : "Busy"),
+		p_unmap, dmz_nr_unmap_cache_zones(zmd),
+		dmz_nr_cache_zones(zmd),
+		dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx),
+		dmz_nr_rnd_zones(zmd, zrc->dev_idx));
 
 	ret = dmz_do_reclaim(zrc);
-	if (ret) {
-		dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret);
-		if (!dmz_check_bdev(zrc->dev))
+	if (ret && ret != -EINTR) {
+		if (!dmz_check_dev(zmd))
 			return;
 	}
 
@@ -500,8 +553,8 @@ static void dmz_reclaim_work(struct work_struct *work)
 /*
  * Initialize reclaim.
  */
-int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
-		    struct dmz_reclaim **reclaim)
+int dmz_ctr_reclaim(struct dmz_metadata *zmd,
+		    struct dmz_reclaim **reclaim, int idx)
 {
 	struct dmz_reclaim *zrc;
 	int ret;
@@ -510,9 +563,9 @@ int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
 	if (!zrc)
 		return -ENOMEM;
 
-	zrc->dev = dev;
 	zrc->metadata = zmd;
 	zrc->atime = jiffies;
+	zrc->dev_idx = idx;
 
 	/* Reclaim kcopyd client */
 	zrc->kc = dm_kcopyd_client_create(&zrc->kc_throttle);
@@ -524,8 +577,8 @@ int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd,
 
 	/* Reclaim work */
 	INIT_DELAYED_WORK(&zrc->work, dmz_reclaim_work);
-	zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s", WQ_MEM_RECLAIM,
-					  dev->name);
+	zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s_%d", WQ_MEM_RECLAIM,
+					  dmz_metadata_label(zmd), idx);
 	if (!zrc->wq) {
 		ret = -ENOMEM;
 		goto err;
@@ -583,7 +636,8 @@ void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc)
  */
 void dmz_schedule_reclaim(struct dmz_reclaim *zrc)
 {
-	if (dmz_should_reclaim(zrc))
+	unsigned int p_unmap = dmz_reclaim_percentage(zrc);
+
+	if (dmz_should_reclaim(zrc, p_unmap))
 		mod_delayed_work(zrc->wq, &zrc->work, 0);
 }
-