lightnvm: pblk: implement get log report chunk

In preparation of pblk supporting 2.0, implement the get log report
chunk in pblk. Also, define the chunk states as given in the 2.0 spec.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/lightnvm/pblk-core.c

@@ -44,11 +44,12 @@ static void pblk_line_mark_bb(struct work_struct *work)
 }
 
 static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
-			 struct ppa_addr *ppa)
+			 struct ppa_addr ppa_addr)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	int pos = pblk_ppa_to_pos(geo, *ppa);
+	struct ppa_addr *ppa;
+	int pos = pblk_ppa_to_pos(geo, ppa_addr);
 
 	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
@@ -58,26 +59,38 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
+	/* Not necessary to mark bad blocks on 2.0 spec. */
+	if (geo->version == NVM_OCSSD_SPEC_20)
+		return;
+
+	ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
+	if (!ppa)
+		return;
+
+	*ppa = ppa_addr;
 	pblk_gen_run_ws(pblk, NULL, ppa, pblk_line_mark_bb,
 						GFP_ATOMIC, pblk->bb_wq);
 }
 
 static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
 {
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_chk_meta *chunk;
 	struct pblk_line *line;
+	int pos;
 
 	line = &pblk->lines[pblk_ppa_to_line(rqd->ppa_addr)];
+	pos = pblk_ppa_to_pos(geo, rqd->ppa_addr);
+	chunk = &line->chks[pos];
+
 	atomic_dec(&line->left_seblks);
 
 	if (rqd->error) {
-		struct ppa_addr *ppa;
-
-		ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
-		if (!ppa)
-			return;
-
-		*ppa = rqd->ppa_addr;
-		pblk_mark_bb(pblk, line, ppa);
+		chunk->state = NVM_CHK_ST_OFFLINE;
+		pblk_mark_bb(pblk, line, rqd->ppa_addr);
+	} else {
+		chunk->state = NVM_CHK_ST_FREE;
 	}
 
 	atomic_dec(&pblk->inflight_io);
@@ -92,6 +105,49 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
 	mempool_free(rqd, pblk->e_rq_pool);
 }
 
+/*
+ * Get information for all chunks from the device.
+ *
+ * The caller is responsible for freeing the returned structure
+ */
+struct nvm_chk_meta *pblk_chunk_get_info(struct pblk *pblk)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_chk_meta *meta;
+	struct ppa_addr ppa;
+	unsigned long len;
+	int ret;
+
+	ppa.ppa = 0;
+
+	len = geo->all_chunks * sizeof(*meta);
+	meta = kzalloc(len, GFP_KERNEL);
+	if (!meta)
+		return ERR_PTR(-ENOMEM);
+
+	ret = nvm_get_chunk_meta(dev, meta, ppa, geo->all_chunks);
+	if (ret) {
+		kfree(meta);
+		return ERR_PTR(-EIO);
+	}
+
+	return meta;
+}
+
+struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk,
+					      struct nvm_chk_meta *meta,
+					      struct ppa_addr ppa)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int ch_off = ppa.m.grp * geo->num_chk * geo->num_lun;
+	int lun_off = ppa.m.pu * geo->num_chk;
+	int chk_off = ppa.m.chk;
+
+	return meta + ch_off + lun_off + chk_off;
+}
+
 void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
 			   u64 paddr)
 {
@@ -1091,10 +1147,34 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	return 1;
 }
 
+static int pblk_prepare_new_line(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	int blk_to_erase = atomic_read(&line->blk_in_line);
+	int i;
+
+	for (i = 0; i < lm->blk_per_line; i++) {
+		struct pblk_lun *rlun = &pblk->luns[i];
+		int pos = pblk_ppa_to_pos(geo, rlun->bppa);
+		int state = line->chks[pos].state;
+
+		/* Free chunks should not be erased */
+		if (state & NVM_CHK_ST_FREE) {
+			set_bit(pblk_ppa_to_pos(geo, rlun->bppa),
+							line->erase_bitmap);
+			blk_to_erase--;
+		}
+	}
+
+	return blk_to_erase;
+}
+
 static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
-	int blk_in_line = atomic_read(&line->blk_in_line);
+	int blk_to_erase;
 
 	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC);
 	if (!line->map_bitmap)
@@ -1107,7 +1187,21 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 		return -ENOMEM;
 	}
 
+	/* Bad blocks do not need to be erased */
+	bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
+
 	spin_lock(&line->lock);
+
+	/* If we have not written to this line, we need to mark up free chunks
+	 * as already erased
+	 */
+	if (line->state == PBLK_LINESTATE_NEW) {
+		blk_to_erase = pblk_prepare_new_line(pblk, line);
+		line->state = PBLK_LINESTATE_FREE;
+	} else {
+		blk_to_erase = atomic_read(&line->blk_in_line);
+	}
+
 	if (line->state != PBLK_LINESTATE_FREE) {
 		kfree(line->map_bitmap);
 		kfree(line->invalid_bitmap);
@@ -1119,15 +1213,12 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 
 	line->state = PBLK_LINESTATE_OPEN;
 
-	atomic_set(&line->left_eblks, blk_in_line);
-	atomic_set(&line->left_seblks, blk_in_line);
+	atomic_set(&line->left_eblks, blk_to_erase);
+	atomic_set(&line->left_seblks, blk_to_erase);
 
 	line->meta_distance = lm->meta_distance;
 	spin_unlock(&line->lock);
 
-	/* Bad blocks do not need to be erased */
-	bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
-
 	kref_init(&line->ref);
 
 	return 0;
@@ -1583,12 +1674,14 @@ static void pblk_line_should_sync_meta(struct pblk *pblk)
 
 void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 {
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct list_head *move_list;
+	int i;
 
 #ifdef CONFIG_NVM_DEBUG
-	struct pblk_line_meta *lm = &pblk->lm;
-
 	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
 #endif
@@ -1610,6 +1703,15 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 	line->smeta = NULL;
 	line->emeta = NULL;
 
+	for (i = 0; i < lm->blk_per_line; i++) {
+		struct pblk_lun *rlun = &pblk->luns[i];
+		int pos = pblk_ppa_to_pos(geo, rlun->bppa);
+		int state = line->chks[pos].state;
+
+		if (!(state & NVM_CHK_ST_OFFLINE))
+			state = NVM_CHK_ST_CLOSED;
+	}
+
 	spin_unlock(&line->lock);
 	spin_unlock(&l_mg->gc_lock);
 }

drivers/lightnvm/pblk-init.c

@@ -451,6 +451,7 @@ static void pblk_line_meta_free(struct pblk_line *line)
 {
 	kfree(line->blk_bitmap);
 	kfree(line->erase_bitmap);
+	kfree(line->chks);
 }
 
 static void pblk_lines_free(struct pblk *pblk)
@@ -495,55 +496,44 @@ static int pblk_bb_get_tbl(struct nvm_tgt_dev *dev, struct pblk_lun *rlun,
 	return 0;
 }
 
-static void *pblk_bb_get_log(struct pblk *pblk)
+static void *pblk_bb_get_meta(struct pblk *pblk)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	u8 *log;
+	u8 *meta;
 	int i, nr_blks, blk_per_lun;
 	int ret;
 
 	blk_per_lun = geo->num_chk * geo->pln_mode;
 	nr_blks = blk_per_lun * geo->all_luns;
 
-	log = kmalloc(nr_blks, GFP_KERNEL);
-	if (!log)
+	meta = kmalloc(nr_blks, GFP_KERNEL);
+	if (!meta)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < geo->all_luns; i++) {
 		struct pblk_lun *rlun = &pblk->luns[i];
-		u8 *log_pos = log + i * blk_per_lun;
+		u8 *meta_pos = meta + i * blk_per_lun;
 
-		ret = pblk_bb_get_tbl(dev, rlun, log_pos, blk_per_lun);
+		ret = pblk_bb_get_tbl(dev, rlun, meta_pos, blk_per_lun);
 		if (ret) {
-			kfree(log);
+			kfree(meta);
 			return ERR_PTR(-EIO);
 		}
 	}
 
-	return log;
+	return meta;
 }
 
-static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line,
-			u8 *bb_log, int blk_per_line)
+static void *pblk_chunk_get_meta(struct pblk *pblk)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	int i, bb_cnt = 0;
-	int blk_per_lun = geo->num_chk * geo->pln_mode;
 
-	for (i = 0; i < blk_per_line; i++) {
-		struct pblk_lun *rlun = &pblk->luns[i];
-		u8 *lun_bb_log = bb_log + i * blk_per_lun;
-
-		if (lun_bb_log[line->id] == NVM_BLK_T_FREE)
-			continue;
-
-		set_bit(pblk_ppa_to_pos(geo, rlun->bppa), line->blk_bitmap);
-		bb_cnt++;
-	}
-
-	return bb_cnt;
+	if (geo->version == NVM_OCSSD_SPEC_12)
+		return pblk_bb_get_meta(pblk);
+	else
+		return pblk_chunk_get_info(pblk);
 }
 
 static int pblk_luns_init(struct pblk *pblk)
@@ -644,8 +634,131 @@ static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
 	atomic_set(&pblk->rl.free_user_blocks, nr_free_blks);
 }
 
-static int pblk_setup_line_meta(struct pblk *pblk, struct pblk_line *line,
-				void *chunk_log, long *nr_bad_blks)
+static int pblk_setup_line_meta_12(struct pblk *pblk, struct pblk_line *line,
+				   void *chunk_meta)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	int i, chk_per_lun, nr_bad_chks = 0;
+
+	chk_per_lun = geo->num_chk * geo->pln_mode;
+
+	for (i = 0; i < lm->blk_per_line; i++) {
+		struct pblk_lun *rlun = &pblk->luns[i];
+		struct nvm_chk_meta *chunk;
+		int pos = pblk_ppa_to_pos(geo, rlun->bppa);
+		u8 *lun_bb_meta = chunk_meta + pos * chk_per_lun;
+
+		chunk = &line->chks[pos];
+
+		/*
+		 * In 1.2 spec. chunk state is not persisted by the device. Thus
+		 * some of the values are reset each time pblk is instantiated.
+		 */
+		if (lun_bb_meta[line->id] == NVM_BLK_T_FREE)
+			chunk->state =  NVM_CHK_ST_FREE;
+		else
+			chunk->state = NVM_CHK_ST_OFFLINE;
+
+		chunk->type = NVM_CHK_TP_W_SEQ;
+		chunk->wi = 0;
+		chunk->slba = -1;
+		chunk->cnlb = geo->clba;
+		chunk->wp = 0;
+
+		if (!(chunk->state & NVM_CHK_ST_OFFLINE))
+			continue;
+
+		set_bit(pos, line->blk_bitmap);
+		nr_bad_chks++;
+	}
+
+	return nr_bad_chks;
+}
+
+static int pblk_setup_line_meta_20(struct pblk *pblk, struct pblk_line *line,
+				   struct nvm_chk_meta *meta)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_meta *lm = &pblk->lm;
+	int i, nr_bad_chks = 0;
+
+	for (i = 0; i < lm->blk_per_line; i++) {
+		struct pblk_lun *rlun = &pblk->luns[i];
+		struct nvm_chk_meta *chunk;
+		struct nvm_chk_meta *chunk_meta;
+		struct ppa_addr ppa;
+		int pos;
+
+		ppa = rlun->bppa;
+		pos = pblk_ppa_to_pos(geo, ppa);
+		chunk = &line->chks[pos];
+
+		ppa.m.chk = line->id;
+		chunk_meta = pblk_chunk_get_off(pblk, meta, ppa);
+
+		chunk->state = chunk_meta->state;
+		chunk->type = chunk_meta->type;
+		chunk->wi = chunk_meta->wi;
+		chunk->slba = chunk_meta->slba;
+		chunk->cnlb = chunk_meta->cnlb;
+		chunk->wp = chunk_meta->wp;
+
+		if (!(chunk->state & NVM_CHK_ST_OFFLINE))
+			continue;
+
+		if (chunk->type & NVM_CHK_TP_SZ_SPEC) {
+			WARN_ONCE(1, "pblk: custom-sized chunks unsupported\n");
+			continue;
+		}
+
+		set_bit(pos, line->blk_bitmap);
+		nr_bad_chks++;
+	}
+
+	return nr_bad_chks;
+}
+
+static long pblk_setup_line_meta(struct pblk *pblk, struct pblk_line *line,
+				 void *chunk_meta, int line_id)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	long nr_bad_chks, chk_in_line;
+
+	line->pblk = pblk;
+	line->id = line_id;
+	line->type = PBLK_LINETYPE_FREE;
+	line->state = PBLK_LINESTATE_NEW;
+	line->gc_group = PBLK_LINEGC_NONE;
+	line->vsc = &l_mg->vsc_list[line_id];
+	spin_lock_init(&line->lock);
+
+	if (geo->version == NVM_OCSSD_SPEC_12)
+		nr_bad_chks = pblk_setup_line_meta_12(pblk, line, chunk_meta);
+	else
+		nr_bad_chks = pblk_setup_line_meta_20(pblk, line, chunk_meta);
+
+	chk_in_line = lm->blk_per_line - nr_bad_chks;
+	if (nr_bad_chks < 0 || nr_bad_chks > lm->blk_per_line ||
+					chk_in_line < lm->min_blk_line) {
+		line->state = PBLK_LINESTATE_BAD;
+		list_add_tail(&line->list, &l_mg->bad_list);
+		return 0;
+	}
+
+	atomic_set(&line->blk_in_line, chk_in_line);
+	list_add_tail(&line->list, &l_mg->free_list);
+	l_mg->nr_free_lines++;
+
+	return chk_in_line;
+}
+
+static int pblk_alloc_line_meta(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
 
@@ -659,7 +772,13 @@ static int pblk_setup_line_meta(struct pblk *pblk, struct pblk_line *line,
 		return -ENOMEM;
 	}
 
-	*nr_bad_blks = pblk_bb_line(pblk, line, chunk_log, lm->blk_per_line);
+	line->chks = kmalloc(lm->blk_per_line * sizeof(struct nvm_chk_meta),
+								GFP_KERNEL);
+	if (!line->chks) {
+		kfree(line->erase_bitmap);
+		kfree(line->blk_bitmap);
+		return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -846,10 +965,9 @@ static int pblk_line_meta_init(struct pblk *pblk)
 static int pblk_lines_init(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
-	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line *line;
-	void *chunk_log;
-	long nr_bad_blks = 0, nr_free_blks = 0;
+	void *chunk_meta;
+	long nr_free_chks = 0;
 	int i, ret;
 
 	ret = pblk_line_meta_init(pblk);
@@ -864,11 +982,9 @@ static int pblk_lines_init(struct pblk *pblk)
 	if (ret)
 		goto fail_free_meta;
 
-	chunk_log = pblk_bb_get_log(pblk);
-	if (IS_ERR(chunk_log)) {
-		pr_err("pblk: could not get bad block log (%lu)\n",
-							PTR_ERR(chunk_log));
-		ret = PTR_ERR(chunk_log);
+	chunk_meta = pblk_chunk_get_meta(pblk);
+	if (IS_ERR(chunk_meta)) {
+		ret = PTR_ERR(chunk_meta);
 		goto fail_free_luns;
 	}
 
@@ -876,52 +992,30 @@ static int pblk_lines_init(struct pblk *pblk)
 								GFP_KERNEL);
 	if (!pblk->lines) {
 		ret = -ENOMEM;
-		goto fail_free_chunk_log;
+		goto fail_free_chunk_meta;
 	}
 
 	for (i = 0; i < l_mg->nr_lines; i++) {
-		int chk_in_line;
-
 		line = &pblk->lines[i];
 
-		line->pblk = pblk;
-		line->id = i;
-		line->type = PBLK_LINETYPE_FREE;
-		line->state = PBLK_LINESTATE_FREE;
-		line->gc_group = PBLK_LINEGC_NONE;
-		line->vsc = &l_mg->vsc_list[i];
-		spin_lock_init(&line->lock);
-
-		ret = pblk_setup_line_meta(pblk, line, chunk_log, &nr_bad_blks);
+		ret = pblk_alloc_line_meta(pblk, line);
 		if (ret)
 			goto fail_free_lines;
 
-		chk_in_line = lm->blk_per_line - nr_bad_blks;
-		if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line ||
-					chk_in_line < lm->min_blk_line) {
-			line->state = PBLK_LINESTATE_BAD;
-			list_add_tail(&line->list, &l_mg->bad_list);
-			continue;
-		}
-
-		nr_free_blks += chk_in_line;
-		atomic_set(&line->blk_in_line, chk_in_line);
-
-		l_mg->nr_free_lines++;
-		list_add_tail(&line->list, &l_mg->free_list);
+		nr_free_chks += pblk_setup_line_meta(pblk, line, chunk_meta, i);
 	}
 
-	pblk_set_provision(pblk, nr_free_blks);
+	pblk_set_provision(pblk, nr_free_chks);
 
-	kfree(chunk_log);
+	kfree(chunk_meta);
 	return 0;
 
 fail_free_lines:
 	while (--i >= 0)
 		pblk_line_meta_free(&pblk->lines[i]);
 	kfree(pblk->lines);
-fail_free_chunk_log:
-	kfree(chunk_log);
+fail_free_chunk_meta:
+	kfree(chunk_meta);
 fail_free_luns:
 	kfree(pblk->luns);
 fail_free_meta:

drivers/lightnvm/pblk.h

@@ -297,6 +297,7 @@ enum {
 	PBLK_LINETYPE_DATA = 2,
 
 	/* Line state */
+	PBLK_LINESTATE_NEW = 9,
 	PBLK_LINESTATE_FREE = 10,
 	PBLK_LINESTATE_OPEN = 11,
 	PBLK_LINESTATE_CLOSED = 12,
@@ -426,6 +427,8 @@ struct pblk_line {
 
 	unsigned long *lun_bitmap;	/* Bitmap for LUNs mapped in line */
 
+	struct nvm_chk_meta *chks;	/* Chunks forming line */
+
 	struct pblk_smeta *smeta;	/* Start metadata */
 	struct pblk_emeta *emeta;	/* End medatada */
 
@@ -729,6 +732,10 @@ void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write);
 int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
 			struct pblk_c_ctx *c_ctx);
 void pblk_discard(struct pblk *pblk, struct bio *bio);
+struct nvm_chk_meta *pblk_chunk_get_info(struct pblk *pblk);
+struct nvm_chk_meta *pblk_chunk_get_off(struct pblk *pblk,
+					      struct nvm_chk_meta *lp,
+					      struct ppa_addr ppa);
 void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
 void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
 int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd);

include/linux/lightnvm.h

@@ -232,6 +232,19 @@ struct nvm_addrf {
 	u64	rsv_mask[2];
 };
 
+enum {
+	/* Chunk states */
+	NVM_CHK_ST_FREE =	1 << 0,
+	NVM_CHK_ST_CLOSED =	1 << 1,
+	NVM_CHK_ST_OPEN =	1 << 2,
+	NVM_CHK_ST_OFFLINE =	1 << 3,
+
+	/* Chunk types */
+	NVM_CHK_TP_W_SEQ =	1 << 0,
+	NVM_CHK_TP_W_RAN =	1 << 1,
+	NVM_CHK_TP_SZ_SPEC =	1 << 4,
+};
+
 /*
  * Note: The structure size is linked to nvme_nvm_chk_meta such that the same
  * buffer can be used when converting from little endian to cpu addressing.