[PATCH v4 0/5] lightnvm: Flexible metadata

[PATCH v4 0/5] lightnvm: Flexible metadata

[Igor Konopko]

This series of patches extends the way how pblk can
store L2P sector metadata. After this set of changes
any size of NVMe metadata is supported in pblk.
Also there is an support for case without NVMe metadata.

Changes v3 --> v4:
-rename nvm_alloc_dma_pool() to nvm_create_dma_pool()
-split pblk_get_meta() calls and lba setting into
two operations for better core readability
-fixing compilation with CONFIG_NVM disabled
-getting rid of unnecessary memcpy for packed metadata
on write path
-support for drives with oob size >0 and <16B in packed
metadata mode
-minor commit message updates

Changes v2 --> v3:
-Rebase on top of ocssd/for-4.21/core
-get/set_meta_lba helpers were removed
-dma reallocation was replaced with single allocation
-oob metadata size was added to pblk structure
-proper checks on pblk creation were added
 
Changes v1 --> v2:
-Revert sector meta size back to 16b for pblk
-Dma pool for larger oob meta are handled in core instead of pblk
-Pblk oob meta helpers uses __le64 as input outpu instead of u64
-Other minor fixes based on v1 patch review

Igor Konopko (5):
  lightnvm: pblk: Move lba list to partial read context
  lightnvm: pblk: Helpers for OOB metadata
  lightnvm: Flexible DMA pool entry size
  lightnvm: Disable interleaved metadata
  lightnvm: pblk: Support for packed metadata

 drivers/lightnvm/core.c          | 30 ++++++++++++------
 drivers/lightnvm/pblk-core.c     | 61 +++++++++++++++++++++++++++++++------
 drivers/lightnvm/pblk-init.c     | 44 +++++++++++++++++++++++++--
 drivers/lightnvm/pblk-map.c      | 20 +++++++-----
 drivers/lightnvm/pblk-rb.c       |  3 ++
 drivers/lightnvm/pblk-read.c     | 66 +++++++++++++++++++++++-----------------
 drivers/lightnvm/pblk-recovery.c | 25 +++++++++------
 drivers/lightnvm/pblk-sysfs.c    |  7 +++++
 drivers/lightnvm/pblk-write.c    |  9 +++---
 drivers/lightnvm/pblk.h          | 24 +++++++++++++--
 drivers/nvme/host/lightnvm.c     | 16 ++++++----
 include/linux/lightnvm.h         |  8 ++++-
 12 files changed, 233 insertions(+), 80 deletions(-)

-- 
2.14.5

[PATCH v4 1/5] lightnvm: pblk: Move lba list to partial read context

[Igor Konopko]

Currently DMA allocated memory is reused on partial read
for lba_list_mem and lba_list_media arrays. In preparation
for dynamic DMA pool sizes we need to move this arrays
into pblk_pr_ctx structures.

Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
---
 drivers/lightnvm/pblk-read.c | 20 +++++---------------
 drivers/lightnvm/pblk.h      |  2 ++
 2 files changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 9fba614adeeb..19917d3c19b3 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -224,7 +224,6 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 	unsigned long *read_bitmap = pr_ctx->bitmap;
 	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
-	__le64 *lba_list_mem, *lba_list_media;
 	void *src_p, *dst_p;
 	int hole, i;
 
@@ -237,13 +236,9 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 		rqd->ppa_list[0] = ppa;
 	}
 
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
-
 	for (i = 0; i < nr_secs; i++) {
-		lba_list_media[i] = meta_list[i].lba;
-		meta_list[i].lba = lba_list_mem[i];
+		pr_ctx->lba_list_media[i] = meta_list[i].lba;
+		meta_list[i].lba = pr_ctx->lba_list_mem[i];
 	}
 
 	/* Fill the holes in the original bio */
@@ -255,7 +250,7 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 		line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
 		kref_put(&line->ref, pblk_line_put);
 
-		meta_list[hole].lba = lba_list_media[i];
+		meta_list[hole].lba = pr_ctx->lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
 		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
@@ -295,13 +290,9 @@ static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
 	struct pblk_pr_ctx *pr_ctx;
 	struct bio *new_bio, *bio = r_ctx->private;
-	__le64 *lba_list_mem;
 	int nr_secs = rqd->nr_ppas;
 	int i;
 
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-
 	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
 
 	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
@@ -312,12 +303,12 @@ static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		goto fail_free_pages;
 	}
 
-	pr_ctx = kmalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
+	pr_ctx = kzalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
 	if (!pr_ctx)
 		goto fail_free_pages;
 
 	for (i = 0; i < nr_secs; i++)
-		lba_list_mem[i] = meta_list[i].lba;
+		pr_ctx->lba_list_mem[i] = meta_list[i].lba;
 
 	new_bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
@@ -325,7 +316,6 @@ static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->bio = new_bio;
 	rqd->nr_ppas = nr_holes;
 
-	pr_ctx->ppa_ptr = NULL;
 	pr_ctx->orig_bio = bio;
 	bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA);
 	pr_ctx->bio_init_idx = bio_init_idx;
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index e5b88a25d4d6..0e9d3960ac4c 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -132,6 +132,8 @@ struct pblk_pr_ctx {
 	unsigned int bio_init_idx;
 	void *ppa_ptr;
 	dma_addr_t dma_ppa_list;
+	__le64 lba_list_mem[NVM_MAX_VLBA];
+	__le64 lba_list_media[NVM_MAX_VLBA];
 };
 
 /* Pad context */
-- 
2.14.5

[PATCH v4 2/5] lightnvm: pblk: Helpers for OOB metadata

[Igor Konopko]

Currently pblk assumes that size of OOB metadata on drive is always
equal to size of pblk_sec_meta struct. This commit add helpers which will
allow to handle different sizes of OOB metadata on drive in the future.
Still, after this patch only OOB metadata equal to 16 bytes is supported.

Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
---
 drivers/lightnvm/pblk-core.c     |  5 +++--
 drivers/lightnvm/pblk-init.c     |  6 +++++
 drivers/lightnvm/pblk-map.c      | 20 +++++++++++------
 drivers/lightnvm/pblk-read.c     | 48 ++++++++++++++++++++++++++--------------
 drivers/lightnvm/pblk-recovery.c | 16 +++++++++-----
 drivers/lightnvm/pblk.h          |  6 +++++
 6 files changed, 69 insertions(+), 32 deletions(-)

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 6581c35f51ee..aeb10bd78c62 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -796,10 +796,11 @@ static int pblk_line_smeta_write(struct pblk *pblk, struct pblk_line *line,
 	rqd.is_seq = 1;
 
 	for (i = 0; i < lm->smeta_sec; i++, paddr++) {
-		struct pblk_sec_meta *meta_list = rqd.meta_list;
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk,
+							   rqd.meta_list, i);
 
 		rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
-		meta_list[i].lba = lba_list[paddr] = addr_empty;
+		meta->lba = lba_list[paddr] = addr_empty;
 	}
 
 	ret = pblk_submit_io_sync_sem(pblk, &rqd);
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 0e37104de596..6e7a0c6c6655 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -409,6 +409,12 @@ static int pblk_core_init(struct pblk *pblk)
 		queue_max_hw_sectors(dev->q) / (geo->csecs >> SECTOR_SHIFT));
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
+	pblk->oob_meta_size = geo->sos;
+	if (pblk->oob_meta_size != sizeof(struct pblk_sec_meta)) {
+		pblk_err(pblk, "Unsupported metadata size\n");
+		return -EINVAL;
+	}
+
 	pblk->pad_dist = kcalloc(pblk->min_write_pgs - 1, sizeof(atomic64_t),
 								GFP_KERNEL);
 	if (!pblk->pad_dist)
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 5a3c28cce8ab..81e503ec384e 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -22,7 +22,7 @@
 static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 			      struct ppa_addr *ppa_list,
 			      unsigned long *lun_bitmap,
-			      struct pblk_sec_meta *meta_list,
+			      void *meta_list,
 			      unsigned int valid_secs)
 {
 	struct pblk_line *line = pblk_line_get_data(pblk);
@@ -58,6 +58,7 @@ static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 	paddr = pblk_alloc_page(pblk, line, nr_secs);
 
 	for (i = 0; i < nr_secs; i++, paddr++) {
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
 		__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
 
 		/* ppa to be sent to the device */
@@ -74,14 +75,15 @@ static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 			kref_get(&line->ref);
 			w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
 			w_ctx->ppa = ppa_list[i];
-			meta_list[i].lba = cpu_to_le64(w_ctx->lba);
+			meta->lba = cpu_to_le64(w_ctx->lba);
 			lba_list[paddr] = cpu_to_le64(w_ctx->lba);
 			if (lba_list[paddr] != addr_empty)
 				line->nr_valid_lbas++;
 			else
 				atomic64_inc(&pblk->pad_wa);
 		} else {
-			lba_list[paddr] = meta_list[i].lba = addr_empty;
+			lba_list[paddr] = addr_empty;
+			meta->lba = addr_empty;
 			__pblk_map_invalidate(pblk, line, paddr);
 		}
 	}
@@ -94,7 +96,8 @@ int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 		 unsigned long *lun_bitmap, unsigned int valid_secs,
 		 unsigned int off)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
+	void *meta_buffer;
 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
 	unsigned int map_secs;
 	int min = pblk->min_write_pgs;
@@ -103,9 +106,10 @@ int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 
 	for (i = off; i < rqd->nr_ppas; i += min) {
 		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+		meta_buffer = pblk_get_meta(pblk, meta_list, i);
 
 		ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
-					lun_bitmap, &meta_list[i], map_secs);
+					lun_bitmap, meta_buffer, map_secs);
 		if (ret)
 			return ret;
 	}
@@ -121,7 +125,8 @@ int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_line_meta *lm = &pblk->lm;
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
+	void *meta_buffer;
 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
 	struct pblk_line *e_line, *d_line;
 	unsigned int map_secs;
@@ -132,9 +137,10 @@ int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 
 	for (i = 0; i < rqd->nr_ppas; i += min) {
 		map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+		meta_buffer = pblk_get_meta(pblk, meta_list, i);
 
 		ret = pblk_map_page_data(pblk, sentry + i, &ppa_list[i],
-					lun_bitmap, &meta_list[i], map_secs);
+					lun_bitmap, meta_buffer, map_secs);
 		if (ret)
 			return ret;
 
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 19917d3c19b3..6becd85ca4c6 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -43,7 +43,7 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 				 struct bio *bio, sector_t blba,
 				 unsigned long *read_bitmap)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
 	struct ppa_addr ppas[NVM_MAX_VLBA];
 	int nr_secs = rqd->nr_ppas;
 	bool advanced_bio = false;
@@ -53,12 +53,15 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 
 	for (i = 0; i < nr_secs; i++) {
 		struct ppa_addr p = ppas[i];
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
 		sector_t lba = blba + i;
 
 retry:
 		if (pblk_ppa_empty(p)) {
+			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+
 			WARN_ON(test_and_set_bit(i, read_bitmap));
-			meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+			meta->lba = addr_empty;
 
 			if (unlikely(!advanced_bio)) {
 				bio_advance(bio, (i) * PBLK_EXPOSED_PAGE_SIZE);
@@ -78,7 +81,7 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 				goto retry;
 			}
 			WARN_ON(test_and_set_bit(i, read_bitmap));
-			meta_list[i].lba = cpu_to_le64(lba);
+			meta->lba = cpu_to_le64(lba);
 			advanced_bio = true;
 #ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
@@ -105,12 +108,13 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 				sector_t blba)
 {
-	struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
 	int nr_lbas = rqd->nr_ppas;
 	int i;
 
 	for (i = 0; i < nr_lbas; i++) {
-		u64 lba = le64_to_cpu(meta_lba_list[i].lba);
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
+		u64 lba = le64_to_cpu(meta->lba);
 
 		if (lba == ADDR_EMPTY)
 			continue;
@@ -134,17 +138,19 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 				 u64 *lba_list, int nr_lbas)
 {
-	struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
+	void *meta_lba_list = rqd->meta_list;
 	int i, j;
 
 	for (i = 0, j = 0; i < nr_lbas; i++) {
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk,
+							   meta_lba_list, j);
 		u64 lba = lba_list[i];
 		u64 meta_lba;
 
 		if (lba == ADDR_EMPTY)
 			continue;
 
-		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
+		meta_lba = le64_to_cpu(meta->lba);
 
 		if (lba != meta_lba) {
 #ifdef CONFIG_NVM_PBLK_DEBUG
@@ -216,10 +222,11 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 	struct pblk *pblk = rqd->private;
 	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
 	struct pblk_pr_ctx *pr_ctx = r_ctx->private;
+	struct pblk_sec_meta *meta;
 	struct bio *new_bio = rqd->bio;
 	struct bio *bio = pr_ctx->orig_bio;
 	struct bio_vec src_bv, dst_bv;
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
 	int bio_init_idx = pr_ctx->bio_init_idx;
 	unsigned long *read_bitmap = pr_ctx->bitmap;
 	int nr_secs = pr_ctx->orig_nr_secs;
@@ -237,8 +244,9 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 	}
 
 	for (i = 0; i < nr_secs; i++) {
-		pr_ctx->lba_list_media[i] = meta_list[i].lba;
-		meta_list[i].lba = pr_ctx->lba_list_mem[i];
+		meta = pblk_get_meta(pblk, meta_list, i);
+		pr_ctx->lba_list_media[i] = le64_to_cpu(meta->lba);
+		meta->lba = cpu_to_le64(pr_ctx->lba_list_mem[i]);
 	}
 
 	/* Fill the holes in the original bio */
@@ -250,7 +258,8 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 		line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
 		kref_put(&line->ref, pblk_line_put);
 
-		meta_list[hole].lba = pr_ctx->lba_list_media[i];
+		meta = pblk_get_meta(pblk, meta_list, hole);
+		meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
 
 		src_bv = new_bio->bi_io_vec[i++];
 		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
@@ -286,7 +295,7 @@ static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 			    unsigned long *read_bitmap,
 			    int nr_holes)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	void *meta_list = rqd->meta_list;
 	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
 	struct pblk_pr_ctx *pr_ctx;
 	struct bio *new_bio, *bio = r_ctx->private;
@@ -307,8 +316,11 @@ static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	if (!pr_ctx)
 		goto fail_free_pages;
 
-	for (i = 0; i < nr_secs; i++)
-		pr_ctx->lba_list_mem[i] = meta_list[i].lba;
+	for (i = 0; i < nr_secs; i++) {
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
+
+		pr_ctx->lba_list_mem[i] = le64_to_cpu(meta->lba);
+	}
 
 	new_bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
@@ -373,7 +385,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 			 sector_t lba, unsigned long *read_bitmap)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct pblk_sec_meta *meta = pblk_get_meta(pblk, rqd->meta_list, 0);
 	struct ppa_addr ppa;
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
@@ -384,8 +396,10 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 
 retry:
 	if (pblk_ppa_empty(ppa)) {
+		__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+
 		WARN_ON(test_and_set_bit(0, read_bitmap));
-		meta_list[0].lba = cpu_to_le64(ADDR_EMPTY);
+		meta->lba = addr_empty;
 		return;
 	}
 
@@ -399,7 +413,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 		}
 
 		WARN_ON(test_and_set_bit(0, read_bitmap));
-		meta_list[0].lba = cpu_to_le64(lba);
+		meta->lba = cpu_to_le64(lba);
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->cache_reads);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 416d9840544b..6a30b9971283 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -124,7 +124,7 @@ static u64 pblk_sec_in_open_line(struct pblk *pblk, struct pblk_line *line)
 
 struct pblk_recov_alloc {
 	struct ppa_addr *ppa_list;
-	struct pblk_sec_meta *meta_list;
+	void *meta_list;
 	struct nvm_rq *rqd;
 	void *data;
 	dma_addr_t dma_ppa_list;
@@ -158,7 +158,7 @@ static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	struct pblk_sec_meta *meta_list;
+	void *meta_list;
 	struct pblk_pad_rq *pad_rq;
 	struct nvm_rq *rqd;
 	struct bio *bio;
@@ -237,12 +237,15 @@ static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
 
 		for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
 			struct ppa_addr dev_ppa;
+			struct pblk_sec_meta *meta;
 			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
 
 			dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
 
 			pblk_map_invalidate(pblk, dev_ppa);
-			lba_list[w_ptr] = meta_list[i].lba = addr_empty;
+			lba_list[w_ptr] = addr_empty;
+			meta = pblk_get_meta(pblk, meta_list, i);
+			meta->lba = addr_empty;
 			rqd->ppa_list[i] = dev_ppa;
 		}
 	}
@@ -337,7 +340,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct nvm_geo *geo = &dev->geo;
 	struct ppa_addr *ppa_list;
-	struct pblk_sec_meta *meta_list;
+	void *meta_list;
 	struct nvm_rq *rqd;
 	struct bio *bio;
 	void *data;
@@ -435,7 +438,8 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
 	}
 
 	for (i = 0; i < rqd->nr_ppas; i++) {
-		u64 lba = le64_to_cpu(meta_list[i].lba);
+		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
+		u64 lba = le64_to_cpu(meta->lba);
 
 		lba_list[paddr++] = cpu_to_le64(lba);
 
@@ -464,7 +468,7 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 	struct nvm_geo *geo = &dev->geo;
 	struct nvm_rq *rqd;
 	struct ppa_addr *ppa_list;
-	struct pblk_sec_meta *meta_list;
+	void *meta_list;
 	struct pblk_recov_alloc p;
 	void *data;
 	dma_addr_t dma_ppa_list, dma_meta_list;
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 0e9d3960ac4c..80f356688803 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -634,6 +634,7 @@ struct pblk {
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
+	int oob_meta_size; /* Size of OOB sector metadata */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
@@ -1380,6 +1381,11 @@ static inline unsigned int pblk_get_min_chks(struct pblk *pblk)
 	 */
 
 	return DIV_ROUND_UP(100, pblk->op) * lm->blk_per_line;
+}
 
+static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
+							 void *meta, int index)
+{
+	return meta + pblk->oob_meta_size * index;
 }
 #endif /* PBLK_H_ */
-- 
2.14.5

[PATCH v4 3/5] lightnvm: Flexible DMA pool entry size

[Igor Konopko]

Currently whole lightnvm and pblk uses single DMA pool,
for which entry size is always equal to PAGE_SIZE.
PPA list always needs 8B*64, so there is only 56B*64
space for OOB meta. Since NVMe OOB meta can be bigger,
such as 128B, this solution is not robustness.

This patch add the possiblity to support OOB meta above
56b by changing DMA pool size based on OOB meta size.

It also allows pblk to use OOB metadata >=16B.

Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
---
 drivers/lightnvm/core.c          | 30 ++++++++++++++++++++----------
 drivers/lightnvm/pblk-core.c     |  8 ++++----
 drivers/lightnvm/pblk-init.c     |  2 +-
 drivers/lightnvm/pblk-recovery.c |  4 ++--
 drivers/lightnvm/pblk.h          |  6 +++++-
 drivers/nvme/host/lightnvm.c     | 15 +++++++++------
 include/linux/lightnvm.h         |  7 ++++++-
 7 files changed, 47 insertions(+), 25 deletions(-)

diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 73ab3cf26868..e3a83e506458 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -1145,15 +1145,9 @@ int nvm_register(struct nvm_dev *dev)
 	if (!dev->q || !dev->ops)
 		return -EINVAL;
 
-	dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist");
-	if (!dev->dma_pool) {
-		pr_err("nvm: could not create dma pool\n");
-		return -ENOMEM;
-	}
-
 	ret = nvm_init(dev);
 	if (ret)
-		goto err_init;
+		return ret;
 
 	/* register device with a supported media manager */
 	down_write(&nvm_lock);
@@ -1161,9 +1155,6 @@ int nvm_register(struct nvm_dev *dev)
 	up_write(&nvm_lock);
 
 	return 0;
-err_init:
-	dev->ops->destroy_dma_pool(dev->dma_pool);
-	return ret;
 }
 EXPORT_SYMBOL(nvm_register);
 
@@ -1187,6 +1178,25 @@ void nvm_unregister(struct nvm_dev *dev)
 }
 EXPORT_SYMBOL(nvm_unregister);
 
+int nvm_create_dma_pool(struct nvm_dev *dev)
+{
+	int exp_pool_size;
+
+	exp_pool_size = max_t(int, PAGE_SIZE,
+			      (NVM_MAX_VLBA * (sizeof(u64) + dev->geo.sos)));
+	exp_pool_size = round_up(exp_pool_size, PAGE_SIZE);
+
+	dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist",
+						  exp_pool_size);
+	if (!dev->dma_pool) {
+		pr_err("nvm: could not create dma pool\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(nvm_create_dma_pool);
+
 static int __nvm_configure_create(struct nvm_ioctl_create *create)
 {
 	struct nvm_dev *dev;
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index aeb10bd78c62..1347d1a93dd0 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -250,8 +250,8 @@ int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd)
 	if (rqd->nr_ppas == 1)
 		return 0;
 
-	rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
-	rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
+	rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size(pblk);
+	rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size(pblk);
 
 	return 0;
 }
@@ -846,8 +846,8 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
 	if (!meta_list)
 		return -ENOMEM;
 
-	ppa_list = meta_list + pblk_dma_meta_size;
-	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+	ppa_list = meta_list + pblk_dma_meta_size(pblk);
+	dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
 
 next_rq:
 	memset(&rqd, 0, sizeof(struct nvm_rq));
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 6e7a0c6c6655..b67bca810eb7 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -410,7 +410,7 @@ static int pblk_core_init(struct pblk *pblk)
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	pblk->oob_meta_size = geo->sos;
-	if (pblk->oob_meta_size != sizeof(struct pblk_sec_meta)) {
+	if (pblk->oob_meta_size < sizeof(struct pblk_sec_meta)) {
 		pblk_err(pblk, "Unsupported metadata size\n");
 		return -EINVAL;
 	}
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 6a30b9971283..52cbe06e3ebc 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -478,8 +478,8 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 	if (!meta_list)
 		return -ENOMEM;
 
-	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
-	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+	ppa_list = (void *)(meta_list) + pblk_dma_meta_size(pblk);
+	dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
 
 	data = kcalloc(pblk->max_write_pgs, geo->csecs, GFP_KERNEL);
 	if (!data) {
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 80f356688803..9087d53d5c25 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -104,7 +104,6 @@ enum {
 	PBLK_RL_LOW = 4
 };
 
-#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * NVM_MAX_VLBA)
 #define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA)
 
 /* write buffer completion context */
@@ -1388,4 +1387,9 @@ static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
 {
 	return meta + pblk->oob_meta_size * index;
 }
+
+static inline int pblk_dma_meta_size(struct pblk *pblk)
+{
+	return pblk->oob_meta_size * NVM_MAX_VLBA;
+}
 #endif /* PBLK_H_ */
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index d64805dc8efb..60ac32b03fb6 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -732,11 +732,12 @@ static int nvme_nvm_submit_io_sync(struct nvm_dev *dev, struct nvm_rq *rqd)
 	return ret;
 }
 
-static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
+static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name,
+					int size)
 {
 	struct nvme_ns *ns = nvmdev->q->queuedata;
 
-	return dma_pool_create(name, ns->ctrl->dev, PAGE_SIZE, PAGE_SIZE, 0);
+	return dma_pool_create(name, ns->ctrl->dev, size, PAGE_SIZE, 0);
 }
 
 static void nvme_nvm_destroy_dma_pool(void *pool)
@@ -978,11 +979,13 @@ void nvme_nvm_update_nvm_info(struct nvme_ns *ns)
 	struct nvm_dev *ndev = ns->ndev;
 	struct nvm_geo *geo = &ndev->geo;
 
-	if (geo->version == NVM_OCSSD_SPEC_12)
-		return;
+	if (geo->version != NVM_OCSSD_SPEC_12) {
+		geo->csecs = 1 << ns->lba_shift;
+		geo->sos = ns->ms;
+	}
 
-	geo->csecs = 1 << ns->lba_shift;
-	geo->sos = ns->ms;
+	if (nvm_create_dma_pool(ndev))
+		nvm_unregister(ndev);
 }
 
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 2fdeac1a420d..216b373b7fea 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -90,7 +90,7 @@ typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int,
 							struct nvm_chk_meta *);
 typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
 typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *, int);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
 typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
 								dma_addr_t *);
@@ -672,6 +672,7 @@ extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *);
 extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t);
 
 extern struct nvm_dev *nvm_alloc_dev(int);
+extern int nvm_create_dma_pool(struct nvm_dev *);
 extern int nvm_register(struct nvm_dev *);
 extern void nvm_unregister(struct nvm_dev *);
 
@@ -690,6 +691,10 @@ static inline struct nvm_dev *nvm_alloc_dev(int node)
 {
 	return ERR_PTR(-EINVAL);
 }
+static inline int nvm_create_dma_pool(struct nvm_dev *dev)
+{
+	return -EINVAL;
+}
 static inline int nvm_register(struct nvm_dev *dev)
 {
 	return -EINVAL;
-- 
2.14.5

[PATCH v4 4/5] lightnvm: Disable interleaved metadata

[Igor Konopko]

Currently pblk and lightnvm does only check for size
of OOB metadata and does not care wheather this meta
is located in separate buffer or is interleaved with
data in single buffer.

In reality only the first scenario is supported, where
second mode will break pblk functionality during any
IO operation.

The goal of this patch is to block creation of pblk
devices in case of interleaved metadata

Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
---
 drivers/lightnvm/pblk-init.c | 6 ++++++
 drivers/nvme/host/lightnvm.c | 1 +
 include/linux/lightnvm.h     | 1 +
 3 files changed, 8 insertions(+)

diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b67bca810eb7..a728f861edd6 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -1179,6 +1179,12 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (geo->ext) {
+		pblk_err(pblk, "extended metadata not supported\n");
+		kfree(pblk);
+		return ERR_PTR(-EINVAL);
+	}
+
 	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 60ac32b03fb6..ceb92610f43b 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -982,6 +982,7 @@ void nvme_nvm_update_nvm_info(struct nvme_ns *ns)
 	if (geo->version != NVM_OCSSD_SPEC_12) {
 		geo->csecs = 1 << ns->lba_shift;
 		geo->sos = ns->ms;
+		geo->ext = ns->ext;
 	}
 
 	if (nvm_create_dma_pool(ndev))
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 216b373b7fea..2717e6141b1a 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -357,6 +357,7 @@ struct nvm_geo {
 	u32	clba;		/* sectors per chunk */
 	u16	csecs;		/* sector size */
 	u16	sos;		/* out-of-band area size */
+	bool	ext;		/* metadata in extended data buffer */
 
 	/* device write constrains */
 	u32	ws_min;		/* minimum write size */
-- 
2.14.5

[PATCH v4 5/5] lightnvm: pblk: Support for packed metadata

[Igor Konopko]

In current pblk implementation, l2p mapping for not closed lines
is always stored only in OOB metadata and recovered from it.

Such a solution does not provide data integrity when drives does
not have such a OOB metadata space.

The goal of this patch is to add support for so called packed
metadata, which store l2p mapping for open lines in last sector
of every write unit.

After this set of changes, drives with OOB size <16B will use
packed metadata, when >=16B will continue to use OOB metadata.

Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
---
 drivers/lightnvm/pblk-core.c     | 48 ++++++++++++++++++++++++++++++++++++----
 drivers/lightnvm/pblk-init.c     | 38 ++++++++++++++++++++++++++-----
 drivers/lightnvm/pblk-map.c      |  4 ++--
 drivers/lightnvm/pblk-rb.c       |  3 +++
 drivers/lightnvm/pblk-read.c     |  6 +++++
 drivers/lightnvm/pblk-recovery.c |  5 +++--
 drivers/lightnvm/pblk-sysfs.c    |  7 ++++++
 drivers/lightnvm/pblk-write.c    |  9 ++++----
 drivers/lightnvm/pblk.h          | 10 ++++++++-
 9 files changed, 112 insertions(+), 18 deletions(-)

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 1347d1a93dd0..a95e18de5beb 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -376,7 +376,7 @@ void pblk_write_should_kick(struct pblk *pblk)
 {
 	unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
 
-	if (secs_avail >= pblk->min_write_pgs)
+	if (secs_avail >= pblk->min_write_pgs_data)
 		pblk_write_kick(pblk);
 }
 
@@ -407,7 +407,9 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct list_head *move_list = NULL;
-	int vsc = le32_to_cpu(*line->vsc);
+	int packed_meta = (le32_to_cpu(*line->vsc) / pblk->min_write_pgs_data)
+			* (pblk->min_write_pgs - pblk->min_write_pgs_data);
+	int vsc = le32_to_cpu(*line->vsc) + packed_meta;
 
 	lockdep_assert_held(&line->lock);
 
@@ -620,12 +622,15 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 }
 
 int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
-		   unsigned long secs_to_flush)
+		   unsigned long secs_to_flush, bool skip_meta)
 {
 	int max = pblk->sec_per_write;
 	int min = pblk->min_write_pgs;
 	int secs_to_sync = 0;
 
+	if (skip_meta && pblk->min_write_pgs_data != pblk->min_write_pgs)
+		min = max = pblk->min_write_pgs_data;
+
 	if (secs_avail >= max)
 		secs_to_sync = max;
 	else if (secs_avail >= min)
@@ -852,7 +857,7 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
 next_rq:
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
-	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
 	rq_len = rq_ppas * geo->csecs;
 
 	bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len,
@@ -2161,3 +2166,38 @@ void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
 	}
 	spin_unlock(&pblk->trans_lock);
 }
+
+void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	void *buffer;
+
+	if (pblk_is_oob_meta_supported(pblk)) {
+		/* Just use OOB metadata buffer as always */
+		buffer = rqd->meta_list;
+	} else {
+		/* We need to reuse last page of request (packed metadata)
+		 * in similar way as traditional oob metadata
+		 */
+		buffer = page_to_virt(
+			rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page);
+	}
+
+	return buffer;
+}
+
+void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	void *meta_list = rqd->meta_list;
+	void *page;
+	int i = 0;
+
+	if (pblk_is_oob_meta_supported(pblk))
+		return;
+
+	page = page_to_virt(rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page);
+	/* We need to fill oob meta buffer with data from packed metadata */
+	for (; i < rqd->nr_ppas; i++)
+		memcpy(pblk_get_meta(pblk, meta_list, i),
+			page + (i * sizeof(struct pblk_sec_meta)),
+			sizeof(struct pblk_sec_meta));
+}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index a728f861edd6..830ebe3d098a 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -403,6 +403,7 @@ static int pblk_core_init(struct pblk *pblk)
 	pblk->nr_flush_rst = 0;
 
 	pblk->min_write_pgs = geo->ws_opt;
+	pblk->min_write_pgs_data = pblk->min_write_pgs;
 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
 	pblk->max_write_pgs = min_t(int, pblk->max_write_pgs,
@@ -410,9 +411,35 @@ static int pblk_core_init(struct pblk *pblk)
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	pblk->oob_meta_size = geo->sos;
-	if (pblk->oob_meta_size < sizeof(struct pblk_sec_meta)) {
-		pblk_err(pblk, "Unsupported metadata size\n");
-		return -EINVAL;
+	if (!pblk_is_oob_meta_supported(pblk)) {
+		/* For drives which does not have OOB metadata feature
+		 * in order to support recovery feature we need to use
+		 * so called packed metadata. Packed metada will store
+		 * the same information as OOB metadata (l2p table mapping,
+		 * but in the form of the single page at the end of
+		 * every write request.
+		 */
+		if (pblk->min_write_pgs
+			* sizeof(struct pblk_sec_meta) > PAGE_SIZE) {
+			/* We want to keep all the packed metadata on single
+			 * page per write requests. So we need to ensure that
+			 * it will fit.
+			 *
+			 * This is more like sanity check, since there is
+			 * no device with such a big minimal write size
+			 * (above 1 metabytes).
+			 */
+			pblk_err(pblk, "Not supported min write size\n");
+			return -EINVAL;
+		}
+		/* For packed meta approach we do some simplification.
+		 * On read path we always issue requests which size
+		 * equal to max_write_pgs, with all pages filled with
+		 * user payload except of last one page which will be
+		 * filled with packed metadata.
+		 */
+		pblk->max_write_pgs = pblk->min_write_pgs;
+		pblk->min_write_pgs_data = pblk->min_write_pgs - 1;
 	}
 
 	pblk->pad_dist = kcalloc(pblk->min_write_pgs - 1, sizeof(atomic64_t),
@@ -645,7 +672,7 @@ static int pblk_set_provision(struct pblk *pblk, int nr_free_chks)
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct nvm_geo *geo = &dev->geo;
 	sector_t provisioned;
-	int sec_meta, blk_meta;
+	int sec_meta, blk_meta, clba;
 	int minimum;
 
 	if (geo->op == NVM_TARGET_DEFAULT_OP)
@@ -686,7 +713,8 @@ static int pblk_set_provision(struct pblk *pblk, int nr_free_chks)
 	sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines;
 	blk_meta = DIV_ROUND_UP(sec_meta, geo->clba);
 
-	pblk->capacity = (provisioned - blk_meta) * geo->clba;
+	clba = (geo->clba / pblk->min_write_pgs) * pblk->min_write_pgs_data;
+	pblk->capacity = (provisioned - blk_meta) * clba;
 
 	atomic_set(&pblk->rl.free_blocks, nr_free_chks);
 	atomic_set(&pblk->rl.free_user_blocks, nr_free_chks);
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 81e503ec384e..79df583ea709 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -96,7 +96,7 @@ int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
 		 unsigned long *lun_bitmap, unsigned int valid_secs,
 		 unsigned int off)
 {
-	void *meta_list = rqd->meta_list;
+	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
 	void *meta_buffer;
 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
 	unsigned int map_secs;
@@ -125,7 +125,7 @@ int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_line_meta *lm = &pblk->lm;
-	void *meta_list = rqd->meta_list;
+	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
 	void *meta_buffer;
 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
 	struct pblk_line *e_line, *d_line;
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 9f7fa0fe9c77..d4ca8c64ee0f 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -552,6 +552,9 @@ unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
 		to_read = count;
 	}
 
+	/* Add space for packed metadata if in use*/
+	pad += (pblk->min_write_pgs - pblk->min_write_pgs_data);
+
 	c_ctx->sentry = pos;
 	c_ctx->nr_valid = to_read;
 	c_ctx->nr_padded = pad;
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 6becd85ca4c6..3789185144da 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -112,6 +112,9 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 	int nr_lbas = rqd->nr_ppas;
 	int i;
 
+	if (!pblk_is_oob_meta_supported(pblk))
+		return;
+
 	for (i = 0; i < nr_lbas; i++) {
 		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
 		u64 lba = le64_to_cpu(meta->lba);
@@ -141,6 +144,9 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 	void *meta_lba_list = rqd->meta_list;
 	int i, j;
 
+	if (!pblk_is_oob_meta_supported(pblk))
+		return;
+
 	for (i = 0, j = 0; i < nr_lbas; i++) {
 		struct pblk_sec_meta *meta = pblk_get_meta(pblk,
 							   meta_lba_list, j);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 52cbe06e3ebc..d1960aa640d2 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -188,7 +188,7 @@ static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
 	kref_init(&pad_rq->ref);
 
 next_pad_rq:
-	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
 	if (rq_ppas < pblk->min_write_pgs) {
 		pblk_err(pblk, "corrupted pad line %d\n", line->id);
 		goto fail_free_pad;
@@ -368,7 +368,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
 next_rq:
 	memset(rqd, 0, pblk_g_rq_size);
 
-	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
 	if (!rq_ppas)
 		rq_ppas = pblk->min_write_pgs;
 	rq_len = rq_ppas * geo->csecs;
@@ -437,6 +437,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
 		goto retry_rq;
 	}
 
+	pblk_get_packed_meta(pblk, rqd);
 	for (i = 0; i < rqd->nr_ppas; i++) {
 		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
 		u64 lba = le64_to_cpu(meta->lba);
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index 2d2818155aa8..7d8958df9472 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -479,6 +479,13 @@ static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk,
 	if (kstrtouint(page, 0, &sec_per_write))
 		return -EINVAL;
 
+	if (!pblk_is_oob_meta_supported(pblk)) {
+		/* For packed metadata case it is
+		 * not allowed to change sec_per_write.
+		 */
+		return -EINVAL;
+	}
+
 	if (sec_per_write < pblk->min_write_pgs
 				|| sec_per_write > pblk->max_write_pgs
 				|| sec_per_write % pblk->min_write_pgs != 0)
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 2bf78f81862d..06d56deb645d 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -348,7 +348,7 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 {
 	int secs_to_sync;
 
-	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
+	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush, true);
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
 	if ((!secs_to_sync && secs_to_flush)
@@ -569,7 +569,7 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
 	struct bio *bio;
 	struct nvm_rq *rqd;
 	unsigned int secs_avail, secs_to_sync, secs_to_com;
-	unsigned int secs_to_flush;
+	unsigned int secs_to_flush, packed_meta_pgs;
 	unsigned long pos;
 	unsigned int resubmit;
 
@@ -607,7 +607,7 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
 			return 0;
 
 		secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
-		if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+		if (!secs_to_flush && secs_avail < pblk->min_write_pgs_data)
 			return 0;
 
 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
@@ -622,7 +622,8 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
 		pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
 	}
 
-	bio = bio_alloc(GFP_KERNEL, secs_to_sync);
+	packed_meta_pgs = (pblk->min_write_pgs - pblk->min_write_pgs_data);
+	bio = bio_alloc(GFP_KERNEL, secs_to_sync + packed_meta_pgs);
 
 	bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9087d53d5c25..bc40b1381ff6 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -632,6 +632,7 @@ struct pblk {
 	int state;			/* pblk line state */
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
+	int min_write_pgs_data; /* Minimum amount of payload pages */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
 	int oob_meta_size; /* Size of OOB sector metadata */
 
@@ -838,7 +839,7 @@ void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
 int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
-		   unsigned long secs_to_flush);
+		   unsigned long secs_to_flush, bool skip_meta);
 void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa,
 		  unsigned long *lun_bitmap);
 void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa);
@@ -862,6 +863,8 @@ void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
 			  u64 *lba_list, int nr_secs);
 void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
 			 sector_t blba, int nr_secs);
+void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd);
+void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd);
 
 /*
  * pblk user I/O write path
@@ -1392,4 +1395,9 @@ static inline int pblk_dma_meta_size(struct pblk *pblk)
 {
 	return pblk->oob_meta_size * NVM_MAX_VLBA;
 }
+
+static inline int pblk_is_oob_meta_supported(struct pblk *pblk)
+{
+	return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta);
+}
 #endif /* PBLK_H_ */
-- 
2.14.5

Re: [PATCH v4 5/5] lightnvm: pblk: Support for packed metadata

[Javier Gonzalez]

[-- Attachment #1: Type: text/plain, Size: 15372 bytes --]

> On 29 Nov 2018, at 08.16, Igor Konopko <igor.j.konopko@intel.com> wrote:
> 
> In current pblk implementation, l2p mapping for not closed lines
> is always stored only in OOB metadata and recovered from it.
> 
> Such a solution does not provide data integrity when drives does
> not have such a OOB metadata space.
> 
> The goal of this patch is to add support for so called packed
> metadata, which store l2p mapping for open lines in last sector
> of every write unit.
> 
> After this set of changes, drives with OOB size <16B will use
> packed metadata, when >=16B will continue to use OOB metadata.
> 
> Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
> ---
> drivers/lightnvm/pblk-core.c     | 48 ++++++++++++++++++++++++++++++++++++----
> drivers/lightnvm/pblk-init.c     | 38 ++++++++++++++++++++++++++-----
> drivers/lightnvm/pblk-map.c      |  4 ++--
> drivers/lightnvm/pblk-rb.c       |  3 +++
> drivers/lightnvm/pblk-read.c     |  6 +++++
> drivers/lightnvm/pblk-recovery.c |  5 +++--
> drivers/lightnvm/pblk-sysfs.c    |  7 ++++++
> drivers/lightnvm/pblk-write.c    |  9 ++++----
> drivers/lightnvm/pblk.h          | 10 ++++++++-
> 9 files changed, 112 insertions(+), 18 deletions(-)
> 
> diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
> index 1347d1a93dd0..a95e18de5beb 100644
> --- a/drivers/lightnvm/pblk-core.c
> +++ b/drivers/lightnvm/pblk-core.c
> @@ -376,7 +376,7 @@ void pblk_write_should_kick(struct pblk *pblk)
> {
> 	unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
> 
> -	if (secs_avail >= pblk->min_write_pgs)
> +	if (secs_avail >= pblk->min_write_pgs_data)
> 		pblk_write_kick(pblk);
> }
> 
> @@ -407,7 +407,9 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
> 	struct pblk_line_meta *lm = &pblk->lm;
> 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
> 	struct list_head *move_list = NULL;
> -	int vsc = le32_to_cpu(*line->vsc);
> +	int packed_meta = (le32_to_cpu(*line->vsc) / pblk->min_write_pgs_data)
> +			* (pblk->min_write_pgs - pblk->min_write_pgs_data);
> +	int vsc = le32_to_cpu(*line->vsc) + packed_meta;
> 
> 	lockdep_assert_held(&line->lock);
> 
> @@ -620,12 +622,15 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
> }
> 
> int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
> -		   unsigned long secs_to_flush)
> +		   unsigned long secs_to_flush, bool skip_meta)
> {
> 	int max = pblk->sec_per_write;
> 	int min = pblk->min_write_pgs;
> 	int secs_to_sync = 0;
> 
> +	if (skip_meta && pblk->min_write_pgs_data != pblk->min_write_pgs)
> +		min = max = pblk->min_write_pgs_data;
> +
> 	if (secs_avail >= max)
> 		secs_to_sync = max;
> 	else if (secs_avail >= min)
> @@ -852,7 +857,7 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
> next_rq:
> 	memset(&rqd, 0, sizeof(struct nvm_rq));
> 
> -	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
> +	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
> 	rq_len = rq_ppas * geo->csecs;
> 
> 	bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len,
> @@ -2161,3 +2166,38 @@ void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
> 	}
> 	spin_unlock(&pblk->trans_lock);
> }
> +
> +void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd)
> +{
> +	void *buffer;
> +
> +	if (pblk_is_oob_meta_supported(pblk)) {
> +		/* Just use OOB metadata buffer as always */
> +		buffer = rqd->meta_list;
> +	} else {
> +		/* We need to reuse last page of request (packed metadata)
> +		 * in similar way as traditional oob metadata
> +		 */
> +		buffer = page_to_virt(
> +			rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page);
> +	}
> +
> +	return buffer;
> +}
> +
> +void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd)
> +{
> +	void *meta_list = rqd->meta_list;
> +	void *page;
> +	int i = 0;
> +
> +	if (pblk_is_oob_meta_supported(pblk))
> +		return;
> +
> +	page = page_to_virt(rqd->bio->bi_io_vec[rqd->bio->bi_vcnt - 1].bv_page);
> +	/* We need to fill oob meta buffer with data from packed metadata */
> +	for (; i < rqd->nr_ppas; i++)
> +		memcpy(pblk_get_meta(pblk, meta_list, i),
> +			page + (i * sizeof(struct pblk_sec_meta)),
> +			sizeof(struct pblk_sec_meta));
> +}
> diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
> index a728f861edd6..830ebe3d098a 100644
> --- a/drivers/lightnvm/pblk-init.c
> +++ b/drivers/lightnvm/pblk-init.c
> @@ -403,6 +403,7 @@ static int pblk_core_init(struct pblk *pblk)
> 	pblk->nr_flush_rst = 0;
> 
> 	pblk->min_write_pgs = geo->ws_opt;
> +	pblk->min_write_pgs_data = pblk->min_write_pgs;
> 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
> 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
> 	pblk->max_write_pgs = min_t(int, pblk->max_write_pgs,
> @@ -410,9 +411,35 @@ static int pblk_core_init(struct pblk *pblk)
> 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
> 
> 	pblk->oob_meta_size = geo->sos;
> -	if (pblk->oob_meta_size < sizeof(struct pblk_sec_meta)) {
> -		pblk_err(pblk, "Unsupported metadata size\n");
> -		return -EINVAL;
> +	if (!pblk_is_oob_meta_supported(pblk)) {
> +		/* For drives which does not have OOB metadata feature
> +		 * in order to support recovery feature we need to use
> +		 * so called packed metadata. Packed metada will store
> +		 * the same information as OOB metadata (l2p table mapping,
> +		 * but in the form of the single page at the end of
> +		 * every write request.
> +		 */
> +		if (pblk->min_write_pgs
> +			* sizeof(struct pblk_sec_meta) > PAGE_SIZE) {
> +			/* We want to keep all the packed metadata on single
> +			 * page per write requests. So we need to ensure that
> +			 * it will fit.
> +			 *
> +			 * This is more like sanity check, since there is
> +			 * no device with such a big minimal write size
> +			 * (above 1 metabytes).
> +			 */
> +			pblk_err(pblk, "Not supported min write size\n");
> +			return -EINVAL;
> +		}
> +		/* For packed meta approach we do some simplification.
> +		 * On read path we always issue requests which size
> +		 * equal to max_write_pgs, with all pages filled with
> +		 * user payload except of last one page which will be
> +		 * filled with packed metadata.
> +		 */
> +		pblk->max_write_pgs = pblk->min_write_pgs;
> +		pblk->min_write_pgs_data = pblk->min_write_pgs - 1;
> 	}
> 
> 	pblk->pad_dist = kcalloc(pblk->min_write_pgs - 1, sizeof(atomic64_t),
> @@ -645,7 +672,7 @@ static int pblk_set_provision(struct pblk *pblk, int nr_free_chks)
> 	struct pblk_line_meta *lm = &pblk->lm;
> 	struct nvm_geo *geo = &dev->geo;
> 	sector_t provisioned;
> -	int sec_meta, blk_meta;
> +	int sec_meta, blk_meta, clba;
> 	int minimum;
> 
> 	if (geo->op == NVM_TARGET_DEFAULT_OP)
> @@ -686,7 +713,8 @@ static int pblk_set_provision(struct pblk *pblk, int nr_free_chks)
> 	sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines;
> 	blk_meta = DIV_ROUND_UP(sec_meta, geo->clba);
> 
> -	pblk->capacity = (provisioned - blk_meta) * geo->clba;
> +	clba = (geo->clba / pblk->min_write_pgs) * pblk->min_write_pgs_data;
> +	pblk->capacity = (provisioned - blk_meta) * clba;
> 
> 	atomic_set(&pblk->rl.free_blocks, nr_free_chks);
> 	atomic_set(&pblk->rl.free_user_blocks, nr_free_chks);
> diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
> index 81e503ec384e..79df583ea709 100644
> --- a/drivers/lightnvm/pblk-map.c
> +++ b/drivers/lightnvm/pblk-map.c
> @@ -96,7 +96,7 @@ int pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
> 		 unsigned long *lun_bitmap, unsigned int valid_secs,
> 		 unsigned int off)
> {
> -	void *meta_list = rqd->meta_list;
> +	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
> 	void *meta_buffer;
> 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
> 	unsigned int map_secs;
> @@ -125,7 +125,7 @@ int pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
> 	struct nvm_tgt_dev *dev = pblk->dev;
> 	struct nvm_geo *geo = &dev->geo;
> 	struct pblk_line_meta *lm = &pblk->lm;
> -	void *meta_list = rqd->meta_list;
> +	void *meta_list = pblk_get_meta_for_writes(pblk, rqd);
> 	void *meta_buffer;
> 	struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);
> 	struct pblk_line *e_line, *d_line;
> diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
> index 9f7fa0fe9c77..d4ca8c64ee0f 100644
> --- a/drivers/lightnvm/pblk-rb.c
> +++ b/drivers/lightnvm/pblk-rb.c
> @@ -552,6 +552,9 @@ unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
> 		to_read = count;
> 	}
> 
> +	/* Add space for packed metadata if in use*/
> +	pad += (pblk->min_write_pgs - pblk->min_write_pgs_data);
> +
> 	c_ctx->sentry = pos;
> 	c_ctx->nr_valid = to_read;
> 	c_ctx->nr_padded = pad;
> diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
> index 6becd85ca4c6..3789185144da 100644
> --- a/drivers/lightnvm/pblk-read.c
> +++ b/drivers/lightnvm/pblk-read.c
> @@ -112,6 +112,9 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
> 	int nr_lbas = rqd->nr_ppas;
> 	int i;
> 
> +	if (!pblk_is_oob_meta_supported(pblk))
> +		return;
> +
> 	for (i = 0; i < nr_lbas; i++) {
> 		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
> 		u64 lba = le64_to_cpu(meta->lba);
> @@ -141,6 +144,9 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
> 	void *meta_lba_list = rqd->meta_list;
> 	int i, j;
> 
> +	if (!pblk_is_oob_meta_supported(pblk))
> +		return;
> +
> 	for (i = 0, j = 0; i < nr_lbas; i++) {
> 		struct pblk_sec_meta *meta = pblk_get_meta(pblk,
> 							   meta_lba_list, j);
> diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
> index 52cbe06e3ebc..d1960aa640d2 100644
> --- a/drivers/lightnvm/pblk-recovery.c
> +++ b/drivers/lightnvm/pblk-recovery.c
> @@ -188,7 +188,7 @@ static int pblk_recov_pad_line(struct pblk *pblk, struct pblk_line *line,
> 	kref_init(&pad_rq->ref);
> 
> next_pad_rq:
> -	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
> +	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
> 	if (rq_ppas < pblk->min_write_pgs) {
> 		pblk_err(pblk, "corrupted pad line %d\n", line->id);
> 		goto fail_free_pad;
> @@ -368,7 +368,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
> next_rq:
> 	memset(rqd, 0, pblk_g_rq_size);
> 
> -	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
> +	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0, false);
> 	if (!rq_ppas)
> 		rq_ppas = pblk->min_write_pgs;
> 	rq_len = rq_ppas * geo->csecs;
> @@ -437,6 +437,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
> 		goto retry_rq;
> 	}
> 
> +	pblk_get_packed_meta(pblk, rqd);
> 	for (i = 0; i < rqd->nr_ppas; i++) {
> 		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
> 		u64 lba = le64_to_cpu(meta->lba);
> diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
> index 2d2818155aa8..7d8958df9472 100644
> --- a/drivers/lightnvm/pblk-sysfs.c
> +++ b/drivers/lightnvm/pblk-sysfs.c
> @@ -479,6 +479,13 @@ static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk,
> 	if (kstrtouint(page, 0, &sec_per_write))
> 		return -EINVAL;
> 
> +	if (!pblk_is_oob_meta_supported(pblk)) {
> +		/* For packed metadata case it is
> +		 * not allowed to change sec_per_write.
> +		 */
> +		return -EINVAL;
> +	}
> +
> 	if (sec_per_write < pblk->min_write_pgs
> 				|| sec_per_write > pblk->max_write_pgs
> 				|| sec_per_write % pblk->min_write_pgs != 0)
> diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
> index 2bf78f81862d..06d56deb645d 100644
> --- a/drivers/lightnvm/pblk-write.c
> +++ b/drivers/lightnvm/pblk-write.c
> @@ -348,7 +348,7 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
> {
> 	int secs_to_sync;
> 
> -	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
> +	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush, true);
> 
> #ifdef CONFIG_NVM_PBLK_DEBUG
> 	if ((!secs_to_sync && secs_to_flush)
> @@ -569,7 +569,7 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
> 	struct bio *bio;
> 	struct nvm_rq *rqd;
> 	unsigned int secs_avail, secs_to_sync, secs_to_com;
> -	unsigned int secs_to_flush;
> +	unsigned int secs_to_flush, packed_meta_pgs;
> 	unsigned long pos;
> 	unsigned int resubmit;
> 
> @@ -607,7 +607,7 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
> 			return 0;
> 
> 		secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
> -		if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
> +		if (!secs_to_flush && secs_avail < pblk->min_write_pgs_data)
> 			return 0;
> 
> 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
> @@ -622,7 +622,8 @@ static int pblk_submit_write(struct pblk *pblk, int *secs_left)
> 		pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
> 	}
> 
> -	bio = bio_alloc(GFP_KERNEL, secs_to_sync);
> +	packed_meta_pgs = (pblk->min_write_pgs - pblk->min_write_pgs_data);
> +	bio = bio_alloc(GFP_KERNEL, secs_to_sync + packed_meta_pgs);
> 
> 	bio->bi_iter.bi_sector = 0; /* internal bio */
> 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
> diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
> index 9087d53d5c25..bc40b1381ff6 100644
> --- a/drivers/lightnvm/pblk.h
> +++ b/drivers/lightnvm/pblk.h
> @@ -632,6 +632,7 @@ struct pblk {
> 	int state;			/* pblk line state */
> 
> 	int min_write_pgs; /* Minimum amount of pages required by controller */
> +	int min_write_pgs_data; /* Minimum amount of payload pages */
> 	int max_write_pgs; /* Maximum amount of pages supported by controller */
> 	int oob_meta_size; /* Size of OOB sector metadata */
> 
> @@ -838,7 +839,7 @@ void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
> u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
> u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
> int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
> -		   unsigned long secs_to_flush);
> +		   unsigned long secs_to_flush, bool skip_meta);
> void pblk_down_rq(struct pblk *pblk, struct ppa_addr ppa,
> 		  unsigned long *lun_bitmap);
> void pblk_down_chunk(struct pblk *pblk, struct ppa_addr ppa);
> @@ -862,6 +863,8 @@ void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
> 			  u64 *lba_list, int nr_secs);
> void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
> 			 sector_t blba, int nr_secs);
> +void *pblk_get_meta_for_writes(struct pblk *pblk, struct nvm_rq *rqd);
> +void pblk_get_packed_meta(struct pblk *pblk, struct nvm_rq *rqd);
> 
> /*
>  * pblk user I/O write path
> @@ -1392,4 +1395,9 @@ static inline int pblk_dma_meta_size(struct pblk *pblk)
> {
> 	return pblk->oob_meta_size * NVM_MAX_VLBA;
> }
> +
> +static inline int pblk_is_oob_meta_supported(struct pblk *pblk)
> +{
> +	return pblk->oob_meta_size >= sizeof(struct pblk_sec_meta);
> +}
> #endif /* PBLK_H_ */
> --
> 2.14.5


Looks good to me.

Reviewed-by: Javier González <javier@cnexlabs.com>


[-- Attachment #2: Message signed with OpenPGP --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v4 0/5] lightnvm: Flexible metadata

[Javier Gonzalez]

[-- Attachment #1: Type: text/plain, Size: 2457 bytes --]

> On 29 Nov 2018, at 08.16, Igor Konopko <igor.j.konopko@intel.com> wrote:
> 
> This series of patches extends the way how pblk can
> store L2P sector metadata. After this set of changes
> any size of NVMe metadata is supported in pblk.
> Also there is an support for case without NVMe metadata.
> 
> Changes v3 --> v4:
> -rename nvm_alloc_dma_pool() to nvm_create_dma_pool()
> -split pblk_get_meta() calls and lba setting into
> two operations for better core readability
> -fixing compilation with CONFIG_NVM disabled
> -getting rid of unnecessary memcpy for packed metadata
> on write path
> -support for drives with oob size >0 and <16B in packed
> metadata mode
> -minor commit message updates
> 
> Changes v2 --> v3:
> -Rebase on top of ocssd/for-4.21/core
> -get/set_meta_lba helpers were removed
> -dma reallocation was replaced with single allocation
> -oob metadata size was added to pblk structure
> -proper checks on pblk creation were added
> 
> Changes v1 --> v2:
> -Revert sector meta size back to 16b for pblk
> -Dma pool for larger oob meta are handled in core instead of pblk
> -Pblk oob meta helpers uses __le64 as input outpu instead of u64
> -Other minor fixes based on v1 patch review
> 
> Igor Konopko (5):
>  lightnvm: pblk: Move lba list to partial read context
>  lightnvm: pblk: Helpers for OOB metadata
>  lightnvm: Flexible DMA pool entry size
>  lightnvm: Disable interleaved metadata
>  lightnvm: pblk: Support for packed metadata
> 
> drivers/lightnvm/core.c          | 30 ++++++++++++------
> drivers/lightnvm/pblk-core.c     | 61 +++++++++++++++++++++++++++++++------
> drivers/lightnvm/pblk-init.c     | 44 +++++++++++++++++++++++++--
> drivers/lightnvm/pblk-map.c      | 20 +++++++-----
> drivers/lightnvm/pblk-rb.c       |  3 ++
> drivers/lightnvm/pblk-read.c     | 66 +++++++++++++++++++++++-----------------
> drivers/lightnvm/pblk-recovery.c | 25 +++++++++------
> drivers/lightnvm/pblk-sysfs.c    |  7 +++++
> drivers/lightnvm/pblk-write.c    |  9 +++---
> drivers/lightnvm/pblk.h          | 24 +++++++++++++--
> drivers/nvme/host/lightnvm.c     | 16 ++++++----
> include/linux/lightnvm.h         |  8 ++++-
> 12 files changed, 233 insertions(+), 80 deletions(-)
> 
> --
> 2.14.5


I gave a pass to V4 and it looks good.

We will test the patches suite. If nothing comes up, and Matias does not
have any reservations, it should be good for 4.21.

Javier

[-- Attachment #2: Message signed with OpenPGP --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v4 3/5] lightnvm: Flexible DMA pool entry size

[Matias Bjørling]

On 11/29/2018 08:16 AM, Igor Konopko wrote:
> Currently whole lightnvm and pblk uses single DMA pool,
> for which entry size is always equal to PAGE_SIZE.
> PPA list always needs 8B*64, so there is only 56B*64
> space for OOB meta. Since NVMe OOB meta can be bigger,
> such as 128B, this solution is not robustness.
> 
> This patch add the possiblity to support OOB meta above
> 56b by changing DMA pool size based on OOB meta size.
> 
> It also allows pblk to use OOB metadata >=16B.
> 
> Reviewed-by: Javier González <javier@cnexlabs.com>
> Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
> ---
>   drivers/lightnvm/core.c          | 30 ++++++++++++++++++++----------
>   drivers/lightnvm/pblk-core.c     |  8 ++++----
>   drivers/lightnvm/pblk-init.c     |  2 +-
>   drivers/lightnvm/pblk-recovery.c |  4 ++--
>   drivers/lightnvm/pblk.h          |  6 +++++-
>   drivers/nvme/host/lightnvm.c     | 15 +++++++++------
>   include/linux/lightnvm.h         |  7 ++++++-
>   7 files changed, 47 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
> index 73ab3cf26868..e3a83e506458 100644
> --- a/drivers/lightnvm/core.c
> +++ b/drivers/lightnvm/core.c
> @@ -1145,15 +1145,9 @@ int nvm_register(struct nvm_dev *dev)
>   	if (!dev->q || !dev->ops)
>   		return -EINVAL;
>   
> -	dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist");
> -	if (!dev->dma_pool) {
> -		pr_err("nvm: could not create dma pool\n");
> -		return -ENOMEM;
> -	}
> -
>   	ret = nvm_init(dev);
>   	if (ret)
> -		goto err_init;
> +		return ret;
>   
>   	/* register device with a supported media manager */
>   	down_write(&nvm_lock);
> @@ -1161,9 +1155,6 @@ int nvm_register(struct nvm_dev *dev)
>   	up_write(&nvm_lock);
>   
>   	return 0;
> -err_init:
> -	dev->ops->destroy_dma_pool(dev->dma_pool);
> -	return ret;
>   }
>   EXPORT_SYMBOL(nvm_register);
>   
> @@ -1187,6 +1178,25 @@ void nvm_unregister(struct nvm_dev *dev)
>   }
>   EXPORT_SYMBOL(nvm_unregister);
>   
> +int nvm_create_dma_pool(struct nvm_dev *dev)
> +{
> +	int exp_pool_size;
> +
> +	exp_pool_size = max_t(int, PAGE_SIZE,
> +			      (NVM_MAX_VLBA * (sizeof(u64) + dev->geo.sos)));
> +	exp_pool_size = round_up(exp_pool_size, PAGE_SIZE);
> +
> +	dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist",
> +						  exp_pool_size);
> +	if (!dev->dma_pool) {
> +		pr_err("nvm: could not create dma pool\n");
> +		return -ENOMEM;
> +	}
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL(nvm_create_dma_pool);
> +
>   static int __nvm_configure_create(struct nvm_ioctl_create *create)
>   {
>   	struct nvm_dev *dev;
> diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
> index aeb10bd78c62..1347d1a93dd0 100644
> --- a/drivers/lightnvm/pblk-core.c
> +++ b/drivers/lightnvm/pblk-core.c
> @@ -250,8 +250,8 @@ int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd)
>   	if (rqd->nr_ppas == 1)
>   		return 0;
>   
> -	rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
> -	rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
> +	rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size(pblk);
> +	rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size(pblk);
>   
>   	return 0;
>   }
> @@ -846,8 +846,8 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
>   	if (!meta_list)
>   		return -ENOMEM;
>   
> -	ppa_list = meta_list + pblk_dma_meta_size;
> -	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
> +	ppa_list = meta_list + pblk_dma_meta_size(pblk);
> +	dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
>   
>   next_rq:
>   	memset(&rqd, 0, sizeof(struct nvm_rq));
> diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
> index 6e7a0c6c6655..b67bca810eb7 100644
> --- a/drivers/lightnvm/pblk-init.c
> +++ b/drivers/lightnvm/pblk-init.c
> @@ -410,7 +410,7 @@ static int pblk_core_init(struct pblk *pblk)
>   	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
>   
>   	pblk->oob_meta_size = geo->sos;
> -	if (pblk->oob_meta_size != sizeof(struct pblk_sec_meta)) {
> +	if (pblk->oob_meta_size < sizeof(struct pblk_sec_meta)) {
>   		pblk_err(pblk, "Unsupported metadata size\n");
>   		return -EINVAL;
>   	}
> diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
> index 6a30b9971283..52cbe06e3ebc 100644
> --- a/drivers/lightnvm/pblk-recovery.c
> +++ b/drivers/lightnvm/pblk-recovery.c
> @@ -478,8 +478,8 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
>   	if (!meta_list)
>   		return -ENOMEM;
>   
> -	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
> -	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
> +	ppa_list = (void *)(meta_list) + pblk_dma_meta_size(pblk);
> +	dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
>   
>   	data = kcalloc(pblk->max_write_pgs, geo->csecs, GFP_KERNEL);
>   	if (!data) {
> diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
> index 80f356688803..9087d53d5c25 100644
> --- a/drivers/lightnvm/pblk.h
> +++ b/drivers/lightnvm/pblk.h
> @@ -104,7 +104,6 @@ enum {
>   	PBLK_RL_LOW = 4
>   };
>   
> -#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * NVM_MAX_VLBA)
>   #define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA)
>   
>   /* write buffer completion context */
> @@ -1388,4 +1387,9 @@ static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
>   {
>   	return meta + pblk->oob_meta_size * index;
>   }
> +
> +static inline int pblk_dma_meta_size(struct pblk *pblk)
> +{
> +	return pblk->oob_meta_size * NVM_MAX_VLBA;
> +}
>   #endif /* PBLK_H_ */
> diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
> index d64805dc8efb..60ac32b03fb6 100644
> --- a/drivers/nvme/host/lightnvm.c
> +++ b/drivers/nvme/host/lightnvm.c
> @@ -732,11 +732,12 @@ static int nvme_nvm_submit_io_sync(struct nvm_dev *dev, struct nvm_rq *rqd)
>   	return ret;
>   }
>   
> -static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
> +static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name,
> +					int size)
>   {
>   	struct nvme_ns *ns = nvmdev->q->queuedata;
>   
> -	return dma_pool_create(name, ns->ctrl->dev, PAGE_SIZE, PAGE_SIZE, 0);
> +	return dma_pool_create(name, ns->ctrl->dev, size, PAGE_SIZE, 0);
>   }
>   
>   static void nvme_nvm_destroy_dma_pool(void *pool)
> @@ -978,11 +979,13 @@ void nvme_nvm_update_nvm_info(struct nvme_ns *ns)
>   	struct nvm_dev *ndev = ns->ndev;
>   	struct nvm_geo *geo = &ndev->geo;
>   
> -	if (geo->version == NVM_OCSSD_SPEC_12)
> -		return;
> +	if (geo->version != NVM_OCSSD_SPEC_12) {
> +		geo->csecs = 1 << ns->lba_shift;
> +		geo->sos = ns->ms;
> +	}
>   
> -	geo->csecs = 1 << ns->lba_shift;
> -	geo->sos = ns->ms;
> +	if (nvm_create_dma_pool(ndev))
> +		nvm_unregister(ndev);
>   }

This breaks when the drive is invalidated and reread. Each time it 
allocates new memory.

I propose to fix the two step enumeration of the geometry, such that we 
can do the proper allocated from nvm_register(), instead of punting it 
to nvme_nvm_update_info.

Please review the patch I sent, and let me know if we can use that to 
simplify this patch.

Re: [PATCH v4 0/5] lightnvm: Flexible metadata

[Matias Bjørling]

On 11/29/2018 08:16 AM, Igor Konopko wrote:
> This series of patches extends the way how pblk can
> store L2P sector metadata. After this set of changes
> any size of NVMe metadata is supported in pblk.
> Also there is an support for case without NVMe metadata.
> 
> Changes v3 --> v4:
> -rename nvm_alloc_dma_pool() to nvm_create_dma_pool()
> -split pblk_get_meta() calls and lba setting into
> two operations for better core readability
> -fixing compilation with CONFIG_NVM disabled
> -getting rid of unnecessary memcpy for packed metadata
> on write path
> -support for drives with oob size >0 and <16B in packed
> metadata mode
> -minor commit message updates
> 
> Changes v2 --> v3:
> -Rebase on top of ocssd/for-4.21/core
> -get/set_meta_lba helpers were removed
> -dma reallocation was replaced with single allocation
> -oob metadata size was added to pblk structure
> -proper checks on pblk creation were added
>   
> Changes v1 --> v2:
> -Revert sector meta size back to 16b for pblk
> -Dma pool for larger oob meta are handled in core instead of pblk
> -Pblk oob meta helpers uses __le64 as input outpu instead of u64
> -Other minor fixes based on v1 patch review
> 
> Igor Konopko (5):
>    lightnvm: pblk: Move lba list to partial read context
>    lightnvm: pblk: Helpers for OOB metadata
>    lightnvm: Flexible DMA pool entry size
>    lightnvm: Disable interleaved metadata
>    lightnvm: pblk: Support for packed metadata
> 
>   drivers/lightnvm/core.c          | 30 ++++++++++++------
>   drivers/lightnvm/pblk-core.c     | 61 +++++++++++++++++++++++++++++++------
>   drivers/lightnvm/pblk-init.c     | 44 +++++++++++++++++++++++++--
>   drivers/lightnvm/pblk-map.c      | 20 +++++++-----
>   drivers/lightnvm/pblk-rb.c       |  3 ++
>   drivers/lightnvm/pblk-read.c     | 66 +++++++++++++++++++++++-----------------
>   drivers/lightnvm/pblk-recovery.c | 25 +++++++++------
>   drivers/lightnvm/pblk-sysfs.c    |  7 +++++
>   drivers/lightnvm/pblk-write.c    |  9 +++---
>   drivers/lightnvm/pblk.h          | 24 +++++++++++++--
>   drivers/nvme/host/lightnvm.c     | 16 ++++++----
>   include/linux/lightnvm.h         |  8 ++++-
>   12 files changed, 233 insertions(+), 80 deletions(-)
> 

Igor,

I pushed the preparation patch to core. Please rebase and I'll pick up 
the patches.

Thank you.