From cd8ddbf7a5e206fe6995ab0aee245d597dd6a7f2 Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:03 +0200
Subject: lightnvm: pblk: free padded entries in write buffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a REQ_FLUSH reaches pblk, the bio cannot be directly completed.
Instead, data on the write buffer is flushed and the bio is completed on
the completion pah. This might require some sectors to be padded in
order to guarantee a successful write.

This patch fixes a memory leak on the padded pages. A consequence of
this bad free was that internal bios not containing data (only a flush)
were not being completed.

Fixes: a4bd217b4326 ("lightnvm: physical block device (pblk) target")
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-write.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 3ad9e56d2473..d89ac573f8d8 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -33,6 +33,10 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 			bio_endio(original_bio);
 	}
 
+	if (c_ctx->nr_padded)
+		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
+							c_ctx->nr_padded);
+
 #ifdef CONFIG_NVM_DEBUG
 	atomic_long_add(c_ctx->nr_valid, &pblk->sync_writes);
 #endif
@@ -521,7 +525,8 @@ static void pblk_free_write_rqd(struct pblk *pblk, struct nvm_rq *rqd)
 	struct bio *bio = rqd->bio;
 
 	if (c_ctx->nr_padded)
-		pblk_bio_free_pages(pblk, bio, rqd->nr_ppas, c_ctx->nr_padded);
+		pblk_bio_free_pages(pblk, bio, c_ctx->nr_valid,
+							c_ctx->nr_padded);
 }
 
 static int pblk_submit_write(struct pblk *pblk)
-- 
cgit v1.2.3-70-g09d2


From e0e12a707f02fcde1b77a2417d9fb0ae1ce3b003 Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:04 +0200
Subject: lightnvm: pblk: fix write I/O sync stat
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix stat counter to collect the right number of I/Os being synced on the
completion path.

Fixes: 0880a9aa2d91f ("lightnvm: pblk: delete redundant buffer pointer")
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-write.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index d89ac573f8d8..d82ca8bd8390 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -38,7 +38,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 							c_ctx->nr_padded);
 
 #ifdef CONFIG_NVM_DEBUG
-	atomic_long_add(c_ctx->nr_valid, &pblk->sync_writes);
+	atomic_long_add(rqd->nr_ppas, &pblk->sync_writes);
 #endif
 
 	ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
-- 
cgit v1.2.3-70-g09d2


From b84ae4a8b883b96b95fff0e3979ff2c65bbf96b0 Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:07 +0200
Subject: lightnvm: pblk: simplify work_queue mempool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In pblk, we have a mempool to allocate a generic structure that we
pass along workqueues. This is heavily used in the GC path in order
to have enough inflight reads and fully utilize the GC bandwidth.

However, the current GC path copies data to the host memory and puts it
back into the write buffer. This requires a vmalloc allocation for the
data and a memory copy. Thus, guaranteeing the allocation by using a
mempool for the structure in itself does not give us much. Until we
implement support for vector copy to avoid moving data through the host,
just allocate the workqueue structure using kmalloc.

This allows us to have a much smaller mempool.

Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c  | 13 +++++++------
 drivers/lightnvm/pblk-gc.c    | 32 ++++++++++++++++----------------
 drivers/lightnvm/pblk-init.c  | 32 ++++++++++++++++----------------
 drivers/lightnvm/pblk-write.c |  4 ++--
 drivers/lightnvm/pblk.h       | 11 ++++++-----
 5 files changed, 47 insertions(+), 45 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index f5fbb9a46784..b92532211866 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -33,7 +33,8 @@ 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);
 
-	pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq);
+	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)
@@ -1623,7 +1624,7 @@ void pblk_line_close_ws(struct work_struct *work)
 	struct pblk_line *line = line_ws->line;
 
 	pblk_line_close(pblk, line);
-	mempool_free(line_ws, pblk->line_ws_pool);
+	mempool_free(line_ws, pblk->gen_ws_pool);
 }
 
 void pblk_line_mark_bb(struct work_struct *work)
@@ -1648,16 +1649,16 @@ void pblk_line_mark_bb(struct work_struct *work)
 	}
 
 	kfree(ppa);
-	mempool_free(line_ws, pblk->line_ws_pool);
+	mempool_free(line_ws, pblk->gen_ws_pool);
 }
 
-void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
-		      void (*work)(struct work_struct *),
+void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+		      void (*work)(struct work_struct *), gfp_t gfp_mask,
 		      struct workqueue_struct *wq)
 {
 	struct pblk_line_ws *line_ws;
 
-	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_ATOMIC);
+	line_ws = mempool_alloc(pblk->gen_ws_pool, gfp_mask);
 	if (!line_ws)
 		return;
 
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 6090d28f7995..f163829ecca8 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -136,12 +136,12 @@ static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
 
 static void pblk_gc_line_ws(struct work_struct *work)
 {
-	struct pblk_line_ws *line_rq_ws = container_of(work,
+	struct pblk_line_ws *gc_rq_ws = container_of(work,
 						struct pblk_line_ws, ws);
-	struct pblk *pblk = line_rq_ws->pblk;
+	struct pblk *pblk = gc_rq_ws->pblk;
 	struct pblk_gc *gc = &pblk->gc;
-	struct pblk_line *line = line_rq_ws->line;
-	struct pblk_gc_rq *gc_rq = line_rq_ws->priv;
+	struct pblk_line *line = gc_rq_ws->line;
+	struct pblk_gc_rq *gc_rq = gc_rq_ws->priv;
 
 	up(&gc->gc_sem);
 
@@ -151,7 +151,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 						gc_rq->nr_secs);
 	}
 
-	mempool_free(line_rq_ws, pblk->line_ws_pool);
+	kfree(gc_rq_ws);
 }
 
 static void pblk_gc_line_prepare_ws(struct work_struct *work)
@@ -164,7 +164,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_gc *gc = &pblk->gc;
 	struct line_emeta *emeta_buf;
-	struct pblk_line_ws *line_rq_ws;
+	struct pblk_line_ws *gc_rq_ws;
 	struct pblk_gc_rq *gc_rq;
 	__le64 *lba_list;
 	int sec_left, nr_secs, bit;
@@ -223,19 +223,19 @@ next_rq:
 	gc_rq->nr_secs = nr_secs;
 	gc_rq->line = line;
 
-	line_rq_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
-	if (!line_rq_ws)
+	gc_rq_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
+	if (!gc_rq_ws)
 		goto fail_free_gc_rq;
 
-	line_rq_ws->pblk = pblk;
-	line_rq_ws->line = line;
-	line_rq_ws->priv = gc_rq;
+	gc_rq_ws->pblk = pblk;
+	gc_rq_ws->line = line;
+	gc_rq_ws->priv = gc_rq;
 
 	down(&gc->gc_sem);
 	kref_get(&line->ref);
 
-	INIT_WORK(&line_rq_ws->ws, pblk_gc_line_ws);
-	queue_work(gc->gc_line_reader_wq, &line_rq_ws->ws);
+	INIT_WORK(&gc_rq_ws->ws, pblk_gc_line_ws);
+	queue_work(gc->gc_line_reader_wq, &gc_rq_ws->ws);
 
 	sec_left -= nr_secs;
 	if (sec_left > 0)
@@ -243,7 +243,7 @@ next_rq:
 
 out:
 	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
-	mempool_free(line_ws, pblk->line_ws_pool);
+	kfree(line_ws);
 
 	kref_put(&line->ref, pblk_line_put);
 	atomic_dec(&gc->inflight_gc);
@@ -256,7 +256,7 @@ fail_free_emeta:
 	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 	pblk_put_line_back(pblk, line);
 	kref_put(&line->ref, pblk_line_put);
-	mempool_free(line_ws, pblk->line_ws_pool);
+	kfree(line_ws);
 	atomic_dec(&gc->inflight_gc);
 
 	pr_err("pblk: Failed to GC line %d\n", line->id);
@@ -269,7 +269,7 @@ static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 
 	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
 
-	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+	line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
 	if (!line_ws)
 		return -ENOMEM;
 
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 7b1f29c71338..340552253580 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -20,7 +20,7 @@
 
 #include "pblk.h"
 
-static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
+static struct kmem_cache *pblk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
 				*pblk_w_rq_cache, *pblk_line_meta_cache;
 static DECLARE_RWSEM(pblk_lock);
 struct bio_set *pblk_bio_set;
@@ -184,9 +184,9 @@ static int pblk_init_global_caches(struct pblk *pblk)
 	char cache_name[PBLK_CACHE_NAME_LEN];
 
 	down_write(&pblk_lock);
-	pblk_blk_ws_cache = kmem_cache_create("pblk_blk_ws",
+	pblk_ws_cache = kmem_cache_create("pblk_blk_ws",
 				sizeof(struct pblk_line_ws), 0, 0, NULL);
-	if (!pblk_blk_ws_cache) {
+	if (!pblk_ws_cache) {
 		up_write(&pblk_lock);
 		return -ENOMEM;
 	}
@@ -194,7 +194,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
 	pblk_rec_cache = kmem_cache_create("pblk_rec",
 				sizeof(struct pblk_rec_ctx), 0, 0, NULL);
 	if (!pblk_rec_cache) {
-		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_ws_cache);
 		up_write(&pblk_lock);
 		return -ENOMEM;
 	}
@@ -202,7 +202,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
 	pblk_g_rq_cache = kmem_cache_create("pblk_g_rq", pblk_g_rq_size,
 				0, 0, NULL);
 	if (!pblk_g_rq_cache) {
-		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_ws_cache);
 		kmem_cache_destroy(pblk_rec_cache);
 		up_write(&pblk_lock);
 		return -ENOMEM;
@@ -211,7 +211,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
 	pblk_w_rq_cache = kmem_cache_create("pblk_w_rq", pblk_w_rq_size,
 				0, 0, NULL);
 	if (!pblk_w_rq_cache) {
-		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_ws_cache);
 		kmem_cache_destroy(pblk_rec_cache);
 		kmem_cache_destroy(pblk_g_rq_cache);
 		up_write(&pblk_lock);
@@ -223,7 +223,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
 	pblk_line_meta_cache = kmem_cache_create(cache_name,
 				pblk->lm.sec_bitmap_len, 0, 0, NULL);
 	if (!pblk_line_meta_cache) {
-		kmem_cache_destroy(pblk_blk_ws_cache);
+		kmem_cache_destroy(pblk_ws_cache);
 		kmem_cache_destroy(pblk_rec_cache);
 		kmem_cache_destroy(pblk_g_rq_cache);
 		kmem_cache_destroy(pblk_w_rq_cache);
@@ -246,20 +246,20 @@ static int pblk_core_init(struct pblk *pblk)
 	if (pblk_init_global_caches(pblk))
 		return -ENOMEM;
 
-	/* internal bios can be at most the sectors signaled by the device. */
+	/* Internal bios can be at most the sectors signaled by the device. */
 	pblk->page_bio_pool = mempool_create_page_pool(nvm_max_phys_sects(dev),
 									0);
 	if (!pblk->page_bio_pool)
 		return -ENOMEM;
 
-	pblk->line_ws_pool = mempool_create_slab_pool(PBLK_WS_POOL_SIZE,
-							pblk_blk_ws_cache);
-	if (!pblk->line_ws_pool)
+	pblk->gen_ws_pool = mempool_create_slab_pool(PBLK_GEN_WS_POOL_SIZE,
+							pblk_ws_cache);
+	if (!pblk->gen_ws_pool)
 		goto free_page_bio_pool;
 
 	pblk->rec_pool = mempool_create_slab_pool(geo->nr_luns, pblk_rec_cache);
 	if (!pblk->rec_pool)
-		goto free_blk_ws_pool;
+		goto free_gen_ws_pool;
 
 	pblk->g_rq_pool = mempool_create_slab_pool(PBLK_READ_REQ_POOL_SIZE,
 							pblk_g_rq_cache);
@@ -308,8 +308,8 @@ free_g_rq_pool:
 	mempool_destroy(pblk->g_rq_pool);
 free_rec_pool:
 	mempool_destroy(pblk->rec_pool);
-free_blk_ws_pool:
-	mempool_destroy(pblk->line_ws_pool);
+free_gen_ws_pool:
+	mempool_destroy(pblk->gen_ws_pool);
 free_page_bio_pool:
 	mempool_destroy(pblk->page_bio_pool);
 	return -ENOMEM;
@@ -324,13 +324,13 @@ static void pblk_core_free(struct pblk *pblk)
 		destroy_workqueue(pblk->bb_wq);
 
 	mempool_destroy(pblk->page_bio_pool);
-	mempool_destroy(pblk->line_ws_pool);
+	mempool_destroy(pblk->gen_ws_pool);
 	mempool_destroy(pblk->rec_pool);
 	mempool_destroy(pblk->g_rq_pool);
 	mempool_destroy(pblk->w_rq_pool);
 	mempool_destroy(pblk->line_meta_pool);
 
-	kmem_cache_destroy(pblk_blk_ws_cache);
+	kmem_cache_destroy(pblk_ws_cache);
 	kmem_cache_destroy(pblk_rec_cache);
 	kmem_cache_destroy(pblk_g_rq_cache);
 	kmem_cache_destroy(pblk_w_rq_cache);
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index d82ca8bd8390..c73b17bca06b 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -198,8 +198,8 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
 	sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
 	if (sync == emeta->nr_entries)
-		pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws,
-								pblk->close_wq);
+		pblk_gen_run_ws(pblk, line, NULL, pblk_line_close_ws,
+						GFP_ATOMIC, pblk->close_wq);
 
 	bio_put(rqd->bio);
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 229f6020ad8a..efaa781abb06 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -40,7 +40,6 @@
 #define PBLK_MAX_REQ_ADDRS (64)
 #define PBLK_MAX_REQ_ADDRS_PW (6)
 
-#define PBLK_WS_POOL_SIZE (128)
 #define PBLK_META_POOL_SIZE (128)
 #define PBLK_READ_REQ_POOL_SIZE (1024)
 
@@ -61,6 +60,8 @@
 
 #define ERASE 2 /* READ = 0, WRITE = 1 */
 
+#define PBLK_GEN_WS_POOL_SIZE (2)
+
 enum {
 	/* IO Types */
 	PBLK_IOTYPE_USER	= 1 << 0,
@@ -621,7 +622,7 @@ struct pblk {
 	struct list_head compl_list;
 
 	mempool_t *page_bio_pool;
-	mempool_t *line_ws_pool;
+	mempool_t *gen_ws_pool;
 	mempool_t *rec_pool;
 	mempool_t *g_rq_pool;
 	mempool_t *w_rq_pool;
@@ -725,9 +726,9 @@ void pblk_line_close_meta_sync(struct pblk *pblk);
 void pblk_line_close_ws(struct work_struct *work);
 void pblk_pipeline_stop(struct pblk *pblk);
 void pblk_line_mark_bb(struct work_struct *work);
-void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
-		      void (*work)(struct work_struct *),
-		      struct workqueue_struct *wq);
+void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+		     void (*work)(struct work_struct *), gfp_t gfp_mask,
+		     struct workqueue_struct *wq);
 u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
 int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line);
 int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
-- 
cgit v1.2.3-70-g09d2


From e72ec1d31bcb6dffe325418c6d96f2fcab7c2654 Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:09 +0200
Subject: lightnvm: pblk: do not use a mempool for line bitmaps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pblk holds two sector bitmaps: one to keep track of the mapped sectors
while the line is active and another one to keep track of the invalid
sectors. The latter is kept during the whole live of the line, until it
is recycled. Since we cannot guarantee forward progress for the mempool
in this case, get rid of the mempool and simply allocate memory through
kmalloc.

Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     | 26 ++++++++++----------------
 drivers/lightnvm/pblk-init.c     | 29 ++---------------------------
 drivers/lightnvm/pblk-recovery.c |  2 +-
 drivers/lightnvm/pblk-write.c    |  4 +---
 drivers/lightnvm/pblk.h          |  3 ---
 5 files changed, 14 insertions(+), 50 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 0c22e5ccdfdd..215aadb84c6e 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -1095,25 +1095,21 @@ 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);
 
-	line->map_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC);
 	if (!line->map_bitmap)
 		return -ENOMEM;
-	memset(line->map_bitmap, 0, lm->sec_bitmap_len);
 
-	/* invalid_bitmap is special since it is used when line is closed. No
-	 * need to zeroized; it will be initialized using bb info form
-	 * map_bitmap
-	 */
-	line->invalid_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+	/* will be initialized using bb info from map_bitmap */
+	line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_ATOMIC);
 	if (!line->invalid_bitmap) {
-		mempool_free(line->map_bitmap, pblk->line_meta_pool);
+		kfree(line->map_bitmap);
 		return -ENOMEM;
 	}
 
 	spin_lock(&line->lock);
 	if (line->state != PBLK_LINESTATE_FREE) {
-		mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
-		mempool_free(line->map_bitmap, pblk->line_meta_pool);
+		kfree(line->map_bitmap);
+		kfree(line->invalid_bitmap);
 		spin_unlock(&line->lock);
 		WARN(1, "pblk: corrupted line %d, state %d\n",
 							line->id, line->state);
@@ -1165,7 +1161,7 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
 
 void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
 {
-	mempool_free(line->map_bitmap, pblk->line_meta_pool);
+	kfree(line->map_bitmap);
 	line->map_bitmap = NULL;
 	line->smeta = NULL;
 	line->emeta = NULL;
@@ -1440,10 +1436,8 @@ retry_setup:
 
 void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
 {
-	if (line->map_bitmap)
-		mempool_free(line->map_bitmap, pblk->line_meta_pool);
-	if (line->invalid_bitmap)
-		mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+	kfree(line->map_bitmap);
+	kfree(line->invalid_bitmap);
 
 	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
 
@@ -1584,7 +1578,7 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 
 	list_add_tail(&line->list, move_list);
 
-	mempool_free(line->map_bitmap, pblk->line_meta_pool);
+	kfree(line->map_bitmap);
 	line->map_bitmap = NULL;
 	line->smeta = NULL;
 	line->emeta = NULL;
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 2f8d3f9ffbaf..4d719782f65b 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -21,7 +21,7 @@
 #include "pblk.h"
 
 static struct kmem_cache *pblk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
-				*pblk_w_rq_cache, *pblk_line_meta_cache;
+				*pblk_w_rq_cache;
 static DECLARE_RWSEM(pblk_lock);
 struct bio_set *pblk_bio_set;
 
@@ -181,8 +181,6 @@ static int pblk_set_ppaf(struct pblk *pblk)
 
 static int pblk_init_global_caches(struct pblk *pblk)
 {
-	char cache_name[PBLK_CACHE_NAME_LEN];
-
 	down_write(&pblk_lock);
 	pblk_ws_cache = kmem_cache_create("pblk_blk_ws",
 				sizeof(struct pblk_line_ws), 0, 0, NULL);
@@ -217,19 +215,6 @@ static int pblk_init_global_caches(struct pblk *pblk)
 		up_write(&pblk_lock);
 		return -ENOMEM;
 	}
-
-	snprintf(cache_name, sizeof(cache_name), "pblk_line_m_%s",
-							pblk->disk->disk_name);
-	pblk_line_meta_cache = kmem_cache_create(cache_name,
-				pblk->lm.sec_bitmap_len, 0, 0, NULL);
-	if (!pblk_line_meta_cache) {
-		kmem_cache_destroy(pblk_ws_cache);
-		kmem_cache_destroy(pblk_rec_cache);
-		kmem_cache_destroy(pblk_g_rq_cache);
-		kmem_cache_destroy(pblk_w_rq_cache);
-		up_write(&pblk_lock);
-		return -ENOMEM;
-	}
 	up_write(&pblk_lock);
 
 	return 0;
@@ -276,16 +261,10 @@ static int pblk_core_init(struct pblk *pblk)
 	if (!pblk->w_rq_pool)
 		goto free_e_rq_pool;
 
-	pblk->line_meta_pool =
-			mempool_create_slab_pool(PBLK_META_POOL_SIZE,
-							pblk_line_meta_cache);
-	if (!pblk->line_meta_pool)
-		goto free_w_rq_pool;
-
 	pblk->close_wq = alloc_workqueue("pblk-close-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_NR_CLOSE_JOBS);
 	if (!pblk->close_wq)
-		goto free_line_meta_pool;
+		goto free_w_rq_pool;
 
 	pblk->bb_wq = alloc_workqueue("pblk-bb-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
@@ -305,8 +284,6 @@ free_bb_wq:
 	destroy_workqueue(pblk->bb_wq);
 free_close_wq:
 	destroy_workqueue(pblk->close_wq);
-free_line_meta_pool:
-	mempool_destroy(pblk->line_meta_pool);
 free_w_rq_pool:
 	mempool_destroy(pblk->w_rq_pool);
 free_e_rq_pool:
@@ -336,13 +313,11 @@ static void pblk_core_free(struct pblk *pblk)
 	mempool_destroy(pblk->r_rq_pool);
 	mempool_destroy(pblk->e_rq_pool);
 	mempool_destroy(pblk->w_rq_pool);
-	mempool_destroy(pblk->line_meta_pool);
 
 	kmem_cache_destroy(pblk_ws_cache);
 	kmem_cache_destroy(pblk_rec_cache);
 	kmem_cache_destroy(pblk_g_rq_cache);
 	kmem_cache_destroy(pblk_w_rq_cache);
-	kmem_cache_destroy(pblk_line_meta_cache);
 }
 
 static void pblk_luns_free(struct pblk *pblk)
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index caf124279575..de5270712be7 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -987,7 +987,7 @@ next:
 			list_move_tail(&line->list, move_list);
 			spin_unlock(&l_mg->gc_lock);
 
-			mempool_free(line->map_bitmap, pblk->line_meta_pool);
+			kfree(line->map_bitmap);
 			line->map_bitmap = NULL;
 			line->smeta = NULL;
 			line->emeta = NULL;
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index c73b17bca06b..26c2b8345149 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -411,8 +411,6 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	if (emeta->mem >= lm->emeta_len[0]) {
 		spin_lock(&l_mg->close_lock);
 		list_del(&meta_line->list);
-		WARN(!bitmap_full(meta_line->map_bitmap, lm->sec_per_line),
-				"pblk: corrupt meta line %d\n", meta_line->id);
 		spin_unlock(&l_mg->close_lock);
 	}
 
@@ -456,7 +454,7 @@ retry:
 		return 0;
 	}
 	meta_line = list_first_entry(&l_mg->emeta_list, struct pblk_line, list);
-	if (bitmap_full(meta_line->map_bitmap, lm->sec_per_line))
+	if (meta_line->emeta->mem >= lm->emeta_len[0])
 		goto retry;
 	spin_unlock(&l_mg->close_lock);
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 419e1b7328e4..60edcda0fc7f 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -40,8 +40,6 @@
 #define PBLK_MAX_REQ_ADDRS (64)
 #define PBLK_MAX_REQ_ADDRS_PW (6)
 
-#define PBLK_META_POOL_SIZE (128)
-
 #define PBLK_NR_CLOSE_JOBS (4)
 
 #define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
@@ -627,7 +625,6 @@ struct pblk {
 	mempool_t *r_rq_pool;
 	mempool_t *w_rq_pool;
 	mempool_t *e_rq_pool;
-	mempool_t *line_meta_pool;
 
 	struct workqueue_struct *close_wq;
 	struct workqueue_struct *bb_wq;
-- 
cgit v1.2.3-70-g09d2


From 2942f50fa389a62865572452dce6214a8aed69dc Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:10 +0200
Subject: lightnvm: pblk: remove checks on mempool alloc.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As part of the mempool audit on pblk, remove unnecessary mempool
allocation checks on mempools.

Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     |  4 ----
 drivers/lightnvm/pblk-read.c     |  8 --------
 drivers/lightnvm/pblk-recovery.c | 35 +++++++----------------------------
 drivers/lightnvm/pblk-write.c    | 24 +++++-------------------
 4 files changed, 12 insertions(+), 59 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 215aadb84c6e..0da58869006b 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -206,8 +206,6 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 
 	for (i = 0; i < nr_pages; i++) {
 		page = mempool_alloc(pblk->page_bio_pool, flags);
-		if (!page)
-			goto err;
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
@@ -1653,8 +1651,6 @@ void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
 	struct pblk_line_ws *line_ws;
 
 	line_ws = mempool_alloc(pblk->gen_ws_pool, gfp_mask);
-	if (!line_ws)
-		return;
 
 	line_ws->pblk = pblk;
 	line_ws->line = line;
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 402c732f0970..d2b6e2a7d7d5 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -168,10 +168,6 @@ static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
 	DECLARE_COMPLETION_ONSTACK(wait);
 
 	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
-	if (!new_bio) {
-		pr_err("pblk: could not alloc read bio\n");
-		return NVM_IO_ERR;
-	}
 
 	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
 		goto err;
@@ -321,10 +317,6 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	bitmap_zero(&read_bitmap, nr_secs);
 
 	rqd = pblk_alloc_rqd(pblk, READ);
-	if (IS_ERR(rqd)) {
-		pr_err_ratelimited("pblk: not able to alloc rqd");
-		return NVM_IO_ERR;
-	}
 
 	rqd->opcode = NVM_OP_PREAD;
 	rqd->bio = bio;
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index de5270712be7..6b6b4183b41e 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -34,10 +34,6 @@ void pblk_submit_rec(struct work_struct *work)
 								max_secs);
 
 	bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
-	if (!bio) {
-		pr_err("pblk: not able to create recovery bio\n");
-		return;
-	}
 
 	bio->bi_iter.bi_sector = 0;
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
@@ -85,11 +81,6 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
 	int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
 
 	rec_rqd = pblk_alloc_rqd(pblk, WRITE);
-	if (IS_ERR(rec_rqd)) {
-		pr_err("pblk: could not create recovery req.\n");
-		return -ENOMEM;
-	}
-
 	rec_ctx = nvm_rq_to_pdu(rec_rqd);
 
 	/* Copy completion bitmap, but exclude the first X completed entries */
@@ -404,22 +395,18 @@ next_pad_rq:
 	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
 	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
 
-	rqd = pblk_alloc_rqd(pblk, WRITE);
-	if (IS_ERR(rqd)) {
-		ret = PTR_ERR(rqd);
-		goto fail_free_meta;
-	}
-
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 						PBLK_VMALLOC_META, GFP_KERNEL);
 	if (IS_ERR(bio)) {
 		ret = PTR_ERR(bio);
-		goto fail_free_rqd;
+		goto fail_free_meta;
 	}
 
 	bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
+	rqd = pblk_alloc_rqd(pblk, WRITE);
+
 	rqd->bio = bio;
 	rqd->opcode = NVM_OP_PWRITE;
 	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
@@ -490,8 +477,6 @@ free_rq:
 
 fail_free_bio:
 	bio_put(bio);
-fail_free_rqd:
-	pblk_free_rqd(pblk, rqd, WRITE);
 fail_free_meta:
 	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
 fail_free_pad:
@@ -785,15 +770,9 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 	dma_addr_t dma_ppa_list, dma_meta_list;
 	int done, ret = 0;
 
-	rqd = pblk_alloc_rqd(pblk, READ);
-	if (IS_ERR(rqd))
-		return PTR_ERR(rqd);
-
 	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
-	if (!meta_list) {
-		ret = -ENOMEM;
-		goto free_rqd;
-	}
+	if (!meta_list)
+		return -ENOMEM;
 
 	ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
 	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
@@ -804,6 +783,8 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 		goto free_meta_list;
 	}
 
+	rqd = pblk_alloc_rqd(pblk, READ);
+
 	p.ppa_list = ppa_list;
 	p.meta_list = meta_list;
 	p.rqd = rqd;
@@ -832,8 +813,6 @@ out:
 	kfree(data);
 free_meta_list:
 	nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
-free_rqd:
-	pblk_free_rqd(pblk, rqd, READ);
 
 	return ret;
 }
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 26c2b8345149..0fb8f26a6311 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -111,10 +111,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 		ppa_list = &rqd->ppa_addr;
 
 	recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
-	if (!recovery) {
-		pr_err("pblk: could not allocate recovery context\n");
-		return;
-	}
+
 	INIT_LIST_HEAD(&recovery->failed);
 
 	bit = -1;
@@ -375,10 +372,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	int ret;
 
 	rqd = pblk_alloc_rqd(pblk, READ);
-	if (IS_ERR(rqd)) {
-		pr_err("pblk: cannot allocate write req.\n");
-		return PTR_ERR(rqd);
-	}
+
 	m_ctx = nvm_rq_to_pdu(rqd);
 	m_ctx->private = meta_line;
 
@@ -546,19 +540,12 @@ static int pblk_submit_write(struct pblk *pblk)
 	if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
 		return 1;
 
-	rqd = pblk_alloc_rqd(pblk, WRITE);
-	if (IS_ERR(rqd)) {
-		pr_err("pblk: cannot allocate write req.\n");
-		return 1;
-	}
-
 	bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
-	if (!bio) {
-		pr_err("pblk: cannot allocate write bio\n");
-		goto fail_free_rqd;
-	}
+
 	bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+	rqd = pblk_alloc_rqd(pblk, WRITE);
 	rqd->bio = bio;
 
 	secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
@@ -589,7 +576,6 @@ fail_free_bio:
 	pblk_free_write_rqd(pblk, rqd);
 fail_put_bio:
 	bio_put(bio);
-fail_free_rqd:
 	pblk_free_rqd(pblk, rqd, WRITE);
 
 	return 1;
-- 
cgit v1.2.3-70-g09d2


From 55e836d401601e7903b36db015ce899dc11085ab Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:16 +0200
Subject: lightnvm: pblk: put bio on bio completion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simplify put bio by doing it on bio end_io instead of manually putting
it on the completion path.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     | 10 +++++++---
 drivers/lightnvm/pblk-read.c     |  1 -
 drivers/lightnvm/pblk-recovery.c |  1 -
 drivers/lightnvm/pblk-write.c    |  8 +-------
 4 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 6dd4866e579c..3d27d24baa0b 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -417,6 +417,11 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 	return nvm_submit_io(dev, rqd);
 }
 
+static void pblk_bio_map_addr_endio(struct bio *bio)
+{
+	bio_put(bio);
+}
+
 struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 			      unsigned int nr_secs, unsigned int len,
 			      int alloc_type, gfp_t gfp_mask)
@@ -453,6 +458,8 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 
 		kaddr += PAGE_SIZE;
 	}
+
+	bio->bi_end_io = pblk_bio_map_addr_endio;
 out:
 	return bio;
 }
@@ -671,9 +678,6 @@ next_rq:
 	atomic_dec(&pblk->inflight_io);
 	reinit_completion(&wait);
 
-	if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META))
-		bio_put(bio);
-
 	if (rqd.error) {
 		if (dir == WRITE)
 			pblk_log_write_err(pblk, &rqd);
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index c28d6509312e..e7141b1aaded 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -531,7 +531,6 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
 #endif
 
-	bio_put(bio);
 out:
 	nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
 	return ret;
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 6b6b4183b41e..e59270e60b58 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -333,7 +333,6 @@ static void pblk_end_io_recov(struct nvm_rq *rqd)
 
 	pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 
-	bio_put(rqd->bio);
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 	pblk_free_rqd(pblk, rqd, WRITE);
 
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 0fb8f26a6311..0c0481cf9f5d 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -188,17 +188,12 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 		pblk_log_write_err(pblk, rqd);
 		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
 	}
-#ifdef CONFIG_NVM_DEBUG
-	else
-		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
-#endif
 
 	sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
 	if (sync == emeta->nr_entries)
 		pblk_gen_run_ws(pblk, line, NULL, pblk_line_close_ws,
 						GFP_ATOMIC, pblk->close_wq);
 
-	bio_put(rqd->bio);
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 	pblk_free_rqd(pblk, rqd, READ);
 
@@ -427,8 +422,7 @@ fail_rollback:
 
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_free_bio:
-	if (likely(l_mg->emeta_alloc_type == PBLK_VMALLOC_META))
-		bio_put(bio);
+	bio_put(bio);
 fail_free_rqd:
 	pblk_free_rqd(pblk, rqd, READ);
 	return ret;
-- 
cgit v1.2.3-70-g09d2


From 875d94f3a4838f2243334e5ce55ac8153f9bbf5b Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:18 +0200
Subject: lightnvm: pblk: allocate bio size more accurately
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Wait until we know the exact number of ppas to be sent to the device,
before allocating the bio.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-rb.c    |  5 +++--
 drivers/lightnvm/pblk-write.c | 20 ++++++++++----------
 drivers/lightnvm/pblk.h       |  4 ++--
 3 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 05e6b2e9221d..1173e2380137 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -552,12 +552,13 @@ out:
  * persist data on the write buffer to the media.
  */
 unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
-				 struct bio *bio, unsigned int pos,
-				 unsigned int nr_entries, unsigned int count)
+				 unsigned int pos, unsigned int nr_entries,
+				 unsigned int count)
 {
 	struct pblk *pblk = container_of(rb, struct pblk, rwb);
 	struct request_queue *q = pblk->dev->q;
 	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+	struct bio *bio = rqd->bio;
 	struct pblk_rb_entry *entry;
 	struct page *page;
 	unsigned int pad = 0, to_read = nr_entries;
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 0c0481cf9f5d..140a26edd1d3 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -534,24 +534,24 @@ static int pblk_submit_write(struct pblk *pblk)
 	if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
 		return 1;
 
-	bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
-
-	bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
-	rqd = pblk_alloc_rqd(pblk, WRITE);
-	rqd->bio = bio;
-
 	secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
 	if (secs_to_sync > pblk->max_write_pgs) {
 		pr_err("pblk: bad buffer sync calculation\n");
-		goto fail_put_bio;
+		return 1;
 	}
 
 	secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
 	pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
 
-	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, bio, pos, secs_to_sync,
+	bio = bio_alloc(GFP_KERNEL, secs_to_sync);
+
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+	rqd = pblk_alloc_rqd(pblk, WRITE);
+	rqd->bio = bio;
+
+	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
 								secs_avail)) {
 		pr_err("pblk: corrupted write bio\n");
 		goto fail_put_bio;
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 876b50f97234..9f162057d497 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -666,8 +666,8 @@ void pblk_rb_flush(struct pblk_rb *rb);
 
 void pblk_rb_sync_l2p(struct pblk_rb *rb);
 unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
-				 struct bio *bio, unsigned int pos,
-				 unsigned int nr_entries, unsigned int count);
+				 unsigned int pos, unsigned int nr_entries,
+				 unsigned int count);
 unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
 				      struct list_head *list,
 				      unsigned int max);
-- 
cgit v1.2.3-70-g09d2


From e2cddf2082e700218b898b1c899f6a1c2130074a Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:19 +0200
Subject: lightnvm: pblk: improve naming for internal req.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Each request type sent to the LightNVM subsystem requires different
metadata. Until now, we have tailored this metadata based on write, read
and erase commands. However, pblk uses different metadata for internal
writes that do not hit the write buffer. Instead of abusing the metadata
for reads, create a new request type - internal write to improve
code readability.

In the process, create internal values for each I/O type instead of
abusing the READ/WRITE macros, as suggested by Christoph.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     | 32 ++++++++++++++++----------------
 drivers/lightnvm/pblk-read.c     |  6 +++---
 drivers/lightnvm/pblk-recovery.c | 12 ++++++------
 drivers/lightnvm/pblk-write.c    | 16 ++++++++--------
 drivers/lightnvm/pblk.h          | 11 ++++++++---
 5 files changed, 41 insertions(+), 36 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 3d27d24baa0b..a492964abea8 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -152,7 +152,7 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
 	struct nvm_rq *rqd;
 	int rq_size;
 
-	if (rw == WRITE) {
+	if (rw == PBLK_WRITE) {
 		pool = pblk->w_rq_pool;
 		rq_size = pblk_w_rq_size;
 	} else {
@@ -170,7 +170,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
 {
 	mempool_t *pool;
 
-	if (rw == WRITE)
+	if (rw == PBLK_WRITE)
 		pool = pblk->w_rq_pool;
 	else
 		pool = pblk->r_rq_pool;
@@ -569,10 +569,10 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(wait);
 
-	if (dir == WRITE) {
+	if (dir == PBLK_WRITE) {
 		bio_op = REQ_OP_WRITE;
 		cmd_op = NVM_OP_PWRITE;
-	} else if (dir == READ) {
+	} else if (dir == PBLK_READ) {
 		bio_op = REQ_OP_READ;
 		cmd_op = NVM_OP_PREAD;
 	} else
@@ -612,10 +612,10 @@ next_rq:
 	rqd.end_io = pblk_end_io_sync;
 	rqd.private = &wait;
 
-	if (dir == WRITE) {
+	if (dir == PBLK_WRITE) {
 		struct pblk_sec_meta *meta_list = rqd.meta_list;
 
-		rqd.flags = pblk_set_progr_mode(pblk, WRITE);
+		rqd.flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 		for (i = 0; i < rqd.nr_ppas; ) {
 			spin_lock(&line->lock);
 			paddr = __pblk_alloc_page(pblk, line, min);
@@ -679,7 +679,7 @@ next_rq:
 	reinit_completion(&wait);
 
 	if (rqd.error) {
-		if (dir == WRITE)
+		if (dir == PBLK_WRITE)
 			pblk_log_write_err(pblk, &rqd);
 		else
 			pblk_log_read_err(pblk, &rqd);
@@ -722,12 +722,12 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	int flags;
 	DECLARE_COMPLETION_ONSTACK(wait);
 
-	if (dir == WRITE) {
+	if (dir == PBLK_WRITE) {
 		bio_op = REQ_OP_WRITE;
 		cmd_op = NVM_OP_PWRITE;
-		flags = pblk_set_progr_mode(pblk, WRITE);
+		flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 		lba_list = emeta_to_lbas(pblk, line->emeta->buf);
-	} else if (dir == READ) {
+	} else if (dir == PBLK_READ) {
 		bio_op = REQ_OP_READ;
 		cmd_op = NVM_OP_PREAD;
 		flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
@@ -765,7 +765,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 
 		rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
 
-		if (dir == WRITE) {
+		if (dir == PBLK_WRITE) {
 			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
 
 			meta_list[i].lba = lba_list[paddr] = addr_empty;
@@ -791,7 +791,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	atomic_dec(&pblk->inflight_io);
 
 	if (rqd.error) {
-		if (dir == WRITE)
+		if (dir == PBLK_WRITE)
 			pblk_log_write_err(pblk, &rqd);
 		else
 			pblk_log_read_err(pblk, &rqd);
@@ -807,14 +807,14 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
 {
 	u64 bpaddr = pblk_line_smeta_start(pblk, line);
 
-	return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
+	return pblk_line_submit_smeta_io(pblk, line, bpaddr, PBLK_READ);
 }
 
 int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
 			 void *emeta_buf)
 {
 	return pblk_line_submit_emeta_io(pblk, line, emeta_buf,
-						line->emeta_ssec, READ);
+						line->emeta_ssec, PBLK_READ);
 }
 
 static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -823,7 +823,7 @@ static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->opcode = NVM_OP_ERASE;
 	rqd->ppa_addr = ppa;
 	rqd->nr_ppas = 1;
-	rqd->flags = pblk_set_progr_mode(pblk, ERASE);
+	rqd->flags = pblk_set_progr_mode(pblk, PBLK_ERASE);
 	rqd->bio = NULL;
 }
 
@@ -1045,7 +1045,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	line->smeta_ssec = off;
 	line->cur_sec = off + lm->smeta_sec;
 
-	if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
+	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
 		pr_debug("pblk: line smeta I/O failed. Retry\n");
 		return 1;
 	}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index e7141b1aaded..4b1722fbe5a0 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -142,7 +142,7 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
 #endif
 
-	pblk_free_rqd(pblk, rqd, READ);
+	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	atomic_dec(&pblk->inflight_io);
 }
 
@@ -307,7 +307,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 
 	bitmap_zero(&read_bitmap, nr_secs);
 
-	rqd = pblk_alloc_rqd(pblk, READ);
+	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
 	rqd->opcode = NVM_OP_PREAD;
 	rqd->bio = bio;
@@ -382,7 +382,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	return NVM_IO_OK;
 
 fail_rqd_free:
-	pblk_free_rqd(pblk, rqd, READ);
+	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	return ret;
 }
 
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index e59270e60b58..19f2fb1a9e4b 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -67,7 +67,7 @@ void pblk_submit_rec(struct work_struct *work)
 
 err:
 	bio_put(bio);
-	pblk_free_rqd(pblk, rqd, WRITE);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
 }
 
 int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
@@ -80,7 +80,7 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
 	struct pblk_c_ctx *rec_ctx;
 	int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
 
-	rec_rqd = pblk_alloc_rqd(pblk, WRITE);
+	rec_rqd = pblk_alloc_rqd(pblk, PBLK_WRITE);
 	rec_ctx = nvm_rq_to_pdu(rec_rqd);
 
 	/* Copy completion bitmap, but exclude the first X completed entries */
@@ -334,7 +334,7 @@ static void pblk_end_io_recov(struct nvm_rq *rqd)
 	pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
-	pblk_free_rqd(pblk, rqd, WRITE);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
 
 	atomic_dec(&pblk->inflight_io);
 	kref_put(&pad_rq->ref, pblk_recov_complete);
@@ -404,11 +404,11 @@ next_pad_rq:
 	bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
-	rqd = pblk_alloc_rqd(pblk, WRITE);
+	rqd = pblk_alloc_rqd(pblk, PBLK_WRITE_INT);
 
 	rqd->bio = bio;
 	rqd->opcode = NVM_OP_PWRITE;
-	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+	rqd->flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 	rqd->meta_list = meta_list;
 	rqd->nr_ppas = rq_ppas;
 	rqd->ppa_list = ppa_list;
@@ -782,7 +782,7 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 		goto free_meta_list;
 	}
 
-	rqd = pblk_alloc_rqd(pblk, READ);
+	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
 	p.ppa_list = ppa_list;
 	p.meta_list = meta_list;
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 140a26edd1d3..c1b8b83e149d 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -46,7 +46,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 
 	bio_put(rqd->bio);
-	pblk_free_rqd(pblk, rqd, WRITE);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
 
 	return ret;
 }
@@ -195,7 +195,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 						GFP_ATOMIC, pblk->close_wq);
 
 	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
-	pblk_free_rqd(pblk, rqd, READ);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
 
 	atomic_dec(&pblk->inflight_io);
 }
@@ -209,7 +209,7 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	/* Setup write request */
 	rqd->opcode = NVM_OP_PWRITE;
 	rqd->nr_ppas = nr_secs;
-	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+	rqd->flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 	rqd->private = pblk;
 	rqd->end_io = end_io;
 
@@ -275,7 +275,7 @@ int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
 
 	rqd->ppa_status = (u64)0;
-	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+	rqd->flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
 
 	return ret;
 }
@@ -366,7 +366,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	int i, j;
 	int ret;
 
-	rqd = pblk_alloc_rqd(pblk, READ);
+	rqd = pblk_alloc_rqd(pblk, PBLK_WRITE_INT);
 
 	m_ctx = nvm_rq_to_pdu(rqd);
 	m_ctx->private = meta_line;
@@ -424,7 +424,7 @@ fail_rollback:
 fail_free_bio:
 	bio_put(bio);
 fail_free_rqd:
-	pblk_free_rqd(pblk, rqd, READ);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
 	return ret;
 }
 
@@ -548,7 +548,7 @@ static int pblk_submit_write(struct pblk *pblk)
 	bio->bi_iter.bi_sector = 0; /* internal bio */
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
-	rqd = pblk_alloc_rqd(pblk, WRITE);
+	rqd = pblk_alloc_rqd(pblk, PBLK_WRITE);
 	rqd->bio = bio;
 
 	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
@@ -570,7 +570,7 @@ fail_free_bio:
 	pblk_free_write_rqd(pblk, rqd);
 fail_put_bio:
 	bio_put(bio);
-	pblk_free_rqd(pblk, rqd, WRITE);
+	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
 
 	return 1;
 }
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9f162057d497..d01e003d3d74 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -55,11 +55,16 @@
 		for ((i) = 0, rlun = &(pblk)->luns[0]; \
 			(i) < (pblk)->nr_luns; (i)++, rlun = &(pblk)->luns[(i)])
 
-#define ERASE 2 /* READ = 0, WRITE = 1 */
-
 /* Static pool sizes */
 #define PBLK_GEN_WS_POOL_SIZE (2)
 
+enum {
+	PBLK_READ		= READ,
+	PBLK_WRITE		= WRITE,/* Write from write buffer */
+	PBLK_WRITE_INT,			/* Internal write - no write buffer */
+	PBLK_ERASE,
+};
+
 enum {
 	/* IO Types */
 	PBLK_IOTYPE_USER	= 1 << 0,
@@ -1132,7 +1137,7 @@ static inline int pblk_set_progr_mode(struct pblk *pblk, int type)
 
 	flags = geo->plane_mode >> 1;
 
-	if (type == WRITE)
+	if (type == PBLK_WRITE)
 		flags |= NVM_IO_SCRAMBLE_ENABLE;
 
 	return flags;
-- 
cgit v1.2.3-70-g09d2


From 67bf26a3220e3bd403a62a9289aa1d065d3db82c Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:20 +0200
Subject: lightnvm: pblk: refactor rqd alloc/free
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Refactor the rqd allocation and free functions so that all I/O types can
use these helper functions.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     | 40 ++++++++++++++++++++++++++++++----------
 drivers/lightnvm/pblk-read.c     |  2 --
 drivers/lightnvm/pblk-recovery.c |  2 --
 drivers/lightnvm/pblk-write.c    |  7 -------
 drivers/lightnvm/pblk.h          |  4 ++--
 5 files changed, 32 insertions(+), 23 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index a492964abea8..0de3875211b1 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -146,18 +146,26 @@ static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
 	spin_unlock(&pblk->trans_lock);
 }
 
-struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
+/* Caller must guarantee that the request is a valid type */
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type)
 {
 	mempool_t *pool;
 	struct nvm_rq *rqd;
 	int rq_size;
 
-	if (rw == PBLK_WRITE) {
+	switch (type) {
+	case PBLK_WRITE:
+	case PBLK_WRITE_INT:
 		pool = pblk->w_rq_pool;
 		rq_size = pblk_w_rq_size;
-	} else {
+		break;
+	case PBLK_READ:
 		pool = pblk->r_rq_pool;
 		rq_size = pblk_g_rq_size;
+		break;
+	default:
+		pool = pblk->e_rq_pool;
+		rq_size = pblk_g_rq_size;
 	}
 
 	rqd = mempool_alloc(pool, GFP_KERNEL);
@@ -166,15 +174,30 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
 	return rqd;
 }
 
-void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
+/* Typically used on completion path. Cannot guarantee request consistency */
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 {
+	struct nvm_tgt_dev *dev = pblk->dev;
 	mempool_t *pool;
 
-	if (rw == PBLK_WRITE)
+	switch (type) {
+	case PBLK_WRITE:
+		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
+	case PBLK_WRITE_INT:
 		pool = pblk->w_rq_pool;
-	else
+		break;
+	case PBLK_READ:
 		pool = pblk->r_rq_pool;
+		break;
+	case PBLK_ERASE:
+		pool = pblk->e_rq_pool;
+		break;
+	default:
+		pr_err("pblk: trying to free unknown rqd type\n");
+		return;
+	}
 
+	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 	mempool_free(rqd, pool);
 }
 
@@ -1470,8 +1493,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 	struct nvm_rq *rqd;
 	int err;
 
-	rqd = mempool_alloc(pblk->e_rq_pool, GFP_KERNEL);
-	memset(rqd, 0, pblk_g_rq_size);
+	rqd = pblk_alloc_rqd(pblk, PBLK_ERASE);
 
 	pblk_setup_e_rq(pblk, rqd, ppa);
 
@@ -1739,8 +1761,6 @@ void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 		rlun = &pblk->luns[bit];
 		up(&rlun->wr_sem);
 	}
-
-	kfree(lun_bitmap);
 }
 
 void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 4b1722fbe5a0..d7c90c303540 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -124,8 +124,6 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 		WARN_ONCE(bio->bi_status, "pblk: corrupted read error\n");
 #endif
 
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
-
 	bio_put(bio);
 	if (r_ctx->private) {
 		struct bio *orig_bio = r_ctx->private;
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 19f2fb1a9e4b..686bc17f080f 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -329,11 +329,9 @@ static void pblk_end_io_recov(struct nvm_rq *rqd)
 {
 	struct pblk_pad_rq *pad_rq = rqd->private;
 	struct pblk *pblk = pad_rq->pblk;
-	struct nvm_tgt_dev *dev = pblk->dev;
 
 	pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 	pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
 
 	atomic_dec(&pblk->inflight_io);
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index c1b8b83e149d..f2e846fe9242 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -20,7 +20,6 @@
 static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 				    struct pblk_c_ctx *c_ctx)
 {
-	struct nvm_tgt_dev *dev = pblk->dev;
 	struct bio *original_bio;
 	unsigned long ret;
 	int i;
@@ -43,8 +42,6 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 
 	ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
 
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
-
 	bio_put(rqd->bio);
 	pblk_free_rqd(pblk, rqd, PBLK_WRITE);
 
@@ -176,7 +173,6 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 {
 	struct pblk *pblk = rqd->private;
-	struct nvm_tgt_dev *dev = pblk->dev;
 	struct pblk_g_ctx *m_ctx = nvm_rq_to_pdu(rqd);
 	struct pblk_line *line = m_ctx->private;
 	struct pblk_emeta *emeta = line->emeta;
@@ -194,7 +190,6 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 		pblk_gen_run_ws(pblk, line, NULL, pblk_line_close_ws,
 						GFP_ATOMIC, pblk->close_wq);
 
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 	pblk_free_rqd(pblk, rqd, PBLK_WRITE_INT);
 
 	atomic_dec(&pblk->inflight_io);
@@ -419,8 +414,6 @@ fail_rollback:
 	pblk_dealloc_page(pblk, meta_line, rq_ppas);
 	list_add(&meta_line->list, &meta_line->list);
 	spin_unlock(&l_mg->close_lock);
-
-	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_free_bio:
 	bio_put(bio);
 fail_free_rqd:
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index d01e003d3d74..12a20f800c26 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -699,11 +699,11 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
 /*
  * pblk core
  */
-struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw);
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type);
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type);
 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_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw);
 void pblk_wait_for_meta(struct pblk *pblk);
 struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba);
 void pblk_discard(struct pblk *pblk, struct bio *bio);
-- 
cgit v1.2.3-70-g09d2


From 1e82123da6a4c6019ef03bcd47e4b3dc18dd136e Mon Sep 17 00:00:00 2001
From: Javier González <javier@cnexlabs.com>
Date: Fri, 13 Oct 2017 14:46:25 +0200
Subject: lightnvm: pblk: remove I/O dependency on write path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pblk schedules user I/O, metadata I/O and erases on the write path in
order to minimize collisions at the media level. Until now, there has
been a dependency between user and metadata I/Os that could lead to a
deadlock as both take the per-LUN semaphore to schedule submission.

This path removes this dependency and guarantees forward progress at a
per I/O granurality.

Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-write.c | 145 +++++++++++++++++++-----------------------
 1 file changed, 65 insertions(+), 80 deletions(-)

(limited to 'drivers/lightnvm/pblk-write.c')

diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index f2e846fe9242..6c1cafafef53 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -220,15 +220,16 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
 }
 
 static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
-			   struct pblk_c_ctx *c_ctx, struct ppa_addr *erase_ppa)
+			   struct ppa_addr *erase_ppa)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line *e_line = pblk_line_get_erase(pblk);
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
 	unsigned int valid = c_ctx->nr_valid;
 	unsigned int padded = c_ctx->nr_padded;
 	unsigned int nr_secs = valid + padded;
 	unsigned long *lun_bitmap;
-	int ret = 0;
+	int ret;
 
 	lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
 	if (!lun_bitmap)
@@ -294,55 +295,6 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 	return secs_to_sync;
 }
 
-static inline int pblk_valid_meta_ppa(struct pblk *pblk,
-				      struct pblk_line *meta_line,
-				      struct ppa_addr *ppa_list, int nr_ppas)
-{
-	struct nvm_tgt_dev *dev = pblk->dev;
-	struct nvm_geo *geo = &dev->geo;
-	struct pblk_line *data_line;
-	struct ppa_addr ppa, ppa_opt;
-	u64 paddr;
-	int i;
-
-	data_line = &pblk->lines[pblk_dev_ppa_to_line(ppa_list[0])];
-	paddr = pblk_lookup_page(pblk, meta_line);
-	ppa = addr_to_gen_ppa(pblk, paddr, 0);
-
-	if (test_bit(pblk_ppa_to_pos(geo, ppa), data_line->blk_bitmap))
-		return 1;
-
-	/* Schedule a metadata I/O that is half the distance from the data I/O
-	 * with regards to the number of LUNs forming the pblk instance. This
-	 * balances LUN conflicts across every I/O.
-	 *
-	 * When the LUN configuration changes (e.g., due to GC), this distance
-	 * can align, which would result on a LUN deadlock. In this case, modify
-	 * the distance to not be optimal, but allow metadata I/Os to succeed.
-	 */
-	ppa_opt = addr_to_gen_ppa(pblk, paddr + data_line->meta_distance, 0);
-	if (unlikely(ppa_opt.ppa == ppa.ppa)) {
-		data_line->meta_distance--;
-		return 0;
-	}
-
-	for (i = 0; i < nr_ppas; i += pblk->min_write_pgs)
-		if (ppa_list[i].g.ch == ppa_opt.g.ch &&
-					ppa_list[i].g.lun == ppa_opt.g.lun)
-			return 1;
-
-	if (test_bit(pblk_ppa_to_pos(geo, ppa_opt), data_line->blk_bitmap)) {
-		for (i = 0; i < nr_ppas; i += pblk->min_write_pgs)
-			if (ppa_list[i].g.ch == ppa.g.ch &&
-						ppa_list[i].g.lun == ppa.g.lun)
-				return 0;
-
-		return 1;
-	}
-
-	return 0;
-}
-
 int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
@@ -421,8 +373,44 @@ fail_free_rqd:
 	return ret;
 }
 
-static int pblk_sched_meta_io(struct pblk *pblk, struct ppa_addr *prev_list,
-			       int prev_n)
+static inline bool pblk_valid_meta_ppa(struct pblk *pblk,
+				       struct pblk_line *meta_line,
+				       struct nvm_rq *data_rqd)
+{
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_c_ctx *data_c_ctx = nvm_rq_to_pdu(data_rqd);
+	struct pblk_line *data_line = pblk_line_get_data(pblk);
+	struct ppa_addr ppa, ppa_opt;
+	u64 paddr;
+	int pos_opt;
+
+	/* Schedule a metadata I/O that is half the distance from the data I/O
+	 * with regards to the number of LUNs forming the pblk instance. This
+	 * balances LUN conflicts across every I/O.
+	 *
+	 * When the LUN configuration changes (e.g., due to GC), this distance
+	 * can align, which would result on metadata and data I/Os colliding. In
+	 * this case, modify the distance to not be optimal, but move the
+	 * optimal in the right direction.
+	 */
+	paddr = pblk_lookup_page(pblk, meta_line);
+	ppa = addr_to_gen_ppa(pblk, paddr, 0);
+	ppa_opt = addr_to_gen_ppa(pblk, paddr + data_line->meta_distance, 0);
+	pos_opt = pblk_ppa_to_pos(geo, ppa_opt);
+
+	if (test_bit(pos_opt, data_c_ctx->lun_bitmap) ||
+				test_bit(pos_opt, data_line->blk_bitmap))
+		return true;
+
+	if (unlikely(pblk_ppa_comp(ppa_opt, ppa)))
+		data_line->meta_distance--;
+
+	return false;
+}
+
+static struct pblk_line *pblk_should_submit_meta_io(struct pblk *pblk,
+						    struct nvm_rq *data_rqd)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -432,57 +420,45 @@ static int pblk_sched_meta_io(struct pblk *pblk, struct ppa_addr *prev_list,
 retry:
 	if (list_empty(&l_mg->emeta_list)) {
 		spin_unlock(&l_mg->close_lock);
-		return 0;
+		return NULL;
 	}
 	meta_line = list_first_entry(&l_mg->emeta_list, struct pblk_line, list);
 	if (meta_line->emeta->mem >= lm->emeta_len[0])
 		goto retry;
 	spin_unlock(&l_mg->close_lock);
 
-	if (!pblk_valid_meta_ppa(pblk, meta_line, prev_list, prev_n))
-		return 0;
+	if (!pblk_valid_meta_ppa(pblk, meta_line, data_rqd))
+		return NULL;
 
-	return pblk_submit_meta_io(pblk, meta_line);
+	return meta_line;
 }
 
 static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 {
-	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
 	struct ppa_addr erase_ppa;
+	struct pblk_line *meta_line;
 	int err;
 
 	ppa_set_empty(&erase_ppa);
 
 	/* Assign lbas to ppas and populate request structure */
-	err = pblk_setup_w_rq(pblk, rqd, c_ctx, &erase_ppa);
+	err = pblk_setup_w_rq(pblk, rqd, &erase_ppa);
 	if (err) {
 		pr_err("pblk: could not setup write request: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
-	if (likely(ppa_empty(erase_ppa))) {
-		/* Submit metadata write for previous data line */
-		err = pblk_sched_meta_io(pblk, rqd->ppa_list, rqd->nr_ppas);
-		if (err) {
-			pr_err("pblk: metadata I/O submission failed: %d", err);
-			return NVM_IO_ERR;
-		}
+	meta_line = pblk_should_submit_meta_io(pblk, rqd);
 
-		/* Submit data write for current data line */
-		err = pblk_submit_io(pblk, rqd);
-		if (err) {
-			pr_err("pblk: data I/O submission failed: %d\n", err);
-			return NVM_IO_ERR;
-		}
-	} else {
-		/* Submit data write for current data line */
-		err = pblk_submit_io(pblk, rqd);
-		if (err) {
-			pr_err("pblk: data I/O submission failed: %d\n", err);
-			return NVM_IO_ERR;
-		}
+	/* Submit data write for current data line */
+	err = pblk_submit_io(pblk, rqd);
+	if (err) {
+		pr_err("pblk: data I/O submission failed: %d\n", err);
+		return NVM_IO_ERR;
+	}
 
-		/* Submit available erase for next data line */
+	if (!ppa_empty(erase_ppa)) {
+		/* Submit erase for next data line */
 		if (pblk_blk_erase_async(pblk, erase_ppa)) {
 			struct pblk_line *e_line = pblk_line_get_erase(pblk);
 			struct nvm_tgt_dev *dev = pblk->dev;
@@ -495,6 +471,15 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 		}
 	}
 
+	if (meta_line) {
+		/* Submit metadata write for previous data line */
+		err = pblk_submit_meta_io(pblk, meta_line);
+		if (err) {
+			pr_err("pblk: metadata I/O submission failed: %d", err);
+			return NVM_IO_ERR;
+		}
+	}
+
 	return NVM_IO_OK;
 }
 
-- 
cgit v1.2.3-70-g09d2