Merge tag 'for-4.18/block-20180603' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - clean up how we pass around gfp_t and
   blk_mq_req_flags_t (Christoph)

 - prepare us to defer scheduler attach (Christoph)

 - clean up drivers handling of bounce buffers (Christoph)

 - fix timeout handling corner cases (Christoph/Bart/Keith)

 - bcache fixes (Coly)

 - prep work for bcachefs and some block layer optimizations (Kent).

 - convert users of bio_sets to using embedded structs (Kent).

 - fixes for the BFQ io scheduler (Paolo/Davide/Filippo)

 - lightnvm fixes and improvements (Matias, with contributions from Hans
   and Javier)

 - adding discard throttling to blk-wbt (me)

 - sbitmap blk-mq-tag handling (me/Omar/Ming).

 - remove the sparc jsflash block driver, acked by DaveM.

 - Kyber scheduler improvement from Jianchao, making it more friendly
   wrt merging.

 - conversion of symbolic proc permissions to octal, from Joe Perches.
   Previously the block parts were a mix of both.

 - nbd fixes (Josef and Kevin Vigor)

 - unify how we handle the various kinds of timestamps that the block
   core and utility code uses (Omar)

 - three NVMe pull requests from Keith and Christoph, bringing AEN to
   feature completeness, file backed namespaces, cq/sq lock split, and
   various fixes

 - various little fixes and improvements all over the map

* tag 'for-4.18/block-20180603' of git://git.kernel.dk/linux-block: (196 commits)
  blk-mq: update nr_requests when switching to 'none' scheduler
  block: don't use blocking queue entered for recursive bio submits
  dm-crypt: fix warning in shutdown path
  lightnvm: pblk: take bitmap alloc. out of critical section
  lightnvm: pblk: kick writer on new flush points
  lightnvm: pblk: only try to recover lines with written smeta
  lightnvm: pblk: remove unnecessary bio_get/put
  lightnvm: pblk: add possibility to set write buffer size manually
  lightnvm: fix partial read error path
  lightnvm: proper error handling for pblk_bio_add_pages
  lightnvm: pblk: fix smeta write error path
  lightnvm: pblk: garbage collect lines with failed writes
  lightnvm: pblk: rework write error recovery path
  lightnvm: pblk: remove dead function
  lightnvm: pass flag on graceful teardown to targets
  lightnvm: pblk: check for chunk size before allocating it
  lightnvm: pblk: remove unnecessary argument
  lightnvm: pblk: remove unnecessary indirection
  lightnvm: pblk: return NVM_ error on failed submission
  lightnvm: pblk: warn in case of corrupted write buffer
  ...

1 files changed, 154 insertions, 79 deletions

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 94d5d97c9d8a..ed9cc977c8b3 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -40,7 +40,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 	}
 
 	kfree(ppa);
-	mempool_free(line_ws, pblk->gen_ws_pool);
+	mempool_free(line_ws, &pblk->gen_ws_pool);
 }
 
 static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
@@ -102,7 +102,7 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
 	struct pblk *pblk = rqd->private;
 
 	__pblk_end_io_erase(pblk, rqd);
-	mempool_free(rqd, pblk->e_rq_pool);
+	mempool_free(rqd, &pblk->e_rq_pool);
 }
 
 /*
@@ -237,15 +237,15 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type)
 	switch (type) {
 	case PBLK_WRITE:
 	case PBLK_WRITE_INT:
-		pool = pblk->w_rq_pool;
+		pool = &pblk->w_rq_pool;
 		rq_size = pblk_w_rq_size;
 		break;
 	case PBLK_READ:
-		pool = pblk->r_rq_pool;
+		pool = &pblk->r_rq_pool;
 		rq_size = pblk_g_rq_size;
 		break;
 	default:
-		pool = pblk->e_rq_pool;
+		pool = &pblk->e_rq_pool;
 		rq_size = pblk_g_rq_size;
 	}
 
@@ -265,20 +265,22 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int 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;
+		pool = &pblk->w_rq_pool;
 		break;
 	case PBLK_READ:
-		pool = pblk->r_rq_pool;
+		pool = &pblk->r_rq_pool;
 		break;
 	case PBLK_ERASE:
-		pool = pblk->e_rq_pool;
+		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);
+	if (rqd->meta_list)
+		nvm_dev_dma_free(dev->parent, rqd->meta_list,
+				rqd->dma_meta_list);
 	mempool_free(rqd, pool);
 }
 
@@ -292,7 +294,7 @@ void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
 
 	for (i = off; i < nr_pages + off; i++) {
 		bv = bio->bi_io_vec[i];
-		mempool_free(bv.bv_page, pblk->page_bio_pool);
+		mempool_free(bv.bv_page, &pblk->page_bio_pool);
 	}
 }
 
@@ -304,23 +306,23 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 	int i, ret;
 
 	for (i = 0; i < nr_pages; i++) {
-		page = mempool_alloc(pblk->page_bio_pool, flags);
+		page = mempool_alloc(&pblk->page_bio_pool, flags);
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
 			pr_err("pblk: could not add page to bio\n");
-			mempool_free(page, pblk->page_bio_pool);
+			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
 	}
 
 	return 0;
 err:
-	pblk_bio_free_pages(pblk, bio, 0, i - 1);
+	pblk_bio_free_pages(pblk, bio, (bio->bi_vcnt - i), i);
 	return -1;
 }
 
-static void pblk_write_kick(struct pblk *pblk)
+void pblk_write_kick(struct pblk *pblk)
 {
 	wake_up_process(pblk->writer_ts);
 	mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
@@ -342,13 +344,6 @@ void pblk_write_should_kick(struct pblk *pblk)
 		pblk_write_kick(pblk);
 }
 
-void pblk_end_io_sync(struct nvm_rq *rqd)
-{
-	struct completion *waiting = rqd->private;
-
-	complete(waiting);
-}
-
 static void pblk_wait_for_meta(struct pblk *pblk)
 {
 	do {
@@ -380,7 +375,13 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 
 	lockdep_assert_held(&line->lock);
 
-	if (!vsc) {
+	if (line->w_err_gc->has_write_err) {
+		if (line->gc_group != PBLK_LINEGC_WERR) {
+			line->gc_group = PBLK_LINEGC_WERR;
+			move_list = &l_mg->gc_werr_list;
+			pblk_rl_werr_line_in(&pblk->rl);
+		}
+	} else if (!vsc) {
 		if (line->gc_group != PBLK_LINEGC_FULL) {
 			line->gc_group = PBLK_LINEGC_FULL;
 			move_list = &l_mg->gc_full_list;
@@ -467,16 +468,13 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 
-#ifdef CONFIG_NVM_DEBUG
-	int ret;
+	atomic_inc(&pblk->inflight_io);
 
-	ret = pblk_check_io(pblk, rqd);
-	if (ret)
-		return ret;
+#ifdef CONFIG_NVM_DEBUG
+	if (pblk_check_io(pblk, rqd))
+		return NVM_IO_ERR;
 #endif
 
-	atomic_inc(&pblk->inflight_io);
-
 	return nvm_submit_io(dev, rqd);
 }
 
@@ -484,16 +482,13 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 
-#ifdef CONFIG_NVM_DEBUG
-	int ret;
+	atomic_inc(&pblk->inflight_io);
 
-	ret = pblk_check_io(pblk, rqd);
-	if (ret)
-		return ret;
+#ifdef CONFIG_NVM_DEBUG
+	if (pblk_check_io(pblk, rqd))
+		return NVM_IO_ERR;
 #endif
 
-	atomic_inc(&pblk->inflight_io);
-
 	return nvm_submit_io_sync(dev, rqd);
 }
 
@@ -856,9 +851,10 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	atomic_dec(&pblk->inflight_io);
 
 	if (rqd.error) {
-		if (dir == PBLK_WRITE)
+		if (dir == PBLK_WRITE) {
 			pblk_log_write_err(pblk, &rqd);
-		else if (dir == PBLK_READ)
+			ret = 1;
+		} else if (dir == PBLK_READ)
 			pblk_log_read_err(pblk, &rqd);
 	}
 
@@ -1071,6 +1067,25 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 	return 1;
 }
 
+static int pblk_line_alloc_bitmaps(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+
+	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!line->map_bitmap)
+		return -ENOMEM;
+
+	/* will be initialized using bb info from map_bitmap */
+	line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL);
+	if (!line->invalid_bitmap) {
+		kfree(line->map_bitmap);
+		line->map_bitmap = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /* For now lines are always assumed full lines. Thus, smeta former and current
  * lun bitmaps are omitted.
  */
@@ -1108,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
 		pr_debug("pblk: line smeta I/O failed. Retry\n");
-		return 1;
+		return 0;
 	}
 
 	bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
@@ -1174,19 +1189,9 @@ static int pblk_prepare_new_line(struct pblk *pblk, struct pblk_line *line)
 static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
+	int blk_in_line = atomic_read(&line->blk_in_line);
 	int blk_to_erase;
 
-	line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC);
-	if (!line->map_bitmap)
-		return -ENOMEM;
-
-	/* will be initialized using bb info from map_bitmap */
-	line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_ATOMIC);
-	if (!line->invalid_bitmap) {
-		kfree(line->map_bitmap);
-		return -ENOMEM;
-	}
-
 	/* Bad blocks do not need to be erased */
 	bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
 
@@ -1199,16 +1204,19 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 		blk_to_erase = pblk_prepare_new_line(pblk, line);
 		line->state = PBLK_LINESTATE_FREE;
 	} else {
-		blk_to_erase = atomic_read(&line->blk_in_line);
+		blk_to_erase = blk_in_line;
 	}
 
-	if (line->state != PBLK_LINESTATE_FREE) {
-		kfree(line->map_bitmap);
-		kfree(line->invalid_bitmap);
+	if (blk_in_line < lm->min_blk_line) {
 		spin_unlock(&line->lock);
+		return -EAGAIN;
+	}
+
+	if (line->state != PBLK_LINESTATE_FREE) {
 		WARN(1, "pblk: corrupted line %d, state %d\n",
 							line->id, line->state);
-		return -EAGAIN;
+		spin_unlock(&line->lock);
+		return -EINTR;
 	}
 
 	line->state = PBLK_LINESTATE_OPEN;
@@ -1241,13 +1249,16 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
 	}
 	spin_unlock(&l_mg->free_lock);
 
-	pblk_rl_free_lines_dec(&pblk->rl, line, true);
+	ret = pblk_line_alloc_bitmaps(pblk, line);
+	if (ret)
+		return ret;
 
 	if (!pblk_line_init_bb(pblk, line, 0)) {
 		list_add(&line->list, &l_mg->free_list);
 		return -EINTR;
 	}
 
+	pblk_rl_free_lines_dec(&pblk->rl, line, true);
 	return 0;
 }
 
@@ -1259,6 +1270,24 @@ void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
 	line->emeta = NULL;
 }
 
+static void pblk_line_reinit(struct pblk_line *line)
+{
+	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
+
+	line->map_bitmap = NULL;
+	line->invalid_bitmap = NULL;
+	line->smeta = NULL;
+	line->emeta = NULL;
+}
+
+void pblk_line_free(struct pblk_line *line)
+{
+	kfree(line->map_bitmap);
+	kfree(line->invalid_bitmap);
+
+	pblk_line_reinit(line);
+}
+
 struct pblk_line *pblk_line_get(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1292,10 +1321,14 @@ retry:
 
 	ret = pblk_line_prepare(pblk, line);
 	if (ret) {
-		if (ret == -EAGAIN) {
+		switch (ret) {
+		case -EAGAIN:
+			list_add(&line->list, &l_mg->bad_list);
+			goto retry;
+		case -EINTR:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
-		} else {
+		default:
 			pr_err("pblk: failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
@@ -1321,11 +1354,14 @@ retry:
 		return NULL;
 	}
 
+	retry_line->map_bitmap = line->map_bitmap;
+	retry_line->invalid_bitmap = line->invalid_bitmap;
 	retry_line->smeta = line->smeta;
 	retry_line->emeta = line->emeta;
 	retry_line->meta_line = line->meta_line;
 
-	pblk_line_free(pblk, line);
+	pblk_line_reinit(line);
+
 	l_mg->data_line = retry_line;
 	spin_unlock(&l_mg->free_lock);
 
@@ -1378,6 +1414,9 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 	}
 	spin_unlock(&l_mg->free_lock);
 
+	if (pblk_line_alloc_bitmaps(pblk, line))
+		return NULL;
+
 	if (pblk_line_erase(pblk, line)) {
 		line = pblk_line_retry(pblk, line);
 		if (!line)
@@ -1449,7 +1488,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 	flush_workqueue(pblk->close_wq);
 }
 
-void pblk_pipeline_stop(struct pblk *pblk)
+void __pblk_pipeline_flush(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	int ret;
@@ -1474,6 +1513,11 @@ void pblk_pipeline_stop(struct pblk *pblk)
 
 	flush_workqueue(pblk->bb_wq);
 	pblk_line_close_meta_sync(pblk);
+}
+
+void __pblk_pipeline_stop(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 
 	spin_lock(&l_mg->free_lock);
 	pblk->state = PBLK_STATE_STOPPED;
@@ -1482,6 +1526,12 @@ void pblk_pipeline_stop(struct pblk *pblk)
 	spin_unlock(&l_mg->free_lock);
 }
 
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+	__pblk_pipeline_flush(pblk);
+	__pblk_pipeline_stop(pblk);
+}
+
 struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1511,6 +1561,9 @@ retry_erase:
 		goto retry_erase;
 	}
 
+	if (pblk_line_alloc_bitmaps(pblk, new))
+		return NULL;
+
 retry_setup:
 	if (!pblk_line_init_metadata(pblk, new, cur)) {
 		new = pblk_line_retry(pblk, new);
@@ -1550,19 +1603,6 @@ out:
 	return new;
 }
 
-void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
-{
-	kfree(line->map_bitmap);
-	kfree(line->invalid_bitmap);
-
-	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
-
-	line->map_bitmap = NULL;
-	line->invalid_bitmap = NULL;
-	line->smeta = NULL;
-	line->emeta = NULL;
-}
-
 static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1572,9 +1612,14 @@ static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
 	WARN_ON(line->state != PBLK_LINESTATE_GC);
 	line->state = PBLK_LINESTATE_FREE;
 	line->gc_group = PBLK_LINEGC_NONE;
-	pblk_line_free(pblk, line);
-	spin_unlock(&line->lock);
+	pblk_line_free(line);
+
+	if (line->w_err_gc->has_write_err) {
+		pblk_rl_werr_line_out(&pblk->rl);
+		line->w_err_gc->has_write_err = 0;
+	}
 
+	spin_unlock(&line->lock);
 	atomic_dec(&gc->pipeline_gc);
 
 	spin_lock(&l_mg->free_lock);
@@ -1593,7 +1638,7 @@ static void pblk_line_put_ws(struct work_struct *work)
 	struct pblk_line *line = line_put_ws->line;
 
 	__pblk_line_put(pblk, line);
-	mempool_free(line_put_ws, pblk->gen_ws_pool);
+	mempool_free(line_put_ws, &pblk->gen_ws_pool);
 }
 
 void pblk_line_put(struct kref *ref)
@@ -1610,7 +1655,7 @@ void pblk_line_put_wq(struct kref *ref)
 	struct pblk *pblk = line->pblk;
 	struct pblk_line_ws *line_put_ws;
 
-	line_put_ws = mempool_alloc(pblk->gen_ws_pool, GFP_ATOMIC);
+	line_put_ws = mempool_alloc(&pblk->gen_ws_pool, GFP_ATOMIC);
 	if (!line_put_ws)
 		return;
 
@@ -1737,11 +1782,34 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
 
 	spin_lock(&l_mg->close_lock);
 	spin_lock(&line->lock);
+
+	/* Update the in-memory start address for emeta, in case it has
+	 * shifted due to write errors
+	 */
+	if (line->emeta_ssec != line->cur_sec)
+		line->emeta_ssec = line->cur_sec;
+
 	list_add_tail(&line->list, &l_mg->emeta_list);
 	spin_unlock(&line->lock);
 	spin_unlock(&l_mg->close_lock);
 
 	pblk_line_should_sync_meta(pblk);
+
+
+}
+
+static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	unsigned int lba_list_size = lm->emeta_len[2];
+	struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+	struct pblk_emeta *emeta = line->emeta;
+
+	w_err_gc->lba_list = pblk_malloc(lba_list_size,
+					 l_mg->emeta_alloc_type, GFP_KERNEL);
+	memcpy(w_err_gc->lba_list, emeta_to_lbas(pblk, emeta->buf),
+				lba_list_size);
 }
 
 void pblk_line_close_ws(struct work_struct *work)
@@ -1750,9 +1818,16 @@ void pblk_line_close_ws(struct work_struct *work)
 									ws);
 	struct pblk *pblk = line_ws->pblk;
 	struct pblk_line *line = line_ws->line;
+	struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+
+	/* Write errors makes the emeta start address stored in smeta invalid,
+	 * so keep a copy of the lba list until we've gc'd the line
+	 */
+	if (w_err_gc->has_write_err)
+		pblk_save_lba_list(pblk, line);
 
 	pblk_line_close(pblk, line);
-	mempool_free(line_ws, pblk->gen_ws_pool);
+	mempool_free(line_ws, &pblk->gen_ws_pool);
 }
 
 void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
@@ -1761,7 +1836,7 @@ 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);
+	line_ws = mempool_alloc(&pblk->gen_ws_pool, gfp_mask);
 
 	line_ws->pblk = pblk;
 	line_ws->line = line;