Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

1 files changed, 278 insertions, 75 deletions

diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index aef6fd7c4a0c..d62a8f4faaf4 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -17,18 +17,6 @@
 
 #include "pblk.h"
 
-static void pblk_sync_line(struct pblk *pblk, struct pblk_line *line)
-{
-#ifdef CONFIG_NVM_DEBUG
-	atomic_long_inc(&pblk->sync_writes);
-#endif
-
-	/* Counter protected by rb sync lock */
-	line->left_ssecs--;
-	if (!line->left_ssecs)
-		pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
-}
-
 static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 				    struct pblk_c_ctx *c_ctx)
 {
@@ -39,21 +27,14 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 
 	for (i = 0; i < c_ctx->nr_valid; i++) {
 		struct pblk_w_ctx *w_ctx;
-		struct ppa_addr p;
-		struct pblk_line *line;
 
 		w_ctx = pblk_rb_w_ctx(&pblk->rwb, c_ctx->sentry + i);
-
-		p = rqd->ppa_list[i];
-		line = &pblk->lines[pblk_dev_ppa_to_line(p)];
-		pblk_sync_line(pblk, line);
-
 		while ((original_bio = bio_list_pop(&w_ctx->bios)))
 			bio_endio(original_bio);
 	}
 
 #ifdef CONFIG_NVM_DEBUG
-	atomic_long_add(c_ctx->nr_valid, &pblk->compl_writes);
+	atomic_long_add(c_ctx->nr_valid, &pblk->sync_writes);
 #endif
 
 	ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
@@ -169,7 +150,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 	}
 
 	INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
-	queue_work(pblk->kw_wq, &recovery->ws_rec);
+	queue_work(pblk->close_wq, &recovery->ws_rec);
 
 out:
 	pblk_complete_write(pblk, rqd, c_ctx);
@@ -186,14 +167,50 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 	}
 #ifdef CONFIG_NVM_DEBUG
 	else
-		WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n");
+		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
 #endif
 
 	pblk_complete_write(pblk, rqd, c_ctx);
+	atomic_dec(&pblk->inflight_io);
+}
+
+static void pblk_end_io_write_meta(struct nvm_rq *rqd)
+{
+	struct pblk *pblk = rqd->private;
+	struct nvm_tgt_dev *dev = pblk->dev;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_g_ctx *m_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_line *line = m_ctx->private;
+	struct pblk_emeta *emeta = line->emeta;
+	int pos = pblk_ppa_to_pos(geo, rqd->ppa_list[0]);
+	struct pblk_lun *rlun = &pblk->luns[pos];
+	int sync;
+
+	up(&rlun->wr_sem);
+
+	if (rqd->error) {
+		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_line_run_ws(pblk, line, NULL, pblk_line_close_ws,
+								pblk->close_wq);
+
+	bio_put(rqd->bio);
+	pblk_free_rqd(pblk, rqd, READ);
+
+	atomic_dec(&pblk->inflight_io);
 }
 
 static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
-			   unsigned int nr_secs)
+			   unsigned int nr_secs,
+			   nvm_end_io_fn(*end_io))
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 
@@ -202,7 +219,7 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->nr_ppas = nr_secs;
 	rqd->flags = pblk_set_progr_mode(pblk, WRITE);
 	rqd->private = pblk;
-	rqd->end_io = pblk_end_io_write;
+	rqd->end_io = end_io;
 
 	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
 							&rqd->dma_meta_list);
@@ -219,11 +236,10 @@ 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 pblk_c_ctx *c_ctx, struct ppa_addr *erase_ppa)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
-	struct pblk_line *e_line = pblk_line_get_data_next(pblk);
-	struct ppa_addr erase_ppa;
+	struct pblk_line *e_line = pblk_line_get_erase(pblk);
 	unsigned int valid = c_ctx->nr_valid;
 	unsigned int padded = c_ctx->nr_padded;
 	unsigned int nr_secs = valid + padded;
@@ -231,40 +247,23 @@ static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	int ret = 0;
 
 	lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
-	if (!lun_bitmap) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!lun_bitmap)
+		return -ENOMEM;
 	c_ctx->lun_bitmap = lun_bitmap;
 
-	ret = pblk_alloc_w_rq(pblk, rqd, nr_secs);
+	ret = pblk_alloc_w_rq(pblk, rqd, nr_secs, pblk_end_io_write);
 	if (ret) {
 		kfree(lun_bitmap);
-		goto out;
+		return ret;
 	}
 
-	ppa_set_empty(&erase_ppa);
 	if (likely(!e_line || !atomic_read(&e_line->left_eblks)))
 		pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, valid, 0);
 	else
 		pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap,
-							valid, &erase_ppa);
-
-out:
-	if (unlikely(e_line && !ppa_empty(erase_ppa))) {
-		if (pblk_blk_erase_async(pblk, erase_ppa)) {
-			struct nvm_tgt_dev *dev = pblk->dev;
-			struct nvm_geo *geo = &dev->geo;
-			int bit;
-
-			atomic_inc(&e_line->left_eblks);
-			bit = erase_ppa.g.lun * geo->nr_chnls + erase_ppa.g.ch;
-			WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
-			up(&pblk->erase_sem);
-		}
-	}
+							valid, erase_ppa);
 
-	return ret;
+	return 0;
 }
 
 int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -280,7 +279,7 @@ int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
 
 	c_ctx->lun_bitmap = lun_bitmap;
 
-	ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas);
+	ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas, pblk_end_io_write);
 	if (ret)
 		return ret;
 
@@ -311,16 +310,237 @@ 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;
+	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_emeta *emeta = meta_line->emeta;
+	struct pblk_g_ctx *m_ctx;
+	struct pblk_lun *rlun;
+	struct bio *bio;
+	struct nvm_rq *rqd;
+	void *data;
+	u64 paddr;
+	int rq_ppas = pblk->min_write_pgs;
+	int id = meta_line->id;
+	int rq_len;
+	int i, j;
+	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;
+
+	rq_len = rq_ppas * geo->sec_size;
+	data = ((void *)emeta->buf) + emeta->mem;
+
+	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
+					l_mg->emeta_alloc_type, GFP_KERNEL);
+	if (IS_ERR(bio)) {
+		ret = PTR_ERR(bio);
+		goto fail_free_rqd;
+	}
+	bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	rqd->bio = bio;
+
+	ret = pblk_alloc_w_rq(pblk, rqd, rq_ppas, pblk_end_io_write_meta);
+	if (ret)
+		goto fail_free_bio;
+
+	for (i = 0; i < rqd->nr_ppas; ) {
+		spin_lock(&meta_line->lock);
+		paddr = __pblk_alloc_page(pblk, meta_line, rq_ppas);
+		spin_unlock(&meta_line->lock);
+		for (j = 0; j < rq_ppas; j++, i++, paddr++)
+			rqd->ppa_list[i] = addr_to_gen_ppa(pblk, paddr, id);
+	}
+
+	rlun = &pblk->luns[pblk_ppa_to_pos(geo, rqd->ppa_list[0])];
+	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
+	if (ret) {
+		pr_err("pblk: lun semaphore timed out (%d)\n", ret);
+		goto fail_free_bio;
+	}
+
+	emeta->mem += rq_len;
+	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);
+	}
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		goto fail_rollback;
+	}
+
+	return NVM_IO_OK;
+
+fail_rollback:
+	spin_lock(&l_mg->close_lock);
+	pblk_dealloc_page(pblk, meta_line, rq_ppas);
+	list_add(&meta_line->list, &meta_line->list);
+	spin_unlock(&l_mg->close_lock);
+fail_free_bio:
+	if (likely(l_mg->emeta_alloc_type == PBLK_VMALLOC_META))
+		bio_put(bio);
+fail_free_rqd:
+	pblk_free_rqd(pblk, rqd, READ);
+	return ret;
+}
+
+static int pblk_sched_meta_io(struct pblk *pblk, struct ppa_addr *prev_list,
+			       int prev_n)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line *meta_line;
+
+	spin_lock(&l_mg->close_lock);
+retry:
+	if (list_empty(&l_mg->emeta_list)) {
+		spin_unlock(&l_mg->close_lock);
+		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))
+		goto retry;
+	spin_unlock(&l_mg->close_lock);
+
+	if (!pblk_valid_meta_ppa(pblk, meta_line, prev_list, prev_n))
+		return 0;
+
+	return pblk_submit_meta_io(pblk, 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;
+	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);
+	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;
+		}
+
+		/* 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 available 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;
+			struct nvm_geo *geo = &dev->geo;
+			int bit;
+
+			atomic_inc(&e_line->left_eblks);
+			bit = pblk_ppa_to_pos(geo, erase_ppa);
+			WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
+		}
+	}
+
+	return NVM_IO_OK;
+}
+
+static void pblk_free_write_rqd(struct pblk *pblk, struct nvm_rq *rqd)
+{
+	struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+	struct bio *bio = rqd->bio;
+
+	if (c_ctx->nr_padded)
+		pblk_bio_free_pages(pblk, bio, rqd->nr_ppas, c_ctx->nr_padded);
+}
+
 static int pblk_submit_write(struct pblk *pblk)
 {
 	struct bio *bio;
 	struct nvm_rq *rqd;
-	struct pblk_c_ctx *c_ctx;
-	unsigned int pgs_read;
 	unsigned int secs_avail, secs_to_sync, secs_to_com;
 	unsigned int secs_to_flush;
 	unsigned long pos;
-	int err;
 
 	/* If there are no sectors in the cache, flushes (bios without data)
 	 * will be cleared on the cache threads
@@ -338,7 +558,6 @@ static int pblk_submit_write(struct pblk *pblk)
 		pr_err("pblk: cannot allocate write req.\n");
 		return 1;
 	}
-	c_ctx = nvm_rq_to_pdu(rqd);
 
 	bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
 	if (!bio) {
@@ -358,29 +577,14 @@ static int pblk_submit_write(struct pblk *pblk)
 	secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
 	pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
 
-	pgs_read = pblk_rb_read_to_bio(&pblk->rwb, bio, c_ctx, pos,
-						secs_to_sync, secs_avail);
-	if (!pgs_read) {
+	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, bio, pos, secs_to_sync,
+								secs_avail)) {
 		pr_err("pblk: corrupted write bio\n");
 		goto fail_put_bio;
 	}
 
-	if (c_ctx->nr_padded)
-		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, c_ctx->nr_padded))
-			goto fail_put_bio;
-
-	/* Assign lbas to ppas and populate request structure */
-	err = pblk_setup_w_rq(pblk, rqd, c_ctx);
-	if (err) {
-		pr_err("pblk: could not setup write request\n");
-		goto fail_free_bio;
-	}
-
-	err = pblk_submit_io(pblk, rqd);
-	if (err) {
-		pr_err("pblk: I/O submission failed: %d\n", err);
+	if (pblk_submit_io_set(pblk, rqd))
 		goto fail_free_bio;
-	}
 
 #ifdef CONFIG_NVM_DEBUG
 	atomic_long_add(secs_to_sync, &pblk->sub_writes);
@@ -389,8 +593,7 @@ static int pblk_submit_write(struct pblk *pblk)
 	return 0;
 
 fail_free_bio:
-	if (c_ctx->nr_padded)
-		pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded);
+	pblk_free_write_rqd(pblk, rqd);
 fail_put_bio:
 	bio_put(bio);
 fail_free_rqd: