Merge tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "Not a huge amount of changes in this round, the biggest one is that we
  finally have Mings multi-page bvec support merged. Apart from that,
  this pull request contains:

   - Small series that avoids quiescing the queue for sysfs changes that
     match what we currently have (Aleksei)

   - Series of bcache fixes (via Coly)

   - Series of lightnvm fixes (via Mathias)

   - NVMe pull request from Christoph. Nothing major, just SPDX/license
     cleanups, RR mp policy (Hannes), and little fixes (Bart,
     Chaitanya).

   - BFQ series (Paolo)

   - Save blk-mq cpu -> hw queue mapping, removing a pointer indirection
     for the fast path (Jianchao)

   - fops->iopoll() added for async IO polling, this is a feature that
     the upcoming io_uring interface will use (Christoph, me)

   - Partition scan loop fixes (Dongli)

   - mtip32xx conversion from managed resource API (Christoph)

   - cdrom registration race fix (Guenter)

   - MD pull from Song, two minor fixes.

   - Various documentation fixes (Marcos)

   - Multi-page bvec feature. This brings a lot of nice improvements
     with it, like more efficient splitting, larger IOs can be supported
     without growing the bvec table size, and so on. (Ming)

   - Various little fixes to core and drivers"

* tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block: (117 commits)
  block: fix updating bio's front segment size
  block: Replace function name in string with __func__
  nbd: propagate genlmsg_reply return code
  floppy: remove set but not used variable 'q'
  null_blk: fix checking for REQ_FUA
  block: fix NULL pointer dereference in register_disk
  fs: fix guard_bio_eod to check for real EOD errors
  blk-mq: use HCTX_TYPE_DEFAULT but not 0 to index blk_mq_tag_set->map
  block: optimize bvec iteration in bvec_iter_advance
  block: introduce mp_bvec_for_each_page() for iterating over page
  block: optimize blk_bio_segment_split for single-page bvec
  block: optimize __blk_segment_map_sg() for single-page bvec
  block: introduce bvec_nth_page()
  iomap: wire up the iopoll method
  block: add bio_set_polled() helper
  block: wire up block device iopoll method
  fs: add an iopoll method to struct file_operations
  loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
  loop: do not print warn message if partition scan is successful
  block: bounce: make sure that bvec table is updated
  ...

10 files changed, 92 insertions, 56 deletions

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 1ff165351180..6ca868868fee 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -141,7 +141,7 @@ struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk)
 
 	ret = nvm_get_chunk_meta(dev, ppa, geo->all_chunks, meta);
 	if (ret) {
-		kfree(meta);
+		vfree(meta);
 		return ERR_PTR(-EIO);
 	}
 
@@ -1065,7 +1065,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 	bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
 
 	smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC);
-	memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16);
+	guid_copy((guid_t *)&smeta_buf->header.uuid, &pblk->instance_uuid);
 	smeta_buf->header.id = cpu_to_le32(line->id);
 	smeta_buf->header.type = cpu_to_le16(line->type);
 	smeta_buf->header.version_major = SMETA_VERSION_MAJOR;
@@ -1278,6 +1278,7 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 	spin_unlock(&line->lock);
 
 	kref_init(&line->ref);
+	atomic_set(&line->sec_to_update, 0);
 
 	return 0;
 }
@@ -1874,7 +1875,8 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
 
 	if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) {
 		emeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC);
-		memcpy(emeta_buf->header.uuid, pblk->instance_uuid, 16);
+		guid_copy((guid_t *)&emeta_buf->header.uuid,
+							&pblk->instance_uuid);
 		emeta_buf->header.id = cpu_to_le32(line->id);
 		emeta_buf->header.type = cpu_to_le16(line->type);
 		emeta_buf->header.version_major = EMETA_VERSION_MAJOR;
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 2fa118c8eb71..26a52ea7ec45 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -365,16 +365,22 @@ static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk,
 						 struct list_head *group_list)
 {
 	struct pblk_line *line, *victim;
-	int line_vsc, victim_vsc;
+	unsigned int line_vsc = ~0x0L, victim_vsc = ~0x0L;
 
 	victim = list_first_entry(group_list, struct pblk_line, list);
+
 	list_for_each_entry(line, group_list, list) {
-		line_vsc = le32_to_cpu(*line->vsc);
-		victim_vsc = le32_to_cpu(*victim->vsc);
-		if (line_vsc < victim_vsc)
+		if (!atomic_read(&line->sec_to_update))
+			line_vsc = le32_to_cpu(*line->vsc);
+		if (line_vsc < victim_vsc) {
 			victim = line;
+			victim_vsc = le32_to_cpu(*victim->vsc);
+		}
 	}
 
+	if (victim_vsc == ~0x0)
+		return NULL;
+
 	return victim;
 }
 
@@ -448,13 +454,13 @@ next_gc_group:
 
 	do {
 		spin_lock(&l_mg->gc_lock);
-		if (list_empty(group_list)) {
+
+		line = pblk_gc_get_victim_line(pblk, group_list);
+		if (!line) {
 			spin_unlock(&l_mg->gc_lock);
 			break;
 		}
 
-		line = pblk_gc_get_victim_line(pblk, group_list);
-
 		spin_lock(&line->lock);
 		WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
 		line->state = PBLK_LINESTATE_GC;
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index f9a3e47b6a93..8b643d0bffae 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -130,7 +130,7 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	struct pblk_line *line = NULL;
 
 	if (factory_init) {
-		pblk_setup_uuid(pblk);
+		guid_gen(&pblk->instance_uuid);
 	} else {
 		line = pblk_recov_l2p(pblk);
 		if (IS_ERR(line)) {
@@ -584,14 +584,12 @@ static void pblk_lines_free(struct pblk *pblk)
 	struct pblk_line *line;
 	int i;
 
-	spin_lock(&l_mg->free_lock);
 	for (i = 0; i < l_mg->nr_lines; i++) {
 		line = &pblk->lines[i];
 
 		pblk_line_free(line);
 		pblk_line_meta_free(l_mg, line);
 	}
-	spin_unlock(&l_mg->free_lock);
 
 	pblk_line_mg_free(pblk);
 
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 79df583ea709..7fbc99b60cac 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -73,6 +73,7 @@ static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
 		 */
 		if (i < valid_secs) {
 			kref_get(&line->ref);
+			atomic_inc(&line->sec_to_update);
 			w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
 			w_ctx->ppa = ppa_list[i];
 			meta->lba = cpu_to_le64(w_ctx->lba);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index d4ca8c64ee0f..03c241b340ea 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -45,10 +45,23 @@ void pblk_rb_free(struct pblk_rb *rb)
 /*
  * pblk_rb_calculate_size -- calculate the size of the write buffer
  */
-static unsigned int pblk_rb_calculate_size(unsigned int nr_entries)
+static unsigned int pblk_rb_calculate_size(unsigned int nr_entries,
+					   unsigned int threshold)
 {
-	/* Alloc a write buffer that can at least fit 128 entries */
-	return (1 << max(get_count_order(nr_entries), 7));
+	unsigned int thr_sz = 1 << (get_count_order(threshold + NVM_MAX_VLBA));
+	unsigned int max_sz = max(thr_sz, nr_entries);
+	unsigned int max_io;
+
+	/* Alloc a write buffer that can (i) fit at least two split bios
+	 * (considering max I/O size NVM_MAX_VLBA, and (ii) guarantee that the
+	 * threshold will be respected
+	 */
+	max_io = (1 << max((int)(get_count_order(max_sz)),
+				(int)(get_count_order(NVM_MAX_VLBA << 1))));
+	if ((threshold + NVM_MAX_VLBA) >= max_io)
+		max_io <<= 1;
+
+	return max_io;
 }
 
 /*
@@ -67,12 +80,12 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold,
 	unsigned int alloc_order, order, iter;
 	unsigned int nr_entries;
 
-	nr_entries = pblk_rb_calculate_size(size);
+	nr_entries = pblk_rb_calculate_size(size, threshold);
 	entries = vzalloc(array_size(nr_entries, sizeof(struct pblk_rb_entry)));
 	if (!entries)
 		return -ENOMEM;
 
-	power_size = get_count_order(size);
+	power_size = get_count_order(nr_entries);
 	power_seg_sz = get_count_order(seg_size);
 
 	down_write(&pblk_rb_lock);
@@ -149,7 +162,7 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold,
 	 * Initialize rate-limiter, which controls access to the write buffer
 	 * by user and GC I/O
 	 */
-	pblk_rl_init(&pblk->rl, rb->nr_entries);
+	pblk_rl_init(&pblk->rl, rb->nr_entries, threshold);
 
 	return 0;
 }
@@ -247,6 +260,7 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int to_update)
 							entry->cacheline);
 
 		line = pblk_ppa_to_line(pblk, w_ctx->ppa);
+		atomic_dec(&line->sec_to_update);
 		kref_put(&line->ref, pblk_line_put);
 		clean_wctx(w_ctx);
 		rb->l2p_update = pblk_rb_ptr_wrap(rb, rb->l2p_update, 1);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 5ee20da7bdb3..d86f580036d3 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -302,35 +302,55 @@ static int pblk_pad_distance(struct pblk *pblk, struct pblk_line *line)
 	return (distance > line->left_msecs) ? line->left_msecs : distance;
 }
 
-static int pblk_line_wp_is_unbalanced(struct pblk *pblk,
-				      struct pblk_line *line)
+/* Return a chunk belonging to a line by stripe(write order) index */
+static struct nvm_chk_meta *pblk_get_stripe_chunk(struct pblk *pblk,
+						  struct pblk_line *line,
+						  int index)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
-	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_lun *rlun;
-	struct nvm_chk_meta *chunk;
 	struct ppa_addr ppa;
-	u64 line_wp;
-	int pos, i;
+	int pos;
 
-	rlun = &pblk->luns[0];
+	rlun = &pblk->luns[index];
 	ppa = rlun->bppa;
 	pos = pblk_ppa_to_pos(geo, ppa);
-	chunk = &line->chks[pos];
 
-	line_wp = chunk->wp;
+	return &line->chks[pos];
+}
 
-	for (i = 1; i < lm->blk_per_line; i++) {
-		rlun = &pblk->luns[i];
-		ppa = rlun->bppa;
-		pos = pblk_ppa_to_pos(geo, ppa);
-		chunk = &line->chks[pos];
+static int pblk_line_wps_are_unbalanced(struct pblk *pblk,
+				      struct pblk_line *line)
+{
+	struct pblk_line_meta *lm = &pblk->lm;
+	int blk_in_line = lm->blk_per_line;
+	struct nvm_chk_meta *chunk;
+	u64 max_wp, min_wp;
+	int i;
+
+	i = find_first_zero_bit(line->blk_bitmap, blk_in_line);
 
-		if (chunk->wp > line_wp)
+	/* If there is one or zero good chunks in the line,
+	 * the write pointers can't be unbalanced.
+	 */
+	if (i >= (blk_in_line - 1))
+		return 0;
+
+	chunk = pblk_get_stripe_chunk(pblk, line, i);
+	max_wp = chunk->wp;
+	if (max_wp > pblk->max_write_pgs)
+		min_wp = max_wp - pblk->max_write_pgs;
+	else
+		min_wp = 0;
+
+	i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1);
+	while (i < blk_in_line) {
+		chunk = pblk_get_stripe_chunk(pblk, line, i);
+		if (chunk->wp > max_wp || chunk->wp < min_wp)
 			return 1;
-		else if (chunk->wp < line_wp)
-			line_wp = chunk->wp;
+
+		i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1);
 	}
 
 	return 0;
@@ -356,7 +376,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
 	int ret;
 	u64 left_ppas = pblk_sec_in_open_line(pblk, line) - lm->smeta_sec;
 
-	if (pblk_line_wp_is_unbalanced(pblk, line))
+	if (pblk_line_wps_are_unbalanced(pblk, line))
 		pblk_warn(pblk, "recovering unbalanced line (%d)\n", line->id);
 
 	ppa_list = p.ppa_list;
@@ -703,11 +723,13 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 
 		/* The first valid instance uuid is used for initialization */
 		if (!valid_uuid) {
-			memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16);
+			guid_copy(&pblk->instance_uuid,
+				  (guid_t *)&smeta_buf->header.uuid);
 			valid_uuid = 1;
 		}
 
-		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
+		if (!guid_equal(&pblk->instance_uuid,
+				(guid_t *)&smeta_buf->header.uuid)) {
 			pblk_debug(pblk, "ignore line %u due to uuid mismatch\n",
 					i);
 			continue;
@@ -737,7 +759,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 	}
 
 	if (!found_lines) {
-		pblk_setup_uuid(pblk);
+		guid_gen(&pblk->instance_uuid);
 
 		spin_lock(&l_mg->free_lock);
 		WARN_ON_ONCE(!test_and_clear_bit(meta_line,
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index 76116d5f78e4..b014957dde0b 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -207,7 +207,7 @@ void pblk_rl_free(struct pblk_rl *rl)
 	del_timer(&rl->u_timer);
 }
 
-void pblk_rl_init(struct pblk_rl *rl, int budget)
+void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold)
 {
 	struct pblk *pblk = container_of(rl, struct pblk, rl);
 	struct nvm_tgt_dev *dev = pblk->dev;
@@ -217,7 +217,6 @@ void pblk_rl_init(struct pblk_rl *rl, int budget)
 	int sec_meta, blk_meta;
 	unsigned int rb_windows;
 
-
 	/* Consider sectors used for metadata */
 	sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines;
 	blk_meta = DIV_ROUND_UP(sec_meta, geo->clba);
@@ -234,7 +233,7 @@ void pblk_rl_init(struct pblk_rl *rl, int budget)
 	/* To start with, all buffer is available to user I/O writers */
 	rl->rb_budget = budget;
 	rl->rb_user_max = budget;
-	rl->rb_max_io = budget >> 1;
+	rl->rb_max_io = threshold ? (budget - threshold) : (budget - 1);
 	rl->rb_gc_max = 0;
 	rl->rb_state = PBLK_RL_HIGH;
 
diff --git a/drivers/lightnvm/pblk-trace.h b/drivers/lightnvm/pblk-trace.h
index 679e5c458ca6..9534503b69d9 100644
--- a/drivers/lightnvm/pblk-trace.h
+++ b/drivers/lightnvm/pblk-trace.h
@@ -139,7 +139,7 @@ TRACE_EVENT(pblk_state,
 /* This part must be outside protection */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../../drivers/lightnvm
+#define TRACE_INCLUDE_PATH ../../drivers/lightnvm
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE pblk-trace
 #include <trace/define_trace.h>
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 06d56deb645d..6593deab52da 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -177,6 +177,7 @@ static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry,
 		 * re-map these entries
 		 */
 		line = pblk_ppa_to_line(pblk, w_ctx->ppa);
+		atomic_dec(&line->sec_to_update);
 		kref_put(&line->ref, pblk_line_put);
 	}
 	spin_unlock(&pblk->trans_lock);
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 85e38ed62f85..ac3ab778e976 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -131,8 +131,8 @@ struct pblk_pr_ctx {
 	unsigned int bio_init_idx;
 	void *ppa_ptr;
 	dma_addr_t dma_ppa_list;
-	__le64 lba_list_mem[NVM_MAX_VLBA];
-	__le64 lba_list_media[NVM_MAX_VLBA];
+	u64 lba_list_mem[NVM_MAX_VLBA];
+	u64 lba_list_media[NVM_MAX_VLBA];
 };
 
 /* Pad context */
@@ -487,6 +487,7 @@ struct pblk_line {
 	__le32 *vsc;			/* Valid sector count in line */
 
 	struct kref ref;		/* Write buffer L2P references */
+	atomic_t sec_to_update;         /* Outstanding L2P updates to ppa */
 
 	struct pblk_w_err_gc *w_err_gc;	/* Write error gc recovery metadata */
 
@@ -646,7 +647,7 @@ struct pblk {
 
 	int sec_per_write;
 
-	unsigned char instance_uuid[16];
+	guid_t instance_uuid;
 
 	/* Persistent write amplification counters, 4kb sector I/Os */
 	atomic64_t user_wa;		/* Sectors written by user */
@@ -924,7 +925,7 @@ int pblk_gc_sysfs_force(struct pblk *pblk, int force);
 /*
  * pblk rate limiter
  */
-void pblk_rl_init(struct pblk_rl *rl, int budget);
+void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold);
 void pblk_rl_free(struct pblk_rl *rl);
 void pblk_rl_update_rates(struct pblk_rl *rl);
 int pblk_rl_high_thrs(struct pblk_rl *rl);
@@ -1360,14 +1361,6 @@ static inline unsigned int pblk_get_secs(struct bio *bio)
 	return  bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE;
 }
 
-static inline void pblk_setup_uuid(struct pblk *pblk)
-{
-	uuid_le uuid;
-
-	uuid_le_gen(&uuid);
-	memcpy(pblk->instance_uuid, uuid.b, 16);
-}
-
 static inline char *pblk_disk_name(struct pblk *pblk)
 {
 	struct gendisk *disk = pblk->disk;