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

Pull block fixes from Jens Axboe:
 "A collection of fixes that should go into this series. This contains:

   - A set of NVMe fixes, pulled from Christoph. This includes a set of
     fixes for the fiber channel bits from James Smart, rdma queue depth
     fix from Marta, controller removal fixes from Ming, and some more
     APST quirk updates from Andy.

   - A blk-mq debugfs fix from Bart, fixing a problem with the
     untangling of the sysfs and debugfs blk-mq bits that was added in
     this series.

   - Error code fix in add_partition() from Dan.

   - A small series of fixes for the new blk-throttle code from Shaohua"

* 'for-linus' of git://git.kernel.dk/linux-block: (21 commits)
  blk-mq: Only register debugfs attributes for blk-mq queues
  nvme: Quirk APST on Intel 600P/P3100 devices
  nvme: only setup block integrity if supported by the driver
  nvme: replace is_flags field in nvme_ctrl_ops with a flags field
  nvme-pci: consistencly use ctrl->device for logging
  partitions/msdos: FreeBSD UFS2 file systems are not recognized
  block: fix an error code in add_partition()
  blk-throttle: force user to configure all settings for io.low
  blk-throttle: respect 0 bps/iops settings for io.low
  blk-throttle: output some debug info in trace
  blk-throttle: add hierarchy support for latency target and idle time
  nvme_fc: remove extra controller reference taken on reconnect
  nvme_fc: correct nvme status set on abort
  nvme_fc: set logging level on resets/deletes
  nvme_fc: revise comment on teardown
  nvme_fc: Support ctrl_loss_tmo
  nvme_fc: get rid of local reconnect_delay
  blk-mq: remove blk_mq_abort_requeue_list()
  nvme: avoid to use blk_mq_abort_requeue_list()
  nvme: use blk_mq_start_hw_queues() in nvme_kill_queues()
  ...

block/blk-mq.c

@@ -628,25 +628,6 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
-void blk_mq_abort_requeue_list(struct request_queue *q)
-{
-	unsigned long flags;
-	LIST_HEAD(rq_list);
-
-	spin_lock_irqsave(&q->requeue_lock, flags);
-	list_splice_init(&q->requeue_list, &rq_list);
-	spin_unlock_irqrestore(&q->requeue_lock, flags);
-
-	while (!list_empty(&rq_list)) {
-		struct request *rq;
-
-		rq = list_first_entry(&rq_list, struct request, queuelist);
-		list_del_init(&rq->queuelist);
-		blk_mq_end_request(rq, -EIO);
-	}
-}
-EXPORT_SYMBOL(blk_mq_abort_requeue_list);
-
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
 	if (tag < tags->nr_tags) {

block/blk-sysfs.c

@@ -887,10 +887,10 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
-	if (q->mq_ops)
+	if (q->mq_ops) {
 		__blk_mq_register_dev(dev, q);
-
-	blk_mq_debugfs_register(q);
+		blk_mq_debugfs_register(q);
+	}
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 

block/blk-throttle.c

@@ -22,11 +22,11 @@ static int throtl_quantum = 32;
 #define DFL_THROTL_SLICE_HD (HZ / 10)
 #define DFL_THROTL_SLICE_SSD (HZ / 50)
 #define MAX_THROTL_SLICE (HZ)
-#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
-#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
 #define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
-/* default latency target is 0, eg, guarantee IO latency by default */
-#define DFL_LATENCY_TARGET (0)
+#define MIN_THROTL_BPS (320 * 1024)
+#define MIN_THROTL_IOPS (10)
+#define DFL_LATENCY_TARGET (-1L)
+#define DFL_IDLE_THRESHOLD (0)
 
 #define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
 
@@ -157,6 +157,7 @@ struct throtl_grp {
 	unsigned long last_check_time;
 
 	unsigned long latency_target; /* us */
+	unsigned long latency_target_conf; /* us */
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
@@ -165,6 +166,7 @@ struct throtl_grp {
 	unsigned long checked_last_finish_time; /* ns / 1024 */
 	unsigned long avg_idletime; /* ns / 1024 */
 	unsigned long idletime_threshold; /* us */
+	unsigned long idletime_threshold_conf; /* us */
 
 	unsigned int bio_cnt; /* total bios */
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
@@ -201,8 +203,6 @@ struct throtl_data
 	unsigned int limit_index;
 	bool limit_valid[LIMIT_CNT];
 
-	unsigned long dft_idletime_threshold; /* us */
-
 	unsigned long low_upgrade_time;
 	unsigned long low_downgrade_time;
 
@@ -294,8 +294,14 @@ static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
 
 	td = tg->td;
 	ret = tg->bps[rw][td->limit_index];
-	if (ret == 0 && td->limit_index == LIMIT_LOW)
-		return tg->bps[rw][LIMIT_MAX];
+	if (ret == 0 && td->limit_index == LIMIT_LOW) {
+		/* intermediate node or iops isn't 0 */
+		if (!list_empty(&blkg->blkcg->css.children) ||
+		    tg->iops[rw][td->limit_index])
+			return U64_MAX;
+		else
+			return MIN_THROTL_BPS;
+	}
 
 	if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
 	    tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
@@ -315,10 +321,17 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
 
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
 		return UINT_MAX;
+
 	td = tg->td;
 	ret = tg->iops[rw][td->limit_index];
-	if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
-		return tg->iops[rw][LIMIT_MAX];
+	if (ret == 0 && tg->td->limit_index == LIMIT_LOW) {
+		/* intermediate node or bps isn't 0 */
+		if (!list_empty(&blkg->blkcg->css.children) ||
+		    tg->bps[rw][td->limit_index])
+			return UINT_MAX;
+		else
+			return MIN_THROTL_IOPS;
+	}
 
 	if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
 	    tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
@@ -482,6 +495,9 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 	/* LIMIT_LOW will have default value 0 */
 
 	tg->latency_target = DFL_LATENCY_TARGET;
+	tg->latency_target_conf = DFL_LATENCY_TARGET;
+	tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+	tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
 
 	return &tg->pd;
 }
@@ -510,8 +526,6 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
 		sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
 	tg->td = td;
-
-	tg->idletime_threshold = td->dft_idletime_threshold;
 }
 
 /*
@@ -1349,7 +1363,7 @@ static int tg_print_conf_uint(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static void tg_conf_updated(struct throtl_grp *tg)
+static void tg_conf_updated(struct throtl_grp *tg, bool global)
 {
 	struct throtl_service_queue *sq = &tg->service_queue;
 	struct cgroup_subsys_state *pos_css;
@@ -1367,8 +1381,26 @@ static void tg_conf_updated(struct throtl_grp *tg)
 	 * restrictions in the whole hierarchy and allows them to bypass
 	 * blk-throttle.
 	 */
-	blkg_for_each_descendant_pre(blkg, pos_css, tg_to_blkg(tg))
-		tg_update_has_rules(blkg_to_tg(blkg));
+	blkg_for_each_descendant_pre(blkg, pos_css,
+			global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
+		struct throtl_grp *this_tg = blkg_to_tg(blkg);
+		struct throtl_grp *parent_tg;
+
+		tg_update_has_rules(this_tg);
+		/* ignore root/second level */
+		if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent ||
+		    !blkg->parent->parent)
+			continue;
+		parent_tg = blkg_to_tg(blkg->parent);
+		/*
+		 * make sure all children has lower idle time threshold and
+		 * higher latency target
+		 */
+		this_tg->idletime_threshold = min(this_tg->idletime_threshold,
+				parent_tg->idletime_threshold);
+		this_tg->latency_target = max(this_tg->latency_target,
+				parent_tg->latency_target);
+	}
 
 	/*
 	 * We're already holding queue_lock and know @tg is valid.  Let's
@@ -1413,7 +1445,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
 	else
 		*(unsigned int *)((void *)tg + of_cft(of)->private) = v;
 
-	tg_conf_updated(tg);
+	tg_conf_updated(tg, false);
 	ret = 0;
 out_finish:
 	blkg_conf_finish(&ctx);
@@ -1497,34 +1529,34 @@ static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
 	    tg->iops_conf[READ][off] == iops_dft &&
 	    tg->iops_conf[WRITE][off] == iops_dft &&
 	    (off != LIMIT_LOW ||
-	     (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
-	      tg->latency_target == DFL_LATENCY_TARGET)))
+	     (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD &&
+	      tg->latency_target_conf == DFL_LATENCY_TARGET)))
 		return 0;
 
-	if (tg->bps_conf[READ][off] != bps_dft)
+	if (tg->bps_conf[READ][off] != U64_MAX)
 		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
 			tg->bps_conf[READ][off]);
-	if (tg->bps_conf[WRITE][off] != bps_dft)
+	if (tg->bps_conf[WRITE][off] != U64_MAX)
 		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
 			tg->bps_conf[WRITE][off]);
-	if (tg->iops_conf[READ][off] != iops_dft)
+	if (tg->iops_conf[READ][off] != UINT_MAX)
 		snprintf(bufs[2], sizeof(bufs[2]), "%u",
 			tg->iops_conf[READ][off]);
-	if (tg->iops_conf[WRITE][off] != iops_dft)
+	if (tg->iops_conf[WRITE][off] != UINT_MAX)
 		snprintf(bufs[3], sizeof(bufs[3]), "%u",
 			tg->iops_conf[WRITE][off]);
 	if (off == LIMIT_LOW) {
-		if (tg->idletime_threshold == ULONG_MAX)
+		if (tg->idletime_threshold_conf == ULONG_MAX)
 			strcpy(idle_time, " idle=max");
 		else
 			snprintf(idle_time, sizeof(idle_time), " idle=%lu",
-				tg->idletime_threshold);
+				tg->idletime_threshold_conf);
 
-		if (tg->latency_target == ULONG_MAX)
+		if (tg->latency_target_conf == ULONG_MAX)
 			strcpy(latency_time, " latency=max");
 		else
 			snprintf(latency_time, sizeof(latency_time),
-				" latency=%lu", tg->latency_target);
+				" latency=%lu", tg->latency_target_conf);
 	}
 
 	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
@@ -1563,8 +1595,8 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
 	v[2] = tg->iops_conf[READ][index];
 	v[3] = tg->iops_conf[WRITE][index];
 
-	idle_time = tg->idletime_threshold;
-	latency_time = tg->latency_target;
+	idle_time = tg->idletime_threshold_conf;
+	latency_time = tg->latency_target_conf;
 	while (true) {
 		char tok[27];	/* wiops=18446744073709551616 */
 		char *p;
@@ -1623,17 +1655,33 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
 		tg->iops_conf[READ][LIMIT_MAX]);
 	tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
 		tg->iops_conf[WRITE][LIMIT_MAX]);
+	tg->idletime_threshold_conf = idle_time;
+	tg->latency_target_conf = latency_time;
+
+	/* force user to configure all settings for low limit  */
+	if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] ||
+	      tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) ||
+	    tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD ||
+	    tg->latency_target_conf == DFL_LATENCY_TARGET) {
+		tg->bps[READ][LIMIT_LOW] = 0;
+		tg->bps[WRITE][LIMIT_LOW] = 0;
+		tg->iops[READ][LIMIT_LOW] = 0;
+		tg->iops[WRITE][LIMIT_LOW] = 0;
+		tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+		tg->latency_target = DFL_LATENCY_TARGET;
+	} else if (index == LIMIT_LOW) {
+		tg->idletime_threshold = tg->idletime_threshold_conf;
+		tg->latency_target = tg->latency_target_conf;
+	}
 
-	if (index == LIMIT_LOW) {
-		blk_throtl_update_limit_valid(tg->td);
-		if (tg->td->limit_valid[LIMIT_LOW])
+	blk_throtl_update_limit_valid(tg->td);
+	if (tg->td->limit_valid[LIMIT_LOW]) {
+		if (index == LIMIT_LOW)
 			tg->td->limit_index = LIMIT_LOW;
-		tg->idletime_threshold = (idle_time == ULONG_MAX) ?
-			ULONG_MAX : idle_time;
-		tg->latency_target = (latency_time == ULONG_MAX) ?
-			ULONG_MAX : latency_time;
-	}
-	tg_conf_updated(tg);
+	} else
+		tg->td->limit_index = LIMIT_MAX;
+	tg_conf_updated(tg, index == LIMIT_LOW &&
+		tg->td->limit_valid[LIMIT_LOW]);
 	ret = 0;
 out_finish:
 	blkg_conf_finish(&ctx);
@@ -1722,17 +1770,25 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
 	/*
 	 * cgroup is idle if:
 	 * - single idle is too long, longer than a fixed value (in case user
-	 *   configure a too big threshold) or 4 times of slice
+	 *   configure a too big threshold) or 4 times of idletime threshold
 	 * - average think time is more than threshold
 	 * - IO latency is largely below threshold
 	 */
-	unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
-
-	time = min_t(unsigned long, MAX_IDLE_TIME, time);
-	return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
-	       tg->avg_idletime > tg->idletime_threshold ||
-	       (tg->latency_target && tg->bio_cnt &&
+	unsigned long time;
+	bool ret;
+
+	time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
+	ret = tg->latency_target == DFL_LATENCY_TARGET ||
+	      tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
+	      (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	      tg->avg_idletime > tg->idletime_threshold ||
+	      (tg->latency_target && tg->bio_cnt &&
 		tg->bad_bio_cnt * 5 < tg->bio_cnt);
+	throtl_log(&tg->service_queue,
+		"avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d",
+		tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt,
+		tg->bio_cnt, ret, tg->td->scale);
+	return ret;
 }
 
 static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
@@ -1828,6 +1884,7 @@ static void throtl_upgrade_state(struct throtl_data *td)
 	struct cgroup_subsys_state *pos_css;
 	struct blkcg_gq *blkg;
 
+	throtl_log(&td->service_queue, "upgrade to max");
 	td->limit_index = LIMIT_MAX;
 	td->low_upgrade_time = jiffies;
 	td->scale = 0;
@@ -1850,6 +1907,7 @@ static void throtl_downgrade_state(struct throtl_data *td, int new)
 {
 	td->scale /= 2;
 
+	throtl_log(&td->service_queue, "downgrade, scale %d", td->scale);
 	if (td->scale) {
 		td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
 		return;
@@ -2023,6 +2081,11 @@ static void throtl_update_latency_buckets(struct throtl_data *td)
 		td->avg_buckets[i].valid = true;
 		last_latency = td->avg_buckets[i].latency;
 	}
+
+	for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+		throtl_log(&td->service_queue,
+			"Latency bucket %d: latency=%ld, valid=%d", i,
+			td->avg_buckets[i].latency, td->avg_buckets[i].valid);
 }
 #else
 static inline void throtl_update_latency_buckets(struct throtl_data *td)
@@ -2354,19 +2417,14 @@ void blk_throtl_exit(struct request_queue *q)
 void blk_throtl_register_queue(struct request_queue *q)
 {
 	struct throtl_data *td;
-	struct cgroup_subsys_state *pos_css;
-	struct blkcg_gq *blkg;
 
 	td = q->td;
 	BUG_ON(!td);
 
-	if (blk_queue_nonrot(q)) {
+	if (blk_queue_nonrot(q))
 		td->throtl_slice = DFL_THROTL_SLICE_SSD;
-		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
-	} else {
+	else
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
-		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
-	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
@@ -2375,18 +2433,6 @@ void blk_throtl_register_queue(struct request_queue *q)
 	td->track_bio_latency = !q->mq_ops && !q->request_fn;
 	if (!td->track_bio_latency)
 		blk_stat_enable_accounting(q);
-
-	/*
-	 * some tg are created before queue is fully initialized, eg, nonrot
-	 * isn't initialized yet
-	 */
-	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
-		struct throtl_grp *tg = blkg_to_tg(blkg);
-
-		tg->idletime_threshold = td->dft_idletime_threshold;
-	}
-	rcu_read_unlock();
 }
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW

block/partition-generic.c

@@ -320,8 +320,10 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	if (info) {
 		struct partition_meta_info *pinfo = alloc_part_info(disk);
-		if (!pinfo)
+		if (!pinfo) {
+			err = -ENOMEM;
 			goto out_free_stats;
+		}
 		memcpy(pinfo, info, sizeof(*info));
 		p->info = pinfo;
 	}

block/partitions/msdos.c

@@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state,
 			continue;
 		bsd_start = le32_to_cpu(p->p_offset);
 		bsd_size = le32_to_cpu(p->p_size);
+		if (memcmp(flavour, "bsd\0", 4) == 0)
+			bsd_start += offset;
 		if (offset == bsd_start && size == bsd_size)
 			/* full parent partition, we have it already */
 			continue;

drivers/nvme/host/core.c

@@ -925,6 +925,29 @@ static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+		u16 bs)
+{
+	struct nvme_ns *ns = disk->private_data;
+	u16 old_ms = ns->ms;
+	u8 pi_type = 0;
+
+	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+
+	/* PI implementation requires metadata equal t10 pi tuple size */
+	if (ns->ms == sizeof(struct t10_pi_tuple))
+		pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+
+	if (blk_get_integrity(disk) &&
+	    (ns->pi_type != pi_type || ns->ms != old_ms ||
+	     bs != queue_logical_block_size(disk->queue) ||
+	     (ns->ms && ns->ext)))
+		blk_integrity_unregister(disk);
+
+	ns->pi_type = pi_type;
+}
+
 static void nvme_init_integrity(struct nvme_ns *ns)
 {
 	struct blk_integrity integrity;
@@ -951,6 +974,10 @@ static void nvme_init_integrity(struct nvme_ns *ns)
 	blk_queue_max_integrity_segments(ns->queue, 1);
 }
 #else
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+		u16 bs)
+{
+}
 static void nvme_init_integrity(struct nvme_ns *ns)
 {
 }
@@ -997,37 +1024,22 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
 static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	struct nvme_ns *ns = disk->private_data;
-	u8 lbaf, pi_type;
-	u16 old_ms;
-	unsigned short bs;
-
-	old_ms = ns->ms;
-	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
-	ns->lba_shift = id->lbaf[lbaf].ds;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+	u16 bs;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
 	 * block layer can use before failing read/write for 0 capacity.
 	 */
+	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 	bs = 1 << ns->lba_shift;
-	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
-	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
-					id->dps & NVME_NS_DPS_PI_MASK : 0;
 
 	blk_mq_freeze_queue(disk->queue);
-	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
-				ns->ms != old_ms ||
-				bs != queue_logical_block_size(disk->queue) ||
-				(ns->ms && ns->ext)))
-		blk_integrity_unregister(disk);
 
-	ns->pi_type = pi_type;
+	if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+		nvme_prep_integrity(disk, id, bs);
 	blk_queue_logical_block_size(ns->queue, bs);
-
 	if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
 		nvme_init_integrity(ns);
 	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
@@ -1605,7 +1617,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 	memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
 
-	if (ctrl->ops->is_fabrics) {
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		ctrl->icdoff = le16_to_cpu(id->icdoff);
 		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
 		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
@@ -2098,7 +2110,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		if (ns->ndev)
 			nvme_nvm_unregister_sysfs(ns);
 		del_gendisk(ns->disk);
-		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
 
@@ -2436,8 +2447,16 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 			continue;
 		revalidate_disk(ns->disk);
 		blk_set_queue_dying(ns->queue);
-		blk_mq_abort_requeue_list(ns->queue);
-		blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+		/*
+		 * Forcibly start all queues to avoid having stuck requests.
+		 * Note that we must ensure the queues are not stopped
+		 * when the final removal happens.
+		 */
+		blk_mq_start_hw_queues(ns->queue);
+
+		/* draining requests in requeue list */
+		blk_mq_kick_requeue_list(ns->queue);
 	}
 	mutex_unlock(&ctrl->namespaces_mutex);
 }

drivers/nvme/host/fc.c

@@ -45,8 +45,6 @@ enum nvme_fc_queue_flags {
 
 #define NVMEFC_QUEUE_DELAY	3		/* ms units */
 
-#define NVME_FC_MAX_CONNECT_ATTEMPTS	1
-
 struct nvme_fc_queue {
 	struct nvme_fc_ctrl	*ctrl;
 	struct device		*dev;
@@ -165,8 +163,6 @@ struct nvme_fc_ctrl {
 	struct work_struct	delete_work;
 	struct work_struct	reset_work;
 	struct delayed_work	connect_work;
-	int			reconnect_delay;
-	int			connect_attempts;
 
 	struct kref		ref;
 	u32			flags;
@@ -1376,9 +1372,9 @@ done:
 	complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
 	if (!complete_rq) {
 		if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
-			status = cpu_to_le16(NVME_SC_ABORT_REQ);
+			status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
 			if (blk_queue_dying(rq->q))
-				status |= cpu_to_le16(NVME_SC_DNR);
+				status |= cpu_to_le16(NVME_SC_DNR << 1);
 		}
 		nvme_end_request(rq, status, result);
 	} else
@@ -1751,7 +1747,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: transport association error detected: %s\n",
 		ctrl->cnum, errmsg);
-	dev_info(ctrl->ctrl.device,
+	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: resetting controller\n", ctrl->cnum);
 
 	/* stop the queues on error, cleanup is in reset thread */
@@ -2195,9 +2191,6 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (!opts->nr_io_queues)
 		return 0;
 
-	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
-			opts->nr_io_queues);
-
 	nvme_fc_init_io_queues(ctrl);
 
 	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
@@ -2268,9 +2261,6 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->queue_count == 1)
 		return 0;
 
-	dev_info(ctrl->ctrl.device, "Recreating %d I/O queues.\n",
-			opts->nr_io_queues);
-
 	nvme_fc_init_io_queues(ctrl);
 
 	ret = blk_mq_reinit_tagset(&ctrl->tag_set);
@@ -2306,7 +2296,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	int ret;
 	bool changed;
 
-	ctrl->connect_attempts++;
+	++ctrl->ctrl.opts->nr_reconnects;
 
 	/*
 	 * Create the admin queue
@@ -2403,9 +2393,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
-	ctrl->connect_attempts = 0;
-
-	kref_get(&ctrl->ctrl.kref);
+	ctrl->ctrl.opts->nr_reconnects = 0;
 
 	if (ctrl->queue_count > 1) {
 		nvme_start_queues(&ctrl->ctrl);
@@ -2536,26 +2524,32 @@ nvme_fc_delete_ctrl_work(struct work_struct *work)
 
 	/*
 	 * tear down the controller
-	 * This will result in the last reference on the nvme ctrl to
-	 * expire, calling the transport nvme_fc_nvme_ctrl_freed() callback.
-	 * From there, the transport will tear down it's logical queues and
-	 * association.
+	 * After the last reference on the nvme ctrl is removed,
+	 * the transport nvme_fc_nvme_ctrl_freed() callback will be
+	 * invoked. From there, the transport will tear down it's
+	 * logical queues and association.
 	 */
 	nvme_uninit_ctrl(&ctrl->ctrl);
 
 	nvme_put_ctrl(&ctrl->ctrl);
 }
 
-static int
-__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+static bool
+__nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
-		return -EBUSY;
+		return true;
 
 	if (!queue_work(nvme_fc_wq, &ctrl->delete_work))
-		return -EBUSY;
+		return true;
 
-	return 0;
+	return false;
+}
+
+static int
+__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+{
+	return __nvme_fc_schedule_delete_work(ctrl) ? -EBUSY : 0;
 }
 
 /*
@@ -2580,6 +2574,35 @@ nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl)
 	return ret;
 }
 
+static void
+nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
+{
+	/* If we are resetting/deleting then do nothing */
+	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+			ctrl->ctrl.state == NVME_CTRL_LIVE);
+		return;
+	}
+
+	dev_info(ctrl->ctrl.device,
+		"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
+		ctrl->cnum, status);
+
+	if (nvmf_should_reconnect(&ctrl->ctrl)) {
+		dev_info(ctrl->ctrl.device,
+			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+			ctrl->cnum, ctrl->ctrl.opts->reconnect_delay);
+		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+				ctrl->ctrl.opts->reconnect_delay * HZ);
+	} else {
+		dev_warn(ctrl->ctrl.device,
+				"NVME-FC{%d}: Max reconnect attempts (%d) "
+				"reached. Removing controller\n",
+				ctrl->cnum, ctrl->ctrl.opts->nr_reconnects);
+		WARN_ON(__nvme_fc_schedule_delete_work(ctrl));
+	}
+}
+
 static void
 nvme_fc_reset_ctrl_work(struct work_struct *work)
 {
@@ -2591,34 +2614,9 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
 	nvme_fc_delete_association(ctrl);
 
 	ret = nvme_fc_create_association(ctrl);
-	if (ret) {
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
-			ctrl->cnum, ret);
-		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Max reconnect attempts (%d) "
-				"reached. Removing controller\n",
-				ctrl->cnum, ctrl->connect_attempts);
-
-			if (!nvme_change_ctrl_state(&ctrl->ctrl,
-				NVME_CTRL_DELETING)) {
-				dev_err(ctrl->ctrl.device,
-					"NVME-FC{%d}: failed to change state "
-					"to DELETING\n", ctrl->cnum);
-				return;
-			}
-
-			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
-			return;
-		}
-
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
-			ctrl->cnum, ctrl->reconnect_delay);
-		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
-				ctrl->reconnect_delay * HZ);
-	} else
+	if (ret)
+		nvme_fc_reconnect_or_delete(ctrl, ret);
+	else
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: controller reset complete\n", ctrl->cnum);
 }
@@ -2632,7 +2630,7 @@ nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
-	dev_warn(ctrl->ctrl.device,
+	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
@@ -2649,7 +2647,7 @@ nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.name			= "fc",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
@@ -2671,34 +2669,9 @@ nvme_fc_connect_ctrl_work(struct work_struct *work)
 				struct nvme_fc_ctrl, connect_work);
 
 	ret = nvme_fc_create_association(ctrl);
-	if (ret) {
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt failed (%d)\n",
-			ctrl->cnum, ret);
-		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Max reconnect attempts (%d) "
-				"reached. Removing controller\n",
-				ctrl->cnum, ctrl->connect_attempts);
-
-			if (!nvme_change_ctrl_state(&ctrl->ctrl,
-				NVME_CTRL_DELETING)) {
-				dev_err(ctrl->ctrl.device,
-					"NVME-FC{%d}: failed to change state "
-					"to DELETING\n", ctrl->cnum);
-				return;
-			}
-
-			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
-			return;
-		}
-
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
-			ctrl->cnum, ctrl->reconnect_delay);
-		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
-				ctrl->reconnect_delay * HZ);
-	} else
+	if (ret)
+		nvme_fc_reconnect_or_delete(ctrl, ret);
+	else
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: controller reconnect complete\n",
 			ctrl->cnum);
@@ -2755,7 +2728,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work);
 	INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work);
 	INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
-	ctrl->reconnect_delay = opts->reconnect_delay;
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -2819,7 +2791,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		ctrl->ctrl.opts = NULL;
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
-		nvme_put_ctrl(&ctrl->ctrl);
 
 		/* as we're past the point where we transition to the ref
 		 * counting teardown path, if we return a bad pointer here,
@@ -2835,6 +2806,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		return ERR_PTR(ret);
 	}
 
+	kref_get(&ctrl->ctrl.kref);
+
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
 		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
@@ -2971,7 +2944,7 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 static struct nvmf_transport_ops nvme_fc_transport = {
 	.name		= "fc",
 	.required_opts	= NVMF_OPT_TRADDR | NVMF_OPT_HOST_TRADDR,
-	.allowed_opts	= NVMF_OPT_RECONNECT_DELAY,
+	.allowed_opts	= NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_CTRL_LOSS_TMO,
 	.create_ctrl	= nvme_fc_create_ctrl,
 };
 

drivers/nvme/host/nvme.h

@@ -208,7 +208,9 @@ struct nvme_ns {
 struct nvme_ctrl_ops {
 	const char *name;
 	struct module *module;
-	bool is_fabrics;
+	unsigned int flags;
+#define NVME_F_FABRICS			(1 << 0)
+#define NVME_F_METADATA_SUPPORTED	(1 << 1)
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);

drivers/nvme/host/pci.c

@@ -263,7 +263,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev)
 	c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
 
 	if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
-		dev_warn(dev->dev, "unable to set dbbuf\n");
+		dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
 		/* Free memory and continue on */
 		nvme_dbbuf_dma_free(dev);
 	}
@@ -1394,11 +1394,11 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
 	result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
 				      &pci_status);
 	if (result == PCIBIOS_SUCCESSFUL)
-		dev_warn(dev->dev,
+		dev_warn(dev->ctrl.device,
 			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
 			 csts, pci_status);
 	else
-		dev_warn(dev->dev,
+		dev_warn(dev->ctrl.device,
 			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
 			 csts, result);
 }
@@ -1740,8 +1740,8 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 */
 	if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
 		dev->q_depth = 2;
-		dev_warn(dev->dev, "detected Apple NVMe controller, set "
-			"queue depth=%u to work around controller resets\n",
+		dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
+			"set queue depth=%u to work around controller resets\n",
 			dev->q_depth);
 	}
 
@@ -1759,7 +1759,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 		if (dev->cmbsz) {
 			if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 						    &dev_attr_cmb.attr, NULL))
-				dev_warn(dev->dev,
+				dev_warn(dev->ctrl.device,
 					 "failed to add sysfs attribute for CMB\n");
 		}
 	}
@@ -2047,6 +2047,7 @@ static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
+	.flags			= NVME_F_METADATA_SUPPORTED,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
@@ -2293,6 +2294,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0a54),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
+	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */

drivers/nvme/host/rdma.c

@@ -1038,6 +1038,19 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		nvme_rdma_wr_error(cq, wc, "SEND");
 }
 
+static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
+{
+	int sig_limit;
+
+	/*
+	 * We signal completion every queue depth/2 and also handle the
+	 * degenerated case of a  device with queue_depth=1, where we
+	 * would need to signal every message.
+	 */
+	sig_limit = max(queue->queue_size / 2, 1);
+	return (++queue->sig_count % sig_limit) == 0;
+}
+
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
 		struct ib_send_wr *first, bool flush)
@@ -1065,9 +1078,6 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * Would have been way to obvious to handle this in hardware or
 	 * at least the RDMA stack..
 	 *
-	 * This messy and racy code sniplet is copy and pasted from the iSER
-	 * initiator, and the magic '32' comes from there as well.
-	 *
 	 * Always signal the flushes. The magic request used for the flush
 	 * sequencer is not allocated in our driver's tagset and it's
 	 * triggered to be freed by blk_cleanup_queue(). So we need to
@@ -1075,7 +1085,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * embedded in request's payload, is not freed when __ib_process_cq()
 	 * calls wr_cqe->done().
 	 */
-	if ((++queue->sig_count % 32) == 0 || flush)
+	if (nvme_rdma_queue_sig_limit(queue) || flush)
 		wr.send_flags |= IB_SEND_SIGNALED;
 
 	if (first)
@@ -1782,7 +1792,7 @@ static int nvme_rdma_reset_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
 	.name			= "rdma",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,

drivers/nvme/target/loop.c

@@ -558,7 +558,7 @@ static int nvme_loop_reset_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.name			= "loop",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,

include/linux/blk-mq.h

@@ -238,7 +238,6 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 				bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
-void blk_mq_abort_requeue_list(struct request_queue *q);
 void blk_mq_complete_request(struct request *rq);
 
 bool blk_mq_queue_stopped(struct request_queue *q);