Merge tag 'block-5.11-2021-01-10' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Missing CRC32 selections (Arnd)

 - Fix for a merge window regression with bdev inode init (Christoph)

 - bcache fixes

 - rnbd fixes

 - NVMe pull request from Christoph:
    - fix a race in the nvme-tcp send code (Sagi Grimberg)
    - fix a list corruption in an nvme-rdma error path (Israel Rukshin)
    - avoid a possible double fetch in nvme-pci (Lalithambika Krishnakumar)
    - add the susystem NQN quirk for a Samsung driver (Gopal Tiwari)
    - fix two compiler warnings in nvme-fcloop (James Smart)
    - don't call sleeping functions from irq context in nvme-fc (James Smart)
    - remove an unused argument (Max Gurtovoy)
    - remove unused exports (Minwoo Im)

 - Use-after-free fix for partition iteration (Ming)

 - Missing blk-mq debugfs flag annotation (John)

 - Bdev freeze regression fix (Satya)

 - blk-iocost NULL pointer deref fix (Tejun)

* tag 'block-5.11-2021-01-10' of git://git.kernel.dk/linux-block: (26 commits)
  bcache: set bcache device into read-only mode for BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET
  bcache: introduce BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE for large bucket
  bcache: check unsupported feature sets for bcache register
  bcache: fix typo from SUUP to SUPP in features.h
  bcache: set pdev_set_uuid before scond loop iteration
  blk-mq-debugfs: Add decode for BLK_MQ_F_TAG_HCTX_SHARED
  block/rnbd-clt: avoid module unload race with close confirmation
  block/rnbd: Adding name to the Contributors List
  block/rnbd-clt: Fix sg table use after free
  block/rnbd-srv: Fix use after free in rnbd_srv_sess_dev_force_close
  block/rnbd: Select SG_POOL for RNBD_CLIENT
  block: pre-initialize struct block_device in bdev_alloc_inode
  fs: Fix freeze_bdev()/thaw_bdev() accounting of bd_fsfreeze_sb
  nvme: remove the unused status argument from nvme_trace_bio_complete
  nvmet-rdma: Fix list_del corruption on queue establishment failure
  nvme: unexport functions with no external caller
  nvme: avoid possible double fetch in handling CQE
  nvme-tcp: Fix possible race of io_work and direct send
  nvme-pci: mark Samsung PM1725a as IGNORE_DEV_SUBNQN
  nvme-fcloop: Fix sscanf type and list_first_entry_or_null warnings
  ...

Author: torvalds

block/bfq-iosched.c

@@ -6332,13 +6332,13 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * limit 'something'.
 	 */
 	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+	bfqd->word_depths[0][0] = max(bt->sb.depth >> 1, 1U);
 	/*
 	 * no more than 75% of tags for sync writes (25% extra tags
 	 * w.r.t. async I/O, to prevent async I/O from starving sync
 	 * writes)
 	 */
-	bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+	bfqd->word_depths[0][1] = max((bt->sb.depth * 3) >> 2, 1U);
 
 	/*
 	 * In-word depths in case some bfq_queue is being weight-
@@ -6348,9 +6348,9 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * shortage.
 	 */
 	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+	bfqd->word_depths[1][0] = max((bt->sb.depth * 3) >> 4, 1U);
 	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+	bfqd->word_depths[1][1] = max((bt->sb.depth * 6) >> 4, 1U);
 
 	for (i = 0; i < 2; i++)
 		for (j = 0; j < 2; j++)

block/blk-iocost.c

@@ -2551,8 +2551,8 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	bool use_debt, ioc_locked;
 	unsigned long flags;
 
-	/* bypass IOs if disabled or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	/* bypass IOs if disabled, still initializing, or for root cgroup */
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	/* calculate the absolute vtime cost */
@@ -2679,14 +2679,14 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 			   struct bio *bio)
 {
 	struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
-	struct ioc *ioc = iocg->ioc;
+	struct ioc *ioc = rqos_to_ioc(rqos);
 	sector_t bio_end = bio_end_sector(bio);
 	struct ioc_now now;
 	u64 vtime, abs_cost, cost;
 	unsigned long flags;
 
-	/* bypass if disabled or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	/* bypass if disabled, still initializing, or for root cgroup */
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	abs_cost = calc_vtime_cost(bio, iocg, true);
@@ -2863,6 +2863,12 @@ static int blk_iocost_init(struct request_queue *q)
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
+	/*
+	 * rqos must be added before activation to allow iocg_pd_init() to
+	 * lookup the ioc from q. This means that the rqos methods may get
+	 * called before policy activation completion, can't assume that the
+	 * target bio has an iocg associated and need to test for NULL iocg.
+	 */
 	rq_qos_add(q, rqos);
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
 	if (ret) {

block/blk-mq-debugfs.c

@@ -246,6 +246,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
+	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 };
 #undef HCTX_FLAG_NAME
 

block/genhd.c

@@ -246,15 +246,18 @@ struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
+		piter->part = bdgrab(part);
+		if (!piter->part)
+			continue;
 		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
+		      piter->idx == 0)) {
+			bdput(piter->part);
+			piter->part = NULL;
 			continue;
+		}
 
-		piter->part = bdgrab(part);
-		if (!piter->part)
-			continue;
 		piter->idx += inc;
 		break;
 	}

drivers/block/Kconfig

@@ -445,6 +445,7 @@ config BLK_DEV_RBD
 config BLK_DEV_RSXX
 	tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
 	depends on PCI
+	select CRC32
 	help
 	  Device driver for IBM's high speed PCIe SSD
 	  storage device: Flash Adapter 900GB Full Height.

drivers/block/rnbd/Kconfig

@@ -7,6 +7,7 @@ config BLK_DEV_RNBD_CLIENT
 	tristate "RDMA Network Block Device driver client"
 	depends on INFINIBAND_RTRS_CLIENT
 	select BLK_DEV_RNBD
+	select SG_POOL
 	help
 	  RNBD client is a network block device driver using rdma transport.
 

drivers/block/rnbd/README

@@ -90,3 +90,4 @@ Kleber Souza <[email protected]>
 Lutz Pogrell <[email protected]>
 Milind Dumbare <[email protected]>
 Roman Penyaev <[email protected]>
+Swapnil Ingle <[email protected]>

drivers/block/rnbd/rnbd-clt.c

@@ -375,12 +375,19 @@ static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess,
 	init_waitqueue_head(&iu->comp.wait);
 	iu->comp.errno = INT_MAX;
 
+	if (sg_alloc_table(&iu->sgt, 1, GFP_KERNEL)) {
+		rnbd_put_permit(sess, permit);
+		kfree(iu);
+		return NULL;
+	}
+
 	return iu;
 }
 
 static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu)
 {
 	if (atomic_dec_and_test(&iu->refcount)) {
+		sg_free_table(&iu->sgt);
 		rnbd_put_permit(sess, iu->permit);
 		kfree(iu);
 	}
@@ -487,8 +494,6 @@ static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait)
 	iu->buf = NULL;
 	iu->dev = dev;
 
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
-
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_CLOSE);
 	msg.device_id	= cpu_to_le32(device_id);
 
@@ -502,7 +507,6 @@ static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait)
 		err = errno;
 	}
 
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -575,7 +579,6 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait)
 	iu->buf = rsp;
 	iu->dev = dev;
 
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
 	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_OPEN);
@@ -594,7 +597,6 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait)
 		err = errno;
 	}
 
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -622,8 +624,6 @@ static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait)
 
 	iu->buf = rsp;
 	iu->sess = sess;
-
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
 	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO);
@@ -650,7 +650,6 @@ static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait)
 	} else {
 		err = errno;
 	}
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -1698,7 +1697,8 @@ static void rnbd_destroy_sessions(void)
 	 */
 
 	list_for_each_entry_safe(sess, sn, &sess_list, list) {
-		WARN_ON(!rnbd_clt_get_sess(sess));
+		if (!rnbd_clt_get_sess(sess))
+			continue;
 		close_rtrs(sess);
 		list_for_each_entry_safe(dev, tn, &sess->devs_list, list) {
 			/*

drivers/block/rnbd/rnbd-srv.c

@@ -338,10 +338,12 @@ static int rnbd_srv_link_ev(struct rtrs_srv *rtrs,
 
 void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
 {
-	mutex_lock(&sess_dev->sess->lock);
-	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
-	mutex_unlock(&sess_dev->sess->lock);
+	struct rnbd_srv_session	*sess = sess_dev->sess;
+
 	sess_dev->keep_id = true;
+	mutex_lock(&sess->lock);
+	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
+	mutex_unlock(&sess->lock);
 }
 
 static int process_msg_close(struct rtrs_srv *rtrs,

drivers/lightnvm/Kconfig

@@ -19,6 +19,7 @@ if NVM
 
 config NVM_PBLK
 	tristate "Physical Block Device Open-Channel SSD target"
+	select CRC32
 	help
 	  Allows an open-channel SSD to be exposed as a block device to the
 	  host. The target assumes the device exposes raw flash and must be

drivers/md/bcache/features.c

@@ -17,7 +17,7 @@ struct feature {
 };
 
 static struct feature feature_list[] = {
-	{BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET,
+	{BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE,
 		"large_bucket"},
 	{0, 0, 0 },
 };

drivers/md/bcache/features.h

@@ -13,11 +13,15 @@
 
 /* Feature set definition */
 /* Incompat feature set */
-#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET	0x0001 /* 32bit bucket size */
+/* 32bit bucket size, obsoleted */
+#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET		0x0001
+/* real bucket size is (1 << bucket_size) */
+#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE	0x0002
 
-#define BCH_FEATURE_COMPAT_SUUP		0
-#define BCH_FEATURE_RO_COMPAT_SUUP	0
-#define BCH_FEATURE_INCOMPAT_SUUP	BCH_FEATURE_INCOMPAT_LARGE_BUCKET
+#define BCH_FEATURE_COMPAT_SUPP		0
+#define BCH_FEATURE_RO_COMPAT_SUPP	0
+#define BCH_FEATURE_INCOMPAT_SUPP	(BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \
+					 BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE)
 
 #define BCH_HAS_COMPAT_FEATURE(sb, mask) \
 		((sb)->feature_compat & (mask))
@@ -77,7 +81,23 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \
 		~BCH##_FEATURE_INCOMPAT_##flagname; \
 }
 
-BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE);
+
+static inline bool bch_has_unknown_compat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_compat & ~BCH_FEATURE_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_ro_compat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_ro_compat & ~BCH_FEATURE_RO_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_incompat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_incompat & ~BCH_FEATURE_INCOMPAT_SUPP) != 0);
+}
 
 int bch_print_cache_set_feature_compat(struct cache_set *c, char *buf, int size);
 int bch_print_cache_set_feature_ro_compat(struct cache_set *c, char *buf, int size);

drivers/md/bcache/super.c

@@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s
 {
 	unsigned int bucket_size = le16_to_cpu(s->bucket_size);
 
-	if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES &&
-	     bch_has_feature_large_bucket(sb))
-		bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16;
+	if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) {
+		if (bch_has_feature_large_bucket(sb)) {
+			unsigned int max, order;
+
+			max = sizeof(unsigned int) * BITS_PER_BYTE - 1;
+			order = le16_to_cpu(s->bucket_size);
+			/*
+			 * bcache tool will make sure the overflow won't
+			 * happen, an error message here is enough.
+			 */
+			if (order > max)
+				pr_err("Bucket size (1 << %u) overflows\n",
+					order);
+			bucket_size = 1 << order;
+		} else if (bch_has_feature_obso_large_bucket(sb)) {
+			bucket_size +=
+				le16_to_cpu(s->obso_bucket_size_hi) << 16;
+		}
+	}
 
 	return bucket_size;
 }
@@ -228,6 +244,20 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		sb->feature_compat = le64_to_cpu(s->feature_compat);
 		sb->feature_incompat = le64_to_cpu(s->feature_incompat);
 		sb->feature_ro_compat = le64_to_cpu(s->feature_ro_compat);
+
+		/* Check incompatible features */
+		err = "Unsupported compatible feature found";
+		if (bch_has_unknown_compat_features(sb))
+			goto err;
+
+		err = "Unsupported read-only compatible feature found";
+		if (bch_has_unknown_ro_compat_features(sb))
+			goto err;
+
+		err = "Unsupported incompatible feature found";
+		if (bch_has_unknown_incompat_features(sb))
+			goto err;
+
 		err = read_super_common(sb, bdev, s);
 		if (err)
 			goto err;
@@ -1302,6 +1332,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	bcache_device_link(&dc->disk, c, "bdev");
 	atomic_inc(&c->attached_dev_nr);
 
+	if (bch_has_feature_obso_large_bucket(&(c->cache->sb))) {
+		pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+		pr_err("Please update to the latest bcache-tools to create the cache device\n");
+		set_disk_ro(dc->disk.disk, 1);
+	}
+
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
 
@@ -1524,6 +1560,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 
 	bcache_device_link(d, c, "volume");
 
+	if (bch_has_feature_obso_large_bucket(&c->cache->sb)) {
+		pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+		pr_err("Please update to the latest bcache-tools to create the cache device\n");
+		set_disk_ro(d->disk, 1);
+	}
+
 	return 0;
 err:
 	kobject_put(&d->kobj);
@@ -2083,6 +2125,9 @@ static int run_cache_set(struct cache_set *c)
 	c->cache->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
+	if (bch_has_feature_obso_large_bucket(&c->cache->sb))
+		pr_err("Detect obsoleted large bucket layout, all attached bcache device will be read-only\n");
+
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
@@ -2644,8 +2689,8 @@ static ssize_t bch_pending_bdevs_cleanup(struct kobject *k,
 	}
 
 	list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
+		char *pdev_set_uuid = pdev->dc->sb.set_uuid;
 		list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
-			char *pdev_set_uuid = pdev->dc->sb.set_uuid;
 			char *set_uuid = c->set_uuid;
 
 			if (!memcmp(pdev_set_uuid, set_uuid, 16)) {