Merge tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Christoph:
      - Don't access released socket during error recovery (Akinobu
        Mita)
      - Bring back auto-removal of deleted namespaces during sequential
        scan (Christoph Hellwig)
      - Fix an error code in nvme_auth_process_dhchap_challenge (Dan
        Carpenter)
      - Show well known discovery name (Daniel Wagner)
      - Add a missing endianess conversion in effects masking (Keith
        Busch)

 - Fix for a regression introduced in blk-rq-qos during init in this
   merge window (Breno)

 - Reorder a few fields in struct blk_mq_tag_set, eliminating a few
   holes and shrinking it (Christophe)

 - Remove redundant bdev_get_queue() NULL checks (Juhyung)

 - Add sed-opal single user mode support flag (Luca)

 - Remove SQE128 check in ublk as it isn't needed, saving some memory
   (Ming)

 - Op specific segment checking for cloned requests (Uday)

 - Exclusive open partition scan fixes (Yu)

 - Loop offset/size checking before assigning them in the device (Zhong)

 - Bio polling fixes (me)

* tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux:
  blk-mq: enforce op-specific segment limits in blk_insert_cloned_request
  nvme-fabrics: show well known discovery name
  nvme-tcp: don't access released socket during error recovery
  nvme-auth: fix an error code in nvme_auth_process_dhchap_challenge()
  nvme: bring back auto-removal of deleted namespaces during sequential scan
  blk-iocost: Pass gendisk to ioc_refresh_params
  nvme: fix sparse warning on effects masking
  block: be a bit more careful in checking for NULL bdev while polling
  block: clear bio->bi_bdev when putting a bio back in the cache
  loop: loop_set_status_from_info() check before assignment
  ublk: remove check IO_URING_F_SQE128 in ublk_ch_uring_cmd
  block: remove more NULL checks after bdev_get_queue()
  blk-mq: Reorder fields in 'struct blk_mq_tag_set'
  block: fix scan partition for exclusively open device again
  block: Revert "block: Do not reread partition table on exclusively open device"
  sed-opal: add support flag for SUM in status ioctl

10 files changed, 77 insertions, 45 deletions

diff --git a/block/bio.c b/block/bio.c
index 2e421c0dad13..fd11614bba4d 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -772,6 +772,7 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 
 	if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) {
 		bio->bi_next = cache->free_list;
+		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
 	} else {
diff --git a/block/blk-core.c b/block/blk-core.c
index 82b5b2c53f1e..9e5e0277a4d9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -858,10 +858,16 @@ EXPORT_SYMBOL(submit_bio);
  */
 int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 {
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
+	struct block_device *bdev;
+	struct request_queue *q;
 	int ret = 0;
 
+	bdev = READ_ONCE(bio->bi_bdev);
+	if (!bdev)
+		return 0;
+
+	q = bdev_get_queue(bdev);
 	if (cookie == BLK_QC_T_NONE ||
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
@@ -930,7 +936,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
 	 */
 	rcu_read_lock();
 	bio = READ_ONCE(kiocb->private);
-	if (bio && bio->bi_bdev)
+	if (bio)
 		ret = bio_poll(bio, iob, flags);
 	rcu_read_unlock();
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index ff534e9d92dc..4442c7a85112 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -800,7 +800,11 @@ static void ioc_refresh_period_us(struct ioc *ioc)
 	ioc_refresh_margins(ioc);
 }
 
-static int ioc_autop_idx(struct ioc *ioc)
+/*
+ *  ioc->rqos.disk isn't initialized when this function is called from
+ *  the init path.
+ */
+static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk)
 {
 	int idx = ioc->autop_idx;
 	const struct ioc_params *p = &autop[idx];
@@ -808,11 +812,11 @@ static int ioc_autop_idx(struct ioc *ioc)
 	u64 now_ns;
 
 	/* rotational? */
-	if (!blk_queue_nonrot(ioc->rqos.disk->queue))
+	if (!blk_queue_nonrot(disk->queue))
 		return AUTOP_HDD;
 
 	/* handle SATA SSDs w/ broken NCQ */
-	if (blk_queue_depth(ioc->rqos.disk->queue) == 1)
+	if (blk_queue_depth(disk->queue) == 1)
 		return AUTOP_SSD_QD1;
 
 	/* use one of the normal ssd sets */
@@ -901,14 +905,19 @@ static void ioc_refresh_lcoefs(struct ioc *ioc)
 		    &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]);
 }
 
-static bool ioc_refresh_params(struct ioc *ioc, bool force)
+/*
+ * struct gendisk is required as an argument because ioc->rqos.disk
+ * is not properly initialized when called from the init path.
+ */
+static bool ioc_refresh_params_disk(struct ioc *ioc, bool force,
+				    struct gendisk *disk)
 {
 	const struct ioc_params *p;
 	int idx;
 
 	lockdep_assert_held(&ioc->lock);
 
-	idx = ioc_autop_idx(ioc);
+	idx = ioc_autop_idx(ioc, disk);
 	p = &autop[idx];
 
 	if (idx == ioc->autop_idx && !force)
@@ -939,6 +948,11 @@ static bool ioc_refresh_params(struct ioc *ioc, bool force)
 	return true;
 }
 
+static bool ioc_refresh_params(struct ioc *ioc, bool force)
+{
+	return ioc_refresh_params_disk(ioc, force, ioc->rqos.disk);
+}
+
 /*
  * When an iocg accumulates too much vtime or gets deactivated, we throw away
  * some vtime, which lowers the overall device utilization. As the exact amount
@@ -2880,7 +2894,7 @@ static int blk_iocost_init(struct gendisk *disk)
 
 	spin_lock_irq(&ioc->lock);
 	ioc->autop_idx = AUTOP_INVALID;
-	ioc_refresh_params(ioc, true);
+	ioc_refresh_params_disk(ioc, true, disk);
 	spin_unlock_irq(&ioc->lock);
 
 	/*
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 1ac782fdc55c..6460abdb2426 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -587,13 +587,6 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(__blk_rq_map_sg);
 
-static inline unsigned int blk_rq_get_max_segments(struct request *rq)
-{
-	if (req_op(rq) == REQ_OP_DISCARD)
-		return queue_max_discard_segments(rq->q);
-	return queue_max_segments(rq->q);
-}
-
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 						  sector_t offset)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d3494a796ba8..d0cb2ef18fe2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3000,6 +3000,7 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+	unsigned int max_segments = blk_rq_get_max_segments(rq);
 	blk_status_t ret;
 
 	if (blk_rq_sectors(rq) > max_sectors) {
@@ -3026,9 +3027,9 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	 * original queue.
 	 */
 	rq->nr_phys_segments = blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > queue_max_segments(q)) {
-		printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
-			__func__, rq->nr_phys_segments, queue_max_segments(q));
+	if (rq->nr_phys_segments > max_segments) {
+		printk(KERN_ERR "%s: over max segments limit. (%u > %u)\n",
+			__func__, rq->nr_phys_segments, max_segments);
 		return BLK_STS_IOERR;
 	}
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 614b575be899..fce9082384d6 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -334,17 +334,12 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 {
 	void __user *argp = (void __user *)arg;
 	struct zone_report_args args;
-	struct request_queue *q;
 	struct blk_zone_report rep;
 	int ret;
 
 	if (!argp)
 		return -EINVAL;
 
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
 	if (!bdev_is_zoned(bdev))
 		return -ENOTTY;
 
@@ -391,7 +386,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
-	struct request_queue *q;
 	struct blk_zone_range zrange;
 	enum req_op op;
 	int ret;
@@ -399,10 +393,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!argp)
 		return -EINVAL;
 
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
 	if (!bdev_is_zoned(bdev))
 		return -ENOTTY;
 
diff --git a/block/blk.h b/block/blk.h
index 4c3b3325219a..cc4e8873dfde 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -156,6 +156,13 @@ static inline bool blk_discard_mergable(struct request *req)
 	return false;
 }
 
+static inline unsigned int blk_rq_get_max_segments(struct request *rq)
+{
+	if (req_op(rq) == REQ_OP_DISCARD)
+		return queue_max_discard_segments(rq->q);
+	return queue_max_segments(rq->q);
+}
+
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     enum req_op op)
 {
@@ -427,7 +434,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 
 struct request_queue *blk_alloc_queue(int node_id);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner);
+int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
 
 int disk_alloc_events(struct gendisk *disk);
 void disk_add_events(struct gendisk *disk);
diff --git a/block/genhd.c b/block/genhd.c
index d09d775c222a..3ee5577e1586 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -356,9 +356,10 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action)
 }
 EXPORT_SYMBOL_GPL(disk_uevent);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner)
+int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 {
 	struct block_device *bdev;
+	int ret = 0;
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
 		return -EINVAL;
@@ -366,16 +367,29 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner)
 		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
-	/* Someone else has bdev exclusively open? */
-	if (disk->part0->bd_holder && disk->part0->bd_holder != owner)
-		return -EBUSY;
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	bdev = blkdev_get_by_dev(disk_devt(disk), mode, NULL);
+	/*
+	 * If the device is opened exclusively by current thread already, it's
+	 * safe to scan partitons, otherwise, use bd_prepare_to_claim() to
+	 * synchronize with other exclusive openers and other partition
+	 * scanners.
+	 */
+	if (!(mode & FMODE_EXCL)) {
+		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions);
+		if (ret)
+			return ret;
+	}
+
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL);
 	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-	blkdev_put(bdev, mode);
-	return 0;
+		ret =  PTR_ERR(bdev);
+	else
+		blkdev_put(bdev, mode);
+
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(disk->part0, disk_scan_partitions);
+	return ret;
 }
 
 /**
@@ -497,9 +511,14 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 		if (ret)
 			goto out_unregister_bdi;
 
+		/* Make sure the first partition scan will be proceed */
+		if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) &&
+		    !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+			set_bit(GD_NEED_PART_SCAN, &disk->state);
+
 		bdev_add(disk->part0, ddev->devt);
 		if (get_capacity(disk))
-			disk_scan_partitions(disk, FMODE_READ, NULL);
+			disk_scan_partitions(disk, FMODE_READ);
 
 		/*
 		 * Announce the disk and partitions after all partitions are
diff --git a/block/ioctl.c b/block/ioctl.c
index 96617512982e..9c5f637ff153 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -467,10 +467,10 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
  * user space. Note the separate arg/argp parameters that are needed
  * to deal with the compat_ptr() conversion.
  */
-static int blkdev_common_ioctl(struct file *file, fmode_t mode, unsigned cmd,
-			       unsigned long arg, void __user *argp)
+static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
+			       unsigned int cmd, unsigned long arg,
+			       void __user *argp)
 {
-	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	unsigned int max_sectors;
 
 	switch (cmd) {
@@ -528,8 +528,7 @@ static int blkdev_common_ioctl(struct file *file, fmode_t mode, unsigned cmd,
 			return -EACCES;
 		if (bdev_is_partition(bdev))
 			return -EINVAL;
-		return disk_scan_partitions(bdev->bd_disk, mode & ~FMODE_EXCL,
-					    file);
+		return disk_scan_partitions(bdev->bd_disk, mode);
 	case BLKTRACESTART:
 	case BLKTRACESTOP:
 	case BLKTRACETEARDOWN:
@@ -607,7 +606,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		break;
 	}
 
-	ret = blkdev_common_ioctl(file, mode, cmd, arg, argp);
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
 	if (ret != -ENOIOCTLCMD)
 		return ret;
 
@@ -676,7 +675,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		break;
 	}
 
-	ret = blkdev_common_ioctl(file, mode, cmd, arg, argp);
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
 	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
 		ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
 
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 463873f61e01..c320093c14f1 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -487,6 +487,8 @@ static int opal_discovery0_end(struct opal_dev *dev)
 			break;
 		case FC_SINGLEUSER:
 			single_user = check_sum(body->features);
+			if (single_user)
+				dev->flags |= OPAL_FL_SUM_SUPPORTED;
 			break;
 		case FC_GEOMETRY:
 			check_geometry(dev, body);