Merge tag 'block-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block fixes from Jens Axboe:

 - A set of selftest fixes for ublk

 - Fix for a pid mismatch in ublk, comparing PIDs in different
   namespaces if run inside a namespace

 - Fix for a regression added in this release with polling, where the
   nvme tcp connect code would spin forever

 - Zoned device error path fix

 - Tweak the blkzoned uapi additions from this kernel release, making
   them more easily discoverable

 - Fix for a regression in bcache with bio endio handling added in this
   release

* tag 'block-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  bcache: use bio cloning for detached device requests
  blk-mq: use BLK_POLL_ONESHOT for synchronous poll completion
  selftests/ublk: fix garbage output in foreground mode
  selftests/ublk: fix error handling for starting device
  selftests/ublk: fix IO thread idle check
  block: make the new blkzoned UAPI constants discoverable
  ublk: fix ublksrv pid handling for pid namespaces
  block: Fix an error path in disk_update_zone_resources()

Author: torvalds

block/blk-mq.c

@@ -1480,7 +1480,7 @@ EXPORT_SYMBOL_GPL(blk_rq_is_poll);
 static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
 {
 	do {
-		blk_hctx_poll(rq->q, rq->mq_hctx, NULL, 0);
+		blk_hctx_poll(rq->q, rq->mq_hctx, NULL, BLK_POLL_ONESHOT);
 		cond_resched();
 	} while (!completion_done(wait));
 }

block/blk-zoned.c

@@ -1957,6 +1957,7 @@ static int disk_update_zone_resources(struct gendisk *disk,
 
 	disk->nr_zones = args->nr_zones;
 	if (args->nr_conv_zones >= disk->nr_zones) {
+		queue_limits_cancel_update(q);
 		pr_warn("%s: Invalid number of conventional zones %u / %u\n",
 			disk->disk_name, args->nr_conv_zones, disk->nr_zones);
 		ret = -ENODEV;

drivers/block/ublk_drv.c

@@ -2885,6 +2885,15 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
 	return ub;
 }
 
+static bool ublk_validate_user_pid(struct ublk_device *ub, pid_t ublksrv_pid)
+{
+	rcu_read_lock();
+	ublksrv_pid = pid_nr(find_vpid(ublksrv_pid));
+	rcu_read_unlock();
+
+	return ub->ublksrv_tgid == ublksrv_pid;
+}
+
 static int ublk_ctrl_start_dev(struct ublk_device *ub,
 		const struct ublksrv_ctrl_cmd *header)
 {
@@ -2953,7 +2962,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
 
-	if (ub->ublksrv_tgid != ublksrv_pid)
+	if (!ublk_validate_user_pid(ub, ublksrv_pid))
 		return -EINVAL;
 
 	mutex_lock(&ub->mutex);
@@ -2972,7 +2981,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 	disk->fops = &ub_fops;
 	disk->private_data = ub;
 
-	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	ub->dev_info.ublksrv_pid = ub->ublksrv_tgid;
 	ub->ub_disk = disk;
 
 	ublk_apply_params(ub);
@@ -3320,12 +3329,32 @@ static int ublk_ctrl_stop_dev(struct ublk_device *ub)
 static int ublk_ctrl_get_dev_info(struct ublk_device *ub,
 		const struct ublksrv_ctrl_cmd *header)
 {
+	struct task_struct *p;
+	struct pid *pid;
+	struct ublksrv_ctrl_dev_info dev_info;
+	pid_t init_ublksrv_tgid = ub->dev_info.ublksrv_pid;
 	void __user *argp = (void __user *)(unsigned long)header->addr;
 
 	if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr)
 		return -EINVAL;
 
-	if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info)))
+	memcpy(&dev_info, &ub->dev_info, sizeof(dev_info));
+	dev_info.ublksrv_pid = -1;
+
+	if (init_ublksrv_tgid > 0) {
+		rcu_read_lock();
+		pid = find_pid_ns(init_ublksrv_tgid, &init_pid_ns);
+		p = pid_task(pid, PIDTYPE_TGID);
+		if (p) {
+			int vnr = task_tgid_vnr(p);
+
+			if (vnr)
+				dev_info.ublksrv_pid = vnr;
+		}
+		rcu_read_unlock();
+	}
+
+	if (copy_to_user(argp, &dev_info, sizeof(dev_info)))
 		return -EFAULT;
 
 	return 0;
@@ -3470,7 +3499,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	pr_devel("%s: All FETCH_REQs received, dev id %d\n", __func__,
 		 header->dev_id);
 
-	if (ub->ublksrv_tgid != ublksrv_pid)
+	if (!ublk_validate_user_pid(ub, ublksrv_pid))
 		return -EINVAL;
 
 	mutex_lock(&ub->mutex);
@@ -3481,7 +3510,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	ub->dev_info.ublksrv_pid = ub->ublksrv_tgid;
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
 	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
 			__func__, ublksrv_pid, header->dev_id);

drivers/md/bcache/bcache.h

@@ -273,6 +273,8 @@ struct bcache_device {
 
 	struct bio_set		bio_split;
 
+	struct bio_set		bio_detached;
+
 	unsigned int		data_csum:1;
 
 	int (*cache_miss)(struct btree *b, struct search *s,
@@ -753,6 +755,13 @@ struct bbio {
 	struct bio		bio;
 };
 
+struct detached_dev_io_private {
+	struct bcache_device	*d;
+	unsigned long		start_time;
+	struct bio		*orig_bio;
+	struct bio              bio;
+};
+
 #define BTREE_PRIO		USHRT_MAX
 #define INITIAL_PRIO		32768U
 

drivers/md/bcache/request.c

@@ -1077,68 +1077,58 @@ static CLOSURE_CALLBACK(cached_dev_nodata)
 	continue_at(cl, cached_dev_bio_complete, NULL);
 }
 
-struct detached_dev_io_private {
-	struct bcache_device	*d;
-	unsigned long		start_time;
-	bio_end_io_t		*bi_end_io;
-	void			*bi_private;
-	struct block_device	*orig_bdev;
-};
-
 static void detached_dev_end_io(struct bio *bio)
 {
-	struct detached_dev_io_private *ddip;
-
-	ddip = bio->bi_private;
-	bio->bi_end_io = ddip->bi_end_io;
-	bio->bi_private = ddip->bi_private;
+	struct detached_dev_io_private *ddip =
+		container_of(bio, struct detached_dev_io_private, bio);
+	struct bio *orig_bio = ddip->orig_bio;
 
 	/* Count on the bcache device */
-	bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev);
+	bio_end_io_acct(orig_bio, ddip->start_time);
 
 	if (bio->bi_status) {
-		struct cached_dev *dc = container_of(ddip->d,
-						     struct cached_dev, disk);
+		struct cached_dev *dc = bio->bi_private;
+
 		/* should count I/O error for backing device here */
 		bch_count_backing_io_errors(dc, bio);
+		orig_bio->bi_status = bio->bi_status;
 	}
 
-	kfree(ddip);
-	bio_endio(bio);
+	bio_put(bio);
+	bio_endio(orig_bio);
 }
 
-static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
-		struct block_device *orig_bdev, unsigned long start_time)
+static void detached_dev_do_request(struct bcache_device *d,
+		struct bio *orig_bio, unsigned long start_time)
 {
 	struct detached_dev_io_private *ddip;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	struct bio *clone_bio;
 
-	/*
-	 * no need to call closure_get(&dc->disk.cl),
-	 * because upper layer had already opened bcache device,
-	 * which would call closure_get(&dc->disk.cl)
-	 */
-	ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
-	if (!ddip) {
-		bio->bi_status = BLK_STS_RESOURCE;
-		bio_endio(bio);
+	if (bio_op(orig_bio) == REQ_OP_DISCARD &&
+	    !bdev_max_discard_sectors(dc->bdev)) {
+		bio_endio(orig_bio);
 		return;
 	}
 
-	ddip->d = d;
+	clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO,
+				    &d->bio_detached);
+	if (!clone_bio) {
+		orig_bio->bi_status = BLK_STS_RESOURCE;
+		bio_endio(orig_bio);
+		return;
+	}
+
+	ddip = container_of(clone_bio, struct detached_dev_io_private, bio);
 	/* Count on the bcache device */
-	ddip->orig_bdev = orig_bdev;
+	ddip->d = d;
 	ddip->start_time = start_time;
-	ddip->bi_end_io = bio->bi_end_io;
-	ddip->bi_private = bio->bi_private;
-	bio->bi_end_io = detached_dev_end_io;
-	bio->bi_private = ddip;
-
-	if ((bio_op(bio) == REQ_OP_DISCARD) &&
-	    !bdev_max_discard_sectors(dc->bdev))
-		detached_dev_end_io(bio);
-	else
-		submit_bio_noacct(bio);
+	ddip->orig_bio = orig_bio;
+
+	clone_bio->bi_end_io = detached_dev_end_io;
+	clone_bio->bi_private = dc;
+
+	submit_bio_noacct(clone_bio);
 }
 
 static void quit_max_writeback_rate(struct cache_set *c,
@@ -1214,10 +1204,10 @@ void cached_dev_submit_bio(struct bio *bio)
 
 	start_time = bio_start_io_acct(bio);
 
-	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
 
 	if (cached_dev_get(dc)) {
+		bio_set_dev(bio, dc->bdev);
 		s = search_alloc(bio, d, orig_bdev, start_time);
 		trace_bcache_request_start(s->d, bio);
 
@@ -1237,9 +1227,10 @@ void cached_dev_submit_bio(struct bio *bio)
 			else
 				cached_dev_read(dc, s);
 		}
-	} else
+	} else {
 		/* I/O request sent to backing device */
-		detached_dev_do_request(d, bio, orig_bdev, start_time);
+		detached_dev_do_request(d, bio, start_time);
+	}
 }
 
 static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode,

drivers/md/bcache/super.c

@@ -887,6 +887,7 @@ static void bcache_device_free(struct bcache_device *d)
 	}
 
 	bioset_exit(&d->bio_split);
+	bioset_exit(&d->bio_detached);
 	kvfree(d->full_dirty_stripes);
 	kvfree(d->stripe_sectors_dirty);
 
@@ -949,6 +950,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto out_ida_remove;
 
+	if (bioset_init(&d->bio_detached, 4,
+			offsetof(struct detached_dev_io_private, bio),
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+		goto out_bioset_split_exit;
+
 	if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
 		/*
 		 * This should only happen with BCACHE_SB_VERSION_BDEV.
@@ -964,7 +970,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
 	if (IS_ERR(d->disk))
-		goto out_bioset_exit;
+		goto out_bioset_detach_exit;
 
 	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -976,7 +982,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	d->disk->private_data	= d;
 	return 0;
 
-out_bioset_exit:
+out_bioset_detach_exit:
+	bioset_exit(&d->bio_detached);
+out_bioset_split_exit:
 	bioset_exit(&d->bio_split);
 out_ida_remove:
 	ida_free(&bcache_device_idx, idx);

include/uapi/linux/blkzoned.h

@@ -81,7 +81,8 @@ enum blk_zone_cond {
 	BLK_ZONE_COND_FULL	= 0xE,
 	BLK_ZONE_COND_OFFLINE	= 0xF,
 
-	BLK_ZONE_COND_ACTIVE	= 0xFF,
+	BLK_ZONE_COND_ACTIVE	= 0xFF, /* added in Linux 6.19 */
+#define BLK_ZONE_COND_ACTIVE	BLK_ZONE_COND_ACTIVE
 };
 
 /**
@@ -100,7 +101,8 @@ enum blk_zone_report_flags {
 	BLK_ZONE_REP_CAPACITY	= (1U << 0),
 
 	/* Input flags */
-	BLK_ZONE_REP_CACHED	= (1U << 31),
+	BLK_ZONE_REP_CACHED	= (1U << 31), /* added in Linux 6.19 */
+#define BLK_ZONE_REP_CACHED	BLK_ZONE_REP_CACHED
 };
 
 /**

tools/testing/selftests/ublk/kublk.c

@@ -753,7 +753,7 @@ static int ublk_thread_is_idle(struct ublk_thread *t)
 
 static int ublk_thread_is_done(struct ublk_thread *t)
 {
-	return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t);
+	return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t) && !t->cmd_inflight;
 }
 
 static inline void ublksrv_handle_tgt_cqe(struct ublk_thread *t,
@@ -1054,15 +1054,17 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 	}
 	if (ret < 0) {
 		ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
-		goto fail;
+		/* stop device so that inflight uring_cmd can be cancelled */
+		ublk_ctrl_stop_dev(dev);
+		goto fail_start;
 	}
 
 	ublk_ctrl_get_info(dev);
 	if (ctx->fg)
 		ublk_ctrl_dump(dev);
 	else
 		ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
-
+fail_start:
 	/* wait until we are terminated */
 	for (i = 0; i < dev->nthreads; i++)
 		pthread_join(tinfo[i].thread, &thread_ret);
@@ -1272,7 +1274,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 	}
 
 	ret = ublk_start_daemon(ctx, dev);
-	ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\b", ret);
+	ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret);
 	if (ret < 0)
 		ublk_ctrl_del_dev(dev);
 
@@ -1618,6 +1620,7 @@ int main(int argc, char *argv[])
 	int option_idx, opt;
 	const char *cmd = argv[1];
 	struct dev_ctx ctx = {
+		._evtfd         =       -1,
 		.queue_depth	=	128,
 		.nr_hw_queues	=	2,
 		.dev_id		=	-1,