Merge tag 'block-6.16-20250614' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - Fix for a deadlock on queue freeze with zoned writes

 - Fix for zoned append emulation

 - Two bio folio fixes, for sparsemem and for very large folios

 - Fix for a performance regression introduced in 6.13 when plug
   insertion was changed

 - Fix for NVMe passthrough handling for polled IO

 - Document the ublk auto registration feature

 - loop lockdep warning fix

* tag 'block-6.16-20250614' of git://git.kernel.dk/linux:
  nvme: always punt polled uring_cmd end_io work to task_work
  Documentation: ublk: Separate UBLK_F_AUTO_BUF_REG fallback behavior sublists
  block: Fix bvec_set_folio() for very large folios
  bio: Fix bio_first_folio() for SPARSEMEM without VMEMMAP
  block: use plug request list tail for one-shot backmerge attempt
  block: don't use submit_bio_noacct_nocheck in blk_zone_wplug_bio_work
  block: Clear BIO_EMULATES_ZONE_APPEND flag on BIO completion
  ublk: document auto buffer registration(UBLK_F_AUTO_BUF_REG)
  loop: move lo_set_size() out of queue freeze

2 files changed, 12 insertions, 20 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f8d136684109..500840e4a74e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1248,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
 	lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS);
 
-	if (size_changed) {
-		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
-					   lo->lo_backing_file);
-		loop_set_size(lo, new_size);
-	}
-
 	/* update the direct I/O flag if lo_offset changed */
 	loop_update_dio(lo);
 
@@ -1261,6 +1255,11 @@ out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
+	if (!err && size_changed) {
+		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+					   lo->lo_backing_file);
+		loop_set_size(lo, new_size);
+	}
 out_unlock:
 	mutex_unlock(&lo->lo_mutex);
 	if (partscan)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 0b50da2f1175..6b3ac8ae3f34 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly. Note that using the uring_cmd
-	 * helper for this is safe only because we check blk_rq_is_poll().
-	 * As that returns false if we're NOT on a polled queue, then it's
-	 * safe to use the polled completion helper.
-	 *
-	 * Otherwise, move the completion to task work.
+	 * IOPOLL could potentially complete this request directly, but
+	 * if multiple rings are polling on the same queue, then it's possible
+	 * for one ring to find completions for another ring. Punting the
+	 * completion via task_work will always direct it to the right
+	 * location, rather than potentially complete requests for ringA
+	 * under iopoll invocations from ringB.
 	 */
-	if (blk_rq_is_poll(req)) {
-		if (pdu->bio)
-			blk_rq_unmap_user(pdu->bio);
-		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
-
+	io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 	return RQ_END_IO_FREE;
 }