Merge tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
      - Use uring_cmd helper (Pavel)
      - Host Memory Buffer allocation enhancements (Christoph)
      - Target persistent reservation support (Guixin)
      - Persistent reservation tracing (Guixen)
      - NVMe 2.1 specification support (Keith)
      - Rotational Meta Support (Matias, Wang, Keith)
      - Volatile cache detection enhancment (Guixen)

 - MD updates via Song:
      - Maintainers update
      - raid5 sync IO fix
      - Enhance handling of faulty and blocked devices
      - raid5-ppl atomic improvement
      - md-bitmap fix

 - Support for manually defining embedded partition tables

 - Zone append fixes and cleanups

 - Stop sending the queued requests in the plug list to the driver
   ->queue_rqs() handle in reverse order.

 - Zoned write plug cleanups

 - Cleanups disk stats tracking and add support for disk stats for
   passthrough IO

 - Add preparatory support for file system atomic writes

 - Add lockdep support for queue freezing. Already found a bunch of
   issues, and some fixes for that are in here. More will be coming.

 - Fix race between queue stopping/quiescing and IO queueing

 - ublk recovery improvements

 - Fix ublk mmap for 64k pages

 - Various fixes and cleanups

* tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux: (118 commits)
  MAINTAINERS: Update git tree for mdraid subsystem
  block: make struct rq_list available for !CONFIG_BLOCK
  block/genhd: use seq_put_decimal_ull for diskstats decimal values
  block: don't reorder requests in blk_mq_add_to_batch
  block: don't reorder requests in blk_add_rq_to_plug
  block: add a rq_list type
  block: remove rq_list_move
  virtio_blk: reverse request order in virtio_queue_rqs
  nvme-pci: reverse request order in nvme_queue_rqs
  btrfs: validate queue limits
  block: export blk_validate_limits
  nvmet: add tracing of reservation commands
  nvme: parse reservation commands's action and rtype to string
  nvmet: report ns's vwc not present
  md/raid5: Increase r5conf.cache_name size
  block: remove the ioprio field from struct request
  block: remove the write_hint field from struct request
  nvme: check ns's volatile write cache not present
  nvme: add rotational support
  nvme: use command set independent id ns if available
  ...

1 files changed, 46 insertions, 22 deletions

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 908e75a28d90..9ec806f989f2 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1682,8 +1682,8 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i,
 }
 
 /*
- * Extract a list of contiguous pages from an ITER_BVEC iterator.  This does
- * not get references on the pages, nor does it get a pin on them.
+ * Extract a list of virtually contiguous pages from an ITER_BVEC iterator.
+ * This does not get references on the pages, nor does it get a pin on them.
  */
 static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
 					   struct page ***pages, size_t maxsize,
@@ -1691,35 +1691,59 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
 					   iov_iter_extraction_t extraction_flags,
 					   size_t *offset0)
 {
-	struct page **p, *page;
-	size_t skip = i->iov_offset, offset, size;
-	int k;
+	size_t skip = i->iov_offset, size = 0;
+	struct bvec_iter bi;
+	int k = 0;
 
-	for (;;) {
-		if (i->nr_segs == 0)
-			return 0;
-		size = min(maxsize, i->bvec->bv_len - skip);
-		if (size)
-			break;
+	if (i->nr_segs == 0)
+		return 0;
+
+	if (i->iov_offset == i->bvec->bv_len) {
 		i->iov_offset = 0;
 		i->nr_segs--;
 		i->bvec++;
 		skip = 0;
 	}
+	bi.bi_idx = 0;
+	bi.bi_size = maxsize;
+	bi.bi_bvec_done = skip;
+
+	maxpages = want_pages_array(pages, maxsize, skip, maxpages);
+
+	while (bi.bi_size && bi.bi_idx < i->nr_segs) {
+		struct bio_vec bv = bvec_iter_bvec(i->bvec, bi);
+
+		/*
+		 * The iov_iter_extract_pages interface only allows an offset
+		 * into the first page.  Break out of the loop if we see an
+		 * offset into subsequent pages, the caller will have to call
+		 * iov_iter_extract_pages again for the reminder.
+		 */
+		if (k) {
+			if (bv.bv_offset)
+				break;
+		} else {
+			*offset0 = bv.bv_offset;
+		}
 
-	skip += i->bvec->bv_offset;
-	page = i->bvec->bv_page + skip / PAGE_SIZE;
-	offset = skip % PAGE_SIZE;
-	*offset0 = offset;
+		(*pages)[k++] = bv.bv_page;
+		size += bv.bv_len;
 
-	maxpages = want_pages_array(pages, size, offset, maxpages);
-	if (!maxpages)
-		return -ENOMEM;
-	p = *pages;
-	for (k = 0; k < maxpages; k++)
-		p[k] = page + k;
+		if (k >= maxpages)
+			break;
+
+		/*
+		 * We are done when the end of the bvec doesn't align to a page
+		 * boundary as that would create a hole in the returned space.
+		 * The caller will handle this with another call to
+		 * iov_iter_extract_pages.
+		 */
+		if (bv.bv_offset + bv.bv_len != PAGE_SIZE)
+			break;
+
+		bvec_iter_advance_single(i->bvec, &bi, bv.bv_len);
+	}
 
-	size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
 	iov_iter_advance(i, size);
 	return size;
 }