virtio_blk: set the zone write granularitygrafted

virtblk_read_zoned_limits() reads the write granularity that the device
reports in virtio_blk_zoned_characteristics and assigns it to the
physical block size and to io_min, but never to the limit that is named
after it. queue_limits.zone_write_granularity is left at zero, so
blk_validate_zoned_limits() raises it to the logical block size:

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

A device that reports a granularity coarser than its logical block size,
which is what the field exists to express, therefore has it silently
reduced. A 512e host managed disk passed through to a guest reports a
logical block size of 512 and a write granularity of 4096, and the guest
ends up with a zone write granularity of 512.

bio_split_alignment() returns lim->zone_write_granularity if it is non-zero
and bio_split_io_at() may split a bio with as per bio_split_alignment().
This can real to the write getting rejected by the host drive, as the write
is not aligned to the physical block size.

zonefs also takes its block size from bdev_zone_write_granularity(), so it
would incorrectly use 512 on a disk that requires 4096.

sd_zbc_read_zones() sets the limit from the physical block size for the
same reason. NVMe ZNS and null_blk leave it unset, but the fallback
gives the right answer for them, as their write granularity is the
logical block size. virtio carries a separate value that may exceed it.

Set the zone write granularity from the value that the device reports.

Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 308 insertions, 0 deletions

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
new file mode 100644
index 000000000..b375567e0
--- /dev/null
+++ b/fs/netfs/iterator.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Iterator helpers.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/uio.h>
+#include <linux/scatterlist.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/**
+ * netfs_extract_user_iter - Extract the pages from a user iterator into a bvec
+ * @orig: The original iterator
+ * @orig_len: The amount of iterator to copy
+ * @new: The iterator to be set up
+ * @extraction_flags: Flags to qualify the request
+ *
+ * Extract the page fragments from the given amount of the source iterator and
+ * build up a second iterator that refers to all of those bits.  This allows
+ * the original iterator to be disposed of.
+ *
+ * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be
+ * allowed on the pages extracted.
+ *
+ * On success, the number of elements in the bvec is returned, the original
+ * iterator will have been advanced by the amount extracted.
+ *
+ * The iov_iter_extract_mode() function should be used to query how cleanup
+ * should be performed.
+ */
+ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
+				struct iov_iter *new,
+				iov_iter_extraction_t extraction_flags)
+{
+	struct bio_vec *bv = NULL;
+	struct page **pages;
+	unsigned int cur_npages;
+	unsigned int max_pages;
+	unsigned int npages = 0;
+	unsigned int i;
+	ssize_t ret = 0;
+	size_t count = orig_len, offset, len;
+	size_t bv_size, pg_size;
+
+	if (WARN_ON_ONCE(!iter_is_ubuf(orig) && !iter_is_iovec(orig)))
+		return -EIO;
+
+	max_pages = iov_iter_npages(orig, INT_MAX);
+	bv_size = array_size(max_pages, sizeof(*bv));
+	bv = kvmalloc(bv_size, GFP_KERNEL);
+	if (!bv)
+		return -ENOMEM;
+
+	/* Put the page list at the end of the bvec list storage.  bvec
+	 * elements are larger than page pointers, so as long as we work
+	 * 0->last, we should be fine.
+	 */
+	pg_size = array_size(max_pages, sizeof(*pages));
+	pages = (void *)bv + bv_size - pg_size;
+
+	while (count && npages < max_pages) {
+		ret = iov_iter_extract_pages(orig, &pages, count,
+					     max_pages - npages, extraction_flags,
+					     &offset);
+		if (unlikely(ret <= 0)) {
+			ret = ret ?: -EIO;
+			break;
+		}
+
+		if (WARN(ret > count,
+			 "%s: extract_pages overrun %zd > %zu bytes\n",
+			 __func__, ret, count)) {
+			ret = -EIO;
+			break;
+		}
+
+		cur_npages = DIV_ROUND_UP(offset + ret, PAGE_SIZE);
+		if (WARN(cur_npages > max_pages - npages,
+			 "%s: extract_pages overrun %u > %u pages\n",
+			 __func__, npages + cur_npages, max_pages)) {
+			ret = -EIO;
+			break;
+		}
+
+		count -= ret;
+		ret += offset;
+
+		for (i = 0; i < cur_npages; i++) {
+			len = ret > PAGE_SIZE ? PAGE_SIZE : ret;
+			bvec_set_page(bv + npages + i, *pages++, len - offset, offset);
+			ret -= len;
+			offset = 0;
+		}
+
+		npages += cur_npages;
+	}
+
+	/* Note: Don't try to clean up after EIO.  Either we got no pages, so
+	 * nothing to clean up, or we got a buffer overrun, memory corruption
+	 * and can't trust the stuff in the buffer (a WARN was emitted).
+	 */
+
+	if (ret < 0 && (ret == -ENOMEM || npages == 0)) {
+		for (i = 0; i < npages; i++)
+			unpin_user_page(bv[i].bv_page);
+		kvfree(bv);
+		return ret;
+	}
+
+	iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count);
+	return npages;
+}
+EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
+
+/*
+ * Select the span of a bvec iterator we're going to use.  Limit it by both maximum
+ * size and maximum number of segments.  Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct bio_vec *bvecs = iter->bvec;
+	unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_bvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nbv && skip) {
+		len = bvecs[ix].bv_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nbv) {
+		len = min3(n, bvecs[ix].bv_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of a kvec iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  Returns the size of the span
+ * in bytes.
+ */
+static size_t netfs_limit_kvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct kvec *kvecs = iter->kvec;
+	unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_kvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nkv && skip) {
+		len = kvecs[ix].iov_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nkv) {
+		len = min3(n, kvecs[ix].iov_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of an xarray iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  It is assumed that segments
+ * can be larger than a page in size, provided they're physically contiguous.
+ * Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
+				 size_t max_size, size_t max_segs)
+{
+	struct folio *folio;
+	unsigned int nsegs = 0;
+	loff_t pos = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t span = 0, n = iter->count;
+
+	XA_STATE(xas, iter->xarray, index);
+
+	if (WARN_ON(!iov_iter_is_xarray(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+	max_size = min(max_size, n - start_offset);
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		size_t offset, flen, len;
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		flen = folio_size(folio);
+		offset = offset_in_folio(folio, pos);
+		len = min(max_size, flen - offset);
+		span += len;
+		nsegs++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+	}
+
+	rcu_read_unlock();
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of a folio queue iterator we're going to use.  Limit it by
+ * both maximum size and maximum number of segments.  Returns the size of the
+ * span in bytes.
+ */
+static size_t netfs_limit_folioq(const struct iov_iter *iter, size_t start_offset,
+				 size_t max_size, size_t max_segs)
+{
+	const struct folio_queue *folioq = iter->folioq;
+	unsigned int nsegs = 0;
+	unsigned int slot = iter->folioq_slot;
+	size_t span = 0, n = iter->count;
+
+	if (WARN_ON(!iov_iter_is_folioq(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+	max_size = umin(max_size, n - start_offset);
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = folioq->next;
+		slot = 0;
+	}
+
+	start_offset += iter->iov_offset;
+	do {
+		size_t flen = folioq_folio_size(folioq, slot);
+
+		if (start_offset < flen) {
+			span += flen - start_offset;
+			nsegs++;
+			start_offset = 0;
+		} else {
+			start_offset -= flen;
+		}
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+
+		slot++;
+		if (slot >= folioq_nr_slots(folioq)) {
+			folioq = folioq->next;
+			slot = 0;
+		}
+	} while (folioq);
+
+	return umin(span, max_size);
+}
+
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs)
+{
+	if (iov_iter_is_folioq(iter))
+		return netfs_limit_folioq(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_bvec(iter))
+		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_xarray(iter))
+		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_kvec(iter))
+		return netfs_limit_kvec(iter, start_offset, max_size, max_segs);
+	BUG();
+}
+EXPORT_SYMBOL(netfs_limit_iter);