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, 212 insertions, 0 deletions

diff --git a/scripts/setlocalversion b/scripts/setlocalversion
new file mode 100755
index 000000000..28169d7e1
--- /dev/null
+++ b/scripts/setlocalversion
@@ -0,0 +1,212 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# This scripts adds local version information from the version
+# control system git.
+#
+# If something goes wrong, send a mail the kernel build mailinglist
+# (see MAINTAINERS) and CC Nico Schottelius
+# <nico-linuxsetlocalversion -at- schottelius.org>.
+#
+#
+
+set -e
+
+usage() {
+	echo "Usage: $0 [--no-local] [srctree]" >&2
+	exit 1
+}
+
+no_local=false
+if test "$1" = "--no-local"; then
+	no_local=true
+	shift
+fi
+
+srctree=.
+if test $# -gt 0; then
+	srctree=$1
+	shift
+fi
+if test $# -gt 0 -o ! -d "$srctree"; then
+	usage
+fi
+
+try_tag() {
+	tag="$1"
+
+	# Is $tag an annotated tag?
+	if [ "$(git cat-file -t "$tag" 2> /dev/null)" != tag ]; then
+		 return
+	fi
+
+	# Is it an ancestor of HEAD, and if so, how many commits are in $tag..HEAD?
+	# shellcheck disable=SC2046 # word splitting is the point here
+	set -- $(git rev-list --count --left-right "$tag"...HEAD 2> /dev/null)
+
+	# $1 is 0 if and only if $tag is an ancestor of HEAD. Use
+	# string comparison, because $1 is empty if the 'git rev-list'
+	# command somehow failed.
+	if [ "$1" != 0 ]; then
+		return
+	fi
+
+	# $2 is the number of commits in the range $tag..HEAD, possibly 0.
+	count="$2"
+}
+
+scm_version()
+{
+	local short=false
+	local no_dirty=false
+	local tag
+
+	while [ $# -gt 0 ];
+	do
+		case "$1" in
+		--short)
+			short=true;;
+		--no-dirty)
+			no_dirty=true;;
+		esac
+		shift
+	done
+
+	cd "$srctree"
+
+	if test -n "$(git rev-parse --show-cdup 2>/dev/null)"; then
+		return
+	fi
+
+	if ! head=$(git rev-parse --verify HEAD 2>/dev/null); then
+		return
+	fi
+
+	# mainline kernel:  6.2.0-rc5  ->  v6.2-rc5
+	# stable kernel:    6.1.7      ->  v6.1.7
+	version_tag=v$(echo "${KERNELVERSION}" | sed -E 's/^([0-9]+\.[0-9]+)\.0(.*)$/\1\2/')
+
+	# try_tag initializes count if the tag is usable.
+	count=
+
+	# If a localversion* file exists, and the corresponding
+	# annotated tag exists and is an ancestor of HEAD, use
+	# it. This is the case in linux-next.
+	if [ -n "${file_localversion#-}" ] ; then
+		try_tag "${file_localversion#-}"
+	fi
+
+	# Otherwise, if a localversion* file exists, and the tag
+	# obtained by appending it to the tag derived from
+	# KERNELVERSION exists and is an ancestor of HEAD, use
+	# it. This is e.g. the case in linux-rt.
+	if [ -z "${count}" ] && [ -n "${file_localversion}" ]; then
+		try_tag "${version_tag}${file_localversion}"
+	fi
+
+	# Otherwise, default to the annotated tag derived from KERNELVERSION.
+	if [ -z "${count}" ]; then
+		try_tag "${version_tag}"
+	fi
+
+	# If we are at the tagged commit, we ignore it because the
+	# version is well-defined. If none of the attempted tags exist
+	# or were usable, $count is still empty.
+	if [ -z "${count}" ] || [ "${count}" -gt 0 ]; then
+
+		# If only the short version is requested, don't bother
+		# running further git commands
+		if $short; then
+			echo "+"
+			return
+		fi
+
+		# If we are past the tagged commit, we pretty print it.
+		# (like 6.1.0-14595-g292a089d78d3)
+		if [ -n "${count}" ]; then
+			printf "%s%05d" "-" "${count}"
+		fi
+
+		# Add -g and exactly 12 hex chars.
+		printf '%s%.12s' -g "$head"
+	fi
+
+	if ${no_dirty}; then
+		return
+	fi
+
+	# Check for uncommitted changes.
+	# This script must avoid any write attempt to the source tree, which
+	# might be read-only.
+	# You cannot use 'git describe --dirty' because it tries to create
+	# .git/index.lock .
+	# First, with git-status, but --no-optional-locks is only supported in
+	# git >= 2.14, so fall back to git-diff-index if it fails. Note that
+	# git-diff-index does not refresh the index, so it may give misleading
+	# results.
+	# See git-update-index(1), git-diff-index(1), and git-status(1).
+	if {
+		git --no-optional-locks status -uno --porcelain 2>/dev/null ||
+		git diff-index --name-only HEAD
+	} | read dummy; then
+		printf '%s' -dirty
+	fi
+}
+
+collect_files()
+{
+	local file res=
+
+	for file; do
+		case "$file" in
+		*\~*)
+			continue
+			;;
+		esac
+		if test -e "$file"; then
+			res="$res$(cat "$file")"
+		fi
+	done
+	echo "$res"
+}
+
+if [ -z "${KERNELVERSION}" ]; then
+	echo "KERNELVERSION is not set" >&2
+	exit 1
+fi
+
+# localversion* files in the build and source directory
+file_localversion="$(collect_files localversion*)"
+if test ! "$srctree" -ef .; then
+	file_localversion="${file_localversion}$(collect_files "$srctree"/localversion*)"
+fi
+
+if ${no_local}; then
+	echo "${KERNELVERSION}$(scm_version --no-dirty)"
+	exit 0
+fi
+
+if ! test -e include/config/auto.conf; then
+	echo "Error: kernelrelease not valid - run 'make prepare' to update it" >&2
+	exit 1
+fi
+
+# version string from CONFIG_LOCALVERSION
+config_localversion=$(sed -n 's/^CONFIG_LOCALVERSION=\(.*\)$/\1/p' include/config/auto.conf)
+
+# scm version string if not at the kernel version tag or at the file_localversion
+if grep -q "^CONFIG_LOCALVERSION_AUTO=y$" include/config/auto.conf; then
+	# full scm version string
+	scm_version="$(scm_version)"
+elif [ "${LOCALVERSION+set}" != "set" ]; then
+	# If the variable LOCALVERSION is not set, append a plus
+	# sign if the repository is not in a clean annotated or
+	# signed tagged state (as git describe only looks at signed
+	# or annotated tags - git tag -a/-s).
+	#
+	# If the variable LOCALVERSION is set (including being set
+	# to an empty string), we don't want to append a plus sign.
+	scm_version="$(scm_version --short)"
+fi
+
+echo "${KERNELVERSION}${file_localversion}${config_localversion}${LOCALVERSION}${scm_version}"