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, 315 insertions, 0 deletions

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
new file mode 100755
index 000000000..ab0b8125c
--- /dev/null
+++ b/scripts/link-vmlinux.sh
@@ -0,0 +1,315 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# link vmlinux
+#
+# vmlinux is linked from the objects in vmlinux.a and $(KBUILD_VMLINUX_LIBS).
+# vmlinux.a contains objects that are linked unconditionally.
+# $(KBUILD_VMLINUX_LIBS) are archives which are linked conditionally
+# (not within --whole-archive), and do not require symbol indexes added.
+#
+# vmlinux
+#   ^
+#   |
+#   +--< vmlinux.a
+#   |
+#   +--< $(KBUILD_VMLINUX_LIBS)
+#   |    +--< lib/lib.a + more
+#   |
+#   +-< ${kallsymso} (see description in KALLSYMS section)
+#
+# vmlinux version (uname -v) cannot be updated during normal
+# descending-into-subdirs phase since we do not yet know if we need to
+# update vmlinux.
+# Therefore this step is delayed until just before final link of vmlinux.
+#
+# System.map is generated to document addresses of all kernel symbols
+
+# Error out on error
+set -e
+
+LD="$1"
+KBUILD_LDFLAGS="$2"
+LDFLAGS_vmlinux="$3"
+VMLINUX="$4"
+
+is_enabled() {
+	grep -q "^$1=y" include/config/auto.conf
+}
+
+# Nice output in kbuild format
+# Will be suppressed by "make -s"
+info()
+{
+	printf "  %-7s %s\n" "${1}" "${2}"
+}
+
+# Link of vmlinux
+# ${1} - output file
+vmlinux_link()
+{
+	local output=${1}
+	local objs
+	local libs
+	local ld
+	local ldflags
+	local ldlibs
+
+	info LD ${output}
+
+	# skip output file argument
+	shift
+
+	if is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT ||
+	   is_enabled CONFIG_KLP_BUILD; then
+		# Use vmlinux.o instead of performing the slow LTO link again.
+		objs=vmlinux.o
+		libs=
+	else
+		objs=vmlinux.a
+		libs="${KBUILD_VMLINUX_LIBS}"
+	fi
+
+	if is_enabled CONFIG_GENERIC_BUILTIN_DTB; then
+		objs="${objs} .builtin-dtbs.o"
+	fi
+
+	objs="${objs} .vmlinux.export.o"
+	objs="${objs} init/version-timestamp.o"
+
+	if [ "${SRCARCH}" = "um" ]; then
+		wl=-Wl,
+		ld="${CC}"
+		ldflags="${CFLAGS_vmlinux}"
+		ldlibs="-lutil -lrt -lpthread"
+	else
+		wl=
+		ld="${LD}"
+		ldflags="${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux}"
+		ldlibs=
+	fi
+
+	ldflags="${ldflags} ${wl}--script=${objtree}/${KBUILD_LDS}"
+
+	# The kallsyms linking does not need debug symbols included.
+	if [ -n "${strip_debug}" ] ; then
+		ldflags="${ldflags} ${wl}--strip-debug"
+	fi
+
+	if [ -n "${generate_map}" ];  then
+		ldflags="${ldflags} ${wl}-Map=vmlinux.map"
+	fi
+
+	${ld} ${ldflags} -o ${output}					\
+		${wl}--whole-archive ${objs} ${wl}--no-whole-archive	\
+		${wl}--start-group ${libs} ${wl}--end-group		\
+		${kallsymso} ${btf_vmlinux_bin_o} ${arch_vmlinux_o} ${ldlibs}
+}
+
+# Check if kallsymso_prev and kallsymso differ
+# If symbol sizes within ${kallsymso} change, any symbols within vmlinux are
+# likely to shift, invalidating ${kallsymso}.
+# Since file size can remain unchanged even if symbol sizes change, compare the
+# actual symbols instead of relying on file size only.
+kallsymso_changed()
+{
+	${NM} -n "${kallsymso_prev}" > "${kallsymso_prev}.sym"
+	${NM} -n "${kallsymso}" > "${kallsymso}.sym"
+	! cmp -s "${kallsymso_prev}.sym" "${kallsymso}.sym"
+}
+
+# Create ${2}.o file with all symbols from the ${1} object file
+kallsyms()
+{
+	local kallsymopt;
+
+	if is_enabled CONFIG_KALLSYMS_ALL; then
+		kallsymopt="${kallsymopt} --all-symbols"
+	fi
+
+	if is_enabled CONFIG_64BIT || is_enabled CONFIG_RELOCATABLE; then
+		kallsymopt="${kallsymopt} --pc-relative"
+	fi
+
+	info KSYMS "${2}.S"
+	scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
+
+	info AS "${2}.o"
+	${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
+	      ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} -c -o "${2}.o" "${2}.S"
+
+	kallsymso_prev="${kallsymso:-}"
+	kallsymso=${2}.o
+}
+
+# Perform kallsyms for the given temporary vmlinux.
+sysmap_and_kallsyms()
+{
+	mksysmap "${1}" "${1}.syms"
+	kallsyms "${1}.syms" "${1}.kallsyms"
+
+	kallsyms_sysmap=${1}.syms
+}
+
+# Create map file with all symbols from ${1}
+# See mksymap for additional details
+mksysmap()
+{
+	info NM ${2}
+	${NM} -n "${1}" | sed -f "${srctree}/scripts/mksysmap" > "${2}"
+}
+
+sorttable()
+{
+	${NM} -S ${1} > .tmp_vmlinux.nm-sort
+	${objtree}/scripts/sorttable -s .tmp_vmlinux.nm-sort ${1}
+}
+
+cleanup()
+{
+	rm -f .btf.*
+	rm -f .tmp_vmlinux.nm-sort
+	rm -f System.map
+	rm -f vmlinux
+	rm -f vmlinux.map
+}
+
+# Use "make V=1" to debug this script
+case "${KBUILD_VERBOSE}" in
+*1*)
+	set -x
+	;;
+esac
+
+if [ "$1" = "clean" ]; then
+	cleanup
+	exit 0
+fi
+
+${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init init/version-timestamp.o
+
+arch_vmlinux_o=
+if is_enabled CONFIG_ARCH_WANTS_PRE_LINK_VMLINUX; then
+	arch_vmlinux_o=arch/${SRCARCH}/tools/vmlinux.arch.o
+fi
+
+btf_vmlinux_bin_o=
+btfids_vmlinux=
+kallsymso=
+strip_debug=
+generate_map=
+
+# Use "make UT=1" to trigger warnings on unused tracepoints
+case "${WARN_ON_UNUSED_TRACEPOINTS}" in
+*1*)
+	${objtree}/scripts/tracepoint-update vmlinux.o
+	;;
+esac
+
+if is_enabled CONFIG_KALLSYMS; then
+	true > .tmp_vmlinux0.syms
+	kallsyms .tmp_vmlinux0.syms .tmp_vmlinux0.kallsyms
+fi
+
+if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
+
+	# The kallsyms linking does not need debug symbols, but the BTF does.
+	if ! is_enabled CONFIG_DEBUG_INFO_BTF; then
+		strip_debug=1
+	fi
+
+	vmlinux_link .tmp_vmlinux1
+fi
+
+if is_enabled CONFIG_DEBUG_INFO_BTF; then
+	info BTF .tmp_vmlinux1
+	if ! ${CONFIG_SHELL} ${srctree}/scripts/gen-btf.sh .tmp_vmlinux1; then
+		echo >&2 "Failed to generate BTF for vmlinux"
+		echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF"
+		exit 1
+	fi
+	btf_vmlinux_bin_o=.tmp_vmlinux1.btf.o
+	btfids_vmlinux=.tmp_vmlinux1.BTF_ids
+fi
+
+if is_enabled CONFIG_KALLSYMS; then
+
+	# kallsyms support
+	# Generate section listing all symbols and add it into vmlinux
+	# It's a four step process:
+	# 0)  Generate a dummy __kallsyms with empty symbol list.
+	# 1)  Link .tmp_vmlinux1.kallsyms so it has all symbols and sections,
+	#     with a dummy __kallsyms.
+	#     Running kallsyms on that gives us .tmp_vmlinux1.kallsyms.o with
+	#     the right size
+	# 2)  Link .tmp_vmlinux2.kallsyms so it now has a __kallsyms section of
+	#     the right size, but due to the added section, some
+	#     addresses have shifted.
+	#     From here, we generate a correct .tmp_vmlinux2.kallsyms.o
+	# 3)  That link may have expanded the kernel image enough that
+	#     more linker branch stubs / trampolines had to be added, which
+	#     introduces new names, which further expands kallsyms. Do another
+	#     pass if that is the case. In theory it's possible this results
+	#     in even more stubs, but unlikely.
+	#     KALLSYMS_EXTRA_PASS=1 may also used to debug or work around
+	#     other bugs.
+	# 4)  The correct ${kallsymso} is linked into the final vmlinux.
+	#
+	# a)  Verify that the System.map from vmlinux matches the map from
+	#     ${kallsymso}.
+
+	# The kallsyms linking does not need debug symbols included.
+	strip_debug=1
+
+	sysmap_and_kallsyms .tmp_vmlinux1
+	size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+	vmlinux_link .tmp_vmlinux2
+	sysmap_and_kallsyms .tmp_vmlinux2
+	size2=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+	# Due to alignment, file size of the kallsymso object file might remain
+	# unchanged even if individual symbols within change size. Changed
+	# symbol sizes can still shift other symbols, though. Therefore, don't
+	# rely on file size alone.
+	if [ $size1 -ne $size2 ] || kallsymso_changed || \
+			[ -n "${KALLSYMS_EXTRA_PASS}" ]; then
+		vmlinux_link .tmp_vmlinux3
+		sysmap_and_kallsyms .tmp_vmlinux3
+	fi
+fi
+
+strip_debug=
+
+if is_enabled CONFIG_VMLINUX_MAP; then
+	generate_map=1
+fi
+
+vmlinux_link "${VMLINUX}"
+
+if is_enabled CONFIG_DEBUG_INFO_BTF; then
+	info BTFIDS ${VMLINUX}
+	${RESOLVE_BTFIDS} --patch_btfids ${btfids_vmlinux} ${VMLINUX}
+fi
+
+mksysmap "${VMLINUX}" System.map
+
+if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then
+	info SORTTAB "${VMLINUX}"
+	if ! sorttable "${VMLINUX}"; then
+		echo >&2 Failed to sort kernel tables
+		exit 1
+	fi
+fi
+
+# step a (see comment above)
+if is_enabled CONFIG_KALLSYMS; then
+	if ! cmp -s System.map "${kallsyms_sysmap}"; then
+		echo >&2 Inconsistent kallsyms data
+		echo >&2 'Try "make KALLSYMS_EXTRA_PASS=1" as a workaround'
+		exit 1
+	fi
+fi
+
+# For fixdep
+echo "${VMLINUX}: $0" > ".${VMLINUX}.d"