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>

2 files changed, 251 insertions, 0 deletions

diff --git a/tools/debugging/Makefile b/tools/debugging/Makefile
new file mode 100644
index 000000000..e2b7c1a6f
--- /dev/null
+++ b/tools/debugging/Makefile
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for debugging tools
+
+PREFIX ?= /usr
+BINDIR ?= bin
+INSTALL ?= install
+
+TARGET = kernel-chktaint
+
+all: $(TARGET)
+
+clean:
+
+install: kernel-chktaint
+	$(INSTALL) -D -m 755 $(TARGET) $(DESTDIR)$(PREFIX)/$(BINDIR)/$(TARGET)
+
diff --git a/tools/debugging/kernel-chktaint b/tools/debugging/kernel-chktaint
new file mode 100755
index 000000000..e1571c04a
--- /dev/null
+++ b/tools/debugging/kernel-chktaint
@@ -0,0 +1,235 @@
+#! /bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Randy Dunlap <rdunlap@infradead.org>, 2018
+# Thorsten Leemhuis <linux@leemhuis.info>, 2018
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/}
+       ${0##*/} <int>
+
+Call without parameters to decode /proc/sys/kernel/tainted.
+
+Call with a positive integer as parameter to decode a value you
+retrieved from /proc/sys/kernel/tainted on another system.
+
+EOF
+}
+
+if [ "$1"x != "x" ]; then
+	if  [ "$1"x == "--helpx" ] || [ "$1"x == "-hx" ] ; then
+		usage
+		exit 1
+	elif  [ $1 -ge 0 ] 2>/dev/null ; then
+		taint=$1
+	else
+		echo "Error: Parameter '$1' not a positive integer. Aborting." >&2
+		exit 1
+	fi
+else
+	TAINTFILE="/proc/sys/kernel/tainted"
+	if [ ! -r $TAINTFILE ]; then
+		echo "No file: $TAINTFILE"
+		exit
+	fi
+
+	taint=`cat $TAINTFILE`
+fi
+
+if [ $taint -eq 0 ]; then
+	echo "Kernel not Tainted"
+	exit
+else
+	echo "Kernel is \"tainted\" for the following reasons:"
+fi
+
+T=$taint
+out=
+
+addout() {
+	out=$out$1
+}
+
+if [ `expr $T % 2` -eq 0 ]; then
+	addout "G"
+else
+	addout "P"
+	echo " * proprietary module was loaded (#0)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "F"
+	echo " * module was force loaded (#1)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "S"
+	echo " * kernel running on an out of specification system (#2)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "R"
+	echo " * module was force unloaded (#3)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "M"
+	echo " * processor reported a Machine Check Exception (MCE) (#4)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "B"
+	echo " * bad page referenced or some unexpected page flags (#5)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "U"
+	echo " * taint requested by userspace application (#6)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "D"
+	echo " * kernel died recently, i.e. there was an OOPS or BUG (#7)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "A"
+	echo " * an ACPI table was overridden by user (#8)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "W"
+	echo " * kernel issued warning (#9)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "C"
+	echo " * staging driver was loaded (#10)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "I"
+	echo " * workaround for bug in platform firmware applied (#11)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "O"
+	echo " * externally-built ('out-of-tree') module was loaded  (#12)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "E"
+	echo " * unsigned module was loaded (#13)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "L"
+	echo " * soft lockup occurred (#14)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "K"
+	echo " * kernel has been live patched (#15)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "X"
+	echo " * auxiliary taint, defined for and used by distros (#16)"
+
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "T"
+	echo " * kernel was built with the struct randomization plugin (#17)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "N"
+	echo " * an in-kernel test (such as a KUnit test) has been run (#18)"
+fi
+
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "J"
+	echo " * fwctl's mutating debug interface was used (#19)"
+fi
+echo "Raw taint value as int/string: $taint/'$out'"
+
+# report on any tainted loadable modules
+[ "$1" = "" ] && [ -r /sys/module/ ] && \
+	cnt=`grep [A-Z] /sys/module/*/taint | wc -l` || cnt=0
+
+if [ $cnt -ne 0 ]; then
+	echo
+	echo "Tainted modules:"
+	for dir in `ls /sys/module` ; do
+		if [ -r /sys/module/$dir/taint ]; then
+			modtnt=`cat /sys/module/$dir/taint`
+			[ "$modtnt" = "" ] || echo " * $dir ($modtnt)"
+		fi
+	done
+fi
+
+echo
+echo "For a more detailed explanation of the various taint flags see"
+echo " Documentation/admin-guide/tainted-kernels.rst in the Linux kernel sources"
+echo " or https://kernel.org/doc/html/latest/admin-guide/tainted-kernels.html"
+#EOF#