In commit
e05491b3, I tried to resolve false test failures that were
a result of device mapper refusing to change access modes on a block
device that supports the FSDAX access mode. Unfortunately, I did
not realize that there are two ways that fsdax support can be
detected via sysfs: /sys/block/XXX/queue/dax and /sys/block/XXX/dax/,
so I only added a test for the latter.
As of 5.15-rc1 this doesn't seem to work anymore for some reason. I
don't know enough about the byzantine world of pmem device driver
initialization, but fsdax mode actually does work even though the
/sys/block/XXX/dax/ path went away. So clearly we have to detect it
via the other sysfs path.
Fixes: e05491b3 ("common/rc: fix detection of device-mapper/persistent memory incompatibility")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
fi
}
+# Decide if the scratch filesystem is likely to be mounted in fsdax mode.
+# If there's a dax clause in the mount options we assume the test runner
+# wants us to test DAX; or if the scratch device itself advertises dax mode
+# in sysfs.
+__detect_scratch_fsdax()
+{
+ _normalize_mount_options | egrep -q "dax(=always| |$)" && return 0
+
+ local sysfs="/sys/block/$(_short_dev $SCRATCH_DEV)"
+ test -e "${sysfs}/dax" && return 0
+ test "$(cat "${sysfs}/queue/dax" 2>/dev/null)" = "1" && return 0
+ return 1
+}
+
# this test requires a specific device mapper target
_require_dm_target()
{
_require_sane_bdev_flush $SCRATCH_DEV
_require_command "$DMSETUP_PROG" dmsetup
- _normalize_mount_options | egrep -q "dax(=always| |$)" || \
- test -e "/sys/block/$(_short_dev $SCRATCH_DEV)/dax"
- if [ $? -eq 0 ]; then
+ if __detect_scratch_fsdax; then
case $target in
stripe|linear|log-writes)
;;