#!/bin/bash
#please run as root
#we need 256M, below is the size in kB
needmem=262144
mnt=./huge
exitcode=0
#get pagesize and freepages from /proc/meminfo
while read name size unit; do
if [ "$name" = "HugePages_Free:" ]; then
freepgs=$size
fi
if [ "$name" = "Hugepagesize:" ]; then
pgsize=$size
fi
done < /proc/meminfo
#set proper nr_hugepages
if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
needpgs=`expr $needmem / $pgsize`
tries=2
while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
lackpgs=$(( $needpgs - $freepgs ))
echo 3 > /proc/sys/vm/drop_caches
echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
if [ $? -ne 0 ]; then
echo "Please run this test as root"
exit 1
fi
while read name size unit; do
if [ "$name" = "HugePages_Free:" ]; then
freepgs=$size
fi
done < /proc/meminfo
tries=$((tries - 1))
done
if [ $freepgs -lt $needpgs ]; then
printf "Not enough huge pages available (%d < %d)\n" \
$freepgs $needpgs
exit 1
fi
else
echo "no hugetlbfs support in kernel?"
exit 1
fi
mkdir $mnt
mount -t hugetlbfs none $mnt
echo "--------------------"
echo "running hugepage-mmap"
echo "--------------------"
./hugepage-mmap
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
shmmax=`cat /proc/sys/kernel/shmmax`
shmall=`cat /proc/sys/kernel/shmall`
echo 268435456 > /proc/sys/kernel/shmmax
echo 4194304 > /proc/sys/kernel/shmall
echo "--------------------"
echo "running hugepage-shm"
echo "--------------------"
./hugepage-shm
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo $shmmax > /proc/sys/kernel/shmmax
echo $shmall > /proc/sys/kernel/shmall
echo "--------------------"
echo "running map_hugetlb"
echo "--------------------"
./map_hugetlb
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo "NOTE: The above hugetlb tests provide minimal coverage. Use"
echo " https://github.com/libhugetlbfs/libhugetlbfs.git for"
echo " hugetlb regression testing."
echo "--------------------"
echo "running userfaultfd"
echo "--------------------"
./userfaultfd 128 32
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
#cleanup
umount $mnt
rm -rf $mnt
echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
echo "-----------------------"
echo "running compaction_test"
echo "-----------------------"
./compaction_test
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo "--------------------"
echo "running on-fault-limit"
echo "--------------------"
sudo -u nobody ./on-fault-limit
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo "--------------------"
echo "running mlock2-tests"
echo "--------------------"
./mlock2-tests
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
exit $exitcode
drm/i915: Check for NULL i915_vma in intel_unpin_fb_obj()
I've seen this trigger twice now, where the i915_gem_object_to_ggtt()
call in intel_unpin_fb_obj() returns NULL, resulting in an oops
immediately afterwards as the (inlined) call to i915_vma_unpin_fence()
tries to dereference it.
It seems to be some race condition where the object is going away at
shutdown time, since both times happened when shutting down the X
server. The call chains were different:
- VT ioctl(KDSETMODE, KD_TEXT):
intel_cleanup_plane_fb+0x5b/0xa0 [i915]
drm_atomic_helper_cleanup_planes+0x6f/0x90 [drm_kms_helper]
intel_atomic_commit_tail+0x749/0xfe0 [i915]
intel_atomic_commit+0x3cb/0x4f0 [i915]
drm_atomic_commit+0x4b/0x50 [drm]
restore_fbdev_mode+0x14c/0x2a0 [drm_kms_helper]
drm_fb_helper_restore_fbdev_mode_unlocked+0x34/0x80 [drm_kms_helper]
drm_fb_helper_set_par+0x2d/0x60 [drm_kms_helper]
intel_fbdev_set_par+0x18/0x70 [i915]
fb_set_var+0x236/0x460
fbcon_blank+0x30f/0x350
do_unblank_screen+0xd2/0x1a0
vt_ioctl+0x507/0x12a0
tty_ioctl+0x355/0xc30
do_vfs_ioctl+0xa3/0x5e0
SyS_ioctl+0x79/0x90
entry_SYSCALL_64_fastpath+0x13/0x94
- i915 unpin_work workqueue:
intel_unpin_work_fn+0x58/0x140 [i915]
process_one_work+0x1f1/0x480
worker_thread+0x48/0x4d0
kthread+0x101/0x140
and this patch purely papers over the issue by adding a NULL pointer
check and a WARN_ON_ONCE() to avoid the oops that would then generally
make the machine unresponsive.
Other callers of i915_gem_object_to_ggtt() seem to also check for the
returned pointer being NULL and warn about it, so this clearly has
happened before in other places.
[ Reported it originally to the i915 developers on Jan 8, applying the
ugly workaround on my own now after triggering the problem for the
second time with no feedback.
This is likely to be the same bug reported as
https://bugs.freedesktop.org/show_bug.cgi?id=98829
https://bugs.freedesktop.org/show_bug.cgi?id=99134
which has a patch for the underlying problem, but it hasn't gotten to
me, so I'm applying the workaround. ]
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>