From: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com

[ Upstream commit 17da2d5f93692086dd096a975225ffd5622d0bf8 ]

As reported:

[ 256.104522] ====================================================== [ 256.113783] WARNING: possible circular locking dependency detected [ 256.120093] 5.16.0-rc6-yocto-standard+ #99 Not tainted [ 256.125362] ------------------------------------------------------ [ 256.131673] intel-speed-sel/844 is trying to acquire lock: [ 256.137290] ffffffffc036f0d0 (punit_misc_dev_lock){+.+.}-{3:3}, at: isst_if_open+0x18/0x90 [isst_if_common] [ 256.147171] [ 256.147171] but task is already holding lock: [ 256.153135] ffffffff8ee7cb50 (misc_mtx){+.+.}-{3:3}, at: misc_open+0x2a/0x170 [ 256.160407] [ 256.160407] which lock already depends on the new lock. [ 256.160407] [ 256.168712] [ 256.168712] the existing dependency chain (in reverse order) is: [ 256.176327] [ 256.176327] -> #1 (misc_mtx){+.+.}-{3:3}: [ 256.181946] lock_acquire+0x1e6/0x330 [ 256.186265] __mutex_lock+0x9b/0x9b0 [ 256.190497] mutex_lock_nested+0x1b/0x20 [ 256.195075] misc_register+0x32/0x1a0 [ 256.199390] isst_if_cdev_register+0x65/0x180 [isst_if_common] [ 256.205878] isst_if_probe+0x144/0x16e [isst_if_mmio] ... [ 256.241976] [ 256.241976] -> #0 (punit_misc_dev_lock){+.+.}-{3:3}: [ 256.248552] validate_chain+0xbc6/0x1750 [ 256.253131] __lock_acquire+0x88c/0xc10 [ 256.257618] lock_acquire+0x1e6/0x330 [ 256.261933] __mutex_lock+0x9b/0x9b0 [ 256.266165] mutex_lock_nested+0x1b/0x20 [ 256.270739] isst_if_open+0x18/0x90 [isst_if_common] [ 256.276356] misc_open+0x100/0x170 [ 256.280409] chrdev_open+0xa5/0x1e0 ...

The call sequence suggested that misc_device /dev file can be opened before misc device is yet to be registered, which is done only once.

Here punit_misc_dev_lock was used as common lock, to protect the registration by multiple ISST HW drivers, one time setup, prevent duplicate registry of misc device and prevent load/unload when device is open.

We can split into locks: - One which just prevent duplicate call to misc_register() and one time setup. Also never call again if the misc_register() failed or required one time setup is failed. This lock is not shared with any misc device callbacks.

- The other lock protects registry, load and unload of HW drivers.

Sequence in isst_if_cdev_register() - Register callbacks under punit_misc_dev_open_lock - Call isst_misc_reg() which registers misc_device on the first registry which is under punit_misc_dev_reg_lock, which is not shared with callbacks.

Sequence in isst_if_cdev_unregister Just opposite of isst_if_cdev_register

Reported-and-tested-by: Liwei Song liwei.song@windriver.com Signed-off-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Link: https://lore.kernel.org/r/20220112022521.54669-1-srinivas.pandruvada@linux.i... Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../intel_speed_select_if/isst_if_common.c | 97 ++++++++++++------- 1 file changed, 63 insertions(+), 34 deletions(-)

diff --git a/drivers/platform/x86/intel_speed_select_if/isst_if_common.c b/drivers/platform/x86/intel_speed_select_if/isst_if_common.c index 0c2aa22c7a12e..407afafc7e83f 100644 --- a/drivers/platform/x86/intel_speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel_speed_select_if/isst_if_common.c @@ -532,7 +532,10 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd, return ret; }

-static DEFINE_MUTEX(punit_misc_dev_lock); +/* Lock to prevent module registration when already opened by user space */ +static DEFINE_MUTEX(punit_misc_dev_open_lock); +/* Lock to allow one share misc device for all ISST interace */ +static DEFINE_MUTEX(punit_misc_dev_reg_lock); static int misc_usage_count; static int misc_device_ret; static int misc_device_open; @@ -542,7 +545,7 @@ static int isst_if_open(struct inode *inode, struct file *file) int i, ret = 0;

/* Fail open, if a module is going away */ - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i];

@@ -564,7 +567,7 @@ static int isst_if_open(struct inode *inode, struct file *file) } else { misc_device_open++; } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

return ret; } @@ -573,7 +576,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) { int i;

- mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); misc_device_open--; for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -581,7 +584,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) if (cb->registered) module_put(cb->owner); } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

return 0; } @@ -598,6 +601,43 @@ static struct miscdevice isst_if_char_driver = { .fops = &isst_if_char_driver_ops, };

+static int isst_misc_reg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_device_ret) + goto unlock_exit; + + if (!misc_usage_count) { + misc_device_ret = isst_if_cpu_info_init(); + if (misc_device_ret) + goto unlock_exit; + + misc_device_ret = misc_register(&isst_if_char_driver); + if (misc_device_ret) { + isst_if_cpu_info_exit(); + goto unlock_exit; + } + } + misc_usage_count++; + +unlock_exit: + mutex_unlock(&punit_misc_dev_reg_lock); + + return misc_device_ret; +} + +static void isst_misc_unreg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_usage_count) + misc_usage_count--; + if (!misc_usage_count && !misc_device_ret) { + misc_deregister(&isst_if_char_driver); + isst_if_cpu_info_exit(); + } + mutex_unlock(&punit_misc_dev_reg_lock); +} + /** * isst_if_cdev_register() - Register callback for IOCTL * @device_type: The device type this callback handling. @@ -615,38 +655,31 @@ static struct miscdevice isst_if_char_driver = { */ int isst_if_cdev_register(int device_type, struct isst_if_cmd_cb *cb) { - if (misc_device_ret) - return misc_device_ret; + int ret;

if (device_type >= ISST_IF_DEV_MAX) return -EINVAL;

- mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); + /* Device is already open, we don't want to add new callbacks */ if (misc_device_open) { - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return -EAGAIN; } - if (!misc_usage_count) { - int ret; - - misc_device_ret = misc_register(&isst_if_char_driver); - if (misc_device_ret) - goto unlock_exit; - - ret = isst_if_cpu_info_init(); - if (ret) { - misc_deregister(&isst_if_char_driver); - misc_device_ret = ret; - goto unlock_exit; - } - } memcpy(&punit_callbacks[device_type], cb, sizeof(*cb)); punit_callbacks[device_type].registered = 1; - misc_usage_count++; -unlock_exit: - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock);

- return misc_device_ret; + ret = isst_misc_reg(); + if (ret) { + /* + * No need of mutex as the misc device register failed + * as no one can open device yet. Hence no contention. + */ + punit_callbacks[device_type].registered = 0; + return ret; + } + return 0; } EXPORT_SYMBOL_GPL(isst_if_cdev_register);

@@ -661,16 +694,12 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_register); */ void isst_if_cdev_unregister(int device_type) { - mutex_lock(&punit_misc_dev_lock); - misc_usage_count--; + isst_misc_unreg(); + mutex_lock(&punit_misc_dev_open_lock); punit_callbacks[device_type].registered = 0; if (device_type == ISST_IF_DEV_MBOX) isst_delete_hash(); - if (!misc_usage_count && !misc_device_ret) { - misc_deregister(&isst_if_char_driver); - isst_if_cpu_info_exit(); - } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); } EXPORT_SYMBOL_GPL(isst_if_cdev_unregister);

From: Li Zhijian lizhijian@cn.fujitsu.com

[ Upstream commit 92d25637a3a45904292c93f1863c6bbda4e3e38f ]

We have some many cases that will create child process as well, such as pidfd_wait. Previously, we will signal/kill the parent process when it is time out, but this signal will not be sent to its child process. In such case, if child process doesn't terminate itself, ksefltest framework will hang forever.

Here we group all its child processes so that kill() can signal all of them in timeout.

Fixed change log: Shuah Khan skhan@linuxfoundation.org

Suggested-by: yang xu xuyang2018.jy@cn.fujitsu.com Signed-off-by: Li Zhijian lizhijian@cn.fujitsu.com Acked-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kselftest_harness.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 5ecb9718e1616..3e7b2e521cde4 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -871,7 +871,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) }

t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); }

void __wait_for_test(struct __test_metadata *t) @@ -981,6 +982,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255);

From: Yang Xu xuyang2018.jy@fujitsu.com

[ Upstream commit fc4eb486a59d70bd35cf1209f0e68c2d8b979193 ]

Since commit 43209ea2d17a ("zram: remove max_comp_streams internals"), zram has switched to per-cpu streams. Even kernel still keep this interface for some reasons, but writing to max_comp_stream doesn't take any effect. So skip it on newer kernel ie 4.7.

The code that comparing kernel version is from xfstests testsuite ext4/053.

Signed-off-by: Yang Xu xuyang2018.jy@fujitsu.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/zram/zram_lib.sh | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 6f872f266fd11..f47fc0f27e99e 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -11,6 +11,9 @@ dev_mounted=-1

# Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +kernel_version=`uname -r | cut -d'.' -f1,2` +kernel_major=${kernel_version%.*} +kernel_minor=${kernel_version#*.}

trap INT

@@ -25,6 +28,20 @@ check_prereqs() fi }

+kernel_gte() +{ + major=${1%.*} + minor=${1#*.} + + if [ $kernel_major -gt $major ]; then + return 0 + elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then + return 0 + fi + + return 1 +} + zram_cleanup() { echo "zram cleanup" @@ -86,6 +103,13 @@ zram_max_streams() { echo "set max_comp_streams to zram device(s)"

+ kernel_gte 4.7 + if [ $? -eq 0 ]; then + echo "The device attribute max_comp_streams was"\ + "deprecated in 4.7" + return 0 + fi + local i=0 for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams"

From: Yang Xu xuyang2018.jy@fujitsu.com

[ Upstream commit 01dabed20573804750af5c7bf8d1598a6bf7bf6e ]

If zram-generator package is installed and works, then we can not remove zram module because zram swap is being used. This case needs a clean zram environment, change this test by using hot_add/hot_remove interface. So even zram device is being used, we still can add zram device and remove them in cleanup.

The two interface was introduced since kernel commit 6566d1a32bf7("zram: add dynamic device add/remove functionality") in v4.2-rc1. If kernel supports these two interface, we use hot_add/hot_remove to slove this problem, if not, just check whether zram is being used or built in, then skip it on old kernel.

Signed-off-by: Yang Xu xuyang2018.jy@fujitsu.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/zram/zram.sh | 15 +--- tools/testing/selftests/zram/zram01.sh | 3 +- tools/testing/selftests/zram/zram02.sh | 1 - tools/testing/selftests/zram/zram_lib.sh | 110 +++++++++++++---------- 4 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 232e958ec4547..b0b91d9b0dc21 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,9 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh"

-# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - . ./zram_lib.sh

run_zram () { @@ -18,14 +15,4 @@ echo ""

check_prereqs

-# check zram module exists -MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko -if [ -f $MODULE_PATH ]; then - run_zram -elif [ -b /dev/zram0 ]; then - run_zram -else - echo "$TCID : No zram.ko module or /dev/zram0 device file not found" - echo "$TCID : CONFIG_ZRAM is not set" - exit $ksft_skip -fi +run_zram diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index e9e9eb777e2c7..8f4affe34f3e4 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,7 +33,7 @@ zram_algs="lzo"

zram_fill_fs() { - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "fill zram$i..." local b=0 while [ true ]; do @@ -67,7 +67,6 @@ zram_mount

zram_fill_fs zram_cleanup -zram_unload

if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh index e83b404807c09..2418b0c4ed136 100755 --- a/tools/testing/selftests/zram/zram02.sh +++ b/tools/testing/selftests/zram/zram02.sh @@ -36,7 +36,6 @@ zram_set_memlimit zram_makeswap zram_swapoff zram_cleanup -zram_unload

if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index f47fc0f27e99e..21ec1966de76c 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -5,10 +5,12 @@ # Author: Alexey Kodanev alexey.kodanev@oracle.com # Modified: Naresh Kamboju naresh.kamboju@linaro.org

-MODULE=0 dev_makeswap=-1 dev_mounted=-1 - +dev_start=0 +dev_end=-1 +module_load=-1 +sys_control=-1 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 kernel_version=`uname -r | cut -d'.' -f1,2` @@ -46,57 +48,72 @@ zram_cleanup() { echo "zram cleanup" local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_makeswap); do swapoff /dev/zram$i done

- for i in $(seq 0 $dev_mounted); do + for i in $(seq $dev_start $dev_mounted); do umount /dev/zram$i done

- for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo 1 > /sys/block/zram${i}/reset rm -rf zram$i done

-} + if [ $sys_control -eq 1 ]; then + for i in $(seq $dev_start $dev_end); do + echo $i > /sys/class/zram-control/hot_remove + done + fi

-zram_unload() -{ - if [ $MODULE -ne 0 ] ; then - echo "zram rmmod zram" + if [ $module_load -eq 1 ]; then rmmod zram > /dev/null 2>&1 fi }

zram_load() { - # check zram module exists - MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko - if [ -f $MODULE_PATH ]; then - MODULE=1 - echo "create '$dev_num' zram device(s)" - modprobe zram num_devices=$dev_num - if [ $? -ne 0 ]; then - echo "failed to insert zram module" - exit 1 - fi - - dev_num_created=$(ls /dev/zram* | wc -w) + echo "create '$dev_num' zram device(s)" + + # zram module loaded, new kernel + if [ -d "/sys/class/zram-control" ]; then + echo "zram modules already loaded, kernel supports" \ + "zram-control interface" + dev_start=$(ls /dev/zram* | wc -w) + dev_end=$(($dev_start + $dev_num - 1)) + sys_control=1 + + for i in $(seq $dev_start $dev_end); do + cat /sys/class/zram-control/hot_add > /dev/null + done + + echo "all zram devices (/dev/zram$dev_start~$dev_end" \ + "successfully created" + return 0 + fi

- if [ "$dev_num_created" -ne "$dev_num" ]; then - echo "unexpected num of devices: $dev_num_created" - ERR_CODE=-1 + # detect old kernel or built-in + modprobe zram num_devices=$dev_num + if [ ! -d "/sys/class/zram-control" ]; then + if grep -q '^zram' /proc/modules; then + rmmod zram > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "zram module is being used on old kernel" \ + "without zram-control interface" + exit $ksft_skip + fi else - echo "zram load module successful" + echo "test needs CONFIG_ZRAM=m on old kernel without" \ + "zram-control interface" + exit $ksft_skip fi - elif [ -b /dev/zram0 ]; then - echo "/dev/zram0 device file found: OK" - else - echo "ERROR: No zram.ko module or no /dev/zram0 device found" - echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + modprobe zram num_devices=$dev_num fi + + module_load=1 + dev_end=$(($dev_num - 1)) + echo "all zram devices (/dev/zram0~$dev_end) successfully created" }

zram_max_streams() @@ -110,7 +127,7 @@ zram_max_streams() return 0 fi

- local i=0 + local i=$dev_start for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams" echo $max_s > $sys_path || \ @@ -122,7 +139,7 @@ zram_max_streams() echo "FAIL can't set max_streams '$max_s', get $max_stream"

i=$(($i + 1)) - echo "$sys_path = '$max_streams' ($i/$dev_num)" + echo "$sys_path = '$max_streams'" done

echo "zram max streams: OK" @@ -132,15 +149,16 @@ zram_compress_alg() { echo "test that we can set compression algorithm"

- local algs=$(cat /sys/block/zram0/comp_algorithm) + local i=$dev_start + local algs=$(cat /sys/block/zram${i}/comp_algorithm) echo "supported algs: $algs" - local i=0 + for alg in $zram_algs; do local sys_path="/sys/block/zram${i}/comp_algorithm" echo "$alg" > $sys_path || \ echo "FAIL can't set '$alg' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$alg' ($i/$dev_num)" + echo "$sys_path = '$alg'" done

echo "zram set compression algorithm: OK" @@ -149,14 +167,14 @@ zram_compress_alg() zram_set_disksizes() { echo "set disk size to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_sizes; do local sys_path="/sys/block/zram${i}/disksize" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path"

i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done

echo "zram set disksizes: OK" @@ -166,14 +184,14 @@ zram_set_memlimit() { echo "set memory limit to zram device(s)"

- local i=0 + local i=$dev_start for ds in $zram_mem_limits; do local sys_path="/sys/block/zram${i}/mem_limit" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path"

i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done

echo "zram set memory limit: OK" @@ -182,8 +200,8 @@ zram_set_memlimit() zram_makeswap() { echo "make swap with zram device(s)" - local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + local i=$dev_start + for i in $(seq $dev_start $dev_end); do mkswap /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -206,7 +224,7 @@ zram_makeswap() zram_swapoff() { local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_end); do swapoff /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -220,7 +238,7 @@ zram_swapoff()

zram_makefs() { - local i=0 + local i=$dev_start for fs in $zram_filesystems; do # if requested fs not supported default it to ext2 which mkfs.$fs > /dev/null 2>&1 || fs=ext2 @@ -239,7 +257,7 @@ zram_makefs() zram_mount() { local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "mount /dev/zram$i" mkdir zram$i mount /dev/zram$i zram$i > /dev/null || \

From: Cristian Marussi cristian.marussi@arm.com

[ Upstream commit ea3396725aa143dd42fe388cb67e44c90d2fb719 ]

Add a dependency on header helpers.h to the main target; while at that add to helpers.h also a missing include for bool types.

Cc: Aleksa Sarai cyphar@cyphar.com Signed-off-by: Cristian Marussi cristian.marussi@arm.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/openat2/Makefile | 2 +- tools/testing/selftests/openat2/helpers.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 4b93b1417b862..843ba56d8e49e 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test

include ../lib.mk

-$(TEST_GEN_PROGS): helpers.c +$(TEST_GEN_PROGS): helpers.c helpers.h diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index ad5d0ba5b6ce9..7056340b9339e 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -9,6 +9,7 @@

#define _GNU_SOURCE #include <stdint.h> +#include <stdbool.h> #include <errno.h> #include <linux/types.h> #include "../kselftest.h"

From: Cristian Marussi cristian.marussi@arm.com

[ Upstream commit dae1d8ac31896988e7313384c0370176a75e9b45 ]

Report mincore.check_file_mmap as SKIP instead of FAIL if the underlying filesystem lacks support of O_TMPFILE or fallocate since such failures are not really related to mincore functionality.

Cc: Ricardo Cañuelo ricardo.canuelo@collabora.com Signed-off-by: Cristian Marussi cristian.marussi@arm.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/mincore/mincore_selftest.c | 20 +++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index 5a1e85ff5d32a..2cf6f2f277ab8 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -208,15 +208,21 @@ TEST(check_file_mmap)

errno = 0; fd = open(".", O_TMPFILE | O_RDWR, 0600); - ASSERT_NE(-1, fd) { - TH_LOG("Can't create temporary file: %s", - strerror(errno)); + if (fd < 0) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Can't create temporary file: %s", + strerror(errno)); + } + SKIP(goto out_free, "O_TMPFILE not supported by filesystem."); } errno = 0; retval = fallocate(fd, 0, 0, FILE_SIZE); - ASSERT_EQ(0, retval) { - TH_LOG("Error allocating space for the temporary file: %s", - strerror(errno)); + if (retval) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Error allocating space for the temporary file: %s", + strerror(errno)); + } + SKIP(goto out_close, "fallocate not supported by filesystem."); }

/* @@ -272,7 +278,9 @@ TEST(check_file_mmap) }

munmap(addr, FILE_SIZE); +out_close: close(fd); +out_free: free(vec); }

From: "Darrick J. Wong" djwong@kernel.org

[ Upstream commit 2719c7160dcfaae1f73a1c0c210ad3281c19022e ]

If we fail to synchronize the filesystem while preparing to freeze the fs, abort the freeze.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/super.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/super.c b/fs/super.c index 20f1707807bbd..bae3fe80f852e 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1667,11 +1667,9 @@ static void lockdep_sb_freeze_acquire(struct super_block *sb) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); }

-static void sb_freeze_unlock(struct super_block *sb) +static void sb_freeze_unlock(struct super_block *sb, int level) { - int level; - - for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) + for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); }

@@ -1742,7 +1740,14 @@ int freeze_super(struct super_block *sb) sb_wait_write(sb, SB_FREEZE_PAGEFAULT);

/* All writers are done so after syncing there won't be dirty data */ - sync_filesystem(sb); + ret = sync_filesystem(sb); + if (ret) { + sb->s_writers.frozen = SB_UNFROZEN; + sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); + wake_up(&sb->s_writers.wait_unfrozen); + deactivate_locked_super(sb); + return ret; + }

/* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; @@ -1754,7 +1759,7 @@ int freeze_super(struct super_block *sb) printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; @@ -1805,7 +1810,7 @@ static int thaw_super_locked(struct super_block *sb) }

sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); out: wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb);

From: Su Yue l@damenly.su

[ Upstream commit ea1d1ca4025ac6c075709f549f9aa036b5b6597d ]

Check item size before accessing the device item to avoid out of bound access, similar to inode_item check.

Signed-off-by: Su Yue l@damenly.su Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/tree-checker.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index d4a3a56726aa8..4a5ee516845f7 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -947,6 +947,7 @@ static int check_dev_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { struct btrfs_dev_item *ditem; + const u32 item_size = btrfs_item_size(leaf, slot);

if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { dev_item_err(leaf, slot, @@ -954,6 +955,13 @@ static int check_dev_item(struct extent_buffer *leaf, key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } + + if (unlikely(item_size != sizeof(*ditem))) { + dev_item_err(leaf, slot, "invalid item size: has %u expect %zu", + item_size, sizeof(*ditem)); + return -EUCLEAN; + } + ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); if (btrfs_device_id(leaf, ditem) != key->offset) { dev_item_err(leaf, slot,

From: John Garry john.garry@huawei.com

[ Upstream commit 61f162aa4381845acbdc7f2be4dfb694d027c018 ]

Currently a use-after-free may occur if a TMF sas_task is aborted before we handle the IO completion in mpi_ssp_completion(). The abort occurs due to timeout.

When the timeout occurs, the SAS_TASK_STATE_ABORTED flag is set and the sas_task is freed in pm8001_exec_internal_tmf_task().

However, if the I/O completion occurs later, the I/O completion still thinks that the sas_task is available. Fix this by clearing the ccb->task if the TMF times out - the I/O completion handler does nothing if this pointer is cleared.

Link: https://lore.kernel.org/r/1643289172-165636-3-git-send-email-john.garry@huaw... Reviewed-by: Damien Le Moal damien.lemoal@opensource.wdc.com Acked-by: Jack Wang jinpu.wang@ionos.com Signed-off-by: John Garry john.garry@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/pm8001/pm8001_sas.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index c3bb58885033b..75ac4d86d9c4b 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -753,8 +753,13 @@ static int pm8001_exec_internal_tmf_task(struct domain_device *dev, res = -TMF_RESP_FUNC_FAILED; /* Even TMF timed out, return direct. */ if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { + struct pm8001_ccb_info *ccb = task->lldd_task; + pm8001_dbg(pm8001_ha, FAIL, "TMF task[%x]timeout.\n", tmf->tmf); + + if (ccb) + ccb->task = NULL; goto ex_err; }

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit 0fa0f99fc84e41057cbdd2efbfe91c6b2f47dd9d ]

Unlike .queue_rq, in .submit_async_event drivers may not check the ctrl readiness for AER submission. This may lead to a use-after-free condition that was observed with nvme-tcp.

The race condition may happen in the following scenario: 1. driver executes its reset_ctrl_work 2. -> nvme_stop_ctrl - flushes ctrl async_event_work 3. ctrl sends AEN which is received by the host, which in turn schedules AEN handling 4. teardown admin queue (which releases the queue socket) 5. AEN processed, submits another AER, calling the driver to submit 6. driver attempts to send the cmd ==> use-after-free

In order to fix that, add ctrl state check to validate the ctrl is actually able to accept the AER submission.

This addresses the above race in controller resets because the driver during teardown should: 1. change ctrl state to RESETTING 2. flush async_event_work (as well as other async work elements)

So after 1,2, any other AER command will find the ctrl state to be RESETTING and bail out without submitting the AER.

Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 99b5152482fe4..71c85c99e86c6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4259,7 +4259,14 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work);

nvme_aen_uevent(ctrl); - ctrl->ops->submit_async_event(ctrl); + + /* + * The transport drivers must guarantee AER submission here is safe by + * flushing ctrl async_event_work after changing the controller state + * from LIVE and before freeing the admin queue. + */ + if (ctrl->state == NVME_CTRL_LIVE) + ctrl->ops->submit_async_event(ctrl); }

static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit b6bb1722f34bbdbabed27acdceaf585d300c5fd2 ]

While nvme_rdma_submit_async_event_work is checking the ctrl and queue state before preparing the AER command and scheduling io_work, in order to fully prevent a race where this check is not reliable the error recovery work must flush async_event_work before continuing to destroy the admin queue after setting the ctrl state to RESETTING such that there is no race .submit_async_event and the error recovery handler itself changing the ctrl state.

Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/rdma.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 1b90563818434..8eacc9bd58f5a 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1200,6 +1200,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl, err_work);

nvme_stop_keep_alive(&ctrl->ctrl); + flush_work(&ctrl->ctrl.async_event_work); nvme_rdma_teardown_io_queues(ctrl, false); nvme_start_queues(&ctrl->ctrl); nvme_rdma_teardown_admin_queue(ctrl, false);

From: Jan Beulich jbeulich@suse.com

[ Upstream commit e25a8d959992f61b64a58fc62fb7951dc6f31d1f ]

This started out with me noticing that "dom0_max_vcpus=<N>" with <N> larger than the number of physical CPUs reported through ACPI tables would not bring up the "excess" vCPU-s. Addressing this is the primary purpose of the change; CPU maps handling is being tidied only as far as is necessary for the change here (with the effect of also avoiding the setting up of too much per-CPU infrastructure, i.e. for CPUs which can never come online).

Noticing that xen_fill_possible_map() is called way too early, whereas xen_filter_cpu_maps() is called too late (after per-CPU areas were already set up), and further observing that each of the functions serves only one of Dom0 or DomU, it looked like it was better to simplify this. Use the .get_smp_config hook instead, uniformly for Dom0 and DomU. xen_fill_possible_map() can be dropped altogether, while xen_filter_cpu_maps() is re-purposed but not otherwise changed.

Signed-off-by: Jan Beulich jbeulich@suse.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Link: https://lore.kernel.org/r/2dbd5f0a-9859-ca2d-085e-a02f7166c610@suse.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/xen/enlighten_pv.c | 4 ---- arch/x86/xen/smp_pv.c | 26 ++++++-------------------- 2 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 16ff25d6935e7..804c65d2b95f3 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1387,10 +1387,6 @@ asmlinkage __visible void __init xen_start_kernel(void)

xen_acpi_sleep_register();

- /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - xen_boot_params_init_edd();

#ifdef CONFIG_ACPI diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index c2ac319f11a4b..8f9e7e2407c87 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -149,28 +149,12 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; }

-static void __init xen_fill_possible_map(void) -{ - int i, rc; - - if (xen_initial_domain()) - return; - - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } - } -} - -static void __init xen_filter_cpu_maps(void) +static void __init _get_smp_config(unsigned int early) { int i, rc; unsigned int subtract = 0;

- if (!xen_initial_domain()) + if (early) return;

num_processors = 0; @@ -211,7 +195,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) * sure the old memory can be recycled. */ make_lowmem_page_readwrite(xen_initial_gdt);

- xen_filter_cpu_maps(); xen_setup_vcpu_info_placement();

/* @@ -491,5 +474,8 @@ static const struct smp_ops xen_smp_ops __initconst = { void __init xen_smp_init(void) { smp_ops = xen_smp_ops; - xen_fill_possible_map(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = _get_smp_config; }

From: Kees Cook keescook@chromium.org

[ Upstream commit dcb85f85fa6f142aae1fe86f399d4503d49f2b60 ]

While the stackleak plugin was already using notrace, objtool is now a bit more picky. Update the notrace uses to noinstr. Silences the following objtool warnings when building with:

CONFIG_DEBUG_ENTRY=y CONFIG_STACK_VALIDATION=y CONFIG_VMLINUX_VALIDATION=y CONFIG_GCC_PLUGIN_STACKLEAK=y

vmlinux.o: warning: objtool: do_syscall_64()+0x9: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x9: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: exc_general_protection()+0x22: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: fixup_bad_iret()+0x20: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: do_machine_check()+0x27: call to stackleak_track_stack() leaves .noinstr.text section vmlinux.o: warning: objtool: .text+0x5346e: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x143: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x10eb: call to stackleak_erase() leaves .noinstr.text section vmlinux.o: warning: objtool: .entry.text+0x17f9: call to stackleak_erase() leaves .noinstr.text section

Note that the plugin's addition of calls to stackleak_track_stack() from noinstr functions is expected to be safe, as it isn't runtime instrumentation and is self-contained.

Cc: Alexander Popov alex.popov@linux.com Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/stackleak.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ce161a8e8d975..dd07239ddff9f 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -48,7 +48,7 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */

-asmlinkage void notrace stackleak_erase(void) +asmlinkage void noinstr stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -102,9 +102,8 @@ asmlinkage void notrace stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } -NOKPROBE_SYMBOL(stackleak_erase);

-void __used __no_caller_saved_registers notrace stackleak_track_stack(void) +void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) { unsigned long sp = current_stack_pointer;