From: Alexandra Winter <wintera@linux.ibm.com>
Date: Tue, 21 Sep 2021 16:52:17 +0200
Subject: s390/qeth: fix deadlock during failing recovery
Git-commit: d2b59bd4b06d84a4eadb520b0f71c62fe8ec0a62
Patch-mainline: v5.15-rc3
References: bsc#1206213 LTC#200742
Commit 0b9902c1fcc5 ("s390/qeth: fix deadlock during recovery") removed
taking discipline_mutex inside qeth_do_reset(), fixing potential
deadlocks. An error path was missed though, that still takes
discipline_mutex and thus has the original deadlock potential.
Intermittent deadlocks were seen when a qeth channel path is configured
offline, causing a race between qeth_do_reset and ccwgroup_remove.
Call qeth_set_offline() directly in the qeth_do_reset() error case and
then a new variant of ccwgroup_set_offline(), without taking
discipline_mutex.
Fixes: b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal")
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[ ptesarik: recover discipline ops are not merged in SLE12-SP5, so there are
separate hunks for qeth_l2_recover() and qeth_l3_recover(). ]
Signed-off-by: Petr Tesarik <ptesarik@suse.com>
---
arch/s390/include/asm/ccwgroup.h | 2 +-
drivers/s390/cio/ccwgroup.c | 10 ++++++++--
drivers/s390/net/qeth_l2_main.c | 3 ++-
drivers/s390/net/qeth_l3_main.c | 3 ++-
4 files changed, 13 insertions(+), 5 deletions(-)
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -65,7 +65,7 @@ int ccwgroup_create_dev(struct device *r
int num_devices, const char *buf);
extern int ccwgroup_set_online(struct ccwgroup_device *gdev);
-extern int ccwgroup_set_offline(struct ccwgroup_device *gdev);
+int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv);
extern int ccwgroup_probe_ccwdev(struct ccw_device *cdev);
extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -97,12 +97,13 @@ EXPORT_SYMBOL(ccwgroup_set_online);
/**
* ccwgroup_set_offline() - disable a ccwgroup device
* @gdev: target ccwgroup device
+ * @call_gdrv: Call the registered gdrv set_offline function
*
* This function attempts to put the ccwgroup device into the offline state.
* Returns:
* %0 on success and a negative error value on failure.
*/
-int ccwgroup_set_offline(struct ccwgroup_device *gdev)
+int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv)
{
struct ccwgroup_driver *gdrv = to_ccwgroupdrv(gdev->dev.driver);
int ret = -EINVAL;
@@ -111,11 +112,16 @@ int ccwgroup_set_offline(struct ccwgroup
return -EAGAIN;
if (gdev->state == CCWGROUP_OFFLINE)
goto out;
+ if (!call_gdrv) {
+ ret = 0;
+ goto offline;
+ }
if (gdrv->set_offline)
ret = gdrv->set_offline(gdev);
if (ret)
goto out;
+offline:
gdev->state = CCWGROUP_OFFLINE;
out:
atomic_set(&gdev->onoff, 0);
@@ -144,7 +150,7 @@ static ssize_t ccwgroup_online_store(str
if (value == 1)
ret = ccwgroup_set_online(gdev);
else if (value == 0)
- ret = ccwgroup_set_offline(gdev);
+ ret = ccwgroup_set_offline(gdev, true);
else
ret = -EINVAL;
out:
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1123,7 +1123,8 @@ static int qeth_l2_recover(void *ptr)
dev_info(&card->gdev->dev,
"Device successfully recovered!\n");
else {
- ccwgroup_set_offline(card->gdev);
+ __qeth_l2_set_offline(card->gdev, true);
+ ccwgroup_set_offline(card->gdev, false);
dev_warn(&card->gdev->dev, "The qeth device driver "
"failed to recover an error on the device\n");
}
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2649,7 +2649,8 @@ static int qeth_l3_recover(void *ptr)
dev_info(&card->gdev->dev,
"Device successfully recovered!\n");
else {
- ccwgroup_set_offline(card->gdev);
+ __qeth_l3_set_offline(card->gdev, 1);
+ ccwgroup_set_offline(card->gdev, false);
dev_warn(&card->gdev->dev, "The qeth device driver "
"failed to recover an error on the device\n");
}