diff mbox series

[net,1/3] s390/qeth: fix deadlock during recovery

Message ID 20210107172442.1737-2-jwi@linux.ibm.com (mailing list archive)
State Accepted
Commit 0b9902c1fcc59ba75268386c0420a554f8844168
Delegated to: Netdev Maintainers
Headers show
Series s390/qeth: fixes 2021-01-07 | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net
netdev/subject_prefix success Link
netdev/cc_maintainers warning 4 maintainers not CCed: borntraeger@de.ibm.com frank.blaschka@de.ibm.com ursula.braun@de.ibm.com gor@linux.ibm.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 17 this patch: 17
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 144 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Julian Wiedmann Jan. 7, 2021, 5:24 p.m. UTC
When qeth_dev_layer2_store() - holding the discipline_mutex - waits
inside qeth_l*_remove_device() for a qeth_do_reset() thread to complete,
we can hit a deadlock if qeth_do_reset() concurrently calls
qeth_set_online() and thus tries to aquire the discipline_mutex.

Move the discipline_mutex locking outside of qeth_set_online() and
qeth_set_offline(), and turn the discipline into a parameter so that
callers understand the dependency.

To fix the deadlock, we can now relax the locking:
As already established, qeth_l*_remove_device() waits for
qeth_do_reset() to complete. So qeth_do_reset() itself is under no risk
of having card->discipline ripped out while it's running, and thus
doesn't need to take the discipline_mutex.

Fixes: 9dc48ccc68b9 ("qeth: serialize sysfs-triggered device configurations")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
---
 drivers/s390/net/qeth_core.h      |  3 ++-
 drivers/s390/net/qeth_core_main.c | 35 +++++++++++++++++++------------
 drivers/s390/net/qeth_l2_main.c   |  7 +++++--
 drivers/s390/net/qeth_l3_main.c   |  7 +++++--
 4 files changed, 34 insertions(+), 18 deletions(-)
diff mbox series

Patch

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6f5ddc3eab8c..28f637042d44 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1079,7 +1079,8 @@  struct qeth_card *qeth_get_card_by_busid(char *bus_id);
 void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads,
 			      int clear_start_mask);
 int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_set_offline(struct qeth_card *card, bool resetting);
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting);
 
 int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  int (*reply_cb)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f4b60294a969..d45e223fc521 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5507,12 +5507,12 @@  static int qeth_hardsetup_card(struct qeth_card *card, bool *carrier_ok)
 	return rc;
 }
 
-static int qeth_set_online(struct qeth_card *card)
+static int qeth_set_online(struct qeth_card *card,
+			   const struct qeth_discipline *disc)
 {
 	bool carrier_ok;
 	int rc;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 2, "setonlin");
 
@@ -5529,7 +5529,7 @@  static int qeth_set_online(struct qeth_card *card)
 		/* no need for locking / error handling at this early stage: */
 		qeth_set_real_num_tx_queues(card, qeth_tx_actual_queues(card));
 
-	rc = card->discipline->set_online(card, carrier_ok);
+	rc = disc->set_online(card, carrier_ok);
 	if (rc)
 		goto err_online;
 
@@ -5537,7 +5537,6 @@  static int qeth_set_online(struct qeth_card *card)
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 
 err_online:
@@ -5552,15 +5551,14 @@  static int qeth_set_online(struct qeth_card *card)
 	qdio_free(CARD_DDEV(card));
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
-int qeth_set_offline(struct qeth_card *card, bool resetting)
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting)
 {
 	int rc, rc2, rc3;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 3, "setoffl");
 
@@ -5581,7 +5579,7 @@  int qeth_set_offline(struct qeth_card *card, bool resetting)
 
 	cancel_work_sync(&card->rx_mode_work);
 
-	card->discipline->set_offline(card);
+	disc->set_offline(card);
 
 	qeth_qdio_clear_card(card, 0);
 	qeth_drain_output_queues(card);
@@ -5602,16 +5600,19 @@  int qeth_set_offline(struct qeth_card *card, bool resetting)
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_set_offline);
 
 static int qeth_do_reset(void *data)
 {
+	const struct qeth_discipline *disc;
 	struct qeth_card *card = data;
 	int rc;
 
+	/* Lock-free, other users will block until we are done. */
+	disc = card->discipline;
+
 	QETH_CARD_TEXT(card, 2, "recover1");
 	if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
 		return 0;
@@ -5619,8 +5620,8 @@  static int qeth_do_reset(void *data)
 	dev_warn(&card->gdev->dev,
 		 "A recovery process has been started for the device\n");
 
-	qeth_set_offline(card, true);
-	rc = qeth_set_online(card);
+	qeth_set_offline(card, disc, true);
+	rc = qeth_set_online(card, disc);
 	if (!rc) {
 		dev_info(&card->gdev->dev,
 			 "Device successfully recovered!\n");
@@ -6647,7 +6648,10 @@  static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		}
 	}
 
-	rc = qeth_set_online(card);
+	mutex_lock(&card->discipline_mutex);
+	rc = qeth_set_online(card, card->discipline);
+	mutex_unlock(&card->discipline_mutex);
+
 err:
 	return rc;
 }
@@ -6655,8 +6659,13 @@  static int qeth_core_set_online(struct ccwgroup_device *gdev)
 static int qeth_core_set_offline(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	return qeth_set_offline(card, false);
+	mutex_lock(&card->discipline_mutex);
+	rc = qeth_set_offline(card, card->discipline, false);
+	mutex_unlock(&card->discipline_mutex);
+
+	return rc;
 }
 
 static void qeth_core_shutdown(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 4ed0fb0705a5..37279b1e29f6 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -2207,8 +2207,11 @@  static void qeth_l2_remove_device(struct ccwgroup_device *gdev)
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
-	if (gdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+	if (gdev->state == CCWGROUP_ONLINE) {
+		mutex_lock(&card->discipline_mutex);
+		qeth_set_offline(card, card->discipline, false);
+		mutex_unlock(&card->discipline_mutex);
+	}
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index d138ac432d01..8d474179ce98 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1970,8 +1970,11 @@  static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
-	if (cgdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+	if (cgdev->state == CCWGROUP_ONLINE) {
+		mutex_lock(&card->discipline_mutex);
+		qeth_set_offline(card, card->discipline, false);
+		mutex_unlock(&card->discipline_mutex);
+	}
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)