qede: fix crash in rmmod qede while automatic debug collection

BugLink: https://bugs.launchpad.net/bugs/1943756
[ Upstream commit 1159e25c137422bdc48ee96e3fb014bd942092c6 ]

A crash has been observed if rmmod is done while automatic debug
collection in progress. It is due to a race  condition between
both of them.

To fix stop the sp_task during unload to avoid running qede_sp_task
even if they are schedule during removal process.

Signed-off-by: Alok Prasad <palok@marvell.com>
Signed-off-by: Shai Malin <smalin@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Prabhakar Kushwaha <pkushwaha@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 3efc5899f65630d133bd482b6d014d2454b95d53..f313fd7303316fd9d8d0dde4ee2cbfc68106c23d 100644 (file)
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -494,6 +494,7 @@ struct qede_fastpath {
 #define QEDE_SP_HW_ERR                  4
 #define QEDE_SP_ARFS_CONFIG             5
 #define QEDE_SP_AER                    7
+#define QEDE_SP_DISABLE                        8
 
 #ifdef CONFIG_RFS_ACCEL
 int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 9cf960a6d0078820ac83f5dfdd8d24d82c0a5939..62e5786b7d72c381e053af94900e5ac42f58066c 100644 (file)
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1006,6 +1006,13 @@ static void qede_sp_task(struct work_struct *work)
        struct qede_dev *edev = container_of(work, struct qede_dev,
                                             sp_task.work);
 
+       /* Disable execution of this deferred work once
+        * qede removal is in progress, this stop any future
+        * scheduling of sp_task.
+        */
+       if (test_bit(QEDE_SP_DISABLE, &edev->sp_flags))
+               return;
+
        /* The locking scheme depends on the specific flag:
         * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to
         * ensure that ongoing flows are ended and new ones are not started.
@@ -1297,6 +1304,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
        qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY));
 
        if (mode != QEDE_REMOVE_RECOVERY) {
+               set_bit(QEDE_SP_DISABLE, &edev->sp_flags);
                unregister_netdev(ndev);
 
                cancel_delayed_work_sync(&edev->sp_task);