ibmvnic: Harden device login requests

BugLink: https://bugs.launchpad.net/bugs/1885942
[ Upstream commit dff515a3e71dc8ab3b9dcc2e23a9b5fca88b3c18 ]

The VNIC driver's "login" command sequence is the final step
in the driver's initialization process with device firmware,
confirming the available device queue resources to be utilized
by the driver. Under high system load, firmware may not respond
to the request in a timely manner or may abort the request. In
such cases, the driver should reattempt the login command
sequence. In case of a device error, the number of retries
is bounded.

Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.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: Kelsey Skunberg <kelsey.skunberg@canonical.com>

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5a42ddeecfe50c2212564aa4189a16676335c525..4f503b9a674c409c053c960117e1c786209ddbe9 100644 (file)
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -779,12 +779,13 @@ static int ibmvnic_login(struct net_device *netdev)
        struct ibmvnic_adapter *adapter = netdev_priv(netdev);
        unsigned long timeout = msecs_to_jiffies(30000);
        int retry_count = 0;
+       int retries = 10;
        bool retry;
        int rc;
 
        do {
                retry = false;
-               if (retry_count > IBMVNIC_MAX_QUEUES) {
+               if (retry_count > retries) {
                        netdev_warn(netdev, "Login attempts exceeded\n");
                        return -1;
                }
@@ -799,11 +800,23 @@ static int ibmvnic_login(struct net_device *netdev)
 
                if (!wait_for_completion_timeout(&adapter->init_done,
                                                 timeout)) {
-                       netdev_warn(netdev, "Login timed out\n");
-                       return -1;
+                       netdev_warn(netdev, "Login timed out, retrying...\n");
+                       retry = true;
+                       adapter->init_done_rc = 0;
+                       retry_count++;
+                       continue;
                }
 
-               if (adapter->init_done_rc == PARTIALSUCCESS) {
+               if (adapter->init_done_rc == ABORTED) {
+                       netdev_warn(netdev, "Login aborted, retrying...\n");
+                       retry = true;
+                       adapter->init_done_rc = 0;
+                       retry_count++;
+                       /* FW or device may be busy, so
+                        * wait a bit before retrying login
+                        */
+                       msleep(500);
+               } else if (adapter->init_done_rc == PARTIALSUCCESS) {
                        retry_count++;
                        release_sub_crqs(adapter, 1);