From 9c3f1a9e0cd90e87c29e71d39e8b5677ae38ef43 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Mon, 15 Jun 2020 10:29:23 -0500 Subject: [PATCH] ibmvnic: Harden device login requests 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 Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1b4d04e4474bb..2baf7b3ff4cbf 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -842,12 +842,13 @@ 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; } @@ -862,11 +863,23 @@ 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); -- 2.39.5