[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240416164128.387920-1-nnac123@linux.ibm.com>
Date: Tue, 16 Apr 2024 11:41:28 -0500
From: Nick Child <nnac123@...ux.ibm.com>
To: netdev@...r.kernel.org
Cc: haren@...ux.ibm.com, ricklind@...ibm.com, mmc@...ux.ibm.com,
Nick Child <nnac123@...ux.ibm.com>
Subject: [PATCH v2 net-next] ibmvnic: Return error code on TX scrq flush fail
In ibmvnic_xmit() if ibmvnic_tx_scrq_flush() returns H_CLOSED then
it will inform upper level networking functions to disable tx
queues. H_CLOSED signals that the connection with the vnic server is
down and a transport event is expected to recover the device.
Previously, ibmvnic_tx_scrq_flush() was hard-coded to return success.
Therefore, the queues would remain active until ibmvnic_cleanup() is
called within do_reset().
The problem is that do_reset() depends on the RTNL lock. If several
ibmvnic devices are resetting then there can be a long wait time until
the last device can grab the lock. During this time the tx/rx queues
still appear active to upper level functions.
FYI, we do make a call to netif_carrier_off() outside the RTNL lock but
its calls to dev_deactivate() are also dependent on the RTNL lock.
As a result, large amounts of retransmissions were observed in a short
period of time, eventually leading to ETIMEOUT. This was specifically
seen with HNV devices, likely because of even more RTNL dependencies.
Therefore, ensure the return code of ibmvnic_tx_scrq_flush() is
propagated to the xmit function to allow for an earlier (and lock-less)
response to a transport event.
Signed-off-by: Nick Child <nnac123@...ux.ibm.com>
---
v1 - https://lore.kernel.org/netdev/20240414102337.GA645060@kernel.org/
Changes:
- Edit based on Simon's review (thanks!), all callers of
ibmvnic_tx_scrq_flush should respoind to the return code
drivers/net/ethernet/ibm/ibmvnic.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 30c47b8470ad..5e9a93bdb518 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2371,7 +2371,7 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
else
ind_bufp->index = 0;
- return 0;
+ return rc;
}
static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
@@ -2424,7 +2424,9 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
tx_dropped++;
tx_send_failed++;
ret = NETDEV_TX_OK;
- ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+ lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+ if (lpar_rc != H_SUCCESS)
+ goto tx_err;
goto out;
}
@@ -2439,8 +2441,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
dev_kfree_skb_any(skb);
tx_send_failed++;
tx_dropped++;
- ibmvnic_tx_scrq_flush(adapter, tx_scrq);
ret = NETDEV_TX_OK;
+ lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+ if (lpar_rc != H_SUCCESS)
+ goto tx_err;
goto out;
}
--
2.39.3
Powered by blists - more mailing lists