4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <jakub.kicinski@xxxxxxxxxxxxx>
commit 46f1c52e66dbc0d7a99f7c2a3c9debb497fe7b7b upstream.
TX completion may happen any time after HW queue was kicked.
We can't access the skb afterwards. Move the time stamping
before ringing the doorbell.
Fixes: 4c3523623dc0 ("net: add driver for Netronome NFP4000/NFP6000 NIC VFs")
Signed-off-by: Jakub Kicinski <jakub.kicinski@xxxxxxxxxxxxx>
Reviewed-by: Simon Horman <simon.horman@xxxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Willy Tarreau <w@xxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -854,6 +854,8 @@ static int nfp_net_tx(struct sk_buff *sk
netdev_tx_sent_queue(nd_q, txbuf->real_len);
+ skb_tx_timestamp(skb);
+
tx_ring->wr_p += nr_frags + 1;
if (nfp_net_tx_ring_should_stop(tx_ring))
nfp_net_tx_ring_stop(nd_q, tx_ring);
@@ -866,8 +868,6 @@ static int nfp_net_tx(struct sk_buff *sk
tx_ring->wr_ptr_add = 0;
}
- skb_tx_timestamp(skb);
-
return NETDEV_TX_OK;
err_unmap:
