[PATCH net] netvsc: reduce maximum GSO size

Subsystems: hyper-v/azure core and drivers, networking drivers, the rest

STALE3549d

2 messages, 2 authors, 2016-12-07 · open the first message on its own page

[PATCH net] netvsc: reduce maximum GSO size

From: Stephen Hemminger <stephen@networkplumber.org>
Date: 2016-12-06 21:44:13

Hyper-V (and Azure) support using NVGRE which requires some extra space
for encapsulation headers. Because of this the largest allowed TSO
packet is reduced.

For older releases, hard code a fixed reduced value.  For next release,
there is a better solution which uses result of host offload
negotiation.

Signed-off-by: Stephen Hemminger <redacted>
---
Please queue this for stable as well.

 drivers/net/hyperv/netvsc_drv.c | 5 +++++
 1 file changed, 5 insertions(+)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f638215..c9140c3 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -47,6 +47,10 @@
 				 NETIF_F_TSO | \
 				 NETIF_F_TSO6 | \
 				 NETIF_F_HW_CSUM)
+
+/* Restrict GSO size to account for NVGRE */
+#define NETVSC_GSO_MAX_SIZE	62768
+
 static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
@@ -1400,6 +1404,7 @@ static int netvsc_probe(struct hv_device *dev,
 	nvdev = net_device_ctx->nvdev;
 	netif_set_real_num_tx_queues(net, nvdev->num_chn);
 	netif_set_real_num_rx_queues(net, nvdev->num_chn);
+	netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE);
 
 	ret = register_netdev(net);
 	if (ret != 0) {
-- 
2.10.2

Re: [PATCH net] netvsc: reduce maximum GSO size

From: David Miller <davem@davemloft.net>
Date: 2016-12-07 18:14:05

From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue,  6 Dec 2016 13:43:54 -0800
Hyper-V (and Azure) support using NVGRE which requires some extra space
for encapsulation headers. Because of this the largest allowed TSO
packet is reduced.

For older releases, hard code a fixed reduced value.  For next release,
there is a better solution which uses result of host offload
negotiation.

Signed-off-by: Stephen Hemminger <redacted>
---
Please queue this for stable as well.
Applied and queued up for -stable, thanks.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help