-----Original Message-----Remote NDIS is the protocol used to send packets from the guest to the host. Every packet
From: David Laight [mailto:David.Laight@xxxxxxxxxx]
Sent: Wednesday, September 16, 2015 9:25 AM
To: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>; Vitaly Kuznetsov
<vkuznets@xxxxxxxxxx>; netdev@xxxxxxxxxxxxxxx
Cc: David S. Miller <davem@xxxxxxxxxxxxx>; linux-kernel@xxxxxxxxxxxxxxx;
KY Srinivasan <kys@xxxxxxxxxxxxx>; Jason Wang <jasowang@xxxxxxxxxx>
Subject: RE: [PATCH net-next RFC] net: increase LL_MAX_HEADER for Hyper-
V
From: Haiyang Zhang
Sent: 16 September 2015 17:09kernel@xxxxxxxxxxxxxxx;
-----Original Message-----
From: Vitaly Kuznetsov [mailto:vkuznets@xxxxxxxxxx]
Sent: Wednesday, September 16, 2015 11:50 AM
To: netdev@xxxxxxxxxxxxxxx
Cc: David S. Miller <davem@xxxxxxxxxxxxx>; linux-
VKY Srinivasan <kys@xxxxxxxxxxxxx>; Haiyang Zhang
<haiyangz@xxxxxxxxxxxxx>; Jason Wang <jasowang@xxxxxxxxxx>
Subject: [PATCH net-next RFC] net: increase LL_MAX_HEADER for Hyper-
EliminateCommit b08cc79155fc26d0d112b1470d1ece5034651a4b ("hv_netvsc:
path,memory allocation in the packet send path") introduced skb headroom
request for Hyper-V netvsc driver:
max_needed_headroom = sizeof(struct hv_netvsc_packet) +
sizeof(struct rndis_message) +
NDIS_VLAN_PPI_SIZE + NDIS_CSUM_PPI_SIZE +
NDIS_LSO_PPI_SIZE + NDIS_HASH_PPI_SIZE;
...
net->needed_headroom = max_needed_headroom;
max_needed_headroom is 220 bytes, it significantly exceeds the
LL_MAX_HEADER setting. This causes each skb to be cloned on send
LL_MAX_HEADERe.g. for IPv4 case we fall into the following clause
(ip_finish_output2()):
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
...
skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
...
}
leading to a significant performance regression. Increase
HVNETVSC_MAX_HEADER.to make it suitable for netvsc, make it 224 to be 16-aligned.Thanks for the patch.
Alternatively we could (partially) revert the commit which introduced
skb
headroom request restoring manual memory allocation on transmit path.
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
include/linux/netdevice.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88a0069..7233790 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -132,7 +132,9 @@ static inline bool dev_xmit_complete(int rc)
* used.
*/
-#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
+#if IS_ENABLED(CONFIG_HYPERV_NET)
+# define LL_MAX_HEADER 224
+#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
# if defined(CONFIG_MAC80211_MESH)
# define LL_MAX_HEADER 128
# else
To avoid we forget to update that 224 number when we add more things
into netvsc header, I suggest that we define a macro in netdevice.h such
as:
#define HVNETVSC_MAX_HEADER 224
#define LL_MAX_HEADER HVNETVSC_MAX_HEADER
And, put a note in netvsc code saying the header reservation shouldn't
exceed HVNETVSC_MAX_HEADER, or you need to update
Am I right in thinking this is adding an extra 96 unused bytes to the front
of almost all skb just so that hyper-v can make its link level header
contiguous with whatever follows (IP header ?).
Doesn't sound ideal.
needs to be decorated with the RNDIS header and the maximum room needed for the RNDIS
header is the hreadroom we want.