The commit f2a4d086ed4c ("openvswitch: Add packet truncation support.")
introduces packet truncation before sending to userspace upcall receiver.
This patch passes up the skb->len before truncation so that the upcall
receiver knows the original packet size. Potentially this will be used
by sFlow, where OVS translates sFlow config header=N to a sample action,
truncating packet to N byte in kernel datapath. Thus, only N bytes instead
of full-packet size is copied from kernel to userspace, saving the
kernel-to-userspace bandwidth.
Signed-off-by: William Tu <u9012...@gmail.com>
Cc: Pravin Shelar <pshe...@nicira.com>
---
v1->v2:
- pass skb->len to userspace instead of cutlen
---
include/uapi/linux/openvswitch.h | 2 ++
net/openvswitch/actions.c | 1 +
net/openvswitch/datapath.c | 15 +++++++++++++++
net/openvswitch/datapath.h | 2 ++
4 files changed, 20 insertions(+)
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 8274675..f9e204e 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -166,6 +166,7 @@ enum ovs_packet_cmd {
* output port is actually a tunnel port. Contains the output tunnel key
* extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
* @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
+ * @OVS_PACKET_ATTR_SKBLEN: Packet size before truncation.
* %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
* size.
*
@@ -185,6 +186,7 @@ enum ovs_packet_attr {
OVS_PACKET_ATTR_PROBE, /* Packet operation is a feature probe,
error logging should be suppressed. */
OVS_PACKET_ATTR_MRU, /* Maximum received IP fragment size. */
+ OVS_PACKET_ATTR_SKBLEN, /* Packet size before truncation. */
__OVS_PACKET_ATTR_MAX
};
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1ecbd77..bb18ca1 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -793,6 +793,7 @@ static int output_userspace(struct datapath *dp, struct
sk_buff *skb,
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
+ upcall.skblen = skb->len;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6739342..3866d87 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -277,6 +277,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct
sw_flow_key *key)
upcall.cmd = OVS_PACKET_CMD_MISS;
upcall.portid = ovs_vport_find_upcall_portid(p, skb);
upcall.mru = OVS_CB(skb)->mru;
+ upcall.skblen = skb->len;
error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
if (unlikely(error))
kfree_skb(skb);
@@ -405,6 +406,10 @@ static size_t upcall_msg_size(const struct dp_upcall_info
*upcall_info,
if (upcall_info->mru)
size += nla_total_size(sizeof(upcall_info->mru));
+ /* OVS_PACKET_ATTR_SKBLEN */
+ if (upcall_info->skblen)
+ size += nla_total_size(sizeof(upcall_info->skblen));
+
return size;
}
@@ -514,6 +519,16 @@ static int queue_userspace_packet(struct datapath *dp,
struct sk_buff *skb,
pad_packet(dp, user_skb);
}
+ /* Add OVS_PACKET_ATTR_SKBLEN */
+ if (upcall_info->skblen) {
+ if (nla_put_u32(user_skb, OVS_PACKET_ATTR_SKBLEN,
+ upcall_info->skblen)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+ pad_packet(dp, user_skb);
+ }
+
/* Only reserve room for attribute header, packet data is added
* in skb_zerocopy() */
if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ab85c1c..f87f526 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -120,6 +120,7 @@ struct ovs_skb_cb {
* counter.
* @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
* @mru: If not zero, Maximum received IP fragment size.
+ * @skblen: The packet size before truncation.
*/
struct dp_upcall_info {
struct ip_tunnel_info *egress_tun_info;
@@ -129,6 +130,7 @@ struct dp_upcall_info {
u32 portid;
u8 cmd;
u16 mru;
+ u32 skblen;
};
/**
--
2.5.0
