summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2015-01-14 15:20:11 -0500
committerDavid S. Miller <davem@davemloft.net>2015-01-14 15:20:11 -0500
commit2733135329e9bbc306be9f58af1b4be92b359d23 (patch)
treeae1ac810501bacae10209b8faa94595fc10c3884 /include
parentd823ab68fbb0fa504a2490bd499ac921bdf497d8 (diff)
parentdfd8645ea1bd91277f841e74c33e1f4dbbede808 (diff)
Merge branch 'vxlan_rco'
Tom Herbert says: ==================== net: Remote checksum offload for VXLAN This patch set adds support for remote checksum offload in VXLAN. The remote checksum offload is generalized by creating a common function (remcsum_adjust) that does the work of modifying the checksum in remote checksum offload. This function can be called from normal or GRO path. GUE was modified to use this function. To support RCO is VXLAN we use the 9th bit in the reserved flags to indicated remote checksum offload. The start and offset values are encoded n a compressed form in the low order (reserved) byte of the vni field. Remote checksum offload is described in https://tools.ietf.org/html/draft-herbert-remotecsumoffload-01 Changes in v2: - Add udp_offload_callbacks which has GRO functions that take a udp_offload pointer argument. This argument can be used to retrieve a per port structure of the encapsulation for use in gro processing (mostly by doing container_of on the structure). - Use the 10th bit in VXLAN flags for RCO which does not seem to conflict with other proposals at this time (ie. VXLAN-GPE and VXLAN-GPB) - Require that RCO must be explicitly enabled on the receiver as well as the sender. Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r--include/linux/netdevice.h15
-rw-r--r--include/net/vxlan.h11
-rw-r--r--include/uapi/linux/if_link.h2
3 files changed, 26 insertions, 2 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 679e6e90aa4c..47921c291dd6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1969,7 +1969,7 @@ struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
struct sk_buff **(*gro_receive)(struct sk_buff **head,
- struct sk_buff *skb);
+ struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
};
@@ -1979,10 +1979,21 @@ struct packet_offload {
struct list_head list;
};
+struct udp_offload;
+
+struct udp_offload_callbacks {
+ struct sk_buff **(*gro_receive)(struct sk_buff **head,
+ struct sk_buff *skb,
+ struct udp_offload *uoff);
+ int (*gro_complete)(struct sk_buff *skb,
+ int nhoff,
+ struct udp_offload *uoff);
+};
+
struct udp_offload {
__be16 port;
u8 ipproto;
- struct offload_callbacks callbacks;
+ struct udp_offload_callbacks callbacks;
};
/* often modified stats are per cpu, other are shared (netdev->stats) */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index a0d80736224f..0a7443b49133 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -19,6 +19,14 @@ struct vxlanhdr {
/* VXLAN header flags. */
#define VXLAN_HF_VNI 0x08000000
+#define VXLAN_HF_RCO 0x00200000
+
+/* Remote checksum offload header option */
+#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
+#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
#define VXLAN_N_VID (1u << 24)
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
@@ -38,6 +46,7 @@ struct vxlan_sock {
struct hlist_head vni_list[VNI_HASH_SIZE];
atomic_t refcnt;
struct udp_offload udp_offloads;
+ u32 flags;
};
#define VXLAN_F_LEARN 0x01
@@ -49,6 +58,8 @@ struct vxlan_sock {
#define VXLAN_F_UDP_CSUM 0x40
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
+#define VXLAN_F_REMCSUM_TX 0x200
+#define VXLAN_F_REMCSUM_RX 0x400
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index f7d0d2d7173a..b2723f65846f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -370,6 +370,8 @@ enum {
IFLA_VXLAN_UDP_CSUM,
IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+ IFLA_VXLAN_REMCSUM_TX,
+ IFLA_VXLAN_REMCSUM_RX,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)