diff options
author | David S. Miller <davem@davemloft.net> | 2018-11-08 03:23:05 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-11-08 03:23:05 +0300 |
commit | cab6949bf70a68ee5aada5f1973c0bb906d354cf (patch) | |
tree | 49e779a4dbf7f0641b0a983253bbc3aa342782a7 /include | |
parent | 7e225619e8afc432fb054ef135f10c11cf8cfc85 (diff) | |
parent | 3327a9c46352f111697d93d6134e7bf37c6bffca (diff) | |
download | linux-cab6949bf70a68ee5aada5f1973c0bb906d354cf.tar.xz |
Merge branch 'udp-gro'
Paolo Abeni says:
====================
udp: implement GRO support
This series implements GRO support for UDP sockets, as the RX counterpart
of commit bec1f6f69736 ("udp: generate gso with UDP_SEGMENT").
The core functionality is implemented by the second patch, introducing a new
sockopt to enable UDP_GRO, while patch 3 implements support for passing the
segment size to the user space via a new cmsg.
UDP GRO performs a socket lookup for each ingress packets and aggregate datagram
directed to UDP GRO enabled sockets with constant l4 tuple.
UDP GRO packets can land on non GRO-enabled sockets, e.g. due to iptables NAT
rules, and that could potentially confuse existing applications.
The solution adopted here is to de-segment the GRO packet before enqueuing
as needed. Since we must cope with packet reinsertion after de-segmentation,
the relevant code is factored-out in ipv4 and ipv6 specific helpers and exposed
to UDP usage.
While the current code can probably be improved, this safeguard ,implemented in
the patches 4-7, allows future enachements to enable UDP GSO offload on more
virtual devices eventually even on forwarded packets.
The last 4 for patches implement some performance and functional self-tests,
re-using the existing udpgso infrastructure. The problematic scenario described
above is explicitly tested.
This revision of the series try to address the feedback provided by Willem and
Subash on previous iteration.
====================
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/udp.h | 25 | ||||
-rw-r--r-- | include/net/ip.h | 1 | ||||
-rw-r--r-- | include/net/ipv6.h | 2 | ||||
-rw-r--r-- | include/net/udp.h | 45 | ||||
-rw-r--r-- | include/net/udp_tunnel.h | 6 | ||||
-rw-r--r-- | include/uapi/linux/udp.h | 1 |
6 files changed, 71 insertions, 9 deletions
diff --git a/include/linux/udp.h b/include/linux/udp.h index 320d49d85484..0a9c54e76305 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -49,7 +49,13 @@ struct udp_sock { unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */ + no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ + encap_enabled:1, /* This socket enabled encap + * processing; UDP tunnels and + * different encapsulation layer set + * this + */ + gro_enabled:1; /* Can accept GRO packets */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -115,6 +121,23 @@ static inline bool udp_get_no_check6_rx(struct sock *sk) return udp_sk(sk)->no_check6_rx; } +static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + int gso_size; + + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + gso_size = skb_shinfo(skb)->gso_size; + put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size); + } +} + +static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) +{ + return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) && + skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4; +} + #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) diff --git a/include/net/ip.h b/include/net/ip.h index 462182f78236..8866bfce6121 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); +void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 829650540780..daf80863d3a5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); +void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, + bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/udp.h b/include/net/udp.h index a496e441645e..eccca2325ee6 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -417,17 +417,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, } while(0) #if IS_ENABLED(CONFIG_IPV6) -#define __UDPX_INC_STATS(sk, field) \ -do { \ - if ((sk)->sk_family == AF_INET) \ - __UDP_INC_STATS(sock_net(sk), field, 0); \ - else \ - __UDP6_INC_STATS(sock_net(sk), field, 0); \ -} while (0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics) : \ + (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ + sock_net(sk)->mib.udp_stats_in6); \ +}) #else -#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics; \ +}) #endif +#define __UDPX_INC_STATS(sk, field) \ + __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) + #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; @@ -461,4 +468,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif +static inline struct sk_buff *udp_rcv_segment(struct sock *sk, + struct sk_buff *skb, bool ipv4) +{ + struct sk_buff *segs; + + /* the GSO CB lays after the UDP one, no need to save and restore any + * CB fragment + */ + segs = __skb_gso_segment(skb, NETIF_F_SG, false); + if (unlikely(IS_ERR_OR_NULL(segs))) { + int segs_nr = skb_shinfo(skb)->gso_segs; + + atomic_add(segs_nr, &sk->sk_drops); + SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); + kfree_skb(skb); + return NULL; + } + + consume_skb(skb); + return segs; +} + #endif /* _UDP_H */ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index fe680ab6b15a..3fbe56430e3b 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -165,6 +165,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) static inline void udp_tunnel_encap_enable(struct socket *sock) { + struct udp_sock *up = udp_sk(sock->sk); + + if (up->encap_enabled) + return; + + up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 09502de447f5..30baccb6c9c4 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -33,6 +33,7 @@ struct udphdr { #define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */ #define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */ #define UDP_SEGMENT 103 /* Set GSO segmentation size */ +#define UDP_GRO 104 /* This socket can receive UDP GRO packets */ /* UDP encapsulation types */ #define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ |