diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-04 20:41:05 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-04 20:41:05 +0300 |
commit | b0f85fa11aefc4f3e03306b4cd47f113bd57dcba (patch) | |
tree | 1333d36d99fde3f97210795941fc246f0ad08a75 /net/openvswitch | |
parent | ccc9d4a6d640cbde05d519edeb727881646cf71b (diff) | |
parent | f32bfb9a8ca083f8d148ea90ae5ba66f4831836e (diff) | |
download | linux-b0f85fa11aefc4f3e03306b4cd47f113bd57dcba.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
Changes of note:
1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.
2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
David Ahern.
3) Allow the user to ask for the statistics to be filtered out of
ipv4/ipv6 address netlink dumps. From Sowmini Varadhan.
4) More work to pass the network namespace context around deep into
various packet path APIs, starting with the netfilter hooks. From
Eric W Biederman.
5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
Richter.
6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.
7) Support Very High Throughput in wireless MESH code, from Bob
Copeland.
8) Allow setting the ageing_time in switchdev/rocker. From Scott
Feldman.
9) Properly autoload L2TP type modules, from Stephen Hemminger.
10) Fix and enable offload features by default in 8139cp driver, from
David Woodhouse.
11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
Jiri Benc.
12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
Opstad.
13) Fix IPSEC flowcache overflows on large systems, from Steffen
Klassert.
14) Convert bridging to track VLANs using rhashtable entries rather than
a bitmap. From Nikolay Aleksandrov.
15) Make TCP listener handling completely lockless, this is a major
accomplishment. Incoming request sockets now live in the
established hash table just like any other socket too.
From Eric Dumazet.
15) Provide more bridging attributes to netlink, from Nikolay
Aleksandrov.
16) Use hash based algorithm for ipv4 multipath routing, this was very
long overdue. From Peter Nørlund.
17) Several y2038 cures, mostly avoiding timespec. From Arnd Bergmann.
18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.
19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet. This
influences the port binding selection logic used by SO_REUSEPORT.
20) Add ipv6 support to VRF, from David Ahern.
21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.
22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.
23) Implement RACK loss recovery in TCP, from Yuchung Cheng.
24) Support multipath routes in MPLS, from Roopa Prabhu.
25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
Dumazet.
26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
Sudarsana Kalluru.
27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
Sowa.
28) Support ipv6 geneve tunnels, from John W Linville.
29) Add flood control support to switchdev layer, from Ido Schimmel.
30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
Hannes Frederic Sowa.
31) Support persistent maps and progs in bpf, from Daniel Borkmann.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
sh_eth: use DMA barriers
switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
net: sched: kill dead code in sch_choke.c
irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
net: dsa: mv88e6xxx: include DSA ports in VLANs
net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
net/core: fix for_each_netdev_feature
vlan: Invoke driver vlan hooks only if device is present
arcnet/com20020: add LEDS_CLASS dependency
bpf, verifier: annotate verbose printer with __printf
dp83640: Only wait for timestamps for packets with timestamping enabled.
ptp: Change ptp_class to a proper bitmask
dp83640: Prune rx timestamp list before reading from it
dp83640: Delay scheduled work.
dp83640: Include hash in timestamp/packet matching
ipv6: fix tunnel error handling
net/mlx5e: Fix LSO vlan insertion
net/mlx5e: Re-eanble client vlan TX acceleration
net/mlx5e: Return error in case mlx5e_set_features() fails
net/mlx5e: Don't allow more than max supported channels
...
Diffstat (limited to 'net/openvswitch')
-rw-r--r-- | net/openvswitch/actions.c | 13 | ||||
-rw-r--r-- | net/openvswitch/conntrack.c | 6 | ||||
-rw-r--r-- | net/openvswitch/datapath.c | 3 | ||||
-rw-r--r-- | net/openvswitch/flow.c | 4 | ||||
-rw-r--r-- | net/openvswitch/flow.h | 1 | ||||
-rw-r--r-- | net/openvswitch/flow_netlink.c | 126 | ||||
-rw-r--r-- | net/openvswitch/flow_table.c | 2 | ||||
-rw-r--r-- | net/openvswitch/vport-geneve.c | 2 | ||||
-rw-r--r-- | net/openvswitch/vport-gre.c | 2 | ||||
-rw-r--r-- | net/openvswitch/vport-internal_dev.c | 8 | ||||
-rw-r--r-- | net/openvswitch/vport-netdev.c | 33 | ||||
-rw-r--r-- | net/openvswitch/vport-netdev.h | 1 | ||||
-rw-r--r-- | net/openvswitch/vport-vxlan.c | 2 | ||||
-rw-r--r-- | net/openvswitch/vport.c | 30 | ||||
-rw-r--r-- | net/openvswitch/vport.h | 22 |
15 files changed, 161 insertions, 94 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index dba635d086b2..c88d0f2d3e01 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -620,7 +620,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int ovs_vport_output(struct sock *sock, struct sk_buff *skb) +static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); struct vport *vport = data->vport; @@ -679,8 +679,8 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb) skb_pull(skb, hlen); } -static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, - __be16 ethertype) +static void ovs_fragment(struct net *net, struct vport *vport, + struct sk_buff *skb, u16 mru, __be16 ethertype) { if (skb_network_offset(skb) > MAX_L2_LEN) { OVS_NLERR(1, "L2 header too long to fragment"); @@ -700,7 +700,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, skb_dst_set_noref(skb, &ovs_dst); IPCB(skb)->frag_max_size = mru; - ip_do_fragment(skb->sk, skb, ovs_vport_output); + ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (ethertype == htons(ETH_P_IPV6)) { const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); @@ -721,7 +721,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(skb->sk, skb, ovs_vport_output); + v6ops->fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", @@ -746,6 +746,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, if (likely(!mru || (skb->len <= mru + ETH_HLEN))) { ovs_vport_send(vport, skb); } else if (mru <= vport->dev->mtu) { + struct net *net = read_pnet(&dp->net); __be16 ethertype = key->eth.type; if (!is_flow_key_valid(key)) { @@ -755,7 +756,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, ethertype = vlan_get_protocol(skb); } - ovs_fragment(vport, skb, mru, ethertype); + ovs_fragment(net, vport, skb, mru, ethertype); } else { kfree_skb(skb); } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 50095820edb7..c2cc11168fd5 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -306,7 +306,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, int err; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - err = ip_defrag(skb, user); + err = ip_defrag(net, skb, user); if (err) return err; @@ -317,7 +317,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, struct sk_buff *reasm; memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - reasm = nf_ct_frag6_gather(skb, user); + reasm = nf_ct_frag6_gather(net, skb, user); if (!reasm) return -EINPROGRESS; @@ -357,7 +357,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, { struct nf_conntrack_tuple tuple; - if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple)) + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple)) return NULL; return __nf_ct_expect_find(net, zone, &tuple); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c5d08ee37730..5633172b791a 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -91,8 +91,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info, static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { - genl_notify(family, skb, genl_info_net(info), info->snd_portid, - 0, info->nlhdr, GFP_KERNEL); + genl_notify(family, skb, info, 0, GFP_KERNEL); } /** diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index c8db44ab2ee7..0ea128eeeab2 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -698,8 +698,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, { /* Extract metadata from packet. */ if (tun_info) { - if (ip_tunnel_info_af(tun_info) != AF_INET) - return -EINVAL; + key->tun_proto = ip_tunnel_info_af(tun_info); memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key)); if (tun_info->options_len) { @@ -714,6 +713,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->tun_opts_len = 0; } } else { + key->tun_proto = 0; key->tun_opts_len = 0; memset(&key->tun_key, 0, sizeof(key->tun_key)); } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 8cfa15a08668..1d055c559eaf 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -63,6 +63,7 @@ struct sw_flow_key { u32 skb_mark; /* SKB mark. */ u16 in_port; /* Input switch port (or DP_MAX_PORTS). */ } __packed phy; /* Safe when right after 'tun_key'. */ + u8 tun_proto; /* Protocol of encapsulating tunnel. */ u32 ovs_flow_hash; /* Datapath computed hash value. */ u32 recirc_id; /* Recirculation ID. */ struct { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 38536c137c54..907d6fd28ede 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -262,8 +262,8 @@ size_t ovs_tun_key_attr_size(void) * updating this function. */ return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ @@ -323,6 +323,8 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, .next = ovs_vxlan_ext_key_lens }, + [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -542,15 +544,15 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int ipv4_tun_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) +static int ip_tun_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) { - struct nlattr *a; - int rem; - bool ttl = false; + bool ttl = false, ipv4 = false, ipv6 = false; __be16 tun_flags = 0; int opts_type = 0; + struct nlattr *a; + int rem; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); @@ -578,10 +580,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, nla_get_in_addr(a), is_mask); + ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst, nla_get_in_addr(a), is_mask); + ipv4 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_DST: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; break; case OVS_TUNNEL_KEY_ATTR_TOS: SW_FLOW_KEY_PUT(match, tun_key.tos, @@ -636,28 +650,46 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, opts_type = type; break; default: - OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d", + OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); return -EINVAL; } } SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask); + if (is_mask) + SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); + else + SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET, + false); if (rem > 0) { - OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.", + OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.", rem); return -EINVAL; } + if (ipv4 && ipv6) { + OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes"); + return -EINVAL; + } + if (!is_mask) { - if (!match->key->tun_key.u.ipv4.dst) { + if (!ipv4 && !ipv6) { + OVS_NLERR(log, "IP tunnel dst address not specified"); + return -EINVAL; + } + if (ipv4 && !match->key->tun_key.u.ipv4.dst) { OVS_NLERR(log, "IPv4 tunnel dst address is zero"); return -EINVAL; } + if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) { + OVS_NLERR(log, "IPv6 tunnel dst address is zero"); + return -EINVAL; + } if (!ttl) { - OVS_NLERR(log, "IPv4 tunnel TTL not specified."); + OVS_NLERR(log, "IP tunnel TTL not specified."); return -EINVAL; } } @@ -682,21 +714,36 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, return 0; } -static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int __ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; - if (output->u.ipv4.src && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, - output->u.ipv4.src)) - return -EMSGSIZE; - if (output->u.ipv4.dst && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, - output->u.ipv4.dst)) - return -EMSGSIZE; + switch (tun_proto) { + case AF_INET: + if (output->u.ipv4.src && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, + output->u.ipv4.src)) + return -EMSGSIZE; + if (output->u.ipv4.dst && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, + output->u.ipv4.dst)) + return -EMSGSIZE; + break; + case AF_INET6: + if (!ipv6_addr_any(&output->u.ipv6.src) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC, + &output->u.ipv6.src)) + return -EMSGSIZE; + if (!ipv6_addr_any(&output->u.ipv6.dst) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST, + &output->u.ipv6.dst)) + return -EMSGSIZE; + break; + } if (output->tos && nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos)) return -EMSGSIZE; @@ -730,9 +777,10 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, return 0; } -static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { struct nlattr *nla; int err; @@ -741,7 +789,8 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, if (!nla) return -EMSGSIZE; - err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len); + err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len, + tun_proto); if (err) return err; @@ -752,9 +801,10 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, int ovs_nla_put_tunnel_info(struct sk_buff *skb, struct ip_tunnel_info *tun_info) { - return __ipv4_tun_to_nlattr(skb, &tun_info->key, - ip_tunnel_info_opts(tun_info), - tun_info->options_len); + return __ip_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len, + ip_tunnel_info_af(tun_info)); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -805,8 +855,8 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, *attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK); } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { - if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, - is_mask, log) < 0) + if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, + is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } @@ -1202,7 +1252,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, /* The userspace does not send tunnel attributes that * are 0, but we should not wildcard them nonetheless. */ - if (match->key->tun_key.u.ipv4.dst) + if (match->key->tun_proto) SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true); @@ -1375,14 +1425,14 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) goto nla_put_failure; - if ((swkey->tun_key.u.ipv4.dst || is_mask)) { + if ((swkey->tun_proto || is_mask)) { const void *opts = NULL; if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); - if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, - swkey->tun_opts_len)) + if (ip_tun_to_nlattr(skb, &output->tun_key, opts, + swkey->tun_opts_len, swkey->tun_proto)) goto nla_put_failure; } @@ -1885,7 +1935,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, int err = 0, start, opts_type; ovs_match_init(&match, &key, NULL); - opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); + opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) return opts_type; @@ -1921,6 +1971,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, tun_info = &tun_dst->u.tun_info; tun_info->mode = IP_TUNNEL_INFO_TX; + if (key.tun_proto == AF_INET6) + tun_info->mode |= IP_TUNNEL_INFO_IPV6; tun_info->key = key.tun_key; /* We need to store the options in the action itself since diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index c7f74aab34b9..d073fff82fdb 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -428,7 +428,7 @@ static u32 flow_hash(const struct sw_flow_key *key, static int flow_key_start(const struct sw_flow_key *key) { - if (key->tun_key.u.ipv4.dst) + if (key->tun_proto) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 5f8aaaaa0785..efb736bb6855 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -116,7 +116,7 @@ static struct vport_ops ovs_geneve_vport_ops = { .create = geneve_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = geneve_get_options, - .send = ovs_netdev_send, + .send = dev_queue_xmit, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 64225bf5eb40..c3257d78d3d2 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -87,7 +87,7 @@ static struct vport *gre_create(const struct vport_parms *parms) static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, - .send = ovs_netdev_send, + .send = dev_queue_xmit, .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index b3934126daa8..ec76398a792f 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -242,22 +242,21 @@ static void internal_dev_destroy(struct vport *vport) rtnl_unlock(); } -static void internal_dev_recv(struct vport *vport, struct sk_buff *skb) +static netdev_tx_t internal_dev_recv(struct sk_buff *skb) { - struct net_device *netdev = vport->dev; + struct net_device *netdev = skb->dev; struct pcpu_sw_netstats *stats; if (unlikely(!(netdev->flags & IFF_UP))) { kfree_skb(skb); netdev->stats.rx_dropped++; - return; + return NETDEV_TX_OK; } skb_dst_drop(skb); nf_reset(skb); secpath_reset(skb); - skb->dev = netdev; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, netdev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -269,6 +268,7 @@ static void internal_dev_recv(struct vport *vport, struct sk_buff *skb) u64_stats_update_end(&stats->syncp); netif_rx(skb); + return NETDEV_TX_OK; } static struct vport_ops ovs_internal_vport_ops = { diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index f7e8dcce7ada..b327368a3848 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -190,37 +190,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); -static unsigned int packet_length(const struct sk_buff *skb) -{ - unsigned int length = skb->len - ETH_HLEN; - - if (skb->protocol == htons(ETH_P_8021Q)) - length -= VLAN_HLEN; - - return length; -} - -void ovs_netdev_send(struct vport *vport, struct sk_buff *skb) -{ - int mtu = vport->dev->mtu; - - if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { - net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - vport->dev->name, - packet_length(skb), mtu); - vport->dev->stats.tx_errors++; - goto drop; - } - - skb->dev = vport->dev; - dev_queue_xmit(skb); - return; - -drop: - kfree_skb(skb); -} -EXPORT_SYMBOL_GPL(ovs_netdev_send); - /* Returns null if this device is not attached to a datapath. */ struct vport *ovs_netdev_get_vport(struct net_device *dev) { @@ -235,7 +204,7 @@ static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, - .send = ovs_netdev_send, + .send = dev_queue_xmit, }; int __init ovs_netdev_init(void) diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index bf22fcedbc69..19e29c12adcc 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -27,7 +27,6 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); struct vport *ovs_netdev_link(struct vport *vport, const char *name); -void ovs_netdev_send(struct vport *vport, struct sk_buff *skb); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index e1c9c0888037..1605691d9414 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -151,7 +151,7 @@ static struct vport_ops ovs_vxlan_netdev_vport_ops = { .create = vxlan_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = vxlan_get_options, - .send = ovs_netdev_send, + .send = dev_queue_xmit, }; static int __init ovs_vxlan_tnl_init(void) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 320c765ce44a..0ac0fd004d7e 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -479,3 +479,33 @@ void ovs_vport_deferred_free(struct vport *vport) call_rcu(&vport->rcu, free_vport_rcu); } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); + +static unsigned int packet_length(const struct sk_buff *skb) +{ + unsigned int length = skb->len - ETH_HLEN; + + if (skb->protocol == htons(ETH_P_8021Q)) + length -= VLAN_HLEN; + + return length; +} + +void ovs_vport_send(struct vport *vport, struct sk_buff *skb) +{ + int mtu = vport->dev->mtu; + + if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { + net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", + vport->dev->name, + packet_length(skb), mtu); + vport->dev->stats.tx_errors++; + goto drop; + } + + skb->dev = vport->dev; + vport->ops->send(skb); + return; + +drop: + kfree_skb(skb); +} diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index d341ad6f3afe..bdfd82a7c064 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -140,7 +140,7 @@ struct vport_ops { int (*set_options)(struct vport *, struct nlattr *); int (*get_options)(const struct vport *, struct sk_buff *); - void (*send)(struct vport *, struct sk_buff *); + netdev_tx_t (*send) (struct sk_buff *skb); struct module *owner; struct list_head list; }; @@ -199,9 +199,25 @@ static inline const char *ovs_vport_name(struct vport *vport) int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); -static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb) +static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, + const struct ip_tunnel_key *key, + u32 mark, + struct flowi4 *fl, + u8 protocol) { - vport->ops->send(vport, skb); + struct rtable *rt; + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->u.ipv4.dst; + fl->saddr = key->u.ipv4.src; + fl->flowi4_tos = RT_TOS(key->tos); + fl->flowi4_mark = mark; + fl->flowi4_proto = protocol; + + rt = ip_route_output_key(net, fl); + return rt; } +void ovs_vport_send(struct vport *vport, struct sk_buff *skb); + #endif /* vport.h */ |