From 1d8fff907342d2339796dbd27ea47d0e76a6a2d0 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 21 Jul 2015 10:43:54 +0200 Subject: ip_tunnel: Make ovs_tunnel_info and ovs_key_ipv4_tunnel generic Rename the tunnel metadata data structures currently internal to OVS and make them generic for use by all IP tunnels. Both structures are kernel internal and will stay that way. Their members are exposed to user space through individual Netlink attributes by OVS. It will therefore be possible to extend/modify these structures without affecting user ABI. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8a8c0b8b4f63..27c1687cfd92 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -611,7 +611,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ovs_tunnel_info info; + struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; -- cgit v1.2.3 From 34ae932a40369be6bd6ea97d66b6686361b4370d Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 21 Jul 2015 10:44:03 +0200 Subject: openvswitch: Make tunnel set action attach a metadata dst Utilize the new metadata dst to attach encapsulation instructions to the skb. The existing egress_tun_info via the OVS_CB() is left in place until all tunnel vports have been converted to the new method. Signed-off-by: Thomas Graf Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 27c1687cfd92..cf04c2f8b32a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -733,7 +733,15 @@ static int execute_set_action(struct sk_buff *skb, { /* Only tunnel set execution is supported without a mask. */ if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) { - OVS_CB(skb)->egress_tun_info = nla_data(a); + struct ovs_tunnel_info *tun = nla_data(a); + + skb_dst_drop(skb); + dst_hold((struct dst_entry *)tun->tun_dst); + skb_dst_set(skb, (struct dst_entry *)tun->tun_dst); + + /* FIXME: Remove when all vports have been converted */ + OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info; + return 0; } -- cgit v1.2.3 From 3576fd794b38306e196498ac54bb3b21c32e1ae4 Mon Sep 17 00:00:00 2001 From: Glenn Griffin Date: Mon, 3 Aug 2015 09:56:54 -0700 Subject: openvswitch: Fix L4 checksum handling when dealing with IP fragments openvswitch modifies the L4 checksum of a packet when modifying the ip address. When an IP packet is fragmented only the first fragment contains an L4 header and checksum. Prior to this change openvswitch would modify all fragments, modifying application data in non-first fragments, causing checksum failures in the reassembled packet. Signed-off-by: Glenn Griffin Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8a8c0b8b4f63..ee34f474ad14 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -273,28 +273,36 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, - __be32 *addr, __be32 new_addr) +static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, + __be32 addr, __be32 new_addr) { int transport_len = skb->len - skb_transport_offset(skb); + if (nh->frag_off & htons(IP_OFFSET)) + return; + if (nh->protocol == IPPROTO_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, - *addr, new_addr, 1); + addr, new_addr, 1); } else if (nh->protocol == IPPROTO_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&uh->check, skb, - *addr, new_addr, 1); + addr, new_addr, 1); if (!uh->check) uh->check = CSUM_MANGLED_0; } } } +} +static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, + __be32 *addr, __be32 new_addr) +{ + update_ip_l4_checksum(skb, nh, *addr, new_addr); csum_replace4(&nh->check, *addr, new_addr); skb_clear_hash(skb); *addr = new_addr; -- cgit v1.2.3 From e05176a3283822bd32a1f3d929ce2050232299a8 Mon Sep 17 00:00:00 2001 From: Wenyu Zhang Date: Wed, 5 Aug 2015 00:30:47 -0700 Subject: openvswitch: Make 100 percents packets sampled when sampling rate is 1. When sampling rate is 1, the sampling probability is UINT32_MAX. The packet should be sampled even the prandom32() generate the number of UINT32_MAX. And none packet need be sampled when the probability is 0. Signed-off-by: Wenyu Zhang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index cf04c2f8b32a..a0ac410e9570 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -669,9 +669,12 @@ static int sample(struct datapath *dp, struct sk_buff *skb, for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { + u32 probability; + switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (prandom_u32() >= nla_get_u32(a)) + probability = nla_get_u32(a); + if (!probability || prandom_u32() > probability) return 0; break; -- cgit v1.2.3 From 4b048d6d9d0b0b90e1e94f2393796bbf1fa8df4e Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 17 Aug 2015 13:42:25 -0700 Subject: net: Change pseudohdr argument of inet_proto_csum_replace* to be a bool inet_proto_csum_replace4,2,16 take a pseudohdr argument which indicates the checksum field carries a pseudo header. This argument should be a boolean instead of an int. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 14da52ddd327..4f4200717bef 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -284,14 +284,14 @@ static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, if (nh->protocol == IPPROTO_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, - addr, new_addr, 1); + addr, new_addr, true); } else if (nh->protocol == IPPROTO_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&uh->check, skb, - addr, new_addr, 1); + addr, new_addr, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } @@ -316,14 +316,14 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, if (l4_proto == NEXTHDR_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb, - addr, new_addr, 1); + addr, new_addr, true); } else if (l4_proto == NEXTHDR_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace16(&uh->check, skb, - addr, new_addr, 1); + addr, new_addr, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } @@ -331,7 +331,7 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, } else if (l4_proto == NEXTHDR_ICMP) { if (likely(transport_len >= sizeof(struct icmp6hdr))) inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum, - skb, addr, new_addr, 1); + skb, addr, new_addr, true); } } @@ -498,7 +498,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) { - inet_proto_csum_replace2(check, skb, *port, new_port, 0); + inet_proto_csum_replace2(check, skb, *port, new_port, false); *port = new_port; } -- cgit v1.2.3 From be26b9a88fcee570796c67701f50800039e25aec Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 26 Aug 2015 11:31:45 -0700 Subject: openvswitch: Move MASKED* macros to datapath.h This will allow the ovs-conntrack code to reuse these macros. Signed-off-by: Joe Stringer Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 52 +++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 27 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 4f4200717bef..520438b77dc8 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -185,10 +185,6 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, return 0; } -/* 'KEY' must not have any bits set outside of the 'MASK' */ -#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK))) -#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK)) - static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, const __be32 *mpls_lse, const __be32 *mask) { @@ -201,7 +197,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, return err; stack = (__be32 *)skb_mpls_header(skb); - lse = MASKED(*stack, *mpls_lse, *mask); + lse = OVS_MASKED(*stack, *mpls_lse, *mask); if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~(*stack), lse }; @@ -244,9 +240,9 @@ static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_) const u16 *src = (const u16 *)src_; const u16 *mask = (const u16 *)mask_; - SET_MASKED(dst[0], src[0], mask[0]); - SET_MASKED(dst[1], src[1], mask[1]); - SET_MASKED(dst[2], src[2], mask[2]); + OVS_SET_MASKED(dst[0], src[0], mask[0]); + OVS_SET_MASKED(dst[1], src[1], mask[1]); + OVS_SET_MASKED(dst[2], src[2], mask[2]); } static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, @@ -338,10 +334,10 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4], const __be32 mask[4], __be32 masked[4]) { - masked[0] = MASKED(old[0], addr[0], mask[0]); - masked[1] = MASKED(old[1], addr[1], mask[1]); - masked[2] = MASKED(old[2], addr[2], mask[2]); - masked[3] = MASKED(old[3], addr[3], mask[3]); + masked[0] = OVS_MASKED(old[0], addr[0], mask[0]); + masked[1] = OVS_MASKED(old[1], addr[1], mask[1]); + masked[2] = OVS_MASKED(old[2], addr[2], mask[2]); + masked[3] = OVS_MASKED(old[3], addr[3], mask[3]); } static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, @@ -358,15 +354,15 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask) { /* Bits 21-24 are always unmasked, so this retains their values. */ - SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); - SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); - SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); + OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); + OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); + OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); } static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl, u8 mask) { - new_ttl = MASKED(nh->ttl, new_ttl, mask); + new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask); csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8)); nh->ttl = new_ttl; @@ -392,7 +388,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key, * makes sense to check if the value actually changed. */ if (mask->ipv4_src) { - new_addr = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src); + new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src); if (unlikely(new_addr != nh->saddr)) { set_ip_addr(skb, nh, &nh->saddr, new_addr); @@ -400,7 +396,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key, } } if (mask->ipv4_dst) { - new_addr = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst); + new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst); if (unlikely(new_addr != nh->daddr)) { set_ip_addr(skb, nh, &nh->daddr, new_addr); @@ -488,7 +484,8 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); } if (mask->ipv6_hlimit) { - SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit); + OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit, + mask->ipv6_hlimit); flow_key->ip.ttl = nh->hop_limit; } return 0; @@ -517,8 +514,8 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key, uh = udp_hdr(skb); /* Either of the masks is non-zero, so do not bother checking them. */ - src = MASKED(uh->source, key->udp_src, mask->udp_src); - dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst); + src = OVS_MASKED(uh->source, key->udp_src, mask->udp_src); + dst = OVS_MASKED(uh->dest, key->udp_dst, mask->udp_dst); if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) { if (likely(src != uh->source)) { @@ -558,12 +555,12 @@ static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key, return err; th = tcp_hdr(skb); - src = MASKED(th->source, key->tcp_src, mask->tcp_src); + src = OVS_MASKED(th->source, key->tcp_src, mask->tcp_src); if (likely(src != th->source)) { set_tp_port(skb, &th->source, src, &th->check); flow_key->tp.src = src; } - dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst); + dst = OVS_MASKED(th->dest, key->tcp_dst, mask->tcp_dst); if (likely(dst != th->dest)) { set_tp_port(skb, &th->dest, dst, &th->check); flow_key->tp.dst = dst; @@ -590,8 +587,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, old_csum = sh->checksum; old_correct_csum = sctp_compute_cksum(skb, sctphoff); - sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src); - sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst); + sh->source = OVS_MASKED(sh->source, key->sctp_src, mask->sctp_src); + sh->dest = OVS_MASKED(sh->dest, key->sctp_dst, mask->sctp_dst); new_csum = sctp_compute_cksum(skb, sctphoff); @@ -770,12 +767,13 @@ static int execute_masked_set_action(struct sk_buff *skb, switch (nla_type(a)) { case OVS_KEY_ATTR_PRIORITY: - SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *)); + OVS_SET_MASKED(skb->priority, nla_get_u32(a), + *get_mask(a, u32 *)); flow_key->phy.priority = skb->priority; break; case OVS_KEY_ATTR_SKB_MARK: - SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *)); + OVS_SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *)); flow_key->phy.skb_mark = skb->mark; break; -- cgit v1.2.3 From 7f8a436eaa2c3ddd8e1ff2fbca267e6275085536 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 26 Aug 2015 11:31:48 -0700 Subject: openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer Signed-off-by: Justin Pettit Signed-off-by: Andy Zhou Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 175 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 169 insertions(+), 6 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 520438b77dc8..72ca2c491b0a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -29,6 +30,7 @@ #include #include +#include #include #include #include @@ -38,6 +40,7 @@ #include "datapath.h" #include "flow.h" +#include "conntrack.h" #include "vport.h" static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, @@ -52,6 +55,20 @@ struct deferred_action { struct sw_flow_key pkt_key; }; +#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN) +struct ovs_frag_data { + unsigned long dst; + struct vport *vport; + struct ovs_skb_cb cb; + __be16 inner_protocol; + __u16 vlan_tci; + __be16 vlan_proto; + unsigned int l2_len; + u8 l2_data[MAX_L2_LEN]; +}; + +static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage); + #define DEFERRED_ACTION_FIFO_SIZE 10 struct action_fifo { int head; @@ -602,14 +619,145 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) +static int ovs_vport_output(struct sock *sock, struct sk_buff *skb) +{ + struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); + struct vport *vport = data->vport; + + if (skb_cow_head(skb, data->l2_len) < 0) { + kfree_skb(skb); + return -ENOMEM; + } + + __skb_dst_copy(skb, data->dst); + *OVS_CB(skb) = data->cb; + skb->inner_protocol = data->inner_protocol; + skb->vlan_tci = data->vlan_tci; + skb->vlan_proto = data->vlan_proto; + + /* Reconstruct the MAC header. */ + skb_push(skb, data->l2_len); + memcpy(skb->data, &data->l2_data, data->l2_len); + ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len); + skb_reset_mac_header(skb); + + ovs_vport_send(vport, skb); + return 0; +} + +static unsigned int +ovs_dst_get_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + +static struct dst_ops ovs_dst_ops = { + .family = AF_UNSPEC, + .mtu = ovs_dst_get_mtu, +}; + +/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is + * ovs_vport_output(), which is called once per fragmented packet. + */ +static void prepare_frag(struct vport *vport, struct sk_buff *skb) +{ + unsigned int hlen = skb_network_offset(skb); + struct ovs_frag_data *data; + + data = this_cpu_ptr(&ovs_frag_data_storage); + data->dst = skb->_skb_refdst; + data->vport = vport; + data->cb = *OVS_CB(skb); + data->inner_protocol = skb->inner_protocol; + data->vlan_tci = skb->vlan_tci; + data->vlan_proto = skb->vlan_proto; + data->l2_len = hlen; + memcpy(&data->l2_data, skb->data, hlen); + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + skb_pull(skb, hlen); +} + +static void ovs_fragment(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"); + return; + } + + if (ethertype == htons(ETH_P_IP)) { + struct dst_entry ovs_dst; + unsigned long orig_dst; + + prepare_frag(vport, skb); + dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1, + DST_OBSOLETE_NONE, DST_NOCOUNT); + ovs_dst.dev = vport->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &ovs_dst); + IPCB(skb)->frag_max_size = mru; + + ip_do_fragment(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(); + unsigned long orig_dst; + struct rt6_info ovs_rt; + + if (!v6ops) { + kfree_skb(skb); + return; + } + + prepare_frag(vport, skb); + memset(&ovs_rt, 0, sizeof(ovs_rt)); + dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1, + DST_OBSOLETE_NONE, DST_NOCOUNT); + ovs_rt.dst.dev = vport->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &ovs_rt.dst); + IP6CB(skb)->frag_max_size = mru; + + v6ops->fragment(skb->sk, skb, ovs_vport_output); + refdst_drop(orig_dst); + } else { + WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", + ovs_vport_name(vport), ntohs(ethertype), mru, + vport->dev->mtu); + kfree_skb(skb); + } +} + +static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, + struct sw_flow_key *key) { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) - ovs_vport_send(vport, skb); - else + if (likely(vport)) { + u16 mru = OVS_CB(skb)->mru; + + if (likely(!mru || (skb->len <= mru + ETH_HLEN))) { + ovs_vport_send(vport, skb); + } else if (mru <= vport->dev->mtu) { + __be16 ethertype = key->eth.type; + + if (!is_flow_key_valid(key)) { + if (eth_p_mpls(skb->protocol)) + ethertype = skb->inner_protocol; + else + ethertype = vlan_get_protocol(skb); + } + + ovs_fragment(vport, skb, mru, ethertype); + } else { + kfree_skb(skb); + } + } else { kfree_skb(skb); + } } static int output_userspace(struct datapath *dp, struct sk_buff *skb, @@ -623,6 +771,7 @@ 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; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -816,6 +965,11 @@ static int execute_masked_set_action(struct sk_buff *skb, err = set_mpls(skb, flow_key, nla_data(a), get_mask(a, __be32 *)); break; + + case OVS_KEY_ATTR_CT_STATE: + case OVS_KEY_ATTR_CT_ZONE: + err = -EINVAL; + break; } return err; @@ -885,7 +1039,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC); if (out_skb) - do_output(dp, out_skb, prev_port); + do_output(dp, out_skb, prev_port, key); prev_port = -1; } @@ -942,6 +1096,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_SAMPLE: err = sample(dp, skb, key, a, attr, len); break; + + case OVS_ACTION_ATTR_CT: + err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, + nla_data(a)); + + /* Hide stolen IP fragments from user space. */ + if (err == -EINPROGRESS) + return 0; + break; } if (unlikely(err)) { @@ -951,7 +1114,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, } if (prev_port != -1) - do_output(dp, skb, prev_port); + do_output(dp, skb, prev_port, key); else consume_skb(skb); -- cgit v1.2.3 From 182e3042e15de759e81618d11fe4f62f5259d982 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 26 Aug 2015 11:31:49 -0700 Subject: openvswitch: Allow matching on conntrack mark Allow matching and setting the ct_mark field. As with ct_state and ct_zone, these fields are populated when the CT action is executed. To write to this field, a value and mask can be specified as a nested attribute under the CT action. This data is stored with the conntrack entry, and is executed after the lookup occurs for the CT action. The conntrack entry itself must be committed using the COMMIT flag in the CT action flags for this change to persist. Signed-off-by: Justin Pettit Signed-off-by: Joe Stringer Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 72ca2c491b0a..9741d2c703df 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -968,6 +968,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: + case OVS_KEY_ATTR_CT_MARK: err = -EINVAL; break; } -- cgit v1.2.3 From c2ac667358708d7cce64c78f58af6adf4c1e848b Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 26 Aug 2015 11:31:52 -0700 Subject: openvswitch: Allow matching on conntrack label Allow matching and setting the ct_label field. As with ct_mark, this is populated by executing the CT action. The label field may be modified by specifying a label and mask nested under the CT action. It is stored as metadata attached to the connection. Label modification occurs after lookup, and will only persist when the conntrack entry is committed by providing the COMMIT flag to the CT action. Labels are currently fixed to 128 bits in size. Signed-off-by: Joe Stringer Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 9741d2c703df..736a113a75c3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -969,6 +969,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: + case OVS_KEY_ATTR_CT_LABEL: err = -EINVAL; break; } -- cgit v1.2.3 From 7b85b4dff2caa5e52726093fd058f87bbc14f156 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Thu, 27 Aug 2015 15:25:46 -0700 Subject: openvswitch: Include ip6_fib.h. kbuild test robot reports that certain configurations will not automatically pick up on the "struct rt6_info" definition, so explicitly include the header for this structure. Fixes: 7f8a436 "openvswitch: Add conntrack action" Signed-off-by: Joe Stringer Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 736a113a75c3..4487543806bb 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 3eedb41fb43461b5fde3f72fd00a7706f0b90103 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sat, 29 Aug 2015 17:44:06 -0700 Subject: openvswitch: Remove egress_tun_info. tun info is passed using skb-dst pointer. Now we have converted all vports to netdev based implementation so Now we can remove redundant pointer to tun-info from OVS_CB. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 4487543806bb..090d9e3a460c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -896,10 +896,6 @@ static int execute_set_action(struct sk_buff *skb, skb_dst_drop(skb); dst_hold((struct dst_entry *)tun->tun_dst); skb_dst_set(skb, (struct dst_entry *)tun->tun_dst); - - /* FIXME: Remove when all vports have been converted */ - OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info; - return 0; } @@ -1159,7 +1155,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, int err; this_cpu_inc(exec_actions_level); - OVS_CB(skb)->egress_tun_info = NULL; err = do_execute_actions(dp, skb, key, acts->actions, acts->actions_len); -- cgit v1.2.3 From 4c22279848c531fc7f555d463daf3d0df963bd41 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sun, 30 Aug 2015 18:09:38 -0700 Subject: ip-tunnel: Use API to access tunnel metadata options. Currently tun-info options pointer is used in few cases to pass options around. But tunnel options can be accessed using ip_tunnel_info_opts() API without using the pointer. Following patch removes the redundant pointer and consistently make use of API. Signed-off-by: Pravin B Shelar Acked-by: Thomas Graf Reviewed-by: Jesse Gross Signed-off-by: David S. Miller --- net/openvswitch/actions.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'net/openvswitch/actions.c') diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 090d9e3a460c..315f5330b6e5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -793,11 +793,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, if (vport) { int err; + upcall.egress_tun_info = &info; err = ovs_vport_get_egress_tun_info(vport, skb, - &info); - if (!err) - upcall.egress_tun_info = &info; + &upcall); + if (err) + upcall.egress_tun_info = NULL; } + break; } -- cgit v1.2.3