diff options
author | 2016-03-19 10:05:34 -0700 | |
---|---|---|
committer | 2016-03-19 10:05:34 -0700 | |
commit | 1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch) | |
tree | 552e03de245cdbd0780ca1215914edc4a26540f7 /net/openvswitch | |
parent | Merge branch 'for-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cg... (diff) | |
parent | bonding: fix bond_get_stats() (diff) | |
download | linux-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.gz linux-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.bz2 linux-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support more Realtek wireless chips, from Jes Sorenson.
2) New BPF types for per-cpu hash and arrap maps, from Alexei
Starovoitov.
3) Make several TCP sysctls per-namespace, from Nikolay Borisov.
4) Allow the use of SO_REUSEPORT in order to do per-thread processing
of incoming TCP/UDP connections. The muxing can be done using a
BPF program which hashes the incoming packet. From Craig Gallek.
5) Add a multiplexer for TCP streams, to provide a messaged based
interface. BPF programs can be used to determine the message
boundaries. From Tom Herbert.
6) Add 802.1AE MACSEC support, from Sabrina Dubroca.
7) Avoid factorial complexity when taking down an inetdev interface
with lots of configured addresses. We were doing things like
traversing the entire address less for each address removed, and
flushing the entire netfilter conntrack table for every address as
well.
8) Add and use SKB bulk free infrastructure, from Jesper Brouer.
9) Allow offloading u32 classifiers to hardware, and implement for
ixgbe, from John Fastabend.
10) Allow configuring IRQ coalescing parameters on a per-queue basis,
from Kan Liang.
11) Extend ethtool so that larger link mode masks can be supported.
From David Decotigny.
12) Introduce devlink, which can be used to configure port link types
(ethernet vs Infiniband, etc.), port splitting, and switch device
level attributes as a whole. From Jiri Pirko.
13) Hardware offload support for flower classifiers, from Amir Vadai.
14) Add "Local Checksum Offload". Basically, for a tunneled packet
the checksum of the outer header is 'constant' (because with the
checksum field filled into the inner protocol header, the payload
of the outer frame checksums to 'zero'), and we can take advantage
of that in various ways. From Edward Cree"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
bonding: fix bond_get_stats()
net: bcmgenet: fix dma api length mismatch
net/mlx4_core: Fix backward compatibility on VFs
phy: mdio-thunder: Fix some Kconfig typos
lan78xx: add ndo_get_stats64
lan78xx: handle statistics counter rollover
RDS: TCP: Remove unused constant
RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
net: smc911x: convert pxa dma to dmaengine
team: remove duplicate set of flag IFF_MULTICAST
bonding: remove duplicate set of flag IFF_MULTICAST
net: fix a comment typo
ethernet: micrel: fix some error codes
ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
bpf, dst: add and use dst_tclassid helper
bpf: make skb->tc_classid also readable
net: mvneta: bm: clarify dependencies
cls_bpf: reset class and reuse major in da
ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
ldmvsw: Add ldmvsw.c driver code
...
Diffstat (limited to 'net/openvswitch')
-rw-r--r-- | net/openvswitch/Kconfig | 4 | ||||
-rw-r--r-- | net/openvswitch/actions.c | 8 | ||||
-rw-r--r-- | net/openvswitch/conntrack.c | 660 | ||||
-rw-r--r-- | net/openvswitch/conntrack.h | 3 | ||||
-rw-r--r-- | net/openvswitch/datapath.c | 108 | ||||
-rw-r--r-- | net/openvswitch/datapath.h | 4 | ||||
-rw-r--r-- | net/openvswitch/flow.h | 2 | ||||
-rw-r--r-- | net/openvswitch/flow_netlink.c | 9 | ||||
-rw-r--r-- | net/openvswitch/vport-internal_dev.c | 10 | ||||
-rw-r--r-- | net/openvswitch/vport-netdev.c | 2 | ||||
-rw-r--r-- | net/openvswitch/vport.h | 7 |
11 files changed, 726 insertions, 91 deletions
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index d143aa9f6654..234a73344c6e 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -6,10 +6,12 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET depends on !NF_CONNTRACK || \ - (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6)) + (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ + (!NF_NAT || NF_NAT))) select LIBCRC32C select MPLS select NET_MPLS_GSO + select DST_CACHE ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2d59df521915..e9dd47b2a85b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -158,9 +158,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, new_mpls_lse = (__be32 *)skb_mpls_header(skb); *new_mpls_lse = mpls->mpls_lse; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse, - MPLS_HLEN, 0)); + skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN); hdr = eth_hdr(skb); hdr->h_proto = mpls->mpls_ethertype; @@ -280,7 +278,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst, mask->eth_dst); - ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); + skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source); ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest); @@ -639,7 +637,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk /* 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_postpush_rcsum(skb, skb->data, data->l2_len); skb_reset_mac_header(skb); ovs_vport_send(vport, skb); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index ee6ff8ffc12d..dc5eb29fe7d6 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -13,21 +13,31 @@ #include <linux/module.h> #include <linux/openvswitch.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/sctp.h> #include <net/ip.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_labels.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#ifdef CONFIG_NF_NAT_NEEDED +#include <linux/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#endif + #include "datapath.h" #include "conntrack.h" #include "flow.h" #include "flow_netlink.h" struct ovs_ct_len_tbl { - size_t maxlen; - size_t minlen; + int maxlen; + int minlen; }; /* Metadata mark for masked write to conntrack mark */ @@ -42,15 +52,25 @@ struct md_labels { struct ovs_key_ct_labels mask; }; +enum ovs_ct_nat { + OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */ + OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */ + OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */ +}; + /* Conntrack action context for execution. */ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; u8 commit : 1; + u8 nat : 3; /* enum ovs_ct_nat */ u16 family; struct md_mark mark; struct md_labels labels; +#ifdef CONFIG_NF_NAT_NEEDED + struct nf_nat_range range; /* Only present for SRC NAT and DST NAT. */ +#endif }; static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); @@ -75,7 +95,6 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) switch (ctinfo) { case IP_CT_ESTABLISHED_REPLY: case IP_CT_RELATED_REPLY: - case IP_CT_NEW_REPLY: ct_state |= OVS_CS_F_REPLY_DIR; break; default: @@ -92,7 +111,6 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) ct_state |= OVS_CS_F_RELATED; break; case IP_CT_NEW: - case IP_CT_NEW_REPLY: ct_state |= OVS_CS_F_NEW; break; default: @@ -139,12 +157,15 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, ovs_ct_get_labels(ct, &key->ct.labels); } -/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has - * previously sent the packet to conntrack via the ct action. +/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has + * previously sent the packet to conntrack via the ct action. If + * 'keep_nat_flags' is true, the existing NAT flags retained, else they are + * initialized from the connection status. */ static void ovs_ct_update_key(const struct sk_buff *skb, const struct ovs_conntrack_info *info, - struct sw_flow_key *key, bool post_ct) + struct sw_flow_key *key, bool post_ct, + bool keep_nat_flags) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; @@ -154,10 +175,22 @@ static void ovs_ct_update_key(const struct sk_buff *skb, ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); + /* All unconfirmed entries are NEW connections. */ if (!nf_ct_is_confirmed(ct)) state |= OVS_CS_F_NEW; + /* OVS persists the related flag for the duration of the + * connection. + */ if (ct->master) state |= OVS_CS_F_RELATED; + if (keep_nat_flags) { + state |= key->ct.state & OVS_CS_F_NAT_MASK; + } else { + if (ct->status & IPS_SRC_NAT) + state |= OVS_CS_F_SRC_NAT; + if (ct->status & IPS_DST_NAT) + state |= OVS_CS_F_DST_NAT; + } zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; @@ -167,9 +200,12 @@ static void ovs_ct_update_key(const struct sk_buff *skb, __ovs_ct_update_key(key, state, zone, ct); } +/* This is called to initialize CT key fields possibly coming in from the local + * stack. + */ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { - ovs_ct_update_key(skb, NULL, key, false); + ovs_ct_update_key(skb, NULL, key, false, false); } int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) @@ -201,7 +237,6 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, struct nf_conn *ct; u32 new_mark; - /* The connection could be invalid, in which case set_mark is no-op. */ ct = nf_ct_get(skb, &ctinfo); if (!ct) @@ -259,6 +294,7 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) enum ip_conntrack_info ctinfo; unsigned int protoff; struct nf_conn *ct; + int err; ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) @@ -295,7 +331,18 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) return NF_DROP; } - return helper->help(skb, protoff, ct, ctinfo); + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; } /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero @@ -352,14 +399,101 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, return __nf_ct_expect_find(net, zone, &tuple); } +/* This replicates logic from nf_conntrack_core.c that is not exported. */ +static enum ip_conntrack_info +ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h) +{ + const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + return IP_CT_ESTABLISHED_REPLY; + /* Once we've had two way comms, always ESTABLISHED. */ + if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) + return IP_CT_ESTABLISHED; + if (test_bit(IPS_EXPECTED_BIT, &ct->status)) + return IP_CT_RELATED; + return IP_CT_NEW; +} + +/* Find an existing connection which this packet belongs to without + * re-attributing statistics or modifying the connection state. This allows an + * skb->nfct lost due to an upcall to be recovered during actions execution. + * + * Must be called with rcu_read_lock. + * + * On success, populates skb->nfct and skb->nfctinfo, and returns the + * connection. Returns NULL if there is no existing entry. + */ +static struct nf_conn * +ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, + u8 l3num, struct sk_buff *skb) +{ + struct nf_conntrack_l3proto *l3proto; + struct nf_conntrack_l4proto *l4proto; + struct nf_conntrack_tuple tuple; + struct nf_conntrack_tuple_hash *h; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + unsigned int dataoff; + u8 protonum; + + l3proto = __nf_ct_l3proto_find(l3num); + if (!l3proto) { + pr_debug("ovs_ct_find_existing: Can't get l3proto\n"); + return NULL; + } + if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, + &protonum) <= 0) { + pr_debug("ovs_ct_find_existing: Can't get protonum\n"); + return NULL; + } + l4proto = __nf_ct_l4proto_find(l3num, protonum); + if (!l4proto) { + pr_debug("ovs_ct_find_existing: Can't get l4proto\n"); + return NULL; + } + if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, + protonum, net, &tuple, l3proto, l4proto)) { + pr_debug("ovs_ct_find_existing: Can't get tuple\n"); + return NULL; + } + + /* look for tuple match */ + h = nf_conntrack_find_get(net, zone, &tuple); + if (!h) + return NULL; /* Not found. */ + + ct = nf_ct_tuplehash_to_ctrack(h); + + ctinfo = ovs_ct_get_info(h); + if (ctinfo == IP_CT_NEW) { + /* This should not happen. */ + WARN_ONCE(1, "ovs_ct_find_existing: new packet for %p\n", ct); + } + skb->nfct = &ct->ct_general; + skb->nfctinfo = ctinfo; + return ct; +} + /* Determine whether skb->nfct is equal to the result of conntrack lookup. */ -static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, - const struct ovs_conntrack_info *info) +static bool skb_nfct_cached(struct net *net, + const struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); + /* If no ct, check if we have evidence that an existing conntrack entry + * might be found for this skb. This happens when we lose a skb->nfct + * due to an upcall. If the connection was not confirmed, it is not + * cached and needs to be run through conntrack again. + */ + if (!ct && key->ct.state & OVS_CS_F_TRACKED && + !(key->ct.state & OVS_CS_F_INVALID) && + key->ct.zone == info->zone.id) + ct = ovs_ct_find_existing(net, &info->zone, info->family, skb); if (!ct) return false; if (!net_eq(net, read_pnet(&ct->ct_net))) @@ -377,6 +511,206 @@ static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, return true; } +#ifdef CONFIG_NF_NAT_NEEDED +/* Modelled after nf_nat_ipv[46]_fn(). + * range is only used for new, uninitialized NAT state. + * Returns either NF_ACCEPT or NF_DROP. + */ +static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype) +{ + int hooknum, nh_off, err = NF_ACCEPT; + + nh_off = skb_network_offset(skb); + skb_pull(skb, nh_off); + + /* See HOOK2MANIP(). */ + if (maniptype == NF_NAT_MANIP_SRC) + hooknum = NF_INET_LOCAL_IN; /* Source NAT */ + else + hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + if (skb->protocol == htons(ETH_P_IP) && + ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + hooknum)) + err = NF_DROP; + goto push; +#if IS_ENABLED(CONFIG_NF_NAT_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6)) { + __be16 frag_off; + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + int hdrlen = ipv6_skip_exthdr(skb, + sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, + ctinfo, + hooknum, + hdrlen)) + err = NF_DROP; + goto push; + } +#endif + } + /* Non-ICMP, fall thru to initialize if needed. */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + /* Initialize according to the NAT action. */ + err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) + /* Action is set up to establish a new + * mapping. + */ + ? nf_nat_setup_info(ct, range, maniptype) + : nf_nat_alloc_null_binding(ct, hooknum); + if (err != NF_ACCEPT) + goto push; + } + break; + + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + break; + + default: + err = NF_DROP; + goto push; + } + + err = nf_nat_packet(ct, ctinfo, hooknum, skb); +push: + skb_push(skb, nh_off); + + return err; +} + +static void ovs_nat_update_key(struct sw_flow_key *key, + const struct sk_buff *skb, + enum nf_nat_manip_type maniptype) +{ + if (maniptype == NF_NAT_MANIP_SRC) { + __be16 src; + + key->ct.state |= OVS_CS_F_SRC_NAT; + if (key->eth.type == htons(ETH_P_IP)) + key->ipv4.addr.src = ip_hdr(skb)->saddr; + else if (key->eth.type == htons(ETH_P_IPV6)) + memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr, + sizeof(key->ipv6.addr.src)); + else + return; + + if (key->ip.proto == IPPROTO_UDP) + src = udp_hdr(skb)->source; + else if (key->ip.proto == IPPROTO_TCP) + src = tcp_hdr(skb)->source; + else if (key->ip.proto == IPPROTO_SCTP) + src = sctp_hdr(skb)->source; + else + return; + + key->tp.src = src; + } else { + __be16 dst; + + key->ct.state |= OVS_CS_F_DST_NAT; + if (key->eth.type == htons(ETH_P_IP)) + key->ipv4.addr.dst = ip_hdr(skb)->daddr; + else if (key->eth.type == htons(ETH_P_IPV6)) + memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr, + sizeof(key->ipv6.addr.dst)); + else + return; + + if (key->ip.proto == IPPROTO_UDP) + dst = udp_hdr(skb)->dest; + else if (key->ip.proto == IPPROTO_TCP) + dst = tcp_hdr(skb)->dest; + else if (key->ip.proto == IPPROTO_SCTP) + dst = sctp_hdr(skb)->dest; + else + return; + + key->tp.dst = dst; + } +} + +/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */ +static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + enum nf_nat_manip_type maniptype; + int err; + + if (nf_ct_is_untracked(ct)) { + /* A NAT action may only be performed on tracked packets. */ + return NF_ACCEPT; + } + + /* Add NAT extension if not confirmed yet. */ + if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) + return NF_ACCEPT; /* Can't NAT. */ + + /* Determine NAT type. + * Check if the NAT type can be deduced from the tracked connection. + * Make sure expected traffic is NATted only when committing. + */ + if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW && + ct->status & IPS_NAT_MASK && + (!(ct->status & IPS_EXPECTED_BIT) || info->commit)) { + /* NAT an established or related connection like before. */ + if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) + /* This is the REPLY direction for a connection + * for which NAT was applied in the forward + * direction. Do the reverse NAT. + */ + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; + else + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; + } else if (info->nat & OVS_CT_SRC_NAT) { + maniptype = NF_NAT_MANIP_SRC; + } else if (info->nat & OVS_CT_DST_NAT) { + maniptype = NF_NAT_MANIP_DST; + } else { + return NF_ACCEPT; /* Connection is not NATed. */ + } + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); + + /* Mark NAT done if successful and update the flow key. */ + if (err == NF_ACCEPT) + ovs_nat_update_key(key, skb, maniptype); + + return err; +} +#else /* !CONFIG_NF_NAT_NEEDED */ +static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + return NF_ACCEPT; +} +#endif + +/* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if + * not done already. Update key with new CT state after passing the packet + * through conntrack. + * Note that if the packet is deemed invalid by conntrack, skb->nfct will be + * set to NULL and 0 will be returned. + */ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) @@ -386,8 +720,13 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, * actually run the packet through conntrack twice unless it's for a * different zone. */ - if (!skb_nfct_cached(net, skb, info)) { + bool cached = skb_nfct_cached(net, key, info, skb); + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (!cached) { struct nf_conn *tmpl = info->ct; + int err; /* Associate skb with specified zone. */ if (tmpl) { @@ -398,17 +737,53 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, skb->nfctinfo = IP_CT_NEW; } - if (nf_conntrack_in(net, info->family, NF_INET_PRE_ROUTING, - skb) != NF_ACCEPT) + /* Repeat if requested, see nf_iterate(). */ + do { + err = nf_conntrack_in(net, info->family, + NF_INET_PRE_ROUTING, skb); + } while (err == NF_REPEAT); + + if (err != NF_ACCEPT) return -ENOENT; - if (ovs_ct_helper(skb, info->family) != NF_ACCEPT) { - WARN_ONCE(1, "helper rejected packet"); + /* Clear CT state NAT flags to mark that we have not yet done + * NAT after the nf_conntrack_in() call. We can actually clear + * the whole state, as it will be re-initialized below. + */ + key->ct.state = 0; + + /* Update the key, but keep the NAT flags. */ + ovs_ct_update_key(skb, info, key, true, true); + } + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + /* Packets starting a new connection must be NATted before the + * helper, so that the helper knows about the NAT. We enforce + * this by delaying both NAT and helper calls for unconfirmed + * connections until the committing CT action. For later + * packets NAT and Helper may be called in either order. + * + * NAT will be done only if the CT action has NAT, and only + * once per packet (per zone), as guarded by the NAT bits in + * the key->ct.state. + */ + if (info->nat && !(key->ct.state & OVS_CS_F_NAT_MASK) && + (nf_ct_is_confirmed(ct) || info->commit) && + ovs_ct_nat(net, key, info, skb, ct, ctinfo) != NF_ACCEPT) { return -EINVAL; } - } - ovs_ct_update_key(skb, info, key, true); + /* Call the helper only if: + * - nf_conntrack_in() was executed above ("!cached") for a + * confirmed connection, or + * - When committing an unconfirmed connection. + */ + if ((nf_ct_is_confirmed(ct) ? !cached : info->commit) && + ovs_ct_helper(skb, info->family) != NF_ACCEPT) { + return -EINVAL; + } + } return 0; } @@ -420,19 +795,24 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, { struct nf_conntrack_expect *exp; + /* If we pass an expected packet through nf_conntrack_in() the + * expectation is typically removed, but the packet could still be + * lost in upcall processing. To prevent this from happening we + * perform an explicit expectation lookup. Expected connections are + * always new, and will be passed through conntrack only when they are + * committed, as it is OK to remove the expectation at that time. + */ exp = ovs_ct_expect_find(net, &info->zone, info->family, skb); if (exp) { u8 state; + /* NOTE: New connections are NATted and Helped only when + * committed, so we are not calling into NAT here. + */ state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED; __ovs_ct_update_key(key, state, &info->zone, exp->master); - } else { - int err; - - err = __ovs_ct_lookup(net, key, info, skb); - if (err) - return err; - } + } else + return __ovs_ct_lookup(net, key, info, skb); return 0; } @@ -442,21 +822,12 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { - u8 state; int err; - state = key->ct.state; - if (key->ct.zone == info->zone.id && - ((state & OVS_CS_F_TRACKED) && !(state & OVS_CS_F_NEW))) { - /* Previous lookup has shown that this connection is already - * tracked and committed. Skip committing. - */ - return 0; - } - err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; + /* This is a no-op if the connection has already been confirmed. */ if (nf_conntrack_confirm(skb) != NF_ACCEPT) return -EINVAL; @@ -541,6 +912,135 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, return 0; } +#ifdef CONFIG_NF_NAT_NEEDED +static int parse_nat(const struct nlattr *attr, + struct ovs_conntrack_info *info, bool log) +{ + struct nlattr *a; + int rem; + bool have_ip_max = false; + bool have_proto_max = false; + bool ip_vers = (info->family == NFPROTO_IPV6); + + nla_for_each_nested(a, attr, rem) { + static const int ovs_nat_attr_lens[OVS_NAT_ATTR_MAX + 1][2] = { + [OVS_NAT_ATTR_SRC] = {0, 0}, + [OVS_NAT_ATTR_DST] = {0, 0}, + [OVS_NAT_ATTR_IP_MIN] = {sizeof(struct in_addr), + sizeof(struct in6_addr)}, + [OVS_NAT_ATTR_IP_MAX] = {sizeof(struct in_addr), + sizeof(struct in6_addr)}, + [OVS_NAT_ATTR_PROTO_MIN] = {sizeof(u16), sizeof(u16)}, + [OVS_NAT_ATTR_PROTO_MAX] = {sizeof(u16), sizeof(u16)}, + [OVS_NAT_ATTR_PERSISTENT] = {0, 0}, + [OVS_NAT_ATTR_PROTO_HASH] = {0, 0}, + [OVS_NAT_ATTR_PROTO_RANDOM] = {0, 0}, + }; + int type = nla_type(a); + + if (type > OVS_NAT_ATTR_MAX) { + OVS_NLERR(log, + "Unknown NAT attribute (type=%d, max=%d).\n", + type, OVS_NAT_ATTR_MAX); + return -EINVAL; + } + + if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) { + OVS_NLERR(log, + "NAT attribute type %d has unexpected length (%d != %d).\n", + type, nla_len(a), + ovs_nat_attr_lens[type][ip_vers]); + return -EINVAL; + } + + switch (type) { + case OVS_NAT_ATTR_SRC: + case OVS_NAT_ATTR_DST: + if (info->nat) { + OVS_NLERR(log, + "Only one type of NAT may be specified.\n" + ); + return -ERANGE; + } + info->nat |= OVS_CT_NAT; + info->nat |= ((type == OVS_NAT_ATTR_SRC) + ? OVS_CT_SRC_NAT : OVS_CT_DST_NAT); + break; + + case OVS_NAT_ATTR_IP_MIN: + nla_memcpy(&info->range.min_addr, a, nla_len(a)); + info->range.flags |= NF_NAT_RANGE_MAP_IPS; + break; + + case OVS_NAT_ATTR_IP_MAX: + have_ip_max = true; + nla_memcpy(&info->range.max_addr, a, + sizeof(info->range.max_addr)); + info->range.flags |= NF_NAT_RANGE_MAP_IPS; + break; + + case OVS_NAT_ATTR_PROTO_MIN: + info->range.min_proto.all = htons(nla_get_u16(a)); + info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + break; + + case OVS_NAT_ATTR_PROTO_MAX: + have_proto_max = true; + info->range.max_proto.all = htons(nla_get_u16(a)); + info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + break; + + case OVS_NAT_ATTR_PERSISTENT: + info->range.flags |= NF_NAT_RANGE_PERSISTENT; + break; + + case OVS_NAT_ATTR_PROTO_HASH: + info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM; + break; + + case OVS_NAT_ATTR_PROTO_RANDOM: + info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM_FULLY; + break; + + default: + OVS_NLERR(log, "Unknown nat attribute (%d).\n", type); + return -EINVAL; + } + } + + if (rem > 0) { + OVS_NLERR(log, "NAT attribute has %d unknown bytes.\n", rem); + return -EINVAL; + } + if (!info->nat) { + /* Do not allow flags if no type is given. */ + if (info->range.flags) { + OVS_NLERR(log, + "NAT flags may be given only when NAT range (SRC or DST) is also specified.\n" + ); + return -EINVAL; + } + info->nat = OVS_CT_NAT; /* NAT existing connections. */ + } else if (!info->commit) { + OVS_NLERR(log, + "NAT attributes may be specified only when CT COMMIT flag is also specified.\n" + ); + return -EINVAL; + } + /* Allow missing IP_MAX. */ + if (info->range.flags & NF_NAT_RANGE_MAP_IPS && !have_ip_max) { + memcpy(&info->range.max_addr, &info->range.min_addr, + sizeof(info->range.max_addr)); + } + /* Allow missing PROTO_MAX. */ + if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && + !have_proto_max) { + info->range.max_proto.all = info->range.min_proto.all; + } + return 0; +} +#endif + static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), @@ -550,7 +1050,11 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, - .maxlen = NF_CT_HELPER_NAME_LEN } + .maxlen = NF_CT_HELPER_NAME_LEN }, +#ifdef CONFIG_NF_NAT_NEEDED + /* NAT length is checked when parsing the nested attributes. */ + [OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX }, +#endif }; static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, @@ -617,6 +1121,15 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, return -EINVAL; } break; +#ifdef CONFIG_NF_NAT_NEEDED + case OVS_CT_ATTR_NAT: { + int err = parse_nat(a, info, log); + + if (err) + return err; + break; + } +#endif default: OVS_NLERR(log, "Unknown conntrack attr (%d)", type); @@ -704,6 +1217,74 @@ err_free_ct: return err; } +#ifdef CONFIG_NF_NAT_NEEDED +static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, + struct sk_buff *skb) +{ + struct nlattr *start; + + start = nla_nest_start(skb, OVS_CT_ATTR_NAT); + if (!start) + return false; + + if (info->nat & OVS_CT_SRC_NAT) { + if (nla_put_flag(skb, OVS_NAT_ATTR_SRC)) + return false; + } else if (info->nat & OVS_CT_DST_NAT) { + if (nla_put_flag(skb, OVS_NAT_ATTR_DST)) + return false; + } else { + goto out; + } + + if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { + if (info->family == NFPROTO_IPV4) { + if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, + info->range.min_addr.ip) || + (info->range.max_addr.ip + != info->range.min_addr.ip && + (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, + info->range.max_addr.ip)))) + return false; +#if IS_ENABLED(CONFIG_NF_NAT_IPV6) + } else if (info->family == NFPROTO_IPV6) { + if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, + &info->range.min_addr.in6) || + (memcmp(&info->range.max_addr.in6, + &info->range.min_addr.in6, + sizeof(info->range.max_addr.in6)) && + (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, + &info->range.max_addr.in6)))) + return false; +#endif + } else { + return false; + } + } + if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && + (nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MIN, + ntohs(info->range.min_proto.all)) || + (info->range.max_proto.all != info->range.min_proto.all && + nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MAX, + ntohs(info->range.max_proto.all))))) + return false; + + if (info->range.flags & NF_NAT_RANGE_PERSISTENT && + nla_put_flag(skb, OVS_NAT_ATTR_PERSISTENT)) + return false; + if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM && + nla_put_flag(skb, OVS_NAT_ATTR_PROTO_HASH)) + return false; + if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY && + nla_put_flag(skb, OVS_NAT_ATTR_PROTO_RANDOM)) + return false; +out: + nla_nest_end(skb, start); + + return true; +} +#endif + int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, struct sk_buff *skb) { @@ -732,7 +1313,10 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, ct_info->helper->name)) return -EMSGSIZE; } - +#ifdef CONFIG_NF_NAT_NEEDED + if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb)) + return -EMSGSIZE; +#endif nla_nest_end(skb, start); return 0; diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index a7544f405c16..8f6230bd6183 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -37,7 +37,8 @@ void ovs_ct_free_action(const struct nlattr *a); #define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \ - OVS_CS_F_INVALID | OVS_CS_F_TRACKED) + OVS_CS_F_INVALID | OVS_CS_F_TRACKED | \ + OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT) #else #include <linux/errno.h> diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index deadfdab1bc3..0cc66a4e492d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -422,10 +422,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, struct sk_buff *nskb = NULL; struct sk_buff *user_skb = NULL; /* to be queued to userspace */ struct nlattr *nla; - struct genl_info info = { - .dst_sk = ovs_dp_get_net(dp)->genl_sock, - .snd_portid = upcall_info->portid, - }; size_t len; unsigned int hlen; int err, dp_ifindex; @@ -466,7 +462,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, hlen = skb->len; len = upcall_msg_size(upcall_info, hlen); - user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC); + user_skb = genlmsg_new(len, GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; goto out; @@ -654,7 +650,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { static const struct genl_ops dp_packet_genl_ops[] = { { .cmd = OVS_PACKET_CMD_EXECUTE, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = packet_policy, .doit = ovs_packet_cmd_execute } @@ -876,7 +872,7 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *act return NULL; len = ovs_flow_cmd_msg_size(acts, sfid, ufid_flags); - skb = genlmsg_new_unicast(len, info, GFP_KERNEL); + skb = genlmsg_new(len, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); @@ -1100,26 +1096,32 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) struct sw_flow_match match; struct sw_flow_id sfid; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); - int error; + int error = 0; bool log = !a[OVS_FLOW_ATTR_PROBE]; bool ufid_present; - /* Extract key. */ - error = -EINVAL; - if (!a[OVS_FLOW_ATTR_KEY]) { - OVS_NLERR(log, "Flow key attribute not present in set flow."); - goto error; - } - ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); - ovs_match_init(&match, &key, &mask); - error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], - a[OVS_FLOW_ATTR_MASK], log); + if (a[OVS_FLOW_ATTR_KEY]) { + ovs_match_init(&match, &key, &mask); + error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], + a[OVS_FLOW_ATTR_MASK], log); + } else if (!ufid_present) { + OVS_NLERR(log, + "Flow set message rejected, Key attribute missing."); + error = -EINVAL; + } if (error) goto error; /* Validate actions. */ if (a[OVS_FLOW_ATTR_ACTIONS]) { + if (!a[OVS_FLOW_ATTR_KEY]) { + OVS_NLERR(log, + "Flow key attribute not present in set flow."); + error = -EINVAL; + goto error; + } + acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &key, &mask, log); if (IS_ERR(acts)) { @@ -1391,12 +1393,12 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { static const struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, .doit = ovs_flow_cmd_new }, { .cmd = OVS_FLOW_CMD_DEL, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, .doit = ovs_flow_cmd_del }, @@ -1407,7 +1409,7 @@ static const struct genl_ops dp_flow_genl_ops[] = { .dumpit = ovs_flow_cmd_dump }, { .cmd = OVS_FLOW_CMD_SET, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, .doit = ovs_flow_cmd_set, }, @@ -1481,9 +1483,9 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info) +static struct sk_buff *ovs_dp_cmd_alloc_info(void) { - return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); + return genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL); } /* Called with rcu_read_lock or ovs_mutex. */ @@ -1536,7 +1538,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1657,7 +1659,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1690,7 +1692,7 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1723,7 +1725,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1777,12 +1779,12 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { static const struct genl_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, .doit = ovs_dp_cmd_new }, { .cmd = OVS_DP_CMD_DEL, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, .doit = ovs_dp_cmd_del }, @@ -1793,7 +1795,7 @@ static const struct genl_ops dp_datapath_genl_ops[] = { .dumpit = ovs_dp_cmd_dump }, { .cmd = OVS_DP_CMD_SET, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, .doit = ovs_dp_cmd_set, }, @@ -1912,6 +1914,29 @@ static struct vport *lookup_vport(struct net *net, return ERR_PTR(-EINVAL); } +/* Called with ovs_mutex */ +static void update_headroom(struct datapath *dp) +{ + unsigned dev_headroom, max_headroom = 0; + struct net_device *dev; + struct vport *vport; + int i; + + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { + dev = vport->dev; + dev_headroom = netdev_get_fwd_headroom(dev); + if (dev_headroom > max_headroom) + max_headroom = dev_headroom; + } + } + + dp->max_headroom = max_headroom; + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) + netdev_set_rx_headroom(vport->dev, max_headroom); +} + static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; @@ -1977,6 +2002,12 @@ restart: err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW); + + if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom) + update_headroom(dp); + else + netdev_set_rx_headroom(vport->dev, dp->max_headroom); + BUG_ON(err < 0); ovs_unlock(); @@ -2043,8 +2074,10 @@ exit_unlock_free: static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) { + bool must_update_headroom = false; struct nlattr **a = info->attrs; struct sk_buff *reply; + struct datapath *dp; struct vport *vport; int err; @@ -2066,7 +2099,16 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_DEL); BUG_ON(err < 0); + + /* the vport deletion may trigger dp headroom update */ + dp = vport->dp; + if (netdev_get_fwd_headroom(vport->dev) == dp->max_headroom) + must_update_headroom = true; + netdev_reset_rx_headroom(vport->dev); ovs_dp_detach_port(vport); + + if (must_update_headroom) + update_headroom(dp); ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); @@ -2158,12 +2200,12 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { static const struct genl_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, .doit = ovs_vport_cmd_new }, { .cmd = OVS_VPORT_CMD_DEL, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, .doit = ovs_vport_cmd_del }, @@ -2174,7 +2216,7 @@ static const struct genl_ops dp_vport_genl_ops[] = { .dumpit = ovs_vport_cmd_dump }, { .cmd = OVS_VPORT_CMD_SET, - .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ + .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, .doit = ovs_vport_cmd_set, }, diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 67bdecd9fdc1..427e39a045cf 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -68,6 +68,8 @@ struct dp_stats_percpu { * ovs_mutex and RCU. * @stats_percpu: Per-CPU datapath statistics. * @net: Reference to net namespace. + * @max_headroom: the maximum headroom of all vports in this datapath; it will + * be used by all the internal vports in this dp. * * Context: See the comment on locking at the top of datapath.c for additional * locking information. @@ -89,6 +91,8 @@ struct datapath { possible_net_t net; u32 user_features; + + u32 max_headroom; }; /** diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1d055c559eaf..03378e75a67c 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -55,7 +55,7 @@ struct ovs_tunnel_info { FIELD_SIZEOF(struct sw_flow_key, recirc_id)) struct sw_flow_key { - u8 tun_opts[255]; + u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d1bd4a45ca2d..689c17264221 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1959,6 +1959,12 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (!tun_dst) return -ENOMEM; + err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL); + if (err) { + dst_release((struct dst_entry *)tun_dst); + return err; + } + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, sizeof(*ovs_tun), log); if (IS_ERR(a)) { @@ -2038,9 +2044,6 @@ static int validate_set(const struct nlattr *a, break; case OVS_KEY_ATTR_TUNNEL: - if (eth_p_mpls(eth_type)) - return -EINVAL; - if (masked) return -EINVAL; /* Masked tunnel set not supported. */ diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index ec76398a792f..7c8b90bf0e54 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -138,6 +138,11 @@ internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) return stats; } +static void internal_set_rx_headroom(struct net_device *dev, int new_hr) +{ + dev->needed_headroom = new_hr; +} + static const struct net_device_ops internal_dev_netdev_ops = { .ndo_open = internal_dev_open, .ndo_stop = internal_dev_stop, @@ -145,6 +150,7 @@ static const struct net_device_ops internal_dev_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = internal_dev_change_mtu, .ndo_get_stats64 = internal_get_stats, + .ndo_set_rx_headroom = internal_set_rx_headroom, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -158,7 +164,8 @@ static void do_setup(struct net_device *netdev) netdev->netdev_ops = &internal_dev_netdev_ops; netdev->priv_flags &= ~IFF_TX_SKB_SHARING; - netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH; + netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | + IFF_PHONY_HEADROOM; netdev->destructor = internal_dev_destructor; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; @@ -199,6 +206,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) err = -ENOMEM; goto error_free_netdev; } + vport->dev->needed_headroom = vport->dp->max_headroom; dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); internal_dev = internal_dev_priv(vport->dev); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 6a6adf314363..4e3972344aa6 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -58,7 +58,7 @@ static void netdev_port_receive(struct sk_buff *skb) return; skb_push(skb, ETH_HLEN); - ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN); + skb_postpush_rcsum(skb, skb->data, ETH_HLEN); ovs_vport_receive(vport, skb, skb_tunnel_info(skb)); return; error: diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index c10899cb9040..f01f28a567ad 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -185,13 +185,6 @@ static inline struct vport *vport_from_priv(void *priv) int ovs_vport_receive(struct vport *, struct sk_buff *, const struct ip_tunnel_info *); -static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); -} - static inline const char *ovs_vport_name(struct vport *vport) { return vport->dev->name; |