diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-12 18:07:07 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-12 18:07:07 -0800 |
commit | 6be35c700f742e911ecedd07fcc43d4439922334 (patch) | |
tree | ca9f37214d204465fcc2d79c82efd291e357c53c /net/ipv4/af_inet.c | |
parent | e37aa63e87bd581f9be5555ed0ba83f5295c92fc (diff) | |
parent | 520dfe3a3645257bf83660f672c47f8558f3d4c4 (diff) | |
download | op-kernel-dev-6be35c700f742e911ecedd07fcc43d4439922334.zip op-kernel-dev-6be35c700f742e911ecedd07fcc43d4439922334.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking changes from David Miller:
1) Allow to dump, monitor, and change the bridge multicast database
using netlink. From Cong Wang.
2) RFC 5961 TCP blind data injection attack mitigation, from Eric
Dumazet.
3) Networking user namespace support from Eric W. Biederman.
4) tuntap/virtio-net multiqueue support by Jason Wang.
5) Support for checksum offload of encapsulated packets (basically,
tunneled traffic can still be checksummed by HW). From Joseph
Gasparakis.
6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
Daniel Borkmann.
7) Bridge port parameters over netlink and BPDU blocking support
from Stephen Hemminger.
8) Improve data access patterns during inet socket demux by rearranging
socket layout, from Eric Dumazet.
9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
Jon Maloy.
10) Update TCP socket hash sizing to be more in line with current day
realities. The existing heurstics were choosen a decade ago.
From Eric Dumazet.
11) Fix races, queue bloat, and excessive wakeups in ATM and
associated drivers, from Krzysztof Mazur and David Woodhouse.
12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
in VXLAN driver, from David Stevens.
13) Add "oops_only" mode to netconsole, from Amerigo Wang.
14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
allow DCB netlink to work on namespaces other than the initial
namespace. From John Fastabend.
15) Support PTP in the Tigon3 driver, from Matt Carlson.
16) tun/vhost zero copy fixes and improvements, plus turn it on
by default, from Michael S. Tsirkin.
17) Support per-association statistics in SCTP, from Michele
Baldessari.
And many, many, driver updates, cleanups, and improvements. Too
numerous to mention individually.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
net/mlx4_en: Add support for destination MAC in steering rules
net/mlx4_en: Use generic etherdevice.h functions.
net: ethtool: Add destination MAC address to flow steering API
bridge: add support of adding and deleting mdb entries
bridge: notify mdb changes via netlink
ndisc: Unexport ndisc_{build,send}_skb().
uapi: add missing netconf.h to export list
pkt_sched: avoid requeues if possible
solos-pci: fix double-free of TX skb in DMA mode
bnx2: Fix accidental reversions.
bna: Driver Version Updated to 3.1.2.1
bna: Firmware update
bna: Add RX State
bna: Rx Page Based Allocation
bna: TX Intr Coalescing Fix
bna: Tx and Rx Optimizations
bna: Code Cleanup and Enhancements
ath9k: check pdata variable before dereferencing it
ath5k: RX timestamp is reported at end of frame
ath9k_htc: RX timestamp is reported at end of frame
...
Diffstat (limited to 'net/ipv4/af_inet.c')
-rw-r--r-- | net/ipv4/af_inet.c | 93 |
1 files changed, 64 insertions, 29 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 766c596..24b384b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -346,7 +346,8 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; err = -EAFNOSUPPORT; @@ -473,6 +474,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; int err; @@ -496,7 +498,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -516,7 +518,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one @@ -1251,7 +1254,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; const struct iphdr *iph; int proto; int ihl; @@ -1275,9 +1278,9 @@ static int inet_gso_send_check(struct sk_buff *skb) err = -EPROTONOSUPPORT; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_send_check)) - err = ops->gso_send_check(skb); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_send_check)) + err = ops->callbacks.gso_send_check(skb); rcu_read_unlock(); out: @@ -1288,7 +1291,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); - const struct net_protocol *ops; + const struct net_offload *ops; struct iphdr *iph; int proto; int ihl; @@ -1325,9 +1328,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_segment)) - segs = ops->gso_segment(skb, features); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) + segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); if (!segs || IS_ERR(segs)) @@ -1356,7 +1359,7 @@ out: static struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; struct sk_buff **pp = NULL; struct sk_buff *p; const struct iphdr *iph; @@ -1378,8 +1381,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, proto = iph->protocol; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (!ops || !ops->gro_receive) + ops = rcu_dereference(inet_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; if (*(u8 *)iph != 0x45) @@ -1420,7 +1423,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->gro_receive(head, skb); + pp = ops->callbacks.gro_receive(head, skb); out_unlock: rcu_read_unlock(); @@ -1435,7 +1438,7 @@ static int inet_gro_complete(struct sk_buff *skb) { __be16 newlen = htons(skb->len - skb_network_offset(skb)); struct iphdr *iph = ip_hdr(skb); - const struct net_protocol *ops; + const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; @@ -1443,11 +1446,11 @@ static int inet_gro_complete(struct sk_buff *skb) iph->tot_len = newlen; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (WARN_ON(!ops || !ops->gro_complete)) + ops = rcu_dereference(inet_offloads[proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->gro_complete(skb); + err = ops->callbacks.gro_complete(skb); out_unlock: rcu_read_unlock(); @@ -1558,23 +1561,33 @@ static const struct net_protocol tcp_protocol = { .early_demux = tcp_v4_early_demux, .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload tcp_offload = { + .callbacks = { + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, +}; + static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, - .gso_send_check = udp4_ufo_send_check, - .gso_segment = udp4_ufo_fragment, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload udp_offload = { + .callbacks = { + .gso_send_check = udp4_ufo_send_check, + .gso_segment = udp4_ufo_fragment, + }, +}; + static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = ping_err, @@ -1659,13 +1672,35 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ +static struct packet_offload ip_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_send_check = inet_gso_send_check, + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, +}; + +static int __init ipv4_offload_init(void) +{ + /* + * Add offloads + */ + if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0) + pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__); + + dev_add_offload(&ip_packet_offload); + return 0; +} + +fs_initcall(ipv4_offload_init); + static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, - .gso_send_check = inet_gso_send_check, - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, }; static int __init inet_init(void) |