diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 10:37:28 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 10:37:28 -0700 |
commit | d7e9660ad9d5e0845f52848bce31bcf5cdcdea6b (patch) | |
tree | c6c67d145771187b194d79d603742b31090a59d6 /net/ipv6 | |
parent | b8cb48aae1b8c50b37dcb7710363aa69a7a0d9ca (diff) | |
parent | 13af7a6ea502fcdd4c0e3d7de6e332b102309491 (diff) | |
download | op-kernel-dev-d7e9660ad9d5e0845f52848bce31bcf5cdcdea6b.zip op-kernel-dev-d7e9660ad9d5e0845f52848bce31bcf5cdcdea6b.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1623 commits)
netxen: update copyright
netxen: fix tx timeout recovery
netxen: fix file firmware leak
netxen: improve pci memory access
netxen: change firmware write size
tg3: Fix return ring size breakage
netxen: build fix for INET=n
cdc-phonet: autoconfigure Phonet address
Phonet: back-end for autoconfigured addresses
Phonet: fix netlink address dump error handling
ipv6: Add IFA_F_DADFAILED flag
net: Add DEVTYPE support for Ethernet based devices
mv643xx_eth.c: remove unused txq_set_wrr()
ucc_geth: Fix hangs after switching from full to half duplex
ucc_geth: Rearrange some code to avoid forward declarations
phy/marvell: Make non-aneg speed/duplex forcing work for 88E1111 PHYs
drivers/net/phy: introduce missing kfree
drivers/net/wan: introduce missing kfree
net: force bridge module(s) to be GPL
Subject: [PATCH] appletalk: Fix skb leak when ipddp interface is not loaded
...
Fixed up trivial conflicts:
- arch/x86/include/asm/socket.h
converted to <asm-generic/socket.h> in the x86 tree. The generic
header has the same new #define's, so that works out fine.
- drivers/net/tun.c
fix conflict between 89f56d1e9 ("tun: reuse struct sock fields") that
switched over to using 'tun->socket.sk' instead of the redundantly
available (and thus removed) 'tun->sk', and 2b980dbd ("lsm: Add hooks
to the TUN driver") which added a new 'tun->sk' use.
Noted in 'next' by Stephen Rothwell.
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 12 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 20 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 17 | ||||
-rw-r--r-- | net/ipv6/ip6_fib.c | 16 | ||||
-rw-r--r-- | net/ipv6/ip6_input.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 44 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 11 | ||||
-rw-r--r-- | net/ipv6/ipv6_sockglue.c | 5 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 1 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 24 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6_tables.c | 48 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_eui64.c | 9 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6table_filter.c | 10 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6table_mangle.c | 16 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6table_raw.c | 10 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6table_security.c | 12 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 18 | ||||
-rw-r--r-- | net/ipv6/proc.c | 4 | ||||
-rw-r--r-- | net/ipv6/protocol.c | 15 | ||||
-rw-r--r-- | net/ipv6/raw.c | 9 | ||||
-rw-r--r-- | net/ipv6/route.c | 34 | ||||
-rw-r--r-- | net/ipv6/sit.c | 11 | ||||
-rw-r--r-- | net/ipv6/sysctl_net_ipv6.c | 4 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 21 | ||||
-rw-r--r-- | net/ipv6/udp.c | 158 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 38 |
27 files changed, 374 insertions, 205 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 43b3c9f..c9b3690 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1371,12 +1371,14 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add /* Gets referenced address, destroys ifaddr */ -static void addrconf_dad_stop(struct inet6_ifaddr *ifp) +static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); addrconf_del_timer(ifp); ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags |= IFA_F_DADFAILED; spin_unlock_bh(&ifp->lock); in6_ifa_put(ifp); #ifdef CONFIG_IPV6_PRIVACY @@ -1422,7 +1424,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - addrconf_dad_stop(ifp); + addrconf_dad_stop(ifp, 1); } /* Join to solicited addr multicast group. */ @@ -2778,7 +2780,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { - ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); @@ -2795,7 +2797,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) * - otherwise, kill it. */ in6_ifa_hold(ifp); - addrconf_dad_stop(ifp); + addrconf_dad_stop(ifp, 0); return; } @@ -2829,7 +2831,7 @@ static void addrconf_dad_timer(unsigned long data) * DAD was successful */ - ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 45f9a2a..a123a32 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -774,6 +774,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; struct inet6_protocol *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; if (!(features & NETIF_F_V6_CSUM)) features &= ~NETIF_F_SG; @@ -793,10 +798,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - + ops = rcu_dereference(inet6_protos[proto]); if (likely(ops && ops->gso_segment)) { skb_reset_transport_header(skb); segs = ops->gso_segment(skb, features); @@ -810,6 +814,16 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) ipv6h = ipv6_hdr(skb); ipv6h->payload_len = htons(skb->len - skb->mac_len - sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } } out: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eab62a7..e2325f6 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -323,7 +323,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int hlimit, tclass; + int hlimit; int err = 0; if ((u8 *)hdr < skb->head || @@ -469,10 +469,6 @@ route_done: if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; @@ -488,8 +484,8 @@ route_done: err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - hlimit, tclass, NULL, &fl, (struct rt6_info*)dst, + sizeof(struct icmp6hdr), hlimit, + np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { ip6_flush_pending_frames(sk); @@ -522,7 +518,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; int err = 0; int hlimit; - int tclass; saddr = &ipv6_hdr(skb)->daddr; @@ -562,10 +557,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - idev = in6_dev_get(skb->dev); msg.skb = skb; @@ -573,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, + sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 52ee1dc..0e93ca5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -164,12 +164,6 @@ static __inline__ void rt6_release(struct rt6_info *rt) dst_free(&rt->u.dst); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES -#define FIB_TABLE_HASHSZ 256 -#else -#define FIB_TABLE_HASHSZ 1 -#endif - static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; @@ -180,7 +174,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) */ rwlock_init(&tb->tb6_lock); - h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); + h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation @@ -231,7 +225,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) if (id == 0) id = RT6_TABLE_MAIN; - h = id & (FIB_TABLE_HASHSZ - 1); + h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { @@ -382,7 +376,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) arg.net = net; w->args = &arg; - for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry(tb, node, head, tb6_hlist) { @@ -1368,7 +1362,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), unsigned int h; rcu_read_lock(); - for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); @@ -1483,7 +1477,7 @@ static int fib6_net_init(struct net *net) if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = kcalloc(FIB_TABLE_HASHSZ, + net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ, sizeof(*net->ipv6.fib_table_hash), GFP_KERNEL); if (!net->ipv6.fib_table_hash) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6d6a427..2d9cbaa 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -63,7 +63,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (skb->pkt_type == PACKET_OTHERHOST) { kfree_skb(skb); - return 0; + return NET_RX_DROP; } rcu_read_lock(); @@ -133,7 +133,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (ipv6_parse_hopopts(skb) < 0) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); rcu_read_unlock(); - return 0; + return NET_RX_DROP; } } @@ -149,7 +149,7 @@ err: drop: rcu_read_unlock(); kfree_skb(skb); - return 0; + return NET_RX_DROP; } /* diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 87f8419..cd48801a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -57,18 +57,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); -static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr) -{ - static u32 ipv6_fragmentation_id = 1; - static DEFINE_SPINLOCK(ip6_id_lock); - - spin_lock_bh(&ip6_id_lock); - fhdr->identification = htonl(ipv6_fragmentation_id); - if (++ipv6_fragmentation_id == 0) - ipv6_fragmentation_id = 1; - spin_unlock_bh(&ip6_id_lock); -} - int __ip6_local_out(struct sk_buff *skb) { int len; @@ -206,7 +194,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; - int hlimit, tclass; + int hlimit = -1; + int tclass = 0; u32 mtu; if (opt) { @@ -249,19 +238,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* * Fill in the IPv6 header */ - - hlimit = -1; - if (np) + if (np) { + tclass = np->tclass; hlimit = np->hop_limit; + } if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = -1; - if (np) - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; hdr->payload_len = htons(seg_len); @@ -706,7 +689,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -844,7 +827,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh); frag_id = fh->identification; } else fh->identification = frag_id; @@ -1087,11 +1070,13 @@ static inline int ip6_ufo_append_data(struct sock *sk, if (!err) { struct frag_hdr fhdr; - /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->gso_size = mtu - fragheaderlen - - sizeof(struct frag_hdr); + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(skb, &fhdr); + ipv6_select_ident(&fhdr); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); @@ -1526,7 +1511,7 @@ int ip6_push_pending_frames(struct sock *sk) err = ip6_local_out(skb); if (err) { if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } @@ -1535,6 +1520,7 @@ out: ip6_cork_release(inet, np); return err; error: + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); goto out; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 51f410e..7d25bbe 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1036,7 +1036,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } -static int +static netdev_tx_t ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); @@ -1063,14 +1063,14 @@ ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; t->recursion--; - return 0; + return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); t->recursion--; - return 0; + return NETDEV_TX_OK; } static void ip6_tnl_set_cap(struct ip6_tnl *t) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c769f15..5c8d737 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -204,7 +204,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ip6mr_vif_seq_ops = { +static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, .next = ip6mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, @@ -217,7 +217,7 @@ static int ip6mr_vif_open(struct inode *inode, struct file *file) sizeof(struct ipmr_vif_iter)); } -static struct file_operations ip6mr_vif_fops = { +static const struct file_operations ip6mr_vif_fops = { .owner = THIS_MODULE, .open = ip6mr_vif_open, .read = seq_read, @@ -341,7 +341,7 @@ static int ipmr_mfc_open(struct inode *inode, struct file *file) sizeof(struct ipmr_mfc_iter)); } -static struct file_operations ip6mr_mfc_fops = { +static const struct file_operations ip6mr_mfc_fops = { .owner = THIS_MODULE, .open = ipmr_mfc_open, .read = seq_read, @@ -416,7 +416,8 @@ static struct inet6_protocol pim6_protocol = { /* Service routines creating virtual interfaces: PIMREG */ -static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, + struct net_device *dev) { struct net *net = dev_net(dev); @@ -427,7 +428,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static const struct net_device_ops reg_vif_netdev_ops = { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7fdf9a..f5e0682 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -315,6 +315,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, goto e_inval; if (val < -1 || val > 0xff) goto e_inval; + /* RFC 3542, 6.5: default traffic class of 0x0 */ + if (val == -1) + val = 0; np->tclass = val; retv = 0; break; @@ -1037,8 +1040,6 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_TCLASS: val = np->tclass; - if (val < 0) - val = 0; break; case IPV6_RECVTCLASS: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4b264ed..71c3dac 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2107,7 +2107,6 @@ static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, for (j=0; j<i; j++) (void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { - struct inet6_dev *idev = pmc->idev; struct ip6_sf_list *psf; /* filter mode change */ diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9eb68e9..7015478 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -98,7 +98,7 @@ static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); -static struct neigh_ops ndisc_generic_ops = { +static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, @@ -108,7 +108,7 @@ static struct neigh_ops ndisc_generic_ops = { .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops ndisc_hh_ops = { +static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, @@ -119,7 +119,7 @@ static struct neigh_ops ndisc_hh_ops = { }; -static struct neigh_ops ndisc_direct_ops = { +static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = dev_queue_xmit, .connected_output = dev_queue_xmit, @@ -955,8 +955,8 @@ static void ndisc_recv_na(struct sk_buff *skb) */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK1(KERN_WARNING - "ICMPv6 NA: someone advertises our address on %s!\n", - ifp->idev->dev->name); + "ICMPv6 NA: someone advertises our address %pI6 on %s!\n", + &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } @@ -1151,10 +1151,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) skb->dev->name); return; } - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) { - in6_dev_put(in6_dev); - return; - } if (!ndisc_parse_options(opt, optlen, &ndopts)) { in6_dev_put(in6_dev); @@ -1163,6 +1159,10 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } + /* skip route and link configuration on routers */ + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + goto skip_linkparms; + #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) @@ -1283,9 +1283,7 @@ skip_defrtr: } } -#ifdef CONFIG_IPV6_NDISC_NODETYPE skip_linkparms: -#endif /* * Process options. @@ -1312,6 +1310,10 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } + /* skip route and link configuration on routers */ + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + goto out; + #ifdef CONFIG_IPV6_ROUTE_INFO if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index ced1f2c..cc9f8ef 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -8,7 +8,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> @@ -222,16 +222,11 @@ get_entry(void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline int -unconditional(const struct ip6t_ip6 *ipv6) +static inline bool unconditional(const struct ip6t_ip6 *ipv6) { - unsigned int i; - - for (i = 0; i < sizeof(*ipv6); i++) - if (((char *)ipv6)[i]) - break; + static const struct ip6t_ip6 uncond; - return (i == sizeof(*ipv6)); + return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ @@ -745,6 +740,21 @@ find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, return ret; } +static bool check_underflow(struct ip6t_entry *e) +{ + const struct ip6t_entry_target *t; + unsigned int verdict; + + if (!unconditional(&e->ipv6)) + return false; + t = ip6t_get_target(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct ip6t_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, @@ -752,6 +762,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, + unsigned int valid_hooks, unsigned int *i) { unsigned int h; @@ -771,15 +782,21 @@ check_entry_size_and_hooks(struct ip6t_entry *e, /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) { + pr_err("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); + return -EINVAL; + } newinfo->underflow[h] = underflows[h]; + } } - /* FIXME: underflows must be unconditional, standard verdicts - < 0 (not IP6T_RETURN). --RR */ - /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; @@ -842,7 +859,7 @@ translate_table(const char *name, newinfo, entry0, entry0 + size, - hook_entries, underflows, &i); + hook_entries, underflows, valid_hooks, &i); if (ret != 0) return ret; @@ -2083,7 +2100,8 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ip6t_register_table(struct net *net, struct xt_table *table, +struct xt_table *ip6t_register_table(struct net *net, + const struct xt_table *table, const struct ip6t_replace *repl) { int ret; diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index db610ba..ca287f6 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -23,7 +23,6 @@ static bool eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par) { unsigned char eui64[8]; - int i = 0; if (!(skb_mac_header(skb) >= skb->head && skb_mac_header(skb) + ETH_HLEN <= skb->data) && @@ -42,12 +41,8 @@ eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par) eui64[4] = 0xfe; eui64[0] ^= 0x02; - i = 0; - while (ipv6_hdr(skb)->saddr.s6_addr[8 + i] == eui64[i] - && i < 8) - i++; - - if (i == 8) + if (!memcmp(ipv6_hdr(skb)->saddr.s6_addr + 8, eui64, + sizeof(eui64))) return true; } } diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index ef5a0a3..6f4383a 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -51,11 +51,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_filter = { +static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -95,21 +95,21 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_FILTER, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_FILTER, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_FILTER, }, diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index ab0d398..0ad9143 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -21,7 +21,7 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[5]; @@ -57,11 +57,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_mangler = { +static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -136,35 +136,35 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_post_routing_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_MANGLE, }, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 4b792b6..ed1a118 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -8,7 +8,7 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[2]; @@ -35,11 +35,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_raw = { +static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -68,14 +68,14 @@ ip6t_local_out_hook(unsigned int hook, static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_pre_routing_hook, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, .owner = THIS_MODULE, }, { .hook = ip6t_local_out_hook, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_FIRST, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 0ea37ff..41b444c 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -26,7 +26,7 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[3]; @@ -56,11 +56,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table security_table = { +static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; static unsigned int @@ -101,21 +101,21 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_local_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_SECURITY, }, { .hook = ip6t_forward_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SECURITY, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SECURITY, }, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 2a15c2d..5f2ec20 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -27,6 +27,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/nf_log.h> static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple) @@ -176,8 +177,11 @@ static unsigned int ipv6_confirm(unsigned int hooknum, } ret = helper->help(skb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL, + "nf_ct_%s: dropping packet", helper->name); return ret; + } out: /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); @@ -265,42 +269,42 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { { .hook = ipv6_defrag, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_conntrack_in, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_conntrack_local, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_defrag, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_confirm, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { .hook = ipv6_confirm, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_LAST-1, }, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 590ddef..c9605c3 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -101,7 +101,7 @@ static struct snmp_mib snmp6_icmp6_list[] = { }; /* RFC 4293 v6 ICMPMsgStatsTable; named items for RFC 2466 compatibility */ -static char *icmp6type2name[256] = { +static const char *const icmp6type2name[256] = { [ICMPV6_DEST_UNREACH] = "DestUnreachs", [ICMPV6_PKT_TOOBIG] = "PktTooBigs", [ICMPV6_TIME_EXCEED] = "TimeExcds", @@ -144,7 +144,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) /* print by name -- deprecated items */ for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { int icmptype; - char *p; + const char *p; icmptype = i & 0xff; p = icmp6type2name[icmptype]; diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 9ab7891..568864f 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -20,20 +20,9 @@ * - Removed unused variable 'inet6_protocol_base' * - Modified inet6_del_protocol() to correctly maintain copy bit. */ - -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/in6.h> +#include <linux/module.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> - -#include <net/sock.h> -#include <net/snmp.h> - -#include <net/ipv6.h> +#include <linux/spinlock.h> #include <net/protocol.h> struct inet6_protocol *inet6_protos[MAX_INET_PROTOS]; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d6c3c1c..7d675b8 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -642,7 +642,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -653,6 +653,8 @@ error_fault: kfree_skb(skb); error: IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !np->recverr) + err = 0; return err; } @@ -877,11 +879,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1473ee0..9ccfef3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -665,7 +665,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad net->ipv6.sysctl.ip6_rt_gc_elasticity = 1; net->ipv6.sysctl.ip6_rt_gc_min_interval = 0; - ip6_dst_gc(net->ipv6.ip6_dst_ops); + ip6_dst_gc(&net->ipv6.ip6_dst_ops); net->ipv6.sysctl.ip6_rt_gc_elasticity = saved_rt_elasticity; @@ -970,7 +970,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; @@ -1060,7 +1060,7 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), static int ip6_dst_gc(struct dst_ops *ops) { unsigned long now = jiffies; - struct net *net = ops->dst_net; + struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; @@ -1154,7 +1154,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt == NULL) { err = -ENOMEM; @@ -1643,7 +1643,7 @@ out: static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { struct net *net = dev_net(ort->rt6i_dev); - struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt) { rt->u.dst.input = ort->u.dst.input; @@ -1923,7 +1923,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, int anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); struct neighbour *neigh; if (rt == NULL) @@ -2501,7 +2501,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) net->ipv6.rt6_stats->fib_rt_alloc, net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, - atomic_read(&net->ipv6.ip6_dst_ops->entries), + atomic_read(&net->ipv6.ip6_dst_ops.entries), net->ipv6.rt6_stats->fib_discarded_routes); return 0; @@ -2637,7 +2637,7 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net) if (table) { table[0].data = &net->ipv6.sysctl.flush_delay; - table[1].data = &net->ipv6.ip6_dst_ops->gc_thresh; + table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; @@ -2655,12 +2655,8 @@ static int ip6_route_net_init(struct net *net) { int ret = -ENOMEM; - net->ipv6.ip6_dst_ops = kmemdup(&ip6_dst_ops_template, - sizeof(*net->ipv6.ip6_dst_ops), - GFP_KERNEL); - if (!net->ipv6.ip6_dst_ops) - goto out; - net->ipv6.ip6_dst_ops->dst_net = hold_net(net); + memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, + sizeof(net->ipv6.ip6_dst_ops)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), @@ -2669,7 +2665,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_dst_ops; net->ipv6.ip6_null_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; - net->ipv6.ip6_null_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_null_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2679,7 +2675,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; - net->ipv6.ip6_prohibit_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_prohibit_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2688,7 +2684,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; - net->ipv6.ip6_blk_hole_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_blk_hole_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; #endif net->ipv6.sysctl.flush_delay = 0; @@ -2717,8 +2713,6 @@ out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_ip6_dst_ops: - release_net(net->ipv6.ip6_dst_ops->dst_net); - kfree(net->ipv6.ip6_dst_ops); goto out; } @@ -2733,8 +2727,6 @@ static void ip6_route_net_exit(struct net *net) kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif - release_net(net->ipv6.ip6_dst_ops->dst_net); - kfree(net->ipv6.ip6_dst_ops); } static struct pernet_operations ip6_route_net_ops = { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 98b7327d..0ae4f64 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -609,7 +609,8 @@ static inline __be32 try_6to4(struct in6_addr *v6dst) * and that skb is filled properly by that function. */ -static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->dev->stats; @@ -753,7 +754,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) stats->tx_dropped++; dev_kfree_skb(skb); tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); @@ -778,7 +779,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; if (mtu > IPV6_MIN_MTU) - iph->frag_off = htons(IP_DF); + iph->frag_off = tiph->frag_off; else iph->frag_off = 0; @@ -794,7 +795,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) IPTUNNEL_XMIT(); tunnel->recursion--; - return 0; + return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); @@ -802,7 +803,7 @@ tx_error: stats->tx_errors++; dev_kfree_skb(skb); tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index a031034..0dc6a4e 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -40,7 +40,7 @@ static ctl_table ipv6_table_template[] = { { .ctl_name = 0 } }; -static ctl_table ipv6_table[] = { +static ctl_table ipv6_rotable[] = { { .ctl_name = NET_IPV6_MLD_MAX_MSF, .procname = "mld_max_msf", @@ -130,7 +130,7 @@ int ipv6_sysctl_register(void) { int err = -ENOMEM; - ip6_header = register_net_sysctl_rotable(net_ipv6_ctl_path, ipv6_table); + ip6_header = register_net_sysctl_rotable(net_ipv6_ctl_path, ipv6_rotable); if (ip6_header == NULL) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d849dd5..3aae0f2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -75,11 +75,11 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static struct inet_connection_sock_af_ops ipv6_mapped; -static struct inet_connection_sock_af_ops ipv6_specific; +static const struct inet_connection_sock_af_ops ipv6_mapped; +static const struct inet_connection_sock_af_ops ipv6_specific; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_specific; -static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, struct in6_addr *addr) @@ -591,7 +591,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, } sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } - if (tcp_alloc_md5sig_pool() == NULL) { + if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } @@ -894,7 +894,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { +static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .md5_lookup = tcp_v6_reqsk_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, }; @@ -1003,6 +1003,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); t1 = (struct tcphdr *) skb_push(buff, tot_len); + skb_reset_transport_header(skb); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); @@ -1760,7 +1761,7 @@ static int tcp_v6_remember_stamp(struct sock *sk) return 0; } -static struct inet_connection_sock_af_ops ipv6_specific = { +static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -1780,7 +1781,7 @@ static struct inet_connection_sock_af_ops ipv6_specific = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_add = tcp_v6_md5_add_func, @@ -1792,7 +1793,7 @@ static struct tcp_sock_af_ops tcp_sock_ipv6_specific = { * TCP over IPv4 via INET6 API */ -static struct inet_connection_sock_af_ops ipv6_mapped = { +static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1812,7 +1813,7 @@ static struct inet_connection_sock_af_ops ipv6_mapped = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_add = tcp_v6_md5_add_func, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 33b59bd..1640406 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -638,6 +638,47 @@ static void udp_v6_flush_pending_frames(struct sock *sk) } } +/** + * udp6_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + unsigned int offset; + struct udphdr *uh = udp_hdr(skb); + __wsum csum = 0; + + if (skb_queue_len(&sk->sk_write_queue) == 1) { + /* Only one fragment on the socket. */ + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); + } else { + /* + * HW-checksum won't work as there are two or more + * fragments on the socket so that all csums of sk_buffs + * should be together + */ + offset = skb_transport_offset(skb); + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + + skb->ip_summed = CHECKSUM_NONE; + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + + uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, + csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } +} + /* * Sending */ @@ -668,7 +709,11 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (is_udplite) csum = udplite_csum_outgoing(sk, skb); - else + else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst, + up->len); + goto send; + } else csum = udp_csum_outgoing(sk, skb); /* add protocol-dependent pseudo-header */ @@ -677,13 +722,20 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (uh->check == 0) uh->check = CSUM_MANGLED_0; +send: err = ip6_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; - if (!err) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } @@ -900,11 +952,8 @@ do_udp_sendmsg: hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -1032,9 +1081,102 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb->csum_start - skb_headroom(skb); + csum = skb_checksum(skb, offset, skb->len- offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_headroom(skb) < frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} + static struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 3a3c677..8ec3d45 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -306,9 +306,26 @@ static void xfrm6_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo); } +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm6_policy_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "xfrm6_gc_thresh", + .data = &xfrm6_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static struct ctl_table_header *sysctl_hdr; +#endif + int __init xfrm6_init(void) { int ret; + unsigned int gc_thresh; ret = xfrm6_policy_init(); if (ret) @@ -317,6 +334,23 @@ int __init xfrm6_init(void) ret = xfrm6_state_init(); if (ret) goto out_policy; + /* + * We need a good default value for the xfrm6 gc threshold. + * In ipv4 we set it to the route hash table size * 8, which + * is half the size of the maximaum route cache for ipv4. It + * would be good to do the same thing for v6, except the table is + * constructed differently here. Here each table for a net namespace + * can have FIB_TABLE_HASHSZ entries, so lets go with the same + * computation that we used for ipv4 here. Also, lets keep the initial + * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults + * to that as a minimum as well + */ + gc_thresh = FIB6_TABLE_HASHSZ * 8; + xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; +#ifdef CONFIG_SYSCTL + sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, + xfrm6_policy_table); +#endif out: return ret; out_policy: @@ -326,6 +360,10 @@ out_policy: void xfrm6_fini(void) { +#ifdef CONFIG_SYSCTL + if (sysctl_hdr) + unregister_net_sysctl_table(sysctl_hdr); +#endif //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); |