diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/core/dev.c | 11 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 6 | ||||
-rw-r--r-- | net/core/skbuff.c | 2 | ||||
-rw-r--r-- | net/ipv4/Kconfig | 6 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_defrag_ipv4.c | 21 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 27 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 24 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 21 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 10 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 18 | ||||
-rw-r--r-- | net/ipv4/udp.c | 7 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 19 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_reasm.c | 7 | ||||
-rw-r--r-- | net/ipv6/reassembly.c | 5 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 28 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 3 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_core.c | 1 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_ctl.c | 4 | ||||
-rw-r--r-- | net/packet/af_packet.c | 71 | ||||
-rw-r--r-- | net/rds/ib.c | 4 | ||||
-rw-r--r-- | net/rds/iw.c | 4 | ||||
-rw-r--r-- | net/sunrpc/sched.c | 15 | ||||
-rw-r--r-- | net/sunrpc/svc_xprt.c | 31 | ||||
-rw-r--r-- | net/sunrpc/svcauth_unix.c | 53 |
25 files changed, 212 insertions, 188 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 6fe7d739e59b..be9924f60ec3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5035,6 +5035,11 @@ int register_netdevice(struct net_device *dev) rollback_registered(dev); dev->reg_state = NETREG_UNREGISTERED; } + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; @@ -5597,6 +5602,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + synchronize_net(); err = 0; out: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 33148a568199..794bcb897ff0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1364,15 +1364,15 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_UNREGISTER: rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); break; - case NETDEV_REGISTER: - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); - break; case NETDEV_UP: case NETDEV_DOWN: rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); break; + case NETDEV_POST_INIT: + case NETDEV_REGISTER: case NETDEV_CHANGE: case NETDEV_GOING_DOWN: + case NETDEV_UNREGISTER_BATCH: break; default: rtmsg_ifinfo(RTM_NEWLINK, dev, 0); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bfa3e7865a8c..93c4e060c91e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -93,7 +93,7 @@ static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, /* Pipe buffer operations for a socket. */ -static struct pipe_buf_operations sock_pipe_buf_ops = { +static const struct pipe_buf_operations sock_pipe_buf_ops = { .can_merge = 0, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 70491d9035eb..0c94a1ac2946 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -166,7 +166,7 @@ config IP_PNP_DHCP If unsure, say Y. Note that if you want to use DHCP, a DHCP server must be operating on your network. Read - <file:Documentation/filesystems/nfsroot.txt> for details. + <file:Documentation/filesystems/nfs/nfsroot.txt> for details. config IP_PNP_BOOTP bool "IP: BOOTP support" @@ -181,7 +181,7 @@ config IP_PNP_BOOTP does BOOTP itself, providing all necessary information on the kernel command line, you can say N here. If unsure, say Y. Note that if you want to use BOOTP, a BOOTP server must be operating on your network. - Read <file:Documentation/filesystems/nfsroot.txt> for details. + Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details. config IP_PNP_RARP bool "IP: RARP support" @@ -194,7 +194,7 @@ config IP_PNP_RARP older protocol which is being obsoleted by BOOTP and DHCP), say Y here. Note that if you want to use RARP, a RARP server must be operating on your network. Read - <file:Documentation/filesystems/nfsroot.txt> for details. + <file:Documentation/filesystems/nfs/nfsroot.txt> for details. # not yet ready.. # bool ' IP: ARP support' CONFIG_IP_PNP_ARP diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 4e08b7f2331c..10a6a604bf32 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config); /* * Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel - * command line parameter. See Documentation/filesystems/nfsroot.txt. + * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt. */ static int __init ic_proto_name(char *name) { diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index fa2d6b6fc3e5..331ead3ebd1b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -14,6 +14,7 @@ #include <net/route.h> #include <net/ip.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> @@ -34,6 +35,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } +static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP_DEFRAG_CONNTRACK_BRIDGE_IN; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP_DEFRAG_CONNTRACK_IN; + else + return IP_DEFRAG_CONNTRACK_OUT; +} + static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, @@ -50,10 +65,8 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif /* Gather fragments. */ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { - if (nf_ct_ipv4_gather_frags(skb, - hooknum == NF_INET_PRE_ROUTING ? - IP_DEFRAG_CONNTRACK_IN : - IP_DEFRAG_CONNTRACK_OUT)) + enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); + if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; } return NF_ACCEPT; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 26399ad2a289..66fd80ef2473 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -277,6 +277,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + ret = NULL; req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) @@ -292,6 +299,12 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; ireq->ecn_ok = 0; + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -340,20 +353,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } } - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - /* Try to redo what tcp_v4_send_synack did. */ req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 12cab7d74dba..28e029632493 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3727,7 +3727,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - u8 **hvpp, int estab, struct dst_entry *dst) + u8 **hvpp, int estab) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3766,8 +3766,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) { + !estab && sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { @@ -3783,8 +3782,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps && - !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) { + (!estab && sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3792,8 +3790,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack && - !dst_feature(dst, RTAX_FEATURE_NO_SACK)) { + !estab && sysctl_tcp_sack) { opt_rx->sack_ok = 1; tcp_sack_reset(opt_rx); } @@ -3878,7 +3875,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); return 1; } @@ -4133,10 +4130,8 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack && - !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4165,15 +4160,13 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack && - !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -5428,11 +5421,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); struct tcp_cookie_values *cvp = tp->cookie_values; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0); if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 15e96030ce47..65b8ebfd078a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1262,20 +1262,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops; #endif - ireq = inet_rsk(req); - ireq->loc_addr = daddr; - ireq->rmt_addr = saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(sk, skb); - - dst = inet_csk_route_req(sk, req); - if(!dst) - goto drop_and_free; - tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1319,8 +1309,14 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(sk, skb); + if (security_inet_conn_request(sk, skb, req)) - goto drop_and_release; + goto drop_and_free; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -1345,6 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && + (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && peer->v4daddr == saddr) { if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 87accec8d097..f206ee5dda80 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -95,9 +95,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; + tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -526,9 +526,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); int paws_reject = 0; - if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) { - tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); + tmp_opt.saw_tstamp = 0; + if (th->doff > (sizeof(struct tcphdr)>>2)) { + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 93316a96d820..383ce237640f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -553,7 +553,6 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; - struct dst_entry *dst = __sk_dst_get(sk); unsigned remaining = MAX_TCP_OPTION_SPACE; u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : @@ -581,22 +580,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && - !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) && - *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) { + if (likely(sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack && - !dst_feature(dst, RTAX_FEATURE_NO_SACK))) { + if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -2527,9 +2522,7 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps && - (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ? - TCPOLEN_TSTAMP_ALIGNED : 0)); + (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk) != NULL) @@ -2555,8 +2548,7 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - (sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)), + sysctl_tcp_window_scaling, &rcv_wscale); tp->rx_opt.rcv_wscale = rcv_wscale; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1f9534846ca9..f0126fdd7e04 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -216,9 +216,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, * force rand to be an odd multiple of UDP_HTABLE_SIZE */ rand = (rand | 1) * (udptable->mask + 1); - for (last = first + udptable->mask + 1; - first != last; - first++) { + last = first + udptable->mask + 1; + do { hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); @@ -238,7 +237,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, snum += rand; } while (snum != first); spin_unlock_bh(&hslot->lock); - } + } while (++first != last); goto fail; } else { hslot = udp_hashslot(udptable, net, snum); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 5f2ec208a8c3..0956ebabbff2 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -20,6 +20,7 @@ #include <net/ipv6.h> #include <net/inet_frag.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> @@ -187,6 +188,21 @@ out: return nf_conntrack_confirm(skb); } +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN; + else + return IP6_DEFRAG_CONNTRACK_OUT; + +} + static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, @@ -199,8 +215,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (skb->nfct) return NF_ACCEPT; - reasm = nf_ct_frag6_gather(skb); - + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e0b9424fa1b2..312c20adc83f 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -168,13 +168,14 @@ out: /* Creation primitives. */ static __inline__ struct nf_ct_frag6_queue * -fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; unsigned int hash; arg.id = id; + arg.user = user; arg.src = src; arg.dst = dst; @@ -559,7 +560,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) +struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; @@ -605,7 +606,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh) nf_ct_frag6_evictor(); - fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr); + fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4d98549a6868..3b3a95607125 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -72,6 +72,7 @@ struct frag_queue struct inet_frag_queue q; __be32 id; /* fragment id */ + u32 user; struct in6_addr saddr; struct in6_addr daddr; @@ -141,7 +142,7 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); - return (fq->id == arg->id && + return (fq->id == arg->id && fq->user == arg->user && ipv6_addr_equal(&fq->saddr, arg->src) && ipv6_addr_equal(&fq->daddr, arg->dst)); } @@ -163,6 +164,7 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq->id = arg->id; + fq->user = arg->user; ipv6_addr_copy(&fq->saddr, arg->src); ipv6_addr_copy(&fq->daddr, arg->dst); } @@ -243,6 +245,7 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst, unsigned int hash; arg.id = id; + arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5b9af508b8f2..7208a06576c6 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -185,6 +185,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + ret = NULL; req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (!req) @@ -218,6 +225,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->expires = 0UL; req->retrans = 0; ireq->ecn_ok = 0; + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; @@ -253,21 +266,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ee9cf62458d4..febfd595a40d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1169,7 +1169,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); __u32 isn = TCP_SKB_CB(skb)->when; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; @@ -1208,7 +1207,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b95699f00545..847ffca40184 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1366,6 +1366,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, == sysctl_ip_vs_sync_threshold[0])) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || + (cp->state == IP_VS_TCP_S_CLOSE) || (cp->state == IP_VS_TCP_S_CLOSE_WAIT) || (cp->state == IP_VS_TCP_S_TIME_WAIT))))) ip_vs_sync_conn(cp); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e55a6861d26f..6bde12da2fe0 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2714,6 +2714,8 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr)))) return -EINVAL; + memset(usvc, 0, sizeof(*usvc)); + usvc->af = nla_get_u16(nla_af); #ifdef CONFIG_IP_VS_IPV6 if (usvc->af != AF_INET && usvc->af != AF_INET6) @@ -2901,6 +2903,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, if (!(nla_addr && nla_port)) return -EINVAL; + memset(udest, 0, sizeof(*udest)); + nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr)); udest->port = nla_get_u16(nla_port); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 020562164b56..e0516a22be2e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -415,7 +415,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct net_device *dev; __be16 proto = 0; int err; @@ -437,6 +437,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, */ saddr->spkt_device[13] = 0; +retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; @@ -456,58 +457,48 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, if (len > dev->mtu + dev->hard_header_len) goto out_unlock; - err = -ENOBUFS; - skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL); - - /* - * If the write buffer is full, then tough. At this level the user - * gets to deal with the problem - do your own algorithmic backoffs. - * That's far more flexible. - */ - - if (skb == NULL) - goto out_unlock; - - /* - * Fill it in - */ - - /* FIXME: Save some space for broken drivers that write a - * hard header at transmission time by themselves. PPP is the - * notable one here. This should really be fixed at the driver level. - */ - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - skb_reset_network_header(skb); - - /* Try to align data part correctly */ - if (dev->header_ops) { - skb->data -= dev->hard_header_len; - skb->tail -= dev->hard_header_len; - if (len < dev->hard_header_len) - skb_reset_network_header(skb); + if (!skb) { + size_t reserved = LL_RESERVED_SPACE(dev); + unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + + rcu_read_unlock(); + skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL); + if (skb == NULL) + return -ENOBUFS; + /* FIXME: Save some space for broken drivers that write a hard + * header at transmission time by themselves. PPP is the notable + * one here. This should really be fixed at the driver level. + */ + skb_reserve(skb, reserved); + skb_reset_network_header(skb); + + /* Try to align data part correctly */ + if (hhlen) { + skb->data -= hhlen; + skb->tail -= hhlen; + if (len < hhlen) + skb_reset_network_header(skb); + } + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + if (err) + goto out_free; + goto retry; } - /* Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - if (err) - goto out_free; - - /* - * Now send it - */ dev_queue_xmit(skb); rcu_read_unlock(); return len; -out_free: - kfree_skb(skb); out_unlock: rcu_read_unlock(); +out_free: + kfree_skb(skb); return err; } diff --git a/net/rds/ib.c b/net/rds/ib.c index 536ebe5d3f6b..3b8992361042 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -182,8 +182,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, ic = conn->c_transport_data; dev_addr = &ic->i_cm_id->route.addr.dev_addr; - ib_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); - ib_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); + rdma_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); + rdma_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); rds_ibdev = ib_get_client_data(ic->i_cm_id->device, &rds_ib_client); iinfo->max_send_wr = ic->i_send_ring.w_nr; diff --git a/net/rds/iw.c b/net/rds/iw.c index db224f7c2937..b28fa8525b24 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -184,8 +184,8 @@ static int rds_iw_conn_info_visitor(struct rds_connection *conn, ic = conn->c_transport_data; dev_addr = &ic->i_cm_id->route.addr.dev_addr; - ib_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); - ib_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); + rdma_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); + rdma_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); rds_iwdev = ib_get_client_data(ic->i_cm_id->device, &rds_iw_client); iinfo->max_send_wr = ic->i_send_ring.w_nr; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index cef74ba0666c..aae6907fd546 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -210,6 +210,7 @@ void rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qnam { __rpc_init_priority_wait_queue(queue, qname, RPC_NR_PRIORITY); } +EXPORT_SYMBOL_GPL(rpc_init_priority_wait_queue); void rpc_init_wait_queue(struct rpc_wait_queue *queue, const char *qname) { @@ -385,6 +386,20 @@ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct r } /* + * Tests whether rpc queue is empty + */ +int rpc_queue_empty(struct rpc_wait_queue *queue) +{ + int res; + + spin_lock_bh(&queue->lock); + res = queue->qlen; + spin_unlock_bh(&queue->lock); + return (res == 0); +} +EXPORT_SYMBOL_GPL(rpc_queue_empty); + +/* * Wake up a task on a specific queue */ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b845e2293dfe..1c924ee0a1ef 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -16,8 +16,6 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT -#define SVC_MAX_WAKING 5 - static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -306,7 +304,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; - int thread_avail; if (!(xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED)))) @@ -318,6 +315,12 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_threads) && + !list_empty(&pool->sp_sockets)) + printk(KERN_ERR + "svc_xprt_enqueue: " + "threads and transports both waiting??\n"); + if (test_bit(XPT_DEAD, &xprt->xpt_flags)) { /* Don't enqueue dead transports */ dprintk("svc: transport %p is dead, not enqueued\n", xprt); @@ -358,15 +361,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) } process: - /* Work out whether threads are available */ - thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */ - if (pool->sp_nwaking >= SVC_MAX_WAKING) { - /* too many threads are runnable and trying to wake up */ - thread_avail = 0; - pool->sp_stats.overloads_avoided++; - } - - if (thread_avail) { + if (!list_empty(&pool->sp_threads)) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); @@ -381,8 +376,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) svc_xprt_get(xprt); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); - rqstp->rq_waking = 1; - pool->sp_nwaking++; pool->sp_stats.threads_woken++; BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); @@ -651,11 +644,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) return -EINTR; spin_lock_bh(&pool->sp_lock); - if (rqstp->rq_waking) { - rqstp->rq_waking = 0; - pool->sp_nwaking--; - BUG_ON(pool->sp_nwaking < 0); - } xprt = svc_xprt_dequeue(pool); if (xprt) { rqstp->rq_xprt = xprt; @@ -1204,16 +1192,15 @@ static int svc_pool_stats_show(struct seq_file *m, void *p) struct svc_pool *pool = p; if (p == SEQ_START_TOKEN) { - seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n"); + seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n"); return 0; } - seq_printf(m, "%u %lu %lu %lu %lu %lu\n", + seq_printf(m, "%u %lu %lu %lu %lu\n", pool->sp_id, pool->sp_stats.packets, pool->sp_stats.sockets_queued, pool->sp_stats.threads_woken, - pool->sp_stats.overloads_avoided, pool->sp_stats.threads_timedout); return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 4a8f6558718a..d8c041114497 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -655,23 +655,25 @@ static struct unix_gid *unix_gid_lookup(uid_t uid) return NULL; } -static int unix_gid_find(uid_t uid, struct group_info **gip, - struct svc_rqst *rqstp) +static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp) { - struct unix_gid *ug = unix_gid_lookup(uid); + struct unix_gid *ug; + struct group_info *gi; + int ret; + + ug = unix_gid_lookup(uid); if (!ug) - return -EAGAIN; - switch (cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle)) { + return ERR_PTR(-EAGAIN); + ret = cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle); + switch (ret) { case -ENOENT: - *gip = NULL; - return 0; + return ERR_PTR(-ENOENT); case 0: - *gip = ug->gi; - get_group_info(*gip); + gi = get_group_info(ug->gi); cache_put(&ug->h, &unix_gid_cache); - return 0; + return gi; default: - return -EAGAIN; + return ERR_PTR(-EAGAIN); } } @@ -681,6 +683,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) struct sockaddr_in *sin; struct sockaddr_in6 *sin6, sin6_storage; struct ip_map *ipm; + struct group_info *gi; + struct svc_cred *cred = &rqstp->rq_cred; switch (rqstp->rq_addr.ss_family) { case AF_INET: @@ -721,6 +725,17 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) ip_map_cached_put(rqstp, ipm); break; } + + gi = unix_gid_find(cred->cr_uid, rqstp); + switch (PTR_ERR(gi)) { + case -EAGAIN: + return SVC_DROP; + case -ENOENT: + break; + default: + put_group_info(cred->cr_group_info); + cred->cr_group_info = gi; + } return SVC_OK; } @@ -817,19 +832,11 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) slen = svc_getnl(argv); /* gids length */ if (slen > 16 || (len -= (slen + 2)*4) < 0) goto badcred; - if (unix_gid_find(cred->cr_uid, &cred->cr_group_info, rqstp) - == -EAGAIN) + cred->cr_group_info = groups_alloc(slen); + if (cred->cr_group_info == NULL) return SVC_DROP; - if (cred->cr_group_info == NULL) { - cred->cr_group_info = groups_alloc(slen); - if (cred->cr_group_info == NULL) - return SVC_DROP; - for (i = 0; i < slen; i++) - GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); - } else { - for (i = 0; i < slen ; i++) - svc_getnl(argv); - } + for (i = 0; i < slen; i++) + GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; |