From 59e7e7078d6c2c6294caf454c6e3695f9d3e46a2 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 2 Jun 2011 17:28:37 -0300 Subject: mac80211: call dev_alloc_name before copying name to sdata This partially reverts 1c5cae815d19ffe02bdfda1260949ef2b1806171, because the netdev name is copied into sdata->name, which is used for debugging messages, for example. Otherwise, we get messages like this: wlan%d: authenticated Signed-off-by: Thadeu Lima de Souza Cascardo Cc: Jiri Pirko Cc: David S. Miller Cc: Johannes Berg Cc: "John W. Linville" Signed-off-by: John W. Linville --- net/mac80211/iface.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 49d4f869e0bc..dee30aea9ab3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1145,6 +1145,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, + IEEE80211_ENCRYPT_HEADROOM; ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM; + ret = dev_alloc_name(ndev, ndev->name); + if (ret < 0) + goto fail; + ieee80211_assign_perm_addr(local, ndev, type); memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); -- cgit v1.2.3 From c316e6a3084cef1a5857cd66bb5429c969f06c93 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 Jun 2011 00:37:35 +0000 Subject: get_net_ns_by_fd() oopses if proc_ns_fget() returns an error BTW, looking through the code related to struct net lifetime rules has caught something else: struct net *get_net_ns_by_fd(int fd) { ... file = proc_ns_fget(fd); if (!file) goto out; ei = PROC_I(file->f_dentry->d_inode); while in proc_ns_fget() we have two return ERR_PTR(...) and not a single path that would return NULL. The other caller of proc_ns_fget() treats ERR_PTR() correctly... Signed-off-by: Al Viro Signed-off-by: David S. Miller --- net/core/net_namespace.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6c6b86d0da15..e41e5110c65c 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -310,19 +310,17 @@ struct net *get_net_ns_by_fd(int fd) struct file *file; struct net *net; - net = ERR_PTR(-EINVAL); file = proc_ns_fget(fd); - if (!file) - goto out; + if (IS_ERR(file)) + return ERR_CAST(file); ei = PROC_I(file->f_dentry->d_inode); - if (ei->ns_ops != &netns_operations) - goto out; + if (ei->ns_ops == &netns_operations) + net = get_net(ei->ns); + else + net = ERR_PTR(-EINVAL); - net = get_net(ei->ns); -out: - if (file) - fput(file); + fput(file); return net; } -- cgit v1.2.3 From b8f07a063163f8216cd891c5b007e839a56b6d93 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 Jun 2011 00:54:03 +0000 Subject: fix return values of l2tp_dfs_seq_open() More fallout from struct net lifetime rules review: PTR_ERR() is *already* negative and failing ->open() should return negatives on failure. Signed-off-by: Al Viro Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b8dbae82fab8..76130134bfa6 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -258,7 +258,7 @@ static int l2tp_dfs_seq_open(struct inode *inode, struct file *file) */ pd->net = get_net_ns_by_pid(current->pid); if (IS_ERR(pd->net)) { - rc = -PTR_ERR(pd->net); + rc = PTR_ERR(pd->net); goto err_free_pd; } -- cgit v1.2.3 From fb04883371f2cb7867d24783e7d590036dc9b548 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 May 2011 15:44:27 +0200 Subject: netfilter: add more values to enum ip_conntrack_info Following error is raised (and other similar ones) : net/ipv4/netfilter/nf_nat_standalone.c: In function ‘nf_nat_fn’: net/ipv4/netfilter/nf_nat_standalone.c:119:2: warning: case value ‘4’ not in enumerated type ‘enum ip_conntrack_info’ gcc barfs on adding two enum values and getting a not enumerated result : case IP_CT_RELATED+IP_CT_IS_REPLY: Add missing enum values Signed-off-by: Eric Dumazet CC: David Miller Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 3 +++ net/ipv4/netfilter/ipt_CLUSTERIP.c | 6 +++--- net/ipv4/netfilter/ipt_MASQUERADE.c | 2 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 2 +- net/ipv4/netfilter/nf_nat_core.c | 2 +- net/ipv4/netfilter/nf_nat_rule.c | 2 +- net/ipv4/netfilter/nf_nat_standalone.c | 4 ++-- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 2 +- net/netfilter/nf_conntrack_core.c | 4 ++-- net/netfilter/nf_conntrack_ftp.c | 2 +- net/netfilter/nf_conntrack_h323_main.c | 10 ++++------ net/netfilter/nf_conntrack_irc.c | 3 +-- net/netfilter/nf_conntrack_pptp.c | 3 +-- net/netfilter/nf_conntrack_sane.c | 2 +- net/netfilter/nf_conntrack_sip.c | 2 +- net/netfilter/xt_socket.c | 4 ++-- 16 files changed, 26 insertions(+), 27 deletions(-) (limited to 'net') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 50cdc2559a5a..0d3dd66322ec 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -18,6 +18,9 @@ enum ip_conntrack_info { /* >= this indicates reply direction */ IP_CT_IS_REPLY, + IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY, + IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY, + IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY, /* Number of distinct IP_CT types (no NEW in reply dirn). */ IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1 }; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index d609ac3cb9a4..5c9e97c79017 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -307,7 +307,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) * error messages (RELATED) and information requests (see below) */ if (ip_hdr(skb)->protocol == IPPROTO_ICMP && (ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)) + ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, @@ -321,12 +321,12 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) ct->mark = hash; break; case IP_CT_RELATED: - case IP_CT_RELATED+IP_CT_IS_REPLY: + case IP_CT_RELATED_REPLY: /* FIXME: we don't handle expectations at the * moment. they can arrive on a different node than * the master connection (e.g. FTP passive mode) */ case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED+IP_CT_IS_REPLY: + case IP_CT_ESTABLISHED_REPLY: break; default: break; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index d2ed9dc74ebc..9931152a78b5 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -60,7 +60,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) nat = nfct_nat(ct); NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + ctinfo == IP_CT_RELATED_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 5a03c02af999..db10075dd88e 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -101,7 +101,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY) + if (!ct || ctinfo == IP_CT_RELATED_REPLY) goto out; help = nfct_help(ct); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 9c71b2755ce3..3346de5d94d0 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -433,7 +433,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, /* Must be RELATED */ NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED || - skb->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY); + skb->nfctinfo == IP_CT_RELATED_REPLY); /* Redirects on non-null nats must be dropped, else they'll start talking to each other without our translation, and be diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 21c30426480b..733c9abc1cbd 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -53,7 +53,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) /* Connection must be valid and new. */ NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + ctinfo == IP_CT_RELATED_REPLY)); NF_CT_ASSERT(par->out != NULL); return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC); diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 7317bdf1d457..483b76d042da 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -116,7 +116,7 @@ nf_nat_fn(unsigned int hooknum, switch (ctinfo) { case IP_CT_RELATED: - case IP_CT_RELATED+IP_CT_IS_REPLY: + case IP_CT_RELATED_REPLY: if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(ct, ctinfo, hooknum, skb)) @@ -144,7 +144,7 @@ nf_nat_fn(unsigned int hooknum, default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY)); + ctinfo == IP_CT_ESTABLISHED_REPLY); } return nf_nat_packet(ct, ctinfo, hooknum, skb); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c8af58b22562..4111050a9fc5 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -160,7 +160,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY) + if (!ct || ctinfo == IP_CT_RELATED_REPLY) goto out; help = nfct_help(ct); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2e1c11f78419..0bd568929403 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -850,7 +850,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, /* It exists; we have (non-exclusive) reference. */ if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { - *ctinfo = IP_CT_ESTABLISHED + IP_CT_IS_REPLY; + *ctinfo = IP_CT_ESTABLISHED_REPLY; /* Please set reply bit if this packet OK */ *set_reply = 1; } else { @@ -1143,7 +1143,7 @@ static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) /* This ICMP is in reverse direction to the packet which caused it */ ct = nf_ct_get(skb, &ctinfo); if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) - ctinfo = IP_CT_RELATED + IP_CT_IS_REPLY; + ctinfo = IP_CT_RELATED_REPLY; else ctinfo = IP_CT_RELATED; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index e17cb7c7dd8f..6f5801eac999 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -368,7 +368,7 @@ static int help(struct sk_buff *skb, /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + ctinfo != IP_CT_ESTABLISHED_REPLY) { pr_debug("ftp: Conntrackinfo = %u\n", ctinfo); return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 18b2ce5c8ced..f03c2d4539f6 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -571,10 +571,9 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, int ret; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; - } + pr_debug("nf_ct_h245: skblen = %u\n", skb->len); spin_lock_bh(&nf_h323_lock); @@ -1125,10 +1124,9 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, int ret; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; - } + pr_debug("nf_ct_q931: skblen = %u\n", skb->len); spin_lock_bh(&nf_h323_lock); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index b394aa318776..4f9390b98697 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -125,8 +125,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, return NF_ACCEPT; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* Not a full tcp header? */ diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 088944824e13..2fd4565144de 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -519,8 +519,7 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, u_int16_t msg; /* don't do any tracking before tcp handshake complete */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; nexthdr_off = protoff; diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index d9e27734b2a2..8501823b3f9b 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -78,7 +78,7 @@ static int help(struct sk_buff *skb, ct_sane_info = &nfct_help(ct)->help.ct_sane_info; /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY) + ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* Not a full tcp header? */ diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index cb5a28581782..93faf6a3a637 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1423,7 +1423,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* No Data ? */ diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 9cc46356b577..fe39f7e913df 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -143,9 +143,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && - ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) || + ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && - ctinfo == IP_CT_IS_REPLY + IP_CT_RELATED)) && + ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; -- cgit v1.2.3 From afb523c54718da57ff661950bd3287ec9eeb66bd Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 2 Jun 2011 09:09:54 +0900 Subject: ipvs: restore support for iptables SNAT Fix the IPVS priority in LOCAL_IN hook, so that SNAT target in POSTROUTING is supported for IPVS traffic as in 2.6.36 where it worked depending on module load order. Before 2.6.37 we used priority 100 in LOCAL_IN to process remote requests. We used the same priority as iptables SNAT and if IPVS handlers are installed before SNAT handlers we supported SNAT in POSTROUTING for the IPVS traffic. If SNAT is installed before IPVS, the netfilter handlers are before IPVS and netfilter checks the NAT table twice for the IPVS requests: once in LOCAL_IN where IPS_SRC_NAT_DONE is set and second time in POSTROUTING where the SNAT rules are ignored because IPS_SRC_NAT_DONE was already set in LOCAL_IN. But in 2.6.37 we changed the IPVS priority for LOCAL_IN with the goal to be unique (101) forgetting the fact that for IPVS traffic we should not walk both LOCAL_IN and POSTROUTING nat tables. So, change the priority for processing remote IPVS requests from 101 to 99, i.e. before NAT_SRC (100) because we prefer to support SNAT in POSTROUTING instead of LOCAL_IN. It also moves the priority for IPVS replies from 99 to 98. Use constants instead of magic numbers at these places. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_core.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index bfa808f4da13..55af2242bccd 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1772,7 +1772,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_IN, - .priority = 99, + .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1782,7 +1782,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_IN, - .priority = 101, + .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1790,7 +1790,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -99, + .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { @@ -1798,7 +1798,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -98, + .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ @@ -1824,7 +1824,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, - .priority = 99, + .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1834,7 +1834,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, - .priority = 101, + .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1842,7 +1842,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -99, + .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { @@ -1850,7 +1850,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_OUT, - .priority = -98, + .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ -- cgit v1.2.3 From fcbf12817100d23890832801507107718a1fa448 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 1 Jun 2011 23:35:48 +0200 Subject: netfilter: ipset: Fix return code for destroy when sets are in use Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8041befc6555..42aa64b6b0b1 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -767,7 +767,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { - ret = IPSET_ERR_BUSY; + ret = -IPSET_ERR_BUSY; goto out; } } -- cgit v1.2.3 From b48e3c5c323fea08c12a340cbb8dcc8ca2431d5b Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Wed, 1 Jun 2011 23:35:49 +0200 Subject: netfilter: ipset: Use the stored first cidr value instead of '1' The stored cidr values are tried one after anoter. The boolean condition evaluated to '1' instead of the first stored cidr or the default host cidr. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_ipportnet.c | 10 ++++++---- net/netfilter/ipset/ip_set_hash_net.c | 8 ++++++-- net/netfilter/ipset/ip_set_hash_netport.c | 6 ++++-- 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 4743e5402522..565a7c5b8818 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -146,8 +146,9 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet4_elem data = - { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_ipportnet4_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; @@ -394,8 +395,9 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet6_elem data = - { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_ipportnet6_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c4db202b7da4..2aeeabcd5a21 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -131,7 +131,9 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_net4_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_net4_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; @@ -296,7 +298,9 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_net6_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_net6_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index d2a40362dd3a..e50d9bb8820b 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -144,7 +144,8 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem data = { - .cidr = h->nets[0].cidr || HOST_MASK }; + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; @@ -357,7 +358,8 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem data = { - .cidr = h->nets[0].cidr || HOST_MASK }; + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; -- cgit v1.2.3 From d9be76f38526dccf84062e3ac3ed3a6a97698565 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 29 May 2011 23:42:29 +0300 Subject: netfilter: nf_nat: fix crash in nf_nat_csum Fix crash in nf_nat_csum when mangling packets in OUTPUT hook where skb->dev is not defined, it is set later before POSTROUTING. Problem happens for CHECKSUM_NONE. We can check device from rt but using CHECKSUM_PARTIAL should be safe (skb_checksum_help). Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_nat_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 99cfa28b6d38..ebc5f8894f99 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -160,7 +160,7 @@ static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { + (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + -- cgit v1.2.3 From 88ed01d17b44bc2bed4ad4835d3b1099bff3dd71 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 2 Jun 2011 15:08:45 +0200 Subject: netfilter: nf_conntrack: fix ct refcount leak in l4proto->error() This patch fixes a refcount leak of ct objects that may occur if l4proto->error() assigns one conntrack object to one skbuff. In that case, we have to skip further processing in nf_conntrack_in(). With this patch, we can also fix wrong return values (-NF_ACCEPT) for special cases in ICMP[v6] that should not bump the invalid/error statistic counters. Reported-by: Zoltan Menyhart Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 2 +- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 2 +- net/netfilter/nf_conntrack_core.c | 3 +++ 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 7404bde95994..ab5b27a2916f 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -160,7 +160,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; - return -NF_ACCEPT; + return NF_ACCEPT; } /* Small and modified version of icmp_rcv */ diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 1df3c8b6bf47..7c05e7eacbc6 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -177,7 +177,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; - return -NF_ACCEPT; + return NF_ACCEPT; } static int diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0bd568929403..f7af8b866017 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -922,6 +922,9 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, ret = -ret; goto out; } + /* ICMP[v6] protocol trackers may assign one conntrack. */ + if (skb->nfct) + goto out; } ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, -- cgit v1.2.3 From d232b8dded624af3e346b13807a591c63b601c44 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 27 May 2011 20:36:51 -0400 Subject: netfilter: use unsigned variables for packet lengths in ip[6]_queue. Netlink message lengths can't be negative, so use unsigned variables. Signed-off-by: Dave Jones Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/ip_queue.c | 3 ++- net/ipv6/netfilter/ip6_queue.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index d2c1311cb28d..f7f9bd7ba12d 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -402,7 +402,8 @@ ipq_dev_drop(int ifindex) static inline void __ipq_rcv_skb(struct sk_buff *skb) { - int status, type, pid, flags, nlmsglen, skblen; + int status, type, pid, flags; + unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; skblen = skb->len; diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 413ab0754e1f..065fe405fb58 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -403,7 +403,8 @@ ipq_dev_drop(int ifindex) static inline void __ipq_rcv_skb(struct sk_buff *skb) { - int status, type, pid, flags, nlmsglen, skblen; + int status, type, pid, flags; + unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; skblen = skb->len; -- cgit v1.2.3 From ab6a44ce1da48d35fe7ec95fa068aa617bd7e8dd Mon Sep 17 00:00:00 2001 From: John W. Linville Date: Mon, 6 Jun 2011 14:35:27 -0400 Subject: Revert "mac80211: Skip tailroom reservation for full HW-crypto devices" This reverts commit aac6af5534fade2b18682a0b9efad1a6c04c34c6. Conflicts: net/mac80211/key.c That commit has a race that causes a warning, as documented in the thread here: http://marc.info/?l=linux-wireless&m=130717684914101&w=2 Signed-off-by: John W. Linville --- net/mac80211/ieee80211_i.h | 3 --- net/mac80211/key.c | 21 ++------------------- net/mac80211/tx.c | 7 ++++++- 3 files changed, 8 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 2025af52b195..090b0ec1e056 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -775,9 +775,6 @@ struct ieee80211_local { int tx_headroom; /* required headroom for hardware/radiotap */ - /* count for keys needing tailroom space allocation */ - int crypto_tx_tailroom_needed_cnt; - /* Tasklet and skb queue to process calls from IRQ mode. All frames * added to skb_queue will be processed, but frames in * skb_queue_unreliable may be dropped if the total length of these diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 31afd712930d..f825e2f0a57e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -101,11 +101,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!ret) { key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; - - if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || - (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))) - key->local->crypto_tx_tailroom_needed_cnt--; - return 0; } @@ -161,10 +156,6 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) key->conf.keyidx, sta ? sta->addr : bcast_addr, ret); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; - - if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || - (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))) - key->local->crypto_tx_tailroom_needed_cnt++; } void ieee80211_key_removed(struct ieee80211_key_conf *key_conf) @@ -403,10 +394,8 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key) ieee80211_aes_key_free(key->u.ccmp.tfm); if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC) ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); - if (key->local) { + if (key->local) ieee80211_debugfs_key_remove(key); - key->local->crypto_tx_tailroom_needed_cnt--; - } kfree(key); } @@ -468,8 +457,6 @@ int ieee80211_key_link(struct ieee80211_key *key, ieee80211_debugfs_key_add(key); - key->local->crypto_tx_tailroom_needed_cnt++; - ret = ieee80211_key_enable_hw_accel(key); mutex_unlock(&sdata->local->key_mtx); @@ -511,12 +498,8 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->local->crypto_tx_tailroom_needed_cnt = 0; - - list_for_each_entry(key, &sdata->key_list, list) { - sdata->local->crypto_tx_tailroom_needed_cnt++; + list_for_each_entry(key, &sdata->key_list, list) ieee80211_key_enable_hw_accel(key); - } mutex_unlock(&sdata->local->key_mtx); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 64e0f7587e6d..3104c844b544 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1480,7 +1480,12 @@ static int ieee80211_skb_resize(struct ieee80211_local *local, { int tail_need = 0; - if (may_encrypt && local->crypto_tx_tailroom_needed_cnt) { + /* + * This could be optimised, devices that do full hardware + * crypto (including TKIP MMIC) need no tailroom... But we + * have no drivers for such devices currently. + */ + if (may_encrypt) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); -- cgit v1.2.3 From 5a079c305ad4dda9708b7a29db4a8bd38e21c3a6 Mon Sep 17 00:00:00 2001 From: Marcus Meissner Date: Mon, 6 Jun 2011 06:00:07 +0000 Subject: net/ipv6: check for mistakenly passed in non-AF_INET6 sockaddrs Same check as for IPv4, also do for IPv6. (If you passed in a IPv4 sockaddr_in here, the sizeof check in the line before would have triggered already though.) Signed-off-by: Marcus Meissner Cc: Reinhard Max Signed-off-by: David S. Miller --- net/ipv6/af_inet6.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b7919f901fbf..d450a2f9fc06 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -272,6 +272,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; + + if (addr->sin6_family != AF_INET6) + return -EINVAL; + addr_type = ipv6_addr_type(&addr->sin6_addr); if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM) return -EINVAL; -- cgit v1.2.3 From 3019de124b9f5b1526cb3668b74af14371e21795 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 6 Jun 2011 16:41:33 -0700 Subject: net: Rework netdev_drivername() to avoid warning. This interface uses a temporary buffer, but for no real reason. And now can generate warnings like: net/sched/sch_generic.c: In function dev_watchdog net/sched/sch_generic.c:254:10: warning: unused variable drivername Just return driver->name directly or "". Reported-by: Connor Hansen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 16 +++++----------- net/sched/sch_generic.c | 3 +-- 3 files changed, 7 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca333e79e10f..54b8b4d7b68f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2555,7 +2555,7 @@ extern void netdev_class_remove_file(struct class_attribute *class_attr); extern struct kobj_ns_type_operations net_ns_type_operations; -extern char *netdev_drivername(const struct net_device *dev, char *buffer, int len); +extern const char *netdev_drivername(const struct net_device *dev); extern void linkwatch_run_queue(void); diff --git a/net/core/dev.c b/net/core/dev.c index 939307891e71..1af6cb27f67a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6264,29 +6264,23 @@ err_name: /** * netdev_drivername - network driver for the device * @dev: network device - * @buffer: buffer for resulting name - * @len: size of buffer * * Determine network driver for device. */ -char *netdev_drivername(const struct net_device *dev, char *buffer, int len) +const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; - - if (len <= 0 || !buffer) - return buffer; - buffer[0] = 0; + const char *empty = ""; parent = dev->dev.parent; - if (!parent) - return buffer; + return empty; driver = parent->driver; if (driver && driver->name) - strlcpy(buffer, driver->name, len); - return buffer; + return driver->name; + return empty; } static int __netdev_printk(const char *level, const struct net_device *dev, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b1721d71c27c..b4c680900d7a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -251,9 +251,8 @@ static void dev_watchdog(unsigned long arg) } if (some_queue_timedout) { - char drivername[64]; WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", - dev->name, netdev_drivername(dev, drivername, 64), i); + dev->name, netdev_drivername(dev), i); dev->netdev_ops->ndo_tx_timeout(dev); } if (!mod_timer(&dev->watchdog_timer, -- cgit v1.2.3 From 79b3891587741dfac72cdfead1f2764b56a567b0 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 6 Jun 2011 17:00:35 -0700 Subject: irda: iriap: Use seperate lockdep class for irias_objects->hb_spinlock The SEQ output functions grab the obj->attrib->hb_spinlock lock of sub-objects found in the hash traversal. These locks are in a different realm than the one used for the irias_objects hash table itself. So put the latter into it's own lockdep class. Reported-by: Dave Jones Signed-off-by: David S. Miller --- net/irda/iriap.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 36477538cea8..f876eed7d4aa 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -87,6 +87,8 @@ static inline void iriap_start_watchdog_timer(struct iriap_cb *self, iriap_watchdog_timer_expired); } +static struct lock_class_key irias_objects_key; + /* * Function iriap_init (void) * @@ -114,6 +116,9 @@ int __init iriap_init(void) return -ENOMEM; } + lockdep_set_class_and_name(&irias_objects->hb_spinlock, &irias_objects_key, + "irias_objects"); + /* * Register some default services for IrLMP */ -- cgit v1.2.3 From 13fcb7bd322164c67926ffe272846d4860196dc6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jun 2011 22:42:06 -0700 Subject: af_packet: prevent information leak In 2.6.27, commit 393e52e33c6c2 (packet: deliver VLAN TCI to userspace) added a small information leak. Add padding field and make sure its zeroed before copy to user. Signed-off-by: Eric Dumazet CC: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_packet.h | 2 ++ net/packet/af_packet.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'net') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 6d66ce1791a9..7b318630139f 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -62,6 +62,7 @@ struct tpacket_auxdata { __u16 tp_mac; __u16 tp_net; __u16 tp_vlan_tci; + __u16 tp_padding; }; /* Rx ring - header status */ @@ -101,6 +102,7 @@ struct tpacket2_hdr { __u32 tp_sec; __u32 tp_nsec; __u16 tp_vlan_tci; + __u16 tp_padding; }; #define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll)) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba248d93399a..c0c3cda19712 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -804,6 +804,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } else { h.h2->tp_vlan_tci = 0; } + h.h2->tp_padding = 0; hdrlen = sizeof(*h.h2); break; default: @@ -1736,6 +1737,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, } else { aux.tp_vlan_tci = 0; } + aux.tp_padding = 0; put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } -- cgit v1.2.3 From 6407d74c5106bb362b4087693688afd34942b094 Mon Sep 17 00:00:00 2001 From: Alexander Holler Date: Tue, 7 Jun 2011 00:51:35 -0700 Subject: bridge: provide a cow_metrics method for fake_ops Like in commit 0972ddb237 (provide cow_metrics() methods to blackhole dst_ops), we must provide a cow_metrics for bridges fake_dst_ops as well. This fixes a regression coming from commits 62fa8a846d7d (net: Implement read-only protection and COW'ing of metrics.) and 33eb9873a28 (bridge: initialize fake_rtable metrics) ip link set mybridge mtu 1234 --> [ 136.546243] Pid: 8415, comm: ip Tainted: P 2.6.39.1-00006-g40545b7 #103 ASUSTeK Computer Inc. V1Sn /V1Sn [ 136.546256] EIP: 0060:[<00000000>] EFLAGS: 00010202 CPU: 0 [ 136.546268] EIP is at 0x0 [ 136.546273] EAX: f14a389c EBX: 000005d4 ECX: f80d32c0 EDX: f80d1da1 [ 136.546279] ESI: f14a3000 EDI: f255bf10 EBP: f15c3b54 ESP: f15c3b48 [ 136.546285] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 136.546293] Process ip (pid: 8415, ti=f15c2000 task=f4741f80 task.ti=f15c2000) [ 136.546297] Stack: [ 136.546301] f80c658f f14a3000 ffffffed f15c3b64 c12cb9c8 f80d1b80 ffffffa1 f15c3bbc [ 136.546315] c12da347 c12d9c7d 00000000 f7670b00 00000000 f80d1b80 ffffffa6 f15c3be4 [ 136.546329] 00000004 f14a3000 f255bf20 00000008 f15c3bbc c11d6cae 00000000 00000000 [ 136.546343] Call Trace: [ 136.546359] [] ? br_change_mtu+0x5f/0x80 [bridge] [ 136.546372] [] dev_set_mtu+0x38/0x80 [ 136.546381] [] do_setlink+0x1a7/0x860 [ 136.546390] [] ? rtnl_fill_ifinfo+0x9bd/0xc70 [ 136.546400] [] ? nla_parse+0x6e/0xb0 [ 136.546409] [] rtnl_newlink+0x361/0x510 [ 136.546420] [] ? vmalloc_sync_all+0x100/0x100 [ 136.546429] [] ? error_code+0x5a/0x60 [ 136.546438] [] ? rtnl_configure_link+0x80/0x80 [ 136.546446] [] rtnetlink_rcv_msg+0xfa/0x210 [ 136.546454] [] ? __rtnl_unlock+0x20/0x20 [ 136.546463] [] netlink_rcv_skb+0x8e/0xb0 [ 136.546471] [] rtnetlink_rcv+0x1c/0x30 [ 136.546479] [] netlink_unicast+0x23a/0x280 [ 136.546487] [] netlink_sendmsg+0x26b/0x2f0 [ 136.546497] [] sock_sendmsg+0xc8/0x100 [ 136.546508] [] ? __alloc_pages_nodemask+0xe1/0x750 [ 136.546517] [] ? _copy_from_user+0x42/0x60 [ 136.546525] [] ? verify_iovec+0x4c/0xc0 [ 136.546534] [] sys_sendmsg+0x1c5/0x200 [ 136.546542] [] ? __do_fault+0x310/0x410 [ 136.546549] [] ? do_wp_page+0x1d6/0x6b0 [ 136.546557] [] ? handle_pte_fault+0xe1/0x720 [ 136.546565] [] ? sys_getsockname+0x7f/0x90 [ 136.546574] [] ? handle_mm_fault+0xb1/0x180 [ 136.546582] [] ? vmalloc_sync_all+0x100/0x100 [ 136.546589] [] ? do_page_fault+0x173/0x3d0 [ 136.546596] [] ? sys_recvmsg+0x3b/0x60 [ 136.546605] [] sys_socketcall+0x293/0x2d0 [ 136.546614] [] sysenter_do_call+0x12/0x26 [ 136.546619] Code: Bad EIP value. [ 136.546627] EIP: [<00000000>] 0x0 SS:ESP 0068:f15c3b48 [ 136.546645] CR2: 0000000000000000 [ 136.546652] ---[ end trace 6909b560e78934fa ]--- Signed-off-by: Alexander Holler Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/bridge/br_netfilter.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 3fa123185e89..56149ec36d7f 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -104,10 +104,16 @@ static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + return NULL; +} + static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, + .cow_metrics = fake_cow_metrics, }; /* -- cgit v1.2.3 From 264524d5e5195f6e0f099bee20253a22b651e272 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 6 Jun 2011 20:50:03 +0000 Subject: net: cpu offline cause napi stall Frank Blaschka reported : During heavy network load we turn off/on cpus. Sometimes this causes a stall on the network device. Digging into the dump I found out following: napi is scheduled but does not run. From the I/O buffers and the napi state I see napi/rx_softirq processing has stopped because the budget was reached. napi stays in the softnet_data poll_list and the rx_softirq was raised again. I assume at this time the cpu offline comes in, the rx softirq is raised/moved to another cpu but napi stays in the poll_list of the softnet_data of the now offline cpu. Reviewing dev_cpu_callback (net/core/dev.c) I did not find the poll_list is transfered to the new cpu. This patch is a straightforward implementation of Frank suggestion : Transfert poll_list and trigger NET_RX_SOFTIRQ on new cpu. Reported-by: Frank Blaschka Signed-off-by: Heiko Carstens Signed-off-by: Eric Dumazet Tested-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 1af6cb27f67a..a54c9f87ddbb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6178,6 +6178,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); -- cgit v1.2.3 From bb77f6341728624314f488ebd8b4c69f2caa33ea Mon Sep 17 00:00:00 2001 From: John W. Linville Date: Tue, 7 Jun 2011 14:03:08 -0400 Subject: Revert "mac80211: stop queues before rate control updation" This reverts commit 1d38c16ce4156f63b45abbd09dd28ca2ef5172b4. The mac80211 maintainer raised complaints about abuse of the CSA stop reason, and about whether this patch actually serves its intended purpose at all. Signed-off-by: John W. Linville --- net/mac80211/mlme.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 456cccf26b51..d595265d6c22 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -232,9 +232,6 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); } - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CSA); - /* channel_type change automatically detected */ ieee80211_hw_config(local, 0); @@ -248,9 +245,6 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); } - ieee80211_wake_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CSA); - ht_opmode = le16_to_cpu(hti->operation_mode); /* if bss configuration changed store the new one */ -- cgit v1.2.3 From 57a27e1d6a3bb9ad4efeebd3a8c71156d6207536 Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Tue, 7 Jun 2011 20:42:26 +0300 Subject: nl80211: fix overflow in ssid_len When one of the SSID's length passed in a scan or sched_scan request is larger than 255, there will be an overflow in the u8 that is used to store the length before checking. This causes the check to fail and we overrun the buffer when copying the SSID. Fix this by checking the nl80211 attribute length before copying it to the struct. This is a follow up for the previous commit 208c72f4fe44fe09577e7975ba0e7fa0278f3d03, which didn't fix the problem entirely. Reported-by: Ido Yariv Signed-off-by: Luciano Coelho Signed-off-by: John W. Linville --- net/wireless/nl80211.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 88a565f130a5..98fa8eb6cc4b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3406,11 +3406,11 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) i = 0; if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { - request->ssids[i].ssid_len = nla_len(attr); - if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) { + if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; } + request->ssids[i].ssid_len = nla_len(attr); memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); i++; } @@ -3572,12 +3572,11 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { - request->ssids[i].ssid_len = nla_len(attr); - if (request->ssids[i].ssid_len > - IEEE80211_MAX_SSID_LEN) { + if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; } + request->ssids[i].ssid_len = nla_len(attr); memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); i++; -- cgit v1.2.3 From e756682c8baa47da1648c0c016e9f48ed66bc32d Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sun, 5 Jun 2011 20:46:03 +0000 Subject: xfrm: Fix off by one in the replay advance functions We may write 4 byte too much when we reinitialize the anti replay window in the replay advance functions. This patch fixes this by adjusting the last index of the initialization loop. Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- net/xfrm/xfrm_replay.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 47f1b8638df9..b11ea692bd7d 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -265,7 +265,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); } else { - nr = replay_esn->replay_window >> 5; + nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; @@ -471,7 +471,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); } else { - nr = replay_esn->replay_window >> 5; + nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; -- cgit v1.2.3 From f3209bea110cade12e2b133da8b8499689cb0e2e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 8 Jun 2011 13:27:29 +0200 Subject: mac80211: fix IBSS teardown race Ignacy reports that sometimes after leaving an IBSS joining a new one didn't work because there still were stations on the list. He fixed it by flushing stations when attempting to join a new IBSS, but this shouldn't be happening in the first case. When I looked into it I saw a race condition in teardown that could cause stations to be added after flush, and thus cause this situation. Ignacy confirms that after applying my patch he hasn't seen this happen again. Reported-by: Ignacy Gawedzki Debugged-by: Ignacy Gawedzki Tested-by: Ignacy Gawedzki Cc: stable@kernel.org Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/mac80211/ibss.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 421eaa6b0c2b..56c24cabf26d 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -965,6 +965,10 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->u.ibss.mtx); + sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; + memset(sdata->u.ibss.bssid, 0, ETH_ALEN); + sdata->u.ibss.ssid_len = 0; + active_ibss = ieee80211_sta_active_ibss(sdata); if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) { @@ -999,8 +1003,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) kfree_skb(skb); skb_queue_purge(&sdata->skb_queue); - memset(sdata->u.ibss.bssid, 0, ETH_ALEN); - sdata->u.ibss.ssid_len = 0; del_timer_sync(&sdata->u.ibss.timer); -- cgit v1.2.3 From fe6fe792faec3fc2d2db39b69651682b8c4e7fcb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2011 06:07:07 +0000 Subject: net: pmtu_expires fixes commit 2c8cec5c10bc (ipv4: Cache learned PMTU information in inetpeer) added some racy peer->pmtu_expires accesses. As its value can be changed by another cpu/thread, we should be more careful, reading its value once. Add peer_pmtu_expired() and peer_pmtu_cleaned() helpers Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 78 ++++++++++++++++++++++++++++++++------------------------ 1 file changed, 44 insertions(+), 34 deletions(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 52b0b956508b..045f0ec6a4a0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1316,6 +1316,23 @@ reject_redirect: ; } +static bool peer_pmtu_expired(struct inet_peer *peer) +{ + unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + + return orig && + time_after_eq(jiffies, orig) && + cmpxchg(&peer->pmtu_expires, orig, 0) == orig; +} + +static bool peer_pmtu_cleaned(struct inet_peer *peer) +{ + unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + + return orig && + cmpxchg(&peer->pmtu_expires, orig, 0) == orig; +} + static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; @@ -1331,14 +1348,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) rt_genid(dev_net(dst->dev))); rt_del(hash, rt); ret = NULL; - } else if (rt->peer && - rt->peer->pmtu_expires && - time_after_eq(jiffies, rt->peer->pmtu_expires)) { - unsigned long orig = rt->peer->pmtu_expires; - - if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) - dst_metric_set(dst, RTAX_MTU, - rt->peer->pmtu_orig); + } else if (rt->peer && peer_pmtu_expired(rt->peer)) { + dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig); } } return ret; @@ -1531,8 +1542,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) { - unsigned long expires = peer->pmtu_expires; + unsigned long expires = ACCESS_ONCE(peer->pmtu_expires); + if (!expires) + return; if (time_before(jiffies, expires)) { u32 orig_dst_mtu = dst_mtu(dst); if (peer->pmtu_learned < orig_dst_mtu) { @@ -1555,10 +1568,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; if (peer) { + unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires); + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; - if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { - unsigned long pmtu_expires; + if (!pmtu_expires || mtu < peer->pmtu_learned) { pmtu_expires = jiffies + ip_rt_mtu_expires; if (!pmtu_expires) @@ -1612,13 +1626,14 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) rt_bind_peer(rt, rt->rt_dst, 0); peer = rt->peer; - if (peer && peer->pmtu_expires) + if (peer) { check_peer_pmtu(dst, peer); - if (peer && peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) - return NULL; + if (peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + if (check_peer_redir(dst, peer)) + return NULL; + } } rt->rt_peer_genid = rt_peer_genid(); @@ -1649,14 +1664,8 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt && - rt->peer && - rt->peer->pmtu_expires) { - unsigned long orig = rt->peer->pmtu_expires; - - if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) - dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); - } + if (rt && rt->peer && peer_pmtu_cleaned(rt->peer)) + dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); } static int ip_rt_bug(struct sk_buff *skb) @@ -1770,8 +1779,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, sizeof(u32) * RTAX_MAX); dst_init_metrics(&rt->dst, peer->metrics, false); - if (peer->pmtu_expires) - check_peer_pmtu(&rt->dst, peer); + check_peer_pmtu(&rt->dst, peer); if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -2775,7 +2783,8 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires; + long expires = 0; + const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); @@ -2823,15 +2832,16 @@ static int rt_fill_info(struct net *net, NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark); error = rt->dst.error; - expires = (rt->peer && rt->peer->pmtu_expires) ? - rt->peer->pmtu_expires - jiffies : 0; - if (rt->peer) { + if (peer) { inet_peer_refcheck(rt->peer); - id = atomic_read(&rt->peer->ip_id_count) & 0xffff; - if (rt->peer->tcp_ts_stamp) { - ts = rt->peer->tcp_ts; - tsage = get_seconds() - rt->peer->tcp_ts_stamp; + id = atomic_read(&peer->ip_id_count) & 0xffff; + if (peer->tcp_ts_stamp) { + ts = peer->tcp_ts; + tsage = get_seconds() - peer->tcp_ts_stamp; } + expires = ACCESS_ONCE(peer->pmtu_expires); + if (expires) + expires -= jiffies; } if (rt_is_input_route(rt)) { -- cgit v1.2.3 From 0c1ad04aecb975f2a2014e1bc5a2fa23923ecbd9 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 9 Jun 2011 00:28:13 -0700 Subject: netpoll: prevent netpoll setup on slave devices In commit 8d8fc29d02a33e4bd5f4fa47823c1fd386346093 (netpoll: disable netpoll when enslave a device), we automatically disable netpoll when the underlying device is being enslaved, we also need to prevent people from setuping netpoll on devices that are already enslaved. Signed-off-by: WANG Cong Signed-off-by: David S. Miller --- net/core/netpoll.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2d7d6d473781..42ea4b0e59f1 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -792,6 +792,12 @@ int netpoll_setup(struct netpoll *np) return -ENODEV; } + if (ndev->master) { + printk(KERN_ERR "%s: %s is a slave device, aborting.\n", + np->name, np->dev_name); + return -EBUSY; + } + if (!netif_running(ndev)) { unsigned long atmost, atleast; -- cgit v1.2.3 From 96d7303e9cfb6a9bc664174a4dfdb6fa689284fe Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sun, 5 Jun 2011 20:48:47 +0000 Subject: ipv4: Fix packet size calculation for raw IPsec packets in __ip_append_data We assume that transhdrlen is positive on the first fragment which is wrong for raw packets. So we don't add exthdrlen to the packet size for raw packets. This leads to a reallocation on IPsec because we have not enough headroom on the skb to place the IPsec headers. This patch fixes this by adding exthdrlen to the packet size whenever the send queue of the socket is empty. This issue was introduced with git commit 1470ddf7 (inet: Remove explicit write references to sk/inet in ip_append_data) Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 98af3697c718..a8024eaa0e87 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -799,7 +799,9 @@ static int __ip_append_data(struct sock *sk, int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; - exthdrlen = transhdrlen ? rt->dst.header_len : 0; + skb = skb_peek_tail(queue); + + exthdrlen = !skb ? rt->dst.header_len : 0; length += exthdrlen; transhdrlen += exthdrlen; mtu = cork->fragsize; @@ -825,8 +827,6 @@ static int __ip_append_data(struct sock *sk, !exthdrlen) csummode = CHECKSUM_PARTIAL; - skb = skb_peek_tail(queue); - cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && -- cgit v1.2.3 From 0b5c9db1b11d3175bb42b80663a9f072f801edf5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 10 Jun 2011 06:56:58 +0000 Subject: vlan: Fix the ingress VLAN_FLAG_REORDER_HDR check Testing of VLAN_FLAG_REORDER_HDR does not belong in vlan_untag but rather in vlan_do_receive. Otherwise the vlan header will not be properly put on the packet in the case of vlan header accelleration. As we remove the check from vlan_check_reorder_header rename it vlan_reorder_header to keep the naming clean. Fix up the skb->pkt_type early so we don't look at the packet after adding the vlan tag, which guarantees we don't goof and look at the wrong field. Use a simple if statement instead of a complicated switch statement to decided that we need to increment rx_stats for a multicast packet. Hopefully at somepoint we will just declare the case where VLAN_FLAG_REORDER_HDR is cleared as unsupported and remove the code. Until then this keeps it working correctly. Signed-off-by: Eric W. Biederman Signed-off-by: Jiri Pirko Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 25 ++++++++++++++++++--- include/linux/skbuff.h | 5 +++++ net/8021q/vlan_core.c | 60 +++++++++++++++++++++++++++---------------------- net/core/dev.c | 2 +- 4 files changed, 61 insertions(+), 31 deletions(-) (limited to 'net') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index dc01681fbb42..affa27380b72 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -225,7 +225,7 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, } /** - * __vlan_put_tag - regular VLAN tag inserting + * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_tci: VLAN TCI to insert * @@ -234,8 +234,10 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. + * + * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) { struct vlan_ethhdr *veth; @@ -255,8 +257,25 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); - skb->protocol = htons(ETH_P_8021Q); + return skb; +} +/** + * __vlan_put_tag - regular VLAN tag inserting + * @skb: skbuff to tag + * @vlan_tci: VLAN TCI to insert + * + * Inserts the VLAN tag into @skb as part of the payload + * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * + * Following the skb_unshare() example, in case of error, the calling function + * doesn't have to worry about freeing the original skb. + */ +static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +{ + skb = vlan_insert_tag(skb, vlan_tci); + if (skb) + skb->protocol = htons(ETH_P_8021Q); return skb; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8b78ce14474..c0a4f3ab0cc0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1256,6 +1256,11 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +static inline void skb_reset_mac_len(struct sk_buff *skb) +{ + skb->mac_len = skb->network_header - skb->mac_header; +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 41495dc2a4c9..fcc684678af6 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -23,6 +23,31 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; + if (skb->pkt_type == PACKET_OTHERHOST) { + /* Our lower layer thinks this is not local, let's make sure. + * This allows the VLAN to have a different MAC than the + * underlying device, and still route correctly. */ + if (!compare_ether_addr(eth_hdr(skb)->h_dest, + vlan_dev->dev_addr)) + skb->pkt_type = PACKET_HOST; + } + + if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) { + unsigned int offset = skb->data - skb_mac_header(skb); + + /* + * vlan_insert_tag expect skb->data pointing to mac header. + * So change skb->data before calling it and change back to + * original position later + */ + skb_push(skb, offset); + skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci); + if (!skb) + return false; + skb_pull(skb, offset + VLAN_HLEN); + skb_reset_mac_len(skb); + } + skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci); skb->vlan_tci = 0; @@ -31,22 +56,8 @@ bool vlan_do_receive(struct sk_buff **skbp) u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; - - switch (skb->pkt_type) { - case PACKET_BROADCAST: - break; - case PACKET_MULTICAST: + if (skb->pkt_type == PACKET_MULTICAST) rx_stats->rx_multicast++; - break; - case PACKET_OTHERHOST: - /* Our lower layer thinks this is not local, let's make sure. - * This allows the VLAN to have a different MAC than the - * underlying device, and still route correctly. */ - if (!compare_ether_addr(eth_hdr(skb)->h_dest, - vlan_dev->dev_addr)) - skb->pkt_type = PACKET_HOST; - break; - } u64_stats_update_end(&rx_stats->syncp); return true; @@ -89,18 +100,13 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, } EXPORT_SYMBOL(vlan_gro_frags); -static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) +static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) { - if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) { - if (skb_cow(skb, skb_headroom(skb)) < 0) - skb = NULL; - if (skb) { - /* Lifted from Gleb's VLAN code... */ - memmove(skb->data - ETH_HLEN, - skb->data - VLAN_ETH_HLEN, 12); - skb->mac_header += VLAN_HLEN; - } - } + if (skb_cow(skb, skb_headroom(skb)) < 0) + return NULL; + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + skb_reset_mac_len(skb); return skb; } @@ -161,7 +167,7 @@ struct sk_buff *vlan_untag(struct sk_buff *skb) skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); - skb = vlan_check_reorder_header(skb); + skb = vlan_reorder_header(skb); if (unlikely(!skb)) goto err_free; diff --git a/net/core/dev.c b/net/core/dev.c index a54c9f87ddbb..9c58c1ec41a9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3114,7 +3114,7 @@ static int __netif_receive_skb(struct sk_buff *skb) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + skb_reset_mac_len(skb); pt_prev = NULL; -- cgit v1.2.3 From 83fe32de63e60af34fa8dae83716cb13b8677abd Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 11 Jun 2011 18:55:22 -0700 Subject: netpoll: call dev_put() on error in netpoll_setup() There is a dev_put(ndev) missing on an error path. This was introduced in 0c1ad04aecb "netpoll: prevent netpoll setup on slave devices". Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/core/netpoll.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 42ea4b0e59f1..18d9cbda3a39 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -795,7 +795,8 @@ int netpoll_setup(struct netpoll *np) if (ndev->master) { printk(KERN_ERR "%s: %s is a slave device, aborting.\n", np->name, np->dev_name); - return -EBUSY; + err = -EBUSY; + goto put; } if (!netif_running(ndev)) { -- cgit v1.2.3