diff options
| author |   Yunhong Jiang <yunhong.jiang@linux.intel.com> | 2017-03-08 23:13:28 -0800 |
|---|---|---|
| committer | Yunhong Jiang <yunhong.jiang@linux.intel.com> | 2017-03-08 23:36:15 -0800 |
| commit | 52f993b8e89487ec9ee15a7fb4979e0f09a45b27 (patch) | |
| tree | d65304486afe0bea4a311c783c0d72791c8c0aa2 /kernel/net/ipv4 | |
| parent | c189ccac5702322ed843fe17057035b7222a59b6 (diff) | |
Upgrade to 4.4.50-rt62
The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it
to 4.4.50-rt62.
The command to achieve it is:
a) Clone a git repo from
git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git
b) Get the diff between this two changesets:
git diff 640eca2901f3435e616157b11379d3223a44b391
705619beeea1b0b48219a683fd1a901a86fdaf5e
where the two commits are:
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
640eca2901f3435e616157b11379d3223a44b391
640eca2901f3 v4.4.6-rt14
localversion-rt
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
705619beeea1b0b48219a683fd1a901a86fdaf5e
705619beeea1 Linux 4.4.50-rt62
localversion-rt
c) One patch has been backported thus revert the patch before applying.
filterdiff -p1 -x scripts/package/Makefile
~/tmp/v4.4.6-rt14-4.4.50-rt62.diff |patch -p1 --dry-run
Upstream status: backport
Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01
Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>
Diffstat (limited to 'kernel/net/ipv4')
36 files changed, 621 insertions, 621 deletions
diff --git a/kernel/net/ipv4/af_inet.c b/kernel/net/ipv4/af_inet.c index 5c5db6636..afc18e9ca 100644 --- a/kernel/net/ipv4/af_inet.c +++ b/kernel/net/ipv4/af_inet.c @@ -1372,7 +1372,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); @@ -1383,6 +1383,19 @@ out: return pp; } +static struct sk_buff **ipip_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->encap_mark) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + NAPI_GRO_CB(skb)->encap_mark = 1; + + return inet_gro_receive(head, skb); +} + int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { if (sk->sk_family == AF_INET) @@ -1425,6 +1438,13 @@ out_unlock: return err; } +static int ipip_gro_complete(struct sk_buff *skb, int nhoff) +{ + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP; + return inet_gro_complete(skb, nhoff); +} + int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) @@ -1652,8 +1672,8 @@ static struct packet_offload ip_packet_offload __read_mostly = { static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, + .gro_receive = ipip_gro_receive, + .gro_complete = ipip_gro_complete, }, }; diff --git a/kernel/net/ipv4/cipso_ipv4.c b/kernel/net/ipv4/cipso_ipv4.c index bdb2a07ec..6cc3e1d60 100644 --- a/kernel/net/ipv4/cipso_ipv4.c +++ b/kernel/net/ipv4/cipso_ipv4.c @@ -1657,6 +1657,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) goto validate_return_locked; } + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto validate_return_locked; + } tag_len = tag[1]; if (tag_len > (opt_len - opt_iter)) { err_offset = opt_iter + 1; diff --git a/kernel/net/ipv4/devinet.c b/kernel/net/ipv4/devinet.c index f6303b175..0212591b0 100644 --- a/kernel/net/ipv4/devinet.c +++ b/kernel/net/ipv4/devinet.c @@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, ASSERT_RTNL(); + if (in_dev->dead) + goto no_promotions; + /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ @@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, fib_del_ifaddr(ifa, ifa1); } +no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; diff --git a/kernel/net/ipv4/esp4.c b/kernel/net/ipv4/esp4.c index 477937465..20fb25e30 100644 --- a/kernel/net/ipv4/esp4.c +++ b/kernel/net/ipv4/esp4.c @@ -23,6 +23,11 @@ struct esp_skb_cb { void *tmp; }; +struct esp_output_extra { + __be32 seqhi; + u32 esphoff; +}; + #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) static u32 esp4_get_mtu(struct xfrm_state *x, int mtu); @@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu); * * TODO: Use spare space in skb for this where possible. */ -static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen) +static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen) { unsigned int len; - len = seqhilen; + len = extralen; len += crypto_aead_ivsize(aead); @@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen) return kmalloc(len, GFP_ATOMIC); } -static inline __be32 *esp_tmp_seqhi(void *tmp) +static inline void *esp_tmp_extra(void *tmp) { - return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32)); + return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra)); } -static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) + +static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen) { return crypto_aead_ivsize(aead) ? - PTR_ALIGN((u8 *)tmp + seqhilen, - crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; + PTR_ALIGN((u8 *)tmp + extralen, + crypto_aead_alignmask(aead) + 1) : tmp + extralen; } static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) @@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset) { struct ip_esp_hdr *esph = (void *)(skb->data + offset); void *tmp = ESP_SKB_CB(skb)->tmp; - __be32 *seqhi = esp_tmp_seqhi(tmp); + __be32 *seqhi = esp_tmp_extra(tmp); esph->seq_no = esph->spi; esph->spi = *seqhi; @@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset) static void esp_output_restore_header(struct sk_buff *skb) { - esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32)); + void *tmp = ESP_SKB_CB(skb)->tmp; + struct esp_output_extra *extra = esp_tmp_extra(tmp); + + esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff - + sizeof(__be32)); } static void esp_output_done_esn(struct crypto_async_request *base, int err) @@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err) static int esp_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + struct esp_output_extra *extra; struct ip_esp_hdr *esph; struct crypto_aead *aead; struct aead_request *req; @@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) int tfclen; int nfrags; int assoclen; - int seqhilen; - __be32 *seqhi; + int extralen; __be64 seqno; /* skb is pure payload to encrypt */ @@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) nfrags = err; assoclen = sizeof(*esph); - seqhilen = 0; + extralen = 0; if (x->props.flags & XFRM_STATE_ESN) { - seqhilen += sizeof(__be32); - assoclen += seqhilen; + extralen += sizeof(*extra); + assoclen += sizeof(__be32); } - tmp = esp_alloc_tmp(aead, nfrags, seqhilen); + tmp = esp_alloc_tmp(aead, nfrags, extralen); if (!tmp) { err = -ENOMEM; goto error; } - seqhi = esp_tmp_seqhi(tmp); - iv = esp_tmp_iv(aead, tmp, seqhilen); + extra = esp_tmp_extra(tmp); + iv = esp_tmp_iv(aead, tmp, extralen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); @@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) * encryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)(skb_transport_header(skb) - sizeof(__be32)); - *seqhi = esph->spi; + extra->esphoff = (unsigned char *)esph - + skb_transport_header(skb); + esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4); + extra->seqhi = esph->spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi); aead_request_set_callback(req, 0, esp_output_done_esn, skb); } @@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) goto out; ESP_SKB_CB(skb)->tmp = tmp; - seqhi = esp_tmp_seqhi(tmp); + seqhi = esp_tmp_extra(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); @@ -464,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } diff --git a/kernel/net/ipv4/fib_frontend.c b/kernel/net/ipv4/fib_frontend.c index 473447593..4e60dae86 100644 --- a/kernel/net/ipv4/fib_frontend.c +++ b/kernel/net/ipv4/fib_frontend.c @@ -85,7 +85,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id) if (tb) return tb; - if (id == RT_TABLE_LOCAL) + if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); @@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) struct in_device *in_dev; struct fib_result res; struct rtable *rt; - struct flowi4 fl4; struct net *net; int scope; @@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { - fl4.flowi4_oif = 0; - fl4.flowi4_iif = LOOPBACK_IFINDEX; - fl4.daddr = ip_hdr(skb)->saddr; - fl4.saddr = 0; - fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); - fl4.flowi4_scope = scope; - fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; - fl4.flowi4_tun_key.tun_id = 0; + struct flowi4 fl4 = { + .flowi4_iif = LOOPBACK_IFINDEX, + .daddr = ip_hdr(skb)->saddr, + .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), + .flowi4_scope = scope, + .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -906,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { - pr_warn("%s: bug: prim == NULL\n", __func__); + /* if the device has been deleted, we don't perform + * address promotion + */ + if (!in_dev->dead) + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { @@ -922,6 +924,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) subnet = 1; } + if (in_dev->dead) + goto no_promotions; + /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * @@ -997,6 +1002,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) } } +no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); if (subnet && ifa->ifa_prefixlen < 31) { diff --git a/kernel/net/ipv4/fib_semantics.c b/kernel/net/ipv4/fib_semantics.c index d97268e8f..67d44aa9e 100644 --- a/kernel/net/ipv4/fib_semantics.c +++ b/kernel/net/ipv4/fib_semantics.c @@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + return -EINVAL; + nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; nexthop_nh->nh_oif = rtnh->rtnh_ifindex; @@ -975,6 +978,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) val = 65535 - 40; if (type == RTAX_MTU && val > 65535 - 15) val = 65535 - 15; + if (type == RTAX_HOPLIMIT && val > 255) + val = 255; if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) return -EINVAL; fi->fib_metrics[type - 1] = val; @@ -1001,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + goto err_inval; + #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); @@ -1269,8 +1277,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif - if (fi->fib_nh->nh_lwtstate) - lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); + if (fi->fib_nh->nh_lwtstate && + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0) + goto nla_put_failure; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1306,8 +1315,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif - if (nh->nh_lwtstate) - lwtunnel_fill_encap(skb, nh->nh_lwtstate); + if (nh->nh_lwtstate && + lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); @@ -1580,8 +1591,13 @@ void fib_select_multipath(struct fib_result *res, int hash) void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, int mp_hash) { + bool oif_check; + + oif_check = (fl4->flowi4_oif == 0 || + fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF); + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) { + if (res->fi->fib_nhs > 1 && oif_check) { if (mp_hash < 0) mp_hash = get_hash_from_flowi4(fl4) >> 1; @@ -1591,7 +1607,7 @@ void fib_select_path(struct net *net, struct fib_result *res, #endif if (!res->prefixlen && res->table->tb_num_default > 1 && - res->type == RTN_UNICAST && !fl4->flowi4_oif) + res->type == RTN_UNICAST && oif_check) fib_select_default(fl4, res); if (!fl4->saddr) diff --git a/kernel/net/ipv4/fib_trie.c b/kernel/net/ipv4/fib_trie.c index 744e5936c..7c52afb98 100644 --- a/kernel/net/ipv4/fib_trie.c +++ b/kernel/net/ipv4/fib_trie.c @@ -2453,29 +2453,22 @@ struct fib_route_iter { static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { - struct fib_table *tb = iter->main_tb; struct key_vector *l, **tp = &iter->tnode; - struct trie *t; t_key key; - /* use cache location of next-to-find key */ + /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { - pos -= iter->pos; key = iter->key; } else { - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; - iter->pos = 0; + iter->pos = 1; key = 0; } - while ((l = leaf_walk_rcu(tp, key)) != NULL) { + pos -= iter->pos; + + while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; - - if (--pos <= 0) - break; - l = NULL; /* handle unlikely case of a key wrap */ @@ -2484,7 +2477,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, } if (l) - iter->key = key; /* remember it */ + iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ @@ -2505,14 +2498,14 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return NULL; iter->main_tb = tb; + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; - iter->key = 0; + iter->key = KEY_MAX; return SEQ_START_TOKEN; } @@ -2521,7 +2514,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; - t_key key = iter->key; + t_key key = iter->key + 1; ++*pos; @@ -2530,7 +2523,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) l = leaf_walk_rcu(&iter->tnode, key); if (l) { - iter->key = l->key + 1; + iter->key = l->key; iter->pos++; } else { iter->pos = 0; diff --git a/kernel/net/ipv4/fou.c b/kernel/net/ipv4/fou.c index bd903fe0f..08d8ee124 100644 --- a/kernel/net/ipv4/fou.c +++ b/kernel/net/ipv4/fou.c @@ -48,7 +48,7 @@ static inline struct fou *fou_from_sock(struct sock *sk) return sk->sk_user_data; } -static void fou_recv_pull(struct sk_buff *skb, size_t len) +static int fou_recv_pull(struct sk_buff *skb, size_t len) { struct iphdr *iph = ip_hdr(skb); @@ -59,6 +59,7 @@ static void fou_recv_pull(struct sk_buff *skb, size_t len) __skb_pull(skb, len); skb_postpull_rcsum(skb, udp_hdr(skb), len); skb_reset_transport_header(skb); + return iptunnel_pull_offloads(skb); } static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) @@ -68,9 +69,14 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) if (!fou) return 1; - fou_recv_pull(skb, sizeof(struct udphdr)); + if (fou_recv_pull(skb, sizeof(struct udphdr))) + goto drop; return -fou->protocol; + +drop: + kfree_skb(skb); + return 0; } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, @@ -170,6 +176,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); + if (iptunnel_pull_offloads(skb)) + goto drop; + return -guehdr->proto_ctype; drop: @@ -192,7 +201,7 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head, if (!ops || !ops->callbacks.gro_receive) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); @@ -351,7 +360,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/kernel/net/ipv4/gre_offload.c b/kernel/net/ipv4/gre_offload.c index 5a8ee3282..79ae0d7be 100644 --- a/kernel/net/ipv4/gre_offload.c +++ b/kernel/net/ipv4/gre_offload.c @@ -128,6 +128,11 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, struct packet_offload *ptype; __be16 type; + if (NAPI_GRO_CB(skb)->encap_mark) + goto out; + + NAPI_GRO_CB(skb)->encap_mark = 1; + off = skb_gro_offset(skb); hlen = off + sizeof(*greh); greh = skb_gro_header_fast(skb, off); @@ -214,7 +219,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ skb_gro_postpull_rcsum(skb, greh, grehlen); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/kernel/net/ipv4/icmp.c b/kernel/net/ipv4/icmp.c index 74314d95d..ff2593269 100644 --- a/kernel/net/ipv4/icmp.c +++ b/kernel/net/ipv4/icmp.c @@ -78,6 +78,7 @@ #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> +#include <linux/locallock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> @@ -205,6 +206,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; * * On SMP we have one ICMP socket per-cpu. */ +static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); + static struct sock *icmp_sk(struct net *net) { return *this_cpu_ptr(net->ipv4.icmp_sk); @@ -216,12 +219,14 @@ static inline struct sock *icmp_xmit_lock(struct net *net) local_bh_disable(); + local_lock(icmp_sk_lock); sk = icmp_sk(net); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ + local_unlock(icmp_sk_lock); local_bh_enable(); return NULL; } @@ -231,6 +236,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net) static inline void icmp_xmit_unlock(struct sock *sk) { spin_unlock_bh(&sk->sk_lock.slock); + local_unlock(icmp_sk_lock); } int sysctl_icmp_msgs_per_sec __read_mostly = 1000; @@ -359,6 +365,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, struct sock *sk; struct sk_buff *skb; + local_lock(icmp_sk_lock); sk = icmp_sk(dev_net((*rt)->dst.dev)); if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, @@ -381,6 +388,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); } + local_unlock(icmp_sk_lock); } /* diff --git a/kernel/net/ipv4/igmp.c b/kernel/net/ipv4/igmp.c index 05e4cba14..17adfdaf5 100644 --- a/kernel/net/ipv4/igmp.c +++ b/kernel/net/ipv4/igmp.c @@ -225,9 +225,14 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = prandom_u32() % in_dev->mr_maxdelay; + unsigned long exp = jiffies + tv + 2; + + if (in_dev->mr_gq_running && + time_after_eq(exp, (in_dev->mr_gq_timer).expires)) + return; in_dev->mr_gq_running = 1; - if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2)) + if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } @@ -356,9 +361,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/kernel/net/ipv4/ip_gre.c b/kernel/net/ipv4/ip_gre.c index 614521437..3e4184088 100644 --- a/kernel/net/ipv4/ip_gre.c +++ b/kernel/net/ipv4/ip_gre.c @@ -180,6 +180,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags) return flags; } +/* Fills in tpi and returns header length to be pulled. */ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err) { @@ -239,7 +240,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, return -EINVAL; } } - return iptunnel_pull_header(skb, hdr_len, tpi->proto); + return hdr_len; } static void ipgre_err(struct sk_buff *skb, u32 info, @@ -342,7 +343,7 @@ static void gre_err(struct sk_buff *skb, u32 info) struct tnl_ptk_info tpi; bool csum_err = false; - if (parse_gre_header(skb, &tpi, &csum_err)) { + if (parse_gre_header(skb, &tpi, &csum_err) < 0) { if (!csum_err) /* ignore csum errors. */ return; } @@ -420,6 +421,7 @@ static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; + int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { @@ -429,7 +431,10 @@ static int gre_rcv(struct sk_buff *skb) } #endif - if (parse_gre_header(skb, &tpi, &csum_err) < 0) + hdr_len = parse_gre_header(skb, &tpi, &csum_err); + if (hdr_len < 0) + goto drop; + if (iptunnel_pull_header(skb, hdr_len, tpi.proto) < 0) goto drop; if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) @@ -1242,6 +1247,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, err = ipgre_newlink(net, dev, tb, NULL); if (err < 0) goto out; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); + if (err) + goto out; + return dev; out: free_netdev(dev); diff --git a/kernel/net/ipv4/ip_output.c b/kernel/net/ipv4/ip_output.c index 49f028563..2b7283303 100644 --- a/kernel/net/ipv4/ip_output.c +++ b/kernel/net/ipv4/ip_output.c @@ -102,6 +102,9 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); + + skb->protocol = htons(ETH_P_IP); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); @@ -1237,13 +1240,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/kernel/net/ipv4/ip_sockglue.c b/kernel/net/ipv4/ip_sockglue.c index a50124260..bc14c5bb1 100644 --- a/kernel/net/ipv4/ip_sockglue.c +++ b/kernel/net/ipv4/ip_sockglue.c @@ -98,7 +98,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) } static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, - int offset) + int tlen, int offset) { __wsum csum = skb->csum; @@ -106,7 +106,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, return; if (offset != 0) - csum = csum_sub(csum, csum_partial(skb->data, offset, 0)); + csum = csum_sub(csum, + csum_partial(skb->data + tlen, + offset, 0)); put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); } @@ -152,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) } void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, - int offset) + int tlen, int offset) { struct inet_sock *inet = inet_sk(skb->sk); unsigned int flags = inet->cmsg_flags; @@ -215,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, } if (flags & IP_CMSG_CHECKSUM) - ip_cmsg_recv_checksum(msg, skb, offset); + ip_cmsg_recv_checksum(msg, skb, tlen, offset); } EXPORT_SYMBOL(ip_cmsg_recv_offset); @@ -1190,7 +1192,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + /* We need to keep the dst for __ip_options_echo() + * We could restrict the test to opt.ts_needtime || opt.srr, + * but the following is good enough as IP options are not often used. + */ + if (unlikely(IPCB(skb)->opt.optlen)) + skb_dst_force(skb); + else + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, diff --git a/kernel/net/ipv4/ip_tunnel.c b/kernel/net/ipv4/ip_tunnel.c index cbb51f3fa..3310ac75e 100644 --- a/kernel/net/ipv4/ip_tunnel.c +++ b/kernel/net/ipv4/ip_tunnel.c @@ -663,6 +663,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -760,7 +762,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; @@ -947,17 +948,31 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); -int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; - if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen) + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); + +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + return __ip_tunnel_change_mtu(dev, new_mtu, true); +} EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) diff --git a/kernel/net/ipv4/ip_tunnel_core.c b/kernel/net/ipv4/ip_tunnel_core.c index 6cb9009c3..dbda05657 100644 --- a/kernel/net/ipv4/ip_tunnel_core.c +++ b/kernel/net/ipv4/ip_tunnel_core.c @@ -116,7 +116,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; - return 0; + + return iptunnel_pull_offloads(skb); } EXPORT_SYMBOL_GPL(iptunnel_pull_header); diff --git a/kernel/net/ipv4/ip_vti.c b/kernel/net/ipv4/ip_vti.c index 4d8f0b698..65036891e 100644 --- a/kernel/net/ipv4/ip_vti.c +++ b/kernel/net/ipv4/ip_vti.c @@ -540,6 +540,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -547,6 +574,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -579,6 +608,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -590,6 +620,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); diff --git a/kernel/net/ipv4/ipmr.c b/kernel/net/ipv4/ipmr.c index c3a38353f..8e7778654 100644 --- a/kernel/net/ipv4/ipmr.c +++ b/kernel/net/ipv4/ipmr.c @@ -882,8 +882,10 @@ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c) + if (c) { + c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXVIFS; + } return c; } @@ -2190,7 +2192,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, - struct rtmsg *rtm, int nowait) + struct rtmsg *rtm, int nowait, u32 portid) { struct mfc_cache *cache; struct mr_table *mrt; @@ -2235,6 +2237,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, return -ENOMEM; } + NETLINK_CB(skb2).portid = portid; skb_push(skb2, sizeof(struct iphdr)); skb_reset_network_header(skb2); iph = ip_hdr(skb2); diff --git a/kernel/net/ipv4/netfilter/arp_tables.c b/kernel/net/ipv4/netfilter/arp_tables.c index 11dccba47..6e3e0e8b1 100644 --- a/kernel/net/ipv4/netfilter/arp_tables.c +++ b/kernel/net/ipv4/netfilter/arp_tables.c @@ -359,11 +359,24 @@ unsigned int arpt_do_table(struct sk_buff *skb, } /* All zeroes == unconditional rule. */ -static inline bool unconditional(const struct arpt_arp *arp) +static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; - return memcmp(arp, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct arpt_entry) && + memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; +} + +static bool find_jump_target(const struct xt_table_info *t, + const struct arpt_entry *target) +{ + struct arpt_entry *iter; + + xt_entry_foreach(iter, t->entries, t->size) { + if (iter == target) + return true; + } + return false; } /* Figures out from what hook each rule can be called: returns 0 if @@ -402,11 +415,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->arp)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -439,6 +451,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo, size = e->next_offset; e = (struct arpt_entry *) (entry0 + pos + size); + if (pos + size >= newinfo->size) + return 0; e->counters.pcnt = pos; pos += size; } else { @@ -458,9 +472,15 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); + e = (struct arpt_entry *) + (entry0 + newpos); + if (!find_jump_target(newinfo, e)) + return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; } e = (struct arpt_entry *) (entry0 + newpos); @@ -474,25 +494,6 @@ next: return 1; } -static inline int check_entry(const struct arpt_entry *e, const char *name) -{ - const struct xt_entry_target *t; - - if (!arp_checkentry(&e->arp)) { - duprintf("arp_tables: arp check failed %p %s.\n", e, name); - return -EINVAL; - } - - if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) - return -EINVAL; - - t = arpt_get_target_c(e); - if (e->target_offset + t->u.target_size > e->next_offset) - return -EINVAL; - - return 0; -} - static inline int check_target(struct arpt_entry *e, const char *name) { struct xt_entry_target *t = arpt_get_target(e); @@ -522,10 +523,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) struct xt_target *target; int ret; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -557,7 +554,7 @@ static bool check_underflow(const struct arpt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->arp)) + if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -576,9 +573,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -590,6 +589,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return -EINVAL; } + if (!arp_checkentry(&e->arp)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -598,9 +605,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -691,10 +698,8 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, } } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) { - duprintf("Looping hook\n"); + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) return -ELOOP; - } /* Finally, each sanity check must pass */ i = 0; @@ -1125,55 +1130,17 @@ static int do_add_counters(struct net *net, const void __user *user, unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; - unsigned int num_counters; - const char *name; - int size; - void *ptmp; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct arpt_entry *iter; unsigned int addend; -#ifdef CONFIG_COMPAT - struct compat_xt_counters_info compat_tmp; - - if (compat) { - ptmp = &compat_tmp; - size = sizeof(struct compat_xt_counters_info); - } else -#endif - { - ptmp = &tmp; - size = sizeof(struct xt_counters_info); - } - if (copy_from_user(ptmp, user, size) != 0) - return -EFAULT; - -#ifdef CONFIG_COMPAT - if (compat) { - num_counters = compat_tmp.num_counters; - name = compat_tmp.name; - } else -#endif - { - num_counters = tmp.num_counters; - name = tmp.name; - } + paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); - if (len != size + num_counters * sizeof(struct xt_counters)) - return -EINVAL; - - paddc = vmalloc(len - size); - if (!paddc) - return -ENOMEM; - - if (copy_from_user(paddc, user + size, len - size) != 0) { - ret = -EFAULT; - goto free; - } - - t = xt_find_table_lock(net, NFPROTO_ARP, name); + t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name); if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; @@ -1181,7 +1148,7 @@ static int do_add_counters(struct net *net, const void __user *user, local_bh_disable(); private = t->private; - if (private->number != num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } @@ -1208,6 +1175,18 @@ static int do_add_counters(struct net *net, const void __user *user, } #ifdef CONFIG_COMPAT +struct compat_arpt_replace { + char name[XT_TABLE_MAXNAMELEN]; + u32 valid_hooks; + u32 num_entries; + u32 size; + u32 hook_entry[NF_ARP_NUMHOOKS]; + u32 underflow[NF_ARP_NUMHOOKS]; + u32 num_counters; + compat_uptr_t counters; + struct compat_arpt_entry entries[0]; +}; + static inline void compat_release_entry(struct compat_arpt_entry *e) { struct xt_entry_target *t; @@ -1216,24 +1195,22 @@ static inline void compat_release_entry(struct compat_arpt_entry *e) module_put(t->u.kernel.target->me); } -static inline int +static int check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, - const unsigned char *limit, - const unsigned int *hook_entries, - const unsigned int *underflows, - const char *name) + const unsigned char *limit) { struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; - int ret, off, h; + int ret, off; duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1245,8 +1222,11 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, return -EINVAL; } - /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct arpt_entry *)e, name); + if (!arp_checkentry(&e->arp)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); if (ret) return ret; @@ -1270,17 +1250,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, if (ret) goto release_target; - /* Check hooks & underflows */ - for (h = 0; h < NF_ARP_NUMHOOKS; h++) { - if ((unsigned char *)e - base == hook_entries[h]) - newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) - newinfo->underflow[h] = underflows[h]; - } - - /* Clear counters and comefrom */ - memset(&e->counters, 0, sizeof(e->counters)); - e->comefrom = 0; return 0; release_target: @@ -1289,18 +1258,17 @@ out: return ret; } -static int +static void compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, - unsigned int *size, const char *name, + unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct xt_target *target; struct arpt_entry *de; unsigned int origsize; - int ret, h; + int h; - ret = 0; origsize = *size; de = (struct arpt_entry *)*dstptr; memcpy(de, e, sizeof(struct arpt_entry)); @@ -1321,148 +1289,82 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } - return ret; } -static int translate_compat_table(const char *name, - unsigned int valid_hooks, - struct xt_table_info **pinfo, +static int translate_compat_table(struct xt_table_info **pinfo, void **pentry0, - unsigned int total_size, - unsigned int number, - unsigned int *hook_entries, - unsigned int *underflows) + const struct compat_arpt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_arpt_entry *iter0; - struct arpt_entry *iter1; + struct arpt_replace repl; unsigned int size; int ret = 0; info = *pinfo; entry0 = *pentry0; - size = total_size; - info->number = number; - - /* Init all hooks to impossible value. */ - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - info->hook_entry[i] = 0xFFFFFFFF; - info->underflow[i] = 0xFFFFFFFF; - } + size = compatr->size; + info->number = compatr->num_entries; duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(NFPROTO_ARP); - xt_compat_init_offsets(NFPROTO_ARP, number); + xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, total_size) { + xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, - entry0 + total_size, - hook_entries, - underflows, - name); + entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; - if (j != number) { + if (j != compatr->num_entries) { duprintf("translate_compat_table: %u not %u entries\n", - j, number); + j, compatr->num_entries); goto out_unlock; } - /* Check hooks all assigned */ - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) - continue; - if (info->hook_entry[i] == 0xFFFFFFFF) { - duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); - goto out_unlock; - } - if (info->underflow[i] == 0xFFFFFFFF) { - duprintf("Invalid underflow %u %u\n", - i, underflows[i]); - goto out_unlock; - } - } - ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; - newinfo->number = number; + newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = info->hook_entry[i]; newinfo->underflow[i] = info->underflow[i]; } entry1 = newinfo->entries; pos = entry1; - size = total_size; - xt_entry_foreach(iter0, entry0, total_size) { - ret = compat_copy_entry_from_user(iter0, &pos, &size, - name, newinfo, entry1); - if (ret != 0) - break; - } + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone */ + xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); - if (ret) - goto free_newinfo; - ret = -ELOOP; - if (!mark_source_chains(newinfo, valid_hooks, entry1)) - goto free_newinfo; + memcpy(&repl, compatr, sizeof(*compatr)); - i = 0; - xt_entry_foreach(iter1, entry1, newinfo->size) { - iter1->counters.pcnt = xt_percpu_counter_alloc(); - if (IS_ERR_VALUE(iter1->counters.pcnt)) { - ret = -ENOMEM; - break; - } - - ret = check_target(iter1, name); - if (ret != 0) { - xt_percpu_counter_free(iter1->counters.pcnt); - break; - } - ++i; - if (strcmp(arpt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; - } - if (ret) { - /* - * The first i matches need cleanup_entry (calls ->destroy) - * because they had called ->check already. The other j-i - * entries need only release. - */ - int skip = i; - j -= i; - xt_entry_foreach(iter0, entry0, newinfo->size) { - if (skip-- > 0) - continue; - if (j-- == 0) - break; - compat_release_entry(iter0); - } - xt_entry_foreach(iter1, entry1, newinfo->size) { - if (i-- == 0) - break; - cleanup_entry(iter1); - } - xt_free_table_info(newinfo); - return ret; + for (i = 0; i < NF_ARP_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; } + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(newinfo, entry1, &repl); + if (ret) + goto free_newinfo; + *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); @@ -1470,31 +1372,18 @@ static int translate_compat_table(const char *name, free_newinfo: xt_free_table_info(newinfo); -out: - xt_entry_foreach(iter0, entry0, total_size) { + return ret; +out_unlock: + xt_compat_flush_offsets(NFPROTO_ARP); + xt_compat_unlock(NFPROTO_ARP); + xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; -out_unlock: - xt_compat_flush_offsets(NFPROTO_ARP); - xt_compat_unlock(NFPROTO_ARP); - goto out; } -struct compat_arpt_replace { - char name[XT_TABLE_MAXNAMELEN]; - u32 valid_hooks; - u32 num_entries; - u32 size; - u32 hook_entry[NF_ARP_NUMHOOKS]; - u32 underflow[NF_ARP_NUMHOOKS]; - u32 num_counters; - compat_uptr_t counters; - struct compat_arpt_entry entries[0]; -}; - static int compat_do_replace(struct net *net, void __user *user, unsigned int len) { @@ -1527,10 +1416,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(tmp.name, tmp.valid_hooks, - &newinfo, &loc_cpu_entry, tmp.size, - tmp.num_entries, tmp.hook_entry, - tmp.underflow); + ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; diff --git a/kernel/net/ipv4/netfilter/ip_tables.c b/kernel/net/ipv4/netfilter/ip_tables.c index b99affad6..a399c5419 100644 --- a/kernel/net/ipv4/netfilter/ip_tables.c +++ b/kernel/net/ipv4/netfilter/ip_tables.c @@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ipt_ip *ip) +static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; - return memcmp(ip, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ipt_entry) && + memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; #undef FWINV } @@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ip)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -443,6 +443,18 @@ ipt_do_table(struct sk_buff *skb, #endif } +static bool find_jump_target(const struct xt_table_info *t, + const struct ipt_entry *target) +{ + struct ipt_entry *iter; + + xt_entry_foreach(iter, t->entries, t->size) { + if (iter == target) + return true; + } + return false; +} + /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int @@ -476,11 +488,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->ip)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -521,6 +532,8 @@ mark_source_chains(const struct xt_table_info *newinfo, size = e->next_offset; e = (struct ipt_entry *) (entry0 + pos + size); + if (pos + size >= newinfo->size) + return 0; e->counters.pcnt = pos; pos += size; } else { @@ -539,9 +552,15 @@ mark_source_chains(const struct xt_table_info *newinfo, /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); + e = (struct ipt_entry *) + (entry0 + newpos); + if (!find_jump_target(newinfo, e)) + return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; } e = (struct ipt_entry *) (entry0 + newpos); @@ -569,27 +588,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ipt_entry *e, const char *name) -{ - const struct xt_entry_target *t; - - if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, name); - return -EINVAL; - } - - if (e->target_offset + sizeof(struct xt_entry_target) > - e->next_offset) - return -EINVAL; - - t = ipt_get_target_c(e); - if (e->target_offset + t->u.target_size > e->next_offset) - return -EINVAL; - - return 0; -} - -static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; @@ -666,10 +664,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -721,7 +715,7 @@ static bool check_underflow(const struct ipt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ip)) + if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -741,9 +735,11 @@ check_entry_size_and_hooks(struct ipt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -755,6 +751,14 @@ check_entry_size_and_hooks(struct ipt_entry *e, return -EINVAL; } + if (!ip_checkentry(&e->ip)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -763,9 +767,9 @@ check_entry_size_and_hooks(struct ipt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -1309,55 +1313,17 @@ do_add_counters(struct net *net, const void __user *user, unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; - unsigned int num_counters; - const char *name; - int size; - void *ptmp; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ipt_entry *iter; unsigned int addend; -#ifdef CONFIG_COMPAT - struct compat_xt_counters_info compat_tmp; - - if (compat) { - ptmp = &compat_tmp; - size = sizeof(struct compat_xt_counters_info); - } else -#endif - { - ptmp = &tmp; - size = sizeof(struct xt_counters_info); - } - - if (copy_from_user(ptmp, user, size) != 0) - return -EFAULT; - -#ifdef CONFIG_COMPAT - if (compat) { - num_counters = compat_tmp.num_counters; - name = compat_tmp.name; - } else -#endif - { - num_counters = tmp.num_counters; - name = tmp.name; - } - if (len != size + num_counters * sizeof(struct xt_counters)) - return -EINVAL; - - paddc = vmalloc(len - size); - if (!paddc) - return -ENOMEM; + paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); - if (copy_from_user(paddc, user + size, len - size) != 0) { - ret = -EFAULT; - goto free; - } - - t = xt_find_table_lock(net, AF_INET, name); + t = xt_find_table_lock(net, AF_INET, tmp.name); if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; @@ -1365,7 +1331,7 @@ do_add_counters(struct net *net, const void __user *user, local_bh_disable(); private = t->private; - if (private->number != num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } @@ -1444,7 +1410,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, static int compat_find_calc_match(struct xt_entry_match *m, - const char *name, const struct ipt_ip *ip, int *size) { @@ -1479,21 +1444,19 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, - const unsigned char *limit, - const unsigned int *hook_entries, - const unsigned int *underflows, - const char *name) + const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; - int ret, off, h; + int ret, off; duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1505,8 +1468,11 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, return -EINVAL; } - /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ipt_entry *)e, name); + if (!ip_checkentry(&e->ip)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, + e->target_offset, e->next_offset); if (ret) return ret; @@ -1514,7 +1480,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, &e->ip, &off); + ret = compat_find_calc_match(ematch, &e->ip, &off); if (ret != 0) goto release_matches; ++j; @@ -1537,17 +1503,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, if (ret) goto out; - /* Check hooks & underflows */ - for (h = 0; h < NF_INET_NUMHOOKS; h++) { - if ((unsigned char *)e - base == hook_entries[h]) - newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) - newinfo->underflow[h] = underflows[h]; - } - - /* Clear counters and comefrom */ - memset(&e->counters, 0, sizeof(e->counters)); - e->comefrom = 0; return 0; out: @@ -1561,19 +1516,18 @@ release_matches: return ret; } -static int +static void compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, - unsigned int *size, const char *name, + unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct xt_target *target; struct ipt_entry *de; unsigned int origsize; - int ret, h; + int h; struct xt_entry_match *ematch; - ret = 0; origsize = *size; de = (struct ipt_entry *)*dstptr; memcpy(de, e, sizeof(struct ipt_entry)); @@ -1582,201 +1536,105 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, *dstptr += sizeof(struct ipt_entry); *size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); - xt_ematch_foreach(ematch, e) { - ret = xt_compat_match_from_user(ematch, dstptr, size); - if (ret != 0) - return ret; - } + xt_ematch_foreach(ematch, e) + xt_compat_match_from_user(ematch, dstptr, size); + de->target_offset = e->target_offset - (origsize - *size); t = compat_ipt_get_target(e); target = t->u.kernel.target; xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); + for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } - return ret; -} - -static int -compat_check_entry(struct ipt_entry *e, struct net *net, const char *name) -{ - struct xt_entry_match *ematch; - struct xt_mtchk_param mtpar; - unsigned int j; - int ret = 0; - - e->counters.pcnt = xt_percpu_counter_alloc(); - if (IS_ERR_VALUE(e->counters.pcnt)) - return -ENOMEM; - - j = 0; - mtpar.net = net; - mtpar.table = name; - mtpar.entryinfo = &e->ip; - mtpar.hook_mask = e->comefrom; - mtpar.family = NFPROTO_IPV4; - xt_ematch_foreach(ematch, e) { - ret = check_match(ematch, &mtpar); - if (ret != 0) - goto cleanup_matches; - ++j; - } - - ret = check_target(e, net, name); - if (ret) - goto cleanup_matches; - return 0; - - cleanup_matches: - xt_ematch_foreach(ematch, e) { - if (j-- == 0) - break; - cleanup_match(ematch, net); - } - - xt_percpu_counter_free(e->counters.pcnt); - - return ret; } static int translate_compat_table(struct net *net, - const char *name, - unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, - unsigned int total_size, - unsigned int number, - unsigned int *hook_entries, - unsigned int *underflows) + const struct compat_ipt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ipt_entry *iter0; - struct ipt_entry *iter1; + struct ipt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; - size = total_size; - info->number = number; - - /* Init all hooks to impossible value. */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - info->hook_entry[i] = 0xFFFFFFFF; - info->underflow[i] = 0xFFFFFFFF; - } + size = compatr->size; + info->number = compatr->num_entries; duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET); - xt_compat_init_offsets(AF_INET, number); + xt_compat_init_offsets(AF_INET, compatr->num_entries); /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, total_size) { + xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, - entry0 + total_size, - hook_entries, - underflows, - name); + entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; - if (j != number) { + if (j != compatr->num_entries) { duprintf("translate_compat_table: %u not %u entries\n", - j, number); + j, compatr->num_entries); goto out_unlock; } - /* Check hooks all assigned */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) - continue; - if (info->hook_entry[i] == 0xFFFFFFFF) { - duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); - goto out_unlock; - } - if (info->underflow[i] == 0xFFFFFFFF) { - duprintf("Invalid underflow %u %u\n", - i, underflows[i]); - goto out_unlock; - } - } - ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; - newinfo->number = number; + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; - size = total_size; - xt_entry_foreach(iter0, entry0, total_size) { - ret = compat_copy_entry_from_user(iter0, &pos, &size, - name, newinfo, entry1); - if (ret != 0) - break; - } + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone. + * entry1/newinfo contains a 64bit ruleset that looks exactly as + * generated by 64bit userspace. + * + * Call standard translate_table() to validate all hook_entrys, + * underflows, check for loops, etc. + */ xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); - if (ret) - goto free_newinfo; - ret = -ELOOP; - if (!mark_source_chains(newinfo, valid_hooks, entry1)) - goto free_newinfo; + memcpy(&repl, compatr, sizeof(*compatr)); - i = 0; - xt_entry_foreach(iter1, entry1, newinfo->size) { - ret = compat_check_entry(iter1, net, name); - if (ret != 0) - break; - ++i; - if (strcmp(ipt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; - } - if (ret) { - /* - * The first i matches need cleanup_entry (calls ->destroy) - * because they had called ->check already. The other j-i - * entries need only release. - */ - int skip = i; - j -= i; - xt_entry_foreach(iter0, entry0, newinfo->size) { - if (skip-- > 0) - continue; - if (j-- == 0) - break; - compat_release_entry(iter0); - } - xt_entry_foreach(iter1, entry1, newinfo->size) { - if (i-- == 0) - break; - cleanup_entry(iter1, net); - } - xt_free_table_info(newinfo); - return ret; + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; } + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(net, newinfo, entry1, &repl); + if (ret) + goto free_newinfo; + *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); @@ -1784,17 +1642,16 @@ translate_compat_table(struct net *net, free_newinfo: xt_free_table_info(newinfo); -out: - xt_entry_foreach(iter0, entry0, total_size) { + return ret; +out_unlock: + xt_compat_flush_offsets(AF_INET); + xt_compat_unlock(AF_INET); + xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; -out_unlock: - xt_compat_flush_offsets(AF_INET); - xt_compat_unlock(AF_INET); - goto out; } static int @@ -1830,10 +1687,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, - &newinfo, &loc_cpu_entry, tmp.size, - tmp.num_entries, tmp.hook_entry, - tmp.underflow); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; diff --git a/kernel/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/kernel/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index c6eb42100..ea91058b5 100644 --- a/kernel/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/kernel/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; + struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; struct netdev_notifier_info info; - netdev_notifier_info_init(&info, dev); + /* The masq_dev_notifier will catch the case of the device going + * down. So if the inetdev is dead and being destroyed we have + * no work to do. Otherwise this is an individual address removal + * and we have to perform the flush. + */ + if (idev->dead) + return NOTIFY_DONE; + + netdev_notifier_info_init(&info, idev->dev); return masq_device_event(this, event, &info); } diff --git a/kernel/net/ipv4/ping.c b/kernel/net/ipv4/ping.c index aa67e0e64..3a00512ad 100644 --- a/kernel/net/ipv4/ping.c +++ b/kernel/net/ipv4/ping.c @@ -645,6 +645,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); + if (!skb) + return 0; pfh->wcheck = csum_partial((char *)&pfh->icmph, sizeof(struct icmphdr), pfh->wcheck); pfh->icmph.checksum = csum_fold(pfh->wcheck); @@ -660,6 +662,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, if (len > 0xFFFF) return -EMSGSIZE; + /* Must have at least a full ICMP header. */ + if (len < icmph_len) + return -EINVAL; + /* * Check the flags. */ diff --git a/kernel/net/ipv4/route.c b/kernel/net/ipv4/route.c index 02c62299d..ef2f527a1 100644 --- a/kernel/net/ipv4/route.c +++ b/kernel/net/ipv4/route.c @@ -747,7 +747,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + if (!n) + n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); @@ -2045,6 +2047,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res, */ if (fi && res->prefixlen < 4) fi = NULL; + } else if ((type == RTN_LOCAL) && (orig_oif != 0) && + (orig_oif != dev_out->ifindex)) { + /* For local routes that require a particular output interface + * we do not want to cache the result. Caching the result + * causes incorrect behaviour when there are multiple source + * addresses on the interface, the end result being that if the + * intended recipient is waiting on that interface for the + * packet he won't receive it because it will be delivered on + * the loopback interface and the IP_PKTINFO ipi_ifindex will + * be set to the loopback interface as well. + */ + fi = NULL; } fnhe = NULL; @@ -2416,7 +2430,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = table_id; + r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; @@ -2480,7 +2494,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, - r, nowait); + r, nowait, portid); + if (err <= 0) { if (!nowait) { if (err == 0) diff --git a/kernel/net/ipv4/sysctl_net_ipv4.c b/kernel/net/ipv4/sysctl_net_ipv4.c index 1866f9102..1bcd43670 100644 --- a/kernel/net/ipv4/sysctl_net_ipv4.c +++ b/kernel/net/ipv4/sysctl_net_ipv4.c @@ -97,11 +97,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } /* Update system visible IP port range */ @@ -110,10 +110,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); - write_seqlock(&net->ipv4.ip_local_ports.lock); + write_seqlock(&net->ipv4.ping_group_range.lock); data[0] = low; data[1] = high; - write_sequnlock(&net->ipv4.ip_local_ports.lock); + write_sequnlock(&net->ipv4.ping_group_range.lock); } /* Validate changes from /proc interface. */ diff --git a/kernel/net/ipv4/tcp.c b/kernel/net/ipv4/tcp.c index 036a76ba2..600dcda84 100644 --- a/kernel/net/ipv4/tcp.c +++ b/kernel/net/ipv4/tcp.c @@ -783,6 +783,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } + /* if __tcp_splice_read() got nothing while we have + * an skb in receive queue, we do not want to loop. + * This might happen with URG data. + */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); @@ -1212,7 +1218,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } diff --git a/kernel/net/ipv4/tcp_dctcp.c b/kernel/net/ipv4/tcp_dctcp.c index 7e538f71f..55d7da1d2 100644 --- a/kernel/net/ipv4/tcp_dctcp.c +++ b/kernel/net/ipv4/tcp_dctcp.c @@ -56,6 +56,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 delayed_ack_reserved; + u32 loss_cwnd; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->delayed_ack_reserved = 0; + ca->loss_cwnd = 0; ca->ce_state = 0; dctcp_reset(tp, ca); @@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk) static u32 dctcp_ssthresh(struct sock *sk) { - const struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); } @@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } +static u32 dctcp_cwnd_undo(struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + static struct tcp_congestion_ops dctcp __read_mostly = { .init = dctcp_init, .in_ack_event = dctcp_update_alpha, .cwnd_event = dctcp_cwnd_event, .ssthresh = dctcp_ssthresh, .cong_avoid = tcp_reno_cong_avoid, + .undo_cwnd = dctcp_cwnd_undo, .set_state = dctcp_state, .get_info = dctcp_get_info, .flags = TCP_CONG_NEEDS_ECN, diff --git a/kernel/net/ipv4/tcp_fastopen.c b/kernel/net/ipv4/tcp_fastopen.c index 55be6ac70..fca618272 100644 --- a/kernel/net/ipv4/tcp_fastopen.c +++ b/kernel/net/ipv4/tcp_fastopen.c @@ -112,7 +112,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, struct tcp_fastopen_cookie tmp; if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { - struct in6_addr *buf = (struct in6_addr *) tmp.val; + struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) @@ -161,6 +161,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash diff --git a/kernel/net/ipv4/tcp_input.c b/kernel/net/ipv4/tcp_input.c index d4c511584..7cc0f8aac 100644 --- a/kernel/net/ipv4/tcp_input.c +++ b/kernel/net/ipv4/tcp_input.c @@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -2324,10 +2324,9 @@ static void DBGUNDO(struct sock *sk, const char *msg) } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", msg, - &np->daddr, ntohs(inet->inet_dport), + &sk->sk_v6_daddr, ntohs(inet->inet_dport), tp->snd_cwnd, tcp_left_out(tp), tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); @@ -3390,6 +3389,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3403,21 +3419,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3427,21 +3431,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/kernel/net/ipv4/tcp_ipv4.c b/kernel/net/ipv4/tcp_ipv4.c index 8c7e63163..e90f2507a 100644 --- a/kernel/net/ipv4/tcp_ipv4.c +++ b/kernel/net/ipv4/tcp_ipv4.c @@ -62,6 +62,7 @@ #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/locallock.h> #include <net/net_namespace.h> #include <net/icmp.h> @@ -320,8 +321,6 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort) /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ - WARN_ON(req->sk); - if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); } else if (abort) { @@ -568,6 +567,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_v4_send_check); +static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); /* * This routine will send an RST to the other tcp. * @@ -689,10 +689,13 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.bound_dev_if = sk->sk_bound_dev_if; arg.tos = ip_hdr(skb)->tos; + + local_lock(tcp_sk_lock); ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + local_unlock(tcp_sk_lock); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); @@ -774,10 +777,12 @@ static void tcp_v4_send_ack(struct net *net, if (oif) arg.bound_dev_if = oif; arg.tos = tos; + local_lock(tcp_sk_lock); ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + local_unlock(tcp_sk_lock); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); } @@ -810,8 +815,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v4_send_ack(sock_net(sk), skb, seq, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, 0, @@ -1529,6 +1540,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_prequeue); +int tcp_filter(struct sock *sk, struct sk_buff *skb) +{ + struct tcphdr *th = (struct tcphdr *)skb->data; + unsigned int eaten = skb->len; + int err; + + err = sk_filter_trim_cap(sk, skb, th->doff * 4); + if (!err) { + eaten -= skb->len; + TCP_SKB_CB(skb)->end_seq -= eaten; + } + return err; +} +EXPORT_SYMBOL(tcp_filter); + /* * From tcp_input.c */ @@ -1634,8 +1660,10 @@ process: nf_reset(skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); skb->dev = NULL; diff --git a/kernel/net/ipv4/tcp_metrics.c b/kernel/net/ipv4/tcp_metrics.c index c8cbc2b4b..a726d7853 100644 --- a/kernel/net/ipv4/tcp_metrics.c +++ b/kernel/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/kernel/net/ipv4/tcp_minisocks.c b/kernel/net/ipv4/tcp_minisocks.c index ac6b1961f..9475a2748 100644 --- a/kernel/net/ipv4/tcp_minisocks.c +++ b/kernel/net/ipv4/tcp_minisocks.c @@ -458,7 +458,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -818,6 +818,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/kernel/net/ipv4/tcp_output.c b/kernel/net/ipv4/tcp_output.c index 9bfc39ff2..de95714d0 100644 --- a/kernel/net/ipv4/tcp_output.c +++ b/kernel/net/ipv4/tcp_output.c @@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss, /* Set window scaling on max possible window * See RFC1323 for an explanation of the limit to 14 */ - space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max); + space = max_t(u32, space, sysctl_tcp_rmem[2]); + space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > 65535 && (*rcv_wscale) < 14) { space >>= 1; @@ -1949,12 +1950,14 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - if (nskb->ip_summed) + if (nskb->ip_summed) { skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); - else - nskb->csum = skb_copy_and_csum_bits(skb, 0, - skb_put(nskb, copy), - copy, nskb->csum); + } else { + __wsum csum = skb_copy_and_csum_bits(skb, 0, + skb_put(nskb, copy), + copy, 0); + nskb->csum = csum_block_add(nskb->csum, csum, len); + } if (skb->len <= copy) { /* We've eaten all the data from this skb. @@ -2380,9 +2383,11 @@ u32 __tcp_select_window(struct sock *sk) int full_space = min_t(int, tp->window_clamp, allowed_space); int window; - if (mss > full_space) + if (unlikely(mss > full_space)) { mss = full_space; - + if (mss <= 0) + return 0; + } if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; @@ -2568,7 +2573,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) * copying overhead: fragmentation, tunneling, mangling etc. */ if (atomic_read(&sk->sk_wmem_alloc) > - min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) + min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), + sk->sk_sndbuf)) return -EAGAIN; if (skb_still_in_host_queue(sk, skb)) @@ -2625,8 +2631,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { - struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, - GFP_ATOMIC); + struct sk_buff *nskb; + + skb_mstamp_get(&skb->skb_mstamp); + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; } else { diff --git a/kernel/net/ipv4/tcp_yeah.c b/kernel/net/ipv4/tcp_yeah.c index 3e6a472e6..92ab5bc91 100644 --- a/kernel/net/ipv4/tcp_yeah.c +++ b/kernel/net/ipv4/tcp_yeah.c @@ -75,7 +75,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else if (!yeah->doing_reno_now) { diff --git a/kernel/net/ipv4/udp.c b/kernel/net/ipv4/udp.c index 7f8ab46ad..e9513e397 100644 --- a/kernel/net/ipv4/udp.c +++ b/kernel/net/ipv4/udp.c @@ -1275,6 +1275,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); + bool checksum_valid = false; bool slow; if (flags & MSG_ERRQUEUE) @@ -1300,11 +1301,12 @@ try_again: */ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + checksum_valid = !udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) + if (checksum_valid || skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), msg, copied); else { @@ -1340,7 +1342,7 @@ try_again: *addr_len = sizeof(*sin); } if (inet->cmsg_flags) - ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr)); + ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off); err = copied; if (flags & MSG_TRUNC) @@ -1531,7 +1533,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* if we're overly short, let UDP handle it */ encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv) { + if (encap_rcv) { int ret; /* Verify checksum before giving to encap */ @@ -1990,10 +1992,14 @@ void udp_v4_early_demux(struct sk_buff *skb) if (!in_dev) return; - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; + /* we are supposed to accept bcast packets */ + if (skb->pkt_type == PACKET_MULTICAST) { + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; + } + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); } else if (skb->pkt_type == PACKET_HOST) { diff --git a/kernel/net/ipv4/udp_offload.c b/kernel/net/ipv4/udp_offload.c index f9386160c..6396f1c80 100644 --- a/kernel/net/ipv4/udp_offload.c +++ b/kernel/net/ipv4/udp_offload.c @@ -299,14 +299,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - if (NAPI_GRO_CB(skb)->udp_mark || + if (NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; - /* mark that this skb passed once through the udp gro layer */ - NAPI_GRO_CB(skb)->udp_mark = 1; + /* mark that this skb passed once through the tunnel gro layer */ + NAPI_GRO_CB(skb)->encap_mark = 1; rcu_read_lock(); uo_priv = rcu_dereference(udp_offload_base); @@ -339,8 +339,8 @@ unflush: skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - pp = uo_priv->offload->callbacks.gro_receive(head, skb, - uo_priv->offload); + pp = call_gro_receive_udp(uo_priv->offload->callbacks.gro_receive, + head, skb, uo_priv->offload); out_unlock: rcu_read_unlock(); diff --git a/kernel/net/ipv4/udp_tunnel.c b/kernel/net/ipv4/udp_tunnel.c index aba428626..280a9bded 100644 --- a/kernel/net/ipv4/udp_tunnel.c +++ b/kernel/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, |