summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorTakashi Iwai <tiwai@suse.de>2016-12-13 00:05:20 +0300
committerTakashi Iwai <tiwai@suse.de>2016-12-13 00:05:20 +0300
commit152fce5a2371f64c57abf99dbb0600cc18d399d4 (patch)
treef3b4b8c2cf88cbd5a4a880f8c74b5d23f3f24982 /net/ipv4
parentd71bb23a81f80eeb5291e5c782377024e7265a23 (diff)
parenta5de5b74a50113564a1e0850e2da96c37c35e55d (diff)
downloadlinux-152fce5a2371f64c57abf99dbb0600cc18d399d4.tar.xz
Merge tag 'asoc-v4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus
ASoC: Updates for v4.10 There's been a few bits of framework work this time around and quite a lot of cleanups and improvements to existing code: - Support for stereo DAPM controls from Chen-yu Tsai. - Some initial work on the of-graph sound card from Morimoto-san, the main bulk of this is currently in binding review. - Lots of Renesas cleanups from Morimoto-san and sunxi work from Chen-yu Tsai. - regmap conversions of the remaining AC'97 drivers from Lars-Peter Clausen. - A new version of the topology ABI from Mengdong Lin. - New drivers for Cirrus Logic CS42L42, Qualcomm MSM8916-WCD, and Realtek RT5665.
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig1
-rw-r--r--net/ipv4/af_inet.c11
-rw-r--r--net/ipv4/esp4.c2
-rw-r--r--net/ipv4/fib_frontend.c20
-rw-r--r--net/ipv4/fib_trie.c158
-rw-r--r--net/ipv4/icmp.c4
-rw-r--r--net/ipv4/igmp.c50
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_output.c27
-rw-r--r--net/ipv4/ip_tunnel_core.c11
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/netfilter.c5
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/nft_dup_ipv4.c6
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_cong.c4
-rw-r--r--net/ipv4/tcp_dctcp.c13
-rw-r--r--net/ipv4/tcp_input.c22
-rw-r--r--net/ipv4/tcp_ipv4.c19
-rw-r--r--net/ipv4/udp.c8
-rw-r--r--net/ipv4/udp_impl.h2
-rw-r--r--net/ipv4/udplite.c2
24 files changed, 270 insertions, 115 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 300b06888fdf..b54b3ca939db 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -715,6 +715,7 @@ config DEFAULT_TCP_CONG
default "reno" if DEFAULT_RENO
default "dctcp" if DEFAULT_DCTCP
default "cdg" if DEFAULT_CDG
+ default "bbr" if DEFAULT_BBR
default "cubic"
config TCP_MD5SIG
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9648c97e541f..215143246e4b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect);
static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
/* Basic assumption: if someone sets sk->sk_err, he _must_
@@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
*/
while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
return timeo;
}
@@ -1234,7 +1233,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
/* fixed ID is invalid if DF bit is not set */
- if (fixedid && !(iph->frag_off & htons(IP_DF)))
+ if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF)))
goto out;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index d95631d09248..20fb25e3027b 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -476,7 +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/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c3b80478226e..161fc0f0d752 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old,
int fib_unmerge(struct net *net)
{
- struct fib_table *old, *new;
+ struct fib_table *old, *new, *main_table;
/* attempt to fetch local table if it has been allocated */
old = fib_get_table(net, RT_TABLE_LOCAL);
@@ -162,11 +162,21 @@ int fib_unmerge(struct net *net)
if (!new)
return -ENOMEM;
+ /* table is already unmerged */
+ if (new == old)
+ return 0;
+
/* replace merged table with clean table */
- if (new != old) {
- fib_replace_table(net, old, new);
- fib_free_table(old);
- }
+ fib_replace_table(net, old, new);
+ fib_free_table(old);
+
+ /* attempt to fetch main table if it has been allocated */
+ main_table = fib_get_table(net, RT_TABLE_MAIN);
+ if (!main_table)
+ return 0;
+
+ /* flush local entries from main table */
+ fib_table_flush_external(main_table);
return 0;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31cef3602585..e3665bf7a7f3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -719,6 +719,13 @@ static unsigned char update_suffix(struct key_vector *tn)
{
unsigned char slen = tn->pos;
unsigned long stride, i;
+ unsigned char slen_max;
+
+ /* only vector 0 can have a suffix length greater than or equal to
+ * tn->pos + tn->bits, the second highest node will have a suffix
+ * length at most of tn->pos + tn->bits - 1
+ */
+ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen);
/* search though the list of children looking for nodes that might
* have a suffix greater than the one we currently have. This is
@@ -736,12 +743,8 @@ static unsigned char update_suffix(struct key_vector *tn)
slen = n->slen;
i &= ~(stride - 1);
- /* if slen covers all but the last bit we can stop here
- * there will be nothing longer than that since only node
- * 0 and 1 << (bits - 1) could have that as their suffix
- * length.
- */
- if ((slen + 1) >= (tn->pos + tn->bits))
+ /* stop searching if we have hit the maximum possible value */
+ if (slen >= slen_max)
break;
}
@@ -913,39 +916,27 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn)
return collapse(t, tn);
/* update parent in case halve failed */
- tp = node_parent(tn);
-
- /* Return if at least one deflate was run */
- if (max_work != MAX_WORK)
- return tp;
-
- /* push the suffix length to the parent node */
- if (tn->slen > tn->pos) {
- unsigned char slen = update_suffix(tn);
-
- if (slen > tp->slen)
- tp->slen = slen;
- }
-
- return tp;
+ return node_parent(tn);
}
-static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l)
+static void node_pull_suffix(struct key_vector *tn, unsigned char slen)
{
- while ((tp->slen > tp->pos) && (tp->slen > l->slen)) {
- if (update_suffix(tp) > l->slen)
+ unsigned char node_slen = tn->slen;
+
+ while ((node_slen > tn->pos) && (node_slen > slen)) {
+ slen = update_suffix(tn);
+ if (node_slen == slen)
break;
- tp = node_parent(tp);
+
+ tn = node_parent(tn);
+ node_slen = tn->slen;
}
}
-static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l)
+static void node_push_suffix(struct key_vector *tn, unsigned char slen)
{
- /* if this is a new leaf then tn will be NULL and we can sort
- * out parent suffix lengths as a part of trie_rebalance
- */
- while (tn->slen < l->slen) {
- tn->slen = l->slen;
+ while (tn->slen < slen) {
+ tn->slen = slen;
tn = node_parent(tn);
}
}
@@ -1066,6 +1057,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp,
}
/* Case 3: n is NULL, and will just insert a new leaf */
+ node_push_suffix(tp, new->fa_slen);
NODE_INIT_PARENT(l, tp);
put_child_root(tp, key, l);
trie_rebalance(t, tp);
@@ -1107,7 +1099,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
/* if we added to the tail node then we need to update slen */
if (l->slen < new->fa_slen) {
l->slen = new->fa_slen;
- leaf_push_suffix(tp, l);
+ node_push_suffix(tp, new->fa_slen);
}
return 0;
@@ -1499,6 +1491,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
* out parent suffix lengths as a part of trie_rebalance
*/
if (hlist_empty(&l->leaf)) {
+ if (tp->slen == l->slen)
+ node_pull_suffix(tp, tp->pos);
put_child_root(tp, l->key, NULL);
node_free(l);
trie_rebalance(t, tp);
@@ -1511,7 +1505,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
/* update the trie with the latest suffix length */
l->slen = fa->fa_slen;
- leaf_pull_suffix(tp, l);
+ node_pull_suffix(tp, fa->fa_slen);
}
/* Caller must hold RTNL. */
@@ -1743,8 +1737,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
local_l = fib_find_node(lt, &local_tp, l->key);
if (fib_insert_alias(lt, local_tp, local_l, new_fa,
- NULL, l->key))
+ NULL, l->key)) {
+ kmem_cache_free(fn_alias_kmem, new_fa);
goto out;
+ }
}
/* stop loop if key wrapped back to 0 */
@@ -1760,6 +1756,75 @@ out:
return NULL;
}
+/* Caller must hold RTNL */
+void fib_table_flush_external(struct fib_table *tb)
+{
+ struct trie *t = (struct trie *)tb->tb_data;
+ struct key_vector *pn = t->kv;
+ unsigned long cindex = 1;
+ struct hlist_node *tmp;
+ struct fib_alias *fa;
+
+ /* walk trie in reverse order */
+ for (;;) {
+ unsigned char slen = 0;
+ struct key_vector *n;
+
+ if (!(cindex--)) {
+ t_key pkey = pn->key;
+
+ /* cannot resize the trie vector */
+ if (IS_TRIE(pn))
+ break;
+
+ /* update the suffix to address pulled leaves */
+ if (pn->slen > pn->pos)
+ update_suffix(pn);
+
+ /* resize completed node */
+ pn = resize(t, pn);
+ cindex = get_index(pkey, pn);
+
+ continue;
+ }
+
+ /* grab the next available node */
+ n = get_child(pn, cindex);
+ if (!n)
+ continue;
+
+ if (IS_TNODE(n)) {
+ /* record pn and cindex for leaf walking */
+ pn = n;
+ cindex = 1ul << n->bits;
+
+ continue;
+ }
+
+ hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
+ /* if alias was cloned to local then we just
+ * need to remove the local copy from main
+ */
+ if (tb->tb_id != fa->tb_id) {
+ hlist_del_rcu(&fa->fa_list);
+ alias_free_mem_rcu(fa);
+ continue;
+ }
+
+ /* record local slen */
+ slen = fa->fa_slen;
+ }
+
+ /* update leaf slen */
+ n->slen = slen;
+
+ if (hlist_empty(&n->leaf)) {
+ put_child_root(pn, n->key, NULL);
+ node_free(n);
+ }
+ }
+}
+
/* Caller must hold RTNL. */
int fib_table_flush(struct net *net, struct fib_table *tb)
{
@@ -1782,6 +1847,10 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
if (IS_TRIE(pn))
break;
+ /* update the suffix to address pulled leaves */
+ if (pn->slen > pn->pos)
+ update_suffix(pn);
+
/* resize completed node */
pn = resize(t, pn);
cindex = get_index(pkey, pn);
@@ -2413,22 +2482,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
struct key_vector *l, **tp = &iter->tnode;
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 {
- 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 */
@@ -2437,7 +2503,7 @@ 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 */
@@ -2465,7 +2531,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
return fib_route_get_idx(iter, *pos);
iter->pos = 0;
- iter->key = 0;
+ iter->key = KEY_MAX;
return SEQ_START_TOKEN;
}
@@ -2474,7 +2540,7 @@ 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;
@@ -2483,7 +2549,7 @@ 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/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70e595f..48734ee6293f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
- fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+ fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
rt = __ip_route_output_key_hash(net, fl4,
@@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- if (inet_addr_type_dev_table(net, skb_in->dev,
+ if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
fl4_dec.saddr) == RTN_LOCAL) {
rt2 = __ip_route_output_key(net, &fl4_dec);
if (IS_ERR(rt2))
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 606cc3e85d2b..15db786d50ed 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -162,7 +162,7 @@ static int unsolicited_report_interval(struct in_device *in_dev)
}
static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im);
-static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr);
+static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im);
static void igmpv3_clear_delrec(struct in_device *in_dev);
static int sf_setstate(struct ip_mc_list *pmc);
static void sf_markstate(struct ip_mc_list *pmc);
@@ -1130,10 +1130,15 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
spin_unlock_bh(&in_dev->mc_tomb_lock);
}
-static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
+/*
+ * restore ip_mc_list deleted records
+ */
+static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
{
struct ip_mc_list *pmc, *pmc_prev;
- struct ip_sf_list *psf, *psf_next;
+ struct ip_sf_list *psf;
+ struct net *net = dev_net(in_dev->dev);
+ __be32 multiaddr = im->multiaddr;
spin_lock_bh(&in_dev->mc_tomb_lock);
pmc_prev = NULL;
@@ -1149,16 +1154,26 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
in_dev->mc_tomb = pmc->next;
}
spin_unlock_bh(&in_dev->mc_tomb_lock);
+
+ spin_lock_bh(&im->lock);
if (pmc) {
- for (psf = pmc->tomb; psf; psf = psf_next) {
- psf_next = psf->sf_next;
- kfree(psf);
+ im->interface = pmc->interface;
+ im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ im->sfmode = pmc->sfmode;
+ if (pmc->sfmode == MCAST_INCLUDE) {
+ im->tomb = pmc->tomb;
+ im->sources = pmc->sources;
+ for (psf = im->sources; psf; psf = psf->sf_next)
+ psf->sf_crcount = im->crcount;
}
in_dev_put(pmc->interface);
- kfree(pmc);
}
+ spin_unlock_bh(&im->lock);
}
+/*
+ * flush ip_mc_list deleted records
+ */
static void igmpv3_clear_delrec(struct in_device *in_dev)
{
struct ip_mc_list *pmc, *nextpmc;
@@ -1366,7 +1381,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
ip_mc_hash_add(in_dev, im);
#ifdef CONFIG_IP_MULTICAST
- igmpv3_del_delrec(in_dev, im->multiaddr);
+ igmpv3_del_delrec(in_dev, im);
#endif
igmp_group_added(im);
if (!in_dev->dead)
@@ -1626,8 +1641,12 @@ void ip_mc_remap(struct in_device *in_dev)
ASSERT_RTNL();
- for_each_pmc_rtnl(in_dev, pmc)
+ for_each_pmc_rtnl(in_dev, pmc) {
+#ifdef CONFIG_IP_MULTICAST
+ igmpv3_del_delrec(in_dev, pmc);
+#endif
igmp_group_added(pmc);
+ }
}
/* Device going down */
@@ -1648,7 +1667,6 @@ void ip_mc_down(struct in_device *in_dev)
in_dev->mr_gq_running = 0;
if (del_timer(&in_dev->mr_gq_timer))
__in_dev_put(in_dev);
- igmpv3_clear_delrec(in_dev);
#endif
ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS);
@@ -1688,8 +1706,12 @@ void ip_mc_up(struct in_device *in_dev)
#endif
ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
- for_each_pmc_rtnl(in_dev, pmc)
+ for_each_pmc_rtnl(in_dev, pmc) {
+#ifdef CONFIG_IP_MULTICAST
+ igmpv3_del_delrec(in_dev, pmc);
+#endif
igmp_group_added(pmc);
+ }
}
/*
@@ -1704,13 +1726,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev)
/* Deactivate timers */
ip_mc_down(in_dev);
+#ifdef CONFIG_IP_MULTICAST
+ igmpv3_clear_delrec(in_dev);
+#endif
while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) {
in_dev->mc_list = i->next_rcu;
in_dev->mc_count--;
-
- /* We've dropped the groups in ip_mc_down already */
- ip_mc_clear_src(i);
ip_ma_put(i);
}
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 8b4ffd216839..9f0a7b96646f 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
if (ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 03e7f7310423..877bdb02e887 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -107,6 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
if (unlikely(!skb))
return 0;
+ 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);
@@ -239,19 +241,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
struct sk_buff *segs;
int ret = 0;
- /* common case: fragmentation of segments is not allowed,
- * or seglen is <= mtu
+ /* common case: seglen is <= mtu
*/
- if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
- skb_gso_validate_mtu(skb, mtu))
+ if (skb_gso_validate_mtu(skb, mtu))
return ip_finish_output2(net, sk, skb);
- /* Slowpath - GSO segment length is exceeding the dst MTU.
+ /* Slowpath - GSO segment length exceeds the egress MTU.
*
- * This can happen in two cases:
- * 1) TCP GRO packet, DF bit not set
- * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
- * from host network stack.
+ * This can happen in several cases:
+ * - Forwarding of a TCP GRO skb, when DF flag is not set.
+ * - Forwarding of an skb that arrived on a virtualization interface
+ * (virtio-net/vhost/tap) with TSO/GSO size set by other network
+ * stack.
+ * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
+ * interface with a smaller MTU.
+ * - Arriving GRO skb (or GSO skb in a virtualized environment) that is
+ * bridged to a NETIF_F_TSO tunnel stacked over an interface with an
+ * insufficent MTU.
*/
features = netif_skb_features(skb);
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
@@ -1579,7 +1585,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
}
oif = arg->bound_dev_if;
- oif = oif ? : skb->skb_iif;
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
flowi4_init_output(&fl4, oif,
IP4_REPLY_MARK(net, skb->mark),
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 777bc1883870..fed3d29f9eb3 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
- int skb_iif = skb->skb_iif;
struct iphdr *iph;
int err;
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- if (skb_iif && !(df & htons(IP_DF))) {
- /* Arrived from an ingress interface, got encapsulated, with
- * fragmentation of encapulating frames allowed.
- * If skb is gso, the resulting encapsulated network segments
- * may exceed dst mtu.
- * Allow IP Fragmentation of segments.
- */
- IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
- }
-
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f006e13de56..27089f5ebbb1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
vif->dev->stats.tx_bytes += skb->len;
}
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
* not only before forwarding, but after forwarding on all output
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index c3776ff6749f..b3cc1335adbc 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+ struct net_device *dev = skb_dst(skb)->dev;
unsigned int hh_len;
if (addr_type == RTN_UNSPEC)
- addr_type = inet_addr_type(net, saddr);
+ addr_type = inet_addr_type_dev_table(net, dev, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
flags |= FLOWI_FLAG_ANYSRC;
else
@@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+ if (!fl4.flowi4_oif)
+ fl4.flowi4_oif = l3mdev_master_ifindex(dev);
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = flags;
rt = ip_route_output_key(net, &fl4);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b31df597fd37..697538464e6e 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo,
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];
+ newinfo->hook_entry[i] = compatr->hook_entry[i];
+ newinfo->underflow[i] = compatr->underflow[i];
}
entry1 = newinfo->entries;
pos = entry1;
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index bf855e64fc45..0c01a270bf9f 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -28,7 +28,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr,
struct in_addr gw = {
.s_addr = (__force __be32)regs->data[priv->sreg_addr],
};
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif);
}
@@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 205e2000d395..96b8e2b95731 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -657,6 +657,10 @@ 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/net/ipv4/route.c b/net/ipv4/route.c
index 62d4d90c1389..2a57566e6e91 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -753,7 +753,9 @@ 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);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3251fe71f39f..814af89c1bd3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1164,7 +1164,7 @@ restart:
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto out_err;
+ goto do_error;
sg = !!(sk->sk_route_caps & NETIF_F_SG);
@@ -1241,7 +1241,7 @@ 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/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 1294af4e0127..f9038d6b109e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -200,8 +200,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
icsk->icsk_ca_ops = ca;
icsk->icsk_ca_setsockopt = 1;
- if (sk->sk_state != TCP_CLOSE)
+ if (sk->sk_state != TCP_CLOSE) {
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
tcp_init_congestion_control(sk);
+ }
}
/* Manage refcounts on socket close. */
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 10d728b6804c..ab37c6775630 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/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/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a27b9c0e27c0..c71d49ce0c93 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -128,6 +128,23 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+{
+ static bool __once __read_mostly;
+
+ if (!__once) {
+ struct net_device *dev;
+
+ __once = true;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
+ pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+ dev ? dev->name : "Unknown driver");
+ rcu_read_unlock();
+ }
+}
+
/* Adapt the MSS value used to make delayed ack decision to the
* real world.
*/
@@ -144,7 +161,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
*/
len = skb_shinfo(skb)->gso_size ? : skb->len;
if (len >= icsk->icsk_ack.rcv_mss) {
- icsk->icsk_ack.rcv_mss = len;
+ icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
+ tcp_sk(sk)->advmss);
+ if (unlikely(icsk->icsk_ack.rcv_mss != len))
+ tcp_gro_dev_warn(sk, skb);
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 61b7be303eec..2259114c7242 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1564,6 +1564,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_add_backlog);
+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
*/
@@ -1676,8 +1691,10 @@ 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/net/ipv4/udp.c b/net/ipv4/udp.c
index d123d68f4d1d..5bab6c3f7a2f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1455,7 +1455,7 @@ static void udp_v4_rehash(struct sock *sk)
udp_lib_rehash(sk, new_hash);
}
-static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
@@ -1652,10 +1652,10 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
if (use_hash2) {
hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
- udp_table.mask;
- hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask;
+ udptable->mask;
+ hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
- hslot = &udp_table.hash2[hash2];
+ hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 7e0fe4bdd967..feb50a16398d 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -25,7 +25,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
int flags, int *addr_len);
int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
int flags);
-int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
void udp_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index af817158d830..ff450c2aad9b 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -50,7 +50,7 @@ struct proto udplite_prot = {
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
+ .backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,