summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/arp.c16
-rw-r--r--net/ipv4/datagram.c16
-rw-r--r--net/ipv4/devinet.c14
-rw-r--r--net/ipv4/fib_lookup.h1
-rw-r--r--net/ipv4/fib_semantics.c41
-rw-r--r--net/ipv4/fib_trie.c9
-rw-r--r--net/ipv4/igmp.c33
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/inet_fragment.c40
-rw-r--r--net/ipv4/inet_hashtables.c11
-rw-r--r--net/ipv4/ip_fragment.c18
-rw-r--r--net/ipv4/ip_tunnel.c8
-rw-r--r--net/ipv4/netfilter/arp_tables.c25
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c3
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c10
-rw-r--r--net/ipv4/tcp.c11
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/udp.c13
21 files changed, 166 insertions, 116 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 933a92820d26..6c8b1fbafce8 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1017,14 +1017,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
- read_lock_bh(&neigh->lock);
- memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
- r->arp_flags = arp_state_to_flags(neigh);
- read_unlock_bh(&neigh->lock);
- r->arp_ha.sa_family = dev->type;
- strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+ if (!(neigh->nud_state & NUD_NOARP)) {
+ read_lock_bh(&neigh->lock);
+ memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+ r->arp_flags = arp_state_to_flags(neigh);
+ read_unlock_bh(&neigh->lock);
+ r->arp_ha.sa_family = dev->type;
+ strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+ err = 0;
+ }
neigh_release(neigh);
- err = 0;
}
return err;
}
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 90c0e8386116..574fad9cca05 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
#include <net/route.h>
#include <net/tcp_states.h>
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_reset(sk);
- lock_sock(sk);
-
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_set(sk, &rt->dst);
err = 0;
out:
- release_sock(sk);
return err;
}
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip4_datagram_connect(sk, uaddr, addr_len);
+ release_sock(sk);
+ return res;
+}
EXPORT_SYMBOL(ip4_datagram_connect);
/* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 7498716e8f54..2d9cb1748f81 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
queue_delayed_work(system_power_efficient_wq,
&check_lifetime_work, 0);
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
- blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
}
return 0;
}
@@ -1740,6 +1739,8 @@ static int inet_netconf_msgsize_devconf(int type)
size += nla_total_size(4);
if (type == -1 || type == NETCONFA_PROXY_NEIGH)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
+ size += nla_total_size(4);
return size;
}
@@ -1780,6 +1781,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
+ nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
@@ -1819,6 +1824,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
[NETCONFA_FORWARDING] = { .len = sizeof(int) },
[NETCONFA_RP_FILTER] = { .len = sizeof(int) },
[NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) },
+ [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) },
};
static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -2048,6 +2054,12 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
ifindex, cnf);
}
+ if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
+ new_value != old_value) {
+ ifindex = devinet_conf_ifindex(net, cnf);
+ inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ ifindex, cnf);
+ }
}
return ret;
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed60b03..9c02920725db 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@ struct fib_alias {
u8 fa_state;
u8 fa_slen;
u32 tb_id;
+ s16 fa_default;
struct rcu_head rcu;
};
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c7358ea4ae93..3a06586b170c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1202,23 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
}
/* Must be invoked inside of an RCU protected region. */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
{
struct fib_info *fi = NULL, *last_resort = NULL;
struct hlist_head *fa_head = res->fa_head;
struct fib_table *tb = res->table;
+ u8 slen = 32 - res->prefixlen;
int order = -1, last_idx = -1;
- struct fib_alias *fa;
+ struct fib_alias *fa, *fa1 = NULL;
+ u32 last_prio = res->fi->fib_priority;
+ u8 last_tos = 0;
hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
+ if (fa->fa_slen != slen)
+ continue;
+ if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+ continue;
+ if (fa->tb_id != tb->tb_id)
+ continue;
+ if (next_fi->fib_priority > last_prio &&
+ fa->fa_tos == last_tos) {
+ if (last_tos)
+ continue;
+ break;
+ }
+ if (next_fi->fib_flags & RTNH_F_DEAD)
+ continue;
+ last_tos = fa->fa_tos;
+ last_prio = next_fi->fib_priority;
+
if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
-
- if (next_fi->fib_priority > res->fi->fib_priority)
- break;
if (!next_fi->fib_nh[0].nh_gw ||
next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
continue;
@@ -1228,10 +1245,11 @@ void fib_select_default(struct fib_result *res)
if (!fi) {
if (next_fi != res->fi)
break;
+ fa1 = fa;
} else if (!fib_detect_death(fi, order, &last_resort,
- &last_idx, tb->tb_default)) {
+ &last_idx, fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
fi = next_fi;
@@ -1239,20 +1257,21 @@ void fib_select_default(struct fib_result *res)
}
if (order <= 0 || !fi) {
- tb->tb_default = -1;
+ if (fa1)
+ fa1->fa_default = -1;
goto out;
}
if (!fib_detect_death(fi, order, &last_resort, &last_idx,
- tb->tb_default)) {
+ fa1->fa_default)) {
fib_result_assign(res, fi);
- tb->tb_default = order;
+ fa1->fa_default = order;
goto out;
}
if (last_idx >= 0)
fib_result_assign(res, last_resort);
- tb->tb_default = last_idx;
+ fa1->fa_default = last_idx;
out:
return;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d32612e3c6..b0c6258ffb79 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
err = switchdev_fib_ipv4_add(key, plen, fi,
new_fa->fa_tos,
@@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = 0;
new_fa->fa_slen = slen;
new_fa->tb_id = tb->tb_id;
+ new_fa->fa_default = -1;
/* (Optionally) offload fib entry to switch hardware. */
err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1791,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb)
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
}
@@ -1862,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb)
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
@@ -1990,7 +1988,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
return NULL;
tb->tb_id = id;
- tb->tb_default = -1;
tb->tb_num_default = 0;
tb->tb_data = (alias ? alias->__data : tb->__data);
@@ -2468,7 +2465,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
key = l->key + 1;
iter->pos++;
- if (pos-- <= 0)
+ if (--pos <= 0)
break;
l = NULL;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 651cdf648ec4..9fdfd9deac11 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1435,33 +1435,35 @@ static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
struct sk_buff *skb_chk;
unsigned int transport_len;
unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr);
- int ret;
+ int ret = -EINVAL;
transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb);
- skb_get(skb);
skb_chk = skb_checksum_trimmed(skb, transport_len,
ip_mc_validate_checksum);
if (!skb_chk)
- return -EINVAL;
+ goto err;
- if (!pskb_may_pull(skb_chk, len)) {
- kfree_skb(skb_chk);
- return -EINVAL;
- }
+ if (!pskb_may_pull(skb_chk, len))
+ goto err;
ret = ip_mc_check_igmp_msg(skb_chk);
- if (ret) {
- kfree_skb(skb_chk);
- return ret;
- }
+ if (ret)
+ goto err;
if (skb_trimmed)
*skb_trimmed = skb_chk;
- else
+ /* free now unneeded clone */
+ else if (skb_chk != skb)
kfree_skb(skb_chk);
- return 0;
+ ret = 0;
+
+err:
+ if (ret && skb_chk && skb_chk != skb)
+ kfree_skb(skb_chk);
+
+ return ret;
}
/**
@@ -1470,7 +1472,7 @@ static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
* @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional)
*
* Checks whether an IPv4 packet is a valid IGMP packet. If so sets
- * skb network and transport headers accordingly and returns zero.
+ * skb transport header accordingly and returns zero.
*
* -EINVAL: A broken packet was detected, i.e. it violates some internet
* standard
@@ -1485,7 +1487,8 @@ static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
* to leave the original skb and its full frame unchanged (which might be
* desirable for layer 2 frame jugglers).
*
- * The caller needs to release a reference count from any returned skb_trimmed.
+ * Caller needs to set the skb network header and free any returned skb if it
+ * differs from the provided skb.
*/
int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
{
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 60021d0d9326..134957159c27 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -593,7 +593,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue,
}
spin_unlock(&queue->syn_wait_lock);
- if (del_timer(&req->rsk_timer))
+ if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
reqsk_put(req);
return found;
}
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 9bc26677058e..c3b1f3a0f4cf 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -152,8 +152,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
inet6_sk(sk)->tclass) < 0)
goto errout;
- if (ipv6_only_sock(sk) &&
- nla_put_u8(skb, INET_DIAG_SKV6ONLY, 1))
+ if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
+ nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
goto errout;
}
#endif
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5e346a082e5f..d0a7c0319e3d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -131,34 +131,22 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
unsigned int evicted = 0;
HLIST_HEAD(expired);
-evict_again:
spin_lock(&hb->chain_lock);
hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
if (!inet_fragq_should_evict(fq))
continue;
- if (!del_timer(&fq->timer)) {
- /* q expiring right now thus increment its refcount so
- * it won't be freed under us and wait until the timer
- * has finished executing then destroy it
- */
- atomic_inc(&fq->refcnt);
- spin_unlock(&hb->chain_lock);
- del_timer_sync(&fq->timer);
- inet_frag_put(fq, f);
- goto evict_again;
- }
+ if (!del_timer(&fq->timer))
+ continue;
- fq->flags |= INET_FRAG_EVICTED;
- hlist_del(&fq->list);
- hlist_add_head(&fq->list, &expired);
+ hlist_add_head(&fq->list_evictor, &expired);
++evicted;
}
spin_unlock(&hb->chain_lock);
- hlist_for_each_entry_safe(fq, n, &expired, list)
+ hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
f->frag_expire((unsigned long) fq);
return evicted;
@@ -240,18 +228,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
int i;
nf->low_thresh = 0;
- local_bh_disable();
evict_again:
+ local_bh_disable();
seq = read_seqbegin(&f->rnd_seqlock);
for (i = 0; i < INETFRAGS_HASHSZ ; i++)
inet_evict_bucket(f, &f->hash[i]);
- if (read_seqretry(&f->rnd_seqlock, seq))
- goto evict_again;
-
local_bh_enable();
+ cond_resched();
+
+ if (read_seqretry(&f->rnd_seqlock, seq) ||
+ percpu_counter_sum(&nf->mem))
+ goto evict_again;
percpu_counter_destroy(&nf->mem);
}
@@ -284,8 +274,8 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
struct inet_frag_bucket *hb;
hb = get_frag_bucket_locked(fq, f);
- if (!(fq->flags & INET_FRAG_EVICTED))
- hlist_del(&fq->list);
+ hlist_del(&fq->list);
+ fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
@@ -297,7 +287,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
if (!(fq->flags & INET_FRAG_COMPLETE)) {
fq_unlink(fq, f);
atomic_dec(&fq->refcnt);
- fq->flags |= INET_FRAG_COMPLETE;
}
}
EXPORT_SYMBOL(inet_frag_kill);
@@ -330,11 +319,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
fp = xp;
}
sum = sum_truesize + f->qsize;
- sub_frag_mem_limit(q, sum);
if (f->destructor)
f->destructor(q);
kmem_cache_free(f->frags_cachep, q);
+
+ sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
@@ -390,7 +380,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
q->net = nf;
f->constructor(q, arg);
- add_frag_mem_limit(q, f->qsize);
+ add_frag_mem_limit(nf, f->qsize);
setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
spin_lock_init(&q->lock);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5f9b063bbe8a..0cb9165421d4 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -624,22 +624,21 @@ EXPORT_SYMBOL_GPL(inet_hashinfo_init);
int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
+ unsigned int locksz = sizeof(spinlock_t);
unsigned int i, nblocks = 1;
- if (sizeof(spinlock_t) != 0) {
+ if (locksz != 0) {
/* allocate 2 cache lines or at least one spinlock per cpu */
- nblocks = max_t(unsigned int,
- 2 * L1_CACHE_BYTES / sizeof(spinlock_t),
- 1);
+ nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
/* no more locks than number of hash buckets */
nblocks = min(nblocks, hashinfo->ehash_mask + 1);
- hashinfo->ehash_locks = kmalloc_array(nblocks, sizeof(spinlock_t),
+ hashinfo->ehash_locks = kmalloc_array(nblocks, locksz,
GFP_KERNEL | __GFP_NOWARN);
if (!hashinfo->ehash_locks)
- hashinfo->ehash_locks = vmalloc(nblocks * sizeof(spinlock_t));
+ hashinfo->ehash_locks = vmalloc(nblocks * locksz);
if (!hashinfo->ehash_locks)
return -ENOMEM;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a50dc6d408d1..921138f6c97c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg)
ipq_kill(qp);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
- if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+ if (!inet_frag_evicting(&qp->q)) {
struct sk_buff *head = qp->q.fragments;
const struct iphdr *iph;
int err;
@@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp)
kfree_skb(fp);
fp = xp;
} while (fp);
- sub_frag_mem_limit(&qp->q, sum_truesize);
+ sub_frag_mem_limit(qp->q.net, sum_truesize);
qp->q.flags = 0;
qp->q.len = 0;
@@ -351,7 +351,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
- end = offset + skb->len - ihl;
+ end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
@@ -381,7 +381,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
goto err;
err = -ENOMEM;
- if (!pskb_pull(skb, ihl))
+ if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
@@ -455,7 +455,7 @@ found:
qp->q.fragments = next;
qp->q.meat -= free_it->len;
- sub_frag_mem_limit(&qp->q, free_it->truesize);
+ sub_frag_mem_limit(qp->q.net, free_it->truesize);
kfree_skb(free_it);
}
}
@@ -479,7 +479,7 @@ found:
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
- add_frag_mem_limit(&qp->q, skb->truesize);
+ add_frag_mem_limit(qp->q.net, skb->truesize);
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
@@ -587,7 +587,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(&qp->q, clone->truesize);
+ add_frag_mem_limit(qp->q.net, clone->truesize);
}
skb_push(head, head->data - skb_network_header(head));
@@ -615,7 +615,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
}
fp = next;
}
- sub_frag_mem_limit(&qp->q, sum_truesize);
+ sub_frag_mem_limit(qp->q.net, sum_truesize);
head->next = NULL;
head->dev = dev;
@@ -641,6 +641,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
iph->frag_off = 0;
}
+ ip_send_check(iph);
+
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4c2c3ba4ba65..626d9e56a6bd 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -586,7 +586,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
EXPORT_SYMBOL(ip_tunnel_encap);
static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
- struct rtable *rt, __be16 df)
+ struct rtable *rt, __be16 df,
+ const struct iphdr *inner_iph)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -603,7 +604,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
- (df & htons(IP_DF)) && mtu < pkt_size) {
+ (inner_iph->frag_off & htons(IP_DF)) &&
+ mtu < pkt_size) {
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
return -E2BIG;
@@ -737,7 +739,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+ if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
ip_rt_put(rt);
goto tx_error;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 95c9b6eece25..92305a1a021a 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -254,9 +254,10 @@ unsigned int arpt_do_table(struct sk_buff *skb,
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
unsigned int verdict = NF_DROP;
const struct arphdr *arp;
- struct arpt_entry *e, *back;
+ struct arpt_entry *e, **jumpstack;
const char *indev, *outdev;
const void *table_base;
+ unsigned int cpu, stackidx = 0;
const struct xt_table_info *private;
struct xt_action_param acpar;
unsigned int addend;
@@ -270,15 +271,16 @@ unsigned int arpt_do_table(struct sk_buff *skb,
local_bh_disable();
addend = xt_write_recseq_begin();
private = table->private;
+ cpu = smp_processor_id();
/*
* Ensure we load private-> members after we've fetched the base
* pointer.
*/
smp_read_barrier_depends();
table_base = private->entries;
+ jumpstack = (struct arpt_entry **)private->jumpstack[cpu];
e = get_entry(table_base, private->hook_entry[hook]);
- back = get_entry(table_base, private->underflow[hook]);
acpar.in = state->in;
acpar.out = state->out;
@@ -312,18 +314,23 @@ unsigned int arpt_do_table(struct sk_buff *skb,
verdict = (unsigned int)(-v) - 1;
break;
}
- e = back;
- back = get_entry(table_base, back->comefrom);
+ if (stackidx == 0) {
+ e = get_entry(table_base,
+ private->underflow[hook]);
+ } else {
+ e = jumpstack[--stackidx];
+ e = arpt_next_entry(e);
+ }
continue;
}
if (table_base + v
!= arpt_next_entry(e)) {
- /* Save old back ptr in next entry */
- struct arpt_entry *next = arpt_next_entry(e);
- next->comefrom = (void *)back - table_base;
- /* set back pointer to next entry */
- back = next;
+ if (stackidx >= private->stacksize) {
+ verdict = NF_DROP;
+ break;
+ }
+ jumpstack[stackidx++] = e;
}
e = get_entry(table_base, v);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index fe8cc183411e..95ea633e8356 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -226,7 +226,8 @@ synproxy_send_client_ack(const struct synproxy_net *snet,
synproxy_build_options(nth, opts);
- synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
+ synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+ niph, nth, tcp_hdr_size);
}
static bool
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d0362a2de3d3..e681b852ced1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
res.type == RTN_UNICAST && !fl4->flowi4_oif)
- fib_select_default(&res);
+ fib_select_default(fl4, &res);
if (!fl4->saddr)
fl4->saddr = FIB_RES_PREFSRC(net, res);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 433231ccfb17..0330ab2e2b63 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -41,8 +41,6 @@ static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
-static int min_sndbuf = SOCK_MIN_SNDBUF;
-static int min_rcvbuf = SOCK_MIN_RCVBUF;
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
@@ -530,7 +528,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_tcp_wmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &min_sndbuf,
+ .extra1 = &one,
},
{
.procname = "tcp_notsent_lowat",
@@ -545,7 +543,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_tcp_rmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &min_rcvbuf,
+ .extra1 = &one,
},
{
.procname = "tcp_app_win",
@@ -758,7 +756,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_rmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &min_rcvbuf,
+ .extra1 = &one
},
{
.procname = "udp_wmem_min",
@@ -766,7 +764,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_wmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &min_sndbuf,
+ .extra1 = &one
},
{ }
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7f4056785acc..45534a5ab430 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
ret = -EAGAIN;
break;
}
- sk_wait_data(sk, &timeo);
+ sk_wait_data(sk, &timeo, NULL);
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
break;
@@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
int target; /* Read at least this many bytes */
long timeo;
struct task_struct *user_recv = NULL;
- struct sk_buff *skb;
+ struct sk_buff *skb, *last;
u32 urg_hole = 0;
if (unlikely(flags & MSG_ERRQUEUE))
@@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
/* Next get a buffer. */
+ last = skb_peek_tail(&sk->sk_receive_queue);
skb_queue_walk(&sk->sk_receive_queue, skb) {
+ last = skb;
/* Now that we have two receive queues this
* shouldn't happen.
*/
@@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
/* Do not sleep, just process backlog. */
release_sock(sk);
lock_sock(sk);
- } else
- sk_wait_data(sk, &timeo);
+ } else {
+ sk_wait_data(sk, &timeo, last);
+ }
if (user_recv) {
int chunk;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 684f095d196e..728f5b3d3c64 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1917,14 +1917,13 @@ void tcp_enter_loss(struct sock *sk)
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- bool new_recovery = false;
+ bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
bool is_reneg; /* is receiver reneging on SACKs? */
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
!after(tp->high_seq, tp->snd_una) ||
(icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
- new_recovery = true;
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tcp_ca_event(sk, CA_EVENT_LOSS);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d7d4c2b79cf2..0ea2e1c5d395 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- if (!nsk)
+ if (!nsk || nsk == sk)
reqsk_put(req);
return nsk;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 83aa604f9273..1b8c5ba7d5f7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1995,12 +1995,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_efree;
- dst = sk->sk_rx_dst;
+ dst = READ_ONCE(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
- if (dst)
- skb_dst_set_noref(skb, dst);
+ if (dst) {
+ /* DST_NOCACHE can not be used without taking a reference */
+ if (dst->flags & DST_NOCACHE) {
+ if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+ skb_dst_set(skb, dst);
+ } else {
+ skb_dst_set_noref(skb, dst);
+ }
+ }
}
int udp_rcv(struct sk_buff *skb)
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-20 16:53:13 +0300