summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/fib_trie.c4
-rw-r--r--net/ipv4/ip_gre.c4
-rw-r--r--net/ipv4/ipconfig.c57
-rw-r--r--net/ipv4/ipmr.c14
-rw-r--r--net/ipv4/route.c54
-rw-r--r--net/ipv4/tcp.c66
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c13
-rw-r--r--net/ipv4/tcp_timer.c2
10 files changed, 153 insertions, 66 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 51ca946e339..3feb2b39030 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1194,7 +1194,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
if (idx < s_idx)
goto cont;
- if (idx > s_idx)
+ if (h > s_h || idx > s_idx)
s_ip_idx = 0;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index af5d8979286..01ef8ba9025 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -961,7 +961,9 @@ fib_find_node(struct trie *t, u32 key)
struct node *n;
pos = 0;
- n = rcu_dereference(t->trie);
+ n = rcu_dereference_check(t->trie,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
while (n != NULL && NODE_TYPE(n) == T_TNODE) {
tn = (struct tnode *) n;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f47c9f76754..f78402d097b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -810,11 +810,13 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
tunnel->err_count = 0;
}
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen;
+ max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->u.dst.header_len;
if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+ if (max_headroom > dev->needed_headroom)
+ dev->needed_headroom = max_headroom;
if (!new_skb) {
ip_rt_put(rt);
txq->tx_dropped++;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 10a6a604bf3..67890928164 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -187,6 +187,16 @@ struct ic_device {
static struct ic_device *ic_first_dev __initdata = NULL;/* List of open device */
static struct net_device *ic_dev __initdata = NULL; /* Selected device */
+static bool __init ic_device_match(struct net_device *dev)
+{
+ if (user_dev_name[0] ? !strcmp(dev->name, user_dev_name) :
+ (!(dev->flags & IFF_LOOPBACK) &&
+ (dev->flags & (IFF_POINTOPOINT|IFF_BROADCAST)) &&
+ strncmp(dev->name, "dummy", 5)))
+ return true;
+ return false;
+}
+
static int __init ic_open_devs(void)
{
struct ic_device *d, **last;
@@ -207,10 +217,7 @@ static int __init ic_open_devs(void)
for_each_netdev(&init_net, dev) {
if (dev->flags & IFF_LOOPBACK)
continue;
- if (user_dev_name[0] ? !strcmp(dev->name, user_dev_name) :
- (!(dev->flags & IFF_LOOPBACK) &&
- (dev->flags & (IFF_POINTOPOINT|IFF_BROADCAST)) &&
- strncmp(dev->name, "dummy", 5))) {
+ if (ic_device_match(dev)) {
int able = 0;
if (dev->mtu >= 364)
able |= IC_BOOTP;
@@ -228,7 +235,7 @@ static int __init ic_open_devs(void)
}
if (!(d = kmalloc(sizeof(struct ic_device), GFP_KERNEL))) {
rtnl_unlock();
- return -1;
+ return -ENOMEM;
}
d->dev = dev;
*last = d;
@@ -253,7 +260,7 @@ static int __init ic_open_devs(void)
printk(KERN_ERR "IP-Config: Device `%s' not found.\n", user_dev_name);
else
printk(KERN_ERR "IP-Config: No network devices available.\n");
- return -1;
+ return -ENODEV;
}
return 0;
}
@@ -1303,6 +1310,32 @@ __be32 __init root_nfs_parse_addr(char *name)
return addr;
}
+#define DEVICE_WAIT_MAX 12 /* 12 seconds */
+
+static int __init wait_for_devices(void)
+{
+ int i;
+
+ msleep(CONF_PRE_OPEN);
+ for (i = 0; i < DEVICE_WAIT_MAX; i++) {
+ struct net_device *dev;
+ int found = 0;
+
+ rtnl_lock();
+ for_each_netdev(&init_net, dev) {
+ if (ic_device_match(dev)) {
+ found = 1;
+ break;
+ }
+ }
+ rtnl_unlock();
+ if (found)
+ return 0;
+ ssleep(1);
+ }
+ return -ENODEV;
+}
+
/*
* IP Autoconfig dispatcher.
*/
@@ -1313,6 +1346,7 @@ static int __init ip_auto_config(void)
#ifdef IPCONFIG_DYNAMIC
int retries = CONF_OPEN_RETRIES;
#endif
+ int err;
#ifdef CONFIG_PROC_FS
proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops);
@@ -1325,12 +1359,15 @@ static int __init ip_auto_config(void)
#ifdef IPCONFIG_DYNAMIC
try_try_again:
#endif
- /* Give hardware a chance to settle */
- msleep(CONF_PRE_OPEN);
+ /* Wait for devices to appear */
+ err = wait_for_devices();
+ if (err)
+ return err;
/* Setup all network devices */
- if (ic_open_devs() < 0)
- return -1;
+ err = ic_open_devs();
+ if (err)
+ return err;
/* Give drivers a chance to settle */
ssleep(CONF_POST_OPEN);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8582e12e4a6..d0a6092a67b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -802,6 +802,9 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
int line;
struct mfc_cache *uc, *c, **cp;
+ if (mfc->mfcc_parent >= MAXVIFS)
+ return -ENFILE;
+
line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
for (cp = &net->ipv4.mfc_cache_array[line];
@@ -1613,17 +1616,20 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
int ct;
struct rtnexthop *nhp;
struct net *net = mfc_net(c);
- struct net_device *dev = net->ipv4.vif_table[c->mfc_parent].dev;
u8 *b = skb_tail_pointer(skb);
struct rtattr *mp_head;
- if (dev)
- RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex);
+ /* If cache is unresolved, don't try to parse IIF and OIF */
+ if (c->mfc_parent > MAXVIFS)
+ return -ENOENT;
+
+ if (VIF_EXISTS(net, c->mfc_parent))
+ RTA_PUT(skb, RTA_IIF, 4, &net->ipv4.vif_table[c->mfc_parent].dev->ifindex);
mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
- if (c->mfc_un.res.ttls[ct] < 255) {
+ if (VIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) {
if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
goto rtattr_failure;
nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d9b40248b97..d413b57be9b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -932,10 +932,8 @@ static void rt_secret_rebuild_oneshot(struct net *net)
{
del_timer_sync(&net->ipv4.rt_secret_timer);
rt_cache_invalidate(net);
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ if (ip_rt_secret_interval)
+ mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
}
static void rt_emergency_hash_rebuild(struct net *net)
@@ -1099,7 +1097,7 @@ static int slow_chain_length(const struct rtable *head)
}
static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb)
+ struct rtable **rp, struct sk_buff *skb, int ifindex)
{
struct rtable *rth, **rthp;
unsigned long now;
@@ -1214,11 +1212,16 @@ restart:
slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
struct net *net = dev_net(rt->u.dst.dev);
int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(dev_net(rt->u.dst.dev))) {
+ if (!rt_caching(net)) {
printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
rt->u.dst.dev->name, num);
}
- rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev));
+ rt_emergency_hash_rebuild(net);
+ spin_unlock_bh(rt_hash_lock_addr(hash));
+
+ hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+ ifindex, rt_genid(net));
+ goto restart;
}
}
@@ -1443,7 +1446,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
dev_hold(rt->u.dst.dev);
if (rt->idev)
in_dev_hold(rt->idev);
- rt->u.dst.obsolete = 0;
+ rt->u.dst.obsolete = -1;
rt->u.dst.lastuse = jiffies;
rt->u.dst.path = &rt->u.dst;
rt->u.dst.neighbour = NULL;
@@ -1479,7 +1482,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
&netevent);
rt_del(hash, rth);
- if (!rt_intern_hash(hash, rt, &rt, NULL))
+ if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))
ip_rt_put(rt);
goto do_next;
}
@@ -1508,11 +1511,12 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
struct dst_entry *ret = dst;
if (rt) {
- if (dst->obsolete) {
+ if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- rt->u.dst.expires) {
+ (rt->u.dst.expires &&
+ time_after_eq(jiffies, rt->u.dst.expires))) {
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
rt->fl.oif,
rt_genid(dev_net(dst->dev)));
@@ -1728,7 +1732,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
- return NULL;
+ if (rt_is_expired((struct rtable *)dst))
+ return NULL;
+ return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1890,7 +1896,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.output = ip_rt_bug;
+ rth->u.dst.obsolete = -1;
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
@@ -1929,7 +1936,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
in_dev_put(in_dev);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, NULL, skb);
+ return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
e_nobufs:
in_dev_put(in_dev);
@@ -2056,6 +2063,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->fl.oif = 0;
rth->rt_spec_dst= spec_dst;
+ rth->u.dst.obsolete = -1;
rth->u.dst.input = ip_forward;
rth->u.dst.output = ip_output;
rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
@@ -2095,7 +2103,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
rt_genid(dev_net(rth->u.dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb);
+ return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
}
/*
@@ -2220,6 +2228,7 @@ local_input:
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(net);
atomic_set(&rth->u.dst.__refcnt, 1);
@@ -2251,7 +2260,7 @@ local_input:
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, NULL, skb);
+ err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
goto done;
no_route:
@@ -2446,6 +2455,7 @@ static int __mkroute_output(struct rtable **result,
rth->rt_spec_dst= fl->fl4_src;
rth->u.dst.output=ip_output;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2497,7 +2507,7 @@ static int ip_mkroute_output(struct rtable **rp,
if (err == 0) {
hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
rt_genid(dev_net(dev_out)));
- err = rt_intern_hash(hash, rth, rp, NULL);
+ err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
}
return err;
@@ -3103,22 +3113,20 @@ static void rt_secret_reschedule(int old)
rtnl_lock();
for_each_net(net) {
int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
+ long time;
if (!new)
continue;
if (deleted) {
- long time = net->ipv4.rt_secret_timer.expires - jiffies;
+ time = net->ipv4.rt_secret_timer.expires - jiffies;
if (time <= 0 || (time += diff) <= 0)
time = 0;
-
- net->ipv4.rt_secret_timer.expires = time;
} else
- net->ipv4.rt_secret_timer.expires = new;
+ time = new;
- net->ipv4.rt_secret_timer.expires += jiffies;
- add_timer(&net->ipv4.rt_secret_timer);
+ mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
}
rtnl_unlock();
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5901010fad5..2c75f891914 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -429,7 +429,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (tp->urg_seq == tp->copied_seq &&
!sock_flag(sk, SOCK_URGINLINE) &&
tp->urg_data)
- target--;
+ target++;
/* Potential race condition. If read of tp below will
* escape above sk->sk_state, we can be illegally awaken
@@ -1254,6 +1254,39 @@ static void tcp_prequeue_process(struct sock *sk)
tp->ucopy.memory = 0;
}
+#ifdef CONFIG_NET_DMA
+static void tcp_service_net_dma(struct sock *sk, bool wait)
+{
+ dma_cookie_t done, used;
+ dma_cookie_t last_issued;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tp->ucopy.dma_chan)
+ return;
+
+ last_issued = tp->ucopy.dma_cookie;
+ dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+
+ do {
+ if (dma_async_memcpy_complete(tp->ucopy.dma_chan,
+ last_issued, &done,
+ &used) == DMA_SUCCESS) {
+ /* Safe to free early-copied skbs now */
+ __skb_queue_purge(&sk->sk_async_wait_queue);
+ break;
+ } else {
+ struct sk_buff *skb;
+ while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
+ (dma_async_is_complete(skb->dma_cookie, done,
+ used) == DMA_SUCCESS)) {
+ __skb_dequeue(&sk->sk_async_wait_queue);
+ kfree_skb(skb);
+ }
+ }
+ } while (wait);
+}
+#endif
+
static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
struct sk_buff *skb;
@@ -1335,6 +1368,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_eat_skb(sk, skb, 0);
if (!desc->count)
break;
+ tp->copied_seq = seq;
}
tp->copied_seq = seq;
@@ -1546,6 +1580,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/* __ Set realtime policy in scheduler __ */
}
+#ifdef CONFIG_NET_DMA
+ if (tp->ucopy.dma_chan)
+ dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+#endif
if (copied >= target) {
/* Do not sleep, just process backlog. */
release_sock(sk);
@@ -1554,6 +1592,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sk_wait_data(sk, &timeo);
#ifdef CONFIG_NET_DMA
+ tcp_service_net_dma(sk, false); /* Don't block */
tp->ucopy.wakeup = 0;
#endif
@@ -1633,6 +1672,9 @@ do_prequeue:
copied = -EFAULT;
break;
}
+
+ dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+
if ((offset + used) == skb->len)
copied_early = 1;
@@ -1702,27 +1744,9 @@ skip_copy:
}
#ifdef CONFIG_NET_DMA
- if (tp->ucopy.dma_chan) {
- dma_cookie_t done, used;
-
- dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
-
- while (dma_async_memcpy_complete(tp->ucopy.dma_chan,
- tp->ucopy.dma_cookie, &done,
- &used) == DMA_IN_PROGRESS) {
- /* do partial cleanup of sk_async_wait_queue */
- while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
- (dma_async_is_complete(skb->dma_cookie, done,
- used) == DMA_SUCCESS)) {
- __skb_dequeue(&sk->sk_async_wait_queue);
- kfree_skb(skb);
- }
- }
+ tcp_service_net_dma(sk, true); /* Wait for queue to drain */
+ tp->ucopy.dma_chan = NULL;
- /* Safe to free early-copied skbs now */
- __skb_queue_purge(&sk->sk_async_wait_queue);
- tp->ucopy.dma_chan = NULL;
- }
if (tp->ucopy.pinned_list) {
dma_unpin_iovec_pages(tp->ucopy.pinned_list);
tp->ucopy.pinned_list = NULL;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 788851ca8c5..c096a4218b8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2511,6 +2511,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
int err;
unsigned int mss;
+ if (packets == 0)
+ return;
+
WARN_ON(packets > tp->packets_out);
if (tp->lost_skb_hint) {
skb = tp->lost_skb_hint;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8d51d39ad1b..f4df5f931f3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -370,6 +370,11 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
if (sk->sk_state == TCP_CLOSE)
goto out;
+ if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+ goto out;
+ }
+
icsk = inet_csk(sk);
tp = tcp_sk(sk);
seq = ntohl(th->seq);
@@ -1651,15 +1656,15 @@ int tcp_v4_rcv(struct sk_buff *skb)
if (!sk)
goto no_tcp_socket;
+process:
+ if (sk->sk_state == TCP_TIME_WAIT)
+ goto do_time_wait;
+
if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
goto discard_and_relse;
}
-process:
- if (sk->sk_state == TCP_TIME_WAIT)
- goto do_time_wait;
-
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
nf_reset(skb);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index a17629b8912..b2e6bbccaee 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -134,7 +134,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
}
/* This function calculates a "timeout" which is equivalent to the timeout of a
- * TCP connection after "boundary" unsucessful, exponentially backed-off
+ * TCP connection after "boundary" unsuccessful, exponentially backed-off
* retransmissions with an initial RTO of TCP_RTO_MIN.
*/
static bool retransmits_timed_out(struct sock *sk,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-28 04:40:18 +0000