summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inetpeer.c81
-rw-r--r--net/ipv4/ip_gre.c10
-rw-r--r--net/ipv4/ping.c1
-rw-r--r--net/ipv4/route.c12
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_input.c23
-rw-r--r--net/ipv4/xfrm4_mode_beet.c5
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c6
8 files changed, 109 insertions, 34 deletions
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index bf4a9c4808e..d4d61b694fa 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -17,6 +17,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/net.h>
+#include <linux/workqueue.h>
#include <net/ip.h>
#include <net/inetpeer.h>
#include <net/secure_seq.h>
@@ -66,6 +67,11 @@
static struct kmem_cache *peer_cachep __read_mostly;
+static LIST_HEAD(gc_list);
+static const int gc_delay = 60 * HZ;
+static struct delayed_work gc_work;
+static DEFINE_SPINLOCK(gc_lock);
+
#define node_height(x) x->avl_height
#define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
@@ -102,6 +108,50 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
+static void inetpeer_gc_worker(struct work_struct *work)
+{
+ struct inet_peer *p, *n;
+ LIST_HEAD(list);
+
+ spin_lock_bh(&gc_lock);
+ list_replace_init(&gc_list, &list);
+ spin_unlock_bh(&gc_lock);
+
+ if (list_empty(&list))
+ return;
+
+ list_for_each_entry_safe(p, n, &list, gc_list) {
+
+ if(need_resched())
+ cond_resched();
+
+ if (p->avl_left != peer_avl_empty) {
+ list_add_tail(&p->avl_left->gc_list, &list);
+ p->avl_left = peer_avl_empty;
+ }
+
+ if (p->avl_right != peer_avl_empty) {
+ list_add_tail(&p->avl_right->gc_list, &list);
+ p->avl_right = peer_avl_empty;
+ }
+
+ n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
+
+ if (!atomic_read(&p->refcnt)) {
+ list_del(&p->gc_list);
+ kmem_cache_free(peer_cachep, p);
+ }
+ }
+
+ if (list_empty(&list))
+ return;
+
+ spin_lock_bh(&gc_lock);
+ list_splice(&list, &gc_list);
+ spin_unlock_bh(&gc_lock);
+
+ schedule_delayed_work(&gc_work, gc_delay);
+}
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
@@ -126,6 +176,7 @@ void __init inet_initpeers(void)
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
NULL);
+ INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker);
}
static int addr_compare(const struct inetpeer_addr *a,
@@ -447,9 +498,8 @@ relookup:
p->rate_last = 0;
p->pmtu_expires = 0;
p->pmtu_orig = 0;
- p->redirect_genid = 0;
memset(&p->redirect_learned, 0, sizeof(p->redirect_learned));
-
+ INIT_LIST_HEAD(&p->gc_list);
/* Link the node. */
link_to_pool(p, base);
@@ -509,3 +559,30 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
return rc;
}
EXPORT_SYMBOL(inet_peer_xrlim_allow);
+
+void inetpeer_invalidate_tree(int family)
+{
+ struct inet_peer *old, *new, *prev;
+ struct inet_peer_base *base = family_to_base(family);
+
+ write_seqlock_bh(&base->lock);
+
+ old = base->root;
+ if (old == peer_avl_empty_rcu)
+ goto out;
+
+ new = peer_avl_empty_rcu;
+
+ prev = cmpxchg(&base->root, old, new);
+ if (prev == old) {
+ base->total = 0;
+ spin_lock(&gc_lock);
+ list_add_tail(&prev->gc_list, &gc_list);
+ spin_unlock(&gc_lock);
+ schedule_delayed_work(&gc_work, gc_delay);
+ }
+
+out:
+ write_sequnlock_bh(&base->lock);
+}
+EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6b3ca5ba445..38673d2860e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -65,7 +65,7 @@
it is infeasible task. The most general solutions would be
to keep skb->encapsulation counter (sort of local ttl),
and silently drop packet when it expires. It is a good
- solution, but it supposes maintaing new variable in ALL
+ solution, but it supposes maintaining new variable in ALL
skb, even if no tunneling is used.
Current solution: xmit_recursion breaks dead loops. This is a percpu
@@ -91,14 +91,14 @@
One of them is to parse packet trying to detect inner encapsulation
made by our node. It is difficult or even impossible, especially,
- taking into account fragmentation. TO be short, tt is not solution at all.
+ taking into account fragmentation. TO be short, ttl is not solution at all.
Current solution: The solution was UNEXPECTEDLY SIMPLE.
We force DF flag on tunnels with preconfigured hop limit,
that is ALL. :-) Well, it does not remove the problem completely,
but exponential growth of network traffic is changed to linear
(branches, that exceed pmtu are pruned) and tunnel mtu
- fastly degrades to value <68, where looping stops.
+ rapidly degrades to value <68, where looping stops.
Yes, it is not good if there exists a router in the loop,
which does not force DF, even when encapsulating packets have DF set.
But it is not our problem! Nobody could accuse us, we made
@@ -457,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
GRE tunnels with enabled checksum. Tell them "thank you".
Well, I wonder, rfc1812 was written by Cisco employee,
- what the hell these idiots break standrads established
- by themself???
+ what the hell these idiots break standards established
+ by themselves???
*/
const struct iphdr *iph = (const struct iphdr *)skb->data;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index aea5a199c37..b072386cee2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -630,6 +630,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num);
+ err = -EOPNOTSUPP;
if (flags & MSG_OOB)
goto out;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index bcacf54e541..01977479617 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -132,7 +132,6 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
-static int redirect_genid;
static struct delayed_work expires_work;
static unsigned long expires_ljiffies;
@@ -937,7 +936,7 @@ static void rt_cache_invalidate(struct net *net)
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
- redirect_genid++;
+ inetpeer_invalidate_tree(AF_INET);
}
/*
@@ -1485,10 +1484,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
peer = rt->peer;
if (peer) {
- if (peer->redirect_learned.a4 != new_gw ||
- peer->redirect_genid != redirect_genid) {
+ if (peer->redirect_learned.a4 != new_gw) {
peer->redirect_learned.a4 = new_gw;
- peer->redirect_genid = redirect_genid;
atomic_inc(&__rt_peer_genid);
}
check_peer_redir(&rt->dst, peer);
@@ -1793,8 +1790,6 @@ static void ipv4_validate_peer(struct rtable *rt)
if (peer) {
check_peer_pmtu(&rt->dst, peer);
- if (peer->redirect_genid != redirect_genid)
- peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway)
check_peer_redir(&rt->dst, peer);
@@ -1958,8 +1953,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
dst_init_metrics(&rt->dst, peer->metrics, false);
check_peer_pmtu(&rt->dst, peer);
- if (peer->redirect_genid != redirect_genid)
- peer->redirect_learned.a4 = 0;
+
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway) {
rt->rt_gateway = peer->redirect_learned.a4;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 37755ccc0e9..22ef5f9fd2f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3240,7 +3240,8 @@ void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
unsigned long limit;
- int i, max_share, cnt;
+ int max_share, cnt;
+ unsigned int i;
unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3283,7 +3284,7 @@ void __init tcp_init(void)
&tcp_hashinfo.bhash_size,
NULL,
64 * 1024);
- tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size;
+ tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
spin_lock_init(&tcp_hashinfo.bhash[i].lock);
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 53c8ce4046b..b5e315f1364 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1403,8 +1403,16 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
BUG_ON(!pcount);
- /* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */
- if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint))
+ /* Adjust counters and hints for the newly sacked sequence
+ * range but discard the return value since prev is already
+ * marked. We must tag the range first because the seq
+ * advancement below implicitly advances
+ * tcp_highest_sack_seq() when skb is highest_sack.
+ */
+ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
+ start_seq, end_seq, dup_sack, pcount);
+
+ if (skb == tp->lost_skb_hint)
tp->lost_cnt_hint += pcount;
TCP_SKB_CB(prev)->end_seq += shifted;
@@ -1430,12 +1438,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
skb_shinfo(skb)->gso_type = 0;
}
- /* Adjust counters and hints for the newly sacked sequence range but
- * discard the return value since prev is already marked.
- */
- tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
- start_seq, end_seq, dup_sack, pcount);
-
/* Difference in this won't matter, both ACKed by the same cumul. ACK */
TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
@@ -1583,6 +1585,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
}
}
+ /* tcp_sacktag_one() won't SACK-tag ranges below snd_una */
+ if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
+ goto fallback;
+
if (!skb_shift(prev, skb, len))
goto fallback;
if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
@@ -2567,6 +2573,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
if (cnt > packets) {
if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+ (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
(oldcnt >= packets))
break;
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 63418185f52..e3db3f91511 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb)
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
-
- memmove(skb->data - skb->mac_len, skb_mac_header(skb),
- skb->mac_len);
- skb_set_mac_header(skb, -skb->mac_len);
+ skb_mac_header_rebuild(skb);
xfrm4_beet_make_header(skb);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 534972e114a..ed4bf11ef9f 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- const unsigned char *old_mac;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
@@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip_ecn_decapsulate(skb);
- old_mac = skb_mac_header(skb);
- skb_set_mac_header(skb, -skb->mac_len);
- memmove(skb_mac_header(skb), old_mac, skb->mac_len);
skb_reset_network_header(skb);
+ skb_mac_header_rebuild(skb);
+
err = 0;
out:
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-21 02:29:50 +0000