| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20070330151021.d067d837.dada1@cosmosbay.com>
Date: Fri, 30 Mar 2007 15:10:21 +0200
From: Eric Dumazet <dada1@...mosbay.com>
To: Zacco <zacco@...hu>
Cc: David Miller <davem@...emloft.net>, baruch@...en.org,
netdev@...r.kernel.org
Subject: Re: many sockets, slow sendto
On Thu, 29 Mar 2007 21:24:31 +0200
Zacco <zacco@...hu> wrote:
> Hi,
>
> Thanks for the patch. I almost dare not confess that I don't know which
> version to apply to. I tried 3 different ones (2.6.19-r5-gentoo,
> 2.6.20.1 and 2.6.21-rc4), but in the best case at least two hunks
> failed. Nevertheless, I applied the patches manually. In each case, UDP
> stopped working. I guess, you checked the patch and worked. I don't
> think I made a mistake in the manual copy, and it seems unlikely that
> your patch interfered with other parallel changes in the kernel - but,
> I'm just guessing ...
> I think, I'd better send you the spec and code, as you suggested that
> first we have a common understanding of the issue. I must have failed in
> passing the point. I'm removing irrelevant stuff, and I send it to you
> as soon as I can (sorry for my long delays).
>
> thx a lot,
> Zacco
Hum, please find a (working) patch against linux-2.6.21-rc5
(first patch was against net-2.6.22 git tree and had one bug)
Hope this helps
--- linux-2.6.21-rc5/net/ipv4/udp.c
+++ linux-2.6.21-rc5-ed/net/ipv4/udp.c
@@ -114,14 +114,33 @@ DEFINE_RWLOCK(udp_hash_lock);
static int udp_port_rover;
-static inline int __udp_lib_lport_inuse(__u16 num, struct hlist_head udptable[])
+/*
+ * Note about this hash function :
+ * Typical use is probably daddr = 0, only dport is going to vary hash
+ */
+static inline unsigned int hash_port_and_addr(__u16 port, __be32 addr)
+{
+ addr ^= addr >> 16;
+ addr ^= addr >> 8;
+ return port ^ addr;
+}
+
+static inline int __udp_lib_port_inuse(unsigned int hash, int port,
+ __be32 daddr, struct hlist_head udptable[])
{
struct sock *sk;
struct hlist_node *node;
+ struct inet_sock *inet;
- sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
- if (sk->sk_hash == num)
+ sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
+ if (sk->sk_hash != hash)
+ continue;
+ inet = inet_sk(sk);
+ if (inet->num != port)
+ continue;
+ if (inet->rcv_saddr == daddr)
return 1;
+ }
return 0;
}
@@ -142,6 +161,7 @@ int __udp_lib_get_port(struct sock *sk,
struct hlist_node *node;
struct hlist_head *head;
struct sock *sk2;
+ unsigned int hash;
int error = 1;
write_lock_bh(&udp_hash_lock);
@@ -156,7 +176,9 @@ int __udp_lib_get_port(struct sock *sk,
for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
int size;
- head = &udptable[result & (UDP_HTABLE_SIZE - 1)];
+ hash = hash_port_and_addr(result,
+ inet_sk(sk)->rcv_saddr);
+ head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
if (hlist_empty(head)) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0] +
@@ -180,7 +202,10 @@ int __udp_lib_get_port(struct sock *sk,
result = sysctl_local_port_range[0]
+ ((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
- if (! __udp_lib_lport_inuse(result, udptable))
+ hash = hash_port_and_addr(result,
+ inet_sk(sk)->rcv_saddr);
+ if (! __udp_lib_port_inuse(hash, result,
+ inet_sk(sk)->rcv_saddr, udptable))
break;
}
if (i >= (1 << 16) / UDP_HTABLE_SIZE)
@@ -188,11 +213,13 @@ int __udp_lib_get_port(struct sock *sk,
gotit:
*port_rover = snum = result;
} else {
- head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+ hash = hash_port_and_addr(snum, inet_sk(sk)->rcv_saddr);
+ head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
sk_for_each(sk2, node, head)
- if (sk2->sk_hash == snum &&
+ if (sk2->sk_hash == hash &&
sk2 != sk &&
+ inet_sk(sk2)->num == snum &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
|| sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
@@ -200,9 +227,9 @@ gotit:
goto fail;
}
inet_sk(sk)->num = snum;
- sk->sk_hash = snum;
+ sk->sk_hash = hash;
if (sk_unhashed(sk)) {
- head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+ head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
sk_add_node(sk, head);
sock_prot_inc_use(sk->sk_prot);
}
@@ -241,63 +268,76 @@ static struct sock *__udp4_lib_lookup(__
{
struct sock *sk, *result = NULL;
struct hlist_node *node;
- unsigned short hnum = ntohs(dport);
- int badness = -1;
+ unsigned int hash, hashwild;
+ int score, best = -1, hport = ntohs(dport);
+
+ hash = hash_port_and_addr(hport, daddr);
+ hashwild = hash_port_and_addr(hport, 0);
read_lock(&udp_hash_lock);
- sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
+
+lookup:
+
+ sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
struct inet_sock *inet = inet_sk(sk);
- if (sk->sk_hash == hnum && !ipv6_only_sock(sk)) {
- int score = (sk->sk_family == PF_INET ? 1 : 0);
- if (inet->rcv_saddr) {
- if (inet->rcv_saddr != daddr)
- continue;
- score+=2;
- }
- if (inet->daddr) {
- if (inet->daddr != saddr)
- continue;
- score+=2;
- }
- if (inet->dport) {
- if (inet->dport != sport)
- continue;
- score+=2;
- }
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- continue;
- score+=2;
- }
- if(score == 9) {
- result = sk;
- break;
- } else if(score > badness) {
- result = sk;
- badness = score;
- }
+ if (sk->sk_hash != hash || ipv6_only_sock(sk) ||
+ inet->num != hport)
+ continue;
+
+ score = (sk->sk_family == PF_INET ? 1 : 0);
+ if (inet->rcv_saddr) {
+ if (inet->rcv_saddr != daddr)
+ continue;
+ score+=2;
+ }
+ if (inet->daddr) {
+ if (inet->daddr != saddr)
+ continue;
+ score+=2;
+ }
+ if (inet->dport) {
+ if (inet->dport != sport)
+ continue;
+ score+=2;
+ }
+ if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if != dif)
+ continue;
+ score+=2;
}
+ if(score == 9) {
+ result = sk;
+ goto found;
+ } else if(score > best) {
+ result = sk;
+ best = score;
+ }
+ }
+ if (hash != hashwild) {
+ hash = hashwild;
+ goto lookup;
}
+found:
if (result)
sock_hold(result);
read_unlock(&udp_hash_lock);
return result;
}
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
- __be16 loc_port, __be32 loc_addr,
+static inline struct sock *udp_v4_mcast_next(struct sock *sk, unsigned int hnum,
+ int hport, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif)
{
struct hlist_node *node;
struct sock *s = sk;
- unsigned short hnum = ntohs(loc_port);
sk_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
if (s->sk_hash != hnum ||
+ inet->num != hport ||
(inet->daddr && inet->daddr != rmt_addr) ||
(inet->dport != rmt_port && inet->dport) ||
(inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
@@ -1128,25 +1168,39 @@ static int __udp4_lib_mcast_deliver(stru
__be32 saddr, __be32 daddr,
struct hlist_head udptable[])
{
- struct sock *sk;
+ struct sock *sk, *skw, *sknext;
int dif;
+ int hport = ntohs(uh->dest);
+ unsigned int hash = hash_port_and_addr(hport, daddr);
+ unsigned int hashwild = hash_port_and_addr(hport, 0);
- read_lock(&udp_hash_lock);
- sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
dif = skb->dev->ifindex;
- sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
- if (sk) {
- struct sock *sknext = NULL;
+ read_lock(&udp_hash_lock);
+
+ sk = sk_head(&udptable[hash & (UDP_HTABLE_SIZE - 1)]);
+ skw = sk_head(&udptable[hashwild & (UDP_HTABLE_SIZE - 1)]);
+
+ sk = udp_v4_mcast_next(sk, hash, hport, daddr, uh->source, saddr, dif);
+ if (!sk) {
+ hash = hashwild;
+ sk = udp_v4_mcast_next(skw, hash, hport, daddr, uh->source,
+ saddr, dif);
+ }
+ if (sk) {
do {
struct sk_buff *skb1 = skb;
-
- sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
- uh->source, saddr, dif);
- if(sknext)
+ sknext = udp_v4_mcast_next(sk_next(sk), hash, hport,
+ daddr, uh->source, saddr, dif);
+ if (!sknext && hash != hashwild) {
+ hash = hashwild;
+ sknext = udp_v4_mcast_next(skw, hash, hport,
+ daddr, uh->source, saddr, dif);
+ }
+ if (sknext)
skb1 = skb_clone(skb, GFP_ATOMIC);
- if(skb1) {
+ if (skb1) {
int ret = udp_queue_rcv_skb(sk, skb1);
if (ret > 0)
/* we should probably re-process instead
@@ -1228,7 +1282,7 @@ int __udp4_lib_rcv(struct sk_buff *skb,
return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
- skb->dev->ifindex, udptable );
+ skb->dev->ifindex, udptable);
if (sk != NULL) {
int ret = udp_queue_rcv_skb(sk, skb);
--
Eric Dumazet <dada1@...mosbay.com>
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists