From 98322f22eca889478045cf896b572250d03dc45f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 26 Jan 2009 21:35:35 -0800 Subject: udp: optimize bind(0) if many ports are in use commit 9088c5609584684149f3fb5b065aa7f18dcb03ff (udp: Improve port randomization) introduced a regression for UDP bind() syscall to null port (getting a random port) in case lot of ports are already in use. This is because we do about 28000 scans of very long chains (220 sockets per chain), with many spin_lock_bh()/spin_unlock_bh() calls. Fix this using a bitmap (64 bytes for current value of UDP_HTABLE_SIZE) so that we scan chains at most once. Instead of 250 ms per bind() call, we get after patch a time of 2.9 ms Based on a report from Vitaly Mayatskikh Reported-by: Vitaly Mayatskikh Signed-off-by: Eric Dumazet Tested-by: Vitaly Mayatskikh Signed-off-by: David S. Miller --- net/ipv4/udp.c | 55 +++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 16 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf5ab0581eba..b7faffe5c029 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -120,8 +120,11 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); +#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE) + static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, + unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, const struct sock *sk2)) @@ -132,12 +135,17 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && sk2 != sk && - sk2->sk_hash == num && + (bitmap || sk2->sk_hash == num) && (!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) && - (*saddr_comp)(sk, sk2)) - return 1; + (*saddr_comp)(sk, sk2)) { + if (bitmap) + __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE, + bitmap); + else + return 1; + } return 0; } @@ -160,32 +168,47 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, if (!snum) { int low, high, remaining; unsigned rand; - unsigned short first; + unsigned short first, last; + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); inet_get_local_port_range(&low, &high); remaining = (high - low) + 1; rand = net_random(); - snum = first = rand % remaining + low; - rand |= 1; - for (;;) { - hslot = &udptable->hash[udp_hashfn(net, snum)]; + first = (((u64)rand * remaining) >> 32) + low; + /* + * force rand to be an odd multiple of UDP_HTABLE_SIZE + */ + rand = (rand | 1) * UDP_HTABLE_SIZE; + for (last = first + UDP_HTABLE_SIZE; first != last; first++) { + hslot = &udptable->hash[udp_hashfn(net, first)]; + bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); - if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) - break; - spin_unlock_bh(&hslot->lock); + udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, + saddr_comp); + + snum = first; + /* + * Iterate on all possible values of snum for this hash. + * Using steps of an odd multiple of UDP_HTABLE_SIZE + * give us randomization and full range coverage. + */ do { - snum = snum + rand; - } while (snum < low || snum > high); - if (snum == first) - goto fail; + if (low <= snum && snum <= high && + !test_bit(snum / UDP_HTABLE_SIZE, bitmap)) + goto found; + snum += rand; + } while (snum != first); + spin_unlock_bh(&hslot->lock); } + goto fail; } else { hslot = &udptable->hash[udp_hashfn(net, snum)]; spin_lock_bh(&hslot->lock); - if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp)) goto fail_unlock; } +found: inet_sk(sk)->num = snum; sk->sk_hash = snum; if (sk_unhashed(sk)) { -- cgit v1.2.2 From 9fa5fdf291c9b58b1cb8b4bb2a0ee57efa21d635 Mon Sep 17 00:00:00 2001 From: Dimitris Michailidis Date: Mon, 26 Jan 2009 22:15:31 -0800 Subject: tcp: Fix length tcp_splice_data_recv passes to skb_splice_bits. tcp_splice_data_recv has two lengths to consider: the len parameter it gets from tcp_read_sock, which specifies the amount of data in the skb, and rd_desc->count, which is the amount of data the splice caller still wants. Currently it passes just the latter to skb_splice_bits, which then splices min(rd_desc->count, skb->len - offset) bytes. Most of the time this is fine, except when the skb contains urgent data. In that case len goes only up to the urgent byte and is less than skb->len - offset. By ignoring len tcp_splice_data_recv may a) splice data tcp_read_sock told it not to, b) return to tcp_read_sock a value > len. Now, tcp_read_sock doesn't handle used > len and leaves the socket in a bad state (both sk_receive_queue and copied_seq are bad at that point) resulting in duplicated data and corruption. Fix by passing min(rd_desc->count, len) to skb_splice_bits. Signed-off-by: Dimitris Michailidis Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0cd71b84e483..76b148bcb0dc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -524,7 +524,8 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, struct tcp_splice_state *tss = rd_desc->arg.data; int ret; - ret = skb_splice_bits(skb, offset, tss->pipe, rd_desc->count, tss->flags); + ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len), + tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; -- cgit v1.2.2 From 9d8dba6c979fa99c96938c869611b9a23b73efa9 Mon Sep 17 00:00:00 2001 From: Benjamin Zores Date: Thu, 29 Jan 2009 16:19:13 -0800 Subject: ipv4: fix infinite retry loop in IP-Config Signed-off-by: Benjamin Zores Signed-off-by: David S. Miller --- net/ipv4/ipconfig.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 42a0f3dd3fd6..d722013c1cae 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1268,6 +1268,9 @@ __be32 __init root_nfs_parse_addr(char *name) static int __init ip_auto_config(void) { __be32 addr; +#ifdef IPCONFIG_DYNAMIC + int retries = CONF_OPEN_RETRIES; +#endif #ifdef CONFIG_PROC_FS proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops); @@ -1304,9 +1307,6 @@ static int __init ip_auto_config(void) #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC - - int retries = CONF_OPEN_RETRIES; - if (ic_dynamic() < 0) { ic_close_devs(); -- cgit v1.2.2