summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ipconfig.c6
-rw-r--r--net/ipv4/netfilter/iptable_filter.c7
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c6
-rw-r--r--net/ipv4/netfilter/iptable_raw.c6
-rw-r--r--net/ipv4/netfilter/iptable_security.c6
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c5
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c2
-rw-r--r--net/ipv4/tcp.c41
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/udp.c59
11 files changed, 75 insertions, 67 deletions
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();
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index c9224310ebae..52cb6939d093 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -93,13 +93,8 @@ ipt_local_out_hook(unsigned int hook,
{
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
- ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("iptable_filter: ignoring short SOCK_RAW "
- "packet.\n");
+ ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
-
return ipt_do_table(skb, hook, in, out,
dev_net(out)->ipv4.iptable_filter);
}
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 69f2c4287146..3929d20b9e45 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -132,12 +132,8 @@ ipt_local_hook(unsigned int hook,
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr)
- || ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("iptable_mangle: ignoring short SOCK_RAW "
- "packet.\n");
+ || ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
/* Save things which could affect route */
mark = skb->mark;
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 8faebfe638f1..7f65d18333e3 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -65,12 +65,8 @@ ipt_local_hook(unsigned int hook,
{
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
- ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("iptable_raw: ignoring short SOCK_RAW "
- "packet.\n");
+ ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
return ipt_do_table(skb, hook, in, out,
dev_net(out)->ipv4.iptable_raw);
}
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index 36f3be3cc428..a52a35f4a584 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -96,12 +96,8 @@ ipt_local_out_hook(unsigned int hook,
{
/* Somebody is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr)
- || ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk(KERN_INFO "iptable_security: ignoring short "
- "SOCK_RAW packet.\n");
+ || ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
return ipt_do_table(skb, hook, in, out,
dev_net(out)->ipv4.iptable_security);
}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index b2141e11575e..4beb04fac588 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -145,11 +145,8 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum,
{
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
- ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("ipt_hook: happy cracking.\n");
+ ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- }
return nf_conntrack_in(dev_net(out), PF_INET, hooknum, skb);
}
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 1fd3ef7718b6..2a8bee26f43d 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -20,7 +20,7 @@
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_log.h>
-static unsigned long nf_ct_icmp_timeout __read_mostly = 30*HZ;
+static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ;
static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
struct nf_conntrack_tuple *tuple)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f28acf11fc67..76b148bcb0dc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -522,8 +522,13 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
unsigned int offset, size_t len)
{
struct tcp_splice_state *tss = rd_desc->arg.data;
+ int ret;
- return skb_splice_bits(skb, offset, tss->pipe, tss->len, 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;
}
static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
@@ -531,6 +536,7 @@ static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
/* Store TCP splice context information in read_descriptor_t. */
read_descriptor_t rd_desc = {
.arg.data = tss,
+ .count = tss->len,
};
return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
@@ -580,10 +586,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
else if (!ret) {
if (spliced)
break;
- if (flags & SPLICE_F_NONBLOCK) {
- ret = -EAGAIN;
- break;
- }
if (sock_flag(sk, SOCK_DONE))
break;
if (sk->sk_err) {
@@ -615,11 +617,13 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
tss.len -= ret;
spliced += ret;
+ if (!timeo)
+ break;
release_sock(sk);
lock_sock(sk);
if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
- (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo ||
+ (sk->sk_shutdown & RCV_SHUTDOWN) ||
signal_pending(current))
break;
}
@@ -1317,7 +1321,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if ((available < target) &&
(len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
!sysctl_tcp_low_latency &&
- __get_cpu_var(softnet_data).net_dma) {
+ dma_find_channel(DMA_MEMCPY)) {
preempt_enable_no_resched();
tp->ucopy.pinned_list =
dma_pin_iovec_pages(msg->msg_iov, len);
@@ -1527,7 +1531,7 @@ do_prequeue:
if (!(flags & MSG_TRUNC)) {
#ifdef CONFIG_NET_DMA
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan) {
tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
@@ -1632,7 +1636,6 @@ skip_copy:
/* Safe to free early-copied skbs now */
__skb_queue_purge(&sk->sk_async_wait_queue);
- dma_chan_put(tp->ucopy.dma_chan);
tp->ucopy.dma_chan = NULL;
}
if (tp->ucopy.pinned_list) {
@@ -2387,7 +2390,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
unsigned int seq;
__be32 delta;
unsigned int oldlen;
- unsigned int len;
+ unsigned int mss;
if (!pskb_may_pull(skb, sizeof(*th)))
goto out;
@@ -2403,10 +2406,13 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
oldlen = (u16)~skb->len;
__skb_pull(skb, thlen);
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
int type = skb_shinfo(skb)->gso_type;
- int mss;
if (unlikely(type &
~(SKB_GSO_TCPV4 |
@@ -2417,7 +2423,6 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
- mss = skb_shinfo(skb)->gso_size;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
segs = NULL;
@@ -2428,8 +2433,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
if (IS_ERR(segs))
goto out;
- len = skb_shinfo(skb)->gso_size;
- delta = htonl(oldlen + (thlen + len));
+ delta = htonl(oldlen + (thlen + mss));
skb = segs;
th = tcp_hdr(skb);
@@ -2445,7 +2449,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
- seq += len;
+ seq += mss;
skb = skb->next;
th = tcp_hdr(skb);
@@ -2519,9 +2523,7 @@ found:
flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th));
total = p->len;
- mss = total;
- if (skb_shinfo(p)->frag_list)
- mss = skb_shinfo(p)->frag_list->len;
+ mss = skb_shinfo(p)->gso_size;
flush |= skb->len > mss || skb->len <= 0;
flush |= ntohl(th2->seq) + total != ntohl(th->seq);
@@ -2548,6 +2550,7 @@ out:
return pp;
}
+EXPORT_SYMBOL(tcp_gro_receive);
int tcp_gro_complete(struct sk_buff *skb)
{
@@ -2557,7 +2560,6 @@ int tcp_gro_complete(struct sk_buff *skb)
skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
- skb_shinfo(skb)->gso_size = skb_shinfo(skb)->frag_list->len;
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
if (th->cwr)
@@ -2565,6 +2567,7 @@ int tcp_gro_complete(struct sk_buff *skb)
return 0;
}
+EXPORT_SYMBOL(tcp_gro_complete);
#ifdef CONFIG_TCP_MD5SIG
static unsigned long tcp_md5sig_users;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 99b7ecbe8893..a6961d75c7ea 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5005,7 +5005,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
return 0;
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9d839fa9331e..19d7b429a262 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1594,7 +1594,7 @@ process:
#ifdef CONFIG_NET_DMA
struct tcp_sock *tp = tcp_sk(sk);
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan)
ret = tcp_v4_do_rcv(sk, skb);
else
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cf5ab0581eba..1ab180bad72a 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)) {
@@ -992,9 +1015,11 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM)
+ if (rc == -ENOMEM) {
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
goto drop;
}
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-20 14:46:20 +0000