aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c11
-rw-r--r--net/ipv4/arp.c8
-rw-r--r--net/ipv4/igmp.c13
-rw-r--r--net/ipv4/inet_connection_sock.c17
-rw-r--r--net/ipv4/ip_gre.c4
-rw-r--r--net/ipv4/ip_sockglue.c35
-rw-r--r--net/ipv4/ipconfig.c15
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/proc.c9
-rw-r--r--net/ipv4/raw.c10
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/udp.c6
13 files changed, 84 insertions, 51 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1b5096a..15dc4c4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1250,7 +1250,8 @@ out:
return err;
}
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct iphdr *iph;
@@ -1572,9 +1573,9 @@ static __net_init int ipv4_mib_init_net(struct net *net)
sizeof(struct icmp_mib),
__alignof__(struct icmp_mib)) < 0)
goto err_icmp_mib;
- if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
- sizeof(struct icmpmsg_mib),
- __alignof__(struct icmpmsg_mib)) < 0)
+ net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
+ GFP_KERNEL);
+ if (!net->mib.icmpmsg_statistics)
goto err_icmpmsg_mib;
tcp_mib_init(net);
@@ -1598,7 +1599,7 @@ err_tcp_mib:
static __net_exit void ipv4_mib_exit_net(struct net *net)
{
- snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
+ kfree(net->mib.icmpmsg_statistics);
snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
snmp_mib_free((void __percpu **)net->mib.udp_statistics);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 96a164a..5c29ac5 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -177,7 +177,7 @@ struct neigh_table arp_tbl = {
.gc_staletime = 60 * HZ,
.reachable_time = 30 * HZ,
.delay_probe_time = 5 * HZ,
- .queue_len = 3,
+ .queue_len_bytes = 64*1024,
.ucast_probes = 3,
.mcast_probes = 3,
.anycast_delay = 1 * HZ,
@@ -592,16 +592,18 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
struct sk_buff *skb;
struct arphdr *arp;
unsigned char *arp_ptr;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
/*
* Allocate a buffer
*/
- skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC);
if (skb == NULL)
return NULL;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev));
skb->dev = dev;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c7472ef..fbc5376 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -304,9 +304,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
struct igmpv3_report *pig;
struct net *net = dev_net(dev);
struct flowi4 fl4;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
while (1) {
- skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev),
+ skb = alloc_skb(size + hlen + tlen,
GFP_ATOMIC | __GFP_NOWARN);
if (skb)
break;
@@ -327,7 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
skb_dst_set(skb, &rt->dst);
skb->dev = dev;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
pip = ip_hdr(skb);
@@ -647,6 +649,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
__be32 group = pmc ? pmc->multiaddr : 0;
struct flowi4 fl4;
__be32 dst;
+ int hlen, tlen;
if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
return igmpv3_send_report(in_dev, pmc);
@@ -661,7 +664,9 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
if (IS_ERR(rt))
return -1;
- skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+ hlen = LL_RESERVED_SPACE(dev);
+ tlen = dev->needed_tailroom;
+ skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC);
if (skb == NULL) {
ip_rt_put(rt);
return -1;
@@ -669,7 +674,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
skb_dst_set(skb, &rt->dst);
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
skb_reset_network_header(skb);
iph = ip_hdr(skb);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c14d88a..a598768 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -588,10 +588,19 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
-struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
- const gfp_t priority)
+/**
+ * inet_csk_clone_lock - clone an inet socket, and lock its clone
+ * @sk: the socket to clone
+ * @req: request_sock
+ * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ * Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *inet_csk_clone_lock(const struct sock *sk,
+ const struct request_sock *req,
+ const gfp_t priority)
{
- struct sock *newsk = sk_clone(sk, priority);
+ struct sock *newsk = sk_clone_lock(sk, priority);
if (newsk != NULL) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
@@ -615,7 +624,7 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
}
return newsk;
}
-EXPORT_SYMBOL_GPL(inet_csk_clone);
+EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
/*
* At this point, there should be no process reference to this
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d55110e..2b32296 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -171,7 +171,7 @@ struct pcpu_tstats {
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ipgre_get_stats(struct net_device *dev)
{
@@ -835,6 +835,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
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);
dev->stats.tx_dropped++;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 09ff51b..80d5fa4 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -55,20 +55,13 @@
/*
* SOL_IP control messages.
*/
+#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb))
static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
- struct in_pktinfo info;
- struct rtable *rt = skb_rtable(skb);
+ struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
- if (rt) {
- info.ipi_ifindex = rt->rt_iif;
- info.ipi_spec_dst.s_addr = rt->rt_spec_dst;
- } else {
- info.ipi_ifindex = 0;
- info.ipi_spec_dst.s_addr = 0;
- }
put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
@@ -992,20 +985,28 @@ e_inval:
}
/**
- * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * ipv4_pktinfo_prepare - transfert some info from rtable to skb
* @sk: socket
* @skb: buffer
*
- * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
- * is not set, we drop skb dst entry now, while dst cache line is hot.
+ * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst
+ * in skb->cb[] before dst drop.
+ * This way, receiver doesnt make cache line misses to read rtable.
*/
-int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(struct sk_buff *skb)
{
- if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
- skb_dst_drop(skb);
- return sock_queue_rcv_skb(sk, skb);
+ struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+ const struct rtable *rt = skb_rtable(skb);
+
+ if (rt) {
+ pktinfo->ipi_ifindex = rt->rt_iif;
+ pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst;
+ } else {
+ pktinfo->ipi_ifindex = 0;
+ pktinfo->ipi_spec_dst.s_addr = 0;
+ }
+ skb_dst_drop(skb);
}
-EXPORT_SYMBOL(ip_queue_rcv_skb);
int ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 0da2afc..915eb52 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -763,13 +763,15 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d
struct sk_buff *skb;
struct bootp_pkt *b;
struct iphdr *h;
+ int hlen = LL_RESERVED_SPACE(dev);
+ int tlen = dev->needed_tailroom;
/* Allocate packet */
- skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15,
+ skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15,
GFP_KERNEL);
if (!skb)
return;
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
+ skb_reserve(skb, hlen);
b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt));
memset(b, 0, sizeof(struct bootp_pkt));
@@ -822,8 +824,13 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d
skb->dev = dev;
skb->protocol = htons(ETH_P_IP);
if (dev_hard_header(skb, dev, ntohs(skb->protocol),
- dev->broadcast, dev->dev_addr, skb->len) < 0 ||
- dev_queue_xmit(skb) < 0)
+ dev->broadcast, dev->dev_addr, skb->len) < 0) {
+ kfree_skb(skb);
+ printk("E");
+ return;
+ }
+
+ if (dev_queue_xmit(skb) < 0)
printk("E");
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 065effd..9490690 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -148,7 +148,7 @@ struct pcpu_tstats {
unsigned long rx_bytes;
unsigned long tx_packets;
unsigned long tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
static struct net_device_stats *ipip_get_stats(struct net_device *dev)
{
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 466ea8b..961eed4 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -288,7 +288,7 @@ static void icmpmsg_put(struct seq_file *seq)
count = 0;
for (i = 0; i < ICMPMSG_MIB_MAX; i++) {
- val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i);
+ val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]);
if (val) {
type[count] = i;
vals[count++] = val;
@@ -307,6 +307,7 @@ static void icmp_put(struct seq_file *seq)
{
int i;
struct net *net = seq->private;
+ atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
seq_puts(seq, "\nIcmp: InMsgs InErrors");
for (i=0; icmpmibmap[i].name != NULL; i++)
@@ -319,15 +320,13 @@ static void icmp_put(struct seq_file *seq)
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS));
for (i=0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
- snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
- icmpmibmap[i].index));
+ atomic_long_read(ptr + icmpmibmap[i].index));
seq_printf(seq, " %lu %lu",
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
for (i=0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
- snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
- icmpmibmap[i].index | 0x100));
+ atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
}
/*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 007e2eb..3ccda5a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
/* Charge it to the socket. */
- if (ip_queue_rcv_skb(sk, skb) < 0) {
+ ipv4_pktinfo_prepare(skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
@@ -327,6 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
+ int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -336,12 +338,14 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
if (flags&MSG_PROBE)
goto out;
+ hlen = LL_RESERVED_SPACE(rt->dst.dev);
+ tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
- length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+ length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
- skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+ skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 34f5db1..50c3596 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2653,7 +2653,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct tcphdr *th;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 66363b6..0a7e339 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -425,7 +425,7 @@ static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
*/
struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
{
- struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+ struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
if (newsk != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ab0966d..b867ea2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1357,7 +1357,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (inet_sk(sk)->inet_daddr)
sock_rps_save_rxhash(sk, skb);
- rc = ip_queue_rcv_skb(sk, skb);
+ rc = sock_queue_rcv_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -1473,6 +1473,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
rc = 0;
+ ipv4_pktinfo_prepare(skb);
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
rc = __udp_queue_rcv_skb(sk, skb);
@@ -2246,7 +2247,8 @@ int udp4_ufo_send_check(struct sk_buff *skb)
return 0;
}
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features)
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
generated by cgit v1.1 at 2025-08-17 02:24:40 +0000