summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/fib_trie.c50
-rw-r--r--net/ipv4/ip_gre.c6
-rw-r--r--net/ipv4/ipip.c6
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/tcp_output.c58
-rw-r--r--net/ipv4/udp.c144
-rw-r--r--net/ipv4/xfrm4_policy.c31
9 files changed, 235 insertions, 76 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 566ea6c4321..197d024b253 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1187,6 +1187,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
int proto;
int ihl;
int id;
+ unsigned int offset = 0;
if (!(features & NETIF_F_V4_CSUM))
features &= ~NETIF_F_SG;
@@ -1229,7 +1230,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
skb = segs;
do {
iph = ip_hdr(skb);
- iph->id = htons(id++);
+ if (proto == IPPROTO_UDP) {
+ iph->id = htons(id);
+ iph->frag_off = htons(offset >> 3);
+ if (skb->next != NULL)
+ iph->frag_off |= htons(IP_MF);
+ offset += (skb->len - skb->mac_len - iph->ihl * 4);
+ } else
+ iph->id = htons(id++);
iph->tot_len = htons(skb->len - skb->mac_len);
iph->check = 0;
iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
@@ -1425,6 +1433,8 @@ static struct net_protocol tcp_protocol = {
static struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
+ .gso_send_check = udp4_ufo_send_check,
+ .gso_segment = udp4_ufo_fragment,
.no_policy = 1,
.netns_ok = 1,
};
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 63c2fa7b68c..d58b4911538 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -164,6 +164,14 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn);
static struct tnode *halve(struct trie *t, struct tnode *tn);
/* tnodes to free after resize(); protected by RTNL */
static struct tnode *tnode_free_head;
+static size_t tnode_free_size;
+
+/*
+ * synchronize_rcu after call_rcu for that many pages; it should be especially
+ * useful before resizing the root node with PREEMPT_NONE configs; the value was
+ * obtained experimentally, aiming to avoid visible slowdown.
+ */
+static const int sync_pages = 128;
static struct kmem_cache *fn_alias_kmem __read_mostly;
static struct kmem_cache *trie_leaf_kmem __read_mostly;
@@ -319,6 +327,8 @@ static const int inflate_threshold = 50;
static const int halve_threshold_root = 15;
static const int inflate_threshold_root = 25;
+static int inflate_threshold_root_fix;
+#define INFLATE_FIX_MAX 10 /* a comment in resize() */
static void __alias_free_mem(struct rcu_head *head)
{
@@ -393,6 +403,8 @@ static void tnode_free_safe(struct tnode *tn)
BUG_ON(IS_LEAF(tn));
tn->tnode_free = tnode_free_head;
tnode_free_head = tn;
+ tnode_free_size += sizeof(struct tnode) +
+ (sizeof(struct node *) << tn->bits);
}
static void tnode_free_flush(void)
@@ -404,6 +416,11 @@ static void tnode_free_flush(void)
tn->tnode_free = NULL;
tnode_free(tn);
}
+
+ if (tnode_free_size >= PAGE_SIZE * sync_pages) {
+ tnode_free_size = 0;
+ synchronize_rcu();
+ }
}
static struct leaf *leaf_new(void)
@@ -602,7 +619,8 @@ static struct node *resize(struct trie *t, struct tnode *tn)
/* Keep root node larger */
if (!tn->parent)
- inflate_threshold_use = inflate_threshold_root;
+ inflate_threshold_use = inflate_threshold_root +
+ inflate_threshold_root_fix;
else
inflate_threshold_use = inflate_threshold;
@@ -626,15 +644,27 @@ static struct node *resize(struct trie *t, struct tnode *tn)
}
if (max_resize < 0) {
- if (!tn->parent)
- pr_warning("Fix inflate_threshold_root."
- " Now=%d size=%d bits\n",
- inflate_threshold_root, tn->bits);
- else
+ if (!tn->parent) {
+ /*
+ * It was observed that during large updates even
+ * inflate_threshold_root = 35 might be needed to avoid
+ * this warning; but it should be temporary, so let's
+ * try to handle this automatically.
+ */
+ if (inflate_threshold_root_fix < INFLATE_FIX_MAX)
+ inflate_threshold_root_fix++;
+ else
+ pr_warning("Fix inflate_threshold_root."
+ " Now=%d size=%d bits fix=%d\n",
+ inflate_threshold_root, tn->bits,
+ inflate_threshold_root_fix);
+ } else {
pr_warning("Fix inflate_threshold."
" Now=%d size=%d bits\n",
inflate_threshold, tn->bits);
- }
+ }
+ } else if (max_resize > 3 && !tn->parent && inflate_threshold_root_fix)
+ inflate_threshold_root_fix--;
check_tnode(tn);
@@ -1435,7 +1465,7 @@ static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp,
cindex = tkey_extract_bits(mask_pfx(key, current_prefix_length),
pos, bits);
- n = tnode_get_child(pn, cindex);
+ n = tnode_get_child_rcu(pn, cindex);
if (n == NULL) {
#ifdef CONFIG_IP_FIB_TRIE_STATS
@@ -1570,7 +1600,7 @@ backtrace:
if (chopped_off <= pn->bits) {
cindex &= ~(1 << (chopped_off-1));
} else {
- struct tnode *parent = node_parent((struct node *) pn);
+ struct tnode *parent = node_parent_rcu((struct node *) pn);
if (!parent)
goto failed;
@@ -1783,7 +1813,7 @@ static struct leaf *trie_firstleaf(struct trie *t)
static struct leaf *trie_nextleaf(struct leaf *l)
{
struct node *c = (struct node *) l;
- struct tnode *p = node_parent(c);
+ struct tnode *p = node_parent_rcu(c);
if (!p)
return NULL; /* trie with just one leaf */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index cb4a0f4bd5e..b902ef55be7 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -821,7 +821,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
@@ -889,7 +889,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
IPTUNNEL_XMIT();
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
@@ -898,7 +898,7 @@ tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
static int ipgre_tunnel_bind_dev(struct net_device *dev)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 93e2b787da2..98075b6d619 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -486,7 +486,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
@@ -524,7 +524,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
IPTUNNEL_XMIT();
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
@@ -532,7 +532,7 @@ tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
static void ipip_tunnel_bind_dev(struct net_device *dev)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9a8da5ed92b..06c33fb6b32 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -212,7 +212,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
IGMPMSG_WHOLEPKT);
read_unlock(&mrt_lock);
kfree_skb(skb);
- return 0;
+ return NETDEV_TX_OK;
}
static const struct net_device_ops reg_vif_netdev_ops = {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 278f46f5011..fafbe163e2b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3442,7 +3442,7 @@ int __init ip_rt_init(void)
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
- xfrm4_init();
+ xfrm4_init(ip_rt_max_size);
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bd62712848f..4e004424d40 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -59,6 +59,7 @@ int sysctl_tcp_base_mss __read_mostly = 512;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+/* Account for new data that has been sent to the network. */
static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -142,6 +143,7 @@ static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
tp->snd_cwnd_used = 0;
}
+/* Congestion state accounting after a packet has been sent. */
static void tcp_event_data_sent(struct tcp_sock *tp,
struct sk_buff *skb, struct sock *sk)
{
@@ -161,6 +163,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
icsk->icsk_ack.pingpong = 1;
}
+/* Account for an ACK we sent. */
static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
tcp_dec_quickack_mode(sk, pkts);
@@ -276,6 +279,7 @@ static u16 tcp_select_window(struct sock *sk)
return new_win;
}
+/* Packet ECN state for a SYN-ACK */
static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb)
{
TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR;
@@ -283,6 +287,7 @@ static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb)
TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE;
}
+/* Packet ECN state for a SYN. */
static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -301,6 +306,9 @@ TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th)
th->ece = 1;
}
+/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
+ * be sent.
+ */
static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
int tcp_header_len)
{
@@ -362,7 +370,9 @@ struct tcp_out_options {
__u32 tsval, tsecr; /* need to include OPTION_TS */
};
-/* Beware: Something in the Internet is very sensitive to the ordering of
+/* Write previously computed TCP options to the packet.
+ *
+ * Beware: Something in the Internet is very sensitive to the ordering of
* TCP options, we learned this through the hard way, so be careful here.
* Luckily we can at least blame others for their non-compliance but from
* inter-operatibility perspective it seems that we're somewhat stuck with
@@ -445,6 +455,9 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
}
}
+/* Compute TCP options for SYN packets. This is not the final
+ * network wire format yet.
+ */
static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5) {
@@ -493,6 +506,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
return size;
}
+/* Set up TCP options for SYN-ACKs. */
static unsigned tcp_synack_options(struct sock *sk,
struct request_sock *req,
unsigned mss, struct sk_buff *skb,
@@ -541,6 +555,9 @@ static unsigned tcp_synack_options(struct sock *sk,
return size;
}
+/* Compute TCP options for ESTABLISHED sockets. This is not the
+ * final wire format yet.
+ */
static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5) {
@@ -705,7 +722,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
return net_xmit_eval(err);
}
-/* This routine just queue's the buffer
+/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
* otherwise socket can stall.
@@ -722,6 +739,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
sk_mem_charge(sk, skb->truesize);
}
+/* Initialize TSO segments for a packet. */
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
@@ -909,6 +927,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
skb->len = skb->data_len;
}
+/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
@@ -937,7 +956,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
return 0;
}
-/* Not accounting for SACKs here. */
+/* Calculate MSS. Not accounting for SACKs here. */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -981,6 +1000,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
return mtu;
}
+/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1143,7 +1163,8 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp,
return 0;
}
-/* This must be invoked the first time we consider transmitting
+/* Intialize TSO state of a skb.
+ * This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
@@ -1158,6 +1179,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
return tso_segs;
}
+/* Minshall's variant of the Nagle send check. */
static inline int tcp_minshall_check(const struct tcp_sock *tp)
{
return after(tp->snd_sml, tp->snd_una) &&
@@ -1242,6 +1264,7 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
return cwnd_quota;
}
+/* Test if sending is allowed right now. */
int tcp_may_send_now(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1378,6 +1401,10 @@ send_now:
}
/* Create a new MTU probe if we are ready.
+ * MTU probe is regularly attempting to increase the path MTU by
+ * deliberately sending larger packets. This discovers routing
+ * changes resulting in larger path MTUs.
+ *
* Returns 0 if we should wait to probe (no cwnd available),
* 1 if a probe was sent,
* -1 otherwise
@@ -1790,6 +1817,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
sk_wmem_free_skb(sk, next_skb);
}
+/* Check if coalescing SKBs is legal. */
static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
{
if (tcp_skb_pcount(skb) > 1)
@@ -1808,6 +1836,9 @@ static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
return 1;
}
+/* Collapse packets in the retransmit queue to make to create
+ * less packets on the wire. This is only done on retransmission.
+ */
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
int space)
{
@@ -1957,6 +1988,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
return err;
}
+/* Check if we forward retransmits are possible in the current
+ * window/congestion state.
+ */
static int tcp_can_forward_retransmit(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2145,7 +2179,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
-/* WARNING: This routine must only be called when we have already sent
+/* Send a crossed SYN-ACK during socket establishment.
+ * WARNING: This routine must only be called when we have already sent
* a SYN packet that crossed the incoming SYN that caused this routine
* to get called. If this assumption fails then the initial rcv_wnd
* and rcv_wscale values will not be correct.
@@ -2180,9 +2215,7 @@ int tcp_send_synack(struct sock *sk)
return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
-/*
- * Prepare a SYN-ACK.
- */
+/* Prepare a SYN-ACK. */
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req)
{
@@ -2269,9 +2302,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
return skb;
}
-/*
- * Do all connect socket setups that can be done AF independent.
- */
+/* Do all connect socket setups that can be done AF independent. */
static void tcp_connect_init(struct sock *sk)
{
struct dst_entry *dst = __sk_dst_get(sk);
@@ -2330,9 +2361,7 @@ static void tcp_connect_init(struct sock *sk)
tcp_clear_retrans(tp);
}
-/*
- * Build a SYN and send it off.
- */
+/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2493,6 +2522,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
+/* Initiate keepalive or window probe from timer. */
int tcp_write_wakeup(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 80e3812837a..29ebb0d27a1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -110,11 +110,12 @@ struct udp_table udp_table;
EXPORT_SYMBOL(udp_table);
int sysctl_udp_mem[3] __read_mostly;
-int sysctl_udp_rmem_min __read_mostly;
-int sysctl_udp_wmem_min __read_mostly;
-
EXPORT_SYMBOL(sysctl_udp_mem);
+
+int sysctl_udp_rmem_min __read_mostly;
EXPORT_SYMBOL(sysctl_udp_rmem_min);
+
+int sysctl_udp_wmem_min __read_mostly;
EXPORT_SYMBOL(sysctl_udp_wmem_min);
atomic_t udp_memory_allocated;
@@ -158,7 +159,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
*/
int udp_lib_get_port(struct sock *sk, unsigned short snum,
int (*saddr_comp)(const struct sock *sk1,
- const struct sock *sk2 ) )
+ const struct sock *sk2))
{
struct udp_hslot *hslot;
struct udp_table *udptable = sk->sk_prot->h.udp_table;
@@ -221,14 +222,15 @@ fail_unlock:
fail:
return error;
}
+EXPORT_SYMBOL(udp_lib_get_port);
static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
- return ( !ipv6_only_sock(sk2) &&
- (!inet1->rcv_saddr || !inet2->rcv_saddr ||
- inet1->rcv_saddr == inet2->rcv_saddr ));
+ return (!ipv6_only_sock(sk2) &&
+ (!inet1->rcv_saddr || !inet2->rcv_saddr ||
+ inet1->rcv_saddr == inet2->rcv_saddr));
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
@@ -383,8 +385,8 @@ found:
void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
- struct iphdr *iph = (struct iphdr*)skb->data;
- struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
+ struct iphdr *iph = (struct iphdr *)skb->data;
+ struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
@@ -439,7 +441,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
- ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
+ ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));
}
sk->sk_err = err;
sk->sk_error_report(sk);
@@ -474,7 +476,7 @@ EXPORT_SYMBOL(udp_flush_pending_frames);
* (checksum field must be zeroed out)
*/
static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
- __be32 src, __be32 dst, int len )
+ __be32 src, __be32 dst, int len)
{
unsigned int offset;
struct udphdr *uh = udp_hdr(skb);
@@ -545,7 +547,7 @@ static int udp_push_pending_frames(struct sock *sk)
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
- udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len);
+ udp4_hwcsum_outgoing(sk, skb, fl->fl4_src, fl->fl4_dst, up->len);
goto send;
} else /* `normal' UDP */
@@ -553,7 +555,7 @@ static int udp_push_pending_frames(struct sock *sk)
/* add protocol-dependent pseudo-header */
uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
- sk->sk_protocol, csum );
+ sk->sk_protocol, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
@@ -592,7 +594,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
* Check the flags.
*/
- if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */
+ if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */
return -EOPNOTSUPP;
ipc.opt = NULL;
@@ -619,7 +621,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
* Get and verify the address.
*/
if (msg->msg_name) {
- struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
+ struct sockaddr_in * usin = (struct sockaddr_in *)msg->msg_name;
if (msg->msg_namelen < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET) {
@@ -684,7 +686,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
}
if (connected)
- rt = (struct rtable*)sk_dst_check(sk, 0);
+ rt = (struct rtable *)sk_dst_check(sk, 0);
if (rt == NULL) {
struct flowi fl = { .oif = ipc.oif,
@@ -782,6 +784,7 @@ do_confirm:
err = 0;
goto out;
}
+EXPORT_SYMBOL(udp_sendmsg);
int udp_sendpage(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
@@ -871,6 +874,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return 0;
}
+EXPORT_SYMBOL(udp_ioctl);
/*
* This should be easy, if there is something there we
@@ -892,7 +896,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
* Check any passed addresses
*/
if (addr_len)
- *addr_len=sizeof(*sin);
+ *addr_len = sizeof(*sin);
if (flags & MSG_ERRQUEUE)
return ip_recv_error(sk, msg, len);
@@ -923,9 +927,11 @@ try_again:
if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
- msg->msg_iov, copied );
+ msg->msg_iov, copied);
else {
- err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
+ err = skb_copy_and_csum_datagram_iovec(skb,
+ sizeof(struct udphdr),
+ msg->msg_iov);
if (err == -EINVAL)
goto csum_copy_err;
@@ -941,8 +947,7 @@ try_again:
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
- if (sin)
- {
+ if (sin) {
sin->sin_family = AF_INET;
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
@@ -995,6 +1000,7 @@ int udp_disconnect(struct sock *sk, int flags)
sk_dst_reset(sk);
return 0;
}
+EXPORT_SYMBOL(udp_disconnect);
void udp_lib_unhash(struct sock *sk)
{
@@ -1044,7 +1050,7 @@ drop:
* Note that in the success and error cases, the skb is assumed to
* have either been requeued or freed.
*/
-int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
+int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int rc;
@@ -1214,7 +1220,7 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
if (uh->check == 0) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
proto, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
@@ -1355,7 +1361,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
int err = 0;
int is_udplite = IS_UDPLITE(sk);
- if (optlen<sizeof(int))
+ if (optlen < sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
@@ -1426,6 +1432,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
return err;
}
+EXPORT_SYMBOL(udp_lib_setsockopt);
int udp_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen)
@@ -1453,7 +1460,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
struct udp_sock *up = udp_sk(sk);
int val, len;
- if (get_user(len,optlen))
+ if (get_user(len, optlen))
return -EFAULT;
len = min_t(unsigned int, len, sizeof(int));
@@ -1486,10 +1493,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval, &val,len))
+ if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
+EXPORT_SYMBOL(udp_lib_getsockopt);
int udp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
@@ -1528,9 +1536,9 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
int is_lite = IS_UDPLITE(sk);
/* Check for false positives due to checksum errors */
- if ( (mask & POLLRDNORM) &&
- !(file->f_flags & O_NONBLOCK) &&
- !(sk->sk_shutdown & RCV_SHUTDOWN)){
+ if ((mask & POLLRDNORM) &&
+ !(file->f_flags & O_NONBLOCK) &&
+ !(sk->sk_shutdown & RCV_SHUTDOWN)) {
struct sk_buff_head *rcvq = &sk->sk_receive_queue;
struct sk_buff *skb;
@@ -1552,6 +1560,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
return mask;
}
+EXPORT_SYMBOL(udp_poll);
struct proto udp_prot = {
.name = "UDP",
@@ -1582,6 +1591,7 @@ struct proto udp_prot = {
.compat_getsockopt = compat_udp_getsockopt,
#endif
};
+EXPORT_SYMBOL(udp_prot);
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
@@ -1703,11 +1713,13 @@ int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo)
rc = -ENOMEM;
return rc;
}
+EXPORT_SYMBOL(udp_proc_register);
void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
{
proc_net_remove(net, afinfo->name);
}
+EXPORT_SYMBOL(udp_proc_unregister);
/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, struct seq_file *f,
@@ -1741,7 +1753,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
int len;
udp4_format_sock(v, seq, state->bucket, &len);
- seq_printf(seq, "%*s\n", 127 - len ,"");
+ seq_printf(seq, "%*s\n", 127 - len, "");
}
return 0;
}
@@ -1816,16 +1828,64 @@ void __init udp_init(void)
sysctl_udp_wmem_min = SK_MEM_QUANTUM;
}
-EXPORT_SYMBOL(udp_disconnect);
-EXPORT_SYMBOL(udp_ioctl);
-EXPORT_SYMBOL(udp_prot);
-EXPORT_SYMBOL(udp_sendmsg);
-EXPORT_SYMBOL(udp_lib_getsockopt);
-EXPORT_SYMBOL(udp_lib_setsockopt);
-EXPORT_SYMBOL(udp_poll);
-EXPORT_SYMBOL(udp_lib_get_port);
+int udp4_ufo_send_check(struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ struct udphdr *uh;
+
+ if (!pskb_may_pull(skb, sizeof(*uh)))
+ return -EINVAL;
+
+ iph = ip_hdr(skb);
+ uh = udp_hdr(skb);
+
+ uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ IPPROTO_UDP, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ return 0;
+}
+
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int mss;
+ int offset;
+ __wsum csum;
+
+ 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;
+
+ if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+ !(type & (SKB_GSO_UDP))))
+ goto out;
+
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+ segs = NULL;
+ goto out;
+ }
+
+ /* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+ * do checksum of UDP packets sent as multiple IP fragments.
+ */
+ offset = skb->csum_start - skb_headroom(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
+ /* Fragment the skb. IP headers of the fragments are updated in
+ * inet_gso_segment()
+ */
+ segs = skb_segment(skb, features);
+out:
+ return segs;
+}
-#ifdef CONFIG_PROC_FS
-EXPORT_SYMBOL(udp_proc_register);
-EXPORT_SYMBOL(udp_proc_unregister);
-#endif
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 0071ee6f441..1ba44742ebb 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -264,6 +264,20 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.fill_dst = xfrm4_fill_dst,
};
+static struct ctl_table xfrm4_policy_table[] = {
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "xfrm4_gc_thresh",
+ .data = &xfrm4_dst_ops.gc_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ { }
+};
+
+static struct ctl_table_header *sysctl_hdr;
+
static void __init xfrm4_policy_init(void)
{
xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
@@ -271,12 +285,27 @@ static void __init xfrm4_policy_init(void)
static void __exit xfrm4_policy_fini(void)
{
+ if (sysctl_hdr)
+ unregister_net_sysctl_table(sysctl_hdr);
xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
}
-void __init xfrm4_init(void)
+void __init xfrm4_init(int rt_max_size)
{
xfrm4_state_init();
xfrm4_policy_init();
+ /*
+ * Select a default value for the gc_thresh based on the main route
+ * table hash size. It seems to me the worst case scenario is when
+ * we have ipsec operating in transport mode, in which we create a
+ * dst_entry per socket. The xfrm gc algorithm starts trying to remove
+ * entries at gc_thresh, and prevents new allocations as 2*gc_thresh
+ * so lets set an initial xfrm gc_thresh value at the rt_max_size/2.
+ * That will let us store an ipsec connection per route table entry,
+ * and start cleaning when were 1/2 full
+ */
+ xfrm4_dst_ops.gc_thresh = rt_max_size/2;
+ sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path,
+ xfrm4_policy_table);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-20 00:34:35 +0000