summaryrefslogtreecommitdiff
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/esp4.c6
-rw-r--r--net/ipv4/icmp.c53
-rw-r--r--net/ipv4/inet_fragment.c20
-rw-r--r--net/ipv4/ip_fragment.c26
-rw-r--r--net/ipv4/ip_gre.c5
-rw-r--r--net/ipv4/ip_options.c5
-rw-r--r--net/ipv4/ip_output.c5
-rw-r--r--net/ipv4/netfilter/ipt_rpfilter.c8
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/syncookies.c4
-rw-r--r--net/ipv4/sysctl_net_ipv4.c7
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c77
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/tcp_output.c34
16 files changed, 94 insertions, 187 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fcf104e..24b384b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -248,12 +248,8 @@ EXPORT_SYMBOL(inet_listen);
u32 inet_ehash_secret __read_mostly;
EXPORT_SYMBOL(inet_ehash_secret);
-u32 ipv6_hash_secret __read_mostly;
-EXPORT_SYMBOL(ipv6_hash_secret);
-
/*
- * inet_ehash_secret must be set exactly once, and to a non nul value
- * ipv6_hash_secret must be set exactly once.
+ * inet_ehash_secret must be set exactly once
*/
void build_ehash_secret(void)
{
@@ -263,8 +259,7 @@ void build_ehash_secret(void)
get_random_bytes(&rnd, sizeof(rnd));
} while (rnd == 0);
- if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
- get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
+ cmpxchg(&inet_ehash_secret, 0, rnd);
}
EXPORT_SYMBOL(build_ehash_secret);
@@ -1595,7 +1590,7 @@ static const struct net_offload udp_offload = {
static const struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
- .err_handler = icmp_err,
+ .err_handler = ping_err,
.no_policy = 1,
.netns_ok = 1,
};
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4cfe34d..3b4f0cd 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -139,6 +139,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
/* skb is pure payload to encrypt */
+ err = -ENOMEM;
+
esp = x->data;
aead = esp->aead;
alen = crypto_aead_authsize(aead);
@@ -174,10 +176,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
}
tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
- if (!tmp) {
- err = -ENOMEM;
+ if (!tmp)
goto error;
- }
seqhi = esp_tmp_seqhi(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d8bbe94..17ff9fd 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -69,7 +69,6 @@
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
-#include <linux/sysrq.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
@@ -769,30 +768,6 @@ static void icmp_redirect(struct sk_buff *skb)
}
/*
- * 32bit and 64bit have different timestamp length, so we check for
- * the cookie at offset 20 and verify it is repeated at offset 50
- */
-#define CO_POS0 20
-#define CO_POS1 50
-#define CO_SIZE sizeof(int)
-#define ICMP_SYSRQ_SIZE 57
-
-/*
- * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie
- * pattern and if it matches send the next byte as a trigger to sysrq.
- */
-static void icmp_check_sysrq(struct net *net, struct sk_buff *skb)
-{
- int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq);
- char *p = skb->data;
-
- if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) &&
- !memcmp(&cookie, p + CO_POS1, CO_SIZE) &&
- p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE])
- handle_sysrq(p[CO_POS0 + CO_SIZE]);
-}
-
-/*
* Handle ICMP_ECHO ("ping") requests.
*
* RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
@@ -819,11 +794,6 @@ static void icmp_echo(struct sk_buff *skb)
icmp_param.data_len = skb->len;
icmp_param.head_len = sizeof(struct icmphdr);
icmp_reply(&icmp_param, skb);
-
- if (skb->len == ICMP_SYSRQ_SIZE &&
- net->ipv4.sysctl_icmp_echo_sysrq) {
- icmp_check_sysrq(net, skb);
- }
}
}
@@ -964,29 +934,6 @@ error:
goto drop;
}
-void icmp_err(struct sk_buff *skb, u32 info)
-{
- struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
- int type = icmp_hdr(skb)->type;
- int code = icmp_hdr(skb)->code;
- struct net *net = dev_net(skb->dev);
-
- /*
- * Use ping_err to handle all icmp errors except those
- * triggered by ICMP_ECHOREPLY which sent from kernel.
- */
- if (icmph->type != ICMP_ECHOREPLY) {
- ping_err(skb, info);
- return;
- }
-
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
- else if (type == ICMP_REDIRECT)
- ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
-}
-
/*
* This table is the definition of how we handle ICMP.
*/
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 03f5af7..4750d2b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -21,7 +21,6 @@
#include <linux/rtnetlink.h>
#include <linux/slab.h>
-#include <net/sock.h>
#include <net/inet_frag.h>
static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -277,7 +276,6 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
{
struct inet_frag_queue *q;
struct hlist_node *n;
- int depth = 0;
hlist_for_each_entry(q, n, &f->hash[hash], list) {
if (q->net == nf && f->match(q, key)) {
@@ -285,25 +283,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
read_unlock(&f->lock);
return q;
}
- depth++;
}
read_unlock(&f->lock);
- if (depth <= INETFRAGS_MAXDEPTH)
- return inet_frag_create(nf, f, key);
- else
- return ERR_PTR(-ENOBUFS);
+ return inet_frag_create(nf, f, key);
}
EXPORT_SYMBOL(inet_frag_find);
-
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix)
-{
- static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
- ". Dropping fragment.\n";
-
- if (PTR_ERR(q) == -ENOBUFS)
- LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
-}
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0fcfee3..eb9d63a 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -255,7 +255,8 @@ static void ip_expire(unsigned long arg)
if (!head->dev)
goto out_rcu_unlock;
- /* skb has no dst, perform route lookup again */
+ /* skb dst is stale, drop it, and perform route lookup again */
+ skb_dst_drop(head);
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
@@ -298,11 +299,14 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
- return NULL;
- }
+ if (q == NULL)
+ goto out_nomem;
+
return container_of(q, struct ipq, q);
+
+out_nomem:
+ LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
+ return NULL;
}
/* Is the fragment too far ahead to be part of ipq? */
@@ -524,16 +528,8 @@ found:
qp->q.max_size = skb->len + ihl;
if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- qp->q.meat == qp->q.len) {
- unsigned long orefdst = skb->_skb_refdst;
-
- skb->_skb_refdst = 0UL;
- err = ip_frag_reasm(qp, prev, dev);
- skb->_skb_refdst = orefdst;
- return err;
- }
-
- skb_dst_drop(skb);
+ qp->q.meat == qp->q.len)
+ return ip_frag_reasm(qp, prev, dev);
write_lock(&ip4_frags.lock);
list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a85062b..e81b1ca 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -761,7 +761,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
- tiph = (const struct iphdr *)skb->data;
+ if (skb->protocol == htons(ETH_P_IP))
+ tiph = (const struct iphdr *)skb->data;
+ else
+ tiph = &tunnel->parms.iph;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 8433ffe..a47fc1d 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -370,6 +370,7 @@ int ip_options_compile(struct net *net,
}
switch (optptr[3]&0xF) {
case IPOPT_TS_TSONLY:
+ opt->ts = optptr - iph;
if (skb)
timeptr = &optptr[optptr[2]-1];
opt->ts_needtime = 1;
@@ -380,6 +381,7 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 2;
goto error;
}
+ opt->ts = optptr - iph;
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
@@ -394,6 +396,7 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 2;
goto error;
}
+ opt->ts = optptr - iph;
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
@@ -426,12 +429,12 @@ int ip_options_compile(struct net *net,
pp_ptr = optptr + 3;
goto error;
}
+ opt->ts = optptr - iph;
if (skb) {
optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
opt->is_changed = 1;
}
}
- opt->ts = optptr - iph;
break;
case IPOPT_RA:
if (optlen < 4) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 253692b..3e98ed2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1508,8 +1508,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
if (IS_ERR(rt))
return;
- get_cpu_light();
- inet = &__get_cpu_var(unicast_sock);
+ inet = &get_cpu_var(unicast_sock);
inet->tos = arg->tos;
sk = &inet->sk;
@@ -1533,7 +1532,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
ip_push_pending_frames(sk, &fl4);
}
- put_cpu_light();
+ put_cpu_var(unicast_sock);
ip_rt_put(rt);
}
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index c49dcd0..c301300 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -66,12 +66,6 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4,
return dev_match;
}
-static bool rpfilter_is_local(const struct sk_buff *skb)
-{
- const struct rtable *rt = skb_rtable(skb);
- return rt && (rt->rt_flags & RTCF_LOCAL);
-}
-
static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_rpfilter_info *info;
@@ -82,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
info = par->matchinfo;
invert = info->flags & XT_RPFILTER_INVERT;
- if (rpfilter_is_local(skb))
+ if (par->in->flags & IFF_LOOPBACK)
return true ^ invert;
iph = ip_hdr(skb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index dc454cc..6f9c072 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -322,8 +322,8 @@ void ping_err(struct sk_buff *skb, u32 info)
struct iphdr *iph = (struct iphdr *)skb->data;
struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
struct inet_sock *inet_sock;
- int type = icmp_hdr(skb)->type;
- int code = icmp_hdr(skb)->code;
+ int type = icmph->type;
+ int code = icmph->code;
struct net *net = dev_net(skb->dev);
struct sock *sk;
int harderr;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f962f19..b236ef0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -348,8 +348,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+ flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
+ RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
(opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
ireq->loc_addr, th->source, th->dest);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 44bf3b0..d84400b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -815,13 +815,6 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "icmp_echo_sysrq",
- .data = &init_net.ipv4.sysctl_icmp_echo_sysrq,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "icmp_ignore_bogus_error_responses",
.data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 45b63ca..2aa69c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -773,7 +773,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
* Make sure that we have exactly size bytes
* available to the caller, no more, no less.
*/
- skb->reserved_tailroom = skb->end - skb->tail - size;
+ skb->avail_size = size;
return skb;
}
__kfree_skb(skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b4e8b79..ad70a96 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -116,7 +116,6 @@ int sysctl_tcp_early_retrans __read_mostly = 2;
#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */
-#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -2065,8 +2064,11 @@ void tcp_enter_loss(struct sock *sk, int how)
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- tp->undo_marker = tp->snd_una;
- if (how) {
+ if (!how) {
+ /* Push undo marker, if it was plain RTO and nothing
+ * was retransmitted. */
+ tp->undo_marker = tp->snd_una;
+ } else {
tp->sacked_out = 0;
tp->fackets_out = 0;
}
@@ -3573,27 +3575,6 @@ static void tcp_send_challenge_ack(struct sock *sk)
}
}
-static void tcp_store_ts_recent(struct tcp_sock *tp)
-{
- tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
- tp->rx_opt.ts_recent_stamp = get_seconds();
-}
-
-static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
-{
- if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
- /* PAWS bug workaround wrt. ACK frames, the PAWS discard
- * extra check below makes sure this can only happen
- * for pure ACK frames. -DaveM
- *
- * Not only, also it occurs for expired timestamps.
- */
-
- if (tcp_paws_check(&tp->rx_opt, 0))
- tcp_store_ts_recent(tp);
- }
-}
-
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
@@ -3646,12 +3627,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
prior_fackets = tp->fackets_out;
prior_in_flight = tcp_packets_in_flight(tp);
- /* ts_recent update must be made after we are sure that the packet
- * is in window.
- */
- if (flag & FLAG_UPDATE_TS_RECENT)
- tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
/* Window is constant, pure forward advance.
* No more checks are required.
@@ -3968,6 +3943,27 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
EXPORT_SYMBOL(tcp_parse_md5sig_option);
#endif
+static inline void tcp_store_ts_recent(struct tcp_sock *tp)
+{
+ tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
+ tp->rx_opt.ts_recent_stamp = get_seconds();
+}
+
+static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+{
+ if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
+ /* PAWS bug workaround wrt. ACK frames, the PAWS discard
+ * extra check below makes sure this can only happen
+ * for pure ACK frames. -DaveM
+ *
+ * Not only, also it occurs for expired timestamps.
+ */
+
+ if (tcp_paws_check(&tp->rx_opt, 0))
+ tcp_store_ts_recent(tp);
+ }
+}
+
/* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
*
* It is not fatal. If this ACK does _not_ change critical state (seqs, window)
@@ -5502,9 +5498,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
if (tcp_checksum_complete_user(sk, skb))
goto csum_error;
- if ((int)skb->truesize > sk->sk_forward_alloc)
- goto step5;
-
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
@@ -5516,6 +5509,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
tcp_rcv_rtt_measure_ts(sk, skb);
+ if ((int)skb->truesize > sk->sk_forward_alloc)
+ goto step5;
+
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);
/* Bulk data transfer: receiver */
@@ -5563,9 +5559,14 @@ slow_path:
return 0;
step5:
- if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0)
+ if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
goto discard;
+ /* ts_recent update must be made after we are sure that the packet
+ * is in window.
+ */
+ tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
tcp_rcv_rtt_measure_ts(sk, skb);
/* Process urgent data. */
@@ -5999,8 +6000,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
/* step 5: check the ACK field */
if (true) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
- FLAG_UPDATE_TS_RECENT) > 0;
+ int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
switch (sk->sk_state) {
case TCP_SYN_RECV:
@@ -6151,6 +6151,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
}
}
+ /* ts_recent update must be made after we are sure that the packet
+ * is in window.
+ */
+ tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
/* step 6: check the URG bit */
tcp_urg(sk, skb, th);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d9130a9..eadb693 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -274,6 +274,13 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
struct inet_sock *inet = inet_sk(sk);
u32 mtu = tcp_sk(sk)->mtu_info;
+ /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
+ * send out by Linux are always <576bytes so they should go through
+ * unfragmented).
+ */
+ if (sk->sk_state == TCP_LISTEN)
+ return;
+
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -401,13 +408,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
- /* We are not interested in TCP_LISTEN and open_requests
- * (SYN-ACKs send out by Linux are always <576bytes so
- * they should go through unfragmented).
- */
- if (sk->sk_state == TCP_LISTEN)
- goto out;
-
tp->mtu_info = info;
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a9f50ee..5d45159 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1298,6 +1298,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
eat = min_t(int, len, skb_headlen(skb));
if (eat) {
__skb_pull(skb, eat);
+ skb->avail_size -= eat;
len -= eat;
if (!len)
return;
@@ -1350,8 +1351,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
return 0;
}
-/* Calculate MSS not accounting any TCP options. */
-static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
+/* Calculate MSS. Not accounting for SACKs here. */
+int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1380,15 +1381,11 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
/* Then reserve room for full set of TCP options and 8 bytes of data */
if (mss_now < 48)
mss_now = 48;
- return mss_now;
-}
-/* Calculate MSS. Not accounting for SACKs here. */
-int tcp_mtu_to_mss(struct sock *sk, int pmtu)
-{
- /* Subtract TCP options size, not including SACKs */
- return __tcp_mtu_to_mss(sk, pmtu) -
- (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
+ /* Now subtract TCP options size, not including SACKs */
+ mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);
+
+ return mss_now;
}
/* Inverse of above */
@@ -1809,11 +1806,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
goto send_now;
}
- /* Ok, it looks like it is advisable to defer.
- * Do not rearm the timer if already set to not break TCP ACK clocking.
- */
- if (!tp->tso_deferred)
- tp->tso_deferred = 1 | (jiffies << 1);
+ /* Ok, it looks like it is advisable to defer. */
+ tp->tso_deferred = 1 | (jiffies << 1);
return true;
@@ -2388,12 +2382,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- /* make sure skb->data is aligned on arches that require it
- * and check if ack-trimming & collapsing extended the headroom
- * beyond what csum_start can cover.
- */
- if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
- skb_headroom(skb) >= 0xFFFF)) {
+ /* make sure skb->data is aligned on arches that require it */
+ if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
GFP_ATOMIC);
return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
@@ -2940,7 +2930,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
*/
if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
- space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+ space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
generated by cgit v0.10.2 at 2024-11-15 20:35:24 (GMT)