summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_frontend.c5
-rw-r--r--net/ipv4/igmp.c62
-rw-r--r--net/ipv4/inet_fragment.c8
-rw-r--r--net/ipv4/ip_fragment.c5
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c11
-rw-r--r--net/ipv4/netfilter/ip_tables.c1
-rw-r--r--net/ipv4/netfilter/nf_tproxy_ipv4.c18
-rw-r--r--net/ipv4/sysctl_net_ipv4.c5
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bbr.c4
-rw-r--r--net/ipv4/tcp_dctcp.c75
-rw-r--r--net/ipv4/tcp_input.c74
-rw-r--r--net/ipv4/tcp_ipv4.c23
-rw-r--r--net/ipv4/tcp_output.c36
15 files changed, 213 insertions, 132 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b21833651394..2998b0e47d4b 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -292,18 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
return ip_hdr(skb)->daddr;
in_dev = __in_dev_get_rcu(dev);
- BUG_ON(!in_dev);
net = dev_net(dev);
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
+ bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
struct flowi4 fl4 = {
.flowi4_iif = LOOPBACK_IFINDEX,
+ .flowi4_oif = l3mdev_master_ifindex_rcu(dev),
.daddr = ip_hdr(skb)->saddr,
.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
.flowi4_scope = scope,
- .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+ .flowi4_mark = vmark ? skb->mark : 0,
};
if (!fib_lookup(net, &fl4, &res, 0))
return FIB_RES_PREFSRC(net, res);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 85b617b655bc..75151be21413 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
spin_lock_bh(&im->lock);
if (pmc) {
im->interface = pmc->interface;
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- im->sfmode = pmc->sfmode;
- if (pmc->sfmode == MCAST_INCLUDE) {
+ if (im->sfmode == MCAST_INCLUDE) {
im->tomb = pmc->tomb;
im->sources = pmc->sources;
for (psf = im->sources; psf; psf = psf->sf_next)
- psf->sf_crcount = im->crcount;
+ psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ } else {
+ im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
}
in_dev_put(pmc->interface);
kfree(pmc);
@@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im)
#endif
}
-static void igmp_group_added(struct ip_mc_list *im)
+static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
{
struct in_device *in_dev = im->interface;
#ifdef CONFIG_IP_MULTICAST
@@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im)
}
/* else, v3 */
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should
+ * not send filter-mode change record as the mode should be from
+ * IN() to IN(A).
+ */
+ if (mode == MCAST_EXCLUDE)
+ im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+
igmp_ifc_event(in_dev);
#endif
}
@@ -1381,8 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev,
/*
* A socket has joined a multicast group on device dev.
*/
-
-void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
+ unsigned int mode)
{
struct ip_mc_list *im;
#ifdef CONFIG_IP_MULTICAST
@@ -1394,7 +1400,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
for_each_pmc_rtnl(in_dev, im) {
if (im->multiaddr == addr) {
im->users++;
- ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0);
+ ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0);
goto out;
}
}
@@ -1408,8 +1414,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
in_dev_hold(in_dev);
im->multiaddr = addr;
/* initial mode is (EX, empty) */
- im->sfmode = MCAST_EXCLUDE;
- im->sfcount[MCAST_EXCLUDE] = 1;
+ im->sfmode = mode;
+ im->sfcount[mode] = 1;
refcount_set(&im->refcnt, 1);
spin_lock_init(&im->lock);
#ifdef CONFIG_IP_MULTICAST
@@ -1426,12 +1432,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, im);
#endif
- igmp_group_added(im);
+ igmp_group_added(im, mode);
if (!in_dev->dead)
ip_rt_multicast_event(in_dev);
out:
return;
}
+
+void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+{
+ __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+}
EXPORT_SYMBOL(ip_mc_inc_group);
static int ip_mc_check_iphdr(struct sk_buff *skb)
@@ -1688,7 +1699,7 @@ void ip_mc_remap(struct in_device *in_dev)
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, pmc);
#endif
- igmp_group_added(pmc);
+ igmp_group_added(pmc, pmc->sfmode);
}
}
@@ -1751,7 +1762,7 @@ void ip_mc_up(struct in_device *in_dev)
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, pmc);
#endif
- igmp_group_added(pmc);
+ igmp_group_added(pmc, pmc->sfmode);
}
}
@@ -2130,8 +2141,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc)
/* Join a multicast group
*/
-
-int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
+ unsigned int mode)
{
__be32 addr = imr->imr_multiaddr.s_addr;
struct ip_mc_socklist *iml, *i;
@@ -2172,15 +2183,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
memcpy(&iml->multi, imr, sizeof(*imr));
iml->next_rcu = inet->mc_list;
iml->sflist = NULL;
- iml->sfmode = MCAST_EXCLUDE;
+ iml->sfmode = mode;
rcu_assign_pointer(inet->mc_list, iml);
- ip_mc_inc_group(in_dev, addr);
+ __ip_mc_inc_group(in_dev, addr, mode);
err = 0;
done:
return err;
}
+
+/* Join ASM (Any-Source Multicast) group
+ */
+int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+{
+ return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE);
+}
EXPORT_SYMBOL(ip_mc_join_group);
+/* Join SSM (Source-Specific Multicast) group
+ */
+int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+ unsigned int mode)
+{
+ return __ip_mc_join_group(sk, imr, mode);
+}
+
static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
struct in_device *in_dev)
{
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c9e35b81d093..0d70608cc2e1 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg)
void inet_frags_exit_net(struct netns_frags *nf)
{
- nf->low_thresh = 0; /* prevent creation of new frags */
+ nf->high_thresh = 0; /* prevent creation of new frags */
rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
@@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
{
struct inet_frag_queue *q;
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
- return NULL;
-
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
return NULL;
@@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
struct inet_frag_queue *fq;
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+ return NULL;
+
rcu_read_lock();
fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8e9528ebaa8e..d14d741fb05e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -383,11 +383,16 @@ found:
int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
if (i < next->len) {
+ int delta = -next->truesize;
+
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
+ delta += next->truesize;
+ if (delta)
+ add_frag_mem_limit(qp->q.net, delta);
next->ip_defrag_offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..0e3edd25f881 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->dev = from->dev;
to->mark = from->mark;
+ skb_copy_hash(to, from);
+
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fc32fdbeefa6..c0fe5ad996f2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
const struct iphdr *iph = ip_hdr(skb);
- __be16 *ports = (__be16 *)skb_transport_header(skb);
+ __be16 *ports;
+ int end;
- if (skb_transport_offset(skb) + 4 > (int)skb->len)
+ end = skb_transport_offset(skb) + 4;
+ if (end > 0 && !pskb_may_pull(skb, end))
return;
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = iph->daddr;
@@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
- err = ip_mc_join_group(sk, &mreq);
+ err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
@@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
- err = ip_mc_join_group(sk, &mreq);
+ err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ca0dad90803a..e77872c93c20 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = {
.checkentry = icmp_checkentry,
.proto = IPPROTO_ICMP,
.family = NFPROTO_IPV4,
+ .me = THIS_MODULE,
},
};
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 805e83ec3ad9..164714104965 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
* to a listener socket if there's one */
struct sock *sk2;
- sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+ sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
iph->saddr, laddr ? laddr : iph->daddr,
hp->source, lport ? lport : hp->dest,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
@@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
@@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
const enum nf_tproxy_lookup_t lookup_type)
{
struct sock *sk;
- struct tcphdr *tcph;
switch (protocol) {
- case IPPROTO_TCP:
+ case IPPROTO_TCP: {
+ struct tcphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, ip_hdrlen(skb),
+ sizeof(struct tcphdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
switch (lookup_type) {
case NF_TPROXY_LOOKUP_LISTENER:
- tcph = hp;
sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
ip_hdrlen(skb) +
- __tcp_hdrlen(tcph),
+ __tcp_hdrlen(hp),
saddr, sport,
daddr, dport,
in->ifindex, 0);
@@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
BUG();
}
break;
+ }
case IPPROTO_UDP:
sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index af0a857d8352..5fa335fd3852 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
if (write && ret == 0) {
low = make_kgid(user_ns, urange[0]);
high = make_kgid(user_ns, urange[1]);
- if (!gid_valid(low) || !gid_valid(high) ||
- (urange[1] < urange[0]) || gid_lt(high, low)) {
+ if (!gid_valid(low) || !gid_valid(high))
+ return -EINVAL;
+ if (urange[1] < urange[0] || gid_lt(high, low)) {
low = make_kgid(&init_user_ns, 1);
high = make_kgid(&init_user_ns, 0);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e7b53d2a971f..4491faf83f4f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1998,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
* shouldn't happen.
*/
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
- "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
flags))
break;
@@ -2013,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
- "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+ "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
@@ -2562,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags)
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
+ tp->copied_seq = tp->rcv_nxt;
+ tp->urg_data = 0;
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
skb_rbtree_purge(&tp->out_of_order_queue);
@@ -2821,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_REPAIR:
if (!tcp_can_repair_sock(sk))
err = -EPERM;
- else if (val == 1) {
+ else if (val == TCP_REPAIR_ON) {
tp->repair = 1;
sk->sk_reuse = SK_FORCE_REUSE;
tp->repair_queue = TCP_NO_QUEUE;
- } else if (val == 0) {
+ } else if (val == TCP_REPAIR_OFF) {
tp->repair = 0;
sk->sk_reuse = SK_NO_REUSE;
tcp_send_window_probe(sk);
+ } else if (val == TCP_REPAIR_OFF_NO_WP) {
+ tp->repair = 0;
+ sk->sk_reuse = SK_NO_REUSE;
} else
err = -EINVAL;
@@ -3720,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err)
struct request_sock *req = inet_reqsk(sk);
local_bh_disable();
- inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
- req);
+ inet_csk_reqsk_queue_drop(req->rsk_listener, req);
local_bh_enable();
return 0;
}
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 58e2f479ffb4..4bfff3c87e8e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
cwnd = (cwnd + 1) & ~1U;
+ /* Ensure gain cycling gets inflight above BDP even for small BDPs. */
+ if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+ cwnd += 2;
+
return cwnd;
}
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..8b637f9f23a2 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
u32 dctcp_alpha;
u32 next_seq;
u32 ce_state;
- u32 delayed_ack_reserved;
u32 loss_cwnd;
};
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
- ca->delayed_ack_reserved = 0;
ca->loss_cwnd = 0;
ca->ce_state = 0;
@@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=0 to CE=1 and delayed
- * ACK has not sent yet.
- */
- if (!ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=0. */
- tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (!ca->ce_state) {
+ /* State has changed from CE=0 to CE=1, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- /* State has changed from CE=1 to CE=0 and delayed
- * ACK has not sent yet.
- */
- if (ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=1. */
- tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (ca->ce_state) {
+ /* State has changed from CE=1 to CE=0, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk, 1);
}
ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
}
}
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
- struct dctcp *ca = inet_csk_ca(sk);
-
- switch (ev) {
- case CA_EVENT_DELAYED_ACK:
- if (!ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 1;
- break;
- case CA_EVENT_NON_DELAYED_ACK:
- if (ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 0;
- break;
- default:
- /* Don't care for the rest. */
- break;
- }
-}
-
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
switch (ev) {
@@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
- case CA_EVENT_DELAYED_ACK:
- case CA_EVENT_NON_DELAYED_ACK:
- dctcp_update_ack_reserved(sk, ev);
- break;
default:
/* Don't care for the rest. */
break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8e5522c6833a..f9dcb29be12d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.quick = quickacks;
}
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
@@ -245,8 +246,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
{
- if (tcp_hdr(skb)->cwr)
+ if (tcp_hdr(skb)->cwr) {
tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+
+ /* If the sender is telling us it has entered CWR, then its
+ * cwnd may be very low (even just 1 packet), so we should ACK
+ * immediately.
+ */
+ tcp_enter_quickack_mode((struct sock *)tp, 2);
+ }
}
static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
@@ -4357,6 +4365,23 @@ static bool tcp_try_coalesce(struct sock *sk,
return true;
}
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+ struct sk_buff *to,
+ struct sk_buff *from,
+ bool *fragstolen)
+{
+ bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+ /* In case tcp_drop() is called later, update to->gso_segs */
+ if (res) {
+ u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+ max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+ skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+ }
+ return res;
+}
+
static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
sk_drops_add(sk, skb);
@@ -4480,8 +4505,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, tp->ooo_last_skb,
- skb, &fragstolen)) {
+ if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+ skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
kfree_skb_partial(skb, fragstolen);
@@ -4509,7 +4534,7 @@ coalesce_done:
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb);
+ tcp_drop(sk, skb);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
@@ -4528,11 +4553,11 @@ coalesce_done:
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb1);
+ tcp_drop(sk, skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, skb1,
- skb, &fragstolen)) {
+ } else if (tcp_ooo_try_coalesce(sk, skb1,
+ skb, &fragstolen)) {
goto coalesce_done;
}
p = &parent->rb_right;
@@ -4901,6 +4926,7 @@ end:
static void tcp_collapse_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 range_truesize, sum_tiny = 0;
struct sk_buff *skb, *head;
u32 start, end;
@@ -4912,6 +4938,7 @@ new_range:
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
+ range_truesize = skb->truesize;
for (head = skb;;) {
skb = skb_rb_next(skb);
@@ -4922,11 +4949,20 @@ new_range:
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, NULL, &tp->out_of_order_queue,
- head, skb, start, end);
+ /* Do not attempt collapsing tiny skbs */
+ if (range_truesize != head->truesize ||
+ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+ tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+ head, skb, start, end);
+ } else {
+ sum_tiny += range_truesize;
+ if (sum_tiny > sk->sk_rcvbuf >> 3)
+ return;
+ }
goto new_range;
}
+ range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4941,6 +4977,7 @@ new_range:
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
@@ -4948,20 +4985,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
+ int goal;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;
NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+ goal = sk->sk_rcvbuf >> 3;
node = &tp->ooo_last_skb->rbnode;
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
+ goal -= rb_to_skb(node)->truesize;
tcp_drop(sk, rb_to_skb(node));
- sk_mem_reclaim(sk);
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !tcp_under_memory_pressure(sk))
- break;
+ if (!prev || goal <= 0) {
+ sk_mem_reclaim(sk);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ !tcp_under_memory_pressure(sk))
+ break;
+ goal = sk->sk_rcvbuf >> 3;
+ }
node = prev;
} while (node);
tp->ooo_last_skb = rb_to_skb(prev);
@@ -4996,6 +5039,9 @@ static int tcp_prune_queue(struct sock *sk)
else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+ return 0;
+
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bea17f1e8302..3b2711e33e4c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
*/
if (tcptw->tw_ts_recent_stamp &&
(!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
- tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
- tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
- tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ /* In case of repair and re-using TIME-WAIT sockets we still
+ * want to be sure that it is safe as above but honor the
+ * sequence numbers and time stamps set as part of the repair
+ * process.
+ *
+ * Without this check re-using a TIME-WAIT socket with TCP
+ * repair would accumulate a -1 on the repair assigned
+ * sequence number. The first time it is reused the sequence
+ * is -1, the second time -2, etc. This fixes that issue
+ * without appearing to create any others.
+ */
+ if (likely(!tp->repair)) {
+ tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+ if (tp->write_seq == 0)
+ tp->write_seq = 1;
+ tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+ tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ }
sock_hold(sktw);
return 1;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
}
/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+ u32 rcv_nxt)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
}
+
+ if (unlikely(rcv_nxt != tp->rcv_nxt))
+ return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
- gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+ int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
- th->ack_seq = htonl(tp->rcv_nxt);
+ th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
return err;
}
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+ gfp_t gfp_mask)
+{
+ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+ tcp_sk(sk)->rcv_nxt);
+}
+
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk)
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
- tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
@@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
}
/* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;
@@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk)
if (sk->sk_state == TCP_CLOSE)
return;
- tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
@@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
skb_set_tcp_pure_ack(buff);
/* Send it off, this clears delayed acks for us. */
- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
-EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-24 23:01:06 +0000