summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c5
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/inet_fragment.c29
-rw-r--r--net/ipv4/ip_forward.c1
-rw-r--r--net/ipv4/ip_fragment.c37
-rw-r--r--net/ipv4/ip_input.c4
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/ip_sockglue.c6
-rw-r--r--net/ipv4/ip_tunnel_core.c2
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipmr.c4
-rw-r--r--net/ipv4/netfilter/ipt_MASQUERADE.c7
-rw-r--r--net/ipv4/netfilter/nf_nat_masquerade_ipv4.c38
-rw-r--r--net/ipv4/netfilter/nft_masq_ipv4.c4
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/tcp_input.c31
-rw-r--r--net/ipv4/tcp_output.c51
-rw-r--r--net/ipv4/tcp_timer.c22
18 files changed, 172 insertions, 80 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a34602ae27de..608a6f4223fb 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -952,17 +952,18 @@ static int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
- if (ipv4_is_zeronet(addr))
+ if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
rc = 0;
else {
__u32 haddr = ntohl(addr);
-
if (IN_CLASSA(haddr))
rc = 8;
else if (IN_CLASSB(haddr))
rc = 16;
else if (IN_CLASSC(haddr))
rc = 24;
+ else if (IN_CLASSE(haddr))
+ rc = 32;
}
return rc;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 4e5bc4b2f14e..1a4e9ff02762 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -998,7 +998,9 @@ next_chunk:
if (!inet_diag_bc_sk(bc, sk))
goto next_normal;
- sock_hold(sk);
+ if (!refcount_inc_not_zero(&sk->sk_refcnt))
+ goto next_normal;
+
num_arr[accum] = num;
sk_arr[accum] = sk;
if (++accum == SKARR_SZ)
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bcb11f3a27c0..760a9e52e02b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
- void *arg)
+ void *arg,
+ struct inet_frag_queue **prev)
{
struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
- int err;
q = inet_frag_alloc(nf, f, arg);
- if (!q)
+ if (!q) {
+ *prev = ERR_PTR(-ENOMEM);
return NULL;
-
+ }
mod_timer(&q->timer, jiffies + nf->timeout);
- err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
- f->rhash_params);
- if (err < 0) {
+ *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+ &q->node, f->rhash_params);
+ if (*prev) {
q->flags |= INET_FRAG_COMPLETE;
inet_frag_kill(q);
inet_frag_destroy(q);
@@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
- struct inet_frag_queue *fq;
+ struct inet_frag_queue *fq = NULL, *prev;
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);
- if (fq) {
+ prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+ if (!prev)
+ fq = inet_frag_create(nf, key, &prev);
+ if (prev && !IS_ERR(prev)) {
+ fq = prev;
if (!refcount_inc_not_zero(&fq->refcnt))
fq = NULL;
- rcu_read_unlock();
- return fq;
}
rcu_read_unlock();
-
- return inet_frag_create(nf, key);
+ return fq;
}
EXPORT_SYMBOL(inet_frag_find);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 32662e9e5d21..d5984d31ab93 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -72,6 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ skb->tstamp = 0;
return dst_output(net, sk, skb);
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9b0158fa431f..867be8f7f1fa 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -346,10 +346,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct rb_node **rbn, *parent;
struct sk_buff *skb1, *prev_tail;
+ int ihl, end, skb1_run_end;
struct net_device *dev;
unsigned int fragsize;
int flags, offset;
- int ihl, end;
int err = -ENOENT;
u8 ecn;
@@ -419,7 +419,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*
- * We do the same here for IPv4 (and increment an snmp counter).
+ * We do the same here for IPv4 (and increment an snmp counter) but
+ * we do not want to drop the whole queue in response to a duplicate
+ * fragment.
*/
err = -EINVAL;
@@ -444,13 +446,17 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
do {
parent = *rbn;
skb1 = rb_to_skb(parent);
+ skb1_run_end = skb1->ip_defrag_offset +
+ FRAG_CB(skb1)->frag_run_len;
if (end <= skb1->ip_defrag_offset)
rbn = &parent->rb_left;
- else if (offset >= skb1->ip_defrag_offset +
- FRAG_CB(skb1)->frag_run_len)
+ else if (offset >= skb1_run_end)
rbn = &parent->rb_right;
- else /* Found an overlap with skb1. */
- goto overlap;
+ else if (offset >= skb1->ip_defrag_offset &&
+ end <= skb1_run_end)
+ goto err; /* No new data, potential duplicate */
+ else
+ goto overlap; /* Found an overlap */
} while (*rbn);
/* Here we have parent properly set, and rbn pointing to
* one of its NULL left/right children. Insert skb.
@@ -515,6 +521,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct rb_node *rbn;
int len;
int ihlen;
+ int delta;
int err;
u8 ecn;
@@ -556,10 +563,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
if (len > 65535)
goto out_oversize;
+ delta = - head->truesize;
+
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
+ delta += head->truesize;
+ if (delta)
+ add_frag_mem_limit(qp->q.net, delta);
+
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
@@ -722,10 +735,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
if (ip_is_fragment(&iph)) {
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb) {
- if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
- return skb;
- if (pskb_trim_rcsum(skb, netoff + len))
- return skb;
+ if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
+ kfree_skb(skb);
+ return NULL;
+ }
+ if (pskb_trim_rcsum(skb, netoff + len)) {
+ kfree_skb(skb);
+ return NULL;
+ }
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (ip_defrag(net, skb, user))
return NULL;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 35a786c0aaa0..e609b08c9df4 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -547,7 +547,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
list_for_each_entry_safe(skb, next, head, list) {
struct dst_entry *dst;
- list_del(&skb->list);
+ skb_list_del_init(skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
@@ -594,7 +594,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
- list_del(&skb->list);
+ skb_list_del_init(skb);
skb = ip_rcv_core(skb, net);
if (skb == NULL)
continue;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c09219e7f230..5dbec21856f4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk,
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
- unsigned int pagedlen = 0;
+ unsigned int pagedlen;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
@@ -956,6 +956,7 @@ alloc_new_skb:
if (datalen > mtu - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
+ pagedlen = 0;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 26c36cccabdc..fffcc130900e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level,
return -ENOPROTOOPT;
err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
optname < BPFILTER_IPT_SET_MAX)
err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
@@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level,
int err;
err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0);
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
if (optname >= BPFILTER_IPT_SO_GET_INFO &&
optname < BPFILTER_IPT_GET_MAX)
err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
@@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
err = do_ip_getsockopt(sk, level, optname, optval, optlen,
MSG_CMSG_COMPAT);
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
if (optname >= BPFILTER_IPT_SO_GET_INFO &&
optname < BPFILTER_IPT_GET_MAX)
err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index dde671e97829..c248e0dccbe1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
+ iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 88212615bf4c..2393e5c106bf 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -429,6 +429,8 @@ static int __init ic_defaults(void)
ic_netmask = htonl(IN_CLASSB_NET);
else if (IN_CLASSC(ntohl(ic_myaddr)))
ic_netmask = htonl(IN_CLASSC_NET);
+ else if (IN_CLASSE(ntohl(ic_myaddr)))
+ ic_netmask = htonl(IN_CLASSE_NET);
else {
pr_err("IP-Config: Unable to guess netmask for address %pI4\n",
&ic_myaddr);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a6defbec4f1b..e7a3879cedd0 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -69,6 +69,8 @@
#include <net/nexthop.h>
#include <net/switchdev.h>
+#include <linux/nospec.h>
+
struct ipmr_rule {
struct fib_rule common;
};
@@ -1612,6 +1614,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
return -EFAULT;
if (vr.vifi >= mrt->maxvif)
return -EINVAL;
+ vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
read_lock(&mrt_lock);
vif = &mrt->vif_table[vr.vifi];
if (VIF_EXISTS(mrt, vr.vifi)) {
@@ -1686,6 +1689,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
return -EFAULT;
if (vr.vifi >= mrt->maxvif)
return -EINVAL;
+ vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
read_lock(&mrt_lock);
vif = &mrt->vif_table[vr.vifi];
if (VIF_EXISTS(mrt, vr.vifi)) {
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index ce1512b02cb2..fd3f9e8a74da 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void)
int ret;
ret = xt_register_target(&masquerade_tg_reg);
+ if (ret)
+ return ret;
- if (ret == 0)
- nf_nat_masquerade_ipv4_register_notifier();
+ ret = nf_nat_masquerade_ipv4_register_notifier();
+ if (ret)
+ xt_unregister_target(&masquerade_tg_reg);
return ret;
}
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index a9d5e013e555..41327bb99093 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -147,28 +147,50 @@ static struct notifier_block masq_inet_notifier = {
.notifier_call = masq_inet_event,
};
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
-void nf_nat_masquerade_ipv4_register_notifier(void)
+int nf_nat_masquerade_ipv4_register_notifier(void)
{
+ int ret = 0;
+
+ mutex_lock(&masq_mutex);
/* check if the notifier was already set */
- if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
- return;
+ if (++masq_refcnt > 1)
+ goto out_unlock;
/* Register for device down reports */
- register_netdevice_notifier(&masq_dev_notifier);
+ ret = register_netdevice_notifier(&masq_dev_notifier);
+ if (ret)
+ goto err_dec;
/* Register IP address change reports */
- register_inetaddr_notifier(&masq_inet_notifier);
+ ret = register_inetaddr_notifier(&masq_inet_notifier);
+ if (ret)
+ goto err_unregister;
+
+ mutex_unlock(&masq_mutex);
+ return ret;
+
+err_unregister:
+ unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+ masq_refcnt--;
+out_unlock:
+ mutex_unlock(&masq_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
void nf_nat_masquerade_ipv4_unregister_notifier(void)
{
+ mutex_lock(&masq_mutex);
/* check if the notifier still has clients */
- if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
- return;
+ if (--masq_refcnt > 0)
+ goto out_unlock;
unregister_netdevice_notifier(&masq_dev_notifier);
unregister_inetaddr_notifier(&masq_inet_notifier);
+out_unlock:
+ mutex_unlock(&masq_mutex);
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index f1193e1e928a..6847de1d1db8 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void)
if (ret < 0)
return ret;
- nf_nat_masquerade_ipv4_register_notifier();
+ ret = nf_nat_masquerade_ipv4_register_notifier();
+ if (ret)
+ nft_unregister_expr(&nft_masq_ipv4_type);
return ret;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8ca3eb06ba04..169a652b3dd1 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
skb->ip_summed = CHECKSUM_NONE;
- sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
+ skb_setup_tx_timestamp(skb, sockc->tsflags);
if (flags & MSG_CONFIRM)
skb_set_dst_pending_confirm(skb, 1);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2868ef28ce52..a9d9555a973f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
u32 delta_us;
- if (!delta)
- delta = 1;
- delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
- tcp_rcv_rtt_update(tp, delta_us, 0);
+ if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+ if (!delta)
+ delta = 1;
+ delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+ tcp_rcv_rtt_update(tp, delta_us, 0);
+ }
}
}
@@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
flag & FLAG_ACKED) {
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
- u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
- seq_rtt_us = ca_rtt_us = delta_us;
+ if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+ seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+ ca_rtt_us = seq_rtt_us;
+ }
}
rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
if (seq_rtt_us < 0)
@@ -4268,7 +4272,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
* If the sack array is full, forget about the last one.
*/
if (this_sack >= TCP_NUM_SACKS) {
- if (tp->compressed_ack)
+ if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
tcp_send_ack(sk);
this_sack--;
tp->rx_opt.num_sacks--;
@@ -4363,6 +4367,7 @@ static bool tcp_try_coalesce(struct sock *sk,
if (TCP_SKB_CB(from)->has_rxtstamp) {
TCP_SKB_CB(to)->has_rxtstamp = true;
to->tstamp = from->tstamp;
+ skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp;
}
return true;
@@ -5188,7 +5193,17 @@ send_now:
if (!tcp_is_sack(tp) ||
tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
goto send_now;
- tp->compressed_ack++;
+
+ if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
+ tp->compressed_ack_rcv_nxt = tp->rcv_nxt;
+ if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
+ tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+ tp->compressed_ack = 0;
+ }
+
+ if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH)
+ goto send_now;
if (hrtimer_is_queued(&tp->compressed_ack_timer))
return;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c34b97d365d..d1676d8a6ed7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -180,10 +180,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
{
struct tcp_sock *tp = tcp_sk(sk);
- if (unlikely(tp->compressed_ack)) {
+ if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) {
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
- tp->compressed_ack);
- tp->compressed_ack = 0;
+ tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+ tp->compressed_ack = TCP_FASTRETRANS_THRESH;
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
}
@@ -1904,7 +1904,9 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
* This algorithm is from John Heffner.
*/
static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
- bool *is_cwnd_limited, u32 max_segs)
+ bool *is_cwnd_limited,
+ bool *is_rwnd_limited,
+ u32 max_segs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 age, send_win, cong_win, limit, in_flight;
@@ -1912,9 +1914,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
struct sk_buff *head;
int win_divisor;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
- goto send_now;
-
if (icsk->icsk_ca_state >= TCP_CA_Recovery)
goto send_now;
@@ -1973,10 +1972,27 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
if (age < (tp->srtt_us >> 4))
goto send_now;
- /* Ok, it looks like it is advisable to defer. */
+ /* Ok, it looks like it is advisable to defer.
+ * Three cases are tracked :
+ * 1) We are cwnd-limited
+ * 2) We are rwnd-limited
+ * 3) We are application limited.
+ */
+ if (cong_win < send_win) {
+ if (cong_win <= skb->len) {
+ *is_cwnd_limited = true;
+ return true;
+ }
+ } else {
+ if (send_win <= skb->len) {
+ *is_rwnd_limited = true;
+ return true;
+ }
+ }
- if (cong_win < send_win && cong_win <= skb->len)
- *is_cwnd_limited = true;
+ /* If this packet won't get more data, do not wait. */
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ goto send_now;
return true;
@@ -2356,7 +2372,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
} else {
if (!push_one &&
tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
- max_segs))
+ &is_rwnd_limited, max_segs))
break;
}
@@ -2494,15 +2510,18 @@ void tcp_send_loss_probe(struct sock *sk)
goto rearm_timer;
}
skb = skb_rb_last(&sk->tcp_rtx_queue);
+ if (unlikely(!skb)) {
+ WARN_ONCE(tp->packets_out,
+ "invalid inflight: %u state %u cwnd %u mss %d\n",
+ tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+ inet_csk(sk)->icsk_pending = 0;
+ return;
+ }
/* At most one outstanding TLP retransmission. */
if (tp->tlp_high_seq)
goto rearm_timer;
- /* Retransmit last segment. */
- if (WARN_ON(!skb))
- goto rearm_timer;
-
if (skb_still_in_host_queue(sk, skb))
goto rearm_timer;
@@ -2920,7 +2939,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
trace_tcp_retransmit_skb(sk, skb);
} else if (err != -EBUSY) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
}
return err;
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 676020663ce8..f87dbc78b6bc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
u32 elapsed, start_ts;
+ s32 remaining;
start_ts = tcp_retransmit_stamp(sk);
if (!icsk->icsk_user_timeout || !start_ts)
return icsk->icsk_rto;
elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
- if (elapsed >= icsk->icsk_user_timeout)
+ remaining = icsk->icsk_user_timeout - elapsed;
+ if (remaining <= 0)
return 1; /* user timeout has passed; fire ASAP */
- else
- return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
+
+ return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
}
/**
@@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk,
(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
timeout = jiffies_to_msecs(timeout);
}
- return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
+ return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
}
/* A write timeout has occurred. Process the after effects. */
@@ -376,7 +378,7 @@ static void tcp_probe_timer(struct sock *sk)
return;
}
- if (icsk->icsk_probes_out > max_probes) {
+ if (icsk->icsk_probes_out >= max_probes) {
abort: tcp_write_err(sk);
} else {
/* Only send another probe if we didn't close things up. */
@@ -482,11 +484,12 @@ void tcp_retransmit_timer(struct sock *sk)
goto out_reset_timer;
}
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
if (tcp_write_timeout(sk))
goto out;
if (icsk->icsk_retransmits == 0) {
- int mib_idx;
+ int mib_idx = 0;
if (icsk->icsk_ca_state == TCP_CA_Recovery) {
if (tcp_is_sack(tp))
@@ -501,10 +504,9 @@ void tcp_retransmit_timer(struct sock *sk)
mib_idx = LINUX_MIB_TCPSACKFAILURES;
else
mib_idx = LINUX_MIB_TCPRENOFAILURES;
- } else {
- mib_idx = LINUX_MIB_TCPTIMEOUTS;
}
- __NET_INC_STATS(sock_net(sk), mib_idx);
+ if (mib_idx)
+ __NET_INC_STATS(sock_net(sk), mib_idx);
}
tcp_enter_loss(sk);
@@ -740,7 +742,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
- if (tp->compressed_ack)
+ if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
tcp_send_ack(sk);
} else {
if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-30 22:16:40 +0300