summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_trie.c121
-rw-r--r--net/ipv4/sysctl_net_ipv4.c9
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_metrics.c13
5 files changed, 104 insertions, 44 deletions
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b9df9c09b84e..b92a42433a7d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -980,9 +980,12 @@ static struct key_vector *fib_find_node(struct trie *t,
/* Return the first fib alias matching TOS with
* priority less than or equal to PRIO.
+ * If 'find_first' is set, return the first matching
+ * fib alias, regardless of TOS and priority.
*/
static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
- u8 tos, u32 prio, u32 tb_id)
+ u8 tos, u32 prio, u32 tb_id,
+ bool find_first)
{
struct fib_alias *fa;
@@ -998,6 +1001,8 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
continue;
if (fa->tb_id != tb_id)
break;
+ if (find_first)
+ return fa;
if (fa->fa_tos > tos)
continue;
if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos)
@@ -1063,9 +1068,6 @@ noleaf:
return -ENOMEM;
}
-/* fib notifier for ADD is sent before calling fib_insert_alias with
- * the expectation that the only possible failure ENOMEM
- */
static int fib_insert_alias(struct trie *t, struct key_vector *tp,
struct key_vector *l, struct fib_alias *new,
struct fib_alias *fa, t_key key)
@@ -1118,11 +1120,13 @@ static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack)
return true;
}
+static void fib_remove_alias(struct trie *t, struct key_vector *tp,
+ struct key_vector *l, struct fib_alias *old);
+
/* Caller must hold RTNL. */
int fib_table_insert(struct net *net, struct fib_table *tb,
struct fib_config *cfg, struct netlink_ext_ack *extack)
{
- enum fib_event_type event = FIB_EVENT_ENTRY_ADD;
struct trie *t = (struct trie *)tb->tb_data;
struct fib_alias *fa, *new_fa;
struct key_vector *l, *tp;
@@ -1149,7 +1153,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
l = fib_find_node(t, &tp, key);
fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority,
- tb->tb_id) : NULL;
+ tb->tb_id, false) : NULL;
/* Now fa, if non-NULL, points to the first fib alias
* with the same keys [prefix,tos,priority], if such key already
@@ -1217,12 +1221,17 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
- err = call_fib_entry_notifiers(net,
- FIB_EVENT_ENTRY_REPLACE,
- key, plen, new_fa,
- extack);
- if (err)
- goto out_free_new_fa;
+ if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0,
+ tb->tb_id, true) == fa) {
+ enum fib_event_type fib_event;
+
+ fib_event = FIB_EVENT_ENTRY_REPLACE;
+ err = call_fib_entry_notifiers(net, fib_event,
+ key, plen,
+ new_fa, extack);
+ if (err)
+ goto out_free_new_fa;
+ }
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, nlflags);
@@ -1244,12 +1253,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
if (fa_match)
goto out;
- if (cfg->fc_nlflags & NLM_F_APPEND) {
- event = FIB_EVENT_ENTRY_APPEND;
+ if (cfg->fc_nlflags & NLM_F_APPEND)
nlflags |= NLM_F_APPEND;
- } else {
+ else
fa = fa_first;
- }
}
err = -ENOENT;
if (!(cfg->fc_nlflags & NLM_F_CREATE))
@@ -1269,14 +1276,26 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
- err = call_fib_entry_notifiers(net, event, key, plen, new_fa, extack);
- if (err)
- goto out_free_new_fa;
-
/* Insert new entry to the list. */
err = fib_insert_alias(t, tp, l, new_fa, fa, key);
if (err)
- goto out_fib_notif;
+ goto out_free_new_fa;
+
+ /* The alias was already inserted, so the node must exist. */
+ l = l ? l : fib_find_node(t, &tp, key);
+ if (WARN_ON_ONCE(!l))
+ goto out_free_new_fa;
+
+ if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
+ new_fa) {
+ enum fib_event_type fib_event;
+
+ fib_event = FIB_EVENT_ENTRY_REPLACE;
+ err = call_fib_entry_notifiers(net, fib_event, key, plen,
+ new_fa, extack);
+ if (err)
+ goto out_remove_new_fa;
+ }
if (!plen)
tb->tb_num_default++;
@@ -1287,14 +1306,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
succeeded:
return 0;
-out_fib_notif:
- /* notifier was sent that entry would be added to trie, but
- * the add failed and need to recover. Only failure for
- * fib_insert_alias is ENOMEM.
- */
- NL_SET_ERR_MSG(extack, "Failed to insert route into trie");
- call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key,
- plen, new_fa, NULL);
+out_remove_new_fa:
+ fib_remove_alias(t, tp, l, new_fa);
out_free_new_fa:
kmem_cache_free(fn_alias_kmem, new_fa);
out:
@@ -1545,6 +1558,36 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
node_pull_suffix(tp, fa->fa_slen);
}
+static void fib_notify_alias_delete(struct net *net, u32 key,
+ struct hlist_head *fah,
+ struct fib_alias *fa_to_delete,
+ struct netlink_ext_ack *extack)
+{
+ struct fib_alias *fa_next, *fa_to_notify;
+ u32 tb_id = fa_to_delete->tb_id;
+ u8 slen = fa_to_delete->fa_slen;
+ enum fib_event_type fib_event;
+
+ /* Do not notify if we do not care about the route. */
+ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete)
+ return;
+
+ /* Determine if the route should be replaced by the next route in the
+ * list.
+ */
+ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next,
+ struct fib_alias, fa_list);
+ if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) {
+ fib_event = FIB_EVENT_ENTRY_REPLACE;
+ fa_to_notify = fa_next;
+ } else {
+ fib_event = FIB_EVENT_ENTRY_DEL;
+ fa_to_notify = fa_to_delete;
+ }
+ call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen,
+ fa_to_notify, extack);
+}
+
/* Caller must hold RTNL. */
int fib_table_delete(struct net *net, struct fib_table *tb,
struct fib_config *cfg, struct netlink_ext_ack *extack)
@@ -1566,7 +1609,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
if (!l)
return -ESRCH;
- fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id);
+ fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false);
if (!fa)
return -ESRCH;
@@ -1598,8 +1641,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
if (!fa_to_delete)
return -ESRCH;
- call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
- fa_to_delete, extack);
+ fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack);
rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
@@ -1923,10 +1965,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
continue;
}
- call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL,
- n->key,
- KEYLENGTH - fa->fa_slen, fa,
- NULL);
+ fib_notify_alias_delete(net, n->key, &n->leaf, fa,
+ NULL);
hlist_del_rcu(&fa->fa_list);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
@@ -2022,6 +2062,7 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb,
struct netlink_ext_ack *extack)
{
struct fib_alias *fa;
+ int last_slen = -1;
int err;
hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
@@ -2036,8 +2077,12 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb,
if (tb->tb_id != fa->tb_id)
continue;
- err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key,
- KEYLENGTH - fa->fa_slen,
+ if (fa->fa_slen == last_slen)
+ continue;
+
+ last_slen = fa->fa_slen;
+ err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE,
+ l->key, KEYLENGTH - fa->fa_slen,
fa, extack);
if (err)
return err;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index fcb2cd167f64..9684af02e0a5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1193,6 +1193,15 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "tcp_no_ssthresh_metrics_save",
+ .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
.procname = "tcp_moderate_rcvbuf",
.data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d885ba868822..f09fbc85b108 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -443,8 +443,6 @@ void tcp_init_sock(struct sock *sk)
tp->tsoffset = 0;
tp->rack.reo_wnd_steps = 1;
- sk->sk_state = TCP_CLOSE;
-
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
@@ -1778,6 +1776,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
while (length + PAGE_SIZE <= zc->length) {
if (zc->recv_skip_hint < PAGE_SIZE) {
if (skb) {
+ if (zc->recv_skip_hint > 0)
+ break;
skb = skb->next;
offset = seq - TCP_SKB_CB(skb)->seq;
} else {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1c7326e04f9b..6f52e5288a6f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2675,6 +2675,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
net->ipv4.sysctl_tcp_tw_reuse = 2;
+ net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1;
cnt = tcp_hashinfo.ehash_mask + 1;
net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index c4848e7a0aad..279db8822439 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -385,7 +385,8 @@ void tcp_update_metrics(struct sock *sk)
if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
- if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
+ if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && (tp->snd_cwnd >> 1) > val)
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
@@ -400,7 +401,8 @@ void tcp_update_metrics(struct sock *sk)
} else if (!tcp_in_slow_start(tp) &&
icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
- if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
+ if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) {
@@ -416,7 +418,8 @@ void tcp_update_metrics(struct sock *sk)
tcp_metric_set(tm, TCP_METRIC_CWND,
(val + tp->snd_ssthresh) >> 1);
}
- if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
+ if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && tp->snd_ssthresh > val)
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
@@ -441,6 +444,7 @@ void tcp_init_metrics(struct sock *sk)
{
struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
struct tcp_metrics_block *tm;
u32 val, crtt = 0; /* cached RTT scaled by 8 */
@@ -458,7 +462,8 @@ void tcp_init_metrics(struct sock *sk)
if (tcp_metric_locked(tm, TCP_METRIC_CWND))
tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
- val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
+ val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+ 0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val) {
tp->snd_ssthresh = val;
if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-14 14:56:59 +0300