introduce a new sysctl knob sysctl_tcp_rto_max to control the max value of TCP_RTO and make it in netns

netns: tcp_rto_max.diff

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 9a14a08..f12c655 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -125,6 +125,7 @@ struct netns_ipv4 {
    int sysctl_tcp_sack;
    int sysctl_tcp_window_scaling;
    int sysctl_tcp_timestamps;
+    int sysctl_tcp_rto_max;
    struct inet_timewait_death_row tcp_death_row;
    int sysctl_max_syn_backlog;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7048329..801a03a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -137,7 +137,7 @@
 #define TCP_DELACK_MIN 4U
 #define TCP_ATO_MIN    4U
 #endif
-#define TCP_RTO_MAX    ((unsigned)(120*HZ))
+#define TCP_RTO_MAX ((unsigned)(net->ipv4.sysctl_tcp_rto_max*HZ))
 #define TCP_RTO_MIN    ((unsigned)(HZ/5))
 #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))    /* RFC6298 2.1 initial RTO value    */
 #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ))    /* RFC 1122 initial RTO value, now
@@ -624,6 +624,8 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,

 static inline void tcp_bound_rto(const struct sock *sk)
 {
+    struct net *net = sock_net(sk);
+
    if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
        inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
 }
@@ -1210,6 +1212,8 @@ static inline unsigned long tcp_probe0_when(const struct sock *sk,

 static inline void tcp_check_probe_timer(struct sock *sk)
 {
+    struct net *net = sock_net(sk);
+
    if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
        inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
                      tcp_probe0_base(sk), TCP_RTO_MAX);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4089c01..c46d441 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -729,6 +729,8 @@ static void reqsk_timer_handler(unsigned long data)
         !inet_rtx_syn_ack(sk_listener, req) ||
         inet_rsk(req)->acked)) {
        unsigned long timeo;
+        struct sock *sk = sk_listener;
+        struct net *net = sock_net(sk);

        if (req->num_timeout++ == 0)
            atomic_dec(&queue->young);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9bf8097..b46847f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1141,6 +1141,13 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
        .mode       = 0644,
        .proc_handler   = proc_dointvec
    },
+    {    
+        .procname       = "tcp_rto_max",
+        .data           = &init_net.ipv4.sysctl_tcp_rto_max,
+        .maxlen         = sizeof(int),
+        .mode           = 0644, 
+        .proc_handler   = proc_dointvec,
+    },
    { }
 };

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index ce9c7fe..ac61aa7 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -176,6 +176,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 {
    struct tcp_sock *tp;
    struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+    struct net *net = sock_net(sk);
    struct sock *child;
    bool own_req;

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2920e0c..4f7ffc5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2030,6 +2030,7 @@ static bool tcp_check_sack_reneging(struct sock *sk, int flag)
 {
    if (flag & FLAG_SACK_RENEGING) {
        struct tcp_sock *tp = tcp_sk(sk);
+        struct net *net = sock_net(sk);
        unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
                      msecs_to_jiffies(10));

@@ -2990,6 +2991,7 @@ void tcp_rearm_rto(struct sock *sk)
 {
    const struct inet_connection_sock *icsk = inet_csk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);

    /* If the retrans timer is currently being used by Fast Open
     * for SYN-ACK retrans purpose, stay put.
@@ -3250,6 +3252,7 @@ static void tcp_ack_probe(struct sock *sk)
 {
    const struct tcp_sock *tp = tcp_sk(sk);
    struct inet_connection_sock *icsk = inet_csk(sk);
+    struct net *net = sock_net(sk);

    /* Was it a usable window open? */

@@ -5655,6 +5658,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 {
    struct inet_connection_sock *icsk = inet_csk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    struct tcp_fastopen_cookie foc = { .len = -1 };
    int saved_clamp = tp->rx_opt.mss_clamp;
    bool fastopen_fail;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a20e7f0..db03ab6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1551,6 +1551,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 {
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);

    if (sysctl_tcp_low_latency || !tp->ucopy.task)
        return false;
@@ -2527,6 +2528,7 @@ static int __net_init tcp_sk_init(struct net *net)
    net->ipv4.sysctl_tcp_sack = 1;
    net->ipv4.sysctl_tcp_window_scaling = 1;
    net->ipv4.sysctl_tcp_timestamps = 1;
+    net->ipv4.sysctl_tcp_rto_max = 120;

    return 0;
 fail:
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0ff83c1..9f2b12d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -563,6 +563,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
    __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
    bool paws_reject = false;
    bool own_req;
+    struct net *net = sock_net(sk);

    tmp_opt.saw_tstamp = 0;
    if (th->doff > (sizeof(struct tcphdr)>>2)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2f1588b..6b2c463 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2377,6 +2377,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 {
    struct inet_connection_sock *icsk = inet_csk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    u32 timeout, tlp_time_stamp, rto_time_stamp;
    u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);

@@ -2933,6 +2934,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 {
    const struct inet_connection_sock *icsk = inet_csk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    struct sk_buff *skb;
    struct sk_buff *hole = NULL;
    u32 max_segs;
@@ -3445,6 +3447,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 int tcp_connect(struct sock *sk)
 {
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    struct sk_buff *buff;
    int err;

@@ -3549,6 +3552,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 void tcp_send_ack(struct sock *sk)
 {
    struct sk_buff *buff;
+    struct net *net = sock_net(sk);

    /* If we have been reset, we may not send again. */
    if (sk->sk_state == TCP_CLOSE)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c0feeee..9f55728 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -59,6 +59,7 @@ static void tcp_write_err(struct sock *sk)
 static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    int shift = 0;

    /* If peer does not open window for long time, or did not transmit
@@ -151,6 +152,7 @@ static bool retransmits_timed_out(struct sock *sk,
 {
    const unsigned int rto_base = TCP_RTO_MIN;
    unsigned int linear_backoff_thresh, start_ts;
+    struct net *net = sock_net(sk);

    if (!inet_csk(sk)->icsk_retransmits)
        return false;
@@ -317,6 +319,7 @@ static void tcp_probe_timer(struct sock *sk)
 {
    struct inet_connection_sock *icsk = inet_csk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
+    struct net *net = sock_net(sk);
    int max_probes;
    u32 start_ts;

@@ -367,8 +370,9 @@ static void tcp_probe_timer(struct sock *sk)
 static void tcp_fastopen_synack_timer(struct sock *sk)
 {
    struct inet_connection_sock *icsk = inet_csk(sk);
+    struct net *net = sock_net(sk);
    int max_retries = icsk->icsk_syn_retries ? :
-       sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
+       net->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
    struct request_sock *req;

    req = tcp_sk(sk)->fastopen_rsk;