tcp: add generic netlink support for tcp_metrics

Add support for genl "tcp_metrics". No locking
is changed, only that now we can unlink and delete
entries after grace period. We implement get/del for
single entry and dump to support show/flush filtering
in user space. Del without address attribute causes
flush for all addresses, sadly under genl_mutex.

v2:
- remove rcu_assign_pointer as suggested by Eric Dumazet,
it is not needed because there are no other writes under lock
- move the flushing code in tcp_metrics_flush_all

v3:
- remove synchronize_rcu on flush as suggested by Eric Dumazet

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 396 insertions, 13 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 1f2c1c787f17..90da0af28352 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -363,6 +363,7 @@ header-y += sysctl.h
 header-y += sysinfo.h
 header-y += taskstats.h
 header-y += tcp.h
+header-y += tcp_metrics.h
 header-y += telephony.h
 header-y += termios.h
 header-y += time.h
diff --git a/include/linux/tcp_metrics.h b/include/linux/tcp_metrics.h
new file mode 100644
index 000000000000..cb5157b55f32
--- /dev/null
+++ b/include/linux/tcp_metrics.h
@@ -0,0 +1,54 @@
+/* tcp_metrics.h - TCP Metrics Interface */
+
+#ifndef _LINUX_TCP_METRICS_H
+#define _LINUX_TCP_METRICS_H
+
+#include <linux/types.h>
+
+/* NETLINK_GENERIC related info
+ */
+#define TCP_METRICS_GENL_NAME           "tcp_metrics"
+#define TCP_METRICS_GENL_VERSION        0x1
+
+enum tcp_metric_index {
+        TCP_METRIC_RTT,
+        TCP_METRIC_RTTVAR,
+        TCP_METRIC_SSTHRESH,
+        TCP_METRIC_CWND,
+        TCP_METRIC_REORDERING,
+
+        /* Always last.  */
+        __TCP_METRIC_MAX,
+};
+
+#define TCP_METRIC_MAX  (__TCP_METRIC_MAX - 1)
+
+enum {
+        TCP_METRICS_ATTR_UNSPEC,
+        TCP_METRICS_ATTR_ADDR_IPV4,             /* u32 */
+        TCP_METRICS_ATTR_ADDR_IPV6,             /* binary */
+        TCP_METRICS_ATTR_AGE,                   /* msecs */
+        TCP_METRICS_ATTR_TW_TSVAL,              /* u32, raw, rcv tsval */
+        TCP_METRICS_ATTR_TW_TS_STAMP,           /* s32, sec age */
+        TCP_METRICS_ATTR_VALS,                  /* nested +1, u32 */
+        TCP_METRICS_ATTR_FOPEN_MSS,             /* u16 */
+        TCP_METRICS_ATTR_FOPEN_SYN_DROPS,       /* u16, count of drops */
+        TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS,     /* msecs age */
+        TCP_METRICS_ATTR_FOPEN_COOKIE,          /* binary */
+
+        __TCP_METRICS_ATTR_MAX,
+};
+
+#define TCP_METRICS_ATTR_MAX    (__TCP_METRICS_ATTR_MAX - 1)
+
+enum {
+        TCP_METRICS_CMD_UNSPEC,
+        TCP_METRICS_CMD_GET,
+        TCP_METRICS_CMD_DEL,
+
+        __TCP_METRICS_CMD_MAX,
+};
+
+#define TCP_METRICS_CMD_MAX     (__TCP_METRICS_CMD_MAX - 1)
+
+#endif /* _LINUX_TCP_METRICS_H */
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0abe67bb4d3a..988edb63ee73 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/tcp.h>
 #include <linux/hash.h>
+#include <linux/tcp_metrics.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/net_namespace.h>
@@ -17,20 +18,10 @@
 #include <net/ipv6.h>
 #include <net/dst.h>
 #include <net/tcp.h>
+#include <net/genetlink.h>
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
-enum tcp_metric_index {
-        TCP_METRIC_RTT,
-        TCP_METRIC_RTTVAR,
-        TCP_METRIC_SSTHRESH,
-        TCP_METRIC_CWND,
-        TCP_METRIC_REORDERING,
-
-        /* Always last.  */
-        TCP_METRIC_MAX,
-};
-
 struct tcp_fastopen_metrics {
         u16     mss;
         u16     syn_loss:10;            /* Recurring Fast Open SYN losses */
@@ -45,8 +36,10 @@ struct tcp_metrics_block {
         u32                             tcpm_ts;
         u32                             tcpm_ts_stamp;
         u32                             tcpm_lock;
-        u32                             tcpm_vals[TCP_METRIC_MAX];
+        u32                             tcpm_vals[TCP_METRIC_MAX + 1];
         struct tcp_fastopen_metrics     tcpm_fastopen;
+
+        struct rcu_head                 rcu_head;
 };
 
 static bool tcp_metric_locked(struct tcp_metrics_block *tm,
@@ -690,6 +683,325 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
         rcu_read_unlock();
 }
 
+static struct genl_family tcp_metrics_nl_family = {
+        .id             = GENL_ID_GENERATE,
+        .hdrsize        = 0,
+        .name           = TCP_METRICS_GENL_NAME,
+        .version        = TCP_METRICS_GENL_VERSION,
+        .maxattr        = TCP_METRICS_ATTR_MAX,
+        .netnsok        = true,
+};
+
+static struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = {
+        [TCP_METRICS_ATTR_ADDR_IPV4]    = { .type = NLA_U32, },
+        [TCP_METRICS_ATTR_ADDR_IPV6]    = { .type = NLA_BINARY,
+                                            .len = sizeof(struct in6_addr), },
+        /* Following attributes are not received for GET/DEL,
+         * we keep them for reference
+         */
+#if 0
+        [TCP_METRICS_ATTR_AGE]          = { .type = NLA_MSECS, },
+        [TCP_METRICS_ATTR_TW_TSVAL]     = { .type = NLA_U32, },
+        [TCP_METRICS_ATTR_TW_TS_STAMP]  = { .type = NLA_S32, },
+        [TCP_METRICS_ATTR_VALS]         = { .type = NLA_NESTED, },
+        [TCP_METRICS_ATTR_FOPEN_MSS]    = { .type = NLA_U16, },
+        [TCP_METRICS_ATTR_FOPEN_SYN_DROPS]      = { .type = NLA_U16, },
+        [TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS]    = { .type = NLA_MSECS, },
+        [TCP_METRICS_ATTR_FOPEN_COOKIE] = { .type = NLA_BINARY,
+                                            .len = TCP_FASTOPEN_COOKIE_MAX, },
+#endif
+};
+
+/* Add attributes, caller cancels its header on failure */
+static int tcp_metrics_fill_info(struct sk_buff *msg,
+                                 struct tcp_metrics_block *tm)
+{
+        struct nlattr *nest;
+        int i;
+
+        switch (tm->tcpm_addr.family) {
+        case AF_INET:
+                if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4,
+                                tm->tcpm_addr.addr.a4) < 0)
+                        goto nla_put_failure;
+                break;
+        case AF_INET6:
+                if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16,
+                            tm->tcpm_addr.addr.a6) < 0)
+                        goto nla_put_failure;
+                break;
+        default:
+                return -EAFNOSUPPORT;
+        }
+
+        if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE,
+                          jiffies - tm->tcpm_stamp) < 0)
+                goto nla_put_failure;
+        if (tm->tcpm_ts_stamp) {
+                if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,
+                                (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)
+                        goto nla_put_failure;
+                if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,
+                                tm->tcpm_ts) < 0)
+                        goto nla_put_failure;
+        }
+
+        {
+                int n = 0;
+
+                nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
+                if (!nest)
+                        goto nla_put_failure;
+                for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
+                        if (!tm->tcpm_vals[i])
+                                continue;
+                        if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0)
+                                goto nla_put_failure;
+                        n++;
+                }
+                if (n)
+                        nla_nest_end(msg, nest);
+                else
+                        nla_nest_cancel(msg, nest);
+        }
+
+        {
+                struct tcp_fastopen_metrics tfom_copy[1], *tfom;