summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorFlorian Westphal <fw@strlen.de>2020-03-28 00:48:50 +0300
committerDavid S. Miller <davem@davemloft.net>2020-03-30 08:14:49 +0300
commitfc518953bc9c8d7d33c6ab261995f5038f3c87f9 (patch)
tree9c4eebd575e693916feb8d234411d08a17ec430a /net
parent5147dfb5083204d6f5468d6d6d2d04b2cdc0cf2b (diff)
downloadlinux-fc518953bc9c8d7d33c6ab261995f5038f3c87f9.tar.xz
mptcp: add and use MIB counter infrastructure
Exported via same /proc file as the Linux TCP MIB counters, so "netstat -s" or "nstat" will show them automatically. The MPTCP MIB counters are allocated in a distinct pcpu area in order to avoid bloating/wasting TCP pcpu memory. Counters are allocated once the first MPTCP socket is created in a network namespace and free'd on exit. If no sockets have been allocated, all-zero mptcp counters are shown. The MIB counter list is taken from the multipath-tcp.org kernel, but only a few counters have been picked up so far. The counter list can be increased at any time later on. v2 -> v3: - remove 'inline' in foo.c files (David S. Miller) Co-developed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/mptcp/Makefile2
-rw-r--r--net/mptcp/mib.c69
-rw-r--r--net/mptcp/mib.h40
-rw-r--r--net/mptcp/protocol.c30
-rw-r--r--net/mptcp/subflow.c33
7 files changed, 165 insertions, 15 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index bd7b4e92e07f..cf58e29cf746 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1793,6 +1793,10 @@ static __net_exit void ipv4_mib_exit_net(struct net *net)
free_percpu(net->mib.net_statistics);
free_percpu(net->mib.ip_statistics);
free_percpu(net->mib.tcp_statistics);
+#ifdef CONFIG_MPTCP
+ /* allocated on demand, see mptcp_init_sock() */
+ free_percpu(net->mib.mptcp_statistics);
+#endif
}
static __net_initdata struct pernet_operations ipv4_mib_ops = {
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 2580303249e2..75545a829a2b 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -32,6 +32,7 @@
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <linux/bottom_half.h>
@@ -485,6 +486,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
offsetof(struct ipstats_mib, syncp)));
seq_putc(seq, '\n');
+ mptcp_seq_show(seq);
return 0;
}
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index 54494cf5bec0..faebe8ec9f73 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -1,4 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_MPTCP) += mptcp.o
-mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o
+mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o mib.o
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
new file mode 100644
index 000000000000..0a6a15f3456d
--- /dev/null
+++ b/net/mptcp/mib.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/seq_file.h>
+#include <net/ip.h>
+#include <net/mptcp.h>
+#include <net/snmp.h>
+#include <net/net_namespace.h>
+
+#include "mib.h"
+
+static const struct snmp_mib mptcp_snmp_list[] = {
+ SNMP_MIB_ITEM("MPCapableSYNRX", MPTCP_MIB_MPCAPABLEPASSIVE),
+ SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK),
+ SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK),
+ SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
+ SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
+ SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
+ SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+ SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+ SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
+ SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
+ SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
+ SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
+ SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
+ SNMP_MIB_SENTINEL
+};
+
+/* mptcp_mib_alloc - allocate percpu mib counters
+ *
+ * These are allocated when the first mptcp socket is created so
+ * we do not waste percpu memory if mptcp isn't in use.
+ */
+bool mptcp_mib_alloc(struct net *net)
+{
+ struct mptcp_mib __percpu *mib = alloc_percpu(struct mptcp_mib);
+
+ if (!mib)
+ return false;
+
+ if (cmpxchg(&net->mib.mptcp_statistics, NULL, mib))
+ free_percpu(mib);
+
+ return true;
+}
+
+void mptcp_seq_show(struct seq_file *seq)
+{
+ struct net *net = seq->private;
+ int i;
+
+ seq_puts(seq, "MPTcpExt:");
+ for (i = 0; mptcp_snmp_list[i].name; i++)
+ seq_printf(seq, " %s", mptcp_snmp_list[i].name);
+
+ seq_puts(seq, "\nMPTcpExt:");
+
+ if (!net->mib.mptcp_statistics) {
+ for (i = 0; mptcp_snmp_list[i].name; i++)
+ seq_puts(seq, " 0");
+
+ return;
+ }
+
+ for (i = 0; mptcp_snmp_list[i].name; i++)
+ seq_printf(seq, " %lu",
+ snmp_fold_field(net->mib.mptcp_statistics,
+ mptcp_snmp_list[i].entry));
+ seq_putc(seq, '\n');
+}
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
new file mode 100644
index 000000000000..d7de340fc997
--- /dev/null
+++ b/net/mptcp/mib.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+enum linux_mptcp_mib_field {
+ MPTCP_MIB_NUM = 0,
+ MPTCP_MIB_MPCAPABLEPASSIVE, /* Received SYN with MP_CAPABLE */
+ MPTCP_MIB_MPCAPABLEPASSIVEACK, /* Received third ACK with MP_CAPABLE */
+ MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK,/* Server-side fallback during 3-way handshake */
+ MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */
+ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
+ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
+ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
+ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
+ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */
+ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */
+ __MPTCP_MIB_MAX
+};
+
+#define LINUX_MIB_MPTCP_MAX __MPTCP_MIB_MAX
+struct mptcp_mib {
+ unsigned long mibs[LINUX_MIB_MPTCP_MAX];
+};
+
+static inline void MPTCP_INC_STATS(struct net *net,
+ enum linux_mptcp_mib_field field)
+{
+ if (likely(net->mib.mptcp_statistics))
+ SNMP_INC_STATS(net->mib.mptcp_statistics, field);
+}
+
+static inline void __MPTCP_INC_STATS(struct net *net,
+ enum linux_mptcp_mib_field field)
+{
+ if (likely(net->mib.mptcp_statistics))
+ __SNMP_INC_STATS(net->mib.mptcp_statistics, field);
+}
+
+bool mptcp_mib_alloc(struct net *net);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 8d2777092390..1833bc1f4a43 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -21,6 +21,7 @@
#endif
#include <net/mptcp.h>
#include "protocol.h"
+#include "mib.h"
#define MPTCP_SAME_STATE TCP_MAX_STATES
@@ -1032,6 +1033,7 @@ static void mptcp_worker(struct work_struct *work)
if (ret < 0)
break;
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
copied += ret;
dfrag->data_len -= ret;
dfrag->offset += ret;
@@ -1081,17 +1083,22 @@ static int __mptcp_init_sock(struct sock *sk)
static int mptcp_init_sock(struct sock *sk)
{
- int ret = __mptcp_init_sock(sk);
+ struct net *net = sock_net(sk);
+ int ret;
+ if (!mptcp_is_enabled(net))
+ return -ENOPROTOOPT;
+
+ if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
+ return -ENOMEM;
+
+ ret = __mptcp_init_sock(sk);
if (ret)
return ret;
sk_sockets_allocated_inc(sk);
sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2];
- if (!mptcp_is_enabled(sock_net(sk)))
- return -ENOPROTOOPT;
-
return 0;
}
@@ -1327,7 +1334,12 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
list_add(&subflow->node, &msk->conn_list);
bh_unlock_sock(new_mptcp_sock);
+
+ __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
local_bh_enable();
+ } else {
+ MPTCP_INC_STATS(sock_net(sk),
+ MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
}
return newsk;
@@ -1448,13 +1460,15 @@ void mptcp_finish_connect(struct sock *ssk)
u64 ack_seq;
subflow = mptcp_subflow_ctx(ssk);
-
- if (!subflow->mp_capable)
- return;
-
sk = subflow->conn;
msk = mptcp_sk(sk);
+ if (!subflow->mp_capable) {
+ MPTCP_INC_STATS(sock_net(sk),
+ MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
+ return;
+ }
+
pr_debug("msk=%p, token=%u", sk, subflow->token);
mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c051db074708..b5180c81588e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -20,6 +20,13 @@
#endif
#include <net/mptcp.h>
#include "protocol.h"
+#include "mib.h"
+
+static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
+ enum linux_mptcp_mib_field field)
+{
+ MPTCP_INC_STATS(sock_net(req_to_sk(req)), field);
+}
static int subflow_rebuild_header(struct sock *sk)
{
@@ -88,8 +95,7 @@ static bool subflow_token_join_request(struct request_sock *req,
msk = mptcp_token_get_sock(subflow_req->token);
if (!msk) {
- pr_debug("subflow_req=%p, token=%u - not found\n",
- subflow_req, subflow_req->token);
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
return false;
}
@@ -137,8 +143,14 @@ static void subflow_init_req(struct request_sock *req,
return;
#endif
- if (rx_opt.mptcp.mp_capable && rx_opt.mptcp.mp_join)
- return;
+ if (rx_opt.mptcp.mp_capable) {
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
+
+ if (rx_opt.mptcp.mp_join)
+ return;
+ } else if (rx_opt.mptcp.mp_join) {
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+ }
if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
int err;
@@ -237,6 +249,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow, subflow->thmac,
subflow->remote_nonce);
if (!subflow_thmac_valid(subflow)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
subflow->mp_join = 0;
goto do_reset;
}
@@ -253,6 +266,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
goto do_reset;
subflow->conn_finished = 1;
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
} else {
do_reset:
tcp_send_active_reset(sk, GFP_ATOMIC);
@@ -382,8 +396,10 @@ create_msk:
opt_rx.mptcp.mp_join = 0;
mptcp_get_options(skb, &opt_rx);
if (!opt_rx.mptcp.mp_join ||
- !subflow_hmac_valid(req, &opt_rx))
+ !subflow_hmac_valid(req, &opt_rx)) {
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
return NULL;
+ }
}
create_child:
@@ -420,6 +436,8 @@ create_child:
ctx->conn = (struct sock *)owner;
if (!mptcp_finish_join(child))
goto close_child;
+
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
}
}
@@ -535,6 +553,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk)
data_len = mpext->data_len;
if (data_len == 0) {
pr_err("Infinite mapping not handled");
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
return MAPPING_INVALID;
}
@@ -578,8 +597,10 @@ static enum mapping_status get_mapping_status(struct sock *ssk)
/* If this skb data are fully covered by the current mapping,
* the new map would need caching, which is not supported
*/
- if (skb_is_fully_mapped(ssk, skb))
+ if (skb_is_fully_mapped(ssk, skb)) {
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSNOMATCH);
return MAPPING_INVALID;
+ }
/* will validate the next map after consuming the current one */
return MAPPING_OK;