From: Cong Wang <cong.wang@xxxxxxxxxxxxx>
Currently there is no way to know which sockmap a socket has been added
to from outside, especially for that a socket can be added to multiple
sockmap's. We could dump this via socket diag, as shown below.
Sample output:
# ./iproute2/misc/ss -tnaie --sockmap
ESTAB 0 344329 127.0.0.1:1234 127.0.0.1:40912 ino:21098 sk:5 cgroup:/user.slice/user-0.slice/session-c1.scope <-> sockmap: 1
# bpftool map
1: sockmap flags 0x0
key 4B value 4B max_entries 2 memlock 4096B
pids echo-sockmap(549)
4: array name pid_iter.rodata flags 0x480
key 4B value 4B max_entries 1 memlock 4096B
btf_id 10 frozen
pids bpftool(624)
In the future, we could dump other sockmap related stats too, hence I
make it a nested attribute.
Cc: John Fastabend <john.fastabend@xxxxxxxxx>
Cc: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
Signed-off-by: Cong Wang <cong.wang@xxxxxxxxxxxxx>
---
include/linux/bpf.h | 1 +
include/uapi/linux/inet_diag.h | 1 +
include/uapi/linux/sock_diag.h | 8 ++++++
include/uapi/linux/unix_diag.h | 1 +
net/core/sock_map.c | 49 ++++++++++++++++++++++++++++++++++
net/ipv4/inet_diag.c | 5 ++++
net/unix/diag.c | 6 +++++
7 files changed, 71 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 35c18a98c21a..f23b97e0fe71 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2539,6 +2539,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
void sock_map_unhash(struct sock *sk);
void sock_map_destroy(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
+int sock_map_idiag_dump(struct sock *sk, struct sk_buff *skb, int attr);
#else
static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
struct bpf_prog_aux *prog_aux)
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 50655de04c9b..6c6952c2eb70 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -161,6 +161,7 @@ enum {
INET_DIAG_SK_BPF_STORAGES,
INET_DIAG_CGROUP_ID,
INET_DIAG_SOCKOPT,
+ INET_DIAG_SOCKMAP,
__INET_DIAG_MAX,
};
diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h
index 5f74a5f6091d..5deb22057d14 100644
--- a/include/uapi/linux/sock_diag.h
+++ b/include/uapi/linux/sock_diag.h
@@ -62,4 +62,12 @@ enum {
#define SK_DIAG_BPF_STORAGE_MAX (__SK_DIAG_BPF_STORAGE_MAX - 1)
+enum {
+ SK_DIAG_BPF_SOCKMAP_NONE,
+ SK_DIAG_BPF_SOCKMAP_MAP_ID,
+ __SK_DIAG_BPF_SOCKMAP_MAX,
+};
+
+#define SK_DIAG_BPF_SOCKMAP_MAX (__SK_DIAG_BPF_SOCKMAP_MAX - 1)
+
#endif /* _UAPI__SOCK_DIAG_H__ */
diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h
index a1988576fa8a..a21a25030b13 100644
--- a/include/uapi/linux/unix_diag.h
+++ b/include/uapi/linux/unix_diag.h
@@ -42,6 +42,7 @@ enum {
UNIX_DIAG_MEMINFO,
UNIX_DIAG_SHUTDOWN,
UNIX_DIAG_UID,
+ UNIX_DIAG_SOCKMAP,
__UNIX_DIAG_MAX,
};
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index a68a7290a3b2..fa3068857a8a 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1636,6 +1636,55 @@ void sock_map_close(struct sock *sk, long timeout)
}
EXPORT_SYMBOL_GPL(sock_map_close);
+int sock_map_idiag_dump(struct sock *sk, struct sk_buff *skb, int attrtype)
+{
+ struct sk_psock_link *link;
+ struct nlattr *nla, *attr;
+ int nr_links = 0, ret = 0;
+ struct sk_psock *psock;
+ u32 *ids;
+
+ rcu_read_lock();
+ psock = sk_psock_get(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return 0;
+ }
+
+ nla = nla_nest_start_noflag(skb, attrtype);
+ if (!nla) {
+ sk_psock_put(sk, psock);
+ rcu_read_unlock();
+ return -EMSGSIZE;
+ }
+ spin_lock_bh(&psock->link_lock);
+ list_for_each_entry(link, &psock->link, list)
+ nr_links++;
+
+ attr = nla_reserve(skb, SK_DIAG_BPF_SOCKMAP_MAP_ID,
+ sizeof(link->map->id) * nr_links);
+ if (!attr) {
+ ret = -EMSGSIZE;
+ goto unlock;
+ }
+
+ ids = nla_data(attr);
+ list_for_each_entry(link, &psock->link, list) {
+ *ids = link->map->id;
+ ids++;
+ }
+unlock:
+ spin_unlock_bh(&psock->link_lock);
+ sk_psock_put(sk, psock);
+ rcu_read_unlock();
+ if (ret)
+ nla_nest_cancel(skb, nla);
+ else
+ nla_nest_end(skb, nla);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(sock_map_idiag_dump);
+
static int sock_map_iter_attach_target(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index b812eb36f0e3..8fe43b6324c2 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -197,6 +197,11 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
&inet_sockopt))
goto errout;
+#ifdef CONFIG_BPF_SYSCALL
+ if (sock_map_idiag_dump(sk, skb, INET_DIAG_SOCKMAP))
+ goto errout;
+#endif
+
return 0;
errout:
return 1;
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 616b55c5b890..0c5d39889045 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -6,6 +6,7 @@
#include <linux/skbuff.h>
#include <linux/module.h>
#include <linux/uidgid.h>
+#include <linux/bpf.h>
#include <net/netlink.h>
#include <net/af_unix.h>
#include <net/tcp_states.h>
@@ -172,6 +173,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
sk_diag_dump_uid(sk, skb, user_ns))
goto out_nlmsg_trim;
+#ifdef CONFIG_BPF_SYSCALL
+ if (sock_map_idiag_dump(sk, skb, UNIX_DIAG_SOCKMAP))
+ goto out_nlmsg_trim;
+#endif
+
nlmsg_end(skb, nlh);
return 0;
--
2.34.1
