[PATCH bpf-next v3 07/12] bpf, sockmap: Return socket cookie on lookup from syscall

[Jakub Sitnicki <jakub@cloudflare.com>]

Tooling that populates the SOCKMAP with sockets from user-space needs a way
to inspect its contents. Returning the struct sock * that SOCKMAP holds to
user-space is neither safe nor useful. An approach established by
REUSEPORT_SOCKARRAY is to return a socket cookie (a unique identifier)
instead.

Since socket cookies are u64 values, SOCKMAP needs to support such a value
size for lookup to be possible. This requires special handling on update,
though. Attempts to do a lookup on SOCKMAP holding u32 values will be met
with ENOSPC error.

Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 net/core/sock_map.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 439f1e0b995e..cabe85892ba3 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -10,6 +10,7 @@
 #include <linux/skmsg.h>
 #include <linux/list.h>
 #include <linux/jhash.h>
+#include <linux/sock_diag.h>
 
 struct bpf_stab {
 	struct bpf_map map;
@@ -31,7 +32,8 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-EPERM);
 	if (attr->max_entries == 0 ||
 	    attr->key_size    != 4 ||
-	    attr->value_size  != 4 ||
+	    (attr->value_size != sizeof(u32) &&
+	     attr->value_size != sizeof(u64)) ||
 	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
@@ -298,6 +300,21 @@ static void *sock_map_lookup(struct bpf_map *map, void *key)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
+{
+	struct sock *sk;
+
+	if (map->value_size != sizeof(u64))
+		return ERR_PTR(-ENOSPC);
+
+	sk = __sock_map_lookup_elem(map, *(u32 *)key);
+	if (!sk)
+		return ERR_PTR(-ENOENT);
+
+	sock_gen_cookie(sk);
+	return &sk->sk_cookie;
+}
+
 static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 			     struct sock **psk)
 {
@@ -460,12 +477,19 @@ static bool sock_map_redirect_okay(const struct sock *sk)
 static int sock_map_update_elem(struct bpf_map *map, void *key,
 				void *value, u64 flags)
 {
-	u32 ufd = *(u32 *)value;
 	u32 idx = *(u32 *)key;
 	struct socket *sock;
 	struct sock *sk;
+	u64 ufd;
 	int ret;
 
+	if (map->value_size == sizeof(u64))
+		ufd = *(u64 *)value;
+	else
+		ufd = *(u32 *)value;
+	if (ufd > S32_MAX)
+		return -EINVAL;
+
 	sock = sockfd_lookup(ufd, &ret);
 	if (!sock)
 		return ret;
@@ -569,6 +593,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_alloc		= sock_map_alloc,
 	.map_free		= sock_map_free,
 	.map_get_next_key	= sock_map_get_next_key,
+	.map_lookup_elem_sys_only = sock_map_lookup_sys,
 	.map_update_elem	= sock_map_update_elem,
 	.map_delete_elem	= sock_map_delete_elem,
 	.map_lookup_elem	= sock_map_lookup,
-- 
2.24.1