bpf: Require only one of cong_avoid() and cong_control() from a TCP CC

Remove the check for required and optional functions in a struct
tcp_congestion_ops from bpf_tcp_ca.c. Rely on
tcp_register_congestion_control() to reject a BPF CC that does not
implement all required functions, as it will do for a non-BPF CC.

When a CC implements tcp_congestion_ops.cong_control(), the alternate
cong_avoid() is not in use in the TCP stack. Previously, a BPF CC was
still forced to implement cong_avoid() as a no-op since it was
non-optional in bpf_tcp_ca.c.

Signed-off-by: Jörn-Thorben Hinz <jthinz@mailbox.tu-berlin.de>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220622191227.898118-3-jthinz@mailbox.tu-berlin.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index d9a3c92..7e0068c 100644 (file)
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -503,10 +503,9 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
                goto unlock;
        }
 
-       /* Error during st_ops->reg().  It is very unlikely since
-        * the above init_member() should have caught it earlier
-        * before reg().  The only possibility is if there was a race
-        * in registering the struct_ops (under the same name) to
+       /* Error during st_ops->reg(). Can happen if this struct_ops needs to be
+        * verified as a whole, after all init_member() calls. Can also happen if
+        * there was a race in registering the struct_ops (under the same name) to
         * a sub-system through different struct_ops's maps.
         */
        set_memory_nx((long)st_map->image, 1);

diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 1f5c53e..7a18163 100644 (file)
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -14,18 +14,6 @@
 /* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
 extern struct bpf_struct_ops bpf_tcp_congestion_ops;
 
-static u32 optional_ops[] = {
-       offsetof(struct tcp_congestion_ops, init),
-       offsetof(struct tcp_congestion_ops, release),
-       offsetof(struct tcp_congestion_ops, set_state),
-       offsetof(struct tcp_congestion_ops, cwnd_event),
-       offsetof(struct tcp_congestion_ops, in_ack_event),
-       offsetof(struct tcp_congestion_ops, pkts_acked),
-       offsetof(struct tcp_congestion_ops, min_tso_segs),
-       offsetof(struct tcp_congestion_ops, sndbuf_expand),
-       offsetof(struct tcp_congestion_ops, cong_control),
-};
-
 static u32 unsupported_ops[] = {
        offsetof(struct tcp_congestion_ops, get_info),
 };
@@ -51,18 +39,6 @@ static int bpf_tcp_ca_init(struct btf *btf)
        return 0;
 }
 
-static bool is_optional(u32 member_offset)
-{
-       unsigned int i;
-
-       for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
-               if (member_offset == optional_ops[i])
-                       return true;
-       }
-
-       return false;
-}
-
 static bool is_unsupported(u32 member_offset)
 {
        unsigned int i;
@@ -246,7 +222,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 {
        const struct tcp_congestion_ops *utcp_ca;
        struct tcp_congestion_ops *tcp_ca;
-       int prog_fd;
        u32 moff;
 
        utcp_ca = (const struct tcp_congestion_ops *)udata;
@@ -268,14 +243,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
                return 1;
        }
 
-       if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
-               return 0;
-
-       /* Ensure bpf_prog is provided for compulsory func ptr */
-       prog_fd = (int)(*(unsigned long *)(udata + moff));
-       if (!prog_fd && !is_optional(moff) && !is_unsupported(moff))
-               return -EINVAL;
-
        return 0;
 }