Lorenz Bauer wrote:
> Allow calling bpf_map_update_elem on sockmap and sockhash from a BPF
> context. The synchronization required for this is a bit fiddly: we
> need to prevent the socket from changing it's state while we add it
> to the sockmap, since we rely on getting a callback via
> sk_prot->unhash. However, we can't just lock_sock like in
> sock_map_sk_acquire because that might sleep. So instead we disable
> softirq processing and use bh_lock_sock to prevent further
> modification.
>
> Signed-off-by: Lorenz Bauer <l...@cloudflare.com>
> ---
> kernel/bpf/verifier.c | 6 ++++--
> net/core/sock_map.c | 24 ++++++++++++++++++++++++
> 2 files changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 47f9b94bb9d4..421fccf18dea 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -4254,7 +4254,8 @@ static int check_map_func_compatibility(struct
> bpf_verifier_env *env,
> func_id != BPF_FUNC_map_delete_elem &&
> func_id != BPF_FUNC_msg_redirect_map &&
> func_id != BPF_FUNC_sk_select_reuseport &&
> - func_id != BPF_FUNC_map_lookup_elem)
> + func_id != BPF_FUNC_map_lookup_elem &&
> + func_id != BPF_FUNC_map_update_elem)
> goto error;
> break;
> case BPF_MAP_TYPE_SOCKHASH:
> @@ -4263,7 +4264,8 @@ static int check_map_func_compatibility(struct
> bpf_verifier_env *env,
> func_id != BPF_FUNC_map_delete_elem &&
> func_id != BPF_FUNC_msg_redirect_hash &&
> func_id != BPF_FUNC_sk_select_reuseport &&
> - func_id != BPF_FUNC_map_lookup_elem)
> + func_id != BPF_FUNC_map_lookup_elem &&
> + func_id != BPF_FUNC_map_update_elem)
I lost track of a detail here, map_lookup_elem should return
PTR_TO_MAP_VALUE_OR_NULL but if we want to feed that back into
the map_update_elem() we need to return PTR_TO_SOCKET_OR_NULL
and then presumably have a null check to get a PTR_TO_SOCKET
type as expect.
Can we use the same logic for expected arg (previous patch) on the
ret_type. Or did I miss it:/ Need some coffee I guess.
> goto error;
> break;
> case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
> diff --git a/net/core/sock_map.c b/net/core/sock_map.c
> index 018367fb889f..b2c886c34566 100644
> --- a/net/core/sock_map.c
> +++ b/net/core/sock_map.c
> @@ -603,6 +603,28 @@ int sock_map_update_elem_sys(struct bpf_map *map, void
> *key,
> return ret;
> }
>
> +static int sock_map_update_elem(struct bpf_map *map, void *key,
> + void *value, u64 flags)
> +{
> + struct sock *sk = (struct sock *)value;
> + int ret;
> +
> + if (!sock_map_sk_is_suitable(sk))
> + return -EOPNOTSUPP;
> +
> + local_bh_disable();
> + bh_lock_sock(sk);
How do ensure we are not being called from some context which
already has the bh_lock_sock() held? It seems we can call map_update_elem()
from any context, kprobes, tc, xdp, etc.?
> + if (!sock_map_sk_state_allowed(sk))
> + ret = -EOPNOTSUPP;
> + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP)
> + ret = sock_map_update_common(map, *(u32 *)key, sk, flags);
> + else
> + ret = sock_hash_update_common(map, key, sk, flags);
> + bh_unlock_sock(sk);
> + local_bh_enable();
> + return ret;
> +}
> +
> BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops,
> struct bpf_map *, map, void *, key, u64, flags)
> {
> @@ -687,6 +709,7 @@ const struct bpf_map_ops sock_map_ops = {
> .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,
> .map_release_uref = sock_map_release_progs,
> @@ -1180,6 +1203,7 @@ const struct bpf_map_ops sock_hash_ops = {
> .map_alloc = sock_hash_alloc,
> .map_free = sock_hash_free,
> .map_get_next_key = sock_hash_get_next_key,
> + .map_update_elem = sock_map_update_elem,
> .map_delete_elem = sock_hash_delete_elem,
> .map_lookup_elem = sock_hash_lookup,
> .map_lookup_elem_sys_only = sock_hash_lookup_sys,
> --
> 2.25.1
>
