netdev - [PATCH bpf-next v2 5/6] bpf: sockmap: allow update from BPF

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200820135729.135783-6-lmb@cloudflare.com>
Date:   Thu, 20 Aug 2020 14:57:28 +0100
From:   Lorenz Bauer <lmb@...udflare.com>
To:     jakub@...udflare.com, john.fastabend@...il.com,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Lorenz Bauer <lmb@...udflare.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>
Cc:     kernel-team@...udflare.com, netdev@...r.kernel.org,
        bpf@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH bpf-next v2 5/6] bpf: sockmap: allow update from BPF

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 its 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 <lmb@...udflare.com>
---
 kernel/bpf/verifier.c | 41 +++++++++++++++++++++++++++++++++++++++--
 net/core/sock_map.c   | 24 ++++++++++++++++++++++++
 2 files changed, 63 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 24feec515d3e..7779057f57dc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4180,6 +4180,41 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	return -EACCES;
 }
 
+static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
+{
+	enum bpf_attach_type eatype = env->prog->expected_attach_type;
+	enum bpf_prog_type type = env->prog->type;
+
+	if (func_id != BPF_FUNC_map_update_elem)
+		return false;
+
+	/* It's not possible to get access to a locked struct sock in these
+	 * contexts, so updating is safe.
+	 */
+	switch (type) {
+	case BPF_PROG_TYPE_TRACING:
+		if (eatype == BPF_TRACE_ITER)
+			return true;
+		break;
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		return true;
+	default:
+		break;
+	}
+
+	verbose(env, "cannot update sockmap in this context\n");
+	return false;
+}
+
 static int check_map_func_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map, int func_id)
 {
@@ -4251,7 +4286,8 @@ 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 &&
+		    !may_update_sockmap(env, func_id))
 			goto error;
 		break;
 	case BPF_MAP_TYPE_SOCKHASH:
@@ -4260,7 +4296,8 @@ 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 &&
+		    !may_update_sockmap(env, func_id))
 			goto error;
 		break;
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 48e83f93ee66..d6c6e1e312fc 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, void *value,
 	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);
+	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