bpf: Add a bpf_sock pointer to __sk_buff and a bpf_sk_fullsock helper

In kernel, it is common to check "skb->sk && sk_fullsock(skb->sk)"
before accessing the fields in sock.  For example, in __netdev_pick_tx:

static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
			    struct net_device *sb_dev)
{
	/* ... */

	struct sock *sk = skb->sk;

		if (queue_index != new_index && sk &&
		    sk_fullsock(sk) &&
		    rcu_access_pointer(sk->sk_dst_cache))
			sk_tx_queue_set(sk, new_index);

	/* ... */

	return queue_index;
}

This patch adds a "struct bpf_sock *sk" pointer to the "struct __sk_buff"
where a few of the convert_ctx_access() in filter.c has already been
accessing the skb->sk sock_common's fields,
e.g. sock_ops_convert_ctx_access().

"__sk_buff->sk" is a PTR_TO_SOCK_COMMON_OR_NULL in the verifier.
Some of the fileds in "bpf_sock" will not be directly
accessible through the "__sk_buff->sk" pointer.  It is limited
by the new "bpf_sock_common_is_valid_access()".
e.g. The existing "type", "protocol", "mark" and "priority" in bpf_sock
     are not allowed.

The newly added "struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)"
can be used to get a sk with all accessible fields in "bpf_sock".
This helper is added to both cg_skb and sched_(cls|act).

int cg_skb_foo(struct __sk_buff *skb) {
	struct bpf_sock *sk;

	sk = skb->sk;
	if (!sk)
		return 1;

	sk = bpf_sk_fullsock(sk);
	if (!sk)
		return 1;

	if (sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP)
		return 1;

	/* some_traffic_shaping(); */

	return 1;
}

(1) The sk is read only

(2) There is no new "struct bpf_sock_common" introduced.

(3) Future kernel sock's members could be added to bpf_sock only
    instead of repeatedly adding at multiple places like currently
    in bpf_sock_ops_md, bpf_sock_addr_md, sk_reuseport_md...etc.

(4) After "sk = skb->sk", the reg holding sk is in type
    PTR_TO_SOCK_COMMON_OR_NULL.

(5) After bpf_sk_fullsock(), the return type will be in type
    PTR_TO_SOCKET_OR_NULL which is the same as the return type of
    bpf_sk_lookup_xxx().

    However, bpf_sk_fullsock() does not take refcnt.  The
    acquire_reference_state() is only depending on the return type now.
    To avoid it, a new is_acquire_function() is checked before calling
    acquire_reference_state().

(6) The WARN_ON in "release_reference_state()" is no longer an
    internal verifier bug.

    When reg->id is not found in state->refs[], it means the
    bpf_prog does something wrong like
    "bpf_sk_release(bpf_sk_fullsock(skb->sk))" where reference has
    never been acquired by calling "bpf_sk_fullsock(skb->sk)".

    A -EINVAL and a verbose are done instead of WARN_ON.  A test is
    added to the test_verifier in a later patch.

    Since the WARN_ON in "release_reference_state()" is no longer
    needed, "__release_reference_state()" is folded into
    "release_reference_state()" also.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 12 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bd169a7bcc93..a60463b45b54 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -194,6 +194,7 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
+	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 };
 
 /* type of values returned from helper functions */
@@ -256,6 +257,8 @@ enum bpf_reg_type {
 	PTR_TO_FLOW_KEYS,	 /* reg points to bpf_flow_keys */
 	PTR_TO_SOCKET,		 /* reg points to struct bpf_sock */
 	PTR_TO_SOCKET_OR_NULL,	 /* reg points to struct bpf_sock or NULL */
+	PTR_TO_SOCK_COMMON,	 /* reg points to sock_common */
+	PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -920,6 +923,9 @@ void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
 #if defined(CONFIG_NET)
+bool bpf_sock_common_is_valid_access(int off, int size,
+				     enum bpf_access_type type,
+				     struct bpf_insn_access_aux *info);
 bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 			      struct bpf_insn_access_aux *info);
 u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
@@ -928,6 +934,12 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				struct bpf_prog *prog,
 				u32 *target_size);
 #else
+static inline bool bpf_sock_common_is_valid_access(int off, int size,
+						   enum bpf_access_type type,
+						   struct bpf_insn_access_aux *info)
+{
+	return false;
+}
 static inline bool bpf_sock_is_valid_access(int off, int size,
 					    enum bpf_access_type type,
 					    struct bpf_insn_access_aux *info)