bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection

This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a
SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in
the earlier patch.  "bpf_run_sk_reuseport()" will return -ECONNREFUSED
when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP.
The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to
handle this case and return NULL immediately instead of continuing the
sk search from its hashtable.

It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach
BPF_PROG_TYPE_SK_REUSEPORT.  The "sk_reuseport_attach_bpf()" will check
if the attaching bpf prog is in the new SK_REUSEPORT or the existing
SOCKET_FILTER type and then check different things accordingly.

One level of "__reuseport_attach_prog()" call is removed.  The
"sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed
back to "reuseport_attach_prog()" in sock_reuseport.c.  sock_reuseport.c
seems to have more knowledge on those test requirements than filter.c.
In "reuseport_attach_prog()", after new_prog is attached to reuse->prog,
the old_prog (if any) is also directly freed instead of returning the
old_prog to the caller and asking the caller to free.

The sysctl_optmem_max check is moved back to the
"sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()".
As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only
bounded by the usual "bpf_prog_charge_memlock()" during load time
instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max.

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

1 files changed, 26 insertions, 10 deletions

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index d260167f5f77..ba5cba56f574 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -9,6 +9,7 @@
 #include <net/sock_reuseport.h>
 #include <linux/bpf.h>
 #include <linux/idr.h>
+#include <linux/filter.h>
 #include <linux/rcupdate.h>
 
 #define INIT_SOCKS 128
@@ -133,8 +134,7 @@ static void reuseport_free_rcu(struct rcu_head *head)
 	struct sock_reuseport *reuse;
 
 	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
+	sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1));
 	if (reuse->reuseport_id)
 		ida_simple_remove(&reuseport_ida, reuse->reuseport_id);
 	kfree(reuse);
@@ -219,9 +219,9 @@ void reuseport_detach_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
 
-static struct sock *run_bpf(struct sock_reuseport *reuse, u16 socks,
-			    struct bpf_prog *prog, struct sk_buff *skb,
-			    int hdr_len)
+static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
+				   struct bpf_prog *prog, struct sk_buff *skb,
+				   int hdr_len)
 {
 	struct sk_buff *nskb = NULL;
 	u32 index;
@@ -282,9 +282,15 @@ struct sock *reuseport_select_sock(struct sock *sk,
 		/* paired with smp_wmb() in reuseport_add_sock() */
 		smp_rmb();
 
-		if (prog && skb)
-			sk2 = run_bpf(reuse, socks, prog, skb, hdr_len);
+		if (!prog || !skb)
+			goto select_by_hash;
+
+		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+		else
+			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
+select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
 		if (!sk2)
 			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
@@ -296,12 +302,21 @@ out:
 }
 EXPORT_SYMBOL(reuseport_select_sock);
 
-struct bpf_prog *
-reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
+int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 {
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
+	if (sk_unhashed(sk) && sk->sk_reuseport) {
+		int err = reuseport_alloc(sk, false);
+
+		if (err)
+			return err;
+	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
+		/* The socket wasn't bound with SO_REUSEPORT */
+		return -EINVAL;
+	}
+
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
@@ -310,6 +325,7 @@ reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 	rcu_assign_pointer(reuse->prog, prog);
 	spin_unlock_bh(&reuseport_lock);
 
-	return old_prog;
+	sk_reuseport_prog_free(old_prog);
+	return 0;
 }
 EXPORT_SYMBOL(reuseport_attach_prog);