bpf, netns: Keep attached programs in bpf_prog_array

Prepare for having multi-prog attachments for new netns attach types by
storing programs to run in a bpf_prog_array, which is well suited for
iterating over programs and running them in sequence.

After this change bpf(PROG_QUERY) may block to allocate memory in
bpf_prog_array_copy_to_user() for collected program IDs. This forces a
change in how we protect access to the attached program in the query
callback. Because bpf_prog_array_copy_to_user() can sleep, we switch from
an RCU read lock to holding a mutex that serializes updaters.

Because we allow only one BPF flow_dissector program to be attached to
netns at all times, the bpf_prog_array pointed by net->bpf.run_array is
always either detached (null) or one element long.

No functional changes intended.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200625141357.910330-3-jakub@cloudflare.com

1 files changed, 10 insertions, 9 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b57fb1359395..142a8824f0a8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -86,14 +86,14 @@ int flow_dissector_bpf_prog_attach_check(struct net *net,
 		for_each_net(ns) {
 			if (ns == &init_net)
 				continue;
-			if (rcu_access_pointer(ns->bpf.progs[type]))
+			if (rcu_access_pointer(ns->bpf.run_array[type]))
 				return -EEXIST;
 		}
 	} else {
 		/* Make sure root flow dissector is not attached
 		 * when attaching to the non-root namespace.
 		 */
-		if (rcu_access_pointer(init_net.bpf.progs[type]))
+		if (rcu_access_pointer(init_net.bpf.run_array[type]))
 			return -EEXIST;
 	}
 
@@ -894,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net,
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
 	bool mpls_el = false;
@@ -951,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net,
 	WARN_ON_ONCE(!net);
 	if (net) {
 		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+		struct bpf_prog_array *run_array;
 
 		rcu_read_lock();
-		attached = rcu_dereference(init_net.bpf.progs[type]);
+		run_array = rcu_dereference(init_net.bpf.run_array[type]);
+		if (!run_array)
+			run_array = rcu_dereference(net->bpf.run_array[type]);
 
-		if (!attached)
-			attached = rcu_dereference(net->bpf.progs[type]);
-
-		if (attached) {
+		if (run_array) {
 			struct bpf_flow_keys flow_keys;
 			struct bpf_flow_dissector ctx = {
 				.flow_keys = &flow_keys,
@@ -966,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net,
 				.data_end = data + hlen,
 			};
 			__be16 n_proto = proto;
+			struct bpf_prog *prog;
 
 			if (skb) {
 				ctx.skb = skb;
@@ -976,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net,
 				n_proto = skb->protocol;
 			}
 
-			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+			prog = READ_ONCE(run_array->items[0].prog);
+			ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
 					       hlen, flags);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);