Merge branch 'bpf-multi-prog-prep'

Jakub Sitnicki says:

====================
This patch set prepares ground for link-based multi-prog attachment for
future netns attach types, with BPF_SK_LOOKUP attach type in mind [0].

Two changes are needed in order to attach and run a series of BPF programs:

  1) an bpf_prog_array of programs to run (patch #2), and
  2) a list of attached links to keep track of attachments (patch #3).

Nothing changes for BPF flow_dissector. Just as before only one program can
be attached to netns.

In v3 I've simplified patch #2 that introduces bpf_prog_array to take
advantage of the fact that it will hold at most one program for now.

In particular, I'm no longer using bpf_prog_array_copy. It turned out to be
less suitable for link operations than I thought as it fails to append the
same BPF program.

bpf_prog_array_replace_item is also gone, because we know we always want to
replace the first element in prog_array.

Naturally the code that handles bpf_prog_array will need change once
more when there is a program type that allows multi-prog attachment. But I
feel it will be better to do it gradually and present it together with
tests that actually exercise multi-prog code paths.

[0] https://lore.kernel.org/bpf/20200511185218.1422406-1-jakub@cloudflare.com/

v2 -> v3:
- Don't check if run_array is null in link update callback. (Martin)
- Allow updating the link with the same BPF program. (Andrii)
- Add patch #4 with a test for the above case.
- Kill bpf_prog_array_replace_item. Access the run_array directly.
- Switch from bpf_prog_array_copy() to bpf_prog_array_alloc(1, ...).
- Replace rcu_deref_protected & RCU_INIT_POINTER with rcu_replace_pointer.
- Drop Andrii's Ack from patch #2. Code changed.

v1 -> v2:

- Show with a (void) cast that bpf_prog_array_replace_item() return value
  is ignored on purpose. (Andrii)
- Explain why bpf-cgroup cannot replace programs in bpf_prog_array based
  on bpf_prog pointer comparison in patch #2 description. (Andrii)
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 113 insertions, 49 deletions

diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 78cf061f8179..7a34a8caf954 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -19,18 +19,21 @@ struct bpf_netns_link {
 	 * with netns_bpf_mutex held.
 	 */
 	struct net *net;
+	struct list_head node; /* node in list of links attached to net */
 };
 
 /* Protects updates to netns_bpf */
 DEFINE_MUTEX(netns_bpf_mutex);
 
 /* Must be called with netns_bpf_mutex held. */
-static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link)
+static void netns_bpf_run_array_detach(struct net *net,
+				       enum netns_bpf_attach_type type)
 {
-	struct bpf_netns_link *net_link =
-		container_of(link, struct bpf_netns_link, link);
+	struct bpf_prog_array *run_array;
 
-	net_link->net = NULL;
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
 }
 
 static void bpf_netns_link_release(struct bpf_link *link)
@@ -54,8 +57,8 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	if (!net)
 		goto out_unlock;
 
-	net->bpf.links[type] = NULL;
-	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+	netns_bpf_run_array_detach(net, type);
+	list_del(&net_link->node);
 
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
@@ -76,6 +79,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 	struct bpf_netns_link *net_link =
 		container_of(link, struct bpf_netns_link, link);
 	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct bpf_prog_array *run_array;
 	struct net *net;
 	int ret = 0;
 
@@ -93,8 +97,11 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 		goto out_unlock;
 	}
 
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	WRITE_ONCE(run_array->items[0].prog, new_prog);
+
 	old_prog = xchg(&link->prog, new_prog);
-	rcu_assign_pointer(net->bpf.progs[type], new_prog);
 	bpf_prog_put(old_prog);
 
 out_unlock:
@@ -142,14 +149,38 @@ static const struct bpf_link_ops bpf_netns_link_ops = {
 	.show_fdinfo = bpf_netns_link_show_fdinfo,
 };
 
+/* Must be called with netns_bpf_mutex held. */
+static int __netns_bpf_prog_query(const union bpf_attr *attr,
+				  union bpf_attr __user *uattr,
+				  struct net *net,
+				  enum netns_bpf_attach_type type)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	struct bpf_prog_array *run_array;
+	u32 prog_cnt = 0, flags = 0;
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array)
+		prog_cnt = bpf_prog_array_length(run_array);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		return -EFAULT;
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		return 0;
+
+	return bpf_prog_array_copy_to_user(run_array, prog_ids,
+					   attr->query.prog_cnt);
+}
+
 int netns_bpf_prog_query(const union bpf_attr *attr,
 			 union bpf_attr __user *uattr)
 {
-	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
-	u32 prog_id, prog_cnt = 0, flags = 0;
 	enum netns_bpf_attach_type type;
-	struct bpf_prog *attached;
 	struct net *net;
+	int ret;
 
 	if (attr->query.query_flags)
 		return -EINVAL;
@@ -162,33 +193,19 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
 	if (IS_ERR(net))
 		return PTR_ERR(net);
 
-	rcu_read_lock();
-	attached = rcu_dereference(net->bpf.progs[type]);
-	if (attached) {
-		prog_cnt = 1;
-		prog_id = attached->aux->id;
-	}
-	rcu_read_unlock();
+	mutex_lock(&netns_bpf_mutex);
+	ret = __netns_bpf_prog_query(attr, uattr, net, type);
+	mutex_unlock(&netns_bpf_mutex);
 
 	put_net(net);
-
-	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
-		return -EFAULT;
-	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
-		return -EFAULT;
-
-	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
-		return 0;
-
-	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
-		return -EFAULT;
-
-	return 0;
+	return ret;
 }
 
 int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
+	struct bpf_prog_array *run_array;
 	enum netns_bpf_attach_type type;
+	struct bpf_prog *attached;
 	struct net *net;
 	int ret;
 
@@ -200,19 +217,47 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	mutex_lock(&netns_bpf_mutex);
 
 	/* Attaching prog directly is not compatible with links */
-	if (net->bpf.links[type]) {
+	if (!list_empty(&net->bpf.links[type])) {
 		ret = -EEXIST;
 		goto out_unlock;
 	}
 
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
-		ret = flow_dissector_bpf_prog_attach(net, prog);
+		ret = flow_dissector_bpf_prog_attach_check(net, prog);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
+	if (ret)
+		goto out_unlock;
+
+	attached = net->bpf.progs[type];
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array) {
+		WRITE_ONCE(run_array->items[0].prog, prog);
+	} else {
+		run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+		if (!run_array) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
+		run_array->items[0].prog = prog;
+		rcu_assign_pointer(net->bpf.run_array[type], run_array);
+	}
+
+	net->bpf.progs[type] = prog;
+	if (attached)
+		bpf_prog_put(attached);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 
@@ -226,14 +271,14 @@ static int __netns_bpf_prog_detach(struct net *net,
 	struct bpf_prog *attached;
 
 	/* Progs attached via links cannot be detached */
-	if (net->bpf.links[type])
+	if (!list_empty(&net->bpf.links[type]))
 		return -EINVAL;
 
-	attached = rcu_dereference_protected(net->bpf.progs[type],
-					     lockdep_is_held(&netns_bpf_mutex));
+	attached = net->bpf.progs[type];
 	if (!attached)
 		return -ENOENT;
-	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+	netns_bpf_run_array_detach(net, type);
+	net->bpf.progs[type] = NULL;
 	bpf_prog_put(attached);
 	return 0;
 }
@@ -257,27 +302,27 @@ int netns_bpf_prog_detach(const union bpf_attr *attr)
 static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 				 enum netns_bpf_attach_type type)
 {
-	struct bpf_prog *prog;
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	struct bpf_prog_array *run_array;
 	int err;
 
 	mutex_lock(&netns_bpf_mutex);
 
 	/* Allow attaching only one prog or link for now */
-	if (net->bpf.links[type]) {
+	if (!list_empty(&net->bpf.links[type])) {
 		err = -E2BIG;
 		goto out_unlock;
 	}
 	/* Links are not compatible with attaching prog directly */
-	prog = rcu_dereference_protected(net->bpf.progs[type],
-					 lockdep_is_held(&netns_bpf_mutex));
-	if (prog) {
+	if (net->bpf.progs[type]) {
 		err = -EEXIST;
 		goto out_unlock;
 	}
 
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
-		err = flow_dissector_bpf_prog_attach(net, link->prog);
+		err = flow_dissector_bpf_prog_attach_check(net, link->prog);
 		break;
 	default:
 		err = -EINVAL;
@@ -286,7 +331,15 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	if (err)
 		goto out_unlock;
 
-	net->bpf.links[type] = link;
+	run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+	if (!run_array) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	run_array->items[0].prog = link->prog;
+	rcu_assign_pointer(net->bpf.run_array[type], run_array);
+
+	list_add_tail(&net_link->node, &net->bpf.links[type]);
 
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
@@ -345,23 +398,34 @@ out_put_net:
 	return err;
 }
 
+static int __net_init netns_bpf_pernet_init(struct net *net)
+{
+	int type;
+
+	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++)
+		INIT_LIST_HEAD(&net->bpf.links[type]);
+
+	return 0;
+}
+
 static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
 {
 	enum netns_bpf_attach_type type;
-	struct bpf_link *link;
+	struct bpf_netns_link *net_link;
 
 	mutex_lock(&netns_bpf_mutex);
 	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
-		link = net->bpf.links[type];
-		if (link)
-			bpf_netns_link_auto_detach(link);
-		else
-			__netns_bpf_prog_detach(net, type);
+		netns_bpf_run_array_detach(net, type);
+		list_for_each_entry(net_link, &net->bpf.links[type], node)
+			net_link->net = NULL; /* auto-detach link */
+		if (net->bpf.progs[type])
+			bpf_prog_put(net->bpf.progs[type]);
 	}
 	mutex_unlock(&netns_bpf_mutex);
 }
 
 static struct pernet_operations netns_bpf_pernet_ops __net_initdata = {
+	.init = netns_bpf_pernet_init,
 	.pre_exit = netns_bpf_pernet_pre_exit,
 };