netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jakub Sitnicki <jakub@cloudflare.com>
To: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, kernel-team@cloudflare.com,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>
Subject: [PATCH bpf-next v3 01/16] bpf, netns: Handle multiple link attachments
Date: Thu,  2 Jul 2020 11:24:01 +0200	[thread overview]
Message-ID: <20200702092416.11961-2-jakub@cloudflare.com> (raw)
In-Reply-To: <20200702092416.11961-1-jakub@cloudflare.com>

Extend the BPF netns link callbacks to rebuild (grow/shrink) or update the
prog_array at given position when link gets attached/updated/released.

This let's us lift the limit of having just one link attached for the new
attach type introduced by subsequent patch.

No functional changes intended.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---

Notes:
    v3:
    - New in v3 to support multi-prog attachments. (Alexei)

 include/linux/bpf.h        |  4 ++
 kernel/bpf/core.c          | 22 ++++++++++
 kernel/bpf/net_namespace.c | 88 +++++++++++++++++++++++++++++++++++---
 3 files changed, 107 insertions(+), 7 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3d2ade703a35..26bc70533db0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -928,6 +928,10 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 
 void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
 				struct bpf_prog *old_prog);
+void bpf_prog_array_delete_safe_at(struct bpf_prog_array *array,
+				   unsigned int index);
+void bpf_prog_array_update_at(struct bpf_prog_array *array, unsigned int index,
+			      struct bpf_prog *prog);
 int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9df4cc9a2907..d4b3b9ee6bf1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1958,6 +1958,28 @@ void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
 		}
 }
 
+void bpf_prog_array_delete_safe_at(struct bpf_prog_array *array,
+				   unsigned int index)
+{
+	bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog);
+}
+
+void bpf_prog_array_update_at(struct bpf_prog_array *array, unsigned int index,
+			      struct bpf_prog *prog)
+{
+	struct bpf_prog_array_item *item;
+
+	for (item = array->items; item->prog; item++) {
+		if (item->prog == &dummy_bpf_prog.prog)
+			continue;
+		if (!index) {
+			WRITE_ONCE(item->prog, prog);
+			break;
+		}
+		index--;
+	}
+}
+
 int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 247543380fa6..6011122c35b6 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -36,11 +36,51 @@ static void netns_bpf_run_array_detach(struct net *net,
 	bpf_prog_array_free(run_array);
 }
 
+static unsigned int link_index(struct net *net,
+			       enum netns_bpf_attach_type type,
+			       struct bpf_netns_link *link)
+{
+	struct bpf_netns_link *pos;
+	unsigned int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		if (pos == link)
+			return i;
+		i++;
+	}
+	return UINT_MAX;
+}
+
+static unsigned int link_count(struct net *net,
+			       enum netns_bpf_attach_type type)
+{
+	struct list_head *pos;
+	unsigned int i = 0;
+
+	list_for_each(pos, &net->bpf.links[type])
+		i++;
+	return i;
+}
+
+static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type,
+			    struct bpf_prog_array *prog_array)
+{
+	struct bpf_netns_link *pos;
+	unsigned int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		prog_array->items[i].prog = pos->link.prog;
+		i++;
+	}
+}
+
 static void bpf_netns_link_release(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 *old_array, *new_array;
+	unsigned int cnt, idx;
 	struct net *net;
 
 	mutex_lock(&netns_bpf_mutex);
@@ -53,9 +93,27 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	if (!net)
 		goto out_unlock;
 
-	netns_bpf_run_array_detach(net, type);
+	/* Remember link position in case of safe delete */
+	idx = link_index(net, type, net_link);
 	list_del(&net_link->node);
 
+	cnt = link_count(net, type);
+	if (!cnt) {
+		netns_bpf_run_array_detach(net, type);
+		goto out_unlock;
+	}
+
+	old_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+	if (!new_array) {
+		bpf_prog_array_delete_safe_at(old_array, idx);
+		goto out_unlock;
+	}
+	fill_prog_array(net, type, new_array);
+	rcu_assign_pointer(net->bpf.run_array[type], new_array);
+	bpf_prog_array_free(old_array);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 }
@@ -76,6 +134,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *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;
+	unsigned int idx;
 	struct net *net;
 	int ret = 0;
 
@@ -95,7 +154,8 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 
 	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);
+	idx = link_index(net, type, net_link);
+	bpf_prog_array_update_at(run_array, idx, new_prog);
 
 	old_prog = xchg(&link->prog, new_prog);
 	bpf_prog_put(old_prog);
@@ -295,18 +355,29 @@ int netns_bpf_prog_detach(const union bpf_attr *attr)
 	return ret;
 }
 
+static int netns_bpf_max_progs(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
 static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 				 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;
+	unsigned int cnt;
 	int err;
 
 	mutex_lock(&netns_bpf_mutex);
 
-	/* Allow attaching only one prog or link for now */
-	if (!list_empty(&net->bpf.links[type])) {
+	cnt = link_count(net, type);
+	if (cnt >= netns_bpf_max_progs(type)) {
 		err = -E2BIG;
 		goto out_unlock;
 	}
@@ -327,16 +398,19 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	if (err)
 		goto out_unlock;
 
-	run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+	run_array = bpf_prog_array_alloc(cnt + 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]);
 
+	fill_prog_array(net, type, run_array);
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 	return err;
-- 
2.25.4


  reply	other threads:[~2020-07-02  9:24 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-02  9:24 [PATCH bpf-next v3 00/16] Run a BPF program on socket lookup Jakub Sitnicki
2020-07-02  9:24 ` Jakub Sitnicki [this message]
2020-07-09  3:44   ` [PATCH bpf-next v3 01/16] bpf, netns: Handle multiple link attachments Andrii Nakryiko
2020-07-09 12:49     ` Jakub Sitnicki
2020-07-09 22:02       ` Andrii Nakryiko
2020-07-10 19:23         ` Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 02/16] bpf: Introduce SK_LOOKUP program type with a dedicated attach point Jakub Sitnicki
2020-07-04 18:42   ` Yonghong Song
2020-07-06 11:44     ` Jakub Sitnicki
2020-07-05  9:20   ` kernel test robot
2020-07-05  9:20   ` [RFC PATCH] bpf: sk_lookup_prog_ops can be static kernel test robot
2020-07-07  9:21   ` [PATCH bpf-next v3 02/16] bpf: Introduce SK_LOOKUP program type with a dedicated attach point Jakub Sitnicki
2020-07-09  4:08   ` Andrii Nakryiko
2020-07-09 13:25     ` Jakub Sitnicki
2020-07-09 23:09       ` Andrii Nakryiko
2020-07-10  8:55         ` Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 03/16] inet: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 04/16] inet: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-07-02 10:27   ` Lorenz Bauer
2020-07-02 12:46     ` Jakub Sitnicki
2020-07-02 13:19       ` Lorenz Bauer
2020-07-06 11:24         ` Jakub Sitnicki
2020-07-06 12:06   ` Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 05/16] inet6: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 06/16] inet6: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 07/16] udp: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 08/16] udp: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 09/16] udp6: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 10/16] udp6: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-07-02 14:51   ` kernel test robot
2020-07-03 13:04     ` Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 11/16] bpf: Sync linux/bpf.h to tools/ Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 12/16] libbpf: Add support for SK_LOOKUP program type Jakub Sitnicki
2020-07-09  4:23   ` Andrii Nakryiko
2020-07-09 15:51     ` Jakub Sitnicki
2020-07-09 23:13       ` Andrii Nakryiko
2020-07-10  8:37         ` Jakub Sitnicki
2020-07-10 18:55           ` Andrii Nakryiko
2020-07-10 19:24             ` Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 13/16] tools/bpftool: Add name mappings for SK_LOOKUP prog and attach type Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 14/16] selftests/bpf: Add verifier tests for bpf_sk_lookup context access Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 15/16] selftests/bpf: Rename test_sk_lookup_kern.c to test_ref_track_kern.c Jakub Sitnicki
2020-07-02  9:24 ` [PATCH bpf-next v3 16/16] selftests/bpf: Tests for BPF_SK_LOOKUP attach point Jakub Sitnicki
2020-07-02 11:01   ` Lorenz Bauer
2020-07-02 12:59     ` Jakub Sitnicki
2020-07-09  4:28       ` Andrii Nakryiko
2020-07-09 15:54         ` Jakub Sitnicki
2020-07-02 11:05 ` [PATCH bpf-next v3 00/16] Run a BPF program on socket lookup Lorenz Bauer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200702092416.11961-2-jakub@cloudflare.com \
    --to=jakub@cloudflare.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=kernel-team@cloudflare.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).