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 <ja...@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
