[bpf PATCH 1/3] bpf: sockmap, map_release does not hold refcnt for pinned maps

[John Fastabend <john.fastabend@gmail.com>]

Relying on map_release hook to decrement the reference counts when a
map is removed only works if the map is not being pinned. In the
pinned case the ref is decremented immediately and the BPF programs
released. After this BPF programs may not be in-use which is not
what the user would expect.

This patch moves the release logic into bpf_map_put_uref() and brings
sockmap in-line with how a similar case is handled in prog array maps.

Fixes: 3d9e952697de ("bpf: sockmap, fix leaking maps with attached but not detached progs")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
 include/linux/bpf.h  |    3 +++
 kernel/bpf/sockmap.c |    3 +--
 kernel/bpf/syscall.c |   10 +++++++++-
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 95a7abd..8a71058 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -646,6 +646,7 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+void sock_map_release(struct bpf_map *map);
 #else
 static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -658,6 +659,8 @@ static inline int sock_map_prog(struct bpf_map *map,
 {
 	return -EOPNOTSUPP;
 }
+
+void sock_map_release(struct bpf_map *map) {}
 #endif
 
 /* verifier prototypes for helper functions called from eBPF programs */
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 8dd9210..cef187f 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -1834,7 +1834,7 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+void sock_map_release(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	struct bpf_prog *orig;
@@ -1858,7 +1858,6 @@ static void sock_map_release(struct bpf_map *map, struct file *map_file)
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0244973..449a618 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -257,8 +257,16 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_PROG_ARRAY:
 			bpf_fd_array_map_clear(map);
+			break;
+		case BPF_MAP_TYPE_SOCKMAP:
+			sock_map_release(map);
+			break;
+		default:
+			break;
+		}
 	}
 }