bpf: wait for running BPF programs when updating map-in-map

The map-in-map frequently serves as a mechanism for atomic
snapshotting of state that a BPF program might record.  The current
implementation is dangerous to use in this way, however, since
userspace has no way of knowing when all programs that might have
retrieved the "old" value of the map may have completed.

This change ensures that map update operations on map-in-map map types
always wait for all references to the old map to drop before returning
to userspace.

Signed-off-by: Daniel Colascione <dancol@google.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 13 insertions, 0 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4f416234251f..53968f82b919 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -748,6 +748,17 @@ err_put:
         return err;
 }
 
+static void maybe_wait_bpf_programs(struct bpf_map *map)
+{
+        /* Wait for any running BPF programs to complete so that
+         * userspace, when we return to it, knows that all programs
+         * that could be running use the new map value.
+         */
+        if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
+            map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+                synchronize_rcu();
+}
+
 #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
 static int map_update_elem(union bpf_attr *attr)
@@ -842,6 +853,7 @@ static int map_update_elem(union bpf_attr *attr)
         }
         __this_cpu_dec(bpf_prog_active);
         preempt_enable();
+        maybe_wait_bpf_programs(map);
 out:
 free_value:
         kfree(value);
@@ -894,6 +906,7 @@ static int map_delete_elem(union bpf_attr *attr)
         rcu_read_unlock();
         __this_cpu_dec(bpf_prog_active);
         preempt_enable();
+        maybe_wait_bpf_programs(map);
 out:
         kfree(key);
 err_put: