bpf: add missing rcu protection when releasing programs from prog_array

Normally the program attachment place (like sockets, qdiscs) takes
care of rcu protection and calls bpf_prog_put() after a grace period.
The programs stored inside prog_array may not be attached anywhere,
so prog_array needs to take care of preserving rcu protection.
Otherwise bpf_tail_call() will race with bpf_prog_put().
To solve that introduce bpf_prog_put_rcu() helper function and use
it in 3 places where unattached program can decrement refcnt:
closing program fd, deleting/replacing program in prog_array.

Fixes: 04fd61ab36ec ("bpf: allow bpf programs to tail-call other bpf programs")
Reported-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8821b9a8689e67756df757f632353b05c7e519e8..5f520f5f087e7fabc4cff0716c8619ffd90e9141 100644 (file)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -123,7 +123,10 @@ struct bpf_prog_aux {
        const struct bpf_verifier_ops *ops;
        struct bpf_map **used_maps;
        struct bpf_prog *prog;
-       struct work_struct work;
+       union {
+               struct work_struct work;
+               struct rcu_head rcu;
+       };
 };
 
 struct bpf_array {
@@ -153,6 +156,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
+void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get(struct fd f);
 void bpf_map_put(struct bpf_map *map);

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 614bcd4c1d74fbed64d1780a34abf41fe2a76d18..cb31229a6fa4ddd39c1d69038b998bc0c0dee4db 100644 (file)
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -202,7 +202,7 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key,
 
        old_prog = xchg(array->prog + index, prog);
        if (old_prog)
-               bpf_prog_put(old_prog);
+               bpf_prog_put_rcu(old_prog);
 
        return 0;
 }
@@ -218,7 +218,7 @@ static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
 
        old_prog = xchg(array->prog + index, NULL);
        if (old_prog) {
-               bpf_prog_put(old_prog);
+               bpf_prog_put_rcu(old_prog);
                return 0;
        } else {
                return -ENOENT;

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 98a69bd83069598487236d7c6cce9e6895f267cf..a1b14d197a4fc2da6acf2d812372284e78bc5af8 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -432,6 +432,23 @@ static void free_used_maps(struct bpf_prog_aux *aux)
        kfree(aux->used_maps);
 }
 
+static void __prog_put_rcu(struct rcu_head *rcu)
+{
+       struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
+
+       free_used_maps(aux);
+       bpf_prog_free(aux->prog);
+}
+
+/* version of bpf_prog_put() that is called after a grace period */
+void bpf_prog_put_rcu(struct bpf_prog *prog)
+{
+       if (atomic_dec_and_test(&prog->aux->refcnt)) {
+               prog->aux->prog = prog;
+               call_rcu(&prog->aux->rcu, __prog_put_rcu);
+       }
+}
+
 void bpf_prog_put(struct bpf_prog *prog)
 {
        if (atomic_dec_and_test(&prog->aux->refcnt)) {
@@ -445,7 +462,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
        struct bpf_prog *prog = filp->private_data;
 
-       bpf_prog_put(prog);
+       bpf_prog_put_rcu(prog);
        return 0;
 }