It is possible for bpf_kfunc_call_test_release() to be called from
bpf_map_free_deferred() when bpf_testmod is already unloaded and
perf_test_stuct.cnt which it tries to decrease is no longer in memory.
This patch tries to fix the issue by waiting for all references to be
dropped in bpf_testmod_exit().

The issue can be triggered by running 'test_progs -t map_kptr' in 6.5,
but is obscured in 6.6 by d119357d07435 ("rcu-tasks: Treat only
synchronous grace periods urgently").

Fixes: 65eb006d85a2a ("bpf: Move kernel test kfuncs to bpf_testmod")
Signed-off-by: Artem Savkov <asavkov@redhat.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
---
 tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 91907b321f913..e7c9e1c7fde04 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include <linux/btf.h>
 #include <linux/btf_ids.h>
+#include <linux/delay.h>
 #include <linux/error-injection.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -544,6 +545,14 @@ static int bpf_testmod_init(void)
 
 static void bpf_testmod_exit(void)
 {
+        /* Need to wait for all references to be dropped because
+         * bpf_kfunc_call_test_release() which currently resides in kernel can
+         * be called after bpf_testmod is unloaded. Once release function is
+         * moved into the module this wait can be removed.
+         */
+	while (refcount_read(&prog_test_struct.cnt) > 1)
+		msleep(20);
+
 	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 
-- 
2.43.0

On Wed, Jan 10, 2024 at 09:57:37AM +0100, Artem Savkov wrote:
> It is possible for bpf_kfunc_call_test_release() to be called from
> bpf_map_free_deferred() when bpf_testmod is already unloaded and
> perf_test_stuct.cnt which it tries to decrease is no longer in memory.
> This patch tries to fix the issue by waiting for all references to be
> dropped in bpf_testmod_exit().
> 
> The issue can be triggered by running 'test_progs -t map_kptr' in 6.5,
> but is obscured in 6.6 by d119357d07435 ("rcu-tasks: Treat only
> synchronous grace periods urgently").
> 
> Fixes: 65eb006d85a2a ("bpf: Move kernel test kfuncs to bpf_testmod")
> Signed-off-by: Artem Savkov <asavkov@redhat.com>
> Acked-by: Yonghong Song <yonghong.song@linux.dev>

Acked-by: Jiri Olsa <jolsa@kernel.org>

jirka

> ---
>  tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
> 
> diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
> index 91907b321f913..e7c9e1c7fde04 100644
> --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
> +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
> @@ -2,6 +2,7 @@
>  /* Copyright (c) 2020 Facebook */
>  #include <linux/btf.h>
>  #include <linux/btf_ids.h>
> +#include <linux/delay.h>
>  #include <linux/error-injection.h>
>  #include <linux/init.h>
>  #include <linux/module.h>
> @@ -544,6 +545,14 @@ static int bpf_testmod_init(void)
>  
>  static void bpf_testmod_exit(void)
>  {
> +        /* Need to wait for all references to be dropped because
> +         * bpf_kfunc_call_test_release() which currently resides in kernel can
> +         * be called after bpf_testmod is unloaded. Once release function is
> +         * moved into the module this wait can be removed.
> +         */
> +	while (refcount_read(&prog_test_struct.cnt) > 1)
> +		msleep(20);
> +
>  	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
>  }
>  
> -- 
> 2.43.0
>