| Message ID | 20211221094447.2241-1-sj@kernel.org (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm/damon/dbgfs: Protect targets destructions with kdamond_lock | expand |
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 58dbb9692279..489be9c830c4 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -659,10 +659,12 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx) if (!targetid_is_pid(ctx)) return; + mutex_lock(&ctx->kdamond_lock); damon_for_each_target_safe(t, next, ctx) { put_pid((struct pid *)t->id); damon_destroy_target(t); } + mutex_unlock(&ctx->kdamond_lock); } static struct damon_ctx *dbgfs_new_ctx(void)
DAMON debugfs interface iterates current monitoring targets in 'dbgfs_target_ids_read()' while holding the corresponding 'kdamond_lock'. However, it also destructs the monitoring targets in 'dbgfs_before_terminate()' without holding the lock. This can result in a use_after_free bug. This commit avoids the race by protecting the destruction with the corresponding 'kdamond_lock'. Reported-by: Sangwoo Bae <sangwoob@amazon.com> Fixes: 4bc05954d007 ("mm/damon: implement a debugfs-based user space interface") Signed-off-by: SeongJae Park <sj@kernel.org> Cc: <stable@vger.kernel.org> # 5.15.x --- This cannot cleanly applied on 5.15.y tree. I will post a backport as soon as this is applied on the mainline. mm/damon/dbgfs.c | 2 ++ 1 file changed, 2 insertions(+)