ASoC: Intel: Skylake: Fix mcps freeup after module unbind failure

While cleaning resources on module pmd event, we check for return
of skl_unbind_modules(). On failure this causes leak as all modules
attached do not have resources freed.

So ignore return value of module unbind and continue freeing
resources. This makes dapm state and resources correct.

Signed-off-by: Guneshwor Singh <[email protected]>
Signed-off-by: Vinod Koul <[email protected]>
Signed-off-by: Mark Brown <[email protected]>

diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index c67e3acb81022371622e6097d38d6cb8cf3ebc27..86d5323e91846547c221d7183cac435ae4b20c39 100644 (file)
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -98,7 +98,7 @@ static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
                        "%s: module_id %d instance %d\n", __func__,
                        mconfig->id.module_id, mconfig->id.instance_id);
                dev_err(ctx->dev,
-                       "exceeds ppl memory available %d > mem %d\n",
+                       "exceeds ppl mcps available %d > mem %d\n",
                        skl->resource.max_mcps, skl->resource.mcps);
                return false;
        }
@@ -773,10 +773,7 @@ static int skl_tplg_mixer_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
                        continue;
                }
 
-               ret = skl_unbind_modules(ctx, src_module, dst_module);
-               if (ret < 0)
-                       return ret;
-
+               skl_unbind_modules(ctx, src_module, dst_module);
                src_module = dst_module;
        }