ASoC: SOF: core: release resources on errors in probe_continue

BugLink: https://bugs.launchpad.net/bugs/1863588
[ Upstream commit 410e5e55c9c1c9c0d452ac5b9adb37b933a7747e ]

The initial intent of releasing resources in the .remove does not work
well with HDaudio codecs. If the probe_continue() fails in a work
queue, e.g. due to missing firmware or authentication issues, we don't
release any resources, and as a result the kernel oopses during
suspend operations.

The suggested fix is to release all resources during errors in
probe_continue(), and use fw_state to track resource allocation
state, so that .remove does not attempt to release the same
hardware resources twice. PM operations are also modified so that
no action is done if DSP resources have been freed due to
an error at probe.

Reported-by: Takashi Iwai <tiwai@suse.de>
Co-developed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Bugzilla:  http://bugzilla.suse.com/show_bug.cgi?id=1161246
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20200124213625.30186-4-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Paolo Pisati <paolo.pisati@canonical.com>

diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index f9ebdf2cfc31d54eacf1e46b8c0313fecb579f2a..12aec140819a29c4398798095e081d43d7021858 100644 (file)
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -440,7 +440,6 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 
        return 0;
 
-#if !IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)
 fw_trace_err:
        snd_sof_free_trace(sdev);
 fw_run_err:
@@ -451,22 +450,10 @@ ipc_err:
        snd_sof_free_debug(sdev);
 dbg_err:
        snd_sof_remove(sdev);
-#else
-
-       /*
-        * when the probe_continue is handled in a work queue, the
-        * probe does not fail so we don't release resources here.
-        * They will be released with an explicit call to
-        * snd_sof_device_remove() when the PCI/ACPI device is removed
-        */
-
-fw_trace_err:
-fw_run_err:
-fw_load_err:
-ipc_err:
-dbg_err:
 
-#endif
+       /* all resources freed, update state to match */
+       sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
+       sdev->first_boot = true;
 
        return ret;
 }
@@ -545,10 +532,12 @@ int snd_sof_device_remove(struct device *dev)
        if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE))
                cancel_work_sync(&sdev->probe_work);
 
-       snd_sof_fw_unload(sdev);
-       snd_sof_ipc_free(sdev);
-       snd_sof_free_debug(sdev);
-       snd_sof_free_trace(sdev);
+       if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED) {
+               snd_sof_fw_unload(sdev);
+               snd_sof_ipc_free(sdev);
+               snd_sof_free_debug(sdev);
+               snd_sof_free_trace(sdev);
+       }
 
        /*
         * Unregister machine driver. This will unbind the snd_card which
@@ -564,7 +553,8 @@ int snd_sof_device_remove(struct device *dev)
         * scheduled on, when they are unloaded. Therefore, the DSP must be
         * removed only after the topology has been unloaded.
         */
-       snd_sof_remove(sdev);
+       if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED)
+               snd_sof_remove(sdev);
 
        /* release firmware */
        release_firmware(pdata->fw);

diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index e9fbac38d9238cbdac2474b80d5c077b82fbafa1..195af259e78e30b2c2f576afc9e328efbe9594a8 100644 (file)
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -269,6 +269,10 @@ static int sof_resume(struct device *dev, bool runtime_resume)
        if (!sof_ops(sdev)->resume || !sof_ops(sdev)->runtime_resume)
                return 0;
 
+       /* DSP was never successfully started, nothing to resume */
+       if (sdev->first_boot)
+               return 0;
+
        /*
         * if the runtime_resume flag is set, call the runtime_resume routine
         * or else call the system resume routine