drm/amd/pm: fix runpm hang when amdgpu loaded prior to sound driver

Current RUNPM mechanism relies on PMFW to master the timing for BACO
in/exit. And that needs cooperation from sound driver for dstate
change notification for function 1(audio). Otherwise(on sound driver
missing), BACO cannot be kicked in correctly and hang will be observed
on RUNPM exit.

By switching back to legacy message way on sound driver missing,
we are able to fix the runpm hang observed for the scenario below:
amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reported-and-tested-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

4 files changed, 47 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index aec7cb21cc0f..b1ad451af06b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2274,7 +2274,27 @@ static int navi10_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	/*
+	 * This aims the case below:
+	 *   amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded
+	 *
+	 * For NAVI10 and later ASICs, we rely on PMFW to handle the runpm. To
+	 * make that possible, PMFW needs to acknowledge the dstate transition
+	 * process for both gfx(function 0) and audio(function 1) function of
+	 * the ASIC.
+	 *
+	 * The PCI device's initial runpm status is RUNPM_SUSPENDED. So as the
+	 * device representing the audio function of the ASIC. And that means
+	 * even if the sound driver(snd_hda_intel) was not loaded yet, it's still
+	 * possible runpm suspend kicked on the ASIC. However without the dstate
+	 * transition notification from audio function, pmfw cannot handle the
+	 * BACO in/exit correctly. And that will cause driver hang on runpm
+	 * resuming.
+	 *
+	 * To address this, we revert to legacy message way(driver masters the
+	 * timing for BACO in/exit) on sound driver missing.
+	 */
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2284,7 +2304,7 @@ static int navi10_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index d7519688065f..ca57221e3962 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -2189,7 +2189,7 @@ static int sienna_cichlid_baco_enter(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm)
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev))
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
 	else
 		return smu_v11_0_baco_enter(smu);
@@ -2199,7 +2199,7 @@ static int sienna_cichlid_baco_exit(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	if (adev->in_runpm) {
+	if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) {
 		/* Wait for PMFW handling for the Dstate change */
 		msleep(10);
 		return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 66711ab24c15..843d2cbfc71d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1053,3 +1053,24 @@ int smu_cmn_set_mp1_state(struct smu_context *smu,
 
 	return ret;
 }
+
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev)
+{
+	struct pci_dev *p = NULL;
+	bool snd_driver_loaded;
+
+	/*
+	 * If the ASIC comes with no audio function, we always assume
+	 * it is "enabled".
+	 */
+	p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus),
+			adev->pdev->bus->number, 1);
+	if (!p)
+		return true;
+
+	snd_driver_loaded = pci_is_enabled(p) ? true : false;
+
+	pci_dev_put(p);
+
+	return snd_driver_loaded;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 4054d9493e77..beea03810bca 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -123,5 +123,7 @@ static inline void smu_cmn_get_sysfs_buf(char **buf, int *offset)
 	*buf -= *offset;
 }
 
+bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev);
+
 #endif
 #endif