drm/amdgpu: add module parameter choose reset mode

Default value is auto, doesn't change
original reset method logic.

v2: change to use parameter reset_method
v3: add warn msg if specified mode isn't supported

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Wenhui Sheng <Wenhui.Sheng@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -193,6 +193,7 @@ static const bool debug_evictions; /* = false */
 #endif
 
 extern int amdgpu_tmz;
+extern int amdgpu_reset_method;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -149,6 +149,7 @@ int amdgpu_mes = 0;
 int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
+int amdgpu_reset_method = -1; /* auto */
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -757,6 +758,13 @@ module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444);
 MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto, 0 = off (default), 1 = on)");
 module_param_named(tmz, amdgpu_tmz, int, 0444);
 
+/**
+ * DOC: reset_method (int)
+ * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
+ */
+MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)");
+module_param_named(reset_method, amdgpu_reset_method, int, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},

drivers/gpu/drm/amd/amdgpu/cik.c

@@ -1326,6 +1326,14 @@ cik_asic_reset_method(struct amdgpu_device *adev)
 {
 	bool baco_reset;
 
+	if (amdgpu_reset_method == AMD_RESET_METHOD_LEGACY ||
+	    amdgpu_reset_method == AMD_RESET_METHOD_BACO)
+		return amdgpu_reset_method;
+
+	if (amdgpu_reset_method != -1)
+		dev_warn(adev->dev, "Specified reset:%d isn't supported, using AUTO instead.\n",
+				  amdgpu_reset_method);
+
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
 	case CHIP_HAWAII:

drivers/gpu/drm/amd/amdgpu/nv.c

@@ -311,6 +311,14 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 {
 	struct smu_context *smu = &adev->smu;
 
+	if (amdgpu_reset_method == AMD_RESET_METHOD_MODE1 ||
+	    amdgpu_reset_method == AMD_RESET_METHOD_BACO)
+		return amdgpu_reset_method;
+
+	if (amdgpu_reset_method != -1)
+		dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
+				  amdgpu_reset_method);
+
 	if (smu_baco_is_support(smu))
 		return AMD_RESET_METHOD_BACO;
 	else

drivers/gpu/drm/amd/amdgpu/si.c

@@ -1229,6 +1229,11 @@ static bool si_asic_supports_baco(struct amdgpu_device *adev)
 static enum amd_reset_method
 si_asic_reset_method(struct amdgpu_device *adev)
 {
+	if (amdgpu_reset_method != AMD_RESET_METHOD_LEGACY &&
+	    amdgpu_reset_method != -1)
+		dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
+				  amdgpu_reset_method);
+
 	return AMD_RESET_METHOD_LEGACY;
 }
 

drivers/gpu/drm/amd/amdgpu/soc15.c

@@ -532,6 +532,15 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 	bool baco_reset = false;
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
+	if (amdgpu_reset_method == AMD_RESET_METHOD_MODE1 ||
+	    amdgpu_reset_method == AMD_RESET_METHOD_MODE2 ||
+		amdgpu_reset_method == AMD_RESET_METHOD_BACO)
+		return amdgpu_reset_method;
+
+	if (amdgpu_reset_method != -1)
+		dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
+				  amdgpu_reset_method);
+
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:

drivers/gpu/drm/amd/amdgpu/vi.c

@@ -710,6 +710,14 @@ vi_asic_reset_method(struct amdgpu_device *adev)
 {
 	bool baco_reset;
 
+	if (amdgpu_reset_method == AMD_RESET_METHOD_LEGACY ||
+	    amdgpu_reset_method == AMD_RESET_METHOD_BACO)
+		return amdgpu_reset_method;
+
+	if (amdgpu_reset_method != -1)
+		dev_warn(adev->dev, "Specified reset method:%d isn't supported, using AUTO instead.\n",
+				  amdgpu_reset_method);
+
 	switch (adev->asic_type) {
 	case CHIP_FIJI:
 	case CHIP_TONGA: