Merge tag 'amd-drm-next-6.3-2023-01-13' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.3-2023-01-13:

amdgpu:
- Fix possible segfault in failure case
- Rework FW requests to happen in early_init for all IPs so
  that we don't lose the sbios console if FW is missing
- PSR fixes
- Misc cleanups
- Unload fix
- SMU13 fixes

amdkfd:
- Fix for cleared VRAM BOs
- Fix cleanup if GPUVM creation fails
- Memory accounting fix
- Use resource_size rather than open codeing it
- GC11 mGPU fix

radeon:
- Fix memory leak on shutdown

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230113225911.7776-1-alexander.deucher@amd.com

3 files changed, 22 insertions, 73 deletions

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 2fa79f892a92..ec52830dde24 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -623,6 +623,7 @@ static int smu_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu;
+	int r;
 
 	smu = kzalloc(sizeof(struct smu_context), GFP_KERNEL);
 	if (!smu)
@@ -640,7 +641,10 @@ static int smu_early_init(void *handle)
 	adev->powerplay.pp_handle = smu;
 	adev->powerplay.pp_funcs = &swsmu_pm_funcs;
 
-	return smu_set_funcs(adev);
+	r = smu_set_funcs(adev);
+	if (r)
+		return r;
+	return smu_init_microcode(smu);
 }
 
 static int smu_set_default_dpm_table(struct smu_context *smu)
@@ -1067,12 +1071,6 @@ static int smu_sw_init(void *handle)
 	smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 
-	ret = smu_init_microcode(smu);
-	if (ret) {
-		dev_err(adev->dev, "Failed to load smu firmware!\n");
-		return ret;
-	}
-
 	ret = smu_smc_table_sw_init(smu);
 	if (ret) {
 		dev_err(adev->dev, "Failed to sw init smc table!\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index ad66d57aa102..6492d69e2e60 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -93,7 +93,7 @@ static void smu_v11_0_poll_baco_exit(struct smu_context *smu)
 int smu_v11_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	const char *chip_name;
+	char ucode_prefix[30];
 	char fw_name[SMU_FW_NAME_LEN];
 	int err = 0;
 	const struct smc_firmware_header_v1_0 *hdr;
@@ -105,43 +105,11 @@ int smu_v11_0_init_microcode(struct smu_context *smu)
 	     (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7))))
 		return 0;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
-	case IP_VERSION(11, 0, 0):
-		chip_name = "navi10";
-		break;
-	case IP_VERSION(11, 0, 5):
-		chip_name = "navi14";
-		break;
-	case IP_VERSION(11, 0, 9):
-		chip_name = "navi12";
-		break;
-	case IP_VERSION(11, 0, 7):
-		chip_name = "sienna_cichlid";
-		break;
-	case IP_VERSION(11, 0, 11):
-		chip_name = "navy_flounder";
-		break;
-	case IP_VERSION(11, 0, 12):
-		chip_name = "dimgrey_cavefish";
-		break;
-	case IP_VERSION(11, 0, 13):
-		chip_name = "beige_goby";
-		break;
-	case IP_VERSION(11, 0, 2):
-		chip_name = "arcturus";
-		break;
-	default:
-		dev_err(adev->dev, "Unsupported IP version 0x%x\n",
-			adev->ip_versions[MP1_HWIP][0]);
-		return -EINVAL;
-	}
+	amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix);
 
-	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
-	if (err)
-		goto out;
-	err = amdgpu_ucode_validate(adev->pm.fw);
+	err = amdgpu_ucode_request(adev, &adev->pm.fw, fw_name);
 	if (err)
 		goto out;
 
@@ -159,12 +127,8 @@ int smu_v11_0_init_microcode(struct smu_context *smu)
 	}
 
 out:
-	if (err) {
-		DRM_ERROR("smu_v11_0: Failed to load firmware \"%s\"\n",
-			  fw_name);
-		release_firmware(adev->pm.fw);
-		adev->pm.fw = NULL;
-	}
+	if (err)
+		amdgpu_ucode_release(&adev->pm.fw);
 	return err;
 }
 
@@ -172,8 +136,7 @@ void smu_v11_0_fini_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	release_firmware(adev->pm.fw);
-	adev->pm.fw = NULL;
+	amdgpu_ucode_release(&adev->pm.fw);
 	adev->pm.fw_version = 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 8bc70ed7ed00..78945e79dbee 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -88,7 +88,6 @@ static const int link_speed[] = {25, 50, 80, 160};
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	const char *chip_name;
 	char fw_name[30];
 	char ucode_prefix[30];
 	int err = 0;
@@ -100,21 +99,11 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
-	case IP_VERSION(13, 0, 2):
-		chip_name = "aldebaran_smc";
-		break;
-	default:
-		amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
-		chip_name = ucode_prefix;
-	}
+	amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix);
 
-	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
-	if (err)
-		goto out;
-	err = amdgpu_ucode_validate(adev->pm.fw);
+	err = amdgpu_ucode_request(adev, &adev->pm.fw, fw_name);
 	if (err)
 		goto out;
 
@@ -132,12 +121,8 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
 	}
 
 out:
-	if (err) {
-		DRM_ERROR("smu_v13_0: Failed to load firmware \"%s\"\n",
-			  fw_name);
-		release_firmware(adev->pm.fw);
-		adev->pm.fw = NULL;
-	}
+	if (err)
+		amdgpu_ucode_release(&adev->pm.fw);
 	return err;
 }
 
@@ -145,8 +130,7 @@ void smu_v13_0_fini_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	release_firmware(adev->pm.fw);
-	adev->pm.fw = NULL;
+	amdgpu_ucode_release(&adev->pm.fw);
 	adev->pm.fw_version = 0;
 }
 
@@ -2259,6 +2243,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu)
 	    !smu_baco->platform_support)
 		return false;
 
+	/* return true if ASIC is in BACO state already */
+	if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER)
+		return true;
+
 	if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
 	    !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
 		return false;