[v7,17/45] drm/amd: Load GFX10 microcode during early_init

Message ID 20230105170138.717-18-mario.limonciello@amd.com
State New
Headers
Series Recover from failure to probe GPU |

Commit Message

Mario Limonciello Jan. 5, 2023, 5:01 p.m. UTC
  Simplifies the code so that GFX10 will get the firmware
name from `amdgpu_ucode_ip_version_decode` and then use this filename
to load microcode as part of the early_init process.

Any failures will cause the driver to fail to probe before the firmware
framebuffer has been removed.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 84 ++++++--------------------
 1 file changed, 18 insertions(+), 66 deletions(-)
  

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 140bb18ff768..6983acc456b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3968,9 +3968,9 @@  static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 
 static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 {
-	const char *chip_name;
 	char fw_name[40];
-	char *wks = "";
+	char ucode_prefix[30];
+	const char *wks = "";
 	int err;
 	const struct rlc_firmware_header_v2_0 *rlc_hdr;
 	uint16_t version_major;
@@ -3978,71 +3978,31 @@  static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	DRM_DEBUG("\n");
 
-	switch (adev->ip_versions[GC_HWIP][0]) {
-	case IP_VERSION(10, 1, 10):
-		chip_name = "navi10";
-		break;
-	case IP_VERSION(10, 1, 1):
-		chip_name = "navi14";
-		if (!(adev->pdev->device == 0x7340 &&
-		      adev->pdev->revision != 0x00))
-			wks = "_wks";
-		break;
-	case IP_VERSION(10, 1, 2):
-		chip_name = "navi12";
-		break;
-	case IP_VERSION(10, 3, 0):
-		chip_name = "sienna_cichlid";
-		break;
-	case IP_VERSION(10, 3, 2):
-		chip_name = "navy_flounder";
-		break;
-	case IP_VERSION(10, 3, 1):
-		chip_name = "vangogh";
-		break;
-	case IP_VERSION(10, 3, 4):
-		chip_name = "dimgrey_cavefish";
-		break;
-	case IP_VERSION(10, 3, 5):
-		chip_name = "beige_goby";
-		break;
-	case IP_VERSION(10, 3, 3):
-		chip_name = "yellow_carp";
-		break;
-	case IP_VERSION(10, 3, 6):
-		chip_name = "gc_10_3_6";
-		break;
-	case IP_VERSION(10, 1, 3):
-	case IP_VERSION(10, 1, 4):
-		chip_name = "cyan_skillfish2";
-		break;
-	case IP_VERSION(10, 3, 7):
-		chip_name = "gc_10_3_7";
-		break;
-	default:
-		BUG();
-	}
+	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 1) &&
+	   (!(adev->pdev->device == 0x7340 && adev->pdev->revision != 0x00)))
+		wks = "_wks";
+	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", ucode_prefix, wks);
 	err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name);
 	if (err)
 		goto out;
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", ucode_prefix, wks);
 	err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name);
 	if (err)
 		goto out;
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", ucode_prefix, wks);
 	err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name);
 	if (err)
 		goto out;
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE);
 
 	if (!amdgpu_sriov_vf(adev)) {
-		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
 		err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name);
 		/* don't check this.  There are apparently firmwares in the wild with
 		 * incorrect size in the header
@@ -4051,7 +4011,7 @@  static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 		if (err)
 			dev_dbg(adev->dev,
-				"gfx10: amdgpu_ucode_validate() failed \"%s\"\n",
+				"gfx10: amdgpu_ucode_request() failed \"%s\"\n",
 				fw_name);
 		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
@@ -4061,14 +4021,14 @@  static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", ucode_prefix, wks);
 	err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name);
 	if (err)
 		goto out;
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1);
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", ucode_prefix, wks);
 	err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name);
 	if (!err) {
 		amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
@@ -4077,6 +4037,8 @@  static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
+	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
+	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 
 	gfx_v10_0_check_fw_write_wait(adev);
 out:
@@ -4239,19 +4201,11 @@  static void gfx_v10_0_mec_fini(struct amdgpu_device *adev)
 	amdgpu_bo_free_kernel(&adev->gfx.mec.mec_fw_obj, NULL, NULL);
 }
 
-static int gfx_v10_0_me_init(struct amdgpu_device *adev)
+static void gfx_v10_0_me_init(struct amdgpu_device *adev)
 {
-	int r;
-
 	bitmap_zero(adev->gfx.me.queue_bitmap, AMDGPU_MAX_GFX_QUEUES);
 
 	amdgpu_gfx_graphics_queue_acquire(adev);
-
-	r = gfx_v10_0_init_microcode(adev);
-	if (r)
-		DRM_ERROR("Failed to load gfx firmware!\n");
-
-	return r;
 }
 
 static int gfx_v10_0_mec_init(struct amdgpu_device *adev)
@@ -4619,9 +4573,7 @@  static int gfx_v10_0_sw_init(void *handle)
 
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
-	r = gfx_v10_0_me_init(adev);
-	if (r)
-		return r;
+	gfx_v10_0_me_init(adev);
 
 	if (adev->gfx.rlc.funcs) {
 		if (adev->gfx.rlc.funcs->init) {
@@ -7599,7 +7551,7 @@  static int gfx_v10_0_early_init(void *handle)
 	/* init rlcg reg access ctrl */
 	gfx_v10_0_init_rlcg_reg_access_ctrl(adev);
 
-	return 0;
+	return gfx_v10_0_init_microcode(adev);
 }
 
 static int gfx_v10_0_late_init(void *handle)