diff mbox series

[v3,10/11] drm/amd: Request GFX11 microcode during IP discovery

Message ID 20221230052119.15096-11-mario.limonciello@amd.com (mailing list archive)
State New, archived
Headers show
Series Recover from failure to probe GPU | expand

Commit Message

Mario Limonciello Dec. 30, 2022, 5:21 a.m. UTC 
If GFX11 microcode is required but not available during early init, the
firmware framebuffer will have already been released and the screen will
freeze.

Move the request for GFX11 microcode into the IP discovery phase
so that if it's not available, IP discovery will fail.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 52 +++++++++++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c        | 64 +------------------
 2 files changed, 53 insertions(+), 63 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 439b10fdff1b..ce1aa7683738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -316,6 +316,29 @@  MODULE_FIRMWARE("amdgpu/gc_10_3_7_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_10_3_7_mec2.bin");
 MODULE_FIRMWARE("amdgpu/gc_10_3_7_rlc.bin");
 
+/* gfx11 */
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_1_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_1_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_1_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_2_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_2_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_2_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_2_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_rlc.bin");
+
 static const char *hw_id_names[HW_ID_MAX] = {
 	[MP1_HWID]		= "MP1",
 	[MP2_HWID]		= "MP2",
@@ -2114,6 +2137,32 @@  static int amdgpu_discovery_load_gfx10(struct amdgpu_device *adev, char *ucode_p
 	r = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 	if (r)
 		return r;
+	return 0;
+}
+
+static int amdgpu_discovery_load_gfx11(struct amdgpu_device *adev, char *ucode_prefix)
+{
+	char fw_name[40];
+	int r;
+
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", ucode_prefix);
+	r = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
+	if (r)
+		return r;
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", ucode_prefix);
+	r = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
+	if (r)
+		return r;
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix);
+	r = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
+	if (r)
+		return r;
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) {
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_toc.bin", ucode_prefix);
+		r = request_firmware(&adev->psp.toc_fw, fw_name, adev->dev);
+		if (r)
+			return r;
+	}
 
 	return 0;
 }
@@ -2162,6 +2211,9 @@  static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
+		r = amdgpu_discovery_load_gfx11(adev, ucode_prefix);
+		if (r)
+			return r;
 		amdgpu_device_ip_block_add(adev, &gfx_v11_0_ip_block);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index a56c6e106d00..576fa591c6da 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -60,27 +60,6 @@ 
 #define regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1	0x4e7e
 #define regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1_BASE_IDX	1
 
-MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_1_me.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_1_mec.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_1_rlc.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_2_pfp.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_2_me.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_2_mec.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_2_rlc.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_3_pfp.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_3_me.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_3_mec.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_3_rlc.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_4_pfp.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_4_me.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_4_mec.bin");
-MODULE_FIRMWARE("amdgpu/gc_11_0_4_rlc.bin");
 
 static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 {
@@ -445,8 +424,6 @@  static void gfx_v11_0_free_microcode(struct amdgpu_device *adev)
 
 static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 {
-	char fw_name[40];
-	char ucode_prefix[30];
 	int err;
 	const struct rlc_firmware_header_v2_0 *rlc_hdr;
 	uint16_t version_major;
@@ -454,12 +431,6 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 
 	DRM_DEBUG("\n");
 
-	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
-
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", ucode_prefix);
-	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.pfp_fw);
 	if (err)
 		goto out;
@@ -476,10 +447,6 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 		amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP);
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", ucode_prefix);
-	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.me_fw);
 	if (err)
 		goto out;
@@ -492,10 +459,6 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 	}
 
 	if (!amdgpu_sriov_vf(adev)) {
-		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
-		err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
-		if (err)
-			goto out;
 		err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
 		if (err)
 			goto out;
@@ -507,10 +470,6 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix);
-	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.mec_fw);
 	if (err)
 		goto out;
@@ -530,9 +489,7 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 
 out:
 	if (err) {
-		dev_err(adev->dev,
-			"gfx11: Failed to init firmware \"%s\"\n",
-			fw_name);
+		dev_err(adev->dev, "gfx11: Failed to init firmware\n");
 		release_firmware(adev->gfx.pfp_fw);
 		adev->gfx.pfp_fw = NULL;
 		release_firmware(adev->gfx.me_fw);
@@ -549,20 +506,6 @@  static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 static int gfx_v11_0_init_toc_microcode(struct amdgpu_device *adev)
 {
 	const struct psp_firmware_header_v1_0 *toc_hdr;
-	int err = 0;
-	char fw_name[40];
-	char ucode_prefix[30];
-
-	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
-
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_toc.bin", ucode_prefix);
-	err = request_firmware(&adev->psp.toc_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
-
-	err = amdgpu_ucode_validate(adev->psp.toc_fw);
-	if (err)
-		goto out;
 
 	toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data;
 	adev->psp.toc.fw_version = le32_to_cpu(toc_hdr->header.ucode_version);
@@ -571,11 +514,6 @@  static int gfx_v11_0_init_toc_microcode(struct amdgpu_device *adev)
 	adev->psp.toc.start_addr = (uint8_t *)toc_hdr +
 				le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes);
 	return 0;
-out:
-	dev_err(adev->dev, "Failed to load TOC microcode\n");
-	release_firmware(adev->psp.toc_fw);
-	adev->psp.toc_fw = NULL;
-	return err;
 }
 
 static u32 gfx_v11_0_get_csb_size(struct amdgpu_device *adev)