Merge tag 'amd-drm-next-6.7-2023-11-03' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.7-2023-11-03:

amdgpu:
- Fix RAS support check
- RAS fixes
- MES fixes
- SMU13 fixes
- Contiguous memory allocation fix
- BACO fixes
- GPU reset fixes
- Min power limit fixes
- GFX11 fixes
- USB4/TB hotplug fixes
- ARM regression fix
- GFX9.4.3 fixes
- KASAN/KCSAN stack size check fixes
- SR-IOV fixes
- SMU14 fixes
- PSP13 fixes
- Display blend fixes
- Flexible array size fixes

amdkfd:
- GPUVM fix

radeon:
- Flexible array size fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231103173203.4912-1-alexander.deucher@amd.com

1 files changed, 78 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 4142e2fcd866..3cf4684d0d3f 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -759,6 +759,83 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp)
 	return 0;
 }
 
+
+static void psp_v13_0_boot_error_reporting(struct amdgpu_device *adev,
+					   uint32_t inst,
+					   uint32_t boot_error)
+{
+	uint32_t socket_id;
+	uint32_t aid_id;
+	uint32_t hbm_id;
+	uint32_t reg_data;
+
+	socket_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, SOCKET_ID);
+	aid_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, AID_ID);
+	hbm_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, HBM_ID);
+
+	reg_data = RREG32_SOC15(MP0, inst, regMP0_SMN_C2PMSG_109);
+	dev_info(adev->dev, "socket: %d, aid: %d, firmware boot failed, fw status is 0x%x\n",
+		 socket_id, aid_id, reg_data);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_MEM_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, memory training failed\n",
+			 socket_id, aid_id, hbm_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_FW_LOAD))
+		dev_info(adev->dev, "socket: %d, aid: %d, firmware load failed at boot time\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_WAFL_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, wafl link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_XGMI_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, xgmi link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_CP_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, usr cp link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_DP_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, usr dp link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_MEM_TEST))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm memory test failed\n",
+			 socket_id, aid_id, hbm_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_BIST_TEST))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm bist test failed\n",
+			 socket_id, aid_id, hbm_id);
+}
+
+static int psp_v13_0_query_boot_status(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+	int inst_mask = adev->aid_mask;
+	uint32_t reg_data;
+	uint32_t i;
+	int ret = 0;
+
+	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
+		return 0;
+
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+		return 0;
+
+	for_each_inst(i, inst_mask) {
+		reg_data = RREG32_SOC15(MP0, i, regMP0_SMN_C2PMSG_126);
+		if (!REG_GET_FIELD(reg_data, MP0_SMN_C2PMSG_126, BOOT_STATUS)) {
+			psp_v13_0_boot_error_reporting(adev, i, reg_data);
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static const struct psp_funcs psp_v13_0_funcs = {
 	.init_microcode = psp_v13_0_init_microcode,
 	.wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state,
@@ -781,6 +858,7 @@ static const struct psp_funcs psp_v13_0_funcs = {
 	.update_spirom = psp_v13_0_update_spirom,
 	.vbflash_stat = psp_v13_0_vbflash_status,
 	.fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk,
+	.query_boot_status = psp_v13_0_query_boot_status,
 };
 
 void psp_v13_0_set_psp_funcs(struct psp_context *psp)