[PATCH 4/9] drm/amdgpu: break driver init process when it's bad GPU

[Guchun Chen]

When retrieving bad gpu tag from eeprom, GPU init should
fail as the GPU needs to be retired for further check.

Signed-off-by: Guchun Chen <guchun.chen at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c     | 12 +++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c        | 15 +++++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 11 ++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h |  3 ++-
 4 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2662cd7c8685..882f8a0964a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2059,13 +2059,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	 * it should be called after amdgpu_device_ip_hw_init_phase2  since
 	 * for some ASICs the RAS EEPROM code relies on SMU fully functioning
 	 * for I2C communication which only true at this point.
-	 * recovery_init may fail, but it can free all resources allocated by
-	 * itself and its failure should not stop amdgpu init process.
+	 *
+	 * amdgpu_ras_recovery_init may fail, but the upper only cares the
+	 * failure from bad gpu situation and stop amdgpu init process
+	 * arrordingly. For other failed cases, it will still release all
+	 * the resource and print error message, rather than returning one
+	 * negative value to upper level.
 	 *
 	 * Note: theoretically, this should be called before all vram allocations
 	 * to protect retired page from abusing
 	 */
-	amdgpu_ras_recovery_init(adev);
+	r = amdgpu_ras_recovery_init(adev);
+	if (r)
+		goto init_failed;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_add_device(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 8daeb54917ed..06db2f0b78d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1819,6 +1819,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data **data;
 	uint32_t max_eeprom_records_len = 0;
+	bool bad_gpu = false;
 	int ret;
 
 	if (con)
@@ -1840,9 +1841,12 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
 	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
 
-	ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
-	if (ret)
+	ret = amdgpu_ras_eeprom_init(&con->eeprom_control, &bad_gpu);
+	/* We only fail this calling and halt booting when bad_gpu is true. */
+	if (bad_gpu) {
+		ret = -EINVAL;
 		goto free;
+	}
 
 	if (con->eeprom_control.num_recs) {
 		ret = amdgpu_ras_load_bad_pages(adev);
@@ -1865,6 +1869,13 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 out:
 	dev_warn(adev->dev, "Failed to initialize ras recovery!\n");
 
+	/*
+	 * Except bad_gpu case, other failure cases in this function
+	 * would not fail amdgpu driver init.
+	 */
+	if (!bad_gpu)
+		ret = 0;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 35c0c849d49b..3f1b167afe6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -241,12 +241,14 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 
 }
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *bad_gpu)
 {
 	int ret = 0;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	struct i2c_msg msg = {
 			.addr	= 0,
 			.flags	= I2C_M_RD,
@@ -254,6 +256,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 			.buf	= buff,
 	};
 
+	*bad_gpu = false;
+
 	/* Verify i2c adapter is initialized */
 	if (!adev->pm.smu_i2c.algo)
 		return -ENOENT;
@@ -282,6 +286,11 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->num_recs);
 
+	} else if ((ras->bad_page_cnt_threshold != 0xFFFFFFFF) && (
+			hdr->header == EEPROM_TABLE_HDR_BAD)) {
+		*bad_gpu = true;
+		DRM_ERROR("Detect BAD GPU TAG in eeprom table and "
+			"GPU shall be retired.\n");
 	} else {
 		DRM_INFO("Creating new EEPROM table");
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index b272840cb069..a2de243da31d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -77,7 +77,8 @@ struct eeprom_table_record {
 	unsigned char mcumc_id;
 }__attribute__((__packed__));
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control);
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *bad_gpu);
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control);
 
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
-- 
2.17.1