[PATCH 7/9] drm/amdgpu: break GPU recovery once it's bad

[Guchun Chen]

When GPU executes recovery and retriving bad GPU tag
from external eerpom device, the recovery will be stopped
and print GPU retirement message for user's awareness.

Signed-off-by: Guchun Chen <guchun.chen at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 17 ++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c       | 13 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h       |  2 +
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c    | 43 +++++++++++++++++++
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h    |  3 ++
 5 files changed, 75 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 882f8a0964a5..771c4e6b7a0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4139,8 +4139,20 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 
 				amdgpu_fbdev_set_suspend(tmp_adev, 0);
 
-				/* must succeed. */
-				amdgpu_ras_resume(tmp_adev);
+				/*
+				 * The CPU is BAD once faulty pages by ECC has
+				 * reached the threshold, and ras recovery is
+				 * scheduled. So add one check here to break
+				 * recovery if it's one BAD GPU, and remind
+				 * user to retire this GPU.
+				 */
+				if (!amdgpu_ras_check_bad_gpu(tmp_adev)) {
+					/* must succeed. */
+					amdgpu_ras_resume(tmp_adev);
+				} else {
+					r = -EINVAL;
+					goto out;
+				}
 
 				/* Update PSP FW topology after reset */
 				if (hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1)
@@ -4148,7 +4160,6 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 			}
 		}
 
-
 out:
 		if (!r) {
 			amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 4c86c7a64bcc..acb8231f2052 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2200,3 +2200,16 @@ bool amdgpu_ras_need_emergency_restart(struct amdgpu_device *adev)
 
 	return false;
 }
+
+bool amdgpu_ras_check_bad_gpu(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	bool bad_gpu = false;
+
+	if (con && (con->bad_page_cnt_threshold != 0xFFFFFFFF))
+		amdgpu_ras_eeprom_check_bad_gpu(&con->eeprom_control,
+						&bad_gpu);
+
+	/* We are only interested in variable bad_gpu. */
+	return bad_gpu;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index cf9f60202334..95918d355fa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -497,6 +497,8 @@ void amdgpu_ras_suspend(struct amdgpu_device *adev);
 unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 		bool is_ce);
 
+bool amdgpu_ras_check_bad_gpu(struct amdgpu_device *adev);
+
 /* error handling functions */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 		struct eeprom_table_record *bps, int pages);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 0cd594c74bff..d27cd5ae431a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -387,6 +387,49 @@ static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
 	return curr_address;
 }
 
+int amdgpu_ras_eeprom_check_bad_gpu(struct amdgpu_ras_eeprom_control *control,
+				bool *bad_gpu)
+{
+	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 i2c_msg msg = {
+			.addr = control->i2c_address,
+			.flags = I2C_M_RD,
+			.len = EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
+			.buf = buff,
+	};
+	int ret;
+
+	*bad_gpu = false;
+
+	/* read EEPROM table header */
+	mutex_lock(&control->tbl_mutex);
+	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	if (ret < 1) {
+		dev_err(adev->dev, "Failed to read EEPROM table header.\n");
+		goto err;
+	}
+
+	__decode_table_header_from_buff(hdr, &buff[2]);
+
+	if (hdr->header == EEPROM_TABLE_HDR_BAD) {
+		dev_warn(adev->dev, "Current GPU is BAD and should be retired.\n");
+		*bad_gpu = true;
+	}
+	__decode_table_header_from_buff(hdr, &buff[2]);
+
+	if (hdr->header == EEPROM_TABLE_HDR_BAD) {
+		dev_warn(adev->dev, "Current GPU is BAD and should be retired.\n");
+		*bad_gpu = true;
+	}
+
+err:
+	mutex_unlock(&control->tbl_mutex);
+	return 0;
+}
+
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index a2de243da31d..82757c88db9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -81,6 +81,9 @@ 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_check_bad_gpu(struct amdgpu_ras_eeprom_control *control,
+				bool *bad_gpu);
+
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
-- 
2.17.1