From: Guchun Chen <guchun.chen@amd.com>
Date: Thu, 23 Jul 2020 08:05:00 +0000 (+0800)
Subject: drm/amdgpu: schedule ras recovery when reaching bad page threshold(v2)
X-Git-Tag: v5.10.7~1332^2~30^2~267
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=9c06f91ff2349da67651cddf88507aa967b58b08;p=platform%2Fkernel%2Flinux-rpi.git

drm/amdgpu: schedule ras recovery when reaching bad page threshold(v2)

Once the bad page saved to eeprom reaches the configured
threshold, ras recovery will be issued to notify user.

v2: Fix spelling typo.

Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index da8b35a..461dfd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -394,8 +394,10 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 	int i, ret = 0;
 	struct i2c_msg *msgs, *msg;
 	unsigned char *buffs, *buff;
+	bool sched_ras_recovery = false;
 	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	if (adev->asic_type != CHIP_VEGA20 && adev->asic_type != CHIP_ARCTURUS)
 		return 0;
@@ -413,11 +415,30 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		goto free_buff;
 	}
 
+	/*
+	 * If saved bad pages number exceeds the bad page threshold for
+	 * the whole VRAM, update table header to mark the BAD GPU tag
+	 * and schedule one ras recovery after eeprom write is done,
+	 * this can avoid the missing for latest records.
+	 *
+	 * This new header will be picked up and checked in the bootup
+	 * by ras recovery, which may break bootup process to notify
+	 * user this GPU is in bad state and to retire such GPU for
+	 * further check.
+	 */
+	if (write && (amdgpu_bad_page_threshold != 0) &&
+		((control->num_recs + num) >= ras->bad_page_cnt_threshold)) {
+		dev_warn(adev->dev,
+			"Saved bad pages(%d) reaches threshold value(%d).\n",
+			control->num_recs + num, ras->bad_page_cnt_threshold);
+		control->tbl_hdr.header = EEPROM_TABLE_HDR_BAD;
+		sched_ras_recovery = true;
+	}
+
 	/* In case of overflow just start from beginning to not lose newest records */
 	if (write && (control->next_addr + EEPROM_TABLE_RECORD_SIZE * num > EEPROM_SIZE_BYTES))
 		control->next_addr = EEPROM_RECORD_START;
 
-
 	/*
 	 * TODO Currently makes EEPROM writes for each record, this creates
 	 * internal fragmentation. Optimized the code to do full page write of
@@ -493,6 +514,20 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		__update_tbl_checksum(control, records, num, old_hdr_byte_sum);
 
 		__update_table_header(control, buffs);
+
+		if (sched_ras_recovery) {
+			/*
+			 * Before scheduling ras recovery, assert the related
+			 * flag first, which shall bypass common bad page
+			 * reservation execution in amdgpu_ras_reset_gpu.
+			 */
+			amdgpu_ras_get_context(adev)->flags |=
+				AMDGPU_RAS_FLAG_SKIP_BAD_PAGE_RESV;
+
+			dev_warn(adev->dev, "Conduct ras recovery due to bad "
+				"page threshold reached.\n");
+			amdgpu_ras_reset_gpu(adev);
+		}
 	} else if (!__validate_tbl_checksum(control, records, num)) {
 		DRM_WARN("EEPROM Table checksum mismatch!");
 		/* TODO Uncomment when EEPROM read/write is relliable */