From 70b1b9bf80a256286f664e08289aba87b75c6cf9 Mon Sep 17 00:00:00 2001
From: Kent Russell <kent.russell@amd.com>
Date: Tue, 19 Oct 2021 10:05:07 -0400
Subject: drm/amdgpu: Add kernel parameter support for ignoring bad page
threshold
Git-commit: 68daadf3d673568bb7122b1683fd8b0e27c55d9b
Patch-mainline: v5.16-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
When a GPU hits the bad_page_threshold, it will not be initialized by
the amdgpu driver. This means that the table cannot be cleared, nor can
information gathering be performed (getting serial number, BDF, etc).
If the bad_page_threshold kernel parameter is set to -2,
continue to initialize the GPU, while printing a warning to dmesg that
this action has been done
v2: squash in Luben's fix to restore RAS info reporting
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Mukul Joshi <Mukul.Joshi@amd.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 15 +++++++++++----
3 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d58e37fd01f4..b85b67a88a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -205,6 +205,7 @@ extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
extern int amdgpu_bad_page_threshold;
+extern bool amdgpu_ignore_bad_page_threshold;
extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer;
extern int amdgpu_async_gfx_ring;
extern int amdgpu_mcbp;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 85e7854394fd..ad95de6399af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -878,7 +878,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444);
* result in the GPU entering bad status when the number of total
* faulty pages by ECC exceeds the threshold value.
*/
-MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)");
module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 3978152e5ccc..05117eda105b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1105,11 +1105,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
res = amdgpu_ras_eeprom_correct_header_tag(control,
RAS_TABLE_HDR_VAL);
} else {
- *exceed_err_limit = true;
- dev_err(adev->dev,
- "RAS records:%d exceed threshold:%d, "
- "GPU will not be initialized. Replace this GPU or increase the threshold",
+ dev_err(adev->dev, "RAS records:%d exceed threshold:%d",
control->ras_num_recs, ras->bad_page_cnt_threshold);
+ if (amdgpu_bad_page_threshold == -2) {
+ dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2.");
+ res = 0;
+ } else {
+ *exceed_err_limit = true;
+ dev_err(adev->dev,
+ "RAS records:%d exceed threshold:%d, "
+ "GPU will not be initialized. Replace this GPU or increase the threshold",
+ control->ras_num_recs, ras->bad_page_cnt_threshold);
+ }
}
} else {
DRM_INFO("Creating a new EEPROM table");
--
2.38.1