[PATCH 2/3] drm/amdgpu: Add kernel parameter support for ignoring bad page threshold

[Kent Russell]

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).
Add an override by using amdgpu_bad_page_threshold = -2 which will still
initialize the GPU, even when the bad page threshold has been reached.

Cc: Luben Tuikov <luben.tuikov at amd.com>
Cc: Mukul Joshi <Mukul.Joshi at amd.com>
Signed-off-by: Kent Russell <kent.russell at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

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 96bd63aeeddd..eee3cf874e7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -877,7 +877,7 @@ 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+)");
-- 
2.25.1