drm/amdgpu: add bad page count threshold in module parameter(v3)

bad_page_threshold could be configured to enable/disable the
associated bad page retirement feature in RAS.

When it's -1, ras will use typical bad page failure value to
handle bad page retirement.

When it's 0, disable bad page retirement, and no bad page
will be recorded and saved.

For other valid value, driver will use this manual value
as the threshold value of totoal bad pages.

v2: correct documentation of this parameter.

v3: remove confused statement in documentation.

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.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 58e3942..e2eed5c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -178,6 +178,7 @@ extern uint amdgpu_dm_abm_level;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
+extern int amdgpu_bad_page_threshold;
 extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 26127c7..dc47549 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -156,6 +156,7 @@ struct amdgpu_mgpu_info mgpu_info = {
 };
 int amdgpu_ras_enable = -1;
 uint amdgpu_ras_mask = 0xffffffff;
+int amdgpu_bad_page_threshold = -1;
 
 /**
  * DOC: vramlimit (int)
@@ -765,6 +766,16 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
 MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)");
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
+/**
+ * DOC: bad_page_threshold (int)
+ * Bad page threshold is to specify the threshold value of faulty pages
+ * detected by RAS ECC, that may result in GPU entering bad status if total
+ * faulty pages by ECC exceed threshold value and leave it for user's further
+ * check.
+ */
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
        {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},