[PATCH 2/3] drm/amd/ras: use the per-ASIC reserved VRAM size for the bad page threshold

The default bad page threshold is derived from the VRAM reserved for
retirement, but ras_eeprom_i2c_config() hardcodes
RAS_RESERVED_VRAM_SIZE_DEFAULT. amdgpu_ras_validate_threshold() instead
derives it from con->reserved_pages_in_bytes, which
amdgpu_ras_init_reserved_vram_size() doubles on MP0 v13.0.14.

That part therefore ends up with a 128 bad page threshold where it
should have 256, and reaches the limit after half as many retirements
as intended.

Reuse the value already computed for con->reserved_pages_in_bytes
rather than deriving it again, so the two cannot drift apart.

Fixes: e383baf88f7d ("drm/amd/ras: Refactor EEPROM parameter config to support multiple ras EEPROMs")
Signed-off-by: Xiang Liu <[email protected]>
---
 .../drm/amd/ras/ras_mgr/amdgpu_ras_eeprom_i2c.c   | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_eeprom_i2c.c b/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_eeprom_i2c.c
index d2c9fc525af5..a56d3116c5fd 100644
--- a/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_eeprom_i2c.c
+++ b/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_eeprom_i2c.c
@@ -77,6 +77,19 @@
 #define BAD_PAGE_NUM_PER_EEPROM_RECORD_V13  16
 #define BAD_PAGE_NUM_PER_EEPROM_RECORD_V15  128
 
+static u64 ras_eeprom_reserved_vram_size(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	/* Set by amdgpu_ras_init_reserved_vram_size(); 0 means that path
+	 * does not cover this ASIC.
+	 */
+	if (con && con->reserved_pages_in_bytes)
+		return con->reserved_pages_in_bytes;
+
+	return RAS_RESERVED_VRAM_SIZE_DEFAULT;
+}
+
 static int ras_eeprom_i2c_config(struct ras_core_context *ras_core,
 		struct ras_eeprom_param_config *cfg)
 {
@@ -168,7 +181,7 @@ static int ras_eeprom_i2c_config(struct ras_core_context *ras_core,
 		badpages = ESTIMATE_BAD_PAGE_THRESHOLD(adev->gmc.mc_vram_size);
 	} else if (badpage_threshold == WARN_NONSTOP_OVER_THRESHOLD) {
 		cfg->work_mode_over_thresh = RAS_WORK_MODE_OVER_THRESH_STRICT;
-		badpages = COUNT_BAD_PAGE_THRESHOLD(RAS_RESERVED_VRAM_SIZE_DEFAULT);
+		badpages = COUNT_BAD_PAGE_THRESHOLD(ras_eeprom_reserved_vram_size(adev));
 	} else if (!badpage_threshold) {
 		cfg->work_mode_over_thresh = RAS_WORK_MODE_OVER_THRESH_DEBUG;
 		badpages = 128;
-- 
2.34.1