From 0d2cde1cdd49551004ef7107064f3871acafb5a1 Mon Sep 17 00:00:00 2001
From: Luben Tuikov <luben.tuikov@amd.com>
Date: Thu, 29 Apr 2021 20:15:42 -0400
Subject: drm/amdgpu: Fix koops when accessing RAS EEPROM
Git-commit: 1d9d2ca85b32605ac9c74c8fa42d0c1cfbe019d4
Patch-mainline: v5.15-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
Debugfs RAS EEPROM files are available when
the ASIC supports RAS, and when the debugfs is
enabled, an also when "ras_enable" module
parameter is set to 0. However in this case,
we get a kernel oops when accessing some of
the "ras_..." controls in debugfs. The reason
for this is that struct amdgpu_ras::adev is
unset. This commit sets it, thus enabling access
to those facilities. Note that this facilitates
EEPROM access and not necessarily RAS features or
functionality.
Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1960,11 +1960,20 @@
bool exc_err_limit = false;
int ret;
- if (adev->ras_enabled && con)
- data = &con->eh_data;
- else
+ if (!con)
return 0;
+ /* Allow access to RAS EEPROM via debugfs, when the ASIC
+ * supports RAS and debugfs is enabled, but when
+ * adev->ras_enabled is unset, i.e. when "ras_enable"
+ * module parameter is set to 0.
+ */
+ con->adev = adev;
+
+ if (!adev->ras_enabled)
+ return 0;
+
+ data = &con->eh_data;
*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
if (!*data) {
ret = -ENOMEM;
@@ -1974,7 +1983,6 @@
mutex_init(&con->recovery_lock);
INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
atomic_set(&con->in_recovery, 0);
- con->adev = adev;
max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count();
amdgpu_ras_validate_threshold(adev, max_eeprom_records_count);