bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-25 10:02:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: fix the issue of reserving bad pages failed

Browse Source 
In amdgpu_ras_reset_gpu, because bad pages may not be freed,
it has high probability to reserve bad pages failed.

Change to reserve bad pages when freeing VRAM.

v2:
1. avoid allocating the drm_mm node outside of amdgpu_vram_mgr.c
2. move bad page reserving into amdgpu_ras_add_bad_pages, if vram mgr
   reserve bad page failed, it will put it into pending list, otherwise
   put it into processed list;
3. remove amdgpu_ras_release_bad_pages, because retired page's info has
   been moved into amdgpu_vram_mgr

v3:
1. formate code style;
2. rename amdgpu_vram_reserve_scope as amdgpu_vram_reservation;
3. rename scope_pending as reservations_pending;
4. rename scope_processed as reserved_pages;
5. change to iterate over all the pending ones and try to insert them
   with drm_mm_reserve_node();

v4:
1. rename amdgpu_vram_mgr_reserve_scope as
amdgpu_vram_mgr_reserve_range;
2. remove unused include "amdgpu_ras.h";
3. rename amdgpu_vram_mgr_check_and_reserve as
amdgpu_vram_mgr_do_reserve;
4. refine amdgpu_vram_mgr_reserve_range to call
amdgpu_vram_mgr_do_reserve.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Signed-off-by: Wenhui Sheng <Wenhui.Sheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Dennis Li
2020-10-22 17:44:55 +08:00
committed by Alex Deucher
parent 5eeb45934c
commit 676deb3877
4 changed files with 156 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
View File

@@ -362,14 +362,10 @@ struct ras_err_data {
struct ras_err_handler_data {
/* point to bad page records array */
struct eeprom_table_record *bps;
/* point to reserved bo array */
struct amdgpu_bo **bps_bo;
/* the count of entries */
int count;
/* the space can place new entries */
int space_left;
/* last reserved entry's index + 1 */
int last_reserved;
};
typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
@@ -506,15 +502,11 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
struct eeprom_table_record *bps, int pages);
int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev);
int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
{
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
if (in_task())
amdgpu_ras_reserve_bad_pages(adev);
if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
schedule_work(&ras->recovery_work);
return 0;