summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
diff options
context:
space:
mode:
authorDave Airlie <airlied@redhat.com>2022-02-14 10:31:51 +1000
committerDave Airlie <airlied@redhat.com>2022-02-14 10:31:51 +1000
commit123db17ddff007080d464e785689fb14f94cbc7a (patch)
tree11da22fd6a508e496be838e43e0b504266c4a4d3 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
parente7a09cea6483b44ea0c82f07145fcbd8a918bf96 (diff)
parent7f161df1a513e2961f4e3c96a8355c8ce93ad175 (diff)
downloadlinux-123db17ddff007080d464e785689fb14f94cbc7a.tar.bz2
Merge tag 'amd-drm-next-5.18-2022-02-11-1' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.18-2022-02-11-1: amdgpu: - Clean up of power management code - Enable freesync video mode by default - Clean up of RAS code - Improve VRAM access for debug using SDMA - Coding style cleanups - SR-IOV fixes - More display FP reorg - TLB flush fixes for Arcuturus, Vega20 - Misc display fixes - Rework special register access methods for SR-IOV - DP2 fixes - DP tunneling fixes - DSC fixes - More IP discovery cleanups - Misc RAS fixes - Enable both SMU i2c buses where applicable - s2idle improvements - DPCS header cleanup - Add new CAP firmware support for SR-IOV amdkfd: - Misc cleanups - SVM fixes - CRIU support - Clean up MQD manager UAPI: - Add interface to amdgpu CTX ioctl to request a stable power state for profiling https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/207 - Add amdkfd support for CRIU https://github.com/checkpoint-restore/criu/pull/1709 - Remove old unused amdkfd debugger interface Was only implemented for Kaveri and was only ever used by an old HSA tool that was never open sourced radeon: - Fix error handling in radeon_driver_open_kms - UVD suspend fix - Misc fixes From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220211220706.5803-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h61
1 files changed, 37 insertions, 24 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 1c708122d492..a55743b12d57 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -26,11 +26,11 @@
#include <linux/debugfs.h>
#include <linux/list.h>
-#include "amdgpu.h"
-#include "amdgpu_psp.h"
#include "ta_ras_if.h"
#include "amdgpu_ras_eeprom.h"
+struct amdgpu_iv_entry;
+
#define AMDGPU_RAS_FLAG_INIT_BY_VBIOS (0x1 << 0)
enum amdgpu_ras_block {
@@ -484,6 +484,31 @@ struct ras_debug_if {
};
int op;
};
+
+struct amdgpu_ras_block_object {
+ /* block name */
+ char name[32];
+
+ enum amdgpu_ras_block block;
+
+ uint32_t sub_block_index;
+
+ int (*ras_block_match)(struct amdgpu_ras_block_object *block_obj,
+ enum amdgpu_ras_block block, uint32_t sub_block_index);
+ int (*ras_late_init)(struct amdgpu_device *adev, void *ras_info);
+ void (*ras_fini)(struct amdgpu_device *adev);
+ const struct amdgpu_ras_block_hw_ops *hw_ops;
+};
+
+struct amdgpu_ras_block_hw_ops {
+ int (*ras_error_inject)(struct amdgpu_device *adev, void *inject_if);
+ void (*query_ras_error_count)(struct amdgpu_device *adev, void *ras_error_status);
+ void (*query_ras_error_status)(struct amdgpu_device *adev);
+ void (*query_ras_error_address)(struct amdgpu_device *adev, void *ras_error_status);
+ void (*reset_ras_error_count)(struct amdgpu_device *adev);
+ void (*reset_ras_error_status)(struct amdgpu_device *adev);
+};
+
/* work flow
* vbios
* 1: ras feature enable (enabled by default)
@@ -498,19 +523,6 @@ struct ras_debug_if {
* 8: feature disable
*/
-#define amdgpu_ras_get_context(adev) ((adev)->psp.ras_context.ras)
-#define amdgpu_ras_set_context(adev, ras_con) ((adev)->psp.ras_context.ras = (ras_con))
-
-/* check if ras is supported on block, say, sdma, gfx */
-static inline int amdgpu_ras_is_supported(struct amdgpu_device *adev,
- unsigned int block)
-{
- struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
-
- if (block >= AMDGPU_RAS_BLOCK_COUNT)
- return 0;
- return ras && (adev->ras_enabled & (1 << block));
-}
int amdgpu_ras_recovery_init(struct amdgpu_device *adev);
@@ -527,15 +539,6 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
int amdgpu_ras_save_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 (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
- schedule_work(&ras->recovery_work);
- return 0;
-}
-
static inline enum ta_ras_block
amdgpu_ras_block_to_ta(enum amdgpu_ras_block block) {
switch (block) {
@@ -667,4 +670,14 @@ const char *get_ras_block_str(struct ras_common_if *ras_block);
bool amdgpu_ras_is_poison_mode_supported(struct amdgpu_device *adev);
+int amdgpu_ras_is_supported(struct amdgpu_device *adev, unsigned int block);
+
+int amdgpu_ras_reset_gpu(struct amdgpu_device *adev);
+
+struct amdgpu_ras* amdgpu_ras_get_context(struct amdgpu_device *adev);
+
+int amdgpu_ras_set_context(struct amdgpu_device *adev, struct amdgpu_ras *ras_con);
+
+int amdgpu_ras_register_ras_block(struct amdgpu_device *adev,
+ struct amdgpu_ras_block_object *ras_block_obj);
#endif