drm/amdgpu/sdma: fix engine reset handling

Move the kfd suspend/resume code into the caller.  That
is where the KFD is likely to detect a reset so on the KFD
side there is no need to call them.  Also add a mutex to
lock the actual reset sequence.

v2: make the locking per instance

Fixes: bac38ca8c4 ("drm/amdkfd: implement per queue sdma reset for gfx 9.4+")
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher
2025-03-14 19:23:46 -04:00
parent fc70d1ea1b
commit e02fcf7308
4 changed files with 13 additions and 15 deletions

View File

@@ -64,6 +64,7 @@ struct amdgpu_sdma_instance {
struct amdgpu_bo *sdma_fw_obj;
uint64_t sdma_fw_gpu_addr;
uint32_t *sdma_fw_ptr;
struct mutex engine_reset_mutex;
};
enum amdgpu_sdma_ras_memory_id {
@@ -169,7 +170,7 @@ struct amdgpu_buffer_funcs {
};
void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs);
int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id, bool suspend_user_queues);
int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id);
#define amdgpu_emit_copy_buffer(adev, ib, s, d, b, t) (adev)->mman.buffer_funcs->emit_copy_buffer((ib), (s), (d), (b), (t))
#define amdgpu_emit_fill_buffer(adev, ib, s, d, b) (adev)->mman.buffer_funcs->emit_fill_buffer((ib), (s), (d), (b))