On 11/17/26 12:39, Mu, Zihao wrote:
> From: Thadeu Lima de Souza Cascardo <[email protected]>
>
> Keep the original identifier in the update context so replacement jobs
> and phases restarted around allocation use the same tracing identity.
>
> Initialize the ID for range, PDE and table-clear contexts. Use it in
> SDMA's initial and rollover allocations, and remove prepare's separate
> job-ID argument from both backends and the callback type.
>
> [zmu: Complete the SDMA prepare/alloc_job/rollover changes omitted from
> the inline proposal, and adapt to the current context layout.]
> Link:
> https://lore.kernel.org/amd-gfx/[email protected]/
> Signed-off-by: Thadeu Lima de Souza Cascardo <[email protected]>
> Signed-off-by: Zihao Mu <[email protected]>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 8 ++++----
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c | 4 +---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h | 7 ++++++-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 12 +++++-------
> 5 files changed, 18 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 172af3b8f1a..7199cec1f95 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -1055,8 +1055,8 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
> params.vm = vm;
> params.immediate = immediate;
>
> - r = vm->update_funcs->prepare(¶ms, NULL,
> - AMDGPU_KERNEL_JOB_ID_VM_UPDATE_PDES);
> + params.k_job_id = AMDGPU_KERNEL_JOB_ID_VM_UPDATE_PDES;
Seeting that up should probably be grouped together with setting the other
params fields.
Same for other places, apart from that nit pick looks good to me.
Regards,
Christian.
> + r = vm->update_funcs->prepare(¶ms, NULL);
> if (r)
> goto error;
>
> @@ -1218,8 +1218,8 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev,
> struct amdgpu_vm *vm,
> dma_fence_put(tmp);
> }
>
> - r = vm->update_funcs->prepare(¶ms, sync,
> - AMDGPU_KERNEL_JOB_ID_VM_UPDATE_RANGE);
> + params.k_job_id = AMDGPU_KERNEL_JOB_ID_VM_UPDATE_RANGE;
> + r = vm->update_funcs->prepare(¶ms, sync);
> if (r)
> goto error_free;
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
> index 8c7afd34783..7521c5be207 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
> @@ -43,14 +43,12 @@ static int amdgpu_vm_cpu_map_table(struct amdgpu_bo_vm
> *table)
> *
> * @p: see amdgpu_vm_update_params definition
> * @sync: sync obj with fences to wait on
> - * @k_job_id: the id for tracing/debug purposes
> *
> * Returns:
> * Negativ errno, 0 for success.
> */
> static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p,
> - struct amdgpu_sync *sync,
> - u64 k_job_id)
> + struct amdgpu_sync *sync)
> {
> if (!sync)
> return 0;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h
> index 0b7cc3a1701..ea52be053d8 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_internal.h
> @@ -77,6 +77,11 @@ struct amdgpu_vm_update_params {
> */
> struct amdgpu_job *job;
>
> + /**
> + * @k_job_id: original job identifier for every submission in this
> context
> + */
> + u64 k_job_id;
> +
> /**
> * @num_dw_left: number of dw left for the IB
> */
> @@ -107,7 +112,7 @@ struct amdgpu_vm_update_params {
> struct amdgpu_vm_update_funcs {
> int (*map_table)(struct amdgpu_bo_vm *bo);
> int (*prepare)(struct amdgpu_vm_update_params *p,
> - struct amdgpu_sync *sync, u64 k_job_id);
> + struct amdgpu_sync *sync);
> int (*update)(struct amdgpu_vm_update_params *p,
> struct amdgpu_bo_vm *bo, uint64_t pe, uint64_t addr,
> unsigned count, uint32_t incr, uint64_t flags);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> index f205adfd59e..0ff2d06bf53 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> @@ -399,8 +399,8 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct
> amdgpu_vm *vm,
> params.vm = vm;
> params.immediate = immediate;
>
> - r = vm->update_funcs->prepare(¶ms, NULL,
> - AMDGPU_KERNEL_JOB_ID_VM_PT_CLEAR);
> + params.k_job_id = AMDGPU_KERNEL_JOB_ID_VM_PT_CLEAR;
> + r = vm->update_funcs->prepare(¶ms, NULL);
> if (r)
> goto exit;
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> index e7180a6661a..38ca2d78b38 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
> @@ -41,7 +41,7 @@ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm
> *table)
>
> /* Allocate a new job for @count PTE updates */
> static int amdgpu_vm_sdma_alloc_job(struct amdgpu_vm_update_params *p,
> - unsigned int count, u64 k_job_id)
> + unsigned int count)
> {
> enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE
> : AMDGPU_IB_POOL_DELAYED;
> @@ -57,7 +57,7 @@ static int amdgpu_vm_sdma_alloc_job(struct
> amdgpu_vm_update_params *p,
> ndw = min(ndw, AMDGPU_VM_SDMA_MAX_NUM_DW);
>
> r = amdgpu_job_alloc_with_ib(p->adev, entity, AMDGPU_FENCE_OWNER_VM,
> - ndw * 4, pool, k_job_id, &p->job);
> + ndw * 4, pool, p->k_job_id, &p->job);
> if (r)
> return r;
>
> @@ -70,17 +70,16 @@ static int amdgpu_vm_sdma_alloc_job(struct
> amdgpu_vm_update_params *p,
> *
> * @p: see amdgpu_vm_update_params definition
> * @sync: amdgpu_sync object with fences to wait for
> - * @k_job_id: identifier of the job, for tracing purpose
> *
> * Returns:
> * Negativ errno, 0 for success.
> */
> static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
> - struct amdgpu_sync *sync, u64 k_job_id)
> + struct amdgpu_sync *sync)
> {
> int r;
>
> - r = amdgpu_vm_sdma_alloc_job(p, 0, k_job_id);
> + r = amdgpu_vm_sdma_alloc_job(p, 0);
> if (r)
> return r;
>
> @@ -256,8 +255,7 @@ static int amdgpu_vm_sdma_update(struct
> amdgpu_vm_update_params *p,
> if (ndw < 32) {
> amdgpu_vm_sdma_commit(p, NULL);
>
> - r = amdgpu_vm_sdma_alloc_job(p, count,
> -
> AMDGPU_KERNEL_JOB_ID_VM_UPDATE);
> + r = amdgpu_vm_sdma_alloc_job(p, count);
> if (r)
> return r;
>