Re: [PATCH v2 2/4] drm/amdkfd: Add domain parameter to alloc kernel BO

Wed, 03 Dec 2025 09:45:29 -0800 


On 2025-12-01 15:31, Philip Yang wrote:



On 2025-12-01 12:38, Russell, Kent wrote:

[Public]


I know that it makes the change more complicated, but should we be 
renaming the function since we're no longer guaranteeing a GTT memory 
allocation in the alloc_gtt_mem function?

yes, you are right, I have the patch to 
s/alloc_gtt_mem/alloc_kernel_mem/g, s/free_gtt_mem/free_kernel_mem/g, 
and found it is too much changes,



I see amdgpu_amdkfd_alloc_gtt_mem being called in 7 places in KFD. I 
don't think that's too much churn. You need to change all those places 
anyway to add a new parameter, so you might as well change the function 
name while you're there.


Regards,
  Felix



 not related to the purpose of this patch series, so I dropped that 
patch. We can cleanup this in the followup patch, probably remove the 
alloc/free_gtt_mem functions and use amdgpu_bo_create_kernel instead.


Regards,
Philip


  Kent


-----Original Message-----

From: amd-gfx <[email protected]> On Behalf Of 
Philip Yang

Sent: Monday, December 1, 2025 9:29 AM
To: [email protected]
Cc: Kuehling, Felix <[email protected]>; Koenig, Christian

<[email protected]>; Yat Sin, David <[email protected]>; 
Yang,

Philip <[email protected]>

Subject: [PATCH v2 2/4] drm/amdkfd: Add domain parameter to alloc 
kernel BO


To allocate kernel BO from VRAM domain for MQD in the following patch.

No functional change because kernel BO allocate are all from GTT 
domain so far.


amdgpu_amdkfd_alloc_gtt_mem has many duplicate code as
function amdgpu_bo_create_kernel, with one extra flag MQD_GFX9
to bind MQD and control stack in GART with different mtype,
the duplicate code could be removed in future.

Signed-off-by: Philip Yang <[email protected]>
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c             | 6 +++---
  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h             | 2 +-
  drivers/gpu/drm/amd/amdkfd/kfd_debug.c                 | 1 +
  drivers/gpu/drm/amd/amdkfd/kfd_device.c                | 3 ++-
  drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 1 +
  drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c        | 1 +
  drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 2 ++
  7 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index a2879d2b7c8e..9cd1660b8f60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -317,7 +317,7 @@ void amdgpu_amdkfd_gpu_reset(struct amdgpu_device
*adev)
  }


  int amdgpu_amdkfd_alloc_gtt_mem(struct amdgpu_device *adev, size_t 
size,

-                             void **mem_obj, uint64_t *gpu_addr,

+                             u32 domain, void **mem_obj, uint64_t 
*gpu_addr,

                               void **cpu_ptr, bool cp_mqd_gfx9)
  {
       struct amdgpu_bo *bo = NULL;

@@ -328,7 +328,7 @@ int amdgpu_amdkfd_alloc_gtt_mem(struct 
amdgpu_device

*adev, size_t size,
       memset(&bp, 0, sizeof(bp));
       bp.size = size;
       bp.byte_align = PAGE_SIZE;
-     bp.domain = AMDGPU_GEM_DOMAIN_GTT;
+     bp.domain = domain;
       bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
       bp.type = ttm_bo_type_kernel;
       bp.resv = NULL;

@@ -351,7 +351,7 @@ int amdgpu_amdkfd_alloc_gtt_mem(struct 
amdgpu_device

*adev, size_t size,
               goto allocate_mem_reserve_bo_failed;
       }

-     r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+     r = amdgpu_bo_pin(bo, domain);
       if (r) {

               dev_err(adev->dev, "(%d) failed to pin bo for 
amdkfd\n", r);

               goto allocate_mem_pin_bo_failed;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 335d733751cb..14b5ab6fa051 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -237,7 +237,7 @@ int amdgpu_amdkfd_bo_validate_and_fence(struct
amdgpu_bo *bo,
  #endif
  /* Shared API */

  int amdgpu_amdkfd_alloc_gtt_mem(struct amdgpu_device *adev, size_t 
size,

-                             void **mem_obj, uint64_t *gpu_addr,

+                             u32 domain, void **mem_obj, uint64_t 
*gpu_addr,

                               void **cpu_ptr, bool mqd_gfx9);

  void amdgpu_amdkfd_free_gtt_mem(struct amdgpu_device *adev, void 
**mem_obj);

  int amdgpu_amdkfd_alloc_gws(struct amdgpu_device *adev, size_t size,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
index ba9a09b6589a..494a563e072e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -359,6 +359,7 @@ int kfd_dbg_set_mes_debug_mode(struct
kfd_process_device *pdd, bool sq_trap_en)
       if (!pdd->proc_ctx_cpu_ptr) {
               r = amdgpu_amdkfd_alloc_gtt_mem(adev,
                       AMDGPU_MES_PROC_CTX_SIZE,
+                     AMDGPU_GEM_DOMAIN_GTT,
                       &pdd->proc_ctx_bo,
                       &pdd->proc_ctx_gpu_addr,
                       &pdd->proc_ctx_cpu_ptr,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9f183d27a0ef..b0cfad750919 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -787,7 +787,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
       size += 512 * 1024;

       if (amdgpu_amdkfd_alloc_gtt_mem(
-                     kfd->adev, size, &kfd->gtt_mem,
+                     kfd->adev, size, AMDGPU_GEM_DOMAIN_GTT,
+                     &kfd->gtt_mem,

                       &kfd->gtt_start_gpu_addr, 
&kfd->gtt_start_cpu_ptr,

                       false)) {

               dev_err(kfd_device, "Could not allocate %d bytes\n", 
size);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 36ac35d64126..028fca1d2755 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2906,6 +2906,7 @@ static int allocate_hiq_sdma_mqd(struct
device_queue_manager *dqm)
               NUM_XCC(dqm->dev->xcc_mask));

       retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, size,
+             AMDGPU_GEM_DOMAIN_GTT,
               &(mem_obj->gtt_mem), &(mem_obj->gpu_addr),
               (void *)&(mem_obj->cpu_ptr), false);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 2e9b6bcf2704..a489d43d5f64 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c

@@ -139,6 +139,7 @@ static struct kfd_mem_obj *allocate_mqd(struct 
kfd_node

*node,
                       (ALIGN(q->ctl_stack_size, PAGE_SIZE) +
                       ALIGN(sizeof(struct v9_mqd), PAGE_SIZE)) *
                       NUM_XCC(node->xcc_mask),
+                     AMDGPU_GEM_DOMAIN_GTT,
                       &(mqd_mem_obj->gtt_mem),
                       &(mqd_mem_obj->gpu_addr),
                       (void *)&(mqd_mem_obj->cpu_ptr), true);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 5f8cda4733f9..e0c5ec7e2fe9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c

@@ -266,6 +266,7 @@ static int init_user_queue(struct 
process_queue_manager

*pqm,
       if (dev->kfd->shared_resources.enable_mes) {
               retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev,
AMDGPU_MES_GANG_CTX_SIZE,
+ AMDGPU_GEM_DOMAIN_GTT,
&(*q)->gang_ctx_bo,
&(*q)->gang_ctx_gpu_addr,
&(*q)->gang_ctx_cpu_ptr,
@@ -369,6 +370,7 @@ int pqm_create_queue(struct process_queue_manager
*pqm,

       if (!pdd->proc_ctx_cpu_ptr && 
dev->kfd->shared_resources.enable_mes) {

               retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev,
AMDGPU_MES_PROC_CTX_SIZE,
+ AMDGPU_GEM_DOMAIN_GTT,
&pdd->proc_ctx_bo,
&pdd->proc_ctx_gpu_addr,
&pdd->proc_ctx_cpu_ptr,
--
2.50.1
























					Reply via email to