[PATCH 4/4] drm/amdkfd: Optimize out sdma doorbell array in kgd2kfd_shared_resources
We can directly calculate sdma doorbell indexes in the process doorbell
pages through the doorbell_index structure in amdgpu_device, so no need
to cache them in kgd2kfd_shared_resources any more. This alleviates the
adaptation needs when new SDMA configurations are introduced.
Change-Id: Ic657799856ed0256f36b01e502ef0cab263b1f49
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 41 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 16 +---
.../gpu/drm/amd/include/kgd_kfd_interface.h | 4 +-
3 files changed, 23 insertions(+), 38 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 30e2b371578e..fe1d7368c1e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -131,7 +131,7 @@ static void amdgpu_doorbell_get_kfd_info(struct
amdgpu_device *adev,
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
- int i, n;
+ int i;
int last_valid_bit;
if (adev->kfd.dev) {
@@ -142,7 +142,9 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
.gpuvm_size = min(adev->vm_manager.max_pfn
<< AMDGPU_GPU_PAGE_SHIFT,
AMDGPU_GMC_HOLE_START),
- .drm_render_minor = adev->ddev->render->index
+ .drm_render_minor = adev->ddev->render->index,
+ .sdma_doorbell_idx = adev->doorbell_index.sdma_engine,
+
};
/* this is going to have a few of the MSBs set that we need to
@@ -172,31 +174,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
_resources.doorbell_aperture_size,
_resources.doorbell_start_offset);
- if (adev->asic_type < CHIP_VEGA10) {
- kgd2kfd_device_init(adev->kfd.dev, _resources);
- return;
- }
-
- n = (adev->asic_type < CHIP_VEGA20) ? 2 : 8;
-
- for (i = 0; i < n; i += 2) {
- /* On SOC15 the BIF is involved in routing
-* doorbells using the low 12 bits of the
-* address. Communicate the assignments to
-* KFD. KFD uses two doorbell pages per
-* process in case of 64-bit doorbells so we
-* can use each doorbell assignment twice.
-*/
- gpu_resources.sdma_doorbell[0][i] =
- adev->doorbell_index.sdma_engine[0] + (i >> 1);
- gpu_resources.sdma_doorbell[0][i+1] =
- adev->doorbell_index.sdma_engine[0] + 0x200 +
(i >> 1);
- gpu_resources.sdma_doorbell[1][i] =
- adev->doorbell_index.sdma_engine[1] + (i >> 1);
- gpu_resources.sdma_doorbell[1][i+1] =
- adev->doorbell_index.sdma_engine[1] + 0x200 +
(i >> 1);
- }
-
/* Since SOC15, BIF starts to statically use the
* lower 12 bits of doorbell addresses for routing
* based on settings in registers like
@@ -205,10 +182,12 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
* 12 bits of its address has to be outside the range
* set for SDMA, VCN, and IH blocks.
*/
- gpu_resources.non_cp_doorbells_start =
- adev->doorbell_index.first_non_cp;
- gpu_resources.non_cp_doorbells_end =
- adev->doorbell_index.last_non_cp;
+ if (adev->asic_type >= CHIP_VEGA10) {
+ gpu_resources.non_cp_doorbells_start =
+ adev->doorbell_index.first_non_cp;
+ gpu_resources.non_cp_doorbells_end =
+ adev->doorbell_index.last_non_cp;
+ }
kgd2kfd_device_init(adev->kfd.dev, _resources);
}
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 8372556b52eb..c6c9530e704e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -134,12 +134,18 @@ static int allocate_doorbell(struct qcm_process_device
*qpd, struct queue *q)
*/
q->doorbell_id = q->properties.queue_id;
} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
- /* For SDMA queues on SOC15, use static doorbell
-* assignments based on the engine and queue.
+ /* For SDMA queues on SOC15 with
[PATCH 4/4] drm/amdkfd: Optimize out sdma doorbell array in kgd2kfd_shared_resources
We can directly calculate sdma doorbell indexes in the process doorbell
pages through the doorbell_index structure in amdgpu_device, so no need
to cache them in kgd2kfd_shared_resources any more. This alleviates the
adaptation needs when new SDMA configurations are introduced.
Change-Id: Ic657799856ed0256f36b01e502ef0cab263b1f49
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 41 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 16 +---
.../gpu/drm/amd/include/kgd_kfd_interface.h | 4 +-
3 files changed, 23 insertions(+), 38 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index a8a166fff1e3..88f6f0ae38a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -131,7 +131,7 @@ static void amdgpu_doorbell_get_kfd_info(struct
amdgpu_device *adev,
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
- int i, n;
+ int i;
int last_valid_bit;
if (adev->kfd.dev) {
@@ -142,7 +142,9 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
.gpuvm_size = min(adev->vm_manager.max_pfn
<< AMDGPU_GPU_PAGE_SHIFT,
AMDGPU_GMC_HOLE_START),
- .drm_render_minor = adev->ddev->render->index
+ .drm_render_minor = adev->ddev->render->index,
+ .sdma_doorbell_idx = adev->doorbell_index.sdma_engine,
+
};
/* this is going to have a few of the MSBs set that we need to
@@ -172,31 +174,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
_resources.doorbell_aperture_size,
_resources.doorbell_start_offset);
- if (adev->asic_type < CHIP_VEGA10) {
- kgd2kfd_device_init(adev->kfd.dev, _resources);
- return;
- }
-
- n = (adev->asic_type < CHIP_VEGA20) ? 2 : 8;
-
- for (i = 0; i < n; i += 2) {
- /* On SOC15 the BIF is involved in routing
-* doorbells using the low 12 bits of the
-* address. Communicate the assignments to
-* KFD. KFD uses two doorbell pages per
-* process in case of 64-bit doorbells so we
-* can use each doorbell assignment twice.
-*/
- gpu_resources.sdma_doorbell[0][i] =
- adev->doorbell_index.sdma_engine[0] + (i >> 1);
- gpu_resources.sdma_doorbell[0][i+1] =
- adev->doorbell_index.sdma_engine[0] + 0x200 +
(i >> 1);
- gpu_resources.sdma_doorbell[1][i] =
- adev->doorbell_index.sdma_engine[1] + (i >> 1);
- gpu_resources.sdma_doorbell[1][i+1] =
- adev->doorbell_index.sdma_engine[1] + 0x200 +
(i >> 1);
- }
-
/* Since SOC15, BIF starts to statically use the
* lower 12 bits of doorbell addresses for routing
* based on settings in registers like
@@ -205,10 +182,12 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
* 12 bits of its address has to be outside the range
* set for SDMA, VCN, and IH blocks.
*/
- gpu_resources.non_cp_doorbells_start =
- adev->doorbell_index.sdma_engine[0];
- gpu_resources.non_cp_doorbells_end =
- adev->doorbell_index.last_non_cp;
+ if (adev->asic_type >= CHIP_VEGA10) {
+ gpu_resources.non_cp_doorbells_start =
+ adev->doorbell_index.sdma_engine[0];
+ gpu_resources.non_cp_doorbells_end =
+ adev->doorbell_index.last_non_cp;
+ }
kgd2kfd_device_init(adev->kfd.dev, _resources);
}
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 8372556b52eb..c6c9530e704e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -134,12 +134,18 @@ static int allocate_doorbell(struct qcm_process_device
*qpd, struct queue *q)
*/
q->doorbell_id = q->properties.queue_id;
} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
- /* For SDMA queues on SOC15, use static doorbell
-* assignments based on the engine and queue.
+ /* For SDMA queues on SOC15
