summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
diff options
context:
space:
mode:
authorAndres Rodriguez <andresx7@gmail.com>2017-02-03 16:28:48 -0500
committerAlex Deucher <alexander.deucher@amd.com>2017-05-31 16:48:54 -0400
commitd0b63bb3385c5683c7531044425f4507ca5251b2 (patch)
treeb2c6c0dc8ac159a6e08f3a940be5b9b66408a96a /drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
parent763a47b8e1abc7cee0a0f550330124ef1199d58d (diff)
downloadop-kernel-dev-d0b63bb3385c5683c7531044425f4507ca5251b2.zip
op-kernel-dev-d0b63bb3385c5683c7531044425f4507ca5251b2.tar.gz
drm/amdkfd: allow split HQD on per-queue granularity v5
Update the KGD to KFD interface to allow sharing pipes with queue granularity instead of pipe granularity. This allows for more interesting pipe/queue splits. v2: fix overflow check for res.queue_mask v3: fix shift overflow when setting res.queue_mask v4: fix comment in is_pipeline_enabled() v5: clamp res.queue_mask to the first MEC only Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Andres Rodriguez <andresx7@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c22
1 files changed, 19 insertions, 3 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 3200ff9..8fc5aa3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -95,14 +95,30 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
+ int i;
+ int last_valid_bit;
if (adev->kfd) {
struct kgd2kfd_shared_resources gpu_resources = {
.compute_vmid_bitmap = 0xFF00,
-
- .first_compute_pipe = 1,
- .compute_pipe_count = 4 - 1,
+ .num_mec = adev->gfx.mec.num_mec,
+ .num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
+ .num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
};
+ /* this is going to have a few of the MSBs set that we need to
+ * clear */
+ bitmap_complement(gpu_resources.queue_bitmap,
+ adev->gfx.mec.queue_bitmap,
+ KGD_MAX_QUEUES);
+
+ /* According to linux/bitmap.h we shouldn't use bitmap_clear if
+ * nbits is not compile time constant */
+ last_valid_bit = adev->gfx.mec.num_mec
+ * adev->gfx.mec.num_pipe_per_mec
+ * adev->gfx.mec.num_queue_per_pipe;
+ for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
+ clear_bit(i, gpu_resources.queue_bitmap);
+
amdgpu_doorbell_get_kfd_info(adev,
&gpu_resources.doorbell_physical_address,
&gpu_resources.doorbell_aperture_size,
OpenPOWER on IntegriCloud