We have a list of all rings, so no sense writing the same loop N
times. With how often this gets called and how small the ring list
is the performance of this shouldn't matter.
Note that some of the loops included some checking wrt harvesting.
That is redundant now, as those rings never get initialized and
hence never added to the adev->rings array.
Signed-off-by: Bas Nieuwenhuizen <bas@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 61 ++++++-------------------
1 file changed, 15 insertions(+), 46 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 0efb38539d70..89689b940493 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -366,7 +366,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
uint32_t ib_size_alignment = 0;
enum amd_ip_block_type type;
unsigned int num_rings = 0;
- unsigned int i, j;
+ unsigned int i;
if (info->query_hw_ip.ip_instance >= AMDGPU_HW_IP_INSTANCE_MAX_COUNT)
return -EINVAL;
@@ -374,83 +374,49 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
switch (info->query_hw_ip.type) {
case AMDGPU_HW_IP_GFX:
type = AMD_IP_BLOCK_TYPE_GFX;
- for (i = 0; i < adev->gfx.num_gfx_rings; i++)
- if (adev->gfx.gfx_ring[i].sched.ready)
- ++num_rings;
+
ib_start_alignment = 32;
ib_size_alignment = 32;
break;
case AMDGPU_HW_IP_COMPUTE:
type = AMD_IP_BLOCK_TYPE_GFX;
- for (i = 0; i < adev->gfx.num_compute_rings; i++)
- if (adev->gfx.compute_ring[i].sched.ready)
- ++num_rings;
+
ib_start_alignment = 32;
ib_size_alignment = 32;
break;
case AMDGPU_HW_IP_DMA:
type = AMD_IP_BLOCK_TYPE_SDMA;
- for (i = 0; i < adev->sdma.num_instances; i++)
- if (adev->sdma.instance[i].ring.sched.ready)
- ++num_rings;
+
ib_start_alignment = 256;
ib_size_alignment = 4;
break;
case AMDGPU_HW_IP_UVD:
type = AMD_IP_BLOCK_TYPE_UVD;
- for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
- if (adev->uvd.harvest_config & (1 << i))
- continue;
- if (adev->uvd.inst[i].ring.sched.ready)
- ++num_rings;
- }
ib_start_alignment = 64;
ib_size_alignment = 64;
break;
case AMDGPU_HW_IP_VCE:
type = AMD_IP_BLOCK_TYPE_VCE;
- for (i = 0; i < adev->vce.num_rings; i++)
- if (adev->vce.ring[i].sched.ready)
- ++num_rings;
+
ib_start_alignment = 4;
ib_size_alignment = 1;
break;
case AMDGPU_HW_IP_UVD_ENC:
type = AMD_IP_BLOCK_TYPE_UVD;
- for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
- if (adev->uvd.harvest_config & (1 << i))
- continue;
- for (j = 0; j < adev->uvd.num_enc_rings; j++)
- if (adev->uvd.inst[i].ring_enc[j].sched.ready)
- ++num_rings;
- }
ib_start_alignment = 64;
ib_size_alignment = 64;
break;
case AMDGPU_HW_IP_VCN_DEC:
type = AMD_IP_BLOCK_TYPE_VCN;
- for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
- if (adev->vcn.harvest_config & (1 << i))
- continue;
- if (adev->vcn.inst[i].ring_dec.sched.ready)
- ++num_rings;
- }
ib_start_alignment = 16;
ib_size_alignment = 16;
break;
case AMDGPU_HW_IP_VCN_ENC:
type = AMD_IP_BLOCK_TYPE_VCN;
- for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
- if (adev->vcn.harvest_config & (1 << i))
- continue;
- for (j = 0; j < adev->vcn.num_enc_rings; j++)
- if (adev->vcn.inst[i].ring_enc[j].sched.ready)
- ++num_rings;
- }
ib_start_alignment = 64;
ib_size_alignment = 1;
break;
@@ -458,13 +424,6 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ?
AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN;
- for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
- if (adev->jpeg.harvest_config & (1 << i))
- continue;
-
- if (adev->jpeg.inst[i].ring_dec.sched.ready)
- ++num_rings;
- }
ib_start_alignment = 16;
ib_size_alignment = 16;
break;
@@ -472,6 +431,16 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
return -EINVAL;
}
+ for (i = 0; i < adev->num_rings; ++i) {
+ /* Note that this uses that ring types alias the equivalent
+ * HW IP exposes to userspace.
+ */
+ if (adev->rings[i]->funcs->type == info->query_hw_ip.type &&
+ adev->rings[i]->sched.ready) {
+ ++num_rings;
+ }
+ }
+
for (i = 0; i < adev->num_ip_blocks; i++)
if (adev->ip_blocks[i].version->type == type &&
adev->ip_blocks[i].status.valid)
--
2.40.0
