summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
diff options
context:
space:
mode:
authorMonk Liu <Monk.Liu@amd.com>2020-07-27 10:20:12 +0300
committerAlex Deucher <alexander.deucher@amd.com>2020-08-05 00:27:29 +0300
commita300de40f66b87fa90703c94ffb22917f98eb902 (patch)
treee1690029e39055ed5af5896a15ede13c51eba6a0 /drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
parent9b856defbe355f886f99777e667506841bd267a8 (diff)
downloadlinux-a300de40f66b87fa90703c94ffb22917f98eb902.tar.xz
drm/amdgpu: introduce a new parameter to configure how many KCQ we want(v5)
what: the MQD's save and restore of KCQ (kernel compute queue) cost lots of clocks during world switch which impacts a lot to multi-VF performance how: introduce a paramter to control the number of KCQ to avoid performance drop if there is no kernel compute queue needed notes: this paramter only affects gfx 8/9/10 v2: refine namings v3: choose queues for each ring to that try best to cross pipes evenly. v4: fix indentation some cleanupsin the gfx_compute_queue_acquire() v5: further fix on indentations more cleanupsin gfx_compute_queue_acquire() TODO: in the future we will let hypervisor driver to set this paramter automatically thus no need for user to configure it through modprobe in virtual machine Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c29
1 files changed, 15 insertions, 14 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 8d7208959c95..7df567a6656d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1343,21 +1343,22 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
amdgpu_gfx_compute_queue_acquire(adev);
mec_hpd_size = adev->gfx.num_compute_rings * GFX8_MEC_HPD_SIZE;
+ if (mec_hpd_size) {
+ r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &adev->gfx.mec.hpd_eop_obj,
+ &adev->gfx.mec.hpd_eop_gpu_addr,
+ (void **)&hpd);
+ if (r) {
+ dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
+ return r;
+ }
- r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE,
- AMDGPU_GEM_DOMAIN_VRAM,
- &adev->gfx.mec.hpd_eop_obj,
- &adev->gfx.mec.hpd_eop_gpu_addr,
- (void **)&hpd);
- if (r) {
- dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
- return r;
- }
-
- memset(hpd, 0, mec_hpd_size);
+ memset(hpd, 0, mec_hpd_size);
- amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
- amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+ amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
+ amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
+ }
return 0;
}
@@ -5294,7 +5295,7 @@ static int gfx_v8_0_early_init(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
adev->gfx.num_gfx_rings = GFX8_NUM_GFX_RINGS;
- adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+ adev->gfx.num_compute_rings = amdgpu_num_kcq;
adev->gfx.funcs = &gfx_v8_0_gfx_funcs;
gfx_v8_0_set_ring_funcs(adev);
gfx_v8_0_set_irq_funcs(adev);