why we need to do infinite RLC_SPM register setting during VM flush

[Liu, Monk]

Hi Jaco & Christian

As titled , check below patch:

commit 10790a09ea584cc832353a5c2a481012e5e31a13
Author: Jacob He <jacob.he at amd.com>
Date:   Fri Feb 28 20:24:41 2020 +0800

    drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid

    SPM access the video memory according to SPM_VMID. It should be updated
    with the job's vmid right before the job is scheduled. SPM_VMID is a
    global resource

    Change-Id: Id3881908960398f87e7c95026a54ff83ff826700
    Signed-off-by: Jacob He <jacob.he at amd.com>
    Reviewed-by: Christian König <christian.koenig at amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6e6fc8c..ba2236a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1056,8 +1056,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
        struct dma_fence *fence = NULL;
        bool pasid_mapping_needed = false;
        unsigned patch_offset = 0;
+       bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL));
        int r;

+       if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid)
+               adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid);
+
        if (amdgpu_vmid_had_gpu_reset(adev, id)) {
                gds_switch_needed = true;
                vm_flush_needed = true;

this update_spm_vmid() looks an completely overkill to me, we only need to do it once for its VM ...

in SRIOV the register reading/writing for update_spm_vmid() is now carried by KIQ thus there is too much burden on KIQ for such unnecessary jobs ...

I want to change it to only do it once per VM, like:

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6e6fc8c..ba2236a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1056,8 +1056,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
        struct dma_fence *fence = NULL;
       bool pasid_mapping_needed = false;
        unsigned patch_offset = 0;
+       bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL));
        int r;

+       if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid &&  !vm->spm_updated) {
+               adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid);
+               vm->spm_updated = true;
+       }

        if (amdgpu_vmid_had_gpu_reset(adev, id)) {
                gds_switch_needed = true;
                vm_flush_needed = true;

what do you think ?

P.S.: the best way is to let GFX ring itself to do the update_spm_vmid() instead of let CPU doing it, e.g.: we put more PM4 command in VM-FLUSH packets ....
But I prefer the simple way first like I demonstrated above
_____________________________________
Monk Liu|GPU Virtualization Team |AMD
[sig-cloud-gpu]

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20200420/e02f933c/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 12243 bytes
Desc: image001.png
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20200420/e02f933c/attachment-0001.png>