drm/amdgpu: return error when sriov access requests get timeout
Subsystems (2)
PATCH 1/2 drm/amdgpu: return error when sriov access requests get timeout
From: pding <[email protected]>
--- drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +1 -1
@@ -450,7 +450,7 @@ static int xgpu_vi_send_access_requests(struct amdgpu_device *adev,pr_err ("Doesn't get ack from pf, continue\n" ); } -return 0 ; +return r; }static int xgpu_vi_request_reset (struct amdgpu_device *adev)
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1509433855-21354-1-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
PATCH 2/2 drm/amdgpu: retry init if exclusive mode request is failed
From: pding <[email protected]>
This is caused of that hypervisor fails to handle request, one known issue is MMIO unblocking timeout. In theory we can retry init here.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
@@ -1625,7 +1625,7 @@ static int amdgpu_early_init(struct amdgpu_device *adev)if (amdgpu_sriov_vf (adev)) { r =amdgpu_virt_request_full_gpu (adev, true);if (r) -return r; +return -EAGAIN ; }for (i =0 ; i < adev->num_ip_blocks; i++) {
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1509433855-21354-2-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 2/2] drm/amdgpu: retry init if exclusive mode request is failed
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Tuesday, October 31, 2017 3:11 PM
To: [email protected]
Cc: Ding, Pixel <[email protected]>
Subject: [PATCH 2/2] drm/amdgpu: retry init if exclusive mode request is failed
From: pding <[email protected]>
This is caused of that hypervisor fails to handle request, one known issue is MMIO unblocking timeout. In theory we can retry init here.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1 -1
@@ -1625,7 +1625,7 @@ static int amdgpu_early_init(struct amdgpu_device *adev)if (amdgpu_sriov_vf (adev)) { r =amdgpu_virt_request_full_gpu (adev, true);if (r) -return r; +return -EAGAIN ; }for (i =0 ; i < adev->num_ip_blocks; i++) {
--
2.9.5
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c static int xgpu_vi_send_access_requests(struct amdgpu_device *adev, · line 450
Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +0
-0@@ -450,7 +450,7 @@ static int xgpu_vi_send_access_requests(struct amdgpu_device *adev,pr_err ("Doesn't get ack from pf, continue\n" );
Why don't return error in this place?
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c static int xgpu_vi_send_access_requests(struct amdgpu_device *adev, · line 454
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +1
-1} -return 0 ; +return r; }
static int xgpu_vi_request_reset(struct amdgpu_device *adev)
Signature · 10 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx