leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

drm/amdgpu: retry init if it fails due to exclusive mode timeout (v3)

Browse Source 
The exclusive mode has real-time limitation in reality, such like being
done in 300ms. It's easy observed if running many VF/VMs in single host
with heavy CPU workload.

If we find the init fails due to exclusive mode timeout, try it again.

v2:
 - rewrite the condition for readable value.

v3:
 - fix typo, add comments for sleep

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: pding <Pixel.Ding@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
pding
2017-10-23 17:22:09 +08:00
committed by Alex Deucher
parent b59142384e
commit 8840a3878d
2 changed files with 23 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@@ -2303,6 +2303,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_init(adev); r = amdgpu_init(adev);
if (r) { if (r) {
/* failed in exclusive mode due to timeout */
if (amdgpu_sriov_vf(adev) &&
!amdgpu_sriov_runtime(adev) &&
amdgpu_virt_mmio_blocked(adev) &&
!amdgpu_virt_wait_reset(adev)) {
dev_err(adev->dev, "VF exclusive mode timeout\n");
r = -EAGAIN;
goto failed;
}
dev_err(adev->dev, "amdgpu_init failed\n"); dev_err(adev->dev, "amdgpu_init failed\n");
amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0); amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
amdgpu_fini(adev); amdgpu_fini(adev);
@@ -2390,6 +2399,7 @@ failed:
amdgpu_vf_error_trans_all(adev); amdgpu_vf_error_trans_all(adev);
if (runtime) if (runtime)
vga_switcheroo_fini_domain_pm_ops(adev->dev); vga_switcheroo_fini_domain_pm_ops(adev->dev);
return r; return r;
} }

15
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
View File

@@ -86,7 +86,7 @@ done_free:
int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
{ {
struct amdgpu_device *adev; struct amdgpu_device *adev;
int r, acpi_status; int r, acpi_status, retry = 0;
#ifdef CONFIG_DRM_AMDGPU_SI #ifdef CONFIG_DRM_AMDGPU_SI
if (!amdgpu_si_support) { if (!amdgpu_si_support) {
@@ -122,6 +122,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
} }
} }
#endif #endif
retry_init:
adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL); adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
if (adev == NULL) { if (adev == NULL) {
@@ -144,7 +145,17 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
* VRAM allocation * VRAM allocation
*/ */
r = amdgpu_device_init(adev, dev, dev->pdev, flags); r = amdgpu_device_init(adev, dev, dev->pdev, flags);
if (r) { if (r == -EAGAIN && ++retry <= 3) {
adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
adev->virt.ops = NULL;
amdgpu_device_fini(adev);
kfree(adev);
dev->dev_private = NULL;
/* Don't request EX mode too frequently which is attacking */
msleep(5000);
dev_err(&dev->pdev->dev, "retry init %d\n", retry);
goto retry_init;
} else if (r) {
dev_err(&dev->pdev->dev, "Fatal error during GPU init\n"); dev_err(&dev->pdev->dev, "Fatal error during GPU init\n");
goto out; goto out;
} }