summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
diff options
context:
space:
mode:
authorFelix Kuehling <Felix.Kuehling@amd.com>2017-09-21 23:26:41 +0300
committerAlex Deucher <alexander.deucher@amd.com>2017-09-28 23:03:30 +0300
commitc98171ccf6580407d07a3b5dc8188ce9e1f4f7ca (patch)
tree191e13e83451ea87c6e4fdc758425b046a0c4bf8 /drivers/gpu/drm/amd/amdgpu/tonga_ih.c
parent1bab0fc01b84c1aa8a65a1f1de885e1faab48264 (diff)
downloadlinux-c98171ccf6580407d07a3b5dc8188ce9e1f4f7ca.tar.xz
drm/amdgpu: Handle GPUVM fault storms
When many wavefronts cause VM faults at the same time, it can overwhelm the interrupt handler and cause IH ring overflows before the driver can notify or kill the faulting application. As a workaround I'm introducing limited per-VM fault credit. After that number of VM faults have occurred, further VM faults are filtered out at the prescreen stage of processing. This depends on the PASID in the interrupt packet, so it currently only works for KFD contexts. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/tonga_ih.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/tonga_ih.c19
1 files changed, 17 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 5ed00692618e..aa4e320e31f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -227,8 +227,23 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev)
*/
static bool tonga_ih_prescreen_iv(struct amdgpu_device *adev)
{
- /* Process all interrupts */
- return true;
+ u32 ring_index = adev->irq.ih.rptr >> 2;
+ u16 pasid;
+
+ switch (le32_to_cpu(adev->irq.ih.ring[ring_index]) & 0xff) {
+ case 146:
+ case 147:
+ pasid = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]) >> 16;
+ if (!pasid || amdgpu_vm_pasid_fault_credit(adev, pasid))
+ return true;
+ break;
+ default:
+ /* Not a VM fault */
+ return true;
+ }
+
+ adev->irq.ih.rptr += 16;
+ return false;
}
/**