drm/amdgpu: Perform gpu reset after gfx finishes processing ras poison consumption on gfx_v11_0_3

Perform gpu reset after gfx finishes processing
ras poison consumption on gfx_v11_0_3.

V2:
 Move gfx poison consumption handler from hw_ops to ip
 function level.

V3:
 Adjust the calling position of amdgpu_gfx_poison_consumation_handler.

V4:
   Since gfx v11_0_3 does not have .hw_ops instance, the .hw_ops null
 pointer check in amdgpu_ras_interrupt_poison_consumption_handler
 needs to be adjusted.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 13 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c
index a18e09de31dd..b07a72ca25d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c
@@ -70,6 +70,19 @@ static int gfx_v11_0_3_rlc_gc_fed_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v11_0_3_poison_consumption_handler(struct amdgpu_device *adev,
+					struct amdgpu_iv_entry *entry)
+{
+	/* Workaround: when vmid and pasid are both zero, trigger gpu reset in KGD. */
+	if (entry && (entry->client_id == SOC21_IH_CLIENTID_GFX) &&
+	    (entry->src_id == GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT) &&
+	     !entry->vmid && !entry->pasid)
+		amdgpu_ras_reset_gpu(adev);
+
+	return 0;
+}
+
 struct amdgpu_gfx_ras gfx_v11_0_3_ras = {
 	.rlc_gc_fed_irq = gfx_v11_0_3_rlc_gc_fed_irq,
+	.poison_consumption_handler = gfx_v11_0_3_poison_consumption_handler,
 };