drm/radeon: stop page faults from hanging the system (v2)

Redirect invalid memory accesses to the default page
instead of locking up the memory controller. Also
enable the invalid memory access interrupts and
start spamming system log with it.

v2 (agd5f): fix up against 2 level PT changes

Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

1 files changed, 10 insertions, 0 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 219942c660d7..78de2e4097b5 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3093,6 +3093,16 @@ restart_ih:
                                 break;
                         }
                         break;
+                case 146:
+                case 147:
+                        dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
+                        dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
+                                RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR));
+                        dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+                                RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
+                        /* reset addr and status */
+                        WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
+                        break;
                 case 176: /* CP_INT in ring buffer */
                 case 177: /* CP_INT in IB1 */
                 case 178: /* CP_INT in IB2 */