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, 23 insertions, 2 deletions

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 4422d630b33b..c4d9eb623ce5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2426,9 +2426,20 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
         /* enable context1-15 */
         WREG32(VM_CONTEXT1_PROTECTION_FAULT_DEFAULT_ADDR,
                (u32)(rdev->dummy_page.addr >> 12));
-        WREG32(VM_CONTEXT1_CNTL2, 0);
+        WREG32(VM_CONTEXT1_CNTL2, 4);
         WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
-                                RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
+                                RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
+                                DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT |
+                                PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                PDE0_PROTECTION_FAULT_ENABLE_DEFAULT |
+                                VALID_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                VALID_PROTECTION_FAULT_ENABLE_DEFAULT |
+                                READ_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                READ_PROTECTION_FAULT_ENABLE_DEFAULT |
+                                WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT |
+                                WRITE_PROTECTION_FAULT_ENABLE_DEFAULT);
 
         si_pcie_gart_tlb_flush(rdev);
         DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
@@ -3684,6 +3695,16 @@ 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: /* RINGID0 CP_INT */
                         radeon_fence_process(rdev, RADEON_RING_TYPE_GFX_INDEX);
                         break;