On CI with sharded SNB igt@gem_tiled_partial_pwrite_pread@writes failed assertion: (drm_intel_gem_bo_context_exec(batch->bo, ctx, used, ring)) == 0 Hostname shard-snb2 Returncode 99 Out IGT-Version: 1.19-g5ce65a9a (x86_64) (Linux: 4.13.0-rc7-CI-CI_DRM_3023+ x86_64) Stack trace: #0 [__igt_fail_assert+0x101] #1 [intel_batchbuffer_flush_on_ring+0xc7] #2 [__real_main252+0x158] #3 [main+0x33] #4 [__libc_start_main+0xf1] #5 [_start+0x2a] #6 [<unknown>+0x2a] Subtest writes: FAIL (0.120s) Err (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Test assertion failure function intel_batchbuffer_flush_on_ring, file intel_batchbuffer.c:184: (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Failed assertion: (drm_intel_gem_bo_context_exec(batch->bo, ctx, used, ring)) == 0 (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Last errno: 5, Input/output error Subtest writes failed. **** DEBUG **** (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Test assertion failure function intel_batchbuffer_flush_on_ring, file intel_batchbuffer.c:184: (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Failed assertion: (drm_intel_gem_bo_context_exec(batch->bo, ctx, used, ring)) == 0 (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Last errno: 5, Input/output error (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: Stack trace: (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #0 [__igt_fail_assert+0x101] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #1 [intel_batchbuffer_flush_on_ring+0xc7] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #2 [__real_main252+0x158] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #3 [main+0x33] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #4 [__libc_start_main+0xf1] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #5 [_start+0x2a] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #6 [<unknown>+0x2a] **** END ****Hostname shard-snb2 Returncode 99 Out IGT-Version: 1.19-g5ce65a9a (x86_64) (Linux: 4.13.0-rc7-CI-CI_DRM_3023+ x86_64) Stack trace: #0 [__igt_fail_assert+0x101] #1 [intel_batchbuffer_flush_on_ring+0xc7] #2 [__real_main252+0x158] #3 [main+0x33] #4 [__libc_start_main+0xf1] #5 [_start+0x2a] #6 [<unknown>+0x2a] Subtest writes: FAIL (0.120s) Err (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Test assertion failure function intel_batchbuffer_flush_on_ring, file intel_batchbuffer.c:184: (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Failed assertion: (drm_intel_gem_bo_context_exec(batch->bo, ctx, used, ring)) == 0 (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Last errno: 5, Input/output error Subtest writes failed. **** DEBUG **** (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Test assertion failure function intel_batchbuffer_flush_on_ring, file intel_batchbuffer.c:184: (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Failed assertion: (drm_intel_gem_bo_context_exec(batch->bo, ctx, used, ring)) == 0 (gem_tiled_partial_pwrite_pread:1432) intel-batchbuffer-CRITICAL: Last errno: 5, Input/output error (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: Stack trace: (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #0 [__igt_fail_assert+0x101] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #1 [intel_batchbuffer_flush_on_ring+0xc7] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #2 [__real_main252+0x158] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #3 [main+0x33] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #4 [__libc_start_main+0xf1] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #5 [_start+0x2a] (gem_tiled_partial_pwrite_pread:1432) igt-core-INFO: #6 [<unknown>+0x2a] **** END **** https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_3023/shard-snb2/igt@gem_tiled_partial_pwrite_pread@writes.html See logs also on above link.
Same issues seen on 102457. Dup?
Kind off. Except you will need to add a test that is run at the start of each shard to check that the GPU is usable (along the lines of gem_exec_store) as well as the kernel integrity is intact. What you are looking at here is that the GPU died on its very first execution of the BSD (VCS) ring, which uses means a stale TLB.
Never seen again. Closing
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.