https://intel-gfx-ci.01.org/tree/drm-tip/drmtip_327/fi-byt-n2820/igt@gem_ctx_shared@exec-shared-gtt-render.html Starting subtest: exec-shared-gtt-render (gem_ctx_shared:1045) CRITICAL: Test assertion failure function exec_shared_gtt, file ../tests/i915/gem_ctx_shared.c:258: (gem_ctx_shared:1045) CRITICAL: Failed assertion: *s == 0xc0ffee (gem_ctx_shared:1045) CRITICAL: error: 0x5000000 != 0xc0ffee Subtest exec-shared-gtt-render failed. **** DEBUG **** (gem_ctx_shared:1045) ioctl_wrappers-DEBUG: Test requirement passed: gem_has_ring(fd, ring) (gem_ctx_shared:1045) DEBUG: Test requirement passed: gem_can_store_dword(i915, ring) (gem_ctx_shared:1045) CRITICAL: Test assertion failure function exec_shared_gtt, file ../tests/i915/gem_ctx_shared.c:258: (gem_ctx_shared:1045) CRITICAL: Failed assertion: *s == 0xc0ffee (gem_ctx_shared:1045) CRITICAL: error: 0x5000000 != 0xc0ffee (gem_ctx_shared:1045) igt_core-INFO: Stack trace: (gem_ctx_shared:1045) igt_core-INFO: #0 ../lib/igt_core.c:1674 __igt_fail_assert() (gem_ctx_shared:1045) igt_core-INFO: #1 ../tests/i915/gem_ctx_shared.c:862 __real_main778() (gem_ctx_shared:1045) igt_core-INFO: #2 [<unknown>+0x0] **** END **** Subtest exec-shared-gtt-render: FAIL (0.036s)
The CI Bug Log issue associated to this bug has been updated. ### New filters associated * BYT: igt@gem_ctx_shared@exec-shared-gtt-render - fail - Failed assertion: *s == 0xc0ffee - https://intel-gfx-ci.01.org/tree/drm-tip/drmtip_327/fi-byt-n2820/igt@gem_ctx_shared@exec-shared-gtt-render.html
commit 7e4d10507088055413769a020dd674f52b4bc1b0 (HEAD, upstream/master) Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Tue Jul 23 17:13:18 2019 +0100 i915/gem_ctx_shared: Avoid clflush by using WC for readback As we never officially write to the scratch buffer, the kernel will leave it in the CPU read domain upon execution. Our attempt to invalidate the CPU cache on !llc is therefore skipped as the kernel doesn't believe the backing store has been invalidated. Use a WC mmap to avoid the CPU cache for readback, and add an extra sanity check that the scratch buffer is found at the same location after execution. (This sanity check does not affect the failure rate on bsw, that is only fixed after realising that we do not clflush for the invalidate prior to the read). Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111187 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com>
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.