Created attachment 95991 [details] dmesg System Environment: -------------------------- Platform: Broadwell kernel: (drm-intel-nightly)b1859622badb7509586987af5269aa525a0c112f Bug detailed description: ------------------------- It fails with OOM killer on Broadwell with -nightly kernel, and doesn't happen on -fixes, -queued, drm-next, drm-fixes and core-stuff branch. igt/kms_flip/flip-vs-fences-interruptible also fails. It doesn't happen on commit: 32faf6da913d67a4a3fcddd810305ec3445ed581(-nightly branch) output: IGT-Version: 1.6-g10571b8 (x86_64) (Linux: 3.14.0-rc6_drm-intel-nightly_b18596_20140314+ x86_64) Using monotonic timestamps Beginning flip-vs-fences on crtc 3, connector 10 1920x1080 60 1920 1966 1996 2080 1080 1082 1086 1112 0xa 0x48 138780 ............................................................................................................................... flip-vs-fences on crtc 3, connector 10: PASSED Beginning flip-vs-fences on crtc 5, connector 10 1920x1080 60 1920 1966 1996 2080 1080 1082 1086 1112 0xa 0x48 138780 ..............................Killed [ 158.480224] Call Trace: [ 158.480237] [<ffffffff817170e3>] ? dump_stack+0x41/0x51 [ 158.480244] [<ffffffff817143b1>] ? dump_header.isra.8+0x69/0x191 [ 158.480253] [<ffffffff8107225e>] ? ktime_get_ts+0x49/0xab [ 158.480262] [<ffffffff812d6cf2>] ? ___ratelimit+0xae/0xc8 [ 158.480271] [<ffffffff810a7244>] ? oom_kill_process+0x76/0x32c [ 158.480278] [<ffffffff810a7009>] ? find_lock_task_mm+0x22/0x6e [ 158.480288] [<ffffffff8103af8a>] ? has_ns_capability_noaudit+0xe/0x15 [ 158.480295] [<ffffffff810a7a79>] ? out_of_memory+0x41c/0x44f [ 158.480301] [<ffffffff810ab2bd>] ? __alloc_pages_nodemask+0x680/0x78d [ 158.480310] [<ffffffff810d4a2b>] ? alloc_pages_current+0xbf/0xdc [ 158.480317] [<ffffffff810a6196>] ? filemap_fault+0x25c/0x381 [ 158.480325] [<ffffffff810bc2a1>] ? __do_fault+0xac/0x3bf [ 158.480332] [<ffffffff810bfa31>] ? handle_mm_fault+0x1e7/0x7e2 [ 158.480341] [<ffffffff8171f4bd>] ? __do_page_fault+0x42e/0x47b [ 158.480348] [<ffffffff81038055>] ? timespec_add_safe+0x1e/0x4d [ 158.480353] [<ffffffff810f08e8>] ? dput+0x16/0xeb [ 158.480359] [<ffffffff8107225e>] ? ktime_get_ts+0x49/0xab [ 158.480368] [<ffffffff810edcfa>] ? poll_select_copy_remaining+0xe0/0xf6 [ 158.480374] [<ffffffff8171ca72>] ? page_fault+0x22/0x30 [ 158.480377] Mem-Info: [ 158.480380] Node 0 DMA per-cpu: [ 158.480385] CPU 0: hi: 0, btch: 1 usd: 0 [ 158.480389] CPU 1: hi: 0, btch: 1 usd: 0 [ 158.480392] CPU 2: hi: 0, btch: 1 usd: 0 [ 158.480396] CPU 3: hi: 0, btch: 1 usd: 0 [ 158.480398] Node 0 DMA32 per-cpu: [ 158.480403] CPU 0: hi: 186, btch: 31 usd: 0 [ 158.480407] CPU 1: hi: 186, btch: 31 usd: 0 [ 158.480410] CPU 2: hi: 186, btch: 31 usd: 0 [ 158.480413] CPU 3: hi: 186, btch: 31 usd: 0 [ 158.480436] Node 0 Normal per-cpu: [ 158.480440] CPU 0: hi: 186, btch: 31 usd: 0 [ 158.480443] CPU 1: hi: 186, btch: 31 usd: 0 [ 158.480446] CPU 2: hi: 186, btch: 31 usd: 0 [ 158.480449] CPU 3: hi: 186, btch: 31 usd: 0 Reproduce steps: ---------------------------- 1. ./kms_flip --run-subtest flip-vs-fences
Wut ... Is this still an issue on latest -nightly?
It still happens on latest -nightly kernel.
Created attachment 96510 [details] dmesg
Hua, can you help to retest this issue.
Sounds like a dupe of the filp leak ... Please retest and reopen if it still happens. Also we'd need the bisect result here ...
Verified.Fixed.
Closing old verified.
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.