Created attachment 111349 [details] dmesg ==System Environment== -------------------------- Regression: Yes. Good commit on -next-queued: 372ee59699d9704086dadb084209542d10e28851(2014_12_01) Non-working platforms: BSW ==kernel== -------------------------- drm-intel-nightly/4fa23142a15526f4a4b5df61f26eacdd558a849a commit 4fa23142a15526f4a4b5df61f26eacdd558a849a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Fri Dec 19 15:33:33 2014 +0100 drm-intel-nightly: 2014y-12m-19d-14h-33m-07s UTC integration manifest ==Bug detailed description== ----------------------------- It causes OOM killer on BSW with drm-intel-nightly and drm-intel-next-queued kernel. root@x-bsw01:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# ./gem_ctx_thrash --run-subtest processes IGT-Version: 1.9-geb799b2 (x86_64) (Linux: 3.18.0_drm-intel-nightly_4fa231_20141226+ x86_64) Creating 1536 contexts (assuming of size 2097152) dmesg: [ 94.514575] Call Trace: [ 94.514591] [<ffffffff8178d5e2>] ? dump_stack+0x41/0x51 [ 94.514599] [<ffffffff8178ac83>] ? dump_header.isra.10+0x69/0x191 [ 94.514608] [<ffffffff8107f537>] ? ktime_get+0x44/0x80 [ 94.514617] [<ffffffff8133894a>] ? ___ratelimit+0xae/0xc8 [ 94.514626] [<ffffffff810d1bc4>] ? oom_kill_process+0x76/0x330 [ 94.514631] [<ffffffff810d1981>] ? find_lock_task_mm+0x22/0x6e [ 94.514639] [<ffffffff810406de>] ? has_ns_capability_noaudit+0xe/0x15 [ 94.514645] [<ffffffff810d23fb>] ? out_of_memory+0x41f/0x452 [ 94.514654] [<ffffffff810d638a>] ? __alloc_pages_nodemask+0x65e/0x7aa [ 94.514695] [<ffffffffa009d8df>] ? __hw_ppgtt_init+0x3cd/0x8a5 [i915] [ 94.514704] [<ffffffff81104d10>] ? alloc_pages_current+0xaf/0xcc [ 94.514732] [<ffffffffa009d8df>] ? __hw_ppgtt_init+0x3cd/0x8a5 [i915] [ 94.514760] [<ffffffffa009d8fa>] ? __hw_ppgtt_init+0x3e8/0x8a5 [i915] [ 94.514768] [<ffffffff81335128>] ? idr_get_empty_slot+0x1dd/0x2fa [ 94.514778] [<ffffffff81334c03>] ? idr_mark_full+0x49/0x52 [ 94.514811] [<ffffffffa009e161>] ? i915_ppgtt_init+0x12/0x50 [i915] [ 94.514841] [<ffffffffa009e41e>] ? i915_ppgtt_create+0x33/0x8f [i915] [ 94.514868] [<ffffffffa0097ece>] ? i915_gem_create_context+0x1b3/0x26e [i915] [ 94.514897] [<ffffffffa00982f2>] ? i915_gem_context_open+0x34/0x5c [i915] [ 94.514929] [<ffffffffa00a2ceb>] ? i915_gem_open+0xbf/0xe3 [i915] [ 94.514949] [<ffffffffa000ee2d>] ? drm_open+0x209/0x40e [drm] [ 94.514978] [<ffffffffa0013c7d>] ? drm_stub_open+0xb5/0xe4 [drm] [ 94.514987] [<ffffffff811139ae>] ? chrdev_open+0x12b/0x154 [ 94.514993] [<ffffffff81113883>] ? cdev_put+0x19/0x19 [ 94.515002] [<ffffffff8110e5cd>] ? do_dentry_open+0x184/0x2a6 [ 94.515009] [<ffffffff8111b8ed>] ? do_last+0x942/0xb75 [ 94.515015] [<ffffffff811185d6>] ? __inode_permission+0x53/0x6e [ 94.515021] [<ffffffff8111870e>] ? link_path_walk+0x64/0x74a [ 94.515028] [<ffffffff8111bd4d>] ? path_openat+0x22d/0x5b9 [ 94.515034] [<ffffffff8111c97a>] ? do_filp_open+0x2d/0x75 [ 94.515042] [<ffffffff8112611d>] ? __alloc_fd+0x58/0xe3 [ 94.515048] [<ffffffff8110f740>] ? do_sys_open+0x14b/0x1cf [ 94.515057] [<ffffffff81792c92>] ? system_call_fastpath+0x12/0x17 [ 94.515061] Mem-Info: [ 94.515065] Node 0 DMA per-cpu: [ 94.515070] CPU 0: hi: 0, btch: 1 usd: 0 [ 94.515073] CPU 1: hi: 0, btch: 1 usd: 0 [ 94.515077] CPU 2: hi: 0, btch: 1 usd: 0 [ 94.515081] CPU 3: hi: 0, btch: 1 usd: 0 [ 94.515084] Node 0 DMA32 per-cpu: [ 94.515089] CPU 0: hi: 186, btch: 31 usd: 0 [ 94.515093] CPU 1: hi: 186, btch: 31 usd: 0 [ 94.515097] CPU 2: hi: 186, btch: 31 usd: 0 [ 94.515101] CPU 3: hi: 186, btch: 31 usd: 0 [ 94.515104] Node 0 Normal per-cpu: [ 94.515108] CPU 0: hi: 186, btch: 31 usd: 0 [ 94.515112] CPU 1: hi: 186, btch: 31 usd: 0 [ 94.515117] CPU 2: hi: 186, btch: 31 usd: 0 [ 94.515120] CPU 3: hi: 186, btch: 31 usd: 0 [ 94.515132] active_anon:6019 inactive_anon:2074 isolated_anon:0 [ 94.515326] [ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name [ 94.515337] [ 2484] 0 2484 1113 0 7 25 0 sh [ 94.515344] [ 2511] 0 2511 4428 173 13 368 0 initctl [ 94.515351] [ 2611] 0 2611 5002 1 13 201 0 upstart-udev-br [ 94.515358] [ 2615] 0 2615 12449 19 27 220 -1000 systemd-udevd [ 94.515364] [ 3385] 0 3385 7444 0 19 62 0 rpc.idmapd [ 94.515371] [ 3403] 102 3403 9892 101 23 77 0 dbus-daemon [ 94.515376] [ 3443] 0 3443 10864 12 26 75 0 systemd-logind [ 94.515383] [ 3466] 101 3466 65535 0 31 176 0 rsyslogd [ 94.515390] [ 3512] 0 3512 19215 152 42 122 0 cupsd [ 94.515397] [ 3517] 0 3517 82589 103 63 199 0 ModemManager [ 94.515402] [ 3520] 111 3520 8089 47 21 30 0 avahi-daemon [ 94.515409] [ 3522] 111 3522 8058 30 20 32 0 avahi-daemon [ 94.515414] [ 3625] 0 3625 89163 384 70 21 0 NetworkManager [ 94.515420] [ 3645] 0 3645 73632 199 48 0 0 polkitd [ 94.515425] [ 3652] 0 3652 1113 28 7 0 0 sh [ 94.515431] [ 3673] 7 3673 15791 126 34 0 0 dbus [ 94.515437] [ 3679] 0 3679 5006 40 13 0 0 getty [ 94.515444] [ 3683] 0 3683 5006 42 15 0 0 getty [ 94.515450] [ 3689] 0 3689 5006 42 13 0 0 getty [ 94.515456] [ 3690] 0 3690 5006 40 13 0 0 getty [ 94.515462] [ 3693] 0 3693 5006 41 12 0 0 getty [ 94.515469] [ 3716] 0 3716 15343 171 34 0 -1000 sshd [ 94.515476] [ 3728] 0 3728 4799 60 16 0 0 irqbalance [ 94.515482] [ 3732] 0 3732 5916 63 16 0 0 cron [ 94.515489] [ 3740] 0 3740 1094 46 8 0 0 acpid [ 94.515494] [ 3742] 106 3742 9288 80 22 0 0 kerneloops [ 94.515501] [ 3751] 109 3751 90875 356 77 0 0 whoopsie [ 94.515508] [ 3845] 0 3845 18840 223 40 0 0 cups-browsed [ 94.515513] [ 3857] 0 3857 5857 66 18 0 0 rpcbind [ 94.515519] [ 3873] 0 3873 5006 42 13 0 0 getty [ 94.515525] [ 3909] 117 3909 5388 114 17 0 0 rpc.statd [ 94.515531] [ 3927] 0 3927 2560 576 10 0 0 dhclient [ 94.515538] [ 4003] 0 4003 4052 247 12 39 0 upstart-file-br [ 94.515544] [ 4020] 0 4020 3883 128 12 0 0 upstart-socket- [ 94.515550] [ 4103] 65534 4103 8808 66 23 0 0 dnsmasq [ 94.515555] [ 4303] 0 4303 27447 256 56 0 0 sshd [ 94.515561] [ 4377] 0 4377 6814 626 18 0 0 bash [ 94.515567] [ 4391] 0 4391 1088 18 8 0 0 sleep [ 94.515573] [ 4392] 0 4392 18529 121 39 0 1000 gem_ctx_thrash [ 94.515578] [ 4393] 0 4393 27447 250 57 0 0 sshd [ 94.515584] [ 4395] 0 4395 1113 20 7 0 0 sh [ 94.515589] [ 4396] 0 4396 1086 20 8 0 0 run-parts [ 94.515596] [ 4415] 0 4415 1113 21 7 0 0 91-release-upgr [ 94.515601] [ 4416] 0 4416 1113 26 7 0 0 91-release-upgr [ 94.515608] [ 4417] 0 4417 5921 495 16 0 0 lsb_release [ 94.515615] [ 4418] 0 4418 1093 19 7 0 0 cut [ 94.515619] Out of memory: Kill process 4392 (gem_ctx_thrash) score 999 or sacrifice child [ 94.515775] Killed process 4392 (gem_ctx_thrash) total-vm:74116kB, anon-rss:484kB, file-rss:0kB ==Reproduce steps== ---------------------------- 1. ./gem_ctx_thrash --run-subtest processes
2f82bbdf3d4f1361c3d713c516d8aa390102374d is the first bad commit commit 2f82bbdf3d4f1361c3d713c516d8aa390102374d Author: Michel Thierry <michel.thierry@intel.com> AuthorDate: Mon Dec 15 14:58:00 2014 +0000 Commit: Daniel Vetter <daniel.vetter@ffwll.ch> CommitDate: Tue Dec 16 10:39:12 2014 +0100 drm/i915: Use true PPGTT in Gen8+ when execlists are enabled In Gen8+, full ppgtt needs execlist, otherwise the ctx switch can hang. Also remove the current restriction, a user should be able to explicitly set ppgtt=2. Note, this patch considers that execlist support has been enabled by default on Gen8. v2: Remove non-default restriction and clarify commit message (Daniel) Cc: Daniel Vetter <daniel@ffwll.ch> Signed-off-by: Michel Thierry <michel.thierry@intel.com> [danvet: s/comment/commit message/ in the commit message since that's what Michel meant as per our irc discussion.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The bisect commit looks like 10 days ago.It's a new case and merged in recently. The bisect commit is earlier than merging commit and This case also has bug 87575 and 87572..
(In reply to lu hua from comment #2) > The bisect commit looks like 10 days ago.It's a new case and merged in > recently. > The bisect commit is earlier than merging commit and This case also has bug > 87575 and 87572.. This is the type of bug the test is intended to provoke and the bisect is reasonable - since full-ppgtt requires deferred allocation for this test to pass.
gem_close_race/gem-close-race also has OOM Killer issue and caused by the same bisect commit.
What I believe Chris meant is that that patch isn't a valid bisect result since it just enable the feature that before it was hidden under ppgtt=2. So for a propper bisect or use i915.ppgtt=2 when booting kernel or try to apply this patch on all bisect iteractions. Anyway, does it still happens on latest -nithly? I run this tests ok here on my BSW...
Created attachment 112873 [details] dmesg(0127) Test on the latest -nightly kernel. It still exists. output: IGT-Version: 1.9-gfa94e01 (x86_64) (Linux: 3.19.0-rc6_drm-intel-nightly_2c2cd3_20150127+ x86_64) Creating 1536 contexts (assuming of size 2097152)
This test (and gem_close_race) should fail if i915.enable_ppgtt=2. Deffered page table allocation is still under review and hasn't been merged. If it's failing with enable_ppgtt=1, then it's something else.
(In reply to Michel Thierry from comment #7) > This test (and gem_close_race) should fail if i915.enable_ppgtt=2. > > Deffered page table allocation is still under review and hasn't been merged. > > If it's failing with enable_ppgtt=1, then it's something else. Add i915.enable_ppgtt=1, it's skip. IGT-Version: 1.9-g7848d21 (x86_64) (Linux: 3.19.0-rc6_drm-intel-nightly_70438b_20150128+ x86_64) Creating 49152 contexts (assuming of size 65536) Creating 98304 surfaces (of size 45056) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 4479516672 bytes for the test, but only have 3767533568 bytes available (RAM) Subtest processes: SKIP (1.106s) add i915.enable_ppgtt=2, it still fails.
Hi, I'm an end-user affected by this; is there any workaround? I tried twiddling the enable_ppgtt option but at random points when using OpenGL apps (Chromium (hw acceleration), and a video game called "Team Fortress 2"). BTW when these freezes happen my hard drive is constantly being used by seemingly unrelated processes. (iotop and the LED light both concur). (my GPU is Sandy Bridge Intel HD 3000 I believe).
Please try with current drm-intel-nightly.
Still happening with the latest "linux-image-3.19.0-994-generic_3.19.0-994.201502100205_amd64.deb" Ubuntu drm-nightly package on http://kernel.ubuntu.com/~kernel-ppa/mainline/drm-intel-nightly/ . Doing empirical testing with the game "Team Fortress 2" yielded a OOM kill after about 10 minutes of running the game. However, gem_ctx_thrash yielded a skip: ramchandra@ramchandra-LIFEBOOK-AH532:~/Downloads/intel-gpu-tools/tests$ sudo ./gem_ctx_thrash IGT-Version: 1.9-gbef692d (x86_64) (Linux: 3.19.0-994-generic x86_64) Creating 49152 contexts (assuming of size 65536) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 3246391296 bytes for the test, but only have 432013312 bytes available (RAM + swap) Subtest processes: SKIP (0.192s) Creating 49152 contexts (assuming of size 65536) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 3246391296 bytes for the test, but only have 432013312 bytes available (RAM + swap) Subtest threads: SKIP (0.132s) I will soon try with different enable_ppgtt options to see whether that makes any difference.
Created attachment 113312 [details] Ramchandra Apte's dmesg result
(In reply to Ramchandra Apte from comment #9) > Hi, I'm an end-user affected by this; is there any workaround? Ramchandra Apte, you probably have a different bug, please file a new one. Thanks.
It still happens on the latest drm-intel-nightly kernel. root@x-bsw06:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# ./gem_ctx_thrash IGT-Version: 1.9-g9846e7f (x86_64) (Linux: 3.19.0_drm-intel-nightly_ad9512_20150210+ x86_64) Creating 1536 contexts (assuming of size 2097152) Connection to x-bsw06 closed.
Run gem_close_race/gem-close-race and gem_ctx_thrash on SKL, they also have this issue.
Dynamic page allocation finally landed in nightly: http://cgit.freedesktop.org/drm-intel/commit/?id=90ae20039e11a91e7144ab4e1800616d03403df5 Test should not cause OOM.
Tested on the latest nightly kernel(044307) and the latest igt(gd36465d). gem_ctx_thrash two subcases(processes and threads) are good on SKL mobile, gem_close_race subcase gem-close-race causes OOM killer on SKL mobile. gem_ctx_thrash sucases processes is good, threads is fail on BSW gem_close_race subcase gem-close-race causes OOM killer on BSW. I will full test next week. output: ----------------- root@x-skly03:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# ./gem_ctx_thrash IGT-Version: 1.10-gd36465d (x86_64) (Linux: 4.0.0-rc7_drm-intel-nightly_044307_20150410+ x86_64) Creating 1536 contexts (assuming of size 4194304) Creating 3072 surfaces (of size 2797568) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 8595701760 bytes for the test, but only have 3576692736 bytes available (RAM) Subtest processes: SKIP (0.092s) Creating 1536 contexts (assuming of size 4194304) Creating 6144 surfaces (of size 1048576) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 6445596672 bytes for the test, but only have 3537895424 bytes available (RAM) Subtest threads: SKIP (0.065s)
Created attachment 115051 [details] dmesg info on bsw "gem_ctx_thrash --run-subtest threads" costs more than 10 minutes on bsw with the latest nightly kernel.I get this dmesg before this case finish.
./gem_close_race --run-subtest gem-close-race also causes oom killer on BDW with the latest drm-intel-fixes kernel.Add i915.enable_ppgtt=0, it works well, add i915.enable_ppgtt=2, it has this issue. root@x-bdw01:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# time ./gem_close_race --run-subtest gem-close-race IGT-Version: 1.10-g2e526ae (x86_64) (Linux: 4.0.0_drm-intel-fixes_39a880_20150414+ x86_64) Connection to x-bdw01 closed.
It was indicated last week that there was potentially a fix for this from the Android tree - is this pending?
It needs 8595701760 bytes(RAM) for the test, it skips. IGT-Version: 1.10-gc4ec47b (x86_64) (Linux: 4.1.0-rc2_drm-intel-nightly_2ead07_20150505+ x86_64) Creating 1536 contexts (assuming of size 4194304) Creating 3072 surfaces (of size 2797568) Test requirement not met in function intel_require_memory, file intel_os.c:244: Test requirement: !(total <= required) Estimated that we need 8595701760 bytes for the test, but only have 3593469952 bytes available (RAM) Subtest processes: SKIP (0.129s)
Mika has a patch to set the estimated allocations correctly for bdw+ (I wrote it based on ilk/snb/ivb contexts).
(In reply to Chris Wilson from comment #22) > Mika has a patch to set the estimated allocations correctly for bdw+ (I > wrote it based on ilk/snb/ivb contexts). I haven't looked at gem_close_race. But for gem_ctx_trash, I have a work in progress patch. For gem_ctx_trash the problem is in the test way underestimating the context size for gen > 8, and then running out of memory. The gem_close_race might have a similar problem, but we should keep the bugs separate.
run ./gem_close_race on SKL, gem-close-race doesn't exit testing. IGT-Version: 1.10-gc4ec47b (x86_64) (Linux: 4.1.0-rc3_drm-intel-nightly_6cf0ff_20150514+ x86_64) Subtest process-exit: SUCCESS (38.968s) ^C^C^C^C real 24m1.225s user 0m1.499s sys 35m35.644s dmesg: [ 288.381353] gem_close_race: starting subtest gem-close-race [ 288.452019] [drm:i915_gem_open] [ 288.494088] [drm:i915_gem_open] [ 288.536087] [drm:i915_gem_open] [ 288.578129] [drm:i915_gem_open] [ 288.620134] [drm:i915_gem_open] ....... [ 1628.873157] [drm:i915_gem_open] [ 1628.917946] [drm:i915_gem_open] [ 1667.277431] [drm:intel_atomic_setup_scalers] crtc_state = ffff880076ea7000 need = 0 avail = 2 scaler_users = 0x0 [ 1667.402148] [drm:skl_detach_scalers] CRTC:20 Disabled scaler id 0.0 [ 1667.479335] [drm:skl_detach_scalers] CRTC:20 Disabled scaler id 0.1 [ 1667.556553] [drm:skl_detach_scalers] CRTC:25 Disabled scaler id 1.0 [ 1667.633751] [drm:skl_detach_scalers] CRTC:25 Disabled scaler id 1.1 [ 1667.711030] [drm:skl_detach_scalers] CRTC:30 Disabled scaler id 2.0 [ 1667.788240] [drm:intel_crtc_set_config] [CRTC:20] [FB:57] #connectors=1 (x y) (0 0) [ 1667.882393] [drm:intel_modeset_stage_output_state] [CONNECTOR:34:eDP-1] to [CRTC:20] [ 1667.977616] [drm:connected_sink_compute_bpp] [CONNECTOR:34:eDP-1] checking for sink bpp constrains [ 1668.087671] [drm:connected_sink_compute_bpp] clamping display bpp (was 36) to default limit of 24 [ 1668.196698] [drm:intel_dp_compute_config] DP link computation with max lane count 4 max bw 540000 pixel clock 361310KHz [ 1668.329039] [drm:intel_dp_compute_config] clamping bpp for eDP panel to BIOS-provided 18 [ 1668.428656] [drm:intel_dp_compute_config] DP link bw 14 lane count 4 clock 540000 bpp 18 [ 1668.528306] [drm:intel_dp_compute_config] DP link bw required 650358 available 1728000 [ 1668.625952] [drm:intel_crtc_compute_config] intel_crtc = ffff88009ba6a000 drm_state (pipe_config->base.state) = ffff8801486ad180 [ 1668.767973] [drm:intel_atomic_setup_scalers] crtc_state = ffff880137984400 need = 0 avail = 2 scaler_users = 0x0 [ 1668.893118] [drm:intel_modeset_pipe_config] plane bpp: 36, pipe bpp: 18, dithering: 1 [ 1668.989785] [drm:intel_dump_pipe_config] [CRTC:20][modeset] config ffff880137984400 for pipe A [ 1669.096015] [drm:intel_dump_pipe_config] cpu_transcoder: D [ 1669.164214] [drm:intel_dump_pipe_config] pipe bpp: 18, dithering: 1 [ 1669.241935] [drm:intel_dump_pipe_config] fdi/pch: 0, lanes: 0, gmch_m: 0, gmch_n: 0, link_m: 0, link_n: 0, tu: 0 [ 1669.367280] [drm:intel_dump_pipe_config] dp: 1, gmch_m: 3157174, gmch_n: 8388608, link_m: 701594, link_n: 1048576, tu: 64 [ 1669.502136] [drm:intel_dump_pipe_config] dp: 1, gmch_m2: 0, gmch_n2: 0, link_m2: 0, link_n2: 0, tu2: 0 [ 1669.617001] [drm:intel_dump_pipe_config] audio: 0, infoframes: 0 [ 1669.691733] [drm:intel_dump_pipe_config] requested mode: [ 1669.758044] [drm:drm_mode_debug_printmodeline] Modeline 0:"3200x1800" 60 361310 3200 3248 3280 3316 1800 1802 1807 1816 0x48 0xa [ 1669.900548] [drm:intel_dump_pipe_config] adjusted mode: [ 1669.965892] [drm:drm_mode_debug_printmodeline] Modeline 0:"3200x1800" 60 361310 3200 3248 3280 3316 1800 1802 1807 1816 0x48 0xa [ 1670.108435] [drm:intel_dump_crtc_timings] crtc timings: 361310 3200 3248 3280 3316 1800 1802 1807 1816, type: 0x48 flags: 0xa [ 1670.247883] [drm:intel_dump_pipe_config] port clock: 540000 [ 1670.317701] [drm:intel_dump_pipe_config] pipe src size: 3200x1800 [ 1670.393809] [drm:intel_dump_pipe_config] num_scalers: 2 [ 1670.459374] [drm:intel_dump_pipe_config] scaler_users: 0x0 [ 1670.528185] [drm:intel_dump_pipe_config] scaler id: -1 [ 1670.592706] [drm:intel_dump_pipe_config] gmch pfit: control: 0x00000000, ratios: 0x00000000, lvds border: 0x00000000 [ 1670.722830] [drm:intel_dump_pipe_config] pch pfit: pos: 0x00000000, size: 0x00000000, disabled [ 1670.829703] [drm:intel_dump_pipe_config] ips: 0 [ 1670.886948] [drm:intel_dump_pipe_config] double wide: 0 [ 1670.952686] [drm:intel_dump_pipe_config] planes on this crtc [ 1671.023702] [drm:intel_dump_pipe_config] STANDARD PLANE:17 plane: 0.0 idx: 0 enabled [ 1671.115755] [drm:intel_dump_pipe_config] FB:57, fb = 3200x1800 format = 0x34325258[ 1671.211210] [drm:intel_dump_pipe_config] scaler:-1 src (0, 0) 3200x1800 dst (0, 0) 3200x1800 [ 1671.317156] [drm:intel_dump_pipe_config] CURSOR PLANE:19 plane: 0.1 idx: 1 disabled, scaler_id = -1 [ 1671.429574] [drm:intel_dump_pipe_config] STANDARD PLANE:21 plane: 0.1 idx: 2 disabled, scaler_id = -1 [ 1671.544110] [drm:intel_dump_pipe_config] STANDARD PLANE:22 plane: 0.2 idx: 3 disabled, scaler_id = -1 [ 1671.658762] [drm:intel_connector_check_state] [CONNECTOR:34:eDP-1] [ 1671.736410] [drm:check_encoder_state] [ENCODER:33:TMDS-33] [ 1671.805562] [drm:check_encoder_state] [ENCODER:42:TMDS-42] [ 1671.874753] [drm:check_encoder_state] [ENCODER:44:DP MST-44] [ 1671.946101] [drm:check_encoder_state] [ENCODER:45:DP MST-45] [ 1672.017434] [drm:check_encoder_state] [ENCODER:46:DP MST-46] [ 1672.088707] [drm:check_encoder_state] [ENCODER:49:TMDS-49] [ 1672.157857] [drm:check_encoder_state] [ENCODER:51:DP MST-51] [ 1672.229202] [drm:check_encoder_state] [ENCODER:52:DP MST-52] [ 1672.300521] [drm:check_encoder_state] [ENCODER:53:DP MST-53] [ 1672.371815] [drm:check_crtc_state] [CRTC:20] [ 1672.426253] [drm:check_crtc_state] [CRTC:25] [ 1672.480667] [drm:check_crtc_state] [CRTC:30] [ 1672.535129] [drm:check_shared_dpll_state] DPLL 1 [ 1672.593775] [drm:check_shared_dpll_state] DPLL 2 [ 1672.652574] [drm:check_shared_dpll_state] DPLL 3 [ 1672.711277] [drm:intel_crtc_set_config] [CRTC:25] [NOFB] [ 1672.778481] [drm:intel_connector_check_state] [CONNECTOR:34:eDP-1] [ 1672.856235] [drm:check_encoder_state] [ENCODER:33:TMDS-33] [ 1672.925551] [drm:check_encoder_state] [ENCODER:42:TMDS-42] [ 1672.994850] [drm:check_encoder_state] [ENCODER:44:DP MST-44] [ 1673.066252] [drm:check_encoder_state] [ENCODER:45:DP MST-45] [ 1673.137697] [drm:check_encoder_state] [ENCODER:46:DP MST-46] [ 1673.209140] [drm:check_encoder_state] [ENCODER:49:TMDS-49] [ 1673.278526] [drm:check_encoder_state] [ENCODER:51:DP MST-51] [ 1673.349984] [drm:check_encoder_state] [ENCODER:52:DP MST-52] [ 1673.421408] [drm:check_encoder_state] [ENCODER:53:DP MST-53] [ 1673.492875] [drm:check_crtc_state] [CRTC:20] [ 1673.547449] [drm:check_crtc_state] [CRTC:25] [ 1673.602026] [drm:check_crtc_state] [CRTC:30] [ 1673.656598] [drm:check_shared_dpll_state] DPLL 1 [ 1673.715456] [drm:check_shared_dpll_state] DPLL 2 [ 1673.774314] [drm:check_shared_dpll_state] DPLL 3 [ 1673.833142] [drm:intel_crtc_set_config] [CRTC:30] [NOFB] [ 1673.900486] [drm:intel_connector_check_state] [CONNECTOR:34:eDP-1] [ 1673.978358] [drm:check_encoder_state] [ENCODER:33:TMDS-33] [ 1674.047878] [drm:check_encoder_state] [ENCODER:42:TMDS-42] [ 1674.117375] [drm:check_encoder_state] [ENCODER:44:DP MST-44] [ 1674.188984] [drm:check_encoder_state] [ENCODER:45:DP MST-45] [ 1674.260604] [drm:check_encoder_state] [ENCODER:46:DP MST-46] [ 1674.332228] [drm:check_encoder_state] [ENCODER:49:TMDS-49] [ 1674.401742] [drm:check_encoder_state] [ENCODER:51:DP MST-51] [ 1674.473304] [drm:check_encoder_state] [ENCODER:52:DP MST-52] [ 1674.544897] [drm:check_encoder_state] [ENCODER:53:DP MST-53] [ 1674.616493] [drm:check_crtc_state] [CRTC:20] [ 1674.671105] [drm:check_crtc_state] [CRTC:25] [ 1674.725799] [drm:check_crtc_state] [CRTC:30] [ 1674.780481] [drm:check_shared_dpll_state] DPLL 1 [ 1674.839405] [drm:check_shared_dpll_state] DPLL 2 [ 1674.898318] [drm:check_shared_dpll_state] DPLL 3
Created attachment 117673 [details] BDW-U dmesg log
Should be fixed with commit e9f24d5fb7cf3628b195b18ff3ac4e37937ceeae.
(In reply to Tvrtko Ursulin from comment #26) > Should be fixed with commit e9f24d5fb7cf3628b195b18ff3ac4e37937ceeae. RESOLVED FIXED then. Christophe, please verify.
Confirmed, this issue is not present anymore on BDW Kernel: 4.5.0-rc5-nightly
Issue is not present any more on BSW. Software Configuration ================================================ Linux distribution: Ubuntu 15.10 64 bits Kernel: drm-intel-nightly 4.6.0-rc3_d9131d6 from http://cgit.freedesktop.org/drm-intel/ commit d9131d62d18ba94fb3ca019f1156c22b5f4ce23c Author: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Date: Fri Apr 15 14:54:26 2016 +0100 drm-intel-nightly: 2016y-04m-15d-13h-53m-44s UTC integration manifestdrm: tag libdrm-2.4.66-33-gf884af9 libdrm 2.4.67-25 cc9a53f from git://git.freedesktop.org/git/mesa/drm mesa 11.1.2 7bcd827 from git://git.freedesktop.org/git/mesa/mesa cairo 1.15.2 db8a7f1 from git://git.freedesktop.org/git/cairo xorg/xserver 1.18.0-274 8437955 from git://git.freedesktop.org/git/xorg/xserver xf86-video-intel 2.99.917-634 81029be from git://git.freedesktop.org/git/xorg/driver/xf86-video-intel vaapi/libva 1.7.0-1 2339d10 from git://git.freedesktop.org/git/vaapi/libva vaapi/intel-driver 1.7.0-8 2c1bec0 from git://git.freedesktop.org/git/vaapi/intel-driver intel-gpu-tool 1.14 7bd2ac6 from http://anongit.freedesktop.org/git/xorg/app/intel-gpu-tools.git rendercheck master 44032a7 from http://anongit.freedesktop.org/git/xorg/app/rendercheck.git
All subtests are Pass on BDW, BSW and SKL. No OOM killer. # ./gem_close_race IGT-Version: 1.16-g48a9e1e (x86_64) (Linux: 4.8.0-nightly+ x86_64) Subtest basic-process: SUCCESS (0.001s) Subtest basic-threads: SUCCESS (10.744s) Subtest process-exit: SUCCESS (1.192s) Subtest gem-close-race: SUCCESS (161.070s) Platform SKL Skull Canyon: NUC6i7KYK CPU: Intel® Core(TM) i7-6770HQ CPU @ 2.6GHz (family 6, model 94, stepping 3) GPU: Intel® IrisTM Pro Graphics 580 - Intel Corporation Sky Lake Integrated Graphics (rev 09) Motherboard version: H90766-405 Memory: 2 x 4GB card Kingston KVR21S15S8/4 Software Bios: KYSKLi70.86A.0041.2016.0817.1130 from https://downloadcenter.intel.com/downloads/eula/26210/BIOS-Update-KYSKLi70-86A-?httpDown=https%3A%2F%2Fdownloadmirror.intel.com%2F26210%2Feng%2FKY0041.bio Linux distribution: Ubuntu 16.04 64 bits DMC 1.26 from https://01.org/sites/default/files/downloads/intelr-graphics-linux/skldmcver126.tar_1.bz2 GUC 6.1 from https://01.org/sites/default/files/downloads/intelr-graphics-linux/sklgucver61.tar.bz2 External screens: ASUS PB287Q (DP), DELL P2715Qt (HDMI) Hardware BSW: Acer Desktop Motherboard: Aspire XC-704 CPU: Intel(R) Pentium(R) CPU N3700 @ 1.60GHz (Family 6, Model 76, Stepping 3) GPU: Intel® HD Graphics - Intel Corporation Device 22b1 (rev 21) Memory card: 1 card 4GB Hynix HMT451S6BFR8APB HDD: Western Digital WDC WD10EZEX-21M (1TB) Software: Bios: R01-A2 Linux distribution: Ubuntu 16.04 64 bits Platform BDW: NUC5i3RYB CPU: Intel(R) Core(TM) i3-5010U CPU @ 2.10GHz (family 6, model 61, stepping 4) Motherboard version: H41000-503 GPU: Intel® HD Graphics 5500 - Intel Corporation Broadwell-U Integrated Graphics (rev 09) Memory: two 4GB card Crucial CT51264BF160B.C16F SSD: INTEL SSDSC2BW48 480 Go Software Bios: RYBDWi35.86A.0358.2016.0606.1423 from https://downloadcenter.intel.com/downloads/eula/26081/BIOS-Update-RYBDWi35-86A-?httpDown=https%3A%2F%2Fdownloadmirror.intel.com%2F26081%2Feng%2FRY0358.bio Linux distribution: Ubuntu 16.04 64 bits External screen: DELL U2311Hb Kernel: 4.8.0 f35ed31 from http://cgit.freedesktop.org/drm-intel/ commit f35ed31aea66b3230c366fcba5f3456ae2cb956e Author: Jani Nikula <jani.nikula@intel.com> Date: Mon Oct 10 14:29:09 2016 +0300 drm-intel-nightly: 2016y-10m-10d-11h-28m-51s UTC integration manifest libdrm-2.4.71 a44c9c3 from git://anongit.freedesktop.org/mesa/drm mesa: mesa-12.0.0 8b06176 from git://anongit.freedesktop.org/mesa/mesa cairo 1.15.2 db8a7f1 from git://anongit.freedesktop.org/cairo xorg-server-1.18.99.901-76 97a8353 from git://git.freedesktop.org/git/xorg/xserver xf86-video-intel 2.99.917-712 696f58f from git://git.freedesktop.org/git/xorg/driver/xf86-video-intel libva-1.7.2-38 3b7e499 from git://git.freedesktop.org/git/vaapi/libva vaapi-intel-driver: 1.7.2-133 dd73514 from git://git.freedesktop.org/git/vaapi/intel-driver IGT: intel-gpu-tools-1.16-59 48a9e1e from http://anongit.freedesktop.org/git/xorg/app/intel-gpu-tools.git
So closed
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.