[Intel-gfx] [PATCH] drm/i915: Flush the change in debugobject before reallocation

Joonas Lahtinen joonas.lahtinen at linux.intel.com
Mon Jan 16 11:55:42 UTC 2017


On pe, 2017-01-13 at 21:43 +0000, Chris Wilson wrote:
> When marking the debugobject as freed, be sure that write is flushed
> before another CPU may see it on a reallocation path.
> 
> Only seen once in CI:
> 
> [  159.240873] WARNING: CPU: 3 PID: 6735 at lib/debugobjects.c:263 debug_print_object+0x87/0xb0
> [  159.240897] ODEBUG: init destroyed (active state 0) object type: i915_sw_fence hint: submit_notify+0x0/0x4c [i915]
> [  159.240902] Modules linked in: snd_hda_intel i915 x86_pkg_temp_thermal intel_powerclamp coretemp crct10dif_pclmul snd_hda_codec_realtek crc32_pclmul snd_hda_codec_generic snd_hda_codec_hdmi ghash_clmulni_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm mei_me lpc_ich mei e1000e ptp pps_core [last unloaded: i915]
> [  159.240913] CPU: 3 PID: 6735 Comm: gem_exec_nop Tainted: G     U          4.10.0-rc3-CI-Trybot_479+ #1
> [  159.240913] Hardware name: LENOVO 10AGS00601/SHARKBAY, BIOS FBKT34AUS 04/24/2013
> [  159.240914] Call Trace:
> [  159.240916]  dump_stack+0x67/0x92
> [  159.240919]  __warn+0xc6/0xe0
> [  159.240920]  warn_slowpath_fmt+0x4a/0x50
> [  159.240921]  debug_print_object+0x87/0xb0
> [  159.240935]  ? __i915_request_wait_for_execute+0x1d0/0x1d0 [i915]
> [  159.240936]  __debug_object_init+0xb2/0x410
> [  159.240950]  ? __i915_request_wait_for_execute+0x1d0/0x1d0 [i915]
> [  159.240951]  debug_object_init+0x16/0x20
> [  159.240962]  __i915_sw_fence_init+0x29/0x60 [i915]
> [  159.240975]  i915_gem_request_alloc+0x1fb/0x450 [i915]
> [  159.240987]  i915_gem_do_execbuffer.isra.15+0x798/0x1b20 [i915]
> [  159.241000]  i915_gem_execbuffer2+0xc0/0x250 [i915]
> [  159.241003]  drm_ioctl+0x200/0x450
> [  159.241016]  ? i915_gem_execbuffer+0x330/0x330 [i915]
> [  159.241018]  do_vfs_ioctl+0x90/0x6e0
> [  159.241020]  ? trace_hardirqs_on_caller+0x122/0x1b0
> [  159.241021]  SyS_ioctl+0x3c/0x70
> [  159.241023]  entry_SYSCALL_64_fastpath+0x1c/0xb1
> [  159.241024] RIP: 0033:0x7f9bc4f41357
> [  159.241025] RSP: 002b:00007ffc6cd5c568 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
> [  159.241026] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bc4f41357
> [  159.241026] RDX: 00007ffc6cd5c640 RSI: 0000000040406469 RDI: 0000000000000003
> [  159.241027] RBP: 00007ffc6cd5c640 R08: 0000000000047508 R09: 0000000000000001
> [  159.241027] R10: 000b58552d323c3d R11: 0000000000000246 R12: 0000000040406469
> [  159.241028] R13: 0000000000000003 R14: 0000000000000004 R15: 0000000000000001
> 
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>

Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation


More information about the Intel-gfx mailing list