[Intel-gfx] [PATCH] drm/i915: Check we have an wake device before flushing GTT writes

Chris Wilson chris at chris-wilson.co.uk
Mon Mar 27 12:25:04 UTC 2017


On Mon, Mar 27, 2017 at 01:29:18PM +0300, Joonas Lahtinen wrote:
> On to, 2017-03-23 at 15:00 +0000, Chris Wilson wrote:
> > We can assume that if the device is asleep then all pending GTT writes
> > will have been posted, and so we can defer the flush from
> > i915_gem_object_flush_gtt_write_domain()
> > 
> > [ 1957.462568] WARNING: CPU: 0 PID: 6132 at drivers/gpu/drm/i915/intel_drv.h:1742 fwtable_read32+0x123/0x150 [i915]
> > [ 1957.462582] RPM wakelock ref not held during HW access
> > [ 1957.462583] Modules linked in: i915 intel_gtt drm_kms_helper prime_numbers
> > [ 1957.462607] CPU: 0 PID: 6132 Comm: gem_concurrent_ Tainted: G     U          4.11.0-rc1+ #464
> > [ 1957.462619] Hardware name:                  /        , BIOS PYBSWCEL.86A.0027.2015.0507.1758 05/07/2015
> > [ 1957.462630] Call Trace:
> > [ 1957.462646]  dump_stack+0x4d/0x6f
> > [ 1957.462657]  __warn+0xc1/0xe0
> > [ 1957.462667]  warn_slowpath_fmt+0x4a/0x50
> > [ 1957.462709]  fwtable_read32+0x123/0x150 [i915]
> > [ 1957.462750]  i915_gem_object_flush_gtt_write_domain+0x43/0x70 [i915]
> > [ 1957.462791]  i915_gem_object_set_to_cpu_domain+0x46/0xa0 [i915]
> > [ 1957.462831]  i915_gem_set_domain_ioctl+0x15d/0x220 [i915]
> > [ 1957.462843]  drm_ioctl+0x1d7/0x440
> > [ 1957.462885]  ? i915_gem_obj_prepare_shmem_write+0x1d0/0x1d0 [i915]
> > [ 1957.462896]  ? pick_next_task_fair+0x436/0x440
> > [ 1957.462906]  ? mntput+0x1f/0x30
> > [ 1957.462915]  do_vfs_ioctl+0x8f/0x5c0
> > [ 1957.462925]  ? __schedule+0x16f/0x5f0
> > [ 1957.462935]  ? ____fput+0x9/0x10
> > [ 1957.462943]  SyS_ioctl+0x3c/0x70
> > [ 1957.462952]  entry_SYSCALL_64_fastpath+0x17/0x98
> > [ 1957.462961] RIP: 0033:0x7fc542179ca7
> > [ 1957.462968] RSP: 002b:00007ffeef12ff98 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
> > [ 1957.462982] RAX: ffffffffffffffda RBX: 00007ffeef1301d0 RCX: 00007fc542179ca7
> > [ 1957.462990] RDX: 00007ffeef12ffd0 RSI: 00000000400c645f RDI: 0000000000000003
> > [ 1957.462999] RBP: 0000000000000003 R08: 000055f433bc7c40 R09: 000000000000002c
> > [ 1957.463006] R10: 0000000000000073 R11: 0000000000000246 R12: 0000000000000018
> > [ 1957.463015] R13: 000055f432c89d20 R14: 000055f432c87690 R15: 0000000000000000
> > 
> > Fixes: 3b5724d702ef ("drm/i915: Wait for writes through the GTT to land before reading back")
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> > Cc: <stable at vger.kernel.org> # v4.9
> 
> Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>

Ta, one less warning (not yet seen by CI, come on CI stop slacking)!
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre


More information about the Intel-gfx mailing list