[Beignet] runtime_alloc_host_ptr_buffer intermittent failure

[Rebecca N. Palmer]

The dmesg output from a failure is:

[  427.521907] [drm:drm_ioctl] pid=776, dev=0xe200, auth=1, 
I915_GEM_THROTTLE
[  427.533899] [drm:drm_ioctl] pid=2340, dev=0xe200, auth=1, 
I915_GEM_MADVISE
[  427.533905] [drm:drm_ioctl] pid=2340, dev=0xe200, auth=1, I915_GEM_PWRITE
[  427.533916] [drm:drm_ioctl] pid=2340, dev=0xe200, auth=1, 
I915_GEM_USERPTR
[  427.533939] [drm:drm_ioctl] ret = -22
[  427.533950] [drm:drm_ioctl] pid=2340, dev=0xe200, auth=1, 
I915_GEM_USERPTR
[  427.533952] [drm:drm_ioctl] ret = -1
[  427.536096] [drm:drm_ioctl] pid=776, dev=0xe200, auth=1, 
I915_GEM_THROTTLE
[  427.538128] [drm:drm_calc_vbltimestamp_from_scanoutpos] crtc 0 : v 7 
p(0,-22)@ 427.251356 -> 427.251820 [e 0 us, 0 rep]

I haven't specifically checked for running out of memory but it seems 
unlikely: in repeated runs the first is the most likely to fail, and it 
doesn't cause system hangs/slowdowns.

The Debian experimental kernel (3.18) doesn't appear to have this 
problem, so it may well be a kernel bug that has already been fixed.

Both it and the 3.16 kernel have a different intermittent failure I have 
yet to investigate:

compiler_fill_image_1d_array()    [FAILED]
     Error: dst[j*w + i] == 0
   at file 
/home/rnpalmer/Debian/builds/stackbuild/beignet/utests/compiler_fill_image_1d_array.cpp, 
function compiler_fill_image_1d_array, line 63