[Intel-gfx] [PATCH 2/2] intel_gpu_top: Add param to force ring reads for busyness

2016-02-21 Thread Ben Widawsky
Signed-off-by: Ben Widawsky --- man/intel_gpu_top.man | 3 +++ tools/intel_gpu_top.c | 25 + 2 files changed, 20 insertions(+), 8 deletions(-) diff --git a/man/intel_gpu_top.man b/man/intel_gpu_top.man index d90a7ee..be0f1be 100644 --- a/man/intel_gpu_top.man +++ b/man/i

[Intel-gfx] [PATCH 1/2] intel_gpu_top: Skip head/tail reads on HSW

2016-02-21 Thread Ben Widawsky
Haswell has a known issue when doing concurrent reads of MMIO (see reference for details). This issue results in a system wide unrecoverable hang. As this tool is shipped by default in the IGT package, this is a very mean behavior to accidentally impose on the user. This patch shuts this behavior

[Intel-gfx] 4.1.4 / skylake / /usr/lib/x86_64-linux-gnu/dri/i965_drv_video.so init failed

2016-02-21 Thread Marc MERLIN
I'm testing a new thinkpad skylake based P70 with dual graphics legolas:~# lspci | grep VGA 00:02.0 VGA compatible controller: Intel Corporation Device 191b (rev 06) 01:00.0 VGA compatible controller: NVIDIA Corporation GM107GLM [Quadro M600M] (rev a2) LIBVA_DRIVER_NAME=i965 VA_INTEL_DEBUG=1 vai

Re: [Intel-gfx] 4.1.4 / skylake / /usr/lib/x86_64-linux-gnu/dri/i965_drv_video.so init failed

2016-02-21 Thread Marc MERLIN
On Sun, Feb 21, 2016 at 09:12:07AM -0800, Marc MERLIN wrote: > I'm testing a new thinkpad skylake based P70 with dual graphics > legolas:~# lspci | grep VGA > 00:02.0 VGA compatible controller: Intel Corporation Device 191b (rev 06) > 01:00.0 VGA compatible controller: NVIDIA Corporation GM107GLM [