diff options
| author | Zhi Wang <zhi.a.wang@intel.com> | 2017-09-10 22:01:10 +0800 |
|---|---|---|
| committer | Zhenyu Wang <zhenyuw@linux.intel.com> | 2017-11-16 11:46:51 +0800 |
| commit | 8652a8aca614cc2576cf5d4c73d3b87e871ce004 (patch) | |
| tree | b4633f1e115f3d4312a84caba3c03194dd489a79 /drivers/gpu/drm/i915/gvt/gvt.h | |
| parent | 325eb94a33451db138e8da7393ad8e9a0e22dd18 (diff) | |
| download | talos-op-linux-8652a8aca614cc2576cf5d4c73d3b87e871ce004.tar.gz talos-op-linux-8652a8aca614cc2576cf5d4c73d3b87e871ce004.zip | |
drm/i915/gvt: Do not allocate initial ring scan buffer
Theoretically, the largest bulk of commands in the ring buffer of an
engine might be the first submission, which usually contains a lot
of commands to initialize the HW. After removing the initial allocation
of the ring scan buffer and let krealloc() do everything we need, we
still have a big chance to get the buffer of suitable size in the first
submission.
Tested on my SKL NUC.
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915/gvt/gvt.h')
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/gvt.h | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 49fe54870000..7a770b1c99d6 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -150,7 +150,6 @@ struct intel_vgpu_submission { struct i915_gem_context *shadow_ctx; DECLARE_BITMAP(shadow_ctx_desc_updated, I915_NUM_ENGINES); DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES); - /* 1/2K for each engine */ void *ring_scan_buffer[I915_NUM_ENGINES]; int ring_scan_buffer_size[I915_NUM_ENGINES]; }; |
