On Tue, Apr 28, 2015 at 05:56:17PM +0300, Mika Kuoppala wrote: > When we have bound vma into an address space, the layout > of page table structures is immutable. So we can be absolutely > certain that if vma is already bound, there is no need to > (re)allocate a virtual address range for it. > > v2: - add sanity checks and remove superfluous GLOBAL_BIND set > - we might do update for an unbound vma (Chris) > > Testcase: igt/gem_exec_big #bdw > Reported-by: Chris Wilson <[email protected]> > Cc: Chris Wilson <[email protected]> > Cc: Michel Thierry <[email protected]> > Cc: Daniel Vetter <[email protected]> > Signed-off-by: Mika Kuoppala <[email protected]> > --- > drivers/gpu/drm/i915/i915_gem_gtt.c | 39 > +++++++++++++++++++++---------------- > 1 file changed, 22 insertions(+), 17 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c > b/drivers/gpu/drm/i915/i915_gem_gtt.c > index 6fae6bd..9d3852c 100644 > --- a/drivers/gpu/drm/i915/i915_gem_gtt.c > +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c > @@ -1928,8 +1928,6 @@ static int ggtt_bind_vma(struct i915_vma *vma, > vma->vm->insert_entries(vma->vm, pages, > vma->node.start, > cache_level, pte_flags); > - > - vma->bound |= GLOBAL_BIND; > } > > if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) { > @@ -2804,21 +2802,13 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma) > int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, > u32 flags) > { > - int ret = 0; > - u32 bind_flags = 0; > - > - if (vma->vm->allocate_va_range) { > - trace_i915_va_alloc(vma->vm, vma->node.start, > - vma->node.size, > - VM_TO_TRACE_NAME(vma->vm)); > + int ret; > + u32 bind_flags;
Whilst you are here, can you fix this to be plain unsigned. Reviewed-by: Chris Wilson <[email protected]> -Chris -- Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
