[Intel-gfx] [PATCH 16/21] drm/i915/gtt: Pin vma during virtual address allocation

[Michel Thierry]

On 5/22/2015 6:05 PM, Mika Kuoppala wrote:
> Dynamic page table allocation might wake the shrinker
> when memory is requested for page table structures.
> As this happens when we try to allocate the virtual address
> during binding, our vma might be among the targets for eviction.
> We should do i915_vma_pin() and do pin early in there like Chris
> suggests but this is interim solution.
>
> Shield our vma from shrinker by incrementing pin count before
> the virtual address is allocated.
>
> The proper place to fix this would be in gem, inside of
> i915_vma_pin(). But we don't have that yet so take the short
> cut as a intermediate solution.
>
> Testcase: igt/gem_ctx_thrash
> Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
Reviewed-by: Michel Thierry <michel.thierry at intel.com>
> ---
>   drivers/gpu/drm/i915/i915_gem_gtt.c | 3 +++
>   1 file changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index a2a0c88..b938964 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -2916,9 +2916,12 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
>                                      vma->node.size,
>                                      VM_TO_TRACE_NAME(vma->vm));
>
> +               /* XXX: i915_vma_pin() will fix this +- hack */
> +               vma->pin_count++;
>                  ret = vma->vm->allocate_va_range(vma->vm,
>                                                   vma->node.start,
>                                                   vma->node.size);
> +               vma->pin_count--;
>                  if (ret)
>                          return ret;
>          }
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx