[Intel-gfx] [PATCH] drm/i915: Handle recursive shrinker for vma->last_active allocation

[Tvrtko Ursulin]

On 19/07/2018 08:22, Chris Wilson wrote:
> If we call into the shrinker for direct relcaim inside kmalloc, it will
> retire the requests. If we retire the vma->last_active while a new
> i915_vma_move_to_active() we can upset the delicate bookkeeping required
> for the cache. After the possible invocation of the shrinker, we need to
> double check the vma->last_active is still valid.
> 
> Fixes: 8b293eb53a7d ("drm/i915: Track the last-active inside the i915_vma")
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> ---
>   drivers/gpu/drm/i915/i915_vma.c | 8 ++++++++
>   1 file changed, 8 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
> index ed4e0fb558f7..11d834f94220 100644
> --- a/drivers/gpu/drm/i915/i915_vma.c
> +++ b/drivers/gpu/drm/i915/i915_vma.c
> @@ -942,6 +942,14 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
>   	}
>   
>   	active = kmalloc(sizeof(*active), GFP_KERNEL);
> +
> +	/* kmalloc may retire the vma->last_active request (thanks shrinker)! */
> +	if (unlikely(!i915_gem_active_raw(&vma->last_active,
> +					  &vma->vm->i915->drm.struct_mutex))) {
> +		kfree(active);
> +		goto out;
> +	}
> +
>   	if (unlikely(!active))
>   		return ERR_PTR(-ENOMEM);
>   
> 

Fun!

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Regards,

Tvrtko