On Thu, 18 May 2017, Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> wrote:
> Due to the complex dependencies between workqueues and RCU, which
> are not easily detected by lockdep, do not synchronize RCU during
> shrinking.
>
> On low-on-memory systems (mem=1G for example), the RCU sync leads
> to all system workqueus freezing and unrelated lockdep splats are
> displayed according to reports. GIT bisecting done by J. R.
> Okajima points to the commit where RCU syncing was extended.
>
> RCU sync gains us very little benefit in real life scenarios
> where the amount of memory used by object backing storage is
> dominant over the metadata under RCU, so drop it altogether.
>
> " Yeeeaah, if core could just, go ahead and reclaim RCU
> queues, that'd be great. "
>
> - Chris Wilson, 2016 (0eafec6d3244)
>
> v2: More information to commit message.
> v3: Remove "grep _rcu_" escapee from i915_gem_shrink_all (Andrea)
>
> Fixes: c053b5a506d3 ("drm/i915: Don't call synchronize_rcu_expedited under struct_mutex")
> Suggested-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> Reported-by: J. R. Okajima <hooanon05g@xxxxxxxxx>
> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
> Reviewed-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> Tested-by: Hugh Dickins <hughd@xxxxxxxxxx>
> Tested-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
> Cc: J. R. Okajima <hooanon05g@xxxxxxxxx>
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Jani Nikula <jani.nikula@xxxxxxxxx>
> Cc: <stable@xxxxxxxxxxxxxxx> # v4.11+
Pushed to drm-intel-fixes, thanks for the patch.
BR,
Jani.
> ---
> drivers/gpu/drm/i915/i915_gem_shrinker.c | 5 -----
> 1 file changed, 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
> index 129ed30..57d9f7f 100644
> --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
> +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
> @@ -59,9 +59,6 @@ static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock)
> return;
>
> mutex_unlock(&dev->struct_mutex);
> -
> - /* expedite the RCU grace period to free some request slabs */
> - synchronize_rcu_expedited();
> }
>
> static bool any_vma_pinned(struct drm_i915_gem_object *obj)
> @@ -274,8 +271,6 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
> I915_SHRINK_ACTIVE);
> intel_runtime_pm_put(dev_priv);
>
> - synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */
> -
> return freed;
> }
--
Jani Nikula, Intel Open Source Technology Center