Now, i915_gem_inactive_shrink() should return -1 instead of 0 if it can't take a lock. Otherwise, vmscan is getting a lot of confusing because vmscan can't distinguish "can't take a lock temporary" and "we've shrank all of i915 objects".
Signed-off-by: KOSAKI Motohiro kosaki.motohiro@jp.fujitsu.com Cc: Keith Packard keithp@keithp.com Cc: David Airlie airlied@linux.ie Cc: dri-devel@lists.freedesktop.org ---
I've found this issue by reviewing. I hope i915 developers confirm this. Thx.
drivers/gpu/drm/i915/i915_gem.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 94c84d7..2f9a9b2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -4104,7 +4104,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) int cnt;
if (!mutex_trylock(&dev->struct_mutex)) - return 0; + return nr_to_scan ? -1 : 0;
/* "fast-path" to count number of available objects */ if (nr_to_scan == 0) {