So don't return -EAGAIN, even in the case of a gpu hang. Remap it to -EIO instead. This is a bit ugly because intel_ring_begin is all non-interruptible and hence only returns -EIO. But as the comment in there says, auditing all the callsites would be a pain. To avoid duplicating code, reuse i915_gem_check_wedge in __wait_seqno. Use the opportunity to clarify the different cases a bit with comments. Signed-Off-by: Daniel Vetter <daniel.vetter at ffwll.ch> --- drivers/gpu/drm/i915/i915_gem.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 1214850..32b4db3 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1878,7 +1878,16 @@ i915_gem_check_wedge(struct drm_i915_private *dev_priv) recovery_complete = x->done > 0; spin_unlock_irqrestore(&x->wait.lock, flags); - return recovery_complete ? -EIO : -EAGAIN; + /* Non-interruptible callers can't handle -EAGAIN, hence return + * -EIO unconditionally for these. */ + if (!dev_priv->mm.interruptible) + return -EIO; + + /* Recovery complete, but still wedged means reset failure. */ + if (recovery_complete) + return -EIO; + + return -EAGAIN; } return 0; @@ -1932,6 +1941,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, unsigned long timeout_jiffies; long end; bool wait_forever = true; + int ret; if (i915_seqno_passed(ring->get_seqno(ring), seqno)) return 0; @@ -1963,8 +1973,9 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, end = wait_event_timeout(ring->irq_queue, EXIT_COND, timeout_jiffies); - if (atomic_read(&dev_priv->mm.wedged)) - end = -EAGAIN; + ret = i915_gem_check_wedge(dev_priv); + if (ret) + end = ret; } while (end == 0 && wait_forever); getrawmonotonic(&now); -- 1.7.10
