Chris Wilson <[email protected]> writes: > If we detect a hang in a closed context, just flush all of its requests > and cancel any remaining execution along the context. Note that after > closing the context, the last reference to the context may be dropped, > leaving it only valid under RCU.
Sound good. But is there a window for userspace to start to see -EIO if it resubmits to a closed context? In other words, after userspace doing gem_ctx_destroy(ctx_handle), we would return -EINVAL due to ctx_handle being stale earlier than we check for banned status and return -EIO? -Mika > > Signed-off-by: Chris Wilson <[email protected]> > --- > drivers/gpu/drm/i915/gt/intel_reset.c | 7 +++++++ > 1 file changed, 7 insertions(+) > > diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c > b/drivers/gpu/drm/i915/gt/intel_reset.c > index f03e000051c1..a6b0d00c3a51 100644 > --- a/drivers/gpu/drm/i915/gt/intel_reset.c > +++ b/drivers/gpu/drm/i915/gt/intel_reset.c > @@ -81,6 +81,11 @@ static bool context_mark_guilty(struct i915_gem_context > *ctx) > bool banned; > int i; > > + if (i915_gem_context_is_closed(ctx)) { > + i915_gem_context_set_banned(ctx); > + return true; > + } > + > atomic_inc(&ctx->guilty_count); > > /* Cool contexts are too cool to be banned! (Used for reset testing.) */ > @@ -124,6 +129,7 @@ void __i915_request_reset(struct i915_request *rq, bool > guilty) > > GEM_BUG_ON(i915_request_completed(rq)); > > + rcu_read_lock(); /* protect the GEM context */ > if (guilty) { > i915_request_skip(rq, -EIO); > if (context_mark_guilty(rq->gem_context)) > @@ -132,6 +138,7 @@ void __i915_request_reset(struct i915_request *rq, bool > guilty) > dma_fence_set_error(&rq->fence, -EAGAIN); > context_mark_innocent(rq->gem_context); > } > + rcu_read_unlock(); > } > > static bool i915_in_reset(struct pci_dev *pdev) > -- > 2.24.0 > > _______________________________________________ > Intel-gfx mailing list > [email protected] > https://lists.freedesktop.org/mailman/listinfo/intel-gfx _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
