drm/i915: Cancel context if it hangs after it is closed

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.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191111114323.5833-5-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 86d52383bf9d1415bd6e0b295cc43a3bc35878ef..b7007cd78c6f0c419104fd6be8db721bf1de4507 100644 (file)
--- 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.) */
@@ -128,6 +133,7 @@ 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))
@@ -136,6 +142,7 @@ 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)