From fccebc8d1540402a8e0f6acf97f56bec0252c647 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Nov 2019 11:43:23 +0000
Subject: drm/i915: Cancel context if it hangs after it is closed
Git-commit: e8887bb3eb6f55401e0d0f9ee5739e5baca4a58c
Patch-mainline: v5.6-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322
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
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
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 1eb1fb039e7c..0388f9375366 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.) */
@@ -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)
--
2.28.0