There is an unlikely corner case whereby a lockless wait may not notice
a GPU hang and reset, and so continue to wait for the device to advance
beyond the chosen seqno. This of course may never happen as the waiter
may be the only user. Instead, we can explicitly advance the device
seqno to match the requests that are forcibly retired following the
hang.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_gem.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 84ee1f2..b3c8abd 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2118,8 +2118,11 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request)
}
static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
- struct intel_ring_buffer *ring)
+ struct intel_ring_buffer *ring,
+ u32 seqno)
{
+ int i;
+
while (!list_empty(&ring->request_list)) {
struct drm_i915_gem_request *request;
@@ -2139,6 +2142,10 @@ static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
i915_gem_object_move_to_inactive(obj);
}
+
+ intel_ring_init_seqno(ring, seqno);
+ for (i = 0; i < ARRAY_SIZE(ring->sync_seqno); i++)
+ ring->sync_seqno[i] = 0;
}
static void i915_gem_reset_fences(struct drm_device *dev)
@@ -2167,10 +2174,14 @@ void i915_gem_reset(struct drm_device *dev)
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj;
struct intel_ring_buffer *ring;
+ u32 seqno;
int i;
+ if (i915_gem_get_seqno(dev, &seqno))
+ seqno = dev_priv->next_seqno - 1;
+
for_each_ring(ring, dev_priv, i)
- i915_gem_reset_ring_lists(dev_priv, ring);
+ i915_gem_reset_ring_lists(dev_priv, ring, seqno);
/* Move everything out of the GPU domains to ensure we do any
* necessary invalidation upon reuse.
--
1.7.10.4
