Sometimes it may be the case when we idle the gpu or wait on something
we don't actually want to process the retiring list. This patch allows
callers to choose the behavior.
Reviewed-by: Keith Packard <keithp at keithp.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov at intel.com>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/i915/i915_dma.c | 2 +-
drivers/gpu/drm/i915/i915_drv.h | 5 ++-
drivers/gpu/drm/i915/i915_gem.c | 30 +++++++++++++++------------
drivers/gpu/drm/i915/i915_gem_evict.c | 2 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
drivers/gpu/drm/i915/intel_overlay.c | 6 +++-
7 files changed, 28 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 8122738..3f27173 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2131,7 +2131,7 @@ int i915_driver_unload(struct drm_device *dev)
unregister_shrinker(&dev_priv->mm.inactive_shrinker);
mutex_lock(&dev->struct_mutex);
- ret = i915_gpu_idle(dev);
+ ret = i915_gpu_idle(dev, true);
if (ret)
DRM_ERROR("failed to idle hardware: %d\n", ret);
mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f02a5f5..1d10b8c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1179,13 +1179,14 @@ void i915_gem_do_init(struct drm_device *dev,
unsigned long start,
unsigned long mappable_end,
unsigned long end);
-int __must_check i915_gpu_idle(struct drm_device *dev);
+int __must_check i915_gpu_idle(struct drm_device *dev, bool do_retire);
int __must_check i915_gem_idle(struct drm_device *dev);
int __must_check i915_add_request(struct intel_ring_buffer *ring,
struct drm_file *file,
struct drm_i915_gem_request *request);
int __must_check i915_wait_request(struct intel_ring_buffer *ring,
- uint32_t seqno);
+ uint32_t seqno,
+ bool do_retire);
int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
int __must_check
i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eb98a7f..5b63c56 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1942,8 +1942,9 @@ i915_gem_retire_work_handler(struct work_struct *work)
* request and object lists appropriately for that event.
*/
int
-i915_wait_request(struct intel_ring_buffer *ring,
- uint32_t seqno)
+i915_gem_wait_request(struct intel_ring_buffer *ring,
+ uint32_t seqno,
+ bool do_retire)
{
drm_i915_private_t *dev_priv = ring->dev->dev_private;
u32 ier;
@@ -2027,7 +2028,7 @@ i915_wait_request(struct intel_ring_buffer *ring,
* buffer to have made it to the inactive list, and we would need
* a separate wait queue to handle that.
*/
- if (ret == 0)
+ if (ret == 0 && do_retire)
i915_gem_retire_requests_ring(ring);
return ret;
@@ -2051,7 +2052,8 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj)
* it.
*/
if (obj->active) {
- ret = i915_wait_request(obj->ring, obj->last_rendering_seqno);
+ ret = i915_wait_request(obj->ring, obj->last_rendering_seqno,
+ true);
if (ret)
return ret;
}
@@ -2172,7 +2174,7 @@ i915_gem_flush_ring(struct intel_ring_buffer *ring,
return 0;
}
-static int i915_ring_idle(struct intel_ring_buffer *ring)
+static int i915_ring_idle(struct intel_ring_buffer *ring, bool do_retire)
{
int ret;
@@ -2186,18 +2188,18 @@ static int i915_ring_idle(struct intel_ring_buffer *ring)
return ret;
}
- return i915_wait_request(ring, i915_gem_next_request_seqno(ring));
+ return i915_gem_wait_request(ring, i915_gem_next_request_seqno(ring),
+ do_retire);
}
-int
-i915_gpu_idle(struct drm_device *dev)
+int i915_gpu_idle(struct drm_device *dev, bool do_retire)
{
drm_i915_private_t *dev_priv = dev->dev_private;
int ret, i;
/* Flush everything onto the inactive list. */
for (i = 0; i < I915_NUM_RINGS; i++) {
- ret = i915_ring_idle(&dev_priv->ring[i]);
+ ret = i915_ring_idle(&dev_priv->ring[i], do_retire);
if (ret)
return ret;
}
@@ -2400,7 +2402,8 @@ i915_gem_object_flush_fence(struct drm_i915_gem_object *obj,
if (!ring_passed_seqno(obj->last_fenced_ring,
obj->last_fenced_seqno)) {
ret = i915_wait_request(obj->last_fenced_ring,
- obj->last_fenced_seqno);
+ obj->last_fenced_seqno,
+ true);
if (ret)
return ret;
}
@@ -2541,7 +2544,8 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj,
if (!ring_passed_seqno(obj->last_fenced_ring,
reg->setup_seqno)) {
ret = i915_wait_request(obj->last_fenced_ring,
- reg->setup_seqno);
+ reg->setup_seqno,
+ true);
if (ret)
return ret;
}
@@ -3710,7 +3714,7 @@ i915_gem_idle(struct drm_device *dev)
return 0;
}
- ret = i915_gpu_idle(dev);
+ ret = i915_gpu_idle(dev, true);
if (ret) {
mutex_unlock(&dev->struct_mutex);
return ret;
@@ -4201,7 +4205,7 @@ rescan:
* This has a dramatic impact to reduce the number of
* OOM-killer events whilst running the GPU aggressively.
*/
- if (i915_gpu_idle(dev) == 0)
+ if (i915_gpu_idle(dev, true) == 0)
goto rescan;
}
mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index ead5d00..097119c 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -195,7 +195,7 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
trace_i915_gem_evict_everything(dev, purgeable_only);
/* Flush everything (on to the inactive lists) and evict */
- ret = i915_gpu_idle(dev);
+ ret = i915_gpu_idle(dev, true);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index c01cb20..c649e0f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1186,7 +1186,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
* so every billion or so execbuffers, we need to stall
* the GPU in order to reset the counters.
*/
- ret = i915_gpu_idle(dev);
+ ret = i915_gpu_idle(dev, true);
if (ret)
goto err;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6042c5e..e050b90 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -55,7 +55,7 @@ static bool do_idling(struct drm_i915_private *dev_priv)
if (unlikely(dev_priv->mm.gtt->do_idle_maps)) {
dev_priv->mm.interruptible = false;
- if (i915_gpu_idle(dev_priv->dev)) {
+ if (i915_gpu_idle(dev_priv->dev, true)) {
DRM_ERROR("Couldn't idle GPU\n");
/* Wait a bit, in hopes it avoids the hang */
udelay(10);
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index cdf17d4..23a543c 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -227,7 +227,8 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
}
overlay->last_flip_req = request->seqno;
overlay->flip_tail = tail;
- ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req);
+ ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req,
+ true);
if (ret)
return ret;
@@ -448,7 +449,8 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
if (overlay->last_flip_req == 0)
return 0;
- ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req);
+ ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req,
+ true);
if (ret)
return ret;
--
1.7.8.4
