[RFC 07/12] drm/i915: Delay the freeing of requests until retire time

From: John.C.Harrison@Intel.com
To: Intel-GFX@Lists.FreeDesktop.Org
Subject: [RFC 07/12] drm/i915: Delay the freeing of requests until retire time
Date: Mon, 23 Nov 2015 11:34:26 +0000	[thread overview]
Message-ID: <1448278471-31181-8-git-send-email-John.C.Harrison@Intel.com> (raw)
In-Reply-To: <1448278471-31181-1-git-send-email-John.C.Harrison@Intel.com>

From: John Harrison <John.C.Harrison@Intel.com>

The request structure is reference counted. When the count reached
zero, the request was immediately freed and all associated objects
were unrefereced/unallocated. This meant that the driver mutex lock
must be held at the point where the count reaches zero. This was fine
while all references were held internally to the driver. However, the
plan is to allow the underlying fence object (and hence the request
itself) to be returned to other drivers and to userland. External
users cannot be expected to acquire a driver private mutex lock.

Rather than attempt to disentangle the request structure from the
driver mutex lock, the decsion was to defer the free code until a
later (safer) point. Hence this patch changes the unreference callback
to merely move the request onto a delayed free list. The driver's
retire worker thread will then process the list and actually call the
free function on the requests.

v2: New patch in series.

v3: Updated after review comments by Tvrtko Ursulin. Rename list nodes
to 'link' rather than 'list'. Update list processing to be more
efficient/safer with respect to spinlocks.

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         | 22 +++----------------
 drivers/gpu/drm/i915/i915_gem.c         | 39 +++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_display.c    |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c        |  2 ++
 drivers/gpu/drm/i915/intel_pm.c         |  2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c |  2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++++
 7 files changed, 48 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7d6a7c0..fbf591f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2185,14 +2185,9 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
  * initial reference taken using kref_init
  */
 struct drm_i915_gem_request {
-	/**
-	 * Underlying object for implementing the signal/wait stuff.
-	 * NB: Never return this fence object to user land! It is unsafe to
-	 * let anything outside of the i915 driver get hold of the fence
-	 * object as the clean up when decrementing the reference count
-	 * requires holding the driver mutex lock.
-	 */
+	/** Underlying object for implementing the signal/wait stuff. */
 	struct fence fence;
+	struct list_head delayed_free_link;
 
 	/** On Which ring this request was generated */
 	struct drm_i915_private *i915;
@@ -2305,21 +2300,10 @@ i915_gem_request_reference(struct drm_i915_gem_request *req)
 static inline void
 i915_gem_request_unreference(struct drm_i915_gem_request *req)
 {
-	WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
-	fence_put(&req->fence);
-}
-
-static inline void
-i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req)
-{
-	struct drm_device *dev;
-
 	if (!req)
 		return;
 
-	dev = req->ring->dev;
-	if (kref_put_mutex(&req->fence.refcount, fence_release, &dev->struct_mutex))
-		mutex_unlock(&dev->struct_mutex);
+	fence_put(&req->fence);
 }
 
 static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7a37fb7..171ae5f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2617,10 +2617,27 @@ static void i915_set_reset_status(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void i915_gem_request_free(struct fence *req_fence)
+static void i915_gem_request_release(struct fence *req_fence)
 {
 	struct drm_i915_gem_request *req = container_of(req_fence,
 						 typeof(*req), fence);
+	struct intel_engine_cs *ring = req->ring;
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+	unsigned long flags;
+
+	/*
+	 * Need to add the request to a deferred dereference list to be
+	 * processed at a mutex lock safe time.
+	 */
+	spin_lock_irqsave(&ring->delayed_free_lock, flags);
+	list_add_tail(&req->delayed_free_link, &ring->delayed_free_list);
+	spin_unlock_irqrestore(&ring->delayed_free_lock, flags);
+
+	queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0);
+}
+
+static void i915_gem_request_free(struct drm_i915_gem_request *req)
+{
 	struct intel_context *ctx = req->ctx;
 
 	WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
@@ -2697,7 +2714,7 @@ static const struct fence_ops i915_gem_request_fops = {
 	.enable_signaling	= i915_gem_request_enable_signaling,
 	.signaled		= i915_gem_request_is_completed,
 	.wait			= fence_default_wait,
-	.release		= i915_gem_request_free,
+	.release		= i915_gem_request_release,
 	.get_driver_name	= i915_gem_request_get_driver_name,
 	.get_timeline_name	= i915_gem_request_get_timeline_name,
 	.fence_value_str	= i915_gem_request_fence_value_str,
@@ -2951,6 +2968,10 @@ void i915_gem_reset(struct drm_device *dev)
 void
 i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 {
+	struct drm_i915_gem_request *req, *req_next;
+	LIST_HEAD(list_head);
+	unsigned long flags;
+
 	WARN_ON(i915_verify_lists(ring->dev));
 
 	/* Retire requests first as we use it above for the early return.
@@ -2994,6 +3015,15 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 		i915_gem_request_assign(&ring->trace_irq_req, NULL);
 	}
 
+	/* Really free any requests that were recently unreferenced */
+	spin_lock_irqsave(&ring->delayed_free_lock, flags);
+	list_splice_init(&ring->delayed_free_list, &list_head);
+	spin_unlock_irqrestore(&ring->delayed_free_lock, flags);
+	list_for_each_entry_safe(req, req_next, &list_head, delayed_free_link) {
+		list_del(&req->delayed_free_link);
+		i915_gem_request_free(req);
+	}
+
 	WARN_ON(i915_verify_lists(ring->dev));
 }
 
@@ -3184,7 +3214,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 			ret = __i915_wait_request(req[i], reset_counter, true,
 						  args->timeout_ns > 0 ? &args->timeout_ns : NULL,
 						  file->driver_priv);
-		i915_gem_request_unreference__unlocked(req[i]);
+		i915_gem_request_unreference(req[i]);
 	}
 	return ret;
 
@@ -4179,7 +4209,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 	if (ret == 0)
 		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0);
 
-	i915_gem_request_unreference__unlocked(target);
+	i915_gem_request_unreference(target);
 
 	return ret;
 }
@@ -5036,6 +5066,7 @@ init_ring_lists(struct intel_engine_cs *ring)
 {
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
+	INIT_LIST_HEAD(&ring->delayed_free_list);
 }
 
 void
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 510365e..9291a1d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11256,7 +11256,7 @@ static void intel_mmio_flip_work_func(struct work_struct *work)
 					    mmio_flip->crtc->reset_counter,
 					    false, NULL,
 					    &mmio_flip->i915->rps.mmioflips));
-		i915_gem_request_unreference__unlocked(mmio_flip->req);
+		i915_gem_request_unreference(mmio_flip->req);
 	}
 
 	intel_do_mmio_flip(mmio_flip);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 2b56651..06a398a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1920,7 +1920,9 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
+	INIT_LIST_HEAD(&ring->delayed_free_list);
 	spin_lock_init(&ring->fence_lock);
+	spin_lock_init(&ring->delayed_free_lock);
 	i915_gem_batch_pool_init(dev, &ring->batch_pool);
 	init_waitqueue_head(&ring->irq_queue);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index c207a3a..e2d34a6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7174,7 +7174,7 @@ static void __intel_rps_boost_work(struct work_struct *work)
 		gen6_rps_boost(to_i915(req->ring->dev), NULL,
 			       req->emitted_jiffies);
 
-	i915_gem_request_unreference__unlocked(req);
+	i915_gem_request_unreference(req);
 	kfree(boost);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index f4a6403..e5573e7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2158,7 +2158,9 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	INIT_LIST_HEAD(&ring->request_list);
 	INIT_LIST_HEAD(&ring->execlist_queue);
 	INIT_LIST_HEAD(&ring->buffers);
+	INIT_LIST_HEAD(&ring->delayed_free_list);
 	spin_lock_init(&ring->fence_lock);
+	spin_lock_init(&ring->delayed_free_lock);
 	i915_gem_batch_pool_init(dev, &ring->batch_pool);
 	memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 356b6a8..77384ed 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -301,6 +301,10 @@ struct  intel_engine_cs {
 	 */
 	u32 last_submitted_seqno;
 
+	/* deferred free list to allow unreferencing requests outside the driver */
+	struct list_head delayed_free_list;
+	spinlock_t delayed_free_lock;
+
 	bool gpu_caches_dirty;
 
 	wait_queue_head_t irq_queue;
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
