[Intel-gfx] [PATCH v6 1/7] drm/i915: Convert requests to use struct fence

John.C.Harrison at Intel.com John.C.Harrison at Intel.com
Thu Feb 18 14:24:04 UTC 2016


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

There is a construct in the linux kernel called 'struct fence' that is
intended to keep track of work that is executed on hardware. I.e. it
solves the basic problem that the drivers 'struct
drm_i915_gem_request' is trying to address. The request structure does
quite a lot more than simply track the execution progress so is very
definitely still required. However, the basic completion status side
could be updated to use the ready made fence implementation and gain
all the advantages that provides.

This patch makes the first step of integrating a struct fence into the
request. It replaces the explicit reference count with that of the
fence. It also replaces the 'is completed' test with the fence's
equivalent. Currently, that simply chains on to the original request
implementation. A future patch will improve this.

v3: Updated after review comments by Tvrtko Ursulin. Added fence
context/seqno pair to the debugfs request info. Renamed fence 'driver
name' to just 'i915'. Removed BUG_ONs.

v5: Changed seqno format in debugfs to %x rather than %u as that is
apparently the preferred appearance. Line wrapped some long lines to
keep the style checker happy.

v6: Updated to newer nigthly and resolved conflicts. The biggest issue
was with the re-worked busy spin precursor to waiting on a request. In
particular, the addition of a 'request_started' helper function. This
has no corresponding concept within the fence framework. However, it
is only ever used in one place and the whole point of that place is to
always directly read the seqno for absolutely lowest latency possible.
So the simple solution is to just make the seqno test explicit at that
point now rather than later in the series (it was previously being
done anyway when fences become interrupt driven).

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Reviewed-by: Jesse Barnes <jbarnes at virtuousgeek.org>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  5 ++-
 drivers/gpu/drm/i915/i915_drv.h         | 47 +++++++++++------------
 drivers/gpu/drm/i915/i915_gem.c         | 67 +++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_lrc.c        |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.c |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h |  3 ++
 6 files changed, 89 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ebe7063..d032e9f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -709,11 +709,12 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 			task = NULL;
 			if (req->pid)
 				task = pid_task(req->pid, PIDTYPE_PID);
-			seq_printf(m, "    %x @ %d: %s [%d]\n",
+			seq_printf(m, "    %x @ %d: %s [%d], fence = %x:%x\n",
 				   req->seqno,
 				   (int) (jiffies - req->emitted_jiffies),
 				   task ? task->comm : "<unknown>",
-				   task ? task->pid : -1);
+				   task ? task->pid : -1,
+				   req->fence.context, req->fence.seqno);
 			rcu_read_unlock();
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 351308f..7c64cc1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -53,6 +53,7 @@
 #include <linux/kref.h>
 #include <linux/pm_qos.h>
 #include "intel_guc.h"
+#include <linux/fence.h>
 
 /* General customization:
  */
@@ -2197,7 +2198,17 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
  * initial reference taken using kref_init
  */
 struct drm_i915_gem_request {
-	struct kref ref;
+	/**
+	 * Underlying object for implementing the signal/wait stuff.
+	 * NB: Never call fence_later() or return this fence object to user
+	 * land! Due to lazy allocation, scheduler re-ordering, pre-emption,
+	 * etc., there is no guarantee at all about the validity or
+	 * sequentiality of the fence's seqno! It is also 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.
+	 */
+	struct fence fence;
 
 	/** On Which ring this request was generated */
 	struct drm_i915_private *i915;
@@ -2283,7 +2294,13 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
 			   struct intel_context *ctx,
 			   struct drm_i915_gem_request **req_out);
 void i915_gem_request_cancel(struct drm_i915_gem_request *req);
-void i915_gem_request_free(struct kref *req_ref);
+
+static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
+					      bool lazy_coherency)
+{
+	return fence_is_signaled(&req->fence);
+}
+
 int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
 				   struct drm_file *file);
 
@@ -2303,7 +2320,7 @@ static inline struct drm_i915_gem_request *
 i915_gem_request_reference(struct drm_i915_gem_request *req)
 {
 	if (req)
-		kref_get(&req->ref);
+		fence_get(&req->fence);
 	return req;
 }
 
@@ -2311,7 +2328,7 @@ static inline void
 i915_gem_request_unreference(struct drm_i915_gem_request *req)
 {
 	WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
-	kref_put(&req->ref, i915_gem_request_free);
+	fence_put(&req->fence);
 }
 
 static inline void
@@ -2323,7 +2340,7 @@ i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req)
 		return;
 
 	dev = req->ring->dev;
-	if (kref_put_mutex(&req->ref, i915_gem_request_free, &dev->struct_mutex))
+	if (kref_put_mutex(&req->fence.refcount, fence_release, &dev->struct_mutex))
 		mutex_unlock(&dev->struct_mutex);
 }
 
@@ -2340,12 +2357,6 @@ static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
 }
 
 /*
- * XXX: i915_gem_request_completed should be here but currently needs the
- * definition of i915_seqno_passed() which is below. It will be moved in
- * a later patch when the call to i915_seqno_passed() is obsoleted...
- */
-
-/*
  * A command that requires special handling by the command parser.
  */
 struct drm_i915_cmd_descriptor {
@@ -2966,20 +2977,6 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2)
 	return (int32_t)(seq1 - seq2) >= 0;
 }
 
-static inline bool i915_gem_request_started(struct drm_i915_gem_request *req,
-					   bool lazy_coherency)
-{
-	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
-	return i915_seqno_passed(seqno, req->previous_seqno);
-}
-
-static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
-					      bool lazy_coherency)
-{
-	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
-	return i915_seqno_passed(seqno, req->seqno);
-}
-
 int __must_check i915_gem_get_seqno(struct drm_device *dev, u32 *seqno);
 int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 915b4e2..901be6c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1192,6 +1192,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 {
 	unsigned long timeout;
 	unsigned cpu;
+	uint32_t seqno;
 
 	/* When waiting for high frequency requests, e.g. during synchronous
 	 * rendering split between the CPU and GPU, the finite amount of time
@@ -1207,12 +1208,14 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 		return -EBUSY;
 
 	/* Only spin if we know the GPU is processing this request */
-	if (!i915_gem_request_started(req, true))
+	seqno = req->ring->get_seqno(req->ring, true);
+	if (!i915_seqno_passed(seqno, req->previous_seqno))
 		return -EAGAIN;
 
 	timeout = local_clock_us(&cpu) + 5;
 	while (!need_resched()) {
-		if (i915_gem_request_completed(req, true))
+		seqno = req->ring->get_seqno(req->ring, true);
+		if (i915_seqno_passed(seqno, req->seqno))
 			return 0;
 
 		if (signal_pending_state(state, current))
@@ -1224,7 +1227,8 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 		cpu_relax_lowlatency();
 	}
 
-	if (i915_gem_request_completed(req, false))
+	seqno = req->ring->get_seqno(req->ring, false);
+	if (i915_seqno_passed(seqno, req->seqno))
 		return 0;
 
 	return -EAGAIN;
@@ -2679,12 +2683,14 @@ static void i915_set_reset_status(struct drm_i915_private *dev_priv,
 	}
 }
 
-void i915_gem_request_free(struct kref *req_ref)
+static void i915_gem_request_free(struct fence *req_fence)
 {
-	struct drm_i915_gem_request *req = container_of(req_ref,
-						 typeof(*req), ref);
+	struct drm_i915_gem_request *req = container_of(req_fence,
+						 typeof(*req), fence);
 	struct intel_context *ctx = req->ctx;
 
+	WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
+
 	if (req->file_priv)
 		i915_gem_request_remove_from_client(req);
 
@@ -2700,6 +2706,45 @@ void i915_gem_request_free(struct kref *req_ref)
 	kmem_cache_free(req->i915->requests, req);
 }
 
+static bool i915_gem_request_enable_signaling(struct fence *req_fence)
+{
+	/* Interrupt driven fences are not implemented yet.*/
+	WARN(true, "This should not be called!");
+	return true;
+}
+
+static bool i915_gem_request_is_completed(struct fence *req_fence)
+{
+	struct drm_i915_gem_request *req = container_of(req_fence,
+						 typeof(*req), fence);
+	u32 seqno;
+
+	seqno = req->ring->get_seqno(req->ring, false/*lazy_coherency*/);
+
+	return i915_seqno_passed(seqno, req->seqno);
+}
+
+static const char *i915_gem_request_get_driver_name(struct fence *req_fence)
+{
+	return "i915";
+}
+
+static const char *i915_gem_request_get_timeline_name(struct fence *req_fence)
+{
+	struct drm_i915_gem_request *req = container_of(req_fence,
+						 typeof(*req), fence);
+	return req->ring->name;
+}
+
+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,
+	.get_driver_name	= i915_gem_request_get_driver_name,
+	.get_timeline_name	= i915_gem_request_get_timeline_name,
+};
+
 int i915_gem_request_alloc(struct intel_engine_cs *ring,
 			   struct intel_context *ctx,
 			   struct drm_i915_gem_request **req_out)
@@ -2721,7 +2766,6 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
 	if (ret)
 		goto err;
 
-	kref_init(&req->ref);
 	req->i915 = dev_priv;
 	req->ring = ring;
 	req->ctx  = ctx;
@@ -2736,6 +2780,9 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
 		goto err;
 	}
 
+	fence_init(&req->fence, &i915_gem_request_fops, &ring->fence_lock,
+		   ring->fence_context, req->seqno);
+
 	/*
 	 * Reserve space in the ring buffer for all the commands required to
 	 * eventually emit this request. This is to guarantee that the
@@ -4810,7 +4857,7 @@ i915_gem_init_hw(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
-	int ret, i, j;
+	int ret, i, j, fence_base;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4880,12 +4927,16 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (ret)
 		goto out;
 
+	fence_base = fence_context_alloc(I915_NUM_RINGS);
+
 	/* Now it is safe to go back round and do everything else: */
 	for_each_ring(ring, dev_priv, i) {
 		struct drm_i915_gem_request *req;
 
 		WARN_ON(!ring->default_context);
 
+		ring->fence_context = fence_base + i;
+
 		ret = i915_gem_request_alloc(ring, ring->default_context, &req);
 		if (ret) {
 			i915_gem_cleanup_ringbuffer(dev);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index faaf490..4e5195b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2013,6 +2013,7 @@ logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
+	spin_lock_init(&ring->fence_lock);
 	i915_gem_batch_pool_init(dev, &ring->batch_pool);
 	init_waitqueue_head(&ring->irq_queue);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d4e33ac..651b700 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2159,6 +2159,7 @@ 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);
+	spin_lock_init(&ring->fence_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 ede5795..22e3d87 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -352,6 +352,9 @@ struct  intel_engine_cs {
 	 * to encode the command length in the header).
 	 */
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
+
+	unsigned fence_context;
+	spinlock_t fence_lock;
 };
 
 static inline bool
-- 
1.9.1



More information about the Intel-gfx mailing list