drm/i915: Convert trace-irq to the breadcrumb waiter

If we convert the tracing over from direct use of ring->irq_get() and
over to the breadcrumb infrastructure, we only have a single user of the
ring->irq_get and so we will be able to simplify the driver routines
(eliminating the redundant validation and irq refcounting).

Process context is preferred over softirq (or even hardirq) for a couple
of reasons:

 - we already utilize process context to have fast wakeup of a single
   client (i.e. the client waiting for the GPU inspects the seqno for
   itself following an interrupt to avoid the overhead of a context
   switch before it returns to userspace)

 - engine->irq_seqno() is not suitable for use from an softirq/hardirq
   context as we may require long waits (100-250us) to ensure the seqno
   write is posted before we read it from the CPU

A signaling framework is a requirement for enabling dma-fences.

v2: Move to a signaling framework based upon the waiter.
v3: Track the first-signal to avoid having to walk the rbtree everytime.
v4: Mark the signaler thread as RT priority to reduce latency in the
indirect wakeups.
v5: Make failure to allocate the thread fatal.
v6: Rename kthreads to i915/signal:%u

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-16-git-send-email-chris@chris-wilson.co.uk

1 files changed, 7 insertions, 1 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index fcc348376080..1d4a23681285 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -129,6 +129,8 @@ struct  i915_ctx_workarounds {
 	struct drm_i915_gem_object *obj;
 };
 
+struct drm_i915_gem_request;
+
 struct intel_engine_cs {
 	struct drm_i915_private *i915;
 	const char	*name;
@@ -167,8 +169,11 @@ struct intel_engine_cs {
 	struct intel_breadcrumbs {
 		spinlock_t lock; /* protects the lists of requests */
 		struct rb_root waiters; /* sorted by retirement, priority */
+		struct rb_root signals; /* sorted by retirement */
 		struct intel_wait *first_wait; /* oldest waiter by retirement */
 		struct task_struct *tasklet; /* bh for user interrupts */
+		struct task_struct *signaler; /* used for fence signalling */
+		void *first_signal;
 		struct timer_list fake_irq; /* used after a missed interrupt */
 		bool irq_enabled;
 		bool rpm_wakelock;
@@ -187,7 +192,6 @@ struct intel_engine_cs {
 	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
 	bool		irq_posted;
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
-	struct drm_i915_gem_request *trace_irq_req;
 	bool __must_check (*irq_get)(struct intel_engine_cs *ring);
 	void		(*irq_put)(struct intel_engine_cs *ring);
 
@@ -532,6 +536,7 @@ bool intel_engine_add_wait(struct intel_engine_cs *engine,
 			   struct intel_wait *wait);
 void intel_engine_remove_wait(struct intel_engine_cs *engine,
 			      struct intel_wait *wait);
+int intel_engine_enable_signaling(struct drm_i915_gem_request *request);
 
 static inline bool intel_engine_has_waiter(struct intel_engine_cs *engine)
 {
@@ -558,5 +563,6 @@ static inline bool intel_engine_wakeup(struct intel_engine_cs *engine)
 void intel_engine_enable_fake_irq(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 unsigned int intel_kick_waiters(struct drm_i915_private *i915);
+unsigned int intel_kick_signalers(struct drm_i915_private *i915);
 
 #endif /* _INTEL_RINGBUFFER_H_ */