Merge branch 'drm-kms-locking' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

The aim of this locking rework is that ioctls which a compositor should be
might call for every frame (set_cursor, page_flip, addfb, rmfb and
getfb/create_handle) should not be able to block on kms background
activities like output detection. And since each EDID read takes about
25ms (in the best case), that always means we'll drop at least one frame.

The solution is to add per-crtc locking for these ioctls, and restrict
background activities to only use the global lock. Change-the-world type
of events (modeset, dpms, ...) need to grab all locks.

Two tricky parts arose in the conversion:
- A lot of current code assumes that a kms fb object can't disappear while
  holding the global lock, since the current code serializes fb
  destruction with it. Hence proper lifetime management using the already
  created refcounting for fbs need to be instantiated for all ioctls and
  interfaces/users.

- The rmfb ioctl removes the to-be-deleted fb from all active users. But
  unconditionally taking the global kms lock to do so introduces an
  unacceptable potential stall point. And obviously changing the userspace
  abi isn't on the table, either. Hence this conversion opportunistically
  checks whether the rmfb ioctl holds the very last reference, which
  guarantees that the fb isn't in active use on any crtc or plane (thanks
  to the conversion to the new lifetime rules using proper refcounting).
  Only if this is not the case will the code go through the slowpath and
  grab all modeset locks. Sane compositors will never hit this path and so
  avoid the stall, but userspace relying on these semantics will also not
  break.

All these cases are exercised by the newly added subtests for the i-g-t
kms_flip, tested on a machine where a full detect cycle takes around 100
ms.  It works, and no frames are dropped any more with these patches
applied.  kms_flip also contains a special case to exercise the
above-describe rmfb slowpath.

* 'drm-kms-locking' of git://people.freedesktop.org/~danvet/drm-intel: (335 commits)
  drm/fb_helper: check whether fbcon is bound
  drm/doc: updates for new framebuffer lifetime rules
  drm: don't hold crtc mutexes for connector ->detect callbacks
  drm: only grab the crtc lock for pageflips
  drm: optimize drm_framebuffer_remove
  drm/vmwgfx: add proper framebuffer refcounting
  drm/i915: dump refcount into framebuffer debugfs file
  drm: refcounting for crtc framebuffers
  drm: refcounting for sprite framebuffers
  drm: fb refcounting for dirtyfb_ioctl
  drm: don't take modeset locks in getfb ioctl
  drm: push modeset_lock_all into ->fb_create driver callbacks
  drm: nest modeset locks within fpriv->fbs_lock
  drm: reference framebuffers which are on the idr
  drm: revamp framebuffer cleanup interfaces
  drm: create drm_framebuffer_lookup
  drm: revamp locking around fb creation/destruction
  drm: only take the crtc lock for ->cursor_move
  drm: only take the crtc lock for ->cursor_set
  drm: add per-crtc locks
  ...

1 files changed, 49 insertions, 5 deletions

diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 145dec5267c..5fbed5caba6 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -45,6 +45,7 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 	if (!rmap)
 		return NULL;
 
+	kref_init(&rmap->refcount);
 	rmap->obj = (void **)((char *)rmap + obj_offset);
 
 	/* Initially assign CPUs to objects on a rota, since we have
@@ -63,6 +64,35 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 }
 EXPORT_SYMBOL(alloc_cpu_rmap);
 
+/**
+ * cpu_rmap_release - internal reclaiming helper called from kref_put
+ * @ref: kref to struct cpu_rmap
+ */
+static void cpu_rmap_release(struct kref *ref)
+{
+	struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
+	kfree(rmap);
+}
+
+/**
+ * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+{
+	kref_get(&rmap->refcount);
+}
+
+/**
+ * cpu_rmap_put - release ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+int cpu_rmap_put(struct cpu_rmap *rmap)
+{
+	return kref_put(&rmap->refcount, cpu_rmap_release);
+}
+EXPORT_SYMBOL(cpu_rmap_put);
+
 /* Reevaluate nearest object for given CPU, comparing with the given
  * neighbours at the given distance.
  */
@@ -197,8 +227,7 @@ struct irq_glue {
  * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
  * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
  *
- * Must be called in process context, before freeing the IRQs, and
- * without holding any locks required by global workqueue items.
+ * Must be called in process context, before freeing the IRQs.
  */
 void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 {
@@ -212,12 +241,18 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 		glue = rmap->obj[index];
 		irq_set_affinity_notifier(glue->notify.irq, NULL);
 	}
-	irq_run_affinity_notifiers();
 
-	kfree(rmap);
+	cpu_rmap_put(rmap);
 }
 EXPORT_SYMBOL(free_irq_cpu_rmap);
 
+/**
+ * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
+ * @notify: struct irq_affinity_notify passed by irq/manage.c
+ * @mask: cpu mask for new SMP affinity
+ *
+ * This is executed in workqueue context.
+ */
 static void
 irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 {
@@ -230,10 +265,16 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 		pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
 }
 
+/**
+ * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
+ * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
+ */
 static void irq_cpu_rmap_release(struct kref *ref)
 {
 	struct irq_glue *glue =
 		container_of(ref, struct irq_glue, notify.kref);
+
+	cpu_rmap_put(glue->rmap);
 	kfree(glue);
 }
 
@@ -258,10 +299,13 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
 	glue->notify.notify = irq_cpu_rmap_notify;
 	glue->notify.release = irq_cpu_rmap_release;
 	glue->rmap = rmap;
+	cpu_rmap_get(rmap);
 	glue->index = cpu_rmap_add(rmap, glue);
 	rc = irq_set_affinity_notifier(irq, &glue->notify);
-	if (rc)
+	if (rc) {
+		cpu_rmap_put(glue->rmap);
 		kfree(glue);
+	}
 	return rc;
 }
 EXPORT_SYMBOL(irq_cpu_rmap_add);