[PATCH 11/12 v2] drm/i915: wait render timeout ioctl

[Ben Widawsky <ben@bwidawsk.net>]

This helps implement glClientWaitSync.

Finally we can use the new timed seqno waiting function to allow
userspace to wait on a request with a timeout. This implements that
interface.

The new ioctl is very straight forward, there is a flags field which I
envision may be useful for various flush permutations of the command.

On 32bit systems, the timeout is restricted to 2^32 - 1 microseconds.

v2: ETIME/ERESTARTSYS instead of changing to EBUSY, and EGAIN (Chris)
Flush the object from the gpu write domain (Chris + Daniel)
Fix leaked refcount in good case (Chris)
Naturally align ioctl struct (Chris)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_dma.c |    1 +
 drivers/gpu/drm/i915/i915_drv.h |    2 ++
 drivers/gpu/drm/i915/i915_gem.c |   55 +++++++++++++++++++++++++++++++++++++++
 include/drm/i915_drm.h          |    8 ++++++
 4 files changed, 66 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index e73389d..ed0ccb7 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2189,6 +2189,7 @@ struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, intel_sprite_get_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_UNLOCKED),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d260762..d415f0f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1221,6 +1221,8 @@ int i915_gem_get_tiling(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
+int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
 int i915_gem_init_object(struct drm_gem_object *obj);
 int __must_check i915_gem_flush_ring(struct intel_ring_buffer *ring,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 63eda79..0dee6bc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1991,6 +1991,61 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
+int
+i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_i915_gem_wait *args = data;
+	struct drm_i915_gem_object *obj;
+	struct intel_ring_buffer *ring = NULL;
+	long timeout;
+	u32 seqno = 0;
+	int ret = 0;
+
+	/* For now timeout is microseconds only */
+	timeout = (long)DIV_ROUND_UP_ULL(args->timeout_ns, NSEC_PER_USEC);
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ret;
+
+	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->bo_handle));
+	if (&obj->base == NULL) {
+		mutex_unlock(&dev->struct_mutex);
+		return -ENOENT;
+	}
+
+	/* Need to make sure the object is flushed first. This non-obvious
+	 * flush is required to enforce that (active && !olr) == no wait
+	 * necessary.
+	 */
+	ret = i915_gem_object_flush_gpu_write_domain(obj);
+	if (ret)
+		goto out;
+
+	if (obj->active) {
+		seqno = obj->last_rendering_seqno;
+		ring = obj->ring;
+	}
+
+	if (seqno == 0)
+		 goto out;
+
+	ret = i915_gem_check_olr(ring, &seqno);
+	if (ret)
+		goto out;
+
+	mutex_unlock(&dev->struct_mutex);
+	ret = __wait_seqno(ring, seqno, true, &timeout);
+	drm_gem_object_unreference_unlocked(&obj->base);
+	args->timeout_ns = timeout * NSEC_PER_USEC;
+	return ret;
+
+out:
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
 /**
  * i915_gem_object_sync - sync an object to a ring.
  *
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index f3f8224..8f818f8 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -200,6 +200,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_EXECBUFFER2	0x29
 #define DRM_I915_GET_SPRITE_COLORKEY	0x2a
 #define DRM_I915_SET_SPRITE_COLORKEY	0x2b
+#define DRM_I915_GEM_WAIT	0x2c
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -243,6 +244,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_OVERLAY_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
 #define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
 #define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -886,4 +888,10 @@ struct drm_intel_sprite_colorkey {
 	__u32 flags;
 };
 
+struct drm_i915_gem_wait {
+	__u32 bo_handle;
+	__u32 flags;
+	__u64 timeout_ns;
+};
+
 #endif				/* _I915_DRM_H_ */
-- 
1.7.10