drm/i915: wait render timeout ioctl

This helps implement GL_ARB_sync but stops short of allowing full blown
sync objects. Finally we can use the new timed seqno waiting function
to allow userspace to wait on a buffer object with a timeout. This
implements that interface.

The IOCTL will take as input a buffer object handle, and a timeout in
nanoseconds (flags is currently optional but will likely be used for
permutations of flush operations). Users may specify 0 nanoseconds to
instantly check.

The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
non-zero timeout parameter the wait ioctl will wait for the given number
of nanoseconds on an object becoming unbusy. Since the wait itself does
so holding struct_mutex the object may become re-busied before this
completes. A similar but shorter race condition exists in the busy
ioctl.

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)

v3: Drop lock after getting seqno to avoid ugly dance (Chris)

v4: check for 0 timeout after olr check to allow polling (Chris)

v5: Updated the comment. (Chris)

v6: Return -ETIME instead of -EBUSY when timeout_ns is 0 (Daniel)
Fix the commit message comment to be less ugly (Ben)
Add a warning to check the return timespec (Ben)

v7: Use DRM_AUTH for the ioctl. (Eugeni)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

4 files changed, 99 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index f94792626b94..262a74d1f852 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1803,6 +1803,7 @@ 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_AUTH|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 11c7a6a330c1..8ac10e8c0cdb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1229,6 +1229,8 @@ 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 c8a5b04bc8d5..a0d740fac240 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2001,6 +2001,92 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj)
 }
 
 /**
+ * i915_gem_wait_ioctl - implements DRM_IOCTL_I915_GEM_WAIT
+ * @DRM_IOCTL_ARGS: standard ioctl arguments
+ *
+ * Returns 0 if successful, else an error is returned with the remaining time in
+ * the timeout parameter.
+ *  -ETIME: object is still busy after timeout
+ *  -ERESTARTSYS: signal interrupted the wait
+ *  -ENONENT: object doesn't exist
+ * Also possible, but rare:
+ *  -EAGAIN: GPU wedged
+ *  -ENOMEM: damn
+ *  -ENODEV: Internal IRQ fail
+ *  -E?: The add request failed
+ *
+ * The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
+ * non-zero timeout parameter the wait ioctl will wait for the given number of
+ * nanoseconds on an object becoming unbusy. Since the wait itself does so
+ * without holding struct_mutex the object may become re-busied before this
+ * function completes. A similar but shorter * race condition exists in the busy
+ * ioctl
+ */
+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;
+	struct timespec timeout;
+	u32 seqno = 0;
+	int ret = 0;
+
+	timeout = ns_to_timespec(args->timeout_ns);
+
+	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;
+
+	/* Do this after OLR check to make sure we make forward progress polling
+	 * on this IOCTL with a 0 timeout (like busy ioctl)
+	 */
+	if (!args->timeout_ns) {
+		ret = -ETIME;
+		goto out;
+	}
+
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+
+	ret = __wait_seqno(ring, seqno, true, &timeout);
+	WARN_ON(!timespec_valid(&timeout));
+	args->timeout_ns = timespec_to_ns(&timeout);
+	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.
  *
  * @obj: object which may be in use on another ring.
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index f3f82242bf1d..bab174334da5 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 +888,12 @@ struct drm_intel_sprite_colorkey {
 	__u32 flags;
 };
 
+struct drm_i915_gem_wait {
+	/** Handle of BO we shall wait on */
+	__u32 bo_handle;
+	__u32 flags;
+	/** Number of nanoseconds to wait, Returns time remaining. */
+	__u64 timeout_ns;
+};
+
 #endif				/* _I915_DRM_H_ */