drm/i915: Support explicit fencing for execbuf

Now that the user can opt-out of implicit fencing, we need to give them
back control over the fencing. We employ sync_file to wrap our
drm_i915_gem_request and provide an fd that userspace can merge with
other sync_file fds and pass back to the kernel to wait upon before
future execution.

Testcase: igt/gem_exec_fence
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Chad Versace <chadversary@chromium.org>
Link: http://patchwork.freedesktop.org/patch/msgid/20170127094008.27489-2-chris@chris-wilson.co.uk

4 files changed, 87 insertions, 7 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 183f5dc1c3f2..1ae0bb91ee60 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -19,6 +19,7 @@ config DRM_I915
 	select INPUT if ACPI
 	select ACPI_VIDEO if ACPI
 	select ACPI_BUTTON if ACPI
+	select SYNC_FILE
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6c9c2037fadf..3aa5bf58cf32 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -350,6 +350,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_COHERENT_PHYS_GTT:
 	case I915_PARAM_HAS_EXEC_SOFTPIN:
 	case I915_PARAM_HAS_EXEC_ASYNC:
+	case I915_PARAM_HAS_EXEC_FENCE:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
@@ -2550,7 +2551,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_HWS_ADDR, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2_WR, i915_gem_execbuffer2, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6fd60682bf93..91c2393199a3 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -28,6 +28,7 @@
 
 #include <linux/dma_remapping.h>
 #include <linux/reservation.h>
+#include <linux/sync_file.h>
 #include <linux/uaccess.h>
 
 #include <drm/drmP.h>
@@ -1595,6 +1596,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct i915_execbuffer_params *params = &params_master;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
 	u32 dispatch_flags;
+	struct dma_fence *in_fence = NULL;
+	struct sync_file *out_fence = NULL;
+	int out_fence_fd = -1;
 	int ret;
 	bool need_relocs;
 
@@ -1638,6 +1642,23 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		dispatch_flags |= I915_DISPATCH_RS;
 	}
 
+	if (args->flags & I915_EXEC_FENCE_IN) {
+		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
+		if (!in_fence) {
+			ret = -EINVAL;
+			goto pre_mutex_err;
+		}
+	}
+
+	if (args->flags & I915_EXEC_FENCE_OUT) {
+		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
+		if (out_fence_fd < 0) {
+			ret = out_fence_fd;
+			out_fence_fd = -1;
+			goto pre_mutex_err;
+		}
+	}
+
 	/* Take a local wakeref for preparing to dispatch the execbuf as
 	 * we expect to access the hardware fairly frequently in the
 	 * process. Upon first dispatch, we acquire another prolonged
@@ -1782,6 +1803,21 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		goto err_batch_unpin;
 	}
 
+	if (in_fence) {
+		ret = i915_gem_request_await_dma_fence(params->request,
+						       in_fence);
+		if (ret < 0)
+			goto err_request;
+	}
+
+	if (out_fence_fd != -1) {
+		out_fence = sync_file_create(&params->request->fence);
+		if (!out_fence) {
+			ret = -ENOMEM;
+			goto err_request;
+		}
+	}
+
 	/* Whilst this request exists, batch_obj will be on the
 	 * active_list, and so will hold the active reference. Only when this
 	 * request is retired will the the batch_obj be moved onto the
@@ -1809,6 +1845,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	ret = execbuf_submit(params, args, &eb->vmas);
 err_request:
 	__i915_add_request(params->request, ret == 0);
+	if (out_fence) {
+		if (ret == 0) {
+			fd_install(out_fence_fd, out_fence->file);
+			args->rsvd2 &= GENMASK_ULL(0, 31); /* keep in-fence */
+			args->rsvd2 |= (u64)out_fence_fd << 32;
+			out_fence_fd = -1;
+		} else {
+			fput(out_fence->file);
+		}
+	}
 
 err_batch_unpin:
 	/*
@@ -1830,6 +1876,9 @@ pre_mutex_err:
 	/* intel_gpu_busy should also get a ref, so it will free when the device
 	 * is really idle. */
 	intel_runtime_pm_put(dev_priv);
+	if (out_fence_fd != -1)
+		put_unused_fd(out_fence_fd);
+	dma_fence_put(in_fence);
 	return ret;
 }
 
@@ -1937,11 +1986,6 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (args->rsvd2 != 0) {
-		DRM_DEBUG("dirty rvsd2 field\n");
-		return -EINVAL;
-	}
-
 	exec2_list = drm_malloc_gfp(args->buffer_count,
 				    sizeof(*exec2_list),
 				    GFP_TEMPORARY);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 6620b6ad76ed..3554495bef13 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -246,6 +246,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_OVERLAY_PUT_IMAGE	0x27
 #define DRM_I915_OVERLAY_ATTRS	0x28
 #define DRM_I915_GEM_EXECBUFFER2	0x29
+#define DRM_I915_GEM_EXECBUFFER2_WR	DRM_I915_GEM_EXECBUFFER2
 #define DRM_I915_GET_SPRITE_COLORKEY	0x2a
 #define DRM_I915_SET_SPRITE_COLORKEY	0x2b
 #define DRM_I915_GEM_WAIT	0x2c
@@ -280,6 +281,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_INIT		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
 #define DRM_IOCTL_I915_GEM_EXECBUFFER	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
 #define DRM_IOCTL_I915_GEM_EXECBUFFER2	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
 #define DRM_IOCTL_I915_GEM_PIN		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
 #define DRM_IOCTL_I915_GEM_UNPIN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
 #define DRM_IOCTL_I915_GEM_BUSY		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
@@ -403,6 +405,13 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_ASYNC	 43
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
+ * both being able to pass in a sync_file fd to wait upon before executing,
+ * and being able to return a new sync_file fd that is signaled when the
+ * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE	 44
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -855,7 +864,32 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_RESOURCE_STREAMER     (1<<15)
 
-#define __I915_EXEC_UNKNOWN_FLAGS -(I915_EXEC_RESOURCE_STREAMER<<1)
+/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_IN		(1<<16)
+
+/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
+ * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
+ * to the caller, and it should be close() after use. (The fd is a regular
+ * file descriptor and will be cleaned up on process termination. It holds
+ * a reference to the request, but nothing else.)
+ *
+ * The sync_file fd can be combined with other sync_file and passed either
+ * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
+ * will only occur after this request completes), or to other devices.
+ *
+ * Using I915_EXEC_FENCE_OUT requires use of
+ * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
+ * back to userspace. Failure to do so will cause the out-fence to always
+ * be reported as zero, and the real fence fd to be leaked.
+ */
+#define I915_EXEC_FENCE_OUT		(1<<17)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_OUT<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \