drm/i915: Add sync framework support to execbuff IOCTL

Various projects desire a mechanism for managing dependencies between
work items asynchronously. This can also include work items across
complete different and independent systems. For example, an
application wants to retrieve a frame from a video in device,
using it for rendering on a GPU then send it to the video out device
for display all without having to stall waiting for completion along
the way. The sync framework allows this. It encapsulates
synchronisation events in file descriptors. The application can
request a sync point for the completion of each piece of work. Drivers
should also take sync points in with each new work request and not
schedule the work to start until the sync has been signalled.

This patch adds sync framework support to the exec buffer IOCTL. A
sync point can be passed in to stall execution of the batch buffer
until signalled. And a sync point can be returned after each batch
buffer submission which will be signalled upon that batch buffer's
completion.

At present, the input sync point is simply waited on synchronously
inside the exec buffer IOCTL call. Once the GPU scheduler arrives,
this will be handled asynchronously inside the scheduler and the IOCTL
can return without having to wait.

Note also that the scheduler will re-order the execution of batch
buffers, e.g. because a batch buffer is stalled on a sync point and
cannot be submitted yet but other, independent, batch buffers are
being presented to the driver. This means that the timeline within the
sync points returned cannot be global to the engine. Instead they must
be kept per context per engine (the scheduler may not re-order batches
within a context). Hence the timeline cannot be based on the existing
seqno values but must be a new implementation.

This patch is a port of work by several people that has been pulled
across from Android. It has been updated several times across several
patches. Rather than attempt to port each individual patch, this
version is the finished product as a single patch. The various
contributors/authors along the way (in addition to myself) were:
  Satyanantha RamaGopal M <rama.gopal.m.satyanantha@intel.com>
  Tvrtko Ursulin <tvrtko.ursulin@intel.com>
  Michel Thierry <michel.thierry@intel.com>
  Arun Siluvery <arun.siluvery@linux.intel.com>

v0.2: New patch in series.

v0.3: Updated to use the new 'sync_fence_is_signaled' API rather than
having to know about the internal meaning of the 'fence::status' field
(which recently got inverted!) [work by Peter Lawthers].

Updated after review comments by Daniel Vetter. Removed '#ifdef
CONFIG_SYNC' and add 'select SYNC' to the Kconfig instead. Moved the
fd installation of fences to the end of the execbuff call to in order
to remove the need to use 'sys_close' to clean up on failure.

Updated after review comments by Tvrtko Ursulin. Remvoed the
'fence_external' flag as redundant. Covnerted DRM_ERRORs to
DRM_DEBUGs. Changed one second wait to a wait forever when waiting on
incoming fences.

v0.4: Re-instated missing return of fd to user land that somehow got
lost in the anti-sys_close() re-factor.

v0.5: Correct typo in commit message. Twiddled white space and wrapped
some long lines to keep style checker happy.

Corrected return codes, removed redundant test and added a descriptive
comment to i915_early_fence_wait() - review feedback from Tvrtko.

Also, patch appears somewhat different in a few places due to being
rebased after the scheduler patches rather than before.

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Peter Lawthers <peter.lawthers@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>

5 files changed, 207 insertions, 10 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 29a32b11953b..634bf20e671a 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -18,6 +18,9 @@ config DRM_I915
 	select INPUT if ACPI
 	select ACPI_VIDEO if ACPI
 	select ACPI_BUTTON if ACPI
+	# ANDROID is required for SYNC
+	select ANDROID
+	select SYNC
 	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.h b/drivers/gpu/drm/i915/i915_drv.h
index ac9fcc19897a..b95d67ba42c1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2366,6 +2366,13 @@ void i915_gem_request_notify(struct intel_engine_cs *ring, bool fence_locked);
 int i915_create_fence_timeline(struct drm_device *dev,
 			       struct intel_context *ctx,
 			       struct intel_engine_cs *ring);
+struct sync_fence;
+int i915_create_sync_fence(struct drm_i915_gem_request *req,
+			   struct sync_fence **sync_fence, int *fence_fd);
+void i915_install_sync_fence_fd(struct drm_i915_gem_request *req,
+				struct sync_fence *sync_fence, int fence_fd);
+bool i915_safe_to_ignore_fence(struct intel_engine_cs *ring,
+			       struct sync_fence *fence);
 
 static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 165b8a38c16f..95e5bdc18558 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -38,6 +38,7 @@
 #include <linux/swap.h>
 #include <linux/pci.h>
 #include <linux/dma-buf.h>
+#include <../drivers/android/sync.h>
 
 #define RQ_BUG_ON(expr)
 
@@ -2680,7 +2681,13 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 
 	/*
 	 * Add the fence to the pending list before emitting the commands to
-	 * generate a seqno notification interrupt.
+	 * generate a seqno notification interrupt. This will also enable
+	 * interrupts if 'signal_requested' has been set.
+	 *
+	 * For example, if an exported sync point has been requested for this
+	 * request then it can be waited on without the driver's knowledge,
+	 * i.e. without calling __i915_wait_request(). Thus interrupts must
+	 * be enabled from the start rather than only on demand.
 	 */
 	i915_gem_request_submit(request);
 
@@ -3061,6 +3068,87 @@ static unsigned i915_fence_timeline_get_next_seqno(struct i915_fence_timeline *t
 	return seqno;
 }
 
+int i915_create_sync_fence(struct drm_i915_gem_request *req,
+			   struct sync_fence **sync_fence, int *fence_fd)
+{
+	char engine_name[] = "i915_engine0";
+	int fd;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0) {
+		DRM_DEBUG("No available file descriptors!\n");
+		*fence_fd = -1;
+		return fd;
+	}
+
+	engine_name[11] += req->engine->id;
+	*sync_fence = sync_fence_create_dma(engine_name, &req->fence);
+	if (!*sync_fence) {
+		put_unused_fd(fd);
+		*fence_fd = -1;
+		return -ENOMEM;
+	}
+
+	*fence_fd = fd;
+
+	return 0;
+}
+
+void i915_install_sync_fence_fd(struct drm_i915_gem_request *req,
+				struct sync_fence *sync_fence, int fence_fd)
+{
+	sync_fence_install(sync_fence, fence_fd);
+
+	/*
+	 * NB: The corresponding put happens automatically on file close
+	 * from sync_fence_release() via the fops callback.
+	 */
+	fence_get(&req->fence);
+
+	/*
+	 * The sync framework adds a callback to the fence. The fence
+	 * framework calls 'enable_signalling' when a callback is added.
+	 * Thus this flag should have been set by now. If not then
+	 * 'enable_signalling' must be called explicitly because exporting
+	 * a fence to user land means it can be waited on asynchronously and
+	 * thus must be signalled asynchronously.
+	 */
+	WARN_ON(!req->signal_requested);
+}
+
+bool i915_safe_to_ignore_fence(struct intel_engine_cs *engine,
+			       struct sync_fence *sync_fence)
+{
+	struct fence *dma_fence;
+	struct drm_i915_gem_request *req;
+	int i;
+
+	if (sync_fence_is_signaled(sync_fence))
+		return true;
+
+	for (i = 0; i < sync_fence->num_fences; i++) {
+		dma_fence = sync_fence->cbs[i].sync_pt;
+
+		/* No need to worry about dead points: */
+		if (fence_is_signaled(dma_fence))
+			continue;
+
+		/* Can't ignore other people's points: */
+		if (dma_fence->ops != &i915_gem_request_fops)
+			return false;
+
+		req = container_of(dma_fence, typeof(*req), fence);
+
+		/* Can't ignore points on other rings: */
+		if (req->engine != engine)
+			return false;
+
+		/* Same engine means guaranteed to be in order so ignore it. */
+	}
+
+	return true;
+}
+
 static inline int
 __i915_gem_request_alloc(struct intel_engine_cs *engine,
 			 struct intel_context *ctx,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 84ef58003dd6..fa0278b16dcf 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
  *
  */
 
+#include <linux/syscalls.h>
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -33,6 +34,7 @@
 #include "intel_drv.h"
 #include <linux/dma_remapping.h>
 #include <linux/uaccess.h>
+#include <../drivers/android/sync.h>
 #include "i915_scheduler.h"
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
@@ -1503,6 +1505,41 @@ eb_select_ring(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+/*
+ * Do a synchronous wait on any incoming fence object (until the scheduler
+ * arrives and implements asynchronous waits). NB: This must be called before
+ * acquiring the driver mutex lock!
+ */
+static int i915_early_fence_wait(struct intel_engine_cs *ring, int fence_fd)
+{
+	struct sync_fence *fence;
+	int ret = 0;
+
+	if (fence_fd < 0) {
+		DRM_DEBUG("Invalid wait fence fd %d on ring %d\n", fence_fd,
+			  (int) ring->id);
+		return -EINVAL;
+	}
+
+	fence = sync_fence_fdget(fence_fd);
+	if (fence == NULL) {
+		DRM_DEBUG("Invalid wait fence %d on ring %d\n", fence_fd,
+			  (int) ring->id);
+		return -EINVAL;
+	}
+
+	/*
+	 * Wait forever for the fence to be signalled. This is safe
+	 * because the the mutex lock has not yet been acquired and
+	 * the wait is interruptible.
+	 */
+	if (!i915_safe_to_ignore_fence(ring, fence))
+		ret = sync_fence_wait(fence, -1);
+
+	sync_fence_put(fence);
+	return ret;
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
@@ -1523,6 +1560,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	u32 dispatch_flags;
 	int ret, i;
 	bool need_relocs;
+	int fd_fence_complete = -1;
+	int fd_fence_wait = lower_32_bits(args->rsvd2);
+	struct sync_fence *sync_fence;
+
+	/*
+	 * Make sure an broken fence handle is not returned no matter how
+	 * early an error might be hit. Note that rsvd2 is both an input and
+	 * an output parameter. Need to preserve the input half to allow
+	 * calls to be retried.
+	 */
+	if (args->flags & I915_EXEC_CREATE_FENCE)
+		args->rsvd2 = fd_fence_wait | (((__u64) -1) << 32);
 
 	if (!i915_gem_check_execbuffer(args))
 		return -EINVAL;
@@ -1564,6 +1613,17 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		dispatch_flags |= I915_DISPATCH_RS;
 	}
 
+	/*
+	 * Without a GPU scheduler, any fence waits must be done up front.
+	 */
+	if (args->flags & I915_EXEC_WAIT_FENCE) {
+		ret = i915_early_fence_wait(engine, fd_fence_wait);
+		if (ret < 0)
+			return ret;
+
+		args->flags &= ~I915_EXEC_WAIT_FENCE;
+	}
+
 	intel_runtime_pm_get(dev_priv);
 
 	ret = i915_mutex_lock_interruptible(dev);
@@ -1753,13 +1813,41 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	i915_gem_context_reference(ctx);
 	params->ctx = ctx;
 
+	if (args->flags & I915_EXEC_CREATE_FENCE) {
+		/*
+		 * Caller has requested a sync fence.
+		 * User interrupts will be enabled to make sure that
+		 * the timeline is signalled on completion.
+		 */
+		ret = i915_create_sync_fence(params->request, &sync_fence,
+					     &fd_fence_complete);
+		if (ret) {
+			DRM_ERROR("Fence creation failed for engine %d, ctx %p\n",
+				  engine->id, ctx);
+			goto err_client;
+		}
+	}
+
 	ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
 	if (ret)
-		goto err_client;
+		goto err_fence;
 
 	/* the request owns the ref now */
 	i915_gem_context_unreference(ctx);
 
+	if (fd_fence_complete != -1) {
+		/*
+		 * Install the fence into the pre-allocated file
+		 * descriptor to the fence object so that user land
+		 * can wait on it...
+		 */
+		i915_install_sync_fence_fd(params->request,
+					   sync_fence, fd_fence_complete);
+
+		/* Return the fence through the rsvd2 field */
+		args->rsvd2 = fd_fence_wait | (((__u64) fd_fence_complete) << 32);
+	}
+
 	/*
 	 * The eb list is no longer required. The scheduler has extracted all
 	 * the information than needs to persist.
@@ -1776,6 +1864,12 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	return 0;
 
+err_fence:
+	if (fd_fence_complete != -1) {
+		sync_fence_put(sync_fence);
+		put_unused_fd(fd_fence_complete);
+	}
+
 err_client:
 	if (req->file_priv)
 		i915_gem_request_remove_from_client(req);
@@ -1939,11 +2033,6 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (args->rsvd2 != 0) {
-		DRM_DEBUG("dirty rvsd2 field\n");
-		return -EINVAL;
-	}
-
 	/* Throttle batch requests per device file */
 	if (i915_scheduler_file_queue_wait(file))
 		return -EAGAIN;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 0e87551db1b7..88af8ea4370a 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -250,7 +250,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_HWS_ADDR		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
 #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	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, 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)
@@ -701,7 +701,7 @@ struct drm_i915_gem_exec_object2 {
 	__u64 flags;
 
 	__u64 rsvd1;
-	__u64 rsvd2;
+	__u64 rsvd2;	/* Used for fence fd */
 };
 
 struct drm_i915_gem_execbuffer2 {
@@ -784,7 +784,17 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_RESOURCE_STREAMER     (1<<15)
 
-#define __I915_EXEC_UNKNOWN_FLAGS -(I915_EXEC_RESOURCE_STREAMER<<1)
+/** Caller supplies a sync fence fd in the rsvd2 field.
+ * Wait for it to be signalled before starting the work
+ */
+#define I915_EXEC_WAIT_FENCE		(1<<16)
+
+/** Caller wants a sync fence fd for this execbuffer.
+ *  It will be returned in rsvd2
+ */
+#define I915_EXEC_CREATE_FENCE		(1<<17)
+
+#define __I915_EXEC_UNKNOWN_FLAGS -(I915_EXEC_CREATE_FENCE<<1)
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \