[PATCH v5 00/14] dma-fence: Deadline awareness

[PATCH v5 00/14] dma-fence: Deadline awareness

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

This series adds a deadline hint to fences, so realtime deadlines
such as vblank can be communicated to the fence signaller for power/
frequency management decisions.

This is partially inspired by a trick i915 does, but implemented
via dma-fence for a couple of reasons:

1) To continue to be able to use the atomic helpers
2) To support cases where display and gpu are different drivers

This iteration adds a dma-fence ioctl to set a deadline (both to
support igt-tests, and compositors which delay decisions about which
client buffer to display), and a sw_sync ioctl to read back the
deadline.  IGT tests utilizing these can be found at:

  https://gitlab.freedesktop.org/robclark/igt-gpu-tools/-/commits/fence-deadline


v1: https://patchwork.freedesktop.org/series/93035/
v2: Move filtering out of later deadlines to fence implementation
    to avoid increasing the size of dma_fence
v3: Add support in fence-array and fence-chain; Add some uabi to
    support igt tests and userspace compositors.
v4: Rebase, address various comments, and add syncobj deadline
    support, and sync_file EPOLLPRI based on experience with perf/
    freq issues with clvk compute workloads on i915 (anv)
v5: Clarify that this is a hint as opposed to a more hard deadline
    guarantee, switch to using u64 ns values in UABI (still absolute
    CLOCK_MONOTONIC values), drop syncobj related cap and driver
    feature flag in favor of allowing count_handles==0 for probing
    kernel support.

Rob Clark (14):
  dma-buf/dma-fence: Add deadline awareness
  dma-buf/fence-array: Add fence deadline support
  dma-buf/fence-chain: Add fence deadline support
  dma-buf/dma-resv: Add a way to set fence deadline
  dma-buf/sync_file: Add SET_DEADLINE ioctl
  dma-buf/sync_file: Support (E)POLLPRI
  dma-buf/sw_sync: Add fence deadline support
  drm/scheduler: Add fence deadline support
  drm/syncobj: Add deadline support for syncobj waits
  drm/vblank: Add helper to get next vblank time
  drm/atomic-helper: Set fence deadline for vblank
  drm/msm: Add deadline based boost support
  drm/msm: Add wait-boost support
  drm/i915: Add deadline based boost support

 drivers/dma-buf/dma-fence-array.c       | 11 ++++
 drivers/dma-buf/dma-fence-chain.c       | 13 +++++
 drivers/dma-buf/dma-fence.c             | 21 +++++++
 drivers/dma-buf/dma-resv.c              | 22 ++++++++
 drivers/dma-buf/sw_sync.c               | 58 +++++++++++++++++++
 drivers/dma-buf/sync_debug.h            |  2 +
 drivers/dma-buf/sync_file.c             | 27 +++++++++
 drivers/gpu/drm/drm_atomic_helper.c     | 36 ++++++++++++
 drivers/gpu/drm/drm_syncobj.c           | 59 +++++++++++++++-----
 drivers/gpu/drm/drm_vblank.c            | 32 +++++++++++
 drivers/gpu/drm/i915/i915_request.c     | 20 +++++++
 drivers/gpu/drm/msm/msm_drv.c           | 12 ++--
 drivers/gpu/drm/msm/msm_fence.c         | 74 +++++++++++++++++++++++++
 drivers/gpu/drm/msm/msm_fence.h         | 20 +++++++
 drivers/gpu/drm/msm/msm_gem.c           |  5 ++
 drivers/gpu/drm/scheduler/sched_fence.c | 46 +++++++++++++++
 drivers/gpu/drm/scheduler/sched_main.c  |  2 +-
 include/drm/drm_vblank.h                |  1 +
 include/drm/gpu_scheduler.h             |  8 +++
 include/linux/dma-fence.h               | 20 +++++++
 include/linux/dma-resv.h                |  2 +
 include/uapi/drm/drm.h                  |  5 ++
 include/uapi/drm/msm_drm.h              | 14 ++++-
 include/uapi/linux/sync_file.h          | 23 ++++++++
 24 files changed, 513 insertions(+), 20 deletions(-)

-- 
2.39.1

[PATCH v5 12/14] drm/msm: Add deadline based boost support

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Track the nearest deadline on a fence timeline and set a timer to expire
shortly before to trigger boost if the fence has not yet been signaled.

v2: rebase

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_fence.c | 74 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/msm_fence.h | 20 +++++++++
 2 files changed, 94 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index 56641408ea74..51b461f32103 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -8,6 +8,35 @@
 
 #include "msm_drv.h"
 #include "msm_fence.h"
+#include "msm_gpu.h"
+
+static struct msm_gpu *fctx2gpu(struct msm_fence_context *fctx)
+{
+	struct msm_drm_private *priv = fctx->dev->dev_private;
+	return priv->gpu;
+}
+
+static enum hrtimer_restart deadline_timer(struct hrtimer *t)
+{
+	struct msm_fence_context *fctx = container_of(t,
+			struct msm_fence_context, deadline_timer);
+
+	kthread_queue_work(fctx2gpu(fctx)->worker, &fctx->deadline_work);
+
+	return HRTIMER_NORESTART;
+}
+
+static void deadline_work(struct kthread_work *work)
+{
+	struct msm_fence_context *fctx = container_of(work,
+			struct msm_fence_context, deadline_work);
+
+	/* If deadline fence has already passed, nothing to do: */
+	if (msm_fence_completed(fctx, fctx->next_deadline_fence))
+		return;
+
+	msm_devfreq_boost(fctx2gpu(fctx), 2);
+}
 
 
 struct msm_fence_context *
@@ -36,6 +65,13 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
 	fctx->completed_fence = fctx->last_fence;
 	*fctx->fenceptr = fctx->last_fence;
 
+	hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	fctx->deadline_timer.function = deadline_timer;
+
+	kthread_init_work(&fctx->deadline_work, deadline_work);
+
+	fctx->next_deadline = ktime_get();
+
 	return fctx;
 }
 
@@ -62,6 +98,8 @@ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 	spin_lock_irqsave(&fctx->spinlock, flags);
 	if (fence_after(fence, fctx->completed_fence))
 		fctx->completed_fence = fence;
+	if (msm_fence_completed(fctx, fctx->next_deadline_fence))
+		hrtimer_cancel(&fctx->deadline_timer);
 	spin_unlock_irqrestore(&fctx->spinlock, flags);
 }
 
@@ -92,10 +130,46 @@ static bool msm_fence_signaled(struct dma_fence *fence)
 	return msm_fence_completed(f->fctx, f->base.seqno);
 }
 
+static void msm_fence_set_deadline(struct dma_fence *fence, ktime_t deadline)
+{
+	struct msm_fence *f = to_msm_fence(fence);
+	struct msm_fence_context *fctx = f->fctx;
+	unsigned long flags;
+	ktime_t now;
+
+	spin_lock_irqsave(&fctx->spinlock, flags);
+	now = ktime_get();
+
+	if (ktime_after(now, fctx->next_deadline) ||
+			ktime_before(deadline, fctx->next_deadline)) {
+		fctx->next_deadline = deadline;
+		fctx->next_deadline_fence =
+			max(fctx->next_deadline_fence, (uint32_t)fence->seqno);
+
+		/*
+		 * Set timer to trigger boost 3ms before deadline, or
+		 * if we are already less than 3ms before the deadline
+		 * schedule boost work immediately.
+		 */
+		deadline = ktime_sub(deadline, ms_to_ktime(3));
+
+		if (ktime_after(now, deadline)) {
+			kthread_queue_work(fctx2gpu(fctx)->worker,
+					&fctx->deadline_work);
+		} else {
+			hrtimer_start(&fctx->deadline_timer, deadline,
+					HRTIMER_MODE_ABS);
+		}
+	}
+
+	spin_unlock_irqrestore(&fctx->spinlock, flags);
+}
+
 static const struct dma_fence_ops msm_fence_ops = {
 	.get_driver_name = msm_fence_get_driver_name,
 	.get_timeline_name = msm_fence_get_timeline_name,
 	.signaled = msm_fence_signaled,
+	.set_deadline = msm_fence_set_deadline,
 };
 
 struct dma_fence *
diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
index 7f1798c54cd1..cdaebfb94f5c 100644
--- a/drivers/gpu/drm/msm/msm_fence.h
+++ b/drivers/gpu/drm/msm/msm_fence.h
@@ -52,6 +52,26 @@ struct msm_fence_context {
 	volatile uint32_t *fenceptr;
 
 	spinlock_t spinlock;
+
+	/*
+	 * TODO this doesn't really deal with multiple deadlines, like
+	 * if userspace got multiple frames ahead.. OTOH atomic updates
+	 * don't queue, so maybe that is ok
+	 */
+
+	/** next_deadline: Time of next deadline */
+	ktime_t next_deadline;
+
+	/**
+	 * next_deadline_fence:
+	 *
+	 * Fence value for next pending deadline.  The deadline timer is
+	 * canceled when this fence is signaled.
+	 */
+	uint32_t next_deadline_fence;
+
+	struct hrtimer deadline_timer;
+	struct kthread_work deadline_work;
 };
 
 struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
-- 
2.39.1

[PATCH v5 13/14] drm/msm: Add wait-boost support

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Add a way for various userspace waits to signal urgency.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c | 12 ++++++++----
 drivers/gpu/drm/msm/msm_gem.c |  5 +++++
 include/uapi/drm/msm_drm.h    | 14 ++++++++++++--
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index aca48c868c14..f6764a86b2da 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -46,6 +46,7 @@
  * - 1.8.0 - Add MSM_BO_CACHED_COHERENT for supported GPUs (a6xx)
  * - 1.9.0 - Add MSM_SUBMIT_FENCE_SN_IN
  * - 1.10.0 - Add MSM_SUBMIT_BO_NO_IMPLICIT
+ * - 1.11.0 - Add wait boost (MSM_WAIT_FENCE_BOOST, MSM_PREP_BOOST)
  */
 #define MSM_VERSION_MAJOR	1
 #define MSM_VERSION_MINOR	10
@@ -899,7 +900,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 }
 
 static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
-		      ktime_t timeout)
+		      ktime_t timeout, uint32_t flags)
 {
 	struct dma_fence *fence;
 	int ret;
@@ -929,6 +930,9 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
 	if (!fence)
 		return 0;
 
+	if (flags & MSM_WAIT_FENCE_BOOST)
+		dma_fence_set_deadline(fence, ktime_get());
+
 	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
 	if (ret == 0) {
 		ret = -ETIMEDOUT;
@@ -949,8 +953,8 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	struct msm_gpu_submitqueue *queue;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (args->flags & ~MSM_WAIT_FENCE_FLAGS) {
+		DRM_ERROR("invalid flags: %08x\n", args->flags);
 		return -EINVAL;
 	}
 
@@ -961,7 +965,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout), args->flags);
 
 	msm_submitqueue_put(queue);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 1dee0d18abbb..dd4a0d773f6e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -846,6 +846,11 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
 		op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout);
 	long ret;
 
+	if (op & MSM_PREP_BOOST) {
+		dma_resv_set_deadline(obj->resv, dma_resv_usage_rw(write),
+				      ktime_get());
+	}
+
 	ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write),
 				    true,  remain);
 	if (ret == 0)
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 329100016e7c..dbf0d6f43fa9 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -151,8 +151,13 @@ struct drm_msm_gem_info {
 #define MSM_PREP_READ        0x01
 #define MSM_PREP_WRITE       0x02
 #define MSM_PREP_NOSYNC      0x04
+#define MSM_PREP_BOOST       0x08
 
-#define MSM_PREP_FLAGS       (MSM_PREP_READ | MSM_PREP_WRITE | MSM_PREP_NOSYNC)
+#define MSM_PREP_FLAGS       (MSM_PREP_READ | \
+			      MSM_PREP_WRITE | \
+			      MSM_PREP_NOSYNC | \
+			      MSM_PREP_BOOST | \
+			      0)
 
 struct drm_msm_gem_cpu_prep {
 	__u32 handle;         /* in */
@@ -286,6 +291,11 @@ struct drm_msm_gem_submit {
 
 };
 
+#define MSM_WAIT_FENCE_BOOST	0x00000001
+#define MSM_WAIT_FENCE_FLAGS	( \
+		MSM_WAIT_FENCE_BOOST | \
+		0)
+
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
  * a buffer if you need to access it from the CPU (other cmdstream
  * submission from same or other contexts, PAGE_FLIP ioctl, etc, all
@@ -295,7 +305,7 @@ struct drm_msm_gem_submit {
  */
 struct drm_msm_wait_fence {
 	__u32 fence;          /* in */
-	__u32 pad;
+	__u32 flags;          /* in, bitmask of MSM_WAIT_FENCE_x */
 	struct drm_msm_timespec timeout;   /* in */
 	__u32 queueid;         /* in, submitqueue id */
 };
-- 
2.39.1