1 files changed, 117 insertions, 54 deletions

diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index cd59a5918038..d41e5a6bbee0 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -8,23 +8,69 @@
 
 #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 *
-msm_fence_context_alloc(struct drm_device *dev, const char *name)
+msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
+		const char *name)
 {
 	struct msm_fence_context *fctx;
+	static int index = 0;
 
 	fctx = kzalloc(sizeof(*fctx), GFP_KERNEL);
 	if (!fctx)
 		return ERR_PTR(-ENOMEM);
 
 	fctx->dev = dev;
-	strncpy(fctx->name, name, sizeof(fctx->name));
+	strscpy(fctx->name, name, sizeof(fctx->name));
 	fctx->context = dma_fence_context_alloc(1);
-	init_waitqueue_head(&fctx->event);
+	fctx->index = index++;
+	fctx->fenceptr = fenceptr;
 	spin_lock_init(&fctx->spinlock);
 
+	/*
+	 * Start out close to the 32b fence rollover point, so we can
+	 * catch bugs with fence comparisons.
+	 */
+	fctx->last_fence = 0xffffff00;
+	fctx->completed_fence = fctx->last_fence;
+	*fctx->fenceptr = fctx->last_fence;
+
+	hrtimer_setup(&fctx->deadline_timer, deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+
+	kthread_init_work(&fctx->deadline_work, deadline_work);
+
+	fctx->next_deadline = ktime_get();
+
 	return fctx;
 }
 
@@ -33,58 +79,27 @@ void msm_fence_context_free(struct msm_fence_context *fctx)
 	kfree(fctx);
 }
 
-static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fence)
+bool msm_fence_completed(struct msm_fence_context *fctx, uint32_t fence)
 {
-	return (int32_t)(fctx->completed_fence - fence) >= 0;
+	/*
+	 * Note: Check completed_fence first, as fenceptr is in a write-combine
+	 * mapping, so it will be more expensive to read.
+	 */
+	return (int32_t)(fctx->completed_fence - fence) >= 0 ||
+		(int32_t)(*fctx->fenceptr - fence) >= 0;
 }
 
-/* legacy path for WAIT_FENCE ioctl: */
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible)
-{
-	int ret;
-
-	if (fence > fctx->last_fence) {
-		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
-				fctx->name, fence, fctx->last_fence);
-		return -EINVAL;
-	}
-
-	if (!timeout) {
-		/* no-wait: */
-		ret = fence_completed(fctx, fence) ? 0 : -EBUSY;
-	} else {
-		unsigned long remaining_jiffies = timeout_to_jiffies(timeout);
-
-		if (interruptible)
-			ret = wait_event_interruptible_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-		else
-			ret = wait_event_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-
-		if (ret == 0) {
-			DBG("timeout waiting for fence: %u (completed: %u)",
-					fence, fctx->completed_fence);
-			ret = -ETIMEDOUT;
-		} else if (ret != -ERESTARTSYS) {
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-
-/* called from workqueue */
+/* called from irq handler and workqueue (in recover path) */
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 {
-	spin_lock(&fctx->spinlock);
-	fctx->completed_fence = max(fence, fctx->completed_fence);
-	spin_unlock(&fctx->spinlock);
-
-	wake_up_all(&fctx->event);
+	unsigned long flags;
+
+	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);
 }
 
 struct msm_fence {
@@ -111,17 +126,53 @@ static const char *msm_fence_get_timeline_name(struct dma_fence *fence)
 static bool msm_fence_signaled(struct dma_fence *fence)
 {
 	struct msm_fence *f = to_msm_fence(fence);
-	return fence_completed(f->fctx, f->base.seqno);
+	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 *
-msm_fence_alloc(struct msm_fence_context *fctx)
+msm_fence_alloc(void)
 {
 	struct msm_fence *f;
 
@@ -129,10 +180,22 @@ msm_fence_alloc(struct msm_fence_context *fctx)
 	if (!f)
 		return ERR_PTR(-ENOMEM);
 
+	return &f->base;
+}
+
+void
+msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
+{
+	struct msm_fence *f = to_msm_fence(fence);
+
 	f->fctx = fctx;
 
+	/*
+	 * Until this point, the fence was just some pre-allocated memory,
+	 * no-one should have taken a reference to it yet.
+	 */
+	WARN_ON(kref_read(&fence->refcount));
+
 	dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
 		       fctx->context, ++fctx->last_fence);
-
-	return &f->base;
 }