[PATCH 1/6] dma-buf: Proxy fence, an unsignaled fence placeholder

[Chris Wilson]

Often we need to create a fence for a future event that has not yet been
associated with a fence. We can store a proxy fence, a placeholder, in
the timeline and replace it later when the real fence is known. Any
listeners that attach to the proxy fence will automatically be signaled
when the real fence completes, and any future listeners will instead be
attach directly to the real fence avoiding any indirection overhead.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
---
 drivers/dma-buf/Makefile          |  10 +-
 drivers/dma-buf/dma-fence-proxy.c | 170 ++++++++++++++++++++++++++++++
 include/linux/dma-fence-proxy.h   |  18 ++++
 3 files changed, 196 insertions(+), 2 deletions(-)
 create mode 100644 drivers/dma-buf/dma-fence-proxy.c
 create mode 100644 include/linux/dma-fence-proxy.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 9c190026bfab..5599803b0ebd 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,6 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
-	 dma-resv.o seqno-fence.o
+obj-y := \
+	dma-buf.o \
+	dma-fence.o \
+	dma-fence-array.o \
+	dma-fence-chain.o \
+	dma-fence-proxy.o \
+	dma-resv.o \
+	seqno-fence.o
 obj-$(CONFIG_DMABUF_HEAPS)	+= dma-heap.o
 obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
diff --git a/drivers/dma-buf/dma-fence-proxy.c b/drivers/dma-buf/dma-fence-proxy.c
new file mode 100644
index 000000000000..8881171e3932
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-proxy.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * dma-fence-proxy: placeholder unsignaled fence
+ *
+ * Copyright (C) 2017-2019 Intel Corporation
+ */
+
+#include <linux/dma-fence.h>
+#include <linux/dma-fence-proxy.h>
+#include <linux/export.h>
+#include <linux/irq_work.h>
+#include <linux/slab.h>
+
+struct dma_fence_proxy {
+	struct dma_fence base;
+	spinlock_t lock;
+
+	struct dma_fence *real;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+static const char *proxy_get_driver_name(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	return real ? real->ops->get_driver_name(real) : "proxy";
+}
+
+static const char *proxy_get_timeline_name(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	return real ? real->ops->get_timeline_name(real) : "unset";
+}
+
+static void proxy_irq_work(struct irq_work *work)
+{
+	struct dma_fence_proxy *p = container_of(work, typeof(*p), work);
+
+	dma_fence_signal(&p->base);
+	dma_fence_put(&p->base);
+}
+
+static void proxy_callback(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct dma_fence_proxy *p = container_of(cb, typeof(*p), cb);
+
+	/* beware the alleged spinlock inversion */
+	irq_work_queue(&p->work);
+}
+
+static bool proxy_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	if (!real)
+		return true;
+
+	if (dma_fence_add_callback(real, &p->cb, proxy_callback))
+		return false;
+
+	dma_fence_get(fence);
+	return true;
+}
+
+static bool proxy_signaled(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	return real ? dma_fence_is_signaled(real) : false;
+}
+
+static void proxy_release(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+
+	dma_fence_put(p->real);
+	dma_fence_free(&p->base);
+}
+
+static const struct dma_fence_ops dma_fence_proxy_ops = {
+	.get_driver_name = proxy_get_driver_name,
+	.get_timeline_name = proxy_get_timeline_name,
+	.enable_signaling = proxy_enable_signaling,
+	.signaled = proxy_signaled,
+	.wait = dma_fence_default_wait,
+	.release = proxy_release,
+};
+
+/**
+ * dma_fence_create_proxy - Create an unset dma-fence
+ *
+ * dma_fence_create_proxy() creates a new dma_fence stub that is initially
+ * unsignaled and may later be replaced with a real fence. Any listeners
+ * to the proxy fence will be signaled when the target fence signals its
+ * completion.
+ */
+struct dma_fence *dma_fence_create_proxy(void)
+{
+	struct dma_fence_proxy *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return NULL;
+
+	spin_lock_init(&p->lock);
+	dma_fence_init(&p->base, &dma_fence_proxy_ops, &p->lock, 0, 0);
+	init_irq_work(&p->work, proxy_irq_work);
+
+	return &p->base;
+}
+EXPORT_SYMBOL(dma_fence_create_proxy);
+
+static void proxy_assign(struct dma_fence *fence, struct dma_fence *real)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	unsigned long flags;
+
+	if (fence == real)
+		return;
+
+	if (WARN_ON(p->real))
+		return;
+
+	spin_lock_irqsave(p->base.lock, flags);
+
+	p->real = dma_fence_get(real);
+
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &p->base.flags)) {
+		if (dma_fence_add_callback(real, &p->cb, proxy_callback))
+			dma_fence_signal_locked(&p->base);
+		else
+			dma_fence_get(&p->base);
+	} else if (dma_fence_is_signaled(real)) {
+		dma_fence_signal_locked(&p->base);
+	}
+
+	spin_unlock_irqrestore(p->base.lock, flags);
+}
+
+/**
+ * dma_fence_replace_proxy - Replace the proxy fence with the real target
+ * @slot: pointer to location of fence to update
+ * @fence: the new fence to store in @slot
+ *
+ * Once the real dma_fence is known, we can replace the proxy fence holder
+ * with a pointer to the real dma fence. Future listeners will attach to
+ * the real fence, avoiding any indirection overhead. Previous listeners
+ * will remain attached to the proxy fence, and be signaled in turn when
+ * the target fence completes.
+ */
+struct dma_fence *
+dma_fence_replace_proxy(struct dma_fence **slot, struct dma_fence *fence)
+{
+	struct dma_fence *old;
+
+	dma_fence_get(fence);
+
+	old = xchg(slot, fence);
+	if (old && old->ops == &dma_fence_proxy_ops)
+		proxy_assign(old, fence);
+
+	return old;
+}
+EXPORT_SYMBOL(dma_fence_replace_proxy);
diff --git a/include/linux/dma-fence-proxy.h b/include/linux/dma-fence-proxy.h
new file mode 100644
index 000000000000..244b12a80c65
--- /dev/null
+++ b/include/linux/dma-fence-proxy.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * dma-fence-proxy: allows waiting upon unset and future fences
+ *
+ * Copyright (C) 2017 Intel Corporation
+ */
+
+#ifndef __LINUX_DMA_FENCE_PROXY_H
+#define __LINUX_DMA_FENCE_PROXY_H
+
+struct dma_fence;
+
+struct dma_fence *dma_fence_create_proxy(void);
+
+struct dma_fence *
+dma_fence_replace_proxy(struct dma_fence **slot, struct dma_fence *fence);
+
+#endif /* __LINUX_DMA_FENCE_PROXY_H */
-- 
2.25.1