path: root/drivers/dma-buf/dma-fence.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Fence mechanism for dma-buf and to allow for asynchronous dma access
 *
 * Copyright (C) 2012 Canonical Ltd
 * Copyright (C) 2012 Texas Instruments
 *
 * Authors:
 * Rob Clark <robdclark@gmail.com>
 * Maarten Lankhorst <maarten.lankhorst@canonical.com>
 */

#include <linux/slab.h>
#include <linux/export.h>
#include <linux/atomic.h>
#include <linux/dma-fence.h>
#include <linux/sched/signal.h>

#define CREATE_TRACE_POINTS
#include <trace/events/dma_fence.h>

EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit);
EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal);
EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled);

static DEFINE_SPINLOCK(dma_fence_stub_lock);
static struct dma_fence dma_fence_stub;

/*
 * fence context counter: each execution context should have its own
 * fence context, this allows checking if fences belong to the same
 * context or not. One device can have multiple separate contexts,
 * and they're used if some engine can run independently of another.
 */
static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1);

/**
 * DOC: DMA fences overview
 *
 * DMA fences, represented by &struct dma_fence, are the kernel internal
 * synchronization primitive for DMA operations like GPU rendering, video
 * encoding/decoding, or displaying buffers on a screen.
 *
 * A fence is initialized using dma_fence_init() and completed using
 * dma_fence_signal(). Fences are associated with a context, allocated through
 * dma_fence_context_alloc(), and all fences on the same context are
 * fully ordered.
 *
 * Since the purposes of fences is to facilitate cross-device and
 * cross-application synchronization, there's multiple ways to use one:
 *
 * - Individual fences can be exposed as a &sync_file, accessed as a file
 *   descriptor from userspace, created by calling sync_file_create(). This is
 *   called explicit fencing, since userspace passes around explicit
 *   synchronization points.
 *
 * - Some subsystems also have their own explicit fencing primitives, like
 *   &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying
 *   fence to be updated.
 *
 * - Then there's also implicit fencing, where the synchronization points are
 *   implicitly passed around as part of shared &dma_buf instances. Such
 *   implicit fences are stored in &struct dma_resv through the
 *   &dma_buf.resv pointer.
 */

static const char *dma_fence_stub_get_name(struct dma_fence *fence)
{
        return "stub";
}

static const struct dma_fence_ops dma_fence_stub_ops = {
	.get_driver_name = dma_fence_stub_get_name,
	.get_timeline_name = dma_fence_stub_get_name,
};

/**
 * dma_fence_get_stub - return a signaled fence
 *
 * Return a stub fence which is already signaled.
 */
struct dma_fence *dma_fence_get_stub(void)
{
	spin_lock(&dma_fence_stub_lock);
	if (!dma_fence_stub.ops) {
		dma_fence_init(&dma_fence_stub,
			       &dma_fence_stub_ops,
			       &dma_fence_stub_lock,
			       0, 0);
		dma_fence_signal_locked(&dma_fence_stub);
	}
	spin_unlock(&dma_fence_stub_lock);

	return dma_fence_get(&dma_fence_stub);
}
EXPORT_SYMBOL(dma_fence_get_stub);

/**
 * dma_fence_context_alloc - allocate an array of fence contexts
 * @num: amount of contexts to allocate
 *
 * This function will return the first index of the number of fence contexts
 * allocated.  The fence context is used for setting &dma_fence.context to a
 * unique number by passing the context to dma_fence_init().
 */
u64 dma_fence_context_alloc(unsigned num)
{
	WARN_ON(!num);
	return atomic64_add_return(num, &dma_fence_context_counter) - num;
}
EXPORT_SYMBOL(dma_fence_context_alloc);

/**
 * dma_fence_signal_locked - signal completion of a fence
 * @fence: the fence to signal
 *
 * Signal completion for software callbacks on a fence, this will unblock
 * dma_fence_wait() calls and run all the callbacks added with
 * dma_fence_add_callback(). Can be called multiple times, but since a fence
 * can only go from the unsignaled to the signaled state and not back, it will
 * only be effective the first time.
 *
 * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
 * held.
 *
 * Returns 0 on success and a negative error value when @fence has been
 * signalled already.
 */
int dma_fence_signal_locked(struct dma_fence *fence)
{
	struct dma_fence_cb *cur, *tmp;
	struct list_head cb_list;

	lockdep_assert_held(fence->lock);

	if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
				      &fence->flags)))
		return -EINVAL;

	/* Stash the cb_list before replacing it with the timestamp */
	list_replace(&fence->cb_list, &cb_list);

	fence->timestamp = ktime_get();
	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
	trace_dma_fence_signaled(fence);

	list_for_each_entry_safe(cur, tmp, &cb_list, node) {
		INIT_LIST_HEAD(&cur->node);
		cur->func(fence, cur);
	}

	return 0;
}
EXPORT_SYMBOL(dma_fence_signal_locked);

/**
 * dma_fence_signal - signal completion of a fence
 * @fence: the fence to signal
 *
 * Signal completion for software callbacks on a fence, this will unblock
 * dma_fence_wait() calls and run all the callbacks added with
 * dma_fence_add_callback(). Can be called multiple times, but since a fence
 * can only go from the unsignaled to the signaled state and not back, it will
 * only be effective the first time.
 *
 * Returns 0 on success and a negative error value when @fence has been
 * signalled already.
 */
int dma_fence_signal(struct dma_fence *fence)
{
	unsigned long flags;
	int ret;

	if (!fence)
		return -EINVAL;

	spin_lock_irqsave(fence->lock, flags);
	ret = dma_fence_signal_locked(fence);
	spin_unlock_irqrestore(fence->lock, flags);

	return ret;
}
EXPORT_SYMBOL(dma_fence_signal);

/**
 * dma_fence_wait_timeout - sleep until the fence gets signaled
 * or until timeout elapses
 * @fence: the fence to wait on
 * @intr: if true, do an interruptible wait
 * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
 *
 * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
 * remaining timeout in jiffies on success. Other error values may be
 * returned on custom implementations.
 *
 * Performs a synchronous wait on this fence. It is assumed the caller
 * directly or indirectly (buf-mgr between reservation and committing)
 * holds a reference to the fence, otherwise the fence might be
 * freed before return, resulting in undefined behavior.
 *
 * See also dma_fence_wait() and dma_fence_wait_any_timeout().
 */
signed long
dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
{
	signed long ret;

	if (WARN_ON(timeout < 0))
		return -EINVAL;

	trace_dma_fence_wait_start(fence);
	if (fence->ops->wait)
		ret = fence->ops->wait(fence, intr, timeout);
	else
		ret = dma_fence_default_wait(fence, intr, timeout);
	trace_dma_fence_wait_end(fence);
	return ret;
}
EXPORT_SYMBOL(dma_fence_wait_timeout);

/**
 * dma_fence_release - default relese function for fences
 * @kref: &dma_fence.recfount
 *
 * This is the default release functions for &dma_fence. Drivers shouldn't call
 * this directly, but instead call dma_fence_put().
 */
void dma_fence_release(struct kref *kref)
{
	struct dma_fence *fence =
		container_of(kref, struct dma_fence, refcount);

	trace_dma_fence_destroy(fence);

	if (WARN(!list_empty(&fence->cb_list) &&
		 !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags),
		 "Fence %s:%s:%llx:%llx released with pending signals!\n",
		 fence->ops->get_driver_name(fence),
		 fence->ops->get_timeline_name(fence),
		 fence->context, fence->seqno)) {
		unsigned long flags;

		/*
		 * Failed to signal before release, likely a refcounting issue.
		 *
		 * This should never happen, but if it does make sure that we
		 * don't leave chains dangling. We set the error flag first
		 * so that the callbacks know this signal is due to an error.
		 */
		spin_lock_irqsave(fence->lock, flags);
		fence->error = -EDEADLK;
		dma_fence_signal_locked(fence);
		spin_unlock_irqrestore(fence->lock, flags);
	}

	if (fence->ops->release)
		fence->ops->release(fence);
	else
		dma_fence_free(fence);
}
EXPORT_SYMBOL(dma_fence_release);

/**
 * dma_fence_free - default release function for &dma_fence.
 * @fence: fence to release
 *
 * This is the default implementation for &dma_fence_ops.release. It calls
 * kfree_rcu() on @fence.
 */
void dma_fence_free(struct dma_fence *fence)
{
	kfree_rcu(fence, rcu);
}
EXPORT_SYMBOL(dma_fence_free);

static bool __dma_fence_enable_signaling(struct dma_fence *fence)
{
	bool was_set;

	lockdep_assert_held(fence->lock);

	was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
				   &fence->flags);

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		return false;

	if (!was_set && fence->ops->enable_signaling) {
		trace_dma_fence_enable_signal(fence);

		if (!fence->ops->enable_signaling(fence)) {
			dma_fence_signal_locked(fence);
			return false;
		}
	}

	return true;
}

/**
 * dma_fence_enable_sw_signaling - enable signaling on fence
 * @fence: the fence to enable
 *
 * This will request for sw signaling to be enabled, to make the fence
 * complete as soon as possible. This calls &dma_fence_ops.enable_signaling
 * internally.
 */
void dma_fence_enable_sw_signaling(struct dma_fence *fence)
{
	unsigned long flags;

	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
		return;

	spin_lock_irqsave(fence->lock, flags);
	__dma_fence_enable_signaling(fence);
	spin_unlock_irqrestore(fence->lock, flags);
}