[PATCH 2/3] dma-buf/fence: add fence_array fences v5

[Daniel Vetter]

On Mon, May 23, 2016 at 01:25:21PM +0200, Christian König wrote:
> From: Gustavo Padovan <gustavo.padovan at collabora.co.uk>
> 
> struct fence_collection inherits from struct fence and carries a
> collection of fences that needs to be waited together.
> 
> It is useful to translate a sync_file to a fence to remove the complexity
> of dealing with sync_files on DRM drivers. So even if there are many
> fences in the sync_file that needs to waited for a commit to happen,
> they all get added to the fence_collection and passed for DRM use as
> a standard struct fence.
> 
> That means that no changes needed to any driver besides supporting fences.
> 
> fence_collection's fence doesn't belong to any timeline context, so
> fence_is_later() and fence_later() are not meant to be called with
> fence_collections fences.
> 
> v2: Comments by Daniel Vetter:
> 	- merge fence_collection_init() and fence_collection_add()
> 	- only add callbacks at ->enable_signalling()
> 	- remove fence_collection_put()
> 	- check for type on to_fence_collection()
> 	- adjust fence_is_later() and fence_later() to WARN_ON() if they
> 	are used with collection fences.
> 
> v3: - Initialize fence_cb.node at fence init.
> 
>     Comments by Chris Wilson:
> 	- return "unbound" on fence_collection_get_timeline_name()
> 	- don't stop adding callbacks if one fails
> 	- remove redundant !! on fence_collection_enable_signaling()
> 	- remove redundant () on fence_collection_signaled
> 	- use fence_default_wait() instead
> 
> v4 (chk): Rework, simplification and cleanup:
> 	- Drop FENCE_NO_CONTEXT handling, always allocate a context.
> 	- Rename to fence_array.
> 	- Return fixed driver name.
> 	- Register only one callback at a time.
> 	- Document that create function takes ownership of array.
> 
> v5 (chk): More work and fixes:
> 	- Avoid deadlocks by adding all callbacks at once again.
> 	- Stop trying to remove the callbacks.
> 	- Provide context and sequence number for the array fence.

That looks like even more a step backwards - I don't see how it's used in
your amdgpu code, but now callers need to either allocate a context
unconditionally (more boilerplate code) or do some fragile dance to figure
out whether maybe they can share the context with some other, previous
fence_array.

If you just want to avoid allocating a new context if all the fences in
the array are from the same one, then I'd say detect that and just return
that single fence directly (with an additional reference ofc).

Or I'm not entirely understanding things, or probably not at all ;-)
-Daniel

> 
> Signed-off-by: Gustavo Padovan <gustavo.padovan at collabora.co.uk>
> Signed-off-by: Christian König <christian.koenig at amd.com>
> ---
>  drivers/dma-buf/Makefile      |   2 +-
>  drivers/dma-buf/fence-array.c | 127 ++++++++++++++++++++++++++++++++++++++++++
>  include/linux/fence-array.h   |  72 ++++++++++++++++++++++++
>  3 files changed, 200 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/dma-buf/fence-array.c
>  create mode 100644 include/linux/fence-array.h
> 
> diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
> index 57a675f..85f6928 100644
> --- a/drivers/dma-buf/Makefile
> +++ b/drivers/dma-buf/Makefile
> @@ -1 +1 @@
> -obj-y := dma-buf.o fence.o reservation.o seqno-fence.o
> +obj-y := dma-buf.o fence.o reservation.o seqno-fence.o fence-array.o
> diff --git a/drivers/dma-buf/fence-array.c b/drivers/dma-buf/fence-array.c
> new file mode 100644
> index 0000000..bbcf79f
> --- /dev/null
> +++ b/drivers/dma-buf/fence-array.c
> @@ -0,0 +1,127 @@
> +/*
> + * fence-array: aggregate fences to be waited together
> + *
> + * Copyright (C) 2016 Collabora Ltd
> + * Copyright (C) 2016 Advanced Micro Devices, Inc.
> + * Authors:
> + *	Gustavo Padovan <gustavo at padovan.org>
> + *	Christian König <christian.koenig at amd.com>
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms of the GNU General Public License version 2 as published by
> + * the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + */
> +
> +#include <linux/export.h>
> +#include <linux/slab.h>
> +#include <linux/fence-array.h>
> +
> +static void fence_array_cb_func(struct fence *f, struct fence_cb *cb);
> +
> +static const char *fence_array_get_driver_name(struct fence *fence)
> +{
> +	return "fence_array";
> +}
> +
> +static const char *fence_array_get_timeline_name(struct fence *fence)
> +{
> +	return "unbound";
> +}
> +
> +static void fence_array_cb_func(struct fence *f, struct fence_cb *cb)
> +{
> +	struct fence_array_cb *array_cb =
> +		container_of(cb, struct fence_array_cb, cb);
> +	struct fence_array *array = array_cb->array;
> +
> +	if (atomic_dec_and_test(&array->num_pending))
> +		fence_signal(&array->base);
> +}
> +
> +static bool fence_array_enable_signaling(struct fence *fence)
> +{
> +	struct fence_array *array = to_fence_array(fence);
> +	struct fence_array_cb *cb = (void *)(&array[1]);
> +	unsigned i;
> +
> +	for (i = 0; i < array->num_fences; ++i) {
> +		cb[i].array = array;
> +		if (!fence_add_callback(array->fences[i], &cb[i].cb,
> +					fence_array_cb_func))
> +			if (atomic_dec_and_test(&array->num_pending))
> +				return false;
> +	}
> +
> +	return true;
> +}
> +
> +static bool fence_array_signaled(struct fence *fence)
> +{
> +	struct fence_array *array = to_fence_array(fence);
> +
> +	return atomic_read(&array->num_pending) == 0;
> +}
> +
> +static void fence_array_release(struct fence *fence)
> +{
> +	struct fence_array *array = to_fence_array(fence);
> +	unsigned i;
> +
> +	for (i = 0; i < array->num_fences; ++i)
> +		fence_put(array->fences[i]);
> +
> +	kfree(array->fences);
> +	fence_free(fence);
> +}
> +
> +const struct fence_ops fence_array_ops = {
> +	.get_driver_name = fence_array_get_driver_name,
> +	.get_timeline_name = fence_array_get_timeline_name,
> +	.enable_signaling = fence_array_enable_signaling,
> +	.signaled = fence_array_signaled,
> +	.wait = fence_default_wait,
> +	.release = fence_array_release,
> +};
> +
> +/**
> + * fence_array_create - Create a custom fence array
> + * @num_fences:	[in]	number of fences to add in the array
> + * @fences:	[in]	array containing the fences
> + * @context:	[in]	fence context to use
> + * @seqno:	[in]	sequence number to use
> + *
> + * Allocate a fence_array object and initialize the base fence with fence_init().
> + * In case of error it returns NULL.
> + *
> + * The caller should allocte the fences array with num_fences size
> + * and fill it with the fences it wants to add to the object. Ownership of this
> + * array is take and fence_put() is used on each fence on release.
> + */
> +struct fence_array *fence_array_create(int num_fences, struct fence **fences,
> +				       u64 context, unsigned seqno)
> +{
> +	struct fence_array *array;
> +	size_t size = sizeof(*array);
> +
> +	/* Allocate the callback structures behind the array. */
> +	size += num_fences * sizeof(struct fence_array_cb);
> +	array = kzalloc(size, GFP_KERNEL);
> +	if (!array)
> +		return NULL;
> +
> +	spin_lock_init(&array->lock);
> +	fence_init(&array->base, &fence_array_ops, &array->lock,
> +		   context, seqno);
> +
> +	array->num_fences = num_fences;
> +	atomic_set(&array->num_pending, num_fences);
> +	array->fences = fences;
> +
> +	return array;
> +}
> +EXPORT_SYMBOL(fence_array_create);
> diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h
> new file mode 100644
> index 0000000..593ab98
> --- /dev/null
> +++ b/include/linux/fence-array.h
> @@ -0,0 +1,72 @@
> +/*
> + * fence-array: aggregates fence to be waited together
> + *
> + * Copyright (C) 2016 Collabora Ltd
> + * Copyright (C) 2016 Advanced Micro Devices, Inc.
> + * Authors:
> + *	Gustavo Padovan <gustavo at padovan.org>
> + *	Christian König <christian.koenig at amd.com>
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms of the GNU General Public License version 2 as published by
> + * the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
> + * more details.
> + */
> +
> +#ifndef __LINUX_FENCE_ARRAY_H
> +#define __LINUX_FENCE_ARRAY_H
> +
> +#include <linux/fence.h>
> +
> +/**
> + * struct fence_array_cb - callback helper for fence array
> + * @cb: fence callback structure for signaling
> + * @array: reference to the parent fence array object
> + */
> +struct fence_array_cb {
> +	struct fence_cb cb;
> +	struct fence_array *array;
> +};
> +
> +/**
> + * struct fence_array - fence to represent an array of fences
> + * @base: fence base class
> + * @lock: spinlock for fence handling
> + * @num_fences: number of fences in the array
> + * @num_pending: fences in the array still pending
> + * @fences: array of the fences
> + */
> +struct fence_array {
> +	struct fence base;
> +
> +	spinlock_t lock;
> +	unsigned num_fences;
> +	atomic_t num_pending;
> +	struct fence **fences;
> +};
> +
> +extern const struct fence_ops fence_array_ops;
> +
> +/**
> + * to_fence_array - cast a fence to a fence_array
> + * @fence: fence to cast to a fence_array
> + *
> + * Returns NULL if the fence is not a fence_array,
> + * or the fence_array otherwise.
> + */
> +static inline struct fence_array *to_fence_array(struct fence *fence)
> +{
> +	if (fence->ops != &fence_array_ops)
> +		return NULL;
> +
> +	return container_of(fence, struct fence_array, base);
> +}
> +
> +struct fence_array *fence_array_create(int num_fences, struct fence **fences,
> +				       u64 context, unsigned seqno);
> +
> +#endif /* __LINUX_FENCE_ARRAY_H */
> -- 
> 2.5.0
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch