mirror of
https://github.com/torvalds/linux
synced 2024-09-20 19:17:24 +00:00
0403e38277
Some engines optimize operation by reading ahead in the descriptor chain such that descriptor2 may start execution before descriptor1 completes. If descriptor2 depends on the result from descriptor1 then a fence is required (on descriptor2) to disable this optimization. The async_tx api could implicitly identify dependencies via the 'depend_tx' parameter, but that would constrain cases where the dependency chain only specifies a completion order rather than a data dependency. So, provide an ASYNC_TX_FENCE to explicitly identify data dependencies. Signed-off-by: Dan Williams <dan.j.williams@intel.com>
99 lines
2.9 KiB
C
99 lines
2.9 KiB
C
/*
|
|
* copy offload engine support
|
|
*
|
|
* Copyright © 2006, Intel Corporation.
|
|
*
|
|
* Dan Williams <dan.j.williams@intel.com>
|
|
*
|
|
* with architecture considerations by:
|
|
* Neil Brown <neilb@suse.de>
|
|
* Jeff Garzik <jeff@garzik.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope 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.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc.,
|
|
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
|
|
*
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/dma-mapping.h>
|
|
#include <linux/async_tx.h>
|
|
|
|
/**
|
|
* async_memcpy - attempt to copy memory with a dma engine.
|
|
* @dest: destination page
|
|
* @src: src page
|
|
* @dest_offset: offset into 'dest' to start transaction
|
|
* @src_offset: offset into 'src' to start transaction
|
|
* @len: length in bytes
|
|
* @submit: submission / completion modifiers
|
|
*
|
|
* honored flags: ASYNC_TX_ACK
|
|
*/
|
|
struct dma_async_tx_descriptor *
|
|
async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
|
|
unsigned int src_offset, size_t len,
|
|
struct async_submit_ctl *submit)
|
|
{
|
|
struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMCPY,
|
|
&dest, 1, &src, 1, len);
|
|
struct dma_device *device = chan ? chan->device : NULL;
|
|
struct dma_async_tx_descriptor *tx = NULL;
|
|
|
|
if (device) {
|
|
dma_addr_t dma_dest, dma_src;
|
|
unsigned long dma_prep_flags = 0;
|
|
|
|
if (submit->cb_fn)
|
|
dma_prep_flags |= DMA_PREP_INTERRUPT;
|
|
if (submit->flags & ASYNC_TX_FENCE)
|
|
dma_prep_flags |= DMA_PREP_FENCE;
|
|
dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
|
|
DMA_FROM_DEVICE);
|
|
|
|
dma_src = dma_map_page(device->dev, src, src_offset, len,
|
|
DMA_TO_DEVICE);
|
|
|
|
tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
|
|
len, dma_prep_flags);
|
|
}
|
|
|
|
if (tx) {
|
|
pr_debug("%s: (async) len: %zu\n", __func__, len);
|
|
async_tx_submit(chan, tx, submit);
|
|
} else {
|
|
void *dest_buf, *src_buf;
|
|
pr_debug("%s: (sync) len: %zu\n", __func__, len);
|
|
|
|
/* wait for any prerequisite operations */
|
|
async_tx_quiesce(&submit->depend_tx);
|
|
|
|
dest_buf = kmap_atomic(dest, KM_USER0) + dest_offset;
|
|
src_buf = kmap_atomic(src, KM_USER1) + src_offset;
|
|
|
|
memcpy(dest_buf, src_buf, len);
|
|
|
|
kunmap_atomic(dest_buf, KM_USER0);
|
|
kunmap_atomic(src_buf, KM_USER1);
|
|
|
|
async_tx_sync_epilog(submit);
|
|
}
|
|
|
|
return tx;
|
|
}
|
|
EXPORT_SYMBOL_GPL(async_memcpy);
|
|
|
|
MODULE_AUTHOR("Intel Corporation");
|
|
MODULE_DESCRIPTION("asynchronous memcpy api");
|
|
MODULE_LICENSE("GPL");
|