/**
* 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 && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
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) {
dma_unmap_page(device->dev, dma_dest, len,
DMA_FROM_DEVICE);
dma_unmap_page(device->dev, dma_src, len,
DMA_TO_DEVICE);
}
}
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(src_buf, KM_USER1);
kunmap_atomic(dest_buf, KM_USER0);
async_tx_sync_epilog(submit);
}
return tx;
}
/**
* 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;
struct dmaengine_unmap_data *unmap = NULL;
if (device)
unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
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;
unmap->to_cnt = 1;
unmap->addr[0] = dma_map_page(device->dev, src, src_offset, len,
DMA_TO_DEVICE);
unmap->from_cnt = 1;
unmap->addr[1] = dma_map_page(device->dev, dest, dest_offset, len,
DMA_FROM_DEVICE);
unmap->len = len;
tx = device->device_prep_dma_memcpy(chan, unmap->addr[1],
unmap->addr[0], len,
dma_prep_flags);
}
if (tx) {
pr_debug("%s: (async) len: %zu\n", __func__, len);
dma_set_unmap(tx, unmap);
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) + dest_offset;
src_buf = kmap_atomic(src) + src_offset;
memcpy(dest_buf, src_buf, len);
kunmap_atomic(src_buf);
kunmap_atomic(dest_buf);
async_tx_sync_epilog(submit);
}
dmaengine_unmap_put(unmap);
return tx;
}
static ssize_t perf_copy(struct pthr_ctx *pctx, char __iomem *dst,
char *src, size_t size)
{
struct perf_ctx *perf = pctx->perf;
struct dma_async_tx_descriptor *txd;
struct dma_chan *chan = pctx->dma_chan;
struct dma_device *device;
struct dmaengine_unmap_data *unmap;
dma_cookie_t cookie;
size_t src_off, dst_off;
struct perf_mw *mw = &perf->mw;
void __iomem *vbase;
void __iomem *dst_vaddr;
dma_addr_t dst_phys;
int retries = 0;
if (!use_dma) {
memcpy_toio(dst, src, size);
return size;
}
if (!chan) {
dev_err(&perf->ntb->dev, "DMA engine does not exist\n");
return -EINVAL;
}
device = chan->device;
src_off = (uintptr_t)src & ~PAGE_MASK;
dst_off = (uintptr_t __force)dst & ~PAGE_MASK;
if (!is_dma_copy_aligned(device, src_off, dst_off, size))
return -ENODEV;
vbase = mw->vbase;
dst_vaddr = dst;
dst_phys = mw->phys_addr + (dst_vaddr - vbase);
unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
if (!unmap)
return -ENOMEM;
unmap->len = size;
unmap->addr[0] = dma_map_page(device->dev, virt_to_page(src),
src_off, size, DMA_TO_DEVICE);
if (dma_mapping_error(device->dev, unmap->addr[0]))
goto err_get_unmap;
unmap->to_cnt = 1;
do {
txd = device->device_prep_dma_memcpy(chan, dst_phys,
unmap->addr[0],
size, DMA_PREP_INTERRUPT);
if (!txd) {
set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout(DMA_OUT_RESOURCE_TO);
}
} while (!txd && (++retries < DMA_RETRIES));
if (!txd) {
pctx->dma_prep_err++;
goto err_get_unmap;
}
txd->callback = perf_copy_callback;
txd->callback_param = pctx;
dma_set_unmap(txd, unmap);
cookie = dmaengine_submit(txd);
if (dma_submit_error(cookie))
goto err_set_unmap;
dmaengine_unmap_put(unmap);
atomic_inc(&pctx->dma_sync);
dma_async_issue_pending(chan);
return size;
err_set_unmap:
dmaengine_unmap_put(unmap);
err_get_unmap:
dmaengine_unmap_put(unmap);
return 0;
}
