/**
* do_async_pqxor - asynchronously calculate P and/or Q
*/
static struct dma_async_tx_descriptor *
do_async_pqxor(struct dma_device *device,
struct dma_chan *chan,
struct page *pdest, struct page *qdest,
struct page **src_list, unsigned char *scoef_list,
unsigned int offset, unsigned int src_cnt, size_t len,
enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct page *dest;
dma_addr_t dma_dest[2];
dma_addr_t *dma_src = (dma_addr_t *) src_list;
unsigned char *scf = qdest ? scoef_list : NULL;
struct dma_async_tx_descriptor *tx;
int i, dst_cnt = 0, zdst = flags & ASYNC_TX_XOR_ZERO_DST ? 1 : 0;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
if (flags & ASYNC_TX_XOR_ZERO_DST)
dma_prep_flags |= DMA_PREP_ZERO_DST;
/* One parity (P or Q) calculation is initiated always;
* first always try Q
*/
dest = qdest ? qdest : pdest;
dma_dest[dst_cnt++] = dma_map_page(device->dev, dest, offset, len,
DMA_FROM_DEVICE);
/* Switch to the next destination */
if (qdest && pdest) {
/* Both destinations are set, thus here we deal with P */
dma_dest[dst_cnt++] = dma_map_page(device->dev, pdest, offset,
len, DMA_FROM_DEVICE);
}
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i],
offset, len, DMA_TO_DEVICE);
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward progress
* in case they can not provide a descriptor
*/
tx = device->device_prep_dma_pqxor(chan, dma_dest, dst_cnt, dma_src,
src_cnt, scf, len, dma_prep_flags);
if (!tx) {
if (depend_tx)
dma_wait_for_async_tx(depend_tx);
while (!tx)
tx = device->device_prep_dma_pqxor(chan,
dma_dest, dst_cnt,
dma_src, src_cnt,
scf, len,
dma_prep_flags);
}
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
return tx;
}
struct dma_async_tx_descriptor *
async_trigger_callback(struct async_submit_ctl *submit)
{
struct dma_chan *chan;
struct dma_device *device;
struct dma_async_tx_descriptor *tx;
struct dma_async_tx_descriptor *depend_tx = submit->depend_tx;
if (depend_tx) {
chan = depend_tx->chan;
device = chan->device;
if (device && !dma_has_cap(DMA_INTERRUPT, device->cap_mask))
device = NULL;
tx = device ? device->device_prep_dma_interrupt(chan, 0) : NULL;
} else
tx = NULL;
if (tx) {
pr_debug("%s: (async)\n", __func__);
async_tx_submit(chan, tx, submit);
} else {
pr_debug("%s: (sync)\n", __func__);
async_tx_quiesce(&submit->depend_tx);
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;
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;
}
static struct dma_async_tx_descriptor *
async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
size_t len, struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, srcs, 2, len);
struct dma_device *dma = chan ? chan->device : NULL;
const u8 *amul, *bmul;
u8 ax, bx;
u8 *a, *b, *c;
if (dma) {
dma_addr_t dma_dest[2];
dma_addr_t dma_src[2];
struct device *dev = dma->dev;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef,
len, dma_flags);
if (tx) {
async_tx_submit(chan, tx, submit);
return tx;
}
/* could not get a descriptor, unmap and fall through to
* the synchronous path
*/
dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
dma_unmap_page(dev, dma_src[1], len, DMA_TO_DEVICE);
}
/* run the operation synchronously */
async_tx_quiesce(&submit->depend_tx);
amul = raid6_gfmul[coef[0]];
bmul = raid6_gfmul[coef[1]];
a = page_address(srcs[0]);
b = page_address(srcs[1]);
c = page_address(dest);
while (len--) {
ax = amul[*a++];
bx = bmul[*b++];
*c++ = ax ^ bx;
}
return NULL;
}
/**
* async_memset - attempt to fill memory with a dma engine.
* @dest: destination page
* @val: fill value
* @offset: offset in pages to start transaction
* @len: length in bytes
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: memset depends on the result of this transaction
* @cb_fn: function to call when the memcpy completes
* @cb_param: parameter to pass to the callback routine
*/
struct dma_async_tx_descriptor *
async_memset(struct page *dest, int val, unsigned int offset,
size_t len, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMSET,
&dest, 1, NULL, 0, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
if (device) {
dma_addr_t dma_dest;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
dma_dest = dma_map_page(device->dev, dest, offset, len,
DMA_FROM_DEVICE);
tx = device->device_prep_dma_memset(chan, dma_dest, val, len,
dma_prep_flags);
}
if (tx) {
pr_debug("%s: (async) len: %zu\n", __func__, len);
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
} else { /* run the memset synchronously */
void *dest_buf;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
dest_buf = (void *) (((char *) page_address(dest)) + offset);
/* wait for any prerequisite operations */
if (depend_tx) {
/* if ack is already set then we cannot be sure
* we are referring to the correct operation
*/
BUG_ON(depend_tx->ack);
if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR)
panic("%s: DMA_ERROR waiting for depend_tx\n",
__func__);
}
memset(dest_buf, val, len);
async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param);
}
return tx;
}
static struct dma_async_tx_descriptor *
async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
&dest, 1, &src, 1, len);
struct dma_device *dma = chan ? chan->device : NULL;
const u8 *qmul; /* Q multiplier table */
u8 *d, *s;
if (dma) {
dma_addr_t dma_dest[2];
dma_addr_t dma_src[1];
struct device *dev = dma->dev;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef,
len, dma_flags);
if (tx) {
async_tx_submit(chan, tx, submit);
return tx;
}
/* could not get a descriptor, unmap and fall through to
* the synchronous path
*/
dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
}
/* no channel available, or failed to allocate a descriptor, so
* perform the operation synchronously
*/
async_tx_quiesce(&submit->depend_tx);
qmul = raid6_gfmul[coef];
d = page_address(dest);
s = page_address(src);
while (len--)
*d++ = qmul[*s++];
return NULL;
}
struct dma_async_tx_descriptor *
async_memset(struct page *dest, int val, unsigned int offset, size_t len,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMSET,
&dest, 1, NULL, 0, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
if (device && is_dma_fill_aligned(device, offset, 0, len)) {
dma_addr_t dma_dest;
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, offset, len,
DMA_FROM_DEVICE);
tx = device->device_prep_dma_memset(chan, dma_dest, val, len,
dma_prep_flags);
}
if (tx) {
pr_debug("%s: (async) len: %zu\n", __func__, len);
async_tx_submit(chan, tx, submit);
} else { /* run the memset synchronously */
void *dest_buf;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
dest_buf = page_address(dest) + offset;
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
memset(dest_buf, val, len);
async_tx_sync_epilog(submit);
}
return tx;
}
/* do_async_xor - dma map the pages and perform the xor with an engine.
* This routine is marked __always_inline so it can be compiled away
* when CONFIG_DMA_ENGINE=n
*/
static __always_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_device *device,
struct dma_chan *chan, struct page *dest, struct page **src_list,
unsigned int offset, unsigned int src_cnt, size_t len,
enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
dma_addr_t dma_dest;
dma_addr_t *dma_src = (dma_addr_t *) src_list;
struct dma_async_tx_descriptor *tx;
int i;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
pr_debug("%s: len: %zu\n", __func__, len);
dma_dest = dma_map_page(device->dev, dest, offset, len,
DMA_FROM_DEVICE);
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i], offset,
len, DMA_TO_DEVICE);
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward progress
* in case they can not provide a descriptor
*/
tx = device->device_prep_dma_xor(chan, dma_dest, dma_src, src_cnt, len,
dma_prep_flags);
if (!tx) {
if (depend_tx)
dma_wait_for_async_tx(depend_tx);
while (!tx)
tx = device->device_prep_dma_xor(chan, dma_dest,
dma_src, src_cnt, len,
dma_prep_flags);
}
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
return tx;
}
/**
* async_trigger_callback - schedules the callback function to be run after
* any dependent operations have been completed.
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: 'callback' requires the completion of this transaction
* @cb_fn: function to call after depend_tx completes
* @cb_param: parameter to pass to the callback routine
*/
struct dma_async_tx_descriptor *
async_trigger_callback(enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan;
struct dma_device *device;
struct dma_async_tx_descriptor *tx;
if (depend_tx) {
chan = depend_tx->chan;
device = chan->device;
/* see if we can schedule an interrupt
* otherwise poll for completion
*/
if (device && !dma_has_cap(DMA_INTERRUPT, device->cap_mask))
device = NULL;
tx = device ? device->device_prep_dma_interrupt(chan, 0) : NULL;
} else
tx = NULL;
if (tx) {
pr_debug("%s: (async)\n", __func__);
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
} else {
pr_debug("%s: (sync)\n", __func__);
/* wait for any prerequisite operations */
async_tx_quiesce(&depend_tx);
async_tx_sync_epilog(cb_fn, cb_param);
}
return tx;
}
/**
* async_memcpy - attempt to copy memory with a dma engine.
* @dest: destination page
* @src: src page
* @offset: offset in pages to start transaction
* @len: length in bytes
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK,
* @depend_tx: memcpy depends on the result of this transaction
* @cb_fn: function to call when the memcpy completes
* @cb_param: parameter to pass to the callback routine
*/
struct dma_async_tx_descriptor *
async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
unsigned int src_offset, size_t len, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, 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 = cb_fn ? DMA_PREP_INTERRUPT : 0;
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, flags, depend_tx, cb_fn, cb_param);
} else {
void *dest_buf, *src_buf;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
/* wait for any prerequisite operations */
if (depend_tx) {
/* if ack is already set then we cannot be sure
* we are referring to the correct operation
*/
BUG_ON(depend_tx->ack);
if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR)
panic("%s: DMA_ERROR waiting for depend_tx\n",
__func__);
}
if (flags & ASYNC_TX_KMAP_DST)
dest_buf = kmap_atomic(dest, KM_USER0) + dest_offset;
else
dest_buf = page_address(dest) + dest_offset;
if (flags & ASYNC_TX_KMAP_SRC)
src_buf = kmap_atomic(src, KM_USER0) + src_offset;
else
src_buf = page_address(src) + src_offset;
memcpy(dest_buf, src_buf, len);
if (flags & ASYNC_TX_KMAP_DST)
kunmap_atomic(dest_buf, KM_USER0);
if (flags & ASYNC_TX_KMAP_SRC)
kunmap_atomic(src_buf, KM_USER0);
async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param);
}
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;
}
/* do_async_xor - dma map the pages and perform the xor with an engine */
static __async_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
struct async_submit_ctl *submit)
{
struct dma_device *dma = chan->device;
struct dma_async_tx_descriptor *tx = NULL;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *cb_param_orig = submit->cb_param;
enum async_tx_flags flags_orig = submit->flags;
enum dma_ctrl_flags dma_flags = 0;
int src_cnt = unmap->to_cnt;
int xor_src_cnt;
dma_addr_t dma_dest = unmap->addr[unmap->to_cnt];
dma_addr_t *src_list = unmap->addr;
while (src_cnt) {
dma_addr_t tmp;
submit->flags = flags_orig;
xor_src_cnt = min(src_cnt, (int)dma->max_xor);
/* if we are submitting additional xors, leave the chain open
* and clear the callback parameters
*/
if (src_cnt > xor_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
}
if (submit->cb_fn)
dma_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
/* Drivers force forward progress in case they can not provide a
* descriptor
*/
tmp = src_list[0];
if (src_list > unmap->addr)
src_list[0] = dma_dest;
tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
xor_src_cnt, unmap->len,
dma_flags);
if (unlikely(!tx))
async_tx_quiesce(&submit->depend_tx);
/* spin wait for the preceding transactions to complete */
while (unlikely(!tx)) {
dma_async_issue_pending(chan);
tx = dma->device_prep_dma_xor(chan, dma_dest,
src_list,
xor_src_cnt, unmap->len,
dma_flags);
}
src_list[0] = tmp;
dma_set_unmap(tx, unmap);
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
if (src_cnt > xor_src_cnt) {
/* drop completed sources */
src_cnt -= xor_src_cnt;
/* use the intermediate result a source */
src_cnt++;
src_list += xor_src_cnt - 1;
} else
break;
}
return tx;
}
/* do_async_xor - dma map the pages and perform the xor with an engine */
static __async_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
struct async_submit_ctl *submit)
{
struct dma_device *dma = chan->device;
struct dma_async_tx_descriptor *tx = NULL;
int src_off = 0;
int i;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *cb_param_orig = submit->cb_param;
enum async_tx_flags flags_orig = submit->flags;
enum dma_ctrl_flags dma_flags;
int xor_src_cnt = 0;
dma_addr_t dma_dest;
/* map the dest bidrectional in case it is re-used as a source */
dma_dest = dma_map_page(dma->dev, dest, offset, len, DMA_BIDIRECTIONAL);
for (i = 0; i < src_cnt; i++) {
/* only map the dest once */
if (!src_list[i])
continue;
if (unlikely(src_list[i] == dest)) {
dma_src[xor_src_cnt++] = dma_dest;
continue;
}
dma_src[xor_src_cnt++] = dma_map_page(dma->dev, src_list[i], offset,
len, DMA_TO_DEVICE);
}
src_cnt = xor_src_cnt;
while (src_cnt) {
submit->flags = flags_orig;
dma_flags = 0;
xor_src_cnt = min(src_cnt, (int)dma->max_xor);
/* if we are submitting additional xors, leave the chain open,
* clear the callback parameters, and leave the destination
* buffer mapped
*/
if (src_cnt > xor_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
}
if (submit->cb_fn)
dma_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward progress
* in case they can not provide a descriptor
*/
tx = dma->device_prep_dma_xor(chan, dma_dest, &dma_src[src_off],
xor_src_cnt, len, dma_flags);
if (unlikely(!tx))
async_tx_quiesce(&submit->depend_tx);
/* spin wait for the preceding transactions to complete */
while (unlikely(!tx)) {
dma_async_issue_pending(chan);
tx = dma->device_prep_dma_xor(chan, dma_dest,
&dma_src[src_off],
xor_src_cnt, len,
dma_flags);
}
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
if (src_cnt > xor_src_cnt) {
/* drop completed sources */
src_cnt -= xor_src_cnt;
src_off += xor_src_cnt;
/* use the intermediate result a source */
dma_src[--src_off] = dma_dest;
src_cnt++;
} else
break;
}
return tx;
}
/**
* async_xor_val - attempt a xor parity check with a dma engine.
* @dest: destination page used if the xor is performed synchronously
* @src_list: array of source pages
* @offset: offset in pages to start transaction
* @src_cnt: number of source pages
* @len: length in bytes
* @result: 0 if sum == 0 else non-zero
* @submit: submission / completion modifiers
*
* honored flags: ASYNC_TX_ACK
*
* src_list note: if the dest is also a source it must be at index zero.
* The contents of this array will be overwritten if a scribble region
* is not specified.
*/
struct dma_async_tx_descriptor *
async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
int src_cnt, size_t len, enum sum_check_flags *result,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
dma_addr_t *dma_src = NULL;
BUG_ON(src_cnt <= 1);
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) src_list;
if (dma_src && device && src_cnt <= device->max_xor &&
is_dma_xor_aligned(device, offset, 0, len)) {
unsigned long dma_prep_flags = 0;
int i;
pr_debug("%s: (async) len: %zu\n", __func__, len);
if (submit->cb_fn)
dma_prep_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_prep_flags |= DMA_PREP_FENCE;
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i],
offset, len, DMA_TO_DEVICE);
tx = device->device_prep_dma_xor_val(chan, dma_src, src_cnt,
len, result,
dma_prep_flags);
if (unlikely(!tx)) {
async_tx_quiesce(&submit->depend_tx);
while (!tx) {
dma_async_issue_pending(chan);
tx = device->device_prep_dma_xor_val(chan,
dma_src, src_cnt, len, result,
dma_prep_flags);
}
}
async_tx_submit(chan, tx, submit);
} else {
enum async_tx_flags flags_orig = submit->flags;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
WARN_ONCE(device && src_cnt <= device->max_xor,
"%s: no space for dma address conversion\n",
__func__);
submit->flags |= ASYNC_TX_XOR_DROP_DST;
submit->flags &= ~ASYNC_TX_ACK;
tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
async_tx_quiesce(&tx);
*result = !page_is_zero(dest, offset, len) << SUM_CHECK_P;
async_tx_sync_epilog(submit);
submit->flags = flags_orig;
}
return tx;
}
/**
* async_xor_zero_sum - attempt a xor parity check with a dma engine.
* @dest: destination page used if the xor is performed synchronously
* @src_list: array of source pages. The dest page must be listed as a source
* at index zero. The contents of this array may be overwritten.
* @offset: offset in pages to start transaction
* @src_cnt: number of source pages
* @len: length in bytes
* @result: 0 if sum == 0 else non-zero
* @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: xor depends on the result of this transaction.
* @cb_fn: function to call when the xor completes
* @cb_param: parameter to pass to the callback routine
*/
struct dma_async_tx_descriptor *
async_xor_zero_sum(struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len,
u32 *result, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_ZERO_SUM,
&dest, 1, src_list,
src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
BUG_ON(src_cnt <= 1);
if (device && src_cnt <= device->max_xor) {
dma_addr_t *dma_src = (dma_addr_t *) src_list;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
int i;
pr_debug("%s: (async) len: %zu\n", __func__, len);
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i],
offset, len, DMA_TO_DEVICE);
tx = device->device_prep_dma_zero_sum(chan, dma_src, src_cnt,
len, result,
dma_prep_flags);
if (!tx) {
if (depend_tx)
dma_wait_for_async_tx(depend_tx);
while (!tx)
tx = device->device_prep_dma_zero_sum(chan,
dma_src, src_cnt, len, result,
dma_prep_flags);
}
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
} else {
unsigned long xor_flags = flags;
pr_debug("%s: (sync) len: %zu\n", __func__, len);
xor_flags |= ASYNC_TX_XOR_DROP_DST;
xor_flags &= ~ASYNC_TX_ACK;
tx = async_xor(dest, src_list, offset, src_cnt, len, xor_flags,
depend_tx, NULL, NULL);
if (tx) {
if (dma_wait_for_async_tx(tx) == DMA_ERROR)
panic("%s: DMA_ERROR waiting for tx\n",
__func__);
async_tx_ack(tx);
}
*result = page_is_zero(dest, offset, len) ? 0 : 1;
tx = NULL;
async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param);
}
return tx;
}
/**
* async_syndrome_val - asynchronously validate a raid6 syndrome
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
* @offset: common offset into each block (src and dest) to start transaction
* @disks: number of blocks (including missing P or Q, see below)
* @len: length of operation in bytes
* @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
* @spare: temporary result buffer for the synchronous case
* @submit: submission / completion modifiers
*
* The same notes from async_gen_syndrome apply to the 'blocks',
* and 'disks' parameters of this routine. The synchronous path
* requires a temporary result buffer and submit->scribble to be
* specified.
*/
struct dma_async_tx_descriptor *
async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
size_t len, enum sum_check_flags *pqres, struct page *spare,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx;
unsigned char coefs[disks-2];
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
struct dmaengine_unmap_data *unmap = NULL;
BUG_ON(disks < 4);
if (device)
unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
if (unmap && disks <= dma_maxpq(device, 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {
struct device *dev = device->dev;
dma_addr_t pq[2];
int i, j = 0, src_cnt = 0;
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
unmap->len = len;
for (i = 0; i < disks-2; i++)
if (likely(blocks[i])) {
unmap->addr[j] = dma_map_page(dev, blocks[i],
offset, len,
DMA_TO_DEVICE);
coefs[j] = raid6_gfexp[i];
unmap->to_cnt++;
src_cnt++;
j++;
}
if (!P(blocks, disks)) {
pq[0] = 0;
dma_flags |= DMA_PREP_PQ_DISABLE_P;
} else {
pq[0] = dma_map_page(dev, P(blocks, disks),
offset, len,
DMA_TO_DEVICE);
unmap->addr[j++] = pq[0];
unmap->to_cnt++;
}
if (!Q(blocks, disks)) {
pq[1] = 0;
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
} else {
pq[1] = dma_map_page(dev, Q(blocks, disks),
offset, len,
DMA_TO_DEVICE);
unmap->addr[j++] = pq[1];
unmap->to_cnt++;
}
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
for (;;) {
tx = device->device_prep_dma_pq_val(chan, pq,
unmap->addr,
src_cnt,
coefs,
len, pqres,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
dma_set_unmap(tx, unmap);
async_tx_submit(chan, tx, submit);
return tx;
} else {
struct page *p_src = P(blocks, disks);
struct page *q_src = Q(blocks, disks);
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *scribble = submit->scribble;
void *cb_param_orig = submit->cb_param;
void *p, *q, *s;
pr_debug("%s: (sync) disks: %d len: %zu\n",
__func__, disks, len);
/* caller must provide a temporary result buffer and
* allow the input parameters to be preserved
*/
BUG_ON(!spare || !scribble);
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
/* recompute p and/or q into the temporary buffer and then
* check to see the result matches the current value
*/
tx = NULL;
*pqres = 0;
if (p_src) {
init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
NULL, NULL, scribble);
tx = async_xor(spare, blocks, offset, disks-2, len, submit);
async_tx_quiesce(&tx);
p = page_address(p_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
}
if (q_src) {
P(blocks, disks) = NULL;
Q(blocks, disks) = spare;
init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
tx = async_gen_syndrome(blocks, offset, disks, len, submit);
async_tx_quiesce(&tx);
q = page_address(q_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
}
/* restore P, Q and submit */
P(blocks, disks) = p_src;
Q(blocks, disks) = q_src;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
submit->flags = flags_orig;
async_tx_sync_epilog(submit);
return NULL;
}
}
/**
* do_async_gen_syndrome - asynchronously calculate P and/or Q
*/
static __async_inline struct dma_async_tx_descriptor *
do_async_gen_syndrome(struct dma_chan *chan,
const unsigned char *scfs, int disks,
struct dmaengine_unmap_data *unmap,
enum dma_ctrl_flags dma_flags,
struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct dma_device *dma = chan->device;
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
dma_async_tx_callback cb_param_orig = submit->cb_param;
int src_cnt = disks - 2;
unsigned short pq_src_cnt;
dma_addr_t dma_dest[2];
int src_off = 0;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
while (src_cnt > 0) {
submit->flags = flags_orig;
pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
/* if we are submitting additional pqs, leave the chain open,
* clear the callback parameters, and leave the destination
* buffers mapped
*/
if (src_cnt > pq_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
if (cb_fn_orig)
dma_flags |= DMA_PREP_INTERRUPT;
}
/* Drivers force forward progress in case they can not provide
* a descriptor
*/
for (;;) {
dma_dest[0] = unmap->addr[disks - 2];
dma_dest[1] = unmap->addr[disks - 1];
tx = dma->device_prep_dma_pq(chan, dma_dest,
&unmap->addr[src_off],
pq_src_cnt,
&scfs[src_off], unmap->len,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
dma_set_unmap(tx, unmap);
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
/* drop completed sources */
src_cnt -= pq_src_cnt;
src_off += pq_src_cnt;
dma_flags |= DMA_PREP_CONTINUE;
}
return tx;
}
/**
* async_xor_zero_sum - attempt a PQ parities check with a dma engine.
* @pdest: P-parity destination to check
* @qdest: Q-parity destination to check
* @src_list: array of source pages; the 1st pointer is qdest, the 2nd - pdest.
* @scoef_list: coefficients to use in GF-multiplications
* @offset: offset in pages to start transaction
* @src_cnt: number of source pages
* @len: length in bytes
* @presult: 0 if P parity is OK else non-zero
* @qresult: 0 if Q parity is OK else non-zero
* @flags: ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
* @depend_tx: depends on the result of this transaction.
* @callback: function to call when the xor completes
* @callback_param: parameter to pass to the callback routine
*/
struct dma_async_tx_descriptor *
async_pqxor_zero_sum(struct page *pdest, struct page *qdest,
struct page **src_list, unsigned char *scf,
unsigned int offset, int src_cnt, size_t len,
u32 *presult, u32 *qresult, enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx,
DMA_PQ_ZERO_SUM,
src_list, 2, &src_list[2],
src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx = NULL;
BUG_ON(src_cnt <= 1);
BUG_ON(!qdest || qdest != src_list[0] || pdest != src_list[1]);
if (device) {
dma_addr_t *dma_src = (dma_addr_t *)src_list;
unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
int i;
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(device->dev, src_list[i],
offset, len, DMA_TO_DEVICE);
tx = device->device_prep_dma_pqzero_sum(chan, dma_src, src_cnt,
scf, len,
presult, qresult,
dma_prep_flags);
if (!tx) {
if (depend_tx)
dma_wait_for_async_tx(depend_tx);
while (!tx)
tx = device->device_prep_dma_pqzero_sum(chan,
dma_src, src_cnt, scf, len,
presult, qresult,
dma_prep_flags);
}
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
} else {
unsigned long lflags = flags;
/* TBD: support for lengths size of more than PAGE_SIZE */
lflags &= ~ASYNC_TX_ACK;
spin_lock(&spare_lock);
do_sync_pqxor(spare_pages[0], spare_pages[1],
&src_list[2], offset,
src_cnt - 2, len, lflags,
depend_tx, NULL, NULL);
if (presult && pdest)
*presult = memcmp(page_address(pdest),
page_address(spare_pages[0]),
len) == 0 ? 0 : 1;
if (qresult && qdest)
*qresult = memcmp(page_address(qdest),
page_address(spare_pages[1]),
len) == 0 ? 0 : 1;
spin_unlock(&spare_lock);
}
return tx;
}
static __async_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
struct async_submit_ctl *submit)
{
struct dma_device *dma = chan->device;
struct dma_async_tx_descriptor *tx = NULL;
int src_off = 0;
int i;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *cb_param_orig = submit->cb_param;
enum async_tx_flags flags_orig = submit->flags;
enum dma_ctrl_flags dma_flags;
int xor_src_cnt = 0;
dma_addr_t dma_dest;
dma_dest = dma_map_page(dma->dev, dest, offset, len, DMA_BIDIRECTIONAL);
for (i = 0; i < src_cnt; i++) {
if (!src_list[i])
continue;
if (unlikely(src_list[i] == dest)) {
dma_src[xor_src_cnt++] = dma_dest;
continue;
}
dma_src[xor_src_cnt++] = dma_map_page(dma->dev, src_list[i], offset,
len, DMA_TO_DEVICE);
}
src_cnt = xor_src_cnt;
while (src_cnt) {
submit->flags = flags_orig;
dma_flags = 0;
xor_src_cnt = min(src_cnt, (int)dma->max_xor);
if (src_cnt > xor_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
}
if (submit->cb_fn)
dma_flags |= DMA_PREP_INTERRUPT;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
tx = dma->device_prep_dma_xor(chan, dma_dest, &dma_src[src_off],
xor_src_cnt, len, dma_flags);
if (unlikely(!tx))
async_tx_quiesce(&submit->depend_tx);
while (unlikely(!tx)) {
dma_async_issue_pending(chan);
tx = dma->device_prep_dma_xor(chan, dma_dest,
&dma_src[src_off],
xor_src_cnt, len,
dma_flags);
}
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
if (src_cnt > xor_src_cnt) {
src_cnt -= xor_src_cnt;
src_off += xor_src_cnt;
dma_src[--src_off] = dma_dest;
src_cnt++;
} else
break;
}
return tx;
}
/* do_async_xor - dma map the pages and perform the xor with an engine.
* This routine is marked __always_inline so it can be compiled away
* when CONFIG_DMA_ENGINE=n
*/
static __always_inline struct dma_async_tx_descriptor *
do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
unsigned int offset, int src_cnt, size_t len,
enum async_tx_flags flags,
struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_device *dma = chan->device;
dma_addr_t *dma_src = (dma_addr_t *) src_list;
struct dma_async_tx_descriptor *tx = NULL;
int src_off = 0;
int i;
dma_async_tx_callback _cb_fn;
void *_cb_param;
enum async_tx_flags async_flags;
enum dma_ctrl_flags dma_flags;
int xor_src_cnt;
dma_addr_t dma_dest;
dma_dest = dma_map_page(dma->dev, dest, offset, len, DMA_FROM_DEVICE);
for (i = 0; i < src_cnt; i++)
dma_src[i] = dma_map_page(dma->dev, src_list[i], offset,
len, DMA_TO_DEVICE);
while (src_cnt) {
async_flags = flags;
dma_flags = 0;
xor_src_cnt = min(src_cnt, dma->max_xor);
/* if we are submitting additional xors, leave the chain open,
* clear the callback parameters, and leave the destination
* buffer mapped
*/
if (src_cnt > xor_src_cnt) {
async_flags &= ~ASYNC_TX_ACK;
dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
_cb_fn = NULL;
_cb_param = NULL;
} else {
_cb_fn = cb_fn;
_cb_param = cb_param;
}
if (_cb_fn)
dma_flags |= DMA_PREP_INTERRUPT;
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward progress
* in case they can not provide a descriptor
*/
tx = dma->device_prep_dma_xor(chan, dma_dest, &dma_src[src_off],
xor_src_cnt, len, dma_flags);
if (unlikely(!tx))
async_tx_quiesce(&depend_tx);
/* spin wait for the preceeding transactions to complete */
while (unlikely(!tx)) {
dma_async_issue_pending(chan);
tx = dma->device_prep_dma_xor(chan, dma_dest,
&dma_src[src_off],
xor_src_cnt, len,
dma_flags);
}
async_tx_submit(chan, tx, async_flags, depend_tx, _cb_fn,
_cb_param);
depend_tx = tx;
flags |= ASYNC_TX_DEP_ACK;
if (src_cnt > xor_src_cnt) {
/* drop completed sources */
src_cnt -= xor_src_cnt;
src_off += xor_src_cnt;
/* use the intermediate result a source */
dma_src[--src_off] = dma_dest;
src_cnt++;
} else
break;
}
return tx;
}
/**
* do_async_gen_syndrome - asynchronously calculate P and/or Q
*/
static __async_inline struct dma_async_tx_descriptor *
do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
const unsigned char *scfs, unsigned int offset, int disks,
size_t len, dma_addr_t *dma_src,
struct async_submit_ctl *submit)
{
struct dma_async_tx_descriptor *tx = NULL;
struct dma_device *dma = chan->device;
enum dma_ctrl_flags dma_flags = 0;
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
dma_async_tx_callback cb_param_orig = submit->cb_param;
int src_cnt = disks - 2;
unsigned char coefs[src_cnt];
unsigned short pq_src_cnt;
dma_addr_t dma_dest[2];
int src_off = 0;
int idx;
int i;
/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
if (P(blocks, disks))
dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
len, DMA_BIDIRECTIONAL);
else
dma_flags |= DMA_PREP_PQ_DISABLE_P;
if (Q(blocks, disks))
dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
len, DMA_BIDIRECTIONAL);
else
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
/* convert source addresses being careful to collapse 'empty'
* sources and update the coefficients accordingly
*/
for (i = 0, idx = 0; i < src_cnt; i++) {
if (blocks[i] == NULL)
continue;
dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
DMA_TO_DEVICE);
coefs[idx] = scfs[i];
idx++;
}
src_cnt = idx;
while (src_cnt > 0) {
submit->flags = flags_orig;
pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
/* if we are submitting additional pqs, leave the chain open,
* clear the callback parameters, and leave the destination
* buffers mapped
*/
if (src_cnt > pq_src_cnt) {
submit->flags &= ~ASYNC_TX_ACK;
submit->flags |= ASYNC_TX_FENCE;
dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = NULL;
submit->cb_param = NULL;
} else {
dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
if (cb_fn_orig)
dma_flags |= DMA_PREP_INTERRUPT;
}
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
/* Since we have clobbered the src_list we are committed
* to doing this asynchronously. Drivers force forward
* progress in case they can not provide a descriptor
*/
for (;;) {
tx = dma->device_prep_dma_pq(chan, dma_dest,
&dma_src[src_off],
pq_src_cnt,
&coefs[src_off], len,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
/* drop completed sources */
src_cnt -= pq_src_cnt;
src_off += pq_src_cnt;
dma_flags |= DMA_PREP_CONTINUE;
}
return tx;
}
/**
* async_syndrome_val - asynchronously validate a raid6 syndrome
* @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
* @offset: common offset into each block (src and dest) to start transaction
* @disks: number of blocks (including missing P or Q, see below)
* @len: length of operation in bytes
* @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
* @spare: temporary result buffer for the synchronous case
* @submit: submission / completion modifiers
*
* The same notes from async_gen_syndrome apply to the 'blocks',
* and 'disks' parameters of this routine. The synchronous path
* requires a temporary result buffer and submit->scribble to be
* specified.
*/
struct dma_async_tx_descriptor *
async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
size_t len, enum sum_check_flags *pqres, struct page *spare,
struct async_submit_ctl *submit)
{
struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL,
NULL, 0, blocks, disks,
len);
struct dma_device *device = chan ? chan->device : NULL;
struct dma_async_tx_descriptor *tx;
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
dma_addr_t *dma_src = NULL;
BUG_ON(disks < 4);
if (submit->scribble)
dma_src = submit->scribble;
else if (sizeof(dma_addr_t) <= sizeof(struct page *))
dma_src = (dma_addr_t *) blocks;
if (dma_src && device && disks <= dma_maxpq(device, 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {
struct device *dev = device->dev;
dma_addr_t *pq = &dma_src[disks-2];
int i;
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
if (!P(blocks, disks))
dma_flags |= DMA_PREP_PQ_DISABLE_P;
if (!Q(blocks, disks))
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
if (submit->flags & ASYNC_TX_FENCE)
dma_flags |= DMA_PREP_FENCE;
for (i = 0; i < disks; i++)
if (likely(blocks[i])) {
BUG_ON(is_raid6_zero_block(blocks[i]));
dma_src[i] = dma_map_page(dev, blocks[i],
offset, len,
DMA_TO_DEVICE);
}
for (;;) {
tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
disks - 2,
raid6_gfexp,
len, pqres,
dma_flags);
if (likely(tx))
break;
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
async_tx_submit(chan, tx, submit);
return tx;
} else {
struct page *p_src = P(blocks, disks);
struct page *q_src = Q(blocks, disks);
enum async_tx_flags flags_orig = submit->flags;
dma_async_tx_callback cb_fn_orig = submit->cb_fn;
void *scribble = submit->scribble;
void *cb_param_orig = submit->cb_param;
void *p, *q, *s;
pr_debug("%s: (sync) disks: %d len: %zu\n",
__func__, disks, len);
/* caller must provide a temporary result buffer and
* allow the input parameters to be preserved
*/
BUG_ON(!spare || !scribble);
/* wait for any prerequisite operations */
async_tx_quiesce(&submit->depend_tx);
/* recompute p and/or q into the temporary buffer and then
* check to see the result matches the current value
*/
tx = NULL;
*pqres = 0;
if (p_src) {
init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
NULL, NULL, scribble);
tx = async_xor(spare, blocks, offset, disks-2, len, submit);
async_tx_quiesce(&tx);
p = page_address(p_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
}
if (q_src) {
P(blocks, disks) = NULL;
Q(blocks, disks) = spare;
init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
tx = async_gen_syndrome(blocks, offset, disks, len, submit);
async_tx_quiesce(&tx);
q = page_address(q_src) + offset;
s = page_address(spare) + offset;
*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
}
/* restore P, Q and submit */
P(blocks, disks) = p_src;
Q(blocks, disks) = q_src;
submit->cb_fn = cb_fn_orig;
submit->cb_param = cb_param_orig;
submit->flags = flags_orig;
async_tx_sync_epilog(submit);
return NULL;
}
}
