summaryrefslogtreecommitdiff
path: root/crypto/async_tx/async_pq.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-11-20 13:20:24 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-11-20 13:20:24 -0800
commite6d69a60b77a6ea8d5f9d41765c7571bb8d45531 (patch)
tree4ea3fe7c49a864da2ce7ffb51a703661826dc15d /crypto/async_tx/async_pq.c
parent5a1efc6e68a095917277459091fafba6a6baef17 (diff)
parentdf12a3178d340319b1955be6b973a4eb84aff754 (diff)
Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma
Pull slave-dmaengine changes from Vinod Koul: "This brings for slave dmaengine: - Change dma notification flag to DMA_COMPLETE from DMA_SUCCESS as dmaengine can only transfer and not verify validaty of dma transfers - Bunch of fixes across drivers: - cppi41 driver fixes from Daniel - 8 channel freescale dma engine support and updated bindings from Hongbo - msx-dma fixes and cleanup by Markus - DMAengine updates from Dan: - Bartlomiej and Dan finalized a rework of the dma address unmap implementation. - In the course of testing 1/ a collection of enhancements to dmatest fell out. Notably basic performance statistics, and fixed / enhanced test control through new module parameters 'run', 'wait', 'noverify', and 'verbose'. Thanks to Andriy and Linus [Walleij] for their review. - Testing the raid related corner cases of 1/ triggered bugs in the recently added 16-source operation support in the ioatdma driver. - Some minor fixes / cleanups to mv_xor and ioatdma" * 'next' of git://git.infradead.org/users/vkoul/slave-dma: (99 commits) dma: mv_xor: Fix mis-usage of mmio 'base' and 'high_base' registers dma: mv_xor: Remove unneeded NULL address check ioat: fix ioat3_irq_reinit ioat: kill msix_single_vector support raid6test: add new corner case for ioatdma driver ioatdma: clean up sed pool kmem_cache ioatdma: fix selection of 16 vs 8 source path ioatdma: fix sed pool selection ioatdma: Fix bug in selftest after removal of DMA_MEMSET. dmatest: verbose mode dmatest: convert to dmaengine_unmap_data dmatest: add a 'wait' parameter dmatest: add basic performance metrics dmatest: add support for skipping verification and random data setup dmatest: use pseudo random numbers dmatest: support xor-only, or pq-only channels in tests dmatest: restore ability to start test at module load and init dmatest: cleanup redundant "dmatest: " prefixes dmatest: replace stored results mechanism, with uniform messages Revert "dmatest: append verify result to results" ...
Diffstat (limited to 'crypto/async_tx/async_pq.c')
-rw-r--r--crypto/async_tx/async_pq.c174
1 files changed, 99 insertions, 75 deletions
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 91d5d385899e..d05327caf69d 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -46,49 +46,24 @@ static struct page *pq_scribble_page;
* 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,
+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 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;
+ if (submit->flags & ASYNC_TX_FENCE)
+ dma_flags |= DMA_PREP_FENCE;
while (src_cnt > 0) {
submit->flags = flags_orig;
@@ -100,28 +75,25 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
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
+ /* 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,
- &dma_src[src_off],
+ &unmap->addr[src_off],
pq_src_cnt,
- &coefs[src_off], len,
+ &scfs[src_off], unmap->len,
dma_flags);
if (likely(tx))
break;
@@ -129,6 +101,7 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
dma_async_issue_pending(chan);
}
+ dma_set_unmap(tx, unmap);
async_tx_submit(chan, tx, submit);
submit->depend_tx = tx;
@@ -188,10 +161,6 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
* set to NULL those buffers will be replaced with the raid6_zero_page
* in the synchronous path and omitted in the hardware-asynchronous
* path.
- *
- * 'blocks' note: if submit->scribble is NULL then the contents of
- * 'blocks' may be overwritten to perform address conversions
- * (dma_map_page() or page_address()).
*/
struct dma_async_tx_descriptor *
async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
@@ -202,26 +171,69 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
&P(blocks, disks), 2,
blocks, src_cnt, len);
struct dma_device *device = chan ? chan->device : NULL;
- dma_addr_t *dma_src = NULL;
+ struct dmaengine_unmap_data *unmap = NULL;
BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
- if (submit->scribble)
- dma_src = submit->scribble;
- else if (sizeof(dma_addr_t) <= sizeof(struct page *))
- dma_src = (dma_addr_t *) blocks;
+ if (device)
+ unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
- if (dma_src && device &&
+ if (unmap &&
(src_cnt <= dma_maxpq(device, 0) ||
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
is_dma_pq_aligned(device, offset, 0, len)) {
+ struct dma_async_tx_descriptor *tx;
+ enum dma_ctrl_flags dma_flags = 0;
+ unsigned char coefs[src_cnt];
+ int i, j;
+
/* run the p+q asynchronously */
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
- return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
- disks, len, dma_src, submit);
+
+ /* convert source addresses being careful to collapse 'empty'
+ * sources and update the coefficients accordingly
+ */
+ unmap->len = len;
+ for (i = 0, j = 0; i < src_cnt; i++) {
+ if (blocks[i] == NULL)
+ continue;
+ unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
+ len, DMA_TO_DEVICE);
+ coefs[j] = raid6_gfexp[i];
+ unmap->to_cnt++;
+ j++;
+ }
+
+ /*
+ * DMAs use destinations as sources,
+ * so use BIDIRECTIONAL mapping
+ */
+ unmap->bidi_cnt++;
+ if (P(blocks, disks))
+ unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
+ offset, len, DMA_BIDIRECTIONAL);
+ else {
+ unmap->addr[j++] = 0;
+ dma_flags |= DMA_PREP_PQ_DISABLE_P;
+ }
+
+ unmap->bidi_cnt++;
+ if (Q(blocks, disks))
+ unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
+ offset, len, DMA_BIDIRECTIONAL);
+ else {
+ unmap->addr[j++] = 0;
+ dma_flags |= DMA_PREP_PQ_DISABLE_Q;
+ }
+
+ tx = do_async_gen_syndrome(chan, coefs, j, unmap, dma_flags, submit);
+ dmaengine_unmap_put(unmap);
+ return tx;
}
+ dmaengine_unmap_put(unmap);
+
/* run the pq synchronously */
pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
@@ -277,50 +289,60 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
struct dma_async_tx_descriptor *tx;
unsigned char coefs[disks-2];
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
- dma_addr_t *dma_src = NULL;
- int src_cnt = 0;
+ struct dmaengine_unmap_data *unmap = 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 (device)
+ unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
- if (dma_src && device && disks <= dma_maxpq(device, 0) &&
+ if (unmap && 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;
+ dma_addr_t pq[2];
+ int i, j = 0, src_cnt = 0;
pr_debug("%s: (async) disks: %d len: %zu\n",
__func__, disks, len);
- if (!P(blocks, disks))
+
+ 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
+ } else {
pq[0] = dma_map_page(dev, P(blocks, disks),
offset, len,
DMA_TO_DEVICE);
- if (!Q(blocks, disks))
+ unmap->addr[j++] = pq[0];
+ unmap->to_cnt++;
+ }
+ if (!Q(blocks, disks)) {
+ pq[1] = 0;
dma_flags |= DMA_PREP_PQ_DISABLE_Q;
- else
+ } 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 (i = 0; i < disks-2; i++)
- if (likely(blocks[i])) {
- dma_src[src_cnt] = dma_map_page(dev, blocks[i],
- offset, len,
- DMA_TO_DEVICE);
- coefs[src_cnt] = raid6_gfexp[i];
- src_cnt++;
- }
-
for (;;) {
- tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
+ tx = device->device_prep_dma_pq_val(chan, pq,
+ unmap->addr,
src_cnt,
coefs,
len, pqres,
@@ -330,6 +352,8 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
async_tx_quiesce(&submit->depend_tx);
dma_async_issue_pending(chan);
}
+
+ dma_set_unmap(tx, unmap);
async_tx_submit(chan, tx, submit);
return tx;