6 files changed, 240 insertions, 169 deletions

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 9e62feffb374..f8c0b8dbeb75 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -50,33 +50,36 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
                                                       &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 && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
-                dma_addr_t dma_dest, dma_src;
+        if (device)
+                unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+
+        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;
-                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);
-                }
+
+                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;
@@ -96,6 +99,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
                 async_tx_sync_epilog(submit);
         }
 
+        dmaengine_unmap_put(unmap);
+
         return tx;
 }
 EXPORT_SYMBOL_GPL(async_memcpy);
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);