4 files changed, 110 insertions, 89 deletions

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 047e533fcc5b..0f6282207b32 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -35,7 +35,7 @@
  * @src: src page
  * @offset: offset in pages to start transaction
  * @len: length in bytes
- * @flags: ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK,
+ * @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
@@ -46,33 +46,29 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
         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);
+        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;
-        int int_en = cb_fn ? 1 : 0;
-        struct dma_async_tx_descriptor *tx = device ?
-                device->device_prep_dma_memcpy(chan, len,
-                int_en) : NULL;
+        struct dma_async_tx_descriptor *tx = NULL;
 
-        if (tx) { /* run the memcpy asynchronously */
-                dma_addr_t addr;
-                enum dma_data_direction dir;
+        if (device) {
+                dma_addr_t dma_dest, dma_src;
+                unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
 
-                pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
-
-                dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                        DMA_NONE : DMA_FROM_DEVICE;
-
-                addr = dma_map_page(device->dev, dest, dest_offset, len, dir);
-                tx->tx_set_dest(addr, tx, 0);
+                dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
+                                        DMA_FROM_DEVICE);
 
-                dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                        DMA_NONE : DMA_TO_DEVICE;
+                dma_src = dma_map_page(device->dev, src, src_offset, len,
+                                       DMA_TO_DEVICE);
 
-                addr = dma_map_page(device->dev, src, src_offset, len, dir);
-                tx->tx_set_src(addr, tx, 0);
+                tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
+                                                    len, dma_prep_flags);
+        }
 
+        if (tx) {
+                pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
                 async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
-        } else { /* run the memcpy synchronously */
+        } else {
                 void *dest_buf, *src_buf;
                 pr_debug("%s: (sync) len: %zu\n", __FUNCTION__, len);
 
diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c
index 66ef6351202e..09c0e83664bc 100644
--- a/crypto/async_tx/async_memset.c
+++ b/crypto/async_tx/async_memset.c
@@ -35,7 +35,7 @@
  * @val: fill value
  * @offset: offset in pages to start transaction
  * @len: length in bytes
- * @flags: ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
+ * @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
@@ -46,24 +46,24 @@ async_memset(struct page *dest, int val, unsigned int offset,
         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);
+        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;
-        int int_en = cb_fn ? 1 : 0;
-        struct dma_async_tx_descriptor *tx = device ?
-                device->device_prep_dma_memset(chan, val, len,
-                        int_en) : NULL;
+        struct dma_async_tx_descriptor *tx = NULL;
 
-        if (tx) { /* run the memset asynchronously */
-                dma_addr_t dma_addr;
-                enum dma_data_direction dir;
+        if (device) {
+                dma_addr_t dma_dest;
+                unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0;
 
-                pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
-                dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                        DMA_NONE : DMA_FROM_DEVICE;
+                dma_dest = dma_map_page(device->dev, dest, offset, len,
+                                        DMA_FROM_DEVICE);
 
-                dma_addr = dma_map_page(device->dev, dest, offset, len, dir);
-                tx->tx_set_dest(dma_addr, tx, 0);
+                tx = device->device_prep_dma_memset(chan, dma_dest, val, len,
+                                                    dma_prep_flags);
+        }
 
+        if (tx) {
+                pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
                 async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
         } else { /* run the memset synchronously */
                 void *dest_buf;
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index bc18cbb8ea79..562882189de5 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -57,8 +57,7 @@ static struct chan_ref_percpu *channel_table[DMA_TX_TYPE_END];
  */
 static spinlock_t async_tx_lock;
 
-static struct list_head
-async_tx_master_list = LIST_HEAD_INIT(async_tx_master_list);
+static LIST_HEAD(async_tx_master_list);
 
 /* async_tx_issue_pending_all - start all transactions on all channels */
 void async_tx_issue_pending_all(void)
@@ -362,13 +361,13 @@ static void __exit async_tx_exit(void)
 }
 
 /**
- * async_tx_find_channel - find a channel to carry out the operation or let
+ * __async_tx_find_channel - find a channel to carry out the operation or let
  *      the transaction execute synchronously
  * @depend_tx: transaction dependency
  * @tx_type: transaction type
  */
 struct dma_chan *
-async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
+__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
         enum dma_transaction_type tx_type)
 {
         /* see if we can keep the chain on one channel */
@@ -384,7 +383,7 @@ async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
         } else
                 return NULL;
 }
-EXPORT_SYMBOL_GPL(async_tx_find_channel);
+EXPORT_SYMBOL_GPL(__async_tx_find_channel);
 #else
 static int __init async_tx_init(void)
 {
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 2575f674dcd5..2259a4ff15cb 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -30,35 +30,51 @@
 #include <linux/raid/xor.h>
 #include <linux/async_tx.h>
 
-static void
-do_async_xor(struct dma_async_tx_descriptor *tx, struct dma_device *device,
+/* 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_addr;
-        enum dma_data_direction dir;
+        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", __FUNCTION__, len);
 
-        dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                DMA_NONE : DMA_FROM_DEVICE;
-
-        dma_addr = dma_map_page(device->dev, dest, offset, len, dir);
-        tx->tx_set_dest(dma_addr, tx, 0);
-
-        dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                DMA_NONE : DMA_TO_DEVICE;
+        dma_dest = dma_map_page(device->dev, dest, offset, len,
+                                DMA_FROM_DEVICE);
 
-        for (i = 0; i < src_cnt; i++) {
-                dma_addr = dma_map_page(device->dev, src_list[i],
-                        offset, len, dir);
-                tx->tx_set_src(dma_addr, tx, i);
+        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;
 }
 
 static void
@@ -102,7 +118,7 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST,
- *      ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
+ *      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
@@ -113,14 +129,16 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
         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_XOR);
+        struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR,
+                                                      &dest, 1, src_list,
+                                                      src_cnt, len);
         struct dma_device *device = chan ? chan->device : NULL;
         struct dma_async_tx_descriptor *tx = NULL;
         dma_async_tx_callback _cb_fn;
         void *_cb_param;
         unsigned long local_flags;
         int xor_src_cnt;
-        int i = 0, src_off = 0, int_en;
+        int i = 0, src_off = 0;
 
         BUG_ON(src_cnt <= 1);
 
@@ -140,20 +158,11 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
                                 _cb_param = cb_param;
                         }
 
-                        int_en = _cb_fn ? 1 : 0;
-
-                        tx = device->device_prep_dma_xor(
-                                chan, xor_src_cnt, len, int_en);
-
-                        if (tx) {
-                                do_async_xor(tx, device, chan, dest,
-                                &src_list[src_off], offset, xor_src_cnt, len,
-                                local_flags, depend_tx, _cb_fn,
-                                _cb_param);
-                        } else /* fall through */
-                                goto xor_sync;
+                        tx = do_async_xor(device, chan, dest,
+                                          &src_list[src_off], offset,
+                                          xor_src_cnt, len, local_flags,
+                                          depend_tx, _cb_fn, _cb_param);
                 } else { /* run the xor synchronously */
-xor_sync:
                         /* in the sync case the dest is an implied source
                          * (assumes the dest is at the src_off index)
                          */
@@ -242,7 +251,7 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len)
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @result: 0 if sum == 0 else non-zero
- * @flags: ASYNC_TX_ASSUME_COHERENT, ASYNC_TX_ACK, ASYNC_TX_DEP_ACK
+ * @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
@@ -254,29 +263,36 @@ async_xor_zero_sum(struct page *dest, struct page **src_list,
         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);
+        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;
-        int int_en = cb_fn ? 1 : 0;
-        struct dma_async_tx_descriptor *tx = device ?
-                device->device_prep_dma_zero_sum(chan, src_cnt, len, result,
-                        int_en) : NULL;
-        int i;
+        struct dma_async_tx_descriptor *tx = NULL;
 
         BUG_ON(src_cnt <= 1);
 
-        if (tx) {
-                dma_addr_t dma_addr;
-                enum dma_data_direction dir;
+        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;
 
                 pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
 
-                dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-                        DMA_NONE : DMA_TO_DEVICE;
-
-                for (i = 0; i < src_cnt; i++) {
-                        dma_addr = dma_map_page(device->dev, src_list[i],
-                                offset, len, dir);
-                        tx->tx_set_src(dma_addr, tx, 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_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);
@@ -311,6 +327,16 @@ EXPORT_SYMBOL_GPL(async_xor_zero_sum);
 
 static int __init async_xor_init(void)
 {
+        #ifdef CONFIG_DMA_ENGINE
+        /* To conserve stack space the input src_list (array of page pointers)
+         * is reused to hold the array of dma addresses passed to the driver.
+         * This conversion is only possible when dma_addr_t is less than the
+         * the size of a pointer.  HIGHMEM64G is known to violate this
+         * assumption.
+         */
+        BUILD_BUG_ON(sizeof(dma_addr_t) > sizeof(struct page *));
+        #endif
+
         return 0;
 }