towards an async_tx update for 2.6.25

index 047e533..e8c8956 100644
@@ -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

@@ -55,20 +55,15 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 
 	if (tx) { /* run the memcpy asynchronously */
 		dma_addr_t addr;
-		enum dma_data_direction dir;
 
 		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);
+		addr = dma_map_page(device->dev, dest, dest_offset, len,
+				    DMA_FROM_DEVICE);
 		tx->tx_set_dest(addr, tx, 0);
 
-		dir = (flags & ASYNC_TX_ASSUME_COHERENT) ?
-			DMA_NONE : DMA_TO_DEVICE;
-
-		addr = dma_map_page(device->dev, src, src_offset, len, dir);
+		addr = dma_map_page(device->dev, src, src_offset, len,
+				    DMA_TO_DEVICE);
 		tx->tx_set_src(addr, tx, 0);
 
 		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);

index 66ef635..7609728 100644
@@ -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

@@ -55,13 +55,11 @@ async_memset(struct page *dest, int val, unsigned int offset,
 
 	if (tx) { /* run the memset asynchronously */
 		dma_addr_t dma_addr;
-		enum dma_data_direction dir;
 
 		pr_debug("%s: (async) 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);
+		dma_addr = dma_map_page(device->dev, dest, offset, len,
+					DMA_FROM_DEVICE);
 		tx->tx_set_dest(dma_addr, tx, 0);
 
 		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);

index 2575f67..f332ddc 100644
@@ -38,23 +38,17 @@ do_async_xor(struct dma_async_tx_descriptor *tx, struct dma_device *device,
 	dma_async_tx_callback cb_fn, void *cb_param)
 {
 	dma_addr_t dma_addr;
-	enum dma_data_direction dir;
 	int i;
 
 	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);
+	dma_addr = dma_map_page(device->dev, dest, offset, len,
+				DMA_FROM_DEVICE);
 	tx->tx_set_dest(dma_addr, tx, 0);
 
-	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);
+			offset, len, DMA_TO_DEVICE);
 		tx->tx_set_src(dma_addr, tx, i);
 	}
 

@@ -102,7 +96,7 @@ 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

@@ -242,7 +236,7 @@ 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

@@ -266,16 +260,12 @@ async_xor_zero_sum(struct page *dest, struct page **src_list,
 
 	if (tx) {
 		dma_addr_t dma_addr;
-		enum dma_data_direction dir;
 
 		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);
+				offset, len, DMA_TO_DEVICE);
 			tx->tx_set_src(dma_addr, tx, i);
 		}
 

index bdca3f1..3d59d37 100644
@@ -47,7 +47,6 @@ struct dma_chan_ref {
  * address is an implied source, whereas the asynchronous case it must be listed
  * as a source.  The destination address must be the first address in the source
  * array.
- * @ASYNC_TX_ASSUME_COHERENT: skip cache maintenance operations
  * @ASYNC_TX_ACK: immediately ack the descriptor, precludes setting up a
  * dependency chain
  * @ASYNC_TX_DEP_ACK: ack the dependency descriptor.  Useful for chaining.

@@ -55,7 +54,6 @@ struct dma_chan_ref {
 enum async_tx_flags {
 	ASYNC_TX_XOR_ZERO_DST	 = (1 << 0),
 	ASYNC_TX_XOR_DROP_DST	 = (1 << 1),
-	ASYNC_TX_ASSUME_COHERENT = (1 << 2),
 	ASYNC_TX_ACK		 = (1 << 3),
 	ASYNC_TX_DEP_ACK	 = (1 << 4),
 };

index e8c8956..faca0bc 100644
@@ -48,26 +48,25 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 {
 	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMCPY);
 	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;
+	if (device) {
+		dma_addr_t dma_dest, dma_src;
 
-		pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
+		dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
+					DMA_FROM_DEVICE);
 
-		addr = dma_map_page(device->dev, dest, dest_offset, len,
-				    DMA_FROM_DEVICE);
-		tx->tx_set_dest(addr, tx, 0);
+		dma_src = dma_map_page(device->dev, src, src_offset, len,
+				       DMA_TO_DEVICE);
 
-		addr = dma_map_page(device->dev, src, src_offset, len,
-				    DMA_TO_DEVICE);
-		tx->tx_set_src(addr, tx, 0);
+		tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
+						    len, cb_fn != NULL);
+	}
 
+	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);
 

index 7609728..0c94851 100644
@@ -48,20 +48,20 @@ async_memset(struct page *dest, int val, unsigned int offset,
 {
 	struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMSET);
 	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;
+	if (device) {
+		dma_addr_t dma_dest;
 
-		pr_debug("%s: (async) len: %zu\n", __FUNCTION__, len);
-
-		dma_addr = dma_map_page(device->dev, dest, offset, len,
+		dma_dest = dma_map_page(device->dev, dest, offset, len,
 					DMA_FROM_DEVICE);
-		tx->tx_set_dest(dma_addr, tx, 0);
 
+		tx = device->device_prep_dma_memset(chan, dma_dest, val, len,
+						    cb_fn != NULL);
+	}
+
+	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;

145 lines not on this page · raw message

88 lines not on this page · raw message

index 45e7b46..5bcfc55 100644
@@ -159,20 +159,6 @@ static int ioat_dma_enumerate_channels(struct ioatdma_device *device)
 	return device->common.chancnt;
 }
 
-static void ioat_set_src(dma_addr_t addr,
-			 struct dma_async_tx_descriptor *tx,
-			 int index)
-{
-	tx_to_ioat_desc(tx)->src = addr;
-}
-
-static void ioat_set_dest(dma_addr_t addr,
-			  struct dma_async_tx_descriptor *tx,
-			  int index)
-{
-	tx_to_ioat_desc(tx)->dst = addr;
-}
-
 /**
  * ioat_dma_memcpy_issue_pending - push potentially unrecognized appended
  *                                 descriptors to hw

@@ -415,8 +401,6 @@ static struct ioat_desc_sw *ioat_dma_alloc_descriptor(
 
 	memset(desc, 0, sizeof(*desc));
 	dma_async_tx_descriptor_init(&desc_sw->async_tx, &ioat_chan->common);
-	desc_sw->async_tx.tx_set_src = ioat_set_src;
-	desc_sw->async_tx.tx_set_dest = ioat_set_dest;
 	switch (ioat_chan->device->version) {
 	case IOAT_VER_1_2:
 		desc_sw->async_tx.tx_submit = ioat1_tx_submit;

@@ -714,6 +698,8 @@ static struct ioat_desc_sw *ioat_dma_get_next_descriptor(
 
 static struct dma_async_tx_descriptor *ioat1_dma_prep_memcpy(
 						struct dma_chan *chan,
+						dma_addr_t dma_dest,
+						dma_addr_t dma_src,
 						size_t len,
 						int int_en)
 {

@@ -726,6 +712,8 @@ static struct dma_async_tx_descriptor *ioat1_dma_prep_memcpy(
 
 	if (new) {
 		new->len = len;
+		new->dst = dma_dest;
+		new->src = dma_src;
 		return &new->async_tx;
 	} else
 		return NULL;

@@ -733,6 +721,8 @@ static struct dma_async_tx_descriptor *ioat1_dma_prep_memcpy(
 
 static struct dma_async_tx_descriptor *ioat2_dma_prep_memcpy(
 						struct dma_chan *chan,
+						dma_addr_t dma_dest,
+						dma_addr_t dma_src,
 						size_t len,
 						int int_en)
 {

@@ -749,6 +739,8 @@ static struct dma_async_tx_descriptor *ioat2_dma_prep_memcpy(
 
 	if (new) {
 		new->len = len;
+		new->dst = dma_dest;
+		new->src = dma_src;
 		return &new->async_tx;
 	} else
 		return NULL;

@@ -1045,7 +1037,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	u8 *dest;
 	struct dma_chan *dma_chan;
 	struct dma_async_tx_descriptor *tx;
-	dma_addr_t addr;
+	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
 	int err = 0;
 

@@ -1073,7 +1065,12 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 		goto out;
 	}
 
-	tx = device->common.device_prep_dma_memcpy(dma_chan, IOAT_TEST_SIZE, 0);
+	dma_src = dma_map_single(dma_chan->device->dev, src, IOAT_TEST_SIZE,
+				 DMA_TO_DEVICE);
+	dma_dest = dma_map_single(dma_chan->device->dev, dest, IOAT_TEST_SIZE,
+				  DMA_FROM_DEVICE);
+	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
+						   IOAT_TEST_SIZE, 0);
 	if (!tx) {
 		dev_err(&device->pdev->dev,
 			"Self-test prep failed, disabling\n");

@@ -1082,12 +1079,6 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	}
 
 	async_tx_ack(tx);
-	addr = dma_map_single(dma_chan->device->dev, src, IOAT_TEST_SIZE,
-			      DMA_TO_DEVICE);
-	tx->tx_set_src(addr, tx, 0);
-	addr = dma_map_single(dma_chan->device->dev, dest, IOAT_TEST_SIZE,
-			      DMA_FROM_DEVICE);
-	tx->tx_set_dest(addr, tx, 0);
 	tx->callback = ioat_dma_test_callback;
 	tx->callback_param = (void *)0x8086;
 	cookie = tx->tx_submit(tx);

235 lines not on this page · raw message

index 55c9a69..e38af8b 100644
@@ -209,8 +209,6 @@ typedef void (*dma_async_tx_callback)(void *dma_async_param);
  *	descriptors
  * @chan: target channel for this operation
  * @tx_submit: set the prepared descriptor(s) to be executed by the engine
- * @tx_set_dest: set a destination address in a hardware descriptor
- * @tx_set_src: set a source address in a hardware descriptor
  * @callback: routine to call after this operation is complete
  * @callback_param: general parameter to pass to the callback routine
  * ---async_tx api specific fields---

@@ -227,10 +225,6 @@ struct dma_async_tx_descriptor {
 	struct list_head tx_list;
 	struct dma_chan *chan;
 	dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx);
-	void (*tx_set_dest)(dma_addr_t addr,
-		struct dma_async_tx_descriptor *tx, int index);
-	void (*tx_set_src)(dma_addr_t addr,
-		struct dma_async_tx_descriptor *tx, int index);
 	dma_async_tx_callback callback;
 	void *callback_param;
 	struct list_head depend_list;

@@ -279,15 +273,17 @@ struct dma_device {
 	void (*device_free_chan_resources)(struct dma_chan *chan);
 
 	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
-		struct dma_chan *chan, size_t len, int int_en);
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, int int_en);
 	struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
-		struct dma_chan *chan, unsigned int src_cnt, size_t len,
-		int int_en);
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
+		unsigned int src_cnt, size_t len, int int_en);
 	struct dma_async_tx_descriptor *(*device_prep_dma_zero_sum)(
-		struct dma_chan *chan, unsigned int src_cnt, size_t len,
-		u32 *result, int int_en);
+		struct dma_chan *chan, dma_addr_t *src,	unsigned int src_cnt,
+		size_t len, u32 *result, int int_en);
 	struct dma_async_tx_descriptor *(*device_prep_dma_memset)(
-		struct dma_chan *chan, int value, size_t len, int int_en);
+		struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
+		int int_en);
 	struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
 		struct dma_chan *chan);
 

index faca0bc..25dcf33 100644
@@ -52,6 +52,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 
 	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);

@@ -60,7 +61,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 				       DMA_TO_DEVICE);
 
 		tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
-						    len, cb_fn != NULL);
+						    len, dma_prep_flags);
 	}
 
 	if (tx) {

index 0c94851..8e98ab0 100644
@@ -52,12 +52,13 @@ async_memset(struct page *dest, int val, unsigned int offset,
 
 	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,
-						    cb_fn != NULL);
+						    dma_prep_flags);
 	}
 
 	if (tx) {

index fbf113a..80f30bc 100644
@@ -41,6 +41,7 @@ do_async_xor(struct dma_device *device,
 	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);
 

@@ -56,7 +57,7 @@ do_async_xor(struct dma_device *device,
 	 * in case they can not provide a descriptor
 	 */
 	tx = device->device_prep_dma_xor(chan, dma_dest, dma_src, src_cnt, len,
-					 cb_fn != NULL);
+					 dma_prep_flags);
 	if (!tx) {
 		if (depend_tx)
 			dma_wait_for_async_tx(depend_tx);

@@ -64,7 +65,7 @@ do_async_xor(struct dma_device *device,
 		while (!tx)
 			tx = device->device_prep_dma_xor(chan, dma_dest,
 							 dma_src, src_cnt, len,
-							 cb_fn != NULL);
+							 dma_prep_flags);
 	}
 
 	async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);

@@ -264,6 +265,7 @@ async_xor_zero_sum(struct page *dest, struct page **src_list,
 
 	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);

@@ -274,7 +276,7 @@ async_xor_zero_sum(struct page *dest, struct page **src_list,
 
 		tx = device->device_prep_dma_zero_sum(chan, dma_src, src_cnt,
 						      len, result,
-						      cb_fn != NULL);
+						      dma_prep_flags);
 		if (!tx) {
 			if (depend_tx)
 				dma_wait_for_async_tx(depend_tx);

@@ -282,7 +284,7 @@ async_xor_zero_sum(struct page *dest, struct page **src_list,
 			while (!tx)
 				tx = device->device_prep_dma_zero_sum(chan,
 					dma_src, src_cnt, len, result,
-					cb_fn != NULL);
+					dma_prep_flags);
 		}
 
 		async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);

index 5bcfc55..dff38ac 100644
@@ -701,7 +701,7 @@ static struct dma_async_tx_descriptor *ioat1_dma_prep_memcpy(
 						dma_addr_t dma_dest,
 						dma_addr_t dma_src,
 						size_t len,
-						int int_en)
+						unsigned long flags)
 {
 	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
 	struct ioat_desc_sw *new;

@@ -724,7 +724,7 @@ static struct dma_async_tx_descriptor *ioat2_dma_prep_memcpy(
 						dma_addr_t dma_dest,
 						dma_addr_t dma_src,
 						size_t len,
-						int int_en)
+						unsigned long flags)
 {
 	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
 	struct ioat_desc_sw *new;

index eda841c..3986d54 100644
@@ -537,7 +537,7 @@ iop_adma_prep_dma_interrupt(struct dma_chan *chan)
 
 static struct dma_async_tx_descriptor *
 iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
-			 dma_addr_t dma_src, size_t len, int int_en)
+			 dma_addr_t dma_src, size_t len, unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;

@@ -555,7 +555,7 @@ iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		iop_desc_init_memcpy(grp_start, int_en);
+		iop_desc_init_memcpy(grp_start, flags);
 		iop_desc_set_byte_count(grp_start, iop_chan, len);
 		iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
 		iop_desc_set_memcpy_src_addr(grp_start, dma_src);

@@ -569,7 +569,7 @@ iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 
 static struct dma_async_tx_descriptor *
 iop_adma_prep_dma_memset(struct dma_chan *chan, dma_addr_t dma_dest,
-			 int value, size_t len, int int_en)
+			 int value, size_t len, unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;

@@ -587,7 +587,7 @@ iop_adma_prep_dma_memset(struct dma_chan *chan, dma_addr_t dma_dest,
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		iop_desc_init_memset(grp_start, int_en);
+		iop_desc_init_memset(grp_start, flags);
 		iop_desc_set_byte_count(grp_start, iop_chan, len);
 		iop_desc_set_block_fill_val(grp_start, value);
 		iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);

@@ -602,7 +602,7 @@ iop_adma_prep_dma_memset(struct dma_chan *chan, dma_addr_t dma_dest,
 static struct dma_async_tx_descriptor *
 iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 		      dma_addr_t *dma_src, unsigned int src_cnt, size_t len,
-		      int int_en)
+		      unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;

@@ -613,15 +613,15 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 	BUG_ON(unlikely(len > IOP_ADMA_XOR_MAX_BYTE_COUNT));
 
 	dev_dbg(iop_chan->device->common.dev,
-		"%s src_cnt: %d len: %u int_en: %d\n",
-		__FUNCTION__, src_cnt, len, int_en);
+		"%s src_cnt: %d len: %u flags: %lx\n",
+		__FUNCTION__, src_cnt, len, flags);
 
 	spin_lock_bh(&iop_chan->lock);
 	slot_cnt = iop_chan_xor_slot_count(len, src_cnt, &slots_per_op);
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		iop_desc_init_xor(grp_start, src_cnt, int_en);
+		iop_desc_init_xor(grp_start, src_cnt, flags);
 		iop_desc_set_byte_count(grp_start, iop_chan, len);
 		iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
 		sw_desc->unmap_src_cnt = src_cnt;

@@ -638,7 +638,7 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 static struct dma_async_tx_descriptor *
 iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
 			   unsigned int src_cnt, size_t len, u32 *result,
-			   int int_en)
+			   unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;

@@ -655,7 +655,7 @@ iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		iop_desc_init_zero_sum(grp_start, src_cnt, int_en);
+		iop_desc_init_zero_sum(grp_start, src_cnt, flags);
 		iop_desc_set_zero_sum_byte_count(grp_start, len);
 		grp_start->xor_check_result = result;
 		pr_debug("\t%s: grp_start->xor_check_result: %p\n",

index 04006c1..efd9a5e 100644
@@ -247,7 +247,7 @@ static inline u32 iop_desc_get_src_count(struct iop_adma_desc_slot *desc,
 }
 
 static inline void
-iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, int int_en)
+iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, unsigned long flags)
 {
 	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
 	union {

@@ -257,13 +257,13 @@ iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, int int_en)
 
 	u_desc_ctrl.value = 0;
 	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 	hw_desc->crc_addr = 0;
 }
 
 static inline void
-iop_desc_init_memset(struct iop_adma_desc_slot *desc, int int_en)
+iop_desc_init_memset(struct iop_adma_desc_slot *desc, unsigned long flags)
 {
 	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
 	union {

@@ -274,14 +274,15 @@ iop_desc_init_memset(struct iop_adma_desc_slot *desc, int int_en)
 	u_desc_ctrl.value = 0;
 	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
 	u_desc_ctrl.field.block_fill_en = 1;
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 	hw_desc->crc_addr = 0;
 }
 
 /* to do: support buffers larger than ADMA_MAX_BYTE_COUNT */
 static inline void
-iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
+iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
 {
 	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
 	union {

@@ -292,7 +293,7 @@ iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 	u_desc_ctrl.value = 0;
 	u_desc_ctrl.field.src_select = src_cnt - 1;
 	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 	hw_desc->crc_addr = 0;
 

@@ -301,7 +302,8 @@ iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 
 /* to do: support buffers larger than ADMA_MAX_BYTE_COUNT */
 static inline int
-iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
+iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+		       unsigned long flags)
 {
 	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
 	union {

@@ -314,7 +316,7 @@ iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 	u_desc_ctrl.field.xfer_dir = 3; /* local to internal bus */
 	u_desc_ctrl.field.zero_result = 1;
 	u_desc_ctrl.field.status_write_back_en = 1;
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 	hw_desc->crc_addr = 0;
 

index 10834b5..5c529e6 100644
@@ -414,7 +414,7 @@ static inline void iop3xx_aau_desc_set_src_addr(struct iop3xx_desc_aau *hw_desc,
 }
 
 static inline void
-iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, int int_en)
+iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, unsigned long flags)
 {
 	struct iop3xx_desc_dma *hw_desc = desc->hw_desc;
 	union {

@@ -425,14 +425,14 @@ iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, int int_en)
 	u_desc_ctrl.value = 0;
 	u_desc_ctrl.field.mem_to_mem_en = 1;
 	u_desc_ctrl.field.pci_transaction = 0xe; /* memory read block */
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 	hw_desc->upper_pci_src_addr = 0;
 	hw_desc->crc_addr = 0;
 }
 
 static inline void
-iop_desc_init_memset(struct iop_adma_desc_slot *desc, int int_en)
+iop_desc_init_memset(struct iop_adma_desc_slot *desc, unsigned long flags)
 {
 	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
 	union {

@@ -443,12 +443,13 @@ iop_desc_init_memset(struct iop_adma_desc_slot *desc, int int_en)
 	u_desc_ctrl.value = 0;
 	u_desc_ctrl.field.blk1_cmd_ctrl = 0x2; /* memory block fill */
 	u_desc_ctrl.field.dest_write_en = 1;
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 }
 
 static inline u32
-iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt, int int_en)
+iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt,
+		     unsigned long flags)
 {
 	int i, shift;
 	u32 edcr;

@@ -509,21 +510,23 @@ iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt, int int_en)
 
 	u_desc_ctrl.field.dest_write_en = 1;
 	u_desc_ctrl.field.blk1_cmd_ctrl = 0x7; /* direct fill */
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 
 	return u_desc_ctrl.value;
 }
 
 static inline void
-iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
+iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
 {
-	iop3xx_desc_init_xor(desc->hw_desc, src_cnt, int_en);
+	iop3xx_desc_init_xor(desc->hw_desc, src_cnt, flags);
 }
 
 /* return the number of operations */
 static inline int
-iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
+iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+		       unsigned long flags)
 {
 	int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
 	struct iop3xx_desc_aau *hw_desc, *prev_hw_desc, *iter;

@@ -538,10 +541,10 @@ iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 	for (i = 0, j = 0; (slot_cnt -= slots_per_op) >= 0;
 		i += slots_per_op, j++) {
 		iter = iop_hw_desc_slot_idx(hw_desc, i);
-		u_desc_ctrl.value = iop3xx_desc_init_xor(iter, src_cnt, int_en);
+		u_desc_ctrl.value = iop3xx_desc_init_xor(iter, src_cnt, flags);
 		u_desc_ctrl.field.dest_write_en = 0;
 		u_desc_ctrl.field.zero_result_en = 1;
-		u_desc_ctrl.field.int_en = int_en;
+		u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 		iter->desc_ctrl = u_desc_ctrl.value;
 
 		/* for the subsequent descriptors preserve the store queue

@@ -559,7 +562,8 @@ iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 }
 
 static inline void
-iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
+iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt,
+		       unsigned long flags)
 {
 	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
 	union {

@@ -591,7 +595,7 @@ iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt, int int_en)
 	}
 
 	u_desc_ctrl.field.dest_write_en = 0;
-	u_desc_ctrl.field.int_en = int_en;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 }
 

index e38af8b..586ea37 100644
@@ -95,6 +95,15 @@ enum dma_transaction_type {
 #define DMA_TX_TYPE_END (DMA_INTERRUPT + 1)
 
 /**
+ * enum dma_prep_flags - DMA flags to augment operation preparation
+ * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of
+ * 	this transaction
+ */
+enum dma_prep_flags {
+	DMA_PREP_INTERRUPT = (1 << 0),
+};
+
+/**
  * dma_cap_mask_t - capabilities bitmap modeled after cpumask_t.
  * See linux/cpumask.h
  */

@@ -274,16 +283,16 @@ struct dma_device {
 
 	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
 		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
-		size_t len, int int_en);
+		size_t len, unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
 		struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
-		unsigned int src_cnt, size_t len, int int_en);
+		unsigned int src_cnt, size_t len, unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_zero_sum)(
 		struct dma_chan *chan, dma_addr_t *src,	unsigned int src_cnt,
-		size_t len, u32 *result, int int_en);
+		size_t len, u32 *result, unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_memset)(
 		struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
-		int int_en);
+		unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
 		struct dma_chan *chan);
 

index 25dcf33..0f62822 100644
@@ -46,7 +46,8 @@ 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;
 	struct dma_async_tx_descriptor *tx = NULL;
 

index 8e98ab0..09c0e83 100644
@@ -46,7 +46,8 @@ 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;
 	struct dma_async_tx_descriptor *tx = NULL;
 

index f39777f..5628821 100644
@@ -361,13 +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 */

@@ -383,7 +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)
 {

index 80f30bc..e6dfacc 100644
@@ -125,7 +125,9 @@ 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;

@@ -257,7 +259,9 @@ 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;
 	struct dma_async_tx_descriptor *tx = NULL;
 

index 3d59d37..eb640f0 100644
@@ -62,9 +62,15 @@ enum async_tx_flags {
 void async_tx_issue_pending_all(void);
 enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
 void async_tx_run_dependencies(struct dma_async_tx_descriptor *tx);
+#ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL
+#include <asm/async_tx.h>
+#else
+#define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \
+	 __async_tx_find_channel(dep, 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);
+#endif /* CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL */
 #else
 static inline void async_tx_issue_pending_all(void)
 {

@@ -86,7 +92,8 @@ async_tx_run_dependencies(struct dma_async_tx_descriptor *tx,
 
 static inline struct dma_chan *
 async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
-	enum dma_transaction_type tx_type)
+	enum dma_transaction_type tx_type, struct page **dst, int dst_count,
+	struct page **src, int src_count, size_t len)
 {
 	return NULL;
 }