async_tx: replace 'int_en' with operation preparation flags

Pass a full set of flags to drivers' per-operation 'prep' routines.
Currently the only flag passed is DMA_PREP_INTERRUPT.  The expectation is
that arch-specific async_tx_find_channel() implementations can exploit this
capability to find the best channel for an operation.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Reviewed-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
diff --git a/include/asm-arm/arch-iop13xx/adma.h b/include/asm-arm/arch-iop13xx/adma.h
index 04006c1..efd9a5e 100644
--- a/include/asm-arm/arch-iop13xx/adma.h
+++ b/include/asm-arm/arch-iop13xx/adma.h
@@ -247,7 +247,7 @@
 }
 
 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 @@
 
 	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 @@
 	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 @@
 	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 @@
 
 /* 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 @@
 	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;
 
diff --git a/include/asm-arm/hardware/iop3xx-adma.h b/include/asm-arm/hardware/iop3xx-adma.h
index 10834b5..5c529e6 100644
--- a/include/asm-arm/hardware/iop3xx-adma.h
+++ b/include/asm-arm/hardware/iop3xx-adma.h
@@ -414,7 +414,7 @@
 }
 
 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 @@
 	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 @@
 	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 @@
 
 	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 @@
 	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 @@
 }
 
 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 @@
 	}
 
 	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;
 }
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index b0864f5..acbb364 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -95,6 +95,15 @@
 #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_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);