DMAEngine: Define interleaved transfer request api

Define a new api that could be used for doing fancy data transfers
like interleaved to contiguous copy and vice-versa.
Traditional SG_list based transfers tend to be very inefficient in
such cases as where the interleave and chunk are only a few bytes,
which call for a very condensed api to convey pattern of the transfer.
This api supports all 4 variants of scatter-gather and contiguous transfer.

Of course, neither can this api help transfers that don't lend to DMA by
nature, i.e, scattered tiny read/writes with no periodic pattern.

Also since now we support SLAVE channels that might not provide
device_prep_slave_sg callback but device_prep_interleaved_dma,
remove the BUG_ON check.

Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
Acked-by: Barry Song <Baohua.Song@csr.com>
[renamed dmaxfer_template to dma_interleaved_template
 did fixup after the enum dma_transfer_merge]
Signed-off-by: Vinod Koul <vinod.koul@linux.intel.com>

Documentation/dmaengine.txt

@@ -75,6 +75,10 @@ The slave DMA usage consists of following steps:
    slave_sg	- DMA a list of scatter gather buffers from/to a peripheral
    dma_cyclic	- Perform a cyclic DMA operation from/to a peripheral till the
 		  operation is explicitly stopped.
+   interleaved_dma - This is common to Slave as well as M2M clients. For slave
+		 address of devices' fifo could be already known to the driver.
+		 Various types of operations could be expressed by setting
+		 appropriate values to the 'dma_interleaved_template' members.
 
    A non-NULL return of this transfer API represents a "descriptor" for
    the given transaction.
@@ -89,6 +93,10 @@ The slave DMA usage consists of following steps:
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_data_direction direction);
 
+	struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)(
+		struct dma_chan *chan, struct dma_interleaved_template *xt,
+		unsigned long flags);
+
    The peripheral driver is expected to have mapped the scatterlist for
    the DMA operation prior to calling device_prep_slave_sg, and must
    keep the scatterlist mapped until the DMA operation has completed.

drivers/dma/dmaengine.c

@@ -693,12 +693,12 @@ int dma_async_device_register(struct dma_device *device)
 		!device->device_prep_dma_interrupt);
 	BUG_ON(dma_has_cap(DMA_SG, device->cap_mask) &&
 		!device->device_prep_dma_sg);
-	BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) &&
-		!device->device_prep_slave_sg);
 	BUG_ON(dma_has_cap(DMA_CYCLIC, device->cap_mask) &&
 		!device->device_prep_dma_cyclic);
 	BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) &&
 		!device->device_control);
+	BUG_ON(dma_has_cap(DMA_INTERLEAVE, device->cap_mask) &&
+		!device->device_prep_interleaved_dma);
 
 	BUG_ON(!device->device_alloc_chan_resources);
 	BUG_ON(!device->device_free_chan_resources);

include/linux/dmaengine.h

@@ -71,10 +71,10 @@ enum dma_transaction_type {
 	DMA_ASYNC_TX,
 	DMA_SLAVE,
 	DMA_CYCLIC,
-};
+	DMA_INTERLEAVE,
-
 /* last transaction type for creation of the capabilities mask */
-#define DMA_TX_TYPE_END (DMA_CYCLIC + 1)
+	DMA_TX_TYPE_END,
+};
 
 /**
  * enum dma_transfer_direction - dma transfer mode and direction indicator
@@ -90,6 +90,74 @@ enum dma_transfer_direction {
 	DMA_DEV_TO_DEV,
 };
 
+/**
+ * Interleaved Transfer Request
+ * ----------------------------
+ * A chunk is collection of contiguous bytes to be transfered.
+ * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG).
+ * ICGs may or maynot change between chunks.
+ * A FRAME is the smallest series of contiguous {chunk,icg} pairs,
+ *  that when repeated an integral number of times, specifies the transfer.
+ * A transfer template is specification of a Frame, the number of times
+ *  it is to be repeated and other per-transfer attributes.
+ *
+ * Practically, a client driver would have ready a template for each
+ *  type of transfer it is going to need during its lifetime and
+ *  set only 'src_start' and 'dst_start' before submitting the requests.
+ *
+ *
+ *  |      Frame-1        |       Frame-2       | ~ |       Frame-'numf'  |
+ *  |====....==.===...=...|====....==.===...=...| ~ |====....==.===...=...|
+ *
+ *    ==  Chunk size
+ *    ... ICG
+ */
+
+/**
+ * struct data_chunk - Element of scatter-gather list that makes a frame.
+ * @size: Number of bytes to read from source.
+ *	  size_dst := fn(op, size_src), so doesn't mean much for destination.
+ * @icg: Number of bytes to jump after last src/dst address of this
+ *	 chunk and before first src/dst address for next chunk.
+ *	 Ignored for dst(assumed 0), if dst_inc is true and dst_sgl is false.
+ *	 Ignored for src(assumed 0), if src_inc is true and src_sgl is false.
+ */
+struct data_chunk {
+	size_t size;
+	size_t icg;
+};
+
+/**
+ * struct dma_interleaved_template - Template to convey DMAC the transfer pattern
+ *	 and attributes.
+ * @src_start: Bus address of source for the first chunk.
+ * @dst_start: Bus address of destination for the first chunk.
+ * @dir: Specifies the type of Source and Destination.
+ * @src_inc: If the source address increments after reading from it.
+ * @dst_inc: If the destination address increments after writing to it.
+ * @src_sgl: If the 'icg' of sgl[] applies to Source (scattered read).
+ *		Otherwise, source is read contiguously (icg ignored).
+ *		Ignored if src_inc is false.
+ * @dst_sgl: If the 'icg' of sgl[] applies to Destination (scattered write).
+ *		Otherwise, destination is filled contiguously (icg ignored).
+ *		Ignored if dst_inc is false.
+ * @numf: Number of frames in this template.
+ * @frame_size: Number of chunks in a frame i.e, size of sgl[].
+ * @sgl: Array of {chunk,icg} pairs that make up a frame.
+ */
+struct dma_interleaved_template {
+	dma_addr_t src_start;
+	dma_addr_t dst_start;
+	enum dma_transfer_direction dir;
+	bool src_inc;
+	bool dst_inc;
+	bool src_sgl;
+	bool dst_sgl;
+	size_t numf;
+	size_t frame_size;
+	struct data_chunk sgl[0];
+};
+
 /**
  * enum dma_ctrl_flags - DMA flags to augment operation preparation,
  *  control completion, and communicate status.
@@ -445,6 +513,7 @@ struct dma_tx_state {
  * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio.
  *	The function takes a buffer of size buf_len. The callback function will
  *	be called after period_len bytes have been transferred.
+ * @device_prep_interleaved_dma: Transfer expression in a generic way.
  * @device_control: manipulate all pending operations on a channel, returns
  *	zero or error code
  * @device_tx_status: poll for transaction completion, the optional
@@ -509,6 +578,9 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_dma_cyclic)(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_transfer_direction direction);
+	struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)(
+		struct dma_chan *chan, struct dma_interleaved_template *xt,
+		unsigned long flags);
 	int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		unsigned long arg);