Merge branch 'next' into for-linus-3.0

Author: Vinod Koul

Documentation/dmaengine.txt

@@ -10,87 +10,181 @@ NOTE: For DMA Engine usage in async_tx please see:
 Below is a guide to device driver writers on how to use the Slave-DMA API of the
 DMA Engine. This is applicable only for slave DMA usage only.
 
-The slave DMA usage consists of following steps
+The slave DMA usage consists of following steps:
 1. Allocate a DMA slave channel
 2. Set slave and controller specific parameters
 3. Get a descriptor for transaction
-4. Submit the transaction and wait for callback notification
+4. Submit the transaction
+5. Issue pending requests and wait for callback notification
 
 1. Allocate a DMA slave channel
-Channel allocation is slightly different in the slave DMA context, client
-drivers typically need a channel from a particular DMA controller only and even
-in some cases a specific channel is desired. To request a channel
-dma_request_channel() API is used.
-
-Interface:
-struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
-		dma_filter_fn filter_fn,
-		void *filter_param);
-where dma_filter_fn is defined as:
-typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
-
-When the optional 'filter_fn' parameter is set to NULL dma_request_channel
-simply returns the first channel that satisfies the capability mask.  Otherwise,
-when the mask parameter is insufficient for specifying the necessary channel,
-the filter_fn routine can be used to disposition the available channels in the
-system. The filter_fn routine is called once for each free channel in the
-system.  Upon seeing a suitable channel filter_fn returns DMA_ACK which flags
-that channel to be the return value from dma_request_channel.  A channel
-allocated via this interface is exclusive to the caller, until
-dma_release_channel() is called.
+
+   Channel allocation is slightly different in the slave DMA context,
+   client drivers typically need a channel from a particular DMA
+   controller only and even in some cases a specific channel is desired.
+   To request a channel dma_request_channel() API is used.
+
+   Interface:
+	struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+			dma_filter_fn filter_fn,
+			void *filter_param);
+   where dma_filter_fn is defined as:
+	typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+   The 'filter_fn' parameter is optional, but highly recommended for
+   slave and cyclic channels as they typically need to obtain a specific
+   DMA channel.
+
+   When the optional 'filter_fn' parameter is NULL, dma_request_channel()
+   simply returns the first channel that satisfies the capability mask.
+
+   Otherwise, the 'filter_fn' routine will be called once for each free
+   channel which has a capability in 'mask'.  'filter_fn' is expected to
+   return 'true' when the desired DMA channel is found.
+
+   A channel allocated via this interface is exclusive to the caller,
+   until dma_release_channel() is called.
 
 2. Set slave and controller specific parameters
-Next step is always to pass some specific information to the DMA driver. Most of
-the generic information which a slave DMA can use is in struct dma_slave_config.
-It allows the clients to specify DMA direction, DMA addresses, bus widths, DMA
-burst lengths etc. If some DMA controllers have more parameters to be sent then
-they should try to embed struct dma_slave_config in their controller specific
-structure. That gives flexibility to client to pass more parameters, if
-required.
-
-Interface:
-int dmaengine_slave_config(struct dma_chan *chan,
-					  struct dma_slave_config *config)
+
+   Next step is always to pass some specific information to the DMA
+   driver.  Most of the generic information which a slave DMA can use
+   is in struct dma_slave_config.  This allows the clients to specify
+   DMA direction, DMA addresses, bus widths, DMA burst lengths etc
+   for the peripheral.
+
+   If some DMA controllers have more parameters to be sent then they
+   should try to embed struct dma_slave_config in their controller
+   specific structure. That gives flexibility to client to pass more
+   parameters, if required.
+
+   Interface:
+	int dmaengine_slave_config(struct dma_chan *chan,
+				  struct dma_slave_config *config)
+
+   Please see the dma_slave_config structure definition in dmaengine.h
+   for a detailed explaination of the struct members.  Please note
+   that the 'direction' member will be going away as it duplicates the
+   direction given in the prepare call.
 
 3. Get a descriptor for transaction
-For slave usage the various modes of slave transfers supported by the
-DMA-engine are:
-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
+
+   For slave usage the various modes of slave transfers supported by the
+   DMA-engine are:
+
+   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.
-The non NULL return of this transfer API represents a "descriptor" for the given
-transaction.
-
-Interface:
-struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_sg)(
-		struct dma_chan *chan,
-		struct scatterlist *dst_sg, unsigned int dst_nents,
-		struct scatterlist *src_sg, unsigned int src_nents,
+
+   A non-NULL return of this transfer API represents a "descriptor" for
+   the given transaction.
+
+   Interface:
+	struct dma_async_tx_descriptor *(*chan->device->device_prep_slave_sg)(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_data_direction direction,
 		unsigned long flags);
-struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
+
+	struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_data_direction direction);
 
-4. Submit the transaction and wait for callback notification
-To schedule the transaction to be scheduled by dma device, the "descriptor"
-returned in above (3) needs to be submitted.
-To tell the dma driver that a transaction is ready to be serviced, the
-descriptor->submit() callback needs to be invoked. This chains the descriptor to
-the pending queue.
-The transactions in the pending queue can be activated by calling the
-issue_pending API. If channel is idle then the first transaction in queue is
-started and subsequent ones queued up.
-On completion of the DMA operation the next in queue is submitted and a tasklet
-triggered. The tasklet would then call the client driver completion callback
-routine for notification, if set.
-Interface:
-void dma_async_issue_pending(struct dma_chan *chan);
-
-==============================================================================
-
-Additional usage notes for dma driver writers
-1/ Although DMA engine specifies that completion callback routines cannot submit
-any new operations, but typically for slave DMA subsequent transaction may not
-be available for submit prior to callback routine being called. This requirement
-is not a requirement for DMA-slave devices. But they should take care to drop
-the spin-lock they might be holding before calling the callback routine
+   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.
+   The scatterlist must be mapped using the DMA struct device.  So,
+   normal setup should look like this:
+
+	nr_sg = dma_map_sg(chan->device->dev, sgl, sg_len);
+	if (nr_sg == 0)
+		/* error */
+
+	desc = chan->device->device_prep_slave_sg(chan, sgl, nr_sg,
+			direction, flags);
+
+   Once a descriptor has been obtained, the callback information can be
+   added and the descriptor must then be submitted.  Some DMA engine
+   drivers may hold a spinlock between a successful preparation and
+   submission so it is important that these two operations are closely
+   paired.
+
+   Note:
+	Although the async_tx API specifies that completion callback
+	routines cannot submit any new operations, this is not the
+	case for slave/cyclic DMA.
+
+	For slave DMA, the subsequent transaction may not be available
+	for submission prior to callback function being invoked, so
+	slave DMA callbacks are permitted to prepare and submit a new
+	transaction.
+
+	For cyclic DMA, a callback function may wish to terminate the
+	DMA via dmaengine_terminate_all().
+
+	Therefore, it is important that DMA engine drivers drop any
+	locks before calling the callback function which may cause a
+	deadlock.
+
+	Note that callbacks will always be invoked from the DMA
+	engines tasklet, never from interrupt context.
+
+4. Submit the transaction
+
+   Once the descriptor has been prepared and the callback information
+   added, it must be placed on the DMA engine drivers pending queue.
+
+   Interface:
+	dma_cookie_t dmaengine_submit(struct dma_async_tx_descriptor *desc)
+
+   This returns a cookie can be used to check the progress of DMA engine
+   activity via other DMA engine calls not covered in this document.
+
+   dmaengine_submit() will not start the DMA operation, it merely adds
+   it to the pending queue.  For this, see step 5, dma_async_issue_pending.
+
+5. Issue pending DMA requests and wait for callback notification
+
+   The transactions in the pending queue can be activated by calling the
+   issue_pending API. If channel is idle then the first transaction in
+   queue is started and subsequent ones queued up.
+
+   On completion of each DMA operation, the next in queue is started and
+   a tasklet triggered. The tasklet will then call the client driver
+   completion callback routine for notification, if set.
+
+   Interface:
+	void dma_async_issue_pending(struct dma_chan *chan);
+
+Further APIs:
+
+1. int dmaengine_terminate_all(struct dma_chan *chan)
+
+   This causes all activity for the DMA channel to be stopped, and may
+   discard data in the DMA FIFO which hasn't been fully transferred.
+   No callback functions will be called for any incomplete transfers.
+
+2. int dmaengine_pause(struct dma_chan *chan)
+
+   This pauses activity on the DMA channel without data loss.
+
+3. int dmaengine_resume(struct dma_chan *chan)
+
+   Resume a previously paused DMA channel.  It is invalid to resume a
+   channel which is not currently paused.
+
+4. enum dma_status dma_async_is_tx_complete(struct dma_chan *chan,
+        dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used)
+
+   This can be used to check the status of the channel.  Please see
+   the documentation in include/linux/dmaengine.h for a more complete
+   description of this API.
+
+   This can be used in conjunction with dma_async_is_complete() and
+   the cookie returned from 'descriptor->submit()' to check for
+   completion of a specific DMA transaction.
+
+   Note:
+	Not all DMA engine drivers can return reliable information for
+	a running DMA channel.  It is recommended that DMA engine users
+	pause or stop (via dmaengine_terminate_all) the channel before
+	using this API.

Documentation/spi/ep93xx_spi

@@ -88,6 +88,16 @@ static void __init ts72xx_init_machine(void)
 			    ARRAY_SIZE(ts72xx_spi_devices));
 }
 
+The driver can use DMA for the transfers also. In this case ts72xx_spi_info
+becomes:
+
+static struct ep93xx_spi_info ts72xx_spi_info = {
+	.num_chipselect	= ARRAY_SIZE(ts72xx_spi_devices),
+	.use_dma	= true;
+};
+
+Note that CONFIG_EP93XX_DMA should be enabled as well.
+
 Thanks to
 =========
 Martin Guy, H. Hartley Sweeten and others who helped me during development of

arch/arm/mach-ep93xx/Makefile

@@ -1,11 +1,13 @@
 #
 # Makefile for the linux kernel.
 #
-obj-y			:= core.o clock.o dma-m2p.o gpio.o
+obj-y			:= core.o clock.o gpio.o
 obj-m			:=
 obj-n			:=
 obj-			:=
 
+obj-$(CONFIG_EP93XX_DMA)	+= dma.o
+
 obj-$(CONFIG_MACH_ADSSPHERE)	+= adssphere.o
 obj-$(CONFIG_MACH_EDB93XX)	+= edb93xx.o
 obj-$(CONFIG_MACH_GESBC9312)	+= gesbc9312.o

arch/arm/mach-ep93xx/core.c

@@ -492,11 +492,15 @@ static struct resource ep93xx_spi_resources[] = {
 	},
 };
 
+static u64 ep93xx_spi_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device ep93xx_spi_device = {
 	.name		= "ep93xx-spi",
 	.id		= 0,
 	.dev		= {
-		.platform_data = &ep93xx_spi_master_data,
+		.platform_data		= &ep93xx_spi_master_data,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.dma_mask		= &ep93xx_spi_dma_mask,
 	},
 	.num_resources	= ARRAY_SIZE(ep93xx_spi_resources),
 	.resource	= ep93xx_spi_resources,