iio: Add generic DMA buffer infrastructure

The traditional approach used in IIO to implement buffered capture requires
the generation of at least one interrupt per sample. In the interrupt
handler the driver reads the sample from the device and copies it to a
software buffer. This approach has a rather large per sample overhead
associated with it. And while it works fine for samplerates in the range of
up to 1000 samples per second it starts to consume a rather large share of
the available CPU processing time once we go beyond that, this is
especially true on an embedded system with limited processing power. The
regular interrupt also causes increased power consumption by not allowing
the hardware into deeper sleep states, which is something that becomes more
and more important on mobile battery powered devices.

And while the recently added watermark support mitigates some of the issues
by allowing the device to generate interrupts at a rate lower than the data
output rate, this still requires a storage buffer inside the device and
even if it exists it is only a few 100 samples deep at most.

DMA support on the other hand allows to capture multiple millions or even
more samples without any CPU interaction. This allows the CPU to either go
to sleep for longer periods or focus on other tasks which increases overall
system performance and power consumption. In addition to that some devices
might not even offer a way to read the data other than using DMA, which
makes DMA mandatory to use for them.

The tasks involved in implementing a DMA buffer can be divided into two
categories. The first category is memory buffer management (allocation,
mapping, etc.) and hooking this up the IIO buffer callbacks like read(),
enable(), disable(), etc. The second category of tasks is to setup the
DMA hardware and manage the DMA transfers. Tasks from the first category
will be very similar for all IIO drivers supporting DMA buffers, while the
tasks from the second category will be hardware specific.

This patch implements a generic infrastructure that take care of the former
tasks. It provides a set of functions that implement the standard IIO
buffer iio_buffer_access_funcs callbacks. These can either be used as is or
be overloaded and augmented with driver specific code where necessary.

For the DMA buffer support infrastructure that is introduced in this series
sample data is grouped by so called blocks. A block is the basic unit at
which data is exchanged between the application and the hardware. The
application is responsible for allocating the memory associated with the
block and then passes the block to the hardware. When the hardware has
captured the amount of samples equal to size of a block it will notify the
application, which can then read the data from the block and process it.
The block size can freely chosen (within the constraints of the hardware).
This allows to make a trade-off between latency and management overhead.
The larger the block size the lower the per sample overhead but the latency
between when the data was captured and when the application will be able to
access it increases, in a similar way smaller block sizes have a larger per
sample management overhead but a lower latency. The ideal block size thus
depends on system and application requirements.

For the time being the infrastructure only implements a simple double
buffered scheme which allocates two blocks each with half the size of the
configured buffer size. This provides basic support for capturing
continuous uninterrupted data over the existing file-IO ABI. Future
extensions to the DMA buffer infrastructure will give applications a more
fine grained control over how many blocks are allocated and the size of
each block. But this requires userspace ABI additions which are
intentionally not part of this patch and will be added separately.

Tasks of the second category need to be implemented by a device specific
driver. They can be hooked up into the generic infrastructure using two
simple callbacks, submit() and abort().

The submit() callback is used to schedule DMA transfers for blocks. Once a
DMA transfer has been completed it is expected that the buffer driver calls
iio_dma_buffer_block_done() to notify. The abort() callback is used for
stopping all pending and active DMA transfers when the buffer is disabled.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>

drivers/iio/buffer/Kconfig

@@ -9,6 +9,15 @@ config IIO_BUFFER_CB
 	  Should be selected by any drivers that do in-kernel push
 	  usage.  That is, those where the data is pushed to the consumer.
 
+config IIO_BUFFER_DMA
+	tristate
+	help
+	  Provides the generic IIO DMA buffer infrastructure that can be used by
+	  drivers for devices with DMA support to implement the IIO buffer.
+
+	  Should be selected by drivers that want to use the generic DMA buffer
+	  infrastructure.
+
 config IIO_KFIFO_BUF
 	tristate "Industrial I/O buffering based on kfifo"
 	help

drivers/iio/buffer/Makefile

@@ -4,5 +4,6 @@
 
 # When adding new entries keep the list in alphabetical order
 obj-$(CONFIG_IIO_BUFFER_CB) += industrialio-buffer-cb.o
+obj-$(CONFIG_IIO_BUFFER_DMA) += industrialio-buffer-dma.o
 obj-$(CONFIG_IIO_TRIGGERED_BUFFER) += industrialio-triggered-buffer.o
 obj-$(CONFIG_IIO_KFIFO_BUF) += kfifo_buf.o

include/linux/iio/buffer-dma.h

+/*
+ * Copyright 2013-2015 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#ifndef __INDUSTRIALIO_DMA_BUFFER_H__
+#define __INDUSTRIALIO_DMA_BUFFER_H__
+
+#include <linux/list.h>
+#include <linux/kref.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/iio/buffer.h>
+
+struct iio_dma_buffer_queue;
+struct iio_dma_buffer_ops;
+struct device;
+
+struct iio_buffer_block {
+	u32 size;
+	u32 bytes_used;
+};
+
+/**
+ * enum iio_block_state - State of a struct iio_dma_buffer_block
+ * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued
+ * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue
+ * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA
+ * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue
+ * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed
+ */
+enum iio_block_state {
+	IIO_BLOCK_STATE_DEQUEUED,
+	IIO_BLOCK_STATE_QUEUED,
+	IIO_BLOCK_STATE_ACTIVE,
+	IIO_BLOCK_STATE_DONE,
+	IIO_BLOCK_STATE_DEAD,
+};
+
+/**
+ * struct iio_dma_buffer_block - IIO buffer block
+ * @head: List head
+ * @size: Total size of the block in bytes
+ * @bytes_used: Number of bytes that contain valid data
+ * @vaddr: Virutal address of the blocks memory
+ * @phys_addr: Physical address of the blocks memory
+ * @queue: Parent DMA buffer queue
+ * @kref: kref used to manage the lifetime of block
+ * @state: Current state of the block
+ */
+struct iio_dma_buffer_block {
+	/* May only be accessed by the owner of the block */
+	struct list_head head;
+	size_t bytes_used;
+
+	/*
+	 * Set during allocation, constant thereafter. May be accessed read-only
+	 * by anybody holding a reference to the block.
+	 */
+	void *vaddr;
+	dma_addr_t phys_addr;
+	size_t size;
+	struct iio_dma_buffer_queue *queue;
+
+	/* Must not be accessed outside the core. */
+	struct kref kref;
+	/*
+	 * Must not be accessed outside the core. Access needs to hold
+	 * queue->list_lock if the block is not owned by the core.
+	 */
+	enum iio_block_state state;
+};
+
+/**
+ * struct iio_dma_buffer_queue_fileio - FileIO state for the DMA buffer
+ * @blocks: Buffer blocks used for fileio
+ * @active_block: Block being used in read()
+ * @pos: Read offset in the active block
+ * @block_size: Size of each block
+ */
+struct iio_dma_buffer_queue_fileio {
+	struct iio_dma_buffer_block *blocks[2];
+	struct iio_dma_buffer_block *active_block;
+	size_t pos;
+	size_t block_size;
+};
+
+/**
+ * struct iio_dma_buffer_queue - DMA buffer base structure
+ * @buffer: IIO buffer base structure
+ * @dev: Parent device
+ * @ops: DMA buffer callbacks
+ * @lock: Protects the incoming list, active and the fields in the fileio
+ *   substruct
+ * @list_lock: Protects lists that contain blocks which can be modified in
+ *   atomic context as well as blocks on those lists. This is the outgoing queue
+ *   list and typically also a list of active blocks in the part that handles
+ *   the DMA controller
+ * @incoming: List of buffers on the incoming queue
+ * @outgoing: List of buffers on the outgoing queue
+ * @active: Whether the buffer is currently active
+ * @fileio: FileIO state
+ */
+struct iio_dma_buffer_queue {
+	struct iio_buffer buffer;
+	struct device *dev;
+	const struct iio_dma_buffer_ops *ops;
+
+	struct mutex lock;
+	spinlock_t list_lock;
+	struct list_head incoming;
+	struct list_head outgoing;
+
+	bool active;
+
+	struct iio_dma_buffer_queue_fileio fileio;
+};
+
+/**
+ * struct iio_dma_buffer_ops - DMA buffer callback operations
+ * @submit: Called when a block is submitted to the DMA controller
+ * @abort: Should abort all pending transfers
+ */
+struct iio_dma_buffer_ops {
+	int (*submit)(struct iio_dma_buffer_queue *queue,
+		struct iio_dma_buffer_block *block);
+	void (*abort)(struct iio_dma_buffer_queue *queue);
+};
+
+void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block);
+void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue,
+	struct list_head *list);
+
+int iio_dma_buffer_enable(struct iio_buffer *buffer,
+	struct iio_dev *indio_dev);
+int iio_dma_buffer_disable(struct iio_buffer *buffer,
+	struct iio_dev *indio_dev);
+int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n,
+	char __user *user_buffer);
+size_t iio_dma_buffer_data_available(struct iio_buffer *buffer);
+int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd);
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length);
+int iio_dma_buffer_request_update(struct iio_buffer *buffer);
+
+int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
+	struct device *dma_dev, const struct iio_dma_buffer_ops *ops);
+void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue);
+void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue);
+
+#endif