dmaengine: Add Synopsys eDMA IP core driver

Add Synopsys PCIe Endpoint eDMA IP core driver to kernel.

This IP is generally distributed with Synopsys PCIe Endpoint IP (depends
of the use and licensing agreement).

This core driver, initializes and configures the eDMA IP using vma-helpers
functions and dma-engine subsystem.

This driver can be compile as built-in or external module in kernel.

To enable this driver just select DW_EDMA option in kernel configuration,
however it requires and selects automatically DMA_ENGINE and
DMA_VIRTUAL_CHANNELS option too.

In order to transfer data from point A to B as fast as possible this IP
requires a dedicated memory space containing linked list of elements.

All elements of this linked list are continuous and each one describes a
data transfer (source and destination addresses, length and a control
variable).

For the sake of simplicity, lets assume a memory space for channel write
0 which allows about 42 elements.

+---------+
| Desc #0 |-+
+---------+ |
            V
       +----------+
       | Chunk #0 |-+
       |  CB = 1  | |  +----------+  +-----+  +-----------+  +-----+
       +----------+ +->| Burst #0 |->| ... |->| Burst #41 |->| llp |
            |          +----------+  +-----+  +-----------+  +-----+
            V
       +----------+
       | Chunk #1 |-+
       |  CB = 0  | |  +-----------+  +-----+  +-----------+  +-----+
       +----------+ +->| Burst #42 |->| ... |->| Burst #83 |->| llp |
            |          +-----------+  +-----+  +-----------+  +-----+
            V
       +----------+
       | Chunk #2 |-+
       |  CB = 1  | |  +-----------+  +-----+  +------------+  +-----+
       +----------+ +->| Burst #84 |->| ... |->| Burst #125 |->| llp |
            |          +-----------+  +-----+  +------------+  +-----+
            V
       +----------+
       | Chunk #3 |-+
       |  CB = 0  | |  +------------+  +-----+  +------------+  +-----+
       +----------+ +->| Burst #126 |->| ... |->| Burst #129 |->| llp |
                       +------------+  +-----+  +------------+  +-----+

Legend:
 - Linked list, also know as Chunk
 - Linked list element*, also know as Burst *CB*, also know as Change Bit,
it's a control bit (and typically is toggled) that allows to easily
identify and differentiate between the current linked list and the
previous or the next one.
 - LLP, is a special element that indicates the end of the linked list
element stream also informs that the next CB should be toggle

On every last Burst of the Chunk (Burst #41, Burst #83, Burst #125 or
even Burst #129) is set some flags on their control variable (RIE and
LIE bits) that will trigger the send of "done" interruption.

On the interruptions callback, is decided whether to recycle the linked
list memory space by writing a new set of Bursts elements (if still
exists Chunks to transfer) or is considered completed (if there is no
Chunks available to transfer).

On scatter-gather transfer mode, the client will submit a scatter-gather
list of n (on this case 130) elements, that will be divide in multiple
Chunks, each Chunk will have (on this case 42) a limited number of
Bursts and after transferring all Bursts, an interrupt will be
triggered, which will allow to recycle the all linked list dedicated
memory again with the new information relative to the next Chunk and
respective Burst associated and repeat the whole cycle again.

On cyclic transfer mode, the client will submit a buffer pointer, length
of it and number of repetitions, in this case each burst will correspond
directly to each repetition.

Each Burst can describes a data transfer from point A(source) to point
B(destination) with a length that can be from 1 byte up to 4 GB. Since
dedicated the memory space where the linked list will reside is limited,
the whole n burst elements will be organized in several Chunks, that
will be used later to recycle the dedicated memory space to initiate a
new sequence of data transfers.

The whole transfer is considered has completed when it was transferred
all bursts.

Currently this IP has a set well-known register map, which includes
support for legacy and unroll modes. Legacy mode is version of this
register map that has multiplexer register that allows to switch
registers between all write and read channels and the unroll modes
repeats all write and read channels registers with an offset between
them. This register map is called v0.

The IP team is creating a new register map more suitable to the latest
PCIe features, that very likely will change the map register, which this
version will be called v1. As soon as this new version is released by
the IP team the support for this version in be included on this driver.

According to the logic, patches 1, 2 and 3 should be squashed into 1
unique patch, but for the sake of simplicity of review, it was divided
in this 3 patches files.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: Vinod Koul <vkoul@kernel.org>

1 files changed, 165 insertions, 0 deletions

diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
new file mode 100644
index 000000000000..b6cc90cbc9dc
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA core driver
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#ifndef _DW_EDMA_CORE_H
+#define _DW_EDMA_CORE_H
+
+#include <linux/msi.h>
+#include <linux/dma/edma.h>
+
+#include "../virt-dma.h"
+
+#define EDMA_LL_SZ					24
+
+enum dw_edma_dir {
+	EDMA_DIR_WRITE = 0,
+	EDMA_DIR_READ
+};
+
+enum dw_edma_mode {
+	EDMA_MODE_LEGACY = 0,
+	EDMA_MODE_UNROLL
+};
+
+enum dw_edma_request {
+	EDMA_REQ_NONE = 0,
+	EDMA_REQ_STOP,
+	EDMA_REQ_PAUSE
+};
+
+enum dw_edma_status {
+	EDMA_ST_IDLE = 0,
+	EDMA_ST_PAUSE,
+	EDMA_ST_BUSY
+};
+
+struct dw_edma_chan;
+struct dw_edma_chunk;
+
+struct dw_edma_burst {
+	struct list_head		list;
+	u64				sar;
+	u64				dar;
+	u32				sz;
+};
+
+struct dw_edma_region {
+	phys_addr_t			paddr;
+	dma_addr_t			vaddr;
+	size_t				sz;
+};
+
+struct dw_edma_chunk {
+	struct list_head		list;
+	struct dw_edma_chan		*chan;
+	struct dw_edma_burst		*burst;
+
+	u32				bursts_alloc;
+
+	u8				cb;
+	struct dw_edma_region		ll_region;	/* Linked list */
+};
+
+struct dw_edma_desc {
+	struct virt_dma_desc		vd;
+	struct dw_edma_chan		*chan;
+	struct dw_edma_chunk		*chunk;
+
+	u32				chunks_alloc;
+
+	u32				alloc_sz;
+	u32				xfer_sz;
+};
+
+struct dw_edma_chan {
+	struct virt_dma_chan		vc;
+	struct dw_edma_chip		*chip;
+	int				id;
+	enum dw_edma_dir		dir;
+
+	off_t				ll_off;
+	u32				ll_max;
+
+	off_t				dt_off;
+
+	struct msi_msg			msi;
+
+	enum dw_edma_request		request;
+	enum dw_edma_status		status;
+	u8				configured;
+
+	struct dma_slave_config		config;
+};
+
+struct dw_edma_irq {
+	struct msi_msg                  msi;
+	u32				wr_mask;
+	u32				rd_mask;
+	struct dw_edma			*dw;
+};
+
+struct dw_edma {
+	char				name[20];
+
+	struct dma_device		wr_edma;
+	u16				wr_ch_cnt;
+
+	struct dma_device		rd_edma;
+	u16				rd_ch_cnt;
+
+	struct dw_edma_region		rg_region;	/* Registers */
+	struct dw_edma_region		ll_region;	/* Linked list */
+	struct dw_edma_region		dt_region;	/* Data */
+
+	struct dw_edma_irq		*irq;
+	int				nr_irqs;
+
+	u32				version;
+	enum dw_edma_mode		mode;
+
+	struct dw_edma_chan		*chan;
+	const struct dw_edma_core_ops	*ops;
+
+	raw_spinlock_t			lock;		/* Only for legacy */
+};
+
+struct dw_edma_sg {
+	struct scatterlist		*sgl;
+	unsigned int			len;
+};
+
+struct dw_edma_cyclic {
+	dma_addr_t			paddr;
+	size_t				len;
+	size_t				cnt;
+};
+
+struct dw_edma_transfer {
+	struct dma_chan			*dchan;
+	union dw_edma_xfer {
+		struct dw_edma_sg	sg;
+		struct dw_edma_cyclic	cyclic;
+	} xfer;
+	enum dma_transfer_direction	direction;
+	unsigned long			flags;
+	bool				cyclic;
+};
+
+static inline
+struct dw_edma_chan *vc2dw_edma_chan(struct virt_dma_chan *vc)
+{
+	return container_of(vc, struct dw_edma_chan, vc);
+}
+
+static inline
+struct dw_edma_chan *dchan2dw_edma_chan(struct dma_chan *dchan)
+{
+	return vc2dw_edma_chan(to_virt_chan(dchan));
+}
+
+#endif /* _DW_EDMA_CORE_H */