dmaengine: Driver for the Synopsys DesignWare DMA controller

This adds a driver for the Synopsys DesignWare DMA controller (aka
DMACA on AVR32 systems.) This DMA controller can be found integrated
on the AT32AP7000 chip and is primarily meant for peripheral DMA
transfer, but can also be used for memory-to-memory transfers.

This patch is based on a driver from David Brownell which was based on
an older version of the DMA Engine framework. It also implements the
proposed extensions to the DMA Engine API for slave DMA operations.

The dmatest client shows no problems, but there may still be room for
improvement performance-wise. DMA slave transfer performance is
definitely "good enough"; reading 100 MiB from an SD card running at ~20
MHz yields ~7.2 MiB/s average transfer rate.

Full documentation for this controller can be found in the Synopsys
DW AHB DMAC Databook:

http://www.synopsys.com/designware/docs/iip/DW_ahb_dmac/latest/doc/dw_ahb_dmac_db.pdf

The controller has lots of implementation options, so it's usually a
good idea to check the data sheet of the chip it's intergrated on as
well. The AT32AP7000 data sheet can be found here:

http://www.atmel.com/dyn/products/datasheets.asp?family_id=682


Changes since v4:
  * Use client_count instead of dma_chan_is_in_use()
  * Add missing include
  * Unmap buffers unless client told us not to

Changes since v3:
  * Update to latest DMA engine and DMA slave APIs
  * Embed the hw descriptor into the sw descriptor
  * Clean up and update MODULE_DESCRIPTION, copyright date, etc.

Changes since v2:
  * Dequeue all pending transfers in terminate_all()
  * Rename dw_dmac.h -> dw_dmac_regs.h
  * Define and use controller-specific dma_slave data
  * Fix up a few outdated comments
  * Define hardware registers as structs (doesn't generate better
    code, unfortunately, but it looks nicer.)
  * Get number of channels from platform_data instead of hardcoding it
    based on CONFIG_WHATEVER_CPU.
  * Give slave clients exclusive access to the channel

Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>,
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 225 insertions, 0 deletions

diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
new file mode 100644
index 000000000000..00fdd187bb0c
--- /dev/null
+++ b/drivers/dma/dw_dmac_regs.h
@@ -0,0 +1,225 @@
+/*
+ * Driver for the Synopsys DesignWare AHB DMA Controller
+ *
+ * Copyright (C) 2005-2007 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/dw_dmac.h>
+
+#define DW_DMA_MAX_NR_CHANNELS	8
+
+/*
+ * Redefine this macro to handle differences between 32- and 64-bit
+ * addressing, big vs. little endian, etc.
+ */
+#define DW_REG(name)		u32 name; u32 __pad_##name
+
+/* Hardware register definitions. */
+struct dw_dma_chan_regs {
+	DW_REG(SAR);		/* Source Address Register */
+	DW_REG(DAR);		/* Destination Address Register */
+	DW_REG(LLP);		/* Linked List Pointer */
+	u32	CTL_LO;		/* Control Register Low */
+	u32	CTL_HI;		/* Control Register High */
+	DW_REG(SSTAT);
+	DW_REG(DSTAT);
+	DW_REG(SSTATAR);
+	DW_REG(DSTATAR);
+	u32	CFG_LO;		/* Configuration Register Low */
+	u32	CFG_HI;		/* Configuration Register High */
+	DW_REG(SGR);
+	DW_REG(DSR);
+};
+
+struct dw_dma_irq_regs {
+	DW_REG(XFER);
+	DW_REG(BLOCK);
+	DW_REG(SRC_TRAN);
+	DW_REG(DST_TRAN);
+	DW_REG(ERROR);
+};
+
+struct dw_dma_regs {
+	/* per-channel registers */
+	struct dw_dma_chan_regs	CHAN[DW_DMA_MAX_NR_CHANNELS];
+
+	/* irq handling */
+	struct dw_dma_irq_regs	RAW;		/* r */
+	struct dw_dma_irq_regs	STATUS;		/* r (raw & mask) */
+	struct dw_dma_irq_regs	MASK;		/* rw (set = irq enabled) */
+	struct dw_dma_irq_regs	CLEAR;		/* w (ack, affects "raw") */
+
+	DW_REG(STATUS_INT);			/* r */
+
+	/* software handshaking */
+	DW_REG(REQ_SRC);
+	DW_REG(REQ_DST);
+	DW_REG(SGL_REQ_SRC);
+	DW_REG(SGL_REQ_DST);
+	DW_REG(LAST_SRC);
+	DW_REG(LAST_DST);
+
+	/* miscellaneous */
+	DW_REG(CFG);
+	DW_REG(CH_EN);
+	DW_REG(ID);
+	DW_REG(TEST);
+
+	/* optional encoded params, 0x3c8..0x3 */
+};
+
+/* Bitfields in CTL_LO */
+#define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
+#define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
+#define DWC_CTLL_SRC_WIDTH(n)	((n)<<4)
+#define DWC_CTLL_DST_INC	(0<<7)		/* DAR update/not */
+#define DWC_CTLL_DST_DEC	(1<<7)
+#define DWC_CTLL_DST_FIX	(2<<7)
+#define DWC_CTLL_SRC_INC	(0<<7)		/* SAR update/not */
+#define DWC_CTLL_SRC_DEC	(1<<9)
+#define DWC_CTLL_SRC_FIX	(2<<9)
+#define DWC_CTLL_DST_MSIZE(n)	((n)<<11)	/* burst, #elements */
+#define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
+#define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
+#define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
+#define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
+#define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
+#define DWC_CTLL_FC_P2P		(3 << 20)	/* periph-to-periph */
+/* plus 4 transfer types for peripheral-as-flow-controller */
+#define DWC_CTLL_DMS(n)		((n)<<23)	/* dst master select */
+#define DWC_CTLL_SMS(n)		((n)<<25)	/* src master select */
+#define DWC_CTLL_LLP_D_EN	(1 << 27)	/* dest block chain */
+#define DWC_CTLL_LLP_S_EN	(1 << 28)	/* src block chain */
+
+/* Bitfields in CTL_HI */
+#define DWC_CTLH_DONE		0x00001000
+#define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
+
+/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
+#define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
+#define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
+#define DWC_CFGL_HS_SRC		(1 << 11)	/* handshake w/src */
+#define DWC_CFGL_MAX_BURST(x)	((x) << 20)
+#define DWC_CFGL_RELOAD_SAR	(1 << 30)
+#define DWC_CFGL_RELOAD_DAR	(1 << 31)
+
+/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGH_DS_UPD_EN	(1 << 5)
+#define DWC_CFGH_SS_UPD_EN	(1 << 6)
+
+/* Bitfields in SGR */
+#define DWC_SGR_SGI(x)		((x) << 0)
+#define DWC_SGR_SGC(x)		((x) << 20)
+
+/* Bitfields in DSR */
+#define DWC_DSR_DSI(x)		((x) << 0)
+#define DWC_DSR_DSC(x)		((x) << 20)
+
+/* Bitfields in CFG */
+#define DW_CFG_DMA_EN		(1 << 0)
+
+#define DW_REGLEN		0x400
+
+struct dw_dma_chan {
+	struct dma_chan		chan;
+	void __iomem		*ch_regs;
+	u8			mask;
+
+	spinlock_t		lock;
+
+	/* these other elements are all protected by lock */
+	dma_cookie_t		completed;
+	struct list_head	active_list;
+	struct list_head	queue;
+	struct list_head	free_list;
+
+	struct dw_dma_slave	*dws;
+
+	unsigned int		descs_allocated;
+};
+
+static inline struct dw_dma_chan_regs __iomem *
+__dwc_regs(struct dw_dma_chan *dwc)
+{
+	return dwc->ch_regs;
+}
+
+#define channel_readl(dwc, name) \
+	__raw_readl(&(__dwc_regs(dwc)->name))
+#define channel_writel(dwc, name, val) \
+	__raw_writel((val), &(__dwc_regs(dwc)->name))
+
+static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct dw_dma_chan, chan);
+}
+
+
+struct dw_dma {
+	struct dma_device	dma;
+	void __iomem		*regs;
+	struct tasklet_struct	tasklet;
+	struct clk		*clk;
+
+	u8			all_chan_mask;
+
+	struct dw_dma_chan	chan[0];
+};
+
+static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
+{
+	return dw->regs;
+}
+
+#define dma_readl(dw, name) \
+	__raw_readl(&(__dw_regs(dw)->name))
+#define dma_writel(dw, name, val) \
+	__raw_writel((val), &(__dw_regs(dw)->name))
+
+#define channel_set_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | (mask))
+#define channel_clear_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | 0)
+
+static inline struct dw_dma *to_dw_dma(struct dma_device *ddev)
+{
+	return container_of(ddev, struct dw_dma, dma);
+}
+
+/* LLI == Linked List Item; a.k.a. DMA block descriptor */
+struct dw_lli {
+	/* values that are not changed by hardware */
+	dma_addr_t	sar;
+	dma_addr_t	dar;
+	dma_addr_t	llp;		/* chain to next lli */
+	u32		ctllo;
+	/* values that may get written back: */
+	u32		ctlhi;
+	/* sstat and dstat can snapshot peripheral register state.
+	 * silicon config may discard either or both...
+	 */
+	u32		sstat;
+	u32		dstat;
+};
+
+struct dw_desc {
+	/* FIRST values the hardware uses */
+	struct dw_lli			lli;
+
+	/* THEN values for driver housekeeping */
+	struct list_head		desc_node;
+	struct dma_async_tx_descriptor	txd;
+	size_t				len;
+};
+
+static inline struct dw_desc *
+txd_to_dw_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct dw_desc, txd);
+}