Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dmaengine updates from Vinod Koul:
 "This is fairly big pull by my standards as I had missed last merge
  window.  So we have the support for device tree for slave-dmaengine,
  large updates to dw_dmac driver from Andy for reusing on different
  architectures.  Along with this we have fixes on bunch of the drivers"

Fix up trivial conflicts, usually due to #include line movement next to
each other.

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (111 commits)
  Revert "ARM: SPEAr13xx: Pass DW DMAC platform data from DT"
  ARM: dts: pl330: Add #dma-cells for generic dma binding support
  DMA: PL330: Register the DMA controller with the generic DMA helpers
  DMA: PL330: Add xlate function
  DMA: PL330: Add new pl330 filter for DT case.
  dma: tegra20-apb-dma: remove unnecessary assignment
  edma: do not waste memory for dma_mask
  dma: coh901318: set residue only if dma is in progress
  dma: coh901318: avoid unbalanced locking
  dmaengine.h: remove redundant else keyword
  dma: of-dma: protect list write operation by spin_lock
  dmaengine: ste_dma40: do not remove descriptors for cyclic transfers
  dma: of-dma.c: fix memory leakage
  dw_dmac: apply default dma_mask if needed
  dmaengine: ioat - fix spare sparse complain
  dmaengine: move drivers/of/dma.c -> drivers/dma/of-dma.c
  ioatdma: fix race between updating ioat->head and IOAT_COMPLETION_PENDING
  dw_dmac: add support for Lynxpoint DMA controllers
  dw_dmac: return proper residue value
  dw_dmac: fill individual length of descriptor
  ...

5 files changed, 285 insertions, 41 deletions

diff --git a/include/linux/amba/pl080.h b/include/linux/amba/pl080.h
new file mode 100644
index 000000000000..3e7b62fbefbd
--- /dev/null
+++ b/include/linux/amba/pl080.h
@@ -0,0 +1,146 @@
+/* include/linux/amba/pl080.h
+ *
+ * Copyright 2008 Openmoko, Inc.
+ * Copyright 2008 Simtec Electronics
+ *      http://armlinux.simtec.co.uk/
+ *      Ben Dooks <ben@simtec.co.uk>
+ *
+ * ARM PrimeCell PL080 DMA controller
+ *
+ * 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.
+*/
+
+/* Note, there are some Samsung updates to this controller block which
+ * make it not entierly compatible with the PL080 specification from
+ * ARM. When in doubt, check the Samsung documentation first.
+ *
+ * The Samsung defines are PL080S, and add an extra control register,
+ * the ability to move more than 2^11 counts of data and some extra
+ * OneNAND features.
+*/
+
+#ifndef ASM_PL080_H
+#define ASM_PL080_H
+
+#define PL080_INT_STATUS			(0x00)
+#define PL080_TC_STATUS				(0x04)
+#define PL080_TC_CLEAR				(0x08)
+#define PL080_ERR_STATUS			(0x0C)
+#define PL080_ERR_CLEAR				(0x10)
+#define PL080_RAW_TC_STATUS			(0x14)
+#define PL080_RAW_ERR_STATUS			(0x18)
+#define PL080_EN_CHAN				(0x1c)
+#define PL080_SOFT_BREQ				(0x20)
+#define PL080_SOFT_SREQ				(0x24)
+#define PL080_SOFT_LBREQ			(0x28)
+#define PL080_SOFT_LSREQ			(0x2C)
+
+#define PL080_CONFIG				(0x30)
+#define PL080_CONFIG_M2_BE			(1 << 2)
+#define PL080_CONFIG_M1_BE			(1 << 1)
+#define PL080_CONFIG_ENABLE			(1 << 0)
+
+#define PL080_SYNC				(0x34)
+
+/* Per channel configuration registers */
+
+#define PL080_Cx_STRIDE				(0x20)
+#define PL080_Cx_BASE(x)			((0x100 + (x * 0x20)))
+#define PL080_Cx_SRC_ADDR(x)			((0x100 + (x * 0x20)))
+#define PL080_Cx_DST_ADDR(x)			((0x104 + (x * 0x20)))
+#define PL080_Cx_LLI(x)				((0x108 + (x * 0x20)))
+#define PL080_Cx_CONTROL(x)			((0x10C + (x * 0x20)))
+#define PL080_Cx_CONFIG(x)			((0x110 + (x * 0x20)))
+#define PL080S_Cx_CONTROL2(x)			((0x110 + (x * 0x20)))
+#define PL080S_Cx_CONFIG(x)			((0x114 + (x * 0x20)))
+
+#define PL080_CH_SRC_ADDR			(0x00)
+#define PL080_CH_DST_ADDR			(0x04)
+#define PL080_CH_LLI				(0x08)
+#define PL080_CH_CONTROL			(0x0C)
+#define PL080_CH_CONFIG				(0x10)
+#define PL080S_CH_CONTROL2			(0x10)
+#define PL080S_CH_CONFIG			(0x14)
+
+#define PL080_LLI_ADDR_MASK			(0x3fffffff << 2)
+#define PL080_LLI_ADDR_SHIFT			(2)
+#define PL080_LLI_LM_AHB2			(1 << 0)
+
+#define PL080_CONTROL_TC_IRQ_EN			(1 << 31)
+#define PL080_CONTROL_PROT_MASK			(0x7 << 28)
+#define PL080_CONTROL_PROT_SHIFT		(28)
+#define PL080_CONTROL_PROT_CACHE		(1 << 30)
+#define PL080_CONTROL_PROT_BUFF			(1 << 29)
+#define PL080_CONTROL_PROT_SYS			(1 << 28)
+#define PL080_CONTROL_DST_INCR			(1 << 27)
+#define PL080_CONTROL_SRC_INCR			(1 << 26)
+#define PL080_CONTROL_DST_AHB2			(1 << 25)
+#define PL080_CONTROL_SRC_AHB2			(1 << 24)
+#define PL080_CONTROL_DWIDTH_MASK		(0x7 << 21)
+#define PL080_CONTROL_DWIDTH_SHIFT		(21)
+#define PL080_CONTROL_SWIDTH_MASK		(0x7 << 18)
+#define PL080_CONTROL_SWIDTH_SHIFT		(18)
+#define PL080_CONTROL_DB_SIZE_MASK		(0x7 << 15)
+#define PL080_CONTROL_DB_SIZE_SHIFT		(15)
+#define PL080_CONTROL_SB_SIZE_MASK		(0x7 << 12)
+#define PL080_CONTROL_SB_SIZE_SHIFT		(12)
+#define PL080_CONTROL_TRANSFER_SIZE_MASK	(0xfff << 0)
+#define PL080_CONTROL_TRANSFER_SIZE_SHIFT	(0)
+
+#define PL080_BSIZE_1				(0x0)
+#define PL080_BSIZE_4				(0x1)
+#define PL080_BSIZE_8				(0x2)
+#define PL080_BSIZE_16				(0x3)
+#define PL080_BSIZE_32				(0x4)
+#define PL080_BSIZE_64				(0x5)
+#define PL080_BSIZE_128				(0x6)
+#define PL080_BSIZE_256				(0x7)
+
+#define PL080_WIDTH_8BIT			(0x0)
+#define PL080_WIDTH_16BIT			(0x1)
+#define PL080_WIDTH_32BIT			(0x2)
+
+#define PL080N_CONFIG_ITPROT			(1 << 20)
+#define PL080N_CONFIG_SECPROT			(1 << 19)
+#define PL080_CONFIG_HALT			(1 << 18)
+#define PL080_CONFIG_ACTIVE			(1 << 17)  /* RO */
+#define PL080_CONFIG_LOCK			(1 << 16)
+#define PL080_CONFIG_TC_IRQ_MASK		(1 << 15)
+#define PL080_CONFIG_ERR_IRQ_MASK		(1 << 14)
+#define PL080_CONFIG_FLOW_CONTROL_MASK		(0x7 << 11)
+#define PL080_CONFIG_FLOW_CONTROL_SHIFT		(11)
+#define PL080_CONFIG_DST_SEL_MASK		(0xf << 6)
+#define PL080_CONFIG_DST_SEL_SHIFT		(6)
+#define PL080_CONFIG_SRC_SEL_MASK		(0xf << 1)
+#define PL080_CONFIG_SRC_SEL_SHIFT		(1)
+#define PL080_CONFIG_ENABLE			(1 << 0)
+
+#define PL080_FLOW_MEM2MEM			(0x0)
+#define PL080_FLOW_MEM2PER			(0x1)
+#define PL080_FLOW_PER2MEM			(0x2)
+#define PL080_FLOW_SRC2DST			(0x3)
+#define PL080_FLOW_SRC2DST_DST			(0x4)
+#define PL080_FLOW_MEM2PER_PER			(0x5)
+#define PL080_FLOW_PER2MEM_PER			(0x6)
+#define PL080_FLOW_SRC2DST_SRC			(0x7)
+
+/* DMA linked list chain structure */
+
+struct pl080_lli {
+	u32	src_addr;
+	u32	dst_addr;
+	u32	next_lli;
+	u32	control0;
+};
+
+struct pl080s_lli {
+	u32	src_addr;
+	u32	dst_addr;
+	u32	next_lli;
+	u32	control0;
+	u32	control1;
+};
+
+#endif /* ASM_PL080_H */
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index d3201e438d16..f5939999cb65 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -608,7 +608,10 @@ static inline int dmaengine_device_control(struct dma_chan *chan,
 					   enum dma_ctrl_cmd cmd,
 					   unsigned long arg)
 {
-	return chan->device->device_control(chan, cmd, arg);
+	if (chan->device->device_control)
+		return chan->device->device_control(chan, cmd, arg);
+
+	return -ENOSYS;
 }
 
 static inline int dmaengine_slave_config(struct dma_chan *chan,
@@ -618,6 +621,11 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 			(unsigned long)config);
 }
 
+static inline bool is_slave_direction(enum dma_transfer_direction direction)
+{
+	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM);
+}
+
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
 	struct dma_chan *chan, dma_addr_t buf, size_t len,
 	enum dma_transfer_direction dir, unsigned long flags)
@@ -660,6 +668,13 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_cyclic(
 						period_len, dir, flags, NULL);
 }
 
+static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
+		struct dma_chan *chan, struct dma_interleaved_template *xt,
+		unsigned long flags)
+{
+	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
+}
+
 static inline int dmaengine_terminate_all(struct dma_chan *chan)
 {
 	return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0);
@@ -849,20 +864,6 @@ static inline bool async_tx_test_ack(struct dma_async_tx_descriptor *tx)
 	return (tx->flags & DMA_CTRL_ACK) == DMA_CTRL_ACK;
 }
 
-#define first_dma_cap(mask) __first_dma_cap(&(mask))
-static inline int __first_dma_cap(const dma_cap_mask_t *srcp)
-{
-	return min_t(int, DMA_TX_TYPE_END,
-		find_first_bit(srcp->bits, DMA_TX_TYPE_END));
-}
-
-#define next_dma_cap(n, mask) __next_dma_cap((n), &(mask))
-static inline int __next_dma_cap(int n, const dma_cap_mask_t *srcp)
-{
-	return min_t(int, DMA_TX_TYPE_END,
-		find_next_bit(srcp->bits, DMA_TX_TYPE_END, n+1));
-}
-
 #define dma_cap_set(tx, mask) __dma_cap_set((tx), &(mask))
 static inline void
 __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
@@ -891,9 +892,7 @@ __dma_has_cap(enum dma_transaction_type tx_type, dma_cap_mask_t *srcp)
 }
 
 #define for_each_dma_cap_mask(cap, mask) \
-	for ((cap) = first_dma_cap(mask);	\
-		(cap) < DMA_TX_TYPE_END;	\
-		(cap) = next_dma_cap((cap), (mask)))
+	for_each_set_bit(cap, mask.bits, DMA_TX_TYPE_END)
 
 /**
  * dma_async_issue_pending - flush pending transactions to HW
@@ -907,8 +906,6 @@ static inline void dma_async_issue_pending(struct dma_chan *chan)
 	chan->device->device_issue_pending(chan);
 }
 
-#define dma_async_memcpy_issue_pending(chan) dma_async_issue_pending(chan)
-
 /**
  * dma_async_is_tx_complete - poll for transaction completion
  * @chan: DMA channel
@@ -934,16 +931,13 @@ static inline enum dma_status dma_async_is_tx_complete(struct dma_chan *chan,
 	return status;
 }
 
-#define dma_async_memcpy_complete(chan, cookie, last, used)\
-	dma_async_is_tx_complete(chan, cookie, last, used)
-
 /**
  * dma_async_is_complete - test a cookie against chan state
  * @cookie: transaction identifier to test status of
  * @last_complete: last know completed transaction
  * @last_used: last cookie value handed out
  *
- * dma_async_is_complete() is used in dma_async_memcpy_complete()
+ * dma_async_is_complete() is used in dma_async_is_tx_complete()
  * the test logic is separated for lightweight testing of multiple cookies
  */
 static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie,
@@ -974,6 +968,7 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie);
 enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
 void dma_issue_pending_all(void);
 struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param);
+struct dma_chan *dma_request_slave_channel(struct device *dev, char *name);
 void dma_release_channel(struct dma_chan *chan);
 #else
 static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
@@ -988,6 +983,11 @@ static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask,
 {
 	return NULL;
 }
+static inline struct dma_chan *dma_request_slave_channel(struct device *dev,
+							 char *name)
+{
+	return NULL;
+}
 static inline void dma_release_channel(struct dma_chan *chan)
 {
 }
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index e1c8c9e919ac..41766de66e33 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -15,14 +15,38 @@
 #include <linux/dmaengine.h>
 
 /**
+ * struct dw_dma_slave - Controller-specific information about a slave
+ *
+ * @dma_dev: required DMA master device. Depricated.
+ * @bus_id: name of this device channel, not just a device name since
+ *          devices may have more than one channel e.g. "foo_tx"
+ * @cfg_hi: Platform-specific initializer for the CFG_HI register
+ * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ * @src_master: src master for transfers on allocated channel.
+ * @dst_master: dest master for transfers on allocated channel.
+ */
+struct dw_dma_slave {
+	struct device		*dma_dev;
+	const char		*bus_id;
+	u32			cfg_hi;
+	u32			cfg_lo;
+	u8			src_master;
+	u8			dst_master;
+};
+
+/**
  * struct dw_dma_platform_data - Controller configuration parameters
  * @nr_channels: Number of channels supported by hardware (max 8)
  * @is_private: The device channels should be marked as private and not for
  *	by the general purpose DMA channel allocator.
+ * @chan_allocation_order: Allocate channels starting from 0 or 7
+ * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
  * @block_size: Maximum block size supported by the controller
  * @nr_masters: Number of AHB masters supported by the controller
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
+ * @sd: slave specific data. Used for configuring channels
+ * @sd_count: count of slave data structures passed.
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
@@ -36,6 +60,9 @@ struct dw_dma_platform_data {
 	unsigned short	block_size;
 	unsigned char	nr_masters;
 	unsigned char	data_width[4];
+
+	struct dw_dma_slave *sd;
+	unsigned int sd_count;
 };
 
 /* bursts size */
@@ -50,23 +77,6 @@ enum dw_dma_msize {
 	DW_DMA_MSIZE_256,
 };
 
-/**
- * struct dw_dma_slave - Controller-specific information about a slave
- *
- * @dma_dev: required DMA master device
- * @cfg_hi: Platform-specific initializer for the CFG_HI register
- * @cfg_lo: Platform-specific initializer for the CFG_LO register
- * @src_master: src master for transfers on allocated channel.
- * @dst_master: dest master for transfers on allocated channel.
- */
-struct dw_dma_slave {
-	struct device		*dma_dev;
-	u32			cfg_hi;
-	u32			cfg_lo;
-	u8			src_master;
-	u8			dst_master;
-};
-
 /* Platform-configurable bits in CFG_HI */
 #define DWC_CFGH_FCMODE		(1 << 0)
 #define DWC_CFGH_FIFO_MODE	(1 << 1)
@@ -104,5 +114,6 @@ void dw_dma_cyclic_stop(struct dma_chan *chan);
 dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
 
 dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+bool dw_dma_generic_filter(struct dma_chan *chan, void *param);
 
 #endif /* DW_DMAC_H */
diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h
new file mode 100644
index 000000000000..d15073e080dd
--- /dev/null
+++ b/include/linux/of_dma.h
@@ -0,0 +1,74 @@
+/*
+ * OF helpers for DMA request / controller
+ *
+ * Based on of_gpio.h
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * 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.
+ */
+
+#ifndef __LINUX_OF_DMA_H
+#define __LINUX_OF_DMA_H
+
+#include <linux/of.h>
+#include <linux/dmaengine.h>
+
+struct device_node;
+
+struct of_dma {
+	struct list_head	of_dma_controllers;
+	struct device_node	*of_node;
+	int			of_dma_nbcells;
+	struct dma_chan		*(*of_dma_xlate)
+				(struct of_phandle_args *, struct of_dma *);
+	void			*of_dma_data;
+	int			use_count;
+};
+
+struct of_dma_filter_info {
+	dma_cap_mask_t	dma_cap;
+	dma_filter_fn	filter_fn;
+};
+
+#ifdef CONFIG_OF
+extern int of_dma_controller_register(struct device_node *np,
+		struct dma_chan *(*of_dma_xlate)
+		(struct of_phandle_args *, struct of_dma *),
+		void *data);
+extern int of_dma_controller_free(struct device_node *np);
+extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
+						     char *name);
+extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *ofdma);
+#else
+static inline int of_dma_controller_register(struct device_node *np,
+		struct dma_chan *(*of_dma_xlate)
+		(struct of_phandle_args *, struct of_dma *),
+		void *data)
+{
+	return -ENODEV;
+}
+
+static inline int of_dma_controller_free(struct device_node *np)
+{
+	return -ENODEV;
+}
+
+static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
+						     char *name)
+{
+	return NULL;
+}
+
+static inline struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *ofdma)
+{
+	return NULL;
+}
+
+#endif
+
+#endif /* __LINUX_OF_DMA_H */
diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h
index 9ff93b065686..4b781014b0a0 100644
--- a/include/linux/platform_data/dma-ste-dma40.h
+++ b/include/linux/platform_data/dma-ste-dma40.h
@@ -147,6 +147,16 @@ struct stedma40_chan_cfg {
  * @memcpy_conf_log: default configuration of logical channel memcpy
  * @disabled_channels: A vector, ending with -1, that marks physical channels
  * that are for different reasons not available for the driver.
+ * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
+ * which avoids HW bug that exists in some versions of the controller.
+ * SoftLLI introduces relink overhead that could impact performace for
+ * certain use cases.
+ * @num_of_soft_lli_chans: The number of channels that needs to be configured
+ * to use SoftLLI.
+ * @use_esram_lcla: flag for mapping the lcla into esram region
+ * @num_of_phy_chans: The number of physical channels implemented in HW.
+ * 0 means reading the number of channels from DMA HW but this is only valid
+ * for 'multiple of 4' channels, like 8.
  */
 struct stedma40_platform_data {
 	u32				 dev_len;
@@ -157,7 +167,10 @@ struct stedma40_platform_data {
 	struct stedma40_chan_cfg	*memcpy_conf_phy;
 	struct stedma40_chan_cfg	*memcpy_conf_log;
 	int				 disabled_channels[STEDMA40_MAX_PHYS];
+	int				*soft_lli_chans;
+	int				 num_of_soft_lli_chans;
 	bool				 use_esram_lcla;
+	int				 num_of_phy_chans;
 };
 
 #ifdef CONFIG_STE_DMA40