Merge tag 'dmaengine-4.9-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This is bit large pile of code which bring in some nice additions:

   - Error reporting: we have added a new mechanism for users of
     dmaenegine to register a callback_result which tells them the
     result of the dma transaction. Right now only one user (ntb) is
     using it.

   - As we discussed on KS mailing list and pointed out NO_IRQ has no
     place in kernel, this also remove NO_IRQ from dmaengine subsystem
     (both arm and ppc users)

   - Support for IOMMU slave transfers and its implementation for arm.

   - To get better build coverage, enable COMPILE_TEST for bunch of
     driver, and fix the warning and sparse complaints on these.

   - Apart from above, usual updates spread across drivers"

* tag 'dmaengine-4.9-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (169 commits)
  async_pq_val: fix DMA memory leak
  dmaengine: virt-dma: move function declarations
  dmaengine: omap-dma: Enable burst and data pack for SG
  DT: dmaengine: rcar-dmac: document R8A7743/5 support
  dmaengine: fsldma: Unmap region obtained by of_iomap
  dmaengine: jz4780: fix resource leaks on error exit return
  dma-debug: fix ia64 build, use PHYS_PFN
  dmaengine: coh901318: fix integer overflow when shifting more than 32 places
  dmaengine: edma: avoid uninitialized variable use
  dma-mapping: fix m32r build warning
  dma-mapping: fix ia64 build, use PHYS_PFN
  dmaengine: ti-dma-crossbar: enable COMPILE_TEST
  dmaengine: omap-dma: enable COMPILE_TEST
  dmaengine: edma: enable COMPILE_TEST
  dmaengine: ti-dma-crossbar: Fix of_device_id data parameter usage
  dmaengine: ti-dma-crossbar: Correct type for of_find_property() third parameter
  dmaengine/ARM: omap-dma: Fix the DMAengine compile test on non OMAP configs
  dmaengine: edma: Rename set_bits and remove unused clear_bits helper
  dmaengine: edma: Use correct type for of_find_property() third parameter
  dmaengine: edma: Fix of_device_id data parameter usage (legacy vs TPCC)
  ...

2 files changed, 107 insertions, 37 deletions

diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 0dd953884d1d..2e441d0ccd79 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -118,14 +118,34 @@ struct rcar_dmac_desc_page {
 	sizeof(struct rcar_dmac_xfer_chunk))
 
 /*
+ * struct rcar_dmac_chan_slave - Slave configuration
+ * @slave_addr: slave memory address
+ * @xfer_size: size (in bytes) of hardware transfers
+ */
+struct rcar_dmac_chan_slave {
+	phys_addr_t slave_addr;
+	unsigned int xfer_size;
+};
+
+/*
+ * struct rcar_dmac_chan_map - Map of slave device phys to dma address
+ * @addr: slave dma address
+ * @dir: direction of mapping
+ * @slave: slave configuration that is mapped
+ */
+struct rcar_dmac_chan_map {
+	dma_addr_t addr;
+	enum dma_data_direction dir;
+	struct rcar_dmac_chan_slave slave;
+};
+
+/*
  * struct rcar_dmac_chan - R-Car Gen2 DMA Controller Channel
  * @chan: base DMA channel object
  * @iomem: channel I/O memory base
  * @index: index of this channel in the controller
- * @src_xfer_size: size (in bytes) of hardware transfers on the source side
- * @dst_xfer_size: size (in bytes) of hardware transfers on the destination side
- * @src_slave_addr: slave source memory address
- * @dst_slave_addr: slave destination memory address
+ * @src: slave memory address and size on the source side
+ * @dst: slave memory address and size on the destination side
  * @mid_rid: hardware MID/RID for the DMA client using this channel
  * @lock: protects the channel CHCR register and the desc members
  * @desc.free: list of free descriptors
@@ -142,10 +162,9 @@ struct rcar_dmac_chan {
 	void __iomem *iomem;
 	unsigned int index;
 
-	unsigned int src_xfer_size;
-	unsigned int dst_xfer_size;
-	dma_addr_t src_slave_addr;
-	dma_addr_t dst_slave_addr;
+	struct rcar_dmac_chan_slave src;
+	struct rcar_dmac_chan_slave dst;
+	struct rcar_dmac_chan_map map;
 	int mid_rid;
 
 	spinlock_t lock;
@@ -793,13 +812,13 @@ static void rcar_dmac_chan_configure_desc(struct rcar_dmac_chan *chan,
 	case DMA_DEV_TO_MEM:
 		chcr = RCAR_DMACHCR_DM_INC | RCAR_DMACHCR_SM_FIXED
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->src_xfer_size;
+		xfer_size = chan->src.xfer_size;
 		break;
 
 	case DMA_MEM_TO_DEV:
 		chcr = RCAR_DMACHCR_DM_FIXED | RCAR_DMACHCR_SM_INC
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->dst_xfer_size;
+		xfer_size = chan->dst.xfer_size;
 		break;
 
 	case DMA_MEM_TO_MEM:
@@ -1023,13 +1042,65 @@ rcar_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 				      DMA_MEM_TO_MEM, flags, false);
 }
 
+static int rcar_dmac_map_slave_addr(struct dma_chan *chan,
+				    enum dma_transfer_direction dir)
+{
+	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
+	struct rcar_dmac_chan_map *map = &rchan->map;
+	phys_addr_t dev_addr;
+	size_t dev_size;
+	enum dma_data_direction dev_dir;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = rchan->src.slave_addr;
+		dev_size = rchan->src.xfer_size;
+		dev_dir = DMA_TO_DEVICE;
+	} else {
+		dev_addr = rchan->dst.slave_addr;
+		dev_size = rchan->dst.xfer_size;
+		dev_dir = DMA_FROM_DEVICE;
+	}
+
+	/* Reuse current map if possible. */
+	if (dev_addr == map->slave.slave_addr &&
+	    dev_size == map->slave.xfer_size &&
+	    dev_dir == map->dir)
+		return 0;
+
+	/* Remove old mapping if present. */
+	if (map->slave.xfer_size)
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+	map->slave.xfer_size = 0;
+
+	/* Create new slave address map. */
+	map->addr = dma_map_resource(chan->device->dev, dev_addr, dev_size,
+				     dev_dir, 0);
+
+	if (dma_mapping_error(chan->device->dev, map->addr)) {
+		dev_err(chan->device->dev,
+			"chan%u: failed to map %zx@%pap", rchan->index,
+			dev_size, &dev_addr);
+		return -EIO;
+	}
+
+	dev_dbg(chan->device->dev, "chan%u: map %zx@%pap to %pad dir: %s\n",
+		rchan->index, dev_size, &dev_addr, &map->addr,
+		dev_dir == DMA_TO_DEVICE ? "DMA_TO_DEVICE" : "DMA_FROM_DEVICE");
+
+	map->slave.slave_addr = dev_addr;
+	map->slave.xfer_size = dev_size;
+	map->dir = dev_dir;
+
+	return 0;
+}
+
 static struct dma_async_tx_descriptor *
 rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction dir,
 			unsigned long flags, void *context)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
-	dma_addr_t dev_addr;
 
 	/* Someone calling slave DMA on a generic channel? */
 	if (rchan->mid_rid < 0 || !sg_len) {
@@ -1039,9 +1110,10 @@ rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		return NULL;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
+	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, false);
 }
 
@@ -1055,7 +1127,6 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct dma_async_tx_descriptor *desc;
 	struct scatterlist *sgl;
-	dma_addr_t dev_addr;
 	unsigned int sg_len;
 	unsigned int i;
 
@@ -1067,6 +1138,9 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		return NULL;
 	}
 
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
 	sg_len = buf_len / period_len;
 	if (sg_len > RCAR_DMAC_MAX_SG_LEN) {
 		dev_err(chan->device->dev,
@@ -1094,9 +1168,7 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		sg_dma_len(&sgl[i]) = period_len;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, true);
 
 	kfree(sgl);
@@ -1112,10 +1184,10 @@ static int rcar_dmac_device_config(struct dma_chan *chan,
 	 * We could lock this, but you shouldn't be configuring the
 	 * channel, while using it...
 	 */
-	rchan->src_slave_addr = cfg->src_addr;
-	rchan->dst_slave_addr = cfg->dst_addr;
-	rchan->src_xfer_size = cfg->src_addr_width;
-	rchan->dst_xfer_size = cfg->dst_addr_width;
+	rchan->src.slave_addr = cfg->src_addr;
+	rchan->dst.slave_addr = cfg->dst_addr;
+	rchan->src.xfer_size = cfg->src_addr_width;
+	rchan->dst.xfer_size = cfg->dst_addr_width;
 
 	return 0;
 }
@@ -1389,21 +1461,18 @@ static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
 {
 	struct rcar_dmac_chan *chan = dev;
 	struct rcar_dmac_desc *desc;
+	struct dmaengine_desc_callback cb;
 
 	spin_lock_irq(&chan->lock);
 
 	/* For cyclic transfers notify the user after every chunk. */
 	if (chan->desc.running && chan->desc.running->cyclic) {
-		dma_async_tx_callback callback;
-		void *callback_param;
-
 		desc = chan->desc.running;
-		callback = desc->async_tx.callback;
-		callback_param = desc->async_tx.callback_param;
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
 
-		if (callback) {
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irq(&chan->lock);
-			callback(callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irq(&chan->lock);
 		}
 	}
@@ -1418,14 +1487,15 @@ static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
 		dma_cookie_complete(&desc->async_tx);
 		list_del(&desc->node);
 
-		if (desc->async_tx.callback) {
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irq(&chan->lock);
 			/*
 			 * We own the only reference to this descriptor, we can
 			 * safely dereference it without holding the channel
 			 * lock.
 			 */
-			desc->async_tx.callback(desc->async_tx.callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irq(&chan->lock);
 		}
 
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 10fcabad80f3..12fa48e380cf 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -330,10 +330,11 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 	bool head_acked = false;
 	dma_cookie_t cookie = 0;
 	dma_async_tx_callback callback = NULL;
-	void *param = NULL;
+	struct dmaengine_desc_callback cb;
 	unsigned long flags;
 	LIST_HEAD(cyclic_list);
 
+	memset(&cb, 0, sizeof(cb));
 	spin_lock_irqsave(&schan->chan_lock, flags);
 	list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) {
 		struct dma_async_tx_descriptor *tx = &desc->async_tx;
@@ -367,8 +368,8 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		/* Call callback on the last chunk */
 		if (desc->mark == DESC_COMPLETED && tx->callback) {
 			desc->mark = DESC_WAITING;
+			dmaengine_desc_get_callback(tx, &cb);
 			callback = tx->callback;
-			param = tx->callback_param;
 			dev_dbg(schan->dev, "descriptor #%d@%p on %d callback\n",
 				tx->cookie, tx, schan->id);
 			BUG_ON(desc->chunks != 1);
@@ -430,8 +431,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 
 	spin_unlock_irqrestore(&schan->chan_lock, flags);
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 
 	return callback;
 }
@@ -885,9 +885,9 @@ bool shdma_reset(struct shdma_dev *sdev)
 		/* Complete all  */
 		list_for_each_entry(sdesc, &dl, node) {
 			struct dma_async_tx_descriptor *tx = &sdesc->async_tx;
+
 			sdesc->mark = DESC_IDLE;
-			if (tx->callback)
-				tx->callback(tx->callback_param);
+			dmaengine_desc_get_callback_invoke(tx, NULL);
 		}
 
 		spin_lock(&schan->chan_lock);