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

Pull slave-dma updates from Vinod Koul:
 "Some notable changes are:
   - new driver for AMBA AXI NBPF by Guennadi
   - new driver for sun6i controller by Maxime
   - pl330 drivers fixes from Lar's
   - sh-dma updates and fixes from Laurent, Geert and Kuninori
   - Documentation updates from Geert
   - drivers fixes and updates spread over dw, edma, freescale, mpc512x
     etc.."

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (72 commits)
  dmaengine: sun6i: depends on RESET_CONTROLLER
  dma: at_hdmac: fix invalid remaining bytes detection
  dmaengine: nbpfaxi: don't build this driver where it cannot be used
  dmaengine: nbpf_error_get_channel() can be static
  dma: pl08x: Use correct specifier for size_t values
  dmaengine: Remove the context argument to the prep_dma_cyclic operation
  dmaengine: nbpfaxi: convert to tasklet
  dmaengine: nbpfaxi: fix a theoretical race
  dmaengine: add a driver for AMBA AXI NBPF DMAC IP cores
  dmaengine: add device tree binding documentation for the nbpfaxi driver
  dmaengine: edma: Do not register second device when booted with DT
  dmaengine: edma: Do not change the error code returned from edma_alloc_slot
  dmaengine: rcar-dmac: Add device tree bindings documentation
  dmaengine: shdma: Allocate cyclic sg list dynamically
  dmaengine: shdma: Make channel filter ignore unrelated devices
  dmaengine: sh: Rework Kconfig and Makefile
  dmaengine: sun6i: Fix memory leaks
  dmaengine: sun6i: Free the interrupt before killing the tasklet
  dmaengine: sun6i: Remove switch statement from buswidth convertion routine
  dmaengine: of: kconfig: select DMA_ENGINE when DMA_OF is selected
  ...

38 files changed, 3526 insertions, 873 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 8f6afbf9ba54..9b1ea0ef59af 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -393,6 +393,22 @@ config XILINX_VDMA
 	  channels, Memory Mapped to Stream (MM2S) and Stream to
 	  Memory Mapped (S2MM) for the data transfers.
 
+config DMA_SUN6I
+	tristate "Allwinner A31 SoCs DMA support"
+	depends on MACH_SUN6I || COMPILE_TEST
+	depends on RESET_CONTROLLER
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the DMA engine for Allwinner A31 SoCs.
+
+config NBPFAXI_DMA
+	tristate "Renesas Type-AXI NBPF DMA support"
+	select DMA_ENGINE
+	depends on ARM || COMPILE_TEST
+	help
+	  Support for "Type-AXI" NBPF DMA IPs from Renesas
+
 config DMA_ENGINE
 	bool
 
@@ -406,6 +422,7 @@ config DMA_ACPI
 config DMA_OF
 	def_bool y
 	depends on OF
+	select DMA_ENGINE
 
 comment "DMA Clients"
 	depends on DMA_ENGINE
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index bd9e7fa928bd..c6adb925f0b9 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -1,5 +1,5 @@
-ccflags-$(CONFIG_DMADEVICES_DEBUG)  := -DDEBUG
-ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG
+subdir-ccflags-$(CONFIG_DMADEVICES_DEBUG)  := -DDEBUG
+subdir-ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG
 
 obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
 obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
@@ -48,3 +48,5 @@ obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
 obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
 obj-y += xilinx/
 obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
+obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
+obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o
diff --git a/drivers/dma/TODO b/drivers/dma/TODO
index 734ed0206cd5..b8045cd42ee1 100644
--- a/drivers/dma/TODO
+++ b/drivers/dma/TODO
@@ -7,7 +7,6 @@ TODO for slave dma
 	- imx-dma
 	- imx-sdma
 	- mxs-dma.c
-	- dw_dmac
 	- intel_mid_dma
 4. Check other subsystems for dma drivers and merge/move to dmaengine
 5. Remove dma_slave_config's dma direction.
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 8114731a1c62..e34024b000a4 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1040,7 +1040,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 
 		if (early_bytes) {
 			dev_vdbg(&pl08x->adev->dev,
-				"%s byte width LLIs (remain 0x%08x)\n",
+				"%s byte width LLIs (remain 0x%08zx)\n",
 				__func__, bd.remainder);
 			prep_byte_width_lli(pl08x, &bd, &cctl, early_bytes,
 				num_llis++, &total_bytes);
@@ -1653,7 +1653,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_transfer_direction direction,
-		unsigned long flags, void *context)
+		unsigned long flags)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
@@ -1662,7 +1662,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic(
 	dma_addr_t slave_addr;
 
 	dev_dbg(&pl08x->adev->dev,
-		"%s prepare cyclic transaction of %d/%d bytes %s %s\n",
+		"%s prepare cyclic transaction of %zd/%zd bytes %s %s\n",
 		__func__, period_len, buf_len,
 		direction == DMA_MEM_TO_DEV ? "to" : "from",
 		plchan->name);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c13a3bb0f594..ca9dd2613283 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -294,14 +294,16 @@ static int atc_get_bytes_left(struct dma_chan *chan)
 			ret = -EINVAL;
 			goto out;
 		}
-		atchan->remain_desc -= (desc_cur->lli.ctrla & ATC_BTSIZE_MAX)
-						<< (desc_first->tx_width);
-		if (atchan->remain_desc < 0) {
+
+		count = (desc_cur->lli.ctrla & ATC_BTSIZE_MAX)
+			<< desc_first->tx_width;
+		if (atchan->remain_desc < count) {
 			ret = -EINVAL;
 			goto out;
-		} else {
-			ret = atchan->remain_desc;
 		}
+
+		atchan->remain_desc -= count;
+		ret = atchan->remain_desc;
 	} else {
 		/*
 		 * Get residual bytes when current
@@ -893,12 +895,11 @@ atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc,
  * @period_len: number of bytes for each period
  * @direction: transfer direction, to or from device
  * @flags: tx descriptor status flags
- * @context: transfer context (ignored)
  */
 static struct dma_async_tx_descriptor *
 atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		size_t period_len, enum dma_transfer_direction direction,
-		unsigned long flags, void *context)
+		unsigned long flags)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma_slave	*atslave = chan->private;
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index a03602164e3e..68007974961a 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -335,7 +335,7 @@ static void bcm2835_dma_issue_pending(struct dma_chan *chan)
 static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic(
 	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	size_t period_len, enum dma_transfer_direction direction,
-	unsigned long flags, void *context)
+	unsigned long flags)
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
 	enum dma_slave_buswidth dev_width;
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index 94c380f07538..6a9d89c93b1f 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -433,7 +433,7 @@ static struct dma_async_tx_descriptor *jz4740_dma_prep_slave_sg(
 static struct dma_async_tx_descriptor *jz4740_dma_prep_dma_cyclic(
 	struct dma_chan *c, dma_addr_t buf_addr, size_t buf_len,
 	size_t period_len, enum dma_transfer_direction direction,
-	unsigned long flags, void *context)
+	unsigned long flags)
 {
 	struct jz4740_dmaengine_chan *chan = to_jz4740_dma_chan(c);
 	struct jz4740_dma_desc *desc;
@@ -614,4 +614,4 @@ module_platform_driver(jz4740_dma_driver);
 
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
 MODULE_DESCRIPTION("JZ4740 DMA driver");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index a27ded53ab4f..1af731b83b3f 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -279,6 +279,19 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 	channel_set_bit(dw, CH_EN, dwc->mask);
 }
 
+static void dwc_dostart_first_queued(struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc;
+
+	if (list_empty(&dwc->queue))
+		return;
+
+	list_move(dwc->queue.next, &dwc->active_list);
+	desc = dwc_first_active(dwc);
+	dev_vdbg(chan2dev(&dwc->chan), "%s: started %u\n", __func__, desc->txd.cookie);
+	dwc_dostart(dwc, desc);
+}
+
 /*----------------------------------------------------------------------*/
 
 static void
@@ -335,10 +348,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * the completed ones.
 	 */
 	list_splice_init(&dwc->active_list, &list);
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -467,10 +477,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	/* Try to continue after resetting the channel... */
 	dwc_chan_disable(dw, dwc);
 
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
@@ -677,17 +684,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	 * possible, perhaps even appending to those already submitted
 	 * for DMA. But this is hard to do in a race-free manner.
 	 */
-	if (list_empty(&dwc->active_list)) {
-		dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__,
-				desc->txd.cookie);
-		list_add_tail(&desc->desc_node, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	} else {
-		dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__,
-				desc->txd.cookie);
 
-		list_add_tail(&desc->desc_node, &dwc->queue);
-	}
+	dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie);
+	list_add_tail(&desc->desc_node, &dwc->queue);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -1092,9 +1091,12 @@ dwc_tx_status(struct dma_chan *chan,
 static void dwc_issue_pending(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
 
-	if (!list_empty(&dwc->queue))
-		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (list_empty(&dwc->active_list))
+		dwc_dostart_first_queued(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index b512caf46944..7b65633f495e 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -23,6 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/of.h>
 
 #include <linux/platform_data/edma.h>
 
@@ -256,8 +257,13 @@ static int edma_terminate_all(struct edma_chan *echan)
 	 * echan->edesc is NULL and exit.)
 	 */
 	if (echan->edesc) {
+		int cyclic = echan->edesc->cyclic;
 		echan->edesc = NULL;
 		edma_stop(echan->ch_num);
+		/* Move the cyclic channel back to default queue */
+		if (cyclic)
+			edma_assign_channel_eventq(echan->ch_num,
+						   EVENTQ_DEFAULT);
 	}
 
 	vchan_get_all_descriptors(&echan->vchan, &head);
@@ -592,7 +598,7 @@ struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	size_t period_len, enum dma_transfer_direction direction,
-	unsigned long tx_flags, void *context)
+	unsigned long tx_flags)
 {
 	struct edma_chan *echan = to_edma_chan(chan);
 	struct device *dev = chan->device->dev;
@@ -718,12 +724,15 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		edesc->absync = ret;
 
 		/*
-		 * Enable interrupts for every period because callback
-		 * has to be called for every period.
+		 * Enable period interrupt only if it is requested
 		 */
-		edesc->pset[i].param.opt |= TCINTEN;
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[i].param.opt |= TCINTEN;
 	}
 
+	/* Place the cyclic channel to highest priority queue */
+	edma_assign_channel_eventq(echan->ch_num, EVENTQ_0);
+
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
 }
 
@@ -993,7 +1002,7 @@ static int edma_dma_device_slave_caps(struct dma_chan *dchan,
 	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	caps->cmd_pause = true;
 	caps->cmd_terminate = true;
-	caps->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	caps->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
 	return 0;
 }
@@ -1040,7 +1049,7 @@ static int edma_probe(struct platform_device *pdev)
 	ecc->dummy_slot = edma_alloc_slot(ecc->ctlr, EDMA_SLOT_ANY);
 	if (ecc->dummy_slot < 0) {
 		dev_err(&pdev->dev, "Can't allocate PaRAM dummy slot\n");
-		return -EIO;
+		return ecc->dummy_slot;
 	}
 
 	dma_cap_zero(ecc->dma_slave.cap_mask);
@@ -1125,7 +1134,7 @@ static int edma_init(void)
 		}
 	}
 
-	if (EDMA_CTLRS == 2) {
+	if (!of_have_populated_dt() && EDMA_CTLRS == 2) {
 		pdev1 = platform_device_register_full(&edma_dev_info1);
 		if (IS_ERR(pdev1)) {
 			platform_driver_unregister(&edma_driver);
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index cb4bf682a708..7650470196c4 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -1092,7 +1092,6 @@ fail:
  * @period_len: length of a single period
  * @dir: direction of the operation
  * @flags: tx descriptor status flags
- * @context: operation context (ignored)
  *
  * Prepares a descriptor for cyclic DMA operation. This means that once the
  * descriptor is submitted, we will be submitting in a @period_len sized
@@ -1105,8 +1104,7 @@ fail:
 static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 			   size_t buf_len, size_t period_len,
-			   enum dma_transfer_direction dir, unsigned long flags,
-			   void *context)
+			   enum dma_transfer_direction dir, unsigned long flags)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	struct ep93xx_dma_desc *desc, *first;
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index b396a7fb53ab..3c5711d5fe97 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -248,11 +248,12 @@ static void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
 			unsigned int slot, bool enable)
 {
 	u32 ch = fsl_chan->vchan.chan.chan_id;
-	void __iomem *muxaddr = fsl_chan->edma->muxbase[ch / DMAMUX_NR];
+	void __iomem *muxaddr;
 	unsigned chans_per_mux, ch_off;
 
 	chans_per_mux = fsl_chan->edma->n_chans / DMAMUX_NR;
 	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
+	muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux];
 
 	if (enable)
 		edma_writeb(fsl_chan->edma,
@@ -516,7 +517,7 @@ err:
 static struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
 		size_t period_len, enum dma_transfer_direction direction,
-		unsigned long flags, void *context)
+		unsigned long flags)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 	struct fsl_edma_desc *fsl_desc;
@@ -724,6 +725,7 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data;
 	struct dma_chan *chan, *_chan;
+	unsigned long chans_per_mux = fsl_edma->n_chans / DMAMUX_NR;
 
 	if (dma_spec->args_count != 2)
 		return NULL;
@@ -732,7 +734,7 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 	list_for_each_entry_safe(chan, _chan, &fsl_edma->dma_dev.channels, device_node) {
 		if (chan->client_count)
 			continue;
-		if ((chan->chan_id / DMAMUX_NR) == dma_spec->args[0]) {
+		if ((chan->chan_id / chans_per_mux) == dma_spec->args[0]) {
 			chan = dma_get_slave_channel(chan);
 			if (chan) {
 				chan->device->privatecnt++;
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index e0fec68aed25..d5d6885ab341 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -396,10 +396,17 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct fsldma_chan *chan = to_fsl_chan(tx->chan);
 	struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
 	struct fsl_desc_sw *child;
-	unsigned long flags;
 	dma_cookie_t cookie = -EINVAL;
 
-	spin_lock_irqsave(&chan->desc_lock, flags);
+	spin_lock_bh(&chan->desc_lock);
+
+#ifdef CONFIG_PM
+	if (unlikely(chan->pm_state != RUNNING)) {
+		chan_dbg(chan, "cannot submit due to suspend\n");
+		spin_unlock_bh(&chan->desc_lock);
+		return -1;
+	}
+#endif
 
 	/*
 	 * assign cookies to all of the software descriptors
@@ -412,7 +419,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	/* put this transaction onto the tail of the pending queue */
 	append_ld_queue(chan, desc);
 
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
+	spin_unlock_bh(&chan->desc_lock);
 
 	return cookie;
 }
@@ -459,6 +466,88 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(struct fsldma_chan *chan)
 }
 
 /**
+ * fsldma_clean_completed_descriptor - free all descriptors which
+ * has been completed and acked
+ * @chan: Freescale DMA channel
+ *
+ * This function is used on all completed and acked descriptors.
+ * All descriptors should only be freed in this function.
+ */
+static void fsldma_clean_completed_descriptor(struct fsldma_chan *chan)
+{
+	struct fsl_desc_sw *desc, *_desc;
+
+	/* Run the callback for each descriptor, in order */
+	list_for_each_entry_safe(desc, _desc, &chan->ld_completed, node)
+		if (async_tx_test_ack(&desc->async_tx))
+			fsl_dma_free_descriptor(chan, desc);
+}
+
+/**
+ * fsldma_run_tx_complete_actions - cleanup a single link descriptor
+ * @chan: Freescale DMA channel
+ * @desc: descriptor to cleanup and free
+ * @cookie: Freescale DMA transaction identifier
+ *
+ * This function is used on a descriptor which has been executed by the DMA
+ * controller. It will run any callbacks, submit any dependencies.
+ */
+static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan,
+		struct fsl_desc_sw *desc, dma_cookie_t cookie)
+{
+	struct dma_async_tx_descriptor *txd = &desc->async_tx;
+	dma_cookie_t ret = cookie;
+
+	BUG_ON(txd->cookie < 0);
+
+	if (txd->cookie > 0) {
+		ret = txd->cookie;
+
+		/* Run the link descriptor callback function */
+		if (txd->callback) {
+			chan_dbg(chan, "LD %p callback\n", desc);
+			txd->callback(txd->callback_param);
+		}
+	}
+
+	/* Run any dependencies */
+	dma_run_dependencies(txd);
+
+	return ret;
+}
+
+/**
+ * fsldma_clean_running_descriptor - move the completed descriptor from
+ * ld_running to ld_completed
+ * @chan: Freescale DMA channel
+ * @desc: the descriptor which is completed
+ *
+ * Free the descriptor directly if acked by async_tx api, or move it to
+ * queue ld_completed.
+ */
+static void fsldma_clean_running_descriptor(struct fsldma_chan *chan,
+		struct fsl_desc_sw *desc)
+{
+	/* Remove from the list of transactions */
+	list_del(&desc->node);
+
+	/*
+	 * the client is allowed to attach dependent operations
+	 * until 'ack' is set
+	 */
+	if (!async_tx_test_ack(&desc->async_tx)) {
+		/*
+		 * Move this descriptor to the list of descriptors which is
+		 * completed, but still awaiting the 'ack' bit to be set.
+		 */
+		list_add_tail(&desc->node, &chan->ld_completed);
+		return;
+	}
+
+	dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
+}
+
+/**
  * fsl_chan_xfer_ld_queue - transfer any pending transactions
  * @chan : Freescale DMA channel
  *
@@ -526,31 +615,58 @@ static void fsl_chan_xfer_ld_queue(struct fsldma_chan *chan)
 }
 
 /**
- * fsldma_cleanup_descriptor - cleanup and free a single link descriptor
+ * fsldma_cleanup_descriptors - cleanup link descriptors which are completed
+ * and move them to ld_completed to free until flag 'ack' is set
  * @chan: Freescale DMA channel
- * @desc: descriptor to cleanup and free
  *
- * This function is used on a descriptor which has been executed by the DMA
- * controller. It will run any callbacks, submit any dependencies, and then
- * free the descriptor.
+ * This function is used on descriptors which have been executed by the DMA
+ * controller. It will run any callbacks, submit any dependencies, then
+ * free these descriptors if flag 'ack' is set.
  */
-static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
-				      struct fsl_desc_sw *desc)
+static void fsldma_cleanup_descriptors(struct fsldma_chan *chan)
 {
-	struct dma_async_tx_descriptor *txd = &desc->async_tx;
+	struct fsl_desc_sw *desc, *_desc;
+	dma_cookie_t cookie = 0;
+	dma_addr_t curr_phys = get_cdar(chan);
+	int seen_current = 0;
+
+	fsldma_clean_completed_descriptor(chan);
+
+	/* Run the callback for each descriptor, in order */
+	list_for_each_entry_safe(desc, _desc, &chan->ld_running, node) {
+		/*
+		 * do not advance past the current descriptor loaded into the
+		 * hardware channel, subsequent descriptors are either in
+		 * process or have not been submitted
+		 */
+		if (seen_current)
+			break;
+
+		/*
+		 * stop the search if we reach the current descriptor and the
+		 * channel is busy
+		 */
+		if (desc->async_tx.phys == curr_phys) {
+			seen_current = 1;
+			if (!dma_is_idle(chan))
+				break;
+		}
+
+		cookie = fsldma_run_tx_complete_actions(chan, desc, cookie);
 
-	/* Run the link descriptor callback function */
-	if (txd->callback) {
-		chan_dbg(chan, "LD %p callback\n", desc);
-		txd->callback(txd->callback_param);
+		fsldma_clean_running_descriptor(chan, desc);
 	}
 
-	/* Run any dependencies */
-	dma_run_dependencies(txd);
+	/*
+	 * Start any pending transactions automatically
+	 *
+	 * In the ideal case, we keep the DMA controller busy while we go
+	 * ahead and free the descriptors below.
+	 */
+	fsl_chan_xfer_ld_queue(chan);
 
-	dma_descriptor_unmap(txd);
-	chan_dbg(chan, "LD %p free\n", desc);
-	dma_pool_free(chan->desc_pool, desc, txd->phys);
+	if (cookie > 0)
+		chan->common.completed_cookie = cookie;
 }
 
 /**
@@ -617,13 +733,14 @@ static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan,
 static void fsl_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct fsldma_chan *chan = to_fsl_chan(dchan);
-	unsigned long flags;
 
 	chan_dbg(chan, "free all channel resources\n");
-	spin_lock_irqsave(&chan->desc_lock, flags);
+	spin_lock_bh(&chan->desc_lock);
+	fsldma_cleanup_descriptors(chan);
 	fsldma_free_desc_list(chan, &chan->ld_pending);
 	fsldma_free_desc_list(chan, &chan->ld_running);
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
+	fsldma_free_desc_list(chan, &chan->ld_completed);
+	spin_unlock_bh(&chan->desc_lock);
 
 	dma_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
@@ -842,7 +959,6 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 {
 	struct dma_slave_config *config;
 	struct fsldma_chan *chan;
-	unsigned long flags;
 	int size;
 
 	if (!dchan)
@@ -852,7 +968,7 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
-		spin_lock_irqsave(&chan->desc_lock, flags);
+		spin_lock_bh(&chan->desc_lock);
 
 		/* Halt the DMA engine */
 		dma_halt(chan);
@@ -860,9 +976,10 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 		/* Remove and free all of the descriptors in the LD queue */
 		fsldma_free_desc_list(chan, &chan->ld_pending);
 		fsldma_free_desc_list(chan, &chan->ld_running);
+		fsldma_free_desc_list(chan, &chan->ld_completed);
 		chan->idle = true;
 
-		spin_unlock_irqrestore(&chan->desc_lock, flags);
+		spin_unlock_bh(&chan->desc_lock);
 		return 0;
 
 	case DMA_SLAVE_CONFIG:
@@ -904,11 +1021,10 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 static void fsl_dma_memcpy_issue_pending(struct dma_chan *dchan)
 {
 	struct fsldma_chan *chan = to_fsl_chan(dchan);
-	unsigned long flags;
 
-	spin_lock_irqsave(&chan->desc_lock, flags);
+	spin_lock_bh(&chan->desc_lock);
 	fsl_chan_xfer_ld_queue(chan);
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
+	spin_unlock_bh(&chan->desc_lock);
 }
 
 /**
@@ -919,6 +1035,17 @@ static enum dma_status fsl_tx_status(struct dma_chan *dchan,
 					dma_cookie_t cookie,
 					struct dma_tx_state *txstate)
 {
+	struct fsldma_chan *chan = to_fsl_chan(dchan);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	spin_lock_bh(&chan->desc_lock);
+	fsldma_cleanup_descriptors(chan);
+	spin_unlock_bh(&chan->desc_lock);
+
 	return dma_cookie_status(dchan, cookie, txstate);
 }
 
@@ -996,52 +1123,18 @@ static irqreturn_t fsldma_chan_irq(int irq, void *data)
 static void dma_