Merge tag 'dmaengine-4.6-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This is smallish update with minor changes to core and new driver and
  usual updates.  Nothing super exciting here..

   - We have made slave address as physical to enable driver to do the
     mapping.

   - We now expose the maxburst for slave dma as new capability so
     clients can know this and program accordingly

   - addition of device synchronize callbacks on omap and edma.

   - pl330 updates to support DMAFLUSHP for Rockchip platforms.

   - Updates and improved sg handling in Xilinx VDMA driver.

   - New hidma qualcomm dma driver, though some bits are still in
     progress"

* tag 'dmaengine-4.6-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (40 commits)
  dmaengine: IOATDMA: revise channel reset workaround on CB3.3 platforms
  dmaengine: add Qualcomm Technologies HIDMA channel driver
  dmaengine: add Qualcomm Technologies HIDMA management driver
  dmaengine: hidma: Add Device Tree binding
  dmaengine: qcom_bam_dma: move to qcom directory
  dmaengine: tegra: Move of_device_id table near to its user
  dmaengine: xilinx_vdma: Remove unnecessary variable initializations
  dmaengine: sirf: use __maybe_unused to hide pm functions
  dmaengine: rcar-dmac: clear pertinence number of channels
  dmaengine: sh: shdmac: don't open code of_device_get_match_data()
  dmaengine: tegra: don't open code of_device_get_match_data()
  dmaengine: qcom_bam_dma: Make driver work for BE
  dmaengine: sun4i: support module autoloading
  dma/mic_x100_dma: IS_ERR() vs PTR_ERR() typo
  dmaengine: xilinx_vdma: Use readl_poll_timeout instead of do while loop's
  dmaengine: xilinx_vdma: Simplify spin lock handling
  dmaengine: xilinx_vdma: Fix issues with non-parking mode
  dmaengine: xilinx_vdma: Improve SG engine handling
  dmaengine: pl330: fix to support the burst mode
  dmaengine: make slave address physical
  ...

33 files changed, 1953 insertions, 462 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 79b1390f2016..d96d87c56f2e 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -341,12 +341,13 @@ config MV_XOR
 
 config MXS_DMA
 	bool "MXS DMA support"
-	depends on SOC_IMX23 || SOC_IMX28 || SOC_IMX6Q
+	depends on SOC_IMX23 || SOC_IMX28 || SOC_IMX6Q || SOC_IMX6UL
 	select STMP_DEVICE
 	select DMA_ENGINE
 	help
 	  Support the MXS DMA engine. This engine including APBH-DMA
-	  and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips.
+	  and APBX-DMA is integrated into Freescale
+	  i.MX23/28/MX6Q/MX6DL/MX6UL chips.
 
 config MX3_IPU
 	bool "MX3x Image Processing Unit support"
@@ -408,15 +409,6 @@ config PXA_DMA
 	  16 to 32 channels for peripheral to memory or memory to memory
 	  transfers.
 
-config QCOM_BAM_DMA
-	tristate "QCOM BAM DMA support"
-	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	---help---
-	  Enable support for the QCOM BAM DMA controller.  This controller
-	  provides DMA capabilities for a variety of on-chip devices.
-
 config SIRF_DMA
 	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
 	depends on ARCH_SIRF
@@ -539,6 +531,8 @@ config ZX_DMA
 # driver files
 source "drivers/dma/bestcomm/Kconfig"
 
+source "drivers/dma/qcom/Kconfig"
+
 source "drivers/dma/dw/Kconfig"
 
 source "drivers/dma/hsu/Kconfig"
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 2dd0a067a0ca..6084127c1486 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -52,7 +52,6 @@ obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
 obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
 obj-$(CONFIG_PXA_DMA) += pxa_dma.o
-obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
@@ -67,4 +66,5 @@ obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx296702_dma.o
 
+obj-y += qcom/
 obj-y += xilinx/
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index eed6bda01790..4a748c3435d7 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -438,7 +438,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 			return ERR_PTR(-ENODEV);
 	}
 
-	dev_dbg(dev, "found DMA channel \"%s\" at index %d\n", name, index);
+	dev_dbg(dev, "Looking for DMA channel \"%s\" at index %d...\n", name, index);
 	return acpi_dma_request_slave_chan_by_index(dev, index);
 }
 EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_name);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index c50a247be2e0..0cb259c59916 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -496,6 +496,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->src_addr_widths = device->src_addr_widths;
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
+	caps->max_burst = device->max_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
 
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 241ff2b1402b..0a50c18d85b8 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -150,7 +150,7 @@ enum dw_dma_msize {
 #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_INC	(0<<9)		/* 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 */
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index e3d7fcb69b4c..ee3463e774f8 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -869,6 +869,13 @@ static int edma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void edma_synchronize(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	vchan_synchronize(&echan->vchan);
+}
+
 static int edma_slave_config(struct dma_chan *chan,
 	struct dma_slave_config *cfg)
 {
@@ -1365,36 +1372,36 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 static void edma_completion_handler(struct edma_chan *echan)
 {
 	struct device *dev = echan->vchan.chan.device->dev;
-	struct edma_desc *edesc = echan->edesc;
-
-	if (!edesc)
-		return;
+	struct edma_desc *edesc;
 
 	spin_lock(&echan->vchan.lock);
-	if (edesc->cyclic) {
-		vchan_cyclic_callback(&edesc->vdesc);
-		spin_unlock(&echan->vchan.lock);
-		return;
-	} else if (edesc->processed == edesc->pset_nr) {
-		edesc->residue = 0;
-		edma_stop(echan);
-		vchan_cookie_complete(&edesc->vdesc);
-		echan->edesc = NULL;
-
-		dev_dbg(dev, "Transfer completed on channel %d\n",
-			echan->ch_num);
-	} else {
-		dev_dbg(dev, "Sub transfer completed on channel %d\n",
-			echan->ch_num);
-
-		edma_pause(echan);
-
-		/* Update statistics for tx_status */
-		edesc->residue -= edesc->sg_len;
-		edesc->residue_stat = edesc->residue;
-		edesc->processed_stat = edesc->processed;
+	edesc = echan->edesc;
+	if (edesc) {
+		if (edesc->cyclic) {
+			vchan_cyclic_callback(&edesc->vdesc);
+			spin_unlock(&echan->vchan.lock);
+			return;
+		} else if (edesc->processed == edesc->pset_nr) {
+			edesc->residue = 0;
+			edma_stop(echan);
+			vchan_cookie_complete(&edesc->vdesc);
+			echan->edesc = NULL;
+
+			dev_dbg(dev, "Transfer completed on channel %d\n",
+				echan->ch_num);
+		} else {
+			dev_dbg(dev, "Sub transfer completed on channel %d\n",
+				echan->ch_num);
+
+			edma_pause(echan);
+
+			/* Update statistics for tx_status */
+			edesc->residue -= edesc->sg_len;
+			edesc->residue_stat = edesc->residue;
+			edesc->processed_stat = edesc->processed;
+		}
+		edma_execute(echan);
 	}
-	edma_execute(echan);
 
 	spin_unlock(&echan->vchan.lock);
 }
@@ -1837,6 +1844,7 @@ static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode)
 	s_ddev->device_pause = edma_dma_pause;
 	s_ddev->device_resume = edma_dma_resume;
 	s_ddev->device_terminate_all = edma_terminate_all;
+	s_ddev->device_synchronize = edma_synchronize;
 
 	s_ddev->src_addr_widths = EDMA_DMA_BUSWIDTHS;
 	s_ddev->dst_addr_widths = EDMA_DMA_BUSWIDTHS;
@@ -1862,6 +1870,7 @@ static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode)
 		m_ddev->device_pause = edma_dma_pause;
 		m_ddev->device_resume = edma_dma_resume;
 		m_ddev->device_terminate_all = edma_terminate_all;
+		m_ddev->device_synchronize = edma_synchronize;
 
 		m_ddev->src_addr_widths = EDMA_DMA_BUSWIDTHS;
 		m_ddev->dst_addr_widths = EDMA_DMA_BUSWIDTHS;
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 57ff46284f15..21f08cc3352b 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -421,23 +421,25 @@ static int m2p_hw_interrupt(struct ep93xx_dma_chan *edmac)
 			desc->size);
 	}
 
-	switch (irq_status & (M2P_INTERRUPT_STALL | M2P_INTERRUPT_NFB)) {
-	case M2P_INTERRUPT_STALL:
-		/* Disable interrupts */
-		control = readl(edmac->regs + M2P_CONTROL);
-		control &= ~(M2P_CONTROL_STALLINT | M2P_CONTROL_NFBINT);
-		m2p_set_control(edmac, control);
-
-		return INTERRUPT_DONE;
-
-	case M2P_INTERRUPT_NFB:
-		if (ep93xx_dma_advance_active(edmac))
-			m2p_fill_desc(edmac);
+	/*
+	 * Even latest E2 silicon revision sometimes assert STALL interrupt
+	 * instead of NFB. Therefore we treat them equally, basing on the
+	 * amount of data we still have to transfer.
+	 */
+	if (!(irq_status & (M2P_INTERRUPT_STALL | M2P_INTERRUPT_NFB)))
+		return INTERRUPT_UNKNOWN;
 
+	if (ep93xx_dma_advance_active(edmac)) {
+		m2p_fill_desc(edmac);
 		return INTERRUPT_NEXT_BUFFER;
 	}
 
-	return INTERRUPT_UNKNOWN;
+	/* Disable interrupts */
+	control = readl(edmac->regs + M2P_CONTROL);
+	control &= ~(M2P_CONTROL_STALLINT | M2P_CONTROL_NFBINT);
+	m2p_set_control(edmac, control);
+
+	return INTERRUPT_DONE;
 }
 
 /*
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 3cb7b2c78197..1953e57505f4 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -289,6 +289,9 @@ static void idma64_desc_fill(struct idma64_chan *idma64c,
 
 	/* Trigger an interrupt after the last block is transfered */
 	lli->ctllo |= IDMA64C_CTLL_INT_EN;
+
+	/* Disable LLP transfer in the last block */
+	lli->ctllo &= ~(IDMA64C_CTLL_LLP_S_EN | IDMA64C_CTLL_LLP_D_EN);
 }
 
 static struct dma_async_tx_descriptor *idma64_prep_slave_sg(
diff --git a/drivers/dma/idma64.h b/drivers/dma/idma64.h
index 8423f13ed0da..dc6874424188 100644
--- a/drivers/dma/idma64.h
+++ b/drivers/dma/idma64.h
@@ -71,7 +71,7 @@
 #define IDMA64C_CFGH_SRC_PER(x)		((x) << 0)	/* src peripheral */
 #define IDMA64C_CFGH_DST_PER(x)		((x) << 4)	/* dst peripheral */
 #define IDMA64C_CFGH_RD_ISSUE_THD(x)	((x) << 8)
-#define IDMA64C_CFGH_RW_ISSUE_THD(x)	((x) << 18)
+#define IDMA64C_CFGH_WR_ISSUE_THD(x)	((x) << 18)
 
 /* Interrupt registers */
 
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 21539d5c54c3..bd09961443b1 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -31,6 +31,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/workqueue.h>
 #include <linux/prefetch.h>
+#include <linux/sizes.h>
 #include "dma.h"
 #include "registers.h"
 #include "hw.h"
@@ -290,24 +291,30 @@ static dma_cookie_t ioat_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
 }
 
 static struct ioat_ring_ent *
-ioat_alloc_ring_ent(struct dma_chan *chan, gfp_t flags)
+ioat_alloc_ring_ent(struct dma_chan *chan, int idx, gfp_t flags)
 {
 	struct ioat_dma_descriptor *hw;
 	struct ioat_ring_ent *desc;
 	struct ioatdma_device *ioat_dma;
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);
+	int chunk;
 	dma_addr_t phys;
+	u8 *pos;
+	off_t offs;
 
 	ioat_dma = to_ioatdma_device(chan->device);
-	hw = pci_pool_alloc(ioat_dma->dma_pool, flags, &phys);
-	if (!hw)
-		return NULL;
+
+	chunk = idx / IOAT_DESCS_PER_2M;
+	idx &= (IOAT_DESCS_PER_2M - 1);
+	offs = idx * IOAT_DESC_SZ;
+	pos = (u8 *)ioat_chan->descs[chunk].virt + offs;
+	phys = ioat_chan->descs[chunk].hw + offs;
+	hw = (struct ioat_dma_descriptor *)pos;
 	memset(hw, 0, sizeof(*hw));
 
 	desc = kmem_cache_zalloc(ioat_cache, flags);
-	if (!desc) {
-		pci_pool_free(ioat_dma->dma_pool, hw, phys);
+	if (!desc)
 		return NULL;
-	}
 
 	dma_async_tx_descriptor_init(&desc->txd, chan);
 	desc->txd.tx_submit = ioat_tx_submit_unlock;
@@ -318,32 +325,63 @@ ioat_alloc_ring_ent(struct dma_chan *chan, gfp_t flags)
 
 void ioat_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *chan)
 {
-	struct ioatdma_device *ioat_dma;
-
-	ioat_dma = to_ioatdma_device(chan->device);
-	pci_pool_free(ioat_dma->dma_pool, desc->hw, desc->txd.phys);
 	kmem_cache_free(ioat_cache, desc);
 }
 
 struct ioat_ring_ent **
 ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 {
+	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
 	struct ioat_ring_ent **ring;
-	int descs = 1 << order;
-	int i;
-
-	if (order > ioat_get_max_alloc_order())
-		return NULL;
+	int total_descs = 1 << order;
+	int i, chunks;
 
 	/* allocate the array to hold the software ring */
-	ring = kcalloc(descs, sizeof(*ring), flags);
+	ring = kcalloc(total_descs, sizeof(*ring), flags);
 	if (!ring)
 		return NULL;
-	for (i = 0; i < descs; i++) {
-		ring[i] = ioat_alloc_ring_ent(c, flags);
+
+	ioat_chan->desc_chunks = chunks = (total_descs * IOAT_DESC_SZ) / SZ_2M;
+
+	for (i = 0; i < chunks; i++) {
+		struct ioat_descs *descs = &ioat_chan->descs[i];
+
+		descs->virt = dma_alloc_coherent(to_dev(ioat_chan),
+						 SZ_2M, &descs->hw, flags);
+		if (!descs->virt && (i > 0)) {
+			int idx;
+
+			for (idx = 0; idx < i; idx++) {
+				dma_free_coherent(to_dev(ioat_chan), SZ_2M,
+						  descs->virt, descs->hw);
+				descs->virt = NULL;
+				descs->hw = 0;
+			}
+
+			ioat_chan->desc_chunks = 0;
+			kfree(ring);
+			return NULL;
+		}
+	}
+
+	for (i = 0; i < total_descs; i++) {
+		ring[i] = ioat_alloc_ring_ent(c, i, flags);
 		if (!ring[i]) {
+			int idx;
+
 			while (i--)
 				ioat_free_ring_ent(ring[i], c);
+
+			for (idx = 0; idx < ioat_chan->desc_chunks; idx++) {
+				dma_free_coherent(to_dev(ioat_chan),
+						  SZ_2M,
+						  ioat_chan->descs[idx].virt,
+						  ioat_chan->descs[idx].hw);
+				ioat_chan->descs[idx].virt = NULL;
+				ioat_chan->descs[idx].hw = 0;
+			}
+
+			ioat_chan->desc_chunks = 0;
 			kfree(ring);
 			return NULL;
 		}
@@ -351,7 +389,7 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 	}
 
 	/* link descs */
-	for (i = 0; i < descs-1; i++) {
+	for (i = 0; i < total_descs-1; i++) {
 		struct ioat_ring_ent *next = ring[i+1];
 		struct ioat_dma_descriptor *hw = ring[i]->hw;
 
@@ -362,114 +400,6 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 	return ring;
 }
 
-static bool reshape_ring(struct ioatdma_chan *ioat_chan, int order)
-{
-	/* reshape differs from normal ring allocation in that we want
-	 * to allocate a new software ring while only
-	 * extending/truncating the hardware ring
-	 */
-	struct dma_chan *c = &ioat_chan->dma_chan;
-	const u32 curr_size = ioat_ring_size(ioat_chan);
-	const u16 active = ioat_ring_active(ioat_chan);
-	const u32 new_size = 1 << order;
-	struct ioat_ring_ent **ring;
-	u32 i;
-
-	if (order > ioat_get_max_alloc_order())
-		return false;
-
-	/* double check that we have at least 1 free descriptor */
-	if (active == curr_size)
-		return false;
-
-	/* when shrinking, verify that we can hold the current active
-	 * set in the new ring
-	 */
-	if (active >= new_size)
-		return false;
-
-	/* allocate the array to hold the software ring */
-	ring = kcalloc(new_size, sizeof(*ring), GFP_NOWAIT);
-	if (!ring)
-		return false;
-
-	/* allocate/trim descriptors as needed */
-	if (new_size > curr_size) {
-		/* copy current descriptors to the new ring */
-		for (i = 0; i < curr_size; i++) {
-			u16 curr_idx = (ioat_chan->tail+i) & (curr_size-1);
-			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat_chan->ring[curr_idx];
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* add new descriptors to the ring */
-		for (i = curr_size; i < new_size; i++) {
-			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat_alloc_ring_ent(c, GFP_NOWAIT);
-			if (!ring[new_idx]) {
-				while (i--) {
-					u16 new_idx = (ioat_chan->tail+i) &
-						       (new_size-1);
-
-					ioat_free_ring_ent(ring[new_idx], c);
-				}
-				kfree(ring);
-				return false;
-			}
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* hw link new descriptors */
-		for (i = curr_size-1; i < new_size; i++) {
-			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
-			struct ioat_ring_ent *next =
-				ring[(new_idx+1) & (new_size-1)];
-			struct ioat_dma_descriptor *hw = ring[new_idx]->hw;
-
-			hw->next = next->txd.phys;
-		}
-	} else {
-		struct ioat_dma_descriptor *hw;
-		struct ioat_ring_ent *next;
-
-		/* copy current descriptors to the new ring, dropping the
-		 * removed descriptors
-		 */
-		for (i = 0; i < new_size; i++) {
-			u16 curr_idx = (ioat_chan->tail+i) & (curr_size-1);
-			u16 new_idx = (ioat_chan->tail+i) & (new_size-1);
-
-			ring[new_idx] = ioat_chan->ring[curr_idx];
-			set_desc_id(ring[new_idx], new_idx);
-		}
-
-		/* free deleted descriptors */
-		for (i = new_size; i < curr_size; i++) {
-			struct ioat_ring_ent *ent;
-
-			ent = ioat_get_ring_ent(ioat_chan, ioat_chan->tail+i);
-			ioat_free_ring_ent(ent, c);
-		}
-
-		/* fix up hardware ring */
-		hw = ring[(ioat_chan->tail+new_size-1) & (new_size-1)]->hw;
-		next = ring[(ioat_chan->tail+new_size) & (new_size-1)];
-		hw->next = next->txd.phys;
-	}
-
-	dev_dbg(to_dev(ioat_chan), "%s: allocated %d descriptors\n",
-		__func__, new_size);
-
-	kfree(ioat_chan->ring);
-	ioat_chan->ring = ring;
-	ioat_chan->alloc_order = order;
-
-	return true;
-}
-
 /**
  * ioat_check_space_lock - verify space and grab ring producer lock
  * @ioat: ioat,3 channel (ring) to operate on
@@ -478,9 +408,6 @@ static bool reshape_ring(struct ioatdma_chan *ioat_chan, int order)
 int ioat_check_space_lock(struct ioatdma_chan *ioat_chan, int num_descs)
 	__acquires(&ioat_chan->prep_lock)
 {
-	bool retry;
-
- retry:
 	spin_lock_bh(&ioat_chan->prep_lock);
 	/* never allow the last descriptor to be consumed, we need at
 	 * least one free at all times to allow for on-the-fly ring
@@ -493,24 +420,8 @@ int ioat_check_space_lock(struct ioatdma_chan *ioat_chan, int num_descs)
 		ioat_chan->produce = num_descs;
 		return 0;  /* with ioat->prep_lock held */
 	}
-	retry = test_and_set_bit(IOAT_RESHAPE_PENDING, &ioat_chan->state);
 	spin_unlock_bh(&ioat_chan->prep_lock);
 
-	/* is another cpu already trying to expand the ring? */
-	if (retry)
-		goto retry;
-
-	spin_lock_bh(&ioat_chan->cleanup_lock);
-	spin_lock_bh(&ioat_chan->prep_lock);
-	retry = reshape_ring(ioat_chan, ioat_chan->alloc_order + 1);
-	clear_bit(IOAT_RESHAPE_PENDING, &ioat_chan->state);
-	spin_unlock_bh(&ioat_chan->prep_lock);
-	spin_unlock_bh(&ioat_chan->cleanup_lock);
-
-	/* if we were able to expand the ring retry the allocation */
-	if (retry)
-		goto retry;
-
 	dev_dbg_ratelimited(to_dev(ioat_chan),
 			    "%s: ring full! num_descs: %d (%x:%x:%x)\n",
 			    __func__, num_descs, ioat_chan->head,
@@ -823,19 +734,6 @@ static void check_active(struct ioatdma_chan *ioat_chan)
 
 	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &ioat_chan->state))
 		mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
-	else if (ioat_chan->alloc_order > ioat_get_alloc_order()) {
-		/* if the ring is idle, empty, and oversized try to step
-		 * down the size
-		 */
-		reshape_ring(ioat_chan, ioat_chan->alloc_order - 1);
-
-		/* keep shrinking until we get back to our minimum
-		 * default size
-		 */
-		if (ioat_chan->alloc_order > ioat_get_alloc_order())
-			mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
-	}
-
 }
 
 void ioat_timer_event(unsigned long data)
@@ -916,40 +814,6 @@ ioat_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 	return dma_cookie_status(c, cookie, txstate);
 }
 
-static int ioat_irq_reinit(struct ioatdma_device *ioat_dma)
-{
-	struct pci_dev *pdev = ioat_dma->pdev;
-	int irq = pdev->irq, i;
-
-	if (!is_bwd_ioat(pdev))
-		return 0;
-
-	switch (ioat_dma->irq_mode) {
-	case IOAT_MSIX:
-		for (i = 0; i < ioat_dma->dma_dev.chancnt; i++) {
-			struct msix_entry *msix = &ioat_dma->msix_entries[i];
-			struct ioatdma_chan *ioat_chan;
-
-			ioat_chan = ioat_chan_by_index(ioat_dma, i);
-			devm_free_irq(&pdev->dev, msix->vector, ioat_chan);
-		}
-
-		pci_disable_msix(pdev);
-		break;
-	case IOAT_MSI:
-		pci_disable_msi(pdev);
-		/* fall through */
-	case IOAT_INTX:
-		devm_free_irq(&pdev->dev, irq, ioat_dma);
-		break;
-	default:
-		return 0;
-	}
-	ioat_dma->irq_mode = IOAT_NOIRQ;
-
-	return ioat_dma_setup_interrupts(ioat_dma);
-}
-
 int ioat_reset_hw(struct ioatdma_chan *ioat_chan)
 {
 	/* throw away whatever the channel was doing and get it
@@ -989,9 +853,21 @@ int ioat_reset_hw(struct ioatdma_chan *ioat_chan)
 		}
 	}
 
+	if (is_bwd_ioat(pdev) && (ioat_dma->irq_mode == IOAT_MSIX)) {
+		ioat_dma->msixtba0 = readq(ioat_dma->reg_base + 0x1000);
+		ioat_dma->msixdata0 = readq(ioat_dma->reg_base + 0x1008);
+		ioat_dma->msixpba = readq(ioat_dma->reg_base + 0x1800);
+	}
+
+
 	err = ioat_reset_sync(ioat_chan, msecs_to_jiffies(200));
-	if (!err)
-		err = ioat_irq_reinit(ioat_dma);
+	if (!err) {
+		if (is_bwd_ioat(pdev) && (ioat_dma->irq_mode == IOAT_MSIX)) {
+			writeq(ioat_dma->msixtba0, ioat_dma->reg_base + 0x1000);
+			writeq(ioat_dma->msixdata0, ioat_dma->reg_base + 0x1008);
+			writeq(ioat_dma->msixpba, ioat_dma->reg_base + 0x1800);
+		}
+	}
 
 	if (err)
 		dev_err(&pdev->dev, "Failed to reset: %d\n", err);
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index b8f48074789f..a9bc1a15b0d1 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -62,7 +62,6 @@ enum ioat_irq_mode {
  * struct ioatdma_device - internal representation of a IOAT device
  * @pdev: PCI-Express device
  * @reg_base: MMIO register space base address
- * @dma_pool: for allocating DMA descriptors
  * @completion_pool: DMA buffers for completion ops
  * @sed_hw_pool: DMA super descriptor pools
  * @dma_dev: embedded struct dma_device
@@ -76,8 +75,7 @@ enum ioat_irq_mode {
 struct ioatdma_device {
 	struct pci_dev *pdev;
 	void __iomem *reg_base;
-	struct pci_pool *dma_pool;
-	struct pci_pool *completion_pool;
+	struct dma_pool *completion_pool;
 #define MAX_SED_POOLS	5
 	struct dma_pool *sed_hw_pool[MAX_SED_POOLS];
 	struct dma_device dma_dev;
@@ -88,6 +86,16 @@ struct ioatdma_device {
 	struct dca_provider *dca;
 	enum ioat_irq_mode irq_mode;
 	u32 cap;
+
+	/* shadow version for CB3.3 chan reset errata workaround */
+	u64 msixtba0;
+	u64 msixdata0;
+	u32 msixpba;
+};
+
+struct ioat_descs {
+	void *virt;
+	dma_addr_t hw;
 };
 
 struct ioatdma_chan {
@@ -100,7 +108,6 @@ struct ioatdma_chan {
 	#define IOAT_COMPLETION_ACK 1
 	#define IOAT_RESET_PENDING 2
 	#define IOAT_KOBJ_INIT_FAIL 3
-	#define IOAT_RESHAPE_PENDING 4
 	#define IOAT_RUN 5
 	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
@@ -133,6 +140,8 @@ struct ioatdma_chan {
 	u16 produce;
 	struct ioat_ring_ent **ring;
 	spinlock_t prep_lock;
+	struct ioat_descs descs[2];
+	int desc_chunks;
 };
 
 struct ioat_sysfs_entry {
@@ -302,10 +311,8 @@ static inline bool is_ioat_bug(unsigned long err)
 }
 
 #define IOAT_MAX_ORDER 16
-#define ioat_get_alloc_order() \
-	(min(ioat_ring_alloc_order, IOAT_MAX_ORDER))
-#define ioat_get_max_alloc_order() \
-	(min(ioat_ring_max_alloc_order, IOAT_MAX_ORDER))
+#define IOAT_MAX_DESCS 65536
+#define IOAT_DESCS_PER_2M 32768
 
 static inline u32 ioat_ring_size(struct ioatdma_chan *ioat_chan)
 {
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index 690e3b4f8202..8e67895bcca3 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -73,6 +73,8 @@
 
 int system_has_dca_enabled(struct pci_dev *pdev);
 
+#define IOAT_DESC_SZ	64
+
 struct ioat_dma_descriptor {
 	uint32_t	size;
 	union {
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 4ef0c5e07912..efdee1a69fc4 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -28,6 +28,7 @@
 #include <linux/prefetch.h>
 #include <linux/dca.h>
 #include <linux/aer.h>
+#include <linux/sizes.h>
 #include "dma.h"
 #include "registers.h"
 #include "hw.h"
@@ -136,14 +137,6 @@ int ioat_pending_level = 4;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
 		 "high-water mark for pushing ioat descriptors (default: 4)");
-int ioat_ring_alloc_order = 8;
-module_param(ioat_ring_alloc_order, int, 0644);
-MODULE_PARM_DESC(ioat_ring_alloc_order,
-		 "ioat+: allocate 2^n descriptors per channel (default: 8 max: 16)");
-int ioat_ring_max_alloc_order = IOAT_MAX_ORDER;
-module_param(ioat_ring_max_alloc_order, int, 0644);
-MODULE_PARM_DESC(ioat_ring_max_alloc_order,
-		 "ioat+: upper limit for ring size (default: 16)");
 static char ioat_interrupt_style[32] = "msix";
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
 		    sizeof(ioat_interrupt_style), 0644);
@@ -504,23 +497,14 @@ static int ioat_probe(struct ioatdma_device *ioat_dma)
 	struct pci_dev *pdev = ioat_dma->pdev;
 	struct device *dev = &pdev->dev;
 
-	/* DMA coherent memory pool for DMA descriptor allocations */
-	ioat_dma->dma_pool = pci_pool_create("dma_desc_pool", pdev,
-					     sizeof(struct ioat_dma_descriptor),
-					     64, 0);
-	if (!ioat_dma->dma_pool) {
-		err = -ENOMEM;
-		goto err_dma_pool;
-	}
-
-	ioat_dma->completion_pool = pci_pool_create("completion_pool", pdev,
+	ioat_dma->completion_pool = dma_pool_create("completion_pool", dev,
 						    sizeof(u64),
 						    SMP_CACHE_BYTES,
 						    SMP_CACHE_BYTES);
 
 	if (!ioat_dma->completion_pool) {
 		err = -ENOMEM;
-		goto err_completion_pool;
+		goto err_out;
 	}
 
 	ioat_enumerate_channels(ioat_dma);
@@ -546,10 +530,8 @@ static int ioat_probe(struct ioatdma_device *ioat_dma)
 err_self_test:
 	ioat_disable_interrupts(ioat_dma);
 err_setup_interrupts:
-	pci_pool_destroy(ioat_dma->completion_pool);
-err_completion_pool:
-	pci_pool_destroy(ioat_dma->dma_pool);
-err_dma_pool:
+	dma_pool_destroy(ioat_dma->completion_pool);
+err_out:
 	return err;
 }
 
@@ -559,8 +541,7 @@ static int ioat_register(struct ioatdma_device *ioat_dma)
 
 	if (err) {
 		ioat_disable_interrupts(ioat_dma);
-		pci_pool_destroy(ioat_dma->completion_pool);
-		pci_pool_destroy(ioat_dma->dma_pool);
+		dma_pool_destroy(ioat_dma->completion_pool);
 	}
 
 	return err;
@@ -576,8 +557,7 @@ static void ioat_dma_remove(struct ioatdma_device *ioat_dma)
 
 	dma_async_device_unregister(dma);
 
-	pci_pool_destroy(ioat_dma->dma_pool);
-	pci_pool_destroy(ioat_dma->completion_pool);
+	dma_pool_destroy(ioat_dma->completion_pool);
 
 	INIT_LIST_HEAD(&dma->channels);
 }
@@ -666,10 +646,19 @@ static void ioat_free_chan_resources(struct dma_chan *c)
 		ioat_free_ring_ent(desc, c);
 	}
 
+	for (i = 0; i < ioat_chan->desc_chunks; i++) {
+		dma_free_coherent(to_dev(ioat_chan), SZ_2M,
+				  ioat_chan->descs[i].virt,
+				  ioat_chan->descs[i].hw);
+		ioat_chan->descs[i].virt = NULL;
+		ioat_chan->descs[i].hw = 0;
+	}
+	ioat_chan->desc_chunks = 0;
+
 	kfree(ioat_chan->ring);
 	ioat_chan->ring = NULL;
 	ioat_chan->alloc_order = 0;
-	pci_pool_free(ioat_dma->completion_pool, ioat_chan->completion,
+	dma_pool_free(ioat_dma->completion_pool, ioat_chan->completion,
 		      ioat_chan->completion_dma);
 	spin_unlock_bh(&ioat_chan->prep_lock);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
@@ -701,7 +690,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	/* allocate a completion writeback area */
 	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
 	ioat_chan->completion =
-		pci_pool_alloc(ioat_chan->ioat_dma->completion_pool,
+		dma_pool_alloc(ioat_chan->ioat_dma->completion_pool,
 			       GFP_KERNEL, &ioat_chan->completion_dma);
 	if (!ioat_chan->completion)
 		return -ENOMEM;
@@ -712,7 +701,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	writel(((u64)ioat_chan->completion_dma) >> 32,
 	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	order = ioat_get_alloc_order();
+	order = IOAT_MAX_ORDER;
 	ring = ioat_alloc_ring(c, order, GFP_KERNEL);
 	if (!ring)
 		return -ENOMEM;
diff --git a/drivers/dma/ioat/prep.c b/drivers/dma/ioat/prep.c
index 6bb4a13a8fbd..243421af888f 100644
--- a/drivers/dma/ioat/prep.c
+++ b/drivers/dma/ioat/prep.c
@@ -26,7 +26,7 @@
 #include "hw.h"
 #include "dma.h"
 
-#define MAX_SCF	1024
+#define MAX_SCF	256
 
 /* provide a lookup table for setting the source address in the base or
  * extended descriptor of an xor or pq descriptor
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 068e920ecb68..1502b24b7c7d 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -483,7 +483,7 @@ static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 			mic_dma_intr_handler, mic_dma_thread_fn,
 			"mic dma_channel", ch, ch->ch_num);
 	if (IS_ERR(ch->cookie))
-		return IS_ERR(ch->cookie);
+		return PTR_ERR(ch->cookie);
 	return 0;
 }
 
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 9794b073d7d7..43bd5aee7ffe 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -1009,6 +1009,13 @@ static int omap_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void omap_dma_synchronize(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
 static int omap_dma_pause(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
@@ -1112,6 +1119,7 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.device_pause = omap_dma_pause;
 	od->ddev.device_resume = omap_dma_resume;
 	od->ddev.device_terminate_all = omap_dma_terminate_all;
+	od->ddev.device_synchronize = omap_dma_synchronize;
 	od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 17ee758b419f..372b4359da97 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -33,6 +33,9 @@
 #define PL330_MAX_CHAN		8
 #define PL330_MAX_IRQS		32
 #define PL330_MAX_PERI		32
+#define PL330_MAX_BURST         16
+
+#define PL330_QUIRK_BROKEN_NO_FLUSHP BIT(0)
 
 enum pl330_cachectrl {
 	CCTRL0,		/* Noncacheable and nonbufferable */
@@ -488,6 +491,17 @@ struct pl330_dmac {
 	/* Peripheral channels connected to this DMAC */
 	unsigned int num_peripherals;
 	struct dma_pl330_chan *peripherals; /* keep at end */
+	int quirks;
+};
+
+static struct pl330_of_quirks {
+	char *quirk;
+	int id;
+} of_quirks[] = {
+	{
+		.quirk = "arm,pl330-broken-no-flushp",
+		.id = PL330_QUIRK_BROKEN_NO_FLUSHP,
+	}
 };
 
 struct dma_pl330_desc {
@@ -1137,47 +1151,67 @@ static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
 	return off;
 }
 
-static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
+static inline int _ldst_devtomem(struct pl330_dmac *pl330, unsigned dry_run,
+				 u8 buf[], const struct _xfer_spec *pxs,
+				 int cyc)
 {
 	int off = 0;
+	enum pl330_cond cond;
+
+	if (pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
+		cond = BURST;
+	else
+		cond = SINGLE;
 
 	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
-		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
+		off += _emit_WFP(dry_run, &buf[off], cond, pxs->desc->peri);
+		off += _emit_LDP(dry_run, &buf[off], cond, pxs->desc->peri);
 		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri);
+
+		if (!(pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP))
+			off += _emit_FLUSHP(dry_run, &buf[off],
+					    pxs->desc->peri);
 	}
 
 	return off;
 }
 
-static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
+static inline int _ldst_memtodev(struct pl330_dmac *pl330,
+				 unsigned dry_run, u8 buf[],
+				 const struct _xfer_spec *pxs, int cyc)
 {
 	int off = 0;
+	enum pl330_cond cond;
+
+	if (pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
+		cond = BURST;
+	else
+		cond = SINGLE;
 
 	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
+		off += _emit_WFP(dry_run, &buf[off], cond, pxs->desc->peri);
 		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri);
+		off += _emit_STP(dry_run, &buf[off], cond, pxs->desc->peri);
+
+		if (!(pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP))
+			off += _emit_FLUSHP(dry_run, &buf[off],
+					    pxs->desc->peri);
 	}
 
 	return off;
 }
 
-static int _bursts(unsigned dry_run, u8 buf[],
+static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 		const struct _xfer_spec *pxs, int cyc)
 {
 	int off = 0;
 
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
-		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
+		off += _ldst_memtodev(pl330, dry_run, &buf[off], pxs, cyc);
 		break;
 	case DMA_DEV_TO_MEM:
-		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
+		off += _ldst_devtomem(pl330, dry_run, &buf[off], pxs, cyc);
 		break;
 	case DMA_MEM_TO_MEM:
 		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
@@ -1191,7 +1225,7 @@ static int _bursts(unsigned dry_run, u8 buf[],
 }
 
 /* Returns bytes consumed and updates bursts */
-static inline int _loop(unsigned dry_run, u8 buf[],
+static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 		unsigned long *bursts, const struct _xfer_spec *pxs)
 {
 	int cyc, cycmax, szlp, szlpend, szbrst, off;
@@ -1199,7 +1233,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	struct _arg_LPEND lpend;
 
 	if (*bursts == 1)
-		return _bursts(dry_run, buf, pxs, 1);
+		return _bursts(pl330, dry_run, buf, pxs, 1);
 
 	/* Max iterations possible in DMALP is 256 */
 	if (*bursts >= 256*256) {
@@ -1217,7 +1251,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	}
 
 	szlp = _emit_LP(1, buf, 0, 0);
-	szbrst = _bursts(1, buf, pxs, 1);
+	szbrst = _bursts(pl330, 1, buf, pxs, 1);
 
 	lpend.cond = ALWAYS;
 	lpend.forever = false;
@@ -1249,7 +1283,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
 	ljmp1 = off;
 
-	off += _bursts(dry_run, &buf[off], pxs, cyc);
+	off += _bursts(pl330, dry_run, &buf[off], pxs, cyc);
 
 	lpend.cond = ALWAYS;
 	lpend.forever = false;
@@ -1272,8 +1306,9 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	return off;
 }
 
-static inline int _setup_loops(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
+static inline int _setup_loops(struct pl330_dmac *pl330,
+			       unsigned dry_run, u8 buf[],
+			       const struct _xfer_spec *pxs)
 {
 	struct pl330_xfer *x = &pxs->desc->px;
 	u32 ccr = pxs->ccr;
@@ -1282,15 +1317,16 @@ static inline int _setup_loops(unsigned dry_run, u8 buf[],
 
 	while (bursts) {
 		c = bursts;
-		off += _loop(dry_run, &buf[off], &c, pxs);
+		off += _loop(pl330, dry_run, &buf[off], &c, pxs);
 		bursts -= c;
 	}
 
 	return off;
 }
 
-static inline int _setup_xfer(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
+static inline int _setup_xfer(struct pl330_dmac *pl330,
+			      unsigned dry_run, u8 buf[],
+			      const struct _xfer_spec *pxs)
 {
 	struct pl330_xfer *x = &pxs->desc->px;
 	int off = 0;
@@ -1301,7 +1337,7 @@ static inline int _setup_xfer(unsigned dry_run, u8 buf[],
 	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
 
 	/* Setup Loop(s) */
-	off += _setup_loops(dry_run, &buf[off], pxs);
+	off += _setup_loops(pl330, dry_run, &buf[off], pxs);
 
 	return off;
 }
@@ -1310,8 +1346,9 @@ static inline int _setup_xfer(unsigned dry_run, u8 buf[],
  * A req is a sequence of one or more xfer units.
  * Returns the number of bytes taken to setup the MC for the req.
  */
-static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
-		unsigned index, struct _xfer_spec *pxs)
+static int _setup_req(struct pl330_dmac *pl330, unsigned dry_run,
+		      struct pl330_thread *thrd, unsigned index,
+		      struct _xfer_spec *pxs)
 {
 	struct _pl330_req *req = &thrd->req[index];
 	struct pl330_xfer *x;
@@ -1328,7 +1365,7 @@ static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
 	if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
 		return -EINVAL;
 
-	off += _setup_xfer(dry_run, &buf[off], pxs);
+	off += _setup_xfer(pl330, dry_run, &buf[off], pxs);
 
 	/* DMASEV peripheral/event */
 	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
@@ -1422,7 +1459,7 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 	xs.desc = desc;
 
 	/* First dry run to check if req is acceptable */
-	ret = _setup_req(1, thrd, idx, &xs);
+	ret = _setup_req(pl330, 1, thrd, idx, &xs);
 	if (ret < 0)
 		goto xfer_exit;
 
@@ -1436,7 +1473,7 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 	/* Hook the request */
 	thrd->lstenq = idx;
 	thrd->req[idx].desc = desc;
-	_setup_req(0, thrd, idx, &xs);
+	_setup_req(pl330, 0, thrd, idx, &xs);
 
 	ret = 0;
 
@@ -2781,6 +2818,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	struct resource *res;
 	int i, ret, irq;
 	int num_chan;
+	struct device_node *np = adev->dev.of_node;
 
 	pdat = dev_get_platdata(&adev->dev);
 
@@ -2800,6 +2838,11 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 
 	pl330->mcbufsz = pdat ? pdat->mcbuf_sz : 0;
 
+	/* get quirk */
+	for (i = 0; i < ARRAY_SIZE(of_quirks); i++)
+		if (of_property_read_bool(np, of_quirks[i].quirk))
+			pl330->quirks |= of_quirks[i].id;
+
 	res = &adev->res;
 	pl330->base = devm_ioremap_resource(&adev->dev, res);
 	if (IS_ERR(pl330->base))
@@ -2895,6 +2938,8 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pd->dst_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
+			 1 : PL330_MAX_BURST);
 
 	ret = dma_async_device_register(pd);
 	if (ret) {
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
new file mode 100644
index 000000000000..a7761c4025f4
--- /dev/null
+++ b/drivers/dma/qcom/Kconfig
@@ -0,0 +1,29 @@
+config QCOM_BAM_DMA
+	tristate "QCOM BAM DMA support"
+	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	---help---
+	  Enable support for the QCOM BAM DMA controller.  This controller
+	  provides DMA capabilities for a variety of on-chip devices.
+
+config QCOM_HIDMA_MGMT
+	tristate "Qualcomm Technologies HIDMA Management support"
+	select DMA_ENGINE
+	help
+	  Enable support for the Qualcomm Technologies HIDMA Management.
+	  Each DMA device requires one management interface driver
+	  for basic initialization before QCOM_HIDMA channel driver can
+	  start managing the channels. In a virtualized environment,
+	  the guest OS would run QCOM_HIDMA channel driver and the
+	  host would run the QCOM_HIDMA_MGMT management driver.
+
+config QCOM_HIDMA
+	tristate "Qualcomm Technologies HIDMA Channel support"
+	select DMA_ENGINE
+	help
+	  Enable support for the Qualcomm Technologies HIDMA controller.
+	  The HIDMA controller supports optimized buffer copies
+	  (user to kernel, kernel to kernel, etc.).  It only supports
+	  memcpy interface. The core is not intended for general
+	  purpose slave DMA.
diff --git a/drivers/dma/qcom/Makefile b/drivers/dma/qcom/Makefile
new file mode 100644
index 000000000000..bfea6990229f
--- /dev/null
+++ b/drivers/dma/qcom/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_QCOM_BAM_DMA) += bam_dma.o
+obj-$(CONFIG_QCOM_HIDMA_MGMT) += hdma_mgmt.o
+hdma_mgmt-objs	 := hidma_mgmt.o hidma_mgmt_sys.o
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom/bam_dma.c
index d34aef7a101b..d5e0a9c3ad5d 100644
--- a/drivers/dma/qcom_bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -49,13 +49,13 @@
 #include <linux/clk.h>
 #include <linux/dmaengine.h>
 
-#include "dmaengine.h"
-#include "virt-dma.h"
+#include "../dmaengine.h"
+#include "../virt-dma.h"
 
 struct bam_desc_hw {
-	u32 addr;		/* Buffer physical address */
-	u16 size;		/* Buffer size in bytes */
-	u16 flags;
+	__le32 addr;		/* Buffer physical address */
+	__le16 size;		/* Buffer size in bytes */
+	__le16 flags;
 };
 
 #define DESC_FLAG_INT BIT(15)
@@ -632,14 +632,15 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 		unsigned int curr_offset = 0;
 
 		do {
-			desc->addr = sg_dma_address(sg) + curr_offset;
+			desc->addr = cpu_to_le32(sg_dma_address(sg) +
+						 curr_offset);
 
 			if (remainder > BAM_MAX_DATA_SIZE) {
-				desc->size = BAM_MAX_DATA_SIZE;
+				desc->size = cpu_to_le16(BAM_MAX_DATA_SIZE);
 				remainder -= BAM_MAX_DATA_SIZE;
 				curr_offset += BAM_MAX_DATA_SIZE;
 			} else {
-				desc->size = remainder;
+				desc->size = cpu_to_le16(remainder);
 				remainder = 0;
 			}
 
@@ -915,9 +916,11 @@ static void bam_start_dma(struct bam_chan *bchan)
 
 	/* set any special flags on the last descriptor */
 	if (async_desc->num_desc == async_desc->xfer_len)
-		desc[async_desc->xfer_len - 1].flags = async_desc->flags;
+		desc[async_desc->xfer_len - 1].flags =
+					cpu_to_le16(async_desc->flags);
 	else
-		desc[async_desc->xfer_len - 1].flags |= DESC_FLAG_INT;
+		desc[async_desc->xfer_len - 1].flags |=
+					cpu_to_le16(DESC_FLAG_INT);
 
 	if (bchan->tail + async_desc->xfer_len > MAX_DESCRIPTORS) {
 		u32 partial = MAX_DESCRIPTORS - bchan->tail;
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
new file mode 100644
index 000000000000..cccc78efbca9
--- /dev/null
+++ b/drivers/dma/qcom/hidma.c
@@ -0,0 +1,706 @@
+/*
+ * Qualcomm Technologies HIDMA DMA engine interface
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008.
+ * Copyright (C) Semihalf 2009
+ * Copyright (C) Ilya Yanok, Emcraft Systems 2010
+ * Copyright (C) Alexander Popov, Promcontroller 2014
+ *
+ * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description
+ * (defines, structures and comments) was taken from MPC5121 DMA driver
+ * written by Hongjun Chen <hong-jun.chen@freescale.com>.
+ *
+ * Approved as OSADL project by a majority of OSADL members and funded
+ * by OSADL membership fees in 2009;  for details see www.osadl.org.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ */
+
+/* Linux Foundation elects GPLv2 license only. */
+
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of_dma.h>
+#include <linux/property.h>
+#include <linux/delay.h>
+#include <linux/acpi.h>
+#include <linux/irq.h>
+#include <linux/atomic.h>
+#include <linux/pm_runtime.h>
+
+#include "../dmaengine.h"
+#include "hidma.h"
+
+/*
+ * Default idle time is 2 seconds. This parameter can
+ * be overridden by changing the following
+ * /sys/bus/platform/devices/QCOM8061:<xy>/power/autosuspend_delay_ms
+ * during kernel boot.
+ */
+#define HIDMA_AUTOSUSPEND_TIMEOUT		2000
+#define HIDMA_ERR_INFO_SW			0xFF
+#define HIDMA_ERR_CODE_UNEXPECTED_TERMINATE	0x0
+#define HIDMA_NR_DEFAULT_DESC			10
+
+static inline struct hidma_dev *to_hidma_dev(struct dma_device *dmadev)
+{
+	return container_of(dmadev, struct hidma_dev, ddev);
+}
+
+static inline
+struct hidma_dev *to_hidma_dev_from_lldev(struct hidma_lldev **_lldevp)
+{
+	return container_of(_lldevp, struct hidma_dev, lldev);
+}
+
+static inline struct hidma_chan *to_hidma_chan(struct dma_chan *dmach)
+{
+	return container_of(dmach, struct hidma_chan, chan);
+}
+
+static inline
+struct hidma_desc *to_hidma_desc(struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct hidma_desc, desc);
+}
+
+static void hidma_free(struct hidma_dev *dmadev)
+{
+	INIT_LIST_HEAD(&dmadev->ddev.channels);
+}
+
+static unsigned int nr_desc_prm;
+module_param(nr_desc_prm, uint, 0644);
+MODULE_PARM_DESC(nr_desc_prm, "number of descriptors (default: 0)");
+
+
+/* process completed descriptors */
+static void hidma_process_completed(struct hidma_chan *mchan)
+{
+	struct dma_device *ddev = mchan->chan.device;
+	struct hidma_dev *mdma = to_hidma_dev(ddev);
+	struct dma_async_tx_descriptor *desc;
+	dma_cookie_t last_cookie;
+	struct hidma_desc *mdesc;
+	unsigned long irqflags;
+	struct list_head list;
+
+	INIT_LIST_HEAD(&list);
+
+	/* Get all completed descriptors */
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	list_splice_tail_init(&mchan->completed, &list);
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	/* Execute callbacks and run dependencies */
+	list_for_each_entry(mdesc, &list, node) {
+		enum dma_status llstat;
+
+		desc = &mdesc->desc;
+
+		spin_lock_irqsave(&mchan->lock, irqflags);
+		dma_cookie_complete(desc);
+		spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
+		if (desc->callback && (llstat == DMA_COMPLETE))
+			desc->callback(desc->callback_param);
+
+		last_cookie = desc->cookie;
+		dma_run_dependencies(desc);
+	}
+
+	/* Free descriptors */
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	list_splice_tail_init(&list, &mchan->free);
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+}
+
+/*
+ * Called once for each submitted descriptor.
+ * PM is locked once for each descriptor that is currently
+ * in execution.
+ */
+static void hidma_callback(void *data)
+{
+	struct hidma_desc *mdesc = data;
+	struct hidma_chan *mchan = to_hidma_chan(mdesc->desc.chan);
+	struct dma_device *ddev = mchan->chan.device;
+	struct hidma_dev *dmadev = to_hidma_dev(ddev);
+	unsigned long irqflags;
+	bool queued = false;
+
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	if (mdesc->node.next) {
+		/* Delete from the active list, add to completed list */
+		list_move_tail(&mdesc->node, &mchan->completed);
+		queued = true;
+
+		/* calculate the next running descriptor */
+		mchan->running = list_first_entry(&mchan->active,
+						  struct hidma_desc, node);
+	}
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	hidma_process_completed(mchan);
+
+	if (queued) {
+		pm_runtime_mark_last_busy(dmadev->ddev.dev);
+		pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	}
+}
+
+static int hidma_chan_init(struct hidma_dev *dmadev, u32 dma_sig)
+{
+	struct hidma_chan *mchan;
+	struct dma_device *ddev;
+
+	mchan = devm_kzalloc(dmadev->ddev.dev, sizeof(*mchan), GFP_KERNEL);
+	if (!mchan)
+		return -ENOMEM;
+
+	ddev = &dmadev->ddev;
+	mchan->dma_sig = dma_sig;
+	mchan->dmadev = dmadev;
+	mchan->chan.device = ddev;
+	dma_cookie_init(&mchan->chan);
+
+	INIT_LIST_HEAD(&mchan->free);
+	INIT_LIST_HEAD(&mchan->prepared);
+	INIT_LIST_HEAD(&mchan->active);
+	INIT_LIST_HEAD(&mchan->completed);
+
+	spin_lock_init(&mchan->lock);
+	list_add_tail(&mchan->chan.device_node, &ddev->channels);
+	dmadev->ddev.chancnt++;
+	return 0;
+}
+
+static void hidma_issue_task(unsigned long arg)
+{
+	struct hidma_dev *dmadev = (struct hidma_dev *)arg;
+
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	hidma_ll_start(dmadev->lldev);
+}
+
+static void hidma_issue_pending(struct dma_chan *dmach)
+{
+	struct hidma_chan *mchan = to_hidma_chan(dmach);
+	struct hidma_dev *dmadev = mchan->dmadev;
+	unsigned long flags;
+	int status;
+
+	spin_lock_irqsave(&mchan->lock, flags);
+	if (!mchan->running) {
+		struct hidma_desc *desc = list_first_entry(&mchan->active,
+							   struct hidma_desc,
+							   node);
+		mchan->running = desc;
+	}
+	spin_unlock_irqrestore(&mchan->lock, flags);
+
+	/* PM will be released in hidma_callback function. */
+	status = pm_runtime_get(dmadev->ddev.dev);
+	if (status < 0)
+		tasklet_schedule(&dmadev->task);
+	else
+		hidma_ll_start(dmadev->lldev);
+}
+
+static enum dma_status hidma_tx_status(struct dma_chan *dmach,
+				       dma_cookie_t cookie,
+				       struct dma_tx_state *txstate)
+{
+	struct hidma_chan *mchan = to_hidma_chan(dmach);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(dmach, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	if (mchan->paused && (ret == DMA_IN_PROGRESS)) {
+		unsigned long flags;
+		dma_cookie_t runcookie;
+
+		spin_lock_irqsave(&mchan->lock, flags);
+		if (mchan->running)
+			runcookie = mchan->running->desc.cookie;
+		else
+			runcookie = -EINVAL;
+
+		if (runcookie == cookie)
+			ret = DMA_PAUSED;
+
+		spin_unlock_irqrestore(&mchan->lock, flags);
+	}
+
+	return ret;
+}
+
+/*
+ * Submit descriptor to hardware.
+ * Lock the PM for each descriptor we are sending.
+ */
+static dma_cookie_t hidma_tx_submit(struct dma_async_tx_descriptor *txd)
+{
+	struct hidma_chan *mchan = to_hidma_chan(txd->chan);
+	struct hidma_dev *dmadev = mchan->dmadev;
+	struct hidma_desc *mdesc;
+	unsigned long irqflags;
+	dma_cookie_t cookie;
+
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	if (!hidma_ll_isenabled(dmadev->lldev)) {
+		pm_runtime_mark_last_busy(dmadev->ddev.dev);
+		pm_runtime_put_autosuspend(dmadev->ddev.dev);
+		return -ENODEV;
+	}
+
+	mdesc = container_of(txd, struct hidma_desc, desc);
+	spin_lock_irqsave(&mchan->lock, irqflags);
+
+	/* Move descriptor to active */
+	list_move_tail(&mdesc->node, &mchan->active);
+
+	/* Update cookie */
+	cookie = dma_cookie_assign(txd);
+
+	hidma_ll_queue_request(dmadev->lldev, mdesc->tre_ch);
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	return cookie;
+}
+
+static int hidma_alloc_chan_resources(struct dma_chan *dmach)
+{
+	struct hidma_chan *mchan = to_hidma_chan(dmach);
+	struct hidma_dev *dmadev = mchan->dmadev;
+	struct hidma_desc *mdesc, *tmp;
+	unsigned long irqflags;
+	LIST_HEAD(descs);
+	unsigned int i;
+	int rc = 0;
+
+	if (mchan->allocated)
+		return 0;
+
+	/* Alloc descriptors for this channel */
+	for (i = 0; i < dmadev->nr_descriptors; i++) {
+		mdesc = kzalloc(sizeof(struct hidma_desc), GFP_NOWAIT);
+		if (!mdesc) {
+			rc = -ENOMEM;
+			break;
+		}
+		dma_async_tx_descriptor_init(&mdesc->desc, dmach);
+		mdesc->desc.tx_submit = hidma_tx_submit;
+
+		rc = hidma_ll_request(dmadev->lldev, mchan->dma_sig,
+				      "DMA engine", hidma_callback, mdesc,
+				      &mdesc->tre_ch);
+		if (rc) {
+			dev_err(dmach->device->dev,
+				"channel alloc failed at %u\n", i);
+			kfree(mdesc);
+			break;
+		}
+		list_add_tail(&mdesc->node, &descs);
+	}
+
+	if (rc) {
+		/* return the allocated descriptors */
+		list_for_each_entry_safe(mdesc, tmp, &descs, node) {
+			hidma_ll_free(dmadev->lldev, mdesc->tre_ch);
+			kfree(mdesc);
+		}
+		return rc;
+	}
+
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	list_splice_tail_init(&descs, &mchan->free);
+	mchan->allocated = true;
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+	return 1;
+}
+
+static struct dma_async_tx_descriptor *
+hidma_prep_dma_memcpy(struct dma_chan *dmach, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct hidma_chan *mchan = to_hidma_chan(dmach);
+	struct hidma_desc *mdesc = NULL;
+	struct hidma_dev *mdma = mchan->dmadev;
+	unsigned long irqflags;
+
+	/* Get free descriptor */
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	if (!list_empty(&mchan->free)) {
+		mdesc = list_first_entry(&mchan->free, struct hidma_desc, node);
+		list_del(&mdesc->node);
+	}
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	if (!mdesc)
+		return NULL;
+
+	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
+				     src, dest, len, flags);
+
+	/* Place descriptor in prepared list */
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	list_add_tail(&mdesc->node, &mchan->prepared);
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	return &mdesc->desc;
+}
+
+static int hidma_terminate_channel(struct dma_chan *chan)
+{
+	struct hidma_chan *mchan = to_hidma_chan(chan);
+	struct hidma_dev *dmadev = to_hidma_dev(mchan->chan.device);
+	struct hidma_desc *tmp, *mdesc;
+	unsigned long irqflags;
+	LIST_HEAD(list);
+	int rc;
+
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	/* give completed requests a chance to finish */
+	hidma_process_completed(mchan);
+
+	spin_lock_irqsave(&mchan->lock, irqflags);
+	list_splice_init(&mchan->active, &list);
+	list_splice_init(&mchan->prepared, &list);
+	list_splice_init(&mchan->completed, &list);
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+
+	/* this suspends the existing transfer */
+	rc = hidma_ll_pause(dmadev->lldev);
+	if (rc) {
+		dev_err(dmadev->ddev.dev, "channel did not pause\n");
+		goto out;
+	}
+
+	/* return all user requests */
+	list_for_each_entry_safe(mdesc, tmp, &list, node) {
+		struct dma_async_tx_descriptor *txd = &mdesc->desc;
+		dma_async_tx_callback callback = mdesc->desc.callback;
+		void *param = mdesc->desc.callback_param;
+
+		dma_descriptor_unmap(txd);
+
+		if (callback)
+			callback(param);
+
+		dma_run_dependencies(txd);
+
+		/* move myself to free_list */
+		list_move(&mdesc->node, &mchan->free);
+	}
+
+	rc = hidma_ll_resume(dmadev->lldev);
+out:
+	pm_runtime_mark_last_busy(dmadev->ddev.dev);
+	pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	return rc;
+}
+
+static int hidma_terminate_all(struct dma_chan *chan)
+{
+	struct hidma_chan *mchan = to_hidma_chan(chan);
+	struct hidma_dev *dmadev = to_hidma_dev(mchan->chan.device);
+	int rc;
+
+	rc = hidma_terminate_channel(chan);
+	if (rc)
+		return rc;
+
+	/* reinitialize the hardware */
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	rc = hidma_ll_setup(dmadev->lldev);
+	pm_runtime_mark_last_busy(dmadev->ddev.dev);
+	pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	return rc;
+}
+
+static void hidma_free_chan_resources(struct dma_chan *dmach)
+{
+	struct hidma_chan *mchan = to_hidma_chan(dmach);
+	struct hidma_dev *mdma = mchan->dmadev;
+	struct hidma_desc *mdesc, *tmp;
+	unsigned long irqflags;
+	LIST_HEAD(descs);
+
+	/* terminate running transactions and free descriptors */
+	hidma_terminate_channel(dmach);
+
+	spin_lock_irqsave(&mchan->lock, irqflags);
+
+	/* Move data */
+	list_splice_tail_init(&mchan->free, &descs);
+
+	/* Free descriptors */
+	list_for_each_entry_safe(mdesc, tmp, &descs, node) {
+		hidma_ll_free(mdma->lldev, mdesc->tre_ch);
+		list_del(&mdesc->node);
+		kfree(mdesc);
+	}
+
+	mchan->allocated = 0;
+	spin_unlock_irqrestore(&mchan->lock, irqflags);
+}
+
+static int hidma_pause(struct dma_chan *chan)
+{
+	struct hidma_chan *mchan;
+	struct hidma_dev *dmadev;
+
+	mchan = to_hidma_chan(chan);
+	dmadev = to_hidma_dev(mchan->chan.device);
+	if (!mchan->paused) {
+		pm_runtime_get_sync(dmadev->ddev.dev);
+		if (hidma_ll_pause(dmadev->lldev))
+			dev_warn(dmadev->ddev.dev, "channel did not stop\n");
+		mchan->paused = true;
+		pm_runtime_mark_last_busy(dmadev->ddev.dev);
+		pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	}
+	return 0;
+}
+
+static int hidma_resume(struct dma_chan *chan)
+{
+	struct hidma_chan *mchan;
+	struct hidma_dev *dmadev;
+	int rc = 0;
+
+	mchan = to_hidma_chan(chan);
+	dmadev = to_hidma_dev(mchan->chan.device);
+	if (mchan->paused) {
+		pm_runtime_get_sync(dmadev->ddev.dev);
+		rc = hidma_ll_resume(dmadev->lldev);
+		if (!rc)
+			mchan->paused = false;
+		else
+			dev_err(dmadev->ddev.dev,
+				"failed to resume the channel");
+		pm_runtime_mark_last_busy(dmadev->ddev.dev);
+		pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	}
+	return rc;
+}
+
+static irqreturn_t hidma_chirq_handler(int chirq, void *arg)
+{
+	struct hidma_lldev *lldev = arg;
+
+	/*
+	 * All interrupts are request driven.
+	 * HW doesn't send an interrupt by itself.
+	 */
+	return hidma_ll_inthandler(chirq, lldev);
+}
+
+static int hidma_probe(struct platform_device *pdev)
+{
+	struct hidma_dev *dmadev;
+	struct resource *trca_resource;
+	struct resource *evca_resource;
+	int chirq;
+	void __iomem *evca;
+	void __iomem *trca;
+	int rc;
+
+	pm_runtime_set_autosuspend_delay(&pdev->dev, HIDMA_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	trca_resource = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	trca = devm_ioremap_resource(&pdev->dev, trca_resource);
+	if (IS_ERR(trca)) {
+		rc = -ENOMEM;
+		goto bailout;
+	}
+
+	evca_resource = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	evca = devm_ioremap_resource(&pdev->dev, evca_resource);
+	if (IS_ERR(evca)) {
+		rc = -ENOMEM;
+		goto bailout;
+	}
+
+	/*
+	 * This driver only handles the channel IRQs.
+	 * Common IRQ is handled by the management driver.
+	 */
+	chirq = platform_get_irq(pdev, 0);
+	if (chirq < 0) {
+		rc = -ENODEV;
+		goto bailout;
+	}
+
+	dmadev = devm_kzalloc(&pdev->dev, sizeof(*dmadev), GFP_KERNEL);
+	if (!dmadev) {
+		rc = -ENOMEM;
+		goto bailout;
+	}
+
+	INIT_LIST_HEAD(&dmadev->ddev.channels);
+	spin_lock_init(&dmadev->lock);
+	dmadev->ddev.dev = &pdev->dev;
+	pm_runtime_get_sync(dmadev->ddev.dev);
+
+	dma_cap_set(DMA_MEMCPY, dmadev->ddev.cap_mask);
+	if (WARN_ON(!pdev->dev.dma_mask)) {
+		rc = -ENXIO;
+		goto dmafree;
+	}
+
+	dmadev->dev_evca = evca;
+	dmadev->evca_resource = evca_resource;
+	dmadev->dev_trca = trca;
+	dmadev->trca_resource = trca_resource;
+	dmadev->ddev.device_prep_dma_memcpy = hidma_prep_dma_memcpy;
+	dmadev->ddev.device_alloc_chan_resources = hidma_alloc_chan_resources;
+	dmadev->ddev.device_free_chan_resources = hidma_free_chan_resources;
+	dmadev->ddev.device_tx_status = hidma_tx_status;
+	dmadev->ddev.device_issue_pending = hidma_issue_pending;
+	dmadev->ddev.device_pause = hidma_pause;
+	dmadev->ddev.device_resume = hidma_resume;
+	dmadev->ddev.device_terminate_all = hidma_terminate_all;
+	dmadev->ddev.copy_align = 8;
+
+	device_property_read_u32(&pdev->dev, "desc-count",
+				 &dmadev->nr_descriptors);
+
+	if (!dmadev->nr_descriptors && nr_desc_prm)
+		dmadev->nr_descriptors = nr_desc_prm;
+
+	if (!dmadev->nr_descriptors)
+		dmadev->nr_descriptors = HIDMA_NR_DEFAULT_DESC;
+
+	dmadev->chidx = readl(dmadev->dev_trca + 0x28);
+
+	/* Set DMA mask to 64 bits. */
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (rc) {
+		dev_warn(&pdev->dev, "unable to set coherent mask to 64");
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (rc)
+			goto dmafree;
+	}
+
+	dmadev->lldev = hidma_ll_init(dmadev->ddev.dev,
+				      dmadev->nr_descriptors, dmadev->dev_trca,
+				      dmadev->dev_evca, dmadev->chidx);
+	if (!dmadev->lldev) {
+		rc = -EPROBE_DEFER;
+		goto dmafree;
+	}
+
+	rc = devm_request_irq(&pdev->dev, chirq, hidma_chirq_handler, 0,
+			      "qcom-hidma", dmadev->lldev);
+	if (rc)
+		goto uninit;
+
+	INIT_LIST_HEAD(&dmadev->ddev.channels);
+	rc = hidma_chan_init(dmadev, 0);
+	if (rc)
+		goto uninit;
+
+	rc = dma_async_device_register(&dmadev->ddev);
+	if (rc)
+		goto uninit;
+
+	dmadev->irq = chirq;
+	tasklet_init(&dmadev->task, hidma_issue_task, (unsigned long)dmadev);
+	dev_info(&pdev->dev, "HI-DMA engine driver registration complete\n");
+	platform_set_drvdata(pdev, dmadev);
+	pm_runtime_mark_last_busy(dmadev->ddev.dev);
+	pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	return 0;
+
+uninit:
+	hidma_ll_uninit(dmadev->lldev);
+dmafree:
+	if (dmadev)
+		hidma_free(dmadev);
+bailout:
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return rc;
+}
+
+static int hidma_remove(struct platform_device *pdev)
+{
+	struct hidma_dev *dmadev = platform_get_drvdata(pdev);
+
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	dma_async_device_unregister(&dmadev->ddev);
+	devm_free_irq(dmadev->ddev.dev, dmadev->irq, dmadev->lldev);
+	hidma_ll_uninit(dmadev->lldev);
+	hidma_free(dmadev);
+
+	dev_info(&pdev->dev, "HI-DMA engine removed\n");
+	pm_runtime_put_sync_suspend(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_ACPI)
+static const struct acpi_device_id hidma_acpi_ids[] = {
+	{"QCOM8061"},
+	{},
+};
+#endif
+
+static const struct of_device_id hidma_match[] = {
+	{.compatible = "qcom,hidma-1.0",},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, hidma_match);
+
+static struct platform_driver hidma_driver = {
+	.probe = hidma_probe,
+	.remove = hidma_remove,
+	.driver = {
+		   .name = "hidma",
+		   .of_match_table = hidma_match,
+		   .acpi_match_table = ACPI_PTR(hidma_acpi_ids),
+	},
+};
+
+module_platform_driver(hidma_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/qcom/hidma.h b/drivers/dma/qcom/hidma.h
new file mode 100644
index 000000000000..231e306f6d87
--- /dev/null
+++ b/drivers/dma/qcom/hidma.h
@@ -0,0 +1,160 @@
+/*
+ * Qualcomm Technologies HIDMA data structures
+ *
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef QCOM_HIDMA_H
+#define QCOM_HIDMA_H
+
+#include <linux/kfifo.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+
+#define TRE_SIZE			32 /* each TRE is 32 bytes  */
+#define TRE_CFG_IDX			0
+#define TRE_LEN_IDX			1
+#define TRE_SRC_LOW_IDX		2
+#define TRE_SRC_HI_IDX			3
+#define TRE_DEST_LOW_IDX		4
+#define TRE_DEST_HI_IDX		5
+
+struct hidma_tx_status {
+	u8 err_info;			/* error record in this transfer    */
+	u8 err_code;			/* completion code		    */
+};
+
+struct hidma_tre {
+	atomic_t allocated;		/* if this channel is allocated	    */
+	bool queued;			/* flag whether this is pending     */
+	u16 status;			/* status			    */
+	u32 chidx;			/* index of the tre		    */
+	u32 dma_sig;			/* signature of the tre		    */
+	const char *dev_name;		/* name of the device		    */
+	void (*callback)(void *data);	/* requester callback		    */
+	void *data;			/* Data associated with this channel*/
+	struct hidma_lldev *lldev;	/* lldma device pointer		    */
+	u32 tre_local[TRE_SIZE / sizeof(u32) + 1]; /* TRE local copy        */
+	u32 tre_index;			/* the offset where this was written*/
+	u32 int_flags;			/* interrupt flags		    */
+};
+
+struct hidma_lldev {
+	bool initialized;		/* initialized flag               */
+	u8 trch_state;			/* trch_state of the device	  */
+	u8 evch_state;			/* evch_state of the device	  */
+	u8 chidx;			/* channel index in the core	  */
+	u32 nr_tres;			/* max number of configs          */
+	spinlock_t lock;		/* reentrancy                     */
+	struct hidma_tre *trepool;	/* trepool of user configs */
+	struct device *dev;		/* device			  */
+	void __iomem *trca;		/* Transfer Channel address       */
+	void __iomem *evca;		/* Event Channel address          */
+	struct hidma_tre
+		**pending_tre_list;	/* Pointers to pending TREs	  */
+	struct hidma_tx_status
+		*tx_status_list;	/* Pointers to pending TREs status*/
+	s32 pending_tre_count;		/* Number of TREs pending	  */
+
+	void *tre_ring;			/* TRE ring			  */
+	dma_addr_t tre_ring_handle;	/* TRE ring to be shared with HW  */
+	u32 tre_ring_size;		/* Byte size of the ring	  */
+	u32 tre_processed_off;		/* last processed TRE		  */
+
+	void *evre_ring;		/* EVRE ring			   */
+	dma_addr_t evre_ring_handle;	/* EVRE ring to be shared with HW  */
+	u32 evre_ring_size;		/* Byte size of the ring	   */
+	u32 evre_processed_off;		/* last processed EVRE		   */
+
+	u32 tre_write_offset;           /* TRE write location              */
+	struct tasklet_struct task;	/* task delivering notifications   */
+	DECLARE_KFIFO_PTR(handoff_fifo,
+		struct hidma_tre *);    /* pending TREs FIFO               */
+};
+
+struct hidma_desc {
+	struct dma_async_tx_descriptor	desc;
+	/* link list node for this channel*/
+	struct list_head		node;
+	u32				tre_ch;
+};
+
+struct hidma_chan {
+	bool				paused;
+	bool				allocated;
+	char				dbg_name[16];
+	u32				dma_sig;
+
+	/*
+	 * active descriptor on this channel
+	 * It is used by the DMA complete notification to
+	 * locate the descriptor that initiated the transfer.
+	 */
+	struct dentry			*debugfs;
+	struct dentry			*stats;
+	struct hidma_dev		*dmadev;
+	struct hidma_desc		*running;
+
+	struct dma_chan			chan;
+	struct list_head		free;
+	struct list_head		prepared;
+	struct list_head		active;
+	struct list_head		completed;
+
+	/* Lock for this structure */
+	spinlock_t			lock;
+};
+
+struct hidma_dev {
+	int				irq;
+	int				chidx;
+	u32				nr_descriptors;
+
+	struct hidma_lldev		*lldev;
+	void				__iomem *dev_trca;
+	struct resource			*trca_resource;
+	void				__iomem *dev_evca;
+	struct resource			*evca_resource;
+
+	/* used to protect the pending channel list*/
+	spinlock_t			lock;
+	struct dma_device		ddev;
+
+	struct dentry			*debugfs;
+	struct dentry			*stats;
+
+	/* Task delivering issue_pending */
+	struct tasklet_struct		task;
+};
+
+int hidma_ll_request(struct hidma_lldev *llhndl, u32 dev_id,
+			const char *dev_name,
+			void (*callback)(void *data), void *data, u32 *tre_ch);
+
+void hidma_ll_free(struct hidma_lldev *llhndl, u32 tre_ch);
+enum dma_status hidma_ll_status(struct hidma_lldev *llhndl, u32 tre_ch);
+bool hidma_ll_isenabled(struct hidma_lldev *llhndl);
+void hidma_ll_queue_request(struct hidma_lldev *llhndl, u32 tre_ch);
+void hidma_ll_start(struct hidma_lldev *llhndl);
+int hidma_ll_pause(struct hidma_lldev *llhndl);
+int hidma_ll_resume(struct hidma_lldev *llhndl);
+void hidma_ll_set_transfer_params(struct hidma_lldev *llhndl, u32 tre_ch,
+	dma_addr_t src, dma_addr_t dest, u32 len, u32 flags);
+int hidma_ll_setup(struct hidma_lldev *lldev);
+struct hidma_lldev *hidma_ll_init(struct device *dev, u32 max_channels,
+			void __iomem *trca, void __iomem *evca,
+			u8 chidx);
+int hidma_ll_uninit(struct hidma_lldev *llhndl);
+irqreturn_t hidma_ll_inthandler(int irq, void *arg);
+void hidma_cleanup_pending_tre(struct hidma_lldev *llhndl, u8 err_info,
+				u8 err_code);
+#endif
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
new file mode 100644
index 000000000000..ef491b893f40
--- /dev/null
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -0,0 +1,302 @@
+/*
+ * Qualcomm Technologies HIDMA DMA engine Management interface
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/acpi.h>
+#include <linux/of.h>
+#include <linux/property.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/bitops.h>
+
+#include "hidma_mgmt.h"
+
+#define HIDMA_QOS_N_OFFSET		0x300
+#define HIDMA_CFG_OFFSET		0x400
+#define HIDMA_MAX_BUS_REQ_LEN_OFFSET	0x41C
+#define HIDMA_MAX_XACTIONS_OFFSET	0x420
+#define HIDMA_HW_VERSION_OFFSET	0x424
+#define HIDMA_CHRESET_TIMEOUT_OFFSET	0x418
+
+#define HIDMA_MAX_WR_XACTIONS_MASK	GENMASK(4, 0)
+#define HIDMA_MAX_RD_XACTIONS_MASK	GENMASK(4, 0)
+#define HIDMA_WEIGHT_MASK		GENMASK(6, 0)
+#define HIDMA_MAX_BUS_REQ_LEN_MASK	GENMASK(15, 0)
+#define HIDMA_CHRESET_TIMEOUT_MASK	GENMASK(19, 0)
+
+#define HIDMA_MAX_WR_XACTIONS_BIT_POS	16
+#define HIDMA_MAX_BUS_WR_REQ_BIT_POS	16
+#define HIDMA_WRR_BIT_POS		8
+#define HIDMA_PRIORITY_BIT_POS		15
+
+#define HIDMA_AUTOSUSPEND_TIMEOUT	2000
+#define HIDMA_MAX_CHANNEL_WEIGHT	15
+
+int hidma_mgmt_setup(struct hidma_mgmt_dev *mgmtdev)
+{
+	unsigned int i;
+	u32 val;
+
+	if (!is_power_of_2(mgmtdev->max_write_request) ||
+	    (mgmtdev->max_write_request < 128) ||
+	    (mgmtdev->max_write_request > 1024)) {
+		dev_err(&mgmtdev->pdev->dev, "invalid write request %d\n",
+			mgmtdev->max_write_request);
+		return -EINVAL;
+	}
+
+	if (!is_power_of_2(mgmtdev->max_read_request) ||
+	    (mgmtdev->max_read_request < 128) ||
+	    (mgmtdev->max_read_request > 1024)) {
+		dev_err(&mgmtdev->pdev->dev, "invalid read request %d\n",
+			mgmtdev->max_read_request);
+		return -EINVAL;
+	}
+
+	if (mgmtdev->max_wr_xactions > HIDMA_MAX_WR_XACTIONS_MASK) {
+		dev_err(&mgmtdev->pdev->dev,
+			"max_wr_xactions cannot be bigger than %ld\n",
+			HIDMA_MAX_WR_XACTIONS_MASK);
+		return -EINVAL;
+	}
+
+	if (mgmtdev->max_rd_xactions > HIDMA_MAX_RD_XACTIONS_MASK) {
+		dev_err(&mgmtdev->pdev->dev,
+			"max_rd_xactions cannot be bigger than %ld\n",
+			HIDMA_MAX_RD_XACTIONS_MASK);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < mgmtdev->dma_channels; i++) {
+		if (mgmtdev->priority[i] > 1) {
+			dev_err(&mgmtdev->pdev->dev,
+				"priority can be 0 or 1\n");
+			return -EINVAL;
+		}
+
+		if (mgmtdev->weight[i] > HIDMA_MAX_CHANNEL_WEIGHT) {
+			dev_err(&mgmtdev->pdev->dev,
+				"max value of weight can be %d.\n",
+				HIDMA_MAX_CHANNEL_WEIGHT);
+			return -EINVAL;
+		}
+
+		/* weight needs to be at least one */
+		if (mgmtdev->weight[i] == 0)
+			mgmtdev->weight[i] = 1;
+	}
+
+	pm_runtime_get_sync(&mgmtdev->pdev->dev);
+	val = readl(mgmtdev->virtaddr + HIDMA_MAX_BUS_REQ_LEN_OFFSET);
+	val &= ~(HIDMA_MAX_BUS_REQ_LEN_MASK << HIDMA_MAX_BUS_WR_REQ_BIT_POS);
+	val |= mgmtdev->max_write_request << HIDMA_MAX_BUS_WR_REQ_BIT_POS;
+	val &= ~HIDMA_MAX_BUS_REQ_LEN_MASK;
+	val |= mgmtdev->max_read_request;
+	writel(val, mgmtdev->virtaddr + HIDMA_MAX_BUS_REQ_LEN_OFFSET);
+
+	val = readl(mgmtdev->virtaddr + HIDMA_MAX_XACTIONS_OFFSET);
+	val &= ~(HIDMA_MAX_WR_XACTIONS_MASK << HIDMA_MAX_WR_XACTIONS_BIT_POS);
+	val |= mgmtdev->max_wr_xactions << HIDMA_MAX_WR_XACTIONS_BIT_POS;
+	val &= ~HIDMA_MAX_RD_XACTIONS_MASK;
+	val |= mgmtdev->max_rd_xactions;
+	writel(val, mgmtdev->virtaddr + HIDMA_MAX_XACTIONS_OFFSET);
+
+	mgmtdev->hw_version =
+	    readl(mgmtdev->virtaddr + HIDMA_HW_VERSION_OFFSET);
+	mgmtdev->hw_version_major = (mgmtdev->hw_version >> 28) & 0xF;
+	mgmtdev->hw_version_minor = (mgmtdev->hw_version >> 16) & 0xF;
+
+	for (i = 0; i < mgmtdev->dma_channels; i++) {
+		u32 weight = mgmtdev->weight[i];
+		u32 priority = mgmtdev->priority[i];
+
+		val = readl(mgmtdev->virtaddr + HIDMA_QOS_N_OFFSET + (4 * i));
+		val &= ~(1 << HIDMA_PRIORITY_BIT_POS);
+		val |= (priority & 0x1) << HIDMA_PRIORITY_BIT_POS;
+		val &= ~(HIDMA_WEIGHT_MASK << HIDMA_WRR_BIT_POS);
+		val |= (weight & HIDMA_WEIGHT_MASK) << HIDMA_WRR_BIT_POS;
+		writel(val, mgmtdev->virtaddr + HIDMA_QOS_N_OFFSET + (4 * i));
+	}
+
+	val = readl(mgmtdev->virtaddr + HIDMA_CHRESET_TIMEOUT_OFFSET);
+	val &= ~HIDMA_CHRESET_TIMEOUT_MASK;
+	val |= mgmtdev->chreset_timeout_cycles & HIDMA_CHRESET_TIMEOUT_MASK;
+	writel(val, mgmtdev->virtaddr + HIDMA_CHRESET_TIMEOUT_OFFSET);
+
+	pm_runtime_mark_last_busy(&mgmtdev->pdev->dev);
+	pm_runtime_put_autosuspend(&mgmtdev->pdev->dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hidma_mgmt_setup);
+
+static int hidma_mgmt_probe(struct platform_device *pdev)
+{
+	struct hidma_mgmt_dev *mgmtdev;
+	struct resource *res;
+	void __iomem *virtaddr;
+	int irq;
+	int rc;
+	u32 val;
+
+	pm_runtime_set_autosuspend_delay(&pdev->dev, HIDMA_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	virtaddr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(virtaddr)) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "irq resources not found\n");
+		rc = irq;
+		goto out;
+	}
+
+	mgmtdev = devm_kzalloc(&pdev->dev, sizeof(*mgmtdev), GFP_KERNEL);
+	if (!mgmtdev) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	mgmtdev->pdev = pdev;
+	mgmtdev->addrsize = resource_size(res);
+	mgmtdev->virtaddr = virtaddr;
+
+	rc = device_property_read_u32(&pdev->dev, "dma-channels",
+				      &mgmtdev->dma_channels);
+	if (rc) {
+		dev_err(&pdev->dev, "number of channels missing\n");
+		goto out;
+	}
+
+	rc = device_property_read_u32(&pdev->dev,
+				      "channel-reset-timeout-cycles",
+				      &mgmtdev->chreset_timeout_cycles);
+	if (rc) {
+		dev_err(&pdev->dev, "channel reset timeout missing\n");
+		goto out;
+	}
+
+	rc = device_property_read_u32(&pdev->dev, "max-write-burst-bytes",
+				      &mgmtdev->max_write_request);
+	if (rc) {
+		dev_err(&pdev->dev, "max-write-burst-bytes missing\n");
+		goto out;
+	}
+
+	rc = device_property_read_u32(&pdev->dev, "max-read-burst-bytes",
+				      &mgmtdev->max_read_request);
+	if (rc) {
+		dev_err(&pdev->dev, "max-read-burst-bytes missing\n");
+		goto out;
+	}
+
+	rc = device_property_read_u32(&pdev->dev, "max-write-transactions",
+				      &mgmtdev->max_wr_xactions);
+	if (rc) {
+		dev_err(&pdev->dev, "max-write-transactions missing\n");
+		goto out;
+	}
+
+	rc = device_property_read_u32(&pdev->dev, "max-read-transactions",
+				      &mgmtdev->max_rd_xactions);
+	if (rc) {
+		dev_err(&pdev->dev, "max-read-transactions missing\n");
+		goto out;
+	}
+
+	mgmtdev->priority = devm_kcalloc(&pdev->dev,
+					 mgmtdev->dma_channels,
+					 sizeof(*mgmtdev->priority),
+					 GFP_KERNEL);
+	if (!mgmtdev->priority) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	mgmtdev->weight = devm_kcalloc(&pdev->dev,
+				       mgmtdev->dma_channels,
+				       sizeof(*mgmtdev->weight), GFP_KERNEL);
+	if (!mgmtdev->weight) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	rc = hidma_mgmt_setup(mgmtdev);
+	if (rc) {
+		dev_err(&pdev->dev, "setup failed\n");
+		goto out;
+	}
+
+	/* start the HW */
+	val = readl(mgmtdev->virtaddr + HIDMA_CFG_OFFSET);
+	val |= 1;
+	writel(val, mgmtdev->virtaddr + HIDMA_CFG_OFFSET);
+
+	rc = hidma_mgmt_init_sys(mgmtdev);
+	if (rc) {
+		dev_err(&pdev->dev, "sysfs setup failed\n");
+		goto out;
+	}
+
+	dev_info(&pdev->dev,
+		 "HW rev: %d.%d @ %pa with %d physical channels\n",
+		 mgmtdev->hw_version_major, mgmtdev->hw_version_minor,
+		 &res->start, mgmtdev->dma_channels);
+
+	platform_set_drvdata(pdev, mgmtdev);
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+	return 0;
+out:
+	pm_runtime_put_sync_suspend(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return rc;
+}
+
+#if IS_ENABLED(CONFIG_ACPI)
+static const struct acpi_device_id hidma_mgmt_acpi_ids[] = {
+	{"QCOM8060"},
+	{},
+};
+#endif
+
+static const struct of_device_id hidma_mgmt_match[] = {
+	{.compatible = "qcom,hidma-mgmt-1.0",},
+	{},
+};
+MODULE_DEVICE_TABLE(of, hidma_mgmt_match);
+
+static struct platform_driver hidma_mgmt_driver = {
+	.probe = hidma_mgmt_probe,
+	.driver = {
+		   .name = "hidma-mgmt",
+		   .of_match_table = hidma_mgmt_match,
+		   .acpi_match_table = ACPI_PTR(hidma_mgmt_acpi_ids),
+	},
+};
+
+module_platform_driver(hidma_mgmt_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/qcom/hidma_mgmt.h b/drivers/dma/qcom/hidma_mgmt.h
new file mode 100644
index 000000000000..f7daf33769f4
--- /dev/null
+++ b/drivers/dma/qcom/hidma_mgmt.h
@@ -0,0 +1,39 @@
+/*
+ * Qualcomm Technologies HIDMA Management common header
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+struct hidma_mgmt_dev {
+	u8 hw_version_major;
+	u8 hw_version_minor;
+
+	u32 max_wr_xactions;
+	u32 max_rd_xactions;
+	u32 max_write_request;
+	u32 max_read_request;
+	u32 dma_channels;
+	u32 chreset_timeout_cycles;
+	u32 hw_version;
+	u32 *priority;
+	u32 *weight;
+
+	/* Hardware device constants */
+	void __iomem *virtaddr;
+	resource_size_t addrsize;
+
+	struct kobject **chroots;
+	struct platform_device *pdev;
+};
+
+int hidma_mgmt_init_sys(struct hidma_mgmt_dev *dev);
+int hidma_mgmt_setup(struct hidma_mgmt_dev *mgmtdev);
diff --git a/drivers/dma/qcom/hidma_mgmt_sys.c b/drivers/dma/qcom/hidma_mgmt_sys.c
new file mode 100644
index 000000000000..d61f1068a34b
--- /dev/null
+++ b/drivers/dma/qcom/hidma_mgmt_sys.c
@@ -0,0 +1,295 @@
+/*
+ * Qualcomm Technologies HIDMA Management SYS interface
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/sysfs.h>
+#include <linux/platform_device.h>
+
+#include "hidma_mgmt.h"
+
+struct hidma_chan_attr {
+	struct hidma_mgmt_dev *mdev;
+	int index;
+	struct kobj_attribute attr;
+};
+
+struct hidma_mgmt_fileinfo {
+	char *name;
+	int mode;
+	int (*get)(struct hidma_mgmt_dev *mdev);
+	int (*set)(struct hidma_mgmt_dev *mdev, u64 val);
+};
+
+#define IMPLEMENT_GETSET(name)					\
+static int get_##name(struct hidma_mgmt_dev *mdev)		\
+{								\
+	return mdev->name;					\
+}								\
+static int set_##name(struct hidma_mgmt_dev *mdev, u64 val)	\
+{								\
+	u64 tmp;						\
+	int rc;							\
+								\
+	tmp = mdev->name;					\
+	mdev->name = val;					\
+	rc = hidma_mgmt_setup(mdev);				\
+	if (rc)							\
+		mdev->name = tmp;				\
+	return rc;						\
+}
+
+#define DECLARE_ATTRIBUTE(name, mode)				\
+	{#name, mode, get_##name, set_##name}
+
+IMPLEMENT_GETSET(hw_version_major)
+IMPLEMENT_GETSET(hw_version_minor)
+IMPLEMENT_GETSET(max_wr_xactions)
+IMPLEMENT_GETSET(max_rd_xactions)
+IMPLEMENT_GETSET(max_write_request)
+IMPLEMENT_GETSET(max_read_request)
+IMPLEMENT_GETSET(dma_channels)
+IMPLEMENT_GETSET(chreset_timeout_cycles)
+
+static int set_priority(struct hidma_mgmt_dev *mdev, unsigned int i, u64 val)
+{
+	u64 tmp;
+	int rc;
+
+	if (i >= mdev->dma_channels)
+		return -EINVAL;
+
+	tmp = mdev->priority[i];
+	mdev->priority[i] = val;
+	rc = hidma_mgmt_setup(mdev);
+	if (rc)
+		mdev->priority[i] = tmp;
+	return rc;
+}
+
+static int set_weight(struct hidma_mgmt_dev *mdev, unsigned int i, u64 val)
+{
+	u64 tmp;
+	int rc;
+
+	if (i >= mdev->dma_channels)
+		return -EINVAL;
+
+	tmp = mdev->weight[i];
+	mdev->weight[i] = val;
+	rc = hidma_mgmt_setup(mdev);
+	if (rc)
+		mdev->weight[i] = tmp;
+	return rc;
+}
+
+static struct hidma_mgmt_fileinfo hidma_mgmt_files[] = {
+	DECLARE_ATTRIBUTE(hw_version_major, S_IRUGO),
+	DECLARE_ATTRIBUTE(hw_version_minor, S_IRUGO),
+	DECLARE_ATTRIBUTE(dma_channels, S_IRUGO),
+	DECLARE_ATTRIBUTE(chreset_timeout_cycles, S_IRUGO),
+	DECLARE_ATTRIBUTE(max_wr_xactions, S_IRUGO),
+	DECLARE_ATTRIBUTE(max_rd_xactions, S_IRUGO),
+	DECLARE_ATTRIBUTE(max_write_request, S_IRUGO),
+	DECLARE_ATTRIBUTE(max_read_request, S_IRUGO),
+};
+
+static ssize_t show_values(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct hidma_mgmt_dev *mdev = platform_get_drvdata(pdev);
+	unsigned int i;
+
+	buf[0] = 0;
+
+	for (i = 0; i < ARRAY_SIZE(hidma_mgmt_files); i++) {
+		if (strcmp(attr->attr.name, hidma_mgmt_files[i].name) == 0) {
+			sprintf(buf, "%d\n", hidma_mgmt_files[i].get(mdev));
+			break;
+		}
+	}
+	return strlen(buf);
+}
+
+static ssize_t set_values(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct hidma_mgmt_dev *mdev = platform_get_drvdata(pdev);
+	unsigned long tmp;
+	unsigned int i;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &tmp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < ARRAY_SIZE(hidma_mgmt_files); i++) {
+		if (strcmp(attr->attr.name, hidma_mgmt_files[i].name) == 0) {
+			rc = hidma_mgmt_files[i].set(mdev, tmp);
+			if (rc)
+				return rc;
+
+			break;
+		}
+	}
+	return count;
+}
+
+static ssize_t show_values_channel(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *buf)
+{
+	struct hidma_chan_attr *chattr;
+	struct hidma_mgmt_dev *mdev;
+
+	buf[0] = 0;
+	chattr = container_of(attr, struct hidma_chan_attr, attr);
+	mdev = chattr->mdev;
+	if (strcmp(attr->attr.name, "priority") == 0)
+		sprintf(buf, "%d\n", mdev->priority[chattr->index]);
+	else if (strcmp(attr->attr.name, "weight") == 0)
+		sprintf(buf, "%d\n", mdev->weight[chattr->index]);
+
+	return strlen(buf);
+}
+
+static ssize_t set_values_channel(struct kobject *kobj,
+				  struct kobj_attribute *attr, const char *buf,
+				  size_t count)
+{
+	struct hidma_chan_attr *chattr;
+	struct hidma_mgmt_dev *mdev;
+	unsigned long tmp;
+	int rc;
+
+	chattr = container_of(attr, struct hidma_chan_attr, attr);
+	mdev = chattr->mdev;
+
+	rc = kstrtoul(buf, 0, &tmp);
+	if (rc)
+		return rc;
+
+	if (strcmp(attr->attr.name, "priority") == 0) {
+		rc = set_priority(mdev, chattr->index, tmp);
+		if (rc)
+			return rc;
+	} else if (strcmp(attr->attr.name, "weight") == 0) {
+		rc = set_weight(mdev, chattr->index, tmp);
+		if (rc)
+			return rc;
+	}
+	return count;
+}
+
+static int create_sysfs_entry(struct hidma_mgmt_dev *dev, char *name, int mode)
+{
+	struct device_attribute *attrs;
+	char *name_copy;
+
+	attrs = devm_kmalloc(&dev->pdev->dev,
+			     sizeof(struct device_attribute), GFP_KERNEL);
+	if (!attrs)
+		return -ENOMEM;
+
+	name_copy = devm_kstrdup(&dev->pdev->dev, name, GFP_KERNEL);
+	if (!name_copy)
+		return -ENOMEM;
+
+	attrs->attr.name = name_copy;
+	attrs->attr.mode = mode;
+	attrs->show = show_values;
+	attrs->store = set_values;
+	sysfs_attr_init(&attrs->attr);
+
+	return device_create_file(&dev->pdev->dev, attrs);
+}
+
+static int create_sysfs_entry_channel(struct hidma_mgmt_dev *mdev, char *name,
+				      int mode, int index,
+				      struct kobject *parent)
+{
+	struct hidma_chan_attr *chattr;
+	char *name_copy;
+
+	chattr = devm_kmalloc(&mdev->pdev->dev, sizeof(*chattr), GFP_KERNEL);
+	if (!chattr)
+		return -ENOMEM;
+
+	name_copy = devm_kstrdup(&mdev->pdev->dev, name, GFP_KERNEL);
+	if (!name_copy)
+		return -ENOMEM;
+
+	chattr->mdev = mdev;
+	chattr->index = index;
+	chattr->attr.attr.name = name_copy;
+	chattr->attr.attr.mode = mode;
+	chattr->attr.show = show_values_channel;
+	chattr->attr.store = set_values_channel;
+	sysfs_attr_init(&chattr->attr.attr);
+
+	return sysfs_create_file(parent, &chattr->attr.attr);
+}
+
+int hidma_mgmt_init_sys(struct hidma_mgmt_dev *mdev)
+{
+	unsigned int i;
+	int rc;
+	int required;
+	struct kobject *chanops;
+
+	required = sizeof(*mdev->chroots) * mdev->dma_channels;
+	mdev->chroots = devm_kmalloc(&mdev->pdev->dev, required, GFP_KERNEL);
+	if (!mdev->chroots)
+		return -ENOMEM;
+
+	chanops = kobject_create_and_add("chanops", &mdev->pdev->dev.kobj);
+	if (!chanops)
+		return -ENOMEM;
+
+	/* create each channel directory here */
+	for (i = 0; i < mdev->dma_channels; i++) {
+		char name[20];
+
+		snprintf(name, sizeof(name), "chan%d", i);
+		mdev->chroots[i] = kobject_create_and_add(name, chanops);
+		if (!mdev->chroots[i])
+			return -ENOMEM;
+	}
+
+	/* populate common parameters */
+	for (i = 0; i < ARRAY_SIZE(hidma_mgmt_files); i++) {
+		rc = create_sysfs_entry(mdev, hidma_mgmt_files[i].name,
+					hidma_mgmt_files[i].mode);
+		if (rc)
+			return rc;
+	}
+
+	/* populate parameters that are per channel */
+	for (i = 0; i < mdev->dma_channels; i++) {
+		rc = create_sysfs_entry_channel(mdev, "priority",
+						(S_IRUGO | S_IWUGO), i,
+						mdev->chroots[i]);
+		if (rc)
+			return rc;
+
+		rc = create_sysfs_entry_channel(mdev, "weight",
+						(S_IRUGO | S_IWUGO), i,
+						mdev->chroots[i]);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hidma_mgmt_init_sys);
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index f32c430eb16c..6e0685f1a838 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -12,7 +12,7 @@ config RENESAS_DMA
 
 config SH_DMAE_BASE
 	bool "Renesas SuperH DMA Engine support"
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	depends on !SUPERH || SH_DMA
 	depends on !SH_DMA_API
 	default y
@@ -41,7 +41,7 @@ endif
 
 config RCAR_DMAC
 	tristate "Renesas R-Car Gen2 DMA Controller"
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	select RENESAS_DMA
 	help
 	  This driver supports the general purpose DMA controller found in the
@@ -49,7 +49,7 @@ config RCAR_DMAC
 
 config RENESAS_USB_DMAC
 	tristate "Renesas USB-DMA Controller"
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	select RENESAS_DMA
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 7820d07e7bee..dfb17926297b 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -413,7 +413,7 @@ static int rcar_dmac_init(struct rcar_dmac *dmac)
 	u16 dmaor;
 
 	/* Clear all channels and enable the DMAC globally. */
-	rcar_dmac_write(dmac, RCAR_DMACHCLR, 0x7fff);
+	rcar_dmac_write(dmac, RCAR_DMACHCLR, GENMASK(dmac->n_channels - 1, 0));
 	rcar_dmac_write(dmac, RCAR_DMAOR,
 			RCAR_DMAOR_PRI_FIXED | RCAR_DMAOR_DME);
 
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 11707df1a689..80d86402490e 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -699,7 +699,7 @@ static int sh_dmae_probe(struct platform_device *pdev)
 	struct resource *chan, *dmars, *errirq_res, *chanirq_res;
 
 	if (pdev->dev.of_node)
-		pdata = of_match_device(sh_dmae_of_match, &pdev->dev)->data;
+		pdata = of_device_get_match_data(&pdev->dev);
 	else
 		pdata = dev_get_platdata(&pdev->dev);
 
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 22ea2419ee56..e48350e65089 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -989,7 +989,7 @@ static int sirfsoc_dma_remove(struct platform_device *op)
 	return 0;
 }
 
-static int sirfsoc_dma_runtime_suspend(struct device *dev)
+static int __maybe_unused sirfsoc_dma_runtime_suspend(struct device *dev)
 {
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 
@@ -997,7 +997,7 @@ static int sirfsoc_dma_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int sirfsoc_dma_runtime_resume(struct device *dev)
+static int __maybe_unused sirfsoc_dma_runtime_resume(struct device *dev)
 {
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 	int ret;
@@ -1010,8 +1010,7 @@ static int sirfsoc_dma_runtime_resume(struct device *dev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int sirfsoc_dma_pm_suspend(struct device *dev)
+static int __maybe_unused sirfsoc_dma_pm_suspend(struct device *dev)
 {
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 	struct sirfsoc_dma_regs *save = &sdma->regs_save;
@@ -1062,7 +1061,7 @@ static int sirfsoc_dma_pm_suspend(struct device *dev)
 	return 0;
 }
 
-static int sirfsoc_dma_pm_resume(struct device *dev)
+static int __maybe_unused sirfsoc_dma_pm_resume(struct device *dev)
 {
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 	struct sirfsoc_dma_regs *save = &sdma->regs_save;
@@ -1121,7 +1120,6 @@ static int sirfsoc_dma_pm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops sirfsoc_dma_pm_ops = {
 	SET_RUNTIME_PM_OPS(sirfsoc_dma_runtime_suspend, sirfsoc_dma_runtime_resume, NULL)
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index 1661d518224a..e0df233dde92 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -1271,6 +1271,7 @@ static const struct of_device_id sun4i_dma_match[] = {
 	{ .compatible = "allwinner,sun4i-a10-dma" },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, sun4i_dma_match);
 
 static struct platform_driver sun4i_dma_driver = {
 	.probe	= sun4i_dma_probe,
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 935da8192f59..3871f29e523d 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -1292,40 +1292,19 @@ static const struct tegra_dma_chip_data tegra148_dma_chip_data = {
 	.support_separate_wcount_reg = true,
 };
 
-
-static const struct of_device_id tegra_dma_of_match[] = {
-	{
-		.compatible = "nvidia,tegra148-apbdma",
-		.data = &tegra148_dma_chip_data,
-	}, {
-		.compatible = "nvidia,tegra114-apbdma",
-		.data = &tegra114_dma_chip_data,
-	}, {
-		.compatible = "nvidia,tegra30-apbdma",
-		.data = &tegra30_dma_chip_data,
-	}, {
-		.compatible = "nvidia,tegra20-apbdma",
-		.data = &tegra20_dma_chip_data,
-	}, {
-	},
-};
-MODULE_DEVICE_TABLE(of, tegra_dma_of_match);
-
 static int tegra_dma_probe(struct platform_device *pdev)
 {
 	struct resource	*res;
 	struct tegra_dma *tdma;
 	int ret;
 	int i;
-	const struct tegra_dma_chip_data *cdata = NULL;
-	const struct of_device_id *match;
+	const struct tegra_dma_chip_data *cdata;
 
-	match = of_match_device(tegra_dma_of_match, &pdev->dev);
-	if (!match) {
-		dev_err(&pdev->dev, "Error: No device match found\n");
+	cdata = of_device_get_match_data(&pdev->dev);
+	if (!cdata) {
+		dev_err(&pdev->dev, "Error: No device match data found\n");
 		return -ENODEV;
 	}
-	cdata = match->data;
 
 	tdma = devm_kzalloc(&pdev->dev, sizeof(*tdma) + cdata->nr_channels *
 			sizeof(struct tegra_dma_channel), GFP_KERNEL);
@@ -1612,6 +1591,24 @@ static const struct dev_pm_ops tegra_dma_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_dma_pm_suspend, tegra_dma_pm_resume)
 };
 
+static const struct of_device_id tegra_dma_of_match[] = {
+	{
+		.compatible = "nvidia,tegra148-apbdma",
+		.data = &tegra148_dma_chip_data,
+	}, {
+		.compatible = "nvidia,tegra114-apbdma",
+		.data = &tegra114_dma_chip_data,
+	}, {
+		.compatible = "nvidia,tegra30-apbdma",
+		.data = &tegra30_dma_chip_data,
+	}, {
+		.compatible = "nvidia,tegra20-apbdma",
+		.data = &tegra20_dma_chip_data,
+	}, {
+	},
+};
+MODULE_DEVICE_TABLE(of, tegra_dma_of_match);
+
 static struct platform_driver tegra_dmac_driver = {
 	.driver = {
 		.name	= "tegra-apbdma",
diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c
index 6f4b5017ca3b..0ee0321868d3 100644
--- a/drivers/dma/xilinx/xilinx_vdma.c
+++ b/drivers/dma/xilinx/xilinx_vdma.c
@@ -28,6 +28,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_dma.h>
@@ -190,8 +191,7 @@ struct xilinx_vdma_tx_descriptor {
  * @desc_offset: TX descriptor registers offset
  * @lock: Descriptor operation lock
  * @pending_list: Descriptors waiting
- * @active_desc: Active descriptor
- * @allocated_desc: Allocated descriptor
+ * @active_list: Descriptors ready to submit
  * @done_list: Complete descriptors
  * @common: DMA common channel
  * @desc_pool: Descriptors pool
@@ -206,6 +206,7 @@ struct xilinx_vdma_tx_descriptor {
  * @tasklet: Cleanup work after irq
  * @config: Device configuration info
  * @flush_on_fsync: Flush on Frame sync
+ * @desc_pendingcount: Descriptor pending count
  */
 struct xilinx_vdma_chan {
 	struct xilinx_vdma_device *xdev;
@@ -213,8 +214,7 @@ struct xilinx_vdma_chan {
 	u32 desc_offset;
 	spinlock_t lock;
 	struct list_head pending_list;
-	struct xilinx_vdma_tx_descriptor *active_desc;
-	struct xilinx_vdma_tx_descriptor *allocated_desc;
+	struct list_head active_list;
 	struct list_head done_list;
 	struct dma_chan common;
 	struct dma_pool *desc_pool;
@@ -229,6 +229,7 @@ struct xilinx_vdma_chan {
 	struct tasklet_struct tasklet;
 	struct xilinx_vdma_config config;
 	bool flush_on_fsync;
+	u32 desc_pendingcount;
 };
 
 /**
@@ -254,6 +255,9 @@ struct xilinx_vdma_device {
 	container_of(chan, struct xilinx_vdma_chan, common)
 #define to_vdma_tx_descriptor(tx) \
 	container_of(tx, struct xilinx_vdma_tx_descriptor, async_tx)
+#define xilinx_vdma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \
+	readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \
+			   cond, delay_us, timeout_us)
 
 /* IO accessors */
 static inline u32 vdma_read(struct xilinx_vdma_chan *chan, u32 reg)
@@ -342,19 +346,11 @@ static struct xilinx_vdma_tx_descriptor *
 xilinx_vdma_alloc_tx_descriptor(struct xilinx_vdma_chan *chan)
 {
 	struct xilinx_vdma_tx_descriptor *desc;
-	unsigned long flags;
-
-	if (chan->allocated_desc)
-		return chan->allocated_desc;
 
 	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 	if (!desc)
 		return NULL;
 
-	spin_lock_irqsave(&chan->lock, flags);
-	chan->allocated_desc = desc;
-	spin_unlock_irqrestore(&chan->lock, flags);
-
 	INIT_LIST_HEAD(&desc->segments);
 
 	return desc;
@@ -412,9 +408,7 @@ static void xilinx_vdma_free_descriptors(struct xilinx_vdma_chan *chan)
 
 	xilinx_vdma_free_desc_list(chan, &chan->pending_list);
 	xilinx_vdma_free_desc_list(chan, &chan->done_list);
-
-	xilinx_vdma_free_tx_descriptor(chan, chan->active_desc);
-	chan->active_desc = NULL;
+	xilinx_vdma_free_desc_list(chan, &chan->active_list);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 }
@@ -560,18 +554,17 @@ static bool xilinx_vdma_is_idle(struct xilinx_vdma_chan *chan)
  */
 static void xilinx_vdma_halt(struct xilinx_vdma_chan *chan)
 {
-	int loop = XILINX_VDMA_LOOP_COUNT;
+	int err;
+	u32 val;
 
 	vdma_ctrl_clr(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP);
 
 	/* Wait for the hardware to halt */
-	do {
-		if (vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
-		    XILINX_VDMA_DMASR_HALTED)
-			break;
-	} while (loop--);
+	err = xilinx_vdma_poll_timeout(chan, XILINX_VDMA_REG_DMASR, val,
+				      (val & XILINX_VDMA_DMASR_HALTED), 0,
+				      XILINX_VDMA_LOOP_COUNT);
 
-	if (!loop) {
+	if (err) {
 		dev_err(chan->dev, "Cannot stop channel %p: %x\n",
 			chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
 		chan->err = true;
@@ -586,18 +579,17 @@ static void xilinx_vdma_halt(struct xilinx_vdma_chan *chan)
  */
 static void xilinx_vdma_start(struct xilinx_vdma_chan *chan)
 {
-	int loop = XILINX_VDMA_LOOP_COUNT;
+	int err;
+	u32 val;
 
 	vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP);
 
 	/* Wait for the hardware to start */
-	do {
-		if (!(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
-		      XILINX_VDMA_DMASR_HALTED))
-			break;
-	} while (loop--);
+	err = xilinx_vdma_poll_timeout(chan, XILINX_VDMA_REG_DMASR, val,
+				      !(val & XILINX_VDMA_DMASR_HALTED), 0,
+				      XILINX_VDMA_LOOP_COUNT);
 
-	if (!loop) {
+	if (err) {
 		dev_err(chan->dev, "Cannot start channel %p: %x\n",
 			chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
 
@@ -614,45 +606,39 @@ static void xilinx_vdma_start(struct xilinx_vdma_chan *chan)
 static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
 {
 	struct xilinx_vdma_config *config = &chan->config;
-	struct xilinx_vdma_tx_descriptor *desc;
-	unsigned long flags;
+	struct xilinx_vdma_tx_descriptor *desc, *tail_desc;
 	u32 reg;
-	struct xilinx_vdma_tx_segment *head, *tail = NULL;
+	struct xilinx_vdma_tx_segment *tail_segment;
 
+	/* This function was invoked with lock held */
 	if (chan->err)
 		return;
 
-	spin_lock_irqsave(&chan->lock, flags);
-
-	/* There's already an active descriptor, bail out. */
-	if (chan->active_desc)
-		goto out_unlock;
-
 	if (list_empty(&chan->pending_list))
-		goto out_unlock;
+		return;
 
 	desc = list_first_entry(&chan->pending_list,
 				struct xilinx_vdma_tx_descriptor, node);
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_vdma_tx_descriptor, node);
+
+	tail_segment = list_last_entry(&tail_desc->segments,
+				       struct xilinx_vdma_tx_segment, node);
 
 	/* If it is SG mode and hardware is busy, cannot submit */
 	if (chan->has_sg && xilinx_vdma_is_running(chan) &&
 	    !xilinx_vdma_is_idle(chan)) {
 		dev_dbg(chan->dev, "DMA controller still busy\n");
-		goto out_unlock;
+		return;
 	}
 
 	/*
 	 * If hardware is idle, then all descriptors on the running lists are
 	 * done, start new transfers
 	 */
-	if (chan->has_sg) {
-		head = list_first_entry(&desc->segments,
-					struct xilinx_vdma_tx_segment, node);
-		tail = list_entry(desc->segments.prev,
-				  struct xilinx_vdma_tx_segment, node);
-
-		vdma_ctrl_write(chan, XILINX_VDMA_REG_CURDESC, head->phys);
-	}
+	if (chan->has_sg)
+		vdma_ctrl_write(chan, XILINX_VDMA_REG_CURDESC,
+				desc->async_tx.phys);
 
 	/* Configure the hardware using info in the config structure */
 	reg = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR);
@@ -662,6 +648,10 @@ static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
 	else
 		reg &= ~XILINX_VDMA_DMACR_FRAMECNT_EN;
 
+	/* Configure channel to allow number frame buffers */
+	vdma_ctrl_write(chan, XILINX_VDMA_REG_FRMSTORE,
+			chan->desc_pendingcount);
+
 	/*
 	 * With SG, start with circular mode, so that BDs can be fetched.
 	 * In direct register mode, if not parking, enable circular mode
@@ -690,16 +680,19 @@ static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
 	xilinx_vdma_start(chan);
 
 	if (chan->err)
-		goto out_unlock;
+		return;
 
 	/* Start the transfer */
 	if (chan->has_sg) {
-		vdma_ctrl_write(chan, XILINX_VDMA_REG_TAILDESC, tail->phys);
+		vdma_ctrl_write(chan, XILINX_VDMA_REG_TAILDESC,
+				tail_segment->phys);
 	} else {
 		struct xilinx_vdma_tx_segment *segment, *last = NULL;
 		int i = 0;
 
-		list_for_each_entry(segment, &desc->segments, node) {
+		list_for_each_entry(desc, &chan->pending_list, node) {
+			segment = list_first_entry(&desc->segments,
+					   struct xilinx_vdma_tx_segment, node);
 			vdma_desc_write(chan,
 					XILINX_VDMA_REG_START_ADDRESS(i++),
 					segment->hw.buf_addr);
@@ -707,7 +700,7 @@ static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
 		}
 
 		if (!last)
-			goto out_unlock;
+			return;
 
 		/* HW expects these parameters to be same for one transaction */
 		vdma_desc_write(chan, XILINX_VDMA_REG_HSIZE, last->hw.hsize);
@@ -716,11 +709,8 @@ static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
 		vdma_desc_write(chan, XILINX_VDMA_REG_VSIZE, last->hw.vsize);
 	}
 
-	list_del(&desc->node);
-	chan->active_desc = desc;
-
-out_unlock:
-	spin_unlock_irqrestore(&chan->lock, flags);
+	list_splice_tail_init(&chan->pending_list, &chan->active_list);
+	chan->desc_pendingcount = 0;
 }
 
 /**
@@ -730,8 +720,11 @@ out_unlock:
 static void xilinx_vdma_issue_pending(struct dma_chan *dchan)
 {
 	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
 
+	spin_lock_irqsave(&chan->lock, flags);
 	xilinx_vdma_start_transfer(chan);
+	spin_unlock_irqrestore(&chan->lock, flags);
 }
 
 /**
@@ -742,24 +735,17 @@ static void xilinx_vdma_issue_pending(struct dma_chan *dchan)
  */
 static void xilinx_vdma_complete_descriptor(struct xilinx_vdma_chan *chan)
 {
-	struct xilinx_vdma_tx_descriptor *desc;
-	unsigned long flags;
+	struct xilinx_vdma_tx_descriptor *desc, *next;
 
-	spin_lock_irqsave(&chan->lock, flags);
+	/* This function was invoked with lock held */
+	if (list_empty(&chan->active_list))
+		return;
 
-	desc = chan->active_desc;
-	if (!desc) {
-		dev_dbg(chan->dev, "no running descriptors\n");
-		goto out_unlock;
+	list_for_each_entry_safe(desc, next, &chan->active_list, node) {
+		list_del(&desc->node);
+		dma_cookie_complete(&desc->async_tx);
+		list_add_tail(&desc->node, &chan->done_list);
 	}
-
-	dma_cookie_complete(&desc->async_tx);
-	list_add_tail(&desc->node, &chan->done_list);
-
-	chan->active_desc = NULL;
-
-out_unlock:
-	spin_unlock_irqrestore(&chan->lock, flags);
 }
 
 /**
@@ -770,21 +756,17 @@ out_unlock:
  */
 static int xilinx_vdma_reset(struct xilinx_vdma_chan *chan)
 {
-	int loop = XILINX_VDMA_LOOP_COUNT;
+	int err;
 	u32 tmp;
 
 	vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RESET);
 
-	tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) &
-		XILINX_VDMA_DMACR_RESET;
-
 	/* Wait for the hardware to finish reset */
-	do {
-		tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) &
-			XILINX_VDMA_DMACR_RESET;
-	} while (loop-- && tmp);
+	err = xilinx_vdma_poll_timeout(chan, XILINX_VDMA_REG_DMACR, tmp,
+				      !(tmp & XILINX_VDMA_DMACR_RESET), 0,
+				      XILINX_VDMA_LOOP_COUNT);
 
-	if (!loop) {
+	if (err) {
 		dev_err(chan->dev, "reset timeout, cr %x, sr %x\n",
 			vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR),
 			vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
@@ -793,7 +775,7 @@ static int xilinx_vdma_reset(struct xilinx_vdma_chan *chan)
 
 	chan->err = false;
 
-	return 0;
+	return err;
 }
 
 /**
@@ -870,8 +852,10 @@ static irqreturn_t xilinx_vdma_irq_handler(int irq, void *data)
 	}
 
 	if (status & XILINX_VDMA_DMASR_FRM_CNT_IRQ) {
+		spin_lock(&chan->lock);
 		xilinx_vdma_complete_descriptor(chan);
 		xilinx_vdma_start_transfer(chan);
+		spin_unlock(&chan->lock);
 	}
 
 	tasklet_schedule(&chan->tasklet);
@@ -879,6 +863,44 @@ static irqreturn_t xilinx_vdma_irq_handler(int irq, void *data)
 }
 
 /**
+ * append_desc_queue - Queuing descriptor
+ * @chan: Driver specific dma channel
+ * @desc: dma transaction descriptor
+ */
+static void append_desc_queue(struct xilinx_vdma_chan *chan,
+			      struct xilinx_vdma_tx_descriptor *desc)
+{
+	struct xilinx_vdma_tx_segment *tail_segment;
+	struct xilinx_vdma_tx_descriptor *tail_desc;
+
+	if (list_empty(&chan->pending_list))
+		goto append;
+
+	/*
+	 * Add the hardware descriptor to the chain of hardware descriptors
+	 * that already exists in memory.
+	 */
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_vdma_tx_descriptor, node);
+	tail_segment = list_last_entry(&tail_desc->segments,
+				       struct xilinx_vdma_tx_segment, node);
+	tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+
+	/*
+	 * Add the software descriptor and all children to the list
+	 * of pending transactions
+	 */
+append:
+	list_add_tail(&desc->node, &chan->pending_list);
+	chan->desc_pendingcount++;
+
+	if (unlikely(chan->desc_pendingcount > chan->num_frms)) {
+		dev_dbg(chan->dev, "desc pendingcount is too high\n");
+		chan->desc_pendingcount = chan->num_frms;
+	}
+}
+
+/**
  * xilinx_vdma_tx_submit - Submit DMA transaction
  * @tx: Async transaction descriptor
  *
@@ -906,11 +928,8 @@ static dma_cookie_t xilinx_vdma_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	cookie = dma_cookie_assign(tx);
 
-	/* Append the transaction to the pending transactions queue. */
-	list_add_tail(&desc->node, &chan->pending_list);
-
-	/* Free the allocated desc */
-	chan->allocated_desc = NULL;
+	/* Put this transaction onto the tail of the pending queue */
+	append_desc_queue(chan, desc);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 
@@ -973,13 +992,6 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	else
 		hw->buf_addr = xt->src_start;
 
-	/* Link the previous next descriptor to current */
-	if (!list_empty(&desc->segments)) {
-		prev = list_last_entry(&desc->segments,
-				       struct xilinx_vdma_tx_segment, node);
-		prev->hw.next_desc = segment->phys;
-	}
-
 	/* Insert the segment into the descriptor segments list. */
 	list_add_tail(&segment->node, &desc->segments);
 
@@ -988,7 +1000,7 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	/* Link the last hardware descriptor with the first. */
 	segment = list_first_entry(&desc->segments,
 				   struct xilinx_vdma_tx_segment, node);
-	prev->hw.next_desc = segment->phys;
+	desc->async_tx.phys = segment->phys;
 
 	return &desc->async_tx;
 
@@ -1127,10 +1139,12 @@ static int xilinx_vdma_chan_probe(struct xilinx_vdma_device *xdev,
 	chan->dev = xdev->dev;
 	chan->xdev = xdev;
 	chan->has_sg = xdev->has_sg;
+	chan->desc_pendingcount = 0x0;
 
 	spin_lock_init(&chan->lock);
 	INIT_LIST_HEAD(&chan->pending_list);
 	INIT_LIST_HEAD(&chan->done_list);
+	INIT_LIST_HEAD(&chan->active_list);
 
 	/* Retrieve the channel properties from the device tree */
 	has_dre = of_property_read_bool(node, "xlnx,include-dre");
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 26e2688c104e..8f50a4020f6f 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -191,6 +191,7 @@ struct rockchip_spi {
 	struct sg_table rx_sg;
 	struct rockchip_spi_dma_data dma_rx;
 	struct rockchip_spi_dma_data dma_tx;
+	struct dma_slave_caps dma_caps;
 };
 
 static inline void spi_enable_chip(struct rockchip_spi *rs, int enable)
@@ -446,7 +447,10 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		rxconf.direction = rs->dma_rx.direction;
 		rxconf.src_addr = rs->dma_rx.addr;
 		rxconf.src_addr_width = rs->n_bytes;
-		rxconf.src_maxburst = rs->n_bytes;
+		if (rs->dma_caps.max_burst > 4)
+			rxconf.src_maxburst = 4;
+		else
+			rxconf.src_maxburst = 1;
 		dmaengine_slave_config(rs->dma_rx.ch, &rxconf);
 
 		rxdesc = dmaengine_prep_slave_sg(
@@ -465,7 +469,10 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		txconf.direction = rs->dma_tx.direction;
 		txconf.dst_addr = rs->dma_tx.addr;
 		txconf.dst_addr_width = rs->n_bytes;
-		txconf.dst_maxburst = rs->n_bytes;
+		if (rs->dma_caps.max_burst > 4)
+			txconf.dst_maxburst = 4;
+		else
+			txconf.dst_maxburst = 1;
 		dmaengine_slave_config(rs->dma_tx.ch, &txconf);
 
 		txdesc = dmaengine_prep_slave_sg(
@@ -743,6 +750,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	}
 
 	if (rs->dma_tx.ch && rs->dma_rx.ch) {
+		dma_get_slave_caps(rs->dma_rx.ch, &(rs->dma_caps));
 		rs->dma_tx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_TXDR);
 		rs->dma_rx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_RXDR);
 		rs->dma_tx.direction = DMA_MEM_TO_DEV;