Merge tag 'pci-v6.3-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci

Pull PCI updates from Bjorn Helgaas:
 "Enumeration:

   - Rework portdrv shutdown so it disables interrupts but doesn't
     disable bus mastering, which leads to hangs on Loongson LS7A

   - Add mechanism to prevent Max_Read_Request_Size (MRRS) increases,
     again to avoid hardware issues on Loongson LS7A (and likely other
     devices based on DesignWare IP)

   - Ignore devices with a firmware (DT or ACPI) node that says the
     device is disabled

  Resource management:

   - Distribute spare resources to unconfigured hotplug bridges at
     boot-time (not just when hot-adding such a bridge), which makes
     hot-adding devices to docks work better. Tried this in v6.1 but had
     to revert for regressions, so try again

   - Fix root bus issue that dropped resources that happened to end
     at 0, e.g., [bus 00]

  PCI device hotplug:

   - Remove device locking when marking device as disconnected so this
     doesn't have to wait for concurrent driver bind/unbind to complete

   - Quirk more Qualcomm bridges that don't fully implement the PCIe
     Slot Status 'Command Completed' bit

  Power management:

   - Account for _S0W of the target bridge in acpi_pci_bridge_d3() so we
     don't miss hot-add notifications for USB4 docks, Thunderbolt, etc

  Reset:

   - Observe delay after reset, e.g., resuming from system sleep,
     regardless of whether a bridge can suspend to D3cold at runtime

   - Wait for secondary bus to become ready after a bridge reset

  Virtualization:

   - Avoid FLR on some AMD FCH AHCI adapters where it doesn't work

   - Allow independent IOMMU groups for some Wangxun NICs that prevent
     peer-to-peer transactions but don't advertise an ACS Capability

  Error handling:

   - Configure End-to-End-CRC (ECRC) only if Linux owns the AER
     Capability

   - Remove redundant Device Control Error Reporting Enable in the AER
     service driver since this is already done for all devices during
     enumeration

  ASPM:

   - Add pci_enable_link_state() interface to allow drivers to enable
     ASPM link state

  Endpoint framework:

   - Move dra7xx and tegra194 linkup processing from hard IRQ to
     threaded IRQ handler

   - Add a separate lock for endpoint controller list of endpoint
     function drivers to prevent deadlock in callbacks

   - Pass events from endpoint controller to endpoint function drivers
     via callbacks instead of notifiers

  Synopsys DesignWare eDMA controller driver (acked by Vinod):

   - Fix CPU vs PCI address issues

   - Fix source vs destination address issues

   - Fix issues with interleaved transfer semantics

   - Fix channel count initialization issue (issue still exists in
     several other drivers)

   - Clean up and improve debugfs usage so it will work on platforms
     with several eDMA devices

  Baikal T-1 PCIe controller driver:

   - Set a 64-bit DMA mask

  Freescale i.MX6 PCIe controller driver:

   - Add i.MX8MM, i.MX8MQ, i.MX8MP endpoint mode DT binding and driver
     support

  Intel VMD host bridge driver:

   - Add quirk to configure PCIe ASPM and LTR. This is normally done by
     BIOS, and will be for future products

  Marvell MVEBU PCIe controller driver:

   - Mark this driver as broken in Kconfig since bugs prevent its daily
     usage

  MediaTek MT7621 PCIe controller driver:

   - Delay PHY port initialization to improve boot reliability for ZBT
     WE1326, ZBT WF3526-P, and some Netgear models

  Qualcomm PCIe controller driver:

   - Add MSM8998 DT compatible string

   - Unify MSM8996 and MSM8998 clock orderings

   - Add SM8350 DT binding and driver support

   - Add IPQ8074 Gen3 DT binding and driver support

   - Correct qcom,perst-regs in DT binding

   - Add qcom_pcie_host_deinit() so the PHY is powered off and
     regulators and clocks are disabled on late host-init errors

  Socionext UniPhier Pro5 controller driver:

   - Clean up uniphier-ep reg, clocks, resets, and their names in DT
     binding

  Synopsys DesignWare PCIe controller driver:

   - Restrict coherent DMA mask to 32 bits for MSI, but allow controller
     drivers to set 64-bit streaming DMA mask

   - Add eDMA engine support in both Root Port and Endpoint controllers

  Miscellaneous:

   - Remove MODULE_LICENSE from boolean drivers so they don't look like
     modules so modprobe can complain about them"

* tag 'pci-v6.3-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci: (86 commits)
  PCI: dwc: Add Root Port and Endpoint controller eDMA engine support
  PCI: bt1: Set 64-bit DMA mask
  PCI: dwc: Restrict only coherent DMA mask for MSI address allocation
  dmaengine: dw-edma: Prepare dw_edma_probe() for builtin callers
  dmaengine: dw-edma: Depend on DW_EDMA instead of selecting it
  dmaengine: dw-edma: Add mem-mapped LL-entries support
  PCI: Remove MODULE_LICENSE so boolean drivers don't look like modules
  PCI: hv: Drop duplicate PCI_MSI dependency
  PCI/P2PDMA: Annotate RCU dereference
  PCI/sysfs: Constify struct kobj_type pci_slot_ktype
  PCI: hotplug: Allow marking devices as disconnected during bind/unbind
  PCI: pciehp: Add Qualcomm quirk for Command Completed erratum
  PCI: qcom: Add IPQ8074 Gen3 port support
  dt-bindings: PCI: qcom: Add IPQ8074 Gen3 port
  dt-bindings: PCI: qcom: Sort compatibles alphabetically
  PCI: qcom: Fix host-init error handling
  PCI: qcom: Add SM8350 support
  dt-bindings: PCI: qcom: Add SM8350
  dt-bindings: PCI: qcom-ep: Correct qcom,perst-regs
  dt-bindings: PCI: qcom: Unify MSM8996 and MSM8998 clock order
  ...

8 files changed, 369 insertions, 378 deletions

diff --git a/drivers/dma/dw-edma/Kconfig b/drivers/dma/dw-edma/Kconfig
index 7ff17b2db6a1..2b6f2679508d 100644
--- a/drivers/dma/dw-edma/Kconfig
+++ b/drivers/dma/dw-edma/Kconfig
@@ -9,11 +9,14 @@ config DW_EDMA
 	  Support the Synopsys DesignWare eDMA controller, normally
 	  implemented on endpoints SoCs.
 
+if DW_EDMA
+
 config DW_EDMA_PCIE
 	tristate "Synopsys DesignWare eDMA PCIe driver"
 	depends on PCI && PCI_MSI
-	select DW_EDMA
 	help
 	  Provides a glue-logic between the Synopsys DesignWare
 	  eDMA controller and an endpoint PCIe device. This also serves
 	  as a reference design to whom desires to use this IP.
+
+endif # DW_EDMA
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index c54b24ff5206..1906a836f0aa 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -39,6 +39,17 @@ struct dw_edma_desc *vd2dw_edma_desc(struct virt_dma_desc *vd)
 	return container_of(vd, struct dw_edma_desc, vd);
 }
 
+static inline
+u64 dw_edma_get_pci_address(struct dw_edma_chan *chan, phys_addr_t cpu_addr)
+{
+	struct dw_edma_chip *chip = chan->dw->chip;
+
+	if (chip->ops->pci_address)
+		return chip->ops->pci_address(chip->dev, cpu_addr);
+
+	return cpu_addr;
+}
+
 static struct dw_edma_burst *dw_edma_alloc_burst(struct dw_edma_chunk *chunk)
 {
 	struct dw_edma_burst *burst;
@@ -197,6 +208,24 @@ static void dw_edma_start_transfer(struct dw_edma_chan *chan)
 	desc->chunks_alloc--;
 }
 
+static void dw_edma_device_caps(struct dma_chan *dchan,
+				struct dma_slave_caps *caps)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		if (chan->dir == EDMA_DIR_READ)
+			caps->directions = BIT(DMA_DEV_TO_MEM);
+		else
+			caps->directions = BIT(DMA_MEM_TO_DEV);
+	} else {
+		if (chan->dir == EDMA_DIR_WRITE)
+			caps->directions = BIT(DMA_DEV_TO_MEM);
+		else
+			caps->directions = BIT(DMA_MEM_TO_DEV);
+	}
+}
+
 static int dw_edma_device_config(struct dma_chan *dchan,
 				 struct dma_slave_config *config)
 {
@@ -327,11 +356,12 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
 	enum dma_transfer_direction dir = xfer->direction;
-	phys_addr_t src_addr, dst_addr;
 	struct scatterlist *sg = NULL;
 	struct dw_edma_chunk *chunk;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
+	u64 src_addr, dst_addr;
+	size_t fsz = 0;
 	u32 cnt = 0;
 	int i;
 
@@ -381,9 +411,9 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		if (xfer->xfer.sg.len < 1)
 			return NULL;
 	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
-		if (!xfer->xfer.il->numf)
+		if (!xfer->xfer.il->numf || xfer->xfer.il->frame_size < 1)
 			return NULL;
-		if (xfer->xfer.il->numf > 0 && xfer->xfer.il->frame_size > 0)
+		if (!xfer->xfer.il->src_inc || !xfer->xfer.il->dst_inc)
 			return NULL;
 	} else {
 		return NULL;
@@ -405,16 +435,19 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		dst_addr = chan->config.dst_addr;
 	}
 
+	if (dir == DMA_DEV_TO_MEM)
+		src_addr = dw_edma_get_pci_address(chan, (phys_addr_t)src_addr);
+	else
+		dst_addr = dw_edma_get_pci_address(chan, (phys_addr_t)dst_addr);
+
 	if (xfer->type == EDMA_XFER_CYCLIC) {
 		cnt = xfer->xfer.cyclic.cnt;
 	} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
 		cnt = xfer->xfer.sg.len;
 		sg = xfer->xfer.sg.sgl;
 	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
-		if (xfer->xfer.il->numf > 0)
-			cnt = xfer->xfer.il->numf;
-		else
-			cnt = xfer->xfer.il->frame_size;
+		cnt = xfer->xfer.il->numf * xfer->xfer.il->frame_size;
+		fsz = xfer->xfer.il->frame_size;
 	}
 
 	for (i = 0; i < cnt; i++) {
@@ -436,7 +469,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		else if (xfer->type == EDMA_XFER_SCATTER_GATHER)
 			burst->sz = sg_dma_len(sg);
 		else if (xfer->type == EDMA_XFER_INTERLEAVED)
-			burst->sz = xfer->xfer.il->sgl[i].size;
+			burst->sz = xfer->xfer.il->sgl[i % fsz].size;
 
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
@@ -455,6 +488,8 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
+			} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+				burst->dar = dst_addr;
 			}
 		} else {
 			burst->dar = dst_addr;
@@ -470,25 +505,24 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
+			}  else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+				burst->sar = src_addr;
 			}
 		}
 
 		if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
 			sg = sg_next(sg);
-		} else if (xfer->type == EDMA_XFER_INTERLEAVED &&
-			   xfer->xfer.il->frame_size > 0) {
+		} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
 			struct dma_interleaved_template *il = xfer->xfer.il;
-			struct data_chunk *dc = &il->sgl[i];
+			struct data_chunk *dc = &il->sgl[i % fsz];
 
-			if (il->src_sgl) {
-				src_addr += burst->sz;
+			src_addr += burst->sz;
+			if (il->src_sgl)
 				src_addr += dmaengine_get_src_icg(il, dc);
-			}
 
-			if (il->dst_sgl) {
-				dst_addr += burst->sz;
+			dst_addr += burst->sz;
+			if (il->dst_sgl)
 				dst_addr += dmaengine_get_dst_icg(il, dc);
-			}
 		}
 	}
 
@@ -701,92 +735,76 @@ static void dw_edma_free_chan_resources(struct dma_chan *dchan)
 	}
 }
 
-static int dw_edma_channel_setup(struct dw_edma *dw, bool write,
-				 u32 wr_alloc, u32 rd_alloc)
+static int dw_edma_channel_setup(struct dw_edma *dw, u32 wr_alloc, u32 rd_alloc)
 {
 	struct dw_edma_chip *chip = dw->chip;
-	struct dw_edma_region *dt_region;
 	struct device *dev = chip->dev;
 	struct dw_edma_chan *chan;
 	struct dw_edma_irq *irq;
 	struct dma_device *dma;
-	u32 alloc, off_alloc;
-	u32 i, j, cnt;
-	int err = 0;
+	u32 i, ch_cnt;
 	u32 pos;
 
-	if (write) {
-		i = 0;
-		cnt = dw->wr_ch_cnt;
-		dma = &dw->wr_edma;
-		alloc = wr_alloc;
-		off_alloc = 0;
-	} else {
-		i = dw->wr_ch_cnt;
-		cnt = dw->rd_ch_cnt;
-		dma = &dw->rd_edma;
-		alloc = rd_alloc;
-		off_alloc = wr_alloc;
-	}
+	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
+	dma = &dw->dma;
 
 	INIT_LIST_HEAD(&dma->channels);
-	for (j = 0; (alloc || dw->nr_irqs == 1) && j < cnt; j++, i++) {
+
+	for (i = 0; i < ch_cnt; i++) {
 		chan = &dw->chan[i];
 
-		dt_region = devm_kzalloc(dev, sizeof(*dt_region), GFP_KERNEL);
-		if (!dt_region)
-			return -ENOMEM;
+		chan->dw = dw;
 
-		chan->vc.chan.private = dt_region;
+		if (i < dw->wr_ch_cnt) {
+			chan->id = i;
+			chan->dir = EDMA_DIR_WRITE;
+		} else {
+			chan->id = i - dw->wr_ch_cnt;
+			chan->dir = EDMA_DIR_READ;
+		}
 
-		chan->dw = dw;
-		chan->id = j;
-		chan->dir = write ? EDMA_DIR_WRITE : EDMA_DIR_READ;
 		chan->configured = false;
 		chan->request = EDMA_REQ_NONE;
 		chan->status = EDMA_ST_IDLE;
 
-		if (write)
-			chan->ll_max = (chip->ll_region_wr[j].sz / EDMA_LL_SZ);
+		if (chan->dir == EDMA_DIR_WRITE)
+			chan->ll_max = (chip->ll_region_wr[chan->id].sz / EDMA_LL_SZ);
 		else
-			chan->ll_max = (chip->ll_region_rd[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_rd[chan->id].sz / EDMA_LL_SZ);
 		chan->ll_max -= 1;
 
 		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
-			 write ? "write" : "read", j, chan->ll_max);
+			 chan->dir == EDMA_DIR_WRITE ? "write" : "read",
+			 chan->id, chan->ll_max);
 
 		if (dw->nr_irqs == 1)
 			pos = 0;
+		else if (chan->dir == EDMA_DIR_WRITE)
+			pos = chan->id % wr_alloc;
 		else
-			pos = off_alloc + (j % alloc);
+			pos = wr_alloc + chan->id % rd_alloc;
 
 		irq = &dw->irq[pos];
 
-		if (write)
-			irq->wr_mask |= BIT(j);
+		if (chan->dir == EDMA_DIR_WRITE)
+			irq->wr_mask |= BIT(chan->id);
 		else
-			irq->rd_mask |= BIT(j);
+			irq->rd_mask |= BIT(chan->id);
 
 		irq->dw = dw;
 		memcpy(&chan->msi, &irq->msi, sizeof(chan->msi));
 
 		dev_vdbg(dev, "MSI:\t\tChannel %s[%u] addr=0x%.8x%.8x, data=0x%.8x\n",
-			 write ? "write" : "read", j,
+			 chan->dir == EDMA_DIR_WRITE  ? "write" : "read", chan->id,
 			 chan->msi.address_hi, chan->msi.address_lo,
 			 chan->msi.data);
 
 		chan->vc.desc_free = vchan_free_desc;
-		vchan_init(&chan->vc, dma);
+		chan->vc.chan.private = chan->dir == EDMA_DIR_WRITE ?
+					&dw->chip->dt_region_wr[chan->id] :
+					&dw->chip->dt_region_rd[chan->id];
 
-		if (write) {
-			dt_region->paddr = chip->dt_region_wr[j].paddr;
-			dt_region->vaddr = chip->dt_region_wr[j].vaddr;
-			dt_region->sz = chip->dt_region_wr[j].sz;
-		} else {
-			dt_region->paddr = chip->dt_region_rd[j].paddr;
-			dt_region->vaddr = chip->dt_region_rd[j].vaddr;
-			dt_region->sz = chip->dt_region_rd[j].sz;
-		}
+		vchan_init(&chan->vc, dma);
 
 		dw_edma_v0_core_device_config(chan);
 	}
@@ -797,16 +815,16 @@ static int dw_edma_channel_setup(struct dw_edma *dw, bool write,
 	dma_cap_set(DMA_CYCLIC, dma->cap_mask);
 	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
 	dma_cap_set(DMA_INTERLEAVE, dma->cap_mask);
-	dma->directions = BIT(write ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV);
+	dma->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	dma->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
-	dma->chancnt = cnt;
 
 	/* Set DMA channel callbacks */
 	dma->dev = chip->dev;
 	dma->device_alloc_chan_resources = dw_edma_alloc_chan_resources;
 	dma->device_free_chan_resources = dw_edma_free_chan_resources;
+	dma->device_caps = dw_edma_device_caps;
 	dma->device_config = dw_edma_device_config;
 	dma->device_pause = dw_edma_device_pause;
 	dma->device_resume = dw_edma_device_resume;
@@ -820,9 +838,7 @@ static int dw_edma_channel_setup(struct dw_edma *dw, bool write,
 	dma_set_max_seg_size(dma->dev, U32_MAX);
 
 	/* Register DMA device */
-	err = dma_async_device_register(dma);
-
-	return err;
+	return dma_async_device_register(dma);
 }
 
 static inline void dw_edma_dec_irq_alloc(int *nr_irqs, u32 *alloc, u16 cnt)
@@ -893,10 +909,8 @@ static int dw_edma_irq_request(struct dw_edma *dw,
 						dw_edma_interrupt_read,
 					  IRQF_SHARED, dw->name,
 					  &dw->irq[i]);
-			if (err) {
-				dw->nr_irqs = i;
-				return err;
-			}
+			if (err)
+				goto err_irq_free;
 
 			if (irq_get_msi_desc(irq))
 				get_cached_msi_msg(irq, &dw->irq[i].msi);
@@ -905,6 +919,14 @@ static int dw_edma_irq_request(struct dw_edma *dw,
 		dw->nr_irqs = i;
 	}
 
+	return 0;
+
+err_irq_free:
+	for  (i--; i >= 0; i--) {
+		irq = chip->ops->irq_vector(dev, i);
+		free_irq(irq, &dw->irq[i]);
+	}
+
 	return err;
 }
 
@@ -951,7 +973,8 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	if (!dw->chan)
 		return -ENOMEM;
 
-	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%d", chip->id);
+	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%s",
+		 dev_name(chip->dev));
 
 	/* Disable eDMA, only to establish the ideal initial conditions */
 	dw_edma_v0_core_off(dw);
@@ -961,13 +984,8 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	if (err)
 		return err;
 
-	/* Setup write channels */
-	err = dw_edma_channel_setup(dw, true, wr_alloc, rd_alloc);
-	if (err)
-		goto err_irq_free;
-
-	/* Setup read channels */
-	err = dw_edma_channel_setup(dw, false, wr_alloc, rd_alloc);
+	/* Setup write/read channels */
+	err = dw_edma_channel_setup(dw, wr_alloc, rd_alloc);
 	if (err)
 		goto err_irq_free;
 
@@ -993,6 +1011,10 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	struct dw_edma *dw = chip->dw;
 	int i;
 
+	/* Skip removal if no private data found */
+	if (!dw)
+		return -ENODEV;
+
 	/* Disable eDMA */
 	dw_edma_v0_core_off(dw);
 
@@ -1001,23 +1023,13 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	/* Deregister eDMA device */
-	dma_async_device_unregister(&dw->wr_edma);
-	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
+	dma_async_device_unregister(&dw->dma);
+	list_for_each_entry_safe(chan, _chan, &dw->dma.channels,
 				 vc.chan.device_node) {
 		tasklet_kill(&chan->vc.task);
 		list_del(&chan->vc.chan.device_node);
 	}
 
-	dma_async_device_unregister(&dw->rd_edma);
-	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
-				 vc.chan.device_node) {
-		tasklet_kill(&chan->vc.task);
-		list_del(&chan->vc.chan.device_node);
-	}
-
-	/* Turn debugfs off */
-	dw_edma_v0_core_debugfs_off(dw);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_edma_remove);
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 85df2d511907..0ab2b6dba880 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -96,12 +96,11 @@ struct dw_edma_irq {
 };
 
 struct dw_edma {
-	char				name[20];
+	char				name[32];
 
-	struct dma_device		wr_edma;
-	u16				wr_ch_cnt;
+	struct dma_device		dma;
 
-	struct dma_device		rd_edma;
+	u16				wr_ch_cnt;
 	u16				rd_ch_cnt;
 
 	struct dw_edma_irq		*irq;
@@ -112,9 +111,6 @@ struct dw_edma {
 	raw_spinlock_t			lock;		/* Only for legacy */
 
 	struct dw_edma_chip             *chip;
-#ifdef CONFIG_DEBUG_FS
-	struct dentry			*debugfs;
-#endif /* CONFIG_DEBUG_FS */
 };
 
 struct dw_edma_sg {
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index d6b5e2463884..2b40f2b44f5e 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -95,8 +95,23 @@ static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
 	return pci_irq_vector(to_pci_dev(dev), nr);
 }
 
+static u64 dw_edma_pcie_address(struct device *dev, phys_addr_t cpu_addr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus_region region;
+	struct resource res = {
+		.flags = IORESOURCE_MEM,
+		.start = cpu_addr,
+		.end = cpu_addr,
+	};
+
+	pcibios_resource_to_bus(pdev->bus, &region, &res);
+	return region.start;
+}
+
 static const struct dw_edma_core_ops dw_edma_pcie_core_ops = {
 	.irq_vector = dw_edma_pcie_irq_vector,
+	.pci_address = dw_edma_pcie_address,
 };
 
 static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
@@ -207,7 +222,6 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 
 	/* Data structure initialization */
 	chip->dev = dev;
-	chip->id = pdev->devfn;
 
 	chip->mf = vsec_data.mf;
 	chip->nr_irqs = nr_irqs;
@@ -226,21 +240,21 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		struct dw_edma_block *ll_block = &vsec_data.ll_wr[i];
 		struct dw_edma_block *dt_block = &vsec_data.dt_wr[i];
 
-		ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar];
-		if (!ll_region->vaddr)
+		ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr.io)
 			return -ENOMEM;
 
-		ll_region->vaddr += ll_block->off;
-		ll_region->paddr = pdev->resource[ll_block->bar].start;
+		ll_region->vaddr.io += ll_block->off;
+		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
-		dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar];
-		if (!dt_region->vaddr)
+		dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr.io)
 			return -ENOMEM;
 
-		dt_region->vaddr += dt_block->off;
-		dt_region->paddr = pdev->resource[dt_block->bar].start;
+		dt_region->vaddr.io += dt_block->off;
+		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
@@ -251,21 +265,21 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		struct dw_edma_block *ll_block = &vsec_data.ll_rd[i];
 		struct dw_edma_block *dt_block = &vsec_data.dt_rd[i];
 
-		ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar];
-		if (!ll_region->vaddr)
+		ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr.io)
 			return -ENOMEM;
 
-		ll_region->vaddr += ll_block->off;
-		ll_region->paddr = pdev->resource[ll_block->bar].start;
+		ll_region->vaddr.io += ll_block->off;
+		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
-		dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar];
-		if (!dt_region->vaddr)
+		dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr.io)
 			return -ENOMEM;
 
-		dt_region->vaddr += dt_block->off;
-		dt_region->paddr = pdev->resource[dt_block->bar].start;
+		dt_region->vaddr.io += dt_block->off;
+		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
@@ -289,24 +303,24 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.ll_wr[i].bar,
 			vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz,
-			chip->ll_region_wr[i].vaddr, &chip->ll_region_wr[i].paddr);
+			chip->ll_region_wr[i].vaddr.io, &chip->ll_region_wr[i].paddr);
 
 		pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.dt_wr[i].bar,
 			vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz,
-			chip->dt_region_wr[i].vaddr, &chip->dt_region_wr[i].paddr);
+			chip->dt_region_wr[i].vaddr.io, &chip->dt_region_wr[i].paddr);
 	}
 
 	for (i = 0; i < chip->ll_rd_cnt; i++) {
 		pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.ll_rd[i].bar,
 			vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz,
-			chip->ll_region_rd[i].vaddr, &chip->ll_region_rd[i].paddr);
+			chip->ll_region_rd[i].vaddr.io, &chip->ll_region_rd[i].paddr);
 
 		pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.dt_rd[i].bar,
 			vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz,
-			chip->dt_region_rd[i].vaddr, &chip->dt_region_rd[i].paddr);
+			chip->dt_region_rd[i].vaddr.io, &chip->dt_region_rd[i].paddr);
 	}
 
 	pci_dbg(pdev, "Nr. IRQs:\t%u\n", chip->nr_irqs);
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index 77e6cfe52e0a..72e79a0c0a4e 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -8,6 +8,8 @@
 
 #include <linux/bitfield.h>
 
+#include <linux/io-64-nonatomic-lo-hi.h>
+
 #include "dw-edma-core.h"
 #include "dw-edma-v0-core.h"
 #include "dw-edma-v0-regs.h"
@@ -53,8 +55,6 @@ static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
 		SET_32(dw, rd_##name, value);		\
 	} while (0)
 
-#ifdef CONFIG_64BIT
-
 #define SET_64(dw, name, value)				\
 	writeq(value, &(__dw_regs(dw)->name))
 
@@ -80,8 +80,6 @@ static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
 		SET_64(dw, rd_##name, value);		\
 	} while (0)
 
-#endif /* CONFIG_64BIT */
-
 #define SET_COMPAT(dw, name, value)			\
 	writel(value, &(__dw_regs(dw)->type.unroll.name))
 
@@ -161,11 +159,6 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 #define GET_CH_32(dw, dir, ch, name) \
 	readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
 
-#define SET_LL_32(ll, value) \
-	writel(value, ll)
-
-#ifdef CONFIG_64BIT
-
 static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 			     u64 value, void __iomem *addr)
 {
@@ -192,7 +185,7 @@ static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 			   const void __iomem *addr)
 {
-	u32 value;
+	u64 value;
 
 	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
@@ -222,11 +215,6 @@ static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 #define GET_CH_64(dw, dir, ch, name) \
 	readq_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
 
-#define SET_LL_64(ll, value) \
-	writeq(value, ll)
-
-#endif /* CONFIG_64BIT */
-
 /* eDMA management callbacks */
 void dw_edma_v0_core_off(struct dw_edma *dw)
 {
@@ -298,17 +286,53 @@ u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir)
 			 GET_RW_32(dw, dir, int_status));
 }
 
+static void dw_edma_v0_write_ll_data(struct dw_edma_chunk *chunk, int i,
+				     u32 control, u32 size, u64 sar, u64 dar)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli);
+
+	if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_edma_v0_lli *lli = chunk->ll_region.vaddr.mem + ofs;
+
+		lli->control = control;
+		lli->transfer_size = size;
+		lli->sar.reg = sar;
+		lli->dar.reg = dar;
+	} else {
+		struct dw_edma_v0_lli __iomem *lli = chunk->ll_region.vaddr.io + ofs;
+
+		writel(control, &lli->control);
+		writel(size, &lli->transfer_size);
+		writeq(sar, &lli->sar.reg);
+		writeq(dar, &lli->dar.reg);
+	}
+}
+
+static void dw_edma_v0_write_ll_link(struct dw_edma_chunk *chunk,
+				     int i, u32 control, u64 pointer)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli);
+
+	if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_edma_v0_llp *llp = chunk->ll_region.vaddr.mem + ofs;
+
+		llp->control = control;
+		llp->llp.reg = pointer;
+	} else {
+		struct dw_edma_v0_llp __iomem *llp = chunk->ll_region.vaddr.io + ofs;
+
+		writel(control, &llp->control);
+		writeq(pointer, &llp->llp.reg);
+	}
+}
+
 static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 {
 	struct dw_edma_burst *child;
 	struct dw_edma_chan *chan = chunk->chan;
-	struct dw_edma_v0_lli __iomem *lli;
-	struct dw_edma_v0_llp __iomem *llp;
 	u32 control = 0, i = 0;
 	int j;
 
-	lli = chunk->ll_region.vaddr;
-
 	if (chunk->cb)
 		control = DW_EDMA_V0_CB;
 
@@ -320,41 +344,16 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 			if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
 				control |= DW_EDMA_V0_RIE;
 		}
-		/* Channel control */
-		SET_LL_32(&lli[i].control, control);
-		/* Transfer size */
-		SET_LL_32(&lli[i].transfer_size, child->sz);
-		/* SAR */
-		#ifdef CONFIG_64BIT
-			SET_LL_64(&lli[i].sar.reg, child->sar);
-		#else /* CONFIG_64BIT */
-			SET_LL_32(&lli[i].sar.lsb, lower_32_bits(child->sar));
-			SET_LL_32(&lli[i].sar.msb, upper_32_bits(child->sar));
-		#endif /* CONFIG_64BIT */
-		/* DAR */
-		#ifdef CONFIG_64BIT
-			SET_LL_64(&lli[i].dar.reg, child->dar);
-		#else /* CONFIG_64BIT */
-			SET_LL_32(&lli[i].dar.lsb, lower_32_bits(child->dar));
-			SET_LL_32(&lli[i].dar.msb, upper_32_bits(child->dar));
-		#endif /* CONFIG_64BIT */
-		i++;
+
+		dw_edma_v0_write_ll_data(chunk, i++, control, child->sz,
+					 child->sar, child->dar);
 	}
 
-	llp = (void __iomem *)&lli[i];
 	control = DW_EDMA_V0_LLP | DW_EDMA_V0_TCB;
 	if (!chunk->cb)
 		control |= DW_EDMA_V0_CB;
 
-	/* Channel control */
-	SET_LL_32(&llp->control, control);
-	/* Linked list */
-	#ifdef CONFIG_64BIT
-		SET_LL_64(&llp->llp.reg, chunk->ll_region.paddr);
-	#else /* CONFIG_64BIT */
-		SET_LL_32(&llp->llp.lsb, lower_32_bits(chunk->ll_region.paddr));
-		SET_LL_32(&llp->llp.msb, upper_32_bits(chunk->ll_region.paddr));
-	#endif /* CONFIG_64BIT */
+	dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
 void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
@@ -504,8 +503,3 @@ void dw_edma_v0_core_debugfs_on(struct dw_edma *dw)
 {
 	dw_edma_v0_debugfs_on(dw);
 }
-
-void dw_edma_v0_core_debugfs_off(struct dw_edma *dw)
-{
-	dw_edma_v0_debugfs_off(dw);
-}
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.h b/drivers/dma/dw-edma/dw-edma-v0-core.h
index 75aec6d31b21..ab96a1f48080 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.h
@@ -23,6 +23,5 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first);
 int dw_edma_v0_core_device_config(struct dw_edma_chan *chan);
 /* eDMA debug fs callbacks */
 void dw_edma_v0_core_debugfs_on(struct dw_edma *dw);
-void dw_edma_v0_core_debugfs_off(struct dw_edma *dw);
 
 #endif /* _DW_EDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 5226c9014703..0745d9e7d259 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -13,76 +13,79 @@
 #include "dw-edma-v0-regs.h"
 #include "dw-edma-core.h"
 
-#define REGS_ADDR(name) \
-	((void __force *)&regs->name)
-#define REGISTER(name) \
-	{ #name, REGS_ADDR(name) }
-
-#define WR_REGISTER(name) \
-	{ #name, REGS_ADDR(wr_##name) }
-#define RD_REGISTER(name) \
-	{ #name, REGS_ADDR(rd_##name) }
-
-#define WR_REGISTER_LEGACY(name) \
-	{ #name, REGS_ADDR(type.legacy.wr_##name) }
+#define REGS_ADDR(dw, name)						       \
+	({								       \
+		struct dw_edma_v0_regs __iomem *__regs = (dw)->chip->reg_base; \
+									       \
+		(void __iomem *)&__regs->name;				       \
+	})
+
+#define REGS_CH_ADDR(dw, name, _dir, _ch)				       \
+	({								       \
+		struct dw_edma_v0_ch_regs __iomem *__ch_regs;		       \
+									       \
+		if ((dw)->chip->mf == EDMA_MF_EDMA_LEGACY)		       \
+			__ch_regs = REGS_ADDR(dw, type.legacy.ch);	       \
+		else if (_dir == EDMA_DIR_READ)				       \
+			__ch_regs = REGS_ADDR(dw, type.unroll.ch[_ch].rd);     \
+		else							       \
+			__ch_regs = REGS_ADDR(dw, type.unroll.ch[_ch].wr);     \
+									       \
+		(void __iomem *)&__ch_regs->name;			       \
+	})
+
+#define REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, name) }
+
+#define CTX_REGISTER(dw, name, dir, ch) \
+	{ dw, #name, REGS_CH_ADDR(dw, name, dir, ch), dir, ch }
+
+#define WR_REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, wr_##name) }
+#define RD_REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, rd_##name) }
+
+#define WR_REGISTER_LEGACY(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.legacy.wr_##name) }
 #define RD_REGISTER_LEGACY(name) \
-	{ #name, REGS_ADDR(type.legacy.rd_##name) }
+	{ dw, #name, REGS_ADDR(dw, type.legacy.rd_##name) }
 
-#define WR_REGISTER_UNROLL(name) \
-	{ #name, REGS_ADDR(type.unroll.wr_##name) }
-#define RD_REGISTER_UNROLL(name) \
-	{ #name, REGS_ADDR(type.unroll.rd_##name) }
+#define WR_REGISTER_UNROLL(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.unroll.wr_##name) }
+#define RD_REGISTER_UNROLL(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.unroll.rd_##name) }
 
 #define WRITE_STR				"write"
 #define READ_STR				"read"
 #define CHANNEL_STR				"channel"
 #define REGISTERS_STR				"registers"
 
-static struct dw_edma				*dw;
-static struct dw_edma_v0_regs			__iomem *regs;
-
-static struct {
-	void					__iomem *start;
-	void					__iomem *end;
-} lim[2][EDMA_V0_MAX_NR_CH];
-
-struct debugfs_entries {
+struct dw_edma_debugfs_entry {
+	struct dw_edma				*dw;
 	const char				*name;
-	dma_addr_t				*reg;
+	void __iomem				*re