[PATCH RESEND v6 0/2] Add AMD MDB Endpoint and non-LL mode Support

[PATCH RESEND v6 0/2] Add AMD MDB Endpoint and non-LL mode Support

[Devendra K Verma]

This series of patch support the following:

 - AMD MDB Endpoint Support, as part of this patch following are
   added:
   o AMD supported device ID and vendor ID (Xilinx)
   o AMD MDB specific driver data
   o AMD specific VSEC capabilities to retrieve the base of
     phys address of MDB side DDR
   o Logic to assign the offsets to LL and data blocks if
     more number of channels are enabled than configured
     in the given pci_data struct.

 - Addition of non-LL mode
   o The IP supported non-LL mode functions
   o Flexibility to choose non-LL mode via dma_slave_config
     param peripheral_config, by the client for all the vendors
     using HDMA IP.
   o Allow IP utilization if LL mode is not available

Devendra K Verma (2):
  dmaengine: dw-edma: Add AMD MDB Endpoint Support
  dmaengine: dw-edma: Add non-LL mode

 drivers/dma/dw-edma/dw-edma-core.c    |  41 ++++++++-
 drivers/dma/dw-edma/dw-edma-core.h    |   1 +
 drivers/dma/dw-edma/dw-edma-pcie.c    | 169 ++++++++++++++++++++++++++++++++--
 drivers/dma/dw-edma/dw-hdma-v0-core.c |  61 +++++++++++-
 drivers/dma/dw-edma/dw-hdma-v0-regs.h |   1 +
 include/linux/dma/edma.h              |   1 +
 6 files changed, 260 insertions(+), 14 deletions(-)

-- 
1.8.3.1

[PATCH RESEND v6 1/2] dmaengine: dw-edma: Add AMD MDB Endpoint Support

[Devendra K Verma]

AMD MDB PCIe endpoint support. For AMD specific support
added the following
  - AMD supported PCIe Device IDs and Vendor ID (Xilinx).
  - AMD MDB specific driver data
  - AMD MDB specific VSEC capability to retrieve the device DDR
    base address.

Signed-off-by: Devendra K Verma <devendra.verma@amd.com>
---
Changes in v6:
Included "sizes.h" header and used the appropriate
definitions instead of constants.

Changes in v5:
Added the definitions for Xilinx specific VSEC header id,
revision, and register offsets.
Corrected the error type when no physical offset found for
device side memory.
Corrected the order of variables.

Changes in v4:
Configured 8 read and 8 write channels for Xilinx vendor
Added checks to validate vendor ID for vendor
specific vsec id.
Added Xilinx specific vendor id for vsec specific to Xilinx
Added the LL and data region offsets, size as input params to
function dw_edma_set_chan_region_offset().
Moved the LL and data region offsets assignment to function
for Xilinx specific case.
Corrected comments.

Changes in v3:
Corrected a typo when assigning AMD (Xilinx) vsec id macro
and condition check.

Changes in v2:
Reverted the devmem_phys_off type to u64.
Renamed the function appropriately to suit the
functionality for setting the LL & data region offsets.

Changes in v1:
Removed the pci device id from pci_ids.h file.
Added the vendor id macro as per the suggested method.
Changed the type of the newly added devmem_phys_off variable.
Added to logic to assign offsets for LL and data region blocks
in case more number of channels are enabled than given in
amd_mdb_data struct.
---
 drivers/dma/dw-edma/dw-edma-pcie.c | 139 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 137 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 3371e0a7..3d7247c 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -14,15 +14,31 @@
 #include <linux/pci-epf.h>
 #include <linux/msi.h>
 #include <linux/bitfield.h>
+#include <linux/sizes.h>
 
 #include "dw-edma-core.h"
 
+/* Synopsys */
 #define DW_PCIE_VSEC_DMA_ID			0x6
 #define DW_PCIE_VSEC_DMA_BAR			GENMASK(10, 8)
 #define DW_PCIE_VSEC_DMA_MAP			GENMASK(2, 0)
 #define DW_PCIE_VSEC_DMA_WR_CH			GENMASK(9, 0)
 #define DW_PCIE_VSEC_DMA_RD_CH			GENMASK(25, 16)
 
+/* AMD MDB (Xilinx) specific defines */
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_ID		0x6
+#define DW_PCIE_XILINX_MDB_VSEC_ID		0x20
+#define PCI_DEVICE_ID_AMD_MDB_B054		0xb054
+#define DW_PCIE_AMD_MDB_INVALID_ADDR		(~0ULL)
+#define DW_PCIE_XILINX_LL_OFF_GAP		0x200000
+#define DW_PCIE_XILINX_LL_SIZE			0x800
+#define DW_PCIE_XILINX_DT_OFF_GAP		0x100000
+#define DW_PCIE_XILINX_DT_SIZE			0x800
+#define DW_PCIE_XILINX_MDB_VSEC_HDR_ID		0x20
+#define DW_PCIE_XILINX_MDB_VSEC_REV		0x1
+#define DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_HIGH	0xc
+#define DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_LOW	0x8
+
 #define DW_BLOCK(a, b, c) \
 	{ \
 		.bar = a, \
@@ -50,6 +66,7 @@ struct dw_edma_pcie_data {
 	u8				irqs;
 	u16				wr_ch_cnt;
 	u16				rd_ch_cnt;
+	u64				devmem_phys_off;
 };
 
 static const struct dw_edma_pcie_data snps_edda_data = {
@@ -90,6 +107,64 @@ struct dw_edma_pcie_data {
 	.rd_ch_cnt			= 2,
 };
 
+static const struct dw_edma_pcie_data amd_mdb_data = {
+	/* MDB registers location */
+	.rg.bar				= BAR_0,
+	.rg.off				= SZ_4K,	/*  4 Kbytes */
+	.rg.sz				= SZ_8K,	/*  8 Kbytes */
+
+	/* Other */
+	.mf				= EDMA_MF_HDMA_NATIVE,
+	.irqs				= 1,
+	.wr_ch_cnt			= 8,
+	.rd_ch_cnt			= 8,
+};
+
+static void dw_edma_set_chan_region_offset(struct dw_edma_pcie_data *pdata,
+					   enum pci_barno bar, off_t start_off,
+					   off_t ll_off_gap, size_t ll_size,
+					   off_t dt_off_gap, size_t dt_size)
+{
+	u16 wr_ch = pdata->wr_ch_cnt;
+	u16 rd_ch = pdata->rd_ch_cnt;
+	off_t off;
+	u16 i;
+
+	off = start_off;
+
+	/* Write channel LL region */
+	for (i = 0; i < wr_ch; i++) {
+		pdata->ll_wr[i].bar = bar;
+		pdata->ll_wr[i].off = off;
+		pdata->ll_wr[i].sz = ll_size;
+		off += ll_off_gap;
+	}
+
+	/* Read channel LL region */
+	for (i = 0; i < rd_ch; i++) {
+		pdata->ll_rd[i].bar = bar;
+		pdata->ll_rd[i].off = off;
+		pdata->ll_rd[i].sz = ll_size;
+		off += ll_off_gap;
+	}
+
+	/* Write channel data region */
+	for (i = 0; i < wr_ch; i++) {
+		pdata->dt_wr[i].bar = bar;
+		pdata->dt_wr[i].off = off;
+		pdata->dt_wr[i].sz = dt_size;
+		off += dt_off_gap;
+	}
+
+	/* Read channel data region */
+	for (i = 0; i < rd_ch; i++) {
+		pdata->dt_rd[i].bar = bar;
+		pdata->dt_rd[i].off = off;
+		pdata->dt_rd[i].sz = dt_size;
+		off += dt_off_gap;
+	}
+}
+
 static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
 {
 	return pci_irq_vector(to_pci_dev(dev), nr);
@@ -120,9 +195,24 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	u32 val, map;
 	u16 vsec;
 	u64 off;
+	int cap;
+
+	/*
+	 * Synopsys and AMD (Xilinx) use the same VSEC ID for the purpose
+	 * of map, channel counts, etc.
+	 */
+	switch (pdev->vendor) {
+	case PCI_VENDOR_ID_SYNOPSYS:
+		cap = DW_PCIE_VSEC_DMA_ID;
+		break;
+	case PCI_VENDOR_ID_XILINX:
+		cap = DW_PCIE_XILINX_MDB_VSEC_DMA_ID;
+		break;
+	default:
+		return;
+	}
 
-	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_SYNOPSYS,
-					DW_PCIE_VSEC_DMA_ID);
+	vsec = pci_find_vsec_capability(pdev, pdev->vendor, cap);
 	if (!vsec)
 		return;
 
@@ -155,6 +245,28 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	off <<= 32;
 	off |= val;
 	pdata->rg.off = off;
+
+	/* Xilinx specific VSEC capability */
+	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_XILINX,
+					DW_PCIE_XILINX_MDB_VSEC_ID);
+	if (!vsec)
+		return;
+
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	if (PCI_VNDR_HEADER_ID(val) != DW_PCIE_XILINX_MDB_VSEC_HDR_ID ||
+	    PCI_VNDR_HEADER_REV(val) != DW_PCIE_XILINX_MDB_VSEC_REV)
+		return;
+
+	pci_read_config_dword(pdev,
+			      vsec + DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_HIGH,
+			      &val);
+	off = val;
+	pci_read_config_dword(pdev,
+			      vsec + DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_LOW,
+			      &val);
+	off <<= 32;
+	off |= val;
+	pdata->devmem_phys_off = off;
 }
 
 static int dw_edma_pcie_probe(struct pci_dev *pdev,
@@ -179,6 +291,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	}
 
 	memcpy(vsec_data, pdata, sizeof(struct dw_edma_pcie_data));
+	vsec_data->devmem_phys_off = DW_PCIE_AMD_MDB_INVALID_ADDR;
 
 	/*
 	 * Tries to find if exists a PCIe Vendor-Specific Extended Capability
@@ -186,6 +299,26 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	 */
 	dw_edma_pcie_get_vsec_dma_data(pdev, vsec_data);
 
+	if (pdev->vendor == PCI_VENDOR_ID_XILINX) {
+		/*
+		 * There is no valid address found for the LL memory
+		 * space on the device side.
+		 */
+		if (vsec_data->devmem_phys_off == DW_PCIE_AMD_MDB_INVALID_ADDR)
+			return -ENOMEM;
+
+		/*
+		 * Configure the channel LL and data blocks if number of
+		 * channels enabled in VSEC capability are more than the
+		 * channels configured in amd_mdb_data.
+		 */
+		dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
+					       DW_PCIE_XILINX_LL_OFF_GAP,
+					       DW_PCIE_XILINX_LL_SIZE,
+					       DW_PCIE_XILINX_DT_OFF_GAP,
+					       DW_PCIE_XILINX_DT_SIZE);
+	}
+
 	/* Mapping PCI BAR regions */
 	mask = BIT(vsec_data->rg.bar);
 	for (i = 0; i < vsec_data->wr_ch_cnt; i++) {
@@ -367,6 +500,8 @@ static void dw_edma_pcie_remove(struct pci_dev *pdev)
 
 static const struct pci_device_id dw_edma_pcie_id_table[] = {
 	{ PCI_DEVICE_DATA(SYNOPSYS, EDDA, &snps_edda_data) },
+	{ PCI_VDEVICE(XILINX, PCI_DEVICE_ID_AMD_MDB_B054),
+	  (kernel_ulong_t)&amd_mdb_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, dw_edma_pcie_id_table);
-- 
1.8.3.1

[PATCH RESEND v6 2/2] dmaengine: dw-edma: Add non-LL mode

[Devendra K Verma]

AMD MDB IP supports Linked List (LL) mode as well as non-LL mode.
The current code does not have the mechanisms to enable the
DMA transactions using the non-LL mode. The following two cases
are added with this patch:
- When a valid physical base address is not configured via the
  Xilinx VSEC capability then the IP can still be used in non-LL
  mode. The default mode for all the DMA transactions and for all
  the DMA channels then is non-LL mode.
- When a valid physical base address is configured but the client
  wants to use the non-LL mode for DMA transactions then also the
  flexibility is provided via the peripheral_config struct member of
  dma_slave_config. In this case the channels can be individually
  configured in non-LL mode. This use case is desirable for single
  DMA transfer of a chunk, this saves the effort of preparing the
  Link List. This particular scenario is applicable to AMD as well
  as Synopsys IP.

Signed-off-by: Devendra K Verma <devendra.verma@amd.com>
---
Changes in v6
  Gave definition to bits used for channel configuration.
  Removed the comment related to doorbell.

Changes in v5
  Variable name 'nollp' changed to 'non_ll'.
  In the dw_edma_device_config() WARN_ON replaced with dev_err().
  Comments follow the 80-column guideline.

Changes in v4
  No change

Changes in v3
  No change

Changes in v2
  Reverted the function return type to u64 for
  dw_edma_get_phys_addr().

Changes in v1
  Changed the function return type for dw_edma_get_phys_addr().
  Corrected the typo raised in review.
---
 drivers/dma/dw-edma/dw-edma-core.c    | 41 ++++++++++++++++++++---
 drivers/dma/dw-edma/dw-edma-core.h    |  1 +
 drivers/dma/dw-edma/dw-edma-pcie.c    | 44 +++++++++++++++++--------
 drivers/dma/dw-edma/dw-hdma-v0-core.c | 61 ++++++++++++++++++++++++++++++++++-
 drivers/dma/dw-edma/dw-hdma-v0-regs.h |  1 +
 include/linux/dma/edma.h              |  1 +
 6 files changed, 130 insertions(+), 19 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index b43255f..60a3279 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -223,8 +223,31 @@ static int dw_edma_device_config(struct dma_chan *dchan,
 				 struct dma_slave_config *config)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	int non_ll = 0;
+
+	if (config->peripheral_config &&
+	    config->peripheral_size != sizeof(int)) {
+		dev_err(dchan->device->dev,
+			"config param peripheral size mismatch\n");
+		return -EINVAL;
+	}
 
 	memcpy(&chan->config, config, sizeof(*config));
+
+	/*
+	 * When there is no valid LLP base address available then the default
+	 * DMA ops will use the non-LL mode.
+	 * Cases where LL mode is enabled and client wants to use the non-LL
+	 * mode then also client can do so via providing the peripheral_config
+	 * param.
+	 */
+	if (config->peripheral_config)
+		non_ll = *(int *)config->peripheral_config;
+
+	chan->non_ll = false;
+	if (chan->dw->chip->non_ll || (!chan->dw->chip->non_ll && non_ll))
+		chan->non_ll = true;
+
 	chan->configured = true;
 
 	return 0;
@@ -353,7 +376,7 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan)
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
 	enum dma_transfer_direction dir = xfer->direction;
 	struct scatterlist *sg = NULL;
-	struct dw_edma_chunk *chunk;
+	struct dw_edma_chunk *chunk = NULL;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
 	u64 src_addr, dst_addr;
@@ -419,9 +442,11 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan)
 	if (unlikely(!desc))
 		goto err_alloc;
 
-	chunk = dw_edma_alloc_chunk(desc);
-	if (unlikely(!chunk))
-		goto err_alloc;
+	if (!chan->non_ll) {
+		chunk = dw_edma_alloc_chunk(desc);
+		if (unlikely(!chunk))
+			goto err_alloc;
+	}
 
 	if (xfer->type == EDMA_XFER_INTERLEAVED) {
 		src_addr = xfer->xfer.il->src_start;
@@ -450,7 +475,13 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan)
 		if (xfer->type == EDMA_XFER_SCATTER_GATHER && !sg)
 			break;
 
-		if (chunk->bursts_alloc == chan->ll_max) {
+		/*
+		 * For non-LL mode, only a single burst can be handled
+		 * in a single chunk unlike LL mode where multiple bursts
+		 * can be configured in a single chunk.
+		 */
+		if ((chunk && chunk->bursts_alloc == chan->ll_max) ||
+		    chan->non_ll) {
 			chunk = dw_edma_alloc_chunk(desc);
 			if (unlikely(!chunk))
 				goto err_alloc;
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 71894b9..c8e3d19 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -86,6 +86,7 @@ struct dw_edma_chan {
 	u8				configured;
 
 	struct dma_slave_config		config;
+	bool				non_ll;
 };
 
 struct dw_edma_irq {
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 3d7247c..e7e95df 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -269,6 +269,15 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	pdata->devmem_phys_off = off;
 }
 
+static u64 dw_edma_get_phys_addr(struct pci_dev *pdev,
+				 struct dw_edma_pcie_data *pdata,
+				 enum pci_barno bar)
+{
+	if (pdev->vendor == PCI_VENDOR_ID_XILINX)
+		return pdata->devmem_phys_off;
+	return pci_bus_address(pdev, bar);
+}
+
 static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *pid)
 {
@@ -278,6 +287,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	struct dw_edma_chip *chip;
 	int err, nr_irqs;
 	int i, mask;
+	bool non_ll = false;
 
 	vsec_data = kmalloc(sizeof(*vsec_data), GFP_KERNEL);
 	if (!vsec_data)
@@ -302,21 +312,24 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	if (pdev->vendor == PCI_VENDOR_ID_XILINX) {
 		/*
 		 * There is no valid address found for the LL memory
-		 * space on the device side.
+		 * space on the device side. In the absence of LL base
+		 * address use the non-LL mode or simple mode supported by
+		 * the HDMA IP.
 		 */
 		if (vsec_data->devmem_phys_off == DW_PCIE_AMD_MDB_INVALID_ADDR)
-			return -ENOMEM;
+			non_ll = true;
 
 		/*
 		 * Configure the channel LL and data blocks if number of
 		 * channels enabled in VSEC capability are more than the
 		 * channels configured in amd_mdb_data.
 		 */
-		dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
-					       DW_PCIE_XILINX_LL_OFF_GAP,
-					       DW_PCIE_XILINX_LL_SIZE,
-					       DW_PCIE_XILINX_DT_OFF_GAP,
-					       DW_PCIE_XILINX_DT_SIZE);
+		if (!non_ll)
+			dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
+						       DW_PCIE_XILINX_LL_OFF_GAP,
+						       DW_PCIE_XILINX_LL_SIZE,
+						       DW_PCIE_XILINX_DT_OFF_GAP,
+						       DW_PCIE_XILINX_DT_SIZE);
 	}
 
 	/* Mapping PCI BAR regions */
@@ -364,6 +377,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	chip->mf = vsec_data->mf;
 	chip->nr_irqs = nr_irqs;
 	chip->ops = &dw_edma_pcie_plat_ops;
+	chip->non_ll = non_ll;
 
 	chip->ll_wr_cnt = vsec_data->wr_ch_cnt;
 	chip->ll_rd_cnt = vsec_data->rd_ch_cnt;
@@ -372,7 +386,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	if (!chip->reg_base)
 		return -ENOMEM;
 
-	for (i = 0; i < chip->ll_wr_cnt; i++) {
+	for (i = 0; i < chip->ll_wr_cnt && !non_ll; i++) {
 		struct dw_edma_region *ll_region = &chip->ll_region_wr[i];
 		struct dw_edma_region *dt_region = &chip->dt_region_wr[i];
 		struct dw_edma_block *ll_block = &vsec_data->ll_wr[i];
@@ -383,7 +397,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		ll_region->vaddr.io += ll_block->off;
-		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
+		ll_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
@@ -392,12 +407,13 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		dt_region->vaddr.io += dt_block->off;
-		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
+		dt_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
 
-	for (i = 0; i < chip->ll_rd_cnt; i++) {
+	for (i = 0; i < chip->ll_rd_cnt && !non_ll; i++) {
 		struct dw_edma_region *ll_region = &chip->ll_region_rd[i];
 		struct dw_edma_region *dt_region = &chip->dt_region_rd[i];
 		struct dw_edma_block *ll_block = &vsec_data->ll_rd[i];
@@ -408,7 +424,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		ll_region->vaddr.io += ll_block->off;
-		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
+		ll_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
@@ -417,7 +434,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		dt_region->vaddr.io += dt_block->off;
-		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
+		dt_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index e3f8db4..ee31c9a 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -225,7 +225,7 @@ static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
 		readl(chunk->ll_region.vaddr.io);
 }
 
-static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+static void dw_hdma_v0_core_ll_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma *dw = chan->dw;
@@ -263,6 +263,65 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
 }
 
+static void dw_hdma_v0_core_non_ll_start(struct dw_edma_chunk *chunk)
+{
+	struct dw_edma_chan *chan = chunk->chan;
+	struct dw_edma *dw = chan->dw;
+	struct dw_edma_burst *child;
+	u32 val;
+
+	list_for_each_entry(child, &chunk->burst->list, list) {
+		SET_CH_32(dw, chan->dir, chan->id, ch_en, HDMA_V0_CH_EN);
+
+		/* Source address */
+		SET_CH_32(dw, chan->dir, chan->id, sar.lsb,
+			  lower_32_bits(child->sar));
+		SET_CH_32(dw, chan->dir, chan->id, sar.msb,
+			  upper_32_bits(child->sar));
+
+		/* Destination address */
+		SET_CH_32(dw, chan->dir, chan->id, dar.lsb,
+			  lower_32_bits(child->dar));
+		SET_CH_32(dw, chan->dir, chan->id, dar.msb,
+			  upper_32_bits(child->dar));
+
+		/* Transfer size */
+		SET_CH_32(dw, chan->dir, chan->id, transfer_size, child->sz);
+
+		/* Interrupt setup */
+		val = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
+				HDMA_V0_STOP_INT_MASK |
+				HDMA_V0_ABORT_INT_MASK |
+				HDMA_V0_LOCAL_STOP_INT_EN |
+				HDMA_V0_LOCAL_ABORT_INT_EN;
+
+		if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL)) {
+			val |= HDMA_V0_REMOTE_STOP_INT_EN |
+			       HDMA_V0_REMOTE_ABORT_INT_EN;
+		}
+
+		SET_CH_32(dw, chan->dir, chan->id, int_setup, val);
+
+		/* Channel control setup */
+		val = GET_CH_32(dw, chan->dir, chan->id, control1);
+		val &= ~HDMA_V0_LINKLIST_EN;
+		SET_CH_32(dw, chan->dir, chan->id, control1, val);
+
+		SET_CH_32(dw, chan->dir, chan->id, doorbell,
+			  HDMA_V0_DOORBELL_START);
+	}
+}
+
+static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+{
+	struct dw_edma_chan *chan = chunk->chan;
+
+	if (!chan->non_ll)
+		dw_hdma_v0_core_ll_start(chunk, first);
+	else
+		dw_hdma_v0_core_non_ll_start(chunk);
+}
+
 static void dw_hdma_v0_core_ch_config(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
index eab5fd7..7759ba9 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -12,6 +12,7 @@
 #include <linux/dmaengine.h>
 
 #define HDMA_V0_MAX_NR_CH			8
+#define HDMA_V0_CH_EN				BIT(0)
 #define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
 #define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
 #define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index 3080747..78ce31b 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -99,6 +99,7 @@ struct dw_edma_chip {
 	enum dw_edma_map_format	mf;
 
 	struct dw_edma		*dw;
+	bool			non_ll;
 };
 
 /* Export to the platform drivers */
-- 
1.8.3.1

[PATCH RESEND v6 0/2] Add AMD MDB Endpoint and non-LL mode Support

[Devendra K Verma]

This series of patch support the following:

 - AMD MDB Endpoint Support, as part of this patch following are
   added:
   o AMD supported device ID and vendor ID (Xilinx)
   o AMD MDB specific driver data
   o AMD specific VSEC capabilities to retrieve the base of
     phys address of MDB side DDR
   o Logic to assign the offsets to LL and data blocks if
     more number of channels are enabled than configured
     in the given pci_data struct.

 - Addition of non-LL mode
   o The IP supported non-LL mode functions
   o Flexibility to choose non-LL mode via dma_slave_config
     param peripheral_config, by the client for all the vendors
     using HDMA IP.
   o Allow IP utilization if LL mode is not available

Devendra K Verma (2):
  dmaengine: dw-edma: Add AMD MDB Endpoint Support
  dmaengine: dw-edma: Add non-LL mode

 drivers/dma/dw-edma/dw-edma-core.c    |  41 ++++++++-
 drivers/dma/dw-edma/dw-edma-core.h    |   1 +
 drivers/dma/dw-edma/dw-edma-pcie.c    | 169 ++++++++++++++++++++++++++++++++--
 drivers/dma/dw-edma/dw-hdma-v0-core.c |  61 +++++++++++-
 drivers/dma/dw-edma/dw-hdma-v0-regs.h |   1 +
 include/linux/dma/edma.h              |   1 +
 6 files changed, 260 insertions(+), 14 deletions(-)

-- 
1.8.3.1