Add AMD MDB Endpoint and non-LL mode Support

index 3371e0a7..7549125 100644
@@ -17,12 +17,19 @@
 
 #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 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_BLOCK(a, b, c) \
 	{ \
 		.bar = a, \

@@ -50,6 +57,7 @@ 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 +98,91 @@ 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				= 0x00001000,	/*  4 Kbytes */
+	.rg.sz				= 0x00002000,	/*  8 Kbytes */
+	/* MDB memory linked list location */
+	.ll_wr = {
+		/* Channel 0 - BAR 2, offset 0 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00000000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 2 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00200000, 0x00000800)
+	},
+	.ll_rd = {
+		/* Channel 0 - BAR 2, offset 4 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00400000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 6 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00600000, 0x00000800)
+	},
+	/* MDB memory data location */
+	.dt_wr = {
+		/* Channel 0 - BAR 2, offset 8 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00800000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 9 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00900000, 0x00000800)
+	},
+	.dt_rd = {
+		/* Channel 0 - BAR 2, offset 10 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00a00000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 11 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00b00000, 0x00000800)
+	},
+	/* Other */
+	.mf				= EDMA_MF_HDMA_NATIVE,
+	.irqs				= 1,
+	.wr_ch_cnt			= 2,
+	.rd_ch_cnt			= 2,
+};
+
+static void dw_edma_set_chan_region_offset(struct dw_edma_pcie_data *pdata,
+					   enum pci_barno bar, off_t start_off,
+					   off_t off_gap, size_t size)
+{
+	u16 i;
+	off_t off;
+	u16 wr_ch = pdata->wr_ch_cnt;
+	u16 rd_ch = pdata->rd_ch_cnt;
+
+	if (wr_ch <= 2 || rd_ch <= 2)
+		return;
+
+	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 = size;
+		off += off_gap + size;
+	}
+
+	/* 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 = size;
+		off += off_gap + size;
+	}
+
+	/* 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 = size;
+		off += off_gap + size;
+	}
+
+	/* 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 = size;
+		off += off_gap + size;
+	}
+}
+
 static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
 {
 	return pci_irq_vector(to_pci_dev(dev), nr);

@@ -120,9 +213,22 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	u32 val, map;
 	u16 vsec;
 	u64 off;
+	u16 vendor = pdev->vendor;
+	int cap;
 
-	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_SYNOPSYS,
-					DW_PCIE_VSEC_DMA_ID);
+	/*
+	 * Synopsys and AMD (Xilinx) use the same VSEC ID for the purpose
+	 * of map, channel counts, etc.
+	 */
+	if (vendor != PCI_VENDOR_ID_SYNOPSYS &&
+	    vendor != PCI_VENDOR_ID_XILINX)
+		return;
+
+	cap = DW_PCIE_VSEC_DMA_ID;
+	if (vendor == PCI_VENDOR_ID_XILINX)
+		cap = DW_PCIE_XILINX_MDB_VSEC_DMA_ID;
+
+	vsec = pci_find_vsec_capability(pdev, vendor, cap);
 	if (!vsec)
 		return;
 

@@ -155,6 +261,24 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	off <<= 32;
 	off |= val;
 	pdata->rg.off = off;
+
+	/* AMD specific VSEC capability */
+	vsec = pci_find_vsec_capability(pdev, vendor,
+					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) != 0x20 ||
+	    PCI_VNDR_HEADER_REV(val) != 0x1)
+		return;
+
+	pci_read_config_dword(pdev, vsec + 0xc, &val);
+	off = val;
+	pci_read_config_dword(pdev, vsec + 0x8, &val);
+	off <<= 32;
+	off |= val;
+	pdata->devmem_phys_off = off;
 }
 
 static int dw_edma_pcie_probe(struct pci_dev *pdev,

@@ -179,6 +303,7 @@ 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 +311,22 @@ 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 -EINVAL;
+
+		/*
+		 * 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, 0x200000, 0x800);
+	}
+
 	/* Mapping PCI BAR regions */
 	mask = BIT(vsec_data->rg.bar);
 	for (i = 0; i < vsec_data->wr_ch_cnt; i++) {

@@ -367,6 +508,8 @@ 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);

index b43255f..3283ac5 100644
@@ -223,8 +223,28 @@ 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 nollp = 0;
+
+	if (WARN_ON(config->peripheral_config &&
+		    config->peripheral_size != sizeof(int)))
+		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)
+		nollp = *(int *)config->peripheral_config;
+
+	chan->nollp = false;
+	if (chan->dw->chip->nollp || (!chan->dw->chip->nollp && nollp))
+		chan->nollp = true;
+
 	chan->configured = true;
 
 	return 0;

@@ -353,7 +373,7 @@ 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 +439,11 @@ 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->nollp) {
+		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 +472,13 @@ 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->nollp) {
 			chunk = dw_edma_alloc_chunk(desc);
 			if (unlikely(!chunk))
 				goto err_alloc;

index 71894b9..2a4ad45 100644
@@ -86,6 +86,7 @@ struct dw_edma_chan {
 	u8				configured;
 
 	struct dma_slave_config		config;
+	bool				nollp;
 };
 
 struct dw_edma_irq {

index 7549125..68300fa 100644
@@ -281,6 +281,15 @@ 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)
 {

@@ -290,6 +299,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	struct dw_edma_chip *chip;
 	int err, nr_irqs;
 	int i, mask;
+	bool nollp = false;
 
 	vsec_data = kmalloc(sizeof(*vsec_data), GFP_KERNEL);
 	if (!vsec_data)

@@ -314,17 +324,21 @@ 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 -EINVAL;
+			nollp = 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, 0x200000, 0x800);
+		if (!nollp)
+			dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
+						       0x200000, 0x800);
 	}
 
 	/* Mapping PCI BAR regions */

@@ -372,6 +386,7 @@ 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->nollp = nollp;
 
 	chip->ll_wr_cnt = vsec_data->wr_ch_cnt;
 	chip->ll_rd_cnt = vsec_data->rd_ch_cnt;

@@ -380,7 +395,7 @@ 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 && !nollp; 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];

@@ -391,7 +406,8 @@ 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;
 

@@ -400,12 +416,13 @@ 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 && !nollp; 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];

@@ -416,7 +433,8 @@ 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;
 

@@ -425,7 +443,8 @@ 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;
 	}

74 lines not on this page · raw message

index 3080747..e14e16f 100644
@@ -99,6 +99,7 @@ struct dw_edma_chip {
 	enum dw_edma_map_format	mf;
 
 	struct dw_edma		*dw;
+	bool			nollp;
 };
 
 /* Export to the platform drivers */