[PATCH v2 5/5] PCI: endpoint: functions/pci-epf-test: Support PCI controller DMA

[Frank Li <Frank.Li@nxp.com>]

Designware provided DMA support in controller. This enabled use
this DMA controller to transfer data.

The whole flow align with standard DMA usage module

1. Using dma_request_channel() and filter function to find correct
RX and TX Channel.
2. dmaengine_slave_config() config remote side physcial address.
3. using dmaengine_prep_slave_single() create transfer descriptor
4. tx_submit();
5. dma_async_issue_pending();

Tested at i.MX8DXL platform.

root@imx8qmmek:~# /usr/bin/pcitest -d -w
WRITE ( 102400 bytes):          OKAY
root@imx8qmmek:~# /usr/bin/pcitest -d -r
READ ( 102400 bytes):           OKAY

WRITE => Size: 102400 bytes DMA: YES  Time: 0.000180145 seconds Rate: 555108 KB/s
READ => Size: 102400 bytes  DMA: YES  Time: 0.000194397 seconds Rate: 514411 KB/s

READ => Size: 102400 bytes  DMA: NO   Time: 0.013532597 seconds Rate: 7389 KB/s
WRITE => Size: 102400 bytes DMA: NO   Time: 0.000857090 seconds Rate: 116673 KB/s

Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
Change from v1 to v2
 - none

 drivers/pci/endpoint/functions/pci-epf-test.c | 106 ++++++++++++++++--
 1 file changed, 96 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 90d84d3bc868f..22ae420c30693 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -52,9 +52,11 @@ struct pci_epf_test {
 	enum pci_barno		test_reg_bar;
 	size_t			msix_table_offset;
 	struct delayed_work	cmd_handler;
-	struct dma_chan		*dma_chan;
+	struct dma_chan		*dma_chan_tx;
+	struct dma_chan		*dma_chan_rx;
 	struct completion	transfer_complete;
 	bool			dma_supported;
+	bool			dma_private;
 	const struct pci_epc_features *epc_features;
 };
 
@@ -105,14 +107,17 @@ static void pci_epf_test_dma_callback(void *param)
  */
 static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 				      dma_addr_t dma_dst, dma_addr_t dma_src,
-				      size_t len)
+				      size_t len, dma_addr_t remote,
+				      enum dma_transfer_direction dir)
 {
 	enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-	struct dma_chan *chan = epf_test->dma_chan;
+	struct dma_chan *chan = (dir == DMA_DEV_TO_MEM) ? epf_test->dma_chan_tx : epf_test->dma_chan_rx;
 	struct pci_epf *epf = epf_test->epf;
 	struct dma_async_tx_descriptor *tx;
 	struct device *dev = &epf->dev;
 	dma_cookie_t cookie;
+	struct dma_slave_config	sconf;
+	dma_addr_t local = (dir == DMA_MEM_TO_DEV) ? dma_src : dma_dst;
 	int ret;
 
 	if (IS_ERR_OR_NULL(chan)) {
@@ -120,7 +125,20 @@ static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 		return -EINVAL;
 	}
 
-	tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags);
+	if (epf_test->dma_private) {
+		memset(&sconf, 0, sizeof(sconf));
+		sconf.direction = dir;
+		if (dir == DMA_MEM_TO_DEV)
+			sconf.dst_addr = remote;
+		else
+			sconf.src_addr = remote;
+
+		dmaengine_slave_config(chan, &sconf);
+		tx = dmaengine_prep_slave_single(chan, local, len, dir, flags);
+	} else {
+		tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags);
+	}
+
 	if (!tx) {
 		dev_err(dev, "Failed to prepare DMA memcpy\n");
 		return -EIO;
@@ -148,6 +166,23 @@ static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 	return 0;
 }
 
+struct epf_dma_filter {
+	struct device *dev;
+	u32 dma_mask;
+};
+
+static bool epf_dma_filter_fn(struct dma_chan *chan, void *node)
+{
+	struct epf_dma_filter *filter = node;
+	struct dma_slave_caps caps;
+
+	memset(&caps, 0, sizeof(caps));
+	dma_get_slave_caps(chan, &caps);
+
+	return chan->device->dev == filter->dev
+		&& (filter->dma_mask & caps.directions);
+}
+
 /**
  * pci_epf_test_init_dma_chan() - Function to initialize EPF test DMA channel
  * @epf_test: the EPF test device that performs data transfer operation
@@ -160,8 +195,42 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test)
 	struct device *dev = &epf->dev;
 	struct dma_chan *dma_chan;
 	dma_cap_mask_t mask;
+	struct epf_dma_filter filter;
 	int ret;
 
+	filter.dev = epf->epc->dev.parent;
+	filter.dma_mask = BIT(DMA_DEV_TO_MEM);
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+	if (IS_ERR(dma_chan)) {
+		dev_info(dev, "Failure get built-in DMA channel, fail back to try allocate general DMA channel\n");
+		goto fail_back_tx;
+	}
+
+	epf_test->dma_chan_rx = dma_chan;
+
+	filter.dma_mask = BIT(DMA_MEM_TO_DEV);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+
+	if (IS_ERR(dma_chan)) {
+		dev_info(dev, "Failure get built-in DMA channel, fail back to try allocate general DMA channel\n");
+		goto fail_back_rx;
+	}
+
+	epf_test->dma_chan_tx = dma_chan;
+	epf_test->dma_private = true;
+
+	init_completion(&epf_test->transfer_complete);
+
+	return 0;
+
+fail_back_rx:
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_tx = NULL;
+
+fail_back_tx:
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_MEMCPY, mask);
 
@@ -174,7 +243,7 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test)
 	}
 	init_completion(&epf_test->transfer_complete);
 
-	epf_test->dma_chan = dma_chan;
+	epf_test->dma_chan_tx = epf_test->dma_chan_rx = dma_chan;
 
 	return 0;
 }
@@ -190,8 +259,17 @@ static void pci_epf_test_clean_dma_chan(struct pci_epf_test *epf_test)
 	if (!epf_test->dma_supported)
 		return;
 
-	dma_release_channel(epf_test->dma_chan);
-	epf_test->dma_chan = NULL;
+	dma_release_channel(epf_test->dma_chan_tx);
+	if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) {
+		epf_test->dma_chan_tx = NULL;
+		epf_test->dma_chan_rx = NULL;
+		return;
+	}
+
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_rx = NULL;
+
+	return;
 }
 
 static void pci_epf_test_print_rate(const char *ops, u64 size,
@@ -280,8 +358,14 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 			goto err_map_addr;
 		}
 
+		if (epf_test->dma_private) {
+			dev_err(dev, "Cannot transfer data using DMA\n");
+			ret = -EINVAL;
+			goto err_map_addr;
+		}
+
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size, 0, DMA_MEM_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 	} else {
@@ -363,7 +447,8 @@ static int pci_epf_test_read(struct pci_epf_test *epf_test)
 
 		ktime_get_ts64(&start);
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 phys_addr, reg->size);
+						 phys_addr, reg->size,
+						 reg->src_addr, DMA_DEV_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
@@ -453,8 +538,9 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
 		}
 
 		ktime_get_ts64(&start);
+
 		ret = pci_epf_test_data_transfer(epf_test, phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size, reg->dst_addr, DMA_MEM_TO_DEV);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
-- 
2.24.0.rc1