[PATCH net-next v9 07/15] net: lan966x: use a dedicated device for DMA operations

[Daniel Machon <daniel.machon@microchip.com>]

In preparation for the PCIe FDMA implementation, add lan966x->dma_dev,
resolved once at probe time, and use it for every DMA operation the
FDMA path performs: coherent allocations, streaming mappings and the RX
page pool. Natively, dma_dev is lan966x->dev, so there is no functional
change.

Since dma_dev differs from dev only on the PCIe path, add
lan966x_is_pci() on top of it, for the later PCIe patches to key off.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Simon Horman <horms@kernel.org>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 30 +++++++++++-----------
 .../net/ethernet/microchip/lan966x/lan966x_main.c  | 16 ++++++++++++
 .../net/ethernet/microchip/lan966x/lan966x_main.h  | 10 ++++++++
 3 files changed, 41 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 651ea03eede7..ae6e5aec5e13 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -80,7 +80,7 @@ static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.pool_size = rx->fdma.n_dcbs,
 		.nid = NUMA_NO_NODE,
-		.dev = lan966x->dev,
+		.dev = lan966x->dma_dev,
 		.dma_dir = DMA_FROM_DEVICE,
 		.offset = XDP_PACKET_HEADROOM,
 		.max_len = rx->max_mtu -
@@ -126,7 +126,7 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 	if (err)
 		return err;
 
-	err = fdma_alloc_coherent(lan966x->dev, fdma);
+	err = fdma_alloc_coherent(lan966x->dma_dev, fdma);
 	if (err) {
 		page_pool_destroy(rx->page_pool);
 		return err;
@@ -210,7 +210,7 @@ static int lan966x_fdma_tx_alloc(struct lan966x_tx *tx)
 	if (!tx->dcbs_buf)
 		return -ENOMEM;
 
-	err = fdma_alloc_coherent(lan966x->dev, fdma);
+	err = fdma_alloc_coherent(lan966x->dma_dev, fdma);
 	if (err)
 		goto out;
 
@@ -230,7 +230,7 @@ static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 	struct lan966x *lan966x = tx->lan966x;
 
 	kfree(tx->dcbs_buf);
-	fdma_free_coherent(lan966x->dev, &tx->fdma);
+	fdma_free_coherent(lan966x->dma_dev, &tx->fdma);
 }
 
 static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
@@ -355,7 +355,7 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 
 		dcb_buf->used = false;
 		if (dcb_buf->use_skb) {
-			dma_unmap_single(lan966x->dev,
+			dma_unmap_single(lan966x->dma_dev,
 					 dcb_buf->dma_addr,
 					 dcb_buf->len,
 					 DMA_TO_DEVICE);
@@ -364,7 +364,7 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 				napi_consume_skb(dcb_buf->data.skb, weight);
 		} else {
 			if (dcb_buf->xdp_ndo)
-				dma_unmap_single(lan966x->dev,
+				dma_unmap_single(lan966x->dma_dev,
 						 dcb_buf->dma_addr,
 						 dcb_buf->len,
 						 DMA_TO_DEVICE);
@@ -400,7 +400,7 @@ static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port)
 	if (unlikely(!page))
 		return FDMA_ERROR;
 
-	dma_sync_single_for_cpu(lan966x->dev,
+	dma_sync_single_for_cpu(lan966x->dma_dev,
 				(dma_addr_t)fdma_db_dataptr_get(db) +
 				XDP_PACKET_HEADROOM,
 				fdma_db_len_get(db),
@@ -636,11 +636,11 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 		lan966x_ifh_set_bypass(ifh, 1);
 		lan966x_ifh_set_port(ifh, BIT_ULL(port->chip_port));
 
-		dma_addr = dma_map_single(lan966x->dev,
+		dma_addr = dma_map_single(lan966x->dma_dev,
 					  xdpf->data - IFH_LEN_BYTES,
 					  xdpf->len + IFH_LEN_BYTES,
 					  DMA_TO_DEVICE);
-		if (dma_mapping_error(lan966x->dev, dma_addr)) {
+		if (dma_mapping_error(lan966x->dma_dev, dma_addr)) {
 			ret = NETDEV_TX_OK;
 			goto out;
 		}
@@ -656,7 +656,7 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 		lan966x_ifh_set_port(ifh, BIT_ULL(port->chip_port));
 
 		dma_addr = page_pool_get_dma_addr(page);
-		dma_sync_single_for_device(lan966x->dev,
+		dma_sync_single_for_device(lan966x->dma_dev,
 					   dma_addr + XDP_PACKET_HEADROOM,
 					   len + IFH_LEN_BYTES,
 					   DMA_TO_DEVICE);
@@ -735,9 +735,9 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 	memcpy(skb->data, ifh, IFH_LEN_BYTES);
 	skb_put(skb, 4);
 
-	dma_addr = dma_map_single(lan966x->dev, skb->data, skb->len,
+	dma_addr = dma_map_single(lan966x->dma_dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
-	if (dma_mapping_error(lan966x->dev, dma_addr)) {
+	if (dma_mapping_error(lan966x->dma_dev, dma_addr)) {
 		dev->stats.tx_dropped++;
 		err = NETDEV_TX_OK;
 		goto release;
@@ -843,7 +843,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 			page_pool_put_full_page(page_pool,
 						old_pages[i][j], false);
 
-	fdma_free_coherent(lan966x->dev, &fdma_rx_old);
+	fdma_free_coherent(lan966x->dma_dev, &fdma_rx_old);
 
 	page_pool_destroy(page_pool);
 
@@ -993,7 +993,7 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 
 	err = lan966x_fdma_tx_alloc(&lan966x->tx);
 	if (err) {
-		fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma);
+		fdma_free_coherent(lan966x->dma_dev, &lan966x->rx.fdma);
 		page_pool_destroy(lan966x->rx.page_pool);
 		return err;
 	}
@@ -1015,7 +1015,7 @@ void lan966x_fdma_deinit(struct lan966x *lan966x)
 	napi_disable(&lan966x->napi);
 
 	lan966x_fdma_rx_free_pages(&lan966x->rx);
-	fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma);
+	fdma_free_coherent(lan966x->dma_dev, &lan966x->rx.fdma);
 	page_pool_destroy(lan966x->rx.page_pool);
 	lan966x_fdma_tx_free(&lan966x->tx);
 }
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 1179a6e127c5..2741f7c9fa4c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -7,6 +7,7 @@
 #include <linux/ip.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/pci.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
@@ -1081,6 +1082,20 @@ static int lan966x_reset_switch(struct lan966x *lan966x)
 	return 0;
 }
 
+/* When enumerated over PCIe, dev is a platform device with no
+ * iommus/dma-ranges of its own, so DMA must target the PCIe endpoint instead.
+ * The result differs from dev only in that case; lan966x_is_pci() relies on it.
+ */
+static struct device *lan966x_get_dma_dev(struct device *dev)
+{
+	for (struct device *p = dev->parent; p; p = p->parent) {
+		if (dev_is_pci(p))
+			return p;
+	}
+
+	return dev;
+}
+
 static int lan966x_probe(struct platform_device *pdev)
 {
 	struct fwnode_handle *ports, *portnp;
@@ -1094,6 +1109,7 @@ static int lan966x_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, lan966x);
 	lan966x->dev = &pdev->dev;
+	lan966x->dma_dev = lan966x_get_dma_dev(lan966x->dev);
 
 	if (!device_get_mac_address(&pdev->dev, mac_addr)) {
 		ether_addr_copy(lan966x->base_mac, mac_addr);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 83c361abb789..3f09f8ddf620 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -270,6 +270,9 @@ struct lan966x_skb_cb {
 struct lan966x {
 	struct device *dev;
 
+	/* Device used for DMA; the PCIe endpoint when enumerated over PCIe. */
+	struct device *dma_dev;
+
 	u8 num_phys_ports;
 	struct lan966x_port **ports;
 
@@ -573,6 +576,13 @@ void lan966x_fdma_wakeup_netdev(struct lan966x *lan966x);
 int lan966x_fdma_get_max_frame(struct lan966x *lan966x);
 int lan966x_qsys_sw_status(struct lan966x *lan966x);
 
+/* dma_dev differs from dev only on the PCIe path. */
+static inline bool lan966x_is_pci(struct lan966x *lan966x)
+{
+	return IS_ENABLED(CONFIG_MCHP_LAN966X_PCI) &&
+	       lan966x->dma_dev != lan966x->dev;
+}
+
 int lan966x_lag_port_join(struct lan966x_port *port,
 			  struct net_device *brport_dev,
 			  struct net_device *bond,

-- 
2.34.1