queue_api: add support for fetching per queue DMA dev

For zerocopy (io_uring, devmem), there is an assumption that the
parent device can do DMA. However that is not always the case:
- Scalable Function netdevs [1] have the DMA device in the grandparent.
- For Multi-PF netdevs [2] queues can be associated to different DMA
devices.

This patch introduces the a queue based interface for allowing drivers
to expose a different DMA device for zerocopy.

[1] Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
[2] Documentation/networking/multi-pf-netdev.rst

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250827144017.1529208-3-dtatulea@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 35 insertions, 0 deletions

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 6e835972abd1..b9d02bc65c97 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -127,6 +127,9 @@ void netdev_stat_queue_sum(struct net_device *netdev,
  * @ndo_queue_stop:	Stop the RX queue at the specified index. The stopped
  *			queue's memory is written at the specified address.
  *
+ * @ndo_queue_get_dma_dev: Get dma device for zero-copy operations to be used
+ *			   for this queue. Return NULL on error.
+ *
  * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while
  * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only
  * be called for an interface which is open.
@@ -144,6 +147,8 @@ struct netdev_queue_mgmt_ops {
 	int			(*ndo_queue_stop)(struct net_device *dev,
 						  void *per_queue_mem,
 						  int idx);
+	struct device *		(*ndo_queue_get_dma_dev)(struct net_device *dev,
+							 int idx);
 };
 
 /**
@@ -321,4 +326,6 @@ static inline void netif_subqueue_sent(const struct net_device *dev,
 					 get_desc, start_thrs);		\
 	})
 
+struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx);
+
 #endif
diff --git a/net/core/Makefile b/net/core/Makefile
index b2a76ce33932..9ef2099c5426 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 obj-y += net-sysfs.o
 obj-y += hotdata.o
 obj-y += netdev_rx_queue.o
+obj-y += netdev_queues.o
 obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
diff --git a/net/core/netdev_queues.c b/net/core/netdev_queues.c
new file mode 100644
index 000000000000..251f27a8307f
--- /dev/null
+++ b/net/core/netdev_queues.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <net/netdev_queues.h>
+
+/**
+ * netdev_queue_get_dma_dev() - get dma device for zero-copy operations
+ * @dev:	net_device
+ * @idx:	queue index
+ *
+ * Get dma device for zero-copy operations to be used for this queue.
+ * When such device is not available or valid, the function will return NULL.
+ *
+ * Return: Device or NULL on error
+ */
+struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx)
+{
+	const struct netdev_queue_mgmt_ops *queue_ops = dev->queue_mgmt_ops;
+	struct device *dma_dev;
+
+	if (queue_ops && queue_ops->ndo_queue_get_dma_dev)
+		dma_dev = queue_ops->ndo_queue_get_dma_dev(dev, idx);
+	else
+		dma_dev = dev->dev.parent;
+
+	return dma_dev && dma_dev->dma_mask ? dma_dev : NULL;
+}
+