net: Proxy netdev_queue_get_dma_dev for leased queues

Extend netdev_queue_get_dma_dev to return the physical device of the
real rxq for DMA in case the queue was leased. This allows memory
providers like io_uring zero-copy or devmem to bind to the physically
leased rxq via virtual devices such as netkit.

Signed-off-by: David Wei <dw@davidwei.uk>
Co-developed-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-8-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 748b70552ed1c844183639406ad8646fcea1a7fd..70c9fe9e83cc4ed17baaa6be6d967e9aeca43c37 100644 (file)
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -380,7 +380,9 @@ static inline unsigned int netif_xmit_timeout_ms(struct netdev_queue *txq)
                                         get_desc, start_thrs);         \
        })
 
-struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx);
+struct device *netdev_queue_get_dma_dev(struct net_device *dev,
+                                       unsigned int idx,
+                                       enum netdev_queue_type type);
 bool netdev_can_create_queue(const struct net_device *dev,
                             struct netlink_ext_ack *extack);
 bool netdev_can_lease_queue(const struct net_device *dev,

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index d3ec63c83d0ca12aaf1af1a9e895a23aa97b3f3b..f4a7809ba0c2b14c43dd8c545451d4c069961a9a 100644 (file)
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -829,7 +829,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
        }
        netdev_hold(ifq->netdev, &ifq->netdev_tracker, GFP_KERNEL);
 
-       ifq->dev = netdev_queue_get_dma_dev(ifq->netdev, reg.if_rxq);
+       ifq->dev = netdev_queue_get_dma_dev(ifq->netdev, reg.if_rxq,
+                                           NETDEV_QUEUE_TYPE_RX);
        if (!ifq->dev) {
                ret = -EOPNOTSUPP;
                goto netdev_put_unlock;

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 515832854251f4d29a2820f111d8b888fe628ff9..056460d019408112a123d9362e8aea9e17d28072 100644 (file)
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -976,7 +976,8 @@ netdev_nl_get_dma_dev(struct net_device *netdev, unsigned long *rxq_bitmap,
        for_each_set_bit(rxq_idx, rxq_bitmap, netdev->real_num_rx_queues) {
                struct device *rxq_dma_dev;
 
-               rxq_dma_dev = netdev_queue_get_dma_dev(netdev, rxq_idx);
+               rxq_dma_dev = netdev_queue_get_dma_dev(netdev, rxq_idx,
+                                                      NETDEV_QUEUE_TYPE_RX);
                if (dma_dev && rxq_dma_dev != dma_dev) {
                        NL_SET_ERR_MSG_FMT(extack, "DMA device mismatch between queue %u and %u (multi-PF device?)",
                                           rxq_idx, prev_rxq_idx);
@@ -1153,7 +1154,7 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
                goto err_unlock_netdev;
        }
 
-       dma_dev = netdev_queue_get_dma_dev(netdev, 0);
+       dma_dev = netdev_queue_get_dma_dev(netdev, 0, NETDEV_QUEUE_TYPE_TX);
        binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_TO_DEVICE,
                                         dmabuf_fd, priv, info->extack);
        if (IS_ERR(binding)) {

diff --git a/net/core/netdev_queues.c b/net/core/netdev_queues.c
index 177401828e7992ec4e257ccb60f56bd0f4e6ddc8..265161e12a9c19e7469c1aa28ac42a2cb5432e9a 100644 (file)
--- a/net/core/netdev_queues.c
+++ b/net/core/netdev_queues.c
@@ -6,27 +6,50 @@
 
 #include "dev.h"
 
+static struct device *
+__netdev_queue_get_dma_dev(struct net_device *dev, unsigned 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;
+}
+
 /**
  * netdev_queue_get_dma_dev() - get dma device for zero-copy operations
  * @dev:       net_device
  * @idx:       queue index
+ * @type:      queue type (RX or TX)
  *
- * 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.
+ * Get dma device for zero-copy operations to be used for this queue. If
+ * the queue is an RX queue leased from a physical queue, we retrieve the
+ * physical queue's dma device. When the dma 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)
+struct device *netdev_queue_get_dma_dev(struct net_device *dev,
+                                       unsigned int idx,
+                                       enum netdev_queue_type type)
 {
-       const struct netdev_queue_mgmt_ops *queue_ops = dev->queue_mgmt_ops;
+       struct net_device *orig_dev = dev;
        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;
+       /* Only RX side supports queue leasing today. */
+       if (type != NETDEV_QUEUE_TYPE_RX || !netif_rxq_is_leased(dev, idx))
+               return __netdev_queue_get_dma_dev(dev, idx);
 
-       return dma_dev && dma_dev->dma_mask ? dma_dev : NULL;
+       if (!netif_get_rx_queue_lease_locked(&dev, &idx))
+               return NULL;
+
+       dma_dev = __netdev_queue_get_dma_dev(dev, idx);
+       netif_put_rx_queue_lease_locked(orig_dev, dev);
+       return dma_dev;
 }
 
 bool netdev_can_create_queue(const struct net_device *dev,