1 files changed, 87 insertions, 14 deletions

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index b8f6076d8007..cb18db681640 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -2,6 +2,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
+#include <linux/pid_namespace.h>
 #include <linux/rtnetlink.h>
 #include <net/busy_poll.h>
 #include <net/net_namespace.h>
@@ -189,7 +190,8 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 		goto nla_put_failure;
 
 	if (napi->thread) {
-		pid = task_pid_nr(napi->thread);
+		pid = task_pid_nr_ns(napi->thread,
+				     task_active_pid_ns(current));
 		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
 			goto nla_put_failure;
 	}
@@ -1011,6 +1013,7 @@ netdev_nl_get_dma_dev(struct net_device *netdev, unsigned long *rxq_bitmap,
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net_devmem_dmabuf_binding *binding;
+	unsigned int niov_shift = PAGE_SHIFT;
 	u32 ifindex, dmabuf_fd, rxq_idx;
 	struct netdev_nl_sock *priv;
 	struct net_device *netdev;
@@ -1028,6 +1031,18 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
 	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
 
+	if (info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE]) {
+		u32 rx_page_size = nla_get_u32(info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE]);
+
+		if (!is_power_of_2(rx_page_size)) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    info->attrs[NETDEV_A_DMABUF_RX_PAGE_SIZE],
+					    "rx-page-size must be a power of 2");
+			return -EINVAL;
+		}
+		niov_shift = ilog2(rx_page_size);
+	}
+
 	priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk);
 	if (IS_ERR(priv))
 		return PTR_ERR(priv);
@@ -1077,8 +1092,9 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_rxq_bitmap;
 	}
 
-	binding = net_devmem_bind_dmabuf(netdev, dma_dev, DMA_FROM_DEVICE,
-					 dmabuf_fd, priv, info->extack);
+	binding = net_devmem_bind_dmabuf(netdev, NULL, dma_dev, DMA_FROM_DEVICE,
+					 dmabuf_fd, niov_shift, priv,
+					 info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
 		goto err_rxq_bitmap;
@@ -1091,12 +1107,12 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 			goto err_unbind;
 	}
 
-	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+	/* rsp was allocated large enough */
+	WARN_ON_ONCE(nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id));
+
 	genlmsg_end(rsp, hdr);
 
 	err = genlmsg_reply(rsp, info);
-	if (err)
-		goto err_unbind;
 
 	bitmap_free(rxq_bitmap);
 
@@ -1104,7 +1120,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 
 	mutex_unlock(&priv->lock);
 
-	return 0;
+	return err < 0 ? err : 0;
 
 err_unbind:
 	net_devmem_unbind_dmabuf(binding);
@@ -1119,9 +1135,43 @@ err_genlmsg_free:
 	return err;
 }
 
+/* Find the DMA-capable device for a netmem TX binding.
+ *
+ * For NETMEM_TX_DMA devices, return the device itself.
+ * For NETMEM_TX_NO_DMA devices, walk leased RX queues to find the underlying
+ * physical device and return it.
+ */
+static struct net_device *
+netdev_find_netmem_tx_dev(struct net_device *dev)
+{
+	struct netdev_rx_queue *lease_rxq;
+	struct net_device *phys_dev;
+	int i;
+
+	if (dev->netmem_tx == NETMEM_TX_DMA)
+		return dev;
+
+	if (dev->netmem_tx != NETMEM_TX_NO_DMA)
+		return NULL;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		lease_rxq = READ_ONCE(__netif_get_rx_queue(dev, i)->lease);
+		if (!lease_rxq)
+			continue;
+
+		phys_dev = lease_rxq->dev;
+		if (netif_device_present(phys_dev) &&
+		    phys_dev->netmem_tx == NETMEM_TX_DMA)
+			return phys_dev;
+	}
+
+	return NULL;
+}
+
 int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net_devmem_dmabuf_binding *binding;
+	struct net_device *bind_dev;
 	struct netdev_nl_sock *priv;
 	struct net_device *netdev;
 	struct device *dma_dev;
@@ -1164,29 +1214,50 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_netdev;
 	}
 
-	if (!netdev->netmem_tx) {
+	if (netdev->netmem_tx == NETMEM_TX_NONE) {
 		err = -EOPNOTSUPP;
 		NL_SET_ERR_MSG(info->extack,
 			       "Driver does not support netmem TX");
 		goto err_unlock_netdev;
 	}
 
-	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);
+	bind_dev = netdev_find_netmem_tx_dev(netdev);
+	if (!bind_dev) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG(info->extack,
+			       "No DMA-capable device found for netmem TX");
+		goto err_unlock_netdev;
+	}
+
+	if (bind_dev != netdev)
+		netdev_lock(bind_dev);
+
+	dma_dev = netdev_queue_get_dma_dev(bind_dev, 0, NETDEV_QUEUE_TYPE_TX);
+
+	binding = net_devmem_bind_dmabuf(bind_dev,
+					 bind_dev != netdev ? netdev : NULL,
+					 dma_dev, DMA_TO_DEVICE, dmabuf_fd,
+					 PAGE_SHIFT, priv, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
-		goto err_unlock_netdev;
+		goto err_unlock_bind_dev;
 	}
 
-	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+	/* rsp was allocated large enough */
+	WARN_ON_ONCE(nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id));
+
 	genlmsg_end(rsp, hdr);
 
+	if (bind_dev != netdev)
+		netdev_unlock(bind_dev);
 	netdev_unlock(netdev);
 	mutex_unlock(&priv->lock);
 
 	return genlmsg_reply(rsp, info);
 
+err_unlock_bind_dev:
+	if (bind_dev != netdev)
+		netdev_unlock(bind_dev);
 err_unlock_netdev:
 	netdev_unlock(netdev);
 err_unlock_sock:
@@ -1341,7 +1412,9 @@ int netdev_nl_queue_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	netdev_rx_queue_lease(rxq, rxq_lease);
 
-	nla_put_u32(rsp, NETDEV_A_QUEUE_ID, queue_id);
+	/* rsp was allocated large enough */
+	WARN_ON_ONCE(nla_put_u32(rsp, NETDEV_A_QUEUE_ID, queue_id));
+
 	genlmsg_end(rsp, hdr);
 
 	netdev_unlock(dev_lease);