netdev: support binding dma-buf to netdevice

Add a netdev_dmabuf_binding struct which represents the
dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to
rx queues on the netdevice. On the binding, the dma_buf_attach
& dma_buf_map_attachment will occur. The entries in the sg_table from
mapping will be inserted into a genpool to make it ready
for allocation.

The chunks in the genpool are owned by a dmabuf_chunk_owner struct which
holds the dma-buf offset of the base of the chunk and the dma_addr of
the chunk. Both are needed to use allocations that come from this chunk.

We create a new type that represents an allocation from the genpool:
net_iov. We setup the net_iov allocation size in the
genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally
allocated by the page pool and given to the drivers.

The user can unbind the dmabuf from the netdevice by closing the netlink
socket that established the binding. We do this so that the binding is
automatically unbound even if the userspace process crashes.

The binding and unbinding leaves an indicator in struct netdev_rx_queue
that the given queue is bound, and the binding is actuated by resetting
the rx queue using the queue API.

The netdev_dmabuf_binding struct is refcounted, and releases its
resources only when all the refs are released.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com> # excluding netlink
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-4-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 123 insertions, 5 deletions

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 699c34b9b03c..9153a8ab0cf8 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -3,16 +3,17 @@
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
 #include <linux/rtnetlink.h>
+#include <net/busy_poll.h>
 #include <net/net_namespace.h>
+#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
 #include <net/sock.h>
 #include <net/xdp.h>
 #include <net/xdp_sock.h>
-#include <net/netdev_rx_queue.h>
-#include <net/netdev_queues.h>
-#include <net/busy_poll.h>
 
-#include "netdev-genl-gen.h"
 #include "dev.h"
+#include "devmem.h"
+#include "netdev-genl-gen.h"
 
 struct netdev_nl_dump_ctx {
 	unsigned long	ifindex;
@@ -723,10 +724,127 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 	return err;
 }
 
-/* Stub */
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 {
+	struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)];
+	struct net_devmem_dmabuf_binding *binding;
+	struct list_head *sock_binding_list;
+	u32 ifindex, dmabuf_fd, rxq_idx;
+	struct net_device *netdev;
+	struct sk_buff *rsp;
+	struct nlattr *attr;
+	int rem, err = 0;
+	void *hdr;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES))
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
+
+	sock_binding_list = genl_sk_priv_get(&netdev_nl_family,
+					     NETLINK_CB(skb).sk);
+	if (IS_ERR(sock_binding_list))
+		return PTR_ERR(sock_binding_list);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_genlmsg_free;
+	}
+
+	rtnl_lock();
+
+	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	if (!netdev || !netif_device_present(netdev)) {
+		err = -ENODEV;
+		goto err_unlock;
+	}
+
+	if (dev_xdp_prog_count(netdev)) {
+		NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached");
+		err = -EEXIST;
+		goto err_unlock;
+	}
+
+	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
+	if (IS_ERR(binding)) {
+		err = PTR_ERR(binding);
+		goto err_unlock;
+	}
+
+	nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES,
+			       genlmsg_data(info->genlhdr),
+			       genlmsg_len(info->genlhdr), rem) {
+		err = nla_parse_nested(
+			tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr,
+			netdev_queue_id_nl_policy, info->extack);
+		if (err < 0)
+			goto err_unbind;
+
+		if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) ||
+		    NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) {
+			err = -EINVAL;
+			goto err_unbind;
+		}
+
+		if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) {
+			NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]);
+			err = -EINVAL;
+			goto err_unbind;
+		}
+
+		rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]);
+
+		err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding,
+						      info->extack);
+		if (err)
+			goto err_unbind;
+	}
+
+	list_add(&binding->list, sock_binding_list);
+
+	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+	genlmsg_end(rsp, hdr);
+
+	err = genlmsg_reply(rsp, info);
+	if (err)
+		goto err_unbind;
+
+	rtnl_unlock();
+
 	return 0;
+
+err_unbind:
+	net_devmem_unbind_dmabuf(binding);
+err_unlock:
+	rtnl_unlock();
+err_genlmsg_free:
+	nlmsg_free(rsp);
+	return err;
+}
+
+void netdev_nl_sock_priv_init(struct list_head *priv)
+{
+	INIT_LIST_HEAD(priv);
+}
+
+void netdev_nl_sock_priv_destroy(struct list_head *priv)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct net_devmem_dmabuf_binding *temp;
+
+	list_for_each_entry_safe(binding, temp, priv, list) {
+		rtnl_lock();
+		net_devmem_unbind_dmabuf(binding);
+		rtnl_unlock();
+	}
 }
 
 static int netdev_genl_netdevice_event(struct notifier_block *nb,