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, 124 insertions, 0 deletions

diff --git a/net/core/devmem.h b/net/core/devmem.h
new file mode 100644
index 000000000000..c50f91d858dd
--- /dev/null
+++ b/net/core/devmem.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Device memory TCP support
+ *
+ * Authors:	Mina Almasry <almasrymina@google.com>
+ *		Willem de Bruijn <willemb@google.com>
+ *		Kaiyuan Zhang <kaiyuanz@google.com>
+ *
+ */
+#ifndef _NET_DEVMEM_H
+#define _NET_DEVMEM_H
+
+struct netlink_ext_ack;
+
+struct net_devmem_dmabuf_binding {
+	struct dma_buf *dmabuf;
+	struct dma_buf_attachment *attachment;
+	struct sg_table *sgt;
+	struct net_device *dev;
+	struct gen_pool *chunk_pool;
+
+	/* The user holds a ref (via the netlink API) for as long as they want
+	 * the binding to remain alive. Each page pool using this binding holds
+	 * a ref to keep the binding alive. Each allocated net_iov holds a
+	 * ref.
+	 *
+	 * The binding undos itself and unmaps the underlying dmabuf once all
+	 * those refs are dropped and the binding is no longer desired or in
+	 * use.
+	 */
+	refcount_t ref;
+
+	/* The list of bindings currently active. Used for netlink to notify us
+	 * of the user dropping the bind.
+	 */
+	struct list_head list;
+
+	/* rxq's this binding is active on. */
+	struct xarray bound_rxqs;
+
+	/* ID of this binding. Globally unique to all bindings currently
+	 * active.
+	 */
+	u32 id;
+};
+
+#if defined(CONFIG_NET_DEVMEM)
+/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist
+ * entry from the dmabuf is inserted into the genpool as a chunk, and needs
+ * this owner struct to keep track of some metadata necessary to create
+ * allocations from this chunk.
+ */
+struct dmabuf_genpool_chunk_owner {
+	/* Offset into the dma-buf where this chunk starts.  */
+	unsigned long base_virtual;
+
+	/* dma_addr of the start of the chunk.  */
+	dma_addr_t base_dma_addr;
+
+	/* Array of net_iovs for this chunk. */
+	struct net_iov *niovs;
+	size_t num_niovs;
+
+	struct net_devmem_dmabuf_binding *binding;
+};
+
+void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
+struct net_devmem_dmabuf_binding *
+net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netlink_ext_ack *extack);
+void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
+int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
+				    struct net_devmem_dmabuf_binding *binding,
+				    struct netlink_ext_ack *extack);
+void dev_dmabuf_uninstall(struct net_device *dev);
+
+static inline void
+net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
+{
+	refcount_inc(&binding->ref);
+}
+
+static inline void
+net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
+{
+	if (!refcount_dec_and_test(&binding->ref))
+		return;
+
+	__net_devmem_dmabuf_binding_free(binding);
+}
+
+#else
+static inline void
+__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+{
+}
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netlink_ext_ack *extack)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void
+net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+}
+
+static inline int
+net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
+				struct net_devmem_dmabuf_binding *binding,
+				struct netlink_ext_ack *extack)
+
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void dev_dmabuf_uninstall(struct net_device *dev)
+{
+}
+#endif
+
+#endif /* _NET_DEVMEM_H */