net: devmem: Implement TX path

Augment dmabuf binding to be able to handle TX. Additional to all the RX
binding, we also create tx_vec needed for the TX path.

Provide API for sendmsg to be able to send dmabufs bound to this device:

- Provide a new dmabuf_tx_cmsg which includes the dmabuf to send from.
- MSG_ZEROCOPY with SCM_DEVMEM_DMABUF cmsg indicates send from dma-buf.

Devmem is uncopyable, so piggyback off the existing MSG_ZEROCOPY
implementation, while disabling instances where MSG_ZEROCOPY falls back
to copying.

We additionally pipe the binding down to the new
zerocopy_fill_skb_from_devmem which fills a TX skb with net_iov netmems
instead of the traditional page netmems.

We also special case skb_frag_dma_map to return the dma-address of these
dmabuf net_iovs instead of attempting to map pages.

The TX path may release the dmabuf in a context where we cannot wait.
This happens when the user unbinds a TX dmabuf while there are still
references to its netmems in the TX path. In that case, the netmems will
be put_netmem'd from a context where we can't unmap the dmabuf, Resolve
this by making __net_devmem_dmabuf_binding_free schedule_work'd.

Based on work by Stanislav Fomichev <sdf@fomichev.me>. A lot of the meat
of the implementation came from devmem TCP RFC v1[1], which included the
TX path, but Stan did all the rebasing on top of netmem/net_iov.

Cc: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250508004830.4100853-5-almasrymina@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 50 insertions, 11 deletions

diff --git a/net/core/devmem.h b/net/core/devmem.h
index 946f2e015746..67168aae5e5b 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -23,8 +23,9 @@ struct net_devmem_dmabuf_binding {
 
 	/* 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.
+	 * a ref to keep the binding alive. The page_pool does not release the
+	 * ref until all the net_iovs allocated from this binding are released
+	 * back to the page_pool.
 	 *
 	 * The binding undos itself and unmaps the underlying dmabuf once all
 	 * those refs are dropped and the binding is no longer desired or in
@@ -32,7 +33,10 @@ struct net_devmem_dmabuf_binding {
 	 *
 	 * net_devmem_get_net_iov() on dmabuf net_iovs will increment this
 	 * reference, making sure that the binding remains alive until all the
-	 * net_iovs are no longer used.
+	 * net_iovs are no longer used. net_iovs allocated from this binding
+	 * that are stuck in the TX path for any reason (such as awaiting
+	 * retransmits) hold a reference to the binding until the skb holding
+	 * them is freed.
 	 */
 	refcount_t ref;
 
@@ -48,6 +52,14 @@ struct net_devmem_dmabuf_binding {
 	 * active.
 	 */
 	u32 id;
+
+	/* Array of net_iov pointers for this binding, sorted by virtual
+	 * address. This array is convenient to map the virtual addresses to
+	 * net_iovs in the TX path.
+	 */
+	struct net_iov **tx_vec;
+
+	struct work_struct unbind_w;
 };
 
 #if defined(CONFIG_NET_DEVMEM)
@@ -64,14 +76,17 @@ struct dmabuf_genpool_chunk_owner {
 	dma_addr_t base_dma_addr;
 };
 
-void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
+void __net_devmem_dmabuf_binding_free(struct work_struct *wq);
 struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
-		       struct netlink_ext_ack *extack);
+net_devmem_bind_dmabuf(struct net_device *dev,
+		       enum dma_data_direction direction,
+		       unsigned int dmabuf_fd, struct netlink_ext_ack *extack);
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id);
 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 net_devmem_bind_tx_release(struct sock *sk);
 
 static inline struct dmabuf_genpool_chunk_owner *
 net_devmem_iov_to_chunk_owner(const struct net_iov *niov)
@@ -100,10 +115,10 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-static inline void
+static inline bool
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
-	refcount_inc(&binding->ref);
+	return refcount_inc_not_zero(&binding->ref);
 }
 
 static inline void
@@ -112,7 +127,8 @@ 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);
+	INIT_WORK(&binding->unbind_w, __net_devmem_dmabuf_binding_free);
+	schedule_work(&binding->unbind_w);
 }
 
 void net_devmem_get_net_iov(struct net_iov *niov);
@@ -123,6 +139,11 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
 void net_devmem_free_dmabuf(struct net_iov *ppiov);
 
 bool net_is_devmem_iov(struct net_iov *niov);
+struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id);
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+		       size_t *off, size_t *size);
 
 #else
 struct net_devmem_dmabuf_binding;
@@ -140,18 +161,23 @@ static inline void net_devmem_put_net_iov(struct net_iov *niov)
 {
 }
 
-static inline void
-__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
 {
 }
 
 static inline struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       enum dma_data_direction direction,
 		       struct netlink_ext_ack *extack)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+	return NULL;
+}
+
 static inline void
 net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 {
@@ -190,6 +216,19 @@ static inline bool net_is_devmem_iov(struct net_iov *niov)
 {
 	return false;
 }
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+		       size_t *off, size_t *size)
+{
+	return NULL;
+}
 #endif
 
 #endif /* _NET_DEVMEM_H */