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>

Author: mina

include/linux/skbuff.h

@@ -1707,26 +1707,31 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
 
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg);
+				       struct ubuf_info *uarg, bool devmem);
 
 void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
 
+struct net_devmem_dmabuf_binding;
+
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
-			    size_t length);
+			    size_t length,
+			    struct net_devmem_dmabuf_binding *binding);
 
 int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 				struct iov_iter *from, size_t length);
 
 static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
 					  struct msghdr *msg, int len)
 {
-	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
+	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len,
+				       NULL);
 }
 
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg);
+			     struct ubuf_info *uarg,
+			     struct net_devmem_dmabuf_binding *binding);
 
 /* Internal */
 #define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
@@ -3697,6 +3702,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
 					    size_t offset, size_t size,
 					    enum dma_data_direction dir)
 {
+	if (skb_frag_is_net_iov(frag)) {
+		return netmem_to_net_iov(frag->netmem)->dma_addr + offset +
+		       frag->offset;
+	}
 	return dma_map_page(dev, skb_frag_page(frag),
 			    skb_frag_off(frag) + offset, size, dir);
 }

include/net/sock.h

@@ -1851,6 +1851,7 @@ struct sockcm_cookie {
 	u32 tsflags;
 	u32 ts_opt_id;
 	u32 priority;
+	u32 dmabuf_id;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,

io_uring/zcrx.c

@@ -810,7 +810,7 @@ static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		return io_zcrx_copy_frag(req, ifq, frag, off, len);
 
 	niov = netmem_to_net_iov(frag->netmem);
-	if (niov->pp->mp_ops != &io_uring_pp_zc_ops ||
+	if (!niov->pp || niov->pp->mp_ops != &io_uring_pp_zc_ops ||
 	    io_pp_to_ifq(niov->pp) != ifq)
 		return -EFAULT;
 

net/core/datagram.c

@@ -63,6 +63,8 @@
 #include <net/busy_poll.h>
 #include <crypto/hash.h>
 
+#include "devmem.h"
+
 /*
  *	Is a socket 'connection oriented' ?
  */
@@ -691,16 +693,58 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 	return 0;
 }
 
+static int
+zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from,
+			      int length,
+			      struct net_devmem_dmabuf_binding *binding)
+{
+	int i = skb_shinfo(skb)->nr_frags;
+	size_t virt_addr, size, off;
+	struct net_iov *niov;
+
+	/* Devmem filling works by taking an IOVEC from the user where the
+	 * iov_addrs are interpreted as an offset in bytes into the dma-buf to
+	 * send from. We do not support other iter types.
+	 */
+	if (iov_iter_type(from) != ITER_IOVEC)
+		return -EFAULT;
+
+	while (length && iov_iter_count(from)) {
+		if (i == MAX_SKB_FRAGS)
+			return -EMSGSIZE;
+
+		virt_addr = (size_t)iter_iov_addr(from);
+		niov = net_devmem_get_niov_at(binding, virt_addr, &off, &size);
+		if (!niov)
+			return -EFAULT;
+
+		size = min_t(size_t, size, length);
+		size = min_t(size_t, size, iter_iov_len(from));
+
+		get_netmem(net_iov_to_netmem(niov));
+		skb_add_rx_frag_netmem(skb, i, net_iov_to_netmem(niov), off,
+				       size, PAGE_SIZE);
+		iov_iter_advance(from, size);
+		length -= size;
+		i++;
+	}
+
+	return 0;
+}
+
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
-			    size_t length)
+			    size_t length,
+			    struct net_devmem_dmabuf_binding *binding)
 {
 	unsigned long orig_size = skb->truesize;
 	unsigned long truesize;
 	int ret;
 
 	if (msg && msg->msg_ubuf && msg->sg_from_iter)
 		ret = msg->sg_from_iter(skb, from, length);
+	else if (binding)
+		ret = zerocopy_fill_skb_from_devmem(skb, from, length, binding);
 	else
 		ret = zerocopy_fill_skb_from_iter(skb, from, length);
 
@@ -734,7 +778,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
 		return -EFAULT;
 
-	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
+	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U, NULL);
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 

net/core/devmem.c

@@ -16,6 +16,7 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
+#include <net/sock.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
@@ -52,8 +53,10 @@ static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)
 	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-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 *binding = container_of(wq, typeof(*binding), unbind_w);
+
 	size_t size, avail;
 
 	gen_pool_for_each_chunk(binding->chunk_pool,
@@ -71,8 +74,10 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 	dma_buf_detach(binding->dmabuf, binding->attachment);
 	dma_buf_put(binding->dmabuf);
 	xa_destroy(&binding->bound_rxqs);
+	kvfree(binding->tx_vec);
 	kfree(binding);
 }
+EXPORT_SYMBOL(__net_devmem_dmabuf_binding_free);
 
 struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
@@ -117,6 +122,13 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	unsigned long xa_idx;
 	unsigned int rxq_idx;
 
+	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
+
+	/* Ensure no tx net_devmem_lookup_dmabuf() are in flight after the
+	 * erase.
+	 */
+	synchronize_net();
+
 	if (binding->list.next)
 		list_del(&binding->list);
 
@@ -131,8 +143,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		__net_mp_close_rxq(binding->dev, rxq_idx, &mp_params);
 	}
 
-	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
-
 	net_devmem_dmabuf_binding_put(binding);
 }
 
@@ -166,8 +176,9 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 }
 
 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 *binding;
 	static u32 id_alloc_next;
@@ -189,13 +200,6 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	}
 
 	binding->dev = dev;
-
-	err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id,
-			      binding, xa_limit_32b, &id_alloc_next,
-			      GFP_KERNEL);
-	if (err < 0)
-		goto err_free_binding;
-
 	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);
 
 	refcount_set(&binding->ref, 1);
@@ -206,26 +210,36 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	if (IS_ERR(binding->attachment)) {
 		err = PTR_ERR(binding->attachment);
 		NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device");
-		goto err_free_id;
+		goto err_free_binding;
 	}
 
 	binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment,
-						       DMA_FROM_DEVICE);
+						       direction);
 	if (IS_ERR(binding->sgt)) {
 		err = PTR_ERR(binding->sgt);
 		NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment");
 		goto err_detach;
 	}
 
+	if (direction == DMA_TO_DEVICE) {
+		binding->tx_vec = kvmalloc_array(dmabuf->size / PAGE_SIZE,
+						 sizeof(struct net_iov *),
+						 GFP_KERNEL);
+		if (!binding->tx_vec) {
+			err = -ENOMEM;
+			goto err_unmap;
+		}
+	}
+
 	/* For simplicity we expect to make PAGE_SIZE allocations, but the
 	 * binding can be much more flexible than that. We may be able to
 	 * allocate MTU sized chunks here. Leave that for future work...
 	 */
-	binding->chunk_pool =
-		gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev));
+	binding->chunk_pool = gen_pool_create(PAGE_SHIFT,
+					      dev_to_node(&dev->dev));
 	if (!binding->chunk_pool) {
 		err = -ENOMEM;
-		goto err_unmap;
+		goto err_tx_vec;
 	}
 
 	virtual = 0;
@@ -270,31 +284,54 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 			niov->owner = &owner->area;
 			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
 						      net_devmem_get_dma_addr(niov));
+			if (direction == DMA_TO_DEVICE)
+				binding->tx_vec[owner->area.base_virtual / PAGE_SIZE + i] = niov;
 		}
 
 		virtual += len;
 	}
 
+	err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id,
+			      binding, xa_limit_32b, &id_alloc_next,
+			      GFP_KERNEL);
+	if (err < 0)
+		goto err_free_chunks;
+
 	return binding;
 
 err_free_chunks:
 	gen_pool_for_each_chunk(binding->chunk_pool,
 				net_devmem_dmabuf_free_chunk_owner, NULL);
 	gen_pool_destroy(binding->chunk_pool);
+err_tx_vec:
+	kvfree(binding->tx_vec);
 err_unmap:
 	dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
 					  DMA_FROM_DEVICE);
 err_detach:
 	dma_buf_detach(dmabuf, binding->attachment);
-err_free_id:
-	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
 err_free_binding:
 	kfree(binding);
 err_put_dmabuf:
 	dma_buf_put(dmabuf);
 	return ERR_PTR(err);
 }
 
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+	struct net_devmem_dmabuf_binding *binding;
+
+	rcu_read_lock();
+	binding = xa_load(&net_devmem_dmabuf_bindings, id);
+	if (binding) {
+		if (!net_devmem_dmabuf_binding_get(binding))
+			binding = NULL;
+	}
+	rcu_read_unlock();
+
+	return binding;
+}
+
 void net_devmem_get_net_iov(struct net_iov *niov)
 {
 	net_devmem_dmabuf_binding_get(net_devmem_iov_binding(niov));
@@ -305,6 +342,49 @@ void net_devmem_put_net_iov(struct net_iov *niov)
 	net_devmem_dmabuf_binding_put(net_devmem_iov_binding(niov));
 }
 
+struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
+							 unsigned int dmabuf_id)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct dst_entry *dst = __sk_dst_get(sk);
+	int err = 0;
+
+	binding = net_devmem_lookup_dmabuf(dmabuf_id);
+	if (!binding || !binding->tx_vec) {
+		err = -EINVAL;
+		goto out_err;
+	}
+
+	/* The dma-addrs in this binding are only reachable to the corresponding
+	 * net_device.
+	 */
+	if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) {
+		err = -ENODEV;
+		goto out_err;
+	}
+
+	return binding;
+
+out_err:
+	if (binding)
+		net_devmem_dmabuf_binding_put(binding);
+
+	return ERR_PTR(err);
+}
+
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding,
+		       size_t virt_addr, size_t *off, size_t *size)
+{
+	if (virt_addr >= binding->dmabuf->size)
+		return NULL;
+
+	*off = virt_addr % PAGE_SIZE;
+	*size = PAGE_SIZE - *off;
+
+	return binding->tx_vec[virt_addr / PAGE_SIZE];
+}
+
 /*** "Dmabuf devmem memory provider" ***/
 
 int mp_dmabuf_devmem_init(struct page_pool *pool)