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.

Based on work by Stanislav Fomichev [off-list ref]. 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 <redacted>
Signed-off-by: Mina Almasry <redacted>


---

v2:
- Remove dmabuf_offset from the dmabuf cmsg.
- Update zerocopy_fill_skb_from_devmem to interpret the
  iov_base/iter_iov_addr as the offset into the dmabuf to send from
  (Stan).
- Remove the confusing binding->tx_iter which is not needed if we
  interpret the iov_base/iter_iov_addr as offset into the dmabuf (Stan).
- Remove check for binding->sgt and binding->sgt->nents in dmabuf
  binding.
- Simplify the calculation of binding->tx_vec.
- Check in net_devmem_get_binding that the binding we're returning
  has ifindex matching the sending socket (Willem).
---
 include/linux/skbuff.h                  | 15 +++-
 include/net/sock.h                      |  1 +
 include/uapi/linux/uio.h                |  6 +-
 net/core/datagram.c                     | 41 ++++++++++-
 net/core/devmem.c                       | 96 +++++++++++++++++++++++--
 net/core/devmem.h                       | 42 +++++++++--
 net/core/netdev-genl.c                  | 65 ++++++++++++++++-
 net/core/skbuff.c                       |  6 +-
 net/core/sock.c                         |  8 +++
 net/ipv4/tcp.c                          | 36 +++++++---
 net/vmw_vsock/virtio_transport_common.c |  3 +-
 11 files changed, 285 insertions(+), 34 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb2b751d274a..3ff8f568c382 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h

@@ -1711,9 +1711,12 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 
 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);

@@ -1721,12 +1724,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 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);
 }

diff --git a/include/net/sock.h b/include/net/sock.h
index 8036b3b79cd8..09eb918525b6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h

@@ -1822,6 +1822,7 @@ struct sockcm_cookie {
 	u32 tsflags;
 	u32 ts_opt_id;
 	u32 priority;
+	u32 dmabuf_id;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,

diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 649739e0c404..866bd5dfe39f 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h

@@ -38,10 +38,14 @@ struct dmabuf_token {
 	__u32 token_count;
 };
 
+struct dmabuf_tx_cmsg {
+	__u32 dmabuf_id;
+};
+
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
- 
+
 #define UIO_FASTIOV	8
 #define UIO_MAXIOV	1024
 

diff --git a/net/core/datagram.c b/net/core/datagram.c
index f0693707aece..c989606ff58d 100644
--- a/net/core/datagram.c
+++ b/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' ?
  */

@@ -692,9 +694,42 @@ 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;
+
+	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;

@@ -702,6 +737,8 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 
 	if (msg && msg->msg_ubuf && msg->sg_from_iter)
 		ret = msg->sg_from_iter(skb, from, length);
+	else if (unlikely(binding))
+		ret = zerocopy_fill_skb_from_devmem(skb, from, length, binding);
 	else
 		ret = zerocopy_fill_skb_from_iter(skb, from, length);
 

@@ -735,7 +772,7 @@ 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);
 

diff --git a/net/core/devmem.c b/net/core/devmem.c
index 20985a570662..796338b1599e 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c

@@ -16,6 +16,7 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/sock.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"

@@ -64,8 +65,10 @@ 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);
+	kfree(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)

@@ -110,6 +113,13 @@ 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);
 

@@ -123,8 +133,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
 	}
 
-	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
-
 	net_devmem_dmabuf_binding_put(binding);
 }
 

@@ -185,8 +193,9 @@ 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;

@@ -229,7 +238,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	}
 
 	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");

@@ -240,13 +249,22 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	 * 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;
 	}
 
+	if (direction == DMA_TO_DEVICE) {
+		binding->tx_vec = kcalloc(dmabuf->size / PAGE_SIZE,
+					  sizeof(struct net_iov *), GFP_KERNEL);