Devmem TX frags are bounded only by the net_iov size, which is about
to grow up to 2MB, more than some devices can describe in a single TX
descriptor.

Add netmem_tx_max_frag_size, U32_MAX by default, and cap devmem TX
frags to the limit of the device the binding is attached to.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
---
 Documentation/networking/net_cachelines/net_device.rst | 1 +
 Documentation/networking/netmem.rst                    | 6 ++++++
 include/linux/netdevice.h                              | 2 ++
 net/core/datagram.c                                    | 1 +
 net/core/dev.c                                         | 1 +
 net/core/devmem.c                                      | 1 +
 net/core/devmem.h                                      | 1 +
 7 files changed, 13 insertions(+)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 8eceaa80b686..4f5fd5b99154 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -76,6 +76,7 @@ unsigned_short                      dev_id
 unsigned_short                      dev_port
 spinlock_t                          addr_list_lock
 int                                 irq
+u32                                 netmem_tx_max_frag_size
 struct netdev_hw_addr_list          uc
 struct netdev_hw_addr_list          mc
 struct netdev_hw_addr_list          dev_addrs
diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst
index 6871dcdd700c..04861c60cfa1 100644
--- a/Documentation/networking/netmem.rst
+++ b/Documentation/networking/netmem.rst
@@ -155,3 +155,9 @@ Driver TX Requirements
 
    - `NETMEM_TX_NO_DMA`: for virtual or passthrough devices that do
      not DMA, but still support handling of netmem-backed skbs.
+
+3. Drivers which limit the size of a single TX buffer should set
+   `netdev->netmem_tx_max_frag_size` to that limit. Devmem TX frags are
+   capped at it, otherwise a frag can span a whole net_iov, which may be
+   much larger than a page. The default is U32_MAX, the value is read when
+   the dmabuf binding is created.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c0ae442c4344..4453b80bf7ea 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1845,6 +1845,7 @@ enum netdev_reg_state {
  *			drivers. Mainly used by logical interfaces, such as
  *			bonding and tunnels
  *	@netmem_tx:	device netmem TX mode
+ *	@netmem_tx_max_frag_size: max size of a netmem TX frag
  *	@pacing_offload: enable EDT pacing offload.
  *
  *	@name:	This is the first field of the "visible" part of this structure
@@ -2342,6 +2343,7 @@ struct net_device {
 	unsigned short          dev_port;
 	int			irq;
 	u32			priv_len;
+	u32			netmem_tx_max_frag_size;
 
 	spinlock_t		addr_list_lock;
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 489d92fe6dae..a8d3f87d38c5 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -734,6 +734,7 @@ zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from,
 
 		size = min_t(size_t, size, length);
 		size = min_t(size_t, size, iter_iov_len(from));
+		size = min_t(size_t, size, binding->tx_max_frag_size);
 
 		netmem_inc_ref(net_iov_to_netmem(niov));
 		skb_add_rx_frag_netmem(skb, i, net_iov_to_netmem(niov), off,
diff --git a/net/core/dev.c b/net/core/dev.c
index 3ac700d37e59..ba2f887dcd39 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12350,6 +12350,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
+	dev->netmem_tx_max_frag_size = U32_MAX;
 	dev->upper_level = 1;
 	dev->lower_level = 1;
 #ifdef CONFIG_LOCKDEP
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 6339f221bc82..19c039ed2cb2 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -218,6 +218,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 
 	binding->dev = dev;
 	binding->vdev = vdev;
+	binding->tx_max_frag_size = dev->netmem_tx_max_frag_size;
 	write_pnet(&binding->net, sock_net(nl_sk));
 	binding->uid = sk_uid(nl_sk);
 	binding->niov_shift = niov_shift;
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 8fa089776610..97ff1f13fb84 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -79,6 +79,7 @@ struct net_devmem_dmabuf_binding {
 	struct net_iov **tx_vec;
 
 	unsigned int niov_shift;
+	u32 tx_max_frag_size;
 
 	struct work_struct unbind_w;
 };
-- 
2.53.0-Meta