PAGE_SIZE TX net_iovs cap devmem skbs at MAX_SKB_FRAGS pages (~68KB),
which makes BIG TCP ineffective.

TX net_iovs only need to be DMA contiguous. Use the largest power of 2,
from PAGE_SIZE up to 2MB, which aligns every DMA segment of the dmabuf:
- 2MB hugepage-backed udmabufs get 2MB net_iovs
- no UAPI change, TX addresses are dmabuf offsets
- skbs are still bounded by TCP's size_goal, only frags get larger

The net_iov size doesn't depend on the device: frags are capped to the
device limit when they are built, and many frags share a net_iov.
Capping the net_iov instead would only split frags at net_iov
boundaries and allocate more net_iovs.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry <almasrymina@google.com>
---
 net/core/devmem.c      | 28 ++++++++++++++++++++++++++--
 net/core/netdev-genl.c |  2 +-
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/net/core/devmem.c b/net/core/devmem.c
index 19c039ed2cb2..98c9594dbf99 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -181,6 +181,20 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	return err;
 }
 
+static bool net_devmem_sgt_aligned(struct sg_table *sgt, size_t size)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		if (!IS_ALIGNED(sg_dma_address(sg), size) ||
+		    !IS_ALIGNED(sg_dma_len(sg), size))
+			return false;
+	}
+	return true;
+}
+
+/* niov_shift == 0 picks the net_iov size from the dmabuf, TX only */
 struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct device *dma_dev,
@@ -191,11 +205,11 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		       struct netlink_ext_ack *extack)
 {
 	struct net_devmem_dmabuf_binding *binding;
-	size_t niov_size = 1UL << niov_shift;
 	static u32 id_alloc_next;
 	struct scatterlist *sg;
 	struct dma_buf *dmabuf;
 	unsigned int sg_idx;
+	size_t niov_size;
 	size_t niov_idx;
 	size_t i;
 	long err;
@@ -221,7 +235,6 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *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;
 	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);
 
 	err = percpu_ref_init(&binding->ref,
@@ -266,6 +279,17 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 		goto err_unmap;
 	}
 
+	if (!niov_shift) {
+		niov_size = SZ_2M;
+		while (niov_size > PAGE_SIZE &&
+		       (!IS_ALIGNED(dmabuf->size, niov_size) ||
+			!net_devmem_sgt_aligned(binding->sgt, niov_size)))
+			niov_size /= 2;
+		niov_shift = ilog2(niov_size);
+	}
+	binding->niov_shift = niov_shift;
+	niov_size = 1UL << niov_shift;
+
 	if (!IS_ALIGNED(dmabuf->size, niov_size)) {
 		err = -EINVAL;
 		NL_SET_ERR_MSG_FMT(extack,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 384fdc5ae514..bfd229bd31ca 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -1261,7 +1261,7 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
 	binding = net_devmem_bind_dmabuf(bind_dev,
 					 bind_dev != netdev ? netdev : NULL,
 					 dma_dev, DMA_TO_DEVICE, dmabuf_fd,
-					 PAGE_SHIFT, priv, NETLINK_CB(skb).sk,
+					 0, priv, NETLINK_CB(skb).sk,
 					 info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
-- 
2.53.0-Meta