[PATCH net-next v4 4/5] net: devmem: size TX net_iovs from the dmabuf sg table

[Stanislav Fomichev <sdf.kernel@gmail.com>]

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 keep their size, only the frags get larger

The net_iov size doesn't depend on the device. A frag is never larger
than its skb, and the skb is never larger than the device's
gso_max_size. TCP sizes skbs to fit, and validate_xmit_skb() segments
bigger ones. gso_max_size is 64KB unless BIG TCP is enabled. With BIG
TCP, page frags can already be 64KB or larger, for example with
MSG_ZEROCOPY from huge pages or with 64KB pages. So drivers that
enable BIG TCP already have to handle them. bnxt doesn't handle them
yet. It has a 16-bit BD length and needs a separate fix.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.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 c6868f39261a..713528048897 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -303,6 +303,20 @@ 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,
@@ -313,11 +327,11 @@ 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;
@@ -342,7 +356,6 @@ net_devmem_bind_dmabuf(struct net_device *dev, void *vdev,
 	binding->vdev = vdev;
 	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,
@@ -387,6 +400,17 @@ 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 9c5bf17b04e5..d2ccb1090496 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