[PATCH net-next] net: ag71xx: align the IP header behind DSA tags

[Rosen Penev <rosenp@gmail.com>]

The receive buffer offset includes NET_IP_ALIGN to get the IP header
aligned behind a 14 byte Ethernet header. Most ag71xx devices use DSA
switches whose tag sits in front of the EtherType, which moves the IP
header by another 2 bytes. Every access to the IP and TCP headers then
traps and gets emulated by the unaligned access handler, around 6 times
per forwarded frame.

Take the headroom needed by the DSA tagger into account when choosing
the offset.

TP-Link Archer C7 v2 (qca8k), median of 3 runs, Mbit/s:

                       before   after
  routed up               743     855
  routed down             660     749
  local receive           554     572

The unaligned instruction counter no longer moves while forwarding.

Assisted-by: LLM
Signed-off-by: Rosen Penev <rosenp@gmail.com>
---
 drivers/net/ethernet/atheros/ag71xx.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 8a3c689f6825..414d26118d15 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -38,6 +38,7 @@
 #include <linux/reset.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <net/dsa.h>
 #include <net/selftests.h>
 
 #define AG71XX_OOM_REFILL	(1 + HZ / 10)
@@ -1396,6 +1397,24 @@ static void ag71xx_hw_disable(struct ag71xx *ag)
 	ag71xx_rings_cleanup(ag);
 }
 
+static unsigned int ag71xx_rx_offset(struct ag71xx *ag)
+{
+	unsigned int align = NET_IP_ALIGN;
+
+	if (ag71xx_is(ag, AR7100) || ag71xx_is(ag, AR9130))
+		return NET_SKB_PAD;
+
+#if IS_ENABLED(CONFIG_NET_DSA)
+	/* A tag inserted in front of the EtherType shifts the IP header,
+	 * compensate for it to avoid unaligned accesses in the stack.
+	 */
+	if (netdev_uses_dsa(ag->ndev))
+		align = (align - ag->ndev->dsa_ptr->tag_ops->needed_headroom) & 3;
+#endif
+
+	return NET_SKB_PAD + align;
+}
+
 static int ag71xx_open(struct net_device *ndev)
 {
 	struct ag71xx *ag = netdev_priv(ndev);
@@ -1410,6 +1429,7 @@ static int ag71xx_open(struct net_device *ndev)
 	}
 
 	max_frame_len = ag71xx_max_frame_len(ndev->mtu);
+	ag->rx_buf_offset = ag71xx_rx_offset(ag);
 	ag->rx_buf_size =
 		SKB_DATA_ALIGN(max_frame_len + NET_SKB_PAD + NET_IP_ALIGN);
 
@@ -1874,10 +1894,6 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ndev->min_mtu = 68;
 	ndev->max_mtu = dcfg->max_frame_len - ag71xx_max_frame_len(0);
 
-	ag->rx_buf_offset = NET_SKB_PAD;
-	if (!ag71xx_is(ag, AR7100) && !ag71xx_is(ag, AR9130))
-		ag->rx_buf_offset += NET_IP_ALIGN;
-
 	if (ag71xx_is(ag, AR7100)) {
 		ag->tx_ring.desc_split = AG71XX_TX_RING_SPLIT;
 		tx_size *= AG71XX_TX_RING_DS_PER_PKT;
-- 
2.56.0