--- /dev/null
+From 30fcba19ed88997a2909e4a68b4d39ff371357c3 Mon Sep 17 00:00:00 2001
+From: Linus Walleij <linus.walleij@linaro.org>
+Date: Wed, 1 May 2024 21:46:31 +0200
+Subject: [PATCH 1/5] net: ethernet: cortina: Restore TSO support
+
+An earlier commit deleted the TSO support in the Cortina Gemini
+driver because the driver was confusing gso_size and MTU,
+probably because what the Linux kernel calls "gso_size" was
+called "MTU" in the datasheet.
+
+Restore the functionality properly reading the gso_size from
+the skbuff.
+
+Tested with iperf3, running a server on a different machine
+and client on the device with the cortina gemini ethernet:
+
+Connecting to host 192.168.1.2, port 5201
+60008000.ethernet-port eth0: segment offloading mss = 05ea len=1c8a
+60008000.ethernet-port eth0: segment offloading mss = 05ea len=1c8a
+60008000.ethernet-port eth0: segment offloading mss = 05ea len=27da
+60008000.ethernet-port eth0: segment offloading mss = 05ea len=0b92
+60008000.ethernet-port eth0: segment offloading mss = 05ea len=2bda
+(...)
+
+(The hardware MSS 0x05ea here includes the ethernet headers.)
+
+If I disable all segment offloading on the receiving host and
+dump packets using tcpdump -xx like this:
+
+ethtool -K enp2s0 gro off gso off tso off
+tcpdump -xx -i enp2s0 host 192.168.1.136
+
+I get segmented packages such as this when running iperf3:
+
+23:16:54.024139 IP OpenWrt.lan.59168 > Fecusia.targus-getdata1:
+Flags [.], seq 1486:2934, ack 1, win 4198,
+options [nop,nop,TS val 3886192908 ecr 3601341877], length 1448
+0x0000: fc34 9701 a0c6 14d6 4da8 3c4f 0800 4500
+0x0010: 05dc 16a0 4000 4006 9aa1 c0a8 0188 c0a8
+0x0020: 0102 e720 1451 ff25 9822 4c52 29cf 8010
+0x0030: 1066 ac8c 0000 0101 080a e7a2 990c d6a8
+(...)
+0x05c0: 5e49 e109 fe8c 4617 5e18 7a82 7eae d647
+0x05d0: e8ee ae64 dc88 c897 3f8a 07a4 3a33 6b1b
+0x05e0: 3501 a30f 2758 cc44 4b4a
+
+Several such packets often follow after each other verifying
+the segmentation into 0x05a8 (1448) byte packages also on the
+reveiving end. As can be seen, the ethernet frames are
+0x05ea (1514) in size.
+
+Performance with iperf3 before this patch: ~15.5 Mbit/s
+Performance with iperf3 after this patch: ~175 Mbit/s
+
+This was running a 60 second test (twice) the best measurement
+was 179 Mbit/s.
+
+For comparison if I run iperf3 with UDP I get around 1.05 Mbit/s
+both before and after this patch.
+
+While this is a gigabit ethernet interface, the CPU is a cheap
+D-Link DIR-685 router (based on the ARMv5 Faraday FA526 at
+~50 MHz), and the software is not supposed to drive traffic,
+as the device has a DSA chip, so this kind of numbers can be
+expected.
+
+Fixes: ac631873c9e7 ("net: ethernet: cortina: Drop TSO support")
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
+---
+ drivers/net/ethernet/cortina/gemini.c | 23 +++++++++++++++++++----
+ 1 file changed, 19 insertions(+), 4 deletions(-)
+
+--- a/drivers/net/ethernet/cortina/gemini.c
++++ b/drivers/net/ethernet/cortina/gemini.c
+@@ -79,7 +79,8 @@ MODULE_PARM_DESC(debug, "Debug level (0=
+ #define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT)
+
+ #define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \
+- NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
++ NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \
++ NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
+
+ /**
+ * struct gmac_queue_page - page buffer per-page info
+@@ -1148,13 +1149,25 @@ static int gmac_map_tx_bufs(struct net_d
+ skb_frag_t *skb_frag;
+ dma_addr_t mapping;
+ void *buffer;
++ u16 mss;
+ int ret;
+
+- /* TODO: implement proper TSO using MTU in word3 */
+ word1 = skb->len;
+ word3 = SOF_BIT;
+
+- if (skb->len >= ETH_FRAME_LEN) {
++ mss = skb_shinfo(skb)->gso_size;
++ if (mss) {
++ /* This means we are dealing with TCP and skb->len is the
++ * sum total of all the segments. The TSO will deal with
++ * chopping this up for us.
++ */
++ /* The accelerator needs the full frame size here */
++ mss += skb_tcp_all_headers(skb);
++ netdev_dbg(netdev, "segment offloading mss = %04x len=%04x\n",
++ mss, skb->len);
++ word1 |= TSS_MTU_ENABLE_BIT;
++ word3 |= mss;
++ } else if (skb->len >= ETH_FRAME_LEN) {
+ /* Hardware offloaded checksumming isn't working on frames
+ * bigger than 1514 bytes. A hypothesis about this is that the
+ * checksum buffer is only 1518 bytes, so when the frames get
+@@ -1169,7 +1182,9 @@ static int gmac_map_tx_bufs(struct net_d
+ return ret;
+ }
+ word1 |= TSS_BYPASS_BIT;
+- } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
++ }
++
++ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ int tcp = 0;
+
+ /* We do not switch off the checksumming on non TCP/UDP
projects / openwrt / staging / nbd.git / blobdiff