net: lan966x: Stop using packing library

When a frame is injected from CPU, it is required to create an IFH(Inter
frame header) which sits in front of the frame that is transmitted.
This IFH, contains different fields like destination port, to bypass the
analyzer, priotity, etc. Lan966x it is using packing library to set and
get the fields of this IFH. But this seems to be an expensive
operations.
If this is changed with a simpler implementation, the RX will be
improved with ~5Mbit while on the TX is a much bigger improvement as it
is required to set more fields. Below are the numbers for TX.

Before:
[  5]   0.00-10.02  sec   439 MBytes   367 Mbits/sec    0 sender

After:
[  5]   0.00-10.00  sec   578 MBytes   485 Mbits/sec    0 sender

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig
index 8bcd60f17d6d3b9b8d00788051f8af6ffbda820a..571e6d4da1e9d6963119eeca8b573eee09b0f214 100644 (file)
--- a/drivers/net/ethernet/microchip/lan966x/Kconfig
+++ b/drivers/net/ethernet/microchip/lan966x/Kconfig
@@ -6,7 +6,6 @@ config LAN966X_SWITCH
        depends on NET_SWITCHDEV
        depends on BRIDGE || BRIDGE=n
        select PHYLINK
-       select PACKING
        select PAGE_POOL
        select VCAP
        help

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 4584a78c6ecbdd7b03a88f37eb60f0f5d015f08b..9be6462f1cc564fc95234ff03539fcdf3a290f0a 100644 (file)
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -7,7 +7,6 @@
 #include <linux/ip.h>
 #include <linux/of_platform.h>
 #include <linux/of_net.h>
-#include <linux/packing.h>
 #include <linux/phy/phy.h>
 #include <linux/reset.h>
 #include <net/addrconf.h>
@@ -305,46 +304,57 @@ err:
        return NETDEV_TX_BUSY;
 }
 
+static void lan966x_ifh_set(u8 *ifh, size_t val, size_t pos, size_t length)
+{
+       int i = 0;
+
+       do {
+               u8 p = IFH_LEN_BYTES - (pos + i) / 8 - 1;
+               u8 v = val >> i & 0xff;
+
+               /* There is no need to check for limits of the array, as these
+                * will never be written
+                */
+               ifh[p] |= v << ((pos + i) % 8);
+               ifh[p - 1] |= v >> (8 - (pos + i) % 8);
+
+               i += 8;
+       } while (i < length);
+}
+
 void lan966x_ifh_set_bypass(void *ifh, u64 bypass)
 {
-       packing(ifh, &bypass, IFH_POS_BYPASS + IFH_WID_BYPASS - 1,
-               IFH_POS_BYPASS, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, bypass, IFH_POS_BYPASS, IFH_WID_BYPASS);
 }
 
-void lan966x_ifh_set_port(void *ifh, u64 bypass)
+void lan966x_ifh_set_port(void *ifh, u64 port)
 {
-       packing(ifh, &bypass, IFH_POS_DSTS + IFH_WID_DSTS - 1,
-               IFH_POS_DSTS, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, port, IFH_POS_DSTS, IFH_WID_DSTS);
 }
 
-static void lan966x_ifh_set_qos_class(void *ifh, u64 bypass)
+static void lan966x_ifh_set_qos_class(void *ifh, u64 qos)
 {
-       packing(ifh, &bypass, IFH_POS_QOS_CLASS + IFH_WID_QOS_CLASS - 1,
-               IFH_POS_QOS_CLASS, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, qos, IFH_POS_QOS_CLASS, IFH_WID_QOS_CLASS);
 }
 
-static void lan966x_ifh_set_ipv(void *ifh, u64 bypass)
+static void lan966x_ifh_set_ipv(void *ifh, u64 ipv)
 {
-       packing(ifh, &bypass, IFH_POS_IPV + IFH_WID_IPV - 1,
-               IFH_POS_IPV, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, ipv, IFH_POS_IPV, IFH_WID_IPV);
 }
 
 static void lan966x_ifh_set_vid(void *ifh, u64 vid)
 {
-       packing(ifh, &vid, IFH_POS_TCI + IFH_WID_TCI - 1,
-               IFH_POS_TCI, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, vid, IFH_POS_TCI, IFH_WID_TCI);
 }
 
 static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op)
 {
-       packing(ifh, &rew_op, IFH_POS_REW_CMD + IFH_WID_REW_CMD - 1,
-               IFH_POS_REW_CMD, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, rew_op, IFH_POS_REW_CMD, IFH_WID_REW_CMD);
 }
 
 static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp)
 {
-       packing(ifh, &timestamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1,
-               IFH_POS_TIMESTAMP, IFH_LEN * 4, PACK, 0);
+       lan966x_ifh_set(ifh, timestamp, IFH_POS_TIMESTAMP, IFH_WID_TIMESTAMP);
 }
 
 static netdev_tx_t lan966x_port_xmit(struct sk_buff *skb,
@@ -582,22 +592,38 @@ static int lan966x_rx_frame_word(struct lan966x *lan966x, u8 grp, u32 *rval)
        }
 }
 
+static u64 lan966x_ifh_get(u8 *ifh, size_t pos, size_t length)
+{
+       u64 val = 0;
+       u8 v;
+
+       for (int i = 0; i < length ; i++) {
+               int j = pos + i;
+               int k = j % 8;
+
+               if (i == 0 || k == 0)
+                       v = ifh[IFH_LEN_BYTES - (j / 8) - 1];
+
+               if (v & (1 << k))
+                       val |= (1 << i);
+       }
+
+       return val;
+}
+
 void lan966x_ifh_get_src_port(void *ifh, u64 *src_port)
 {
-       packing(ifh, src_port, IFH_POS_SRCPORT + IFH_WID_SRCPORT - 1,
-               IFH_POS_SRCPORT, IFH_LEN * 4, UNPACK, 0);
+       *src_port = lan966x_ifh_get(ifh, IFH_POS_SRCPORT, IFH_WID_SRCPORT);
 }
 
 static void lan966x_ifh_get_len(void *ifh, u64 *len)
 {
-       packing(ifh, len, IFH_POS_LEN + IFH_WID_LEN - 1,
-               IFH_POS_LEN, IFH_LEN * 4, UNPACK, 0);
+       *len = lan966x_ifh_get(ifh, IFH_POS_LEN, IFH_WID_LEN);
 }
 
 void lan966x_ifh_get_timestamp(void *ifh, u64 *timestamp)
 {
-       packing(ifh, timestamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1,
-               IFH_POS_TIMESTAMP, IFH_LEN * 4, UNPACK, 0);
+       *timestamp = lan966x_ifh_get(ifh, IFH_POS_TIMESTAMP, IFH_WID_TIMESTAMP);
 }
 
 static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args)