net: sched: support hash selecting tx queue

This patch allows users to pick queue_mapping, range
from A to B. Then we can load balance packets from A
to B tx queue. The range is an unsigned 16bit value
in decimal format.

$ tc filter ... action skbedit queue_mapping skbhash A B

"skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit")
is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH

  +----+      +----+      +----+
  | P1 |      | P2 |      | Pn |
  +----+      +----+      +----+
    |           |           |
    +-----------+-----------+
                |
                | clsact/skbedit
                |      MQ
                v
    +-----------+-----------+
    | q0        | qn        | qm
    v           v           v
  HTB/FQ       FIFO   ...  FIFO

For example:
If P1 sends out packets to different Pods on other host, and
we want distribute flows from qn - qm. Then we can use skb->hash
as hash.

setup commands:
$ NETDEV=eth0
$ ip netns add n1
$ ip link add ipv1 link $NETDEV type ipvlan mode l2
$ ip link set ipv1 netns n1
$ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up

$ tc qdisc add dev $NETDEV clsact
$ tc filter add dev $NETDEV egress protocol ip prio 1 \
        flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6
$ tc qdisc add dev $NETDEV handle 1: root mq
$ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb
$ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit
$ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit
$ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1
$ tc qdisc add dev $NETDEV parent 1:3 pfifo
$ tc qdisc add dev $NETDEV parent 1:4 pfifo
$ tc qdisc add dev $NETDEV parent 1:5 pfifo
$ tc qdisc add dev $NETDEV parent 1:6 pfifo
$ tc qdisc add dev $NETDEV parent 1:7 pfifo

$ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10

pick txqueue from 2 - 6:
$ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes
     tx_queue_0_bytes: 42
     tx_queue_1_bytes: 0
     tx_queue_2_bytes: 11442586444
     tx_queue_3_bytes: 7383615334
     tx_queue_4_bytes: 3981365579
     tx_queue_5_bytes: 3983235051
     tx_queue_6_bytes: 6706236461
     tx_queue_7_bytes: 42
     tx_queue_8_bytes: 0
     tx_queue_9_bytes: 0

txqueues 2 - 6 are mapped to classid 1:3 - 1:7
$ tc -s class show dev $NETDEV
...
class mq 1:3 root leaf 8002:
 Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq 1:4 root leaf 8003:
 Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq 1:5 root leaf 8004:
 Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq 1:6 root leaf 8005:
 Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
class mq 1:7 root leaf 8006:
 Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
...

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Talal Ahmad <talalahmad@google.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Antoine Tenart <atenart@kernel.org>
Cc: Wei Wang <weiwan@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index cab8229b9bed3834b596453e83c61582f5c15c58..dc1079f28e13edda9faf084d8c74df130f0fc87a 100644 (file)
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -17,6 +17,7 @@ struct tcf_skbedit_params {
        u32 mark;
        u32 mask;
        u16 queue_mapping;
+       u16 mapping_mod;
        u16 ptype;
        struct rcu_head rcu;
 };

diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
index 800e9337721887d80e5054a2564264bde5fc2936..6cb6101208d0a7f75f4eae9f99d7b3886e8f51a2 100644 (file)
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -29,6 +29,7 @@
 #define SKBEDIT_F_PTYPE                        0x8
 #define SKBEDIT_F_MASK                 0x10
 #define SKBEDIT_F_INHERITDSFIELD       0x20
+#define SKBEDIT_F_TXQ_SKBHASH          0x40
 
 struct tc_skbedit {
        tc_gen;
@@ -45,6 +46,7 @@ enum {
        TCA_SKBEDIT_PTYPE,
        TCA_SKBEDIT_MASK,
        TCA_SKBEDIT_FLAGS,
+       TCA_SKBEDIT_QUEUE_MAPPING_MAX,
        __TCA_SKBEDIT_MAX
 };
 #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 1c5fdb6e7c2f1b51a739c3c4a90174c21759aa1d..e3bd11dfe1ca5a0478977a879984fd71e0f9d9c6 100644 (file)
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -23,6 +23,20 @@
 static unsigned int skbedit_net_id;
 static struct tc_action_ops act_skbedit_ops;
 
+static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params,
+                           struct sk_buff *skb)
+{
+       u16 queue_mapping = params->queue_mapping;
+
+       if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+               u32 hash = skb_get_hash(skb);
+
+               queue_mapping += hash % params->mapping_mod;
+       }
+
+       return netdev_cap_txqueue(skb->dev, queue_mapping);
+}
+
 static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
                           struct tcf_result *res)
 {
@@ -62,7 +76,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 #ifdef CONFIG_NET_EGRESS
                netdev_xmit_skip_txqueue(true);
 #endif
-               skb_set_queue_mapping(skb, params->queue_mapping);
+               skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb));
        }
        if (params->flags & SKBEDIT_F_MARK) {
                skb->mark &= ~params->mask;
@@ -96,6 +110,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
        [TCA_SKBEDIT_PTYPE]             = { .len = sizeof(u16) },
        [TCA_SKBEDIT_MASK]              = { .len = sizeof(u32) },
        [TCA_SKBEDIT_FLAGS]             = { .len = sizeof(u64) },
+       [TCA_SKBEDIT_QUEUE_MAPPING_MAX] = { .len = sizeof(u16) },
 };
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
@@ -112,6 +127,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
        struct tcf_skbedit *d;
        u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
        u16 *queue_mapping = NULL, *ptype = NULL;
+       u16 mapping_mod = 1;
        bool exists = false;
        int ret = 0, err;
        u32 index;
@@ -157,6 +173,25 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
        if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
                u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
 
+               if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) {
+                       u16 *queue_mapping_max;
+
+                       if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] ||
+                           !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) {
+                               NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping.");
+                               return -EINVAL;
+                       }
+
+                       queue_mapping_max =
+                               nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]);
+                       if (*queue_mapping_max < *queue_mapping) {
+                               NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min.");
+                               return -EINVAL;
+                       }
+
+                       mapping_mod = *queue_mapping_max - *queue_mapping + 1;
+                       flags |= SKBEDIT_F_TXQ_SKBHASH;
+               }
                if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
                        flags |= SKBEDIT_F_INHERITDSFIELD;
        }
@@ -208,8 +243,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
        params_new->flags = flags;
        if (flags & SKBEDIT_F_PRIORITY)
                params_new->priority = *priority;
-       if (flags & SKBEDIT_F_QUEUE_MAPPING)
+       if (flags & SKBEDIT_F_QUEUE_MAPPING) {
                params_new->queue_mapping = *queue_mapping;
+               params_new->mapping_mod = mapping_mod;
+       }
        if (flags & SKBEDIT_F_MARK)
                params_new->mark = *mark;
        if (flags & SKBEDIT_F_PTYPE)
@@ -276,6 +313,13 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
                goto nla_put_failure;
        if (params->flags & SKBEDIT_F_INHERITDSFIELD)
                pure_flags |= SKBEDIT_F_INHERITDSFIELD;
+       if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+               if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX,
+                               params->queue_mapping + params->mapping_mod - 1))
+                       goto nla_put_failure;
+
+               pure_flags |= SKBEDIT_F_TXQ_SKBHASH;
+       }
        if (pure_flags != 0 &&
            nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
                goto nla_put_failure;
@@ -325,6 +369,7 @@ static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
        return nla_total_size(sizeof(struct tc_skbedit))
                + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
                + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+               + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */
                + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
                + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
                + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */