diff mbox series

[net-next,v1,2/2] net: sched: support hash/classid selecting queue_mapping

Message ID 20211206080512.36610-3-xiangxia.m.yue@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net: sched: allow user to select txqueue | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 9 this patch: 9
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 20 this patch: 20
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 11 this patch: 11
netdev/checkpatch fail ERROR: spaces required around that '=' (ctx:VxW)
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Tonghao Zhang Dec. 6, 2021, 8:05 a.m. UTC 
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>

This patch allows users to select queue_mapping, range
from A to B. And users can use skb-hash or cgroup classid
to select queues. Then the packets can load balance from A to
B queue.

$ tc filter ... action skbedit queue_mapping hash-type normal 0 4

"skbedit queue_mapping QUEUE_MAPPING"[0] is enhanced with two flags:
SKBEDIT_F_QUEUE_MAPPING_HASH, SKBEDIT_F_QUEUE_MAPPING_CLASSID.
The range is an unsigned 8bit value in decimal format.

[0]: https://man7.org/linux/man-pages/man8/tc-skbedit.8.html

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>
---
 include/net/tc_act/tc_skbedit.h        |  1 +
 include/uapi/linux/tc_act/tc_skbedit.h |  5 +++
 net/sched/act_skbedit.c                | 48 +++++++++++++++++++++++---
 3 files changed, 50 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index 00bfee70609e..ee96e0fa6566 100644
--- 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 800e93377218..badb58ec84ef 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -29,6 +29,11 @@ 
 #define SKBEDIT_F_PTYPE			0x8
 #define SKBEDIT_F_MASK			0x10
 #define SKBEDIT_F_INHERITDSFIELD	0x20
+#define SKBEDIT_F_QUEUE_MAPPING_HASH	0x40
+#define SKBEDIT_F_QUEUE_MAPPING_CLASSID	0x80
+
+#define SKBEDIT_F_QUEUE_MAPPING_HASH_MASK (SKBEDIT_F_QUEUE_MAPPING_HASH | \
+					   SKBEDIT_F_QUEUE_MAPPING_CLASSID)
 
 struct tc_skbedit {
 	tc_gen;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 940091a7c7f0..9cb65bcce001 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -10,6 +10,7 @@ 
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
+#include <net/cls_cgroup.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/ip.h>
@@ -23,6 +24,25 @@ 
 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;
+	u16 mapping_mod = params->mapping_mod;
+	u32 hash = 0;
+
+	if (!(params->flags & SKBEDIT_F_QUEUE_MAPPING_HASH_MASK))
+		return netdev_cap_txqueue(skb->dev, queue_mapping);
+
+	if (params->flags & SKBEDIT_F_QUEUE_MAPPING_CLASSID)
+		hash = jhash_1word(task_get_classid(skb), 0);
+	else if (params->flags & SKBEDIT_F_QUEUE_MAPPING_HASH)
+		hash = skb_get_hash(skb);
+
+	queue_mapping= (queue_mapping & 0xff) + hash % 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)
 {
@@ -57,10 +77,9 @@  static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 			break;
 		}
 	}
-	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > params->queue_mapping) {
+	if (params->flags & SKBEDIT_F_QUEUE_MAPPING) {
 		skb->tc_skip_txqueue = 1;
-		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;
@@ -110,6 +129,7 @@  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 = 0;
 	bool exists = false;
 	int ret = 0, err;
 	u32 index;
@@ -157,6 +177,21 @@  static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 		if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
 			flags |= SKBEDIT_F_INHERITDSFIELD;
+		if (*pure_flags & SKBEDIT_F_QUEUE_MAPPING_HASH_MASK) {
+			u16 max, min;
+
+			if (!queue_mapping)
+				return -EINVAL;
+
+			max = *queue_mapping >> 8;
+			min = *queue_mapping & 0xff;
+			if (max < min)
+				return -EINVAL;
+
+			mapping_mod = max - min + 1;
+			flags |= *pure_flags &
+				 SKBEDIT_F_QUEUE_MAPPING_HASH_MASK;
+		}
 	}
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
@@ -206,8 +241,10 @@  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)
@@ -274,6 +311,9 @@  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_QUEUE_MAPPING_HASH_MASK)
+		pure_flags |= params->flags &
+			      SKBEDIT_F_QUEUE_MAPPING_HASH_MASK;
 	if (pure_flags != 0 &&
 	    nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
 		goto nla_put_failure;