| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20211220123839.54664-3-xiangxia.m.yue@gmail.com>
Date: Mon, 20 Dec 2021 20:38:39 +0800
From: xiangxia.m.yue@...il.com
To: netdev@...r.kernel.org
Cc: Tonghao Zhang <xiangxia.m.yue@...il.com>,
Jamal Hadi Salim <jhs@...atatu.com>,
Cong Wang <xiyou.wangcong@...il.com>,
Jiri Pirko <jiri@...nulli.us>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Jonathan Lemon <jonathan.lemon@...il.com>,
Eric Dumazet <edumazet@...gle.com>,
Alexander Lobakin <alobakin@...me>,
Paolo Abeni <pabeni@...hat.com>,
Talal Ahmad <talalahmad@...gle.com>,
Kevin Hao <haokexin@...il.com>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>,
Kees Cook <keescook@...omium.org>,
Kumar Kartikeya Dwivedi <memxor@...il.com>,
Antoine Tenart <atenart@...nel.org>,
Wei Wang <weiwan@...gle.com>, Arnd Bergmann <arnd@...db.de>
Subject: [net-next v5 2/2] net: sched: support hash/classid/cpuid selecting tx queue
From: Tonghao Zhang <xiangxia.m.yue@...il.com>
This patch allows user to select queue_mapping, range
from A to B. And user can use skbhash, cgroup classid
and cpuid to select Tx queues. Then we can load balance
packets from A to B 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
* SKBEDIT_F_TXQ_CLASSID
* SKBEDIT_F_TXQ_CPUID
Use skb->hash, cgroup classid, or cpuid to distribute packets.
Then same range of tx queues can be shared for different flows,
cgroups, or CPUs in a variety of scenarios.
For example, F1 may share range R1 with F2. The best way to do
that is to set flag to SKBEDIT_F_TXQ_HASH, using skb->hash to
share the queues. If cgroup C1 want to share the R1 with cgroup
C2 .. Cn, use the SKBEDIT_F_TXQ_CLASSID. Of course, in some other
scenario, C1 use R1, while Cn can use the Rn.
Cc: Jamal Hadi Salim <jhs@...atatu.com>
Cc: Cong Wang <xiyou.wangcong@...il.com>
Cc: Jiri Pirko <jiri@...nulli.us>
Cc: "David S. Miller" <davem@...emloft.net>
Cc: Jakub Kicinski <kuba@...nel.org>
Cc: Jonathan Lemon <jonathan.lemon@...il.com>
Cc: Eric Dumazet <edumazet@...gle.com>
Cc: Alexander Lobakin <alobakin@...me>
Cc: Paolo Abeni <pabeni@...hat.com>
Cc: Talal Ahmad <talalahmad@...gle.com>
Cc: Kevin Hao <haokexin@...il.com>
Cc: Ilias Apalodimas <ilias.apalodimas@...aro.org>
Cc: Kees Cook <keescook@...omium.org>
Cc: Kumar Kartikeya Dwivedi <memxor@...il.com>
Cc: Antoine Tenart <atenart@...nel.org>
Cc: Wei Wang <weiwan@...gle.com>
Cc: Arnd Bergmann <arnd@...db.de>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@...il.com>
---
include/net/tc_act/tc_skbedit.h | 1 +
include/uapi/linux/tc_act/tc_skbedit.h | 8 +++
net/sched/act_skbedit.c | 81 ++++++++++++++++++++++++--
3 files changed, 85 insertions(+), 5 deletions(-)
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..5ea1438a4d88 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -29,6 +29,13 @@
#define SKBEDIT_F_PTYPE 0x8
#define SKBEDIT_F_MASK 0x10
#define SKBEDIT_F_INHERITDSFIELD 0x20
+#define SKBEDIT_F_TXQ_SKBHASH 0x40
+#define SKBEDIT_F_TXQ_CLASSID 0x80
+#define SKBEDIT_F_TXQ_CPUID 0x100
+
+#define SKBEDIT_F_TXQ_HASH_MASK (SKBEDIT_F_TXQ_SKBHASH | \
+ SKBEDIT_F_TXQ_CLASSID | \
+ SKBEDIT_F_TXQ_CPUID)
struct tc_skbedit {
tc_gen;
@@ -45,6 +52,7 @@ 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 48504ed3b280..2a7a1f8b2dfc 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 +24,38 @@
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)
+{
+ u32 mapping_hash_type = params->flags & SKBEDIT_F_TXQ_HASH_MASK;
+ u16 queue_mapping = params->queue_mapping;
+ u16 mapping_mod = params->mapping_mod;
+ u32 hash = 0;
+
+ switch (mapping_hash_type) {
+ case SKBEDIT_F_TXQ_CLASSID:
+ hash = task_get_classid(skb);
+ break;
+ case SKBEDIT_F_TXQ_SKBHASH:
+ hash = skb_get_hash(skb);
+ break;
+ case SKBEDIT_F_TXQ_CPUID:
+ hash = raw_smp_processor_id();
+ break;
+ case 0:
+ /* Hash type isn't specified. In this case:
+ * hash % mapping_mod == 0
+ */
+ break;
+ default:
+ net_warn_ratelimited("The type of queue_mapping hash is not supported. 0x%x\n",
+ mapping_hash_type);
+ }
+
+ queue_mapping = queue_mapping + 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 +90,9 @@ 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) {
netdev_xmit_skip_txqueue(true);
- 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;
@@ -94,6 +126,7 @@ 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,
@@ -110,6 +143,7 @@ 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;
@@ -154,7 +188,34 @@ 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]);
-
+ u64 mapping_hash_type;
+
+ mapping_hash_type = *pure_flags & SKBEDIT_F_TXQ_HASH_MASK;
+ if (mapping_hash_type) {
+ u16 *queue_mapping_max;
+
+ /* Hash types are mutually exclusive. */
+ if (mapping_hash_type & (mapping_hash_type - 1)) {
+ NL_SET_ERR_MSG_MOD(extack, "Multi types of hash are specified.");
+ return -EINVAL;
+ }
+
+ 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 |= mapping_hash_type;
+ }
if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
flags |= SKBEDIT_F_INHERITDSFIELD;
}
@@ -206,8 +267,10 @@ 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 +337,13 @@ 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_HASH_MASK) {
+ if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX,
+ params->queue_mapping + params->mapping_mod - 1))
+ goto nla_put_failure;
+
+ pure_flags |= params->flags & SKBEDIT_F_TXQ_HASH_MASK;
+ }
if (pure_flags != 0 &&
nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
goto nla_put_failure;
@@ -323,6 +393,7 @@ 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 */
--
2.27.0
Powered by blists - more mailing lists