renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-20 19:23:57 +08:00
Code

net/sched: act_skbmod: Add SKBMOD_F_ECN option support

Browse Source 
Currently, when doing rate limiting using the tc-police(8) action, the
easiest way is to simply drop the packets which exceed or conform the
configured bandwidth limit.  Add a new option to tc-skbmod(8), so that
users may use the ECN [1] extension to explicitly inform the receiver
about the congestion instead of dropping packets "on the floor".

The 2 least significant bits of the Traffic Class field in IPv4 and IPv6
headers are used to represent different ECN states [2]:

	0b00: "Non ECN-Capable Transport", Non-ECT
	0b10: "ECN Capable Transport", ECT(0)
	0b01: "ECN Capable Transport", ECT(1)
	0b11: "Congestion Encountered", CE

As an example:

	$ tc filter add dev eth0 parent 1: protocol ip prio 10 \
		matchall action skbmod ecn

Doing the above marks all ECT(0) and ECT(1) packets as CE.  It does NOT
affect Non-ECT or non-IP packets.  In the tc-police scenario mentioned
above, users may pipe a tc-police action and a tc-skbmod "ecn" action
together to achieve ECN-based rate limiting.

For TCP connections, upon receiving a CE packet, the receiver will respond
with an ECE packet, asking the sender to reduce their congestion window.
However ECN also works with other L4 protocols e.g. DCCP and SCTP [2], and
our implementation does not touch or care about L4 headers.

The updated tc-skbmod SYNOPSIS looks like the following:

	tc ... action skbmod { set SETTABLE | swap SWAPPABLE | ecn } ...

Only one of "set", "swap" or "ecn" shall be used in a single tc-skbmod
command.  Trying to use more than one of them at a time is considered
undefined behavior; pipe multiple tc-skbmod commands together instead.
"set" and "swap" only affect Ethernet packets, while "ecn" only affects
IPv{4,6} packets.

It is also worth mentioning that, in theory, the same effect could be
achieved by piping a "police" action and a "bpf" action using the
bpf_skb_ecn_set_ce() helper, but this requires eBPF programming from the
user, thus impractical.

Depends on patch "net/sched: act_skbmod: Skip non-Ethernet packets".

[1] https://datatracker.ietf.org/doc/html/rfc3168
[2] https://en.wikipedia.org/wiki/Explicit_Congestion_Notification

Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Peilin Ye 2021-07-27 18:33:15 -07:00 committed by David S. Miller
parent d80f6d6665
commit 56af5e749f
2 changed files with 33 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
include/uapi/linux/tc_act/tc_skbmod.h
View File

@ -17,6 +17,7 @@
#define SKBMOD_F_SMAC 0x2
#define SKBMOD_F_ETYPE 0x4
#define SKBMOD_F_SWAPMAC 0x8
#define SKBMOD_F_ECN 0x10
struct tc_skbmod {
tc_gen;

44
net/sched/act_skbmod.c
View File

@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <net/inet_ecn.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
@ -21,15 +22,13 @@
static unsigned int skbmod_net_id;
static struct tc_action_ops act_skbmod_ops;
#define MAX_EDIT_LEN ETH_HLEN
static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_skbmod *d = to_skbmod(a);
int action;
int action, max_edit_len, err;
struct tcf_skbmod_params *p;
u64 flags;
int err;
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
@ -38,19 +37,34 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
if (unlikely(action == TC_ACT_SHOT))
goto drop;
if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
return action;
max_edit_len = skb_mac_header_len(skb);
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
/* XXX: if you are going to edit more fields beyond ethernet header
* (example when you add IP header replacement or vlan swap)
* then MAX_EDIT_LEN needs to change appropriately
*/
err = skb_ensure_writable(skb, MAX_EDIT_LEN);
/* tcf_skbmod_init() guarantees "flags" to be one of the following:
* 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE}
* 2. SKBMOD_F_SWAPMAC
* 3. SKBMOD_F_ECN
* SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet
* packets.
*/
if (flags == SKBMOD_F_ECN) {
switch (skb_protocol(skb, true)) {
case cpu_to_be16(ETH_P_IP):
case cpu_to_be16(ETH_P_IPV6):
max_edit_len += skb_network_header_len(skb);
break;
default:
goto out;
}
} else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) {
goto out;
}
err = skb_ensure_writable(skb, max_edit_len);
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
if (flags & SKBMOD_F_DMAC)
ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
if (flags & SKBMOD_F_SMAC)
@ -66,6 +80,10 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
}
if (flags & SKBMOD_F_ECN)
INET_ECN_set_ce(skb);
out:
return action;
drop:
@ -129,6 +147,8 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
index = parm->index;
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
if (parm->flags & SKBMOD_F_ECN)
lflags = SKBMOD_F_ECN;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)