mirror of
https://github.com/torvalds/linux.git
synced 2024-12-27 13:22:23 +00:00
1f211a1b92
This work adds a generalization of the ingress qdisc as a qdisc holding only classifiers. The clsact qdisc works on ingress, but also on egress. In both cases, it's execution happens without taking the qdisc lock, and the main difference for the egress part compared to prior version of [1] is that this can be applied with _any_ underlying real egress qdisc (also classless ones). Besides solving the use-case of [1], that is, allowing for more programmability on assigning skb->priority for the mqprio case that is supported by most popular 10G+ NICs, it also opens up a lot more flexibility for other tc applications. The main work on classification can already be done at clsact egress time if the use-case allows and state stored for later retrieval f.e. again in skb->priority with major/minors (which is checked by most classful qdiscs before consulting tc_classify()) and/or in other skb fields like skb->tc_index for some light-weight post-processing to get to the eventual classid in case of a classful qdisc. Another use case is that the clsact egress part allows to have a central egress counterpart to the ingress classifiers, so that classifiers can easily share state (e.g. in cls_bpf via eBPF maps) for ingress and egress. Currently, default setups like mq + pfifo_fast would require for this to use, for example, prio qdisc instead (to get a tc_classify() run) and to duplicate the egress classifier for each queue. With clsact, it allows for leaving the setup as is, it can additionally assign skb->priority to put the skb in one of pfifo_fast's bands and it can share state with maps. Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid) w/o the need to perform a skb_dst_force() to hold on to it any longer. In lwt case, we can also use this facility to setup dst metadata via cls_bpf (bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for that (case of IFF_NO_QUEUE devices, for example). The realization can be done without any changes to the scheduler core framework. All it takes is that we have two a-priori defined minors/child classes, where we can mux between ingress and egress classifier list (dev->ingress_cl_list and dev->egress_cl_list, latter stored close to dev->_tx to avoid extra cacheline miss for moderate loads). The egress part is a bit similar modelled to handle_ing() and patched to a noop in case the functionality is not used. Both handlers are now called sch_handle_ingress() and sch_handle_egress(), code sharing among the two doesn't seem practical as there are various minor differences in both paths, so that making them conditional in a single handler would rather slow things down. Full compatibility to ingress qdisc is provided as well. Since both piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist per netdevice, and thus ingress qdisc specific behaviour can be retained for user space. This means, either a user does 'tc qdisc add dev foo ingress' and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact' alternative, where both, ingress and egress classifier can be configured as in the below example. ingress qdisc supports attaching classifier to any minor number whereas clsact has two fixed minors for muxing between the lists, therefore to not break user space setups, they are better done as two separate qdiscs. I decided to extend the sch_ingress module with clsact functionality so that commonly used code can be reused, the module is being aliased with sch_clsact so that it can be auto-loaded properly. Alternative would have been to add a flag when initializing ingress to alter its behaviour plus aliasing to a different name (as it's more than just ingress). However, the first would end up, based on the flag, choosing the new/old behaviour by calling different function implementations to handle each anyway, the latter would require to register ingress qdisc once again under different alias. So, this really begs to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops by its own that share callbacks used by both. Example, adding qdisc: # tc qdisc add dev foo clsact # tc qdisc show dev foo qdisc mq 0: root qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc clsact ffff: parent ffff:fff1 Adding filters (deleting, etc works analogous by specifying ingress/egress): # tc filter add dev foo ingress bpf da obj bar.o sec ingress # tc filter add dev foo egress bpf da obj bar.o sec egress # tc filter show dev foo ingress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action # tc filter show dev foo egress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will show an empty list for clsact. Either using the parent names (ingress/egress) or specifying the full major/minor will then show the related filter lists. Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend. [1] http://patchwork.ozlabs.org/patch/512949/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
199 lines
4.2 KiB
C
199 lines
4.2 KiB
C
/* net/sched/sch_ingress.c - Ingress and clsact qdisc
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*
|
|
* Authors: Jamal Hadi Salim 1999
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/rtnetlink.h>
|
|
|
|
#include <net/netlink.h>
|
|
#include <net/pkt_sched.h>
|
|
|
|
static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static unsigned long ingress_get(struct Qdisc *sch, u32 classid)
|
|
{
|
|
return TC_H_MIN(classid) + 1;
|
|
}
|
|
|
|
static unsigned long ingress_bind_filter(struct Qdisc *sch,
|
|
unsigned long parent, u32 classid)
|
|
{
|
|
return ingress_get(sch, classid);
|
|
}
|
|
|
|
static void ingress_put(struct Qdisc *sch, unsigned long cl)
|
|
{
|
|
}
|
|
|
|
static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker)
|
|
{
|
|
}
|
|
|
|
static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch,
|
|
unsigned long cl)
|
|
{
|
|
struct net_device *dev = qdisc_dev(sch);
|
|
|
|
return &dev->ingress_cl_list;
|
|
}
|
|
|
|
static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
|
|
{
|
|
net_inc_ingress_queue();
|
|
sch->flags |= TCQ_F_CPUSTATS;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void ingress_destroy(struct Qdisc *sch)
|
|
{
|
|
struct net_device *dev = qdisc_dev(sch);
|
|
|
|
tcf_destroy_chain(&dev->ingress_cl_list);
|
|
net_dec_ingress_queue();
|
|
}
|
|
|
|
static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
|
|
{
|
|
struct nlattr *nest;
|
|
|
|
nest = nla_nest_start(skb, TCA_OPTIONS);
|
|
if (nest == NULL)
|
|
goto nla_put_failure;
|
|
|
|
return nla_nest_end(skb, nest);
|
|
|
|
nla_put_failure:
|
|
nla_nest_cancel(skb, nest);
|
|
return -1;
|
|
}
|
|
|
|
static const struct Qdisc_class_ops ingress_class_ops = {
|
|
.leaf = ingress_leaf,
|
|
.get = ingress_get,
|
|
.put = ingress_put,
|
|
.walk = ingress_walk,
|
|
.tcf_chain = ingress_find_tcf,
|
|
.bind_tcf = ingress_bind_filter,
|
|
.unbind_tcf = ingress_put,
|
|
};
|
|
|
|
static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
|
|
.cl_ops = &ingress_class_ops,
|
|
.id = "ingress",
|
|
.init = ingress_init,
|
|
.destroy = ingress_destroy,
|
|
.dump = ingress_dump,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static unsigned long clsact_get(struct Qdisc *sch, u32 classid)
|
|
{
|
|
switch (TC_H_MIN(classid)) {
|
|
case TC_H_MIN(TC_H_MIN_INGRESS):
|
|
case TC_H_MIN(TC_H_MIN_EGRESS):
|
|
return TC_H_MIN(classid);
|
|
default:
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
static unsigned long clsact_bind_filter(struct Qdisc *sch,
|
|
unsigned long parent, u32 classid)
|
|
{
|
|
return clsact_get(sch, classid);
|
|
}
|
|
|
|
static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch,
|
|
unsigned long cl)
|
|
{
|
|
struct net_device *dev = qdisc_dev(sch);
|
|
|
|
switch (cl) {
|
|
case TC_H_MIN(TC_H_MIN_INGRESS):
|
|
return &dev->ingress_cl_list;
|
|
case TC_H_MIN(TC_H_MIN_EGRESS):
|
|
return &dev->egress_cl_list;
|
|
default:
|
|
return NULL;
|
|
}
|
|
}
|
|
|
|
static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
|
|
{
|
|
net_inc_ingress_queue();
|
|
net_inc_egress_queue();
|
|
|
|
sch->flags |= TCQ_F_CPUSTATS;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void clsact_destroy(struct Qdisc *sch)
|
|
{
|
|
struct net_device *dev = qdisc_dev(sch);
|
|
|
|
tcf_destroy_chain(&dev->ingress_cl_list);
|
|
tcf_destroy_chain(&dev->egress_cl_list);
|
|
|
|
net_dec_ingress_queue();
|
|
net_dec_egress_queue();
|
|
}
|
|
|
|
static const struct Qdisc_class_ops clsact_class_ops = {
|
|
.leaf = ingress_leaf,
|
|
.get = clsact_get,
|
|
.put = ingress_put,
|
|
.walk = ingress_walk,
|
|
.tcf_chain = clsact_find_tcf,
|
|
.bind_tcf = clsact_bind_filter,
|
|
.unbind_tcf = ingress_put,
|
|
};
|
|
|
|
static struct Qdisc_ops clsact_qdisc_ops __read_mostly = {
|
|
.cl_ops = &clsact_class_ops,
|
|
.id = "clsact",
|
|
.init = clsact_init,
|
|
.destroy = clsact_destroy,
|
|
.dump = ingress_dump,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static int __init ingress_module_init(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = register_qdisc(&ingress_qdisc_ops);
|
|
if (!ret) {
|
|
ret = register_qdisc(&clsact_qdisc_ops);
|
|
if (ret)
|
|
unregister_qdisc(&ingress_qdisc_ops);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void __exit ingress_module_exit(void)
|
|
{
|
|
unregister_qdisc(&ingress_qdisc_ops);
|
|
unregister_qdisc(&clsact_qdisc_ops);
|
|
}
|
|
|
|
module_init(ingress_module_init);
|
|
module_exit(ingress_module_exit);
|
|
|
|
MODULE_ALIAS("sch_clsact");
|
|
MODULE_LICENSE("GPL");
|