2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2016-09-13 08:13:09 +08:00
|
|
|
/*
|
|
|
|
|
* net/sched/act_skbmod.c skb data modifier
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
2021-07-20 07:41:24 +08:00
|
|
|
#include <linux/if_arp.h>
|
2016-09-13 08:13:09 +08:00
|
|
|
#include <linux/init.h>
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
#include <linux/rtnetlink.h>
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
#include <net/inet_ecn.h>
|
2016-09-13 08:13:09 +08:00
|
|
|
#include <net/netlink.h>
|
|
|
|
|
#include <net/pkt_sched.h>
|
2019-03-20 22:00:12 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
#include <linux/tc_act/tc_skbmod.h>
|
|
|
|
|
#include <net/tc_act/tc_skbmod.h>
|
|
|
|
|
|
netns: make struct pernet_operations::id unsigned int
Make struct pernet_operations::id unsigned.
There are 2 reasons to do so:
1)
This field is really an index into an zero based array and
thus is unsigned entity. Using negative value is out-of-bound
access by definition.
2)
On x86_64 unsigned 32-bit data which are mixed with pointers
via array indexing or offsets added or subtracted to pointers
are preffered to signed 32-bit data.
"int" being used as an array index needs to be sign-extended
to 64-bit before being used.
void f(long *p, int i)
{
g(p[i]);
}
roughly translates to
movsx rsi, esi
mov rdi, [rsi+...]
call g
MOVSX is 3 byte instruction which isn't necessary if the variable is
unsigned because x86_64 is zero extending by default.
Now, there is net_generic() function which, you guessed it right, uses
"int" as an array index:
static inline void *net_generic(const struct net *net, int id)
{
...
ptr = ng->ptr[id - 1];
...
}
And this function is used a lot, so those sign extensions add up.
Patch snipes ~1730 bytes on allyesconfig kernel (without all junk
messing with code generation):
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
Unfortunately some functions actually grow bigger.
This is a semmingly random artefact of code generation with register
allocator being used differently. gcc decides that some variable
needs to live in new r8+ registers and every access now requires REX
prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be
used which is longer than [r8]
However, overall balance is in negative direction:
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
function old new delta
nfsd4_lock 3886 3959 +73
tipc_link_build_proto_msg 1096 1140 +44
mac80211_hwsim_new_radio 2776 2808 +32
tipc_mon_rcv 1032 1058 +26
svcauth_gss_legacy_init 1413 1429 +16
tipc_bcbase_select_primary 379 392 +13
nfsd4_exchange_id 1247 1260 +13
nfsd4_setclientid_confirm 782 793 +11
...
put_client_renew_locked 494 480 -14
ip_set_sockfn_get 730 716 -14
geneve_sock_add 829 813 -16
nfsd4_sequence_done 721 703 -18
nlmclnt_lookup_host 708 686 -22
nfsd4_lockt 1085 1063 -22
nfs_get_client 1077 1050 -27
tcf_bpf_init 1106 1076 -30
nfsd4_encode_fattr 5997 5930 -67
Total: Before=154856051, After=154854321, chg -0.00%
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
|
|
|
static unsigned int skbmod_net_id;
|
2016-09-13 08:13:09 +08:00
|
|
|
static struct tc_action_ops act_skbmod_ops;
|
|
|
|
|
|
2018-08-12 21:34:59 +08:00
|
|
|
static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
|
2016-09-13 08:13:09 +08:00
|
|
|
struct tcf_result *res)
|
|
|
|
|
{
|
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
int action, max_edit_len, err;
|
2016-09-13 08:13:09 +08:00
|
|
|
struct tcf_skbmod_params *p;
|
|
|
|
|
u64 flags;
|
|
|
|
|
|
|
|
|
|
tcf_lastuse_update(&d->tcf_tm);
|
|
|
|
|
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
|
|
|
|
|
|
2021-07-20 07:41:24 +08:00
|
|
|
action = READ_ONCE(d->tcf_action);
|
|
|
|
|
if (unlikely(action == TC_ACT_SHOT))
|
|
|
|
|
goto drop;
|
|
|
|
|
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
max_edit_len = skb_mac_header_len(skb);
|
|
|
|
|
p = rcu_dereference_bh(d->skbmod_p);
|
|
|
|
|
flags = p->flags;
|
|
|
|
|
|
|
|
|
|
/* 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;
|
|
|
|
|
}
|
2021-07-20 07:41:24 +08:00
|
|
|
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
err = skb_ensure_writable(skb, max_edit_len);
|
2018-07-30 20:30:43 +08:00
|
|
|
if (unlikely(err)) /* best policy is to drop on the floor */
|
|
|
|
|
goto drop;
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
if (flags & SKBMOD_F_DMAC)
|
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
|
|
|
|
|
if (flags & SKBMOD_F_SMAC)
|
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
|
|
|
|
|
if (flags & SKBMOD_F_ETYPE)
|
|
|
|
|
eth_hdr(skb)->h_proto = p->eth_type;
|
|
|
|
|
|
|
|
|
|
if (flags & SKBMOD_F_SWAPMAC) {
|
|
|
|
|
u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
|
|
|
|
|
/*XXX: I am sure we can come up with more efficient swapping*/
|
|
|
|
|
ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest);
|
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source);
|
|
|
|
|
ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
|
|
|
|
|
}
|
|
|
|
|
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
if (flags & SKBMOD_F_ECN)
|
|
|
|
|
INET_ECN_set_ce(skb);
|
|
|
|
|
|
|
|
|
|
out:
|
2016-09-13 08:13:09 +08:00
|
|
|
return action;
|
2018-07-30 20:30:43 +08:00
|
|
|
|
|
|
|
|
drop:
|
|
|
|
|
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
|
|
|
|
|
return TC_ACT_SHOT;
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
|
|
|
|
|
[TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) },
|
|
|
|
|
[TCA_SKBMOD_DMAC] = { .len = ETH_ALEN },
|
|
|
|
|
[TCA_SKBMOD_SMAC] = { .len = ETH_ALEN },
|
|
|
|
|
[TCA_SKBMOD_ETYPE] = { .type = NLA_U16 },
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
|
|
|
|
|
struct nlattr *est, struct tc_action **a,
|
2019-10-30 22:09:05 +08:00
|
|
|
struct tcf_proto *tp, u32 flags,
|
2018-07-05 22:24:25 +08:00
|
|
|
struct netlink_ext_ack *extack)
|
2016-09-13 08:13:09 +08:00
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
2021-07-30 07:12:14 +08:00
|
|
|
bool ovr = flags & TCA_ACT_FLAGS_REPLACE;
|
|
|
|
|
bool bind = flags & TCA_ACT_FLAGS_BIND;
|
2016-09-13 08:13:09 +08:00
|
|
|
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
|
|
|
|
|
struct tcf_skbmod_params *p, *p_old;
|
2019-03-20 22:00:12 +08:00
|
|
|
struct tcf_chain *goto_ch = NULL;
|
2016-09-13 08:13:09 +08:00
|
|
|
struct tc_skbmod *parm;
|
2019-08-01 21:02:51 +08:00
|
|
|
u32 lflags = 0, index;
|
2016-09-13 08:13:09 +08:00
|
|
|
struct tcf_skbmod *d;
|
|
|
|
|
bool exists = false;
|
|
|
|
|
u8 *daddr = NULL;
|
|
|
|
|
u8 *saddr = NULL;
|
|
|
|
|
u16 eth_type = 0;
|
|
|
|
|
int ret = 0, err;
|
|
|
|
|
|
|
|
|
|
if (!nla)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
netlink: make validation more configurable for future strictness
We currently have two levels of strict validation:
1) liberal (default)
- undefined (type >= max) & NLA_UNSPEC attributes accepted
- attribute length >= expected accepted
- garbage at end of message accepted
2) strict (opt-in)
- NLA_UNSPEC attributes accepted
- attribute length >= expected accepted
Split out parsing strictness into four different options:
* TRAILING - check that there's no trailing data after parsing
attributes (in message or nested)
* MAXTYPE - reject attrs > max known type
* UNSPEC - reject attributes with NLA_UNSPEC policy entries
* STRICT_ATTRS - strictly validate attribute size
The default for future things should be *everything*.
The current *_strict() is a combination of TRAILING and MAXTYPE,
and is renamed to _deprecated_strict().
The current regular parsing has none of this, and is renamed to
*_parse_deprecated().
Additionally it allows us to selectively set one of the new flags
even on old policies. Notably, the UNSPEC flag could be useful in
this case, since it can be arranged (by filling in the policy) to
not be an incompatible userspace ABI change, but would then going
forward prevent forgetting attribute entries. Similar can apply
to the POLICY flag.
We end up with the following renames:
* nla_parse -> nla_parse_deprecated
* nla_parse_strict -> nla_parse_deprecated_strict
* nlmsg_parse -> nlmsg_parse_deprecated
* nlmsg_parse_strict -> nlmsg_parse_deprecated_strict
* nla_parse_nested -> nla_parse_nested_deprecated
* nla_validate_nested -> nla_validate_nested_deprecated
Using spatch, of course:
@@
expression TB, MAX, HEAD, LEN, POL, EXT;
@@
-nla_parse(TB, MAX, HEAD, LEN, POL, EXT)
+nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT)
@@
expression NLH, HDRLEN, TB, MAX, POL, EXT;
@@
-nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT)
+nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT)
@@
expression NLH, HDRLEN, TB, MAX, POL, EXT;
@@
-nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
+nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
@@
expression TB, MAX, NLA, POL, EXT;
@@
-nla_parse_nested(TB, MAX, NLA, POL, EXT)
+nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT)
@@
expression START, MAX, POL, EXT;
@@
-nla_validate_nested(START, MAX, POL, EXT)
+nla_validate_nested_deprecated(START, MAX, POL, EXT)
@@
expression NLH, HDRLEN, MAX, POL, EXT;
@@
-nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT)
+nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT)
For this patch, don't actually add the strict, non-renamed versions
yet so that it breaks compile if I get it wrong.
Also, while at it, make nla_validate and nla_parse go down to a
common __nla_validate_parse() function to avoid code duplication.
Ultimately, this allows us to have very strict validation for every
new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the
next patch, while existing things will continue to work as is.
In effect then, this adds fully strict validation for any new command.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
|
|
|
err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla,
|
|
|
|
|
skbmod_policy, NULL);
|
2016-09-13 08:13:09 +08:00
|
|
|
if (err < 0)
|
|
|
|
|
return err;
|
|
|
|
|
|
|
|
|
|
if (!tb[TCA_SKBMOD_PARMS])
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_DMAC]) {
|
|
|
|
|
daddr = nla_data(tb[TCA_SKBMOD_DMAC]);
|
|
|
|
|
lflags |= SKBMOD_F_DMAC;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_SMAC]) {
|
|
|
|
|
saddr = nla_data(tb[TCA_SKBMOD_SMAC]);
|
|
|
|
|
lflags |= SKBMOD_F_SMAC;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (tb[TCA_SKBMOD_ETYPE]) {
|
|
|
|
|
eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]);
|
|
|
|
|
lflags |= SKBMOD_F_ETYPE;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
parm = nla_data(tb[TCA_SKBMOD_PARMS]);
|
2019-08-01 21:02:51 +08:00
|
|
|
index = parm->index;
|
2016-09-13 08:13:09 +08:00
|
|
|
if (parm->flags & SKBMOD_F_SWAPMAC)
|
|
|
|
|
lflags = SKBMOD_F_SWAPMAC;
|
net/sched: act_skbmod: Add SKBMOD_F_ECN option support
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>
2021-07-28 09:33:15 +08:00
|
|
|
if (parm->flags & SKBMOD_F_ECN)
|
|
|
|
|
lflags = SKBMOD_F_ECN;
|
2016-09-13 08:13:09 +08:00
|
|
|
|
2019-08-01 21:02:51 +08:00
|
|
|
err = tcf_idr_check_alloc(tn, &index, a, bind);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (err < 0)
|
|
|
|
|
return err;
|
|
|
|
|
exists = err;
|
2016-09-13 08:13:09 +08:00
|
|
|
if (exists && bind)
|
|
|
|
|
return 0;
|
|
|
|
|
|
2018-05-12 02:35:33 +08:00
|
|
|
if (!lflags) {
|
|
|
|
|
if (exists)
|
|
|
|
|
tcf_idr_release(*a, bind);
|
2018-07-05 22:24:32 +08:00
|
|
|
else
|
2019-08-01 21:02:51 +08:00
|
|
|
tcf_idr_cleanup(tn, index);
|
2016-09-13 08:13:09 +08:00
|
|
|
return -EINVAL;
|
2018-05-12 02:35:33 +08:00
|
|
|
}
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
if (!exists) {
|
2019-08-01 21:02:51 +08:00
|
|
|
ret = tcf_idr_create(tn, index, est, a,
|
2021-12-18 02:16:17 +08:00
|
|
|
&act_skbmod_ops, bind, true, flags);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (ret) {
|
2019-08-01 21:02:51 +08:00
|
|
|
tcf_idr_cleanup(tn, index);
|
2016-09-13 08:13:09 +08:00
|
|
|
return ret;
|
2018-07-05 22:24:32 +08:00
|
|
|
}
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
ret = ACT_P_CREATED;
|
2018-07-05 22:24:30 +08:00
|
|
|
} else if (!ovr) {
|
2017-08-30 14:31:59 +08:00
|
|
|
tcf_idr_release(*a, bind);
|
2018-07-05 22:24:30 +08:00
|
|
|
return -EEXIST;
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
2019-03-20 22:00:12 +08:00
|
|
|
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
|
|
|
|
|
if (err < 0)
|
|
|
|
|
goto release_idr;
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
d = to_skbmod(*a);
|
|
|
|
|
|
|
|
|
|
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
|
|
|
|
|
if (unlikely(!p)) {
|
2019-03-20 22:00:12 +08:00
|
|
|
err = -ENOMEM;
|
|
|
|
|
goto put_chain;
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
p->flags = lflags;
|
|
|
|
|
|
|
|
|
|
if (ovr)
|
|
|
|
|
spin_lock_bh(&d->tcf_lock);
|
2018-08-11 01:51:49 +08:00
|
|
|
/* Protected by tcf_lock if overwriting existing action. */
|
2019-03-20 22:00:12 +08:00
|
|
|
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
|
2018-08-11 01:51:49 +08:00
|
|
|
p_old = rcu_dereference_protected(d->skbmod_p, 1);
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
if (lflags & SKBMOD_F_DMAC)
|
|
|
|
|
ether_addr_copy(p->eth_dst, daddr);
|
|
|
|
|
if (lflags & SKBMOD_F_SMAC)
|
|
|
|
|
ether_addr_copy(p->eth_src, saddr);
|
|
|
|
|
if (lflags & SKBMOD_F_ETYPE)
|
|
|
|
|
p->eth_type = htons(eth_type);
|
|
|
|
|
|
|
|
|
|
rcu_assign_pointer(d->skbmod_p, p);
|
|
|
|
|
if (ovr)
|
|
|
|
|
spin_unlock_bh(&d->tcf_lock);
|
|
|
|
|
|
|
|
|
|
if (p_old)
|
|
|
|
|
kfree_rcu(p_old, rcu);
|
2019-03-20 22:00:12 +08:00
|
|
|
if (goto_ch)
|
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
2016-09-13 08:13:09 +08:00
|
|
|
|
|
|
|
|
return ret;
|
2019-03-20 22:00:12 +08:00
|
|
|
put_chain:
|
|
|
|
|
if (goto_ch)
|
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
|
|
|
|
release_idr:
|
|
|
|
|
tcf_idr_release(*a, bind);
|
|
|
|
|
return err;
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
2017-12-06 04:53:07 +08:00
|
|
|
static void tcf_skbmod_cleanup(struct tc_action *a)
|
2016-09-13 08:13:09 +08:00
|
|
|
{
|
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
|
|
|
|
struct tcf_skbmod_params *p;
|
|
|
|
|
|
|
|
|
|
p = rcu_dereference_protected(d->skbmod_p, 1);
|
2018-03-16 07:00:57 +08:00
|
|
|
if (p)
|
|
|
|
|
kfree_rcu(p, rcu);
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
|
|
|
|
|
int bind, int ref)
|
|
|
|
|
{
|
|
|
|
|
struct tcf_skbmod *d = to_skbmod(a);
|
|
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
2018-08-11 01:51:49 +08:00
|
|
|
struct tcf_skbmod_params *p;
|
2024-04-03 21:09:08 +08:00
|
|
|
struct tc_skbmod opt;
|
2016-09-13 08:13:09 +08:00
|
|
|
struct tcf_t t;
|
|
|
|
|
|
2024-04-03 21:09:08 +08:00
|
|
|
memset(&opt, 0, sizeof(opt));
|
|
|
|
|
opt.index = d->tcf_index;
|
|
|
|
|
opt.refcnt = refcount_read(&d->tcf_refcnt) - ref,
|
|
|
|
|
opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind;
|
2018-08-11 01:51:49 +08:00
|
|
|
spin_lock_bh(&d->tcf_lock);
|
|
|
|
|
opt.action = d->tcf_action;
|
|
|
|
|
p = rcu_dereference_protected(d->skbmod_p,
|
|
|
|
|
lockdep_is_held(&d->tcf_lock));
|
2016-09-13 08:13:09 +08:00
|
|
|
opt.flags = p->flags;
|
|
|
|
|
if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
if ((p->flags & SKBMOD_F_DMAC) &&
|
|
|
|
|
nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
if ((p->flags & SKBMOD_F_SMAC) &&
|
|
|
|
|
nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
if ((p->flags & SKBMOD_F_ETYPE) &&
|
|
|
|
|
nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type)))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
|
|
|
|
tcf_tm_dump(&t, &d->tcf_tm);
|
|
|
|
|
if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
2018-08-11 01:51:49 +08:00
|
|
|
spin_unlock_bh(&d->tcf_lock);
|
2016-09-13 08:13:09 +08:00
|
|
|
return skb->len;
|
|
|
|
|
nla_put_failure:
|
2018-08-11 01:51:49 +08:00
|
|
|
spin_unlock_bh(&d->tcf_lock);
|
2016-09-13 08:13:09 +08:00
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb,
|
|
|
|
|
struct netlink_callback *cb, int type,
|
2018-02-15 23:54:58 +08:00
|
|
|
const struct tc_action_ops *ops,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2016-09-13 08:13:09 +08:00
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
2018-02-15 23:54:59 +08:00
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
2018-08-30 01:15:35 +08:00
|
|
|
static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index)
|
2016-09-13 08:13:09 +08:00
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
2017-08-30 14:31:59 +08:00
|
|
|
return tcf_idr_search(tn, a, index);
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static struct tc_action_ops act_skbmod_ops = {
|
|
|
|
|
.kind = "skbmod",
|
2019-02-10 20:25:00 +08:00
|
|
|
.id = TCA_ACT_SKBMOD,
|
2016-09-13 08:13:09 +08:00
|
|
|
.owner = THIS_MODULE,
|
2018-08-12 21:34:59 +08:00
|
|
|
.act = tcf_skbmod_act,
|
2016-09-13 08:13:09 +08:00
|
|
|
.dump = tcf_skbmod_dump,
|
|
|
|
|
.init = tcf_skbmod_init,
|
|
|
|
|
.cleanup = tcf_skbmod_cleanup,
|
|
|
|
|
.walk = tcf_skbmod_walker,
|
|
|
|
|
.lookup = tcf_skbmod_search,
|
|
|
|
|
.size = sizeof(struct tcf_skbmod),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static __net_init int skbmod_init_net(struct net *net)
|
|
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
|
|
|
|
|
|
2019-08-26 01:01:32 +08:00
|
|
|
return tc_action_net_init(net, tn, &act_skbmod_ops);
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
2017-12-12 07:35:03 +08:00
|
|
|
static void __net_exit skbmod_exit_net(struct list_head *net_list)
|
2016-09-13 08:13:09 +08:00
|
|
|
{
|
2017-12-12 07:35:03 +08:00
|
|
|
tc_action_net_exit(net_list, skbmod_net_id);
|
2016-09-13 08:13:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static struct pernet_operations skbmod_net_ops = {
|
|
|
|
|
.init = skbmod_init_net,
|
2017-12-12 07:35:03 +08:00
|
|
|
.exit_batch = skbmod_exit_net,
|
2016-09-13 08:13:09 +08:00
|
|
|
.id = &skbmod_net_id,
|
|
|
|
|
.size = sizeof(struct tc_action_net),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
|
|
|
|
|
MODULE_DESCRIPTION("SKB data mod-ing");
|
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
|
|
|
|
|
|
static int __init skbmod_init_module(void)
|
|
|
|
|
{
|
|
|
|
|
return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __exit skbmod_cleanup_module(void)
|
|
|
|
|
{
|
|
|
|
|
tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module_init(skbmod_init_module);
|
|
|
|
|
module_exit(skbmod_cleanup_module);
|
