2015-01-15 16:52:39 +08:00
|
|
|
/*
|
|
|
|
|
* Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
|
|
|
|
|
*
|
|
|
|
|
* 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.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
#include <linux/init.h>
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
#include <linux/rtnetlink.h>
|
|
|
|
|
#include <linux/filter.h>
|
2015-03-20 22:11:12 +08:00
|
|
|
#include <linux/bpf.h>
|
|
|
|
|
|
2015-01-15 16:52:39 +08:00
|
|
|
#include <net/netlink.h>
|
|
|
|
|
#include <net/pkt_sched.h>
|
|
|
|
|
|
|
|
|
|
#include <linux/tc_act/tc_bpf.h>
|
|
|
|
|
#include <net/tc_act/tc_bpf.h>
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
#define BPF_TAB_MASK 15
|
|
|
|
|
#define ACT_BPF_NAME_LEN 256
|
|
|
|
|
|
|
|
|
|
struct tcf_bpf_cfg {
|
|
|
|
|
struct bpf_prog *filter;
|
|
|
|
|
struct sock_filter *bpf_ops;
|
|
|
|
|
char *bpf_name;
|
|
|
|
|
u32 bpf_fd;
|
|
|
|
|
u16 bpf_num_ops;
|
|
|
|
|
};
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
|
2015-01-15 16:52:39 +08:00
|
|
|
struct tcf_result *res)
|
|
|
|
|
{
|
2015-03-20 22:11:12 +08:00
|
|
|
struct tcf_bpf *prog = act->priv;
|
act_bpf: allow non-default TC_ACT opcodes as BPF exec outcome
Revisiting commit d23b8ad8ab23 ("tc: add BPF based action") with regards
to eBPF support, I was thinking that it might be better to improve
return semantics from a BPF program invoked through BPF_PROG_RUN().
Currently, in case filter_res is 0, we overwrite the default action
opcode with TC_ACT_SHOT. A default action opcode configured through tc's
m_bpf can be: TC_ACT_RECLASSIFY, TC_ACT_PIPE, TC_ACT_SHOT, TC_ACT_UNSPEC,
TC_ACT_OK.
In cls_bpf, we have the possibility to overwrite the default class
associated with the classifier in case filter_res is _not_ 0xffffffff
(-1).
That allows us to fold multiple [e]BPF programs into a single one, where
they would otherwise need to be defined as a separate classifier with
its own classid, needlessly redoing parsing work, etc.
Similarly, we could do better in act_bpf: Since above TC_ACT* opcodes
are exported to UAPI anyway, we reuse them for return-code-to-tc-opcode
mapping, where we would allow above possibilities. Thus, like in cls_bpf,
a filter_res of 0xffffffff (-1) means that the configured _default_ action
is used. Any unkown return code from the BPF program would fail in
tcf_bpf() with TC_ACT_UNSPEC.
Should we one day want to make use of TC_ACT_STOLEN or TC_ACT_QUEUED,
which both have the same semantics, we have the option to either use
that as a default action (filter_res of 0xffffffff) or non-default BPF
return code.
All that will allow us to transparently use tcf_bpf() for both BPF
flavours.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 03:25:57 +08:00
|
|
|
int action, filter_res;
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-04-16 03:55:45 +08:00
|
|
|
if (unlikely(!skb_mac_header_was_set(skb)))
|
|
|
|
|
return TC_ACT_UNSPEC;
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
spin_lock(&prog->tcf_lock);
|
act_bpf: allow non-default TC_ACT opcodes as BPF exec outcome
Revisiting commit d23b8ad8ab23 ("tc: add BPF based action") with regards
to eBPF support, I was thinking that it might be better to improve
return semantics from a BPF program invoked through BPF_PROG_RUN().
Currently, in case filter_res is 0, we overwrite the default action
opcode with TC_ACT_SHOT. A default action opcode configured through tc's
m_bpf can be: TC_ACT_RECLASSIFY, TC_ACT_PIPE, TC_ACT_SHOT, TC_ACT_UNSPEC,
TC_ACT_OK.
In cls_bpf, we have the possibility to overwrite the default class
associated with the classifier in case filter_res is _not_ 0xffffffff
(-1).
That allows us to fold multiple [e]BPF programs into a single one, where
they would otherwise need to be defined as a separate classifier with
its own classid, needlessly redoing parsing work, etc.
Similarly, we could do better in act_bpf: Since above TC_ACT* opcodes
are exported to UAPI anyway, we reuse them for return-code-to-tc-opcode
mapping, where we would allow above possibilities. Thus, like in cls_bpf,
a filter_res of 0xffffffff (-1) means that the configured _default_ action
is used. Any unkown return code from the BPF program would fail in
tcf_bpf() with TC_ACT_UNSPEC.
Should we one day want to make use of TC_ACT_STOLEN or TC_ACT_QUEUED,
which both have the same semantics, we have the option to either use
that as a default action (filter_res of 0xffffffff) or non-default BPF
return code.
All that will allow us to transparently use tcf_bpf() for both BPF
flavours.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 03:25:57 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
prog->tcf_tm.lastuse = jiffies;
|
|
|
|
|
bstats_update(&prog->tcf_bstats, skb);
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
/* Needed here for accessing maps. */
|
|
|
|
|
rcu_read_lock();
|
|
|
|
|
filter_res = BPF_PROG_RUN(prog->filter, skb);
|
|
|
|
|
rcu_read_unlock();
|
act_bpf: allow non-default TC_ACT opcodes as BPF exec outcome
Revisiting commit d23b8ad8ab23 ("tc: add BPF based action") with regards
to eBPF support, I was thinking that it might be better to improve
return semantics from a BPF program invoked through BPF_PROG_RUN().
Currently, in case filter_res is 0, we overwrite the default action
opcode with TC_ACT_SHOT. A default action opcode configured through tc's
m_bpf can be: TC_ACT_RECLASSIFY, TC_ACT_PIPE, TC_ACT_SHOT, TC_ACT_UNSPEC,
TC_ACT_OK.
In cls_bpf, we have the possibility to overwrite the default class
associated with the classifier in case filter_res is _not_ 0xffffffff
(-1).
That allows us to fold multiple [e]BPF programs into a single one, where
they would otherwise need to be defined as a separate classifier with
its own classid, needlessly redoing parsing work, etc.
Similarly, we could do better in act_bpf: Since above TC_ACT* opcodes
are exported to UAPI anyway, we reuse them for return-code-to-tc-opcode
mapping, where we would allow above possibilities. Thus, like in cls_bpf,
a filter_res of 0xffffffff (-1) means that the configured _default_ action
is used. Any unkown return code from the BPF program would fail in
tcf_bpf() with TC_ACT_UNSPEC.
Should we one day want to make use of TC_ACT_STOLEN or TC_ACT_QUEUED,
which both have the same semantics, we have the option to either use
that as a default action (filter_res of 0xffffffff) or non-default BPF
return code.
All that will allow us to transparently use tcf_bpf() for both BPF
flavours.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 03:25:57 +08:00
|
|
|
|
|
|
|
|
/* A BPF program may overwrite the default action opcode.
|
|
|
|
|
* Similarly as in cls_bpf, if filter_res == -1 we use the
|
|
|
|
|
* default action specified from tc.
|
|
|
|
|
*
|
|
|
|
|
* In case a different well-known TC_ACT opcode has been
|
|
|
|
|
* returned, it will overwrite the default one.
|
|
|
|
|
*
|
|
|
|
|
* For everything else that is unkown, TC_ACT_UNSPEC is
|
|
|
|
|
* returned.
|
|
|
|
|
*/
|
|
|
|
|
switch (filter_res) {
|
|
|
|
|
case TC_ACT_PIPE:
|
|
|
|
|
case TC_ACT_RECLASSIFY:
|
|
|
|
|
case TC_ACT_OK:
|
|
|
|
|
action = filter_res;
|
|
|
|
|
break;
|
|
|
|
|
case TC_ACT_SHOT:
|
|
|
|
|
action = filter_res;
|
2015-03-20 22:11:12 +08:00
|
|
|
prog->tcf_qstats.drops++;
|
act_bpf: allow non-default TC_ACT opcodes as BPF exec outcome
Revisiting commit d23b8ad8ab23 ("tc: add BPF based action") with regards
to eBPF support, I was thinking that it might be better to improve
return semantics from a BPF program invoked through BPF_PROG_RUN().
Currently, in case filter_res is 0, we overwrite the default action
opcode with TC_ACT_SHOT. A default action opcode configured through tc's
m_bpf can be: TC_ACT_RECLASSIFY, TC_ACT_PIPE, TC_ACT_SHOT, TC_ACT_UNSPEC,
TC_ACT_OK.
In cls_bpf, we have the possibility to overwrite the default class
associated with the classifier in case filter_res is _not_ 0xffffffff
(-1).
That allows us to fold multiple [e]BPF programs into a single one, where
they would otherwise need to be defined as a separate classifier with
its own classid, needlessly redoing parsing work, etc.
Similarly, we could do better in act_bpf: Since above TC_ACT* opcodes
are exported to UAPI anyway, we reuse them for return-code-to-tc-opcode
mapping, where we would allow above possibilities. Thus, like in cls_bpf,
a filter_res of 0xffffffff (-1) means that the configured _default_ action
is used. Any unkown return code from the BPF program would fail in
tcf_bpf() with TC_ACT_UNSPEC.
Should we one day want to make use of TC_ACT_STOLEN or TC_ACT_QUEUED,
which both have the same semantics, we have the option to either use
that as a default action (filter_res of 0xffffffff) or non-default BPF
return code.
All that will allow us to transparently use tcf_bpf() for both BPF
flavours.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 03:25:57 +08:00
|
|
|
break;
|
|
|
|
|
case TC_ACT_UNSPEC:
|
2015-03-20 22:11:12 +08:00
|
|
|
action = prog->tcf_action;
|
act_bpf: allow non-default TC_ACT opcodes as BPF exec outcome
Revisiting commit d23b8ad8ab23 ("tc: add BPF based action") with regards
to eBPF support, I was thinking that it might be better to improve
return semantics from a BPF program invoked through BPF_PROG_RUN().
Currently, in case filter_res is 0, we overwrite the default action
opcode with TC_ACT_SHOT. A default action opcode configured through tc's
m_bpf can be: TC_ACT_RECLASSIFY, TC_ACT_PIPE, TC_ACT_SHOT, TC_ACT_UNSPEC,
TC_ACT_OK.
In cls_bpf, we have the possibility to overwrite the default class
associated with the classifier in case filter_res is _not_ 0xffffffff
(-1).
That allows us to fold multiple [e]BPF programs into a single one, where
they would otherwise need to be defined as a separate classifier with
its own classid, needlessly redoing parsing work, etc.
Similarly, we could do better in act_bpf: Since above TC_ACT* opcodes
are exported to UAPI anyway, we reuse them for return-code-to-tc-opcode
mapping, where we would allow above possibilities. Thus, like in cls_bpf,
a filter_res of 0xffffffff (-1) means that the configured _default_ action
is used. Any unkown return code from the BPF program would fail in
tcf_bpf() with TC_ACT_UNSPEC.
Should we one day want to make use of TC_ACT_STOLEN or TC_ACT_QUEUED,
which both have the same semantics, we have the option to either use
that as a default action (filter_res of 0xffffffff) or non-default BPF
return code.
All that will allow us to transparently use tcf_bpf() for both BPF
flavours.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 03:25:57 +08:00
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
action = TC_ACT_UNSPEC;
|
|
|
|
|
break;
|
2015-01-15 16:52:39 +08:00
|
|
|
}
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
spin_unlock(&prog->tcf_lock);
|
2015-01-15 16:52:39 +08:00
|
|
|
return action;
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog)
|
|
|
|
|
{
|
|
|
|
|
return !prog->bpf_ops;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
|
|
|
|
|
struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
struct nlattr *nla;
|
|
|
|
|
|
|
|
|
|
if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops))
|
|
|
|
|
return -EMSGSIZE;
|
|
|
|
|
|
|
|
|
|
nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops *
|
|
|
|
|
sizeof(struct sock_filter));
|
|
|
|
|
if (nla == NULL)
|
|
|
|
|
return -EMSGSIZE;
|
|
|
|
|
|
|
|
|
|
memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
|
|
|
|
|
struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd))
|
|
|
|
|
return -EMSGSIZE;
|
|
|
|
|
|
|
|
|
|
if (prog->bpf_name &&
|
|
|
|
|
nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
|
|
|
|
|
return -EMSGSIZE;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
|
2015-01-15 16:52:39 +08:00
|
|
|
int bind, int ref)
|
|
|
|
|
{
|
|
|
|
|
unsigned char *tp = skb_tail_pointer(skb);
|
2015-03-20 22:11:12 +08:00
|
|
|
struct tcf_bpf *prog = act->priv;
|
2015-01-15 16:52:39 +08:00
|
|
|
struct tc_act_bpf opt = {
|
2015-03-20 22:11:12 +08:00
|
|
|
.index = prog->tcf_index,
|
|
|
|
|
.refcnt = prog->tcf_refcnt - ref,
|
|
|
|
|
.bindcnt = prog->tcf_bindcnt - bind,
|
|
|
|
|
.action = prog->tcf_action,
|
2015-01-15 16:52:39 +08:00
|
|
|
};
|
2015-03-20 22:11:12 +08:00
|
|
|
struct tcf_t tm;
|
|
|
|
|
int ret;
|
2015-01-15 16:52:39 +08:00
|
|
|
|
|
|
|
|
if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
if (tcf_bpf_is_ebpf(prog))
|
|
|
|
|
ret = tcf_bpf_dump_ebpf_info(prog, skb);
|
|
|
|
|
else
|
|
|
|
|
ret = tcf_bpf_dump_bpf_info(prog, skb);
|
|
|
|
|
if (ret)
|
2015-01-15 16:52:39 +08:00
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install);
|
|
|
|
|
tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse);
|
|
|
|
|
tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires);
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm))
|
2015-01-15 16:52:39 +08:00
|
|
|
goto nla_put_failure;
|
2015-03-20 22:11:12 +08:00
|
|
|
|
2015-01-15 16:52:39 +08:00
|
|
|
return skb->len;
|
|
|
|
|
|
|
|
|
|
nla_put_failure:
|
|
|
|
|
nlmsg_trim(skb, tp);
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
|
|
|
|
|
[TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) },
|
2015-03-20 22:11:12 +08:00
|
|
|
[TCA_ACT_BPF_FD] = { .type = NLA_U32 },
|
|
|
|
|
[TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN },
|
2015-01-15 16:52:39 +08:00
|
|
|
[TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 },
|
|
|
|
|
[TCA_ACT_BPF_OPS] = { .type = NLA_BINARY,
|
|
|
|
|
.len = sizeof(struct sock_filter) * BPF_MAXINSNS },
|
|
|
|
|
};
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
|
2015-01-15 16:52:39 +08:00
|
|
|
{
|
|
|
|
|
struct sock_filter *bpf_ops;
|
2015-03-20 22:11:12 +08:00
|
|
|
struct sock_fprog_kern fprog_tmp;
|
2015-01-15 16:52:39 +08:00
|
|
|
struct bpf_prog *fp;
|
2015-03-20 22:11:12 +08:00
|
|
|
u16 bpf_size, bpf_num_ops;
|
2015-01-15 16:52:39 +08:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
|
|
bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
|
|
|
|
|
if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
bpf_size = bpf_num_ops * sizeof(*bpf_ops);
|
2015-01-22 17:58:19 +08:00
|
|
|
if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
2015-01-15 16:52:39 +08:00
|
|
|
bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
|
2015-03-20 22:11:12 +08:00
|
|
|
if (bpf_ops == NULL)
|
2015-01-15 16:52:39 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
fprog_tmp.len = bpf_num_ops;
|
|
|
|
|
fprog_tmp.filter = bpf_ops;
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
ret = bpf_prog_create(&fp, &fprog_tmp);
|
|
|
|
|
if (ret < 0) {
|
|
|
|
|
kfree(bpf_ops);
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
cfg->bpf_ops = bpf_ops;
|
|
|
|
|
cfg->bpf_num_ops = bpf_num_ops;
|
|
|
|
|
cfg->filter = fp;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
|
|
|
|
|
{
|
|
|
|
|
struct bpf_prog *fp;
|
|
|
|
|
char *name = NULL;
|
|
|
|
|
u32 bpf_fd;
|
|
|
|
|
|
|
|
|
|
bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]);
|
|
|
|
|
|
|
|
|
|
fp = bpf_prog_get(bpf_fd);
|
|
|
|
|
if (IS_ERR(fp))
|
|
|
|
|
return PTR_ERR(fp);
|
|
|
|
|
|
|
|
|
|
if (fp->type != BPF_PROG_TYPE_SCHED_ACT) {
|
|
|
|
|
bpf_prog_put(fp);
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (tb[TCA_ACT_BPF_NAME]) {
|
|
|
|
|
name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]),
|
|
|
|
|
nla_len(tb[TCA_ACT_BPF_NAME]),
|
|
|
|
|
GFP_KERNEL);
|
|
|
|
|
if (!name) {
|
|
|
|
|
bpf_prog_put(fp);
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
cfg->bpf_fd = bpf_fd;
|
|
|
|
|
cfg->bpf_name = name;
|
|
|
|
|
cfg->filter = fp;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
|
|
|
|
|
struct nlattr *est, struct tc_action *act,
|
|
|
|
|
int replace, int bind)
|
|
|
|
|
{
|
|
|
|
|
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
|
|
|
|
|
struct tc_act_bpf *parm;
|
|
|
|
|
struct tcf_bpf *prog;
|
|
|
|
|
struct tcf_bpf_cfg cfg;
|
|
|
|
|
bool is_bpf, is_ebpf;
|
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
|
|
if (!nla)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy);
|
|
|
|
|
if (ret < 0)
|
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
|
|
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
|
|
|
|
|
is_ebpf = tb[TCA_ACT_BPF_FD];
|
|
|
|
|
|
|
|
|
|
if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) ||
|
|
|
|
|
!tb[TCA_ACT_BPF_PARMS])
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
|
|
|
|
|
|
|
|
|
|
memset(&cfg, 0, sizeof(cfg));
|
|
|
|
|
|
|
|
|
|
ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) :
|
|
|
|
|
tcf_bpf_init_from_efd(tb, &cfg);
|
|
|
|
|
if (ret < 0)
|
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
|
|
if (!tcf_hash_check(parm->index, act, bind)) {
|
|
|
|
|
ret = tcf_hash_create(parm->index, est, act,
|
|
|
|
|
sizeof(*prog), bind);
|
|
|
|
|
if (ret < 0)
|
2015-01-15 16:52:39 +08:00
|
|
|
goto destroy_fp;
|
|
|
|
|
|
|
|
|
|
ret = ACT_P_CREATED;
|
|
|
|
|
} else {
|
2015-03-20 22:11:12 +08:00
|
|
|
/* Don't override defaults. */
|
2015-01-15 16:52:39 +08:00
|
|
|
if (bind)
|
|
|
|
|
goto destroy_fp;
|
2015-03-20 22:11:12 +08:00
|
|
|
|
|
|
|
|
tcf_hash_release(act, bind);
|
|
|
|
|
if (!replace) {
|
2015-01-15 16:52:39 +08:00
|
|
|
ret = -EEXIST;
|
|
|
|
|
goto destroy_fp;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
prog = to_bpf(act);
|
|
|
|
|
spin_lock_bh(&prog->tcf_lock);
|
|
|
|
|
|
|
|
|
|
prog->bpf_ops = cfg.bpf_ops;
|
|
|
|
|
prog->bpf_name = cfg.bpf_name;
|
|
|
|
|
|
|
|
|
|
if (cfg.bpf_num_ops)
|
|
|
|
|
prog->bpf_num_ops = cfg.bpf_num_ops;
|
|
|
|
|
if (cfg.bpf_fd)
|
|
|
|
|
prog->bpf_fd = cfg.bpf_fd;
|
|
|
|
|
|
|
|
|
|
prog->tcf_action = parm->action;
|
|
|
|
|
prog->filter = cfg.filter;
|
|
|
|
|
|
|
|
|
|
spin_unlock_bh(&prog->tcf_lock);
|
2015-01-15 16:52:39 +08:00
|
|
|
|
|
|
|
|
if (ret == ACT_P_CREATED)
|
2015-03-20 22:11:12 +08:00
|
|
|
tcf_hash_insert(act);
|
|
|
|
|
|
2015-01-15 16:52:39 +08:00
|
|
|
return ret;
|
|
|
|
|
|
|
|
|
|
destroy_fp:
|
2015-03-20 22:11:12 +08:00
|
|
|
if (is_ebpf)
|
|
|
|
|
bpf_prog_put(cfg.filter);
|
|
|
|
|
else
|
|
|
|
|
bpf_prog_destroy(cfg.filter);
|
|
|
|
|
|
|
|
|
|
kfree(cfg.bpf_ops);
|
|
|
|
|
kfree(cfg.bpf_name);
|
|
|
|
|
|
2015-01-15 16:52:39 +08:00
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
static void tcf_bpf_cleanup(struct tc_action *act, int bind)
|
2015-01-15 16:52:39 +08:00
|
|
|
{
|
2015-03-20 22:11:12 +08:00
|
|
|
const struct tcf_bpf *prog = act->priv;
|
2015-01-15 16:52:39 +08:00
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
if (tcf_bpf_is_ebpf(prog))
|
|
|
|
|
bpf_prog_put(prog->filter);
|
|
|
|
|
else
|
|
|
|
|
bpf_prog_destroy(prog->filter);
|
2015-01-15 16:52:39 +08:00
|
|
|
}
|
|
|
|
|
|
2015-03-20 22:11:12 +08:00
|
|
|
static struct tc_action_ops act_bpf_ops __read_mostly = {
|
|
|
|
|
.kind = "bpf",
|
|
|
|
|
.type = TCA_ACT_BPF,
|
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
|
.act = tcf_bpf,
|
|
|
|
|
.dump = tcf_bpf_dump,
|
|
|
|
|
.cleanup = tcf_bpf_cleanup,
|
|
|
|
|
.init = tcf_bpf_init,
|
2015-01-15 16:52:39 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static int __init bpf_init_module(void)
|
|
|
|
|
{
|
|
|
|
|
return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __exit bpf_cleanup_module(void)
|
|
|
|
|
{
|
|
|
|
|
tcf_unregister_action(&act_bpf_ops);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module_init(bpf_init_module);
|
|
|
|
|
module_exit(bpf_cleanup_module);
|
|
|
|
|
|
|
|
|
|
MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
|
|
|
|
|
MODULE_DESCRIPTION("TC BPF based action");
|
|
|
|
|
MODULE_LICENSE("GPL v2");
|