UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/net/sched/cls_bpf.c

383 lines
8.1 KiB
C
Raw Normal View History

net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
/*
* Berkeley Packet Filter based traffic classifier
*
* Might be used to classify traffic through flexible, user-defined and
* possibly JIT-ed BPF filters for traffic control as an alternative to
* ematches.
*
* (C) 2013 Daniel Borkmann <dborkman@redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/filter.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
MODULE_DESCRIPTION("TC BPF based classifier");
struct cls_bpf_head {
struct list_head plist;
u32 hgen;
};
struct cls_bpf_prog {
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
struct bpf_prog *filter;
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
struct sock_filter *bpf_ops;
struct tcf_exts exts;
struct tcf_result res;
struct list_head link;
u32 handle;
u16 bpf_len;
};
static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
[TCA_BPF_CLASSID] = { .type = NLA_U32 },
[TCA_BPF_OPS_LEN] = { .type = NLA_U16 },
[TCA_BPF_OPS] = { .type = NLA_BINARY,
.len = sizeof(struct sock_filter) * BPF_MAXINSNS },
};
static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog;
int ret;
list_for_each_entry(prog, &head->plist, link) {
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
int filter_res = BPF_PROG_RUN(prog->filter, skb);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (filter_res == 0)
continue;
*res = prog->res;
if (filter_res != -1)
res->classid = filter_res;
ret = tcf_exts_exec(skb, &prog->exts, res);
if (ret < 0)
continue;
return ret;
}
return -1;
}
static int cls_bpf_init(struct tcf_proto *tp)
{
struct cls_bpf_head *head;
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (head == NULL)
return -ENOBUFS;
INIT_LIST_HEAD(&head->plist);
tp->root = head;
return 0;
}
static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
{
tcf_unbind_filter(tp, &prog->res);
tcf_exts_destroy(tp, &prog->exts);
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
bpf_prog_destroy(prog->filter);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
kfree(prog->bpf_ops);
kfree(prog);
}
static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg;
list_for_each_entry(prog, &head->plist, link) {
if (prog == todel) {
tcf_tree_lock(tp);
list_del(&prog->link);
tcf_tree_unlock(tp);
cls_bpf_delete_prog(tp, prog);
return 0;
}
}
return -ENOENT;
}
static void cls_bpf_destroy(struct tcf_proto *tp)
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog, *tmp;
list_for_each_entry_safe(prog, tmp, &head->plist, link) {
list_del(&prog->link);
cls_bpf_delete_prog(tp, prog);
}
kfree(head);
}
static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog;
unsigned long ret = 0UL;
if (head == NULL)
return 0UL;
list_for_each_entry(prog, &head->plist, link) {
if (prog->handle == handle) {
ret = (unsigned long) prog;
break;
}
}
return ret;
}
static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
{
}
static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
struct cls_bpf_prog *prog,
unsigned long base, struct nlattr **tb,
sched, cls: check if we could overwrite actions when changing a filter When actions are attached to a filter, they are a part of the filter itself, so when changing a filter we should allow to overwrite the actions inside as well. In my specific case, when I tried to _append_ a new action to an existing filter which already has an action, I got EEXIST since kernel refused to overwrite the existing one in kernel. This patch checks if we are changing the filter checking NLM_F_CREATE flag (Sigh, filters don't use NLM_F_REPLACE...) and then passes the boolean down to actions. This fixes the problem above. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-26 04:54:06 +08:00
struct nlattr *est, bool ovr)
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
{
struct sock_filter *bpf_ops, *bpf_old;
struct tcf_exts exts;
net: filter: let unattached filters use sock_fprog_kern The sk_unattached_filter_create() API is used by BPF filters that are not directly attached or related to sockets, and are used in team, ptp, xt_bpf, cls_bpf, etc. As such all users do their own internal managment of obtaining filter blocks and thus already have them in kernel memory and set up before calling into sk_unattached_filter_create(). As a result, due to __user annotation in sock_fprog, sparse triggers false positives (incorrect type in assignment [different address space]) when filters are set up before passing them to sk_unattached_filter_create(). Therefore, let sk_unattached_filter_create() API use sock_fprog_kern to overcome this issue. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-24 00:43:58 +08:00
struct sock_fprog_kern tmp;
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
struct bpf_prog *fp, *fp_old;
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
u16 bpf_size, bpf_len;
u32 classid;
int ret;
if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
return -EINVAL;
net_sched: cls: refactor out struct tcf_ext_map These information can be saved in tcf_exts, and this will simplify the code. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-16 12:15:07 +08:00
tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
sched, cls: check if we could overwrite actions when changing a filter When actions are attached to a filter, they are a part of the filter itself, so when changing a filter we should allow to overwrite the actions inside as well. In my specific case, when I tried to _append_ a new action to an existing filter which already has an action, I got EEXIST since kernel refused to overwrite the existing one in kernel. This patch checks if we are changing the filter checking NLM_F_CREATE flag (Sigh, filters don't use NLM_F_REPLACE...) and then passes the boolean down to actions. This fixes the problem above. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-26 04:54:06 +08:00
ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (ret < 0)
return ret;
classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
ret = -EINVAL;
goto errout;
}
bpf_size = bpf_len * sizeof(*bpf_ops);
bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
if (bpf_ops == NULL) {
ret = -ENOMEM;
goto errout;
}
memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
tmp.len = bpf_len;
net: filter: let unattached filters use sock_fprog_kern The sk_unattached_filter_create() API is used by BPF filters that are not directly attached or related to sockets, and are used in team, ptp, xt_bpf, cls_bpf, etc. As such all users do their own internal managment of obtaining filter blocks and thus already have them in kernel memory and set up before calling into sk_unattached_filter_create(). As a result, due to __user annotation in sock_fprog, sparse triggers false positives (incorrect type in assignment [different address space]) when filters are set up before passing them to sk_unattached_filter_create(). Therefore, let sk_unattached_filter_create() API use sock_fprog_kern to overcome this issue. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-24 00:43:58 +08:00
tmp.filter = bpf_ops;
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
ret = bpf_prog_create(&fp, &tmp);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (ret)
goto errout_free;
tcf_tree_lock(tp);
fp_old = prog->filter;
bpf_old = prog->bpf_ops;
prog->bpf_len = bpf_len;
prog->bpf_ops = bpf_ops;
prog->filter = fp;
prog->res.classid = classid;
tcf_tree_unlock(tp);
tcf_bind_filter(tp, &prog->res, base);
tcf_exts_change(tp, &prog->exts, &exts);
if (fp_old)
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 11:34:16 +08:00
bpf_prog_destroy(fp_old);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (bpf_old)
kfree(bpf_old);
return 0;
errout_free:
kfree(bpf_ops);
errout:
tcf_exts_destroy(tp, &exts);
return ret;
}
static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
struct cls_bpf_head *head)
{
unsigned int i = 0x80000000;
do {
if (++head->hgen == 0x7FFFFFFF)
head->hgen = 1;
} while (--i > 0 && cls_bpf_get(tp, head->hgen));
if (i == 0)
pr_err("Insufficient number of handles\n");
return i;
}
static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
sched, cls: check if we could overwrite actions when changing a filter When actions are attached to a filter, they are a part of the filter itself, so when changing a filter we should allow to overwrite the actions inside as well. In my specific case, when I tried to _append_ a new action to an existing filter which already has an action, I got EEXIST since kernel refused to overwrite the existing one in kernel. This patch checks if we are changing the filter checking NLM_F_CREATE flag (Sigh, filters don't use NLM_F_REPLACE...) and then passes the boolean down to actions. This fixes the problem above. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-26 04:54:06 +08:00
unsigned long *arg, bool ovr)
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
struct nlattr *tb[TCA_BPF_MAX + 1];
int ret;
if (tca[TCA_OPTIONS] == NULL)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy);
if (ret < 0)
return ret;
if (prog != NULL) {
if (handle && prog->handle != handle)
return -EINVAL;
return cls_bpf_modify_existing(net, tp, prog, base, tb,
sched, cls: check if we could overwrite actions when changing a filter When actions are attached to a filter, they are a part of the filter itself, so when changing a filter we should allow to overwrite the actions inside as well. In my specific case, when I tried to _append_ a new action to an existing filter which already has an action, I got EEXIST since kernel refused to overwrite the existing one in kernel. This patch checks if we are changing the filter checking NLM_F_CREATE flag (Sigh, filters don't use NLM_F_REPLACE...) and then passes the boolean down to actions. This fixes the problem above. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-26 04:54:06 +08:00
tca[TCA_RATE], ovr);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
}
prog = kzalloc(sizeof(*prog), GFP_KERNEL);
if (prog == NULL)
return -ENOBUFS;
net_sched: cls: refactor out struct tcf_ext_map These information can be saved in tcf_exts, and this will simplify the code. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-16 12:15:07 +08:00
tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (handle == 0)
prog->handle = cls_bpf_grab_new_handle(tp, head);
else
prog->handle = handle;
if (prog->handle == 0) {
ret = -EINVAL;
goto errout;
}
sched, cls: check if we could overwrite actions when changing a filter When actions are attached to a filter, they are a part of the filter itself, so when changing a filter we should allow to overwrite the actions inside as well. In my specific case, when I tried to _append_ a new action to an existing filter which already has an action, I got EEXIST since kernel refused to overwrite the existing one in kernel. This patch checks if we are changing the filter checking NLM_F_CREATE flag (Sigh, filters don't use NLM_F_REPLACE...) and then passes the boolean down to actions. This fixes the problem above. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-26 04:54:06 +08:00
ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
if (ret < 0)
goto errout;
tcf_tree_lock(tp);
list_add(&prog->link, &head->plist);
tcf_tree_unlock(tp);
*arg = (unsigned long) prog;
return 0;
errout:
if (*arg == 0UL && prog)
kfree(prog);
return ret;
}
net_sched: add struct net pointer to tcf_proto_ops->dump It will be needed by the next patch. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 08:14:01 +08:00
static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
struct sk_buff *skb, struct tcmsg *tm)
{
struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
struct nlattr *nest, *nla;
if (prog == NULL)
return skb->len;
tm->tcm_handle = prog->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
goto nla_put_failure;
if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
goto nla_put_failure;
nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
sizeof(struct sock_filter));
if (nla == NULL)
goto nla_put_failure;
net_sched: cls_bpf: use tabs to do indent Code indent should use tabs where possible Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-10 20:55:30 +08:00
memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
net_sched: cls: refactor out struct tcf_ext_map These information can be saved in tcf_exts, and this will simplify the code. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-16 12:15:07 +08:00
if (tcf_exts_dump(skb, &prog->exts) < 0)
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
goto nla_put_failure;
nla_nest_end(skb, nest);
net_sched: cls: refactor out struct tcf_ext_map These information can be saved in tcf_exts, and this will simplify the code. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-16 12:15:07 +08:00
if (tcf_exts_dump_stats(skb, &prog->exts) < 0)
net: sched: cls_bpf: add BPF-based classifier This work contains a lightweight BPF-based traffic classifier that can serve as a flexible alternative to ematch-based tree classification, i.e. now that BPF filter engine can also be JITed in the kernel. Naturally, tc actions and policies are supported as well with cls_bpf. Multiple BPF programs/filter can be attached for a class, or they can just as well be written within a single BPF program, that's really up to the user how he wishes to run/optimize the code, e.g. also for inversion of verdicts etc. The notion of a BPF program's return/exit codes is being kept as follows: 0: No match -1: Select classid given in "tc filter ..." command else: flowid, overwrite the default one As a minimal usage example with iproute2, we use a 3 band prio root qdisc on a router with sfq each as leave, and assign ssh and icmp bpf-based filters to band 1, http traffic to band 2 and the rest to band 3. For the first two bands we load the bytecode from a file, in the 2nd we load it inline as an example: echo 1 > /proc/sys/net/core/bpf_jit_enable tc qdisc del dev em1 root tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 tc qdisc add dev em1 parent 1:1 sfq perturb 16 tc qdisc add dev em1 parent 1:2 sfq perturb 16 tc qdisc add dev em1 parent 1:3 sfq perturb 16 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1 tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2 tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3 BPF programs can be easily created and passed to tc, either as inline 'bytecode' or 'bytecode-file'. There are a couple of front-ends that can compile opcodes, for example: 1) People familiar with tcpdump-like filters: tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf 2) People that want to low-level program their filters or use BPF extensions that lack support by libpcap's compiler: bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf ssh.ops example code: ldh [12] jne #0x800, drop ldb [23] jneq #6, drop ldh [20] jset #0x1fff, drop ldxb 4 * ([14] & 0xf) ldh [%x + 14] jeq #0x16, pass ldh [%x + 16] jne #0x16, drop pass: ret #-1 drop: ret #0 It was chosen to load bytecode into tc, since the reverse operation, tc filter list dev em1, is then able to show the exact commands again. Possible follow-up work could also include a small expression compiler for iproute2. Tested with the help of bmon. This idea came up during the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from Eric Dumazet! Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-28 23:43:02 +08:00
goto nla_put_failure;
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct cls_bpf_head *head = tp->root;
struct cls_bpf_prog *prog;
list_for_each_entry(prog, &head->plist, link) {
if (arg->count < arg->skip)
goto skip;
if (arg->fn(tp, (unsigned long) prog, arg) < 0) {
arg->stop = 1;
break;
}
skip:
arg->count++;
}
}
static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
.kind = "bpf",
.owner = THIS_MODULE,
.classify = cls_bpf_classify,
.init = cls_bpf_init,
.destroy = cls_bpf_destroy,
.get = cls_bpf_get,
.put = cls_bpf_put,
.change = cls_bpf_change,
.delete = cls_bpf_delete,
.walk = cls_bpf_walk,
.dump = cls_bpf_dump,
};
static int __init cls_bpf_init_mod(void)
{
return register_tcf_proto_ops(&cls_bpf_ops);
}
static void __exit cls_bpf_exit_mod(void)
{
unregister_tcf_proto_ops(&cls_bpf_ops);
}
module_init(cls_bpf_init_mod);
module_exit(cls_bpf_exit_mod);