Skip to contentSkip to conversation

net: sched: cls_bpf: add BPF-based classifier

PATCH Applied Daniel Borkmann 2 participants 2 messages Oct 28, 2013 – Oct 29, 2013 1 message not in the archive

Subsystems (5)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

PATCH v2 1/1 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!

---
v1->v2:
- Ok, applied Eric Dumazet's feedback with possibility to overwrite default flowid

iproute2 part: http://patchwork.ozlabs.org/patch/286496/

 include/uapi/linux/pkt_cls.h |  14 ++
 net/sched/Kconfig            |  10 ++
 net/sched/Makefile           |   1 +
 net/sched/cls_bpf.c          | 385 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 410 insertions(+)
 create mode 100644 net/sched/cls_bpf.c
include/uapi/linux/pkt_cls.h +14 -0
index 082eafa..25731df 100644
@@ -388,6 +388,20 @@ enum {
 
 #define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
 
+/* BPF classifier */
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
 /* Extended Matches */
 
 struct tcf_ematch_tree_hdr {
net/sched/Kconfig +10 -0
index c03a32a..ad1f1d8 100644
@@ -443,6 +443,16 @@ config NET_CLS_CGROUP
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_cgroup.
 
+config NET_CLS_BPF
+	tristate "BPF-based classifier"
+	select NET_CLS
+	---help---
+	  If you say Y here, you will be able to classify packets based on
+	  programmable BPF (JIT'ed) filters as an alternative to ematches.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called cls_bpf.
+
 config NET_EMATCH
 	bool "Extended Matches"
 	select NET_CLS
net/sched/Makefile +1 -0
index e5f9abe..35fa47a 100644
@@ -50,6 +50,7 @@ obj-$(CONFIG_NET_CLS_RSVP6)	+= cls_rsvp6.o
 obj-$(CONFIG_NET_CLS_BASIC)	+= cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)	+= cls_flow.o
 obj-$(CONFIG_NET_CLS_CGROUP)	+= cls_cgroup.o
+obj-$(CONFIG_NET_CLS_BPF)	+= cls_bpf.o
 obj-$(CONFIG_NET_EMATCH)	+= ematch.o
 obj-$(CONFIG_NET_EMATCH_CMP)	+= em_cmp.o
 obj-$(CONFIG_NET_EMATCH_NBYTE)	+= em_nbyte.o
net/sched/cls_bpf.c new file +385 -0

385 lines not on this page · raw message

Signature · 1 line
1.8.3.1
maintainer Applied
#2 lore raw

From: Daniel Borkmann <[email protected]>
Date: Mon, 28 Oct 2013 16:43:02 +0100

Quoted 8 lines

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:

This looks great, although a lot of things this supports could be done using u32 filters, but this is more flexible.

Applied, thanks.