On Thu, Jan 17, 2013 at 6:53 PM, Pablo Neira Ayuso <pablo@xxxxxxxxxxxxx> wrote: > Hi Willem, > > On Wed, Jan 09, 2013 at 07:15:44PM -0500, Willem de Bruijn wrote: >> Changes: >> - v3: reverted no longer needed changes to x_tables.c >> - v2: use a fixed size match structure to communicate between >> kernel and userspace. >> >> Support arbitrary linux socket filter (BPF) programs as iptables >> match rules. This allows for very expressive filters, and on >> platforms with BPF JIT appears competitive with traditional hardcoded >> iptables rules. >> >> At least, on an x86_64 that achieves 40K netperf TCP_STREAM without >> any iptables rules (40 GBps), >> >> inserting 100x this bpf rule gives 28K >> >> ./iptables -A OUTPUT -m bpf --bytecode '6,40 0 0 14, 21 0 3 2048,48 0 0 25,21 0 1 20,6 0 0 96,6 0 0 0,' -j >> >> (as generated by tcpdump -i any -ddd ip proto 20 | tr '\n' ',') > > That code generated by tcpdump will not work. > > tcpdump generates BPF code assuming that offset 0 is the link layer > header, while iptables considers that offset 0 is the network layer. Ah, yes, of course. We discussed that earlier. I removed the statement from the commit message. Such hints belong in the libxt_bpf man page, if anywhere. To compile code right now, the little bpf compiler that I emailed before can be downloaded from http://code.google.com/p/kernel/downloads/detail?name=bpf2decimal.c I don't think that a compiler has to be shipped with iptables itself, let alone make iptables link against libraries. That said, it is not impossible to detect pcap.h in configure.ac and optionally enable a "-m bpf --string" mode that calls pcap_compile_nopcap from within libxt_bpf, so let me know if you would like me to code that up. I can also try to send a patch to tcpdump that extends compilation (`-ddd -y <type>`) to arbitrary link layer types. > More comments below: > >> inserting 100x this u32 rule gives 21K >> >> ./iptables -A OUTPUT -m u32 --u32 '6&0xFF=0x20' -j DROP >> >> The two are logically equivalent, as far as I can tell. Let me know >> if my test methodology is flawed in some way. Even in cases where >> slower, the filter adds functionality currently lacking in iptables, >> such as access to sk_buff fields like rxhash and queue_mapping. >> --- >> include/uapi/linux/netfilter/xt_bpf.h | 17 ++++++++ >> net/netfilter/Kconfig | 9 ++++ >> net/netfilter/Makefile | 1 + >> net/netfilter/xt_bpf.c | 73 +++++++++++++++++++++++++++++++++ >> 4 files changed, 100 insertions(+), 0 deletions(-) >> create mode 100644 include/uapi/linux/netfilter/xt_bpf.h >> create mode 100644 net/netfilter/xt_bpf.c >> >> diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h >> new file mode 100644 >> index 0000000..5dda450 >> --- /dev/null >> +++ b/include/uapi/linux/netfilter/xt_bpf.h >> @@ -0,0 +1,17 @@ >> +#ifndef _XT_BPF_H >> +#define _XT_BPF_H >> + >> +#include <linux/filter.h> >> +#include <linux/types.h> >> + >> +#define XT_BPF_MAX_NUM_INSTR 64 >> + >> +struct xt_bpf_info { >> + __u16 bpf_program_num_elem; >> + struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; >> + >> + /* only used in the kernel */ >> + struct sk_filter *filter __attribute__((aligned(8))); >> +}; >> + >> +#endif /*_XT_BPF_H */ >> diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig >> index fefa514..d45720f 100644 >> --- a/net/netfilter/Kconfig >> +++ b/net/netfilter/Kconfig >> @@ -798,6 +798,15 @@ config NETFILTER_XT_MATCH_ADDRTYPE >> If you want to compile it as a module, say M here and read >> <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. >> >> +config NETFILTER_XT_MATCH_BPF >> + tristate '"bpf" match support' >> + depends on NETFILTER_ADVANCED >> + help >> + BPF matching applies a linux socket filter to each packet and >> + accepts those for which the filter returns non-zero. >> + >> + To compile it as a module, choose M here. If unsure, say N. >> + >> config NETFILTER_XT_MATCH_CLUSTER >> tristate '"cluster" match support' >> depends on NF_CONNTRACK >> diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile >> index 3259697..6d6194525 100644 >> --- a/net/netfilter/Makefile >> +++ b/net/netfilter/Makefile >> @@ -98,6 +98,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o >> >> # matches >> obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o >> +obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o >> obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o >> obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o >> obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o >> diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c >> new file mode 100644 >> index 0000000..1bdfab8 >> --- /dev/null >> +++ b/net/netfilter/xt_bpf.c >> @@ -0,0 +1,73 @@ >> +/* Xtables module to match packets using a BPF filter. >> + * Copyright 2013 Google Inc. >> + * Written by Willem de Bruijn <willemb@xxxxxxxxxx> >> + * >> + * 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/skbuff.h> >> +#include <linux/ipv6.h> >> +#include <linux/filter.h> >> +#include <net/ip.h> >> + >> +#include <linux/netfilter/xt_bpf.h> >> +#include <linux/netfilter/x_tables.h> >> + >> +MODULE_AUTHOR("Willem de Bruijn <willemb@xxxxxxxxxx>"); >> +MODULE_DESCRIPTION("Xtables: BPF filter match"); >> +MODULE_LICENSE("GPL"); > > Please, add > > MODULE_ALIAS("ipt_bpf"); > MODULE_ALIAS("ip6t_bpf"); Done. > otherwise module auto-loading will not work. > >> + >> +static int bpf_mt_check(const struct xt_mtchk_param *par) >> +{ >> + struct xt_bpf_info *info = par->matchinfo; >> + struct sock_fprog program; >> + >> + program.len = info->bpf_program_num_elem; >> + program.filter = info->bpf_program; > > sparse reports a warning here above. I've been trying to find a quick > solution, please, have a look at it. Thanks for catching this. Apparently, program.filter is annotated as __user. A cast made the warning disappear, and is safe as far as I can see, since it only forces the kernel to be more conservative in accessing the memory. >> + if (sk_unattached_filter_create(&info->filter, &program)) { >> + pr_info("bpf: check failed: parse error\n"); >> + return -EINVAL; >> + } >> + >> + return 0; >> +} >> + >> +static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) >> +{ >> + const struct xt_bpf_info *info = par->matchinfo; >> + >> + return SK_RUN_FILTER(info->filter, skb); >> +} >> + >> +static void bpf_mt_destroy(const struct xt_mtdtor_param *par) >> +{ >> + const struct xt_bpf_info *info = par->matchinfo; >> + sk_unattached_filter_destroy(info->filter); >> +} >> + >> +static struct xt_match bpf_mt_reg __read_mostly = { >> + .name = "bpf", >> + .revision = 0, >> + .family = NFPROTO_UNSPEC, >> + .checkentry = bpf_mt_check, >> + .match = bpf_mt, >> + .destroy = bpf_mt_destroy, >> + .matchsize = sizeof(struct xt_bpf_info), >> + .me = THIS_MODULE, >> +}; >> + >> +static int __init bpf_mt_init(void) >> +{ >> + return xt_register_match(&bpf_mt_reg); >> +} >> + >> +static void __exit bpf_mt_exit(void) >> +{ >> + xt_unregister_match(&bpf_mt_reg); >> +} >> + >> +module_init(bpf_mt_init); >> +module_exit(bpf_mt_exit); >> -- >> 1.7.7.3 >> -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
