diff mbox series

netfilter: fix CONFIG_NF_REJECT_IPV6=m link error

Message ID 20180409105322.2247296-1-arnd@arndb.de
State Accepted
Commit a6615743704fdc179e227f84b7903edd1f0b4241
Headers show
Series netfilter: fix CONFIG_NF_REJECT_IPV6=m link error | expand

Commit Message

Arnd Bergmann April 9, 2018, 10:53 a.m. UTC 
We get a new link error with CONFIG_NFT_REJECT_INET=y and CONFIG_NF_REJECT_IPV6=m
after larger parts of the nftables modules are linked together:

net/netfilter/nft_reject_inet.o: In function `nft_reject_inet_eval':
nft_reject_inet.c:(.text+0x17c): undefined reference to `nf_send_unreach6'
nft_reject_inet.c:(.text+0x190): undefined reference to `nf_send_reset6'

The problem is that with NF_TABLES_INET set, we implicitly try to use
the ipv6 version as well for NFT_REJECT, but when CONFIG_IPV6 is set to
a loadable module, it's impossible to reach that.

The best workaround I found is to express the above as a Kconfig
dependency, forcing NFT_REJECT itself to be 'm' in that particular
configuration.

Fixes: 02c7b25e5f54 ("netfilter: nf_tables: build-in filter chain type")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

---
 net/netfilter/Kconfig | 1 +
 1 file changed, 1 insertion(+)

-- 
2.9.0

Comments

Pablo Neira Ayuso April 9, 2018, 2:37 p.m. UTC | #1 
Hi Arnd,

On Mon, Apr 09, 2018 at 12:53:12PM +0200, Arnd Bergmann wrote:
> We get a new link error with CONFIG_NFT_REJECT_INET=y and CONFIG_NF_REJECT_IPV6=m


I think we can update NFT_REJECT_INET so it depends on NFT_REJECT_IPV4
and NFT_REJECT_IPV6. This doesn't allow here CONFIG_NFT_REJECT_INET=y
and CONFIG_NF_REJECT_IPV6=m.

I mean, just like we do with NFT_FIB_INET.

BTW, I think this problem has been is not related to the recent patch,
but something older that kbuild robot has triggered more easily for
some reason?

Thanks for your patch!
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index d3220b43c832..b48c57bb9aaf 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -601,7 +601,8 @@ config NFT_REJECT
 
 config NFT_REJECT_INET
 	depends on NF_TABLES_INET
-	default NFT_REJECT
+	depends on NFT_REJECT_IPV4
+	depends on NFT_REJECT_IPV6
 	tristate
 
 config NFT_COMPAT
Arnd Bergmann April 9, 2018, 2:43 p.m. UTC | #2 
On Mon, Apr 9, 2018 at 4:37 PM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> Hi Arnd,

>

> On Mon, Apr 09, 2018 at 12:53:12PM +0200, Arnd Bergmann wrote:

>> We get a new link error with CONFIG_NFT_REJECT_INET=y and CONFIG_NF_REJECT_IPV6=m

>

> I think we can update NFT_REJECT_INET so it depends on NFT_REJECT_IPV4

> and NFT_REJECT_IPV6. This doesn't allow here CONFIG_NFT_REJECT_INET=y

> and CONFIG_NF_REJECT_IPV6=m.

>

> I mean, just like we do with NFT_FIB_INET.


That can only work if NFT_REJECT_INET can be made a 'tristate' symbol
again, so that code gets built as a loadable module if
CONFIG_NF_REJECT_IPV6=m.

> BTW, I think this problem has been is not related to the recent patch,

> but something older that kbuild robot has triggered more easily for

> some reason?


02c7b25e5f54 is the one that turned NF_TABLES_INET into a 'bool'
symbol. NFT_REJECT depends on NF_TABLES_INET, so it used to
restricted to a loadable module with IPV6=m, but can now be
built-in, which causes that link error.

      Arnd
Pablo Neira Ayuso April 13, 2018, 1:15 p.m. UTC | #3 
On Mon, Apr 09, 2018 at 04:43:40PM +0200, Arnd Bergmann wrote:
> On Mon, Apr 9, 2018 at 4:37 PM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:

> > Hi Arnd,

> >

> > On Mon, Apr 09, 2018 at 12:53:12PM +0200, Arnd Bergmann wrote:

> >> We get a new link error with CONFIG_NFT_REJECT_INET=y and CONFIG_NF_REJECT_IPV6=m

> >

> > I think we can update NFT_REJECT_INET so it depends on NFT_REJECT_IPV4

> > and NFT_REJECT_IPV6. This doesn't allow here CONFIG_NFT_REJECT_INET=y

> > and CONFIG_NF_REJECT_IPV6=m.

> >

> > I mean, just like we do with NFT_FIB_INET.

> 

> That can only work if NFT_REJECT_INET can be made a 'tristate' symbol

> again, so that code gets built as a loadable module if

> CONFIG_NF_REJECT_IPV6=m.

> 

> > BTW, I think this problem has been is not related to the recent patch,

> > but something older that kbuild robot has triggered more easily for

> > some reason?

> 

> 02c7b25e5f54 is the one that turned NF_TABLES_INET into a 'bool'

> symbol. NFT_REJECT depends on NF_TABLES_INET, so it used to

> restricted to a loadable module with IPV6=m, but can now be

> built-in, which causes that link error.


Still one more spin on this, I would like to see if we have a way to
fix this by simplifing things a bit.

Would this one I'm attaching would work?

Thanks for you patience.
From af07bc7ff5d34ce54e7913233912c058e6699e3c Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>

Date: Fri, 13 Apr 2018 10:48:40 +0200
Subject: [PATCH] netfilter: CONFIG_NF_REJECT_IPV{4,6} becomes bool toggle

Arnd reports that we get a new link error with CONFIG_NFT_REJECT_INET=y
and CONFIG_NF_REJECT_IPV6=m after larger parts of the nftables modules
are linked together:

net/netfilter/nft_reject_inet.o: In function `nft_reject_inet_eval':
nft_reject_inet.c:(.text+0x17c): undefined reference to `nf_send_unreach6'
nft_reject_inet.c:(.text+0x190): undefined reference to `nf_send_reset6'

The problem is that with NF_TABLES_INET set, we implicitly try to use
the ipv6 version as well for NFT_REJECT, but when CONFIG_IPV6 is set to
a loadable module, it's impossible to reach that.

This patch fixes this problem by building-in nf_reject_ipv{4,6}.c, IPv6
symbol dependencies for the IPv6 reject infrastructure are located in
exthdrs_core.c, ip6_checksum.c and ip6_icmp.c which are also built-in,
so let's do the same to simplify this.

Fixes: 02c7b25e5f54 ("netfilter: nf_tables: build-in filter chain type")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

---
 net/ipv4/netfilter/Kconfig | 3 +--
 net/ipv6/netfilter/Kconfig | 3 +--
 net/netfilter/Kconfig      | 2 ++
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 280048e1e395..3e4e0ae2a9a1 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -104,8 +104,7 @@ config NF_LOG_IPV4
 	select NF_LOG_COMMON
 
 config NF_REJECT_IPV4
-	tristate "IPv4 packet rejection"
-	default m if NETFILTER_ADVANCED=n
+	bool "IPv4 packet rejection"
 
 config NF_NAT_IPV4
 	tristate "IPv4 NAT"
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ccbfa83e4bb0..1e5d040a60b8 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -87,8 +87,7 @@ config NF_DUP_IPV6
 	  packet to be rerouted to another destination.
 
 config NF_REJECT_IPV6
-	tristate "IPv6 packet rejection"
-	default m if NETFILTER_ADVANCED=n
+	bool "IPv6 packet rejection"
 
 config NF_LOG_IPV6
 	tristate "IPv6 packet logging"
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 4189f574f5ec..d7b3272fe821 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -609,6 +609,8 @@ config NFT_REJECT
 
 config NFT_REJECT_INET
 	depends on NF_TABLES_INET
+	select NF_REJECT_IPV4
+	select NF_REJECT_IPV6
 	default NFT_REJECT
 	tristate
 
-- 
2.11.0
Arnd Bergmann April 13, 2018, 2:52 p.m. UTC | #4 
On Fri, Apr 13, 2018 at 3:15 PM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> On Mon, Apr 09, 2018 at 04:43:40PM +0200, Arnd Bergmann wrote:

>> On Mon, Apr 9, 2018 at 4:37 PM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:

>> > Hi Arnd,

>> >

>> > On Mon, Apr 09, 2018 at 12:53:12PM +0200, Arnd Bergmann wrote:

>> >> We get a new link error with CONFIG_NFT_REJECT_INET=y and CONFIG_NF_REJECT_IPV6=m

>> >

>> > I think we can update NFT_REJECT_INET so it depends on NFT_REJECT_IPV4

>> > and NFT_REJECT_IPV6. This doesn't allow here CONFIG_NFT_REJECT_INET=y

>> > and CONFIG_NF_REJECT_IPV6=m.

>> >

>> > I mean, just like we do with NFT_FIB_INET.

>>

>> That can only work if NFT_REJECT_INET can be made a 'tristate' symbol

>> again, so that code gets built as a loadable module if

>> CONFIG_NF_REJECT_IPV6=m.

>>

>> > BTW, I think this problem has been is not related to the recent patch,

>> > but something older that kbuild robot has triggered more easily for

>> > some reason?

>>

>> 02c7b25e5f54 is the one that turned NF_TABLES_INET into a 'bool'

>> symbol. NFT_REJECT depends on NF_TABLES_INET, so it used to

>> restricted to a loadable module with IPV6=m, but can now be

>> built-in, which causes that link error.

>

> Still one more spin on this, I would like to see if we have a way to

> fix this by simplifing things a bit.

>

> Would this one I'm attaching would work?


One disadvantage is that it makes the vmlinux bigger since
NF_REJECT_IPV{4,6} can no longer be a module at all now.

I suspect you also stil get a link error with IPV6=m, this time because
the nf_reject_ipv6.o file fails to link against the ipv6 code, e.g.
ipv6_skip_exthdr() and icmpv6_send() appear to be unreachable here.
I haven't tried that though, so I might be missing something.

        Arnd
kernel test robot April 14, 2018, 6:54 a.m. UTC | #5 
Hi Pablo,

I love your patch! Yet something to improve:

[auto build test ERROR on nf-next/master]
[also build test ERROR on v4.16 next-20180413]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Pablo-Neira-Ayuso/netfilter-CONFIG_NF_REJECT_IPV-4-6-becomes-bool-toggle/20180414-101337
base:   https://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git master
config: ia64-allmodconfig (attached as .config)
compiler: ia64-linux-gcc (GCC) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=ia64 

All errors (new ones prefixed by >>):

   net/ipv6/netfilter/nf_reject_ipv6.o: In function `nf_reject_ip6_tcphdr_get':
>> nf_reject_ipv6.c:(.text+0x342): undefined reference to `nf_ip6_checksum'

   net/ipv6/netfilter/nf_reject_ipv6.o: In function `nf_send_reset6':
>> nf_reject_ipv6.c:(.text+0xcc2): undefined reference to `ip6_route_output_flags'

   net/ipv6/netfilter/nf_reject_ipv6.o: In function `nf_send_unreach6':
   nf_reject_ipv6.c:(.text+0x12b2): undefined reference to `nf_ip6_checksum'

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
kernel test robot April 14, 2018, 9:45 a.m. UTC | #6 
Hi Pablo,

I love your patch! Yet something to improve:

[auto build test ERROR on nf-next/master]
[also build test ERROR on v4.16 next-20180413]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Pablo-Neira-Ayuso/netfilter-CONFIG_NF_REJECT_IPV-4-6-becomes-bool-toggle/20180414-101337
base:   https://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git master
config: powerpc64-allmodconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=powerpc64 

All error/warnings (new ones prefixed by >>):

   powerpc64-linux-gnu-ld: warning: orphan section `.gnu.hash' from `linker stubs' being placed in section `.gnu.hash'.
   net/ipv6/netfilter/nf_reject_ipv6.o: In function `.nf_reject_ip6_tcphdr_get':
>> (.text+0x1f0): undefined reference to `.nf_ip6_checksum'

   net/ipv6/netfilter/nf_reject_ipv6.o: In function `.nf_send_reset6':
>> (.text+0x794): undefined reference to `.ip6_route_output_flags'

   net/ipv6/netfilter/nf_reject_ipv6.o: In function `.nf_send_unreach6':
   (.text+0xab8): undefined reference to `.nf_ip6_checksum'

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
diff mbox series

Patch

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 704b3832dbad..44d8a55e9721 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -594,6 +594,7 @@  config NFT_QUOTA
 config NFT_REJECT
 	default m if NETFILTER_ADVANCED=n
 	tristate "Netfilter nf_tables reject support"
+	depends on !NF_TABLES_INET || (IPV6!=m || m)
 	help
 	  This option adds the "reject" expression that you can use to
 	  explicitly deny and notify via TCP reset/ICMP informational errors