Date: Tue, 31 Jan 2006 12:09:13 +0300 From: Oleg Bulyzhin <oleg@freebsd.org> To: Koen Martens <fbsd@metro.cx> Cc: darrenr@freebsd.org, glebius@freebsd.org, freebsd-stable@freebsd.org Subject: Re: ipfilter + bge strangeness Message-ID: <20060131090912.GA88914@lath.rinet.ru> In-Reply-To: <43DCCAA8.4050600@metro.cx> References: <43DB8EA6.7070503@metro.cx> <20060128211710.GA29790@lath.rinet.ru> <43DBED3F.3000408@metro.cx> <20060128230015.GC29790@lath.rinet.ru> <43DCCAA8.4050600@metro.cx>
next in thread | previous in thread | raw e-mail | index | archive | help
--lrZ03NoBR/3+SXJZ
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
On Sun, Jan 29, 2006 at 03:01:12PM +0100, Koen Martens wrote:
> Oleg Bulyzhin wrote:
> > On Sat, Jan 28, 2006 at 11:16:31PM +0100, Koen Martens wrote:
> >>Sure thing, although it happens with other kinds of traffic too (in
> >>the dump, there's some NTP for example). Here's the netstat output
> >>before:
> > ....
> >
> > Btw, until recent changes bge had txcsum (not rxcsum) only.
> >
> > As i can see there is no problem with checksum's at all (at least inside
> > bge driver). tcpdump reports bad checksum on outgoing packets due to
> > nature of tx checksum offloading: packet will get it's checksum calculated
> > right before it goes on wire (If you want to check tx checksum offloading
> > you should look on incoming packets on other end of wire).
> >
> > Looks like something is wrong inside ipfilter. Can you test with ipfilter
> > turned off (ipf -D or, if you using module, kld_unload ipl.ko)?
>
> With ipfilter disabled and rxcsum enabled all is well (also, with
> ipfilter and rxcsum enabled but just two rules to allow anything
> in/out it works fine too).
>
> The tcpdump output looks the same (see below).
>
> It is not a purely ipfilter thing i guess, since on an em interface
> on another box with txcsum/rxcsum on, there is no problem. It is
> something in the combination of bge and ipfilter, although that is
> as far as my speculation goes right now..
Could you please test attached patch?
Root of the problem is inside ipfilter - if driver use 'partial' (i.e. without
pseudo header) rx checksum offloading ipfilter fails to calculate checksum
correctly (it's using ip packet length (ip_fil_freebsd.c:1561) instead of
tcp/udp length).
This patch enables 'full' rxcsum offloading so ipfilter's bug should not be
triggered.
--
Oleg.
--lrZ03NoBR/3+SXJZ
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment; filename="bge_rxcsum.diff"
Index: if_bge.c
===================================================================
RCS file: /home/ncvs/src/sys/dev/bge/if_bge.c,v
retrieving revision 1.118
diff -u -r1.118 if_bge.c
--- if_bge.c 30 Jan 2006 13:45:55 -0000 1.118
+++ if_bge.c 31 Jan 2006 08:53:00 -0000
@@ -1099,7 +1099,7 @@
*/
CSR_WRITE_4(sc, BGE_MODE_CTL, BGE_DMA_SWAP_OPTIONS|
BGE_MODECTL_MAC_ATTN_INTR|BGE_MODECTL_HOST_SEND_BDS|
- BGE_MODECTL_TX_NO_PHDR_CSUM|BGE_MODECTL_RX_NO_PHDR_CSUM);
+ BGE_MODECTL_TX_NO_PHDR_CSUM);
/*
* Disable memory write invalidate. Apparently it is not supported
@@ -2631,7 +2631,8 @@
m->m_pkthdr.len >= ETHER_MIN_NOPAD) {
m->m_pkthdr.csum_data =
cur_rx->bge_tcp_udp_csum;
- m->m_pkthdr.csum_flags |= CSUM_DATA_VALID;
+ m->m_pkthdr.csum_flags |=
+ CSUM_DATA_VALID | CSUM_PSEUDO_HDR;
}
}
--lrZ03NoBR/3+SXJZ--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060131090912.GA88914>