[dpdk-stable] [dpdk-dev] [PATCH] app/testpmd: fix l4 sw csum over multi segments

Li, Xiaoyun xiaoyun.li at intel.com
Mon Oct 18 06:40:57 CEST 2021


> -----Original Message-----
> From: dev <dev-bounces at dpdk.org> On Behalf Of Li, Xiaoyun
> Sent: Monday, October 18, 2021 11:17
> To: Stephen Hemminger <stephen at networkplumber.org>
> Cc: Yigit, Ferruh <ferruh.yigit at intel.com>; dev at dpdk.org; stable at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] app/testpmd: fix l4 sw csum over multi
> segments
> 
> Hi
> 
> > -----Original Message-----
> > From: Stephen Hemminger <stephen at networkplumber.org>
> > Sent: Monday, October 18, 2021 11:00
> > To: Li, Xiaoyun <xiaoyun.li at intel.com>
> > Cc: Yigit, Ferruh <ferruh.yigit at intel.com>; dev at dpdk.org;
> > stable at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH] app/testpmd: fix l4 sw csum over multi
> > segments
> >
> > On Fri, 15 Oct 2021 13:13:06 +0800
> > Xiaoyun Li <xiaoyun.li at intel.com> wrote:
> >
> > > +		/* When sw csum is needed, multi-segs needs a buf to contain
> > > +		 * the whole packet for later UDP/TCP csum calculation.
> > > +		 */
> > > +		if (m->nb_segs > 1 && !(tx_ol_flags & PKT_TX_TCP_SEG) &&
> > > +		    !(tx_offloads & UDP_TCP_CSUM)) {
> > > +			l3_buf = rte_zmalloc("csum l3_buf",
> > > +					     info.pkt_len - info.l2_len,
> > > +					     RTE_CACHE_LINE_SIZE);
> > > +			rte_pktmbuf_read(m, info.l2_len,
> > > +					 info.pkt_len - info.l2_len, l3_buf);
> > > +			l3_hdr = l3_buf;
> > > +		} else
> > > +			l3_hdr = (char *)eth_hdr + info.l2_len;
> > >
> >
> > Rather than copying whole packet, make the code handle checksum streaming.
> 
> Copying is the easiest way to do this.
> 
> The problem of handling checksum streaming is that in the first segment, l2 and
> l3 hdr len is 14 bytes when checksum takes 4 bytes each time.
> If the datalen of the first segment is 4 bytes aligned (usual case), for the second
> segment and the following segments, they may need to add a special 2 bytes
> 0x0 at the start.
> Also, mbuf is not passed down to process_inner/outer_chksum so the change
> will be a lot.

Also, rte_ipv4/6_udptcp_cksum can't be directly called. Because it only takes ip_hdr and whole packet buffer as input.


More information about the stable mailing list