bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Lorenzo Bianconi <lorenzo@kernel.org>
To: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: bpf@vger.kernel.org, netdev@vger.kernel.org,
	lorenzo.bianconi@redhat.com, davem@davemloft.net,
	kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net,
	shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com,
	dsahern@kernel.org, echaudro@redhat.com, jasowang@redhat.com,
	alexander.duyck@gmail.com, saeed@kernel.org,
	maciej.fijalkowski@intel.com
Subject: Re: [PATCH v8 bpf-next 01/14] xdp: introduce mb in xdp_buff/xdp_frame
Date: Thu, 29 Apr 2021 15:54:02 +0200	[thread overview]
Message-ID: <YIq6eoS+5UZRTi/5@lore-desk> (raw)
In-Reply-To: <20210429153629.1fef2386@carbon>

[-- Attachment #1: Type: text/plain, Size: 2141 bytes --]

> >  static __always_inline void
> > @@ -116,7 +120,8 @@ struct xdp_frame {
> >  	u16 len;
> >  	u16 headroom;
> >  	u32 metasize:8;
> > -	u32 frame_sz:24;
> > +	u32 frame_sz:23;
> > +	u32 mb:1; /* xdp non-linear frame */
> >  	/* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time,
> >  	 * while mem info is valid on remote CPU.
> >  	 */
> 
> So, it seems that these bitfield's are the root-cause of the
> performance regression.  Credit to Alexei whom wisely already point
> this out[1] in V2 ;-)
> 
> [1] https://lore.kernel.org/netdev/20200904010705.jm6dnuyj3oq4cpjd@ast-mbp.dhcp.thefacebook.com/

yes, shame on me..yesterday I recalled email from Alexei debugging the issue
reported by Magnus.
In the current approach I am testing (not posted upstream yet) I reduced the
size of xdp_mem_info as proposed by Jesper in [0] and I added a flags field
in xdp_frame/xdp_buff we can use for multiple features (e.g. multi-buff or hw csum
hints). Doing so, running xdp_rxq_info sample on ixgbe 10Gbps NIC I do not have any
performance regressions for xdp_tx or xdp_drop. Same results have been reported by
Magnus off-list on i40e (we have a 1% regression on xdp_sock tests iiuc).
I will continue working on this.

Regards,
Lorenzo

[0] https://patchwork.kernel.org/project/netdevbpf/patch/20210409223801.104657-2-mcroce@linux.microsoft.com/

> 
> 
> > @@ -179,6 +184,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
> >  	xdp->data_end = frame->data + frame->len;
> >  	xdp->data_meta = frame->data - frame->metasize;
> >  	xdp->frame_sz = frame->frame_sz;
> > +	xdp->mb = frame->mb;
> >  }
> >  
> >  static inline
> > @@ -205,6 +211,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp,
> >  	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
> >  	xdp_frame->metasize = metasize;
> >  	xdp_frame->frame_sz = xdp->frame_sz;
> > +	xdp_frame->mb = xdp->mb;
> >  
> >  	return 0;
> >  }
> 
> -- 
> Best regards,
>   Jesper Dangaard Brouer
>   MSc.CS, Principal Kernel Engineer at Red Hat
>   LinkedIn: http://www.linkedin.com/in/brouer
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

  reply	other threads:[~2021-04-29 13:54 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-08 12:50 [PATCH v8 bpf-next 00/14] mvneta: introduce XDP multi-buffer support Lorenzo Bianconi
2021-04-08 12:50 ` [PATCH v8 bpf-next 01/14] xdp: introduce mb in xdp_buff/xdp_frame Lorenzo Bianconi
2021-04-08 18:17   ` Vladimir Oltean
2021-04-09 16:03     ` Lorenzo Bianconi
2021-04-29 13:36   ` Jesper Dangaard Brouer
2021-04-29 13:54     ` Lorenzo Bianconi [this message]
2021-04-08 12:50 ` [PATCH v8 bpf-next 02/14] xdp: add xdp_shared_info data structure Lorenzo Bianconi
2021-04-08 13:39   ` Vladimir Oltean
2021-04-08 14:26     ` Lorenzo Bianconi
2021-04-08 18:06   ` kernel test robot
2021-04-08 12:50 ` [PATCH v8 bpf-next 03/14] net: mvneta: update mb bit before passing the xdp buffer to eBPF layer Lorenzo Bianconi
2021-04-08 18:19   ` Vladimir Oltean
2021-04-09 16:24     ` Lorenzo Bianconi
2021-04-08 12:50 ` [PATCH v8 bpf-next 04/14] xdp: add multi-buff support to xdp_return_{buff/frame} Lorenzo Bianconi
2021-04-08 18:30   ` Vladimir Oltean
2021-04-09 16:28     ` Lorenzo Bianconi
2021-04-08 12:50 ` [PATCH v8 bpf-next 05/14] net: mvneta: add multi buffer support to XDP_TX Lorenzo Bianconi
2021-04-08 18:40   ` Vladimir Oltean
2021-04-09 16:36     ` Lorenzo Bianconi
2021-04-08 12:50 ` [PATCH v8 bpf-next 06/14] net: mvneta: enable jumbo frames for XDP Lorenzo Bianconi
2021-04-08 12:50 ` [PATCH v8 bpf-next 07/14] net: xdp: add multi-buff support to xdp_build_skb_from_fram Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 08/14] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API Lorenzo Bianconi
2021-04-08 19:15   ` Vladimir Oltean
2021-04-08 20:54     ` Vladimir Oltean
2021-04-09 18:13       ` Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 09/14] bpd: add multi-buffer support to xdp copy helpers Lorenzo Bianconi
2021-04-08 20:57   ` Vladimir Oltean
2021-04-09 18:19     ` Lorenzo Bianconi
2021-04-08 21:04   ` Vladimir Oltean
2021-04-14  8:08     ` Eelco Chaudron
2021-04-08 12:51 ` [PATCH v8 bpf-next 10/14] bpf: add new frame_length field to the XDP ctx Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 11/14] bpf: move user_size out of bpf_test_init Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 12/14] bpf: introduce multibuff support to bpf_prog_test_run_xdp() Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 13/14] bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature Lorenzo Bianconi
2021-04-08 12:51 ` [PATCH v8 bpf-next 14/14] bpf: update xdp_adjust_tail selftest to include multi-buffer Lorenzo Bianconi
2021-04-09  0:56 ` [PATCH v8 bpf-next 00/14] mvneta: introduce XDP multi-buffer support John Fastabend
2021-04-09 20:16   ` Lorenzo Bianconi
2021-04-13 15:16   ` Eelco Chaudron
2021-04-16 14:27 ` Magnus Karlsson
2021-04-16 21:29   ` Lorenzo Bianconi
2021-04-16 23:00     ` Daniel Borkmann
2021-04-18 16:18   ` Jesper Dangaard Brouer
2021-04-19  6:20     ` Magnus Karlsson
2021-04-19  6:55       ` Lorenzo Bianconi
2021-04-20 13:49         ` Magnus Karlsson
2021-04-21 12:47           ` Jesper Dangaard Brouer
2021-04-21 14:12             ` Magnus Karlsson
2021-04-21 15:39               ` Jesper Dangaard Brouer
2021-04-22 10:24                 ` Magnus Karlsson
2021-04-22 14:42                   ` Jesper Dangaard Brouer
2021-04-22 15:05                     ` Crash for i40e on net-next (was: [PATCH v8 bpf-next 00/14] mvneta: introduce XDP multi-buffer support) Jesper Dangaard Brouer
2021-04-23  5:28                       ` Magnus Karlsson
2021-04-23 16:43                         ` Alexander Duyck
2021-04-25  9:45                           ` Magnus Karlsson
2021-04-27 18:28   ` [PATCH v8 bpf-next 00/14] mvneta: introduce XDP multi-buffer support Lorenzo Bianconi
2021-04-28  7:41     ` Magnus Karlsson
2021-04-29 12:49       ` Jesper Dangaard Brouer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YIq6eoS+5UZRTi/5@lore-desk \
    --to=lorenzo@kernel.org \
    --cc=alexander.duyck@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=echaudro@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=lorenzo.bianconi@redhat.com \
    --cc=maciej.fijalkowski@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeed@kernel.org \
    --cc=sameehj@amazon.com \
    --cc=shayagr@amazon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).