XDP hardware hints discussion mail archive
 help / color / mirror / Atom feed
From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Cc: Larysa Zaremba <larysa.zaremba@intel.com>,
	bpf@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net,
	andrii@kernel.org, martin.lau@linux.dev, song@kernel.org,
	yhs@fb.com, john.fastabend@gmail.com, kpsingh@kernel.org,
	sdf@google.com, haoluo@google.com, jolsa@kernel.org,
	David Ahern <dsahern@gmail.com>, Jakub Kicinski <kuba@kernel.org>,
	Willem de Bruijn <willemb@google.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Anatoly Burakov <anatoly.burakov@intel.com>,
	Alexander Lobakin <alexandr.lobakin@intel.com>,
	Magnus Karlsson <magnus.karlsson@gmail.com>,
	Maryam Tahhan <mtahhan@redhat.com>,
	xdp-hints@xdp-project.net, netdev@vger.kernel.org,
	Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
	Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Simon Horman <simon.horman@corigine.com>,
	Tariq Toukan <tariqt@mellanox.com>,
	Saeed Mahameed <saeedm@mellanox.com>
Subject: [xdp-hints] Re: [RFC bpf-next 01/23] ice: make RX hash reading code more reusable
Date: Wed, 6 Sep 2023 14:23:05 +0200	[thread overview]
Message-ID: <e2b1bf53-b216-c90d-869e-24008943e41b@intel.com> (raw)
In-Reply-To: <ZPXruYZtN6rA6MuS@boxer>

From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Mon, 4 Sep 2023 16:37:45 +0200

> On Thu, Aug 24, 2023 at 09:26:40PM +0200, Larysa Zaremba wrote:
>> Previously, we only needed RX hash in skb path,
>> hence all related code was written with skb in mind.
>> But with the addition of XDP hints via kfuncs to the ice driver,
>> the same logic will be needed in .xmo_() callbacks.

[...]

>> -	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
>> -	hash = le32_to_cpu(nic_mdid->rss_hash);
>> -	skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
>> +	hash = ice_get_rx_hash(rx_desc);
>> +	if (likely(hash))
>> +		skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
> 
> Looks like a behavior change as you wouldn't be setting l4_hash and
> sw_hash from skb in case !hash ? When can we get hash == 0 ?

I do the same in libie. hash == 0 makes no sense at all no matter if you
set sw or l4, esp. for GRO and other stack pieces.
BTW, sw_hash is never set by drivers, it's meant to be set only from the
core networking hashing functions (when it's hashed by CPU with SIPhash
with the help of Flow Dissector). So we only do care about l4_hash.
Valid hash == 0 for valid L4 frame has 0.0(0)1% probability even for
XOR, not speaking of Toeplitz / CRC (have you even seen MD5 == 0? :D).
if the frame is not L4, the kernel doesn't treat your hash as something
meaningful and falls back to SIP. But the prob of having hash == 0 for
L3- is not higher :D

> 
>>  }
>>  
>>  /**
>> @@ -186,7 +201,7 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
>>  		       union ice_32b_rx_flex_desc *rx_desc,
>>  		       struct sk_buff *skb, u16 ptype)
>>  {
>> -	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
>> +	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
>>  
>>  	/* modifies the skb - consumes the enet header */
>>  	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
>> -- 
>> 2.41.0
>>

Thanks,
Olek

  reply	other threads:[~2023-09-06 12:24 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-24 19:26 [xdp-hints] [RFC bpf-next 00/23] XDP metadata via kfuncs for ice + mlx5 Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 01/23] ice: make RX hash reading code more reusable Larysa Zaremba
2023-09-04 14:37   ` [xdp-hints] " Maciej Fijalkowski
2023-09-06 12:23     ` Alexander Lobakin [this message]
2023-09-14 16:12   ` Alexander Lobakin
2023-09-14 16:15     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 02/23] ice: make RX HW timestamp " Larysa Zaremba
2023-09-04 14:56   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 16:29     ` Larysa Zaremba
2023-09-05 15:22       ` Maciej Fijalkowski
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 03/23] ice: make RX checksum checking " Larysa Zaremba
2023-09-04 15:02   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 18:01     ` Larysa Zaremba
2023-09-05 15:37       ` Maciej Fijalkowski
2023-09-05 16:53         ` Larysa Zaremba
2023-09-05 17:44           ` Maciej Fijalkowski
2023-09-06  9:28             ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 04/23] ice: Make ptype internal to descriptor info processing Larysa Zaremba
2023-09-04 15:04   ` [xdp-hints] " Maciej Fijalkowski
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 05/23] ice: Introduce ice_xdp_buff Larysa Zaremba
2023-09-04 15:32   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 18:11     ` Larysa Zaremba
2023-09-05 17:53       ` Maciej Fijalkowski
2023-09-07 14:21         ` Larysa Zaremba
2023-09-07 16:33           ` Stanislav Fomichev
2023-09-07 16:42             ` Maciej Fijalkowski
2023-09-07 16:43               ` Maciej Fijalkowski
2023-09-13 15:40                 ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 06/23] ice: Support HW timestamp hint Larysa Zaremba
2023-09-04 15:38   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 18:12     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 07/23] ice: Support RX hash XDP hint Larysa Zaremba
2023-09-05 15:42   ` [xdp-hints] " Maciej Fijalkowski
2023-09-05 17:09     ` Larysa Zaremba
2023-09-06 12:03     ` Alexander Lobakin
2023-09-14 16:54   ` Alexander Lobakin
2023-09-14 16:59     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 08/23] ice: Support XDP hints in AF_XDP ZC mode Larysa Zaremba
2023-09-04 15:42   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 18:14     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 09/23] xdp: Add VLAN tag hint Larysa Zaremba
2023-09-14 16:18   ` [xdp-hints] " Alexander Lobakin
2023-09-14 16:21     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 10/23] ice: Implement " Larysa Zaremba
2023-09-04 16:00   ` [xdp-hints] " Maciej Fijalkowski
2023-09-04 18:18     ` Larysa Zaremba
2023-09-14 16:25   ` Alexander Lobakin
2023-09-14 16:28     ` Larysa Zaremba
2023-09-14 16:38       ` Alexander Lobakin
2023-09-14 17:02         ` Larysa Zaremba
2023-09-18 14:07         ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 11/23] ice: use VLAN proto from ring packet context in skb path Larysa Zaremba
2023-09-14 16:30   ` [xdp-hints] " Alexander Lobakin
2023-09-14 16:30     ` Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 12/23] xdp: Add checksum hint Larysa Zaremba
2023-09-14 16:34   ` [xdp-hints] " Alexander Lobakin
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 13/23] ice: Implement " Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 14/23] selftests/bpf: Allow VLAN packets in xdp_hw_metadata Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 15/23] net, xdp: allow metadata > 32 Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 16/23] selftests/bpf: Add flags and new hints to xdp_hw_metadata Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 17/23] veth: Implement VLAN tag and checksum XDP hint Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 18/23] net: make vlan_get_tag() return -ENODATA instead of -EINVAL Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 19/23] selftests/bpf: Use AF_INET for TX in xdp_metadata Larysa Zaremba
2023-08-24 19:26 ` [xdp-hints] [RFC bpf-next 20/23] selftests/bpf: Check VLAN tag and proto " Larysa Zaremba
2023-08-24 19:27 ` [xdp-hints] [RFC bpf-next 21/23] selftests/bpf: check checksum state " Larysa Zaremba
2023-08-24 19:27 ` [xdp-hints] [RFC bpf-next 22/23] mlx5: implement VLAN tag XDP hint Larysa Zaremba
2023-08-24 19:27 ` [xdp-hints] [RFC bpf-next 23/23] mlx5: implement RX checksum " Larysa Zaremba
2023-08-31 14:50 ` [xdp-hints] Re: [RFC bpf-next 00/23] XDP metadata via kfuncs for ice + mlx5 Larysa Zaremba
2023-09-04 16:06 ` Maciej Fijalkowski
2023-09-06 14:09   ` Larysa Zaremba

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

  List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/

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

  git send-email \
    --in-reply-to=e2b1bf53-b216-c90d-869e-24008943e41b@intel.com \
    --to=aleksander.lobakin@intel.com \
    --cc=alexandr.lobakin@intel.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=anatoly.burakov@intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=dsahern@gmail.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=larysa.zaremba@intel.com \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@gmail.com \
    --cc=martin.lau@linux.dev \
    --cc=mtahhan@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=sdf@google.com \
    --cc=simon.horman@corigine.com \
    --cc=song@kernel.org \
    --cc=tariqt@mellanox.com \
    --cc=willemb@google.com \
    --cc=willemdebruijn.kernel@gmail.com \
    --cc=xdp-hints@xdp-project.net \
    --cc=yhs@fb.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