All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: "Morten Brørup" <mb@smartsharesystems.com>
Cc: <dev@dpdk.org>,
	"Konstantin Ananyev" <konstantin.ananyev@huawei.com>,
	"Bruce Richardson" <bruce.richardson@intel.com>
Subject: Re: [PATCH 00/61] reduce use of rte_memcpy
Date: Thu, 20 Aug 2026 13:18:45 -0700	[thread overview]
Message-ID: <20260820131845.100e3cf6@phoenix.local> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35F659FD@smartserver.smartshare.dk>

On Thu, 20 Aug 2026 09:31:40 +0200
Morten Brørup <mb@smartsharesystems.com> wrote:

> > Many platforms have no special rte_memcpy() and just use memcpy().
> > 
> > But many analysis and test tools know that memcpy() is a special
> > case and check for overwrite, bounds errors etc. Therefore memcpy()
> > should be preferred wherever possible.  
> 
> I think this is the only substantial benefit of replacing rte_memcpy() with memcpy()!
> Could we reap this benefit by having special builds for such tools, where rte_memcpy() is modified to use memcpy() instead?
> Then we wouldn't have to compromise on performance.
> 
> Also, rte_memcpy() used to have a pragma disabling bounds checks due to some Intel drivers using [0] instead of []; the pragma was removed from rte_memcpy() when the Intel drivers were fixed.
> I'm not sufficiently familiar with analysis/test tools to say what they can detect when using memcpy() instead of the copy methods used by rte_memcpy().


The most common one is fortify which is runtime checking and part of Ubuntu etc
build. So no doing some #ifdef FORTIFY_SOURCE really is not helping.

      parent reply	other threads:[~2026-08-20 20:18 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-20  5:11 [PATCH 00/61] reduce use of rte_memcpy Stephen Hemminger
2026-08-20  5:11 ` [PATCH 01/61] devtools/cocci: add script to replace fixed size rte_memcpy Stephen Hemminger
2026-08-20  5:11 ` [PATCH 02/61] app/testpmd: replace rte_memcpy with memcpy Stephen Hemminger
2026-08-20  5:11 ` [PATCH 03/61] test: use memcpy instead of rte_memcpy Stephen Hemminger
2026-08-20  6:22   ` Morten Brørup
2026-08-20 16:22     ` Stephen Hemminger
2026-08-20  5:11 ` [PATCH 04/61] app/graph: replace rte_memcpy with memcpy Stephen Hemminger
2026-08-20  5:11 ` [PATCH 05/61] lpm: remove unnecessary include of rte_memcpy.h Stephen Hemminger
2026-08-20  5:11 ` [PATCH 06/61] acl: " Stephen Hemminger
2026-08-20  5:11 ` [PATCH 07/61] drivers/bus: " Stephen Hemminger
2026-08-20  5:11 ` [PATCH 08/61] security: replace fixed size rte_memcpy Stephen Hemminger
2026-08-20  5:11 ` [PATCH 09/61] ethdev: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 10/61] net: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 11/61] pdcp: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 12/61] eventdev: replace fixed size rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 13/61] eal: replace rte_memcpy of cpuset Stephen Hemminger
2026-08-20  5:12 ` [PATCH 14/61] cryptodev: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 15/61] drivers/raw: use memcpy for fixed size data Stephen Hemminger
2026-08-20  5:12 ` [PATCH 16/61] test-pipeline: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 17/61] net/af_xdp: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 18/61] net/avp: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 19/61] net/axgbe: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 20/61] net/bnx2x: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 21/61] net/bnxt: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 22/61] net/bonding: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 23/61] net/cnxk: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 24/61] net/cxgbe: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 25/61] net/dpaa2: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 26/61] net/enic: " Stephen Hemminger
2026-08-20  9:05   ` Hyong Youb Kim (hyonkim)
2026-08-20  5:12 ` [PATCH 27/61] net/failsafe: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 28/61] net/gve: " Stephen Hemminger
2026-08-20 20:42   ` Joshua Washington
2026-08-20  5:12 ` [PATCH 29/61] net/hinic: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 30/61] net/hns3: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 31/61] net/mlx5: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 32/61] net/mvpp2: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 33/61] net/netvsc: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 34/61] net/nfp: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 35/61] net/ngbe: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 36/61] net/ntnic: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 37/61] net/null: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 38/61] net/qede: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 39/61] net/ring: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 40/61] net/sfc: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 41/61] net/txgbe: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 42/61] net/vhost: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 43/61] net/virtio: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 44/61] net/sxe2: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 45/61] net/zxdh: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 46/61] net/memif: use memcpy for fixed size data Stephen Hemminger
2026-08-20  5:12 ` [PATCH 47/61] net/ice: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 48/61] test-bbdev: remove unnecessary include rte_memcpy.h Stephen Hemminger
2026-08-20  5:12 ` [PATCH 49/61] drivers/mempool: use memcpy for fixed size data Stephen Hemminger
2026-08-20  5:12 ` [PATCH 50/61] ml/cnxk: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 51/61] drivers/event: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 52/61] baseband/la12xx: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 53/61] baseband/acc: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 54/61] drivers/*/qat: use memcpy for fixed size data Stephen Hemminger
2026-08-20  5:12 ` [PATCH 55/61] hash: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 56/61] rib: remove rte_memcpy include Stephen Hemminger
2026-08-20  5:12 ` [PATCH 57/61] pcapng: replace use of rte_memcpy Stephen Hemminger
2026-08-20  5:12 ` [PATCH 58/61] efd: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 59/61] net/xsc: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 60/61] net/pcap: " Stephen Hemminger
2026-08-20  5:12 ` [PATCH 61/61] power: " Stephen Hemminger
2026-08-20  7:31 ` [PATCH 00/61] reduce " Morten Brørup
2026-08-20  8:16   ` Bruce Richardson
2026-08-20  8:46   ` Konstantin Ananyev
2026-08-20  9:03     ` Morten Brørup
2026-08-20 13:07       ` Konstantin Ananyev
2026-08-20 14:00         ` Morten Brørup
2026-08-20 20:13           ` Stephen Hemminger
2026-08-20 20:16       ` Stephen Hemminger
2026-08-20 20:18   ` Stephen Hemminger [this message]

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=20260820131845.100e3cf6@phoenix.local \
    --to=stephen@networkplumber.org \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=konstantin.ananyev@huawei.com \
    --cc=mb@smartsharesystems.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.