From: "Michał Krawczyk" <mk@semihalf.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>
Cc: dev <dev@dpdk.org>, "Brandes, Shai" <shaibran@amazon.com>,
upstream@semihalf.com, Dawid Gorecki <dgr@semihalf.com>
Subject: Re: [PATCH v3 09/21] net/ena/base: use optimized memcpy version also on Arm
Date: Wed, 23 Feb 2022 18:40:34 +0100 [thread overview]
Message-ID: <CAJMMOfNQ62pXT8uL5SdugKYofUDZ8abF-+xNfZovDMVxvuSfqQ@mail.gmail.com> (raw)
In-Reply-To: <733b3d43-00f6-d38b-abef-f0c76e82dbc1@intel.com>
śr., 23 lut 2022 o 18:26 Ferruh Yigit <ferruh.yigit@intel.com> napisał(a):
>
> On 2/23/2022 12:19 PM, Michal Krawczyk wrote:
> > As the default behavior for arm64 is to alias rte_memcpy as memcpy, ENA
> > cannot redefine memcpy as rte_memcpy as it would cause nested
> > declaration.
> >
> > To make it possible to use optimized memcpy in the ena_com layer on Arm,
>
> Out of curiosity, do you have any performance measurements for
> the optimized memcpy usage?
>
Unfortunately no - on AWS it's hard to see noticeable performance
improvement due to limitations in terms of the PPS number that can be
processed at maximum. The basic packet generator applications are
mostly idle in that situation.
> > the driver now redefines memcpy when it is beneficial:
> > * For arm64 only when the flag RTE_ARCH_ARM64_MEMCPY was defined
> > * For arm only when the flag RTE_ARCH_ARM_NEON_MEMCPY was defined
> >
> > Signed-off-by: Michal Krawczyk <mk@semihalf.com>
> > Reviewed-by: Dawid Gorecki <dgr@semihalf.com>
> > Reviewed-by: Shai Brandes <shaibran@amazon.com>
> > ---
> > doc/guides/rel_notes/release_22_03.rst | 1 +
> > drivers/net/ena/base/ena_plat_dpdk.h | 7 +++++--
> > 2 files changed, 6 insertions(+), 2 deletions(-)
> >
> > diff --git a/doc/guides/rel_notes/release_22_03.rst b/doc/guides/rel_notes/release_22_03.rst
> > index c8e38d4c70..92490afd60 100644
> > --- a/doc/guides/rel_notes/release_22_03.rst
> > +++ b/doc/guides/rel_notes/release_22_03.rst
> > @@ -112,6 +112,7 @@ New Features
> > * Added new checksum related xstats: ``l3_csum_bad``, ``l4_csum_bad`` and
> > ``l4_csum_good``.
> > * Added support for the link status configuration.
> > + * Added optimized memcpy support for the ARM platforms.
> >
> > * **Updated Cisco enic driver.**
> >
> > diff --git a/drivers/net/ena/base/ena_plat_dpdk.h b/drivers/net/ena/base/ena_plat_dpdk.h
> > index 4e7f52881a..41db883c63 100644
> > --- a/drivers/net/ena/base/ena_plat_dpdk.h
> > +++ b/drivers/net/ena/base/ena_plat_dpdk.h
> > @@ -66,8 +66,11 @@ typedef uint64_t dma_addr_t;
> > #define ENA_UDELAY(x) rte_delay_us_block(x)
> >
> > #define ENA_TOUCH(x) ((void)(x))
> > -/* Avoid nested declaration on arm64, as it may define rte_memcpy as memcpy. */
> > -#if defined(RTE_ARCH_X86)
> > +/* Redefine memcpy with caution: rte_memcpy can be simply aliased to memcpy, so
> > + * make the redefinition only if it's safe (and beneficial) to do so.
> > + */
> > +#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64_MEMCPY) || \
> > + defined(RTE_ARCH_ARM_NEON_MEMCPY)
> > #undef memcpy
> > #define memcpy rte_memcpy
> > #endif
>
> I can see there is 'ena_plat_dpdk.h', which seems like an osdep header,
>
> it is possible to use 'ena_memcpy' in the code and in the 'ena_plat_dpdk.h'
> define it as:
> #define ena_memcpy rte_memcpy
>
>
> This is just for your information if it helps, usage is up to you.
Thanks for the input! It looks like a robust solution, but
unfortunately we can't modify other ena_com files which use raw memcpy
calls.The preferred approach is to do some work-arounds in the osdep
headers instead of modifying the common files.
next prev parent reply other threads:[~2022-02-23 17:40 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-22 16:06 [PATCH 00/21] net/ena: v2.6.0 driver update Michal Krawczyk
2022-02-22 16:06 ` [PATCH 01/21] net/ena: remove linearization function Michal Krawczyk
2022-02-22 16:06 ` [PATCH 02/21] net/ena: add assertion on Tx info mbuf Michal Krawczyk
2022-02-22 16:06 ` [PATCH 03/21] net/ena: remove unused enumeration Michal Krawczyk
2022-02-22 16:06 ` [PATCH 04/21] net/ena: remove unused offloads variables Michal Krawczyk
2022-02-22 16:06 ` [PATCH 05/21] net/ena: add extra Rx checksum related xstats Michal Krawczyk
2022-02-22 16:06 ` [PATCH 06/21] net/ena: make LSC configurable Michal Krawczyk
2022-02-22 16:06 ` [PATCH 07/21] net/ena: skip timer if the reset is triggered Michal Krawczyk
2022-02-22 16:06 ` [PATCH 08/21] net/ena: perform Tx cleanup before sending pkts Michal Krawczyk
2022-02-22 16:06 ` [PATCH 09/21] net/ena/base: use optimized memcpy version also on Arm Michal Krawczyk
2022-02-22 16:06 ` [PATCH 10/21] net/ena: proxy AQ calls to primary process Michal Krawczyk
2022-02-22 16:06 ` [PATCH 11/21] net/ena: enable stats get function for MP mode Michal Krawczyk
2022-02-22 16:06 ` [PATCH 12/21] net/ena/base: make IO memzone unique per port Michal Krawczyk
2022-02-22 16:06 ` [PATCH 13/21] net/ena: expose Tx cleanup function Michal Krawczyk
2022-02-22 16:06 ` [PATCH 14/21] net/ena: add API for probing xstat names by ID Michal Krawczyk
2022-02-22 16:06 ` [PATCH 15/21] net/ena: check if reset was already triggered Michal Krawczyk
2022-02-22 16:06 ` [PATCH 16/21] net/ena: make Tx completion timeout configurable Michal Krawczyk
2022-02-22 16:06 ` [PATCH 17/21] net/ena: fix meta-desc DF flag setup Michal Krawczyk
2022-02-22 16:06 ` [PATCH 18/21] net/ena: extend debug prints for invalid req ID resets Michal Krawczyk
2022-02-22 16:06 ` [PATCH 19/21] net/ena: don't initialize LLQ when membar isn't exposed Michal Krawczyk
2022-02-22 16:06 ` [PATCH 20/21] net/ena: don't indicate bad csum for L4 csum error Michal Krawczyk
2022-02-22 16:06 ` [PATCH 21/21] net/ena: update version to 2.6.0 Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 00/21] net/ena: v2.6.0 driver update Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 01/21] net/ena: remove linearization function Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 02/21] net/ena: add assertion on Tx info mbuf Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 03/21] net/ena: remove unused enumeration Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 04/21] net/ena: remove unused offloads variables Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 05/21] net/ena: add extra Rx checksum related xstats Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 06/21] net/ena: make LSC configurable Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 07/21] net/ena: skip timer if the reset is triggered Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 08/21] net/ena: perform Tx cleanup before sending pkts Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 09/21] net/ena/base: use optimized memcpy version also on Arm Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 10/21] net/ena: proxy AQ calls to primary process Michal Krawczyk
2022-02-22 22:24 ` Ferruh Yigit
2022-02-23 0:50 ` Ferruh Yigit
2022-02-22 18:11 ` [PATCH v2 11/21] net/ena: enable stats get function for MP mode Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 12/21] net/ena/base: make IO memzone unique per port Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 13/21] net/ena: expose Tx cleanup function Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 14/21] net/ena: add API for probing xstat names by ID Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 15/21] net/ena: check if reset was already triggered Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 16/21] net/ena: make Tx completion timeout configurable Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 17/21] net/ena: fix meta-desc DF flag setup Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 18/21] net/ena: extend debug prints for invalid req ID resets Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 19/21] net/ena: don't initialize LLQ when membar isn't exposed Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 20/21] net/ena: don't indicate bad csum for L4 csum error Michal Krawczyk
2022-02-22 18:11 ` [PATCH v2 21/21] net/ena: update version to 2.6.0 Michal Krawczyk
2022-02-22 22:21 ` [PATCH v2 00/21] net/ena: v2.6.0 driver update Ferruh Yigit
2022-02-23 10:07 ` Michał Krawczyk
2022-02-23 12:19 ` [PATCH v3 " Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 01/21] net/ena: remove linearization function Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 02/21] net/ena: add assertion on Tx info mbuf Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 03/21] net/ena: remove unused enumeration Michal Krawczyk
2022-02-23 17:25 ` Ferruh Yigit
2022-02-23 12:19 ` [PATCH v3 04/21] net/ena: remove unused offloads variables Michal Krawczyk
2022-02-23 17:25 ` Ferruh Yigit
2022-02-23 17:47 ` Michał Krawczyk
2022-02-23 18:12 ` Ferruh Yigit
2022-02-23 12:19 ` [PATCH v3 05/21] net/ena: add extra Rx checksum related xstats Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 06/21] net/ena: make LSC configurable Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 07/21] net/ena: skip timer if the reset is triggered Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 08/21] net/ena: perform Tx cleanup before sending pkts Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 09/21] net/ena/base: use optimized memcpy version also on Arm Michal Krawczyk
2022-02-23 17:25 ` Ferruh Yigit
2022-02-23 17:40 ` Michał Krawczyk [this message]
2022-02-23 12:19 ` [PATCH v3 10/21] net/ena: proxy AQ calls to primary process Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 11/21] net/ena: enable stats get function for MP mode Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 12/21] net/ena/base: make IO memzone unique per port Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 13/21] net/ena: expose Tx cleanup function Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 14/21] net/ena: add API for probing xstat names by ID Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 15/21] net/ena: check if reset was already triggered Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 16/21] net/ena: make Tx completion timeout configurable Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 17/21] net/ena: fix meta-desc DF flag setup Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 18/21] net/ena: extend debug prints for invalid req ID resets Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 19/21] net/ena: don't initialize LLQ when membar isn't exposed Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 20/21] net/ena: don't indicate bad csum for L4 csum error Michal Krawczyk
2022-02-23 12:19 ` [PATCH v3 21/21] net/ena: update version to 2.6.0 Michal Krawczyk
2022-02-23 18:12 ` [PATCH v3 00/21] net/ena: v2.6.0 driver update Ferruh Yigit
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=CAJMMOfNQ62pXT8uL5SdugKYofUDZ8abF-+xNfZovDMVxvuSfqQ@mail.gmail.com \
--to=mk@semihalf.com \
--cc=dev@dpdk.org \
--cc=dgr@semihalf.com \
--cc=ferruh.yigit@intel.com \
--cc=shaibran@amazon.com \
--cc=upstream@semihalf.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).