From: Jan Viktorin <viktorin@rehivetech.com>
To: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Cc: Vlastimil Kosar <kosar@rehivetech.com>, dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v5 01/15] eal/arm: atomic operations for ARM
Date: Mon, 2 Nov 2015 14:00:54 +0100 [thread overview]
Message-ID: <20151102140054.3cbe88c2@pcviktorin.fit.vutbr.cz> (raw)
In-Reply-To: <20151102055304.GB17659@localhost.localdomain>
On Mon, 2 Nov 2015 11:23:05 +0530
Jerin Jacob <jerin.jacob@caviumnetworks.com> wrote:
--snip--
> > +/*------------------------- 16 bit atomic operations -------------------------*/
> > +
> > +#ifndef RTE_FORCE_INTRINSICS
> > +static inline int
> > +rte_atomic16_cmpset(volatile uint16_t *dst, uint16_t exp, uint16_t src)
> > +{
> > + return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
> > + __ATOMIC_ACQUIRE) ? 1 : 0;
> > +}
>
> IMO, it should be __ATOMIC_SEQ_CST be instead of __ATOMIC_ACQUIRE.
> __ATOMIC_ACQUIRE works in conjunction with __ATOMIC_RELEASE.
> AFAIK, DPDK atomic api expects full barrier. C11 memory model not yet
> used.
Seems to be reasonable, thanks.
> So why can't we use RTE_FORCE_INTRINSICS based generic
> implementation. Same holds true for spinlock implementation too(i.e using
> RTE_FORCE_INTRINSICS). Am I missing something here ?
True. This was done with the intention to rewrite as a platform-specific
assembly. But it's never been done yet... If you mean to set
RTE_FORCE_INTRINSICS=y in the defconfig and remove this code entirely
(at least for ARMv7), I would agree.
>
>
>
> > +
> > +static inline int rte_atomic16_test_and_set(rte_atomic16_t *v)
> > +{
> > + return rte_atomic16_cmpset((volatile uint16_t *)&v->cnt, 0, 1);
> > +}
--snip--
--
Jan Viktorin E-mail: Viktorin@RehiveTech.com
System Architect Web: www.RehiveTech.com
RehiveTech
Brno, Czech Republic
next prev parent reply other threads:[~2015-11-02 13:02 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-29 17:29 [dpdk-dev] [PATCH 0/5] ARMv8 additions to ARMv7 support David Hunt
2015-10-29 17:29 ` [dpdk-dev] [PATCH 1/5] eal: split arm rte_memcpy.h into 32-bit and 64-bit versions David Hunt
2015-10-29 17:29 ` [dpdk-dev] [PATCH 2/5] eal: split arm rte_prefetch.h " David Hunt
2015-10-29 17:29 ` [dpdk-dev] [PATCH 3/5] eal: fix compilation for armv8 64-bit David Hunt
2015-10-29 17:38 ` Jan Viktorin
2015-10-29 17:29 ` [dpdk-dev] [PATCH 4/5] mk: add support for armv8 on top of armv7 David Hunt
2015-10-29 17:39 ` Jan Viktorin
2015-10-29 17:42 ` Jan Viktorin
2015-10-29 17:29 ` [dpdk-dev] [PATCH 5/5] test: add checks for cpu flags on armv8 David Hunt
2015-10-29 18:27 ` [dpdk-dev] [PATCH 0/5] ARMv8 additions to ARMv7 support Thomas Monjalon
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 00/15] Support ARMv7 architecture Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 01/15] eal/arm: atomic operations for ARM Jan Viktorin
2015-11-02 5:53 ` Jerin Jacob
2015-11-02 13:00 ` Jan Viktorin [this message]
2015-11-02 13:10 ` Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 02/15] eal/arm: byte order " Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 03/15] eal/arm: cpu cycle " Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 04/15] eal/arm: implement rdtsc by PMU or clock_gettime Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 05/15] eal/arm: prefetch operations for ARM Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 06/15] eal/arm: spinlock operations for ARM (without HTM) Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 07/15] eal/arm: vector memcpy for ARM Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 08/15] eal/arm: use vector memcpy only when NEON is enabled Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 09/15] eal/arm: cpu flag checks for ARM Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 10/15] eal/arm: detect arm architecture in cpu flags Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 11/15] eal/arm: rwlock support for ARM Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 12/15] eal/arm: add very incomplete rte_vect Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 13/15] gcc/arm: avoid alignment errors to break build Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 14/15] mk: Introduce ARMv7 architecture Jan Viktorin
2015-10-30 0:25 ` [dpdk-dev] [PATCH v5 15/15] maintainers: claim responsibility for ARMv7 Jan Viktorin
2015-10-30 0:17 ` [dpdk-dev] [PATCH 0/5] ARMv8 additions to ARMv7 support Jan Viktorin
2015-10-30 8:52 ` Hunt, David
2015-10-30 10:48 ` Jan Viktorin
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=20151102140054.3cbe88c2@pcviktorin.fit.vutbr.cz \
--to=viktorin@rehivetech.com \
--cc=dev@dpdk.org \
--cc=jerin.jacob@caviumnetworks.com \
--cc=kosar@rehivetech.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).