From: Stephen Hemminger <stephen@networkplumber.org>
To: Konstantin Ananyev <konstantin.ananyev@huawei.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
Wathsala Vithanage <wathsala.vithanage@arm.com>
Subject: Re: [PATCH v4 03/27] ring: unify memory model on C11, remove atomic32
Date: Mon, 1 Jun 2026 14:18:52 -0700 [thread overview]
Message-ID: <20260601141852.78c3cc79@phoenix.local> (raw)
In-Reply-To: <b8523a4e0ee34e8b9194935574e86f7c@huawei.com>
On Mon, 1 Jun 2026 18:18:18 +0000
Konstantin Ananyev <konstantin.ananyev@huawei.com> wrote:
> > +
> > + /* check that we have enough room in ring */
> > + if (unlikely(n > *entries))
> > + n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries;
> > +
> > + if (n > 0) {
> > + *new_head = *old_head + n;
> > + d->head = *new_head;
>
> There is a bit of inconsistency with the 'load' operation above:
> If we use atomic_load(&d->head. ...) then it would be better to use
> atomic_store(&d->head,..., order_relaxed) here.
>
Will switch to atomic_store, with relaxed.
It generates same code on x86 and ARM as simple store.
And makes C11 checkers happy.
next prev parent reply other threads:[~2026-06-01 21:18 UTC|newest]
Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-21 4:17 [RFC 0/7] prepare deprecation of rte_atomicNN_*() family Stephen Hemminger
2026-05-21 4:17 ` [RFC 1/7] doc: update versions in deprecation file Stephen Hemminger
2026-05-21 4:17 ` [RFC 2/7] eal: reimplement rte_smp_*mb with rte_atomic_thread_fence Stephen Hemminger
2026-05-21 15:43 ` Wathsala Vithanage
2026-05-21 4:17 ` [RFC 3/7] ring: use C11 atomic operations for MP/SP head/tail Stephen Hemminger
2026-05-21 15:57 ` Wathsala Vithanage
2026-05-21 4:17 ` [RFC 4/7] net/zxdh: work around GCC bitfield uninit false positive Stephen Hemminger
2026-05-21 4:17 ` [RFC 5/7] net/bonding: use stdatomic Stephen Hemminger
2026-05-21 4:17 ` [RFC 6/7] net/nbl: remove unused rte_atomic16 field Stephen Hemminger
2026-05-21 4:17 ` [RFC 7/7] config: use RTE_FORCE_INTRINSICS on all platforms Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 00/11] prepare deprecation of rte_atomicNN_*() family Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 01/11] eal: use intrinsics for rte_atomic on all platforms Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 02/11] eal: reimplement rte_smp_*mb with rte_atomic_thread_fence Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 03/11] ring: use C11 atomic operations for MP/SP head/tail Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 04/11] net/bonding: use stdatomic Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 05/11] net/nbl: remove unused rte_atomic16 field Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 06/11] net/ena: replace use of rte_atomicNN Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 07/11] net/failsafe: convert to stdatomic Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 08/11] net/enic: do not use deprecated rte_atomic64 Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 09/11] net/pfe: use ethdev linkstatus helpers Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 10/11] net/sfc: replace rte_atomic with stdatomic Stephen Hemminger
2026-05-21 18:04 ` [RFC v2 11/11] crypto/ccp: replace use of rte_atomic64 " Stephen Hemminger
2026-05-22 14:19 ` [RFC v2 00/11] prepare deprecation of rte_atomicNN_*() family Bruce Richardson
2026-05-22 14:45 ` Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 00/27] deprecate rte_atomicNN family Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 01/27] eal: use intrinsics for rte_atomic on all platforms Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 02/27] eal: reimplement rte_smp_*mb with rte_atomic_thread_fence Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 03/27] ring: use compare-and-swap wrapper Stephen Hemminger
2026-05-25 7:41 ` Konstantin Ananyev
2026-05-25 14:31 ` Stephen Hemminger
2026-05-25 15:35 ` Stephen Hemminger
2026-05-25 15:47 ` Morten Brørup
2026-05-23 19:16 ` [PATCH v3 04/27] bpf: replace atomic op macro with typed helpers Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 05/27] net/bonding: use stdatomic Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 06/27] net/nbl: remove unused rte_atomic16 field Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 07/27] net/ena: replace use of rte_atomicNN Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 08/27] net/failsafe: convert to stdatomic Stephen Hemminger
2026-05-23 19:16 ` [PATCH v3 09/27] net/enic: do not use deprecated rte_atomic64 Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 00/27] deprecate rte_atomicNN family Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 01/27] eal: use intrinsics for rte_atomic on all platforms Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 02/27] eal: reimplement rte_smp_*mb with rte_atomic_thread_fence Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 03/27] ring: use compare-and-swap wrapper Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 04/27] bpf: replace atomic op macro with typed helpers Stephen Hemminger
2026-05-25 10:49 ` Marat Khalili
2026-05-23 19:56 ` [PATCH v3 05/27] net/bonding: use stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 06/27] net/nbl: remove unused rte_atomic16 field Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 07/27] net/ena: replace use of rte_atomicNN Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 08/27] net/failsafe: convert to stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 09/27] net/enic: do not use deprecated rte_atomic64 Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 10/27] net/pfe: use ethdev linkstatus helpers Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 11/27] net/sfc: replace rte_atomic with stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 12/27] crypto/ccp: replace use of rte_atomic64 " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 13/27] bus/dpaa: replace rte_atomic16 " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 14/27] drivers: " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 15/27] net/netvsc: replace rte_atomic32 " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 16/27] event/sw: convert from rte_atomic32 to stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 17/27] bus/vmbus: convert from rte_atomic " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 18/27] common/dpaax: remove unused atomic macros Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 19/27] net/bnx2x: convert from rte_atomic32 to stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 20/27] bus/fslmc: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 21/27] drivers/event: replace rte_atomic32 in selftests Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 22/27] net/hinic: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 23/27] net/txgbe: " Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 24/27] net/vhost: use stdatomic instead of rte_atomic32 Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 25/27] vdpa/ifc: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 26/27] test/atomic: suppress deprecation warnings for legacy APIs Stephen Hemminger
2026-05-23 19:56 ` [PATCH v3 27/27] eal: mark rte_atomicNN as deprecated Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 00/27] deprecate rte_atomicNN family Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 01/27] eal: use intrinsics for rte_atomic on all platforms Stephen Hemminger
2026-06-01 18:23 ` Konstantin Ananyev
2026-05-26 23:23 ` [PATCH v4 02/27] eal: reimplement rte_smp_*mb with rte_atomic_thread_fence Stephen Hemminger
2026-06-01 18:24 ` Konstantin Ananyev
2026-05-26 23:23 ` [PATCH v4 03/27] ring: unify memory model on C11, remove atomic32 Stephen Hemminger
2026-06-01 18:18 ` Konstantin Ananyev
2026-06-01 21:05 ` Stephen Hemminger
2026-06-01 21:18 ` Stephen Hemminger [this message]
2026-06-01 22:07 ` Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 04/27] bpf: use C11 atomics in BPF_ST_ATOMIC_REG Stephen Hemminger
2026-05-27 16:52 ` Marat Khalili
2026-05-26 23:23 ` [PATCH v4 05/27] net/bonding: use stdatomic Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 06/27] net/nbl: remove unused rte_atomic16 field Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 07/27] net/ena: replace use of rte_atomicNN Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 08/27] net/failsafe: convert to stdatomic Stephen Hemminger
2026-05-26 23:23 ` [PATCH v4 09/27] net/enic: do not use deprecated rte_atomic64 Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 10/27] net/pfe: use ethdev linkstatus helpers Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 11/27] net/sfc: replace rte_atomic with stdatomic Stephen Hemminger
2026-06-01 9:22 ` Andrew Rybchenko
2026-05-26 23:24 ` [PATCH v4 12/27] crypto/ccp: replace use of rte_atomic64 " Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 13/27] bus/dpaa: replace rte_atomic16 " Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 14/27] drivers: " Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 15/27] net/netvsc: replace rte_atomic32 " Stephen Hemminger
2026-05-27 0:29 ` [EXTERNAL] " Long Li
2026-05-31 16:35 ` Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 16/27] event/sw: convert from rte_atomic32 to stdatomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 17/27] bus/vmbus: convert from rte_atomic " Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 18/27] common/dpaax: use stdatomic instead of rte_atomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 19/27] net/bnx2x: convert from rte_atomic32 to stdatomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 20/27] bus/fslmc: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 21/27] drivers/event: replace rte_atomic32 in selftests Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 22/27] net/hinic: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 23/27] net/txgbe: " Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 24/27] net/vhost: use stdatomic instead of rte_atomic32 Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 25/27] vdpa/ifc: replace rte_atomic32 with stdatomic Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 26/27] test/atomic: suppress deprecation warnings for legacy APIs Stephen Hemminger
2026-05-26 23:24 ` [PATCH v4 27/27] eal: mark rte_atomicNN as deprecated Stephen Hemminger
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=20260601141852.78c3cc79@phoenix.local \
--to=stephen@networkplumber.org \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@huawei.com \
--cc=wathsala.vithanage@arm.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.