From: "Morten Brørup" <mb@smartsharesystems.com>
To: "Stephen Hemminger" <stephen@networkplumber.org>
Cc: "Mattias Rönnblom" <hofors@lysator.liu.se>,
"Mattias Rönnblom" <mattias.ronnblom@ericsson.com>,
dev@dpdk.org, "Heng Wang" <heng.wang@ericsson.com>,
"Tyler Retzlaff" <roretzla@linux.microsoft.com>
Subject: RE: [RFC v7 3/6] eal: add exactly-once bit access functions
Date: Wed, 8 May 2024 18:16:59 +0200 [thread overview]
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35E9F430@smartserver.smartshare.dk> (raw)
In-Reply-To: <20240508081530.5d5c5d25@hermes.local>
> From: Stephen Hemminger [mailto:stephen@networkplumber.org]
> Sent: Wednesday, 8 May 2024 17.16
>
> On Wed, 8 May 2024 09:33:43 +0200
> Morten Brørup <mb@smartsharesystems.com> wrote:
>
> > > What more specifically did you have in mind? READ_ONCE() and
> > > WRITE_ONCE()? They give almost no guarantees. Very much relaxed.
> >
> > The way I read it, they do provide memory ordering guarantees.
> >
> > Ignore that the kernel's "once" functions operates on words and this RFC
> operates on bits, the behavior is the same. Either there are memory ordering
> guarantees, or there are not.
>
> The kernel's READ_ONCE/WRITE_ONCE are compiler only ordering, i.e only apply
> to single CPU.
> RTFM memory-barriers.txt..
>
> GUARANTEES
> ----------
>
> There are some minimal guarantees that may be expected of a CPU:
>
> (*) On any given CPU, dependent memory accesses will be issued in order, with
> respect to itself. This means that for:
>
> Q = READ_ONCE(P); D = READ_ONCE(*Q);
>
> the CPU will issue the following memory operations:
>
> Q = LOAD P, D = LOAD *Q
>
> and always in that order.
> However, on DEC Alpha, READ_ONCE() also
> emits a memory-barrier instruction, so that a DEC Alpha CPU will
> instead issue the following memory operations:
>
> Q = LOAD P, MEMORY_BARRIER, D = LOAD *Q, MEMORY_BARRIER
>
> Whether on DEC Alpha or not, the READ_ONCE() also prevents compiler
> mischief.
>
> (*) Overlapping loads and stores within a particular CPU will appear to be
> ordered within that CPU. This means that for:
>
> a = READ_ONCE(*X); WRITE_ONCE(*X, b);
>
> the CPU will only issue the following sequence of memory operations:
>
> a = LOAD *X, STORE *X = b
>
> And for:
>
> WRITE_ONCE(*X, c); d = READ_ONCE(*X);
>
> the CPU will only issue:
>
> STORE *X = c, d = LOAD *X
>
> (Loads and stores overlap if they are targeted at overlapping pieces of
> memory).
It says "*the CPU* will issue the following [sequence of] *memory operations*",
not "*the compiler* will generate the following *CPU instructions*".
To me, that reads like a memory ordering guarantee.
next prev parent reply other threads:[~2024-05-08 16:17 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-02 13:53 [RFC 0/7] Improve EAL bit operations API Mattias Rönnblom
2024-03-02 13:53 ` [RFC 1/7] eal: extend bit manipulation functions Mattias Rönnblom
2024-03-02 17:05 ` Stephen Hemminger
2024-03-03 6:26 ` Mattias Rönnblom
2024-03-04 16:34 ` Tyler Retzlaff
2024-03-05 18:01 ` Mattias Rönnblom
2024-03-05 18:06 ` Tyler Retzlaff
2024-04-25 8:58 ` [RFC v2 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-04-25 8:58 ` [RFC v2 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-04-29 11:12 ` Morten Brørup
2024-04-30 9:55 ` [RFC v4 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 0/6] Improve EAL bit operations API Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 1/6] eal: extend bit manipulation functionality Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-05-07 19:17 ` Morten Brørup
2024-05-08 6:47 ` Mattias Rönnblom
2024-05-08 7:33 ` Morten Brørup
2024-05-08 8:00 ` Mattias Rönnblom
2024-05-08 8:11 ` Morten Brørup
2024-05-08 9:27 ` Mattias Rönnblom
2024-05-08 10:08 ` Morten Brørup
2024-05-08 15:15 ` Stephen Hemminger
2024-05-08 16:16 ` Morten Brørup [this message]
2024-05-05 8:37 ` [RFC v7 4/6] eal: add unit tests for " Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-05-05 8:37 ` [RFC v7 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 4/6] eal: add unit tests for " Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-05-03 6:41 ` Mattias Rönnblom
2024-05-03 23:30 ` Tyler Retzlaff
2024-05-04 15:36 ` Mattias Rönnblom
2024-05-02 5:57 ` [RFC v6 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 4/6] eal: add unit tests for " Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-04-30 12:08 ` [RFC v5 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 4/6] eal: add unit tests for " Mattias Rönnblom
2024-04-30 10:37 ` Morten Brørup
2024-04-30 11:58 ` Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-04-30 9:55 ` [RFC v4 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 4/6] eal: add unit tests for " Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-04-29 9:51 ` [RFC v3 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-04-25 8:58 ` [RFC v2 2/6] eal: add unit tests for bit operations Mattias Rönnblom
2024-04-25 8:58 ` [RFC v2 3/6] eal: add exactly-once bit access functions Mattias Rönnblom
2024-04-25 8:58 ` [RFC v2 4/6] eal: add unit tests for " Mattias Rönnblom
2024-04-25 8:58 ` [RFC v2 5/6] eal: add atomic bit operations Mattias Rönnblom
2024-04-25 10:25 ` Morten Brørup
2024-04-25 14:36 ` Mattias Rönnblom
2024-04-25 16:18 ` Morten Brørup
2024-04-26 9:39 ` Mattias Rönnblom
2024-04-26 12:00 ` Morten Brørup
2024-04-28 15:37 ` Mattias Rönnblom
2024-04-29 7:24 ` Morten Brørup
2024-04-30 16:52 ` Tyler Retzlaff
2024-04-25 8:58 ` [RFC v2 6/6] eal: add unit tests for atomic bit access functions Mattias Rönnblom
2024-04-25 18:05 ` [RFC v2 0/6] Improve EAL bit operations API Tyler Retzlaff
2024-04-26 11:17 ` Mattias Rönnblom
2024-04-26 21:35 ` Patrick Robb
2024-03-02 13:53 ` [RFC 2/7] eal: add generic bit manipulation macros Mattias Rönnblom
2024-03-04 8:16 ` Heng Wang
2024-03-04 15:41 ` Mattias Rönnblom
2024-03-04 16:42 ` Tyler Retzlaff
2024-03-05 18:08 ` Mattias Rönnblom
2024-03-05 18:22 ` Tyler Retzlaff
2024-03-05 20:02 ` Mattias Rönnblom
2024-03-05 20:53 ` Tyler Retzlaff
2024-03-02 13:53 ` [RFC 3/7] eal: add bit manipulation functions which read or write once Mattias Rönnblom
2024-03-02 13:53 ` [RFC 4/7] eal: add generic once-type bit operations macros Mattias Rönnblom
2024-03-02 13:53 ` [RFC 5/7] eal: add atomic bit operations Mattias Rönnblom
2024-03-02 13:53 ` [RFC 6/7] eal: add generic " Mattias Rönnblom
2024-03-02 13:53 ` [RFC 7/7] eal: deprecate relaxed family of " Mattias Rönnblom
2024-03-02 17:07 ` Stephen Hemminger
2024-03-03 6:30 ` Mattias Rönnblom
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=98CBD80474FA8B44BF855DF32C47DC35E9F430@smartserver.smartshare.dk \
--to=mb@smartsharesystems.com \
--cc=dev@dpdk.org \
--cc=heng.wang@ericsson.com \
--cc=hofors@lysator.liu.se \
--cc=mattias.ronnblom@ericsson.com \
--cc=roretzla@linux.microsoft.com \
--cc=stephen@networkplumber.org \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).