From: "Morten Brørup" <mb@smartsharesystems.com>
To: "Mattias Rönnblom" <hofors@lysator.liu.se>,
"Mattias Rönnblom" <mattias.ronnblom@ericsson.com>,
dev@dpdk.org
Cc: "Heng Wang" <heng.wang@ericsson.com>,
"Stephen Hemminger" <stephen@networkplumber.org>,
"Tyler Retzlaff" <roretzla@linux.microsoft.com>
Subject: RE: [RFC v7 3/6] eal: add exactly-once bit access functions
Date: Wed, 8 May 2024 10:11:42 +0200 [thread overview]
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35E9F429@smartserver.smartshare.dk> (raw)
In-Reply-To: <c423e568-6a9e-48b2-8edb-c2dd341ed922@lysator.liu.se>
> From: Mattias Rönnblom [mailto:hofors@lysator.liu.se]
> Sent: Wednesday, 8 May 2024 10.00
>
> On 2024-05-08 09:33, Morten Brørup wrote:
> >> From: Mattias Rönnblom [mailto:hofors@lysator.liu.se]
> >> Sent: Wednesday, 8 May 2024 08.47
> >>
> >> On 2024-05-07 21:17, Morten Brørup wrote:
> >>>> From: Mattias Rönnblom [mailto:mattias.ronnblom@ericsson.com]
> >>>> Sent: Sunday, 5 May 2024 10.38
> >>>>
> >>>> Add test/set/clear/assign/flip functions which prevents certain
> >>>> compiler optimizations and guarantees that program-level memory loads
> >>>> and/or stores will actually occur.
> >>>>
> >>>> These functions are useful when interacting with memory-mapped
> >>>> hardware devices.
> >>>>
> >>>> The "once" family of functions does not promise atomicity and provides
> >>>> no memory ordering guarantees beyond the C11 relaxed memory model.
> >>>
> >>> In another thread, Stephen referred to the extended discussion on memory
> >> models in Linux kernel documentation:
> >>> https://www.kernel.org/doc/html/latest/core-api/wrappers/memory-
> >> barriers.html
> >>>
> >>> Unlike the "once" family of functions in this RFC, the "once" family of
> >> functions in the kernel also guarantee memory ordering, specifically for
> >> memory-mapped hardware devices. The document describes the rationale with
> >> examples.
> >>>
> >>
> >> 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.
> >
>
> Sure. All types memory operations comes with some kind guarantees. A
> series of non-atomic, non-volatile stores issued by a particular thread
> are guaranteed to happen in program order, from the point of view of
> that thread, for example. Would be hard to write a program if that
> wasn't true.
>
> "This macro does not give any guarantees in regards to memory ordering /../"
>
> This is not true. I will rephrase to "any *additional* guarantees" for
> both plain and "once" family documentation.
Consider code like this:
set_once(HW_START_BIT);
while (!get_once(HW_DONE_BIT)) /*busy wait*/;
If the "once" functions are used for hardware access, they must guarantee that HW_START_BIT has been written before HW_DONE_BIT is read.
The documentation must reflect this ordering guarantee.
>
> > 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.
> >
> >>
> >> I've read that document.
> >>
> >> What you should keep in mind if you read that document, is that DPDK
> >> doesn't use the kernel's memory model, and doesn't have the kernel's
> >> barrier and atomics APIs. What we have are an obsolete, miniature
> >> look-alike in <rte_atomic.h> and something C11-like in <rte_stdatomic.h>.
> >>
> >> My general impression is that DPDK was moving in the C11 direction
> >> memory model-wise, which is not the model the kernel uses.
> >
> > I think you and I agree that using legacy methods only because "the kernel
> does it that way" would not be the optimal roadmap for DPDK.
> >
> > We should keep moving in the C11 direction memory model-wise.
> > I consider it more descriptive, and thus expect compilers to eventually
> produce better optimized code.
> >
> >>
> >>> It makes me think that DPDK "once" family of functions should behave
> >> similarly.
> >>
> >> I think they do already.
> >
> > I haven't looked deep into it, but the RFC's documentation says otherwise:
> > The "once" family of functions does not promise atomicity and provides *no
> memory ordering* guarantees beyond the C11 relaxed memory model.
> >
> >>
> >> Also, rte_bit_once_set() works as the kernel's __set_bit().
> >>
> >>> Alternatively, if the "once" family of functions cannot be generically
> >> implemented with a memory ordering that is optimal for all use cases, drop
> >> this family of functions, and instead rely on the "atomic" family of
> functions
> >> for interacting with memory-mapped hardware devices.
> >>>
> >>>>
> >>>> RFC v7:
> >>>> * Fix various minor issues in documentation.
> >>>>
> >>>> RFC v6:
> >>>> * Have rte_bit_once_test() accept const-marked bitsets.
> >>>>
> >>>> RFC v3:
> >>>> * Work around lack of C++ support for _Generic (Tyler Retzlaff).
> >>>>
> >>>> Signed-off-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
> >>>> Acked-by: Morten Brørup <mb@smartsharesystems.com>
> >>>> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> >>>> ---
> >>>
next prev parent reply other threads:[~2024-05-08 8:11 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 [this message]
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
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=98CBD80474FA8B44BF855DF32C47DC35E9F429@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 NNTP newsgroup(s).