From: Peter Zijlstra <peterz@infradead.org>
To: Nadav Amit <nadav.amit@gmail.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Hugh Dickins <hughd@google.com>,
Andy Lutomirski <luto@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Nadav Amit <namit@vmware.com>,
Sean Christopherson <seanjc@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
x86@kernel.org
Subject: Re: [RFC 0/6] x86: prefetch_page() vDSO call
Date: Thu, 25 Feb 2021 09:40:07 +0100 [thread overview]
Message-ID: <YDdiZ1SFRrvRPhkR@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20210225072910.2811795-1-namit@vmware.com>
On Wed, Feb 24, 2021 at 11:29:04PM -0800, Nadav Amit wrote:
> From: Nadav Amit <namit@vmware.com>
>
> Just as applications can use prefetch instructions to overlap
> computations and memory accesses, applications may want to overlap the
> page-faults and compute or overlap the I/O accesses that are required
> for page-faults of different pages.
>
> Applications can use multiple threads and cores for this matter, by
> running one thread that prefetches the data (i.e., faults in the data)
> and another that does the compute, but this scheme is inefficient. Using
> mincore() can tell whether a page is mapped, but might not tell whether
> the page is in the page-cache and does not fault in the data.
>
> Introduce prefetch_page() vDSO-call to prefetch, i.e. fault-in memory
> asynchronously. The semantic of this call is: try to prefetch a page of
> in a given address and return zero if the page is accessible following
> the call. Start I/O operations to retrieve the page if such operations
> are required and there is no high memory pressure that might introduce
> slowdowns.
>
> Note that as usual the page might be paged-out at any point and
> therefore, similarly to mincore(), there is no guarantee that the page
> will be present at the time that the user application uses the data that
> resides on the page. Nevertheless, it is expected that in the vast
> majority of the cases this would not happen, since prefetch_page()
> accesses the page and therefore sets the PTE access-bit (if it is
> clear).
>
> The implementation is as follows. The vDSO code accesses the data,
> triggering a page-fault it is not present. The handler detects based on
> the instruction pointer that this is an asynchronous-#PF, using the
> recently introduce vDSO exception tables. If the page can be brought
> without waiting (e.g., the page is already in the page-cache), the
> kernel handles the fault and returns success (zero). If there is memory
> pressure that prevents the proper handling of the fault (i.e., requires
> heavy-weight reclamation) it returns a failure. Otherwise, it starts an
> I/O to bring the page and returns failure.
>
> Compilers can be extended to issue the prefetch_page() calls when
> needed.
Interesting, but given we've been removing explicit prefetch from some
parts of the kernel how useful is this in actual use? I'm thinking there
should at least be a real user and performance numbers with this before
merging.
next prev parent reply other threads:[~2021-02-25 8:40 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-25 7:29 [RFC 0/6] x86: prefetch_page() vDSO call Nadav Amit
2021-02-25 7:29 ` [RFC 1/6] vdso/extable: fix calculation of base Nadav Amit
2021-02-25 21:16 ` Sean Christopherson
2021-02-26 17:24 ` Nadav Amit
2021-02-26 17:47 ` Sean Christopherson
2021-02-28 9:20 ` Nadav Amit
2021-02-25 7:29 ` [RFC 2/6] x86/vdso: add mask and flags to extable Nadav Amit
2021-02-25 7:29 ` [RFC 3/6] x86/vdso: introduce page_prefetch() Nadav Amit
2021-02-25 7:29 ` [RFC 4/6] mm/swap_state: respect FAULT_FLAG_RETRY_NOWAIT Nadav Amit
2021-02-25 7:29 ` [RFC 5/6] mm: use lightweight reclaim on FAULT_FLAG_RETRY_NOWAIT Nadav Amit
2021-02-25 7:29 ` [PATCH 6/6] testing/selftest: test vDSO prefetch_page() Nadav Amit
2021-02-25 8:40 ` Peter Zijlstra [this message]
2021-02-25 8:52 ` [RFC 0/6] x86: prefetch_page() vDSO call Nadav Amit
2021-02-25 9:32 ` Nadav Amit
2021-02-25 9:55 ` Peter Zijlstra
2021-02-25 12:16 ` Matthew Wilcox
2021-02-25 16:56 ` Nadav Amit
2021-02-25 17:32 ` Matthew Wilcox
2021-02-25 17:53 ` Nadav Amit
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=YDdiZ1SFRrvRPhkR@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=bp@alien8.de \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=nadav.amit@gmail.com \
--cc=namit@vmware.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.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).