From: David Hildenbrand <david@redhat.com>
To: Zi Yan <ziy@nvidia.com>, Xu Lu <luxu.kernel@bytedance.com>
Cc: paul.walmsley@sifive.com, palmer@dabbelt.com,
aou@eecs.berkeley.edu, ardb@kernel.org, anup@brainfault.org,
atishp@atishpatra.org, xieyongji@bytedance.com,
lihangjing@bytedance.com, punit.agrawal@bytedance.com,
linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org,
Linux MM <linux-mm@kvack.org>
Subject: Re: [RFC PATCH v2 00/21] riscv: Introduce 64K base page
Date: Fri, 6 Dec 2024 11:13:16 +0100 [thread overview]
Message-ID: <315752c5-6129-4c8b-bf8c-0cc26f0ad5c5@redhat.com> (raw)
In-Reply-To: <F94D21C0-8189-404A-B796-BB3C6620AB89@nvidia.com>
On 06.12.24 03:00, Zi Yan wrote:
> On 5 Dec 2024, at 5:37, Xu Lu wrote:
>
>> This patch series attempts to break through the limitation of MMU and
>> supports larger base page on RISC-V, which only supports 4K page size
>> now. The key idea is to always manage and allocate memory at a
>> granularity of 64K and use SVNAPOT to accelerate address translation.
>> This is the second version and the detailed introduction can be found
>> in [1].
>>
>> Changes from v1:
>> - Rebase on v6.12.
>>
>> - Adjust the page table entry shift to reduce page table memory usage.
>> For example, in SV39, the traditional va behaves as:
>>
>> ----------------------------------------------
>> | pgd index | pmd index | pte index | offset |
>> ----------------------------------------------
>> | 38 30 | 29 21 | 20 12 | 11 0 |
>> ----------------------------------------------
>>
>> When we choose 64K as basic software page, va now behaves as:
>>
>> ----------------------------------------------
>> | pgd index | pmd index | pte index | offset |
>> ----------------------------------------------
>> | 38 34 | 33 25 | 24 16 | 15 0 |
>> ----------------------------------------------
>>
>> - Fix some bugs in v1.
>>
>> Thanks in advance for comments.
>>
>> [1] https://lwn.net/Articles/952722/
>
> This looks very interesting. Can you cc me and linux-mm@kvack.org
> in the future? Thanks.
>
> Have you thought about doing it for ARM64 4KB as well? ARM64’s contig PTE
> should have similar effect of RISC-V’s SVNAPOT, right?
What is the real benefit over 4k + large folios/mTHP?
64K comes with the problem of internal fragmentation: for example, a
page table that only occupies 4k of memory suddenly consumes 64K; quite
a downside.
--
Cheers,
David / dhildenb
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2024-12-06 10:17 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-05 10:37 [RFC PATCH v2 00/21] riscv: Introduce 64K base page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 01/21] riscv: mm: Distinguish hardware base page and software " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 02/21] riscv: mm: Configure satp with hw page pfn Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 03/21] riscv: mm: Reimplement page table entry structures Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 04/21] riscv: mm: Reimplement page table entry constructor function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 05/21] riscv: mm: Reimplement conversion functions between page table entry Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 06/21] riscv: mm: Avoid pte constructor during pte conversion Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 07/21] riscv: mm: Reimplement page table entry get function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 08/21] riscv: mm: Reimplement page table entry atomic " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 09/21] riscv: mm: Replace READ_ONCE with atomic pte " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 10/21] riscv: mm: Reimplement PTE A/D bit check function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 11/21] riscv: mm: Reimplement mk_huge_pte function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 12/21] riscv: mm: Reimplement tlb flush function Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 13/21] riscv: mm: Adjust PGDIR/P4D/PUD/PMD_SHIFT Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 14/21] riscv: mm: Only apply svnapot region bigger than software page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 15/21] riscv: mm: Adjust FIX_BTMAPS_SLOTS for variable PAGE_SIZE Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 16/21] riscv: mm: Adjust FIX_FDT_SIZE for variable PMD_SIZE Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 17/21] riscv: mm: Apply Svnapot for base page mapping if possible Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 18/21] riscv: Kconfig: Introduce 64K page size Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 19/21] riscv: Kconfig: Adjust mmap rnd bits for 64K Page Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 20/21] riscv: mm: Adjust address space layout and init page table " Xu Lu
2024-12-05 10:37 ` [RFC PATCH v2 21/21] riscv: mm: Update EXEC_PAGESIZE " Xu Lu
2024-12-06 2:00 ` [RFC PATCH v2 00/21] riscv: Introduce 64K base page Zi Yan
2024-12-06 2:41 ` [External] " Xu Lu
2024-12-06 10:13 ` David Hildenbrand [this message]
2024-12-06 13:42 ` Xu Lu
2024-12-06 18:48 ` Pedro Falcato
2024-12-07 8:03 ` Xu Lu
2024-12-07 22:02 ` Yu Zhao
2024-12-09 3:36 ` Xu Lu
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=315752c5-6129-4c8b-bf8c-0cc26f0ad5c5@redhat.com \
--to=david@redhat.com \
--cc=anup@brainfault.org \
--cc=aou@eecs.berkeley.edu \
--cc=ardb@kernel.org \
--cc=atishp@atishpatra.org \
--cc=lihangjing@bytedance.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-riscv@lists.infradead.org \
--cc=luxu.kernel@bytedance.com \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=punit.agrawal@bytedance.com \
--cc=xieyongji@bytedance.com \
--cc=ziy@nvidia.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