mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Garg, Shivank" <shivankg@amd.com>
To: "andreas@gaisler.com" <andreas@gaisler.com>,
	"dev.jain@arm.com" <dev.jain@arm.com>,
	"david@kernel.org" <david@kernel.org>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"hughd@google.com" <hughd@google.com>,
	"ljs@kernel.org" <ljs@kernel.org>,
	"chrisl@kernel.org" <chrisl@kernel.org>,
	"kasong@tencent.com" <kasong@tencent.com>,
	"davem@davemloft.net" <davem@davemloft.net>
Cc: "geert@linux-m68k.org" <geert@linux-m68k.org>,
	"rppt@kernel.org" <rppt@kernel.org>,
	"nphamcs@gmail.com" <nphamcs@gmail.com>,
	"shikemeng@huaweicloud.com" <shikemeng@huaweicloud.com>,
	"vbabka@kernel.org" <vbabka@kernel.org>,
	"harry@kernel.org" <harry@kernel.org>,
	"riel@surriel.com" <riel@surriel.com>,
	"anshuman.khandual@arm.com" <anshuman.khandual@arm.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"surenb@google.com" <surenb@google.com>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"youngjun.park@lge.com" <youngjun.park@lge.com>,
	"sparclinux@vger.kernel.org" <sparclinux@vger.kernel.org>,
	"ryan.roberts@arm.com" <ryan.roberts@arm.com>,
	"jannh@google.com" <jannh@google.com>,
	"liam@infradead.org" <liam@infradead.org>,
	"baolin.wang@linux.alibaba.com" <baolin.wang@linux.alibaba.com>,
	"mhocko@suse.com" <mhocko@suse.com>,
	"lance.yang@linux.dev" <lance.yang@linux.dev>,
	"baohua@kernel.org" <baohua@kernel.org>,
	"baoquan.he@linux.dev" <baoquan.he@linux.dev>,
	"pfalcato@suse.de" <pfalcato@suse.de>
Subject: Re: [PATCH v4 0/9] Optimize anonymous swapbacked large folio unmapping
Date: Tue, 17 Nov 2026 16:49:05 +0000	[thread overview]
Message-ID: <4c351ae2672a817df071b5a8b6b402846b897a75.camel@amd.com> (raw)
In-Reply-To: <20261115143905.3045084-1-dev.jain@arm.com>

On Sun, 2026-11-15 at 14:38 +0000, Dev Jain wrote:
> Speed up unmapping of anonymous swapbacked large folios by clearing
> the ptes, and setting swap ptes, in one go.
> 
> The following benchmark (stolen from Barry) is used to measure the
> time taken to swapout 256M worth of memory backed by 64K large folios:
> 
>  #define _GNU_SOURCE
>  #include <stdio.h>
>  #include <stdlib.h>
>  #include <sys/mman.h>
>  #include <string.h>
>  #include <time.h>
>  #include <unistd.h>
>  #include <errno.h>
> 
>  #define SIZE_MB 256
>  #define SIZE_BYTES (SIZE_MB * 1024 * 1024)
> 
>  int main() {
>      void *addr = mmap(NULL, SIZE_BYTES, PROT_READ | PROT_WRITE,
>                        MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
>      if (addr == MAP_FAILED) {
>          perror("mmap failed");
>          return 1;
>      }
> 
>      memset(addr, 0, SIZE_BYTES);
> 
>      struct timespec start, end;
>      clock_gettime(CLOCK_MONOTONIC, &start);
> 
>      if (madvise(addr, SIZE_BYTES, MADV_PAGEOUT) != 0) {
>          perror("madvise(MADV_PAGEOUT) failed");
>          munmap(addr, SIZE_BYTES);
>          return 1;
>      }
> 
>      clock_gettime(CLOCK_MONOTONIC, &end);
> 
>      long duration_ns = (end.tv_sec - start.tv_sec) * 1e9 +
>                         (end.tv_nsec - start.tv_nsec);
>      printf("madvise(MADV_PAGEOUT) took %ld ns (%.3f ms)\n",
>             duration_ns, duration_ns / 1e6);
> 
>      munmap(addr, SIZE_BYTES);
>      return 0;
>  }
> 
> Performance as measured on a Linux VM on Apple M3 (arm64):
> 
> Vanilla - Mean: 37401913 ns, std dev: 12%
> Patched - Mean: 17420282 ns, std dev: 11%
> 
> resulting in more than 2x speedup.
> 
> No regression observed on 4K folios.
> 
> Performance as measured on bare metal x86:
> 
> Vanilla - mean: 54986286 ns, std dev: 1.5%
> Patched - mean: 51930795 ns, std dev: 3%
> 
> I tried magnifying the difference on x86 by using 1M large folios, but
> can't spot an obvious improvement (looks like my system is too fast to
> benefit from batched atomic operations!), hinting that the benefit lies
> mainly in the reduction of ptep_get() calls and the reduction of TLB
> flushes during contpte-unfolding, on arm64.
> 
> No regression is observed on 4K folios on x86 too.
> 
> ---
> Applies on mm-unstable (24231596edf2).

Hi Dev,

Most of this series touches rmap and core MM code, which now go
through the new MM core tree:

T: git://git.kernel.org/pub/scm/linux/kernel/git/mm/core.git for-next

So, it would probably be better to base the next version on this rather than mm-unstable.

Thanks,
Shivank

> 
> mm-selftests pass.
> 
> This breakout patchset is the final completion of
> https://lore.kernel.org/all/20260526063635.61721-1-dev.jain@arm.com/
> 
> The extra addition is the generic set_softleaf_ptes() helper.
> 
> v3->v4:
>  - Make page_anon_exclusive_batch return the exclusivity instead of
>    computing that in the caller
>  - Make ttu_anon_folio() return the number of unmapped pages, to simplify
>    the code
> 
> v2->v3:
>  - page_anon_exclusive_batch returns unsigned long, shift to rmap.h
>  - Drop a para in description of patch 5, use softleaf_is_swap to gate
>    pte_swp_exclusive
>  - finish_folio_unmap -> finish_folio_unmap_batch
>  - Add patch 9 to do batching for sparc
>    
> v1->v2:
>  - Add WARNs for folio span in folio_*_swap_pages
>  - Trivial changes to page_anon_exclusive_batch
>  - Add two sanity checks in patch 4
> 
> Dev Jain (9):
>   mm/swapfile: add batched version of folio_dup_swap
>   mm/swapfile: add batched version of folio_put_swap
>   mm: move anon-exclusive batch helper to rmap.h
>   mm/rmap: Add batched version of folio_try_share_anon_rmap_pte
>   mm/internal: rename swap offset helpers to softleaf offset
>   mm/internal: add set_softleaf_ptes
>   mm/memory: use set_softleaf_ptes for uffd-wp markers
>   mm/rmap: batch unmap anonymous swap-backed large folios
>   mm, sparc: batch arch_unmap_one()
> 
>  arch/sparc/include/asm/pgtable_64.h |  10 ++-
>  arch/sparc/kernel/adi_64.c          |  21 +++++
>  include/linux/pgtable.h             |   6 +-
>  include/linux/rmap.h                |  76 ++++++++++++++----
>  mm/internal.h                       |  64 +++++++++++----
>  mm/memory.c                         |  23 +++---
>  mm/mprotect.c                       |  25 +-----
>  mm/rmap.c                           | 119 ++++++++++++++++++++--------
>  mm/shmem.c                          |   8 +-
>  mm/swap.h                           |  35 +++++++-
>  mm/swapfile.c                       |  39 +++++----
>  11 files changed, 289 insertions(+), 137 deletions(-)

      parent reply	other threads:[~2026-11-17 16:49 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-15 14:38 Dev Jain
2026-11-15 14:38 ` [PATCH v4 1/9] mm/swapfile: add batched version of folio_dup_swap Dev Jain
2026-11-15 14:38 ` [PATCH v4 2/9] mm/swapfile: add batched version of folio_put_swap Dev Jain
2026-11-15 14:38 ` [PATCH v4 3/9] mm: move anon-exclusive batch helper to rmap.h Dev Jain
2026-11-15 14:38 ` [PATCH v4 4/9] mm/rmap: Add batched version of folio_try_share_anon_rmap_pte Dev Jain
2026-11-15 14:39 ` [PATCH v4 5/9] mm/internal: rename swap offset helpers to softleaf offset Dev Jain
2026-11-15 14:39 ` [PATCH v4 6/9] mm/internal: add set_softleaf_ptes Dev Jain
2026-11-15 14:39 ` [PATCH v4 7/9] mm/memory: use set_softleaf_ptes for uffd-wp markers Dev Jain
2026-11-15 14:39 ` [PATCH v4 8/9] mm/rmap: batch unmap anonymous swap-backed large folios Dev Jain
2026-11-15 14:39 ` [PATCH v4 9/9] mm, sparc: batch arch_unmap_one() Dev Jain
2026-11-17 16:49 ` Garg, Shivank [this message]

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=4c351ae2672a817df071b5a8b6b402846b897a75.camel@amd.com \
    --to=shivankg@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=andreas@gaisler.com \
    --cc=anshuman.khandual@arm.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=baoquan.he@linux.dev \
    --cc=chrisl@kernel.org \
    --cc=davem@davemloft.net \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=geert@linux-m68k.org \
    --cc=harry@kernel.org \
    --cc=hughd@google.com \
    --cc=jannh@google.com \
    --cc=kasong@tencent.com \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@suse.com \
    --cc=nphamcs@gmail.com \
    --cc=pfalcato@suse.de \
    --cc=riel@surriel.com \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=shikemeng@huaweicloud.com \
    --cc=sparclinux@vger.kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --cc=youngjun.park@lge.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

all inboxes | Powered by JetHome®