From: Minchan Kim <minchan@kernel.org>
To: akpm@linux-foundation.org
Cc: hca@linux.ibm.com, linux-s390@vger.kernel.org, david@kernel.org,
mhocko@suse.com, brauner@kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, surenb@google.com,
timmurray@google.com, Minchan Kim <minchan@google.com>,
Minchan Kim <minchan@kernel.org>
Subject: [PATCH v1 2/3] mm: process_mrelease: skip LRU movement for exclusive file folios
Date: Tue, 21 Apr 2026 16:02:38 -0700 [thread overview]
Message-ID: <20260421230239.172582-3-minchan@kernel.org> (raw)
In-Reply-To: <20260421230239.172582-1-minchan@kernel.org>
For the process_mrelease reclaim, skip LRU handling for exclusive
file-backed folios since they will be freed soon so pointless
to move around in the LRU.
This avoids costly LRU movement which accounts for a significant portion
of the time during unmap_page_range.
- 91.31% 0.00% mmap_exit_test [kernel.kallsyms] [.] exit_mm
exit_mm
__mmput
exit_mmap
unmap_vmas
- unmap_page_range
- 55.75% folio_mark_accessed
+ 48.79% __folio_batch_add_and_move
4.23% workingset_activation
+ 12.94% folio_remove_rmap_ptes
+ 9.86% page_table_check_clear
+ 3.34% tlb_flush_mmu
1.06% __page_table_check_pte_clear
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
mm/memory.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/mm/memory.c b/mm/memory.c
index 2f815a34d924..fcb57630bb8d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1640,6 +1640,8 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
bool delay_rmap = false;
if (!folio_test_anon(folio)) {
+ bool skip_mark_accessed;
+
ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm);
if (pte_dirty(ptent)) {
folio_mark_dirty(folio);
@@ -1648,7 +1650,16 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
*force_flush = true;
}
}
- if (pte_young(ptent) && likely(vma_has_recency(vma)))
+
+ /*
+ * For the process_mrelease reclaim, skip LRU handling for exclusive
+ * file-backed folios since they will be freed soon so pointless
+ * to move around in the LRU.
+ */
+ skip_mark_accessed = mm_flags_test(MMF_UNSTABLE, mm) &&
+ !folio_maybe_mapped_shared(folio);
+ if (likely(!skip_mark_accessed) && pte_young(ptent) &&
+ likely(vma_has_recency(vma)))
folio_mark_accessed(folio);
rss[mm_counter(folio)] -= nr;
} else {
--
2.54.0.rc1.555.g9c883467ad-goog
next prev parent reply other threads:[~2026-04-21 23:02 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-21 23:02 [PATCH v1 0/3] mm: process_mrelease: expedite clean file folio reclaim and add auto-kill Minchan Kim
2026-04-21 23:02 ` [PATCH v1 1/3] mm: process_mrelease: expedite clean file folio reclaim via mmu_gather Minchan Kim
2026-04-24 7:56 ` David Hildenbrand (Arm)
2026-04-24 21:24 ` Minchan Kim
2026-04-27 9:29 ` David Hildenbrand (Arm)
2026-04-27 22:04 ` Minchan Kim
2026-04-24 19:33 ` Matthew Wilcox
2026-04-24 21:56 ` Minchan Kim
2026-05-05 14:53 ` Alexander Gordeev
2026-05-08 21:56 ` Minchan Kim
2026-05-11 16:13 ` Alexander Gordeev
2026-05-11 21:48 ` Minchan Kim
2026-04-21 23:02 ` Minchan Kim [this message]
2026-04-22 7:22 ` [PATCH v1 2/3] mm: process_mrelease: skip LRU movement for exclusive file folios Baolin Wang
2026-04-23 23:38 ` Minchan Kim
2026-04-24 7:51 ` Michal Hocko
2026-04-24 7:57 ` David Hildenbrand (Arm)
2026-04-24 19:15 ` Minchan Kim
2026-04-27 7:16 ` Michal Hocko
2026-04-27 16:48 ` Suren Baghdasaryan
2026-04-27 17:15 ` Michal Hocko
2026-04-27 23:05 ` Minchan Kim
2026-04-28 6:56 ` Michal Hocko
2026-04-29 1:19 ` Minchan Kim
2026-04-29 8:18 ` Michal Hocko
2026-04-29 9:09 ` David Hildenbrand (Arm)
2026-04-29 10:33 ` Michal Hocko
2026-04-29 13:07 ` David Hildenbrand (Arm)
2026-04-29 14:44 ` Michal Hocko
2026-04-30 6:08 ` David Hildenbrand (Arm)
2026-05-08 20:57 ` Liam R. Howlett
2026-05-11 13:05 ` David Hildenbrand (Arm)
2026-05-13 6:47 ` Michal Hocko
2026-04-29 21:41 ` Minchan Kim
2026-04-30 14:38 ` David Hildenbrand (Arm)
2026-04-29 8:55 ` David Hildenbrand (Arm)
2026-04-29 21:42 ` Minchan Kim
2026-04-24 19:26 ` Minchan Kim
2026-04-21 23:02 ` [PATCH v1 3/3] mm: process_mrelease: introduce PROCESS_MRELEASE_REAP_KILL flag Minchan Kim
2026-04-24 7:57 ` Michal Hocko
2026-04-24 22:49 ` Minchan Kim
2026-04-27 7:02 ` Michal Hocko
2026-04-27 22:03 ` Minchan Kim
2026-04-28 7:01 ` Michal Hocko
2026-04-28 22:37 ` Minchan Kim
2026-04-29 8:25 ` Michal Hocko
2026-04-29 20:01 ` Suren Baghdasaryan
2026-04-29 21:17 ` Minchan Kim
2026-04-29 21:16 ` Minchan Kim
2026-04-27 20:34 ` Suren Baghdasaryan
2026-04-27 22:52 ` Minchan Kim
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=20260421230239.172582-3-minchan@kernel.org \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=david@kernel.org \
--cc=hca@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=minchan@google.com \
--cc=surenb@google.com \
--cc=timmurray@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.