From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
To: Hugh Dickins <hughd@google.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: Ackerley Tng <ackerleytng@google.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Alexandre Ghiti <alex@ghiti.fr>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
Barry Song <baohua@kernel.org>,
Binbin Wu <binbin.wu@linux.intel.com>,
Christian Brauner <brauner@kernel.org>,
Christoph Hellwig <hch@lst.de>, Christoph Lameter <cl@gentwo.org>,
Claudio Imbrenda <imbrenda@linux.ibm.com>,
David Hildenbrand <david@kernel.org>,
JP Kobryn <jp.kobryn@linux.dev>, Jan Kara <jack@suse.cz>,
Jens Axboe <axboe@kernel.dk>,
Johannes Weiner <hannes@cmpxchg.org>,
Kairui Song <ryncsn@gmail.com>, Kiryl Shutsemau <kas@kernel.org>,
Lance Yang <lance.yang@linux.dev>,
Leonardo Bras <leobras.c@gmail.com>,
Lorenzo Stoakes <ljs@kernel.org>,
Marcelo Tosatti <mtosatti@redhat.com>,
Matthew Wilcox <willy@infradead.org>,
Mel Gorman <mgorman@techsingularity.net>,
Miaohe Lin <linmiaohe@huawei.com>, Michal Hocko <mhocko@suse.com>,
Minchan Kim <minchan@kernel.org>,
Muchun Song <muchun.song@linux.dev>,
Oscar Salvador <osalvador@suse.de>,
Peter Zijlstra <peterz@infradead.org>,
Qi Zheng <qi.zheng@linux.dev>, Rik van Riel <riel@surriel.com>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Shakeel Butt <shakeel.butt@linux.dev>,
Suren Baghdasaryan <surenb@google.com>,
Yang Shi <yang@os.amperecomputing.com>,
Yu Zhao <yuzhao@google.com>, Zach O'Keefe <zokeefe@google.com>,
Zi Yan <ziy@nvidia.com>,
linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH v2 06/26] mm/fbatch: fbatch_drain_lazyfree(onstack fbatch) before ptl unlock
Date: Wed, 9 Sep 2026 23:02:20 +0200 [thread overview]
Message-ID: <ac4fedf1-168f-4166-8059-353f2cbf04ae@kernel.org> (raw)
In-Reply-To: <17e1a6c3-525b-1cc3-0731-349f0850e3ea@google.com>
On 9/9/26 11:53, Hugh Dickins wrote:
> Re-enable lazyfree batching for MADV_FREE. But it's not safe now to leave
> potentially stale (then reused) folios in a per-cpu fbatch for lazyfree.
> Instead, madvise_free_pte_range() keep an fbatch on its stack, and drain
> it each time before dropping pagetable lock, while the folios are secure.
>
> Ignore folio_may_be_lru_cached() and lru_cache_disabled(): limitations
> irrelevant to this fbatch drained under spinlock (even if RT); though
> in practice madvise_free_huge_pmd() does have to drain every time.
>
> Signed-off-by: Hugh Dickins <hughd@google.com>
It seems correct to me, so:
Reviewed-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Might be that something regresses performance though. Guess we'll see.
Also seems to me that if this patch was preparatory, the batching wouldn't
have to be temporarily disabled. Doesn't matter ultimately though.
next prev parent reply other threads:[~2026-09-09 21:02 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-09 9:39 [PATCH v2 00/26] mm/fbatch: drain lru_add_drain() and _all() Hugh Dickins
2026-09-09 9:42 ` [PATCH v2 01/26] mm/fbatch: remove !CONFIG_SMP special case of folio_activate() Hugh Dickins
2026-09-09 9:44 ` [PATCH v2 02/26] mm/fbatch: allow folios_put_refs() to skip xa_is_value() entries Hugh Dickins
2026-09-09 9:46 ` [PATCH v2 03/26] mm/fbatch: temporarily disable lazyfree and mlock+munlock batching Hugh Dickins
2026-09-09 9:49 ` [PATCH v2 04/26] mm/fbatch: lru bit set, no extra ref, while folio on per-cpu fbatch Hugh Dickins
2026-09-09 12:25 ` Vlastimil Babka (SUSE)
2026-09-09 9:51 ` [PATCH v2 05/26] mm/fbatch: lru_add_del_folio()+folio_add_lru() after clear_lru() Hugh Dickins
2026-09-09 15:04 ` Vlastimil Babka (SUSE)
2026-09-09 9:53 ` [PATCH v2 06/26] mm/fbatch: fbatch_drain_lazyfree(onstack fbatch) before ptl unlock Hugh Dickins
2026-09-09 21:02 ` Vlastimil Babka (SUSE) [this message]
2026-09-09 9:55 ` [PATCH v2 07/26] mm/fbatch: LRU_NEXT_ACTIVATE bit to optimize folio_activate() Hugh Dickins
2026-09-10 12:01 ` Vlastimil Babka (SUSE)
2026-09-10 16:42 ` Kiryl Shutsemau
2026-09-09 9:57 ` [PATCH v2 08/26] mm/fbatch: replace mlock_new_folio() by __folio_add_lru(,mlockit) Hugh Dickins
2026-09-10 17:47 ` Vlastimil Babka (SUSE)
2026-09-09 9:59 ` [PATCH v2 09/26] mm/fbatch: restore mlock+munlock batching, without extra ref Hugh Dickins
2026-09-10 21:05 ` Vlastimil Babka (SUSE)
2026-09-09 10:01 ` [PATCH v2 10/26] mm/fbatch: remove several uses of mlock_drain_local() Hugh Dickins
2026-09-09 10:03 ` [PATCH v2 11/26] mm/fbatch: remove migration's PAGE_WAS_MLOCKED lru_add_drain() Hugh Dickins
2026-09-09 10:05 ` [PATCH v2 12/26] mm/fbatch: remove percpu_pvec_drained and folios_put() Hugh Dickins
2026-09-09 10:08 ` [PATCH v2 13/26] mm/fbatch: no lru_add_drain to collect_longterm_unpinnable_folios() Hugh Dickins
2026-09-09 10:10 ` [PATCH v2 14/26] mm/fbatch: no lru_add_drain() nor _all() for memfd_wait_for_pins() Hugh Dickins
2026-09-09 10:12 ` [PATCH v2 15/26] mm/fbatch: remove shake_folio() shake_page() from memory-failure Hugh Dickins
2026-09-09 10:14 ` [PATCH v2 16/26] mm/fbatch: remove lru_cache_disable() from NUMA folio migration Hugh Dickins
2026-09-09 10:16 ` [PATCH v2 17/26] mm/fbatch: no lru_cache_disable() in __alloc_contig_migrate_range() Hugh Dickins
2026-09-09 10:18 ` [PATCH v2 18/26] mm/fbatch: remove lru_add_drain() and _all() calls from various Hugh Dickins
2026-09-09 10:20 ` [PATCH v2 19/26] mm/fbatch: vm/stat_refresh include lru_add_drain() on each cpu Hugh Dickins
2026-09-09 10:23 ` [PATCH v2 20/26] s390/fbatch: no lru_add_drain_all() in s390_wiggle_split_folio() Hugh Dickins
2026-09-09 10:25 ` [PATCH v2 21/26] block/fbatch: no lru_add_drain_all() in invalidate_bdev() Hugh Dickins
2026-09-09 10:27 ` [PATCH v2 22/26] fs/fbatch: drop_caches invalidate_bh_lrus() not lru_add_drain_all() Hugh Dickins
2026-09-09 10:30 ` [PATCH v2 23/26] fs,mm/fbatch: use invalidate_bh_lrus() not invalidate_bh_lrus_cpu() Hugh Dickins
2026-09-09 10:33 ` [PATCH v2 24/26] fs,mm/fbatch: lru_cache_disable() keep off buffer_head lrus only Hugh Dickins
2026-09-09 10:35 ` [PATCH v2 25/26] mm/fbatch: move lru_add_drain_all() declaration to mm/internal.h Hugh Dickins
2026-09-09 10:37 ` [PATCH v2 26/26] mm/fbatch: drop reference inside the loop when draining Hugh Dickins
2026-09-09 10:41 ` [PATCH v2 27/26] mm/fbatch: paranoid folio vmstats in folio_batch_move_lru() Hugh Dickins
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=ac4fedf1-168f-4166-8059-353f2cbf04ae@kernel.org \
--to=vbabka@kernel.org \
--cc=ackerleytng@google.com \
--cc=akpm@linux-foundation.org \
--cc=alex@ghiti.fr \
--cc=axboe@kernel.dk \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=bigeasy@linutronix.de \
--cc=binbin.wu@linux.intel.com \
--cc=brauner@kernel.org \
--cc=cl@gentwo.org \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=hch@lst.de \
--cc=hughd@google.com \
--cc=imbrenda@linux.ibm.com \
--cc=jack@suse.cz \
--cc=jp.kobryn@linux.dev \
--cc=kas@kernel.org \
--cc=lance.yang@linux.dev \
--cc=leobras.c@gmail.com \
--cc=linmiaohe@huawei.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=minchan@kernel.org \
--cc=mtosatti@redhat.com \
--cc=muchun.song@linux.dev \
--cc=osalvador@suse.de \
--cc=peterz@infradead.org \
--cc=qi.zheng@linux.dev \
--cc=riel@surriel.com \
--cc=ryncsn@gmail.com \
--cc=shakeel.butt@linux.dev \
--cc=surenb@google.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
--cc=yang@os.amperecomputing.com \
--cc=yuzhao@google.com \
--cc=ziy@nvidia.com \
--cc=zokeefe@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 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®