| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAJD7tkYJ=xKvRxGKm3bsXy9_yO+fz1wYZcBO-XiAJjRacJsdQg@mail.gmail.com>
Date: Thu, 9 Mar 2023 01:39:02 -0800
From: Yosry Ahmed <yosryahmed@...gle.com>
To: Alexander Viro <viro@...iv.linux.org.uk>,
"Darrick J. Wong" <djwong@...nel.org>,
Christoph Lameter <cl@...ux.com>,
David Rientjes <rientjes@...gle.com>,
Joonsoo Kim <iamjoonsoo.kim@....com>,
Vlastimil Babka <vbabka@...e.cz>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Hyeonggon Yoo <42.hyeyoo@...il.com>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
Miaohe Lin <linmiaohe@...wei.com>,
David Hildenbrand <david@...hat.com>,
Johannes Weiner <hannes@...xchg.org>,
Peter Xu <peterx@...hat.com>, NeilBrown <neilb@...e.de>,
Shakeel Butt <shakeelb@...gle.com>,
Michal Hocko <mhocko@...nel.org>, Yu Zhao <yuzhao@...gle.com>
Cc: linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-xfs@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH v2 2/3] mm: vmscan: refactor updating reclaimed pages in reclaim_state
On Thu, Mar 9, 2023 at 1:31 AM Yosry Ahmed <yosryahmed@...gle.com> wrote:
>
> During reclaim, we keep track of pages reclaimed from other means than
> LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab,
> which we stash a pointer to in current task_struct.
>
> However, we keep track of more than just reclaimed slab pages through
> this. We also use it for clean file pages dropped through pruned inodes,
> and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add
> a helper function that wraps updating it through current, so that future
> changes to this logic are contained within mm/vmscan.c.
>
> Signed-off-by: Yosry Ahmed <yosryahmed@...gle.com>
> ---
> fs/inode.c | 3 +--
> fs/xfs/xfs_buf.c | 3 +--
> include/linux/swap.h | 5 ++++-
> mm/slab.c | 3 +--
> mm/slob.c | 6 ++----
> mm/slub.c | 5 ++---
> mm/vmscan.c | 36 ++++++++++++++++++++++++++++++------
> 7 files changed, 41 insertions(+), 20 deletions(-)
>
> diff --git a/fs/inode.c b/fs/inode.c
> index 4558dc2f1355..e60fcc41faf1 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -864,8 +864,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
> __count_vm_events(KSWAPD_INODESTEAL, reap);
> else
> __count_vm_events(PGINODESTEAL, reap);
> - if (current->reclaim_state)
> - current->reclaim_state->reclaimed_slab += reap;
> + mm_account_reclaimed_pages(reap);
> }
> iput(inode);
> spin_lock(lru_lock);
> diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
> index 54c774af6e1c..060079f1e966 100644
> --- a/fs/xfs/xfs_buf.c
> +++ b/fs/xfs/xfs_buf.c
> @@ -286,8 +286,7 @@ xfs_buf_free_pages(
> if (bp->b_pages[i])
> __free_page(bp->b_pages[i]);
> }
> - if (current->reclaim_state)
> - current->reclaim_state->reclaimed_slab += bp->b_page_count;
> + report_freed_pages(bp->b_page_count);
Ugh I missed updating this one to mm_account_reclaimed_page().
This fixup needs to be squashed here. I will include it in v3 if a
respin is needed, otherwise I hope Andrew can squash it in.
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 060079f1e966..15d1e5a7c2d3 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -286,7 +286,7 @@ xfs_buf_free_pages(
if (bp->b_pages[i])
__free_page(bp->b_pages[i]);
}
- report_freed_pages(bp->b_page_count);
+ mm_account_reclaimed_pages(bp->b_page_count);
if (bp->b_pages != bp->b_page_array)
kmem_free(bp->b_pages);
>
>
> if (bp->b_pages != bp->b_page_array)
> kmem_free(bp->b_pages);
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 209a425739a9..589ea2731931 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -153,13 +153,16 @@ union swap_header {
> * memory reclaim
> */
> struct reclaim_state {
> - unsigned long reclaimed_slab;
> + /* pages reclaimed outside of LRU-based reclaim */
> + unsigned long reclaimed;
> #ifdef CONFIG_LRU_GEN
> /* per-thread mm walk data */
> struct lru_gen_mm_walk *mm_walk;
> #endif
> };
>
> +void mm_account_reclaimed_pages(unsigned long pages);
> +
> #ifdef __KERNEL__
>
> struct address_space;
> diff --git a/mm/slab.c b/mm/slab.c
> index dabc2a671fc6..64bf1de817b2 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -1392,8 +1392,7 @@ static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab)
> smp_wmb();
> __folio_clear_slab(folio);
>
> - if (current->reclaim_state)
> - current->reclaim_state->reclaimed_slab += 1 << order;
> + mm_account_reclaimed_pages(1 << order);
> unaccount_slab(slab, order, cachep);
> __free_pages(&folio->page, order);
> }
> diff --git a/mm/slob.c b/mm/slob.c
> index fe567fcfa3a3..79cc8680c973 100644
> --- a/mm/slob.c
> +++ b/mm/slob.c
> @@ -61,7 +61,7 @@
> #include <linux/slab.h>
>
> #include <linux/mm.h>
> -#include <linux/swap.h> /* struct reclaim_state */
> +#include <linux/swap.h> /* mm_account_reclaimed_pages() */
> #include <linux/cache.h>
> #include <linux/init.h>
> #include <linux/export.h>
> @@ -211,9 +211,7 @@ static void slob_free_pages(void *b, int order)
> {
> struct page *sp = virt_to_page(b);
>
> - if (current->reclaim_state)
> - current->reclaim_state->reclaimed_slab += 1 << order;
> -
> + mm_account_reclaimed_pages(1 << order);
> mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
> -(PAGE_SIZE << order));
> __free_pages(sp, order);
> diff --git a/mm/slub.c b/mm/slub.c
> index 39327e98fce3..7aa30eef8235 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -11,7 +11,7 @@
> */
>
> #include <linux/mm.h>
> -#include <linux/swap.h> /* struct reclaim_state */
> +#include <linux/swap.h> /* mm_account_reclaimed_pages() */
> #include <linux/module.h>
> #include <linux/bit_spinlock.h>
> #include <linux/interrupt.h>
> @@ -2063,8 +2063,7 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
> /* Make the mapping reset visible before clearing the flag */
> smp_wmb();
> __folio_clear_slab(folio);
> - if (current->reclaim_state)
> - current->reclaim_state->reclaimed_slab += pages;
> + mm_account_reclaimed_pages(pages);
> unaccount_slab(slab, order, s);
> __free_pages(&folio->page, order);
> }
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index fef7d1c0f82b..a3e38851b34a 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -511,6 +511,34 @@ static void set_task_reclaim_state(struct task_struct *task,
> task->reclaim_state = rs;
> }
>
> +/*
> + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based
> + * reclaim
> + * @pages: number of pages reclaimed
> + *
> + * If the current process is undergoing a reclaim operation, increment the
> + * number of reclaimed pages by @pages.
> + */
> +void mm_account_reclaimed_pages(unsigned long pages)
> +{
> + if (current->reclaim_state)
> + current->reclaim_state->reclaimed += pages;
> +}
> +EXPORT_SYMBOL(mm_account_reclaimed_pages);
> +
> +/*
> + * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to
> + * scan_control->nr_reclaimed.
> + */
> +static void flush_reclaim_state(struct scan_control *sc,
> + struct reclaim_state *rs)
> +{
> + if (rs) {
> + sc->nr_reclaimed += rs->reclaimed;
> + rs->reclaimed = 0;
> + }
> +}
> +
> static long xchg_nr_deferred(struct shrinker *shrinker,
> struct shrink_control *sc)
> {
> @@ -5346,8 +5374,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
> vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned,
> sc->nr_reclaimed - reclaimed);
>
> - sc->nr_reclaimed += current->reclaim_state->reclaimed_slab;
> - current->reclaim_state->reclaimed_slab = 0;
> + flush_reclaim_state(sc, current->reclaim_state);
>
> return success ? MEMCG_LRU_YOUNG : 0;
> }
> @@ -6472,10 +6499,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
>
> shrink_node_memcgs(pgdat, sc);
>
> - if (reclaim_state) {
> - sc->nr_reclaimed += reclaim_state->reclaimed_slab;
> - reclaim_state->reclaimed_slab = 0;
> - }
> + flush_reclaim_state(sc, reclaim_state);
>
> /* Record the subtree's reclaim efficiency */
> if (!sc->proactive)
> --
> 2.40.0.rc0.216.gc4246ad0f0-goog
>
Powered by blists - more mailing lists