| 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: <cd22xnrx67lh5bplerw2tnpnlqln5fzmpomm2vvvag5lc6ibn5@7hpbz27v3m6s>
Date: Tue, 24 Jun 2025 20:26:49 +0200
From: Klara Modin <klarasmodin@...il.com>
To: Davidlohr Bueso <dave@...olabs.net>
Cc: akpm@...ux-foundation.org, mhocko@...nel.org, hannes@...xchg.org,
roman.gushchin@...ux.dev, shakeel.butt@...ux.dev, yosryahmed@...gle.com,
linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 2/4] mm/memcg: make memory.reclaim interface generic
Hi,
On 2025-06-23 11:58:49 -0700, Davidlohr Bueso wrote:
> This adds a general call for both parsing as well as the
> common reclaim semantics. memcg is still the only user and
> no change in semantics.
>
> Signed-off-by: Davidlohr Bueso <dave@...olabs.net>
> ---
> mm/internal.h | 2 +
> mm/memcontrol.c | 77 ++------------------------------------
> mm/vmscan.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 104 insertions(+), 73 deletions(-)
>
> diff --git a/mm/internal.h b/mm/internal.h
> index 3823fb356d3b..fc4262262b31 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -517,6 +517,8 @@ extern unsigned long highest_memmap_pfn;
> bool folio_isolate_lru(struct folio *folio);
> void folio_putback_lru(struct folio *folio);
> extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
> +int user_proactive_reclaim(char *buf,
> + struct mem_cgroup *memcg, pg_data_t *pgdat);
>
> /*
> * in mm/rmap.c:
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 902da8a9c643..015e406eadfa 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -51,7 +51,6 @@
> #include <linux/spinlock.h>
> #include <linux/fs.h>
> #include <linux/seq_file.h>
> -#include <linux/parser.h>
> #include <linux/vmpressure.h>
> #include <linux/memremap.h>
> #include <linux/mm_inline.h>
> @@ -4566,83 +4565,15 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
> return nbytes;
> }
>
> -enum {
> - MEMORY_RECLAIM_SWAPPINESS = 0,
> - MEMORY_RECLAIM_SWAPPINESS_MAX,
> - MEMORY_RECLAIM_NULL,
> -};
> -
> -static const match_table_t tokens = {
> - { MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
> - { MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
> - { MEMORY_RECLAIM_NULL, NULL },
> -};
> -
> static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
> size_t nbytes, loff_t off)
> {
> struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
> - unsigned int nr_retries = MAX_RECLAIM_RETRIES;
> - unsigned long nr_to_reclaim, nr_reclaimed = 0;
> - int swappiness = -1;
> - unsigned int reclaim_options;
> - char *old_buf, *start;
> - substring_t args[MAX_OPT_ARGS];
> -
> - buf = strstrip(buf);
> -
> - old_buf = buf;
> - nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
> - if (buf == old_buf)
> - return -EINVAL;
> -
> - buf = strstrip(buf);
> -
> - while ((start = strsep(&buf, " ")) != NULL) {
> - if (!strlen(start))
> - continue;
> - switch (match_token(start, tokens, args)) {
> - case MEMORY_RECLAIM_SWAPPINESS:
> - if (match_int(&args[0], &swappiness))
> - return -EINVAL;
> - if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS)
> - return -EINVAL;
> - break;
> - case MEMORY_RECLAIM_SWAPPINESS_MAX:
> - swappiness = SWAPPINESS_ANON_ONLY;
> - break;
> - default:
> - return -EINVAL;
> - }
> - }
> -
> - reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
> - while (nr_reclaimed < nr_to_reclaim) {
> - /* Will converge on zero, but reclaim enforces a minimum */
> - unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
> - unsigned long reclaimed;
> -
> - if (signal_pending(current))
> - return -EINTR;
> -
> - /*
> - * This is the final attempt, drain percpu lru caches in the
> - * hope of introducing more evictable pages for
> - * try_to_free_mem_cgroup_pages().
> - */
> - if (!nr_retries)
> - lru_add_drain_all();
> -
> - reclaimed = try_to_free_mem_cgroup_pages(memcg,
> - batch_size, GFP_KERNEL,
> - reclaim_options,
> - swappiness == -1 ? NULL : &swappiness);
> -
> - if (!reclaimed && !nr_retries--)
> - return -EAGAIN;
> + int ret;
>
> - nr_reclaimed += reclaimed;
> - }
> + ret = user_proactive_reclaim(buf, memcg, NULL);
This is outside CONFIG_NUMA.
> + if (ret)
> + return ret;
>
> return nbytes;
> }
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index c13c01eb0b42..63ddec550c3b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -57,6 +57,7 @@
> #include <linux/rculist_nulls.h>
> #include <linux/random.h>
> #include <linux/mmu_notifier.h>
> +#include <linux/parser.h>
>
> #include <asm/tlbflush.h>
> #include <asm/div64.h>
> @@ -6714,6 +6715,15 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
>
> return nr_reclaimed;
> }
> +#else
> +unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
> + unsigned long nr_pages,
> + gfp_t gfp_mask,
> + unsigned int reclaim_options,
> + int *swappiness)
> +{
> + return 0;
> +}
> #endif
>
> static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc)
> @@ -7708,6 +7718,94 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
>
> return ret;
> }
> +
> +enum {
> + MEMORY_RECLAIM_SWAPPINESS = 0,
> + MEMORY_RECLAIM_SWAPPINESS_MAX,
> + MEMORY_RECLAIM_NULL,
> +};
> +static const match_table_t tokens = {
> + { MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
> + { MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
> + { MEMORY_RECLAIM_NULL, NULL },
> +};
> +
> +int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat)
> +{
> + unsigned int nr_retries = MAX_RECLAIM_RETRIES;
> + unsigned long nr_to_reclaim, nr_reclaimed = 0;
> + int swappiness = -1;
> + char *old_buf, *start;
> + substring_t args[MAX_OPT_ARGS];
> +
> + if (!buf || (!memcg && !pgdat))
> + return -EINVAL;
> +
> + buf = strstrip(buf);
> +
> + old_buf = buf;
> + nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
> + if (buf == old_buf)
> + return -EINVAL;
> +
> + buf = strstrip(buf);
> +
> + while ((start = strsep(&buf, " ")) != NULL) {
> + if (!strlen(start))
> + continue;
> + switch (match_token(start, tokens, args)) {
> + case MEMORY_RECLAIM_SWAPPINESS:
> + if (match_int(&args[0], &swappiness))
> + return -EINVAL;
> + if (swappiness < MIN_SWAPPINESS ||
> + swappiness > MAX_SWAPPINESS)
> + return -EINVAL;
> + break;
> + case MEMORY_RECLAIM_SWAPPINESS_MAX:
> + swappiness = SWAPPINESS_ANON_ONLY;
> + break;
> + default:
> + return -EINVAL;
> + }
> + }
> +
> + while (nr_reclaimed < nr_to_reclaim) {
> + /* Will converge on zero, but reclaim enforces a minimum */
> + unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
> + unsigned long reclaimed;
> +
> + if (signal_pending(current))
> + return -EINTR;
> +
> + /*
> + * This is the final attempt, drain percpu lru caches in the
> + * hope of introducing more evictable pages.
> + */
> + if (!nr_retries)
> + lru_add_drain_all();
> +
> + if (memcg) {
> + unsigned int reclaim_options;
> +
> + reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
> + MEMCG_RECLAIM_PROACTIVE;
> + reclaimed = try_to_free_mem_cgroup_pages(memcg,
> + batch_size, GFP_KERNEL,
> + reclaim_options,
> + swappiness == -1 ? NULL : &swappiness);
> + } else {
> + return -EINVAL;
> + }
> +
> + if (!reclaimed && !nr_retries--)
> + return -EAGAIN;
> +
> + nr_reclaimed += reclaimed;
> + }
> +
> + return 0;
> +}
> +
> #endif
Should this really be inside CONFIG_NUMA? It was moved from outside of
CONFIG_NUMA where it's now called which results in a build failure if
it's disabled. Or is there a stub missing?
>
> /**
> --
> 2.39.5
>
Regards,
Klara Modin
Powered by blists - more mailing lists