The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: "Kunwu Chan" <kunwu.chan@linux.dev>
To: "Lian Wang" <lianux.mm@gmail.com>, linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Chris Li" <chrisl@kernel.org>, "Nhat Pham" <nphamcs@gmail.com>,
	"Baoquan He" <baoquan.he@linux.dev>,
	"Barry Song" <baohua@kernel.org>,
	"Youngjun Park" <youngjun.park@lge.com>,
	"Kemeng Shi" <shikemeng@huaweicloud.com>,
	"Kairui Song" <kasong@tencent.com>,
	"Jihan LIN" <linjh22s@gmail.com>, "Kees Cook" <kees@kernel.org>,
	"Gustavo A. R. Silva" <gustavoars@kernel.org>,
	"Thomas Gleixner" <tglx@kernel.org>,
	linux-hardening@vger.kernel.org
Subject: Re: [RFC PATCH v4 07/18] mm/swap: consolidate swap inuse accounting helpers
Date: Fri, 20 Nov 2026 04:30:53 +0000	[thread overview]
Message-ID: <132ae48e0317aa95b8d51c4534230878d6a57ff5@linux.dev> (raw)
In-Reply-To: <4e554bbb557d0456c953d73f008875f6d983b12f.1794666741.git.lianux.mm@gmail.com>

Reviewed-by: Kunwu Chan <kunwu.chan@gmail.com>

Thanks,
Kunwu

> 
> From: Kairui Song <kasong@tencent.com>
> 
> Inline the swap_usage_add/sub helpers into their only callers and
> rename the callers to better reflect what they actually do: track
> per-device inuse page counts.
> 
> Keep the existing accounting and allocation policy. In the inlined
> full-device path, reclaim work is scheduled before availability removal
> rather than afterwards. Slot-free notifications and zswap invalidation
> retain their existing order.
> 
> Signed-off-by: Kairui Song <kasong@tencent.com>
> Signed-off-by: Lian Wang <lianux.mm@gmail.com>
> ---
>  mm/swapfile.c | 64 ++++++++++++++++++++++-----------------------------
>  1 file changed, 27 insertions(+), 37 deletions(-)
> 
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 277a5c749987..aa020f2706b4 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -49,8 +49,8 @@
>  #include "internal.h"
>  #include "swap.h"
>  
> -static void swap_range_alloc(struct swap_info_struct *si,
> - unsigned int nr_entries);
> +static void swap_device_inuse_add(struct swap_info_struct *si,
> + unsigned int nr_entries);
>  static bool folio_swapcache_freeable(struct folio *folio);
>  static void move_cluster(struct swap_info_struct *si,
>  struct swap_cluster_info *ci, struct list_head *list,
> @@ -1045,7 +1045,7 @@ static bool __swap_cluster_alloc_entries(struct swap_info_struct *si,
>  if (cluster_is_empty(ci))
>  ci->order = order;
>  ci->count += nr_pages;
> - swap_range_alloc(si, nr_pages);
> + swap_device_inuse_add(si, nr_pages);
>  
>  return true;
>  }
> @@ -1363,53 +1363,36 @@ static void add_to_avail_list(struct swap_info_struct *si)
>  }
>  
>  /*
> - * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock
> - * within each cluster, so the total contribution to the global counter should
> - * always be positive and cannot exceed the total number of usable slots.
> + * swap_device_inuse_add / swap_device_inuse_sub are called within cluster
> + * update critical sections and serialized by ci->lock within each cluster,
> + * so the total contribution to the global counter should always be positive
> + * and cannot exceed the total number of usable slots.
>  */
> -static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries)
> +static void swap_device_inuse_add(struct swap_info_struct *si,
> + unsigned int nr_entries)
>  {
> - long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages);
> + long inuse_pages;
>  
>  /*
>  * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set,
>  * remove it from the plist.
>  */
> - if (unlikely(val == si->pages)) {
> - del_from_avail_list(si, false);
> - return true;
> - }
> -
> - return false;
> -}
> -
> -static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries)
> -{
> - long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages);
> -
> - /*
> - * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set,
> - * add it to the plist.
> - */
> - if (unlikely(val & SWAP_USAGE_OFFLIST_BIT))
> - add_to_avail_list(si);
> -}
> -
> -static void swap_range_alloc(struct swap_info_struct *si,
> - unsigned int nr_entries)
> -{
> - if (swap_usage_add(si, nr_entries)) {
> + inuse_pages = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages);
> + if (unlikely(inuse_pages == si->pages)) {
>  if (vm_swap_full())
>  schedule_work(&si->reclaim_work);
> + del_from_avail_list(si, false);
>  }
> +
>  atomic_long_sub(nr_entries, &nr_swap_pages);
>  }
>  
> -static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
> - unsigned int nr_entries)
> +static void swap_device_inuse_sub(struct swap_info_struct *si, unsigned long offset,
> + unsigned int nr_entries)
>  {
>  unsigned long end = offset + nr_entries - 1;
>  void (*swap_slot_free_notify)(struct block_device *, unsigned long);
> + long inuse_pages;
>  
>  zswap_invalidate(si->type, offset, nr_entries);
>  
> @@ -1431,7 +1414,14 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
>  */
>  smp_wmb();
>  atomic_long_add(nr_entries, &nr_swap_pages);
> - swap_usage_sub(si, nr_entries);
> +
> + /*
> + * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set,
> + * add it back to the plist.
> + */
> + inuse_pages = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages);
> + if (unlikely(inuse_pages & SWAP_USAGE_OFFLIST_BIT))
> + add_to_avail_list(si);
>  }
>  
>  static bool get_swap_device_info(struct swap_info_struct *si)
> @@ -2059,7 +2049,7 @@ void __swap_cluster_free_entries(struct swap_info_struct *si,
>  if (batch_id)
>  mem_cgroup_uncharge_swap(batch_id, ci_off - batch_off);
>  
> - swap_range_free(si, ci_head + ci_start, nr_pages);
> + swap_device_inuse_sub(si, ci_head + ci_start, nr_pages);
>  swap_cluster_assert_empty(ci, ci_start, nr_pages, false);
>  
>  if (!ci->count)
> @@ -2999,7 +2989,7 @@ static int try_to_unuse(unsigned int type)
>  success:
>  /*
>  * Make sure that further cleanups after try_to_unuse() returns happen
> - * after swap_range_free() reduces si->inuse_pages to 0.
> + * after swap_device_inuse_sub() reduces si->inuse_pages to 0.
>  */
>  smp_mb();
>  return 0;
>

  reply	other threads:[~2026-11-20  4:30 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-14 14:47 [RFC PATCH v4 00/18] mm/swap: introduce priority queues for swap device allocation Lian Wang
2026-11-14 14:48 ` [RFC PATCH v4 01/18] mm/swap: remove unused parameter for reading swap header Lian Wang
2026-11-19 15:56   ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 02/18] mm/swap: clean up hibernation error handling Lian Wang
2026-11-19 15:57   ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 03/18] mm/swap: cleanup and document swap device availability flag usage Lian Wang
2026-11-20  3:58   ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 04/18] mm/swap: introduce swap device iteration helper Lian Wang
2026-11-20  3:59   ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 05/18] mm/swap: change the swapon lock into a percpu rwsem Lian Wang
2026-11-20  4:12   ` Kunwu Chan
2026-11-14 14:49 ` [RFC PATCH v4 06/18] mm/swap: serialize swap publication before removing swapon mutex Lian Wang
2026-11-20  4:30   ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 07/18] mm/swap: consolidate swap inuse accounting helpers Lian Wang
2026-11-20  4:30   ` Kunwu Chan [this message]
2026-11-14 14:50 ` [RFC PATCH v4 08/18] mm/swap: change back to use each swap device's percpu cluster Lian Wang
2026-11-20  4:31   ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 09/18] mm/swap: avoid direct reclaim when populating swap cluster metadata Lian Wang
2026-11-20  4:31   ` Kunwu Chan
2026-11-14 14:50 ` [RFC PATCH v4 10/18] mm/swap: add priority queue for swap device allocation Lian Wang
2026-11-16  3:51   ` Kairui Song
2026-11-16 11:11     ` Lian Wang
2026-11-20  4:34   ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 11/18] mm/swap: remove available list Lian Wang
2026-11-20  4:36   ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 12/18] mm/swap: bound synchronous discard outside the allocation reader Lian Wang
2026-11-20  4:36   ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 13/18] mm/swap: drop swap active plist Lian Wang
2026-11-20  4:37   ` Kunwu Chan
2026-11-14 14:51 ` [RFC PATCH v4 14/18] lib/plist.c: remove requeue function Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 15/18] mm/swap: reuse per-CPU queue readers across priority changes Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 16/18] mm/swap: advance the global queue cursor directly between priority rings Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 17/18] mm/swap: skip reader rotation for single-device " Lian Wang
2026-11-14 14:52 ` [RFC PATCH v4 18/18] mm/swap: redistribute queue readers after membership changes Lian Wang
2026-11-16  3:29   ` Kairui Song
2026-11-16  3:52 ` [RFC PATCH v4 00/18] mm/swap: introduce priority queues for swap device allocation Kairui Song
2026-11-16 11:10   ` Lian Wang

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=132ae48e0317aa95b8d51c4534230878d6a57ff5@linux.dev \
    --to=kunwu.chan@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=baohua@kernel.org \
    --cc=baoquan.he@linux.dev \
    --cc=chrisl@kernel.org \
    --cc=gustavoars@kernel.org \
    --cc=kasong@tencent.com \
    --cc=kees@kernel.org \
    --cc=lianux.mm@gmail.com \
    --cc=linjh22s@gmail.com \
    --cc=linux-hardening@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nphamcs@gmail.com \
    --cc=shikemeng@huaweicloud.com \
    --cc=tglx@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