Linux-mm Archive on lore.kernel.org
 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 16/18] mm/swap: advance the global queue cursor directly between priority rings
Date: Fri, 20 Nov 2026 04:38:17 +0000	[thread overview]
Message-ID: <1391b9e3f25f7f95aedd2b884a998a0d48b324ca@linux.dev> (raw)
In-Reply-To: <e72074ac198130494037e80655685cf25ff4bb5b.1794666741.git.lianux.mm@gmail.com>

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

Thanks,
Kunwu

> 
> The allocation walk previously passed a total retry index to the selector.
> Each retry translated it back to a priority ring by scanning from the
> beginning of swap_queue. Keep the ring index and the number of attempted
> peers in the task-local cursor instead.
> 
> Snapshot the starting device only on the first visit to each ring and
> advance each peer exactly once, including masked entries. Preserve the
> large-folio same-ring boundary and the stale reader-offset correction.
> The selector's complete walk is linear in the devices and priority groups;
> device cluster scanning and availability updates have their own costs.
> 
> Keep the topology read lock and CPU migration protection across the walk.
> The global selector uses only existing priorities and adds no per-memcg
> device-selection state or ABI. Existing swap charging and limits remain
> in folio_alloc_swap(), whose failure path classifies allocation errors.
> 
> The walk no longer returns an ignored internal error to that caller.
> 
> Signed-off-by: Lian Wang <lianux.mm@gmail.com>
> ---
>  mm/swapfile.c | 51 ++++++++++++++++++++++++---------------------------
>  1 file changed, 24 insertions(+), 27 deletions(-)
> 
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 5e5c1aef010f..616339c5ae5b 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -195,10 +195,10 @@ struct swap_queue_reader {
>  };
>  
>  struct swap_queue_cursor {
> - bool valid;
>  bool ring_only;
>  unsigned int ring_idx;
>  unsigned int offset;
> + unsigned int nr_iter;
>  };
>  
>  static __percpu struct swap_queue_reader *swap_queue_readers;
> @@ -308,28 +308,32 @@ static void swap_queue_install_readers(struct swap_queue_reader __percpu *reader
>  swap_queue_reset_readers();
>  }
>  
> -static struct swap_info_struct *swap_queue_get_device(long nr_alloc, int nr_iter,
> - struct swap_queue_cursor *cursor)
> +static struct swap_info_struct *
> +swap_queue_get_device(long nr_alloc, struct swap_queue_cursor *cursor)
>  {
>  bool rotate = false;
>  struct swap_info_struct *si;
>  struct swap_ring_iterator *ri;
>  struct swap_prio_ring *ring;
> - unsigned int dev_idx, queue_idx;
> + unsigned int dev_idx, queue_idx, nr_iter;
>  
> - if (!swap_queue_len)
> + queue_idx = cursor->ring_idx;
> + if (queue_idx >= swap_queue_len)
>  return ERR_PTR(-ENOENT);
>  
> - queue_idx = 0;
> - while (nr_iter >= swap_queue[queue_idx]->size) {
> - nr_iter -= swap_queue[queue_idx]->size;
> - if (++queue_idx >= swap_queue_len)
> - return ERR_PTR(cursor->ring_only ? -E2BIG : -ENOENT);
> - }
> - if (cursor->ring_only && cursor->ring_idx != queue_idx)
> - return ERR_PTR(-E2BIG);
> -
>  ring = swap_queue[queue_idx];
> + if (cursor->nr_iter >= ring->size) {
> + if (cursor->ring_only)
> + return ERR_PTR(-E2BIG);
> + queue_idx = ++cursor->ring_idx;
> + if (queue_idx >= swap_queue_len)
> + return ERR_PTR(-ENOENT);
> + cursor->nr_iter = 0;
> + ring = swap_queue[queue_idx];
> + }
> +
> + /* Consume masked peers too, so every walk remains bounded. */
> + nr_iter = cursor->nr_iter++;
>  local_lock(&swap_queue_readers->lock);
>  ri = this_cpu_ptr(&swap_queue_readers->ri[queue_idx]);
>  /*
> @@ -337,9 +341,7 @@ static struct swap_info_struct *swap_queue_get_device(long nr_alloc, int nr_iter
>  * iterator can move between retries, but the cursor must visit every
>  * device in the ring exactly once before falling through.
>  */
> - if (!cursor->valid || cursor->ring_idx != queue_idx) {
> - cursor->valid = true;
> - cursor->ring_idx = queue_idx;
> + if (!nr_iter) {
>  if (ri->rr_counter < nr_alloc)
>  rotate = true;
>  else if (ri->offset >= ring->size)
> @@ -1847,29 +1849,25 @@ static bool get_swap_device_info(struct swap_info_struct *si)
>  return true;
>  }
>  
> -static int swap_alloc_entry(struct folio *folio)
> +static void swap_alloc_entry(struct folio *folio)
>  {
>  struct swap_queue_cursor cursor = {};
>  long nr_pages = folio_nr_pages(folio);
>  struct swap_info_struct *si;
> - int nr_iter, ret;
>  
>  percpu_down_read(&swapon_rwsem);
>  migrate_disable();
> - for (nr_iter = 0;; nr_iter++) {
> - si = swap_queue_get_device(nr_pages, nr_iter, &cursor);
> + for (;;) {
> + si = swap_queue_get_device(nr_pages, &cursor);
>  if (IS_ERR(si)) {
> - ret = PTR_ERR(si);
> - if (ret == -EBUSY)
> + if (PTR_ERR(si) == -EBUSY)
>  continue;
>  break;
>  }
>  cluster_alloc_swap_entry(si, folio);
>  
> - if (folio_test_swapcache(folio)) {
> - ret = 0;
> + if (folio_test_swapcache(folio))
>  break;
> - }
>  
>  /*
>  * For large allocations, try every device at the same priority,
> @@ -1884,7 +1882,6 @@ static int swap_alloc_entry(struct folio *folio)
>  
>  migrate_enable();
>  percpu_up_read(&swapon_rwsem);
> - return ret;
>  }
>  
>  /*
>


  reply	other threads:[~2026-11-20  4:38 UTC|newest]

Thread overview: 41+ 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
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
2026-11-20  4:37   ` Kunwu Chan
2026-11-14 14:52 ` [RFC PATCH v4 16/18] mm/swap: advance the global queue cursor directly between priority rings Lian Wang
2026-11-20  4:38   ` Kunwu Chan [this message]
2026-11-14 14:52 ` [RFC PATCH v4 17/18] mm/swap: skip reader rotation for single-device " Lian Wang
2026-11-20  4:38   ` Kunwu Chan
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
2026-11-20  4:38   ` Kunwu Chan
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=1391b9e3f25f7f95aedd2b884a998a0d48b324ca@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