Received-SPF: pass (google.com: domain of linux-kernel+bounces-29740-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Precedence: bulk
MIME-Version: 1.0
References: <20240117-zswap-xarray-v1-0-6daa86c08fae@kernel.org> <20240117-zswap-xarray-v1-2-6daa86c08fae@kernel.org>
In-Reply-To: <20240117-zswap-xarray-v1-2-6daa86c08fae@kernel.org>
From: Yosry Ahmed <yosryahmed@google.com>
Date: Wed, 17 Jan 2024 22:35:15 -0800
Message-ID: <CAJD7tkZF102x_8LKAX+sxAttgYD_LNT3cRqeOr7_euwPfNdCFA@mail.gmail.com>
Subject: Re: [PATCH 2/2] mm: zswap.c: remove RB tree
To: Chris Li <chrisl@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, 
	linux-mm@kvack.org, =?UTF-8?B?V2VpIFh177+8?= <weixugc@google.com>, 
	Yu Zhao <yuzhao@google.com>, Greg Thelen <gthelen@google.com>, 
	Chun-Tse Shao <ctshao@google.com>, =?UTF-8?Q?Suren_Baghdasaryan=EF=BF=BC?= <surenb@google.com>, 
	Brain Geffon <bgeffon@google.com>, Minchan Kim <minchan@kernel.org>, Michal Hocko <mhocko@suse.com>, 
	Mel Gorman <mgorman@techsingularity.net>, Huang Ying <ying.huang@intel.com>, 
	Nhat Pham <nphamcs@gmail.com>, Johannes Weiner <hannes@cmpxchg.org>, Kairui Song <kasong@tencent.com>, 
	Zhongkun He <hezhongkun.hzk@bytedance.com>, Kemeng Shi <shikemeng@huaweicloud.com>, 
	Barry Song <v-songbaohua@oppo.com>, "Matthew Wilcox (Oracle)" <willy@infradead.org>, 
	"Liam R. Howlett" <Liam.Howlett@oracle.com>, Joel Fernandes <joel@joelfernandes.org>, 
	Chengming Zhou <zhouchengming@bytedance.com>
Content-Type: text/plain; charset="UTF-8"

> @@ -493,45 +471,47 @@ static struct zswap_entry *zswap_search(struct zswap_tree *tree, pgoff_t offset)
>  static int zswap_insert(struct zswap_tree *tree, struct zswap_entry *entry,
>                         struct zswap_entry **dupentry)
>  {
> -       struct rb_root *root = &tree->rbroot;
> -       struct rb_node **link = &root->rb_node, *parent = NULL;
> -       struct zswap_entry *myentry, *old;
> -       pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry);
> -
> -
> -       while (*link) {
> -               parent = *link;
> -               myentry = rb_entry(parent, struct zswap_entry, rbnode);
> -               myentry_offset = swp_offset(myentry->swpentry);
> -               if (myentry_offset > entry_offset)
> -                       link = &(*link)->rb_left;
> -               else if (myentry_offset < entry_offset)
> -                       link = &(*link)->rb_right;
> -               else {
> -                       old = xa_load(&tree->xarray, entry_offset);
> -                       BUG_ON(old != myentry);
> -                       *dupentry = myentry;
> +       struct zswap_entry *e;
> +       pgoff_t offset = swp_offset(entry->swpentry);
> +       XA_STATE(xas, &tree->xarray, offset);
> +
> +       do {
> +               xas_lock_irq(&xas);
> +               do {
> +                       e = xas_load(&xas);
> +                       if (xa_is_zero(e))
> +                               e = NULL;
> +               } while (xas_retry(&xas, e));
> +               if (xas_valid(&xas) && e) {
> +                       xas_unlock_irq(&xas);
> +                       *dupentry = e;
>                         return -EEXIST;
>                 }
> -       }
> -       rb_link_node(&entry->rbnode, parent, link);
> -       rb_insert_color(&entry->rbnode, root);
> -       old = xa_store(&tree->xarray, entry_offset, entry, GFP_KERNEL);
> -       return 0;
> +               xas_store(&xas, entry);
> +               xas_unlock_irq(&xas);
> +       } while (xas_nomem(&xas, GFP_KERNEL));
> +       return xas_error(&xas);

I think using the xas_* APIs can be avoided here. The only reason we
need it is that we want to check if there's an existing entry first,
and return -EEXIST. However, in that case, the caller will replace it
anyway (and do some operations on the dupentry):

while (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) {
        WARN_ON(1);
        zswap_duplicate_entry++;
        zswap_invalidate_entry(tree, dupentry);
}

So I think we can do something like this in zswap_insert() instead:

dupentry = xa_store(..);
if (WARN_ON(dupentry)) {
        zswap_duplicate_entry++;
        zswap_invalidate_entry(tree, dupentry);
}

WDYT?

>  }
>
>  static bool zswap_erase(struct zswap_tree *tree, struct zswap_entry *entry)
>  {
> +       struct zswap_entry *e;
>         pgoff_t offset = swp_offset(entry->swpentry);
> -       if (!RB_EMPTY_NODE(&entry->rbnode)) {
> -               struct zswap_entry *old;
> -               old = xa_erase(&tree->xarray, offset);
> -               BUG_ON(old != entry);
> -               rb_erase(&entry->rbnode, &tree->rbroot);
> -               RB_CLEAR_NODE(&entry->rbnode);
> -               return true;
> -       }
> -       return false;
> +       XA_STATE(xas, &tree->xarray, offset);
> +
> +       do {
> +               xas_lock_irq(&xas);
> +               do {
> +                       e = xas_load(&xas);
> +               } while (xas_retry(&xas, e));
> +               if (xas_valid(&xas) && e != entry) {
> +                       xas_unlock_irq(&xas);
> +                       return false;
> +               }
> +               xas_store(&xas, NULL);
> +               xas_unlock_irq(&xas);
> +       } while (xas_nomem(&xas, GFP_KERNEL));
> +       return !xas_error(&xas);
>  }

Same here, I think we just want:

return !!xa_erase(..);

>
>  static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
> @@ -583,7 +563,6 @@ static void zswap_entry_put(struct zswap_tree *tree,
>
>         WARN_ON_ONCE(refcount < 0);
>         if (refcount == 0) {
> -               WARN_ON_ONCE(!RB_EMPTY_NODE(&entry->rbnode));
>                 zswap_free_entry(entry);
>         }

nit: the braces are no longer needed here