linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yosry Ahmed <yosry.ahmed@linux.dev>
To: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	 Nhat Pham <nphamcs@gmail.com>, Minchan Kim <minchan@kernel.org>,
	 Johannes Weiner <hannes@cmpxchg.org>,
	Brian Geffon <bgeffon@google.com>,
	linux-kernel@vger.kernel.org,  linux-mm@kvack.org
Subject: Re: [PATCH] zsmalloc: use actual object size to detect spans
Date: Wed, 7 Jan 2026 05:22:24 +0000	[thread overview]
Message-ID: <mumv2eouuqepj5btx4jeghevlleucdslt76erxtt4sm5ntavx5@oipdwrdhzlta> (raw)
In-Reply-To: <3xsreqvvclcuqyllgdz5avxwdvhc3rqri4565xj2hbwk6r6uol@6mnhvdgaxfrl>

On Wed, Jan 07, 2026 at 12:03:37PM +0900, Sergey Senozhatsky wrote:
> On (26/01/07 02:10), Yosry Ahmed wrote:
> > I think the changes need to be shuffled around to avoid this, or just
> > have a combined patch, which would be less pretty.
> 
> Dunno.  Do we want to completely separate HugePage handling
> and make it a fast path?  Then it seems things begin to work.

HugePage should always be PAGE_SIZE, so never spans two pages, right?

I like separating the logic because it's cleaner, but I want us to
understand the problem first (see my other reply) instead of just
papering over it.

> 
> ---
> 
> diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> index cb449acc8809..9b067853b6c2 100644
> --- a/mm/zsmalloc.c
> +++ b/mm/zsmalloc.c
> @@ -1077,6 +1077,7 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
>         unsigned long obj, off;
>         unsigned int obj_idx;
>         struct size_class *class;
> +       size_t sizes[2];
>         void *addr;
>  
>         /* Guarantee we can get zspage from handle safely */
> @@ -1089,35 +1090,27 @@ void *zs_obj_read_begin(struct zs_pool *pool, unsigned long handle,
>         zspage_read_lock(zspage);
>         read_unlock(&pool->lock);
>  
> +       /* Fast path for huge size class */
> +       if (ZsHugePage(zspage))
> +               return kmap_local_zpdesc(zpdesc);

Can we WARN here if somehow the HugePage is spanning two pages?

> +
>         class = zspage_class(pool, zspage);
>         off = offset_in_page(class->size * obj_idx);
>  
> -       /* Normal classes have inlined handle */
> -       if (!ZsHugePage(zspage))
> -               mem_len += ZS_HANDLE_SIZE;
> -
> +       off += ZS_HANDLE_SIZE;
>         if (off + mem_len <= PAGE_SIZE) {
>                 /* this object is contained entirely within a page */
> -               addr = kmap_local_zpdesc(zpdesc);
> -               addr += off;
> -       } else {
> -               size_t sizes[2];
> -
> -               /* this object spans two pages */
> -               sizes[0] = PAGE_SIZE - off;
> -               sizes[1] = mem_len - sizes[0];
> -               addr = local_copy;
> -
> -               memcpy_from_page(addr, zpdesc_page(zpdesc),
> -                                off, sizes[0]);
> -               zpdesc = get_next_zpdesc(zpdesc);
> -               memcpy_from_page(addr + sizes[0],
> -                                zpdesc_page(zpdesc),
> -                                0, sizes[1]);
> +               return kmap_local_zpdesc(zpdesc) + off;
>         }
>  
> -       if (!ZsHugePage(zspage))
> -               addr += ZS_HANDLE_SIZE;
> +       /* this object spans two pages */
> +       sizes[0] = PAGE_SIZE - off;
> +       sizes[1] = mem_len - sizes[0];
> +       addr = local_copy;
> +
> +       memcpy_from_page(addr, zpdesc_page(zpdesc), off, sizes[0]);
> +       zpdesc = get_next_zpdesc(zpdesc);
> +       memcpy_from_page(addr + sizes[0], zpdesc_page(zpdesc), 0, sizes[1]);
>  
>         return addr;
>  }
> @@ -1135,20 +1128,21 @@ void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
>         obj = handle_to_obj(handle);
>         obj_to_location(obj, &zpdesc, &obj_idx);
>         zspage = get_zspage(zpdesc);
> +
> +       /* Fast path for huge size class */
> +       if (ZsHugePage(zspage)) {
> +               kunmap_local(handle_mem);
> +               goto unlock;
> +       }
> +
>         class = zspage_class(pool, zspage);
>         off = offset_in_page(class->size * obj_idx);
>  
> -       /* Normal classes have inlined handle */
> -       if (!ZsHugePage(zspage))
> -               mem_len += ZS_HANDLE_SIZE;
> -
> -       if (off + mem_len <= PAGE_SIZE) {
> -               if (!ZsHugePage(zspage))
> -                       off += ZS_HANDLE_SIZE;
> -               handle_mem -= off;
> +       off += ZS_HANDLE_SIZE;
> +       if (off + mem_len <= PAGE_SIZE)
>                 kunmap_local(handle_mem);
> -       }
>  
> +unlock:
>         zspage_read_unlock(zspage);
>  }
>  EXPORT_SYMBOL_GPL(zs_obj_read_end);


  reply	other threads:[~2026-01-07  5:22 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-06  4:25 Sergey Senozhatsky
2026-01-07  0:23 ` Yosry Ahmed
2026-01-07  0:59   ` Sergey Senozhatsky
2026-01-07  1:37     ` Sergey Senozhatsky
2026-01-07  1:56       ` Yosry Ahmed
2026-01-07  2:06         ` Sergey Senozhatsky
2026-01-07  2:10           ` Yosry Ahmed
2026-01-07  2:20             ` Sergey Senozhatsky
2026-01-07  2:22               ` Sergey Senozhatsky
2026-01-07  5:19               ` Yosry Ahmed
2026-01-07  5:30                 ` Sergey Senozhatsky
2026-01-07  7:12                   ` Sergey Senozhatsky
2026-01-07  3:03             ` Sergey Senozhatsky
2026-01-07  5:22               ` Yosry Ahmed [this message]
2026-01-07  5:38                 ` Sergey Senozhatsky

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=mumv2eouuqepj5btx4jeghevlleucdslt76erxtt4sm5ntavx5@oipdwrdhzlta \
    --to=yosry.ahmed@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=bgeffon@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=nphamcs@gmail.com \
    --cc=senozhatsky@chromium.org \
    /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