From: Vlastimil Babka <vbabka@suse.cz>
To: Matthew Wilcox <willy@infradead.org>, linux-mm@kvack.org
Cc: Matthew Wilcox <mawilcox@microsoft.com>,
Andrew Morton <akpm@linux-foundation.org>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
Christoph Lameter <cl@linux.com>,
Lai Jiangshan <laijs@cn.fujitsu.com>,
Pekka Enberg <penberg@kernel.org>
Subject: [PATCH v3 08/14] mm: Combine first three unions in struct page
Date: Thu, 19 Apr 2018 15:46:42 +0200 [thread overview]
Message-ID: <72eecf42-202e-0c6f-06bc-9c5c07814e24@suse.cz> (raw)
In-Reply-To: <20180418184912.2851-9-willy@infradead.org>
On 04/18/2018 08:49 PM, Matthew Wilcox wrote:
> From: Matthew Wilcox <mawilcox@microsoft.com>
>
> By combining these three one-word unions into one three-word union,
> we make it easier for users to add their own multi-word fields to struct
> page, as well as making it obvious that SLUB needs to keep its double-word
> alignment for its freelist & counters.
>
> No field moves position; verified with pahole.
>
> Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
> ---
> include/linux/mm_types.h | 65 ++++++++++++++++++++--------------------
> 1 file changed, 32 insertions(+), 33 deletions(-)
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 04d9dc442029..39521b8385c1 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -70,45 +70,44 @@ struct hmm;
> #endif
>
> struct page {
> - /* First double word block */
> unsigned long flags; /* Atomic flags, some possibly
> * updated asynchronously */
> - union {
> - /* See page-flags.h for the definition of PAGE_MAPPING_FLAGS */
> - struct address_space *mapping;
> -
> - struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
> + union { /* This union is three words (12/24 bytes) in size */
> + struct { /* Page cache and anonymous pages */
> + /* See page-flags.h for PAGE_MAPPING_FLAGS */
> + struct address_space *mapping;
> + pgoff_t index; /* Our offset within mapping. */
> + /**
> + * @private: Mapping-private opaque data.
> + * Usually used for buffer_heads if PagePrivate.
> + * Used for swp_entry_t if PageSwapCache.
> + * Indicates order in the buddy system if PageBuddy.
> + */
> + unsigned long private;
> + };
> + struct { /* slab and slob */
> + struct kmem_cache *slab_cache;
> + void *freelist; /* first free object */
> + void *s_mem; /* first object */
> + };
> + struct { /* slub also uses some of the slab fields */
> + struct kmem_cache *slub_cache;
> + /* Double-word boundary */
> + void *slub_freelist;
Is slub going to switch to use those? Or maybe this is an overkill and
we could merge the two sl*b structs and just have an union for s_mem and
the 3 counters?
> + unsigned inuse:16;
> + unsigned objects:15;
> + unsigned frozen:1;
> + };
next prev parent reply other threads:[~2018-04-19 13:46 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-18 18:48 [PATCH v3 00/14] Rearrange " Matthew Wilcox
2018-04-18 18:48 ` [PATCH v3 01/14] s390: Use _refcount for pgtables Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 02/14] mm: Split page_type out from _mapcount Matthew Wilcox
2018-04-19 9:04 ` Vlastimil Babka
2018-04-19 11:16 ` Matthew Wilcox
2018-04-20 15:17 ` Christopher Lameter
2018-04-20 20:43 ` Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 03/14] mm: Mark pages in use for page tables Matthew Wilcox
2018-04-19 9:30 ` Vlastimil Babka
2018-04-18 18:49 ` [PATCH v3 04/14] mm: Switch s_mem and slab_cache in struct page Matthew Wilcox
2018-04-19 11:06 ` Vlastimil Babka
2018-04-19 11:19 ` Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 05/14] mm: Move 'private' union within " Matthew Wilcox
2018-04-19 11:31 ` Vlastimil Babka
2018-04-20 15:25 ` Christopher Lameter
2018-04-20 20:27 ` Matthew Wilcox
2018-04-30 9:38 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 06/14] mm: Move _refcount out of struct page union Matthew Wilcox
2018-04-19 11:37 ` Vlastimil Babka
2018-04-30 9:40 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 07/14] slub: Remove page->counters Matthew Wilcox
2018-04-19 13:42 ` Vlastimil Babka
2018-04-19 14:23 ` Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 08/14] mm: Combine first three unions in struct page Matthew Wilcox
2018-04-19 13:46 ` Vlastimil Babka [this message]
2018-04-19 14:08 ` Matthew Wilcox
2018-04-30 9:42 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 09/14] mm: Use page->deferred_list Matthew Wilcox
2018-04-19 13:23 ` Vlastimil Babka
2018-04-30 9:43 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 10/14] mm: Move lru union within struct page Matthew Wilcox
2018-04-19 13:56 ` Vlastimil Babka
2018-04-30 9:44 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 11/14] mm: Combine first two unions in " Matthew Wilcox
2018-04-19 14:03 ` Vlastimil Babka
2018-04-30 9:47 ` Kirill A. Shutemov
2018-04-30 12:42 ` Matthew Wilcox
2018-04-30 13:12 ` Kirill A. Shutemov
2018-04-18 18:49 ` [PATCH v3 12/14] mm: Improve struct page documentation Matthew Wilcox
2018-04-18 23:32 ` Randy Dunlap
2018-04-18 23:43 ` Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 13/14] slab,slub: Remove rcu_head size checks Matthew Wilcox
2018-04-18 18:49 ` [PATCH v3 14/14] slub: Remove kmem_cache->reserved Matthew Wilcox
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=72eecf42-202e-0c6f-06bc-9c5c07814e24@suse.cz \
--to=vbabka@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=laijs@cn.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=mawilcox@microsoft.com \
--cc=penberg@kernel.org \
--cc=willy@infradead.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