| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4DF0991E.6060907@cs.helsinki.fi>
Date: Thu, 09 Jun 2011 12:57:50 +0300
From: Pekka Enberg <penberg@...helsinki.fi>
To: Christoph Lameter <cl@...ux.com>
CC: David Rientjes <rientjes@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>,
"H. Peter Anvin" <hpa@...or.com>, linux-kernel@...r.kernel.org,
Thomas Gleixner <tglx@...utronix.de>,
kamezawa.hiroyu@...fujitsu.com, akpm@...ux-foundation.org,
kosaki.motohiro@...fujitsu.com
Subject: Re: [slubllv7 05/17] mm: Rearrange struct page
On 6/1/11 8:25 PM, Christoph Lameter wrote:
> We need to be able to use cmpxchg_double on the freelist and object count
> field in struct page. Rearrange the fields in struct page according to
> doubleword entities so that the freelist pointer comes before the counters.
> Do the rearranging with a future in mind where we use more doubleword
> atomics to avoid locking of updates to flags/mapping or lru pointers.
>
> Create another union to allow access to counters in struct page as a
> single unsigned long value.
>
> The doublewords must be properly aligned for cmpxchg_double to work.
> Sadly this increases the size of page struct by one word on some architectures.
> But as a resultpage structs are now cacheline aligned on x86_64.
>
> Signed-off-by: Christoph Lameter<cl@...ux.com>
I'd like to queue this SLUB patch series to linux-next through slab.git.
Any NAKs or ACKs for this patch?
Pekka
> ---
> include/linux/mm_types.h | 89 +++++++++++++++++++++++++++++++----------------
> 1 file changed, 60 insertions(+), 29 deletions(-)
>
> Index: linux-2.6/include/linux/mm_types.h
> ===================================================================
> --- linux-2.6.orig/include/linux/mm_types.h 2011-05-31 09:46:41.912987862 -0500
> +++ linux-2.6/include/linux/mm_types.h 2011-05-31 09:46:44.282987846 -0500
> @@ -30,52 +30,74 @@ struct address_space;
> * moment. Note that we have no way to track which tasks are using
> * a page, though if it is a pagecache page, rmap structures can tell us
> * who is mapping it.
> + *
> + * The objects in struct page are organized in double word blocks in
> + * order to allows us to use atomic double word operations on portions
> + * of struct page. That is currently only used by slub but the arrangement
> + * allows the use of atomic double word operations on the flags/mapping
> + * and lru list pointers also.
> */
> struct page {
> + /* First double word block */
> unsigned long flags; /* Atomic flags, some possibly
> * updated asynchronously */
> - atomic_t _count; /* Usage count, see below. */
> + struct address_space *mapping; /* If low bit clear, points to
> + * inode address_space, or NULL.
> + * If page mapped as anonymous
> + * memory, low bit is set, and
> + * it points to anon_vma object:
> + * see PAGE_MAPPING_ANON below.
> + */
> + /* Second double word */
> union {
> - atomic_t _mapcount; /* Count of ptes mapped in mms,
> - * to show when page is mapped
> - *& limit reverse map searches.
> + struct {
> + pgoff_t index; /* Our offset within mapping. */
> + atomic_t _mapcount; /* Count of ptes mapped in mms,
> + * to show when page is mapped
> + *& limit reverse map searches.
> + */
> + atomic_t _count; /* Usage count, see below. */
> + };
> +
> + struct { /* SLUB cmpxchg_double area */
> + void *freelist;
> + union {
> + unsigned long counters;
> + struct {
> + unsigned inuse:16;
> + unsigned objects:15;
> + unsigned frozen:1;
> + /*
> + * Kernel may make use of this field even when slub
> + * uses the rest of the double word!
> */
> - struct { /* SLUB */
> - unsigned inuse:16;
> - unsigned objects:15;
> - unsigned frozen:1;
> + atomic_t _count;
> + };
> + };
> };
> };
> +
> + /* Third double word block */
> + struct list_head lru; /* Pageout list, eg. active_list
> + * protected by zone->lru_lock !
> + */
> +
> + /* Remainder is not double word aligned */
> union {
> - struct {
> - unsigned long private; /* Mapping-private opaque data:
> + unsigned long private; /* Mapping-private opaque data:
> * usually used for buffer_heads
> * if PagePrivate set; used for
> * swp_entry_t if PageSwapCache;
> * indicates order in the buddy
> * system if PG_buddy is set.
> */
> - struct address_space *mapping; /* If low bit clear, points to
> - * inode address_space, or NULL.
> - * If page mapped as anonymous
> - * memory, low bit is set, and
> - * it points to anon_vma object:
> - * see PAGE_MAPPING_ANON below.
> - */
> - };
> #if USE_SPLIT_PTLOCKS
> - spinlock_t ptl;
> + spinlock_t ptl;
> #endif
> - struct kmem_cache *slab; /* SLUB: Pointer to slab */
> - struct page *first_page; /* Compound tail pages */
> + struct kmem_cache *slab; /* SLUB: Pointer to slab */
> + struct page *first_page; /* Compound tail pages */
> };
> - union {
> - pgoff_t index; /* Our offset within mapping. */
> - void *freelist; /* SLUB: freelist req. slab lock */
> - };
> - struct list_head lru; /* Pageout list, eg. active_list
> - * protected by zone->lru_lock !
> - */
> +
> /*
> * On machines where all RAM is mapped into kernel address space,
> * we can simply calculate the virtual address. On machines with
> @@ -101,7 +123,16 @@ struct page {
> */
> void *shadow;
> #endif
> -};
> +}
> +/*
> + * If another subsystem starts using the double word pairing for atomic
> + * operations on struct page then it must change the #if to ensure
> + * proper alignment of the page struct.
> + */
> +#if defined(CONFIG_SLUB)&& defined(CONFIG_CMPXCHG_LOCAL)
> + __attribute__((__aligned__(2*sizeof(unsigned long))))
> +#endif
> +;
>
> typedef unsigned long __nocast vm_flags_t;
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists