Re: [PATCH 3.2.0-rc1 2/3] MM hook for page allocation and release

[Pekka Enberg]

On Wed, Jan 4, 2012 at 7:21 PM, Leonid Moiseichuk
<leonid.moiseichuk@xxxxxxxxx> wrote:
> That is required by Used Memory Meter (UMM) pseudo-device
> to track memory utilization in system. It is expected that
> hook MUST be very light to prevent performance impact
> on the hot allocation path. Accuracy of number managed pages
> does not expected to be absolute but fact of allocation or
> deallocation must be registered.
>
> Signed-off-by: Leonid Moiseichuk <leonid.moiseichuk@xxxxxxxxx>
> ---
>  include/linux/mm.h |   15 +++++++++++++++
>  mm/Kconfig         |    8 ++++++++
>  mm/page_alloc.c    |   31 +++++++++++++++++++++++++++++++
>  3 files changed, 54 insertions(+), 0 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 3dc3a8c..d133f73 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1618,6 +1618,21 @@ extern int soft_offline_page(struct page *page, int flags);
>
>  extern void dump_page(struct page *page);
>
> +#ifdef CONFIG_MM_ALLOC_FREE_HOOK
> +/*
> + * Hook function type which called when some pages allocated or released.
> + * Value of nr_pages is positive for post-allocation calls and negative
> + * after free.
> + */
> +typedef void (*mm_alloc_free_hook_t)(int nr_pages);
> +
> +/*
> + * Setups specified hook function for tracking pages allocation.
> + * Returns value of old hook to organize chains of calls if necessary.
> + */
> +mm_alloc_free_hook_t set_mm_alloc_free_hook(mm_alloc_free_hook_t hook);
> +#endif
> +
>  #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
>  extern void clear_huge_page(struct page *page,
>                            unsigned long addr,
> diff --git a/mm/Kconfig b/mm/Kconfig
> index 011b110..2aaa1e9 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -373,3 +373,11 @@ config CLEANCACHE
>          in a negligible performance hit.
>
>          If unsure, say Y to enable cleancache
> +
> +config MM_ALLOC_FREE_HOOK
> +       bool "Enable callback support for pages allocation and releasing"
> +       default n
> +       help
> +         Required for some features like used memory meter.
> +         If unsure, say N to disable alloc/free hook.
> +
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 9dd443d..9307800 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -236,6 +236,30 @@ static void set_pageblock_migratetype(struct page *page, int migratetype)
>
>  bool oom_killer_disabled __read_mostly;
>
> +#ifdef CONFIG_MM_ALLOC_FREE_HOOK
> +static atomic_long_t alloc_free_hook __read_mostly = ATOMIC_LONG_INIT(0);
> +
> +mm_alloc_free_hook_t set_mm_alloc_free_hook(mm_alloc_free_hook_t hook)
> +{
> +       const mm_alloc_free_hook_t old_hook =
> +               (mm_alloc_free_hook_t)atomic_long_read(&alloc_free_hook);
> +
> +       atomic_long_set(&alloc_free_hook, (long)hook);
> +       pr_info("MM alloc/free hook set to 0x%p (was 0x%p)\n", hook, old_hook);
> +
> +       return old_hook;
> +}
> +EXPORT_SYMBOL(set_mm_alloc_free_hook);
> +
> +static inline void call_alloc_free_hook(int pages)
> +{
> +       const mm_alloc_free_hook_t hook =
> +               (mm_alloc_free_hook_t)atomic_long_read(&alloc_free_hook);
> +       if (hook)
> +               hook(pages);
> +}
> +#endif
> +
>  #ifdef CONFIG_DEBUG_VM
>  static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
>  {
> @@ -2298,6 +2322,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
>        put_mems_allowed();
>
>        trace_mm_page_alloc(page, order, gfp_mask, migratetype);
> +#ifdef CONFIG_MM_ALLOC_FREE_HOOK
> +       call_alloc_free_hook(1 << order);
> +#endif
> +
>        return page;
>  }
>  EXPORT_SYMBOL(__alloc_pages_nodemask);
> @@ -2345,6 +2373,9 @@ void __free_pages(struct page *page, unsigned int order)
>                        free_hot_cold_page(page, 0);
>                else
>                        __free_pages_ok(page, order);
> +#ifdef CONFIG_MM_ALLOC_FREE_HOOK
> +               call_alloc_free_hook(-(1 << order));
> +#endif
>        }
>  }

No, we definitely don't want to allow random modules to insert hooks
to the page allocator:

  Nacked-by: Pekka Enberg <penberg@xxxxxxxxxx>

Can't we introduce some super-lightweight lowmem_{alloc|free}_hook()
hooks that live in mm/lowmem.c and call those directly? If you need to
support different ABIs for lowmem notifier, N9, and Android, you could
make that observer code more generic, no? The swaphook people might be
interested in that as well.

                           Pekka
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/