On Tue 29-01-19 21:02:26, Dan Williams wrote:
> When freeing a page with an order >= shuffle_page_order randomly select
> the front or back of the list for insertion.
>
> While the mm tries to defragment physical pages into huge pages this can
> tend to make the page allocator more predictable over time. Inject the
> front-back randomness to preserve the initial randomness established by
> shuffle_free_memory() when the kernel was booted.
>
> The overhead of this manipulation is constrained by only being applied
> for MAX_ORDER sized pages by default.
I have asked in v7 but didn't get any response. Do we really ned per
free_area random pool? Why a global one is not sufficient?
> Cc: Michal Hocko <mhocko@xxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
> Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>
> Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
> ---
> include/linux/mmzone.h | 12 ++++++++++++
> include/linux/shuffle.h | 12 ++++++++++++
> mm/page_alloc.c | 11 +++++++++--
> mm/shuffle.c | 16 ++++++++++++++++
> 4 files changed, 49 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 6ab8b58c6481..d42aafe23045 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -98,6 +98,10 @@ extern int page_group_by_mobility_disabled;
> struct free_area {
> struct list_head free_list[MIGRATE_TYPES];
> unsigned long nr_free;
> +#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
> + u64 rand;
> + u8 rand_bits;
> +#endif
> };
>
> /* Used for pages not on another list */
> @@ -116,6 +120,14 @@ static inline void add_to_free_area_tail(struct page *page, struct free_area *ar
> area->nr_free++;
> }
>
> +#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
> +/* Used to preserve page allocation order entropy */
> +void add_to_free_area_random(struct page *page, struct free_area *area,
> + int migratetype);
> +#else
> +#define add_to_free_area_random add_to_free_area
> +#endif
> +
> /* Used for pages which are on another list */
> static inline void move_to_free_area(struct page *page, struct free_area *area,
> int migratetype)
> diff --git a/include/linux/shuffle.h b/include/linux/shuffle.h
> index bed2d2901d13..649498442aa0 100644
> --- a/include/linux/shuffle.h
> +++ b/include/linux/shuffle.h
> @@ -29,6 +29,13 @@ static inline void shuffle_zone(struct zone *z)
> return;
> __shuffle_zone(z);
> }
> +
> +static inline bool is_shuffle_order(int order)
> +{
> + if (!static_branch_unlikely(&page_alloc_shuffle_key))
> + return false;
> + return order >= SHUFFLE_ORDER;
> +}
> #else
> static inline void shuffle_free_memory(pg_data_t *pgdat)
> {
> @@ -41,5 +48,10 @@ static inline void shuffle_zone(struct zone *z)
> static inline void page_alloc_shuffle(enum mm_shuffle_ctl ctl)
> {
> }
> +
> +static inline bool is_shuffle_order(int order)
> +{
> + return false;
> +}
> #endif
> #endif /* _MM_SHUFFLE_H */
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 1cb9a467e451..7895f8bd1a32 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -43,6 +43,7 @@
> #include <linux/mempolicy.h>
> #include <linux/memremap.h>
> #include <linux/stop_machine.h>
> +#include <linux/random.h>
> #include <linux/sort.h>
> #include <linux/pfn.h>
> #include <linux/backing-dev.h>
> @@ -889,7 +890,8 @@ static inline void __free_one_page(struct page *page,
> * so it's less likely to be used soon and more likely to be merged
> * as a higher order page
> */
> - if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
> + if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
> + && !is_shuffle_order(order)) {
> struct page *higher_page, *higher_buddy;
> combined_pfn = buddy_pfn & pfn;
> higher_page = page + (combined_pfn - pfn);
> @@ -903,7 +905,12 @@ static inline void __free_one_page(struct page *page,
> }
> }
>
> - add_to_free_area(page, &zone->free_area[order], migratetype);
> + if (is_shuffle_order(order))
> + add_to_free_area_random(page, &zone->free_area[order],
> + migratetype);
> + else
> + add_to_free_area(page, &zone->free_area[order], migratetype);
> +
> }
>
> /*
> diff --git a/mm/shuffle.c b/mm/shuffle.c
> index db517cdbaebe..0da7d1826c6a 100644
> --- a/mm/shuffle.c
> +++ b/mm/shuffle.c
> @@ -186,3 +186,19 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
> for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
> shuffle_zone(z);
> }
> +
> +void add_to_free_area_random(struct page *page, struct free_area *area,
> + int migratetype)
> +{
> + if (area->rand_bits == 0) {
> + area->rand_bits = 64;
> + area->rand = get_random_u64();
> + }
> +
> + if (area->rand & 1)
> + add_to_free_area(page, area, migratetype);
> + else
> + add_to_free_area_tail(page, area, migratetype);
> + area->rand_bits--;
> + area->rand >>= 1;
> +}
>
--
Michal Hocko
SUSE Labs
