lkml.org 
[lkml]   [2019]   [Jun]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v1 1/6] mm: Adjust shuffle code to allow for future coalescing
On Tue, Jun 25, 2019 at 12:56 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 20.06.19 00:33, Alexander Duyck wrote:
> > From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> >
> > This patch is meant to move the head/tail adding logic out of the shuffle
> > code and into the __free_one_page function since ultimately that is where
> > it is really needed anyway. By doing this we should be able to reduce the
> > overhead and can consolidate all of the list addition bits in one spot.
> >
> > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> > ---
> > include/linux/mmzone.h | 12 --------
> > mm/page_alloc.c | 70 +++++++++++++++++++++++++++---------------------
> > mm/shuffle.c | 24 ----------------
> > mm/shuffle.h | 35 ++++++++++++++++++++++++
> > 4 files changed, 74 insertions(+), 67 deletions(-)
> >
> > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> > index 427b79c39b3c..4c07af2cfc2f 100644
> > --- a/include/linux/mmzone.h
> > +++ b/include/linux/mmzone.h
> > @@ -116,18 +116,6 @@ 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
> > -static inline void add_to_free_area_random(struct page *page,
> > - struct free_area *area, int migratetype)
> > -{
> > - add_to_free_area(page, area, migratetype);
> > -}
> > -#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/mm/page_alloc.c b/mm/page_alloc.c
> > index f4651a09948c..ec344ce46587 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -830,6 +830,36 @@ static inline struct capture_control *task_capc(struct zone *zone)
> > #endif /* CONFIG_COMPACTION */
> >
> > /*
> > + * If this is not the largest possible page, check if the buddy
> > + * of the next-highest order is free. If it is, it's possible
> > + * that pages are being freed that will coalesce soon. In case,
> > + * that is happening, add the free page to the tail of the list
> > + * so it's less likely to be used soon and more likely to be merged
> > + * as a higher order page
> > + */
> > +static inline bool
> > +buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
> > + struct page *page, unsigned int order)
> > +{
> > + struct page *higher_page, *higher_buddy;
> > + unsigned long combined_pfn;
> > +
> > + if (is_shuffle_order(order) || order >= (MAX_ORDER - 2))
>
> My intuition tells me you can drop the () around "MAX_ORDER - 2"

I dunno, I always kind of prefer to use the parenthesis in these cases
for readability. I suppose I can drop it though.

> > + return false;
>
> Guess the "is_shuffle_order(order)" check should rather be performed by
> the caller, before calling this function.

I could do that, however I am not sure it adds much. I am pretty sure
the resultant code would be the same. Where things would be a bit more
complicated is that I would then have to probably look at adding a
variable to trap the output of is_shuffle_tail_page or
buddy_merge_likely.

> > +
> > + if (!pfn_valid_within(buddy_pfn))
> > + return false;
> > +
> > + combined_pfn = buddy_pfn & pfn;
> > + higher_page = page + (combined_pfn - pfn);
> > + buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
> > + higher_buddy = higher_page + (buddy_pfn - combined_pfn);
> > +
> > + return pfn_valid_within(buddy_pfn) &&
> > + page_is_buddy(higher_page, higher_buddy, order + 1);
> > +}
> > +
> > +/*
> > * Freeing function for a buddy system allocator.
> > *
> > * The concept of a buddy system is to maintain direct-mapped table
> > @@ -858,11 +888,12 @@ static inline void __free_one_page(struct page *page,
> > struct zone *zone, unsigned int order,
> > int migratetype)
> > {
> > - unsigned long combined_pfn;
> > + struct capture_control *capc = task_capc(zone);
> > unsigned long uninitialized_var(buddy_pfn);
> > - struct page *buddy;
> > + unsigned long combined_pfn;
> > + struct free_area *area;
> > unsigned int max_order;
> > - struct capture_control *capc = task_capc(zone);
> > + struct page *buddy;
> >
> > max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
> >
> > @@ -931,35 +962,12 @@ static inline void __free_one_page(struct page *page,
> > done_merging:
> > set_page_order(page, order);
> >
> > - /*
> > - * If this is not the largest possible page, check if the buddy
> > - * of the next-highest order is free. If it is, it's possible
> > - * that pages are being freed that will coalesce soon. In case,
> > - * that is happening, add the free page to the tail of the list
> > - * 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)
> > - && !is_shuffle_order(order)) {
> > - struct page *higher_page, *higher_buddy;
> > - combined_pfn = buddy_pfn & pfn;
> > - higher_page = page + (combined_pfn - pfn);
> > - buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
> > - higher_buddy = higher_page + (buddy_pfn - combined_pfn);
> > - if (pfn_valid_within(buddy_pfn) &&
> > - page_is_buddy(higher_page, higher_buddy, order + 1)) {
> > - add_to_free_area_tail(page, &zone->free_area[order],
> > - migratetype);
> > - return;
> > - }
> > - }
> > -
> > - if (is_shuffle_order(order))
> > - add_to_free_area_random(page, &zone->free_area[order],
> > - migratetype);
> > + area = &zone->free_area[order];
> > + if (buddy_merge_likely(pfn, buddy_pfn, page, order) ||
> > + is_shuffle_tail_page(order))
> > + add_to_free_area_tail(page, area, migratetype);
>
> I would prefer here something like
>
> if (is_shuffle_order(order)) {
> if (add_shuffle_order_to_tail(order))
> add_to_free_area_tail(page, area, migratetype);
> else
> add_to_free_area(page, area, migratetype);
> } else if (buddy_merge_likely(pfn, buddy_pfn, page, order)) {
> add_to_free_area_tail(page, area, migratetype);
> } else {
> add_to_free_area(page, area, migratetype);
> }
>
> dropping "is_shuffle_order()" from buddy_merge_likely()
>
> Especially, the name "is_shuffle_tail_page(order)" suggests that you are
> passing a page.

Okay, I can look at renaming that. I will probably look at just using
a variable instead of nesting the if statements like that. Otherwise
that is going to get pretty messy fairly quickly.

> > else
> > - add_to_free_area(page, &zone->free_area[order], migratetype);
> > -
> > + add_to_free_area(page, area, migratetype);
> > }
> >
> > /*
> > diff --git a/mm/shuffle.c b/mm/shuffle.c
> > index 3ce12481b1dc..55d592e62526 100644
> > --- a/mm/shuffle.c
> > +++ b/mm/shuffle.c
> > @@ -4,7 +4,6 @@
> > #include <linux/mm.h>
> > #include <linux/init.h>
> > #include <linux/mmzone.h>
> > -#include <linux/random.h>
> > #include <linux/moduleparam.h>
> > #include "internal.h"
> > #include "shuffle.h"
> > @@ -182,26 +181,3 @@ 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)
> > -{
> > - static u64 rand;
> > - static u8 rand_bits;
> > -
> > - /*
> > - * The lack of locking is deliberate. If 2 threads race to
> > - * update the rand state it just adds to the entropy.
> > - */
> > - if (rand_bits == 0) {
> > - rand_bits = 64;
> > - rand = get_random_u64();
> > - }
> > -
> > - if (rand & 1)
> > - add_to_free_area(page, area, migratetype);
> > - else
> > - add_to_free_area_tail(page, area, migratetype);
> > - rand_bits--;
> > - rand >>= 1;
> > -}
> > diff --git a/mm/shuffle.h b/mm/shuffle.h
> > index 777a257a0d2f..3f4edb60a453 100644
> > --- a/mm/shuffle.h
> > +++ b/mm/shuffle.h
> > @@ -3,6 +3,7 @@
> > #ifndef _MM_SHUFFLE_H
> > #define _MM_SHUFFLE_H
> > #include <linux/jump_label.h>
> > +#include <linux/random.h>
> >
> > /*
> > * SHUFFLE_ENABLE is called from the command line enabling path, or by
> > @@ -43,6 +44,35 @@ static inline bool is_shuffle_order(int order)
> > return false;
> > return order >= SHUFFLE_ORDER;
> > }
> > +
> > +static inline bool is_shuffle_tail_page(int order)
> > +{
> > + static u64 rand;
> > + static u8 rand_bits;
> > + u64 rand_old;
> > +
> > + if (!is_shuffle_order(order))
> > + return false;
> > +
> > + /*
> > + * The lack of locking is deliberate. If 2 threads race to
> > + * update the rand state it just adds to the entropy.
> > + */
> > + if (rand_bits-- == 0) {
> > + rand_bits = 64;
> > + rand = get_random_u64();
> > + }
> > +
> > + /*
> > + * Test highest order bit while shifting our random value. This
> > + * should result in us testing for the carry flag following the
> > + * shift.
> > + */
> > + rand_old = rand;
> > + rand <<= 1;
> > +
> > + return rand < rand_old;
> > +}
> > #else
> > static inline void shuffle_free_memory(pg_data_t *pgdat)
> > {
> > @@ -60,5 +90,10 @@ static inline bool is_shuffle_order(int order)
> > {
> > return false;
> > }
> > +
> > +static inline bool is_shuffle_tail_page(int order)
> > +{
> > + return false;
> > +}
> > #endif
> > #endif /* _MM_SHUFFLE_H */
> >
>
>
> --
>
> Thanks,
>
> David / dhildenb

\
 
 \ /
  Last update: 2019-06-28 21:51    [W:0.117 / U:0.008 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site