KVM Archive on lore.kernel.org
 help / color / Atom feed
From: David Hildenbrand <david@redhat.com>
To: Alexander Duyck <alexander.duyck@gmail.com>,
	nitesh@redhat.com, kvm@vger.kernel.org, mst@redhat.com,
	dave.hansen@intel.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, akpm@linux-foundation.org
Cc: yang.zhang.wz@gmail.com, pagupta@redhat.com, riel@surriel.com,
	konrad.wilk@oracle.com, lcapitulino@redhat.com,
	wei.w.wang@intel.com, aarcange@redhat.com, pbonzini@redhat.com,
	dan.j.williams@intel.com, alexander.h.duyck@linux.intel.com
Subject: Re: [PATCH v1 1/6] mm: Adjust shuffle code to allow for future coalescing
Date: Tue, 25 Jun 2019 09:55:38 +0200
Message-ID: <7d959202-b2cd-fe24-5b3c-84e159eafe0a@redhat.com> (raw)
In-Reply-To: <20190619223302.1231.51136.stgit@localhost.localdomain>

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"

> +		return false;

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

> +
> +	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.

>  	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

  reply index

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-19 22:32 [PATCH v1 0/6] mm / virtio: Provide support for paravirtual waste page treatment Alexander Duyck
2019-06-19 22:33 ` [PATCH v1 1/6] mm: Adjust shuffle code to allow for future coalescing Alexander Duyck
2019-06-25  7:55   ` David Hildenbrand [this message]
2019-06-28 19:49     ` Alexander Duyck
2019-06-25 18:25   ` Dave Hansen
2019-06-25 18:26   ` Dave Hansen
2019-06-19 22:33 ` [PATCH v1 2/6] mm: Move set/get_pcppage_migratetype to mmzone.h Alexander Duyck
2019-06-25 18:28   ` Dave Hansen
2019-06-28 19:55     ` Alexander Duyck
2019-06-19 22:33 ` [PATCH v1 3/6] mm: Use zone and order instead of free area in free_list manipulators Alexander Duyck
2019-06-25 18:36   ` Dave Hansen
2019-06-19 22:33 ` [PATCH v1 4/6] mm: Introduce "aerated" pages Alexander Duyck
2019-06-25 19:45   ` Dave Hansen
2019-07-08 17:32     ` Alexander Duyck
2019-06-19 22:33 ` [PATCH v1 5/6] mm: Add logic for separating "aerated" pages from "raw" pages Alexander Duyck
2019-06-25 20:24   ` Dave Hansen
2019-07-08 19:02     ` Alexander Duyck
2019-07-08 19:36       ` Dave Hansen
2019-07-08 22:02         ` Alexander Duyck
2019-06-19 22:33 ` [PATCH v1 6/6] virtio-balloon: Add support for aerating memory via hinting Alexander Duyck
2019-07-16  9:55   ` Michael S. Tsirkin
2019-07-16 14:00     ` Dave Hansen
2019-07-16 14:12       ` David Hildenbrand
2019-07-16 14:17         ` David Hildenbrand
2019-07-16 15:04           ` Michael S. Tsirkin
2019-07-16 14:41         ` Dave Hansen
2019-07-16 15:01           ` Wang, Wei W
2019-07-16 16:12             ` Michael S. Tsirkin
2019-07-16 15:02           ` David Hildenbrand
2019-07-16 15:37     ` Alexander Duyck
2019-07-16 16:07       ` Michael S. Tsirkin
2019-07-16 16:54         ` Alexander Duyck
2019-07-16 17:41           ` Michael S. Tsirkin
2019-07-16 21:06             ` Alexander Duyck
2019-07-17 10:28               ` Michael S. Tsirkin
2019-07-17 16:43                 ` Alexander Duyck
2019-07-18  5:13                   ` Michael S. Tsirkin
2019-07-18 15:34                     ` Alexander Duyck
2019-07-18 16:03                       ` Nitesh Narayan Lal
2019-07-18 20:27                         ` Michael S. Tsirkin
2019-07-18 16:07                       ` Michael S. Tsirkin
2019-07-18 20:29                         ` Alexander Duyck
2019-07-18 20:37                           ` Michael S. Tsirkin
2019-07-18 20:54                             ` Alexander Duyck
2019-07-18 20:24                       ` Michael S. Tsirkin
2019-07-18 20:34                         ` Alexander Duyck
2019-07-18 20:48                           ` Michael S. Tsirkin
2019-07-18 21:09                             ` Alexander Duyck
2019-06-19 22:37 ` [PATCH v1 QEMU] QEMU: Provide a interface for hinting based off of the balloon infrastructure Alexander Duyck
2019-06-25  7:42 ` [PATCH v1 0/6] mm / virtio: Provide support for paravirtual waste page treatment David Hildenbrand
2019-06-25 14:10   ` Dave Hansen
2019-06-25 17:00     ` Alexander Duyck
2019-06-25 18:12       ` David Hildenbrand
2019-06-25 18:22       ` Dave Hansen
2019-07-15  9:41         ` David Hildenbrand
2019-07-15 14:57           ` Alexander Duyck
2019-06-25 16:09   ` Alexander Duyck
2019-06-26  9:01   ` Christophe de Dinechin
2019-06-26  9:12     ` David Hildenbrand

Reply instructions:

You may reply publically 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=7d959202-b2cd-fe24-5b3c-84e159eafe0a@redhat.com \
    --to=david@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=alexander.h.duyck@linux.intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mst@redhat.com \
    --cc=nitesh@redhat.com \
    --cc=pagupta@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=riel@surriel.com \
    --cc=wei.w.wang@intel.com \
    --cc=yang.zhang.wz@gmail.com \
    /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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org kvm@archiver.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox