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
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160908111353.GD17331@node>
Date:   Thu, 8 Sep 2016 14:13:53 +0300
From:   "Kirill A. Shutemov" <kirill@...temov.name>
To:     "Huang, Ying" <ying.huang@...el.com>
Cc:     Andrew Morton <akpm@...ux-foundation.org>, tim.c.chen@...el.com,
        dave.hansen@...el.com, andi.kleen@...el.com, aaron.lu@...el.com,
        linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        Andrea Arcangeli <aarcange@...hat.com>,
        "Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
        Hugh Dickins <hughd@...gle.com>, Shaohua Li <shli@...nel.org>,
        Minchan Kim <minchan@...nel.org>,
        Rik van Riel <riel@...hat.com>
Subject: Re: [PATCH -v3 05/10] mm, THP, swap: Add get_huge_swap_page()

On Wed, Sep 07, 2016 at 09:46:04AM -0700, Huang, Ying wrote:
> From: Huang Ying <ying.huang@...el.com>
> 
> A variation of get_swap_page(), get_huge_swap_page(), is added to
> allocate a swap cluster (512 swap slots) based on the swap cluster
> allocation function.  A fair simple algorithm is used, that is, only the
> first swap device in priority list will be tried to allocate the swap
> cluster.  The function will fail if the trying is not successful, and
> the caller will fallback to allocate a single swap slot instead.  This
> works good enough for normal cases.

For normal cases, yes. But the limitation is not obvious for users and
performance difference after small change in configuration could be
puzzling.

At least this must be documented somewhere.

> 
> This will be used for the THP (Transparent Huge Page) swap support.
> Where get_huge_swap_page() will be used to allocate one swap cluster for
> each THP swapped out.
> 
> Cc: Andrea Arcangeli <aarcange@...hat.com>
> Cc: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
> Cc: Hugh Dickins <hughd@...gle.com>
> Cc: Shaohua Li <shli@...nel.org>
> Cc: Minchan Kim <minchan@...nel.org>
> Cc: Rik van Riel <riel@...hat.com>
> Signed-off-by: "Huang, Ying" <ying.huang@...el.com>
> ---
>  include/linux/swap.h | 24 +++++++++++++++++++++++-
>  mm/swapfile.c        | 18 ++++++++++++------
>  2 files changed, 35 insertions(+), 7 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 75aad24..bc0a84d 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -399,7 +399,7 @@ static inline long get_nr_swap_pages(void)
>  }
>  
>  extern void si_swapinfo(struct sysinfo *);
> -extern swp_entry_t get_swap_page(void);
> +extern swp_entry_t __get_swap_page(bool huge);
>  extern swp_entry_t get_swap_page_of_type(int);
>  extern int add_swap_count_continuation(swp_entry_t, gfp_t);
>  extern void swap_shmem_alloc(swp_entry_t);
> @@ -419,6 +419,23 @@ extern bool reuse_swap_page(struct page *, int *);
>  extern int try_to_free_swap(struct page *);
>  struct backing_dev_info;
>  
> +static inline swp_entry_t get_swap_page(void)
> +{
> +	return __get_swap_page(false);
> +}
> +
> +#ifdef CONFIG_THP_SWAP_CLUSTER
> +static inline swp_entry_t get_huge_swap_page(void)
> +{
> +	return __get_swap_page(true);
> +}
> +#else
> +static inline swp_entry_t get_huge_swap_page(void)
> +{
> +	return (swp_entry_t) {0};
> +}
> +#endif
> +
>  #else /* CONFIG_SWAP */
>  
>  #define swap_address_space(entry)		(NULL)
> @@ -525,6 +542,11 @@ static inline swp_entry_t get_swap_page(void)
>  	return entry;
>  }
>  
> +static inline swp_entry_t get_huge_swap_page(void)
> +{
> +	return (swp_entry_t) {0};
> +}
> +
>  #endif /* CONFIG_SWAP */
>  
>  #ifdef CONFIG_MEMCG
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 0132e8c..3d2bd1f 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -760,14 +760,15 @@ static inline unsigned long swap_alloc_huge_cluster(struct swap_info_struct *si)
>  }
>  #endif
>  
> -swp_entry_t get_swap_page(void)
> +swp_entry_t __get_swap_page(bool huge)
>  {
>  	struct swap_info_struct *si, *next;
>  	pgoff_t offset;
> +	int nr_pages = huge_cluster_nr_entries(huge);
>  
> -	if (atomic_long_read(&nr_swap_pages) <= 0)
> +	if (atomic_long_read(&nr_swap_pages) < nr_pages)
>  		goto noswap;
> -	atomic_long_dec(&nr_swap_pages);
> +	atomic_long_sub(nr_pages, &nr_swap_pages);
>  
>  	spin_lock(&swap_avail_lock);
>  
> @@ -795,10 +796,15 @@ start_over:
>  		}
>  
>  		/* This is called for allocating swap entry for cache */
> -		offset = scan_swap_map(si, SWAP_HAS_CACHE);
> +		if (likely(nr_pages == 1))
> +			offset = scan_swap_map(si, SWAP_HAS_CACHE);
> +		else
> +			offset = swap_alloc_huge_cluster(si);
>  		spin_unlock(&si->lock);
>  		if (offset)
>  			return swp_entry(si->type, offset);
> +		else if (unlikely(nr_pages != 1))
> +			goto fail_alloc;
>  		pr_debug("scan_swap_map of si %d failed to find offset\n",
>  		       si->type);
>  		spin_lock(&swap_avail_lock);
> @@ -818,8 +824,8 @@ nextsi:
>  	}
>  
>  	spin_unlock(&swap_avail_lock);
> -
> -	atomic_long_inc(&nr_swap_pages);
> +fail_alloc:
> +	atomic_long_add(nr_pages, &nr_swap_pages);
>  noswap:
>  	return (swp_entry_t) {0};
>  }
> -- 
> 2.8.1
> 

-- 
 Kirill A. Shutemov

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ