linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Daniel Vacek <neelx@redhat.com>
To: Jia He <hejianet@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Michal Hocko <mhocko@suse.com>,
	Wei Yang <richard.weiyang@gmail.com>,
	Kees Cook <keescook@chromium.org>,
	Laura Abbott <labbott@redhat.com>,
	Vladimir Murzin <vladimir.murzin@arm.com>,
	Philip Derrin <philip@cog.systems>,
	Grygorii Strashko <grygorii.strashko@linaro.org>,
	AKASHI Takahiro <takahiro.akashi@linaro.org>,
	James Morse <james.morse@arm.com>,
	Steve Capper <steve.capper@arm.com>,
	Pavel Tatashin <pasha.tatashin@oracle.com>,
	Gioh Kim <gi-oh.kim@profitbricks.com>,
	Vlastimil Babka <vbabka@suse.cz>, Mel Gorman <mgorman@suse.de>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Kemi Wang <kemi.wang@intel.com>, Petr Tesarik <ptesarik@suse.com>,
	YASUAKI ISHIMATSU <yasu.isimatu@gmail.com>,
	Andrey Ryabinin <aryabinin@virtuozzo.com>,
	Nikolay Borisov <nborisov@suse.com>,
	Daniel Jordan <daniel.m.jordan@oracle.com>,
	Eugeniu Rosca <erosca@de.adit-jv.com>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	open list <linux-kernel@vger.kernel.org>,
	linux-mm@kvack.org, Jia He <jia.he@hxt-semitech.com>
Subject: Re: [PATCH v5 2/5] arm: arm64: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn()
Date: Mon, 2 Apr 2018 10:01:25 +0200	[thread overview]
Message-ID: <CACjP9X-kwbMY2uHgfTthz0ozxsEKqJUX7KFUEbMqVLjs__r6Xw@mail.gmail.com> (raw)
In-Reply-To: <1522636236-12625-3-git-send-email-hejianet@gmail.com>

On Mon, Apr 2, 2018 at 4:30 AM, Jia He <hejianet@gmail.com> wrote:
> Commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns
> where possible") optimized the loop in memmap_init_zone(). But there is
> still some room for improvement. E.g. if pfn and pfn+1 are in the same
> memblock region, we can simply pfn++ instead of doing the binary search
> in memblock_next_valid_pfn.
>
> Signed-off-by: Jia He <jia.he@hxt-semitech.com>
> ---
>  arch/arm/include/asm/page.h   |  1 +
>  arch/arm/mm/init.c            | 28 ++++++++++++++++++++++------
>  arch/arm64/include/asm/page.h |  1 +
>  arch/arm64/mm/init.c          | 28 ++++++++++++++++++++++------
>  4 files changed, 46 insertions(+), 12 deletions(-)
>
> diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
> index 489875c..f38909c 100644
> --- a/arch/arm/include/asm/page.h
> +++ b/arch/arm/include/asm/page.h
> @@ -157,6 +157,7 @@ extern void copy_page(void *to, const void *from);
>  typedef struct page *pgtable_t;
>
>  #ifdef CONFIG_HAVE_ARCH_PFN_VALID
> +extern int early_region_idx;

I believe this is not needed anymore.

>  extern int pfn_valid(unsigned long);
>  extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
>  #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
> index 0fb85ca..06ed190 100644
> --- a/arch/arm/mm/init.c
> +++ b/arch/arm/mm/init.c
> @@ -193,6 +193,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
>  }
>
>  #ifdef CONFIG_HAVE_ARCH_PFN_VALID
> +int early_region_idx __meminitdata = -1;

static?

> +
>  int pfn_valid(unsigned long pfn)
>  {
>         return memblock_is_map_memory(__pfn_to_phys(pfn));
> @@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid);
>  unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
>  {
>         struct memblock_type *type = &memblock.memory;
> +       struct memblock_region *regions = type->regions;
>         unsigned int right = type->cnt;
>         unsigned int mid, left = 0;
> +       unsigned long start_pfn, end_pfn;
>         phys_addr_t addr = PFN_PHYS(++pfn);
>
> +       /* fast path, return pfn+1 if next pfn is in the same region */
> +       if (early_region_idx != -1) {
> +               start_pfn = PFN_DOWN(regions[early_region_idx].base);
> +               end_pfn = PFN_DOWN(regions[early_region_idx].base +
> +                               regions[early_region_idx].size);
> +
> +               if (pfn >= start_pfn && pfn < end_pfn)
> +                       return pfn;
> +       }
> +
> +       /* slow path, do the binary searching */
>         do {
>                 mid = (right + left) / 2;
>
> -               if (addr < type->regions[mid].base)
> +               if (addr < regions[mid].base)
>                         right = mid;
> -               else if (addr >= (type->regions[mid].base +
> -                                 type->regions[mid].size))
> +               else if (addr >= (regions[mid].base + regions[mid].size))
>                         left = mid + 1;
>                 else {
> -                       /* addr is within the region, so pfn is valid */
> +                       early_region_idx = mid;
>                         return pfn;
>                 }
>         } while (left < right);
>
>         if (right == type->cnt)
>                 return -1UL;
> -       else
> -               return PHYS_PFN(type->regions[right].base);
> +
> +       early_region_idx = right;
> +
> +       return PHYS_PFN(regions[early_region_idx].base);
>  }
>  EXPORT_SYMBOL(memblock_next_valid_pfn);
>  #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
> diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
> index e57d3f2..f0d8c8e5 100644
> --- a/arch/arm64/include/asm/page.h
> +++ b/arch/arm64/include/asm/page.h
> @@ -38,6 +38,7 @@ extern void clear_page(void *to);
>  typedef struct page *pgtable_t;
>
>  #ifdef CONFIG_HAVE_ARCH_PFN_VALID
> +extern int early_region_idx;

ditto

>  extern int pfn_valid(unsigned long);
>  extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
>  #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 13e43ff..342e4e2 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -285,6 +285,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
>  #endif /* CONFIG_NUMA */
>
>  #ifdef CONFIG_HAVE_ARCH_PFN_VALID
> +int early_region_idx __meminitdata = -1;

ditto

--nX

> +
>  int pfn_valid(unsigned long pfn)
>  {
>         return memblock_is_map_memory(pfn << PAGE_SHIFT);
> @@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid);
>  unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
>  {
>         struct memblock_type *type = &memblock.memory;
> +       struct memblock_region *regions = type->regions;
>         unsigned int right = type->cnt;
>         unsigned int mid, left = 0;
> +       unsigned long start_pfn, end_pfn;
>         phys_addr_t addr = PFN_PHYS(++pfn);
>
> +       /* fast path, return pfn+1 if next pfn is in the same region */
> +       if (early_region_idx != -1) {
> +               start_pfn = PFN_DOWN(regions[early_region_idx].base);
> +               end_pfn = PFN_DOWN(regions[early_region_idx].base +
> +                               regions[early_region_idx].size);
> +
> +               if (pfn >= start_pfn && pfn < end_pfn)
> +                       return pfn;
> +       }
> +
> +       /* slow path, do the binary searching */
>         do {
>                 mid = (right + left) / 2;
>
> -               if (addr < type->regions[mid].base)
> +               if (addr < regions[mid].base)
>                         right = mid;
> -               else if (addr >= (type->regions[mid].base +
> -                                 type->regions[mid].size))
> +               else if (addr >= (regions[mid].base + regions[mid].size))
>                         left = mid + 1;
>                 else {
> -                       /* addr is within the region, so pfn is valid */
> +                       early_region_idx = mid;
>                         return pfn;
>                 }
>         } while (left < right);
>
>         if (right == type->cnt)
>                 return -1UL;
> -       else
> -               return PHYS_PFN(type->regions[right].base);
> +
> +       early_region_idx = right;
> +
> +       return PHYS_PFN(regions[early_region_idx].base);
>  }
>  EXPORT_SYMBOL(memblock_next_valid_pfn);
>  #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
> --
> 2.7.4
>

  parent reply	other threads:[~2018-04-02  8:01 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-02  2:30 [PATCH v5 0/5] optimize memblock_next_valid_pfn and early_pfn_valid on arm and arm64 Jia He
2018-04-02  2:30 ` [PATCH v5 1/5] mm: page_alloc: remain memblock_next_valid_pfn() " Jia He
2018-04-02  6:55   ` Ard Biesheuvel
2018-04-02  7:49     ` Jia He
2018-04-02  7:53       ` Ard Biesheuvel
2018-04-03  3:07         ` Jia He
2018-04-11  4:47         ` Jia He
2018-04-02  7:50   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 2/5] arm: arm64: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn() Jia He
2018-04-02  6:57   ` Ard Biesheuvel
2018-04-02  8:43     ` Daniel Vacek
2018-04-02  8:01   ` Daniel Vacek [this message]
2018-04-02 15:07   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 3/5] mm/memblock: introduce memblock_search_pfn_regions() Jia He
2018-04-02  6:57   ` Ard Biesheuvel
2018-04-02  2:30 ` [PATCH v5 4/5] arm64: introduce pfn_valid_region() Jia He
2018-04-02  6:59   ` Ard Biesheuvel
2018-04-02 18:53   ` kbuild test robot
2018-04-02  2:30 ` [PATCH v5 5/5] mm: page_alloc: reduce unnecessary binary search in early_pfn_valid() Jia He
2018-04-02  7:00   ` Ard Biesheuvel
2018-04-02  8:15     ` Jia He

Reply instructions:

You may reply publicly 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=CACjP9X-kwbMY2uHgfTthz0ozxsEKqJUX7KFUEbMqVLjs__r6Xw@mail.gmail.com \
    --to=neelx@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=aryabinin@virtuozzo.com \
    --cc=catalin.marinas@arm.com \
    --cc=daniel.m.jordan@oracle.com \
    --cc=erosca@de.adit-jv.com \
    --cc=gi-oh.kim@profitbricks.com \
    --cc=grygorii.strashko@linaro.org \
    --cc=hannes@cmpxchg.org \
    --cc=hejianet@gmail.com \
    --cc=james.morse@arm.com \
    --cc=jia.he@hxt-semitech.com \
    --cc=keescook@chromium.org \
    --cc=kemi.wang@intel.com \
    --cc=labbott@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=nborisov@suse.com \
    --cc=pasha.tatashin@oracle.com \
    --cc=philip@cog.systems \
    --cc=ptesarik@suse.com \
    --cc=richard.weiyang@gmail.com \
    --cc=steve.capper@arm.com \
    --cc=takahiro.akashi@linaro.org \
    --cc=vbabka@suse.cz \
    --cc=vladimir.murzin@arm.com \
    --cc=will.deacon@arm.com \
    --cc=yasu.isimatu@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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).