Re: [PATCH v2] zsmalloc: Add Kconfig for enabling PTE method

[Ric Mason]

On 02/06/2013 10:17 AM, Minchan Kim wrote:
> Zsmalloc has two methods 1) copy-based and 2) pte-based to access
> allocations that span two pages. You can see history why we supported
> two approach from [1].
>
> In summary, copy-based method is 3 times fater in x86 while pte-based
> is 6 times faster in ARM.

Why in some arches copy-based method is better and in the other arches 
pte-based is better? What's the root reason?

> But it was bad choice that adding hard coding to select architecture
> which want to use pte based method. This patch removed it and adds
> new Kconfig to select the approach.
>
> This patch is based on next-20130205.
>
> [1] https://lkml.org/lkml/2012/7/11/58
>
> * Changelog from v1
>    * Fix CONFIG_PGTABLE_MAPPING in zsmalloc-main.c - Greg
>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Seth Jennings <sjenning@xxxxxxxxxxxxxxxxxx>
> Cc: Nitin Gupta <ngupta@xxxxxxxxxx>
> Cc: Dan Magenheimer <dan.magenheimer@xxxxxxxxxx>
> Cc: Konrad Rzeszutek Wilk <konrad@xxxxxxxxxx>
> Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
> ---
>   drivers/staging/zsmalloc/Kconfig         | 12 ++++++++++++
>   drivers/staging/zsmalloc/zsmalloc-main.c | 20 +++++---------------
>   2 files changed, 17 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/staging/zsmalloc/Kconfig b/drivers/staging/zsmalloc/Kconfig
> index 9084565..232b3b6 100644
> --- a/drivers/staging/zsmalloc/Kconfig
> +++ b/drivers/staging/zsmalloc/Kconfig
> @@ -8,3 +8,15 @@ config ZSMALLOC
>   	  non-standard allocator interface where a handle, not a pointer, is
>   	  returned by an alloc().  This handle must be mapped in order to
>   	  access the allocated space.
> +
> +config PGTABLE_MAPPING
> +        bool "Use page table mapping to access allocations that span two pages"
> +        depends on ZSMALLOC
> +        default n
> +        help
> +	  By default, zsmalloc uses a copy-based object mapping method to access
> +	  allocations that span two pages. However, if a particular architecture
> +	  performs VM mapping faster than copying, then you should select this.
> +	  This causes zsmalloc to use page table mapping rather than copying
> +	  for object mapping. You can check speed with zsmalloc benchmark[1].
> +	  [1] https://github.com/spartacus06/zsmalloc
> diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
> index 06f73a9..2c1805c 100644
> --- a/drivers/staging/zsmalloc/zsmalloc-main.c
> +++ b/drivers/staging/zsmalloc/zsmalloc-main.c
> @@ -207,6 +207,7 @@ struct zs_pool {
>   	struct size_class size_class[ZS_SIZE_CLASSES];
>   
>   	gfp_t flags;	/* allocation flags used when growing pool */
> +
>   };
>   
>   /*
> @@ -218,19 +219,8 @@ struct zs_pool {
>   #define CLASS_IDX_MASK	((1 << CLASS_IDX_BITS) - 1)
>   #define FULLNESS_MASK	((1 << FULLNESS_BITS) - 1)
>   
> -/*
> - * By default, zsmalloc uses a copy-based object mapping method to access
> - * allocations that span two pages. However, if a particular architecture
> - * performs VM mapping faster than copying, then it should be added here
> - * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
> - * page table mapping rather than copying for object mapping.
> -*/
> -#if defined(CONFIG_ARM)
> -#define USE_PGTABLE_MAPPING
> -#endif
> -
>   struct mapping_area {
> -#ifdef USE_PGTABLE_MAPPING
> +#ifdef CONFIG_PGTABLE_MAPPING
>   	struct vm_struct *vm; /* vm area for mapping object that span pages */
>   #else
>   	char *vm_buf; /* copy buffer for objects that span pages */
> @@ -622,7 +612,7 @@ static struct page *find_get_zspage(struct size_class *class)
>   	return page;
>   }
>   
> -#ifdef USE_PGTABLE_MAPPING
> +#ifdef CONFIG_PGTABLE_MAPPING
>   static inline int __zs_cpu_up(struct mapping_area *area)
>   {
>   	/*
> @@ -663,7 +653,7 @@ static inline void __zs_unmap_object(struct mapping_area *area,
>   	flush_tlb_kernel_range(addr, end);
>   }
>   
> -#else /* USE_PGTABLE_MAPPING */
> +#else /* CONFIG_PGTABLE_MAPPING*/
>   
>   static inline int __zs_cpu_up(struct mapping_area *area)
>   {
> @@ -741,7 +731,7 @@ out:
>   	pagefault_enable();
>   }
>   
> -#endif /* USE_PGTABLE_MAPPING */
> +#endif /* CONFIG_PGTABLE_MAPPING */
>   
>   static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
>   				void *pcpu)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/