Re: [PATCH v3 2/4] pagemap: add mmap-exclusive bit for marking pages mapped only here

[Mark Williamson]

This looks good from our side - thanks!

Reviewed-by: mwilliamson@xxxxxxxxxxxxxxxxx
Tested-by: mwilliamson@xxxxxxxxxxxxxxxxx

On Tue, Jun 9, 2015 at 9:00 PM, Konstantin Khlebnikov <koct9i@xxxxxxxxx> wrote:
> From: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
>
> This patch sets bit 56 in pagemap if this page is mapped only once.
> It allows to detect exclusively used pages without exposing PFN:
>
> present file exclusive state
> 0       0    0         non-present
> 1       1    0         file page mapped somewhere else
> 1       1    1         file page mapped only here
> 1       0    0         anon non-CoWed page (shared with parent/child)
> 1       0    1         anon CoWed page (or never forked)
>
> CoWed pages in MAP_FILE|MAP_PRIVATE areas are anon in this context.
>
> Mmap-exclusive bit doesn't reflect potential page-sharing via swapcache:
> page could be mapped once but has several swap-ptes which point to it.
> Application could detect that by swap bit in pagemap entry and touch
> that pte via /proc/pid/mem to get real information.
>
> Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
> Link: http://lkml.kernel.org/r/CAEVpBa+_RyACkhODZrRvQLs80iy0sqpdrd0AaP_-tgnX3Y9yNQ@xxxxxxxxxxxxxx
>
> ---
>
> v2:
> * handle transparent huge pages
> * invert bit and rename shared -> exclusive (less confusing name)
> ---
>  Documentation/vm/pagemap.txt |    3 ++-
>  fs/proc/task_mmu.c           |   10 ++++++++++
>  tools/vm/page-types.c        |   12 ++++++++++++
>  3 files changed, 24 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
> index 6bfbc17..3cfbbb3 100644
> --- a/Documentation/vm/pagemap.txt
> +++ b/Documentation/vm/pagemap.txt
> @@ -16,7 +16,8 @@ There are three components to pagemap:
>      * Bits 0-4   swap type if swapped
>      * Bits 5-54  swap offset if swapped
>      * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
> -    * Bits 56-60 zero
> +    * Bit  56    page exlusively mapped
> +    * Bits 57-60 zero
>      * Bit  61    page is file-page or shared-anon
>      * Bit  62    page swapped
>      * Bit  63    page present
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 21bc251..b02e38f 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -982,6 +982,7 @@ struct pagemapread {
>  #define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
>
>  #define __PM_SOFT_DIRTY      (1LL)
> +#define __PM_MMAP_EXCLUSIVE  (2LL)
>  #define PM_PRESENT          PM_STATUS(4LL)
>  #define PM_SWAP             PM_STATUS(2LL)
>  #define PM_FILE             PM_STATUS(1LL)
> @@ -1074,6 +1075,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
>
>         if (page && !PageAnon(page))
>                 flags |= PM_FILE;
> +       if (page && page_mapcount(page) == 1)
> +               flags2 |= __PM_MMAP_EXCLUSIVE;
>         if ((vma->vm_flags & VM_SOFTDIRTY))
>                 flags2 |= __PM_SOFT_DIRTY;
>
> @@ -1119,6 +1122,13 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
>                 else
>                         pmd_flags2 = 0;
>
> +               if (pmd_present(*pmd)) {
> +                       struct page *page = pmd_page(*pmd);
> +
> +                       if (page_mapcount(page) == 1)
> +                               pmd_flags2 |= __PM_MMAP_EXCLUSIVE;
> +               }
> +
>                 for (; addr != end; addr += PAGE_SIZE) {
>                         unsigned long offset;
>                         pagemap_entry_t pme;
> diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
> index 8bdf16b..3a9f193 100644
> --- a/tools/vm/page-types.c
> +++ b/tools/vm/page-types.c
> @@ -70,9 +70,12 @@
>  #define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
>
>  #define __PM_SOFT_DIRTY      (1LL)
> +#define __PM_MMAP_EXCLUSIVE  (2LL)
>  #define PM_PRESENT          PM_STATUS(4LL)
>  #define PM_SWAP             PM_STATUS(2LL)
> +#define PM_FILE             PM_STATUS(1LL)
>  #define PM_SOFT_DIRTY       __PM_PSHIFT(__PM_SOFT_DIRTY)
> +#define PM_MMAP_EXCLUSIVE   __PM_PSHIFT(__PM_MMAP_EXCLUSIVE)
>
>
>  /*
> @@ -100,6 +103,8 @@
>  #define KPF_SLOB_FREE          49
>  #define KPF_SLUB_FROZEN                50
>  #define KPF_SLUB_DEBUG         51
> +#define KPF_FILE               62
> +#define KPF_MMAP_EXCLUSIVE     63
>
>  #define KPF_ALL_BITS           ((uint64_t)~0ULL)
>  #define KPF_HACKERS_BITS       (0xffffULL << 32)
> @@ -149,6 +154,9 @@ static const char * const page_flag_names[] = {
>         [KPF_SLOB_FREE]         = "P:slob_free",
>         [KPF_SLUB_FROZEN]       = "A:slub_frozen",
>         [KPF_SLUB_DEBUG]        = "E:slub_debug",
> +
> +       [KPF_FILE]              = "F:file",
> +       [KPF_MMAP_EXCLUSIVE]    = "1:mmap_exclusive",
>  };
>
>
> @@ -452,6 +460,10 @@ static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
>
>         if (pme & PM_SOFT_DIRTY)
>                 flags |= BIT(SOFTDIRTY);
> +       if (pme & PM_FILE)
> +               flags |= BIT(FILE);
> +       if (pme & PM_MMAP_EXCLUSIVE)
> +               flags |= BIT(MMAP_EXCLUSIVE);
>
>         return flags;
>  }
>
--
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/