Re: [PATCH v3] mm: Add PM_HUGE_THP_MAPPING to /proc/pid/pagemap

[Mina Almasry <almasrymina@google.com>]

On Sun, Nov 7, 2021 at 2:59 PM Mina Almasry <almasrymina@google.com> wrote:
>
> Add PM_HUGE_THP MAPPING to allow userspace to detect whether a given virt
> address is currently mapped by a transparent huge page or not.
>
> Example use case is a process requesting THPs from the kernel (via
> a huge tmpfs mount for example), for a performance critical region of
> memory.  The userspace may want to query whether the kernel is actually
> backing this memory by hugepages or not.
>
> PM_HUGE_THP_MAPPING bit is set if the virt address is mapped at the PMD
> level and the underlying page is a transparent huge page.
>
> Tested manually by adding logging into transhuge-stress, and by
> allocating THP and querying the PM_HUGE_THP_MAPPING flag at those
> virtual addresses.
>
> Signed-off-by: Mina Almasry <almasrymina@google.com>
>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: David Rientjes rientjes@google.com
> Cc: Paul E. McKenney <paulmckrcu@fb.com>
> Cc: Yu Zhao <yuzhao@google.com>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Peter Xu <peterx@redhat.com>
> Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
> Cc: Florian Schmidt <florian.schmidt@nutanix.com>
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-fsdevel@vger.kernel.org
> Cc: linux-mm@kvack.org
>
> ---
>  Documentation/admin-guide/mm/pagemap.rst      |  3 ++-
>  fs/proc/task_mmu.c                            |  6 +++++-
>  tools/testing/selftests/vm/transhuge-stress.c | 21 +++++++++++++++----
>  3 files changed, 24 insertions(+), 6 deletions(-)
>
> diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst
> index fdc19fbc10839..8a0f0064ff336 100644
> --- a/Documentation/admin-guide/mm/pagemap.rst
> +++ b/Documentation/admin-guide/mm/pagemap.rst
> @@ -23,7 +23,8 @@ There are four components to pagemap:
>      * Bit  56    page exclusively mapped (since 4.2)
>      * Bit  57    pte is uffd-wp write-protected (since 5.13) (see
>        :ref:`Documentation/admin-guide/mm/userfaultfd.rst <userfaultfd>`)
> -    * Bits 57-60 zero
> +    * Bit  58    page is a huge (PMD size) THP mapping
> +    * Bits 59-60 zero
>      * Bit  61    page is file-page or shared-anon (since 3.5)
>      * Bit  62    page swapped
>      * Bit  63    page present
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index ad667dbc96f5c..e10b59064c0b9 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -1302,6 +1302,7 @@ struct pagemapread {
>  #define PM_SOFT_DIRTY          BIT_ULL(55)
>  #define PM_MMAP_EXCLUSIVE      BIT_ULL(56)
>  #define PM_UFFD_WP             BIT_ULL(57)
> +#define PM_HUGE_THP_MAPPING    BIT_ULL(58)
>  #define PM_FILE                        BIT_ULL(61)
>  #define PM_SWAP                        BIT_ULL(62)
>  #define PM_PRESENT             BIT_ULL(63)
> @@ -1409,12 +1410,13 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
>         struct pagemapread *pm = walk->private;
>         spinlock_t *ptl;
>         pte_t *pte, *orig_pte;
> +       u64 flags = 0;
>         int err = 0;
>
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>         ptl = pmd_trans_huge_lock(pmdp, vma);
>         if (ptl) {
> -               u64 flags = 0, frame = 0;
> +               u64 frame = 0;

Sorry again, I just noticed moving flags above is not necessary. I'll
upload v4 with a fix shortly.

>                 pmd_t pmd = *pmdp;
>                 struct page *page = NULL;
>
> @@ -1456,6 +1458,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
>
>                 if (page && page_mapcount(page) == 1)
>                         flags |= PM_MMAP_EXCLUSIVE;
> +               if (page && is_transparent_hugepage(page))
> +                       flags |= PM_HUGE_THP_MAPPING;
>
>                 for (; addr != end; addr += PAGE_SIZE) {
>                         pagemap_entry_t pme = make_pme(frame, flags);
> diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
> index fd7f1b4a96f94..7dce18981fff5 100644
> --- a/tools/testing/selftests/vm/transhuge-stress.c
> +++ b/tools/testing/selftests/vm/transhuge-stress.c
> @@ -16,6 +16,12 @@
>  #include <string.h>
>  #include <sys/mman.h>
>
> +/*
> + * We can use /proc/pid/pagemap to detect whether the kernel was able to find
> + * hugepages or no. This can be very noisy, so is disabled by default.
> + */
> +#define NO_DETECT_HUGEPAGES
> +
>  #define PAGE_SHIFT 12
>  #define HPAGE_SHIFT 21
>
> @@ -23,6 +29,7 @@
>  #define HPAGE_SIZE (1 << HPAGE_SHIFT)
>
>  #define PAGEMAP_PRESENT(ent)   (((ent) & (1ull << 63)) != 0)
> +#define PAGEMAP_THP(ent)       (((ent) & (1ull << 58)) != 0)
>  #define PAGEMAP_PFN(ent)       ((ent) & ((1ull << 55) - 1))
>
>  int pagemap_fd;
> @@ -47,10 +54,16 @@ int64_t allocate_transhuge(void *ptr)
>                         (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
>                 err(2, "read pagemap");
>
> -       if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
> -           PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
> -           !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
> -               return PAGEMAP_PFN(ent[0]);
> +       if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1])) {
> +#ifndef NO_DETECT_HUGEPAGES
> +               if (!PAGEMAP_THP(ent[0]))
> +                       fprintf(stderr, "WARNING: detected non THP page\n");
> +#endif
> +               if (PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
> +                   !(PAGEMAP_PFN(ent[0]) &
> +                     ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
> +                       return PAGEMAP_PFN(ent[0]);
> +       }
>
>         return -1;
>  }
> --
> 2.34.0.rc0.344.g81b53c2807-goog