Re: [PATCH v2 09/46] mm: add MADV_SPLIT to enable HugeTLB HGM

[James Houghton <jthoughton@google.com>]

On Fri, Feb 24, 2023 at 3:25 PM Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
> On 02/18/23 00:27, James Houghton wrote:
> > Issuing ioctl(MADV_SPLIT) on a HugeTLB address range will enable
> > HugeTLB HGM. MADV_SPLIT was chosen for the name so that this API can be
> > applied to non-HugeTLB memory in the future, if such an application is
> > to arise.
> >
> > MADV_SPLIT provides several API changes for some syscalls on HugeTLB
> > address ranges:
> > 1. UFFDIO_CONTINUE is allowed for MAP_SHARED VMAs at PAGE_SIZE
> >    alignment.
> > 2. read()ing a page fault event from a userfaultfd will yield a
> >    PAGE_SIZE-rounded address, instead of a huge-page-size-rounded
> >    address (unless UFFD_FEATURE_EXACT_ADDRESS is used).
> >
> > There is no way to disable the API changes that come with issuing
> > MADV_SPLIT. MADV_COLLAPSE can be used to collapse high-granularity page
> > table mappings that come from the extended functionality that comes with
> > using MADV_SPLIT.
> >
> > For post-copy live migration, the expected use-case is:
> > 1. mmap(MAP_SHARED, some_fd) primary mapping
> > 2. mmap(MAP_SHARED, some_fd) alias mapping
> > 3. MADV_SPLIT the primary mapping
> > 4. UFFDIO_REGISTER/etc. the primary mapping
> > 5. Copy memory contents into alias mapping and UFFDIO_CONTINUE the
> >    corresponding PAGE_SIZE sections in the primary mapping.
> >
> > More API changes may be added in the future.
> >
> > Signed-off-by: James Houghton <jthoughton@google.com>
> >
> > diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
> > index 763929e814e9..7a26f3648b90 100644
> > --- a/arch/alpha/include/uapi/asm/mman.h
> > +++ b/arch/alpha/include/uapi/asm/mman.h
> > @@ -78,6 +78,8 @@
> >
> >  #define MADV_COLLAPSE        25              /* Synchronous hugepage collapse */
> >
> > +#define MADV_SPLIT   26              /* Enable hugepage high-granularity APIs */
> > +
> >  /* compatibility flags */
> >  #define MAP_FILE     0
> >
> > diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
> > index c6e1fc77c996..f8a74a3a0928 100644
> > --- a/arch/mips/include/uapi/asm/mman.h
> > +++ b/arch/mips/include/uapi/asm/mman.h
> > @@ -105,6 +105,8 @@
> >
> >  #define MADV_COLLAPSE        25              /* Synchronous hugepage collapse */
> >
> > +#define MADV_SPLIT   26              /* Enable hugepage high-granularity APIs */
> > +
> >  /* compatibility flags */
> >  #define MAP_FILE     0
> >
> > diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
> > index 68c44f99bc93..a6dc6a56c941 100644
> > --- a/arch/parisc/include/uapi/asm/mman.h
> > +++ b/arch/parisc/include/uapi/asm/mman.h
> > @@ -72,6 +72,8 @@
> >
> >  #define MADV_COLLAPSE        25              /* Synchronous hugepage collapse */
> >
> > +#define MADV_SPLIT   74              /* Enable hugepage high-granularity APIs */
> > +
> >  #define MADV_HWPOISON     100                /* poison a page for testing */
> >  #define MADV_SOFT_OFFLINE 101                /* soft offline page for testing */
> >
> > diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
> > index 1ff0c858544f..f98a77c430a9 100644
> > --- a/arch/xtensa/include/uapi/asm/mman.h
> > +++ b/arch/xtensa/include/uapi/asm/mman.h
> > @@ -113,6 +113,8 @@
> >
> >  #define MADV_COLLAPSE        25              /* Synchronous hugepage collapse */
> >
> > +#define MADV_SPLIT   26              /* Enable hugepage high-granularity APIs */
> > +
> >  /* compatibility flags */
> >  #define MAP_FILE     0
> >
> > diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
> > index 6ce1f1ceb432..996e8ded092f 100644
> > --- a/include/uapi/asm-generic/mman-common.h
> > +++ b/include/uapi/asm-generic/mman-common.h
> > @@ -79,6 +79,8 @@
> >
> >  #define MADV_COLLAPSE        25              /* Synchronous hugepage collapse */
> >
> > +#define MADV_SPLIT   26              /* Enable hugepage high-granularity APIs */
> > +
> >  /* compatibility flags */
> >  #define MAP_FILE     0
> >
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index c2202f51e9dd..8c004c678262 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -1006,6 +1006,28 @@ static long madvise_remove(struct vm_area_struct *vma,
> >       return error;
> >  }
> >
> > +static int madvise_split(struct vm_area_struct *vma,
> > +                      unsigned long *new_flags)
> > +{
> > +#ifdef CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING
> > +     if (!is_vm_hugetlb_page(vma) || !hugetlb_hgm_eligible(vma))
> > +             return -EINVAL;
> > +
> > +     /*
> > +      * PMD sharing doesn't work with HGM. If this MADV_SPLIT is on part
> > +      * of a VMA, then we will split the VMA. Here, we're unsharing before
> > +      * splitting because it's simpler, although we may be unsharing more
> > +      * than we need.
> > +      */
> > +     hugetlb_unshare_all_pmds(vma);
>
> I think we should just unshare the (appropriately aligned) range within the
> vma that is the target of MADV_SPLIT.  No need to unshare the entire vma.

Right I can do that, and I can check for appropriate alignment here
(else fail with -EINVAL).

>
> > +
> > +     *new_flags |= VM_HUGETLB_HGM;
> > +     return 0;
> > +#else
> > +     return -EINVAL;
> > +#endif
> > +}
> > +
> >  /*
> >   * Apply an madvise behavior to a region of a vma.  madvise_update_vma
> >   * will handle splitting a vm area into separate areas, each area with its own
> > @@ -1084,6 +1106,11 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
> >               break;
> >       case MADV_COLLAPSE:
> >               return madvise_collapse(vma, prev, start, end);
> > +     case MADV_SPLIT:
> > +             error = madvise_split(vma, &new_flags);
> > +             if (error)
> > +                     goto out;
>
> Not a huge deal, but if one passes an invalid range (such as not huge page
> size aligned) to MADV_SPLIT, then we will not notice the error until
> later in madvise_update_vma() when the vma split fails.  By then, we will
> have unshared all pmds in the entire vma (or just the range if you agree
> with my suggestion above).

Good point. I'll fix this for v3. :) Thanks Mike.