Re: [PATCH RFC] mm: madvise: use per_vma lock for MADV_FREE

[Barry Song <21cnbao@gmail.com>]

On Tue, Jun 10, 2025 at 7:04 PM David Hildenbrand <david@redhat.com> wrote:
>
> On 10.06.25 07:59, Barry Song wrote:
> > From: Barry Song <v-songbaohua@oppo.com>
> >
> > MADV_FREE is another option, besides MADV_DONTNEED, for dynamic memory
> > freeing in user-space native or Java heap memory management. For example,
> > jemalloc can be configured to use MADV_FREE, and recent versions of the
> > Android Java heap have also increasingly adopted MADV_FREE. Supporting
> > per-VMA locking for MADV_FREE thus appears increasingly necessary.
> >
> > We have replaced walk_page_range() with walk_page_range_vma(). Along with
> > the proposed madvise_lock_mode by Lorenzo, the necessary infrastructure is
> > now in place to begin exploring per-VMA locking support for MADV_FREE and
> > potentially other madvise using walk_page_range_vma().
> >
> > This patch adds support for the PGWALK_VMA_RDLOCK walk_lock mode in
> > walk_page_range_vma(), and leverages madvise_lock_mode from
> > madv_behavior to select the appropriate walk_lock—either mmap_lock or
> > per-VMA lock—based on the context.
> >
> > To ensure thread safety, madvise_free_walk_ops is now defined as a stack
> > variable instead of a global constant.
> >
> > Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> > Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
> > Cc: David Hildenbrand <david@redhat.com>
> > Cc: Vlastimil Babka <vbabka@suse.cz>
> > Cc: Jann Horn <jannh@google.com>
> > Cc: Suren Baghdasaryan <surenb@google.com>
> > Cc: Lokesh Gidra <lokeshgidra@google.com>
> > Cc: Mike Rapoport <rppt@kernel.org>
> > Cc: Michal Hocko <mhocko@suse.com>
> > Cc: Tangquan Zheng <zhengtangquan@oppo.com>
> > Cc: Qi Zheng <zhengqi.arch@bytedance.com>
> > Signed-off-by: Barry Song <v-songbaohua@oppo.com>
> > ---
> >   include/linux/pagewalk.h |  2 ++
> >   mm/madvise.c             | 20 ++++++++++++++------
> >   mm/pagewalk.c            |  6 ++++++
> >   3 files changed, 22 insertions(+), 6 deletions(-)
> >
> > diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
> > index 9700a29f8afb..a4afa64ef0ab 100644
> > --- a/include/linux/pagewalk.h
> > +++ b/include/linux/pagewalk.h
> > @@ -14,6 +14,8 @@ enum page_walk_lock {
> >       PGWALK_WRLOCK = 1,
> >       /* vma is expected to be already write-locked during the walk */
> >       PGWALK_WRLOCK_VERIFY = 2,
> > +     /* vma is expected to be already read-locked during the walk */
> > +     PGWALK_VMA_RDLOCK_VERIFY = 3,
> >   };
> >
> >   /**
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index 381eedde8f6d..23d58eb31c8f 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -775,10 +775,14 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
> >       return 0;
> >   }
> >
> > -static const struct mm_walk_ops madvise_free_walk_ops = {
> > -     .pmd_entry              = madvise_free_pte_range,
> > -     .walk_lock              = PGWALK_RDLOCK,
> > -};
> > +static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode)
> > +{
> > +     /* Other modes don't require fixing up the walk_lock. */
> > +     VM_WARN_ON_ONCE(mode != MADVISE_VMA_READ_LOCK &&
> > +                     mode != MADVISE_MMAP_READ_LOCK);
> > +     return mode == MADVISE_VMA_READ_LOCK ?
> > +                     PGWALK_VMA_RDLOCK_VERIFY : PGWALK_RDLOCK;
> > +}
> >
> >   static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
> >                       struct vm_area_struct *vma,
> > @@ -787,6 +791,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
> >       struct mm_struct *mm = vma->vm_mm;
> >       struct mmu_notifier_range range;
> >       struct mmu_gather *tlb = madv_behavior->tlb;
> > +     struct mm_walk_ops walk_ops = {
> > +             .pmd_entry              = madvise_free_pte_range,
> > +     };
> >
> >       /* MADV_FREE works for only anon vma at the moment */
> >       if (!vma_is_anonymous(vma))
> > @@ -806,8 +813,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
> >
> >       mmu_notifier_invalidate_range_start(&range);
> >       tlb_start_vma(tlb, vma);
> > +     walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode);
> >       walk_page_range_vma(vma, range.start, range.end,
> > -                     &madvise_free_walk_ops, tlb);
> > +                     &walk_ops, tlb);
> >       tlb_end_vma(tlb, vma);
> >       mmu_notifier_invalidate_range_end(&range);
> >       return 0;
> > @@ -1653,7 +1661,6 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi
> >       case MADV_WILLNEED:
> >       case MADV_COLD:
> >       case MADV_PAGEOUT:
> > -     case MADV_FREE:
> >       case MADV_POPULATE_READ:
> >       case MADV_POPULATE_WRITE:
> >       case MADV_COLLAPSE:
> > @@ -1662,6 +1669,7 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi
> >               return MADVISE_MMAP_READ_LOCK;
> >       case MADV_DONTNEED:
> >       case MADV_DONTNEED_LOCKED:
> > +     case MADV_FREE:
> >               return MADVISE_VMA_READ_LOCK;
> >       default:
> >               return MADVISE_MMAP_WRITE_LOCK;
> > diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> > index e478777c86e1..c984aacc5552 100644
> > --- a/mm/pagewalk.c
> > +++ b/mm/pagewalk.c
> > @@ -420,6 +420,9 @@ static int __walk_page_range(unsigned long start, unsigned long end,
> >   static inline void process_mm_walk_lock(struct mm_struct *mm,
> >                                       enum page_walk_lock walk_lock)
> >   {
> > +     if (walk_lock == PGWALK_VMA_RDLOCK_VERIFY)
> > +             return;
> > +
> >       if (walk_lock == PGWALK_RDLOCK)
> >               mmap_assert_locked(mm);
>
> Nit: I'd have converted the "else" into "else if (walk_lock !=
> PGWALK_VMA_RDLOCK_VERIFY)

Seems good to me.

>
> >       else
> > @@ -437,6 +440,9 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma,
> >       case PGWALK_WRLOCK_VERIFY:
> >               vma_assert_write_locked(vma);
> >               break;
> > +     case PGWALK_VMA_RDLOCK_VERIFY:
> > +             vma_assert_locked(vma);
> > +             break;
> >       case PGWALK_RDLOCK:
> >               /* PGWALK_RDLOCK is handled by process_mm_walk_lock */
> >               break;
>
> Nothing jumped at me an I think this should be ok
>
> Acked-by: David Hildenbrand <david@redhat.com>

Thanks!

>
> --
> Cheers,
>
> David / dhildenb
>