Re: [PATCH v6 5/6] mm: use vma_start_write_killable() in process_vma_walk_lock()

[Suren Baghdasaryan]

On Tue, Mar 31, 2026 at 3:39 AM Lorenzo Stoakes (Oracle) <ljs@xxxxxxxxxx> wrote:
>
> On Fri, Mar 27, 2026 at 01:54:56PM -0700, Suren Baghdasaryan wrote:
> > Replace vma_start_write() with vma_start_write_killable() when
> > process_vma_walk_lock() is used with PGWALK_WRLOCK option.
> > Adjust its direct and indirect users to check for a possible error
> > and handle it. Ensure users handle EINTR correctly and do not ignore
> > it. When queue_pages_range() fails, check whether it failed due to
> > a fatal signal or some other reason and return appropriate error.
> >
> > Suggested-by: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> > Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
> > ---
> >  fs/proc/task_mmu.c | 12 ++++++------
> >  mm/mempolicy.c     | 10 +++++++++-
> >  mm/pagewalk.c      | 22 +++++++++++++++-------
> >  3 files changed, 30 insertions(+), 14 deletions(-)
> >
> > diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> > index e091931d7ca1..33e5094a7842 100644
> > --- a/fs/proc/task_mmu.c
> > +++ b/fs/proc/task_mmu.c
> > @@ -1774,15 +1774,15 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
> >       struct vm_area_struct *vma;
> >       enum clear_refs_types type;
> >       int itype;
> > -     int rv;
> > +     int err;
> >
> >       if (count > sizeof(buffer) - 1)
> >               count = sizeof(buffer) - 1;
> >       if (copy_from_user(buffer, buf, count))
> >               return -EFAULT;
> > -     rv = kstrtoint(strstrip(buffer), 10, &itype);
> > -     if (rv < 0)
> > -             return rv;
> > +     err = kstrtoint(strstrip(buffer), 10, &itype);
> > +     if (err)
> > +             return err;
> >       type = (enum clear_refs_types)itype;
> >       if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
> >               return -EINVAL;
> > @@ -1824,7 +1824,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
> >                                               0, mm, 0, -1UL);
> >                       mmu_notifier_invalidate_range_start(&range);
> >               }
> > -             walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
> > +             err = walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
> >               if (type == CLEAR_REFS_SOFT_DIRTY) {
> >                       mmu_notifier_invalidate_range_end(&range);
> >                       flush_tlb_mm(mm);
> > @@ -1837,7 +1837,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
> >       }
> >       put_task_struct(task);
> >
> > -     return count;
> > +     return err ? : count;
> >  }
> >
> >  const struct file_operations proc_clear_refs_operations = {
> > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > index c38a90487531..51f298cfc33b 100644
> > --- a/mm/mempolicy.c
> > +++ b/mm/mempolicy.c
> > @@ -969,6 +969,7 @@ static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = {
> >   *      (a hugetlbfs page or a transparent huge page being counted as 1).
> >   * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs.
> >   * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified.
> > + * -EINTR - walk got terminated due to pending fatal signal.
> >   */
> >  static long
> >  queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
> > @@ -1545,7 +1546,14 @@ static long do_mbind(unsigned long start, unsigned long len,
> >                       flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist);
> >
> >       if (nr_failed < 0) {
> > -             err = nr_failed;
> > +             /*
> > +              * queue_pages_range() might override the original error with -EFAULT.
> > +              * Confirm that fatal signals are still treated correctly.
> > +              */
> > +             if (fatal_signal_pending(current))
> > +                     err = -EINTR;
> > +             else
> > +                     err = nr_failed;
>
> Is that really a big deal? Does it really matter if the caller doesn't get
> -EINTR in this case? This feels like another sashiko nitpick and is adding a
> bunch of additional complexity here.

I think there is a difference in that the userspace caller will never
see EINTR, as Matthew explained in an earlier version, while EFAULT
will be seen and can be handled. I don't see why we wouldn't want to
report the correct error, and the code doing that seems clear and
straight-forward to me. That was in fact your suggested solution for
not checking for EINTR :)

>
> I mean if you 'filter' error messages you might always end up with an error
> that's different than the original...
>
> >               nr_failed = 0;
> >       } else {
> >               vma_iter_init(&vmi, mm, start);
> > diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> > index 3ae2586ff45b..eca7bc711617 100644
> > --- a/mm/pagewalk.c
> > +++ b/mm/pagewalk.c
> > @@ -443,14 +443,13 @@ static inline void process_mm_walk_lock(struct mm_struct *mm,
> >               mmap_assert_write_locked(mm);
> >  }
> >
> > -static inline void process_vma_walk_lock(struct vm_area_struct *vma,
> > -                                      enum page_walk_lock walk_lock)
> > +static int process_vma_walk_lock(struct vm_area_struct *vma,
> > +                              enum page_walk_lock walk_lock)
> >  {
> >  #ifdef CONFIG_PER_VMA_LOCK
> >       switch (walk_lock) {
> >       case PGWALK_WRLOCK:
> > -             vma_start_write(vma);
> > -             break;
> > +             return vma_start_write_killable(vma);
> >       case PGWALK_WRLOCK_VERIFY:
> >               vma_assert_write_locked(vma);
> >               break;
> > @@ -462,6 +461,7 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma,
> >               break;
> >       }
> >  #endif
> > +     return 0;
> >  }
> >
> >  /*
> > @@ -505,7 +505,9 @@ int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start,
> >                       if (ops->pte_hole)
> >                               err = ops->pte_hole(start, next, -1, &walk);
> >               } else { /* inside vma */
> > -                     process_vma_walk_lock(vma, ops->walk_lock);
> > +                     err = process_vma_walk_lock(vma, ops->walk_lock);
> > +                     if (err)
> > +                             break;
> >                       walk.vma = vma;
> >                       next = min(end, vma->vm_end);
> >                       vma = find_vma(mm, vma->vm_end);
> > @@ -722,6 +724,7 @@ int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start,
> >               .vma            = vma,
> >               .private        = private,
> >       };
> > +     int err;
> >
> >       if (start >= end || !walk.mm)
> >               return -EINVAL;
> > @@ -729,7 +732,9 @@ int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start,
> >               return -EINVAL;
> >
> >       process_mm_walk_lock(walk.mm, ops->walk_lock);
> > -     process_vma_walk_lock(vma, ops->walk_lock);
> > +     err = process_vma_walk_lock(vma, ops->walk_lock);
> > +     if (err)
> > +             return err;
> >       return __walk_page_range(start, end, &walk);
> >  }
> >
> > @@ -752,6 +757,7 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
> >               .vma            = vma,
> >               .private        = private,
> >       };
> > +     int err;
> >
> >       if (!walk.mm)
> >               return -EINVAL;
> > @@ -759,7 +765,9 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
> >               return -EINVAL;
> >
> >       process_mm_walk_lock(walk.mm, ops->walk_lock);
> > -     process_vma_walk_lock(vma, ops->walk_lock);
> > +     err = process_vma_walk_lock(vma, ops->walk_lock);
> > +     if (err)
> > +             return err;
> >       return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
> >  }
> >
> > --
> > 2.53.0.1018.g2bb0e51243-goog
> >