Re: [RFC PATCH 4/5] mm/mmap: Change munmap to use vma_munmap_struct() for accounting and surrounding vmas
From: Liam R. Howlett
Date: Fri Jun 07 2024 - 11:25:34 EST
* Suren Baghdasaryan <surenb@xxxxxxxxxx> [240607 10:38]:
> On Fri, May 31, 2024 at 9:33 AM Liam R. Howlett <Liam.Howlett@xxxxxxxxxx> wrote:
> >
> > Clean up the code by changing the munmap operation to use a structure
> > for the accounting and munmap variables.
> >
> > Since remove_mt() is only called in one location and the contents will
> > be reduce to almost nothing. The remains of the function can be added
> > to vms_complete_munmap_vmas().
> >
> > Signed-off-by: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
> > ---
> > mm/internal.h | 6 ++++
> > mm/mmap.c | 85 +++++++++++++++++++++++++++------------------------
> > 2 files changed, 51 insertions(+), 40 deletions(-)
> >
> > diff --git a/mm/internal.h b/mm/internal.h
> > index 6ebf77853d68..8c02ebf5736c 100644
> > --- a/mm/internal.h
> > +++ b/mm/internal.h
> > @@ -1435,12 +1435,18 @@ struct vma_munmap_struct {
> > struct vma_iterator *vmi;
> > struct mm_struct *mm;
> > struct vm_area_struct *vma; /* The first vma to munmap */
> > + struct vm_area_struct *next; /* vma after the munmap area */
> > + struct vm_area_struct *prev; /* vma before the munmap area */
> > struct list_head *uf; /* Userfaultfd list_head */
> > unsigned long start; /* Aligned start addr */
> > unsigned long end; /* Aligned end addr */
> > int vma_count; /* Number of vmas that will be removed */
> > unsigned long nr_pages; /* Number of pages being removed */
> > unsigned long locked_vm; /* Number of locked pages */
> > + unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */
> > + unsigned long exec_vm;
> > + unsigned long stack_vm;
> > + unsigned long data_vm;
> > bool unlock; /* Unlock after the munmap */
> > };
> >
> > diff --git a/mm/mmap.c b/mm/mmap.c
> > index 57f2383245ea..3e0930c09213 100644
> > --- a/mm/mmap.c
> > +++ b/mm/mmap.c
> > @@ -482,7 +482,8 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms,
> > vms->unlock = unlock;
> > vms->uf = uf;
> > vms->vma_count = 0;
> > - vms->nr_pages = vms->locked_vm = 0;
> > + vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0;
> > + vms->exec_vm = vms->stack_vm = vms->data_vm = 0;
> > }
> >
> > /*
> > @@ -604,7 +605,6 @@ static inline void vma_complete(struct vma_prepare *vp,
> > }
> > if (vp->insert && vp->file)
> > uprobe_mmap(vp->insert);
> > - validate_mm(mm);
>
> vma_complete() is used in places other than vma_shrink(). You
> effectively removed validate_mm() for all those other users. Is that
> intentional? If so, that should be documented in the changelog.
Oh, right. Yes. This needs to be extracted into its own patch.
We cannot validate_mm() in vma_complete() due to vma_expand() being
called prior to the completion of the MAP_FIXED munmap.
I will extract this into its own patch for the next revision.
>
> > }
> >
> > /*
> > @@ -733,6 +733,7 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
> > vma_iter_clear(vmi);
> > vma_set_range(vma, start, end, pgoff);
> > vma_complete(&vp, vmi, vma->vm_mm);
> > + validate_mm(vma->vm_mm);
> > return 0;
> > }
> >
> > @@ -2347,30 +2348,6 @@ struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr)
> > return vma;
> > }
> >
> > -/*
> > - * Ok - we have the memory areas we should free on a maple tree so release them,
> > - * and do the vma updates.
> > - *
> > - * Called with the mm semaphore held.
> > - */
> > -static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
> > -{
> > - unsigned long nr_accounted = 0;
> > - struct vm_area_struct *vma;
> > -
> > - /* Update high watermark before we lower total_vm */
> > - update_hiwater_vm(mm);
> > - mas_for_each(mas, vma, ULONG_MAX) {
> > - long nrpages = vma_pages(vma);
> > -
> > - if (vma->vm_flags & VM_ACCOUNT)
> > - nr_accounted += nrpages;
> > - vm_stat_account(mm, vma->vm_flags, -nrpages);
> > - remove_vma(vma, false);
> > - }
> > - vm_unacct_memory(nr_accounted);
> > -}
> > -
> > /*
> > * Get rid of page table information in the indicated region.
> > *
> > @@ -2625,13 +2602,14 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> > if (error)
> > goto start_split_failed;
> > }
> > + vms->prev = vma_prev(vms->vmi);
> >
> > /*
> > * Detach a range of VMAs from the mm. Using next as a temp variable as
> > * it is always overwritten.
> > */
> > - next = vms->vma;
> > - do {
> > + for_each_vma_range(*(vms->vmi), next, vms->end) {
> > + long nrpages;
> > /* Does it split the end? */
> > if (next->vm_end > vms->end) {
> > error = __split_vma(vms->vmi, next, vms->end, 0);
> > @@ -2640,8 +2618,21 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> > }
> > vma_start_write(next);
> > mas_set(mas_detach, vms->vma_count++);
> > + nrpages = vma_pages(next);
> > +
> > + vms->nr_pages += nrpages;
> > if (next->vm_flags & VM_LOCKED)
> > - vms->locked_vm += vma_pages(next);
> > + vms->locked_vm += nrpages;
> > +
> > + if (next->vm_flags & VM_ACCOUNT)
> > + vms->nr_accounted += nrpages;
> > +
> > + if (is_exec_mapping(next->vm_flags))
> > + vms->exec_vm += nrpages;
> > + else if (is_stack_mapping(next->vm_flags))
> > + vms->stack_vm += nrpages;
> > + else if (is_data_mapping(next->vm_flags))
> > + vms->data_vm += nrpages;
> >
> > error = mas_store_gfp(mas_detach, next, GFP_KERNEL);
> > if (error)
> > @@ -2667,7 +2658,9 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> > BUG_ON(next->vm_start < vms->start);
> > BUG_ON(next->vm_start > vms->end);
> > #endif
> > - } for_each_vma_range(*(vms->vmi), next, vms->end);
> > + }
> > +
> > + vms->next = vma_next(vms->vmi);
> >
> > #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
> > /* Make sure no VMAs are about to be lost. */
> > @@ -2712,10 +2705,11 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> > * @mas_detach: The maple state of the detached vmas
> > *
> > */
> > +static inline void vms_vm_stat_account(struct vma_munmap_struct *vms);
> > static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
> > struct ma_state *mas_detach)
> > {
> > - struct vm_area_struct *prev, *next;
> > + struct vm_area_struct *vma;
> > struct mm_struct *mm;
> >
> > mm = vms->mm;
> > @@ -2724,21 +2718,21 @@ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
> > if (vms->unlock)
> > mmap_write_downgrade(mm);
> >
> > - prev = vma_iter_prev_range(vms->vmi);
> > - next = vma_next(vms->vmi);
> > - if (next)
> > - vma_iter_prev_range(vms->vmi);
> > -
> > /*
> > * We can free page tables without write-locking mmap_lock because VMAs
> > * were isolated before we downgraded mmap_lock.
> > */
> > mas_set(mas_detach, 1);
> > - unmap_region(mm, mas_detach, vms->vma, prev, next, vms->start, vms->end,
> > - vms->vma_count, !vms->unlock);
> > - /* Statistics and freeing VMAs */
> > + unmap_region(mm, mas_detach, vms->vma, vms->prev, vms->next,
> > + vms->start, vms->end, vms->vma_count, !vms->unlock);
> > + /* Update high watermark before we lower total_vm */
> > + update_hiwater_vm(mm);
> > + vms_vm_stat_account(vms);
> > mas_set(mas_detach, 0);
> > - remove_mt(mm, mas_detach);
> > + mas_for_each(mas_detach, vma, ULONG_MAX)
> > + remove_vma(vma, false);
> > +
> > + vm_unacct_memory(vms->nr_accounted);
> > validate_mm(mm);
> > if (vms->unlock)
> > mmap_read_unlock(mm);
> > @@ -3631,6 +3625,17 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
> > mm->data_vm += npages;
> > }
> >
> > +/* Accounting for munmap */
> > +static inline void vms_vm_stat_account(struct vma_munmap_struct *vms)
> > +{
> > + struct mm_struct *mm = vms->mm;
> > +
> > + WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages);
> > + mm->exec_vm -= vms->exec_vm;
> > + mm->stack_vm -= vms->stack_vm;
> > + mm->data_vm -= vms->data_vm;
> > +}
> > +
> > static vm_fault_t special_mapping_fault(struct vm_fault *vmf);
> >
> > /*
> > --
> > 2.43.0
> >
>