2022-09-01 18:03:43

by Suren Baghdasaryan

Subject: [RFC PATCH RESEND 09/28] mm/mempolicy: mark VMA as locked when changing protection policy

Protect VMA from concurrent page fault handler while performing VMA
protection policy changes.

Signed-off-by: Suren Baghdasaryan <[email protected]>
---
mm/mempolicy.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b73d3248d976..6be1e5c75556 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -383,8 +383,10 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
struct vm_area_struct *vma;

mmap_write_lock(mm);
- for (vma = mm->mmap; vma; vma = vma->vm_next)
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ vma_mark_locked(vma);
mpol_rebind_policy(vma->vm_policy, new);
+ }
mmap_write_unlock(mm);
}

@@ -632,6 +634,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
struct mmu_gather tlb;
int nr_updated;

+ vma_mark_locked(vma);
tlb_gather_mmu(&tlb, vma->vm_mm);

nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
@@ -765,6 +768,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
if (IS_ERR(new))
return PTR_ERR(new);

+ vma_mark_locked(vma);
if (vma->vm_ops && vma->vm_ops->set_policy) {
err = vma->vm_ops->set_policy(vma, new);
if (err)
--
2.37.2.789.g6183377224-goog

2022-09-06 16:16:53

by Laurent Dufour

Subject: Re: [RFC PATCH RESEND 09/28] mm/mempolicy: mark VMA as locked when changing protection policy

Le 01/09/2022 à 19:34, Suren Baghdasaryan a écrit :
> Protect VMA from concurrent page fault handler while performing VMA
> protection policy changes.
>
> Signed-off-by: Suren Baghdasaryan <[email protected]>
> ---
> mm/mempolicy.c | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index b73d3248d976..6be1e5c75556 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -383,8 +383,10 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
> struct vm_area_struct *vma;
>
> mmap_write_lock(mm);
> - for (vma = mm->mmap; vma; vma = vma->vm_next)
> + for (vma = mm->mmap; vma; vma = vma->vm_next) {
> + vma_mark_locked(vma);
> mpol_rebind_policy(vma->vm_policy, new);
> + }
> mmap_write_unlock(mm);
> }
>
> @@ -632,6 +634,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
> struct mmu_gather tlb;
> int nr_updated;
>
> + vma_mark_locked(vma);

If I understand that corretly, the VMA itself is not impacted, only the
PMDs/PTEs, and they are protected using the page table locks.

Am I missing something?

> tlb_gather_mmu(&tlb, vma->vm_mm);
>
> nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
> @@ -765,6 +768,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
> if (IS_ERR(new))
> return PTR_ERR(new);
>
> + vma_mark_locked(vma);
> if (vma->vm_ops && vma->vm_ops->set_policy) {
> err = vma->vm_ops->set_policy(vma, new);
> if (err)

2022-09-09 00:54:40

by Suren Baghdasaryan

Subject: Re: [RFC PATCH RESEND 09/28] mm/mempolicy: mark VMA as locked when changing protection policy

On Tue, Sep 6, 2022 at 7:48 AM Laurent Dufour <[email protected]> wrote:
>
> Le 01/09/2022 à 19:34, Suren Baghdasaryan a écrit :
> > Protect VMA from concurrent page fault handler while performing VMA
> > protection policy changes.
> >
> > Signed-off-by: Suren Baghdasaryan <[email protected]>
> > ---
> > mm/mempolicy.c | 6 +++++-
> > 1 file changed, 5 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > index b73d3248d976..6be1e5c75556 100644
> > --- a/mm/mempolicy.c
> > +++ b/mm/mempolicy.c
> > @@ -383,8 +383,10 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
> > struct vm_area_struct *vma;
> >
> > mmap_write_lock(mm);
> > - for (vma = mm->mmap; vma; vma = vma->vm_next)
> > + for (vma = mm->mmap; vma; vma = vma->vm_next) {
> > + vma_mark_locked(vma);
> > mpol_rebind_policy(vma->vm_policy, new);
> > + }
> > mmap_write_unlock(mm);
> > }
> >
> > @@ -632,6 +634,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
> > struct mmu_gather tlb;
> > int nr_updated;
> >
> > + vma_mark_locked(vma);
>
> If I understand that corretly, the VMA itself is not impacted, only the
> PMDs/PTEs, and they are protected using the page table locks.
>
> Am I missing something?

I thought we would not want pages faulting in the VMA for which we are
changing the protection. However I think what you are saying is that
page table locks would already provide a more granular synchronization
with page fault handlers, which makes sense to me. Sounds like we can
skip locking the VMA here as well. Nice!

>
> > tlb_gather_mmu(&tlb, vma->vm_mm);
> >
> > nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
> > @@ -765,6 +768,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
> > if (IS_ERR(new))
> > return PTR_ERR(new);
> >
> > + vma_mark_locked(vma);
> > if (vma->vm_ops && vma->vm_ops->set_policy) {
> > err = vma->vm_ops->set_policy(vma, new);
> > if (err)
>