From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
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 reduced to almost nothing. The remains of the function can be added
to vms_complete_munmap_vmas().
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
---
mm/vma.c | 79 ++++++++++++++++++++++++++++----------------------------
mm/vma.h | 6 +++++
2 files changed, 46 insertions(+), 39 deletions(-)
diff --git a/mm/vma.c b/mm/vma.c
index e1aee43a3dc4..7b8b8b983399 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -103,7 +103,8 @@ 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;
}
/*
@@ -299,30 +300,6 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
return __split_vma(vmi, vma, addr, new_below);
}
-/*
- * 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);
-}
-
/*
* init_vma_prep() - Initializer wrapper for vma_prepare struct
* @vp: The vma_prepare struct
@@ -722,7 +699,7 @@ static inline void abort_munmap_vmas(struct ma_state *mas_detach)
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;
@@ -731,21 +708,26 @@ 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);
+ /* Stat accounting */
+ 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;
+ /* Remove and clean up vmas */
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);
@@ -799,18 +781,19 @@ 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;
+
if (!can_modify_vma(next)) {
error = -EPERM;
goto modify_vma_failed;
}
-
/* Does it split the end? */
if (next->vm_end > vms->end) {
error = __split_vma(vms->vmi, next, vms->end, 0);
@@ -824,6 +807,22 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
goto munmap_gather_failed;
vma_mark_detached(next, true);
+ nrpages = vma_pages(next);
+
+ vms->nr_pages += nrpages;
+ if (next->vm_flags & VM_LOCKED)
+ 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;
+
if (next->vm_flags & VM_LOCKED)
vms->locked_vm += vma_pages(next);
@@ -847,7 +846,9 @@ 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. */
diff --git a/mm/vma.h b/mm/vma.h
index cb67acf59012..cbf55e0e0c4f 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -33,12 +33,18 @@ 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 *prev; /* vma before the munmap area */
+ struct vm_area_struct *next; /* vma after the munmap area */
struct list_head *uf; /* Userfaultfd list_head */
unsigned long start; /* Aligned start addr (inclusive) */
unsigned long end; /* Aligned end addr (exclusive) */
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 */
};
--
2.43.0On Tue, Aug 20, 2024 at 07:57:15PM GMT, Liam R. Howlett wrote:
> From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
>
> 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 reduced to almost nothing. The remains of the function can be added
> to vms_complete_munmap_vmas().
>
> Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> Reviewed-by: Suren Baghdasaryan <surenb@google.com>
> ---
> mm/vma.c | 79 ++++++++++++++++++++++++++++----------------------------
> mm/vma.h | 6 +++++
> 2 files changed, 46 insertions(+), 39 deletions(-)
>
> diff --git a/mm/vma.c b/mm/vma.c
> index e1aee43a3dc4..7b8b8b983399 100644
> --- a/mm/vma.c
> +++ b/mm/vma.c
[snip]
> mm = vms->mm;
> @@ -731,21 +708,26 @@ 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);
> + /* Stat accounting */
> + 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;
See below, but I bisected a bug to this patch that manifested because of
miscalculated accounting. So I wonder whether it'd be a good idea to take
this opportunity, when updating mm->... stats to add some:
VM_WARN_ON(vms->exec_vm > mm->exec_vm);
etc. for each of the fields updated. This would help catch any accounting
issues like this with CONFIG_DEBUG_VM switched on.
[snip]
> @@ -824,6 +807,22 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> goto munmap_gather_failed;
>
> vma_mark_detached(next, true);
> + nrpages = vma_pages(next);
> +
> + vms->nr_pages += nrpages;
> + if (next->vm_flags & VM_LOCKED)
> + vms->locked_vm += nrpages;
So I bisected a self-test failure, memfd_secret specifically, to this
commit. This is because you are double-counting VM_LOCKED...
> +
> + 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;
> +
> if (next->vm_flags & VM_LOCKED)
> vms->locked_vm += vma_pages(next);
...the double counting being right here :) so I think we should drop the
above couple lines.
>
> @@ -847,7 +846,9 @@ 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. */
> diff --git a/mm/vma.h b/mm/vma.h
> index cb67acf59012..cbf55e0e0c4f 100644
> --- a/mm/vma.h
> +++ b/mm/vma.h
> @@ -33,12 +33,18 @@ 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 *prev; /* vma before the munmap area */
> + struct vm_area_struct *next; /* vma after the munmap area */
> struct list_head *uf; /* Userfaultfd list_head */
> unsigned long start; /* Aligned start addr (inclusive) */
> unsigned long end; /* Aligned end addr (exclusive) */
> 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 */
> };
>
> --
> 2.43.0
>
* Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [240821 05:59]:
> On Tue, Aug 20, 2024 at 07:57:15PM GMT, Liam R. Howlett wrote:
> > From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
> >
> > 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 reduced to almost nothing. The remains of the function can be added
> > to vms_complete_munmap_vmas().
> >
> > Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
> > Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> > Reviewed-by: Suren Baghdasaryan <surenb@google.com>
> > ---
> > mm/vma.c | 79 ++++++++++++++++++++++++++++----------------------------
> > mm/vma.h | 6 +++++
> > 2 files changed, 46 insertions(+), 39 deletions(-)
> >
> > diff --git a/mm/vma.c b/mm/vma.c
> > index e1aee43a3dc4..7b8b8b983399 100644
> > --- a/mm/vma.c
> > +++ b/mm/vma.c
>
> [snip]
>
> > mm = vms->mm;
> > @@ -731,21 +708,26 @@ 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);
> > + /* Stat accounting */
> > + 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;
>
> See below, but I bisected a bug to this patch that manifested because of
> miscalculated accounting. So I wonder whether it'd be a good idea to take
> this opportunity, when updating mm->... stats to add some:
>
> VM_WARN_ON(vms->exec_vm > mm->exec_vm);
>
> etc. for each of the fields updated. This would help catch any accounting
> issues like this with CONFIG_DEBUG_VM switched on.
Sounds good.
>
> [snip]
>
> > @@ -824,6 +807,22 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
> > goto munmap_gather_failed;
> >
> > vma_mark_detached(next, true);
> > + nrpages = vma_pages(next);
> > +
> > + vms->nr_pages += nrpages;
> > + if (next->vm_flags & VM_LOCKED)
> > + vms->locked_vm += nrpages;
>
> So I bisected a self-test failure, memfd_secret specifically, to this
> commit. This is because you are double-counting VM_LOCKED...
>
> > +
> > + 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;
> > +
> > if (next->vm_flags & VM_LOCKED)
> > vms->locked_vm += vma_pages(next);
>
> ...the double counting being right here :) so I think we should drop the
> above couple lines.
Yeah, sure.
Thanks for reviewing!
>
> >
> > @@ -847,7 +846,9 @@ 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. */
> > diff --git a/mm/vma.h b/mm/vma.h
> > index cb67acf59012..cbf55e0e0c4f 100644
> > --- a/mm/vma.h
> > +++ b/mm/vma.h
> > @@ -33,12 +33,18 @@ 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 *prev; /* vma before the munmap area */
> > + struct vm_area_struct *next; /* vma after the munmap area */
> > struct list_head *uf; /* Userfaultfd list_head */
> > unsigned long start; /* Aligned start addr (inclusive) */
> > unsigned long end; /* Aligned end addr (exclusive) */
> > 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 */
> > };
> >
> > --
> > 2.43.0
> >
© 2016 - 2026 Red Hat, Inc.