From: PanJason <pyyjason@gmail.com>
This patch adds support for damos_stat in virtual address space.
It leverages the walk_page_range to walk the page table and gets
the folio from page table. The last folio scanned is stored in
damos->last_applied to prevent double counting.
---
mm/damon/vaddr.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 112 insertions(+), 1 deletion(-)
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 87e825349bdf..3e319b51cfd4 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -890,6 +890,117 @@ static unsigned long damos_va_migrate(struct damon_target *target,
return applied * PAGE_SIZE;
}
+struct damos_va_stat_private {
+ struct damos *scheme;
+ unsigned long *sz_filter_passed;
+};
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ struct damos_va_stat_private *priv = walk->private;
+ struct damos *s = priv->scheme;
+ unsigned long *sz_filter_passed = priv->sz_filter_passed;
+ struct folio *folio;
+ spinlock_t *ptl;
+ pmd_t pmde;
+
+ ptl = pmd_lock(walk->mm, pmd);
+ pmde = pmdp_get(pmd);
+
+ if (!pmd_present(pmde) || !pmd_trans_huge(pmde))
+ goto unlock;
+
+ /* Tell page walk code to not split the PMD */
+ walk->action = ACTION_CONTINUE;
+
+ folio = damon_get_folio(pmd_pfn(pmde));
+ if (!folio)
+ goto unlock;
+
+ if (damon_invalid_damos_folio(folio, s))
+ goto update_last_applied;
+
+ if (!damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd)){
+ *sz_filter_passed += folio_size(folio);
+ }
+
+ folio_put(folio);
+update_last_applied:
+ s->last_applied = folio;
+unlock:
+ spin_unlock(ptl);
+ return 0;
+}
+#else
+#define damon_va_stat_pmd_entry NULL
+#endif
+
+static int damos_va_stat_pte_entry(pte_t *pte, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ struct damos_va_stat_private *priv = walk->private;
+ struct damos *s = priv->scheme;
+ unsigned long *sz_filter_passed = priv->sz_filter_passed;
+ struct folio *folio;
+ pte_t ptent;
+
+ ptent = ptep_get(pte);
+ if (pte_none(ptent) || !pte_present(ptent))
+ return 0;
+
+ folio = damon_get_folio(pte_pfn(ptent));
+ if (!folio)
+ return 0;
+
+ if (damon_invalid_damos_folio(folio, s))
+ goto update_last_applied;
+
+ if (!damos_va_filter_out(s, folio, walk->vma, addr, pte, NULL)){
+ *sz_filter_passed += folio_size(folio);
+ }
+
+ folio_put(folio);
+
+update_last_applied:
+ s->last_applied = folio;
+ return 0;
+}
+
+static unsigned long damos_va_stat(struct damon_target *target,
+ struct damon_region *r, struct damos *s,
+ unsigned long *sz_filter_passed)
+{
+
+ struct damos_va_stat_private priv;
+ struct mm_struct *mm;
+ struct mm_walk_ops walk_ops = {
+ .pmd_entry = damos_va_stat_pmd_entry,
+ .pte_entry = damos_va_stat_pte_entry,
+ .walk_lock = PGWALK_RDLOCK,
+ };
+
+ priv.scheme = s;
+ priv.sz_filter_passed = sz_filter_passed;
+
+ if (!damon_scheme_has_filter(s)){
+ return 0;
+ }
+
+ mm = damon_get_mm(target);
+ if (!mm)
+ return 0;
+
+ mmap_read_lock(mm);
+ walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &priv);
+ mmap_read_unlock(mm);
+ mmput(mm);
+ pr_debug("Call va_stat: %lu\n", *sz_filter_passed);
+ return 0;
+
+}
+
static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
struct damon_target *t, struct damon_region *r,
struct damos *scheme, unsigned long *sz_filter_passed)
@@ -916,7 +1027,7 @@ static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
case DAMOS_MIGRATE_COLD:
return damos_va_migrate(t, r, scheme, sz_filter_passed);
case DAMOS_STAT:
- return 0;
+ return damos_va_stat(t, r, scheme, sz_filter_passed);
default:
/*
* DAMOS actions that are not yet supported by 'vaddr'.
--
2.47.3On Tue, 29 Jul 2025 06:53:30 -0700 Yueyang Pan <pyyjason@gmail.com> wrote: > From: PanJason <pyyjason@gmail.com> > > This patch adds support for damos_stat in virtual address space. > It leverages the walk_page_range to walk the page table and gets > the folio from page table. The last folio scanned is stored in > damos->last_applied to prevent double counting. Please add your Singed-off-by: tag[1] here. [1] https://docs.kernel.org/process/submitting-patches.html#developer-s-certificate-of-origin-1-1 Thanks, SJ [...]
On Tue, 29 Jul 2025 06:53:30 -0700 Yueyang Pan <pyyjason@gmail.com> wrote:
> From: PanJason <pyyjason@gmail.com>
>
> This patch adds support for damos_stat in virtual address space.
> It leverages the walk_page_range to walk the page table and gets
> the folio from page table. The last folio scanned is stored in
> damos->last_applied to prevent double counting.
Thank you for this patch, Pan! I left a few comments below. I think those are
mostly insignificant change requests, though.
> ---
> mm/damon/vaddr.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 112 insertions(+), 1 deletion(-)
>
> diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> index 87e825349bdf..3e319b51cfd4 100644
> --- a/mm/damon/vaddr.c
> +++ b/mm/damon/vaddr.c
> @@ -890,6 +890,117 @@ static unsigned long damos_va_migrate(struct damon_target *target,
> return applied * PAGE_SIZE;
> }
>
> +struct damos_va_stat_private {
> + struct damos *scheme;
> + unsigned long *sz_filter_passed;
> +};
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
> + unsigned long next, struct mm_walk *walk)
> +{
> + struct damos_va_stat_private *priv = walk->private;
> + struct damos *s = priv->scheme;
> + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> + struct folio *folio;
> + spinlock_t *ptl;
> + pmd_t pmde;
> +
> + ptl = pmd_lock(walk->mm, pmd);
> + pmde = pmdp_get(pmd);
> +
> + if (!pmd_present(pmde) || !pmd_trans_huge(pmde))
> + goto unlock;
> +
> + /* Tell page walk code to not split the PMD */
> + walk->action = ACTION_CONTINUE;
As David suggested, let's unify this with pte handler following the pattern of
madvise_cold_or_pageout_pte_range() and drop above ACTION_CONTINUE code, unless
you have different opinions.
> +
> + folio = damon_get_folio(pmd_pfn(pmde));
As also David suggested, let's use vm_normal_folio_pmd() instead, and drop
unnecessary folio_put().
> + if (!folio)
> + goto unlock;
damon_invalid_damos_folio() returns true if folio is NULL, so I think above
check is unnecessary.
> +
> + if (damon_invalid_damos_folio(folio, s))
> + goto update_last_applied;
Because we didn't really apply the DAMOS action, I think it is more proper to
goto 'unlock' directly.
Oh, and I now realize damon_invalid_damos_folio() puts the folio for none-NULL
invalid folio...
Because the code is simple, let's implement and use 'va' version
invalid_damos_folio(), say, damon_va_invalid_damos_folio(), which doesn't put
the folio.
> +
> + if (!damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd)){
> + *sz_filter_passed += folio_size(folio);
> + }
Let's remove braces for single statement, as suggested[1] by the coding style.
> +
> + folio_put(folio);
> +update_last_applied:
> + s->last_applied = folio;
> +unlock:
> + spin_unlock(ptl);
> + return 0;
> +}
> +#else
> +#define damon_va_stat_pmd_entry NULL
> +#endif
> +
> +static int damos_va_stat_pte_entry(pte_t *pte, unsigned long addr,
> + unsigned long next, struct mm_walk *walk)
> +{
> + struct damos_va_stat_private *priv = walk->private;
> + struct damos *s = priv->scheme;
> + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> + struct folio *folio;
> + pte_t ptent;
> +
> + ptent = ptep_get(pte);
> + if (pte_none(ptent) || !pte_present(ptent))
> + return 0;
> +
> + folio = damon_get_folio(pte_pfn(ptent));
As David suggested, let's use vm_normal_folio() here, and remove below
folio_put().
> + if (!folio)
> + return 0;
As also mentioned above, let's drop above NULL case check, in favor of that in
damon_va_invalid_damos_folio().
> +
> + if (damon_invalid_damos_folio(folio, s))
> + goto update_last_applied;
Again, I don't think we need to update s->last_applied in this case. Let's
do only necessary cleanups and return.
> +
> + if (!damos_va_filter_out(s, folio, walk->vma, addr, pte, NULL)){
> + *sz_filter_passed += folio_size(folio);
> + }
Let's drop braces for single statement[1].
> +
> + folio_put(folio);
> +
> +update_last_applied:
> + s->last_applied = folio;
> + return 0;
> +}
> +
> +static unsigned long damos_va_stat(struct damon_target *target,
> + struct damon_region *r, struct damos *s,
> + unsigned long *sz_filter_passed)
> +{
> +
Let's remove this unnecessary blank line.
> + struct damos_va_stat_private priv;
> + struct mm_struct *mm;
> + struct mm_walk_ops walk_ops = {
> + .pmd_entry = damos_va_stat_pmd_entry,
> + .pte_entry = damos_va_stat_pte_entry,
> + .walk_lock = PGWALK_RDLOCK,
> + };
> +
> + priv.scheme = s;
> + priv.sz_filter_passed = sz_filter_passed;
> +
> + if (!damon_scheme_has_filter(s)){
> + return 0;
> + }
Let's remove braces for single statement[1].
> +
> + mm = damon_get_mm(target);
> + if (!mm)
> + return 0;
> +
> + mmap_read_lock(mm);
> + walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &priv);
> + mmap_read_unlock(mm);
> + mmput(mm);
> + pr_debug("Call va_stat: %lu\n", *sz_filter_passed);
I don't think we really need this debug log. Can we remove?
> + return 0;
> +
Yet another unnecessary blank line. Let's remove.
> +}
> +
> static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
> struct damon_target *t, struct damon_region *r,
> struct damos *scheme, unsigned long *sz_filter_passed)
> @@ -916,7 +1027,7 @@ static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
> case DAMOS_MIGRATE_COLD:
> return damos_va_migrate(t, r, scheme, sz_filter_passed);
> case DAMOS_STAT:
> - return 0;
> + return damos_va_stat(t, r, scheme, sz_filter_passed);
> default:
> /*
> * DAMOS actions that are not yet supported by 'vaddr'.
> --
> 2.47.3
[1] https://docs.kernel.org/process/coding-style.html
Thanks,
SJ
On 29.07.25 15:53, Yueyang Pan wrote:
> From: PanJason <pyyjason@gmail.com>
>
> This patch adds support for damos_stat in virtual address space.
> It leverages the walk_page_range to walk the page table and gets
> the folio from page table. The last folio scanned is stored in
> damos->last_applied to prevent double counting.
> ---
> mm/damon/vaddr.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 112 insertions(+), 1 deletion(-)
>
> diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> index 87e825349bdf..3e319b51cfd4 100644
> --- a/mm/damon/vaddr.c
> +++ b/mm/damon/vaddr.c
> @@ -890,6 +890,117 @@ static unsigned long damos_va_migrate(struct damon_target *target,
> return applied * PAGE_SIZE;
> }
>
> +struct damos_va_stat_private {
> + struct damos *scheme;
> + unsigned long *sz_filter_passed;
> +};
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
> + unsigned long next, struct mm_walk *walk)
> +{
> + struct damos_va_stat_private *priv = walk->private;
> + struct damos *s = priv->scheme;
> + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> + struct folio *folio;
> + spinlock_t *ptl;
> + pmd_t pmde;
> +
> + ptl = pmd_lock(walk->mm, pmd);
> + pmde = pmdp_get(pmd);
> +
> + if (!pmd_present(pmde) || !pmd_trans_huge(pmde))
> + goto unlock;
> +
> + /* Tell page walk code to not split the PMD */
> + walk->action = ACTION_CONTINUE;
> +
> + folio = damon_get_folio(pmd_pfn(pmde));
> + if (!folio)
> + goto unlock;
> +
> + if (damon_invalid_damos_folio(folio, s))
> + goto update_last_applied;
> +
> + if (!damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd)){
> + *sz_filter_passed += folio_size(folio);
See my comment below regarding vm_normal_page and folio references.
But this split into two handlers is fairly odd. Usually we only have a
pmd_entry callback (see madvise_cold_or_pageout_pte_range as an
example), and handle !CONFIG_TRANSPARENT_HUGEPAGE in there.
Then, there is also no need to mess with ACTION_CONTINUE
> + }
> +
> + folio_put(folio);
> +update_last_applied:
> + s->last_applied = folio;
> +unlock:
> + spin_unlock(ptl);
> + return 0;
> +}
> +#else
> +#define damon_va_stat_pmd_entry NULL
> +#endif
> +
> +static int damos_va_stat_pte_entry(pte_t *pte, unsigned long addr,
> + unsigned long next, struct mm_walk *walk)
> +{
> + struct damos_va_stat_private *priv = walk->private;
> + struct damos *s = priv->scheme;
> + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> + struct folio *folio;
> + pte_t ptent;
> +
> + ptent = ptep_get(pte);
> + if (pte_none(ptent) || !pte_present(ptent))
> + return 0;
> +
> + folio = damon_get_folio(pte_pfn(ptent));
> + if (!folio)
> + return 0;
We have vm_normal_folio() and friends for a reason -- so you don't have
to do pte_pfn() manually.
... and now I am confused. We are holding the PTL, so why would you have
to grab+put a folio reference here *at all*.
--
Cheers,
David / dhildenb
On Tue, Jul 29, 2025 at 04:11:32PM +0200, David Hildenbrand wrote:
> On 29.07.25 15:53, Yueyang Pan wrote:
> > From: PanJason <pyyjason@gmail.com>
> >
> > This patch adds support for damos_stat in virtual address space.
> > It leverages the walk_page_range to walk the page table and gets
> > the folio from page table. The last folio scanned is stored in
> > damos->last_applied to prevent double counting.
> > ---
> > mm/damon/vaddr.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++-
> > 1 file changed, 112 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> > index 87e825349bdf..3e319b51cfd4 100644
> > --- a/mm/damon/vaddr.c
> > +++ b/mm/damon/vaddr.c
> > @@ -890,6 +890,117 @@ static unsigned long damos_va_migrate(struct damon_target *target,
> > return applied * PAGE_SIZE;
> > }
> > +struct damos_va_stat_private {
> > + struct damos *scheme;
> > + unsigned long *sz_filter_passed;
> > +};
> > +
> > +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> > +static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
> > + unsigned long next, struct mm_walk *walk)
> > +{
> > + struct damos_va_stat_private *priv = walk->private;
> > + struct damos *s = priv->scheme;
> > + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> > + struct folio *folio;
> > + spinlock_t *ptl;
> > + pmd_t pmde;
> > +
> > + ptl = pmd_lock(walk->mm, pmd);
> > + pmde = pmdp_get(pmd);
> > +
> > + if (!pmd_present(pmde) || !pmd_trans_huge(pmde))
> > + goto unlock;
> > +
> > + /* Tell page walk code to not split the PMD */
> > + walk->action = ACTION_CONTINUE;
> > +
> > + folio = damon_get_folio(pmd_pfn(pmde));
> > + if (!folio)
> > + goto unlock;
> > +
> > + if (damon_invalid_damos_folio(folio, s))
> > + goto update_last_applied;
> > +
> > + if (!damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd)){
> > + *sz_filter_passed += folio_size(folio);
>
> See my comment below regarding vm_normal_page and folio references.
>
> But this split into two handlers is fairly odd. Usually we only have a
> pmd_entry callback (see madvise_cold_or_pageout_pte_range as an example),
> and handle !CONFIG_TRANSPARENT_HUGEPAGE in there.
>
> Then, there is also no need to mess with ACTION_CONTINUE
>
Hi David. Thanks for your comment. I was not aware of the convention so I
followed the existing code. I had a discussion with SJ today and in the
next version I will change this by combining *pmd_entry() and *pte_entry().
We will also format the existing code in future patches.
> > + }
> > +
> > + folio_put(folio);
> > +update_last_applied:
> > + s->last_applied = folio;
> > +unlock:
> > + spin_unlock(ptl);
> > + return 0;
> > +}
> > +#else
> > +#define damon_va_stat_pmd_entry NULL
> > +#endif
> > +
> > +static int damos_va_stat_pte_entry(pte_t *pte, unsigned long addr,
> > + unsigned long next, struct mm_walk *walk)
> > +{
> > + struct damos_va_stat_private *priv = walk->private;
> > + struct damos *s = priv->scheme;
> > + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> > + struct folio *folio;
> > + pte_t ptent;
> > +
> > + ptent = ptep_get(pte);
> > + if (pte_none(ptent) || !pte_present(ptent))
> > + return 0;
> > +
> > + folio = damon_get_folio(pte_pfn(ptent));
> > + if (!folio)
> > + return 0;
>
> We have vm_normal_folio() and friends for a reason -- so you don't have to
> do pte_pfn() manually.
>
> ... and now I am confused. We are holding the PTL, so why would you have to
> grab+put a folio reference here *at all*.
>
Thanks for pointing out. I thought someone could still change the folio and
realized it could not happen with PTL. I will use vm_normal_folio* in the
next version.
> --
> Cheers,
>
> David / dhildenb
>
Hi Pan and David, thank you for this patch and comments!
On Tue, 29 Jul 2025 16:11:32 +0200 David Hildenbrand <david@redhat.com> wrote:
> On 29.07.25 15:53, Yueyang Pan wrote:
> > From: PanJason <pyyjason@gmail.com>
> >
> > This patch adds support for damos_stat in virtual address space.
> > It leverages the walk_page_range to walk the page table and gets
> > the folio from page table. The last folio scanned is stored in
> > damos->last_applied to prevent double counting.
> > ---
> > mm/damon/vaddr.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++-
> > 1 file changed, 112 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> > index 87e825349bdf..3e319b51cfd4 100644
> > --- a/mm/damon/vaddr.c
> > +++ b/mm/damon/vaddr.c
> > @@ -890,6 +890,117 @@ static unsigned long damos_va_migrate(struct damon_target *target,
> > return applied * PAGE_SIZE;
> > }
> >
> > +struct damos_va_stat_private {
> > + struct damos *scheme;
> > + unsigned long *sz_filter_passed;
> > +};
> > +
> > +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> > +static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
> > + unsigned long next, struct mm_walk *walk)
> > +{
> > + struct damos_va_stat_private *priv = walk->private;
> > + struct damos *s = priv->scheme;
> > + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> > + struct folio *folio;
> > + spinlock_t *ptl;
> > + pmd_t pmde;
> > +
> > + ptl = pmd_lock(walk->mm, pmd);
> > + pmde = pmdp_get(pmd);
> > +
> > + if (!pmd_present(pmde) || !pmd_trans_huge(pmde))
> > + goto unlock;
> > +
> > + /* Tell page walk code to not split the PMD */
> > + walk->action = ACTION_CONTINUE;
> > +
> > + folio = damon_get_folio(pmd_pfn(pmde));
> > + if (!folio)
> > + goto unlock;
> > +
> > + if (damon_invalid_damos_folio(folio, s))
> > + goto update_last_applied;
> > +
> > + if (!damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd)){
> > + *sz_filter_passed += folio_size(folio);
>
> See my comment below regarding vm_normal_page and folio references.
>
> But this split into two handlers is fairly odd. Usually we only have a
> pmd_entry callback (see madvise_cold_or_pageout_pte_range as an
> example), and handle !CONFIG_TRANSPARENT_HUGEPAGE in there.
>
> Then, there is also no need to mess with ACTION_CONTINUE
I don't really mind this, but I agree keeping the consisteency would be good.
Pan, could you please unify the handlers into one?
>
> > + }
> > +
> > + folio_put(folio);
> > +update_last_applied:
> > + s->last_applied = folio;
> > +unlock:
> > + spin_unlock(ptl);
> > + return 0;
> > +}
> > +#else
> > +#define damon_va_stat_pmd_entry NULL
> > +#endif
> > +
> > +static int damos_va_stat_pte_entry(pte_t *pte, unsigned long addr,
> > + unsigned long next, struct mm_walk *walk)
> > +{
> > + struct damos_va_stat_private *priv = walk->private;
> > + struct damos *s = priv->scheme;
> > + unsigned long *sz_filter_passed = priv->sz_filter_passed;
> > + struct folio *folio;
> > + pte_t ptent;
> > +
> > + ptent = ptep_get(pte);
> > + if (pte_none(ptent) || !pte_present(ptent))
> > + return 0;
> > +
> > + folio = damon_get_folio(pte_pfn(ptent));
> > + if (!folio)
> > + return 0;
>
> We have vm_normal_folio() and friends for a reason -- so you don't have
> to do pte_pfn() manually.
>
> ... and now I am confused. We are holding the PTL, so why would you have
> to grab+put a folio reference here *at all*.
We don't have to. I think Pan does so because other similar existing code in
this file is also doing so. I was doing so because I wanted to use the handy
damon_get_folio() and those are not making real problems.
But, yes, unnecessary things are unnecessary things. Pan, could you please use
vm_normal_folio() instead of damon_get_folio() and remove the related
folio_put() call?
I will also work on cleanup of existing unnecessary folio reference
manipulations, regardless of this patch series.
Thanks,
SJ
[...]
© 2016 - 2026 Red Hat, Inc.