Re: [PATCH v2 1/7] mm: factor out generic PTE batch detection from swap_pte_batch()

From: Garg, Shivank

Date: Sun Aug 16 2026 - 03:49:04 EST


On Fri, 2026-08-14 at 13:30 +0530, Shivank Garg wrote:
> On Thu, 2026-08-13 at 11:57 +0200, David Hildenbrand (Arm) wrote:
> > On 8/13/26 06:23, Shivank Garg wrote:
> > > Factor out the generic PTE batch detection logic from swap_pte_batch()
> > > into softleaf_pte_batch() helper, so that it can be reused by upcoming
> > > patch that adds restore-side batching of migration entries.
> > >
> > > swap_pte_batch() now keeps only its swap-specific concerns and
> > > delegates the batch detection to softleaf_pte_batch().
> > >
> > > No functional changes intended.
> > >
> > > Signed-off-by: Shivank Garg <shivankg@xxxxxxx>
> > > ---
> > > mm/internal.h | 36 +++++++++++++++++++++---------------
> > > 1 file changed, 21 insertions(+), 15 deletions(-)
> > >
> > > diff --git a/mm/internal.h b/mm/internal.h
> > > index a5d0488a54dc..1e1ab53b642e 100644
> > > --- a/mm/internal.h
> > > +++ b/mm/internal.h
> > > @@ -560,6 +560,26 @@ static inline void set_softleaf_ptes(struct mm_struct *mm, unsigned long addr,
> > > }
> > > }
> > >
> > > +static inline int softleaf_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
> > > +{
> > > + pte_t expected_pte = pte_next_softleaf_offset(pte);
> > > + const pte_t *end_ptep = start_ptep + max_nr;
> > > + pte_t *ptep = start_ptep + 1;
> > > +
> >
> > Wouldn't we want some way to make sure that the softleaf entries actually carry
> > offsets or pfns of sorts?
> >
> > > + VM_WARN_ON(max_nr < 1);
> > > +
> > > + while (ptep < end_ptep) {
> > > + pte = ptep_get(ptep);
> > > +
> > > + if (!pte_same(pte, expected_pte))
> > > + break;
> > > + expected_pte = pte_next_softleaf_offset(expected_pte);
> > > + ptep++;
> > > + }
> > > +
> > > + return ptep - start_ptep;
> > > +}
> > > +
> > > /**
> > > * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
> > > * @start_ptep: Page table pointer for the first entry.
> > > @@ -577,23 +597,9 @@ static inline void set_softleaf_ptes(struct mm_struct *mm, unsigned long addr,
> > > */
> > > static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
> > > {
> > > - pte_t expected_pte = pte_next_softleaf_offset(pte);
> > > - const pte_t *end_ptep = start_ptep + max_nr;
> > > - pte_t *ptep = start_ptep + 1;
> > > -
> > > - VM_WARN_ON(max_nr < 1);
> > > VM_WARN_ON(!softleaf_is_swap(softleaf_from_pte(pte)));
> >
> > Any reason we cannot simply rename this thing and drop the VM_WARN_ON? I mean, a
> > caller can just do that.
> >
>
> Thanks David,
>
> Agreed on both suggestions.
>
> I'll add VM_WARN_ON(!softleaf_is_swap(entry) && !softleaf_has_pfn(entry))
> in softleaf_pte_batch() for making sure it has offset/pfn and remove
> swap_pte_batch().
>
> Best regards,
> Shivank

diff --git a/mm/internal.h b/mm/internal.h
index a5d0488a54dc..31c7c6a04eac 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -561,29 +561,31 @@ static inline void set_softleaf_ptes(struct mm_struct *mm, unsigned long addr,
}

/**
- * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
+ * softleaf_pte_batch - detect a PTE batch for a set of contiguous softleaf entries
* @start_ptep: Page table pointer for the first entry.
* @max_nr: The maximum number of table entries to consider.
* @pte: Page table entry for the first entry.
*
- * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
- * containing swap entries all with consecutive offsets and targeting the same
- * swap type, all with matching swp pte bits.
+ * Detect consecutive (non-present) PTEs containing softleaf entries with
+ * consecutive offsets and matching PTE bits. @pte must contain a swap entry or
+ * a softleaf entry carrying PFN.
*
* max_nr must be at least one and must be limited by the caller so scanning
* cannot exceed a single page table.
*
* Return: the number of table entries in the batch.
*/
-static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
+static inline int softleaf_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
{
- pte_t expected_pte = pte_next_softleaf_offset(pte);
+ const softleaf_t entry = softleaf_from_pte(pte);
+ pte_t expected_pte;
const pte_t *end_ptep = start_ptep + max_nr;
pte_t *ptep = start_ptep + 1;

VM_WARN_ON(max_nr < 1);
- VM_WARN_ON(!softleaf_is_swap(softleaf_from_pte(pte)));
+ VM_WARN_ON(!softleaf_is_swap(entry) && !softleaf_has_pfn(entry));

+ expected_pte = pte_next_softleaf_offset(pte);
while (ptep < end_ptep) {
pte = ptep_get(ptep);

diff --git a/mm/madvise.c b/mm/madvise.c
index c179938097bf..8bed1c58c4bb 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -692,7 +692,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,

if (softleaf_is_swap(entry)) {
max_nr = (end - addr) / PAGE_SIZE;
- nr = swap_pte_batch(pte, max_nr, ptent);
+ nr = softleaf_pte_batch(pte, max_nr, ptent);
nr_swap -= nr;
swap_put_entries_direct(entry, nr);
clear_nonpresent_ptes(mm, addr, pte, nr);
diff --git a/mm/memory.c b/mm/memory.c
index a3d450d225ad..687796e1af84 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1889,7 +1889,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
if (!should_zap_cows(details))
return 1;

- nr = swap_pte_batch(pte, max_nr, ptent);
+ nr = softleaf_pte_batch(pte, max_nr, ptent);
rss[MM_SWAPENTS] -= nr;
swap_put_entries_direct(entry, nr);
} else if (softleaf_is_migration(entry)) {
@@ -4758,7 +4758,7 @@ static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
* from different backends. And they are likely corner cases. Similar
* things might be added once zswap support large folios.
*/
- if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages)
+ if (softleaf_pte_batch(ptep, nr_pages, pte) != nr_pages)
return false;
return true;
}
@@ -5062,7 +5062,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
folio_ptep = vmf->pte - idx;
folio_pte = ptep_get(folio_ptep);
if (!pte_same(folio_pte, pte_move_softleaf_offset(vmf->orig_pte, -idx)) ||
- swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
+ softleaf_pte_batch(folio_ptep, nr, folio_pte) != nr)
goto check_folio;

page_idx = idx;