[PATCH 0/2] mm/gup: batch PTE-mapped large folios in follow_page_mask()

[PATCH 0/2] mm/gup: batch PTE-mapped large folios in follow_page_mask()

[Rik van Riel]

follow_page_mask() reports the size of the page it found with a page_mask:
a bitmask of the enclosing naturally-aligned huge page. That form can only
describe a power-of-two block aligned to its own size, so a PTE-mapped
large folio (mTHP) is walked one page at a time even though it maps a
contiguous run, while the PMD/PUD-mapped cases already return their whole
mapping in one step.

Patch 1 replaces the page_mask output with nr_pages (a plain count) and
adds an @end argument bounding the walk, with no functional change: the
huge PMD/PUD paths report the same stride as before, just as a count.

Patch 2 uses the new interface to batch the PTE case: follow_pte_batch()
counts consecutive present PTEs that map consecutive pages of the same
folio with a uniform write bit, bounded by the page table, @end, the VMA,
and the folio itself, then follow_page_pte() hands the whole run back in
one call.

Measured with mm/gup_test.c (PIN_LONGTERM_BENCHMARK, the slow
pin_user_pages() path) on a 256 MB MADV_HUGEPAGE anonymous region in a
4 CPU VM, median get time over 16 iterations. Each folio size was confirmed
through the per-size anon_fault_alloc counters (4096 folios for 64 kB, 128
for 2 MB):

  gup_test -L -m 256 -n 65536 -r 16 -t
                        before      after
  64 kB mTHP            3140 us      412 us   (7.6x)
  2 MB THP (control)      78 us       76 us
  4 kB base (control)   3010 us     3042 us

The PMD-mapped 2 MB THP already returns the whole mapping in one step, so
it stays fast and unchanged. The 4 kB baseline shows the per-page walk cost
that the 64 kB case paid before this change; only the PTE-mapped large
folio case improves.

Both patches apply standalone against mm-unstable; no other series is
required.

Rik van Riel (2):
  mm/gup: pass an end address to follow_page_mask() and return a page
    count
  mm/gup: batch contiguous PTE-mapped large folios in follow_page_mask()

 mm/gup.c | 139 ++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 97 insertions(+), 42 deletions(-)

base-commit: 7368ccdeff50c27809d3a8276c85bae7e402c96c
---
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
To: linux-kernel@vger.kernel.org
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: "Liam R. Howlett" <liam@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: kernel-team@meta.com
-- 
2.53.0-Meta

[PATCH 1/2] mm/gup: pass an end address to follow_page_mask() and return a page count

[Rik van Riel]

follow_page_mask() reports how many pages the returned page covers with a
page_mask: a bitmask of the enclosing naturally-aligned huge page. Callers
turn that into a stride, which assumes the run is a power-of-two block
aligned to its own size.

That form cannot describe an arbitrary contiguous run, which a later patch
needs to batch PTE-mapped large folios.

Replace the page_mask output with nr_pages, the number of contiguous pages
the returned page covers starting at @address, and add an @end argument
bounding how far the walk looks, so a small request does not scan an entire
large folio.

The huge PMD and PUD paths report the same stride as before, now as a count
clamped to @end. __get_user_pages() uses the count directly.

No functional change intended.

Assisted-by: Claude:claude-opus-4.8
Signed-off-by: Rik van Riel <riel@surriel.com>
---
 mm/gup.c | 94 +++++++++++++++++++++++++++++++-------------------------
 1 file changed, 52 insertions(+), 42 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 99902c15703b..3437cd3407d5 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -647,8 +647,9 @@ static inline bool can_follow_write_pud(pud_t pud, struct page *page,
 }
 
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
-				    unsigned long addr, pud_t *pudp,
-				    int flags, unsigned long *page_mask)
+				    unsigned long addr, unsigned long end,
+				    pud_t *pudp, int flags,
+				    unsigned long *nr_pages)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *page;
@@ -672,10 +673,13 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 		return ERR_PTR(-EMLINK);
 
 	ret = try_grab_folio(page_folio(page), 1, flags);
-	if (ret)
+	if (ret) {
 		page = ERR_PTR(ret);
-	else
-		*page_mask = HPAGE_PUD_NR - 1;
+	} else {
+		unsigned long off = (addr & ~PUD_MASK) >> PAGE_SHIFT;
+
+		*nr_pages = min(HPAGE_PUD_NR - off, (end - addr) >> PAGE_SHIFT);
+	}
 
 	return page;
 }
@@ -699,9 +703,9 @@ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
 }
 
 static struct page *follow_huge_pmd(struct vm_area_struct *vma,
-				    unsigned long addr, pmd_t *pmd,
-				    unsigned int flags,
-				    unsigned long *page_mask)
+				    unsigned long addr, unsigned long end,
+				    pmd_t *pmd, unsigned int flags,
+				    unsigned long *nr_pages)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t pmdval = *pmd;
@@ -738,23 +742,25 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 #endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
-	*page_mask = HPAGE_PMD_NR - 1;
+	*nr_pages = min(HPAGE_PMD_NR - ((addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT),
+			(end - addr) >> PAGE_SHIFT);
 
 	return page;
 }
 
 #else  /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
-				    unsigned long addr, pud_t *pudp,
-				    int flags, unsigned long *page_mask)
+				    unsigned long addr, unsigned long end,
+				    pud_t *pudp, int flags,
+				    unsigned long *nr_pages)
 {
 	return NULL;
 }
 
 static struct page *follow_huge_pmd(struct vm_area_struct *vma,
-				    unsigned long addr, pmd_t *pmd,
-				    unsigned int flags,
-				    unsigned long *page_mask)
+				    unsigned long addr, unsigned long end,
+				    pmd_t *pmd, unsigned int flags,
+				    unsigned long *nr_pages)
 {
 	return NULL;
 }
@@ -800,7 +806,8 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page,
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd, unsigned int flags)
+		unsigned long address, unsigned long end, pmd_t *pmd,
+		unsigned int flags, unsigned long *nr_pages)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct folio *folio;
@@ -885,6 +892,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		 */
 		folio_mark_accessed(folio);
 	}
+
 out:
 	pte_unmap_unlock(ptep, ptl);
 	return page;
@@ -896,9 +904,9 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 }
 
 static struct page *follow_pmd_mask(struct vm_area_struct *vma,
-				    unsigned long address, pud_t *pudp,
-				    unsigned int flags,
-				    unsigned long *page_mask)
+				    unsigned long address, unsigned long end,
+				    pud_t *pudp, unsigned int flags,
+				    unsigned long *nr_pages)
 {
 	pmd_t *pmd, pmdval;
 	spinlock_t *ptl;
@@ -912,7 +920,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags, address);
 	if (likely(!pmd_leaf(pmdval)))
-		return follow_page_pte(vma, address, pmd, flags);
+		return follow_page_pte(vma, address, end, pmd, flags, nr_pages);
 
 	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))
 		return no_page_table(vma, flags, address);
@@ -925,24 +933,24 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	}
 	if (unlikely(!pmd_leaf(pmdval))) {
 		spin_unlock(ptl);
-		return follow_page_pte(vma, address, pmd, flags);
+		return follow_page_pte(vma, address, end, pmd, flags, nr_pages);
 	}
 	if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) {
 		spin_unlock(ptl);
 		split_huge_pmd(vma, pmd, address);
 		/* If pmd was left empty, stuff a page table in there quickly */
 		return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) :
-			follow_page_pte(vma, address, pmd, flags);
+			follow_page_pte(vma, address, end, pmd, flags, nr_pages);
 	}
-	page = follow_huge_pmd(vma, address, pmd, flags, page_mask);
+	page = follow_huge_pmd(vma, address, end, pmd, flags, nr_pages);
 	spin_unlock(ptl);
 	return page;
 }
 
 static struct page *follow_pud_mask(struct vm_area_struct *vma,
-				    unsigned long address, p4d_t *p4dp,
-				    unsigned int flags,
-				    unsigned long *page_mask)
+				    unsigned long address, unsigned long end,
+				    p4d_t *p4dp, unsigned int flags,
+				    unsigned long *nr_pages)
 {
 	pud_t *pudp, pud;
 	spinlock_t *ptl;
@@ -955,7 +963,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 		return no_page_table(vma, flags, address);
 	if (pud_leaf(pud)) {
 		ptl = pud_lock(mm, pudp);
-		page = follow_huge_pud(vma, address, pudp, flags, page_mask);
+		page = follow_huge_pud(vma, address, end, pudp, flags, nr_pages);
 		spin_unlock(ptl);
 		if (page)
 			return page;
@@ -964,13 +972,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	if (unlikely(pud_bad(pud)))
 		return no_page_table(vma, flags, address);
 
-	return follow_pmd_mask(vma, address, pudp, flags, page_mask);
+	return follow_pmd_mask(vma, address, end, pudp, flags, nr_pages);
 }
 
 static struct page *follow_p4d_mask(struct vm_area_struct *vma,
-				    unsigned long address, pgd_t *pgdp,
-				    unsigned int flags,
-				    unsigned long *page_mask)
+				    unsigned long address, unsigned long end,
+				    pgd_t *pgdp, unsigned int flags,
+				    unsigned long *nr_pages)
 {
 	p4d_t *p4dp, p4d;
 
@@ -981,15 +989,16 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 	if (!p4d_present(p4d) || p4d_bad(p4d))
 		return no_page_table(vma, flags, address);
 
-	return follow_pud_mask(vma, address, p4dp, flags, page_mask);
+	return follow_pud_mask(vma, address, end, p4dp, flags, nr_pages);
 }
 
 /**
  * follow_page_mask - look up a page descriptor from a user-virtual address
  * @vma: vm_area_struct mapping @address
  * @address: virtual address to look up
+ * @end: virtual address at which to stop batching contiguous pages
  * @flags: flags modifying lookup behaviour
- * @page_mask: a pointer to output page_mask
+ * @nr_pages: output; number of contiguous pages the caller can read
  *
  * @flags can have FOLL_ flags set, defined in <linux/mm.h>
  *
@@ -998,15 +1007,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
  * relevant with FOLL_PIN and !FOLL_WRITE.
  *
- * On output, @page_mask is set according to the size of the page.
+ * On output, @nr_pages holds how many contiguous pages the folio that includes
+ * the returned page has mapped into this process, so the caller can advance
+ * over a large folio in one step.
  *
  * Return: the mapped (struct page *), %NULL if no mapping exists, or
  * an error pointer if there is a mapping to something not represented
  * by a page descriptor (see also vm_normal_page()).
  */
 static struct page *follow_page_mask(struct vm_area_struct *vma,
-			      unsigned long address, unsigned int flags,
-			      unsigned long *page_mask)
+			      unsigned long address, unsigned long end,
+			      unsigned int flags, unsigned long *nr_pages)
 {
 	pgd_t *pgd;
 	struct mm_struct *mm = vma->vm_mm;
@@ -1014,13 +1025,13 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 
 	vma_pgtable_walk_begin(vma);
 
-	*page_mask = 0;
+	*nr_pages = 1;
 	pgd = pgd_offset(mm, address);
 
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		page = no_page_table(vma, flags, address);
 	else
-		page = follow_p4d_mask(vma, address, pgd, flags, page_mask);
+		page = follow_p4d_mask(vma, address, end, pgd, flags, nr_pages);
 
 	vma_pgtable_walk_end(vma);
 
@@ -1358,7 +1369,6 @@ static long __get_user_pages(struct mm_struct *mm,
 {
 	long ret = 0, i = 0;
 	struct vm_area_struct *vma = NULL;
-	unsigned long page_mask = 0;
 
 	if (!nr_pages)
 		return 0;
@@ -1373,7 +1383,7 @@ static long __get_user_pages(struct mm_struct *mm,
 
 	do {
 		struct page *page;
-		unsigned int page_increm;
+		unsigned long page_increm;
 
 		/* first iteration or cross vma bound */
 		if (!vma || start >= vma->vm_end) {
@@ -1400,7 +1410,7 @@ static long __get_user_pages(struct mm_struct *mm,
 						pages ? &page : NULL);
 				if (ret)
 					goto out;
-				page_mask = 0;
+				page_increm = 1;
 				goto next_page;
 			}
 
@@ -1423,7 +1433,8 @@ static long __get_user_pages(struct mm_struct *mm,
 		}
 		cond_resched();
 
-		page = follow_page_mask(vma, start, gup_flags, &page_mask);
+		page = follow_page_mask(vma, start, start + nr_pages * PAGE_SIZE,
+					gup_flags, &page_increm);
 		if (!page || PTR_ERR(page) == -EMLINK) {
 			ret = faultin_page(vma, start, gup_flags,
 					   PTR_ERR(page) == -EMLINK, locked);
@@ -1456,7 +1467,6 @@ static long __get_user_pages(struct mm_struct *mm,
 			goto out;
 		}
 next_page:
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
 		if (page_increm > nr_pages)
 			page_increm = nr_pages;
 
-- 
2.53.0-Meta

Re: [PATCH 1/2] mm/gup: pass an end address to follow_page_mask() and return a page count

[David Hildenbrand (Arm)]

On 7/29/26 05:02, Rik van Riel wrote:
> follow_page_mask() reports how many pages the returned page covers with a
> page_mask: a bitmask of the enclosing naturally-aligned huge page. Callers
> turn that into a stride, which assumes the run is a power-of-two block
> aligned to its own size.
> 
> That form cannot describe an arbitrary contiguous run, which a later patch
> needs to batch PTE-mapped large folios.
> 
> Replace the page_mask output with nr_pages, the number of contiguous pages
> the returned page covers starting at @address, and add an @end argument
> bounding how far the walk looks, so a small request does not scan an entire
> large folio.
> 
> The huge PMD and PUD paths report the same stride as before, now as a count
> clamped to @end. __get_user_pages() uses the count directly.
> 
> No functional change intended.
> 
> Assisted-by: Claude:claude-opus-4.8
> Signed-off-by: Rik van Riel <riel@surriel.com>


This patch moves us closer towards the GUP-fast path, however, that is about to
change:

	https://lore.kernel.org/all/20260219050250.266876166@ruivo.org/

With that in mind, I guess in the future we want to have:

static long follow_page_mask(struct vm_area_struct *vma,
		unsigned long address, unsigned long end,
		unsigned int flags, struct page **pages)

or even better, now that follow_page() no longer exists, in light of gup_fast():


static long gup_slow(struct vm_area_struct *vma,
		unsigned long address, unsigned long end,
		unsigned int flags, struct page **pages)

Returning the number of pinned pages.


In particular, such an interface would allows us to process multiple
ptes/pmds/... in one go, without having to restart the page table walk all the
time for each non-batchable folio.

And make gup_slow make look more like gup_fast.

I think that's one of the suboptimal things that we inherited from the legacy
follow_page() interface I ripped out a while ago.

... and get rid of that nasty "if (page_increm > 1) {" handling outside of
follow_page_mask().


I'm ok with doing this patch here first, because what I describe is a much
bigger rework.

But being able to pin many pages in one page table walk sounds like another
excellent optimization opportunity, which would even reduce the batching benefit
you see today with patch #2 by simply making PTE processing easier.


I think I can find someone to work on this.

> ---
>  mm/gup.c | 94 +++++++++++++++++++++++++++++++-------------------------
>  1 file changed, 52 insertions(+), 42 deletions(-)
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 99902c15703b..3437cd3407d5 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -647,8 +647,9 @@ static inline bool can_follow_write_pud(pud_t pud, struct page *page,
>  }
>  
>  static struct page *follow_huge_pud(struct vm_area_struct *vma,
> -				    unsigned long addr, pud_t *pudp,
> -				    int flags, unsigned long *page_mask)
> +				    unsigned long addr, unsigned long end,
> +				    pud_t *pudp, int flags,
> +				    unsigned long *nr_pages)

While at it, please convert this end the other instances to two-tab indent on
the second+ line.

[...]

>  /**
>   * follow_page_mask - look up a page descriptor from a user-virtual address
>   * @vma: vm_area_struct mapping @address
>   * @address: virtual address to look up
> + * @end: virtual address at which to stop batching contiguous pages
>   * @flags: flags modifying lookup behaviour
> - * @page_mask: a pointer to output page_mask
> + * @nr_pages: output; number of contiguous pages the caller can read
>   *
>   * @flags can have FOLL_ flags set, defined in <linux/mm.h>
>   *
> @@ -998,15 +1007,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
>   * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
>   * relevant with FOLL_PIN and !FOLL_WRITE.
>   *
> - * On output, @page_mask is set according to the size of the page.
> + * On output, @nr_pages holds how many contiguous pages the folio that includes
> + * the returned page has mapped into this process, so the caller can advance
> + * over a large folio in one step.
>   *
>   * Return: the mapped (struct page *), %NULL if no mapping exists, or
>   * an error pointer if there is a mapping to something not represented
>   * by a page descriptor (see also vm_normal_page()).
>   */
>  static struct page *follow_page_mask(struct vm_area_struct *vma,
> -			      unsigned long address, unsigned int flags,
> -			      unsigned long *page_mask)
> +			      unsigned long address, unsigned long end,
> +			      unsigned int flags, unsigned long *nr_pages)
>  {
>  	pgd_t *pgd;
>  	struct mm_struct *mm = vma->vm_mm;
> @@ -1014,13 +1025,13 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
>  
>  	vma_pgtable_walk_begin(vma);
>  
> -	*page_mask = 0;
> +	*nr_pages = 1;
>  	pgd = pgd_offset(mm, address);
>  
>  	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
>  		page = no_page_table(vma, flags, address);
>  	else
> -		page = follow_p4d_mask(vma, address, pgd, flags, page_mask);
> +		page = follow_p4d_mask(vma, address, end, pgd, flags, nr_pages);
>  
>  	vma_pgtable_walk_end(vma);
>  
> @@ -1358,7 +1369,6 @@ static long __get_user_pages(struct mm_struct *mm,
>  {
>  	long ret = 0, i = 0;
>  	struct vm_area_struct *vma = NULL;
> -	unsigned long page_mask = 0;
>  
>  	if (!nr_pages)
>  		return 0;
> @@ -1373,7 +1383,7 @@ static long __get_user_pages(struct mm_struct *mm,
>  
>  	do {
>  		struct page *page;
> -		unsigned int page_increm;
> +		unsigned long page_increm;
>  
>  		/* first iteration or cross vma bound */
>  		if (!vma || start >= vma->vm_end) {
> @@ -1400,7 +1410,7 @@ static long __get_user_pages(struct mm_struct *mm,
>  						pages ? &page : NULL);
>  				if (ret)
>  					goto out;
> -				page_mask = 0;
> +				page_increm = 1;
>  				goto next_page;
>  			}

God is this (existing) page_increm handling a hacked-on mess :)

-- 
Cheers,

David

[PATCH 2/2] mm/gup: batch contiguous PTE-mapped large folios in follow_page_mask()

[Rik van Riel]

follow_page_mask() returns one page per call for a PTE-mapped large folio,
so __get_user_pages() re-walks the page tables for every page of an mTHP
even though the folio maps a contiguous run. The huge PMD and PUD paths
already return the whole mapping in one step.

Report the contiguous run for the PTE case too. follow_pte_batch() uses
folio_pte_batch_flags() to count consecutive present PTEs that map
consecutive pages of the same folio with a uniform write bit, bounded by
the page table, @end, the VMA, and the folio itself.

Keep the per-PTE guarantees that follow_page_pte() makes for the head page.
folio_pte_batch_flags() with FPB_RESPECT_WRITE stops the run at a change in
the write bit, so the whole run matches the head.

A writable run is safe for any access: a writable anon page is exclusive,
so gup_must_unshare() cannot fire, and FOLL_WRITE is satisfied.

A read-only run is batched only for a plain read, since FOLL_WRITE would
need a COW fault per page and FOLL_PIN would need a per-page
gup_must_unshare() check.

Measured with mm/gup_test.c (PIN_LONGTERM_BENCHMARK, the slow
pin_user_pages() path) on a 256 MB MADV_HUGEPAGE anonymous region in a
4 CPU VM, median get time over 16 iterations. Each folio size was confirmed
through the per-size anon_fault_alloc counters (4096 folios for 64 kB, 128
for 2 MB):

  gup_test -L -m 256 -n 65536 -r 16 -t
                        before      after
  64 kB mTHP            3140 us      412 us   (7.6x)
  2 MB THP (control)      78 us       76 us
  4 kB base (control)   3010 us     3042 us

The PMD-mapped 2 MB THP already returns the whole mapping in one step, so
it stays fast and unchanged. The 4 kB baseline shows the per-page walk cost
that the 64 kB case paid before this change; only the PTE-mapped large
folio case improves.

Assisted-by: Claude:claude-opus-4.8
Signed-off-by: Rik van Riel <riel@surriel.com>
---
 mm/gup.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/mm/gup.c b/mm/gup.c
index 3437cd3407d5..8c6ad1ee7ccc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -805,6 +805,43 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page,
 	return !userfaultfd_pte_wp(vma, pte);
 }
 
+/*
+ * Count the pages, starting at @address and bounded by @end, that a PTE-mapped
+ * large @folio maps contiguously and that can be returned together with the
+ * page at @address: consecutive present PTEs mapping consecutive pages of
+ * @folio with a uniform write bit, within this VMA and a single page table.
+ * Returns at least 1.
+ *
+ * gup_must_unshare() and the write-fault check are per PTE. A writable run is
+ * always safe: a writable anon page is exclusive, and FOLL_WRITE is satisfied.
+ * A read-only run is only safe for a plain read; FOLL_WRITE would need a COW
+ * fault per page and FOLL_PIN would need a per-page gup_must_unshare() check,
+ * so those fall back to a single page.
+ */
+static unsigned long follow_pte_batch(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, struct folio *folio,
+		struct page *page, pte_t *ptep, pte_t pte, unsigned int flags)
+{
+	pte_t batch_pte = pte;
+	unsigned long max;
+
+	if (!pte_write(pte) && (flags & (FOLL_WRITE | FOLL_PIN)))
+		return 1;
+
+	/*
+	 * folio_pte_batch_flags() scans forward from @ptep, so the run must
+	 * stay within this page table: bound it by the PMD as well as @end and
+	 * the VMA, since a large folio can be PTE-mapped across a PMD boundary.
+	 */
+	max = min((pmd_addr_end(address, end) - address) >> PAGE_SHIFT,
+		  (vma->vm_end - address) >> PAGE_SHIFT);
+	if (max <= 1)
+		return 1;
+
+	return folio_pte_batch_flags(folio, vma, ptep, &batch_pte, max,
+				     FPB_RESPECT_WRITE);
+}
+
 static struct page *follow_page_pte(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pmd_t *pmd,
 		unsigned int flags, unsigned long *nr_pages)
@@ -893,6 +930,14 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		folio_mark_accessed(folio);
 	}
 
+	/*
+	 * A PTE-mapped large folio can be handed back as a contiguous batch,
+	 * so the caller advances over the whole run in one step instead of
+	 * walking the page tables for every page.
+	 */
+	if (folio_test_large(folio))
+		*nr_pages = follow_pte_batch(vma, address, end, folio, page,
+					     ptep, pte, flags);
 out:
 	pte_unmap_unlock(ptep, ptl);
 	return page;
-- 
2.53.0-Meta