Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Rik van Riel <riel@surriel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-team@meta.com, Dave Hansen <dave.hansen@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Lorenzo Stoakes <ljs@kernel.org>,
	Vlastimil Babka <vbabka@kernel.org>,
	David Hildenbrand <david@kernel.org>,
	"Liam R. Howlett" <liam@infradead.org>,
	Mike Rapoport <rppt@kernel.org>, Michal Hocko <mhocko@suse.com>,
	Jason Gunthorpe <jgg@ziepe.ca>,
	John Hubbard <jhubbard@nvidia.com>, Peter Xu <peterx@redhat.com>,
	Matthew Wilcox <willy@infradead.org>,
	Usama Arif <usamaarif642@gmail.com>,
	Rik van Riel <riel@surriel.com>
Subject: [PATCH RFC v4 10/12] mm/gup: pass an end address to follow_page_mask() and return a page count
Date: Fri, 24 Jul 2026 18:29:32 -0400	[thread overview]
Message-ID: <20260724222934.1463812-11-riel@surriel.com> (raw)
In-Reply-To: <20260724222934.1463812-1-riel@surriel.com>

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.
get_user_page_vma() passes @address + PAGE_SIZE and still returns one page.

No functional change intended.

Assisted-by: Claude:claude-opus-4.8
Signed-off-by: Rik van Riel <riel@surriel.com>
---
 mm/gup.c | 102 ++++++++++++++++++++++++++++++-------------------------
 1 file changed, 56 insertions(+), 46 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 7f4107f7ff10..96b00ddf7e04 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);
 
@@ -1198,7 +1209,7 @@ struct page *get_user_page_vma(struct vm_area_struct *vma, unsigned long addr,
 			       unsigned int gup_flags)
 {
 	bool vma_locked = gup_flags & FOLL_VMA_LOCK;
-	unsigned long page_mask;
+	unsigned long nr_pages;
 	struct page *page;
 	int locked = 1;
 	bool pfnmap;
@@ -1231,10 +1242,10 @@ struct page *get_user_page_vma(struct vm_area_struct *vma, unsigned long addr,
 		}
 		cond_resched();
 
-		/* follow_page_mask() requires @page_mask; it is unused here. */
-		page = follow_page_mask(vma, addr,
+		/* This helper hands back a single page; cap the batch at one. */
+		page = follow_page_mask(vma, addr, addr + PAGE_SIZE,
 					gup_flags | FOLL_TOUCH | FOLL_GET,
-					&page_mask);
+					&nr_pages);
 		if (!IS_ERR_OR_NULL(page)) {
 			/* Match __get_user_pages(): flush for VIVT/aliasing caches. */
 			flush_anon_page(vma, page, addr);
@@ -1529,7 +1540,6 @@ 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;
@@ -1544,7 +1554,7 @@ 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) {
@@ -1571,7 +1581,7 @@ 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;
 			}
 
@@ -1594,7 +1604,8 @@ 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);
@@ -1627,7 +1638,6 @@ 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



  parent reply	other threads:[~2026-07-24 22:30 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-24 22:29 [PATCH RFC v4 0/12] mm: use per-VMA lock in __access_remote_vm for improved monitoring reliability Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 01/12] x86/mm: add untagged_addr_remote_unlocked() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 02/12] riscv/mm: " Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 03/12] mm: rename get_user_page_vma_remote() to get_user_page_lookup_vma() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 04/12] mm/gup: let check_vma_flags() ignore selected VMA flags Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 05/12] mm/gup: add get_user_page_vma() to fault in a page under a held lock Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 06/12] mm: use per-VMA lock in __access_remote_vm() for single-VMA accesses Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 07/12] mm: read remote strings under the per-VMA lock Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 08/12] selftests/mm: cover /proc/pid/mem access to VM_PFNMAP memory Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 09/12] mm/gup: build get_user_page_lookup_vma() on get_user_page_vma() Rik van Riel
2026-07-24 22:29 ` Rik van Riel [this message]
2026-07-24 22:29 ` [PATCH RFC v4 11/12] mm/gup: batch contiguous PTE-mapped large folios in follow_page_mask() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 12/12] selftests/mm: add a slow-GUP content and COW test for mTHP Rik van Riel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260724222934.1463812-11-riel@surriel.com \
    --to=riel@surriel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@kernel.org \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=kernel-team@meta.com \
    --cc=liam@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@suse.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=usamaarif642@gmail.com \
    --cc=vbabka@kernel.org \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox