[to-be-updated] mm-vmalloc-extend-page-table-walk-to-support-larger-page_shift-sizes-and-eliminate-page-table-rewalk.patch removed from -mm tree

[to-be-updated] mm-vmalloc-extend-page-table-walk-to-support-larger-page_shift-sizes-and-eliminate-page-table-rewalk.patch removed from -mm tree

[Andrew Morton]

The quilt patch titled
     Subject: mm/vmalloc: extend page table walk to support larger page_shift sizes and eliminate page table rewalk
has been removed from the -mm tree.  Its filename was
     mm-vmalloc-extend-page-table-walk-to-support-larger-page_shift-sizes-and-eliminate-page-table-rewalk.patch

This patch was dropped because an updated version will be issued

------------------------------------------------------
From: "Barry Song (Xiaomi)" <baohua@kernel.org>
Subject: mm/vmalloc: extend page table walk to support larger page_shift sizes and eliminate page table rewalk
Date: Thu, 18 Jun 2026 16:47:24 +0800

vmap_pages_range_noflush_walk() (formerly
vmap_small_pages_range_noflush()) provides a clean interface by taking
struct page **pages and mapping them via direct PTE iteration.  This
avoids the page table rewalk seen when using vmap_range_noflush() for
page_shift values other than PAGE_SHIFT.

Extend it to support larger page_shift values, and add PMD- and
contiguous-PTE mappings as well.  Rename it to
vmap_pages_range_noflush_walk() since it now handles more than just small
pages.

For vmalloc() allocations with VM_ALLOW_HUGE_VMAP, we no longer need to
iterate over pages one by one via vmap_range_noflush(), which would
otherwise lead to page table rewalk.  The code is now unified with the
PAGE_SHIFT case by simply calling vmap_pages_range_noflush_walk().

Link: https://lore.kernel.org/20260618084726.1070022-5-jiangwen6@xiaomi.com
Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
Signed-off-by: Wen Jiang <jiangwen6@xiaomi.com>
Tested-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
Tested-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Cc: Andrew Donnellan <ajd@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Wen Jiang <jiangwenxiaomi@gmail.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/vmalloc.c |   81 ++++++++++++++++++++++++++++---------------------
 1 file changed, 47 insertions(+), 34 deletions(-)

--- a/mm/vmalloc.c~mm-vmalloc-extend-page-table-walk-to-support-larger-page_shift-sizes-and-eliminate-page-table-rewalk
+++ a/mm/vmalloc.c
@@ -127,7 +127,8 @@ static int vmap_pte_range(pmd_t *pmd, un
 	pte_t *pte;
 	u64 pfn;
 	struct page *page;
-	unsigned long size = PAGE_SIZE;
+	unsigned long size;
+	unsigned int steps;
 
 	if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr)))
 		return -EINVAL;
@@ -149,8 +150,8 @@ static int vmap_pte_range(pmd_t *pmd, un
 		}
 
 		size = vmap_set_ptes(pte, addr, end, pfn, prot, max_page_shift);
-		pfn += PFN_DOWN(size);
-	} while (pte += PFN_DOWN(size), addr += size, addr != end);
+		steps = PFN_DOWN(size);
+	} while (pte += steps, pfn += steps, addr += size, addr != end);
 
 	lazy_mmu_mode_disable();
 	*mask |= PGTBL_PTE_MODIFIED;
@@ -542,8 +543,10 @@ void vunmap_range(unsigned long addr, un
 
 static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
-		pgtbl_mod_mask *mask)
+		pgtbl_mod_mask *mask, unsigned int shift)
 {
+	unsigned long pfn, size;
+	unsigned int steps;
 	int err = 0;
 	pte_t *pte;
 
@@ -574,9 +577,10 @@ static int vmap_pages_pte_range(pmd_t *p
 			break;
 		}
 
-		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
-		(*nr)++;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+		pfn = page_to_pfn(page);
+		size = vmap_set_ptes(pte, addr, end, pfn, prot, shift);
+		steps = PFN_DOWN(size);
+	} while (pte += steps, *nr += steps, addr += size, addr != end);
 
 	lazy_mmu_mode_disable();
 	*mask |= PGTBL_PTE_MODIFIED;
@@ -586,7 +590,7 @@ static int vmap_pages_pte_range(pmd_t *p
 
 static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
-		pgtbl_mod_mask *mask)
+		pgtbl_mod_mask *mask, unsigned int shift)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -596,7 +600,27 @@ static int vmap_pages_pmd_range(pud_t *p
 		return -ENOMEM;
 	do {
 		next = pmd_addr_end(addr, end);
-		if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
+
+		if (shift >= PMD_SHIFT) {
+			struct page *page = pages[*nr];
+			phys_addr_t phys_addr;
+
+			if (WARN_ON(!page))
+				return -ENOMEM;
+			if (WARN_ON(!pfn_valid(page_to_pfn(page))))
+				return -EINVAL;
+
+			phys_addr = page_to_phys(page);
+
+			if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
+						shift)) {
+				*mask |= PGTBL_PMD_MODIFIED;
+				*nr += 1 << (PMD_SHIFT - PAGE_SHIFT);
+				continue;
+			}
+		}
+
+		if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask, shift))
 			return -ENOMEM;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
@@ -604,7 +628,7 @@ static int vmap_pages_pmd_range(pud_t *p
 
 static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
-		pgtbl_mod_mask *mask)
+		pgtbl_mod_mask *mask, unsigned int shift)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -614,7 +638,7 @@ static int vmap_pages_pud_range(p4d_t *p
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
+		if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask, shift))
 			return -ENOMEM;
 	} while (pud++, addr = next, addr != end);
 	return 0;
@@ -622,7 +646,7 @@ static int vmap_pages_pud_range(p4d_t *p
 
 static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
-		pgtbl_mod_mask *mask)
+		pgtbl_mod_mask *mask, unsigned int shift)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -632,14 +656,18 @@ static int vmap_pages_p4d_range(pgd_t *p
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
+		if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask, shift))
 			return -ENOMEM;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
 
-static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
-		pgprot_t prot, struct page **pages)
+/*
+ * It can take an array of pages which are not all contiguous, but it
+ * may have contiguous chunks, as hinted by @shift.
+ */
+static int vmap_pages_range_noflush_walk(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int shift)
 {
 	unsigned long start = addr;
 	pgd_t *pgd;
@@ -654,7 +682,7 @@ static int vmap_small_pages_range_noflus
 		next = pgd_addr_end(addr, end);
 		if (pgd_bad(*pgd))
 			mask |= PGTBL_PGD_MODIFIED;
-		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
+		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask, shift);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
@@ -677,27 +705,12 @@ static int vmap_small_pages_range_noflus
 int __vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 		pgprot_t prot, struct page **pages, unsigned int page_shift)
 {
-	unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
-
 	WARN_ON(page_shift < PAGE_SHIFT);
 
-	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
-			page_shift == PAGE_SHIFT)
-		return vmap_small_pages_range_noflush(addr, end, prot, pages);
-
-	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
-		int err;
-
-		err = vmap_range_noflush(addr, addr + (1UL << page_shift),
-					page_to_phys(pages[i]), prot,
-					page_shift);
-		if (err)
-			return err;
-
-		addr += 1UL << page_shift;
-	}
+	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC))
+		page_shift = PAGE_SHIFT;
 
-	return 0;
+	return vmap_pages_range_noflush_walk(addr, end, prot, pages, page_shift);
 }
 
 int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
_

Patches currently in -mm which might be from baohua@kernel.org are

mm-vmalloc-map-contiguous-pages-in-batches-for-vmap-if-possible.patch
mm-vmalloc-align-vm_area-so-vmap-can-batch-mappings.patch