Re: [PATCH v7 0/7] mm/vmalloc: Speed up ioremap, vmalloc and vmap with contiguous memory

[Andrew Morton]

On Wed, 15 Jul 2026 20:08:06 +0800 Wen Jiang <jiangwenxiaomi@xxxxxxxxx> wrote:

> This patchset accelerates ioremap, vmalloc, and vmap when the memory
> is physically fully or partially contiguous. Two techniques are used:

Thanks, I've updated mm.git's mm-unstable branch to this version.

> Changes since v6:
> - Add a clarifying comment about the reuse of hugetlb helpers
>   by non-hugetlbfs(vmalloc) mm code (patch 1)
> - Expand the arm64/vmalloc commit message and comment to clarify that
>   multi-CONT_PTE_SIZE values are vmalloc mapping spans, not HugeTLB
>   hstate sizes (patch 2)
> - Move the local steps variable change in vmap_pte_range() into the
>   vmap_set_ptes() extraction patch (patch 3)
> - Propagate vmap_pages_pte_range() errors through the upper
>   vmap_pages_*() levels instead of returning -ENOMEM for all failures
>   (patch 4)
> - Add a preparatory vm_shift() helper patch before the batching patch
>   (patch 5)
> - Guard the PFN alignment clamp in get_vmap_batch_order() against PFN 0
>   before calling __ffs() (patch 6)
> - Fix kmsan_vmap_pages_range_noflush() indentation in the batching path
>   (patch 6)

Here's how v7 altered mm.git:


 arch/arm64/include/asm/vmalloc.h |    2 +
 arch/arm64/mm/hugetlbpage.c      |    5 ++++
 mm/vmalloc.c                     |   31 ++++++++++++++++-------------
 3 files changed, 25 insertions(+), 13 deletions(-)

--- a/arch/arm64/include/asm/vmalloc.h~b
+++ a/arch/arm64/include/asm/vmalloc.h
@@ -29,6 +29,8 @@ static inline unsigned long arch_vmap_pt
 	 * If the block is at least CONT_PTE_SIZE in size, and is naturally
 	 * aligned in both virtual and physical space, then we can pte-map the
 	 * block using the PTE_CONT bit for more efficient use of the TLB.
+	 * The returned mapping size may cover multiple CONT_PTE_SIZE blocks,
+	 * capped below PMD_SIZE.
 	 */
 	if (max_page_shift < CONT_PTE_SHIFT)
 		return PAGE_SIZE;
--- a/arch/arm64/mm/hugetlbpage.c~b
+++ a/arch/arm64/mm/hugetlbpage.c
@@ -94,6 +94,11 @@ static int find_num_contig(struct mm_str
 	return CONT_PTES;
 }
 
+/*
+ * num_contig_ptes(), set_huge_pte_at() and arch_make_huge_pte() can be
+ * used by non-hugetlbfs(vmalloc) mm code to set multiple huge mappings
+ * at the PTE level.
+ */
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
 	int contig_ptes = 1;
--- a/mm/vmalloc.c~b
+++ a/mm/vmalloc.c
@@ -616,6 +616,7 @@ static int vmap_pages_pmd_range(pud_t *p
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
 	if (!pmd)
@@ -642,8 +643,9 @@ static int vmap_pages_pmd_range(pud_t *p
 			}
 		}
 
-		if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask, shift))
-			return -ENOMEM;
+		err = vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask, shift);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
@@ -654,14 +656,16 @@ static int vmap_pages_pud_range(p4d_t *p
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
 	if (!pud)
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask, shift))
-			return -ENOMEM;
+		err = vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask, shift);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
@@ -672,14 +676,16 @@ static int vmap_pages_p4d_range(pgd_t *p
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
 	if (!p4d)
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask, shift))
-			return -ENOMEM;
+		err = vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask, shift);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
@@ -3591,6 +3597,7 @@ static inline unsigned int vm_shift(pgpr
 static inline int get_vmap_batch_order(struct page **pages,
 		pgprot_t prot, unsigned int max_steps, unsigned int idx)
 {
+	unsigned long pfn;
 	unsigned int nr_contig;
 	int order;
 
@@ -3602,9 +3609,11 @@ static inline int get_vmap_batch_order(s
 		return 0;
 
 	order = ilog2(nr_contig);
+	pfn = page_to_pfn(pages[idx]);
 
 	/* Limit order by pfn alignment */
-	order = min_t(int, order, __ffs(page_to_pfn(pages[idx])));
+	if (pfn > 0)
+		order = min_t(int, order, __ffs(pfn));
 
 	if (vm_shift(prot, PAGE_SIZE << order) == PAGE_SHIFT)
 		return 0;
@@ -3621,7 +3630,7 @@ static int vmap_pages_range_batched(unsi
 	int err;
 
 	err = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
-						PAGE_SHIFT, GFP_KERNEL);
+					     PAGE_SHIFT, GFP_KERNEL);
 	if (err)
 		goto out;
 
@@ -4199,11 +4208,7 @@ void *__vmalloc_node_range_noprof(unsign
 		 * supporting them.
 		 */
 
-		if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE)
-			shift = PMD_SHIFT;
-		else
-			shift = arch_vmap_pte_supported_shift(size);
-
+		shift = vm_shift(prot, size);
 		align = max(original_align, 1UL << shift);
 	}
 
_