From c6f11553c067d7d9ed2dcffe1e01780441d4e6e2 Mon Sep 17 00:00:00 2001 From: "Kiryl Shutsemau (Meta)" Date: Wed, 8 Jul 2026 12:14:02 +0100 Subject: mm: decouple protnone helpers from CONFIG_NUMA_BALANCING Patch series "userfaultfd: working set tracking for VM guest memory", v10. This series adds userfaultfd support for tracking the working set of VM guest memory, so a VMM can identify hot pages and reclaim cold ones to tiered or remote storage. This patch (of 15): pte_protnone() and pmd_protnone() detect present-but-inaccessible page table entries. This capability is useful beyond NUMA balancing -- for example, userfaultfd working set tracking uses protnone PTEs to track page access without unmapping pages. Introduce CONFIG_ARCH_HAS_PTE_PROTNONE to decouple the protnone PTE infrastructure from CONFIG_NUMA_BALANCING. The six architectures that support protnone PTEs (x86_64, arm64, powerpc, s390, riscv, loongarch) now select this option, and CONFIG_NUMA_BALANCING depends on it. No functional change -- the same set of architectures continues to have working protnone support, but the infrastructure is now available independently of NUMA balancing. Link: https://lore.kernel.org/20260708111417.173443-1-kirill@shutemov.name Link: https://lore.kernel.org/20260708111417.173443-2-kirill@shutemov.name Signed-off-by: Kiryl Shutsemau (Meta) Assisted-by: Claude:claude-opus-4-6 Acked-by: SeongJae Park Acked-by: Mike Rapoport (Microsoft) Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: James Houghton Cc: Jonathan Corbet Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Paolo Bonzini Cc: Peter Xu Cc: Sean Christopherson Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 3df6db1e9e39..8c093c119e5a 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -2110,18 +2110,26 @@ static inline int pud_trans_unstable(pud_t *pud) return 0; } -#ifndef CONFIG_NUMA_BALANCING +#ifndef CONFIG_ARCH_HAS_PTE_PROTNONE /* - * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is - * perfectly valid to indicate "no" in that case, which is why our default - * implementation defaults to "always no". + * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It + * is perfectly valid to indicate "no" in that case, which is why our + * default implementation defaults to "always no". * - * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE - * page protection due to NUMA hinting. NUMA hinting faults only apply in - * accessible VMAs. + * In an accessible VMA, pte_protnone() reliably indicates a present + * PROT_NONE page protection. Today the kernel uses such PTEs for two + * purposes: NUMA hinting faults, and userfaultfd RWP tracking on + * VM_UFFD_RWP VMAs. The two are distinguished by the uffd PTE bit and + * the VMA flag; see include/linux/userfaultfd_k.h. * - * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault, - * looking at the VMA accessibility is sufficient. + * So, to reliably identify PROT_NONE PTEs that require kernel handling, + * looking at the VMA accessibility (and the uffd bit on RWP VMAs) is + * sufficient. + * + * Architectures without CONFIG_ARCH_HAS_PTE_PROTNONE get the always-zero + * stubs below; PAGE_NONE references that survive to runtime fire the + * BUILD_BUG() fallback, since callers should have folded such paths to + * dead code via IS_ENABLED(CONFIG_ARCH_HAS_PTE_PROTNONE). */ static inline int pte_protnone(pte_t pte) { @@ -2132,7 +2140,11 @@ static inline int pmd_protnone(pmd_t pmd) { return 0; } -#endif /* CONFIG_NUMA_BALANCING */ + +#ifndef PAGE_NONE +#define PAGE_NONE ({ BUILD_BUG(); (pgprot_t){0}; }) +#endif +#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */ #endif /* CONFIG_MMU */ -- cgit v1.2.3