github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-09-12 20:53:03 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

mm: decouple protnone helpers from CONFIG_NUMA_BALANCING

Browse Source 
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) <kas@kernel.org>
Assisted-by: Claude:claude-opus-4-6
Acked-by: SeongJae Park <sj@kernel.org>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: James Houghton <jthoughton@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Liam Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Kiryl Shutsemau (Meta) 2026-07-08 12:14:02 +01:00 committed by Andrew Morton
parent 889d3783ae
commit c6f11553c0
15 changed files with 52 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
arch/arm64/Kconfig
View File

@ -78,6 +78,7 @@ config ARM64
select ARCH_SUPPORTS_CFI
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_HAS_PTE_PROTNONE
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_SUPPORTS_PAGE_TABLE_CHECK
select ARCH_SUPPORTS_PER_VMA_LOCK

7
arch/arm64/include/asm/pgtable.h
View File

@ -553,10 +553,7 @@ static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
}
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
#ifdef CONFIG_NUMA_BALANCING
/*
* See the comment in include/linux/pgtable.h
*/
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pte_protnone(pte_t pte)
{
/*
@ -575,7 +572,7 @@ static inline int pmd_protnone(pmd_t pmd)
{
return pte_protnone(pmd_pte(pmd));
}
#endif
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
#define pmd_present(pmd) pte_present(pmd_pte(pmd))
#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))

1
arch/loongarch/Kconfig
View File

@ -67,6 +67,7 @@ config LOONGARCH
select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_LTO_CLANG_THIN
select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
select ARCH_HAS_PTE_PROTNONE if 64BIT
select ARCH_SUPPORTS_NUMA_BALANCING if NUMA
select ARCH_SUPPORTS_PER_VMA_LOCK
select ARCH_SUPPORTS_RT

4
arch/loongarch/include/asm/pgtable.h
View File

@ -623,7 +623,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_NUMA_BALANCING
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline long pte_protnone(pte_t pte)
{
return (pte_val(pte) & _PAGE_PROTNONE);
@ -633,7 +633,7 @@ static inline long pmd_protnone(pmd_t pmd)
{
return (pmd_val(pmd) & _PAGE_PROTNONE);
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
#define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0)
#define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0)

8
arch/powerpc/include/asm/book3s/64/pgtable.h
View File

@ -490,13 +490,13 @@ static inline pte_t pte_clear_soft_dirty(pte_t pte)
}
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
#ifdef CONFIG_NUMA_BALANCING
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pte_protnone(pte_t pte)
{
return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) ==
cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE);
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
static inline bool pte_hw_valid(pte_t pte)
{
@ -1067,12 +1067,12 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
#endif
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
#ifdef CONFIG_NUMA_BALANCING
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pmd_protnone(pmd_t pmd)
{
return pte_protnone(pmd_pte(pmd));
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
#define pmd_write(pmd) pte_write(pmd_pte(pmd))

1
arch/powerpc/platforms/Kconfig.cputype
View File

@ -87,6 +87,7 @@ config PPC_BOOK3S_64
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_SPLIT_PMD_PTLOCK
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_HAS_PTE_PROTNONE
select ARCH_SUPPORTS_NUMA_BALANCING
select HAVE_MOVE_PMD
select HAVE_MOVE_PUD

1
arch/riscv/Kconfig
View File

@ -71,6 +71,7 @@ config RISCV
select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
select ARCH_SUPPORTS_PER_VMA_LOCK if MMU
select ARCH_HAS_PTE_PROTNONE if MMU
select ARCH_SUPPORTS_RT
select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK
select ARCH_SUPPORTS_SCHED_MC if SMP

7
arch/riscv/include/asm/pgtable.h
View File

@ -534,10 +534,7 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
PAGE_SIZE)
#endif
#ifdef CONFIG_NUMA_BALANCING
/*
* See the comment in include/asm-generic/pgtable.h
*/
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pte_protnone(pte_t pte)
{
return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)) == _PAGE_PROT_NONE;
@ -547,7 +544,7 @@ static inline int pmd_protnone(pmd_t pmd)
{
return pte_protnone(pmd_pte(pmd));
}
#endif
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
/* Modify page protection bits */
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)

1
arch/s390/Kconfig
View File

@ -148,6 +148,7 @@ config S390
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && CC_IS_CLANG
select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
select ARCH_HAS_PTE_PROTNONE
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_SUPPORTS_PAGE_TABLE_CHECK
select ARCH_SUPPORTS_PER_VMA_LOCK

4
arch/s390/include/asm/pgtable.h
View File

@ -842,7 +842,7 @@ static inline int pte_same(pte_t a, pte_t b)
return pte_val(a) == pte_val(b);
}
#ifdef CONFIG_NUMA_BALANCING
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pte_protnone(pte_t pte)
{
return pte_present(pte) && !(pte_val(pte) & _PAGE_READ);
@ -853,7 +853,7 @@ static inline int pmd_protnone(pmd_t pmd)
/* pmd_leaf(pmd) implies pmd_present(pmd) */
return pmd_leaf(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_READ);
}
#endif
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
static inline bool pte_swp_exclusive(pte_t pte)
{

1
arch/x86/Kconfig
View File

@ -124,6 +124,7 @@ config X86
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64
select ARCH_HAS_PTE_PROTNONE if X86_64
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096
select ARCH_SUPPORTS_CFI if X86_64

8
arch/x86/include/asm/pgtable.h
View File

@ -985,11 +985,7 @@ static inline int pmd_present(pmd_t pmd)
return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
}
#ifdef CONFIG_NUMA_BALANCING
/*
* These work without NUMA balancing but the kernel does not care. See the
* comment in include/linux/pgtable.h
*/
#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE
static inline int pte_protnone(pte_t pte)
{
return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT))
@ -1001,7 +997,7 @@ static inline int pmd_protnone(pmd_t pmd)
return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT))
== _PAGE_PROTNONE;
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */
static inline int pmd_none(pmd_t pmd)
{

32
include/linux/pgtable.h
View File

@ -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 */

8
init/Kconfig
View File

@ -947,6 +947,13 @@ config SCHED_PROXY_EXEC
endmenu
#
# For architectures that support present-but-inaccessible (PROT_NONE) page
# table entries detectable via pte_protnone() / pmd_protnone():
#
config ARCH_HAS_PTE_PROTNONE
bool
#
# For architectures that want to enable the support for NUMA-affine scheduler
# balancing logic:
@ -1013,6 +1020,7 @@ config ARCH_WANT_NUMA_VARIABLE_LOCALITY
config NUMA_BALANCING
bool "Memory placement aware NUMA scheduler"
depends on ARCH_SUPPORTS_NUMA_BALANCING
depends on ARCH_HAS_PTE_PROTNONE
depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
depends on SMP && NUMA_MIGRATION && !PREEMPT_RT
help

4
mm/debug_vm_pgtable.c
View File

@ -672,7 +672,7 @@ static void __init pte_protnone_tests(struct pgtable_debug_args *args)
{
pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none);
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_PROTNONE))
return;
pr_debug("Validating PTE protnone\n");
@ -685,7 +685,7 @@ static void __init pmd_protnone_tests(struct pgtable_debug_args *args)
{
pmd_t pmd;
if (!IS_ENABLED(CONFIG_NUMA_BALANCING))
if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_PROTNONE))
return;
if (!has_transparent_hugepage())