mm: split PTE/PMD PT table Kconfig cleanups+clarifications
Subsystems (10)
cover mm: split PTE/PMD PT table Kconfig cleanups+clarifications
This series is a follow up to the fixes:
"[PATCH v1 0/2] mm/hugetlb: fix hugetlb vs. core-mm PT locking"
When working on the fixes, I wondered why 8xx is fine (-> never uses split PT locks) and how PT locking even works properly with PMD page table sharing (-> always requires split PMD PT locks).
Let's improve the split PT lock detection, make hugetlb properly depend on it and make 8xx bail out if it would ever get enabled by accident.
As an alternative to patch #3 we could extend the Kconfig SPLIT_PTE_PTLOCKS option from patch #2 -- but enforcing it closer to the code that actually implements it feels a bit nicer for documentation purposes, and there is no need to actually disable it because it should always be disabled (!SMP).
Did a bunch of cross-compilations to make sure that split PTE/PMD PT locks are still getting used where we would expect them.
[1] https://lkml.kernel.org/r/[email protected]
David Hildenbrand (3):
mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig
options
mm/hugetlb: enforce that PMD PT sharing has split PMD PT locks powerpc/8xx: document and enforce that split PT locks are not used
arch/arm/mm/fault-armv.c | 6 +++--- arch/powerpc/mm/pgtable.c | 6 ++++++ arch/x86/xen/mmu_pv.c | 7 ++++--- fs/Kconfig | 4 ++++ include/linux/hugetlb.h | 5 ++--- include/linux/mm.h | 8 ++++---- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 3 --- kernel/fork.c | 4 ++-- mm/Kconfig | 18 +++++++++++------- mm/hugetlb.c | 8 ++++---- mm/memory.c | 2 +- 12 files changed, 42 insertions(+), 31 deletions(-)
Signature · 1 line
2.45.2
PATCH 1/3 mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options
Let's clean that up a bit and prepare for depending on CONFIG_SPLIT_PMD_PTLOCKS in other Kconfig options.
More cleanups would be reasonable (like the arch-specific "depends on" for CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day.
--- arch/arm/mm/fault-armv.c | 6 +++--- arch/x86/xen/mmu_pv.c | 7 ++++--- include/linux/mm.h | 8 ++++---- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 3 --- kernel/fork.c | 4 ++-- mm/Kconfig | 18 +++++++++++------- mm/memory.c | 2 +- 8 files changed, 26 insertions(+), 24 deletions(-)
arch/arm/mm/fault-armv.c +3 -3
@@ -61,7 +61,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,return ret; } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )/* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock
@@ -80,10 +80,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) {spin_unlock (ptl); } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void do_pte_lock (spinlock_t *ptl) {}static inline void do_pte_unlock (spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static int adjust_pte (struct vm_area_struct *vma,unsigned long address,unsigned long pfn)
arch/x86/xen/mmu_pv.c +4 -3
@@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) {spinlock_t *ptl =NULL ; -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) ptl =ptlock_ptr (page_ptdesc (page));spin_lock_nest_lock (ptl, &mm->page_table_lock);#endif
@@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,__set_pfn_prot (pfn,PAGE_KERNEL_RO ); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS && !pinned) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ) && + !pinned)__pin_pagetable_pfn (MMUEXT_PIN_L1_TABLE , pfn);xen_mc_issue (XEN_LAZY_MMU );
@@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)if (pinned) {xen_mc_batch (); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS ) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ))__pin_pagetable_pfn (MMUEXT_UNPIN_TABLE , pfn);__set_pfn_prot (pfn,PAGE_KERNEL );
include/linux/mm.h +4 -4
@@ -2843,7 +2843,7 @@ static inline void pagetable_free(struct ptdesc *pt)__free_pages (page,compound_order (page)); } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )#if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init (void );bool ptlock_alloc (struct ptdesc *ptdesc);
@@ -2895,7 +2895,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) return true; } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */
@@ -2906,7 +2906,7 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pte_t *pte)static inline void ptlock_cache_init (void ) {}static inline bool ptlock_init (struct ptdesc *ptdesc) {return true; }static inline void ptlock_free (struct ptdesc *ptdesc) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline bool pagetable_pte_ctor (struct ptdesc *ptdesc) {
@@ -2966,7 +2966,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, ((unlikely (pmd_none (*(pmd))) &&__pte_alloc_kernel (pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#if USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_SPLIT_PMD_PTLOCKS )static inline struct page *pmd_pgtable_page (pmd_t *pmd) {
include/linux/mm_types.h +1 -1
@@ -947,7 +947,7 @@ struct mm_struct {#ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions;#endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )pgtable_t pmd_huge_pte;/* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING
include/linux/mm_types_task.h +0 -3
@@ -16,9 +16,6 @@#include <asm/tlbbatch.h> #endif -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8)/*
kernel/fork.c +2 -2
@@ -832,7 +832,7 @@ static void check_mm(struct mm_struct *mm)pr_alert ("BUG: non-zero pgtables_bytes on freeing mm: %ld\n" ,mm_pgtables_bytes (mm)); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )VM_BUG_ON_MM (mm->pmd_huge_pte, mm);#endif }
@@ -1276,7 +1276,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,RCU_INIT_POINTER (mm->exe_file,NULL );mmu_notifier_subscriptions_init (mm);init_tlb_flush_pending (mm); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS ) mm->pmd_huge_pte =NULL ;#endif mm_init_uprobes_state (mm);
mm/Kconfig +11 -7
@@ -585,17 +585,21 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE # at the same time (e.g. copy_page_range()). # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. # -config SPLIT_PTLOCK_CPUS - int - default "999999" if !MMU - default "999999" if ARM && !CPU_CACHE_VIPT - default "999999" if PARISC && !PA20 - default "999999" if SPARC32 - default "4" +config SPLIT_PTE_PTLOCKS + def_bool y + depends on MMU + depends on NR_CPUS >= 4 + depends on !ARM || CPU_CACHE_VIPT + depends on !PARISC || PA20 + depends on !SPARC32 config ARCH_ENABLE_SPLIT_PMD_PTLOCK bool +config SPLIT_PMD_PTLOCKS + def_bool y + depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK + # # support for memory balloon config MEMORY_BALLOON
mm/memory.c +1 -1
@@ -6559,7 +6559,7 @@ long copy_folio_from_user(struct folio *dst_folio, }#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS &&ALLOC_SPLIT_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) &&ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep;
Signature · 1 line
2.45.2
Re: [PATCH v1 1/3] mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options
Quoted 7 lines · David Hildenbrand
Let's clean that up a bit and prepare for depending on
CONFIG_SPLIT_PMD_PTLOCKSin otherKconfigoptions.More cleanups would be reasonable (like the arch-specific "depends on" for
CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day.Signed-off-by David Hildenbrand <[email protected]>
Quoted 208 lines
--- arch/arm/mm/fault-armv.c | 6 +++--- arch/x86/xen/mmu_pv.c | 7 ++++--- include/linux/mm.h | 8 ++++---- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 3 --- kernel/fork.c | 4 ++-- mm/Kconfig | 18 +++++++++++------- mm/memory.c | 2 +- 8 files changed, 26 insertions(+), 24 deletions(-)arch/arm/mm/fault-armv.c +3
-3@@ -61,7 +61,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,return ret; } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )/* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock @@ -80,10 +80,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) {spin_unlock (ptl); } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void do_pte_lock (spinlock_t *ptl) {}static inline void do_pte_unlock (spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static int adjust_pte (struct vm_area_struct *vma,unsigned long address,unsigned long pfn)arch/x86/xen/mmu_pv.c +4
-3@@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) {spinlock_t *ptl =NULL ; -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) ptl =ptlock_ptr (page_ptdesc (page));spin_lock_nest_lock (ptl, &mm->page_table_lock);#endif @@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,__set_pfn_prot (pfn,PAGE_KERNEL_RO ); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS && !pinned) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ) && + !pinned)__pin_pagetable_pfn (MMUEXT_PIN_L1_TABLE , pfn);xen_mc_issue (XEN_LAZY_MMU );@@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)if (pinned) {xen_mc_batch (); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS ) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ))__pin_pagetable_pfn (MMUEXT_UNPIN_TABLE , pfn);__set_pfn_prot (pfn,PAGE_KERNEL );include/linux/mm.h +4
-4@@ -2843,7 +2843,7 @@ static inline void pagetable_free(struct ptdesc *pt)__free_pages (page,compound_order (page)); } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )#if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init (void );bool ptlock_alloc (struct ptdesc *ptdesc);@@ -2895,7 +2895,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) return true; } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ @@ -2906,7 +2906,7 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pte_t *pte)static inline void ptlock_cache_init (void ) {}static inline bool ptlock_init (struct ptdesc *ptdesc) {return true; }static inline void ptlock_free (struct ptdesc *ptdesc) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline bool pagetable_pte_ctor (struct ptdesc *ptdesc) {@@ -2966,7 +2966,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, ((unlikely (pmd_none (*(pmd))) &&__pte_alloc_kernel (pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#if USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_SPLIT_PMD_PTLOCKS )static inline struct page *pmd_pgtable_page (pmd_t *pmd) {include/linux/mm_types.h +1
-1@@ -947,7 +947,7 @@ struct mm_struct {#ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions;#endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )pgtable_t pmd_huge_pte;/* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING include/linux/mm_types_task.h +0
-3@@ -16,9 +16,6 @@#include <asm/tlbbatch.h> #endif -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8)/* kernel/fork.c +2
-2@@ -832,7 +832,7 @@ static void check_mm(struct mm_struct *mm)pr_alert ("BUG: non-zero pgtables_bytes on freeing mm: %ld\n" ,mm_pgtables_bytes (mm)); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )VM_BUG_ON_MM (mm->pmd_huge_pte, mm);#endif }@@ -1276,7 +1276,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,RCU_INIT_POINTER (mm->exe_file,NULL );mmu_notifier_subscriptions_init (mm);init_tlb_flush_pending (mm); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS ) mm->pmd_huge_pte =NULL ;#endif mm_init_uprobes_state (mm);mm/Kconfig +11
-7@@ -585,17 +585,21 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE # at the same time (e.g. copy_page_range()). # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. # -config SPLIT_PTLOCK_CPUS - int - default "999999" if !MMU - default "999999" if ARM && !CPU_CACHE_VIPT - default "999999" if PARISC && !PA20 - default "999999" if SPARC32 - default "4" +config SPLIT_PTE_PTLOCKS + def_bool y + depends on MMU + depends on NR_CPUS >= 4 + depends on !ARM || CPU_CACHE_VIPT + depends on !PARISC || PA20 + depends on !SPARC32 config ARCH_ENABLE_SPLIT_PMD_PTLOCK bool +config SPLIT_PMD_PTLOCKS + def_bool y + depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK + # # support for memory balloon config MEMORY_BALLOONmm/memory.c +1
-1@@ -6559,7 +6559,7 @@ long copy_folio_from_user(struct folio *dst_folio, }#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS &&ALLOC_SPLIT_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) &&ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep;Signature · 1 line
2.45.2
Signature · 2 lines
Sincerely yours, Mike.
Re: [PATCH v1 1/3] mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options
In reply to David HildenbrandQuoted 7 lines · David Hildenbrand
Let's clean that up a bit and prepare for depending on
CONFIG_SPLIT_PMD_PTLOCKSin otherKconfigoptions.More cleanups would be reasonable (like the arch-specific "depends on" for
CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day.Signed-off-by David Hildenbrand <[email protected]>
Quoted 10 lines
--- arch/arm/mm/fault-armv.c | 6 +++--- arch/x86/xen/mmu_pv.c | 7 ++++--- include/linux/mm.h | 8 ++++---- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 3 --- kernel/fork.c | 4 ++-- mm/Kconfig | 18 +++++++++++------- mm/memory.c | 2 +- 8 files changed, 26 insertions(+), 24 deletions(-)
That's great. Thanks!
Quoted 194 lines
arch/arm/mm/fault-armv.c +3
-3@@ -61,7 +61,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,return ret; } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )/* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock @@ -80,10 +80,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) {spin_unlock (ptl); } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void do_pte_lock (spinlock_t *ptl) {}static inline void do_pte_unlock (spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static int adjust_pte (struct vm_area_struct *vma,unsigned long address,unsigned long pfn)arch/x86/xen/mmu_pv.c +4
-3@@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) {spinlock_t *ptl =NULL ; -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) ptl =ptlock_ptr (page_ptdesc (page));spin_lock_nest_lock (ptl, &mm->page_table_lock);#endif @@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,__set_pfn_prot (pfn,PAGE_KERNEL_RO ); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS && !pinned) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ) && + !pinned)__pin_pagetable_pfn (MMUEXT_PIN_L1_TABLE , pfn);xen_mc_issue (XEN_LAZY_MMU );@@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)if (pinned) {xen_mc_batch (); -if (level ==PT_PTE &&USE_SPLIT_PTE_PTLOCKS ) +if (level ==PT_PTE &&IS_ENABLED (CONFIG_SPLIT_PTE_PTLOCKS ))__pin_pagetable_pfn (MMUEXT_UNPIN_TABLE , pfn);__set_pfn_prot (pfn,PAGE_KERNEL );include/linux/mm.h +4
-4@@ -2843,7 +2843,7 @@ static inline void pagetable_free(struct ptdesc *pt)__free_pages (page,compound_order (page)); } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS )#if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init (void );bool ptlock_alloc (struct ptdesc *ptdesc);@@ -2895,7 +2895,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) return true; } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ @@ -2906,7 +2906,7 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pte_t *pte)static inline void ptlock_cache_init (void ) {}static inline bool ptlock_init (struct ptdesc *ptdesc) {return true; }static inline void ptlock_free (struct ptdesc *ptdesc) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline bool pagetable_pte_ctor (struct ptdesc *ptdesc) {@@ -2966,7 +2966,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, ((unlikely (pmd_none (*(pmd))) &&__pte_alloc_kernel (pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#if USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_SPLIT_PMD_PTLOCKS )static inline struct page *pmd_pgtable_page (pmd_t *pmd) {include/linux/mm_types.h +1
-1@@ -947,7 +947,7 @@ struct mm_struct {#ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions;#endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )pgtable_t pmd_huge_pte;/* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING include/linux/mm_types_task.h +0
-3@@ -16,9 +16,6 @@#include <asm/tlbbatch.h> #endif -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8)/* kernel/fork.c +2
-2@@ -832,7 +832,7 @@ static void check_mm(struct mm_struct *mm)pr_alert ("BUG: non-zero pgtables_bytes on freeing mm: %ld\n" ,mm_pgtables_bytes (mm)); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS )VM_BUG_ON_MM (mm->pmd_huge_pte, mm);#endif }@@ -1276,7 +1276,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,RCU_INIT_POINTER (mm->exe_file,NULL );mmu_notifier_subscriptions_init (mm);init_tlb_flush_pending (mm); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE ) && !defined(CONFIG_SPLIT_PMD_PTLOCKS ) mm->pmd_huge_pte =NULL ;#endif mm_init_uprobes_state (mm);mm/Kconfig +11
-7@@ -585,17 +585,21 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE # at the same time (e.g. copy_page_range()). # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. # -config SPLIT_PTLOCK_CPUS - int - default "999999" if !MMU - default "999999" if ARM && !CPU_CACHE_VIPT - default "999999" if PARISC && !PA20 - default "999999" if SPARC32 - default "4" +config SPLIT_PTE_PTLOCKS + def_bool y + depends on MMU + depends on NR_CPUS >= 4 + depends on !ARM || CPU_CACHE_VIPT + depends on !PARISC || PA20 + depends on !SPARC32 config ARCH_ENABLE_SPLIT_PMD_PTLOCK bool +config SPLIT_PMD_PTLOCKS + def_bool y + depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK + # # support for memory balloon config MEMORY_BALLOONmm/memory.c +1
-1@@ -6559,7 +6559,7 @@ long copy_folio_from_user(struct folio *dst_folio, }#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS &&ALLOC_SPLIT_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) &&ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep;
Re: [PATCH v1 1/3] mm: turn USE_SPLIT_PTE_PTLOCKS / USE_SPLIT_PTE_PTLOCKS into Kconfig options
In reply to David HildenbrandQuoted 7 lines · David Hildenbrand
Let's clean that up a bit and prepare for depending on
CONFIG_SPLIT_PMD_PTLOCKSin otherKconfigoptions.More cleanups would be reasonable (like the arch-specific "depends on" for
CONFIG_SPLIT_PTE_PTLOCKS), but we'll leave that for another day.Signed-off-by David Hildenbrand <[email protected]>
Thanks!
Signature · 2 lines
RMK's Patch system: https://www.armlinux.org.uk/developer/patches/ FTTP is here! 80Mbps down 10Mbps up. Decent connectivity at last!
PATCH 2/3 mm/hugetlb: enforce that PMD PT sharing has split PMD PT locks
In reply to David HildenbrandSharing page tables between processes but falling back to per-MM page table locks cannot possibly work.
So, let's make sure that we do have split PMD locks by adding a new Kconfig option and letting that depend on CONFIG_SPLIT_PMD_PTLOCKS.
--- fs/Kconfig | 4 ++++ include/linux/hugetlb.h | 5 ++--- mm/hugetlb.c | 8 ++++---- 3 files changed, 10 insertions(+), 7 deletions(-)
fs/Kconfig +4 -0
@@ -288,6 +288,10 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP +config HUGETLB_PMD_PAGE_TABLE_SHARING + def_bool HUGETLB_PAGE + depends on ARCH_WANT_HUGE_PMD_SHARE && SPLIT_PMD_PTLOCKS + config ARCH_HAS_GIGANTIC_PAGE bool
include/linux/hugetlb.h +2 -3
@@ -1243,7 +1243,7 @@ static inline __init void hugetlb_cma_reserve(int order) }#endif -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared (pte_t *pte) {return page_count (virt_to_page (pte)) >1 ;
@@ -1279,8 +1279,7 @@ bool __vma_private_lock(struct vm_area_struct *vma);static inline pte_t *hugetlb_walk (struct vm_area_struct *vma,unsigned long addr,unsigned long sz) { -#if defined(CONFIG_HUGETLB_PAGE ) && \ - defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE ) && defined(CONFIG_LOCKDEP ) +#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING ) && defined(CONFIG_LOCKDEP )struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;/*
mm/hugetlb.c +4 -4
@@ -7211,7 +7211,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end,return 0 ; } -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable (struct vm_area_struct *svma,struct vm_area_struct *vma,unsigned long addr,pgoff_t idx)
@@ -7373,7 +7373,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, return 1; } -#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share (struct mm_struct *mm,struct vm_area_struct *vma,unsigned long addr,pud_t *pud)
@@ -7396,7 +7396,7 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) {return false; } -#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -7494,7 +7494,7 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)/* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page (struct hstate *h) { -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size (h) ==PMD_SIZE )return PUD_SIZE -PMD_SIZE ;#endif
Signature · 1 line
2.45.2
Re: [PATCH v1 2/3] mm/hugetlb: enforce that PMD PT sharing has split PMD PT locks
Quoted 7 lines · David Hildenbrand
Sharing page tables between processes but falling back to per-MM page table locks cannot possibly work.
So, let's make sure that we do have split PMD locks by adding a new
Kconfigoption and letting that depend onCONFIG_SPLIT_PMD_PTLOCKS.Signed-off-by David Hildenbrand <[email protected]>
Quoted 88 lines
--- fs/Kconfig | 4 ++++ include/linux/hugetlb.h | 5 ++--- mm/hugetlb.c | 8 ++++---- 3 files changed, 10 insertions(+), 7 deletions(-)fs/Kconfig +4
-0@@ -288,6 +288,10 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP +config HUGETLB_PMD_PAGE_TABLE_SHARING + def_bool HUGETLB_PAGE + depends on ARCH_WANT_HUGE_PMD_SHARE && SPLIT_PMD_PTLOCKS + config ARCH_HAS_GIGANTIC_PAGE boolinclude/linux/hugetlb.h +2
-3@@ -1243,7 +1243,7 @@ static inline __init void hugetlb_cma_reserve(int order) }#endif -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared (pte_t *pte) {return page_count (virt_to_page (pte)) >1 ;@@ -1279,8 +1279,7 @@ bool __vma_private_lock(struct vm_area_struct *vma);static inline pte_t *hugetlb_walk (struct vm_area_struct *vma,unsigned long addr,unsigned long sz) { -#if defined(CONFIG_HUGETLB_PAGE ) && \ - defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE ) && defined(CONFIG_LOCKDEP ) +#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING ) && defined(CONFIG_LOCKDEP )struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;/* mm/hugetlb.c +4
-4@@ -7211,7 +7211,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end,return 0 ; } -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable (struct vm_area_struct *svma,struct vm_area_struct *vma,unsigned long addr,pgoff_t idx)@@ -7373,7 +7373,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, return 1; } -#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share (struct mm_struct *mm,struct vm_area_struct *vma,unsigned long addr,pud_t *pud)@@ -7396,7 +7396,7 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) {return false; } -#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,@@ -7494,7 +7494,7 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)/* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page (struct hstate *h) { -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size (h) ==PMD_SIZE )return PUD_SIZE -PMD_SIZE ;#endif Signature · 1 line
2.45.2
Signature · 2 lines
Sincerely yours, Mike.
PATCH 3/3 powerpc/8xx: document and enforce that split PT locks are not used
In reply to David HildenbrandRight now, we cannot have split PT locks because 8xx does not support SMP.
But for the sake of documentation *why* 8xx is fine regarding what we documented in huge_pte_lockptr(), let's just add code to enforce it at the same time as documenting it.
This should also make everybody who wants to copy from the 8xx approach of supporting such unusual ways of mapping hugetlb folios aware that it gets tricky once multiple page tables are involved.
--- arch/powerpc/mm/pgtable.c | 6 ++++++ 1 file changed, 6 insertions(+)
arch/powerpc/mm/pgtable.c +6 -0
@@ -297,6 +297,12 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, }#if defined(CONFIG_PPC_8xx) + +#if defined(CONFIG_SPLIT_PTE_PTLOCKS ) || defined(CONFIG_SPLIT_PMD_PTLOCKS ) +/* We need the same lock to protect the PMD table and the two PTE tables. */ +#error "8M hugetlb folios are incompatible with split page table locks" +#endif +static void __set_huge_pte_at (pmd_t *pmd,pte_t *ptep,pte_basic_t val) {pte_basic_t *entry = (pte_basic_t *)ptep;
Signature · 1 line
2.45.2