Some platforms can customize the PTE PMD entry soft-dirty bit making it unavailable even if the architecture provides the resource. Add an API which architectures can define their specific implementations to detect if soft-dirty bit is available on which device the kernel is running. Signed-off-by: Chunyan Zhang --- fs/proc/task_mmu.c | 17 ++++++++++++++++- include/linux/pgtable.h | 12 ++++++++++++ mm/debug_vm_pgtable.c | 10 +++++----- mm/huge_memory.c | 13 +++++++------ mm/internal.h | 2 +- mm/mremap.c | 13 +++++++------ mm/userfaultfd.c | 10 ++++------ 7 files changed, 52 insertions(+), 25 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 29cca0e6d0ff..9e8083b6d4cd 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1058,7 +1058,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) * -Werror=unterminated-string-initialization warning * with GCC 15 */ - static const char mnemonics[BITS_PER_LONG][3] = { + static char mnemonics[BITS_PER_LONG][3] = { /* * In case if we meet a flag we don't know about. */ @@ -1129,6 +1129,16 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_SEALED)] = "sl", #endif }; +/* + * We should remove the VM_SOFTDIRTY flag if the soft-dirty bit is + * unavailable on which the kernel is running, even if the architecture + * provides the resource and soft-dirty is compiled in. + */ +#ifdef CONFIG_MEM_SOFT_DIRTY + if (!pgtable_soft_dirty_supported()) + mnemonics[ilog2(VM_SOFTDIRTY)][0] = 0; +#endif + size_t i; seq_puts(m, "VmFlags: "); @@ -1531,6 +1541,8 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { + if (!pgtable_soft_dirty_supported()) + return; /* * The soft-dirty tracker uses #PF-s to catch writes * to pages, so write-protect the pte as well. See the @@ -1566,6 +1578,9 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, { pmd_t old, pmd = *pmdp; + if (!pgtable_soft_dirty_supported()) + return; + if (pmd_present(pmd)) { /* See comment in change_huge_pmd() */ old = pmdp_invalidate(vma, addr, pmdp); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 4c035637eeb7..2a3578a4ae4c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1537,6 +1537,18 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif +/* + * Some platforms can customize the PTE soft-dirty bit making it unavailable + * even if the architecture provides the resource. + * Adding this API allows architectures to add their own checks for the + * devices on which the kernel is running. + * Note: When overiding it, please make sure the CONFIG_MEM_SOFT_DIRTY + * is part of this macro. + */ +#ifndef pgtable_soft_dirty_supported +#define pgtable_soft_dirty_supported() IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) +#endif + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 830107b6dd08..b32ce2b0b998 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -690,7 +690,7 @@ static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args) { pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + if (!pgtable_soft_dirty_supported()) return; pr_debug("Validating PTE soft dirty\n"); @@ -702,7 +702,7 @@ static void __init pte_swap_soft_dirty_tests(struct pgtable_debug_args *args) { pte_t pte; - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + if (!pgtable_soft_dirty_supported()) return; pr_debug("Validating PTE swap soft dirty\n"); @@ -718,7 +718,7 @@ static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { pmd_t pmd; - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + if (!pgtable_soft_dirty_supported()) return; if (!has_transparent_hugepage()) @@ -734,8 +734,8 @@ static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { pmd_t pmd; - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) || - !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION)) + if (!pgtable_soft_dirty_supported() || + !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION)) return; if (!has_transparent_hugepage()) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9c38a95e9f09..218d430a2ec6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2271,12 +2271,13 @@ static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, static pmd_t move_soft_dirty_pmd(pmd_t pmd) { -#ifdef CONFIG_MEM_SOFT_DIRTY - if (unlikely(is_pmd_migration_entry(pmd))) - pmd = pmd_swp_mksoft_dirty(pmd); - else if (pmd_present(pmd)) - pmd = pmd_mksoft_dirty(pmd); -#endif + if (pgtable_soft_dirty_supported()) { + if (unlikely(is_pmd_migration_entry(pmd))) + pmd = pmd_swp_mksoft_dirty(pmd); + else if (pmd_present(pmd)) + pmd = pmd_mksoft_dirty(pmd); + } + return pmd; } diff --git a/mm/internal.h b/mm/internal.h index 45b725c3dc03..c6ca62f8ecf3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1538,7 +1538,7 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + if (!pgtable_soft_dirty_supported()) return false; /* diff --git a/mm/mremap.c b/mm/mremap.c index e618a706aff5..7beb3114dbf5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -162,12 +162,13 @@ static pte_t move_soft_dirty_pte(pte_t pte) * Set soft dirty bit so we can notice * in userspace the ptes were moved. */ -#ifdef CONFIG_MEM_SOFT_DIRTY - if (pte_present(pte)) - pte = pte_mksoft_dirty(pte); - else if (is_swap_pte(pte)) - pte = pte_swp_mksoft_dirty(pte); -#endif + if (pgtable_soft_dirty_supported()) { + if (pte_present(pte)) + pte = pte_mksoft_dirty(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_mksoft_dirty(pte); + } + return pte; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 45e6290e2e8b..85f43479b67a 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1065,9 +1065,8 @@ static int move_present_pte(struct mm_struct *mm, orig_dst_pte = folio_mk_pte(src_folio, dst_vma->vm_page_prot); /* Set soft dirty bit so userspace can notice the pte was moved */ -#ifdef CONFIG_MEM_SOFT_DIRTY - orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); -#endif + if (pgtable_soft_dirty_supported()) + orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); if (pte_dirty(orig_src_pte)) orig_dst_pte = pte_mkdirty(orig_dst_pte); orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma); @@ -1134,9 +1133,8 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); -#ifdef CONFIG_MEM_SOFT_DIRTY - orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); -#endif + if (pgtable_soft_dirty_supported()) + orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); -- 2.34.1