diff options
Diffstat (limited to 'mm/mprotect.c')
| -rw-r--r-- | mm/mprotect.c | 114 |
1 files changed, 87 insertions, 27 deletions
diff --git a/mm/mprotect.c b/mm/mprotect.c index 7a8e84f86831..1d823b050329 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -37,12 +37,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa) + unsigned long cp_flags) { pte_t *pte, oldpte; spinlock_t *ptl; unsigned long pages = 0; int target_node = NUMA_NO_NODE; + bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT; + bool prot_numa = cp_flags & MM_CP_PROT_NUMA; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * Can be called with only the mmap_sem for reading by @@ -98,7 +102,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * it cannot move them all from MIGRATE_ASYNC * context. */ - if (page_is_file_cache(page) && PageDirty(page)) + if (page_is_file_lru(page) && PageDirty(page)) continue; /* @@ -114,6 +118,19 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (preserve_write) ptent = pte_mk_savedwrite(ptent); + if (uffd_wp) { + ptent = pte_wrprotect(ptent); + ptent = pte_mkuffd_wp(ptent); + } else if (uffd_wp_resolve) { + /* + * Leave the write bit to be handled + * by PF interrupt handler, then + * things like COW could be properly + * handled. + */ + ptent = pte_clear_uffd_wp(ptent); + } + /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && (pte_soft_dirty(ptent) || @@ -122,11 +139,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION)) { + } else if (is_swap_pte(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); + pte_t newpte; if (is_write_migration_entry(entry)) { - pte_t newpte; /* * A protection check is difficult so * just be safe and disable write @@ -135,22 +152,28 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); - set_pte_at(vma->vm_mm, addr, pte, newpte); - - pages++; - } - - if (is_write_device_private_entry(entry)) { - pte_t newpte; - + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else if (is_write_device_private_entry(entry)) { /* * We do not preserve soft-dirtiness. See * copy_one_pte() for explanation. */ make_device_private_entry_read(&entry); newpte = swp_entry_to_pte(entry); - set_pte_at(vma->vm_mm, addr, pte, newpte); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); + } else { + newpte = oldpte; + } + + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + if (!pte_same(oldpte, newpte)) { + set_pte_at(vma->vm_mm, addr, pte, newpte); pages++; } } @@ -161,9 +184,34 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return pages; } +/* + * Used when setting automatic NUMA hinting protection where it is + * critical that a numa hinting PMD is not confused with a bad PMD. + */ +static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + + /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + + if (pmd_none(pmdval)) + return 1; + if (pmd_trans_huge(pmdval)) + return 0; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + + return 0; +} + static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - pgprot_t newprot, int dirty_accountable, int prot_numa) + pgprot_t newprot, unsigned long cp_flags) { pmd_t *pmd; unsigned long next; @@ -178,8 +226,17 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, unsigned long this_pages; next = pmd_addr_end(addr, end); - if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) - && pmd_none_or_clear_bad(pmd)) + + /* + * Automatic NUMA balancing walks the tables with mmap_sem + * held for read. It's possible a parallel update to occur + * between pmd_trans_huge() and a pmd_none_or_clear_bad() + * check leading to a false positive and clearing. + * Hence, it's necessary to atomically read the PMD value + * for all the checks. + */ + if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) && + pmd_none_or_clear_bad_unless_trans_huge(pmd)) goto next; /* invoke the mmu notifier if the pmd is populated */ @@ -195,7 +252,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, __split_huge_pmd(vma, pmd, addr, false, NULL); } else { int nr_ptes = change_huge_pmd(vma, pmd, addr, - newprot, prot_numa); + newprot, cp_flags); if (nr_ptes) { if (nr_ptes == HPAGE_PMD_NR) { @@ -210,7 +267,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, /* fall through, the trans huge pmd just split */ } this_pages = change_pte_range(vma, pmd, addr, next, newprot, - dirty_accountable, prot_numa); + cp_flags); pages += this_pages; next: cond_resched(); @@ -226,7 +283,7 @@ next: static inline unsigned long change_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - pgprot_t newprot, int dirty_accountable, int prot_numa) + pgprot_t newprot, unsigned long cp_flags) { pud_t *pud; unsigned long next; @@ -238,7 +295,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, if (pud_none_or_clear_bad(pud)) continue; pages += change_pmd_range(vma, pud, addr, next, newprot, - dirty_accountable, prot_numa); + cp_flags); } while (pud++, addr = next, addr != end); return pages; @@ -246,7 +303,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, static inline unsigned long change_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - pgprot_t newprot, int dirty_accountable, int prot_numa) + pgprot_t newprot, unsigned long cp_flags) { p4d_t *p4d; unsigned long next; @@ -258,7 +315,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma, if (p4d_none_or_clear_bad(p4d)) continue; pages += change_pud_range(vma, p4d, addr, next, newprot, - dirty_accountable, prot_numa); + cp_flags); } while (p4d++, addr = next, addr != end); return pages; @@ -266,7 +323,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma, static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa) + unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; @@ -283,7 +340,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, if (pgd_none_or_clear_bad(pgd)) continue; pages += change_p4d_range(vma, pgd, addr, next, newprot, - dirty_accountable, prot_numa); + cp_flags); } while (pgd++, addr = next, addr != end); /* Only flush the TLB if we actually modified any entries: */ @@ -296,14 +353,17 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa) + unsigned long cp_flags) { unsigned long pages; + BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); + if (is_vm_hugetlb_page(vma)) pages = hugetlb_change_protection(vma, start, end, newprot); else - pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa); + pages = change_protection_range(vma, start, end, newprot, + cp_flags); return pages; } @@ -425,7 +485,7 @@ success: vma_set_page_prot(vma); change_protection(vma, start, end, vma->vm_page_prot, - dirty_accountable, 0); + dirty_accountable ? MM_CP_DIRTY_ACCT : 0); /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major |