diff --git a/include/linux/mm.h b/include/linux/mm.h index cf3d0d673f6b..09ea26056e2f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1962,8 +1962,12 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, * for now all the callers are only use one of the flags at the same * time. */ -/* Whether we should allow dirty bit accounting */ -#define MM_CP_DIRTY_ACCT (1UL << 0) +/* + * Whether we should manually check if we can map individual PTEs writable, + * because something (e.g., COW, uffd-wp) blocks that from happening for all + * PTEs automatically in a writable mapping. + */ +#define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ diff --git a/mm/mprotect.c b/mm/mprotect.c index ba5592655ee3..996a97e213ad 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -38,6 +38,39 @@ #include "internal.h" +static inline bool can_change_pte_writable(struct vm_area_struct *vma, + unsigned long addr, pte_t pte) +{ + struct page *page; + + VM_BUG_ON(!(vma->vm_flags & VM_WRITE) || pte_write(pte)); + + if (pte_protnone(pte) || !pte_dirty(pte)) + return false; + + /* Do we need write faults for softdirty tracking? */ + if ((vma->vm_flags & VM_SOFTDIRTY) && !pte_soft_dirty(pte)) + return false; + + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_pte_wp(vma, pte)) + return false; + + if (!(vma->vm_flags & VM_SHARED)) { + /* + * We can only special-case on exclusive anonymous pages, + * because we know that our write-fault handler similarly would + * map them writable without any additional checks while holding + * the PT lock. + */ + page = vm_normal_page(vma, addr, pte); + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + } + + return true; +} + static unsigned long change_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) @@ -46,7 +79,6 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, 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; @@ -137,21 +169,27 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, 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) || - !(vma->vm_flags & VM_SOFTDIRTY))) { + /* + * In some writable, shared mappings, we might want + * to catch actual write access -- see + * vma_wants_writenotify(). + * + * In all writable, private mappings, we have to + * properly handle COW. + * + * In both cases, we can sometimes still change PTEs + * writable and avoid the write-fault handler, for + * example, if a PTE is already dirty and no other + * COW or special handling is required. + */ + if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && + !pte_write(ptent) && + can_change_pte_writable(vma, addr, ptent)) ptent = pte_mkwrite(ptent); - } + ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); if (pte_needs_flush(oldpte, ptent)) tlb_flush_pte_range(tlb, addr, PAGE_SIZE); @@ -505,9 +543,9 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long oldflags = vma->vm_flags; long nrpages = (end - start) >> PAGE_SHIFT; unsigned long charged = 0; + bool try_change_writable; pgoff_t pgoff; int error; - int dirty_accountable = 0; if (newflags == oldflags) { *pprev = vma; @@ -583,11 +621,20 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, * held in write mode. */ vma->vm_flags = newflags; - dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); + /* + * We want to check manually if we can change individual PTEs writable + * if we can't do that automatically for all PTEs in a mapping. For + * private mappings, that's always the case when we have write + * permissions as we properly have to handle COW. + */ + if (vma->vm_flags & VM_SHARED) + try_change_writable = vma_wants_writenotify(vma, vma->vm_page_prot); + else + try_change_writable = !!(vma->vm_flags & VM_WRITE); vma_set_page_prot(vma); change_protection(tlb, vma, start, end, vma->vm_page_prot, - dirty_accountable ? MM_CP_DIRTY_ACCT : 0); + try_change_writable ? MM_CP_TRY_CHANGE_WRITABLE : 0); /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major