diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bedc449c14d8..982f2607180b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2885,7 +2885,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ diff --git a/mm/gup.c b/mm/gup.c index 7328251574307..5abdaf4874605 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -478,14 +478,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, return -EEXIST; } -/* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ +static inline bool can_follow_write_pte(pte_t pte, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + /* If the pte is writable, we can write to the page. */ + if (pte_write(pte)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) + return false; + return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -528,12 +556,19 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { - pte_unmap_unlock(ptep, ptl); - return NULL; - } page = vm_normal_page(vma, address, pte); + + /* + * We only care about anon pages in can_follow_write_pte() and don't + * have to worry about pte_devmap() because they are never anon. + */ + if ((flags & FOLL_WRITE) && + !can_follow_write_pte(pte, page, vma, flags)) { + page = NULL; + goto out; + } + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN @@ -986,17 +1021,6 @@ static int faultin_page(struct vm_area_struct *vma, return -EBUSY; } - /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when - * necessary, even if maybe_mkwrite decided not to set pte_write. We - * can thus safely do subsequent page lookups as if they were reads. - * But only do so when looping for pte_write is futile: in some cases - * userspace may also be wanting to write to the gotten user page, - * which a read fault here might prevent (a readonly page might get - * reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags |= FOLL_COW; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8a7c1b344abef..e9414ee57c5b1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1040,12 +1040,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); - /* - * When we COW a devmap PMD entry, we split it into PTEs, so we should - * not be in this function with `flags & FOLL_COW` set. - */ - WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) @@ -1395,14 +1389,42 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) return VM_FAULT_FALLBACK; } -/* - * FOLL_FORCE can write to even unwritable pmd's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1411,12 +1433,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; + struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) - goto out; + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(*pmd, page, vma, flags)) + return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) @@ -1424,10 +1450,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, /* Full NUMA hinting faults to serialise migration in fault paths */ if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) - goto out; - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + return NULL; if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) return ERR_PTR(-EMLINK); @@ -1444,7 +1467,6 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); -out: return page; }