From 84209e87c6963f928194a890399e24e8ad299db1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 16 Nov 2022 11:26:48 +0100 Subject: [PATCH] mm/gup: reliable R/O long-term pinning in COW mappings We already support reliable R/O pinning of anonymous memory. However, assume we end up pinning (R/O long-term) a pagecache page or the shared zeropage inside a writable private ("COW") mapping. The next write access will trigger a write-fault and replace the pinned page by an exclusive anonymous page in the process page tables to break COW: the pinned page no longer corresponds to the page mapped into the process' page table. Now that FAULT_FLAG_UNSHARE can break COW on anything mapped into a COW mapping, let's properly break COW first before R/O long-term pinning something that's not an exclusive anon page inside a COW mapping. FAULT_FLAG_UNSHARE will break COW and map an exclusive anon page instead that can get pinned safely. With this change, we can stop using FOLL_FORCE|FOLL_WRITE for reliable R/O long-term pinning in COW mappings. With this change, the new R/O long-term pinning tests for non-anonymous memory succeed: # [RUN] R/O longterm GUP pin ... with shared zeropage ok 151 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd ok 152 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with tmpfile ok 153 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with huge zeropage ok 154 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd hugetlb (2048 kB) ok 155 Longterm R/O pin is reliable # [RUN] R/O longterm GUP pin ... with memfd hugetlb (1048576 kB) ok 156 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with shared zeropage ok 157 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd ok 158 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with tmpfile ok 159 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with huge zeropage ok 160 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd hugetlb (2048 kB) ok 161 Longterm R/O pin is reliable # [RUN] R/O longterm GUP-fast pin ... with memfd hugetlb (1048576 kB) ok 162 Longterm R/O pin is reliable Note 1: We don't care about short-term R/O-pinning, because they have snapshot semantics: they are not supposed to observe modifications that happen after pinning. As one example, assume we start direct I/O to read from a page and store page content into a file: modifications to page content after starting direct I/O are not guaranteed to end up in the file. So even if we'd pin the shared zeropage, the end result would be as expected -- getting zeroes stored to the file. Note 2: For shared mappings we'll now always fallback to the slow path to lookup the VMA when R/O long-term pining. While that's the necessary price we have to pay right now, it's actually not that bad in practice: most FOLL_LONGTERM users already specify FOLL_WRITE, for example, along with FOLL_FORCE because they tried dealing with COW mappings correctly ... Note 3: For users that use FOLL_LONGTERM right now without FOLL_WRITE, such as VFIO, we'd now no longer pin the shared zeropage. Instead, we'd populate exclusive anon pages that we can pin. There was a concern that this could affect the memlock limit of existing setups. For example, a VM running with VFIO could run into the memlock limit and fail to run. However, we essentially had the same behavior already in commit 17839856fd58 ("gup: document and work around "COW can break either way" issue") which got merged into some enterprise distros, and there were not any such complaints. So most probably, we're fine. Link: https://lkml.kernel.org/r/20221116102659.70287-10-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Daniel Vetter Reviewed-by: Vlastimil Babka Reviewed-by: John Hubbard Signed-off-by: Andrew Morton --- include/linux/mm.h | 27 ++++++++++++++++++++++++--- mm/gup.c | 10 +++++----- mm/huge_memory.c | 2 +- mm/hugetlb.c | 7 ++++--- 4 files changed, 34 insertions(+), 12 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 686879dbb0bd..d8363ac34a7c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3149,8 +3149,12 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. + * + * If the vma is NULL, we're coming from the GUP-fast path and might have + * to fallback to the slow path just to lookup the vma. */ -static inline bool gup_must_unshare(unsigned int flags, struct page *page) +static inline bool gup_must_unshare(struct vm_area_struct *vma, + unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry @@ -3163,8 +3167,25 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) * Note: PageAnon(page) is stable until the page is actually getting * freed. */ - if (!PageAnon(page)) - return false; + if (!PageAnon(page)) { + /* + * We only care about R/O long-term pining: R/O short-term + * pinning does not have the semantics to observe successive + * changes through the process page tables. + */ + if (!(flags & FOLL_LONGTERM)) + return false; + + /* We really need the vma ... */ + if (!vma) + return true; + + /* + * ... because we only care about writable private ("COW") + * mappings where we have to break COW early. + */ + return is_cow_mapping(vma->vm_flags); + } /* Paired with a memory barrier in page_try_share_anon_rmap(). */ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) diff --git a/mm/gup.c b/mm/gup.c index 2500d00db51b..39c84a200f06 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -603,7 +603,7 @@ retry: } } - if (!pte_write(pte) && gup_must_unshare(flags, page)) { + if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } @@ -2380,7 +2380,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, goto pte_unmap; } - if (!pte_write(pte) && gup_must_unshare(flags, page)) { + if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } @@ -2566,7 +2566,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } - if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) { + if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2632,7 +2632,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) { + if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2672,7 +2672,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) { + if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5eb702726a0e..86a30041a2e1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1480,7 +1480,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags)) return NULL; - if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) + if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3d381b26d553..9d97c9a2a15d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6197,7 +6197,8 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, } } -static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, +static inline bool __follow_hugetlb_must_fault(struct vm_area_struct *vma, + unsigned int flags, pte_t *pte, bool *unshare) { pte_t pteval = huge_ptep_get(pte); @@ -6209,7 +6210,7 @@ static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, return false; if (flags & FOLL_WRITE) return true; - if (gup_must_unshare(flags, pte_page(pteval))) { + if (gup_must_unshare(vma, flags, pte_page(pteval))) { *unshare = true; return true; } @@ -6338,7 +6339,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * directly from any kind of swap entries. */ if (absent || - __follow_hugetlb_must_fault(flags, pte, &unshare)) { + __follow_hugetlb_must_fault(vma, flags, pte, &unshare)) { vm_fault_t ret; unsigned int fault_flags = 0;