mm/gup: trigger FAULT_FLAG_UNSHARE when R/O-pinning a possibly shared anonymous page

Whenever GUP currently ends up taking a R/O pin on an anonymous page that
might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault
on the page table entry will end up replacing the mapped anonymous page
due to COW, resulting in the GUP pin no longer being consistent with the
page actually mapped into the page table.

The possible ways to deal with this situation are:
 (1) Ignore and pin -- what we do right now.
 (2) Fail to pin -- which would be rather surprising to callers and
     could break user space.
 (3) Trigger unsharing and pin the now exclusive page -- reliable R/O
     pins.

Let's implement 3) because it provides the clearest semantics and allows
for checking in unpin_user_pages() and friends for possible BUGs: when
trying to unpin a page that's no longer exclusive, clearly something went
very wrong and might result in memory corruptions that might be hard to
debug.  So we better have a nice way to spot such issues.

This change implies that whenever user space *wrote* to a private mapping
(IOW, we have an anonymous page mapped), that GUP pins will always remain
consistent: reliable R/O GUP pins of anonymous pages.

As a side note, this commit fixes the COW security issue for hugetlb with
FOLL_PIN as documented in:
  https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com
The vmsplice reproducer still applies, because vmsplice uses FOLL_GET
instead of FOLL_PIN.

Note that follow_huge_pmd() doesn't apply because we cannot end up in
there with FOLL_PIN.

This commit is heavily based on prototype patches by Andrea.

Link: https://lkml.kernel.org/r/20220428083441.37290-17-david@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Co-developed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 66 insertions, 6 deletions

diff --git a/mm/gup.c b/mm/gup.c
index f424abf5e792..4d089d467e58 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -506,6 +506,10 @@ retry:
 		}
 	}
 
+	if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+		page = ERR_PTR(-EMLINK);
+		goto out;
+	}
 	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	if (unlikely(!try_grab_page(page, flags))) {
 		page = ERR_PTR(-ENOMEM);
@@ -732,6 +736,11 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
  * the device's dev_pagemap metadata to avoid repeating expensive lookups.
  *
+ * When getting an anonymous page and the caller has to trigger unsharing
+ * of a shared anonymous page first, -EMLINK is returned. The caller should
+ * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
+ * relevant with FOLL_PIN and !FOLL_WRITE.
+ *
  * On output, the @ctx->page_mask is set according to the size of the page.
  *
  * Return: the mapped (struct page *), %NULL if no mapping exists, or
@@ -855,7 +864,8 @@ unmap:
  * is, *@locked will be set to 0 and -EBUSY returned.
  */
 static int faultin_page(struct vm_area_struct *vma,
-		unsigned long address, unsigned int *flags, int *locked)
+		unsigned long address, unsigned int *flags, bool unshare,
+		int *locked)
 {
 	unsigned int fault_flags = 0;
 	vm_fault_t ret;
@@ -877,6 +887,11 @@ static int faultin_page(struct vm_area_struct *vma,
 		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
+	if (unshare) {
+		fault_flags |= FAULT_FLAG_UNSHARE;
+		/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
+		VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
+	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
@@ -1098,8 +1113,9 @@ retry:
 		cond_resched();
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
-		if (!page) {
-			ret = faultin_page(vma, start, &foll_flags, locked);
+		if (!page || PTR_ERR(page) == -EMLINK) {
+			ret = faultin_page(vma, start, &foll_flags,
+					   PTR_ERR(page) == -EMLINK, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
@@ -2201,6 +2217,11 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			goto pte_unmap;
 		}
 
+		if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+			gup_put_folio(folio, 1, flags);
+			goto pte_unmap;
+		}
+
 		/*
 		 * We need to make the page accessible if and only if we are
 		 * going to access its content (the FOLL_PIN case).  Please
@@ -2381,6 +2402,11 @@ 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)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2442,6 +2468,11 @@ 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)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2477,6 +2508,11 @@ 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)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 17ec6c939e7f..4414111998df 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1389,6 +1389,9 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
 
+	if (!pmd_write(*pmd) && gup_must_unshare(flags, page))
+		return ERR_PTR(-EMLINK);
+
 	if (!try_grab_page(page, flags))
 		return ERR_PTR(-ENOMEM);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9cefa3dd9af3..5f8d3a77a2ec 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5982,6 +5982,25 @@ 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,
+					       bool *unshare)
+{
+	pte_t pteval = huge_ptep_get(pte);
+
+	*unshare = false;
+	if (is_swap_pte(pteval))
+		return true;
+	if (huge_pte_write(pteval))
+		return false;
+	if (flags & FOLL_WRITE)
+		return true;
+	if (gup_must_unshare(flags, pte_page(pteval))) {
+		*unshare = true;
+		return true;
+	}
+	return false;
+}
+
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
@@ -5996,6 +6015,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
 		spinlock_t *ptl = NULL;
+		bool unshare = false;
 		int absent;
 		struct page *page;
 
@@ -6046,9 +6066,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * both cases, and because we can't follow correct pages
 		 * directly from any kind of swap entries.
 		 */
-		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
-		    ((flags & FOLL_WRITE) &&
-		      !huge_pte_write(huge_ptep_get(pte)))) {
+		if (absent ||
+		    __follow_hugetlb_must_fault(flags, pte, &unshare)) {
 			vm_fault_t ret;
 			unsigned int fault_flags = 0;
 
@@ -6056,6 +6075,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				spin_unlock(ptl);
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
+			else if (unshare)
+				fault_flags |= FAULT_FLAG_UNSHARE;
 			if (locked)
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
 					FAULT_FLAG_KILLABLE;