hugetlb/userfaultfd: forbid huge pmd sharing when uffd enabled

Huge pmd sharing could bring problem to userfaultfd.  The thing is that
userfaultfd is running its logic based on the special bits on page table
entries, however the huge pmd sharing could potentially share page table
entries for different address ranges.  That could cause issues on
either:

 - When sharing huge pmd page tables for an uffd write protected range,
   the newly mapped huge pmd range will also be write protected
   unexpectedly, or,

 - When we try to write protect a range of huge pmd shared range, we'll
   first do huge_pmd_unshare() in hugetlb_change_protection(), however
   that also means the UFFDIO_WRITEPROTECT could be silently skipped for
   the shared region, which could lead to data loss.

While at it, a few other things are done altogether:

 - Move want_pmd_share() from mm/hugetlb.c into linux/hugetlb.h, because
   that's definitely something that arch code would like to use too

 - ARM64 currently directly check against
   CONFIG_ARCH_WANT_HUGE_PMD_SHARE when trying to share huge pmd. Switch
   to the want_pmd_share() helper.

 - Move vma_shareable() from huge_pmd_share() into want_pmd_share().

[peterx@redhat.com: fix build with !ARCH_WANT_HUGE_PMD_SHARE]
  Link: https://lkml.kernel.org/r/20210310185359.88297-1-peterx@redhat.com

Link: https://lkml.kernel.org/r/20210218231202.15426-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm64/mm/hugetlbpage.c

@@ -284,8 +284,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		ptep = pte_alloc_map(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
-		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
-		    pud_none(READ_ONCE(*pudp)))
+		if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp)))
 			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);

include/linux/hugetlb.h

@@ -1040,4 +1040,6 @@ static inline __init void hugetlb_cma_check(void)
 }
 #endif
 
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
+
 #endif /* _LINUX_HUGETLB_H */

include/linux/userfaultfd_k.h

@@ -52,6 +52,15 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 	return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx;
 }
 
+/*
+ * Never enable huge pmd sharing on uffd-wp registered vmas, because uffd-wp
+ * protect information is per pgtable entry.
+ */
+static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_UFFD_WP;
+}
+
 static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_UFFD_MISSING;

mm/hugetlb.c

@@ -5326,6 +5326,15 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	return false;
 }
 
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
+{
+#ifdef CONFIG_USERFAULTFD
+	if (uffd_disable_huge_pmd_share(vma))
+		return false;
+#endif
+	return vma_shareable(vma, addr);
+}
+
 /*
  * Determine if start,end range within vma could be mapped by shared pmd.
  * If yes, adjust start and end to cover range associated with possible
@@ -5382,9 +5391,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (!vma_shareable(vma, addr))
-		return (pte_t *)pmd_alloc(mm, pud, addr);
-
 	i_mmap_assert_locked(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
@@ -5448,7 +5454,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
 	return 1;
 }
-#define want_pmd_share()	(1)
+
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, pud_t *pud)
@@ -5466,7 +5472,11 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
 }
-#define want_pmd_share()	(0)
+
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
+{
+	return false;
+}
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
@@ -5488,7 +5498,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			pte = (pte_t *)pud;
 		} else {
 			BUG_ON(sz != PMD_SIZE);
-			if (want_pmd_share() && pud_none(*pud))
+			if (want_pmd_share(vma, addr) && pud_none(*pud))
 				pte = huge_pmd_share(mm, vma, addr, pud);
 			else
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);