mm: hugetlb: fix UAF in hugetlb_handle_userfault

The vma_lock and hugetlb_fault_mutex are dropped before handling userfault
and reacquire them again after handle_userfault(), but reacquire the
vma_lock could lead to UAF[1,2] due to the following race,

hugetlb_fault
  hugetlb_no_page
    /*unlock vma_lock */
    hugetlb_handle_userfault
      handle_userfault
        /* unlock mm->mmap_lock*/
                                           vm_mmap_pgoff
                                             do_mmap
                                               mmap_region
                                                 munmap_vma_range
                                                   /* clean old vma */
        /* lock vma_lock again  <--- UAF */
    /* unlock vma_lock */

Since the vma_lock will unlock immediately after
hugetlb_handle_userfault(), let's drop the unneeded lock and unlock in
hugetlb_handle_userfault() to fix the issue.

[1] https://lore.kernel.org/linux-mm/000000000000d5e00a05e834962e@google.com/
[2] https://lore.kernel.org/linux-mm/20220921014457.1668-1-liuzixian4@huawei.com/
Link: https://lkml.kernel.org/r/20220923042113.137273-1-liushixin2@huawei.com
Fixes: 1a1aad8a9b7b ("userfaultfd: hugetlbfs: add userfaultfd hugetlb hook")
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reported-by: syzbot+193f9cee8638750b23cf@syzkaller.appspotmail.com
Reported-by: Liu Zixian <liuzixian4@huawei.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: <stable@vger.kernel.org>	[4.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 17 insertions, 20 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2182134216f0..3c1316ad54b5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5489,7 +5489,6 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
 						  unsigned long addr,
 						  unsigned long reason)
 {
-	vm_fault_t ret;
 	u32 hash;
 	struct vm_fault vmf = {
 		.vma = vma,
@@ -5507,18 +5506,14 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
 	};
 
 	/*
-	 * vma_lock and hugetlb_fault_mutex must be
-	 * dropped before handling userfault.  Reacquire
-	 * after handling fault to make calling code simpler.
+	 * vma_lock and hugetlb_fault_mutex must be dropped before handling
+	 * userfault. Also mmap_lock could be dropped due to handling
+	 * userfault, any vma operation should be careful from here.
 	 */
 	hugetlb_vma_unlock_read(vma);
 	hash = hugetlb_fault_mutex_hash(mapping, idx);
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-	ret = handle_userfault(&vmf, reason);
-	mutex_lock(&hugetlb_fault_mutex_table[hash]);
-	hugetlb_vma_lock_read(vma);
-
-	return ret;
+	return handle_userfault(&vmf, reason);
 }
 
 static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
@@ -5536,6 +5531,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	spinlock_t *ptl;
 	unsigned long haddr = address & huge_page_mask(h);
 	bool new_page, new_pagecache_page = false;
+	u32 hash = hugetlb_fault_mutex_hash(mapping, idx);
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -5546,7 +5542,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
 		pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
 			   current->pid);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -5560,12 +5556,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		if (idx >= size)
 			goto out;
 		/* Check for page in userfault range */
-		if (userfaultfd_missing(vma)) {
-			ret = hugetlb_handle_userfault(vma, mapping, idx,
+		if (userfaultfd_missing(vma))
+			return hugetlb_handle_userfault(vma, mapping, idx,
 						       flags, haddr, address,
 						       VM_UFFD_MISSING);
-			goto out;
-		}
 
 		page = alloc_huge_page(vma, haddr, 0);
 		if (IS_ERR(page)) {
@@ -5631,10 +5625,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		if (userfaultfd_minor(vma)) {
 			unlock_page(page);
 			put_page(page);
-			ret = hugetlb_handle_userfault(vma, mapping, idx,
+			return hugetlb_handle_userfault(vma, mapping, idx,
 						       flags, haddr, address,
 						       VM_UFFD_MINOR);
-			goto out;
 		}
 	}
 
@@ -5692,6 +5685,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 
 	unlock_page(page);
 out:
+	hugetlb_vma_unlock_read(vma);
+	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	return ret;
 
 backout:
@@ -5789,11 +5784,13 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	entry = huge_ptep_get(ptep);
 	/* PTE markers should be handled the same way as none pte */
-	if (huge_pte_none_mostly(entry)) {
-		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
+	if (huge_pte_none_mostly(entry))
+		/*
+		 * hugetlb_no_page will drop vma lock and hugetlb fault
+		 * mutex internally, which make us return immediately.
+		 */
+		return hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
 				      entry, flags);
-		goto out_mutex;
-	}
 
 	ret = 0;