mm: hugetlb: fix UAF in hugetlb_handle_userfault

stable inclusion
from stable-v5.10.150
commit 45c33966759ea1b4040c08dacda99ef623c0ca29
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I62WRY
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=45c33966759ea1b4040c08dacda99ef623c0ca29

--------------------------------

commit 958f32ce upstream.

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: 1a1aad8a ("userfaultfd: hugetlbfs: add userfaultfd hugetlb hook")
Signed-off-by: NLiu Shixin <liushixin2@huawei.com>
Signed-off-by: NKefeng Wang <wangkefeng.wang@huawei.com>
Reported-by: syzbot+193f9cee8638750b23cf@syzkaller.appspotmail.com
Reported-by: NLiu Zixian <liuzixian4@huawei.com>
Reviewed-by: NMike 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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Conflicts:
	mm/hugetlb.c
Signed-off-by: NLiu Shixin <liushixin2@huawei.com>
Reviewed-by: NKefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

mm/hugetlb.c

@@ -4770,6 +4770,7 @@ 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 = false;
+	u32 hash = hugetlb_fault_mutex_hash(mapping, idx);
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -4779,7 +4780,7 @@ 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;
 	}
 
 	/*
@@ -4798,7 +4799,6 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		 * Check for page in userfault range
 		 */
 		if (userfaultfd_missing(vma)) {
-			u32 hash;
 			struct vm_fault vmf = {
 				.vma = vma,
 				.address = haddr,
@@ -4813,17 +4813,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			};
 
 			/*
-			 * hugetlb_fault_mutex and i_mmap_rwsem 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 will
+			 * be dropped during handling userfault, any vma
+			 * operation should be careful from here.
 			 */
-			hash = hugetlb_fault_mutex_hash(mapping, idx);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);
-			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
-			i_mmap_lock_read(mapping);
-			mutex_lock(&hugetlb_fault_mutex_table[hash]);
-			goto out;
+			return handle_userfault(&vmf, VM_UFFD_MISSING);
 		}
 
 		page = alloc_huge_page(vma, haddr, 0);
@@ -4930,6 +4927,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 
 	unlock_page(page);
 out:
+	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+	i_mmap_unlock_read(mapping);
 	return ret;
 
 backout:
@@ -5029,7 +5028,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (sp_check_vm_share_pool(vma->vm_flags))
 			ret = sharepool_no_page(mm, vma, mapping, idx, address, ptep, flags);
 		else
-			ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
+			/*
+			 * 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, flags);
 		goto out_mutex;
 	}