Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Liu Shixin <liushixin2@huawei.com>
To:     Liu Zixian <liuzixian4@huawei.com>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Muchun Song <songmuchun@bytedance.com>,
        "Andrew Morton" <akpm@linux-foundation.org>,
        Sidhartha Kumar <sidhartha.kumar@oracle.com>,
        John Hubbard <jhubbard@nvidia.com>,
        "David Hildenbrand" <david@redhat.com>,
        Kefeng Wang <wangkefeng.wang@huawei.com>
CC:     <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
        Liu Shixin <liushixin2@huawei.com>
Subject: [PATCH v2] mm: hugetlb: fix UAF in hugetlb_handle_userfault
Date:   Thu, 22 Sep 2022 22:10:02 +0800
Message-ID: <20220922141002.3242443-1-liushixin2@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

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/
Reported-by: syzbot+193f9cee8638750b23cf@syzkaller.appspotmail.com
Reported-by: Liu Zixian <liuzixian4@huawei.com>
Fixes: 1a1aad8a9b7b ("userfaultfd: hugetlbfs: add userfaultfd hugetlb hook")
CC: stable@vger.kernel.org # 4.14+
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
---
 mm/hugetlb.c | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9b8526d27c29..5a5d466692cf 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,
@@ -5508,17 +5507,12 @@ 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.
+	 * dropped before handling userfault.
 	 */
 	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,
@@ -5537,6 +5531,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	unsigned long haddr = address & huge_page_mask(h);
 	bool new_page, new_pagecache_page = false;
 	bool reserve_alloc = false;
+	u32 hash = hugetlb_fault_mutex_hash(mapping, idx);
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -5547,7 +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;
 	}
 
 	/*
@@ -5561,12 +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)) {
@@ -5634,10 +5627,9 @@ 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;
 		}
 	}
 
@@ -5695,6 +5687,8 @@ 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:
@@ -5792,11 +5786,9 @@ 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))
+		return hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
 				      entry, flags);
-		goto out_mutex;
-	}
 
 	ret = 0;
 
-- 
2.25.1