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:   Peter Xu <peterx@redhat.com>
To:     linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc:     David Hildenbrand <david@redhat.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Nadav Amit <nadav.amit@gmail.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Rik van Riel <riel@surriel.com>, peterx@redhat.com,
        Miaohe Lin <linmiaohe@huawei.com>,
        Jann Horn <jannh@google.com>,
        James Houghton <jthoughton@google.com>,
        Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH v4 7/9] mm/hugetlb: Make follow_hugetlb_page() safe to pmd unshare
Date:   Fri, 16 Dec 2022 10:52:23 -0500
Message-Id: <20221216155223.2043727-1-peterx@redhat.com>
In-Reply-To: <20221216155100.2043537-1-peterx@redhat.com>
References: <20221216155100.2043537-1-peterx@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Since follow_hugetlb_page() walks the pgtable, it needs the vma lock
to make sure the pgtable page will not be freed concurrently.

Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/hugetlb.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0bf0abea388d..33fe73e1e589 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6433,6 +6433,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
+		hugetlb_vma_lock_read(vma);
 		/*
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
@@ -6457,6 +6458,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
 			if (pte)
 				spin_unlock(ptl);
+			hugetlb_vma_unlock_read(vma);
 			remainder = 0;
 			break;
 		}
@@ -6478,6 +6480,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 			if (pte)
 				spin_unlock(ptl);
+			hugetlb_vma_unlock_read(vma);
+
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
 			else if (unshare)
@@ -6540,6 +6544,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			remainder -= pages_per_huge_page(h);
 			i += pages_per_huge_page(h);
 			spin_unlock(ptl);
+			hugetlb_vma_unlock_read(vma);
 			continue;
 		}
 
@@ -6569,6 +6574,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			if (WARN_ON_ONCE(!try_grab_folio(pages[i], refs,
 							 flags))) {
 				spin_unlock(ptl);
+				hugetlb_vma_unlock_read(vma);
 				remainder = 0;
 				err = -ENOMEM;
 				break;
@@ -6580,6 +6586,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		i += refs;
 
 		spin_unlock(ptl);
+		hugetlb_vma_unlock_read(vma);
 	}
 	*nr_pages = remainder;
 	/*
-- 
2.37.3