[PATCH 07/10] mm/hugetlb: Make follow_hugetlb_page() safe to pmd unshare

From: Peter Xu
Date: Tue Nov 29 2022 - 14:38:53 EST


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

Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
mm/hugetlb.c | 7 +++++++
1 file changed, 7 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d6bb1d22f1c4..df645a5824e3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6290,6 +6290,7 @@ 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
@@ -6314,6 +6315,7 @@ 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;
}
@@ -6335,6 +6337,8 @@ 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)
@@ -6394,6 +6398,7 @@ 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;
}

@@ -6421,6 +6426,7 @@ 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;
@@ -6432,6 +6438,7 @@ 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