[RFC,v2,08/12] mm/hugetlb: Use hugetlb walker lock in follow_hugetlb_page()

Commit Message

Peter Xu Nov. 18, 2022, 1:10 a.m. UTC

Hugetlb walker lock makes sure the pte_t* won't go away from under us.
Some trick is used to release the walker lock slightly earlier when we
found present pte.

Signed-off-by: Peter Xu <[e-mail]>
---
 mm/hugetlb.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

Patch

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fc49e3ca8acd..e81af6a46c59 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6280,6 +6280,7 @@  long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
+		hugetlb_walker_lock();
 		/*
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
@@ -6304,6 +6305,7 @@  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_walker_unlock();
 			remainder = 0;
 			break;
 		}
@@ -6325,6 +6327,8 @@  long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 			if (pte)
 				spin_unlock(ptl);
+			hugetlb_walker_unlock();
+
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
 			else if (unshare)
@@ -6367,6 +6371,15 @@  long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 		}
 
+		/*
+		 * When reach here, it means the pteval is not absent, so
+		 * anyone who wants to free and invalidate the pgtable page
+		 * (aka, pte*) should need to first unmap the entries which
+		 * relies on the pgtable lock.  Since we're holding it,
+		 * we're safe even without the walker lock anymore.
+		 */
+		hugetlb_walker_unlock();
+
 		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));