[RFC PATCH v4 1/8] hugetlbfs: revert use i_mmap_rwsem to address page fault/truncate race

[Mike Kravetz <mike.kravetz@oracle.com>]

Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") added code to take i_mmap_rwsem in read mode for the
duration of fault processing.  The use of i_mmap_rwsem to prevent
fault/truncate races depends on this.  However, this has been shown to
cause performance/scaling issues.  As a result, that code will be
reverted.  Since the use i_mmap_rwsem to address page fault/truncate races
depends on this, it must also be reverted.

In a subsequent patch, code will be added to detect the fault/truncate
race and back out operations as required.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 fs/hugetlbfs/inode.c | 30 +++++++++---------------------
 mm/hugetlb.c         | 23 ++++++++++++-----------
 2 files changed, 21 insertions(+), 32 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 20336cb3c040..9fa1af39382d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -451,9 +451,10 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
  *	In this case, we first scan the range and release found pages.
  *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserve
  *	maps and global counts.  Page faults can not race with truncation
- *	in this routine.  hugetlb_no_page() holds i_mmap_rwsem and prevents
- *	page faults in the truncated range by checking i_size.  i_size is
- *	modified while holding i_mmap_rwsem.
+ *	in this routine.  hugetlb_no_page() prevents page faults in the
+ *	truncated range.  It checks i_size before allocation, and again after
+ *	with the page table lock for the page held.  The same lock must be
+ *	acquired to unmap a page.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
  *	Only when releasing a page is the associated region/reserve map
@@ -483,16 +484,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			u32 hash = 0;
 
 			index = folio->index;
-			if (!truncate_op) {
-				/*
-				 * Only need to hold the fault mutex in the
-				 * hole punch case.  This prevents races with
-				 * page faults.  Races are not possible in the
-				 * case of truncation.
-				 */
-				hash = hugetlb_fault_mutex_hash(mapping, index);
-				mutex_lock(&hugetlb_fault_mutex_table[hash]);
-			}
+			hash = hugetlb_fault_mutex_hash(mapping, index);
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
 			 * If folio is mapped, it was faulted in after being
@@ -536,8 +529,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			}
 
 			folio_unlock(folio);
-			if (!truncate_op)
-				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
@@ -575,8 +567,8 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	BUG_ON(offset & ~huge_page_mask(h));
 	pgoff = offset >> PAGE_SHIFT;
 
-	i_mmap_lock_write(mapping);
 	i_size_write(inode, offset);
+	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
 				      ZAP_FLAG_DROP_MARKER);
@@ -735,11 +727,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		/* addr is the offset within the file (zero based) */
 		addr = index * hpage_size;
 
-		/*
-		 * fault mutex taken here, protects against fault path
-		 * and hole punch.  inode_lock previously taken protects
-		 * against truncation.
-		 */
+		/* mutex taken here, fault path and hole punch */
 		hash = hugetlb_fault_mutex_hash(mapping, index);
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ca081078e814..02cceb7b8cce 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5532,18 +5532,17 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	}
 
 	/*
-	 * We can not race with truncation due to holding i_mmap_rwsem.
-	 * i_size is modified when holding i_mmap_rwsem, so check here
-	 * once for faults beyond end of file.
+	 * Use page lock to guard against racing truncation
+	 * before we get page_table_lock.
 	 */
-	size = i_size_read(mapping->host) >> huge_page_shift(h);
-	if (idx >= size)
-		goto out;
-
 retry:
 	new_page = false;
 	page = find_lock_page(mapping, idx);
 	if (!page) {
+		size = i_size_read(mapping->host) >> huge_page_shift(h);
+		if (idx >= size)
+			goto out;
+
 		/* Check for page in userfault range */
 		if (userfaultfd_missing(vma)) {
 			ret = hugetlb_handle_userfault(vma, mapping, idx,
@@ -5633,6 +5632,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
+	if (idx >= size)
+		goto backout;
+
 	ret = 0;
 	/* If pte changed from under us, retry */
 	if (!pte_same(huge_ptep_get(ptep), old_pte))
@@ -5741,10 +5744,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/*
 	 * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
-	 * until finished with ptep.  This serves two purposes:
-	 * 1) It prevents huge_pmd_unshare from being called elsewhere
-	 *    and making the ptep no longer valid.
-	 * 2) It synchronizes us with i_size modifications during truncation.
+	 * until finished with ptep.  This prevents huge_pmd_unshare from
+	 * being called elsewhere and making the ptep no longer valid.
 	 *
 	 * ptep could have already be assigned via huge_pte_offset.  That
 	 * is OK, as huge_pte_alloc will return the same value unless
-- 
2.35.3