Merge tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fs hole punching vs cache filling race fixes from Jan Kara:
 "Fix races leading to possible data corruption or stale data exposure
  in multiple filesystems when hole punching races with operations such
  as readahead.

  This is the series I was sending for the last merge window but with
  your objection fixed - now filemap_fault() has been modified to take
  invalidate_lock only when we need to create new page in the page cache
  and / or bring it uptodate"

* tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  filesystems/locking: fix Malformed table warning
  cifs: Fix race between hole punch and page fault
  ceph: Fix race between hole punch and page fault
  fuse: Convert to using invalidate_lock
  f2fs: Convert to using invalidate_lock
  zonefs: Convert to using invalidate_lock
  xfs: Convert double locking of MMAPLOCK to use VFS helpers
  xfs: Convert to use invalidate_lock
  xfs: Refactor xfs_isilocked()
  ext2: Convert to using invalidate_lock
  ext4: Convert to use mapping->invalidate_lock
  mm: Add functions to lock invalidate_lock for two mappings
  mm: Protect operations adding pages to page cache with invalidate_lock
  documentation: Sync file_operations members with reality
  mm: Fix comments mentioning i_mutex

1 files changed, 17 insertions, 30 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d8de607849df..325c038e7b23 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3950,20 +3950,19 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return ret;
 }
 
-static void ext4_wait_dax_page(struct ext4_inode_info *ei)
+static void ext4_wait_dax_page(struct inode *inode)
 {
-	up_write(&ei->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	schedule();
-	down_write(&ei->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 }
 
 int ext4_break_layouts(struct inode *inode)
 {
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct page *page;
 	int error;
 
-	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+	if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
 		return -EINVAL;
 
 	do {
@@ -3974,7 +3973,7 @@ int ext4_break_layouts(struct inode *inode)
 		error = ___wait_var_event(&page->_refcount,
 				atomic_read(&page->_refcount) == 1,
 				TASK_INTERRUPTIBLE, 0, 0,
-				ext4_wait_dax_page(ei));
+				ext4_wait_dax_page(inode));
 	} while (error == 0);
 
 	return error;
@@ -4005,9 +4004,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	if (ext4_has_inline_data(inode)) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock(mapping);
 		ret = ext4_convert_inline_data(inode);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(mapping);
 		if (ret)
 			return ret;
 	}
@@ -4058,7 +4057,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(mapping);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -4131,7 +4130,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5426,11 +5425,11 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			inode_dio_wait(inode);
 		}
 
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock(inode->i_mapping);
 
 		rc = ext4_break_layouts(inode);
 		if (rc) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(inode->i_mapping);
 			goto err_out;
 		}
 
@@ -5506,7 +5505,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				error = rc;
 		}
 out_mmap_sem:
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(inode->i_mapping);
 	}
 
 	if (!error) {
@@ -5983,10 +5982,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	 * data (and journalled aops don't know how to handle these cases).
 	 */
 	if (val) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock(inode->i_mapping);
 		err = filemap_write_and_wait(inode->i_mapping);
 		if (err < 0) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(inode->i_mapping);
 			return err;
 		}
 	}
@@ -6019,7 +6018,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(inode->i_mapping);
 
 	/* Finally we can mark the inode as dirty. */
 
@@ -6063,7 +6062,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 
-	down_read(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock_shared(mapping);
 
 	err = ext4_convert_inline_data(inode);
 	if (err)
@@ -6176,7 +6175,7 @@ retry_alloc:
 out_ret:
 	ret = block_page_mkwrite_return(err);
 out:
-	up_read(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock_shared(mapping);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 out_error:
@@ -6184,15 +6183,3 @@ out_error:
 	ext4_journal_stop(handle);
 	goto out;
 }
-
-vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	vm_fault_t ret;
-
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	ret = filemap_fault(vmf);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-
-	return ret;
-}