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

4 files changed, 9 insertions, 24 deletions

diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e512630cb63e..3be9dd6412b7 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -667,9 +667,6 @@ struct ext2_inode_info {
 	struct rw_semaphore xattr_sem;
 #endif
 	rwlock_t i_meta_lock;
-#ifdef CONFIG_FS_DAX
-	struct rw_semaphore dax_sem;
-#endif
 
 	/*
 	 * truncate_mutex is for serialising ext2_truncate() against
@@ -685,14 +682,6 @@ struct ext2_inode_info {
 #endif
 };
 
-#ifdef CONFIG_FS_DAX
-#define dax_sem_down_write(ext2_inode)	down_write(&(ext2_inode)->dax_sem)
-#define dax_sem_up_write(ext2_inode)	up_write(&(ext2_inode)->dax_sem)
-#else
-#define dax_sem_down_write(ext2_inode)
-#define dax_sem_up_write(ext2_inode)
-#endif
-
 /*
  * Inode dynamic state flags
  */
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index f98466acc672..eb97aa3d700e 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -81,7 +81,7 @@ out_unlock:
  *
  * mmap_lock (MM)
  *   sb_start_pagefault (vfs, freeze)
- *     ext2_inode_info->dax_sem
+ *     address_space->invalidate_lock
  *       address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
  *         ext2_inode_info->truncate_mutex
  *
@@ -91,7 +91,6 @@ out_unlock:
 static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
 	vm_fault_t ret;
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
@@ -100,11 +99,11 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vmf->vma->vm_file);
 	}
-	down_read(&ei->dax_sem);
+	filemap_invalidate_lock_shared(inode->i_mapping);
 
 	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, NULL, &ext2_iomap_ops);
 
-	up_read(&ei->dax_sem);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
 	if (write)
 		sb_end_pagefault(inode->i_sb);
 	return ret;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 04f0def0f5eb..333fa62661d5 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1178,7 +1178,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de
 		ext2_free_data(inode, p, q);
 }
 
-/* dax_sem must be held when calling this function */
+/* mapping->invalidate_lock must be held when calling this function */
 static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 {
 	__le32 *i_data = EXT2_I(inode)->i_data;
@@ -1195,7 +1195,7 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 	iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb);
 
 #ifdef CONFIG_FS_DAX
-	WARN_ON(!rwsem_is_locked(&ei->dax_sem));
+	WARN_ON(!rwsem_is_locked(&inode->i_mapping->invalidate_lock));
 #endif
 
 	n = ext2_block_to_path(inode, iblock, offsets, NULL);
@@ -1277,9 +1277,9 @@ static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
 	if (ext2_inode_is_fast_symlink(inode))
 		return;
 
-	dax_sem_down_write(EXT2_I(inode));
+	filemap_invalidate_lock(inode->i_mapping);
 	__ext2_truncate_blocks(inode, offset);
-	dax_sem_up_write(EXT2_I(inode));
+	filemap_invalidate_unlock(inode->i_mapping);
 }
 
 static int ext2_setsize(struct inode *inode, loff_t newsize)
@@ -1309,10 +1309,10 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	if (error)
 		return error;
 
-	dax_sem_down_write(EXT2_I(inode));
+	filemap_invalidate_lock(inode->i_mapping);
 	truncate_setsize(inode, newsize);
 	__ext2_truncate_blocks(inode, newsize);
-	dax_sem_up_write(EXT2_I(inode));
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	if (inode_needs_sync(inode)) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 21e09fbaa46f..987bcf32ed46 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -206,9 +206,6 @@ static void init_once(void *foo)
 	init_rwsem(&ei->xattr_sem);
 #endif
 	mutex_init(&ei->truncate_mutex);
-#ifdef CONFIG_FS_DAX
-	init_rwsem(&ei->dax_sem);
-#endif
 	inode_init_once(&ei->vfs_inode);
 }