\n

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEq1nRK9aeMoq1VSgcnJ2qBz9kQNkFAmEmTZcACgkQnJ2qBz9k
 QNkkmAgArW6XoF1CePds/ZaC9vfg/nk66/zVo0n+J8xXjMWAPxcKbWFfV0uWVixq
 yk4lcLV47a2Mu/B/1oLNd3vrSmhwU+srWqNwOFn1nv+lP/6wJqr8oztRHn/0L9Q3
 ZSRrukSejbQ6AvTL/WzTNnCjjCc2ne3Kyko6W41aU6uyJuzhSM32wbx7qlV6t54Z
 iint9OrB4gM0avLohNafTUq6I+tEGzBMNwpCG/tqCmkcvDcv3rTDVAnPSCTm0Tx2
 hdrYDcY/rLxo93pDBaW1rYA/fohR+mIVye6k2TjkPAL6T1x+rxeT5qnc+YijH5yF
 sFPDhlD+ZsfOLi8stWXLOJ+8+gLODg==
 =pDBR
 -----END PGP SIGNATURE-----

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

Documentation/filesystems/locking.rst

@@ -271,19 +271,19 @@ prototypes::
 locking rules:
 	All except set_page_dirty and freepage may block
 
-======================	======================== =========
-ops			PageLocked(page)	 i_rwsem
-======================	======================== =========
+======================	======================== =========	===============
+ops			PageLocked(page)	 i_rwsem	invalidate_lock
+======================	======================== =========	===============
 writepage:		yes, unlocks (see below)
-readpage:		yes, unlocks
+readpage:		yes, unlocks				shared
 writepages:
 set_page_dirty		no
-readahead:		yes, unlocks
-readpages:		no
+readahead:		yes, unlocks				shared
+readpages:		no					shared
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
-invalidatepage:		yes
+invalidatepage:		yes					exclusive
 releasepage:		yes
 freepage:		yes
 direct_IO:
@@ -295,7 +295,7 @@ is_partially_uptodate:	yes
 error_remove_page:	yes
 swap_activate:		no
 swap_deactivate:	no
-======================	======================== =========
+======================	======================== =========	===============
 
 ->write_begin(), ->write_end() and ->readpage() may be called from
 the request handler (/dev/loop).
@@ -378,7 +378,10 @@ keep it that way and don't breed new callers.
 ->invalidatepage() is called when the filesystem must attempt to drop
 some or all of the buffers from the page when it is being truncated. It
 returns zero on success. If ->invalidatepage is zero, the kernel uses
-block_invalidatepage() instead.
+block_invalidatepage() instead. The filesystem must exclusively acquire
+invalidate_lock before invalidating page cache in truncate / hole punch path
+(and thus calling into ->invalidatepage) to block races between page cache
+invalidation and page cache filling functions (fault, read, ...).
 
 ->releasepage() is called when the kernel is about to try to drop the
 buffers from the page in preparation for freeing it.  It returns zero to
@@ -506,6 +509,7 @@ prototypes::
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+	int (*iopoll) (struct kiocb *kiocb, bool spin);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
@@ -518,12 +522,6 @@ prototypes::
 	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
-	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
-			loff_t *);
-	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
-			loff_t *);
-	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
-			void __user *);
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
 			loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
@@ -536,6 +534,14 @@ prototypes::
 			size_t, unsigned int);
 	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int, loff_t, loff_t);
+	void (*show_fdinfo)(struct seq_file *m, struct file *f);
+	unsigned (*mmap_capabilities)(struct file *);
+	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
+			loff_t, size_t, unsigned int);
+	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
+			struct file *file_out, loff_t pos_out,
+			loff_t len, unsigned int remap_flags);
+	int (*fadvise)(struct file *, loff_t, loff_t, int);
 
 locking rules:
 	All may block.
@@ -570,6 +576,25 @@ in sys_read() and friends.
 the lease within the individual filesystem to record the result of the
 operation
 
+->fallocate implementation must be really careful to maintain page cache
+consistency when punching holes or performing other operations that invalidate
+page cache contents. Usually the filesystem needs to call
+truncate_inode_pages_range() to invalidate relevant range of the page cache.
+However the filesystem usually also needs to update its internal (and on disk)
+view of file offset -> disk block mapping. Until this update is finished, the
+filesystem needs to block page faults and reads from reloading now-stale page
+cache contents from the disk. Since VFS acquires mapping->invalidate_lock in
+shared mode when loading pages from disk (filemap_fault(), filemap_read(),
+readahead paths), the fallocate implementation must take the invalidate_lock to
+prevent reloading.
+
+->copy_file_range and ->remap_file_range implementations need to serialize
+against modifications of file data while the operation is running. For
+blocking changes through write(2) and similar operations inode->i_rwsem can be
+used. To block changes to file contents via a memory mapping during the
+operation, the filesystem must take mapping->invalidate_lock to coordinate
+with ->page_mkwrite.
+
 dquot_operations
 ================
 
@@ -627,11 +652,11 @@ pfn_mkwrite:	yes
 access:		yes
 =============	=========	===========================
 
-->fault() is called when a previously not present pte is about
-to be faulted in. The filesystem must find and return the page associated
-with the passed in "pgoff" in the vm_fault structure. If it is possible that
-the page may be truncated and/or invalidated, then the filesystem must lock
-the page, then ensure it is not already truncated (the page lock will block
+->fault() is called when a previously not present pte is about to be faulted
+in. The filesystem must find and return the page associated with the passed in
+"pgoff" in the vm_fault structure. If it is possible that the page may be
+truncated and/or invalidated, then the filesystem must lock invalidate_lock,
+then ensure the page is not already truncated (invalidate_lock will block
 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 locked. The VM will unlock the page.
 
@@ -644,12 +669,14 @@ page table entry. Pointer to entry associated with the page is passed in
 "pte" field in vm_fault structure. Pointers to entries for other offsets
 should be calculated relative to "pte".
 
-->page_mkwrite() is called when a previously read-only pte is
-about to become writeable. The filesystem again must ensure that there are
-no truncate/invalidate races, and then return with the page locked. If
-the page has been truncated, the filesystem should not look up a new page
-like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
-will cause the VM to retry the fault.
+->page_mkwrite() is called when a previously read-only pte is about to become
+writeable. The filesystem again must ensure that there are no
+truncate/invalidate races or races with operations such as ->remap_file_range
+or ->copy_file_range, and then return with the page locked. Usually
+mapping->invalidate_lock is suitable for proper serialization. If the page has
+been truncated, the filesystem should not look up a new page like the ->fault()
+handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to
+retry the fault.
 
 ->pfn_mkwrite() is the same as page_mkwrite but when the pte is
 VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is

fs/ceph/addr.c

@@ -1395,9 +1395,11 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_SIGBUS;
 	} else {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page = find_or_create_page(mapping, 0,
-						mapping_gfp_constraint(mapping,
-						~__GFP_FS));
+		struct page *page;
+
+		filemap_invalidate_lock_shared(mapping);
+		page = find_or_create_page(mapping, 0,
+				mapping_gfp_constraint(mapping, ~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out_inline;
@@ -1418,6 +1420,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		vmf->page = page;
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
+		filemap_invalidate_unlock_shared(mapping);
 		dout("filemap_fault %p %llu read inline data ret %x\n",
 		     inode, off, ret);
 	}

fs/ceph/file.c

@@ -2088,6 +2088,7 @@ static long ceph_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		goto unlock;
 
+	filemap_invalidate_lock(inode->i_mapping);
 	ceph_zero_pagecache_range(inode, offset, length);
 	ret = ceph_zero_objects(inode, offset, length);
 
@@ -2100,6 +2101,7 @@ static long ceph_fallocate(struct file *file, int mode,
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
 	}
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	ceph_put_cap_refs(ci, got);
 unlock:

fs/cifs/smb2ops.c

@@ -3590,6 +3590,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	filemap_invalidate_lock(inode->i_mapping);
 	/*
 	 * We implement the punch hole through ioctl, so we need remove the page
 	 * caches first, otherwise the data may be inconsistent with the server.
@@ -3607,6 +3608,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			sizeof(struct file_zero_data_information),
 			CIFSMaxBufSize, NULL, NULL);
 	free_xid(xid);
+	filemap_invalidate_unlock(inode->i_mapping);
 	return rc;
 }
 

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
  */

fs/ext2/file.c

@@ -81,7 +81,7 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
  *
  * 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 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 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;

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)) {

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);
 }
 

fs/ext4/ext4.h

@@ -1086,15 +1086,6 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
-	/*
-	 * i_mmap_sem is for serializing page faults with truncate / punch hole
-	 * operations. We have to make sure that new page cannot be faulted in
-	 * a section of the inode that is being punched. We cannot easily use
-	 * i_data_sem for this since we need protection for the whole punch
-	 * operation and i_data_sem ranks below transaction start so we have
-	 * to occasionally drop it.
-	 */
-	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -2972,7 +2963,6 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
-extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
 extern void ext4_da_release_space(struct inode *inode, int to_free);

fs/ext4/extents.c

@@ -4474,6 +4474,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 			    loff_t len, int mode)
 {
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	handle_t *handle = NULL;
 	unsigned int max_blocks;
 	loff_t new_size = 0;
@@ -4560,17 +4561,17 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * 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) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(mapping);
 			goto out_mutex;
 		}
 
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(mapping);
 			goto out_mutex;
 		}
 		/* Now release the pages and zero block aligned part of pages */
@@ -4579,7 +4580,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(mapping);
 		if (ret)
 			goto out_mutex;
 	}
@@ -5221,6 +5222,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	ext4_lblk_t punch_start, punch_stop;
 	handle_t *handle;
 	unsigned int credits;
@@ -5274,7 +5276,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * 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)
@@ -5289,15 +5291,15 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Write tail of the last page before removed range since it will get
 	 * removed from the page cache below.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	ret = filemap_write_and_wait_range(mapping, ioffset, offset);
 	if (ret)
 		goto out_mmap;
 	/*
 	 * Write data that will be shifted to preserve them when discarding
 	 * page cache below. We are also protected from pages becoming dirty
-	 * by i_mmap_sem.
+	 * by i_rwsem and invalidate_lock.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+	ret = filemap_write_and_wait_range(mapping, offset + len,
 					   LLONG_MAX);
 	if (ret)
 		goto out_mmap;
@@ -5350,7 +5352,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5367,6 +5369,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	handle_t *handle;
 	struct ext4_ext_path *path;
 	struct ext4_extent *extent;
@@ -5425,7 +5428,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * 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)
@@ -5526,7 +5529,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 out_mutex:
 	inode_unlock(inode);
 	return ret;

fs/ext4/file.c

@@ -704,22 +704,23 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 	 */
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	pfn_t pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vmf->vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock_shared(mapping);
 retry:
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 					       EXT4_DATA_TRANS_BLOCKS(sb));
 		if (IS_ERR(handle)) {
-			up_read(&EXT4_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock_shared(mapping);
 			sb_end_pagefault(sb);
 			return VM_FAULT_SIGBUS;
 		}
 	} else {
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock_shared(mapping);
 	}
 	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
 	if (write) {
@@ -731,10 +732,10 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 		/* Handling synchronous page fault? */
 		if (result & VM_FAULT_NEEDDSYNC)
 			result = dax_finish_sync_fault(vmf, pe_size, pfn);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock_shared(mapping);
 		sb_end_pagefault(sb);
 	} else {
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock_shared(mapping);
 	}
 
 	return result;
@@ -756,7 +757,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= ext4_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };

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 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 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 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	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;
-}

fs/ext4/ioctl.c

@@ -148,7 +148,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		goto journal_err_out;
 	}
 
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 	err = filemap_write_and_wait(inode->i_mapping);
 	if (err)
 		goto err_out;
@@ -256,7 +256,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 journal_err_out:
 	unlock_two_nondirectories(inode, inode_bl);
 	iput(inode_bl);

fs/ext4/super.c

@@ -90,12 +90,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
 /*
  * Lock ordering
  *
- * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
- * i_mmap_rwsem (inode->i_mmap_rwsem)!
- *
  * page fault path:
- * mmap_lock -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
- *   page lock -> i_data_sem (rw)
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
+ *   -> page lock -> i_data_sem (rw)
  *
  * buffered write path:
  * sb_start_write -> i_mutex -> mmap_lock
@@ -103,8 +100,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
  *   i_data_sem (rw)
  *
  * truncate:
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> transaction start ->
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
+ *   page lock
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
  *   i_data_sem (rw)
  *
  * direct IO:
@@ -1360,7 +1358,6 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
-	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 	ext4_fc_init_inode(&ei->vfs_inode);
 }

fs/ext4/truncate.h

@@ -11,14 +11,16 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	struct address_space *mapping = inode->i_mapping;
+
 	/*
 	 * We don't need to call ext4_break_layouts() because the blocks we
 	 * are truncating were never visible to userspace.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
-	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	filemap_invalidate_lock(mapping);
+	truncate_inode_pages(mapping, inode->i_size);
 	ext4_truncate(inode);
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 }
 
 /*

fs/f2fs/data.c

@@ -3187,12 +3187,12 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 	/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
 	if (to > i_size && !f2fs_verity_in_progress(inode)) {
 		down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-		down_write(&F2FS_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock(mapping);
 
 		truncate_pagecache(inode, i_size);
 		f2fs_truncate_blocks(inode, i_size, true);
 
-		up_write(&F2FS_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(mapping);
 		up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	}
 }
@@ -3852,7 +3852,7 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
 	int ret = 0;
 
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	set_inode_flag(inode, FI_ALIGNED_WRITE);
 
@@ -3894,7 +3894,7 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
 	clear_inode_flag(inode, FI_DO_DEFRAG);
 	clear_inode_flag(inode, FI_ALIGNED_WRITE);
 
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
 	return ret;

fs/f2fs/f2fs.h

@@ -754,7 +754,6 @@ struct f2fs_inode_info {
 
 	/* avoid racing between foreground op and gc */
 	struct rw_semaphore i_gc_rwsem[2];
-	struct rw_semaphore i_mmap_sem;
 	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
 
 	int i_extra_isize;		/* size of extra space located in i_addr */

fs/f2fs/file.c

@@ -38,10 +38,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	vm_fault_t ret;
 
-	down_read(&F2FS_I(inode)->i_mmap_sem);
 	ret = filemap_fault(vmf);
-	up_read(&F2FS_I(inode)->i_mmap_sem);
-
 	if (!ret)
 		f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
 							F2FS_BLKSIZE);
@@ -101,7 +98,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
 	file_update_time(vmf->vma->vm_file);
-	down_read(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock_shared(inode->i_mapping);
 	lock_page(page);
 	if (unlikely(page->mapping != inode->i_mapping ||
 			page_offset(page) > i_size_read(inode) ||
@@ -159,7 +156,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	trace_f2fs_vm_page_mkwrite(page, DATA);
 out_sem:
-	up_read(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
 err:
@@ -940,7 +937,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		}
 
 		down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-		down_write(&F2FS_I(inode)->i_mmap_sem);
+		filemap_invalidate_lock(inode->i_mapping);
 
 		truncate_setsize(inode, attr->ia_size);
 
@@ -950,7 +947,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		 * do not trim all blocks after i_size if target size is
 		 * larger than i_size.
 		 */
-		up_write(&F2FS_I(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(inode->i_mapping);
 		up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		if (err)
 			return err;
@@ -1095,7 +1092,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 			blk_end = (loff_t)pg_end << PAGE_SHIFT;
 
 			down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-			down_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_lock(mapping);
 
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
@@ -1104,7 +1101,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 			ret = f2fs_truncate_hole(inode, pg_start, pg_end);
 			f2fs_unlock_op(sbi);
 
-			up_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(mapping);
 			up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		}
 	}
@@ -1339,7 +1336,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
 
 	/* avoid gc operation during block exchange */
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	f2fs_lock_op(sbi);
 	f2fs_drop_extent_tree(inode);
@@ -1347,7 +1344,7 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
 	ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
 	f2fs_unlock_op(sbi);
 
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	return ret;
 }
@@ -1378,13 +1375,13 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		return ret;
 
 	/* write out all moved pages, if possible */
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 	filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
 	truncate_pagecache(inode, offset);
 
 	new_size = i_size_read(inode) - len;
 	ret = f2fs_truncate_blocks(inode, new_size, true);
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
 	return ret;
@@ -1484,7 +1481,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 			pgoff_t end;
 
 			down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-			down_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_lock(mapping);
 
 			truncate_pagecache_range(inode,
 				(loff_t)index << PAGE_SHIFT,
@@ -1496,7 +1493,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 			ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
 			if (ret) {
 				f2fs_unlock_op(sbi);
-				up_write(&F2FS_I(inode)->i_mmap_sem);
+				filemap_invalidate_unlock(mapping);
 				up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 				goto out;
 			}
@@ -1508,7 +1505,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 			f2fs_put_dnode(&dn);
 
 			f2fs_unlock_op(sbi);
-			up_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(mapping);
 			up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
 			f2fs_balance_fs(sbi, dn.node_changed);
@@ -1543,6 +1540,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct address_space *mapping = inode->i_mapping;
 	pgoff_t nr, pg_start, pg_end, delta, idx;
 	loff_t new_size;
 	int ret = 0;
@@ -1565,14 +1563,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	f2fs_balance_fs(sbi, true);
 
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(mapping);
 	ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 	if (ret)
 		return ret;
 
 	/* write out all dirty pages from offset */
-	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+	ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
 	if (ret)
 		return ret;
 
@@ -1583,7 +1581,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	/* avoid gc operation during block exchange */
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(mapping);
 	truncate_pagecache(inode, offset);
 
 	while (!ret && idx > pg_start) {
@@ -1599,14 +1597,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 					idx + delta, nr, false);
 		f2fs_unlock_op(sbi);
 	}
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
 	/* write out all moved pages, if possible */
-	down_write(&F2FS_I(inode)->i_mmap_sem);
-	filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+	filemap_invalidate_lock(mapping);
+	filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
 	truncate_pagecache(inode, offset);
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
@@ -3440,7 +3438,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 		goto out;
 
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
@@ -3476,7 +3474,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	}
 
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 out:
 	inode_unlock(inode);
 
@@ -3593,7 +3591,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	}
 
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
@@ -3629,7 +3627,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	}
 
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	if (ret >= 0) {
 		clear_inode_flag(inode, FI_COMPRESS_RELEASED);
@@ -3748,7 +3746,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 		goto err;
 
 	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-	down_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_lock(mapping);
 
 	ret = filemap_write_and_wait_range(mapping, range.start,
 			to_end ? LLONG_MAX : end_addr - 1);
@@ -3835,7 +3833,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 		ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
 				prev_block, len, range.flags);
 out:
-	up_write(&F2FS_I(inode)->i_mmap_sem);
+	filemap_invalidate_unlock(mapping);
 	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 err:
 	inode_unlock(inode);
@@ -4313,9 +4311,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		/* if we couldn't write data, we should deallocate blocks. */
 		if (preallocated && i_size_read(inode) < target_size) {
 			down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-			down_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_lock(inode->i_mapping);
 			f2fs_truncate(inode);
-			up_write(&F2FS_I(inode)->i_mmap_sem);
+			filemap_invalidate_unlock(inode->i_mapping);
 			up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		}
 

fs/f2fs/super.c

@@ -1289,7 +1289,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	mutex_init(&fi->inmem_lock);
 	init_rwsem(&fi->i_gc_rwsem[READ]);
 	init_rwsem(&fi->i_gc_rwsem[WRITE]);
-	init_rwsem(&fi->i_mmap_sem);
 	init_rwsem(&fi->i_xattr_sem);
 
 	/* Will be used by directory only */

fs/fuse/dax.c

@@ -444,12 +444,12 @@ static int fuse_setup_new_dax_mapping(struct inode *inode, loff_t pos,
 	/*
 	 * Can't do inline reclaim in fault path. We call
 	 * dax_layout_busy_page() before we free a range. And
-	 * fuse_wait_dax_page() drops fi->i_mmap_sem lock and requires it.
-	 * In fault path we enter with fi->i_mmap_sem held and can't drop
-	 * it. Also in fault path we hold fi->i_mmap_sem shared and not
-	 * exclusive, so that creates further issues with fuse_wait_dax_page().
-	 * Hence return -EAGAIN and fuse_dax_fault() will wait for a memory
-	 * range to become free and retry.
+	 * fuse_wait_dax_page() drops mapping->invalidate_lock and requires it.
+	 * In fault path we enter with mapping->invalidate_lock held and can't
+	 * drop it. Also in fault path we hold mapping->invalidate_lock shared
+	 * and not exclusive, so that creates further issues with
+	 * fuse_wait_dax_page().  Hence return -EAGAIN and fuse_dax_fault()
+	 * will wait for a memory range to become free and retry.
 	 */
 	if (flags & IOMAP_FAULT) {
 		alloc_dmap = alloc_dax_mapping(fcd);
@@ -513,7 +513,7 @@ static int fuse_upgrade_dax_mapping(struct inode *inode, loff_t pos,
 	down_write(&fi->dax->sem);
 	node = interval_tree_iter_first(&fi->dax->tree, idx, idx);
 
-	/* We are holding either inode lock or i_mmap_sem, and that should
+	/* We are holding either inode lock or invalidate_lock, and that should
 	 * ensure that dmap can't be truncated. We are holding a reference
 	 * on dmap and that should make sure it can't be reclaimed. So dmap
 	 * should still be there in tree despite the fact we dropped and
@@ -660,14 +660,12 @@ static const struct iomap_ops fuse_iomap_ops = {
 
 static void fuse_wait_dax_page(struct inode *inode)
 {
-	struct fuse_inode *fi = get_fuse_inode(inode);
-
-	up_write(&fi->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	schedule();
-	down_write(&fi->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 }
 
-/* Should be called with fi->i_mmap_sem lock held exclusively */
+/* Should be called with mapping->invalidate_lock held exclusively */
 static int __fuse_dax_break_layouts(struct inode *inode, bool *retry,
 				    loff_t start, loff_t end)
 {
@@ -813,18 +811,18 @@ static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf,
 	 * we do not want any read/write/mmap to make progress and try
 	 * to populate page cache or access memory we are trying to free.
 	 */
-	down_read(&get_fuse_inode(inode)->i_mmap_sem);
+	filemap_invalidate_lock_shared(inode->i_mapping);
 	ret = dax_iomap_fault(vmf, pe_size, &pfn, &error, &fuse_iomap_ops);
 	if ((ret & VM_FAULT_ERROR) && error == -EAGAIN) {
 		error = 0;
 		retry = true;
-		up_read(&get_fuse_inode(inode)->i_mmap_sem);
+		filemap_invalidate_unlock_shared(inode->i_mapping);
 		goto retry;
 	}
 
 	if (ret & VM_FAULT_NEEDDSYNC)
 		ret = dax_finish_sync_fault(vmf, pe_size, pfn);
-	up_read(&get_fuse_inode(inode)->i_mmap_sem);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	if (write)
 		sb_end_pagefault(sb);
@@ -960,7 +958,7 @@ inode_inline_reclaim_one_dmap(struct fuse_conn_dax *fcd, struct inode *inode,
 	int ret;
 	struct interval_tree_node *node;
 
-	down_write(&fi->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	/* Lookup a dmap and corresponding file offset to reclaim. */
 	down_read(&fi->dax->sem);
@@ -1021,7 +1019,7 @@ inode_inline_reclaim_one_dmap(struct fuse_conn_dax *fcd, struct inode *inode,
 out_write_dmap_sem:
 	up_write(&fi->dax->sem);
 out_mmap_sem:
-	up_write(&fi->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	return dmap;
 }
 
@@ -1050,10 +1048,10 @@ alloc_dax_mapping_reclaim(struct fuse_conn_dax *fcd, struct inode *inode)
 		 * had a reference or some other temporary failure,
 		 * Try again. We want to give up inline reclaim only
 		 * if there is no range assigned to this node. Otherwise
-		 * if a deadlock is possible if we sleep with fi->i_mmap_sem
-		 * held and worker to free memory can't make progress due
-		 * to unavailability of fi->i_mmap_sem lock. So sleep
-		 * only if fi->dax->nr=0
+		 * if a deadlock is possible if we sleep with
+		 * mapping->invalidate_lock held and worker to free memory
+		 * can't make progress due to unavailability of
+		 * mapping->invalidate_lock.  So sleep only if fi->dax->nr=0
 		 */
 		if (retry)
 			continue;
@@ -1061,8 +1059,8 @@ alloc_dax_mapping_reclaim(struct fuse_conn_dax *fcd, struct inode *inode)
 		 * There are no mappings which can be reclaimed. Wait for one.
 		 * We are not holding fi->dax->sem. So it is possible
 		 * that range gets added now. But as we are not holding
-		 * fi->i_mmap_sem, worker should still be able to free up
-		 * a range and wake us up.
+		 * mapping->invalidate_lock, worker should still be able to
+		 * free up a range and wake us up.
 		 */
 		if (!fi->dax->nr && !(fcd->nr_free_ranges > 0)) {
 			if (wait_event_killable_exclusive(fcd->range_waitq,
@@ -1108,7 +1106,7 @@ static int lookup_and_reclaim_dmap_locked(struct fuse_conn_dax *fcd,
 /*
  * Free a range of memory.
  * Locking:
- * 1. Take fi->i_mmap_sem to block dax faults.
+ * 1. Take mapping->invalidate_lock to block dax faults.
  * 2. Take fi->dax->sem to protect interval tree and also to make sure
  *    read/write can not reuse a dmap which we might be freeing.
  */
@@ -1122,7 +1120,7 @@ static int lookup_and_reclaim_dmap(struct fuse_conn_dax *fcd,
 	loff_t dmap_start = start_idx << FUSE_DAX_SHIFT;
 	loff_t dmap_end = (dmap_start + FUSE_DAX_SZ) - 1;
 
-	down_write(&fi->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 	ret = fuse_dax_break_layouts(inode, dmap_start, dmap_end);
 	if (ret) {
 		pr_debug("virtio_fs: fuse_dax_break_layouts() failed. err=%d\n",
@@ -1134,7 +1132,7 @@ static int lookup_and_reclaim_dmap(struct fuse_conn_dax *fcd,
 	ret = lookup_and_reclaim_dmap_locked(fcd, inode, start_idx);
 	up_write(&fi->dax->sem);
 out_mmap_sem:
-	up_write(&fi->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 	return ret;
 }
 

fs/fuse/dir.c

@@ -1556,6 +1556,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	struct fuse_conn *fc = fm->fc;
 	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct address_space *mapping = inode->i_mapping;
 	FUSE_ARGS(args);
 	struct fuse_setattr_in inarg;
 	struct fuse_attr_out outarg;
@@ -1580,11 +1581,11 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 	}
 
 	if (FUSE_IS_DAX(inode) && is_truncate) {
-		down_write(&fi->i_mmap_sem);
+		filemap_invalidate_lock(mapping);
 		fault_blocked = true;
 		err = fuse_dax_break_layouts(inode, 0, 0);
 		if (err) {
-			up_write(&fi->i_mmap_sem);
+			filemap_invalidate_unlock(mapping);
 			return err;
 		}
 	}
@@ -1694,13 +1695,13 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 	if ((is_truncate || !is_wb) &&
 	    S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
 		truncate_pagecache(inode, outarg.attr.size);
-		invalidate_inode_pages2(inode->i_mapping);
+		invalidate_inode_pages2(mapping);
 	}
 
 	clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
 out:
 	if (fault_blocked)
-		up_write(&fi->i_mmap_sem);
+		filemap_invalidate_unlock(mapping);
 
 	return 0;
 
@@ -1711,7 +1712,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 	clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
 
 	if (fault_blocked)
-		up_write(&fi->i_mmap_sem);
+		filemap_invalidate_unlock(mapping);
 	return err;
 }
 

fs/fuse/file.c

@@ -243,7 +243,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 	}
 
 	if (dax_truncate) {
-		down_write(&get_fuse_inode(inode)->i_mmap_sem);
+		filemap_invalidate_lock(inode->i_mapping);
 		err = fuse_dax_break_layouts(inode, 0, 0);
 		if (err)
 			goto out;
@@ -255,7 +255,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 
 out:
 	if (dax_truncate)
-		up_write(&get_fuse_inode(inode)->i_mmap_sem);
+		filemap_invalidate_unlock(inode->i_mapping);
 
 	if (is_wb_truncate | dax_truncate) {
 		fuse_release_nowrite(inode);
@@ -2920,7 +2920,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 	if (lock_inode) {
 		inode_lock(inode);
 		if (block_faults) {
-			down_write(&fi->i_mmap_sem);
+			filemap_invalidate_lock(inode->i_mapping);
 			err = fuse_dax_break_layouts(inode, 0, 0);
 			if (err)
 				goto out;
@@ -2976,7 +2976,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
 
 	if (block_faults)
-		up_write(&fi->i_mmap_sem);
+		filemap_invalidate_unlock(inode->i_mapping);
 
 	if (lock_inode)
 		inode_unlock(inode);
@@ -3045,7 +3045,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	 * modifications.  Yet this does give less guarantees than if the
 	 * copying was performed with write(2).
 	 *
-	 * To fix this a i_mmap_sem style lock could be used to prevent new
+	 * To fix this a mapping->invalidate_lock could be used to prevent new
 	 * faults while the copy is ongoing.
 	 */
 	err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1);

fs/fuse/fuse_i.h

@@ -149,13 +149,6 @@ struct fuse_inode {
 	/** Lock to protect write related fields */
 	spinlock_t lock;
 
-	/**
-	 * Can't take inode lock in fault path (leads to circular dependency).
-	 * Introduce another semaphore which can be taken in fault path and
-	 * then other filesystem paths can take this to block faults.
-	 */
-	struct rw_semaphore i_mmap_sem;
-
 #ifdef CONFIG_FUSE_DAX
 	/*
 	 * Dax specific inode data

fs/fuse/inode.c

@@ -85,7 +85,6 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	fi->orig_ino = 0;
 	fi->state = 0;
 	mutex_init(&fi->mutex);
-	init_rwsem(&fi->i_mmap_sem);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
 	if (!fi->forget)

fs/inode.c

@@ -190,6 +190,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
 	mapping->writeback_index = 0;
+	__init_rwsem(&mapping->invalidate_lock, "mapping.invalidate_lock",
+		     &sb->s_type->invalidate_lock_key);
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */

fs/xfs/xfs_bmap_util.c

@@ -1626,7 +1626,6 @@ xfs_swap_extents(
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
-	int			lock_flags;
 	uint64_t		f;
 	int			resblks = 0;
 	unsigned int		flags = 0;
@@ -1638,8 +1637,8 @@ xfs_swap_extents(
 	 * do the rest of the checks.
 	 */
 	lock_two_nondirectories(VFS_I(ip), VFS_I(tip));
-	lock_flags = XFS_MMAPLOCK_EXCL;
-	xfs_lock_two_inodes(ip, XFS_MMAPLOCK_EXCL, tip, XFS_MMAPLOCK_EXCL);
+	filemap_invalidate_lock_two(VFS_I(ip)->i_mapping,
+				    VFS_I(tip)->i_mapping);
 
 	/* Verify that both files have the same format */
 	if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
@@ -1711,7 +1710,6 @@ xfs_swap_extents(
 	 * or cancel will unlock the inodes from this point onwards.
 	 */
 	xfs_lock_two_inodes(ip, XFS_ILOCK_EXCL, tip, XFS_ILOCK_EXCL);
-	lock_flags |= XFS_ILOCK_EXCL;
 	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_ijoin(tp, tip, 0);
 
@@ -1830,13 +1828,16 @@ xfs_swap_extents(
 	trace_xfs_swap_extent_after(ip, 0);
 	trace_xfs_swap_extent_after(tip, 1);
 
+out_unlock_ilock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(tip, XFS_ILOCK_EXCL);
 out_unlock:
-	xfs_iunlock(ip, lock_flags);
-	xfs_iunlock(tip, lock_flags);
+	filemap_invalidate_unlock_two(VFS_I(ip)->i_mapping,
+				      VFS_I(tip)->i_mapping);
 	unlock_two_nondirectories(VFS_I(ip), VFS_I(tip));
 	return error;
 
 out_trans_cancel:
 	xfs_trans_cancel(tp);
-	goto out_unlock;
+	goto out_unlock_ilock;
 }

fs/xfs/xfs_file.c

@@ -1302,7 +1302,7 @@ xfs_file_llseek(
  *
  * mmap_lock (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmaplock (XFS - truncate serialisation)
+ *     invalidate_lock (vfs/XFS_MMAPLOCK - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1323,24 +1323,27 @@ __xfs_filemap_fault(
 		file_update_time(vmf->vma->vm_file);
 	}
 
-	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
 		pfn_t pfn;
 
+		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
 				(write_fault && !vmf->cow_page) ?
 				 &xfs_direct_write_iomap_ops :
 				 &xfs_read_iomap_ops);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
+		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	} else {
-		if (write_fault)
+		if (write_fault) {
+			xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 			ret = iomap_page_mkwrite(vmf,
 					&xfs_buffered_write_iomap_ops);
-		else
+			xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+		} else {
 			ret = filemap_fault(vmf);
 		}
-	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	}
 
 	if (write_fault)
 		sb_end_pagefault(inode->i_sb);

fs/xfs/xfs_inode.c

@@ -132,7 +132,7 @@ xfs_ilock_attr_map_shared(
 
 /*
  * In addition to i_rwsem in the VFS inode, the xfs inode contains 2
- * multi-reader locks: i_mmap_lock and the i_lock.  This routine allows
+ * multi-reader locks: invalidate_lock and the i_lock.  This routine allows
  * various combinations of the locks to be obtained.
  *
  * The 3 locks should always be ordered so that the IO lock is obtained first,
@@ -140,23 +140,23 @@ xfs_ilock_attr_map_shared(
  *
  * Basic locking order:
  *
- * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
+ * i_rwsem -> invalidate_lock -> page_lock -> i_ilock
  *
  * mmap_lock locking order:
  *
  * i_rwsem -> page lock -> mmap_lock
- * mmap_lock -> i_mmap_lock -> page_lock
+ * mmap_lock -> invalidate_lock -> page_lock
  *
  * The difference in mmap_lock locking order mean that we cannot hold the
- * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
- * fault in pages during copy in/out (for buffered IO) or require the mmap_lock
- * in get_user_pages() to map the user pages into the kernel address space for
- * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
- * page faults already hold the mmap_lock.
+ * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths
+ * can fault in pages during copy in/out (for buffered IO) or require the
+ * mmap_lock in get_user_pages() to map the user pages into the kernel address
+ * space for direct IO. Similarly the i_rwsem cannot be taken inside a page
+ * fault because page faults already hold the mmap_lock.
  *
  * Hence to serialise fully against both syscall and mmap based IO, we need to
- * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
- * taken in places where we need to invalidate the page cache in a race
+ * take both the i_rwsem and the invalidate_lock. These locks should *only* be
+ * both taken in places where we need to invalidate the page cache in a race
  * free manner (e.g. truncate, hole punch and other extent manipulation
  * functions).
  */
@@ -188,10 +188,13 @@ xfs_ilock(
 				 XFS_IOLOCK_DEP(lock_flags));
 	}
 
-	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
-	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
+	if (lock_flags & XFS_MMAPLOCK_EXCL) {
+		down_write_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+				  XFS_MMAPLOCK_DEP(lock_flags));
+	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
+		down_read_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+				 XFS_MMAPLOCK_DEP(lock_flags));
+	}
 
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
@@ -240,10 +243,10 @@ xfs_ilock_nowait(
 	}
 
 	if (lock_flags & XFS_MMAPLOCK_EXCL) {
-		if (!mrtryupdate(&ip->i_mmaplock))
+		if (!down_write_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
 			goto out_undo_iolock;
 	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
-		if (!mrtryaccess(&ip->i_mmaplock))
+		if (!down_read_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
 			goto out_undo_iolock;
 	}
 
@@ -258,9 +261,9 @@ xfs_ilock_nowait(
 
 out_undo_mmaplock:
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrunlock_excl(&ip->i_mmaplock);
+		up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
 out_undo_iolock:
 	if (lock_flags & XFS_IOLOCK_EXCL)
 		up_write(&VFS_I(ip)->i_rwsem);
@@ -307,9 +310,9 @@ xfs_iunlock(
 		up_read(&VFS_I(ip)->i_rwsem);
 
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrunlock_excl(&ip->i_mmaplock);
+		up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
 
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrunlock_excl(&ip->i_lock);
@@ -335,7 +338,7 @@ xfs_ilock_demote(
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrdemote(&ip->i_lock);
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrdemote(&ip->i_mmaplock);
+		downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	if (lock_flags & XFS_IOLOCK_EXCL)
 		downgrade_write(&VFS_I(ip)->i_rwsem);
 
@@ -343,9 +346,29 @@ xfs_ilock_demote(
 }
 
 #if defined(DEBUG) || defined(XFS_WARN)
-int
+static inline bool
+__xfs_rwsem_islocked(
+	struct rw_semaphore	*rwsem,
+	bool			shared)
+{
+	if (!debug_locks)
+		return rwsem_is_locked(rwsem);
+
+	if (!shared)
+		return lockdep_is_held_type(rwsem, 0);
+
+	/*
+	 * We are checking that the lock is held at least in shared
+	 * mode but don't care that it might be held exclusively
+	 * (i.e. shared | excl). Hence we check if the lock is held
+	 * in any mode rather than an explicit shared mode.
+	 */
+	return lockdep_is_held_type(rwsem, -1);
+}
+
+bool
 xfs_isilocked(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	uint			lock_flags)
 {
 	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
@@ -355,20 +378,17 @@ xfs_isilocked(
 	}
 
 	if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
-		if (!(lock_flags & XFS_MMAPLOCK_SHARED))
-			return !!ip->i_mmaplock.mr_writer;
-		return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
+		return __xfs_rwsem_islocked(&VFS_I(ip)->i_rwsem,
+				(lock_flags & XFS_IOLOCK_SHARED));
 	}
 
-	if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
-		if (!(lock_flags & XFS_IOLOCK_SHARED))
-			return !debug_locks ||
-				lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0);
-		return rwsem_is_locked(&VFS_I(ip)->i_rwsem);
+	if (lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) {
+		return __xfs_rwsem_islocked(&VFS_I(ip)->i_rwsem,
+				(lock_flags & XFS_IOLOCK_SHARED));
 	}
 
 	ASSERT(0);
-	return 0;
+	return false;
 }
 #endif
 
@@ -532,12 +552,10 @@ xfs_lock_inodes(
 }
 
 /*
- * xfs_lock_two_inodes() can only be used to lock one type of lock at a time -
- * the mmaplock or the ilock, but not more than one type at a time. If we lock
- * more than one at a time, lockdep will report false positives saying we have
- * violated locking orders.  The iolock must be double-locked separately since
- * we use i_rwsem for that.  We now support taking one lock EXCL and the other
- * SHARED.
+ * xfs_lock_two_inodes() can only be used to lock ilock. The iolock and
+ * mmaplock must be double-locked separately since we use i_rwsem and
+ * invalidate_lock for that. We now support taking one lock EXCL and the
+ * other SHARED.
  */
 void
 xfs_lock_two_inodes(
@@ -555,15 +573,8 @@ xfs_lock_two_inodes(
 	ASSERT(hweight32(ip1_mode) == 1);
 	ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
 	ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
-	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
-	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
-	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
-	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
-	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
-	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
-	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
-	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
-
+	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)));
+	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)));
 	ASSERT(ip0->i_ino != ip1->i_ino);
 
 	if (ip0->i_ino > ip1->i_ino) {
@@ -3741,11 +3752,8 @@ xfs_ilock2_io_mmap(
 	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
 	if (ret)
 		return ret;
-	if (ip1 == ip2)
-		xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
-	else
-		xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
-				    ip2, XFS_MMAPLOCK_EXCL);
+	filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
+				    VFS_I(ip2)->i_mapping);
 	return 0;
 }
 
@@ -3755,12 +3763,9 @@ xfs_iunlock2_io_mmap(
 	struct xfs_inode	*ip1,
 	struct xfs_inode	*ip2)
 {
-	bool			same_inode = (ip1 == ip2);
-
-	xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
-	if (!same_inode)
-		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+	filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
+				      VFS_I(ip2)->i_mapping);
 	inode_unlock(VFS_I(ip2));
-	if (!same_inode)
+	if (ip1 != ip2)
 		inode_unlock(VFS_I(ip1));
 }

fs/xfs/xfs_inode.h

@@ -40,7 +40,6 @@ typedef struct xfs_inode {
 	/* Transaction and locking information. */
 	struct xfs_inode_log_item *i_itemp;	/* logging information */
 	mrlock_t		i_lock;		/* inode lock */
-	mrlock_t		i_mmaplock;	/* inode mmap IO lock */
 	atomic_t		i_pincount;	/* inode pin count */
 
 	/*
@@ -410,7 +409,7 @@ void		xfs_ilock(xfs_inode_t *, uint);
 int		xfs_ilock_nowait(xfs_inode_t *, uint);
 void		xfs_iunlock(xfs_inode_t *, uint);
 void		xfs_ilock_demote(xfs_inode_t *, uint);
-int		xfs_isilocked(xfs_inode_t *, uint);
+bool		xfs_isilocked(struct xfs_inode *, uint);
 uint		xfs_ilock_data_map_shared(struct xfs_inode *);
 uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
 

fs/xfs/xfs_super.c

@@ -709,8 +709,6 @@ xfs_fs_inode_init_once(
 	atomic_set(&ip->i_pincount, 0);
 	spin_lock_init(&ip->i_flags_lock);
 
-	mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
-		     "xfsino", ip->i_ino);
 	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
 		     "xfsino", ip->i_ino);
 }

fs/zonefs/super.c

@@ -462,7 +462,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 	inode_dio_wait(inode);
 
 	/* Serialize against page faults */
-	down_write(&zi->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	/* Serialize against zonefs_iomap_begin() */
 	mutex_lock(&zi->i_truncate_mutex);
@@ -500,7 +500,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 
 unlock:
 	mutex_unlock(&zi->i_truncate_mutex);
-	up_write(&zi->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	return ret;
 }
@@ -575,18 +575,6 @@ static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
 	return ret;
 }
 
-static vm_fault_t zonefs_filemap_fault(struct vm_fault *vmf)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(file_inode(vmf->vma->vm_file));
-	vm_fault_t ret;
-
-	down_read(&zi->i_mmap_sem);
-	ret = filemap_fault(vmf);
-	up_read(&zi->i_mmap_sem);
-
-	return ret;
-}
-
 static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -607,16 +595,16 @@ static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 	file_update_time(vmf->vma->vm_file);
 
 	/* Serialize against truncates */
-	down_read(&zi->i_mmap_sem);
+	filemap_invalidate_lock_shared(inode->i_mapping);
 	ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
-	up_read(&zi->i_mmap_sem);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
 static const struct vm_operations_struct zonefs_file_vm_ops = {
-	.fault		= zonefs_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= zonefs_filemap_page_mkwrite,
 };
@@ -1155,7 +1143,6 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb)
 
 	inode_init_once(&zi->i_vnode);
 	mutex_init(&zi->i_truncate_mutex);
-	init_rwsem(&zi->i_mmap_sem);
 	zi->i_wr_refcnt = 0;
 
 	return &zi->i_vnode;

fs/zonefs/zonefs.h

@@ -70,12 +70,11 @@ struct zonefs_inode_info {
 	 * and changes to the inode private data, and in particular changes to
 	 * a sequential file size on completion of direct IO writes.
 	 * Serialization of mmap read IOs with truncate and syscall IO
-	 * operations is done with i_mmap_sem in addition to i_truncate_mutex.
-	 * Only zonefs_seq_file_truncate() takes both lock (i_mmap_sem first,
-	 * i_truncate_mutex second).
+	 * operations is done with invalidate_lock in addition to
+	 * i_truncate_mutex.  Only zonefs_seq_file_truncate() takes both lock
+	 * (invalidate_lock first, i_truncate_mutex second).
 	 */
 	struct mutex		i_truncate_mutex;
-	struct rw_semaphore	i_mmap_sem;
 
 	/* guarded by i_truncate_mutex */
 	unsigned int		i_wr_refcnt;

include/linux/fs.h

@@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
  * struct address_space - Contents of a cacheable, mappable object.
  * @host: Owner, either the inode or the block_device.
  * @i_pages: Cached pages.
+ * @invalidate_lock: Guards coherency between page cache contents and
+ *   file offset->disk block mappings in the filesystem during invalidates.
+ *   It is also used to block modification of page cache contents through
+ *   memory mappings.
  * @gfp_mask: Memory allocation flags to use for allocating pages.
  * @i_mmap_writable: Number of VM_SHARED mappings.
  * @nr_thps: Number of THPs in the pagecache (non-shmem only).
@@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
 struct address_space {
 	struct inode		*host;
 	struct xarray		i_pages;
+	struct rw_semaphore	invalidate_lock;
 	gfp_t			gfp_mask;
 	atomic_t		i_mmap_writable;
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -814,9 +819,42 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla
 	down_read_nested(&inode->i_rwsem, subclass);
 }
 
+static inline void filemap_invalidate_lock(struct address_space *mapping)
+{
+	down_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock(struct address_space *mapping)
+{
+	up_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
+{
+	down_read(&mapping->invalidate_lock);
+}
+
+static inline int filemap_invalidate_trylock_shared(
+					struct address_space *mapping)
+{
+	return down_read_trylock(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock_shared(
+					struct address_space *mapping)
+{
+	up_read(&mapping->invalidate_lock);
+}
+
 void lock_two_nondirectories(struct inode *, struct inode*);
 void unlock_two_nondirectories(struct inode *, struct inode*);
 
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+				 struct address_space *mapping2);
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+				   struct address_space *mapping2);
+
+
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
@@ -2490,6 +2528,7 @@ struct file_system_type {
 
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
+	struct lock_class_key invalidate_lock_key;
 	struct lock_class_key i_mutex_dir_key;
 };
 

mm/filemap.c

@@ -76,7 +76,8 @@
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->i_pages lock
  *
- *  ->i_mutex
+ *  ->i_rwsem
+ *    ->invalidate_lock		(acquired by fs in truncate path)
  *      ->i_mmap_rwsem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_lock
@@ -85,9 +86,10 @@
  *        ->i_pages lock	(arch-dependent flush_dcache_mmap_lock)
  *
  *  ->mmap_lock
- *    ->lock_page		(access_process_vm)
+ *    ->invalidate_lock		(filemap_fault)
+ *      ->lock_page		(filemap_fault, access_process_vm)
  *
- *  ->i_mutex			(generic_perform_write)
+ *  ->i_rwsem			(generic_perform_write)
  *    ->mmap_lock		(fault_in_pages_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
@@ -1007,6 +1009,44 @@ struct page *__page_cache_alloc(gfp_t gfp)
 EXPORT_SYMBOL(__page_cache_alloc);
 #endif
 
+/*
+ * filemap_invalidate_lock_two - lock invalidate_lock for two mappings
+ *
+ * Lock exclusively invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to lock
+ * @mapping2: the second mapping to lock
+ */
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+				 struct address_space *mapping2)
+{
+	if (mapping1 > mapping2)
+		swap(mapping1, mapping2);
+	if (mapping1)
+		down_write(&mapping1->invalidate_lock);
+	if (mapping2 && mapping1 != mapping2)
+		down_write_nested(&mapping2->invalidate_lock, 1);
+}
+EXPORT_SYMBOL(filemap_invalidate_lock_two);
+
+/*
+ * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings
+ *
+ * Unlock exclusive invalidate_lock of any passed mapping that is not NULL.
+ *
+ * @mapping1: the first mapping to unlock
+ * @mapping2: the second mapping to unlock
+ */
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+				   struct address_space *mapping2)
+{
+	if (mapping1)
+		up_write(&mapping1->invalidate_lock);
+	if (mapping2 && mapping1 != mapping2)
+		up_write(&mapping2->invalidate_lock);
+}
+EXPORT_SYMBOL(filemap_invalidate_unlock_two);
+
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -2368,20 +2408,30 @@ static int filemap_update_page(struct kiocb *iocb,
 {
 	int error;
 
-	if (!trylock_page(page)) {
-		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!filemap_invalidate_trylock_shared(mapping))
 			return -EAGAIN;
+	} else {
+		filemap_invalidate_lock_shared(mapping);
+	}
+
+	if (!trylock_page(page)) {
+		error = -EAGAIN;
+		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
+			goto unlock_mapping;
 		if (!(iocb->ki_flags & IOCB_WAITQ)) {
+			filemap_invalidate_unlock_shared(mapping);
 			put_and_wait_on_page_locked(page, TASK_KILLABLE);
 			return AOP_TRUNCATED_PAGE;
 		}
 		error = __lock_page_async(page, iocb->ki_waitq);
 		if (error)
-			return error;
+			goto unlock_mapping;
 	}
 
+	error = AOP_TRUNCATED_PAGE;
 	if (!page->mapping)
-		goto truncated;
+		goto unlock;
 
 	error = 0;
 	if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
@@ -2392,15 +2442,13 @@ static int filemap_update_page(struct kiocb *iocb,
 		goto unlock;
 
 	error = filemap_read_page(iocb->ki_filp, mapping, page);
-	if (error == AOP_TRUNCATED_PAGE)
-		put_page(page);
-	return error;
-truncated:
-	unlock_page(page);
-	put_page(page);
-	return AOP_TRUNCATED_PAGE;
+	goto unlock_mapping;
 unlock:
 	unlock_page(page);
+unlock_mapping:
+	filemap_invalidate_unlock_shared(mapping);
+	if (error == AOP_TRUNCATED_PAGE)
+		put_page(page);
 	return error;
 }
 
@@ -2415,6 +2463,19 @@ static int filemap_create_page(struct file *file,
 	if (!page)
 		return -ENOMEM;
 
+	/*
+	 * Protect against truncate / hole punch. Grabbing invalidate_lock here
+	 * assures we cannot instantiate and bring uptodate new pagecache pages
+	 * after evicting page cache during truncate and before actually
+	 * freeing blocks.  Note that we could release invalidate_lock after
+	 * inserting the page into page cache as the locked page would then be
+	 * enough to synchronize with hole punching. But there are code paths
+	 * such as filemap_update_page() filling in partially uptodate pages or
+	 * ->readpages() that need to hold invalidate_lock while mapping blocks
+	 * for IO so let's hold the lock here as well to keep locking rules
+	 * simple.
+	 */
+	filemap_invalidate_lock_shared(mapping);
 	error = add_to_page_cache_lru(page, mapping, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2426,9 +2487,11 @@ static int filemap_create_page(struct file *file,
 	if (error)
 		goto error;
 
+	filemap_invalidate_unlock_shared(mapping);
 	pagevec_add(pvec, page);
 	return 0;
 error:
+	filemap_invalidate_unlock_shared(mapping);
 	put_page(page);
 	return error;
 }
@@ -2967,6 +3030,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	pgoff_t max_off;
 	struct page *page;
 	vm_fault_t ret = 0;
+	bool mapping_locked = false;
 
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (unlikely(offset >= max_off))
@@ -2976,25 +3040,39 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
-	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+	if (likely(page)) {
 		/*
-		 * We found the page, so try async readahead before
-		 * waiting for the lock.
+		 * We found the page, so try async readahead before waiting for
+		 * the lock.
 		 */
+		if (!(vmf->flags & FAULT_FLAG_TRIED))
 			fpin = do_async_mmap_readahead(vmf, page);
-	} else if (!page) {
+		if (unlikely(!PageUptodate(page))) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
+	} else {
 		/* No page in the page cache at all */
 		count_vm_event(PGMAJFAULT);
 		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 		fpin = do_sync_mmap_readahead(vmf);
 retry_find:
+		/*
+		 * See comment in filemap_create_page() why we need
+		 * invalidate_lock
+		 */
+		if (!mapping_locked) {
+			filemap_invalidate_lock_shared(mapping);
+			mapping_locked = true;
+		}
 		page = pagecache_get_page(mapping, offset,
 					  FGP_CREAT|FGP_FOR_MMAP,
 					  vmf->gfp_mask);
 		if (!page) {
 			if (fpin)
 				goto out_retry;
+			filemap_invalidate_unlock_shared(mapping);
 			return VM_FAULT_OOM;
 		}
 	}
@@ -3014,8 +3092,20 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
 	 */
-	if (unlikely(!PageUptodate(page)))
+	if (unlikely(!PageUptodate(page))) {
+		/*
+		 * The page was in cache and uptodate and now it is not.
+		 * Strange but possible since we didn't hold the page lock all
+		 * the time. Let's drop everything get the invalidate lock and
+		 * try again.
+		 */
+		if (!mapping_locked) {
+			unlock_page(page);
+			put_page(page);
+			goto retry_find;
+		}
 		goto page_not_uptodate;
+	}
 
 	/*
 	 * We've made it this far and we had to drop our mmap_lock, now is the
@@ -3026,6 +3116,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 		unlock_page(page);
 		goto out_retry;
 	}
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 
 	/*
 	 * Found the page and have a reference on it.
@@ -3056,6 +3148,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 
 	if (!error || error == AOP_TRUNCATED_PAGE)
 		goto retry_find;
+	filemap_invalidate_unlock_shared(mapping);
 
 	return VM_FAULT_SIGBUS;
 
@@ -3067,6 +3160,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 */
 	if (page)
 		put_page(page);
+	if (mapping_locked)
+		filemap_invalidate_unlock_shared(mapping);
 	if (fpin)
 		fput(fpin);
 	return ret | VM_FAULT_RETRY;
@@ -3437,6 +3532,8 @@ static struct page *do_read_cache_page(struct address_space *mapping,
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page(struct address_space *mapping,
@@ -3460,6 +3557,8 @@ EXPORT_SYMBOL(read_cache_page);
  *
  * If the page does not get brought uptodate, return -EIO.
  *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
  * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page_gfp(struct address_space *mapping,
@@ -3704,12 +3803,12 @@ EXPORT_SYMBOL(generic_perform_write);
  * modification times and calls proper subroutines depending on whether we
  * do direct IO or a standard buffered write.
  *
- * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * It expects i_rwsem to be grabbed unless we work on a block device or similar
  * object which does not need locking at all.
  *
  * This function does *not* take care of syncing data in case of O_SYNC write.
  * A caller has to handle it. This is mainly due to the fact that we want to
- * avoid syncing under i_mutex.
+ * avoid syncing under i_rwsem.
  *
  * Return:
  * * number of bytes written, even for truncated writes
@@ -3797,7 +3896,7 @@ EXPORT_SYMBOL(__generic_file_write_iter);
  *
  * This is a wrapper around __generic_file_write_iter() to be used by most
  * filesystems. It takes care of syncing the file in case of O_SYNC file
- * and acquires i_mutex as needed.
+ * and acquires i_rwsem as needed.
  * Return:
  * * negative error code if no data has been written at all of
  *   vfs_fsync_range() failed for a synchronous write

mm/madvise.c

@@ -912,7 +912,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
 	/*
-	 * Filesystem's fallocate may need to take i_mutex.  We need to
+	 * Filesystem's fallocate may need to take i_rwsem.  We need to
 	 * explicitly grab a reference because the vma (and hence the
 	 * vma's reference to the file) can go away as soon as we drop
 	 * mmap_lock.

mm/memory-failure.c

@@ -866,7 +866,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn)
 	/*
 	 * Truncation is a bit tricky. Enable it per file system for now.
 	 *
-	 * Open: to take i_mutex or not for this? Right now we don't.
+	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
 	ret = truncate_error_page(p, pfn, mapping);
 out:

mm/readahead.c

@@ -192,6 +192,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	 */
 	unsigned int nofs = memalloc_nofs_save();
 
+	filemap_invalidate_lock_shared(mapping);
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
@@ -236,6 +237,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	 * will then handle the error.
 	 */
 	read_pages(ractl, &page_pool, false);
+	filemap_invalidate_unlock_shared(mapping);
 	memalloc_nofs_restore(nofs);
 }
 EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);

mm/rmap.c

@@ -20,9 +20,10 @@
 /*
  * Lock ordering in mm:
  *
- * inode->i_mutex	(while writing or truncating, not reading or faulting)
+ * inode->i_rwsem	(while writing or truncating, not reading or faulting)
  *   mm->mmap_lock
- *     page->flags PG_locked (lock_page)   * (see huegtlbfs below)
+ *     mapping->invalidate_lock (in filemap_fault)
+ *       page->flags PG_locked (lock_page)   * (see hugetlbfs below)
  *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
  *           mapping->i_mmap_rwsem
  *             hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
@@ -41,7 +42,7 @@
  *                               in arch-dependent flush_dcache_mmap_lock,
  *                               within bdi.wb->list_lock in __sync_single_inode)
  *
- * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
+ * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
  *     pte map lock
  *

mm/shmem.c

@@ -96,7 +96,7 @@ static struct vfsmount *shm_mnt;
 
 /*
  * shmem_fallocate communicates with shmem_fault or shmem_writepage via
- * inode->i_private (with i_mutex making sure that it has only one user at
+ * inode->i_private (with i_rwsem making sure that it has only one user at
  * a time): we would prefer not to enlarge the shmem inode just for that.
  */
 struct shmem_falloc {
@@ -774,7 +774,7 @@ static int shmem_free_swap(struct address_space *mapping,
  * Determine (in bytes) how many of the shmem object's pages mapped by the
  * given offsets are swapped out.
  *
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
  * as long as the inode doesn't go away and racy results are not a problem.
  */
 unsigned long shmem_partial_swap_usage(struct address_space *mapping,
@@ -806,7 +806,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
  * Determine (in bytes) how many of the shmem object's pages mapped by the
  * given vma is swapped out.
  *
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
  * as long as the inode doesn't go away and racy results are not a problem.
  */
 unsigned long shmem_swap_usage(struct vm_area_struct *vma)
@@ -1069,7 +1069,7 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
 
-		/* protected by i_mutex */
+		/* protected by i_rwsem */
 		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
 		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
 			return -EPERM;
@@ -2059,7 +2059,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 	/*
 	 * Trinity finds that probing a hole which tmpfs is punching can
 	 * prevent the hole-punch from ever completing: which in turn
-	 * locks writers out with its hold on i_mutex.  So refrain from
+	 * locks writers out with its hold on i_rwsem.  So refrain from
 	 * faulting pages into the hole while it's being punched.  Although
 	 * shmem_undo_range() does remove the additions, it may be unable to
 	 * keep up, as each new page needs its own unmap_mapping_range() call,
@@ -2070,7 +2070,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 	 * we just need to make racing faults a rare case.
 	 *
 	 * The implementation below would be much simpler if we just used a
-	 * standard mutex or completion: but we cannot take i_mutex in fault,
+	 * standard mutex or completion: but we cannot take i_rwsem in fault,
 	 * and bloating every shmem inode for this unlikely case would be sad.
 	 */
 	if (unlikely(inode->i_private)) {
@@ -2470,7 +2470,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_SHIFT;
 
-	/* i_mutex is held by caller */
+	/* i_rwsem is held by caller */
 	if (unlikely(info->seals & (F_SEAL_GROW |
 				   F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) {
 		if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))
@@ -2570,7 +2570,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		/*
 		 * We must evaluate after, since reads (unlike writes)
-		 * are called without i_mutex protection against truncate
+		 * are called without i_rwsem protection against truncate
 		 */
 		nr = PAGE_SIZE;
 		i_size = i_size_read(inode);
@@ -2640,7 +2640,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 		return -ENXIO;
 
 	inode_lock(inode);
-	/* We're holding i_mutex so we can access i_size directly */
+	/* We're holding i_rwsem so we can access i_size directly */
 	offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence);
 	if (offset >= 0)
 		offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
@@ -2669,7 +2669,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
 		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
 
-		/* protected by i_mutex */
+		/* protected by i_rwsem */
 		if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
 			error = -EPERM;
 			goto out;

mm/truncate.c

@@ -412,7 +412,8 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @mapping: mapping to truncate
  * @lstart: offset from which to truncate
  *
- * Called under (and serialised by) inode->i_mutex.
+ * Called under (and serialised by) inode->i_rwsem and
+ * mapping->invalidate_lock.
  *
  * Note: When this function returns, there can be a page in the process of
  * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
@@ -429,7 +430,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
  * truncate_inode_pages_final - truncate *all* pages before inode dies
  * @mapping: mapping to truncate
  *
- * Called under (and serialized by) inode->i_mutex.
+ * Called under (and serialized by) inode->i_rwsem.
  *
  * Filesystems have to use this in the .evict_inode path to inform the
  * VM that this is the final truncate and the inode is going away.
@@ -748,7 +749,7 @@ EXPORT_SYMBOL(truncate_pagecache);
  * setattr function when ATTR_SIZE is passed in.
  *
  * Must be called with a lock serializing truncates and writes (generally
- * i_mutex but e.g. xfs uses a different lock) and before all filesystem
+ * i_rwsem but e.g. xfs uses a different lock) and before all filesystem
  * specific block truncation has been performed.
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
@@ -777,7 +778,7 @@ EXPORT_SYMBOL(truncate_setsize);
  *
  * The function must be called after i_size is updated so that page fault
  * coming after we unlock the page will already see the new i_size.
- * The function must be called while we still hold i_mutex - this not only
+ * The function must be called while we still hold i_rwsem - this not only
  * makes sure i_size is stable but also that userspace cannot observe new
  * i_size value before we are prepared to store mmap writes at new inode size.
  */