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
2026-03-06 15:25:10 -08:00 · 2021-08-30 10:24:50 -07:00
parent a1ca8e7147 7882c55ef6
commit aa99f3c2b9
40 changed files with 483 additions and 361 deletions
--- a/Documentation/filesystems/locking.rst
+++ b/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
--- a/fs/ceph/addr.c
+++ b/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);
 	}
--- a/fs/ceph/file.c
+++ b/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:
--- a/fs/cifs/smb2ops.c
+++ b/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;
 }

--- 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
 */
--- 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;
--- 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)) {
--- 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);
 }

--- a/fs/ext4/ext4.h
+++ b/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);
--- a/fs/ext4/extents.c
+++ b/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 @@ out:
 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 @@ out_stop:
 	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 @@ out_mutex:
 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 @@ out_stop:
 	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;
--- a/fs/ext4/file.c
+++ b/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 @@ retry:
 		/* 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,
 };
--- 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;
-}
--- a/fs/ext4/ioctl.c
+++ b/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 @@ err_out1:
 	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);
--- a/fs/ext4/super.c
+++ b/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);
 }
--- a/fs/ext4/truncate.h
+++ b/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);
 }

 /*
--- a/fs/f2fs/data.c
+++ b/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 @@ done:
 	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;
--- a/fs/f2fs/f2fs.h
+++ b/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 */
--- a/fs/f2fs/file.c
+++ b/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 @@ out:
 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 @@ write:
 		/* 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]);
 		}

--- a/fs/f2fs/super.c
+++ b/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 */
--- a/fs/fuse/dax.c
+++ b/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 @@ retry:
 	 * 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;
 }

--- a/Show More
+++ b/Show More