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

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

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

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

1 files changed, 53 insertions, 26 deletions

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 2183fd8cc350..2a75dd5da7b5 100644
--- 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