Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull third hunk of vfs changes from Al Viro:
 "This contains the ->direct_IO() changes from Omar + saner
  generic_write_checks() + dealing with fcntl()/{read,write}() races
  (mirroring O_APPEND/O_DIRECT into iocb->ki_flags and instead of
  repeatedly looking at ->f_flags, which can be changed by fcntl(2),
  check ->ki_flags - which cannot) + infrastructure bits for dhowells'
  d_inode annotations + Christophs switch of /dev/loop to
  vfs_iter_write()"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (30 commits)
  block: loop: switch to VFS ITER_BVEC
  configfs: Fix inconsistent use of file_inode() vs file->f_path.dentry->d_inode
  VFS: Make pathwalk use d_is_reg() rather than S_ISREG()
  VFS: Fix up debugfs to use d_is_dir() in place of S_ISDIR()
  VFS: Combine inode checks with d_is_negative() and d_is_positive() in pathwalk
  NFS: Don't use d_inode as a variable name
  VFS: Impose ordering on accesses of d_inode and d_flags
  VFS: Add owner-filesystem positive/negative dentry checks
  nfs: generic_write_checks() shouldn't be done on swapout...
  ocfs2: use __generic_file_write_iter()
  mirror O_APPEND and O_DIRECT into iocb->ki_flags
  switch generic_write_checks() to iocb and iter
  ocfs2: move generic_write_checks() before the alignment checks
  ocfs2_file_write_iter: stop messing with ppos
  udf_file_write_iter: reorder and simplify
  fuse: ->direct_IO() doesn't need generic_write_checks()
  ext4_file_write_iter: move generic_write_checks() up
  xfs_file_aio_write_checks: switch to iocb/iov_iter
  generic_write_checks(): drop isblk argument
  blkdev_write_iter: expand generic_file_checks() call in there
  ...

4 files changed, 80 insertions, 33 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d835879..df334cb 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -404,26 +404,11 @@ static inline bool d_mountpoint(const struct dentry *dentry)
 /*
  * Directory cache entry type accessor functions.
  */
-static inline void __d_set_type(struct dentry *dentry, unsigned type)
-{
-	dentry->d_flags = (dentry->d_flags & ~DCACHE_ENTRY_TYPE) | type;
-}
-
-static inline void __d_clear_type(struct dentry *dentry)
-{
-	__d_set_type(dentry, DCACHE_MISS_TYPE);
-}
-
-static inline void d_set_type(struct dentry *dentry, unsigned type)
-{
-	spin_lock(&dentry->d_lock);
-	__d_set_type(dentry, type);
-	spin_unlock(&dentry->d_lock);
-}
-
 static inline unsigned __d_entry_type(const struct dentry *dentry)
 {
-	return dentry->d_flags & DCACHE_ENTRY_TYPE;
+	unsigned type = READ_ONCE(dentry->d_flags);
+	smp_rmb();
+	return type & DCACHE_ENTRY_TYPE;
 }
 
 static inline bool d_is_miss(const struct dentry *dentry)
@@ -482,6 +467,44 @@ static inline bool d_is_positive(const struct dentry *dentry)
 	return !d_is_negative(dentry);
 }
 
+/**
+ * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs)
+ * @dentry: The dentry in question
+ *
+ * Returns true if the dentry represents either an absent name or a name that
+ * doesn't map to an inode (ie. ->d_inode is NULL).  The dentry could represent
+ * a true miss, a whiteout that isn't represented by a 0,0 chardev or a
+ * fallthrough marker in an opaque directory.
+ *
+ * Note!  (1) This should be used *only* by a filesystem to examine its own
+ * dentries.  It should not be used to look at some other filesystem's
+ * dentries.  (2) It should also be used in combination with d_inode() to get
+ * the inode.  (3) The dentry may have something attached to ->d_lower and the
+ * type field of the flags may be set to something other than miss or whiteout.
+ */
+static inline bool d_really_is_negative(const struct dentry *dentry)
+{
+	return dentry->d_inode == NULL;
+}
+
+/**
+ * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs)
+ * @dentry: The dentry in question
+ *
+ * Returns true if the dentry represents a name that maps to an inode
+ * (ie. ->d_inode is not NULL).  The dentry might still represent a whiteout if
+ * that is represented on medium as a 0,0 chardev.
+ *
+ * Note!  (1) This should be used *only* by a filesystem to examine its own
+ * dentries.  It should not be used to look at some other filesystem's
+ * dentries.  (2) It should also be used in combination with d_inode() to get
+ * the inode.
+ */
+static inline bool d_really_is_positive(const struct dentry *dentry)
+{
+	return dentry->d_inode != NULL;
+}
+
 extern void d_set_fallthru(struct dentry *dentry);
 
 static inline bool d_is_fallthru(const struct dentry *dentry)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f4fc607..f4d6354 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -315,6 +315,8 @@ struct address_space;
 struct writeback_control;
 
 #define IOCB_EVENTFD		(1 << 0)
+#define IOCB_APPEND		(1 << 1)
+#define IOCB_DIRECT		(1 << 2)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -329,10 +331,13 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 	return kiocb->ki_complete == NULL;
 }
 
+static inline int iocb_flags(struct file *file);
+
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
 		.ki_filp = filp,
+		.ki_flags = iocb_flags(filp),
 	};
 }
 
@@ -383,7 +388,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
+	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
 	/*
 	 * migrate the contents of a page to the specified target. If
 	 * migrate_mode is MIGRATE_ASYNC, it must not block.
@@ -2566,7 +2571,7 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
+extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
@@ -2609,8 +2614,8 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
-		loff_t, get_block_t, dio_iodone_t, int flags);
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+		  get_block_t, dio_iodone_t, int flags);
 int dax_clear_blocks(struct inode *, sector_t block, long size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
@@ -2635,16 +2640,18 @@ enum {
 
 void dio_end_io(struct bio *bio, int error);
 
-ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
-	get_block_t get_block, dio_iodone_t end_io,
-	dio_submit_t submit_io,	int flags);
+ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
+			     struct block_device *bdev, struct iov_iter *iter,
+			     loff_t offset, get_block_t get_block,
+			     dio_iodone_t end_io, dio_submit_t submit_io,
+			     int flags);
 
-static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
-		struct inode *inode, struct iov_iter *iter, loff_t offset,
-		get_block_t get_block)
+static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
+					 struct inode *inode,
+					 struct iov_iter *iter, loff_t offset,
+					 get_block_t get_block)
 {
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				    offset, get_block, NULL, NULL,
 				    DIO_LOCKING | DIO_SKIP_HOLES);
 }
@@ -2777,6 +2784,16 @@ static inline bool io_is_direct(struct file *filp)
 	return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
 }
 
+static inline int iocb_flags(struct file *file)
+{
+	int res = 0;
+	if (file->f_flags & O_APPEND)
+		res |= IOCB_APPEND;
+	if (io_is_direct(file))
+		res |= IOCB_DIRECT;
+	return res;
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b01ccf3..410abd1 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -447,13 +447,12 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 /*
  * linux/fs/nfs/direct.c
  */
-extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
+extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			struct iov_iter *iter,
 			loff_t pos);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
-			struct iov_iter *iter,
-			loff_t pos);
+			struct iov_iter *iter);
 
 /*
  * linux/fs/nfs/dir.c
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 15f11fb..8b01e1c 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -112,6 +112,14 @@ static inline bool iter_is_iovec(struct iov_iter *i)
 }
 
 /*
+ * Get one of READ or WRITE out of iter->type without any other flags OR'd in
+ * with it.
+ *
+ * The ?: is just for type safety.
+ */
+#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & RW_MASK)
+
+/*
  * Cap the iov_iter by given limit; note that the second argument is
  * *not* the new size - it's upper limit for such.  Passing it a value
  * greater than the amount of data in iov_iter is fine - it'll just do