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

Pull vfs fixes from Al Viro.

Clean up file table accesses (get rid of fget_light() in favor of the
fdget() interface), add proper file position locking.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  get rid of fget_light()
  sockfd_lookup_light(): switch to fdget^W^Waway from fget_light
  vfs: atomic f_pos accesses as per POSIX
  ocfs2 syncs the wrong range...

fs/file.c

@@ -683,35 +683,65 @@ EXPORT_SYMBOL(fget_raw);
  * The fput_needed flag returned by fget_light should be passed to the
  * corresponding fput_light.
  */
-struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
+static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
 
-	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = __fcheck_files(files, fd);
-		if (file && (file->f_mode & mask))
-			file = NULL;
+		if (!file || unlikely(file->f_mode & mask))
+			return 0;
+		return (unsigned long)file;
 	} else {
 		file = __fget(fd, mask);
-		if (file)
-			*fput_needed = 1;
+		if (!file)
+			return 0;
+		return FDPUT_FPUT | (unsigned long)file;
 	}
-
-	return file;
 }
-struct file *fget_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget(unsigned int fd)
 {
-	return __fget_light(fd, FMODE_PATH, fput_needed);
+	return __fget_light(fd, FMODE_PATH);
 }
-EXPORT_SYMBOL(fget_light);
+EXPORT_SYMBOL(__fdget);
 
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget_raw(unsigned int fd)
 {
-	return __fget_light(fd, 0, fput_needed);
+	return __fget_light(fd, 0);
+}
+
+unsigned long __fdget_pos(unsigned int fd)
+{
+	struct files_struct *files = current->files;
+	struct file *file;
+	unsigned long v;
+
+	if (atomic_read(&files->count) == 1) {
+		file = __fcheck_files(files, fd);
+		v = 0;
+	} else {
+		file = __fget(fd, 0);
+		v = FDPUT_FPUT;
+	}
+	if (!file)
+		return 0;
+
+	if (file->f_mode & FMODE_ATOMIC_POS) {
+		if (file_count(file) > 1) {
+			v |= FDPUT_POS_UNLOCK;
+			mutex_lock(&file->f_pos_lock);
+		}
+	}
+	return v | (unsigned long)file;
 }
 
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+
 void set_close_on_exec(unsigned int fd, int flag)
 {
 	struct files_struct *files = current->files;

fs/file_table.c

@@ -135,6 +135,7 @@ struct file *get_empty_filp(void)
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
+	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
 	return f;

fs/namei.c

@@ -1884,7 +1884,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			if (f.need_put)
+			if (f.flags & FDPUT_FPUT)
 				*fp = f.file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			rcu_read_lock();

fs/ocfs2/file.c

@@ -2393,8 +2393,8 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
 	    ((file->f_flags & O_DIRECT) && !direct_io)) {
-		ret = filemap_fdatawrite_range(file->f_mapping, pos,
-					       pos + count - 1);
+		ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+					       *ppos + count - 1);
 		if (ret < 0)
 			written = ret;
 
@@ -2407,8 +2407,8 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		}
 
 		if (!ret)
-			ret = filemap_fdatawait_range(file->f_mapping, pos,
-						      pos + count - 1);
+			ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+						      *ppos + count - 1);
 	}
 
 	/*

fs/open.c

@@ -705,6 +705,10 @@ static int do_dentry_open(struct file *f,
 		return 0;
 	}
 
+	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+	if (S_ISREG(inode->i_mode))
+		f->f_mode |= FMODE_ATOMIC_POS;
+
 	f->f_op = fops_get(inode->i_fop);
 	if (unlikely(WARN_ON(!f->f_op))) {
 		error = -ENODEV;

fs/read_write.c

@@ -264,10 +264,22 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
 }
 EXPORT_SYMBOL(vfs_llseek);
 
+static inline struct fd fdget_pos(int fd)
+{
+	return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+	if (f.flags & FDPUT_POS_UNLOCK)
+		mutex_unlock(&f.file->f_pos_lock);
+	fdput(f);
+}
+
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 {
 	off_t retval;
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	if (!f.file)
 		return -EBADF;
 
@@ -278,7 +290,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
-	fdput(f);
+	fdput_pos(f);
 	return retval;
 }
 
@@ -498,7 +510,7 @@ static inline void file_pos_write(struct file *file, loff_t pos)
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -506,7 +518,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 		ret = vfs_read(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 	return ret;
 }
@@ -514,7 +526,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		size_t, count)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -522,7 +534,7 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		ret = vfs_write(f.file, buf, count, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	return ret;
@@ -797,7 +809,7 @@ EXPORT_SYMBOL(vfs_writev);
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -805,7 +817,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		ret = vfs_readv(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -817,7 +829,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
@@ -825,7 +837,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		ret = vfs_writev(f.file, vec, vlen, &pos);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
-		fdput(f);
+		fdput_pos(f);
 	}
 
 	if (ret > 0)
@@ -968,7 +980,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 		const struct compat_iovec __user *,vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -978,7 +990,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 	ret = compat_readv(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 
@@ -1035,7 +1047,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 		const struct compat_iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	ssize_t ret;
 	loff_t pos;
 
@@ -1045,7 +1057,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 	ret = compat_writev(f.file, vec, vlen, &pos);
 	if (ret >= 0)
 		f.file->f_pos = pos;
-	fdput(f);
+	fdput_pos(f);
 	return ret;
 }
 

include/linux/file.h

@@ -28,33 +28,36 @@ static inline void fput_light(struct file *file, int fput_needed)
 
 struct fd {
 	struct file *file;
-	int need_put;
+	unsigned int flags;
 };
+#define FDPUT_FPUT       1
+#define FDPUT_POS_UNLOCK 2
 
 static inline void fdput(struct fd fd)
 {
-	if (fd.need_put)
+	if (fd.flags & FDPUT_FPUT)
 		fput(fd.file);
 }
 
 extern struct file *fget(unsigned int fd);
-extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern unsigned long __fdget(unsigned int fd);
+extern unsigned long __fdget_raw(unsigned int fd);
+extern unsigned long __fdget_pos(unsigned int fd);
 
-static inline struct fd fdget(unsigned int fd)
+static inline struct fd __to_fd(unsigned long v)
 {
-	int b;
-	struct file *f = fget_light(fd, &b);
-	return (struct fd){f,b};
+	return (struct fd){(struct file *)(v & ~3),v & 3};
 }
 
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
+static inline struct fd fdget(unsigned int fd)
+{
+	return __to_fd(__fdget(fd));
+}
 
 static inline struct fd fdget_raw(unsigned int fd)
 {
-	int b;
-	struct file *f = fget_raw_light(fd, &b);
-	return (struct fd){f,b};
+	return __to_fd(__fdget_raw(fd));
 }
 
 extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);

include/linux/fs.h

@@ -123,6 +123,9 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)0x4000)
 
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
 
@@ -780,13 +783,14 @@ struct file {
 	const struct file_operations	*f_op;
 
 	/*
-	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+	 * Protects f_ep_links, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
+	struct mutex		f_pos_lock;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	const struct cred	*f_cred;
@@ -808,7 +812,7 @@ struct file {
 #ifdef CONFIG_DEBUG_WRITECOUNT
 	unsigned long f_mnt_write_state;
 #endif
-};
+} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
 	__u32 handle_bytes;

net/socket.c

@@ -450,16 +450,17 @@ EXPORT_SYMBOL(sockfd_lookup);
 
 static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	struct socket *sock;
 
 	*err = -EBADF;
-	file = fget_light(fd, fput_needed);
-	if (file) {
-		sock = sock_from_file(file, err);
-		if (sock)
+	if (f.file) {
+		sock = sock_from_file(f.file, err);
+		if (likely(sock)) {
+			*fput_needed = f.flags;
 			return sock;
-		fput_light(file, *fput_needed);
+		}
+		fdput(f);
 	}
 	return NULL;
 }