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

Pull vfs 'statx()' update from Al Viro.

This adds the new extended stat() interface that internally subsumes our
previous stat interfaces, and allows user mode to specify in more detail
what kind of information it wants.

It also allows for some explicit synchronization information to be
passed to the filesystem, which can be relevant for network filesystems:
is the cached value ok, or do you need open/close consistency, or what?

From David Howells.

Andreas Dilger points out that the first version of the extended statx
interface was posted June 29, 2010:

    https://www.spinics.net/lists/linux-fsdevel/msg33831.html

* 'rebased-statx' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  statx: Add a system call to make enhanced file info available

1 files changed, 176 insertions, 38 deletions

diff --git a/fs/stat.c b/fs/stat.c
index 95bd417..fa0be59 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -19,6 +19,15 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
+/**
+ * generic_fillattr - Fill in the basic attributes from the inode struct
+ * @inode: Inode to use as the source
+ * @stat: Where to fill in the attributes
+ *
+ * Fill in the basic attributes in the kstat structure from data that's to be
+ * found on the VFS inode structure.  This is the default if no getattr inode
+ * operation is supplied.
+ */
 void generic_fillattr(struct inode *inode, struct kstat *stat)
 {
 	stat->dev = inode->i_sb->s_dev;
@@ -34,81 +43,147 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->ctime = inode->i_ctime;
 	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
-}
 
+	if (IS_NOATIME(inode))
+		stat->result_mask &= ~STATX_ATIME;
+	if (IS_AUTOMOUNT(inode))
+		stat->attributes |= STATX_ATTR_AUTOMOUNT;
+}
 EXPORT_SYMBOL(generic_fillattr);
 
 /**
  * vfs_getattr_nosec - getattr without security checks
  * @path: file to get attributes from
  * @stat: structure to return attributes in
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * Get attributes without calling security_inode_getattr.
  *
  * Currently the only caller other than vfs_getattr is internal to the
- * filehandle lookup code, which uses only the inode number and returns
- * no attributes to any user.  Any other code probably wants
- * vfs_getattr.
+ * filehandle lookup code, which uses only the inode number and returns no
+ * attributes to any user.  Any other code probably wants vfs_getattr.
  */
-int vfs_getattr_nosec(struct path *path, struct kstat *stat)
+int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_backing_inode(path->dentry);
 
+	memset(stat, 0, sizeof(*stat));
+	stat->result_mask |= STATX_BASIC_STATS;
+	request_mask &= STATX_ALL;
+	query_flags &= KSTAT_QUERY_FLAGS;
 	if (inode->i_op->getattr)
-		return inode->i_op->getattr(path->mnt, path->dentry, stat);
+		return inode->i_op->getattr(path, stat, request_mask,
+					    query_flags);
 
 	generic_fillattr(inode, stat);
 	return 0;
 }
-
 EXPORT_SYMBOL(vfs_getattr_nosec);
 
-int vfs_getattr(struct path *path, struct kstat *stat)
+/*
+ * vfs_getattr - Get the enhanced basic attributes of a file
+ * @path: The file of interest
+ * @stat: Where to return the statistics
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * Ask the filesystem for a file's attributes.  The caller must indicate in
+ * request_mask and query_flags to indicate what they want.
+ *
+ * If the file is remote, the filesystem can be forced to update the attributes
+ * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can
+ * suppress the update by passing AT_STATX_DONT_SYNC.
+ *
+ * Bits must have been set in request_mask to indicate which attributes the
+ * caller wants retrieving.  Any such attribute not requested may be returned
+ * anyway, but the value may be approximate, and, if remote, may not have been
+ * synchronised with the server.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
 	int retval;
 
 	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
-	return vfs_getattr_nosec(path, stat);
+	return vfs_getattr_nosec(path, stat, request_mask, query_flags);
 }
-
 EXPORT_SYMBOL(vfs_getattr);
 
-int vfs_fstat(unsigned int fd, struct kstat *stat)
+/**
+ * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * @fd: The file descriptor referring to the file of interest
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a file descriptor to determine the file location.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx_fd(unsigned int fd, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
 	struct fd f = fdget_raw(fd);
 	int error = -EBADF;
 
 	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat);
+		error = vfs_getattr(&f.file->f_path, stat,
+				    request_mask, query_flags);
 		fdput(f);
 	}
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstat);
+EXPORT_SYMBOL(vfs_statx_fd);
 
-int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
-		int flag)
+/**
+ * vfs_statx - Get basic and extra attributes by filename
+ * @dfd: A file descriptor representing the base dir for a relative filename
+ * @filename: The name of the file of interest
+ * @flags: Flags to control the query
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a filename and base directory to determine the file location.
+ * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
+ * at the given name from being referenced.
+ *
+ * The caller must have preset stat->request_mask as for vfs_getattr().  The
+ * flags are also used to load up stat->query_flags.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx(int dfd, const char __user *filename, int flags,
+	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
 	int error = -EINVAL;
-	unsigned int lookup_flags = 0;
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
 
-	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
-		      AT_EMPTY_PATH)) != 0)
-		goto out;
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+		return -EINVAL;
 
-	if (!(flag & AT_SYMLINK_NOFOLLOW))
-		lookup_flags |= LOOKUP_FOLLOW;
-	if (flag & AT_EMPTY_PATH)
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
+
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
-	error = vfs_getattr(&path, stat);
+	error = vfs_getattr(&path, stat, request_mask, flags);
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -117,19 +192,7 @@ retry:
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstatat);
-
-int vfs_stat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, 0);
-}
-EXPORT_SYMBOL(vfs_stat);
-
-int vfs_lstat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
-}
-EXPORT_SYMBOL(vfs_lstat);
+EXPORT_SYMBOL(vfs_statx);
 
 
 #ifdef __ARCH_WANT_OLD_STAT
@@ -142,7 +205,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 {
 	static int warncount = 5;
 	struct __old_kernel_stat tmp;
-	
+
 	if (warncount > 0) {
 		warncount--;
 		printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
@@ -167,7 +230,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 #if BITS_PER_LONG == 32
 	if (stat->size > MAX_NON_LFS)
 		return -EOVERFLOW;
-#endif	
+#endif
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;
 	tmp.st_mtime = stat->mtime.tv_sec;
@@ -446,6 +509,81 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
+static inline int __put_timestamp(struct timespec *kts,
+				  struct statx_timestamp __user *uts)
+{
+	return (__put_user(kts->tv_sec,		&uts->tv_sec		) ||
+		__put_user(kts->tv_nsec,	&uts->tv_nsec		) ||
+		__put_user(0,			&uts->__reserved	));
+}
+
+/*
+ * Set the statx results.
+ */
+static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
+{
+	uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
+	gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
+
+	if (__put_user(stat->result_mask,	&buffer->stx_mask	) ||
+	    __put_user(stat->mode,		&buffer->stx_mode	) ||
+	    __clear_user(&buffer->__spare0, sizeof(buffer->__spare0))	  ||
+	    __put_user(stat->nlink,		&buffer->stx_nlink	) ||
+	    __put_user(uid,			&buffer->stx_uid	) ||
+	    __put_user(gid,			&buffer->stx_gid	) ||
+	    __put_user(stat->attributes,	&buffer->stx_attributes	) ||
+	    __put_user(stat->blksize,		&buffer->stx_blksize	) ||
+	    __put_user(MAJOR(stat->rdev),	&buffer->stx_rdev_major	) ||
+	    __put_user(MINOR(stat->rdev),	&buffer->stx_rdev_minor	) ||
+	    __put_user(MAJOR(stat->dev),	&buffer->stx_dev_major	) ||
+	    __put_user(MINOR(stat->dev),	&buffer->stx_dev_minor	) ||
+	    __put_timestamp(&stat->atime,	&buffer->stx_atime	) ||
+	    __put_timestamp(&stat->btime,	&buffer->stx_btime	) ||
+	    __put_timestamp(&stat->ctime,	&buffer->stx_ctime	) ||
+	    __put_timestamp(&stat->mtime,	&buffer->stx_mtime	) ||
+	    __put_user(stat->ino,		&buffer->stx_ino	) ||
+	    __put_user(stat->size,		&buffer->stx_size	) ||
+	    __put_user(stat->blocks,		&buffer->stx_blocks	) ||
+	    __clear_user(&buffer->__spare1, sizeof(buffer->__spare1))	  ||
+	    __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/**
+ * sys_statx - System call to get enhanced stats
+ * @dfd: Base directory to pathwalk from *or* fd to stat.
+ * @filename: File to stat *or* NULL.
+ * @flags: AT_* flags to control pathwalk.
+ * @mask: Parts of statx struct actually required.
+ * @buffer: Result buffer.
+ *
+ * Note that if filename is NULL, then it does the equivalent of fstat() using
+ * dfd to indicate the file of interest.
+ */
+SYSCALL_DEFINE5(statx,
+		int, dfd, const char __user *, filename, unsigned, flags,
+		unsigned int, mask,
+		struct statx __user *, buffer)
+{
+	struct kstat stat;
+	int error;
+
+	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+		return -EINVAL;
+	if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
+		return -EFAULT;
+
+	if (filename)
+		error = vfs_statx(dfd, filename, flags, &stat, mask);
+	else
+		error = vfs_statx_fd(dfd, &stat, mask, flags);
+	if (error)
+		return error;
+	return statx_set_result(&stat, buffer);
+}
+
 /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
 void __inode_add_bytes(struct inode *inode, loff_t bytes)
 {