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

6 files changed, 185 insertions, 15 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 52350947c670..aad3fd0ff5f8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1709,7 +1709,7 @@ struct inode_operations {
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
+	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
@@ -2902,8 +2902,8 @@ extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
 extern void generic_fillattr(struct inode *, struct kstat *);
-int vfs_getattr_nosec(struct path *path, struct kstat *stat);
-extern int vfs_getattr(struct path *, struct kstat *);
+extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
+extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
 void __inode_sub_bytes(struct inode *inode, loff_t bytes);
@@ -2916,10 +2916,29 @@ extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
-extern int vfs_stat(const char __user *, struct kstat *);
-extern int vfs_lstat(const char __user *, struct kstat *);
-extern int vfs_fstat(unsigned int, struct kstat *);
-extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
+extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
+extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int);
+
+static inline int vfs_stat(const char __user *filename, struct kstat *stat)
+{
+	return vfs_statx(AT_FDCWD, filename, 0, stat, STATX_BASIC_STATS);
+}
+static inline int vfs_lstat(const char __user *name, struct kstat *stat)
+{
+	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW,
+			 stat, STATX_BASIC_STATS);
+}
+static inline int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
+{
+	return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS);
+}
+static inline int vfs_fstat(int fd, struct kstat *stat)
+{
+	return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0);
+}
+
+
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
 extern int vfs_readlink(struct dentry *, char __user *, int);
 
@@ -2949,7 +2968,7 @@ extern int dcache_dir_close(struct inode *, struct file *);
 extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
 extern int dcache_readdir(struct file *, struct dir_context *);
 extern int simple_setattr(struct dentry *, struct iattr *);
-extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
 extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f1da8c8dd473..287f34161086 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -335,7 +335,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
-extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
 extern int nfs_permission(struct inode *, int);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 075cb0c7eb2a..c76e524fb34b 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -18,20 +18,32 @@
 #include <linux/time.h>
 #include <linux/uidgid.h>
 
+#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE)
+
 struct kstat {
-	u64		ino;
-	dev_t		dev;
+	u32		result_mask;	/* What fields the user got */
 	umode_t		mode;
 	unsigned int	nlink;
+	uint32_t	blksize;	/* Preferred I/O size */
+	u64		attributes;
+#define KSTAT_ATTR_FS_IOC_FLAGS				\
+	(STATX_ATTR_COMPRESSED |			\
+	 STATX_ATTR_IMMUTABLE |				\
+	 STATX_ATTR_APPEND |				\
+	 STATX_ATTR_NODUMP |				\
+	 STATX_ATTR_ENCRYPTED				\
+	 )/* Attrs corresponding to FS_*_FL flags */
+	u64		ino;
+	dev_t		dev;
+	dev_t		rdev;
 	kuid_t		uid;
 	kgid_t		gid;
-	dev_t		rdev;
 	loff_t		size;
-	struct timespec  atime;
+	struct timespec	atime;
 	struct timespec	mtime;
 	struct timespec	ctime;
-	unsigned long	blksize;
-	unsigned long long	blocks;
+	struct timespec	btime;			/* File creation time */
+	u64		blocks;
 };
 
 #endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91a740f6b884..980c3c9b06f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -48,6 +48,7 @@ struct stat;
 struct stat64;
 struct statfs;
 struct statfs64;
+struct statx;
 struct __sysctl_args;
 struct sysinfo;
 struct timespec;
@@ -902,5 +903,7 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
 				  unsigned long prot, int pkey);
 asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
 asmlinkage long sys_pkey_free(int pkey);
+asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
+			  unsigned mask, struct statx __user *buffer);
 
 #endif
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index beed138bd359..813afd6eee71 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -63,5 +63,10 @@
 #define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
 #define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
 
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7fec7e36d921..51a6b86e3700 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -1,6 +1,7 @@
 #ifndef _UAPI_LINUX_STAT_H
 #define _UAPI_LINUX_STAT_H
 
+#include <linux/types.h>
 
 #if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
 
@@ -41,5 +42,135 @@
 
 #endif
 
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
+ * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
+ *
+ * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
+ * either be both positive or both negative.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+	__s64	tv_sec;
+	__s32	tv_nsec;
+	__s32	__reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx().  What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ *   - the bit will be cleared, and
+ *
+ *   - the datum will be set to an appropriate fabricated value if one is
+ *     available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ *   - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ *     set or if the datum is considered out of date, and
+ *
+ *   - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ *   effort, it will be filled in anyway, and the bit will be set upon return
+ *   (it might not be up to date, however, and no attempt will be made to
+ *   synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+	/* 0x00 */
+	__u32	stx_mask;	/* What results were written [uncond] */
+	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
+	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* 0x10 */
+	__u32	stx_nlink;	/* Number of hard links */
+	__u32	stx_uid;	/* User ID of owner */
+	__u32	stx_gid;	/* Group ID of owner */
+	__u16	stx_mode;	/* File mode */
+	__u16	__spare0[1];
+	/* 0x20 */
+	__u64	stx_ino;	/* Inode number */
+	__u64	stx_size;	/* File size */
+	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
+	__u64	__spare1[1];
+	/* 0x40 */
+	struct statx_timestamp	stx_atime;	/* Last access time */
+	struct statx_timestamp	stx_btime;	/* File creation time */
+	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
+	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* 0x80 */
+	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_minor;
+	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+	__u32	stx_dev_minor;
+	/* 0x90 */
+	__u64	__spare2[14];	/* Spare space for future expansion */
+	/* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
+#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
+#define STATX_UID		0x00000008U	/* Want/got stx_uid */
+#define STATX_GID		0x00000010U	/* Want/got stx_gid */
+#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
+#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
+#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
+#define STATX_INO		0x00000100U	/* Want/got stx_ino */
+#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
+#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
+#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
+#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
+#define STATX_ALL		0x00000fffU	/* All currently supported flags */
+
+/*
+ * Attributes to be found in stx_attributes
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * semantically.  Where possible, the numerical value is picked to correspond
+ * also.
+ */
+#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
+
+#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+
 
 #endif /* _UAPI_LINUX_STAT_H */