Add a pair of system calls to make extended file stats available, including
file creation time, inode version and data version where available through the
underlying filesystem:
struct xstat_dev {
unsigned int major;
unsigned int minor;
};
struct xstat_time {
unsigned long long tv_sec;
unsigned long long tv_nsec;
};
struct xstat {
unsigned int struct_version;
#define XSTAT_STRUCT_VERSION 0
unsigned int st_mode;
unsigned int st_nlink;
unsigned int st_uid;
unsigned int st_gid;
unsigned int st_blksize;
struct xstat_dev st_rdev;
struct xstat_dev st_dev;
unsigned long long st_ino;
unsigned long long st_size;
struct xstat_time st_atime;
struct xstat_time st_mtime;
struct xstat_time st_ctime;
struct xstat_time st_crtime;
unsigned long long st_blocks;
unsigned long long st_inode_version;
unsigned long long st_data_version;
unsigned long long query_flags;
#define XSTAT_QUERY_CREATION_TIME 0x00000001ULL
#define XSTAT_QUERY_INODE_VERSION 0x00000002ULL
#define XSTAT_QUERY_DATA_VERSION 0x00000004ULL
unsigned long long extra_results[0];
};
ssize_t ret = xstat(int dfd,
const char *filename,
unsigned atflag,
struct xstat *buffer,
size_t buflen);
ssize_t ret = fxstat(int fd,
struct xstat *buffer,
size_t buflen);
The dfd, filename, atflag and fd parameters indicate the file to query. There
is no equivalent of lstat() as that can be emulated with xstat(), passing 0
instead of AT_SYMLINK_NOFOLLOW as atflag.
When the system call is executed, the struct_version ID and query_flags bitmask
are read from the buffer to work out what the user is requesting.
If the structure version specified is not supported, the system call will
return ENOTSUPP. The above structure is version 0.
The query_flags should be set by the caller to specify extra results that the
caller may desire. These come in two classes:
(1) Creation time, Inode version and Data version.
These will be returned if available whether the caller asked for them or
not. The corresponding bits in query_flags will be set or cleared as
appropriate to indicate their presence.
Query Flag Field
=============================== ================
XSTAT_QUERY_CREATION_TIME st_crtime
XSTAT_QUERY_INODE_VERSION st_inode_version
XSTAT_QUERY_DATA_VERSION st_data_version
(2) Extra results.
These will only be returned if the caller asked for them by setting their
bits in query_flags. They will be placed in the buffer after the xstat
struct in ascending query_flags bit order. Any bit set in query_flags
mask will be left set if the result is available and cleared otherwise.
The pointer into the results list will be rounded up to the nearest 8-byte
boundary after each result is written in. The size of each extra result
is specific to the definition for that result.
No extra results are currently defined.
If the buffer is insufficiently big, the syscall returns the amount of space it
will need to write the complete result set, but otherwise does nothing.
If successful, the amount of data written into the buffer will be returned.
At the moment, this will only work on x86_64 as it requires system calls to be
wired up.
===========
FILESYSTEMS
===========
Ext4 is modified to make use of this facility. It will return the creation
time and inode version number for all files. It will, however, only return the
data version number for directories as i_version is only maintained for them.
AFS is modified to make use of this facility too. It will return the vnode ID
uniquifier as the inode version and the AFS data version number as the data
version. There is no file creation time available.
=======
TESTING
=======
The following test program can be used to test the xstat system call:
#define _GNU_SOURCE
#define _ATFILE_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <time.h>
#include <sys/syscall.h>
#include <sys/stat.h>
#include <sys/types.h>
struct xstat_dev {
unsigned int major;
unsigned int minor;
};
struct xstat_time {
unsigned long long tv_sec;
unsigned long long tv_nsec;
};
struct xstat {
unsigned int struct_version;
#define XSTAT_STRUCT_VERSION 0
unsigned int st_mode;
unsigned int st_nlink;
unsigned int st_uid;
unsigned int st_gid;
unsigned int st_blksize;
struct xstat_dev st_rdev;
struct xstat_dev st_dev;
unsigned long long st_ino;
unsigned long long st_size;
struct xstat_time st_atim;
struct xstat_time st_mtim;
struct xstat_time st_ctim;
struct xstat_time st_crtim;
unsigned long long st_blocks;
unsigned long long st_inode_version;
unsigned long long st_data_version;
unsigned long long query_flags;
#define XSTAT_QUERY_CREATION_TIME 0x00000001ULL
#define XSTAT_QUERY_INODE_VERSION 0x00000002ULL
#define XSTAT_QUERY_DATA_VERSION 0x00000004ULL
unsigned long long extra_results[0];
};
#define __NR_xstat 300
#define __NR_fxstat 301
static __attribute__((unused))
ssize_t xstat(int dfd, const char *filename, int atflag,
struct xstat *buffer, size_t bufsize)
{
return syscall(__NR_xstat, dfd, filename, atflag, buffer, bufsize);
}
static __attribute__((unused))
ssize_t fxstat(int fd, struct xstat *buffer, size_t bufsize)
{
return syscall(__NR_fxstat, fd, buffer, bufsize);
}
static void print_time(const struct xstat_time *xstm)
{
struct tm tm;
time_t tim;
char buffer[100];
int len;
tim = xstm->tv_sec;
if (!localtime_r(&tim, &tm)) {
perror("localtime_r");
exit(1);
}
len = strftime(buffer, 100, "%F %T", &tm);
if (len == 0) {
perror("strftime");
exit(1);
}
fwrite(buffer, 1, len, stdout);
printf(".%09llu", xstm->tv_nsec);
len = strftime(buffer, 100, "%z", &tm);
if (len == 0) {
perror("strftime2");
exit(1);
}
fwrite(buffer, 1, len, stdout);
}
static void dump_xstat(struct xstat *xst)
{
char buffer[256], ft;
printf(" Size: %-15llu Blocks: %-10llu IO Block: %-6u ",
xst->st_size, xst->st_blocks, xst->st_blksize);
switch (xst->st_mode & S_IFMT) {
case S_IFIFO: printf("FIFO\n"); ft = 'p'; break;
case S_IFCHR: printf("character special file\n"); ft = 'c'; break;
case S_IFDIR: printf("directory\n"); ft = 'd'; break;
case S_IFBLK: printf("block special file\n"); ft = 'b'; break;
case S_IFREG: printf("regular file\n"); ft = '-'; break;
case S_IFLNK: printf("symbolic link\n"); ft = 'l'; break;
case S_IFSOCK: printf("socket\n"); ft = 's'; break;
default:
printf("unknown type (%o)\n", xst->st_mode & S_IFMT);
ft = '?';
break;
}
sprintf(buffer, "%02x:%02x", xst->st_dev.major, xst->st_dev.minor);
printf("Device: %-15s Inode: %-11llu Links: %u\n",
buffer, xst->st_ino, xst->st_nlink);
printf("Access: (%04o/%c%c%c%c%c%c%c%c%c%c) ",
xst->st_mode & 07777,
ft,
xst->st_mode & S_IRUSR ? 'r' : '-',
xst->st_mode & S_IWUSR ? 'w' : '-',
xst->st_mode & S_IXUSR ? 'x' : '-',
xst->st_mode & S_IRGRP ? 'r' : '-',
xst->st_mode & S_IWGRP ? 'w' : '-',
xst->st_mode & S_IXGRP ? 'x' : '-',
xst->st_mode & S_IROTH ? 'r' : '-',
xst->st_mode & S_IWOTH ? 'w' : '-',
xst->st_mode & S_IXOTH ? 'x' : '-');
printf("Uid: %d Gid: %u\n", xst->st_uid, xst->st_gid);
printf("Access: "); print_time(&xst->st_atim); printf("\n");
printf("Modify: "); print_time(&xst->st_mtim); printf("\n");
printf("Change: "); print_time(&xst->st_ctim); printf("\n");
if (xst->query_flags & XSTAT_QUERY_CREATION_TIME) {
printf("Create: "); print_time(&xst->st_crtim); printf("\n");
}
if (xst->query_flags & XSTAT_QUERY_INODE_VERSION)
printf("Inode version: %llxh\n", xst->st_inode_version);
if (xst->query_flags & XSTAT_QUERY_DATA_VERSION)
printf("Data version: %llxh\n", xst->st_data_version);
}
int main(int argc, char **argv)
{
struct xstat xst;
int ret, atflag = AT_SYMLINK_NOFOLLOW;
for (argv++; *argv; argv++) {
if (strcmp(*argv, "-L") == 0) {
atflag = 0;
continue;
}
memset(&xst, 0xbf, sizeof(xst));
xst.struct_version = 0;
xst.query_flags = XSTAT_QUERY_CREATION_TIME |
XSTAT_QUERY_INODE_VERSION |
XSTAT_QUERY_DATA_VERSION;
ret = xstat(AT_FDCWD, *argv, atflag, &xst, sizeof(xst));
printf("xstat(%s) = %d\n", *argv, ret);
if (ret < 0) {
perror(*argv);
exit(1);
}
dump_xstat(&xst);
}
return 0;
}
Just compile and run, passing it paths to the files you want to examine:
[root@andromeda ~]# /tmp/xstat /var/cache/fscache/cache/
xstat(/var/cache/fscache/cache/) = 152
Size: 4096 Blocks: 16 IO Block: 4096 directory
Device: 08:06 Inode: 130561 Links: 3
Access: (0700/drwx------) Uid: 0 Gid: 0
Access: 2010-06-29 18:16:33.680703545+0100
Modify: 2010-06-29 18:16:20.132786632+0100
Change: 2010-06-29 18:16:20.132786632+0100
Create: 2010-06-25 15:17:39.471199293+0100
Inode version: f585ab70h
Data version: 2h
[root@andromeda ~]# /tmp/xstat /afs/archive/linuxdev/fedora9/i386/repodata/
xstat(/afs/archive/linuxdev/fedora9/i386/repodata/) = 152
Size: 2048 Blocks: 0 IO Block: 4096 directory
Device: 00:13 Inode: 83 Links: 2
Access: (0755/drwxr-xr-x) Uid: 75338 Gid: 0
Access: 2008-11-05 20:00:12.000000000+0000
Modify: 2008-11-05 20:00:12.000000000+0000
Change: 2008-11-05 20:00:12.000000000+0000
Inode version: 7a5h
Data version: 5h
Signed-off-by: David Howells <[email protected]>
---
arch/x86/include/asm/unistd_32.h | 4 +
arch/x86/include/asm/unistd_64.h | 4 +
fs/afs/inode.c | 12 ++--
fs/ext4/ext4.h | 2 +
fs/ext4/file.c | 2 -
fs/ext4/inode.c | 27 +++++++-
fs/ext4/namei.c | 2 +
fs/ext4/symlink.c | 2 +
fs/stat.c | 125 +++++++++++++++++++++++++++++++++++++-
include/linux/stat.h | 46 ++++++++++++++
include/linux/syscalls.h | 5 ++
11 files changed, 217 insertions(+), 14 deletions(-)
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index beb9b5f..a9953cc 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -343,10 +343,12 @@
#define __NR_rt_tgsigqueueinfo 335
#define __NR_perf_event_open 336
#define __NR_recvmmsg 337
+#define __NR_xstat 338
+#define __NR_fxstat 339
#ifdef __KERNEL__
-#define NR_syscalls 338
+#define NR_syscalls 340
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index ff4307b..c90d240 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -663,6 +663,10 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
#define __NR_recvmmsg 299
__SYSCALL(__NR_recvmmsg, sys_recvmmsg)
+#define __NR_xstat 300
+__SYSCALL(__NR_xstat, sys_xstat)
+#define __NR_fxstat 301
+__SYSCALL(__NR_fxstat, sys_fxstat)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index ee3190a..1b5b4c8 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -300,16 +300,18 @@ error_unlock:
/*
* read the attributes of an inode
*/
-int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
- struct kstat *stat)
+int afs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
- struct inode *inode;
-
- inode = dentry->d_inode;
+ struct inode *inode = dentry->d_inode;
_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
generic_fillattr(inode, stat);
+
+ stat->result_flags |=
+ XSTAT_QUERY_INODE_VERSION | XSTAT_QUERY_DATA_VERSION;
+ stat->inode_version = inode->i_generation;
+ stat->data_version = inode->i_version;
return 0;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 19a4de5..96823f3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1571,6 +1571,8 @@ extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
+extern int ext4_file_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat);
extern void ext4_delete_inode(struct inode *);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 5313ae4..18c29ab 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -150,7 +150,7 @@ const struct file_operations ext4_file_operations = {
const struct inode_operations ext4_file_inode_operations = {
.truncate = ext4_truncate,
.setattr = ext4_setattr,
- .getattr = ext4_getattr,
+ .getattr = ext4_file_getattr,
#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 42272d6..8e374f3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5550,12 +5550,33 @@ err_out:
int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
- struct inode *inode;
- unsigned long delalloc_blocks;
+ struct inode *inode = dentry->d_inode;
- inode = dentry->d_inode;
generic_fillattr(inode, stat);
+ stat->result_flags |= XSTAT_QUERY_CREATION_TIME;
+ stat->crtime.tv_sec = EXT4_I(inode)->i_crtime.tv_sec;
+ stat->crtime.tv_nsec = EXT4_I(inode)->i_crtime.tv_nsec;
+
+ if (inode->i_ino != EXT4_ROOT_INO) {
+ stat->result_flags |= XSTAT_QUERY_INODE_VERSION;
+ stat->inode_version = inode->i_generation;
+ }
+ if (S_ISDIR(inode->i_mode)) {
+ stat->result_flags |= XSTAT_QUERY_DATA_VERSION;
+ stat->data_version = inode->i_version;
+ }
+ return 0;
+}
+
+int ext4_file_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ unsigned long delalloc_blocks;
+
+ ext4_getattr(mnt, dentry, stat);
+
/*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a43e661..0f776c7 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2542,6 +2542,7 @@ const struct inode_operations ext4_dir_inode_operations = {
.mknod = ext4_mknod,
.rename = ext4_rename,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
@@ -2554,6 +2555,7 @@ const struct inode_operations ext4_dir_inode_operations = {
const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index ed9354a..d8fe7fb 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -35,6 +35,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
@@ -47,6 +48,7 @@ const struct inode_operations ext4_fast_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = ext4_follow_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
#ifdef CONFIG_EXT4_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
diff --git a/fs/stat.c b/fs/stat.c
index 12e90e2..5edb63a 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -115,7 +115,7 @@ 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",
@@ -140,7 +140,7 @@ 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;
@@ -222,7 +222,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
#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;
@@ -408,6 +408,125 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
}
#endif /* __ARCH_WANT_STAT64 */
+/*
+ * check the input parameters in the xstat struct
+ */
+static noinline int xstat_check_param(struct xstat __user *buffer, size_t bufsize,
+ struct kstat *stat)
+{
+ u32 struct_version;
+ int ret;
+
+ /* if the buffer isn't large enough, return how much we wanted to
+ * write, but otherwise do nothing */
+ if (bufsize < sizeof(struct xstat))
+ return sizeof(struct xstat);
+
+ ret = get_user(struct_version, &buffer->struct_version);
+ if (ret < 0)
+ return ret;
+ if (struct_version != 0)
+ return -ENOTSUPP;
+
+ memset(stat, 0xde, sizeof(*stat));
+
+ ret = get_user(stat->query_flags, &buffer->query_flags);
+ if (ret < 0)
+ return ret;
+
+ /* nothing outside this set has a defined purpose */
+ stat->query_flags &= (XSTAT_QUERY_CREATION_TIME |
+ XSTAT_QUERY_INODE_VERSION |
+ XSTAT_QUERY_DATA_VERSION);
+
+ /* the user gets these whatever */
+ stat->query_flags |= (XSTAT_QUERY_CREATION_TIME |
+ XSTAT_QUERY_INODE_VERSION |
+ XSTAT_QUERY_DATA_VERSION);
+ stat->result_flags = 0;
+ return 0;
+}
+
+/*
+ * copy the extended stats to userspace and return the amount of data written
+ * into the buffer
+ */
+static noinline long xstat_set_result(struct kstat *stat,
+ struct xstat __user *buffer, size_t bufsize)
+{
+ struct xstat tmp;
+
+ memset(&tmp, 0, sizeof(tmp));
+ tmp.struct_version = XSTAT_STRUCT_VERSION;
+ tmp.query_flags = stat->result_flags;
+ tmp.st_dev.major = MAJOR(stat->dev);
+ tmp.st_dev.minor = MINOR(stat->dev);
+ tmp.st_rdev.major = MAJOR(stat->rdev);
+ tmp.st_rdev.minor = MINOR(stat->rdev);
+ tmp.st_ino = stat->ino;
+ tmp.st_mode = stat->mode;
+ tmp.st_nlink = stat->nlink;
+ tmp.st_uid = stat->uid;
+ tmp.st_gid = stat->gid;
+ tmp.st_atime.tv_sec = stat->atime.tv_sec;
+ tmp.st_atime.tv_nsec = stat->atime.tv_nsec;
+ tmp.st_mtime.tv_sec = stat->mtime.tv_sec;
+ tmp.st_mtime.tv_nsec = stat->mtime.tv_nsec;
+ tmp.st_ctime.tv_sec = stat->ctime.tv_sec;
+ tmp.st_ctime.tv_nsec = stat->ctime.tv_nsec;
+ tmp.st_size = stat->size;
+ tmp.st_blocks = stat->blocks;
+ tmp.st_blksize = stat->blksize;
+
+ if (stat->result_flags & XSTAT_QUERY_CREATION_TIME) {
+ tmp.st_crtime.tv_sec = stat->crtime.tv_sec;
+ tmp.st_crtime.tv_nsec = stat->crtime.tv_nsec;
+ }
+ if (stat->result_flags & XSTAT_QUERY_INODE_VERSION)
+ tmp.st_inode_version = stat->inode_version;
+ if (stat->result_flags & XSTAT_QUERY_DATA_VERSION)
+ tmp.st_data_version = stat->data_version;
+
+ return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : sizeof(tmp);
+}
+
+/*
+ * System call to get extended stats by path
+ */
+SYSCALL_DEFINE5(xstat,
+ int, dfd, const char __user *, filename, unsigned, atflag,
+ struct xstat __user *, buffer, size_t, bufsize)
+{
+ struct kstat stat;
+ int error;
+
+ error = xstat_check_param(buffer, bufsize, &stat);
+ if (error != 0)
+ return error;
+ error = vfs_fstatat(dfd, filename, &stat, atflag);
+ if (error)
+ return error;
+ return xstat_set_result(&stat, buffer, bufsize);
+}
+
+/*
+ * System call to get extended stats by file descriptor
+ */
+SYSCALL_DEFINE3(fxstat, int, fd, struct xstat __user *, buffer, size_t, bufsize)
+{
+ struct kstat stat;
+ int error;
+
+ error = xstat_check_param(buffer, bufsize, &stat);
+ if (error < 0)
+ return error;
+ error = vfs_fstat(fd, &stat);
+ if (error)
+ return error;
+
+ return xstat_set_result(&stat, buffer, bufsize);
+}
+
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
void __inode_add_bytes(struct inode *inode, loff_t bytes)
{
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 611c398..d48bb5d 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -46,6 +46,45 @@
#endif
+/*
+ * Extended stat structures
+ */
+struct xstat_dev {
+ unsigned int major;
+ unsigned int minor;
+};
+
+struct xstat_time {
+ unsigned long long tv_sec;
+ unsigned long long tv_nsec;
+};
+
+struct xstat {
+ unsigned int struct_version;
+#define XSTAT_STRUCT_VERSION 0
+ unsigned int st_mode;
+ unsigned int st_nlink;
+ unsigned int st_uid;
+ unsigned int st_gid;
+ unsigned int st_blksize;
+ struct xstat_dev st_rdev;
+ struct xstat_dev st_dev;
+ unsigned long long st_ino;
+ unsigned long long st_size;
+ struct xstat_time st_atime;
+ struct xstat_time st_mtime;
+ struct xstat_time st_ctime;
+ struct xstat_time st_crtime;
+ unsigned long long st_blocks;
+ unsigned long long st_inode_version;
+ unsigned long long st_data_version;
+ unsigned long long query_flags;
+#define XSTAT_QUERY_CREATION_TIME 0x00000001ULL
+#define XSTAT_QUERY_INODE_VERSION 0x00000002ULL
+#define XSTAT_QUERY_DATA_VERSION 0x00000004ULL
+ unsigned long long extra_results[0];
+};
+
#ifdef __KERNEL__
#define S_IRWXUGO (S_IRWXU|S_IRWXG|S_IRWXO)
#define S_IALLUGO (S_ISUID|S_ISGID|S_ISVTX|S_IRWXUGO)
@@ -68,11 +107,16 @@ struct kstat {
gid_t gid;
dev_t rdev;
loff_t size;
- struct timespec atime;
+ struct timespec atime;
struct timespec mtime;
struct timespec ctime;
+ struct timespec crtime;
unsigned long blksize;
unsigned long long blocks;
+ u64 query_flags; /* what extras the user asked for */
+ u64 result_flags; /* what extras the user got */
+ u64 inode_version;
+ u64 data_version;
};
#endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8812a63..760a303 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -44,6 +44,7 @@ struct shmid_ds;
struct sockaddr;
struct stat;
struct stat64;
+struct xstat;
struct statfs;
struct statfs64;
struct __sysctl_args;
@@ -824,4 +825,8 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
unsigned long fd, unsigned long pgoff);
asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
+asmlinkage long sys_xstat(int, const char __user *, unsigned,
+ struct xstat __user *, size_t);
+asmlinkage long sys_fxstat(int, struct xstat __user *, size_t);
+
#endif
On Tue, Jun 29, 2010 at 13:03, David Howells <[email protected]> wrote:
> Add a pair of system calls to make extended file stats available, including
> file creation time, inode version and data version where available through the
> underlying filesystem:
If you add something like this you might want to integrate another
extension. This has been discussed a long time ago. In almost no
situation all the information is needed. Some of the pieces of
information returned by the syscall might be harder to collect than
other. It makes sense in such a situation to allow the caller to
specify what she is interested in. A bitmask of some sort. This was
brought up by the HPC people with gigantic filesystems.
For this the syscall interface should have a parameter to specify what
is requested and the stat-like structure should have a field
specifying what is actually present. The latter bitmask must be a
superset of the former.
Previous discussions centered around reusing the stat data structure
and somehow make it work. But no clean solution was found. If a new
structure is added anyway this could solve the issue.
And while you're at it, maybe some spare fields at the end are nice.
On Tue, Jun 29, 2010 at 5:13 PM, Ulrich Drepper <[email protected]> wrote:
> On Tue, Jun 29, 2010 at 13:03, David Howells <[email protected]> wrote:
>> Add a pair of system calls to make extended file stats available, including
>> file creation time, inode version and data version where available through the
>> underlying filesystem:
>
> If you add something like this you might want to integrate another
> extension. ?This has been discussed a long time ago. ?In almost no
> situation all the information is needed. ?Some of the pieces of
> information returned by the syscall might be harder to collect than
> other. ?It makes sense in such a situation to allow the caller to
> specify what she is interested in. ?A bitmask of some sort. ?This was
> brought up by the HPC people with gigantic filesystems.
>
> For this the syscall interface should have a parameter to specify what
> is requested and the stat-like structure should have a field
> specifying what is actually present. ?The latter bitmask must be a
> superset of the former.
>
> Previous discussions centered around reusing the stat data structure
> and somehow make it work. ?But no clean solution was found. ?If a new
> structure is added anyway this could solve the issue.
That makes sense, especially for network file systems. NFSv4
protocol spec anticipates that:
"With the NFS version 4 protocol, the client is able query what attributes
the server supports and construct requests with only those supported
attributes (or a subset thereof)."
and we were talking about something similar for SMB2 Unix Extensions
(posix extensions) at the last plugfest (for SMB2 kernel
client to Samba)
and testing events.
--
Thanks,
Steve
Ulrich Drepper <[email protected]> wrote:
> On Tue, Jun 29, 2010 at 13:03, David Howells <[email protected]> wrote:
> > Add a pair of system calls to make extended file stats available,
> > including file creation time, inode version and data version where
> > available through the underlying filesystem:
>
> If you add something like this you might want to integrate another
> extension. This has been discussed a long time ago. In almost no
> situation all the information is needed. Some of the pieces of
> information returned by the syscall might be harder to collect than
> other.
Trond mentioned this:
There has been a lot of interest in allowing the user to specify
exactly which fields they want the filesystem to return, and whether
or not the kernel can use cached data or not. The main use is to allow
specification of a 'stat light' that could help speed up
"readdir()+multiple stat()" type queries. At last year's Filesystem
and Storage Workshop, Mark Fasheh actually came up with an initial
design:
http://www.kerneltrap.com/mailarchive/linux-fsdevel/2009/4/7/5427274
It'd be easy enough to absorb the functionality from that patch.
> It makes sense in such a situation to allow the caller to specify what she
> is interested in. A bitmask of some sort.
I have one of those. See the query_flags field. One question, though, is how
to break things down. Obvious groupings of the already extant stat stuff
might be:
- st_dev, st_ino, st_mode, st_nlink, st_uid, st_gid, st_rdev, st_size
- st_block, st_blksize
- st_atime, st_mtime, st_ctime
However, what seems obvious to me might not be for some netfs or other.
> For this the syscall interface should have a parameter to specify what
> is requested and the stat-like structure should have a field
> specifying what is actually present. The latter bitmask must be a
> superset of the former.
Got that.
> Previous discussions centered around reusing the stat data structure
> and somehow make it work. But no clean solution was found. If a new
> structure is added anyway this could solve the issue.
That's what I thought. Linux has a tangled mess of stat structs:-/
> And while you're at it, maybe some spare fields at the end are nice.
I made it so that the syscall can return variable length data: the main xstat
struct, plus extra records yet to be defined. They could even be variable
length and assembled/disassembled with something like the control message
macros for recvmsg().
David
On Tue, 29 Jun 2010, David Howells wrote:
> Ulrich Drepper <[email protected]> wrote:
>
> > On Tue, Jun 29, 2010 at 13:03, David Howells <[email protected]> wrote:
> > > Add a pair of system calls to make extended file stats available,
> > > including file creation time, inode version and data version where
> > > available through the underlying filesystem:
> >
> > If you add something like this you might want to integrate another
> > extension. This has been discussed a long time ago. In almost no
> > situation all the information is needed. Some of the pieces of
> > information returned by the syscall might be harder to collect than
> > other.
>
> Trond mentioned this:
>
> There has been a lot of interest in allowing the user to specify
> exactly which fields they want the filesystem to return, and whether
> or not the kernel can use cached data or not. The main use is to allow
> specification of a 'stat light' that could help speed up
> "readdir()+multiple stat()" type queries. At last year's Filesystem
> and Storage Workshop, Mark Fasheh actually came up with an initial
> design:
>
> http://www.kerneltrap.com/mailarchive/linux-fsdevel/2009/4/7/5427274
>
> It'd be easy enough to absorb the functionality from that patch.
That would be nice. HPC folks have been looking for this functionality
for some time now.
> > It makes sense in such a situation to allow the caller to specify what she
> > is interested in. A bitmask of some sort.
>
> I have one of those. See the query_flags field. One question, though, is how
> to break things down. Obvious groupings of the already extant stat stuff
> might be:
>
> - st_dev, st_ino, st_mode, st_nlink, st_uid, st_gid, st_rdev, st_size
> - st_block, st_blksize
> - st_atime, st_mtime, st_ctime
>
> However, what seems obvious to me might not be for some netfs or other.
The problem is that groupings that may seem logical now may not match
reality for some specific file system for various implementation reasons.
IMO a bit per field makes the most sense, with some simple way to include
all fields (-1 or 0). A mask argument that is separate from flags might
make that simpler?
sage
On Tue, Jun 29, 2010 at 11:36:56PM +0100, David Howells wrote:
> Ulrich Drepper <[email protected]> wrote:
> > And while you're at it, maybe some spare fields at the end are nice.
>
> I made it so that the syscall can return variable length data: the main xstat
> struct, plus extra records yet to be defined. They could even be variable
> length and assembled/disassembled with something like the control message
> macros for recvmsg().
The less variable length stuff the better, I think. At least,
for the stuff stat(2) already returns, you should have a fixed-size
structure. Even if I only pass the GIVE_ME_UIDS flag, I don't want to
have to deal with the variable size stuff until I've actually asked for
esoteric things. I'll know that the non-UIDS fields are garbage by the
fact that I didn't ask for them.
Joel
--
"Time is an illusion, lunchtime doubly so."
-Douglas Adams
Joel Becker
Consulting Software Developer
Oracle
E-mail: [email protected]
Phone: (650) 506-8127
Joel Becker <[email protected]> wrote:
> The less variable length stuff the better, I think. At least,
> for the stuff stat(2) already returns, you should have a fixed-size
> structure. Even if I only pass the GIVE_ME_UIDS flag, I don't want to
> have to deal with the variable size stuff until I've actually asked for
> esoteric things. I'll know that the non-UIDS fields are garbage by the
> fact that I didn't ask for them.
I was thinking of the fixed length xstat struct plus appendable extensions to
be defined later.
I could live with each defined extension being of a fixed length, so for
example, you set bit 20, and it adds, say, a 16-byte volume ID in the
appropriate order, padded out appropriately for the filesystem.
David
On Tuesday 29 June 2010 22:03:15 David Howells wrote:
> ssize_t ret = xstat(int dfd,
> const char *filename,
> unsigned atflag,
> struct xstat *buffer,
> size_t buflen);
>
> ssize_t ret = fxstat(int fd,
> struct xstat *buffer,
> size_t buflen);
>
>
> The dfd, filename, atflag and fd parameters indicate the file to query. There
> is no equivalent of lstat() as that can be emulated with xstat(), passing 0
> instead of AT_SYMLINK_NOFOLLOW as atflag.
Do we actually need the fxstat variant? IIRC, some *at syscalls just
operate on dfd when filename==NULL, which would be trivial to do here.
Arnd
Arnd Bergmann <[email protected]> wrote:
> Do we actually need the fxstat variant? IIRC, some *at syscalls just
> operate on dfd when filename==NULL, which would be trivial to do here.
user_path_at() doesn't seem to work like that, so fstatat() doesn't. It's a
possibility though.
David
On Wed, Jun 30, 2010 at 12:29:52AM +0100, David Howells wrote:
> Joel Becker <[email protected]> wrote:
>
> > The less variable length stuff the better, I think. At least,
> > for the stuff stat(2) already returns, you should have a fixed-size
> > structure. Even if I only pass the GIVE_ME_UIDS flag, I don't want to
> > have to deal with the variable size stuff until I've actually asked for
> > esoteric things. I'll know that the non-UIDS fields are garbage by the
> > fact that I didn't ask for them.
>
> I was thinking of the fixed length xstat struct plus appendable extensions to
> be defined later.
I meant this.
Joel
--
Life's Little Instruction Book #267
"Lie on your back and look at the stars."
Joel Becker
Consulting Software Developer
Oracle
E-mail: [email protected]
Phone: (650) 506-8127