* [PATCH 01/18] Mark arguments to certain syscalls as being const [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
` (16 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Mark arguments to certain system calls as being const where they should be but
aren't. The list includes:
(*) The filename arguments of various stat syscalls, execve(), various utimes
syscalls and some mount syscalls.
(*) The filename arguments of some syscall helpers relating to the above.
(*) The buffer argument of various write syscalls.
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/alpha/kernel/osf_sys.c | 6 +++---
arch/alpha/kernel/process.c | 2 +-
arch/arm/kernel/sys_arm.c | 4 ++--
arch/arm/kernel/sys_oabi-compat.c | 6 +++---
arch/avr32/include/asm/syscalls.h | 2 +-
arch/avr32/kernel/process.c | 3 ++-
arch/blackfin/kernel/process.c | 2 +-
arch/frv/kernel/process.c | 3 ++-
arch/h8300/kernel/process.c | 2 +-
arch/ia64/include/asm/unistd.h | 2 +-
arch/ia64/kernel/process.c | 2 +-
arch/m32r/kernel/process.c | 3 ++-
arch/m68k/kernel/process.c | 2 +-
arch/m68knommu/kernel/process.c | 2 +-
arch/microblaze/kernel/sys_microblaze.c | 2 +-
arch/mips/kernel/syscall.c | 2 +-
arch/mn10300/kernel/process.c | 2 +-
arch/parisc/hpux/fs.c | 7 ++++---
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/sys_ppc32.c | 2 +-
arch/s390/kernel/compat_linux.c | 10 +++++-----
arch/s390/kernel/compat_linux.h | 10 +++++-----
arch/s390/kernel/entry.h | 2 +-
arch/s390/kernel/process.c | 2 +-
arch/sh/include/asm/syscalls_32.h | 2 +-
arch/sh/include/asm/syscalls_64.h | 2 +-
arch/sh/kernel/process_64.c | 2 +-
arch/sparc/kernel/sys_sparc32.c | 7 ++++---
arch/um/kernel/exec.c | 6 +++---
arch/um/kernel/internal.h | 2 +-
arch/um/kernel/syscall.c | 2 +-
arch/x86/ia32/sys_ia32.c | 14 +++++++-------
arch/x86/include/asm/sys_ia32.h | 12 ++++++------
arch/x86/include/asm/syscalls.h | 2 +-
arch/x86/kernel/entry_64.S | 4 ++--
arch/x86/kernel/process.c | 2 +-
arch/xtensa/kernel/process.c | 2 +-
fs/compat.c | 23 +++++++++++++----------
fs/stat.c | 29 ++++++++++++++++++-----------
fs/utimes.c | 7 ++++---
include/linux/compat.h | 6 +++---
include/linux/fs.h | 6 +++---
include/linux/syscalls.h | 20 ++++++++++----------
include/linux/time.h | 2 +-
44 files changed, 125 insertions(+), 109 deletions(-)
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index de9d397..1719fe3 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -244,7 +244,7 @@ do_osf_statfs(struct dentry * dentry, struct osf_statfs __user *buffer,
return error;
}
-SYSCALL_DEFINE3(osf_statfs, char __user *, pathname,
+SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
struct osf_statfs __user *, buffer, unsigned long, bufsiz)
{
struct path path;
@@ -358,7 +358,7 @@ osf_procfs_mount(char *dirname, struct procfs_args __user *args, int flags)
return do_mount("", dirname, "proc", flags, NULL);
}
-SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path,
+SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path,
int, flag, void __user *, data)
{
int retval;
@@ -932,7 +932,7 @@ SYSCALL_DEFINE3(osf_setitimer, int, which, struct itimerval32 __user *, in,
}
-SYSCALL_DEFINE2(osf_utimes, char __user *, filename,
+SYSCALL_DEFINE2(osf_utimes, const char __user *, filename,
struct timeval32 __user *, tvs)
{
struct timespec tv[2];
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 395a464..88e608a 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -387,7 +387,7 @@ EXPORT_SYMBOL(dump_elf_task_fp);
* sys_execve() executes a new program.
*/
asmlinkage int
-do_sys_execve(char __user *ufilename, char __user * __user *argv,
+do_sys_execve(const char __user *ufilename, char __user * __user *argv,
char __user * __user *envp, struct pt_regs *regs)
{
int error;
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index c235018..5b7c541 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -62,7 +62,7 @@ asmlinkage int sys_vfork(struct pt_regs *regs)
/* sys_execve() executes a new program.
* This is called indirectly via a small wrapper
*/
-asmlinkage int sys_execve(char __user *filenamei, char __user * __user *argv,
+asmlinkage int sys_execve(const char __user *filenamei, char __user * __user *argv,
char __user * __user *envp, struct pt_regs *regs)
{
int error;
@@ -84,7 +84,7 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
int ret;
memset(®s, 0, sizeof(struct pt_regs));
- ret = do_execve((char *)filename, (char __user * __user *)argv,
+ ret = do_execve(filename, (char __user * __user *)argv,
(char __user * __user *)envp, ®s);
if (ret < 0)
goto out;
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 33ff678..4ad8da1 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -141,7 +141,7 @@ static long cp_oldabi_stat64(struct kstat *stat,
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-asmlinkage long sys_oabi_stat64(char __user * filename,
+asmlinkage long sys_oabi_stat64(const char __user * filename,
struct oldabi_stat64 __user * statbuf)
{
struct kstat stat;
@@ -151,7 +151,7 @@ asmlinkage long sys_oabi_stat64(char __user * filename,
return error;
}
-asmlinkage long sys_oabi_lstat64(char __user * filename,
+asmlinkage long sys_oabi_lstat64(const char __user * filename,
struct oldabi_stat64 __user * statbuf)
{
struct kstat stat;
@@ -172,7 +172,7 @@ asmlinkage long sys_oabi_fstat64(unsigned long fd,
}
asmlinkage long sys_oabi_fstatat64(int dfd,
- char __user *filename,
+ const char __user *filename,
struct oldabi_stat64 __user *statbuf,
int flag)
{
diff --git a/arch/avr32/include/asm/syscalls.h b/arch/avr32/include/asm/syscalls.h
index 66a1972..ab608b7 100644
--- a/arch/avr32/include/asm/syscalls.h
+++ b/arch/avr32/include/asm/syscalls.h
@@ -21,7 +21,7 @@ asmlinkage int sys_clone(unsigned long, unsigned long,
unsigned long, unsigned long,
struct pt_regs *);
asmlinkage int sys_vfork(struct pt_regs *);
-asmlinkage int sys_execve(char __user *, char __user *__user *,
+asmlinkage int sys_execve(const char __user *, char __user *__user *,
char __user *__user *, struct pt_regs *);
/* kernel/signal.c */
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 2d76515..e5daddf 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -383,7 +383,8 @@ asmlinkage int sys_vfork(struct pt_regs *regs)
0, NULL, NULL);
}
-asmlinkage int sys_execve(char __user *ufilename, char __user *__user *uargv,
+asmlinkage int sys_execve(const char __user *ufilename,
+ char __user *__user *uargv,
char __user *__user *uenvp, struct pt_regs *regs)
{
int error;
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 93ec07d..a566f61 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -209,7 +209,7 @@ copy_thread(unsigned long clone_flags,
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp)
+asmlinkage int sys_execve(const char __user *name, char __user * __user *argv, char __user * __user *envp)
{
int error;
char *filename;
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 21d0fd1..428931c 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -250,7 +250,8 @@ int copy_thread(unsigned long clone_flags,
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp)
+asmlinkage int sys_execve(const char __user *name, char __user * __user *argv,
+ char __user * __user *envp)
{
int error;
char * filename;
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 8c8b0ff..8b7b78d 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -212,7 +212,7 @@ int copy_thread(unsigned long clone_flags,
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char *name, char **argv, char **envp,int dummy,...)
+asmlinkage int sys_execve(const char *name, char **argv, char **envp,int dummy,...)
{
int error;
char * filename;
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index bb8b0ff..46f36fc 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -353,7 +353,7 @@ asmlinkage unsigned long sys_mmap2(
int fd, long pgoff);
struct pt_regs;
struct sigaction;
-long sys_execve(char __user *filename, char __user * __user *argv,
+long sys_execve(const char __user *filename, char __user * __user *argv,
char __user * __user *envp, struct pt_regs *regs);
asmlinkage long sys_ia64_pipe(void);
asmlinkage long sys_rt_sigaction(int sig,
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 53f1648..a879c03 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -633,7 +633,7 @@ dump_fpu (struct pt_regs *pt, elf_fpregset_t dst)
}
long
-sys_execve (char __user *filename, char __user * __user *argv, char __user * __user *envp,
+sys_execve (const char __user *filename, char __user * __user *argv, char __user * __user *envp,
struct pt_regs *regs)
{
char *fname;
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index bc8c8c1..8665a4d 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -288,7 +288,8 @@ asmlinkage int sys_vfork(unsigned long r0, unsigned long r1, unsigned long r2,
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char __user *ufilename, char __user * __user *uargv,
+asmlinkage int sys_execve(const char __user *ufilename,
+ char __user * __user *uargv,
char __user * __user *uenvp,
unsigned long r3, unsigned long r4, unsigned long r5,
unsigned long r6, struct pt_regs regs)
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 1a6be27..221d0b7 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -315,7 +315,7 @@ EXPORT_SYMBOL(dump_fpu);
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp)
+asmlinkage int sys_execve(const char __user *name, char __user * __user *argv, char __user * __user *envp)
{
int error;
char * filename;
diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c
index 6aa6613..6350f68 100644
--- a/arch/m68knommu/kernel/process.c
+++ b/arch/m68knommu/kernel/process.c
@@ -350,7 +350,7 @@ void dump(struct pt_regs *fp)
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char *name, char **argv, char **envp)
+asmlinkage int sys_execve(const char *name, char **argv, char **envp)
{
int error;
char * filename;
diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c
index f4e00b7..6abab6e 100644
--- a/arch/microblaze/kernel/sys_microblaze.c
+++ b/arch/microblaze/kernel/sys_microblaze.c
@@ -47,7 +47,7 @@ asmlinkage long microblaze_clone(int flags, unsigned long stack, struct pt_regs
return do_fork(flags, stack, regs, 0, NULL, NULL);
}
-asmlinkage long microblaze_execve(char __user *filenamei, char __user *__user *argv,
+asmlinkage long microblaze_execve(const char __user *filenamei, char __user *__user *argv,
char __user *__user *envp, struct pt_regs *regs)
{
int error;
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index dd81b0f..6322c39 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -207,7 +207,7 @@ asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs)
int error;
char * filename;
- filename = getname((char __user *) (long)regs.regs[4]);
+ filename = getname((const char __user *) (long)regs.regs[4]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 82b817c..762eb32 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -268,7 +268,7 @@ asmlinkage long sys_vfork(void)
0, NULL, NULL);
}
-asmlinkage long sys_execve(char __user *name,
+asmlinkage long sys_execve(const char __user *name,
char __user * __user *argv,
char __user * __user *envp)
{
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 6935123..1444875 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -36,7 +36,7 @@ int hpux_execve(struct pt_regs *regs)
int error;
char *filename;
- filename = getname((char __user *) regs->gr[26]);
+ filename = getname((const char __user *) regs->gr[26]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
@@ -169,7 +169,7 @@ static int cp_hpux_stat(struct kstat *stat, struct hpux_stat64 __user *statbuf)
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-long hpux_stat64(char __user *filename, struct hpux_stat64 __user *statbuf)
+long hpux_stat64(const char __user *filename, struct hpux_stat64 __user *statbuf)
{
struct kstat stat;
int error = vfs_stat(filename, &stat);
@@ -191,7 +191,8 @@ long hpux_fstat64(unsigned int fd, struct hpux_stat64 __user *statbuf)
return error;
}
-long hpux_lstat64(char __user *filename, struct hpux_stat64 __user *statbuf)
+long hpux_lstat64(const char __user *filename,
+ struct hpux_stat64 __user *statbuf)
{
struct kstat stat;
int error = vfs_lstat(filename, &stat);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 773424d..3ef6ed4 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -991,7 +991,7 @@ int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
int error;
char *filename;
- filename = getname((char __user *) a0);
+ filename = getname((const char __user *) a0);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 19471a1..20fd701 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -546,7 +546,7 @@ compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_siz
return sys_pread64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo);
}
-compat_ssize_t compat_sys_pwrite64(unsigned int fd, char __user *ubuf, compat_size_t count,
+compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count,
u32 reg6, u32 poshi, u32 poslo)
{
return sys_pwrite64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo);
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 73b624e..1e6449c 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -436,7 +436,7 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo)
* sys32_execve() executes a new program after the asm stub has set
* things up for us. This should basically do what I want it to.
*/
-asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
+asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
compat_uptr_t __user *envp)
{
struct pt_regs *regs = task_pt_regs(current);
@@ -570,7 +570,7 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat)
return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-asmlinkage long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf)
+asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
{
struct kstat stat;
int ret = vfs_stat(filename, &stat);
@@ -579,7 +579,7 @@ asmlinkage long sys32_stat64(char __user * filename, struct stat64_emu31 __user
return ret;
}
-asmlinkage long sys32_lstat64(char __user * filename, struct stat64_emu31 __user * statbuf)
+asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
{
struct kstat stat;
int ret = vfs_lstat(filename, &stat);
@@ -597,7 +597,7 @@ asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * sta
return ret;
}
-asmlinkage long sys32_fstatat64(unsigned int dfd, char __user *filename,
+asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename,
struct stat64_emu31 __user* statbuf, int flag)
{
struct kstat stat;
@@ -655,7 +655,7 @@ asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
return sys_read(fd, buf, count);
}
-asmlinkage long sys32_write(unsigned int fd, char __user * buf, size_t count)
+asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count)
{
if ((compat_ssize_t) count < 0)
return -EINVAL;
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index cb97afc..9635d75 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -193,7 +193,7 @@ long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set,
compat_sigset_t __user *oset, size_t sigsetsize);
long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize);
long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo);
-long sys32_execve(char __user *name, compat_uptr_t __user *argv,
+long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
compat_uptr_t __user *envp);
long sys32_init_module(void __user *umod, unsigned long len,
const char __user *uargs);
@@ -207,16 +207,16 @@ long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset,
size_t count);
long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset,
s32 count);
-long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf);
-long sys32_lstat64(char __user * filename,
+long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf);
+long sys32_lstat64(const char __user * filename,
struct stat64_emu31 __user * statbuf);
long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf);
-long sys32_fstatat64(unsigned int dfd, char __user *filename,
+long sys32_fstatat64(unsigned int dfd, const char __user *filename,
struct stat64_emu31 __user* statbuf, int flag);
unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg);
long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg);
long sys32_read(unsigned int fd, char __user * buf, size_t count);
-long sys32_write(unsigned int fd, char __user * buf, size_t count);
+long sys32_write(unsigned int fd, const char __user * buf, size_t count);
long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise);
long sys32_fadvise64_64(struct fadvise64_64_args __user *args);
long sys32_sigaction(int sig, const struct old_sigaction32 __user *act,
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index eb15c12..e2c048b 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -42,7 +42,7 @@ long sys_clone(unsigned long newsp, unsigned long clone_flags,
int __user *parent_tidptr, int __user *child_tidptr);
long sys_vfork(void);
void execve_tail(void);
-long sys_execve(char __user *name, char __user * __user *argv,
+long sys_execve(const char __user *name, char __user * __user *argv,
char __user * __user *envp);
long sys_sigsuspend(int history0, int history1, old_sigset_t mask);
long sys_sigaction(int sig, const struct old_sigaction __user *act,
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 1039fde..7eafaf2 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -267,7 +267,7 @@ asmlinkage void execve_tail(void)
/*
* sys_execve() executes a new program.
*/
-SYSCALL_DEFINE3(execve, char __user *, name, char __user * __user *, argv,
+SYSCALL_DEFINE3(execve, const char __user *, name, char __user * __user *, argv,
char __user * __user *, envp)
{
struct pt_regs *regs = task_pt_regs(current);
diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h
index 8b30200..be201fd 100644
--- a/arch/sh/include/asm/syscalls_32.h
+++ b/arch/sh/include/asm/syscalls_32.h
@@ -19,7 +19,7 @@ asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
asmlinkage int sys_vfork(unsigned long r4, unsigned long r5,
unsigned long r6, unsigned long r7,
struct pt_regs __regs);
-asmlinkage int sys_execve(char __user *ufilename, char __user * __user *uargv,
+asmlinkage int sys_execve(const char __user *ufilename, char __user * __user *uargv,
char __user * __user *uenvp, unsigned long r7,
struct pt_regs __regs);
asmlinkage int sys_sigsuspend(old_sigset_t mask, unsigned long r5,
diff --git a/arch/sh/include/asm/syscalls_64.h b/arch/sh/include/asm/syscalls_64.h
index 751fd88..ee519f4 100644
--- a/arch/sh/include/asm/syscalls_64.h
+++ b/arch/sh/include/asm/syscalls_64.h
@@ -21,7 +21,7 @@ asmlinkage int sys_vfork(unsigned long r2, unsigned long r3,
unsigned long r4, unsigned long r5,
unsigned long r6, unsigned long r7,
struct pt_regs *pregs);
-asmlinkage int sys_execve(char *ufilename, char **uargv,
+asmlinkage int sys_execve(const char *ufilename, char **uargv,
char **uenvp, unsigned long r5,
unsigned long r6, unsigned long r7,
struct pt_regs *pregs);
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index d4ca648..68d128d 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -483,7 +483,7 @@ asmlinkage int sys_vfork(unsigned long r2, unsigned long r3,
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char *ufilename, char **uargv,
+asmlinkage int sys_execve(const char *ufilename, char **uargv,
char **uenvp, unsigned long r5,
unsigned long r6, unsigned long r7,
struct pt_regs *pregs)
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index c0ca875..e6375a7 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -162,7 +162,7 @@ static int cp_compat_stat64(struct kstat *stat,
return err;
}
-asmlinkage long compat_sys_stat64(char __user * filename,
+asmlinkage long compat_sys_stat64(const char __user * filename,
struct compat_stat64 __user *statbuf)
{
struct kstat stat;
@@ -173,7 +173,7 @@ asmlinkage long compat_sys_stat64(char __user * filename,
return error;
}
-asmlinkage long compat_sys_lstat64(char __user * filename,
+asmlinkage long compat_sys_lstat64(const char __user * filename,
struct compat_stat64 __user *statbuf)
{
struct kstat stat;
@@ -195,7 +195,8 @@ asmlinkage long compat_sys_fstat64(unsigned int fd,
return error;
}
-asmlinkage long compat_sys_fstatat64(unsigned int dfd, char __user *filename,
+asmlinkage long compat_sys_fstatat64(unsigned int dfd,
+ const char __user *filename,
struct compat_stat64 __user * statbuf, int flag)
{
struct kstat stat;
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 97974c1..59b20d9 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -44,7 +44,7 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
PT_REGS_SP(regs) = esp;
}
-static long execve1(char *file, char __user * __user *argv,
+static long execve1(const char *file, char __user * __user *argv,
char __user *__user *env)
{
long error;
@@ -61,7 +61,7 @@ static long execve1(char *file, char __user * __user *argv,
return error;
}
-long um_execve(char *file, char __user *__user *argv, char __user *__user *env)
+long um_execve(const char *file, char __user *__user *argv, char __user *__user *env)
{
long err;
@@ -71,7 +71,7 @@ long um_execve(char *file, char __user *__user *argv, char __user *__user *env)
return err;
}
-long sys_execve(char __user *file, char __user *__user *argv,
+long sys_execve(const char __user *file, char __user *__user *argv,
char __user *__user *env)
{
long error;
diff --git a/arch/um/kernel/internal.h b/arch/um/kernel/internal.h
index 3bda43c..1303a10 100644
--- a/arch/um/kernel/internal.h
+++ b/arch/um/kernel/internal.h
@@ -1 +1 @@
-extern long um_execve(char *file, char __user *__user *argv, char __user *__user *env);
+extern long um_execve(const char *file, char __user *__user *argv, char __user *__user *env);
diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c
index 4393173..7427c0b 100644
--- a/arch/um/kernel/syscall.c
+++ b/arch/um/kernel/syscall.c
@@ -58,7 +58,7 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
fs = get_fs();
set_fs(KERNEL_DS);
- ret = um_execve((char *)filename, (char __user *__user *)argv,
+ ret = um_execve(filename, (char __user *__user *)argv,
(char __user *__user *) envp);
set_fs(fs);
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 626be15..1baddad 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -51,7 +51,7 @@
#define AA(__x) ((unsigned long)(__x))
-asmlinkage long sys32_truncate64(char __user *filename,
+asmlinkage long sys32_truncate64(const char __user *filename,
unsigned long offset_low,
unsigned long offset_high)
{
@@ -96,7 +96,7 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
return 0;
}
-asmlinkage long sys32_stat64(char __user *filename,
+asmlinkage long sys32_stat64(const char __user *filename,
struct stat64 __user *statbuf)
{
struct kstat stat;
@@ -107,7 +107,7 @@ asmlinkage long sys32_stat64(char __user *filename,
return ret;
}
-asmlinkage long sys32_lstat64(char __user *filename,
+asmlinkage long sys32_lstat64(const char __user *filename,
struct stat64 __user *statbuf)
{
struct kstat stat;
@@ -126,7 +126,7 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
return ret;
}
-asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename,
+asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename,
struct stat64 __user *statbuf, int flag)
{
struct kstat stat;
@@ -408,8 +408,8 @@ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}
-asmlinkage long sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count,
- u32 poslo, u32 poshi)
+asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
+ u32 count, u32 poslo, u32 poshi)
{
return sys_pwrite64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
@@ -449,7 +449,7 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd,
return ret;
}
-asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
+asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
compat_uptr_t __user *envp, struct pt_regs *regs)
{
long error;
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 3ad4217..c8a052a 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -18,13 +18,13 @@
#include <asm/ia32.h>
/* ia32/sys_ia32.c */
-asmlinkage long sys32_truncate64(char __user *, unsigned long, unsigned long);
+asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long);
asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long);
-asmlinkage long sys32_stat64(char __user *, struct stat64 __user *);
-asmlinkage long sys32_lstat64(char __user *, struct stat64 __user *);
+asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *);
+asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *);
asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long sys32_fstatat(unsigned int, char __user *,
+asmlinkage long sys32_fstatat(unsigned int, const char __user *,
struct stat64 __user *, int);
struct mmap_arg_struct32;
asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *);
@@ -49,12 +49,12 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t);
asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *);
asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32);
-asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32);
+asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
asmlinkage long sys32_personality(unsigned long);
asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
-asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *,
+asmlinkage long sys32_execve(const char __user *, compat_uptr_t __user *,
compat_uptr_t __user *, struct pt_regs *);
asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 5c044b4..feb2ff9 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -23,7 +23,7 @@ long sys_iopl(unsigned int, struct pt_regs *);
/* kernel/process.c */
int sys_fork(struct pt_regs *);
int sys_vfork(struct pt_regs *);
-long sys_execve(char __user *, char __user * __user *,
+long sys_execve(const char __user *, char __user * __user *,
char __user * __user *, struct pt_regs *);
long sys_clone(unsigned long, unsigned long, void __user *,
void __user *, struct pt_regs *);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0697ff1..77f5986 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1185,13 +1185,13 @@ END(kernel_thread_helper)
* execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
*
* C extern interface:
- * extern long execve(char *name, char **argv, char **envp)
+ * extern long execve(const char *name, char **argv, char **envp)
*
* asm input arguments:
* rdi: name, rsi: argv, rdx: envp
*
* We want to fallback into:
- * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs)
+ * extern long sys_execve(const char *name, char **argv,char **envp, struct pt_regs *regs)
*
* do_sys_execve asm fallback arguments:
* rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e7e3521..f5c816e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -300,7 +300,7 @@ EXPORT_SYMBOL(kernel_thread);
/*
* sys_execve() executes a new program.
*/
-long sys_execve(char __user *name, char __user * __user *argv,
+long sys_execve(const char __user *name, char __user * __user *argv,
char __user * __user *envp, struct pt_regs *regs)
{
long error;
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index f167e0f..7c2f38f 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -318,7 +318,7 @@ long xtensa_clone(unsigned long clone_flags, unsigned long newsp,
*/
asmlinkage
-long xtensa_execve(char __user *name, char __user * __user *argv,
+long xtensa_execve(const char __user *name, char __user * __user *argv,
char __user * __user *envp,
long a3, long a4, long a5,
struct pt_regs *regs)
diff --git a/fs/compat.c b/fs/compat.c
index 6490d21..d72591a 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -76,7 +76,8 @@ int compat_printk(const char *fmt, ...)
* Not all architectures have sys_utime, so implement this in terms
* of sys_utimes.
*/
-asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __user *t)
+asmlinkage long compat_sys_utime(const char __user *filename,
+ struct compat_utimbuf __user *t)
{
struct timespec tv[2];
@@ -90,7 +91,7 @@ asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __
return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
}
-asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename, struct compat_timespec __user *t, int flags)
+asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, struct compat_timespec __user *t, int flags)
{
struct timespec tv[2];
@@ -105,7 +106,7 @@ asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename, st
return do_utimes(dfd, filename, t ? tv : NULL, flags);
}
-asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, struct compat_timeval __user *t)
+asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct compat_timeval __user *t)
{
struct timespec tv[2];
@@ -124,7 +125,7 @@ asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, st
return do_utimes(dfd, filename, t ? tv : NULL, 0);
}
-asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval __user *t)
+asmlinkage long compat_sys_utimes(const char __user *filename, struct compat_timeval __user *t)
{
return compat_sys_futimesat(AT_FDCWD, filename, t);
}
@@ -168,7 +169,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
return err;
}
-asmlinkage long compat_sys_newstat(char __user * filename,
+asmlinkage long compat_sys_newstat(const char __user * filename,
struct compat_stat __user *statbuf)
{
struct kstat stat;
@@ -180,7 +181,7 @@ asmlinkage long compat_sys_newstat(char __user * filename,
return cp_compat_stat(&stat, statbuf);
}
-asmlinkage long compat_sys_newlstat(char __user * filename,
+asmlinkage long compat_sys_newlstat(const char __user * filename,
struct compat_stat __user *statbuf)
{
struct kstat stat;
@@ -193,7 +194,8 @@ asmlinkage long compat_sys_newlstat(char __user * filename,
}
#ifndef __ARCH_WANT_STAT64
-asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user *filename,
+asmlinkage long compat_sys_newfstatat(unsigned int dfd,
+ const char __user *filename,
struct compat_stat __user *statbuf, int flag)
{
struct kstat stat;
@@ -836,9 +838,10 @@ static int do_nfs4_super_data_conv(void *raw_data)
#define NCPFS_NAME "ncpfs"
#define NFS4_NAME "nfs4"
-asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name,
- char __user * type, unsigned long flags,
- void __user * data)
+asmlinkage long compat_sys_mount(const char __user * dev_name,
+ const char __user * dir_name,
+ const char __user * type, unsigned long flags,
+ const void __user * data)
{
char *kernel_type;
unsigned long data_page;
diff --git a/fs/stat.c b/fs/stat.c
index c4ecd52..12e90e2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -68,7 +68,8 @@ int vfs_fstat(unsigned int fd, struct kstat *stat)
}
EXPORT_SYMBOL(vfs_fstat);
-int vfs_fstatat(int dfd, char __user *filename, struct kstat *stat, int flag)
+int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
+ int flag)
{
struct path path;
int error = -EINVAL;
@@ -91,13 +92,13 @@ out:
}
EXPORT_SYMBOL(vfs_fstatat);
-int vfs_stat(char __user *name, struct kstat *stat)
+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(char __user *name, struct kstat *stat)
+int vfs_lstat(const char __user *name, struct kstat *stat)
{
return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}
@@ -147,7 +148,8 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-SYSCALL_DEFINE2(stat, char __user *, filename, struct __old_kernel_stat __user *, statbuf)
+SYSCALL_DEFINE2(stat, const char __user *, filename,
+ struct __old_kernel_stat __user *, statbuf)
{
struct kstat stat;
int error;
@@ -159,7 +161,8 @@ SYSCALL_DEFINE2(stat, char __user *, filename, struct __old_kernel_stat __user *
return cp_old_stat(&stat, statbuf);
}
-SYSCALL_DEFINE2(lstat, char __user *, filename, struct __old_kernel_stat __user *, statbuf)
+SYSCALL_DEFINE2(lstat, const char __user *, filename,
+ struct __old_kernel_stat __user *, statbuf)
{
struct kstat stat;
int error;
@@ -234,7 +237,8 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-SYSCALL_DEFINE2(newstat, char __user *, filename, struct stat __user *, statbuf)
+SYSCALL_DEFINE2(newstat, const char __user *, filename,
+ struct stat __user *, statbuf)
{
struct kstat stat;
int error = vfs_stat(filename, &stat);
@@ -244,7 +248,8 @@ SYSCALL_DEFINE2(newstat, char __user *, filename, struct stat __user *, statbuf)
return cp_new_stat(&stat, statbuf);
}
-SYSCALL_DEFINE2(newlstat, char __user *, filename, struct stat __user *, statbuf)
+SYSCALL_DEFINE2(newlstat, const char __user *, filename,
+ struct stat __user *, statbuf)
{
struct kstat stat;
int error;
@@ -257,7 +262,7 @@ SYSCALL_DEFINE2(newlstat, char __user *, filename, struct stat __user *, statbuf
}
#if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
-SYSCALL_DEFINE4(newfstatat, int, dfd, char __user *, filename,
+SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename,
struct stat __user *, statbuf, int, flag)
{
struct kstat stat;
@@ -355,7 +360,8 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-SYSCALL_DEFINE2(stat64, char __user *, filename, struct stat64 __user *, statbuf)
+SYSCALL_DEFINE2(stat64, const char __user *, filename,
+ struct stat64 __user *, statbuf)
{
struct kstat stat;
int error = vfs_stat(filename, &stat);
@@ -366,7 +372,8 @@ SYSCALL_DEFINE2(stat64, char __user *, filename, struct stat64 __user *, statbuf
return error;
}
-SYSCALL_DEFINE2(lstat64, char __user *, filename, struct stat64 __user *, statbuf)
+SYSCALL_DEFINE2(lstat64, const char __user *, filename,
+ struct stat64 __user *, statbuf)
{
struct kstat stat;
int error = vfs_lstat(filename, &stat);
@@ -388,7 +395,7 @@ SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
return error;
}
-SYSCALL_DEFINE4(fstatat64, int, dfd, char __user *, filename,
+SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
struct stat64 __user *, statbuf, int, flag)
{
struct kstat stat;
diff --git a/fs/utimes.c b/fs/utimes.c
index e4c75db..179b586 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -126,7 +126,8 @@ out:
* must be owner or have write permission.
* Else, update from *times, must be owner or super user.
*/
-long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags)
+long do_utimes(int dfd, const char __user *filename, struct timespec *times,
+ int flags)
{
int error = -EINVAL;
@@ -170,7 +171,7 @@ out:
return error;
}
-SYSCALL_DEFINE4(utimensat, int, dfd, char __user *, filename,
+SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename,
struct timespec __user *, utimes, int, flags)
{
struct timespec tstimes[2];
@@ -188,7 +189,7 @@ SYSCALL_DEFINE4(utimensat, int, dfd, char __user *, filename,
return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags);
}
-SYSCALL_DEFINE3(futimesat, int, dfd, char __user *, filename,
+SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename,
struct timeval __user *, utimes)
{
struct timeval times[2];
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 168f7da..9ddc878 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -331,7 +331,7 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
const compat_sigset_t __user *sigmask,
compat_size_t sigsetsize);
-asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename,
+asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename,
struct compat_timespec __user *t, int flags);
asmlinkage long compat_sys_signalfd(int ufd,
@@ -348,9 +348,9 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_page,
const int __user *nodes,
int __user *status,
int flags);
-asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename,
+asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename,
struct compat_timeval __user *t);
-asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user * filename,
+asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user * filename,
struct compat_stat __user *statbuf,
int flag);
asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 68ca1b0..f5e7cf2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2349,10 +2349,10 @@ void inode_set_bytes(struct inode *inode, loff_t bytes);
extern int vfs_readdir(struct file *, filldir_t, void *);
-extern int vfs_stat(char __user *, struct kstat *);
-extern int vfs_lstat(char __user *, struct kstat *);
+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 , char __user *, struct kstat *, int);
+extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7f614ce..8812a63 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -393,7 +393,7 @@ asmlinkage long sys_umount(char __user *name, int flags);
asmlinkage long sys_oldumount(char __user *name);
asmlinkage long sys_truncate(const char __user *path, long length);
asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
-asmlinkage long sys_stat(char __user *filename,
+asmlinkage long sys_stat(const char __user *filename,
struct __old_kernel_stat __user *statbuf);
asmlinkage long sys_statfs(const char __user * path,
struct statfs __user *buf);
@@ -402,21 +402,21 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz,
asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf);
asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
struct statfs64 __user *buf);
-asmlinkage long sys_lstat(char __user *filename,
+asmlinkage long sys_lstat(const char __user *filename,
struct __old_kernel_stat __user *statbuf);
asmlinkage long sys_fstat(unsigned int fd,
struct __old_kernel_stat __user *statbuf);
-asmlinkage long sys_newstat(char __user *filename,
+asmlinkage long sys_newstat(const char __user *filename,
struct stat __user *statbuf);
-asmlinkage long sys_newlstat(char __user *filename,
+asmlinkage long sys_newlstat(const char __user *filename,
struct stat __user *statbuf);
asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf);
asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf);
#if BITS_PER_LONG == 32
-asmlinkage long sys_stat64(char __user *filename,
+asmlinkage long sys_stat64(const char __user *filename,
struct stat64 __user *statbuf);
asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf);
-asmlinkage long sys_lstat64(char __user *filename,
+asmlinkage long sys_lstat64(const char __user *filename,
struct stat64 __user *statbuf);
asmlinkage long sys_truncate64(const char __user *path, loff_t length);
asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length);
@@ -756,7 +756,7 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
int newdfd, const char __user *newname, int flags);
asmlinkage long sys_renameat(int olddfd, const char __user * oldname,
int newdfd, const char __user * newname);
-asmlinkage long sys_futimesat(int dfd, char __user *filename,
+asmlinkage long sys_futimesat(int dfd, const char __user *filename,
struct timeval __user *utimes);
asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode);
asmlinkage long sys_fchmodat(int dfd, const char __user * filename,
@@ -765,13 +765,13 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
gid_t group, int flag);
asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
int mode);
-asmlinkage long sys_newfstatat(int dfd, char __user *filename,
+asmlinkage long sys_newfstatat(int dfd, const char __user *filename,
struct stat __user *statbuf, int flag);
-asmlinkage long sys_fstatat64(int dfd, char __user *filename,
+asmlinkage long sys_fstatat64(int dfd, const char __user *filename,
struct stat64 __user *statbuf, int flag);
asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf,
int bufsiz);
-asmlinkage long sys_utimensat(int dfd, char __user *filename,
+asmlinkage long sys_utimensat(int dfd, const char __user *filename,
struct timespec __user *utimes, int flags);
asmlinkage long sys_unshare(unsigned long unshare_flags);
diff --git a/include/linux/time.h b/include/linux/time.h
index ea3559f..16346c0 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -135,7 +135,7 @@ extern void do_gettimeofday(struct timeval *tv);
extern int do_settimeofday(struct timespec *tv);
extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
-extern long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags);
+extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags);
struct itimerval;
extern int do_setitimer(int which, struct itimerval *value,
struct itimerval *ovalue);
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
2010-07-15 2:17 ` [PATCH 01/18] Mark arguments to certain syscalls as being const " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 20:35 ` Arnd Bergmann
` (5 more replies)
2010-07-15 2:17 ` [PATCH 03/18] AFS: Use i_generation not i_version for the vnode uniquifier " David Howells
` (15 subsequent siblings)
17 siblings, 6 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
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.
[This depends on the previously posted pair of patches to (a) constify a number
of syscall string and buffer arguments and (b) rearrange AFS's use of
i_version and i_generation].
This has a number of uses:
(1) Creation time: The SMB protocol carries the creation time, which could be
exported by Samba, which will in turn help CIFS make use of FS-Cache as
that can be used for coherency data.
This is also specified in NFSv4 as a recommended attribute and could be
exported by NFSD [Steve French].
(2) Lightweight stat: Ask for just those details of interest, and allow a
netfs (such as NFS) to approximate anything not of interest, possibly
without going to the server [Trond Myklebust, Ulrich Drepper].
(3) Heavyweight stat: Force a netfs to go to the server, even if it thinks its
cached attributes are up to date [Trond Myklebust].
(4) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd
Schubert].
(5) Data version number: Could be used by userspace NFS servers [Aneesh Kumar].
Can also be used to modify fill_post_wcc() in NFSD which retrieves
i_version directly, but has just called vfs_getattr(). It could get it
from the kstat struct if it used vfs_xgetattr() instead.
(6) BSD stat compatibility: Including more fields from the BSD stat such as
creation time (st_btime) and inode generation number (st_gen) [Jeremy
Allison, Bernd Schubert].
(7) Extra coherency data may be useful in making backups [Andreas Dilger].
(8) Allow the filesystem to indicate what it can/cannot provide: A filesystem
can now say it doesn't support a standard stat feature if that isn't
available.
(9) Make the fields a consistent size on all arches, and make them large.
(10) Can be extended by using more request flags and tagging further data after
the end of the standard return data. Such things as the following could
be returned:
- BSD st_flags or FS_IOC_GETFLAGS.
- Volume ID / Remote Device ID [Steve French].
- Time granularity (NFSv4 time_delta) [Steve French].
- Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
Michael Kerrisk].
This was initially proposed as a set of xattrs, but the general preferance is
for an extended stat structure.
The following structures are defined for the use of these new system calls:
struct xstat_parameters {
unsigned long long request_mask;
};
struct xstat_dev {
unsigned int major, minor;
};
struct xstat_time {
unsigned long long tv_sec, tv_nsec;
};
struct xstat {
unsigned long long st_result_mask;
unsigned int st_mode;
unsigned int st_nlink;
unsigned int st_uid;
unsigned int st_gid;
struct xstat_dev st_rdev;
struct xstat_dev st_dev;
struct xstat_time st_atime;
struct xstat_time st_mtime;
struct xstat_time st_ctime;
struct xstat_time st_btime;
unsigned long long st_ino;
unsigned long long st_size;
unsigned long long st_blksize;
unsigned long long st_blocks;
unsigned long long st_gen;
unsigned long long st_data_version;
unsigned long long st_inode_flags;
unsigned long long st_extra_results[0];
};
where st_btime is the file creation time, st_gen is the inode generation
(i_generation), st_data_version is the data version number (i_version),
st_inode_flags is the flags from FS_IOC_GETFLAGS plus some extras,
request_mask and st_result_mask are bitmasks of data desired/provided and
st_extra_results[] is where as-yet undefined fields are appended.
The defined bits in request_mask and st_result_mask are:
XSTAT_REQUEST_MODE Want/got st_mode
XSTAT_REQUEST_NLINK Want/got st_nlink
XSTAT_REQUEST_UID Want/got st_uid
XSTAT_REQUEST_GID Want/got st_gid
XSTAT_REQUEST_RDEV Want/got st_rdev
XSTAT_REQUEST_ATIME Want/got st_atime
XSTAT_REQUEST_MTIME Want/got st_mtime
XSTAT_REQUEST_CTIME Want/got st_ctime
XSTAT_REQUEST_INO Want/got st_ino
XSTAT_REQUEST_SIZE Want/got st_size
XSTAT_REQUEST_BLOCKS Want/got st_blocks
XSTAT_REQUEST__BASIC_STATS The stuff in the normal stat struct
XSTAT_REQUEST_BTIME Want/got st_btime
XSTAT_REQUEST_GEN Want/got st_gen
XSTAT_REQUEST_DATA_VERSION Want/got st_data_version
XSTAT_REQUEST_INODE_FLAGS Want/got st_inode_flags
XSTAT_REQUEST__EXTENDED_STATS The stuff in the xstat struct
XSTAT_REQUEST__ALL_STATS The defined set of requestables
The defined bits in st_inode_flags are the usual FS_xxx_FL flags in the LSW,
plus some extra flags in the MSW:
FS_SPECIAL_FL Special kernel file, such as found in procfs
FS_AUTOMOUNT_FL Specific automount point
FS_AUTOMOUNT_ANY_FL Free-form automount directory
FS_REMOTE_FL File is remote
FS_ENCRYPTED_FL File is encrypted
FS_SYSTEM_FL File is marked system (DOS/NTFS/CIFS)
FS_TEMPORARY_FL File is temporary (NTFS/CIFS)
FS_OFFLINE_FL File is offline (CIFS)
Note that Ext4 returns flags outside of FS_FL_USER_VISIBLE in response to
FS_IOC_GETFLAGS. Should FS_FL_USER_VISIBLE be extended to cover them? Or
should the extra flags be suppressed?
The system calls are:
ssize_t ret = xstat(int dfd,
const char *filename,
unsigned flags,
const struct xstat_parameters *params,
struct xstat *buffer,
size_t buflen);
ssize_t ret = fxstat(unsigned fd,
unsigned flags,
const struct xstat_parameters *params,
struct xstat *buffer,
size_t buflen);
The dfd, filename, flags and fd parameters indicate the file to query. There
is no equivalent of lstat() as that can be emulated with xstat() by passing
AT_SYMLINK_NOFOLLOW in flags.
AT_FORCE_ATTR_SYNC can also be set in flags. This will require a network
filesystem to synchronise its attributes with the server.
When the system call is executed, the request_mask bitmask is read from the
parameter block to work out what the user is requesting. If params is NULL,
then request_mask will be assumed to be XSTAT_REQUEST__BASIC_STATS.
The request_mask should be set by the caller to specify extra results that the
caller may desire. These come in a number of classes:
(0) dev, blksize.
These are local data and are always available.
(1) mode, nlinks, uid, gid, [amc]time, ino, size, blocks.
These will be returned whether the caller asks for them or not. The
corresponding bits in result_mask will be set to indicate their presence.
If the caller didn't ask for them, then they may be approximated. For
example, NFS won't waste any time updating them from the server, unless as
a byproduct of updating something requested.
(2) rdev.
As for class (1), but this won't be returned if the file is not a blockdev
or chardev. The bit will be cleared if the value is not returned.
(3) File creation time, inode generation and data version.
These will be returned if available whether the caller asked for them or
not. The corresponding bits in result_mask will be set or cleared as
appropriate to indicate their presence.
If the caller didn't ask for them, then they may be approximated. For
example, NFS won't waste any time updating them from the server, unless
as a byproduct of updating something requested.
(4) Inode flags.
Some of the extra flags (in the MSW) may be returned anyway, and if so,
XSTAT_REQUEST_INODE_FLAGS will be set to indicate it. A base set of
flags is stored in a filesystem's file_system_type struct and is loaded
into inode_flags by generic_fileattr() for further addition by the
filesystem.
(5) Extra results.
These will only be returned if the caller asked for them by setting their
bits in request_mask. They will be placed in the buffer after the xstat
struct in ascending result_mask bit order. Any bit set in request_mask
mask will be left set in result_mask 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 and returns a partial result in the
buffer.
At the moment, this will only work on x86_64 as it requires system calls to be
wired up.
=======
TESTING
=======
The following test program can be used to test the xstat system call:
/* Test the xstat() system call
*
* Copyright (C) 2010 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#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>
#define AT_FORCE_ATTR_SYNC 0x800
#define AT_NO_AUTOMOUNT 0x1000
struct xstat_parameters {
unsigned long long request_mask;
#define XSTAT_REQUEST_MODE 0x00000001ULL
#define XSTAT_REQUEST_NLINK 0x00000002ULL
#define XSTAT_REQUEST_UID 0x00000004ULL
#define XSTAT_REQUEST_GID 0x00000008ULL
#define XSTAT_REQUEST_RDEV 0x00000010ULL
#define XSTAT_REQUEST_ATIME 0x00000020ULL
#define XSTAT_REQUEST_MTIME 0x00000040ULL
#define XSTAT_REQUEST_CTIME 0x00000080ULL
#define XSTAT_REQUEST_INO 0x00000100ULL
#define XSTAT_REQUEST_SIZE 0x00000200ULL
#define XSTAT_REQUEST_BLOCKS 0x00000400ULL
#define XSTAT_REQUEST__BASIC_STATS 0x000007ffULL
#define XSTAT_REQUEST_BTIME 0x00000800ULL
#define XSTAT_REQUEST_GEN 0x00001000ULL
#define XSTAT_REQUEST_DATA_VERSION 0x00002000ULL
#define XSTAT_REQUEST_INODE_FLAGS 0x00004000ULL
#define XSTAT_REQUEST__EXTENDED_STATS 0x00007fffULL
#define XSTAT_REQUEST__ALL_STATS 0x00007fffULL
#define XSTAT_REQUEST__EXTRA_STATS (XSTAT_REQUEST__ALL_STATS & ~XSTAT_REQUEST__EXTENDED_STATS)
};
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 long long st_result_mask;
unsigned int st_mode;
unsigned int st_nlink;
unsigned int st_uid;
unsigned int st_gid;
struct xstat_dev st_rdev;
struct xstat_dev st_dev;
struct xstat_time st_atim;
struct xstat_time st_mtim;
struct xstat_time st_ctim;
struct xstat_time st_btim;
unsigned long long st_ino;
unsigned long long st_size;
unsigned long long st_blksize;
unsigned long long st_blocks;
unsigned long long st_gen;
unsigned long long st_data_version;
unsigned long long st_inode_flags;
unsigned long long st_extra_results[0];
};
#define FS__STANDARD_FL 0x00000000ffffffffULL
#define FS_SPECIAL_FL 0x0000000100000000ULL
#define FS_AUTOMOUNT_FL 0x0000000200000000ULL
#define FS_AUTOMOUNT_ANY_FL 0x0000000400000000ULL
#define FS_REMOTE_FL 0x0000000800000000ULL
#define FS_ENCRYPTED_FL 0x0000001000000000ULL
#define FS_SYSTEM_FL 0x0000002000000000ULL
#define FS_TEMPORARY_FL 0x0000004000000000ULL
#define FS_OFFLINE_FL 0x0000008000000000ULL
#define __NR_xstat 300
#define __NR_fxstat 301
static __attribute__((unused))
ssize_t xstat(int dfd, const char *filename, unsigned flags,
struct xstat_parameters *params,
struct xstat *buffer, size_t bufsize)
{
return syscall(__NR_xstat, dfd, filename, flags,
params, buffer, bufsize);
}
static __attribute__((unused))
ssize_t fxstat(int fd, unsigned flags,
struct xstat_parameters *params,
struct xstat *buffer, size_t bufsize)
{
return syscall(__NR_fxstat, fd, flags,
params, buffer, bufsize);
}
static void print_time(const char *field, 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);
}
printf("%s", field);
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);
printf("\n");
}
static void dump_xstat(struct xstat *xst)
{
char buffer[256], ft;
printf("results=%llx\n", xst->st_result_mask);
printf(" ");
if (xst->st_result_mask & XSTAT_REQUEST_SIZE)
printf(" Size: %-15llu", xst->st_size);
if (xst->st_result_mask & XSTAT_REQUEST_BLOCKS)
printf(" Blocks: %-10llu", xst->st_blocks);
printf(" IO Block: %-6llu ", xst->st_blksize);
if (xst->st_result_mask & XSTAT_REQUEST_MODE) {
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", buffer);
if (xst->st_result_mask & XSTAT_REQUEST_INO)
printf(" Inode: %-11llu", xst->st_ino);
if (xst->st_result_mask & XSTAT_REQUEST_SIZE)
printf(" Links: %-5u", xst->st_nlink);
if (xst->st_result_mask & XSTAT_REQUEST_RDEV)
printf(" Device type: %u,%u",
xst->st_rdev.major, xst->st_rdev.minor);
printf("\n");
if (xst->st_result_mask & XSTAT_REQUEST_MODE)
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' : '-');
if (xst->st_result_mask & XSTAT_REQUEST_UID)
printf("Uid: %d \n", xst->st_uid);
if (xst->st_result_mask & XSTAT_REQUEST_GID)
printf("Gid: %u\n", xst->st_gid);
if (xst->st_result_mask & XSTAT_REQUEST_ATIME)
print_time("Access: ", &xst->st_atim);
if (xst->st_result_mask & XSTAT_REQUEST_MTIME)
print_time("Modify: ", &xst->st_mtim);
if (xst->st_result_mask & XSTAT_REQUEST_CTIME)
print_time("Change: ", &xst->st_ctim);
if (xst->st_result_mask & XSTAT_REQUEST_BTIME)
print_time("Create: ", &xst->st_btim);
if (xst->st_result_mask & XSTAT_REQUEST_GEN)
printf("Inode version: %llxh\n", xst->st_gen);
if (xst->st_result_mask & XSTAT_REQUEST_DATA_VERSION)
printf("Data version: %llxh\n", xst->st_data_version);
if (xst->st_result_mask & XSTAT_REQUEST_INODE_FLAGS) {
unsigned char bits;
int loop, byte;
static char flag_representation[64 + 1] =
"????????"
"????????"
"????????"
"otserAaS"
"????????"
"????ehTD"
"tj?IE?XZ"
"AdaiScus"
;
printf("Inode flags: %016llx (", xst->st_inode_flags);
for (byte = 64 - 8; byte >= 0; byte -= 8) {
bits = xst->st_inode_flags >> byte;
for (loop = 7; loop >= 0; loop--) {
int bit = byte + loop;
if (bits & 0x80)
putchar(flag_representation[63 - bit]);
else
putchar('-');
bits <<= 1;
}
if (byte)
putchar(' ');
}
printf(")\n");
}
}
int main(int argc, char **argv)
{
struct xstat_parameters params;
union {
struct xstat xst;
unsigned long long raw[4096 / 8];
} buffer;
int ret, atflag = AT_SYMLINK_NOFOLLOW;
unsigned long long query = XSTAT_REQUEST__ALL_STATS;
for (argv++; *argv; argv++) {
if (strcmp(*argv, "-F") == 0) {
atflag |= AT_FORCE_ATTR_SYNC;
continue;
}
if (strcmp(*argv, "-L") == 0) {
atflag &= ~AT_SYMLINK_NOFOLLOW;
continue;
}
if (strcmp(*argv, "-O") == 0) {
query &= ~XSTAT_REQUEST__BASIC_STATS;
continue;
}
if (strcmp(*argv, "-A") == 0) {
atflag |= AT_NO_AUTOMOUNT;
continue;
}
memset(&buffer, 0xbf, sizeof(buffer));
params.request_mask = query;
ret = xstat(AT_FDCWD, *argv, atflag, ¶ms, &buffer.xst,
sizeof(buffer));
printf("xstat(%s) = %d\n", *argv, ret);
if (ret < 0) {
perror(*argv);
exit(1);
}
dump_xstat(&buffer.xst);
ret = (ret + 7) / 8;
if (ret > sizeof(buffer.xst) / 8) {
unsigned offset, print_offset = 1, col = 0;
if (ret > sizeof(buffer) / 8)
ret = sizeof(buffer) / 8;
for (offset = sizeof(buffer.xst) / 8; offset < ret; offset++) {
if (print_offset) {
printf("%04x: ", offset * 8);
print_offset = 0;
}
printf("%016llx", buffer.raw[offset]);
col++;
if ((col & 3) == 0) {
printf("\n");
print_offset = 1;
} else {
printf(" ");
}
}
if (!print_offset)
printf("\n");
}
}
return 0;
}
Just compile and run, passing it paths to the files you want to examine:
[root@andromeda ~]# /tmp/xstat /proc/$$
xstat(/proc/2074) = 160
results=47ef
Size: 0 Blocks: 0 IO Block: 1024 directory
Device: 00:03 Inode: 9072 Links: 7
Access: (0555/dr-xr-xr-x) Uid: 0
Gid: 0
Access: 2010-07-14 16:50:46.609336272+0100
Modify: 2010-07-14 16:50:46.609336272+0100
Change: 2010-07-14 16:50:46.609336272+0100
Inode flags: 0000000100000000 (-------- -------- -------- -------S -------- -------- -------- --------)
[root@andromeda ~]# /tmp/xstat /afs/archive/linuxdev/fedora9/x86_64/kernel-devel-2.6.25.10-86.fc9.x86_64.rpm
xstat(/afs/archive/linuxdev/fedora9/x86_64/kernel-devel-2.6.25.10-86.fc9.x86_64.rpm) = 160
results=77ef
Size: 5413882 Blocks: 0 IO Block: 4096 regular file
Device: 00:15 Inode: 2288 Links: 1
Access: (0644/-rw-r--r--) Uid: 75338
Gid: 0
Access: 2008-11-05 19:47:22.000000000+0000
Modify: 2008-11-05 19:47:22.000000000+0000
Change: 2008-11-05 19:47:22.000000000+0000
Inode version: 795h
Data version: 2h
Inode flags: 0000000800000000 (-------- -------- -------- ----r--- -------- -------- -------- --------)
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/x86/include/asm/unistd_32.h | 4
arch/x86/include/asm/unistd_64.h | 4
fs/stat.c | 322 +++++++++++++++++++++++++++++++++++---
include/linux/fcntl.h | 1
include/linux/fs.h | 4
include/linux/stat.h | 119 ++++++++++++++
include/linux/syscalls.h | 9 +
7 files changed, 436 insertions(+), 27 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/stat.c b/fs/stat.c
index 12e90e2..89d72fc 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -18,6 +18,15 @@
#include <asm/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;
@@ -33,11 +42,37 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
stat->size = i_size_read(inode);
stat->blocks = inode->i_blocks;
stat->blksize = (1 << inode->i_blkbits);
+ stat->inode_flags = inode->i_sb->s_type->inode_flags;
+ stat->result_mask |= XSTAT_REQUEST__BASIC_STATS & ~XSTAT_REQUEST_RDEV;
+ if (unlikely(S_ISBLK(stat->mode) || S_ISCHR(stat->mode)))
+ stat->result_mask |= XSTAT_REQUEST_RDEV;
+ if (stat->inode_flags)
+ stat->result_mask |= XSTAT_REQUEST_INODE_FLAGS;
}
-
EXPORT_SYMBOL(generic_fillattr);
-int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+/**
+ * vfs_xgetattr - Get the extended attributes of a file
+ * @mnt: The mountpoint to which the dentry belongs
+ * @dentry: The file of interest
+ * @stat: Where to return the statistics
+ *
+ * Ask the filesystem for a file's attributes. The caller must have preset
+ * stat->request_mask and stat->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_FORCE_ATTR_SYNC in query_flags.
+ *
+ * Bits must have been set in stat->request_mask to indicate which attributes
+ * the caller wants retrieving. Only attributes from the set
+ * XSTAT_REQUEST__EXTENDED_STATS can be retrieved through this interface. 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_xgetattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
int retval;
@@ -46,61 +81,176 @@ int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
if (retval)
return retval;
+ stat->result_mask = 0;
if (inode->i_op->getattr)
return inode->i_op->getattr(mnt, dentry, stat);
generic_fillattr(inode, stat);
return 0;
}
+EXPORT_SYMBOL(vfs_xgetattr);
+/**
+ * vfs_getattr - Get the basic attributes of a file
+ * @mnt: The mountpoint to which the dentry belongs
+ * @dentry: The file of interest
+ * @stat: Where to return the statistics
+ *
+ * Ask the filesystem for a file's attributes. If remote, the filesystem isn't
+ * forced to update its files from the backing store. Only the basic set of
+ * attributes will be retrieved; anyone wanting more must use vfs_getxattr(),
+ * as must anyone who wants to force attributes to be sync'd with the server.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+ stat->query_flags = 0;
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ return vfs_xgetattr(mnt, dentry, stat);
+}
EXPORT_SYMBOL(vfs_getattr);
-int vfs_fstat(unsigned int fd, struct kstat *stat)
+/**
+ * vfs_fxstat - Get extended attributes by file descriptor
+ * @fd: The file descriptor refering to the file of interest
+ * @stat: The result structure to fill in.
+ *
+ * This function is a wrapper around vfs_xgetattr(). The main difference is
+ * that it uses a file descriptor to determine the file location.
+ *
+ * The caller must have preset stat->query_flags and stat->request_mask as for
+ * vfs_xgetattr().
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_fxstat(unsigned int fd, struct kstat *stat)
{
struct file *f = fget(fd);
int error = -EBADF;
+ if (stat->query_flags & ~KSTAT_QUERY_FLAGS)
+ return -EINVAL;
if (f) {
- error = vfs_getattr(f->f_path.mnt, f->f_path.dentry, stat);
+ error = vfs_xgetattr(f->f_path.mnt, f->f_path.dentry, stat);
fput(f);
}
return error;
}
+EXPORT_SYMBOL(vfs_fxstat);
+
+/**
+ * vfs_fstat - Get basic attributes by file descriptor
+ * @fd: The file descriptor refering to the file of interest
+ * @stat: The result structure to fill in.
+ *
+ * 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_fstat(unsigned int fd, struct kstat *stat)
+{
+ stat->query_flags = 0;
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ return vfs_fxstat(fd, stat);
+}
EXPORT_SYMBOL(vfs_fstat);
-int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
- int flag)
+/**
+ * vfs_xstat - Get extended 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.
+ *
+ * This function is a wrapper around vfs_xgetattr(). The main difference is
+ * that it uses a filename and base directory to determine the file location.
+ * Additionally, the addition of AT_SYMLINK_NOFOLLOW to flags will prevent a
+ * symlink at the given name from being referenced.
+ *
+ * The caller must have preset stat->request_mask as for vfs_xgetattr(). 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_xstat(int dfd, const char __user *filename, int flags,
+ struct kstat *stat)
{
struct path path;
- int error = -EINVAL;
- int lookup_flags = 0;
+ int error, lookup_flags;
- if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
- goto out;
+ if (flags & ~(AT_SYMLINK_NOFOLLOW | KSTAT_QUERY_FLAGS))
+ return -EINVAL;
- if (!(flag & AT_SYMLINK_NOFOLLOW))
- lookup_flags |= LOOKUP_FOLLOW;
+ stat->query_flags = flags & KSTAT_QUERY_FLAGS;
+ lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
error = user_path_at(dfd, filename, lookup_flags, &path);
- if (error)
- goto out;
-
- error = vfs_getattr(path.mnt, path.dentry, stat);
- path_put(&path);
-out:
+ if (!error) {
+ error = vfs_xgetattr(path.mnt, path.dentry, stat);
+ path_put(&path);
+ }
return error;
}
+EXPORT_SYMBOL(vfs_xstat);
+
+/**
+ * vfs_fstatat - Get basic 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.
+ *
+ * This function is a wrapper around vfs_xstat(). The difference is that it
+ * preselects basic stats only. The flags are used to load up
+ * stat->query_flags in addition to indicating symlink handling during path
+ * resolution.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
+ int flags)
+{
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ return vfs_xstat(dfd, filename, flags, stat);
+}
EXPORT_SYMBOL(vfs_fstatat);
-int vfs_stat(const char __user *name, struct kstat *stat)
+/**
+ * vfs_stat - Get basic attributes by filename
+ * @filename: The name of the file of interest
+ * @stat: The result structure to fill in.
+ *
+ * This function is a wrapper around vfs_xstat(). The difference is that it
+ * preselects basic stats only, terminal symlinks are followed regardless and a
+ * remote filesystem can't be forced to query the server. If such is desired,
+ * vfs_xstat() should be used instead.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_stat(const char __user *filename, struct kstat *stat)
{
- return vfs_fstatat(AT_FDCWD, name, stat, 0);
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ return vfs_xstat(AT_FDCWD, filename, 0, stat);
}
EXPORT_SYMBOL(vfs_stat);
+/**
+ * vfs_stat - Get basic attributes by filename, without following terminal symlink
+ * @filename: The name of the file of interest
+ * @stat: The result structure to fill in.
+ *
+ * This function is a wrapper around vfs_xstat(). The difference is that it
+ * preselects basic stats only, terminal symlinks are note followed regardless
+ * and a remote filesystem can't be forced to query the server. If such is
+ * desired, vfs_xstat() should be used instead.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
int vfs_lstat(const char __user *name, struct kstat *stat)
{
- return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
+ return vfs_xstat(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW, stat);
}
EXPORT_SYMBOL(vfs_lstat);
@@ -115,7 +265,7 @@ 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 +290,7 @@ 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 +372,7 @@ 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 +558,130 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
}
#endif /* __ARCH_WANT_STAT64 */
+/*
+ * Get the xstat parameters if supplied
+ */
+static int xstat_get_params(struct xstat_parameters __user *_params,
+ struct kstat *stat)
+{
+ struct xstat_parameters params;
+
+ memset(stat, 0xde, sizeof(*stat)); // DEBUGGING
+
+ if (_params) {
+ if (copy_from_user(¶ms, _params, sizeof(params)) != 0)
+ return -EFAULT;
+ stat->request_mask =
+ params.request_mask & XSTAT_REQUEST__ALL_STATS;
+ } else {
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ }
+ stat->result_mask = 0;
+ return 0;
+}
+
+/*
+ * Set the xstat results.
+ *
+ * If the buffer size was 0, we just return the size of the buffer needed to
+ * return the full result.
+ *
+ * If bufsize indicates a buffer of insufficient size to hold the full result,
+ * we return -E2BIG.
+ *
+ * Otherwise we copy the extended stats to userspace and return the amount of
+ * data written into the buffer (or -EFAULT).
+ */
+static long xstat_set_result(struct kstat *stat,
+ struct xstat __user *buffer, size_t bufsize)
+{
+ struct xstat tmp;
+ size_t result_size = sizeof(tmp);
+
+ if (bufsize == 0)
+ return result_size;
+ if (bufsize < result_size)
+ return -E2BIG;
+
+ /* transfer the fixed results */
+ memset(&tmp, 0, sizeof(tmp));
+ tmp.st_result_mask = stat->result_mask;
+ tmp.st_mode = stat->mode;
+ tmp.st_nlink = stat->nlink;
+ tmp.st_uid = stat->uid;
+ tmp.st_gid = stat->gid;
+ tmp.st_blksize = stat->blksize;
+ tmp.st_rdev.major = MAJOR(stat->rdev);
+ tmp.st_rdev.minor = MINOR(stat->rdev);
+ tmp.st_dev.major = MAJOR(stat->dev);
+ tmp.st_dev.minor = MINOR(stat->dev);
+ 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_ino = stat->ino;
+ tmp.st_size = stat->size;
+ tmp.st_blocks = stat->blocks;
+
+ if (tmp.st_result_mask & XSTAT_REQUEST_BTIME) {
+ tmp.st_btime.tv_sec = stat->btime.tv_sec;
+ tmp.st_btime.tv_nsec = stat->btime.tv_nsec;
+ }
+ if (tmp.st_result_mask & XSTAT_REQUEST_GEN)
+ tmp.st_gen = stat->gen;
+ if (tmp.st_result_mask & XSTAT_REQUEST_DATA_VERSION)
+ tmp.st_data_version = stat->data_version;
+ if (tmp.st_result_mask & XSTAT_REQUEST_INODE_FLAGS)
+ tmp.st_inode_flags = stat->inode_flags;
+
+ if (copy_to_user(buffer, &tmp, result_size) != 0)
+ return -EFAULT;
+ return result_size;
+}
+
+/*
+ * System call to get extended stats by path
+ */
+SYSCALL_DEFINE6(xstat,
+ int, dfd, const char __user *, filename, unsigned, atflag,
+ struct xstat_parameters __user *, params,
+ struct xstat __user *, buffer, size_t, bufsize)
+{
+ struct kstat stat;
+ int error;
+
+ error = xstat_get_params(params, &stat);
+ if (error != 0)
+ return error;
+ error = vfs_xstat(dfd, filename, atflag, &stat);
+ if (error)
+ return error;
+ return xstat_set_result(&stat, buffer, bufsize);
+}
+
+/*
+ * System call to get extended stats by file descriptor
+ */
+SYSCALL_DEFINE5(fxstat, unsigned int, fd, unsigned int, flags,
+ struct xstat_parameters __user *, params,
+ struct xstat __user *, buffer, size_t, bufsize)
+{
+ struct kstat stat;
+ int error;
+
+ error = xstat_get_params(params, &stat);
+ if (error < 0)
+ return error;
+ stat.query_flags = flags;
+ error = vfs_fxstat(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/fcntl.h b/include/linux/fcntl.h
index afc00af..bcf8083 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -45,6 +45,7 @@
#define AT_REMOVEDIR 0x200 /* Remove directory instead of
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
+#define AT_FORCE_ATTR_SYNC 0x800 /* Force the attributes to be sync'd with the server */
#ifdef __KERNEL__
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5e7cf2..951c36b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1735,6 +1735,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc);
struct file_system_type {
const char *name;
int fs_flags;
+ u64 inode_flags; /* base inode_flags for generic_getattr() */
int (*get_sb) (struct file_system_type *, int,
const char *, void *, struct vfsmount *);
void (*kill_sb) (struct super_block *);
@@ -2341,6 +2342,7 @@ extern const struct inode_operations page_symlink_inode_operations;
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int vfs_xgetattr(struct vfsmount *, struct dentry *, struct kstat *);
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);
@@ -2353,6 +2355,8 @@ 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_xstat(int, const char __user *, int, struct kstat *);
+extern int vfs_xfstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 611c398..41a3c22 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -46,6 +46,114 @@
#endif
+/*
+ * Extended stat structures
+ */
+struct xstat_parameters {
+ /* Query request/result mask
+ *
+ * Bits should be set in request_mask to request particular items
+ * before calling xstat() or fxstat().
+ *
+ * For each item in the set XSTAT_REQUEST__EXTENDED_STATS:
+ *
+ * - if not available at all, the bit will be cleared before returning
+ * and the field will be cleared; otherwise,
+ *
+ * - if AT_FORCE_ATTR_SYNC is set, then the datum will be synchronised
+ * to the server and the bit will be set on return; otherwise,
+ *
+ * - if requested, the datum will be synchronised to a server or other
+ * hardware if out of date before being returned, and the bit will be
+ * set on return; 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 bit will be cleared before returning, and the field will be
+ * cleared.
+ *
+ * For each item not in the set XSTAT_REQUEST__EXTENDED_STATS
+ *
+ * - if not available at all, the bit will be cleared, and no result
+ * data will be returned; otherwise,
+ *
+ * - if requested, the datum will be synchronised to a server or other
+ * hardware before being appended if necessary, and the bit will be
+ * set on return; otherwise,
+ *
+ * - the bit will be cleared, and no result data will be returned.
+ *
+ * Items in XSTAT_REQUEST__BASIC_STATS may be marked unavailable on
+ * return, but they will have a value installed for compatibility
+ * purposes.
+ */
+ unsigned long long request_mask;
+#define XSTAT_REQUEST_MODE 0x00000001ULL /* want/got st_mode */
+#define XSTAT_REQUEST_NLINK 0x00000002ULL /* want/got st_nlink */
+#define XSTAT_REQUEST_UID 0x00000004ULL /* want/got st_uid */
+#define XSTAT_REQUEST_GID 0x00000008ULL /* want/got st_gid */
+#define XSTAT_REQUEST_RDEV 0x00000010ULL /* want/got st_rdev */
+#define XSTAT_REQUEST_ATIME 0x00000020ULL /* want/got st_atime */
+#define XSTAT_REQUEST_MTIME 0x00000040ULL /* want/got st_mtime */
+#define XSTAT_REQUEST_CTIME 0x00000080ULL /* want/got st_ctime */
+#define XSTAT_REQUEST_INO 0x00000100ULL /* want/got st_ino */
+#define XSTAT_REQUEST_SIZE 0x00000200ULL /* want/got st_size */
+#define XSTAT_REQUEST_BLOCKS 0x00000400ULL /* want/got st_blocks */
+#define XSTAT_REQUEST__BASIC_STATS 0x000007ffULL /* the stuff in the normal stat struct */
+#define XSTAT_REQUEST_BTIME 0x00000800ULL /* want/got st_btime */
+#define XSTAT_REQUEST_GEN 0x00001000ULL /* want/got st_gen */
+#define XSTAT_REQUEST_DATA_VERSION 0x00002000ULL /* want/got st_data_version */
+#define XSTAT_REQUEST_INODE_FLAGS 0x00004000ULL /* want/got st_inode_flags */
+#define XSTAT_REQUEST__EXTENDED_STATS 0x00007fffULL /* the stuff in the xstat struct */
+#define XSTAT_REQUEST__ALL_STATS 0x00007fffULL /* the defined set of requestables */
+};
+
+struct xstat_dev {
+ unsigned int major, minor;
+};
+
+struct xstat_time {
+ unsigned long long tv_sec, tv_nsec;
+};
+
+struct xstat {
+ unsigned long long st_result_mask; /* what results were written */
+ unsigned int st_mode; /* file mode */
+ unsigned int st_nlink; /* number of hard links */
+ unsigned int st_uid; /* user ID of owner */
+ unsigned int st_gid; /* group ID of owner */
+ struct xstat_dev st_rdev; /* device ID of special file */
+ struct xstat_dev st_dev; /* ID of device containing file */
+ struct xstat_time st_atime; /* last access time */
+ struct xstat_time st_mtime; /* last data modification time */
+ struct xstat_time st_ctime; /* last attribute change time */
+ struct xstat_time st_btime; /* file creation time */
+ unsigned long long st_ino; /* inode number */
+ unsigned long long st_size; /* file size */
+ unsigned long long st_blksize; /* block size for filesystem I/O */
+ unsigned long long st_blocks; /* number of 512-byte blocks allocated */
+ unsigned long long st_gen; /* inode generation number */
+ unsigned long long st_data_version; /* data version number */
+ unsigned long long st_inode_flags; /* inode flags (!= BSD st_flags) */
+ unsigned long long st_extra_results[0]; /* extra requested results */
+};
+
+#define FS__STANDARD_FL 0x00000000ffffffffULL /* As for user visible FS_IOC_GETFLAGS */
+#define FS_SPECIAL_FL 0x0000000100000000ULL /* Special file as found in procfs/sysfs */
+#define FS_AUTOMOUNT_FL 0x0000000200000000ULL /* Specific automount point */
+#define FS_AUTOMOUNT_ANY_FL 0x0000000400000000ULL /* Unspecific automount directory */
+#define FS_REMOTE_FL 0x0000000800000000ULL /* File is remote */
+#define FS_ENCRYPTED_FL 0x0000001000000000ULL /* File is encrypted */
+#define FS_HIDDEN_FL 0x0000002000000000ULL /* File is marked hidden (DOS+) */
+#define FS_SYSTEM_FL 0x0000004000000000ULL /* File is marked system (DOS+) */
+#define FS_ARCHIVE_FL 0x0000008000000000ULL /* File is marked archive (DOS+) */
+#define FS_TEMPORARY_FL 0x0000010000000000ULL /* File is temporary (NTFS/CIFS) */
+#define FS_OFFLINE_FL 0x0000020000000000ULL /* File is offline (CIFS) */
+#define FS_REPARSE_POINT_FL 0x0000040000000000ULL /* Reparse point (NTFS/CIFS) */
+
#ifdef __KERNEL__
#define S_IRWXUGO (S_IRWXU|S_IRWXG|S_IRWXO)
#define S_IALLUGO (S_ISUID|S_ISGID|S_ISVTX|S_IRWXUGO)
@@ -60,6 +168,8 @@
#include <linux/time.h>
struct kstat {
+ u64 request_mask; /* what fields the user asked for */
+ u64 result_mask; /* what fields the user got */
u64 ino;
dev_t dev;
umode_t mode;
@@ -67,14 +177,19 @@ struct kstat {
uid_t uid;
gid_t gid;
dev_t rdev;
+ unsigned int query_flags; /* operational flags */
+#define KSTAT_QUERY_FLAGS (AT_FORCE_ATTR_SYNC)
loff_t size;
- struct timespec atime;
+ struct timespec atime;
struct timespec mtime;
struct timespec ctime;
+ struct timespec btime; /* file creation time */
unsigned long blksize;
unsigned long long blocks;
+ u64 gen; /* inode generation */
+ u64 data_version;
+ u64 inode_flags; /* inode flags (!= BSD st_flags) */
};
#endif
-
#endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8812a63..5d68b4c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -44,6 +44,8 @@ struct shmid_ds;
struct sockaddr;
struct stat;
struct stat64;
+struct xstat_parameters;
+struct xstat;
struct statfs;
struct statfs64;
struct __sysctl_args;
@@ -824,4 +826,11 @@ 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_parameters __user *,
+ struct xstat __user *, size_t);
+asmlinkage long sys_fxstat(unsigned, unsigned,
+ struct xstat_parameters __user *,
+ struct xstat __user *, size_t);
+
#endif
^ permalink raw reply related [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
@ 2010-07-15 20:35 ` Arnd Bergmann
[not found] ` <201007152235.22373.arnd-r2nGTMty4D4@public.gmane.org>
` (4 subsequent siblings)
5 siblings, 0 replies; 101+ messages in thread
From: Arnd Bergmann @ 2010-07-15 20:35 UTC (permalink / raw)
To: David Howells
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, viro,
linux-fsdevel, linux-ext4
On Thursday 15 July 2010 04:17:12 David Howells wrote:
> (10) Can be extended by using more request flags and tagging further data after
> the end of the standard return data. Such things as the following could
> be returned:
>
> - BSD st_flags or FS_IOC_GETFLAGS.
> - Volume ID / Remote Device ID [Steve French].
> - Time granularity (NFSv4 time_delta) [Steve French].
> - Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
> Michael Kerrisk].
>
> This was initially proposed as a set of xattrs, but the general preferance is
> for an extended stat structure.
I don't think I'd call this general preference. Three of the four
are fixed length and could easily be done inside the structure if you
leave a bit of space instead of a variable-length field at the end.
For the volume id, I could not find any file system that requires more
than 32 bytes here, which is also reasonable to put into the structure.
Make it 36 if you want to cover ascii encoded UUIDs.
That's at most 60 bytes for the extensions you're considering already,
plus the 152 you have already is still less than a cache line on
some machines. Padding it to 256 bytes would make it nice and round,
if you want to be really sure, make it 384 bytes.
> The following structures are defined for the use of these new system calls:
>
> struct xstat_parameters {
> unsigned long long request_mask;
> };
I'd also still argue that 32 bits would be better since you can
put them into the argument list instead of having to use a pointer
to xstat_parameters. You only use 15 bits so far, so the remaining
17 bits should go a long way. It's not as important to me as the
previous point though.
> The system calls are:
>
> ssize_t ret = xstat(int dfd,
> const char *filename,
> unsigned flags,
> const struct xstat_parameters *params,
> struct xstat *buffer,
> size_t buflen);
The resulting syscall I'd hope for would be
int xstat(dfd, const char *filename, unsigned flags,
unsigned mask, struct xstat *buf);
Everything else in your patch looks very good and has my full support.
Arnd
^ permalink raw reply [flat|nested] 101+ messages in thread[parent not found: <201007152235.22373.arnd-r2nGTMty4D4@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <201007152235.22373.arnd-r2nGTMty4D4@public.gmane.org>
@ 2010-07-15 21:53 ` David Howells
2010-07-16 10:24 ` David Howells
` (3 more replies)
0 siblings, 4 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 21:53 UTC (permalink / raw)
To: Arnd Bergmann
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org> wrote:
> > This was initially proposed as a set of xattrs, but the general preferance
> > is for an extended stat structure.
>
> I don't think I'd call this general preference. Three of the four
> are fixed length and could easily be done inside the structure if you
> leave a bit of space instead of a variable-length field at the end.
?
Maybe I wasn't clear: I meant having an extended stat() syscall rather than
using a bunch of getxattr()'s was the general preference.
> For the volume id, I could not find any file system that requires more
> than 32 bytes here, which is also reasonable to put into the structure.
> Make it 36 if you want to cover ascii encoded UUIDs.
You should also include a length. Volume IDs may be binary rather than
NUL-terminated strings.
> That's at most 60 bytes for the extensions you're considering already,
> plus the 152
160, I think.
> you have already is still less than a cache line on
> some machines. Padding it to 256 bytes would make it nice and round,
> if you want to be really sure, make it 384 bytes.
Which we currently allocate on the kernel stack, plus up to a couple of kstat
structs if something like eCryptFS is used. Admittedly, the base xstat struct
could be kmalloc()'d instead, but why use up all that space if you don't need
it?
David
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 21:53 ` David Howells
@ 2010-07-16 10:24 ` David Howells
[not found] ` <8527.1279275842-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
[not found] ` <201007161302.35775.arnd-r2nGTMty4D4@public.gmane.org>
[not found] ` <30646.1279230807-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
` (2 subsequent siblings)
3 siblings, 2 replies; 101+ messages in thread
From: David Howells @ 2010-07-16 10:24 UTC (permalink / raw)
To: Mark Harris, Steve French
Cc: dhowells, viro, linux-fsdevel, linux-nfs, linux-cifs,
linux-kernel, samba-technical, linux-ext4
Mark Harris <mhlk@osj.us> wrote:
> > struct xstat_time {
> > unsigned long long tv_sec, tv_nsec;
> > };
>
> unsigned? Existing filesystems support on-disk timestamps
> representing times prior to the epoch.
I suppose it doesn't hurt to make is signed. It's large enough...
Looking at it again, having a 64-bit field for tv_nsec is overkill. It can't
(or shouldn't) exceed 999,999,999 - well within the capability of a 32-bit
unsigned integer.
So how about using up the dead space for what Steve French wanted:
| One hole that this reminded me about is how to return the superblock
| time granularity (for NFSv4 this is attribute 51 "time_delta" which
| is called on a superblock not on a file). We run into time rounding
| issues with Samba too.
By doing something like:
struct xstat_time {
signed long long tv_sec;
unsigned int tv_nsec;
unsigned short tv_granularity;
unsigned short tv_gran_units;
};
Where tv_granularity is the minimum granularity for tv_sec and tv_nsec given
as a quantity of tv_gran_units. tv_gran_units could then be a constant, such
as:
XSTAT_NANOSECONDS_GRANULARITY
XSTAT_MICROSECONDS_GRANULARITY
XSTAT_MILLISECONDS_GRANULARITY
XSTAT_SECONDS_GRANULARITY
XSTAT_MINUTES_GRANULARITY
XSTAT_HOURS_GRANULARITY
XSTAT_DAYS_GRANULARITY
So, for example, FAT times are a 2s granularity, so FAT would set
tv_granularity to 2 and tv_gran_units to XSTAT_SECONDS_GRANULARITY.
We could even support picosecond granularity if we made tv_nsec a 5-byte
field (tv_psec):
struct xstat_time {
signed long long tv_sec;
unsigned long long tv_gran_units : 8;
unsigned long long tv_granularity : 16;
unsigned long long tv_psec : 48;
};
but that's probably excessive. Does any filesystem we currently support need
that?
David
^ permalink raw reply [flat|nested] 101+ messages in thread[parent not found: <30646.1279230807-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <30646.1279230807-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
@ 2010-07-16 10:46 ` Arnd Bergmann
0 siblings, 0 replies; 101+ messages in thread
From: Arnd Bergmann @ 2010-07-16 10:46 UTC (permalink / raw)
To: David Howells
Cc: viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
On Thursday 15 July 2010, David Howells wrote:
> Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org> wrote:
>
> > > This was initially proposed as a set of xattrs, but the general preferance
> > > is for an extended stat structure.
> >
> > I don't think I'd call this general preference. Three of the four
> > are fixed length and could easily be done inside the structure if you
> > leave a bit of space instead of a variable-length field at the end.
>
> ?
>
> Maybe I wasn't clear: I meant having an extended stat() syscall rather than
> using a bunch of getxattr()'s was the general preference.
Ok, I misparsed your statement there. I don't think anyone was
objecting the use of xstat for this.
The controversial part is only how the extension happens. I would
already feel better about it if you just dropped the
'unsigned long long st_extra_results[0];' at the end and
added a comment saying that the structure may grow in the future, though
my preference would be to space for extensions and make it fixed length.
> > For the volume id, I could not find any file system that requires more
> > than 32 bytes here, which is also reasonable to put into the structure.
> > Make it 36 if you want to cover ascii encoded UUIDs.
>
> You should also include a length. Volume IDs may be binary rather than
> NUL-terminated strings.
Yes, maybe. There are several possible encodings for this. I was actually
thinking of fixed-length string rather than zero-terminated, but that
is possible as well. If this gets added, we need to audit every possible
use to make sure each of them is covered. My point was mostly that if we
need at most 40 bytes, it doesn't have to be variable length at all.
> > That's at most 60 bytes for the extensions you're considering already,
> > plus the 152
>
> 160, I think.
right.
> > you have already is still less than a cache line on
> > some machines. Padding it to 256 bytes would make it nice and round,
> > if you want to be really sure, make it 384 bytes.
>
> Which we currently allocate on the kernel stack, plus up to a couple of kstat
> structs if something like eCryptFS is used. Admittedly, the base xstat struct
> could be kmalloc()'d instead, but why use up all that space if you don't need
> it?
If you're worried about stack utilization, xstat could also be embedded into
kstat, like
struct kstat {
u64 request_mask;
struct xstat x;
};
Then you only need one of them on the stack for sys_xstat, or have both
struct kstat and struct stat/stat64 for the other syscalls.
Arnd
^ permalink raw reply [flat|nested] 101+ messages in thread
[parent not found: <201007161246.15923.arnd-r2nGTMty4D4@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <201007161246.15923.arnd-r2nGTMty4D4@public.gmane.org>
@ 2010-07-16 15:10 ` David Howells
0 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-16 15:10 UTC (permalink / raw)
To: Arnd Bergmann, Steve French
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org> wrote:
> > > For the volume id, I could not find any file system that requires more
> > > than 32 bytes here, which is also reasonable to put into the structure.
> > > Make it 36 if you want to cover ascii encoded UUIDs.
> >
> > You should also include a length. Volume IDs may be binary rather than
> > NUL-terminated strings.
>
> Yes, maybe. There are several possible encodings for this. I was actually
> thinking of fixed-length string rather than zero-terminated, but that
> is possible as well. If this gets added, we need to audit every possible
> use to make sure each of them is covered. My point was mostly that if we
> need at most 40 bytes, it doesn't have to be variable length at all.
I suppose it depends what you want it for. Steve French asked for it:
> (4) Should the inode number and data version number fields be
> 128-bit?
>
This is tricky for SMB2, if you can also provide a device id (or an
object id of some sort for the superblock) then 64 bit inode number is
ok.
But I'm not sure what he wants to put in there. He didn't respond to my reply:
A remote device ID? That would be possible. That could be used by
AFS to return the numeric volume ID (32 bits) and by NFS to return the
FSID (128 bits). Would you be using the VolumeGUID (128 bits) for
SMB2?
so I'm not sure what he's thinking of.
Looking through various filesystems:
FS SOURCE FORMAT LENGTH (BYTES)
======= =============================== ======= =============
- __kernel_fsid_t int 8
- super_block::s_id chars 32
ext234 superblock s_uuid UUID 16
ext234 superblock s_volume_name chars 16
nfs2 FSID int 4
nfs3 FSID int 8
nfs4 FSID int 16
afs Volume Name + type chars 64+1
afs Numeric volume ID int 4
cifs VolumeGUID UUID 16
btrfs superblock fsid bytes 16
fat superblock system_id+version? bytes 8+2
ntfs volume_serial_number int 8
ntfs FILE_Volume object_id UUID 16
xfs superblock sb_fname chars 12
xfs superblock sb_uuid UUID 16
jfs superblock s_uuid UUID 16
jfs superblock s_label bytes 16
isofs medium_catalog_number chars 13
isofs volume_id chars 32
udf volIdent chars 32
it would seem that a 16-byte (128-bit) ID would suit quite well. That would be
able to contain most things and could be added to the super_block struct. That
would also give NFSD something to use as a default FSID and Samba something to
used as a VolumeGUID.
David
^ permalink raw reply [flat|nested] 101+ messages in thread
[parent not found: <20100715021712.5544.44845.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <20100715021712.5544.44845.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
@ 2010-07-16 6:22 ` Mark Harris
2010-07-18 8:48 ` Christoph Hellwig
2010-07-22 10:35 ` Jan Engelhardt
2 siblings, 0 replies; 101+ messages in thread
From: Mark Harris @ 2010-07-16 6:22 UTC (permalink / raw)
To: David Howells
Cc: viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
> struct xstat_time {
> unsigned long long tv_sec, tv_nsec;
> };
unsigned? Existing filesystems support on-disk timestamps
representing times prior to the epoch.
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <20100715021712.5544.44845.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
2010-07-16 6:22 ` Mark Harris
@ 2010-07-18 8:48 ` Christoph Hellwig
2010-07-22 10:52 ` Jan Engelhardt
[not found] ` <alpine.LSU.2.01.1007221248050.9353-SHaQjdQMGhDmsUXKMKRlFA@public.gmane.org>
2010-07-22 10:35 ` Jan Engelhardt
2 siblings, 2 replies; 101+ messages in thread
From: Christoph Hellwig @ 2010-07-18 8:48 UTC (permalink / raw)
To: David Howells
Cc: viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA, drepper-H+wXaHxf7aLQT0dZR+AlfA,
torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Adding Uli to the Cc list to make sure this system call is useful
for glibc / can be exported by it. Otherwise it's rather pointless
to add it.
> (6) BSD stat compatibility: Including more fields from the BSD stat such as
> creation time (st_btime) and inode generation number (st_gen) [Jeremy
> Allison, Bernd Schubert]
How is this different from (1) and (4)?
> (7) Extra coherency data may be useful in making backups [Andreas Dilger].
What do you mean with that?
> (8) Allow the filesystem to indicate what it can/cannot provide: A filesystem
> can now say it doesn't support a standard stat feature if that isn't
> available.
What for?
> (9) Make the fields a consistent size on all arches, and make them large.
Why making them large for the sake of it? We'll need massive changes
all through libc and applications to ever make use of this. So please
coordinate the types used with Uli.
> The following structures are defined for the use of these new system calls:
>
> struct xstat_parameters {
> unsigned long long request_mask;
> };
Just pass this as a single flag by value. And just make it an unsigned
long to make the calling convention a lot simpler.
> struct xstat_dev {
> unsigned int major, minor;
> };
>
> struct xstat_time {
> unsigned long long tv_sec, tv_nsec;
> };
No point in adding special types here that aren't genericly useful.
Also this is the first and only system call using split major/minor
values for the dev_t. All this just creates more churn than it helps.
>
> struct xstat {
> unsigned long long st_result_mask;
Just st_mask?
> unsigned long long st_data_version;
st version?
> unsigned long long st_inode_flags;
> The defined bits in request_mask and st_result_mask are:
>
> XSTAT_REQUEST_MODE Want/got st_mode
> XSTAT_REQUEST_NLINK Want/got st_nlink
> XSTAT_REQUEST_UID Want/got st_uid
> XSTAT_REQUEST_GID Want/got st_gid
> XSTAT_REQUEST_RDEV Want/got st_rdev
> XSTAT_REQUEST_ATIME Want/got st_atime
> XSTAT_REQUEST_MTIME Want/got st_mtime
> XSTAT_REQUEST_CTIME Want/got st_ctime
> XSTAT_REQUEST_INO Want/got st_ino
> XSTAT_REQUEST_SIZE Want/got st_size
> XSTAT_REQUEST_BLOCKS Want/got st_blocks
> XSTAT_REQUEST__BASIC_STATS The stuff in the normal stat struct
> XSTAT_REQUEST_BTIME Want/got st_btime
> XSTAT_REQUEST_GEN Want/got st_gen
> XSTAT_REQUEST_DATA_VERSION Want/got st_data_version
> XSTAT_REQUEST_INODE_FLAGS Want/got st_inode_flags
> XSTAT_REQUEST__EXTENDED_STATS The stuff in the xstat struct
> XSTAT_REQUEST__ALL_STATS The defined set of requestables
What's the point of the REQUEST in the name? Also no double
underscores inside the identifier. Instead adding a _MASK postfix
for masks would make it a lot more clear.
> The defined bits in st_inode_flags are the usual FS_xxx_FL flags in the LSW,
> plus some extra flags in the MSW:
>
> FS_SPECIAL_FL Special kernel file, such as found in procfs
> FS_AUTOMOUNT_FL Specific automount point
> FS_AUTOMOUNT_ANY_FL Free-form automount directory
> FS_REMOTE_FL File is remote
> FS_ENCRYPTED_FL File is encrypted
> FS_SYSTEM_FL File is marked system (DOS/NTFS/CIFS)
> FS_TEMPORARY_FL File is temporary (NTFS/CIFS)
> FS_OFFLINE_FL File is offline (CIFS)
Please don't overload the FL_ namespace even more. It's already a
complete mess given that it overloads the extN on-disk namespace.
You're much better off just adding a clean new namespace.
> The system calls are:
>
> ssize_t ret = xstat(int dfd,
> const char *filename,
> unsigned flags,
> const struct xstat_parameters *params,
> struct xstat *buffer,
> size_t buflen);
If you already have a buflen parameter there is absolute no need for
the extra results field. Just define new fields at the end and include
them if the bufsize is big enough and it's in the mask of requested
fields.
> When the system call is executed, the request_mask bitmask is read from the
> parameter block to work out what the user is requesting. If params is NULL,
> then request_mask will be assumed to be XSTAT_REQUEST__BASIC_STATS.
Why add a special case like that? Especially if we make the request
flags a pass by value scalar initalizing it is trivial.
> The request_mask should be set by the caller to specify extra results that the
> caller may desire. These come in a number of classes:
>
> (0) dev, blksize.
>
> These are local data and are always available.
>
> (1) mode, nlinks, uid, gid, [amc]time, ino, size, blocks.
>
> These will be returned whether the caller asks for them or not. The
> corresponding bits in result_mask will be set to indicate their presence.
>
> If the caller didn't ask for them, then they may be approximated. For
> example, NFS won't waste any time updating them from the server, unless as
> a byproduct of updating something requested.
Please don't introduce tons of special cases. Instead use a simple rule
like:
- a filesystem must return all attributes requests, or return an
error if it can't.
- a filesystem may return additional attributes, the caller can detect
this by looking at st_mask.
plus possibly a list of attributes the filesystem must be able to
provide if requests. I don't see a reason to make that mask different
from the attributes required by Posix.
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-18 8:48 ` Christoph Hellwig
@ 2010-07-22 10:52 ` Jan Engelhardt
[not found] ` <alpine.LSU.2.01.1007221248050.9353-SHaQjdQMGhDmsUXKMKRlFA@public.gmane.org>
1 sibling, 0 replies; 101+ messages in thread
From: Jan Engelhardt @ 2010-07-22 10:52 UTC (permalink / raw)
To: Christoph Hellwig
Cc: David Howells, viro, linux-fsdevel, linux-nfs, linux-cifs,
linux-kernel, samba-technical, linux-ext4, drepper, torvalds
On Sunday 2010-07-18 10:48, Christoph Hellwig wrote:
>Adding Uli to the Cc list to make sure this system call is useful
>for glibc / can be exported by it. Otherwise it's rather pointless
>to add it.
>
>> (6) BSD stat compatibility: Including more fields from the BSD stat such as
>> creation time (st_btime) and inode generation number (st_gen) [Jeremy
>> Allison, Bernd Schubert]
>
>How is this different from (1) and (4)?
(4), the inode generation number, need not be related to time.
>> (8) Allow the filesystem to indicate what it can/cannot provide: A filesystem
>> can now say it doesn't support a standard stat feature if that isn't
>> available.
>
>What for?
Given xstat.otime=0, how would you determine whether the file is really
tagged with a date of 1970, or whether it's just the fs which didnot
store this kind of information.
^ permalink raw reply [flat|nested] 101+ messages in thread[parent not found: <alpine.LSU.2.01.1007221248050.9353-SHaQjdQMGhDmsUXKMKRlFA@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <alpine.LSU.2.01.1007221248050.9353-SHaQjdQMGhDmsUXKMKRlFA@public.gmane.org>
@ 2010-07-22 12:25 ` David Howells
0 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-22 12:25 UTC (permalink / raw)
To: Jan Engelhardt
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA, Christoph Hellwig,
viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA, drepper-H+wXaHxf7aLQT0dZR+AlfA,
torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Jan Engelhardt <jengelh-nopoi9nDyk+ELgA04lAiVw@public.gmane.org> wrote:
> >> (8) Allow the filesystem to indicate what it can/cannot provide: A
> >> filesystem can now say it doesn't support a standard stat feature if
> >> that isn't available.
> >
> >What for?
>
> Given xstat.otime=0, how would you determine whether the file is really
> tagged with a date of 1970, or whether it's just the fs which didnot
> store this kind of information.
I was thinking more of stuff that's already in the Linux stat struct, some of
which is fabricated because the underlying fs doesn't support it.
Take RomFS for example: it fabricates all of st_mtime, st_atime, st_ctime,
st_nlinks, st_blocks, st_uid and st_gid because none of them are stored in the
medium
Similarly, UbiFS fabricates st_blocks and complains in a comment that it makes
no sense for that type of filesystem.
There are other examples.
David
^ permalink raw reply [flat|nested] 101+ messages in thread
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <20100715021712.5544.44845.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
2010-07-16 6:22 ` Mark Harris
2010-07-18 8:48 ` Christoph Hellwig
@ 2010-07-22 10:35 ` Jan Engelhardt
2 siblings, 0 replies; 101+ messages in thread
From: Jan Engelhardt @ 2010-07-22 10:35 UTC (permalink / raw)
To: David Howells
Cc: viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
On Thursday 2010-07-15 04:17, David Howells wrote:
> (6) BSD stat compatibility: Including more fields from the BSD stat such as
> creation time (st_btime) and inode generation number (st_gen) [Jeremy
> Allison, Bernd Schubert].
>where st_btime is the file creation time, st_gen is the inode generation
>(i_generation), st_data_version is the data version number (i_version),
>st_inode_flags is the flags from FS_IOC_GETFLAGS plus some extras,
>request_mask and st_result_mask are bitmasks of data desired/provided and
>st_extra_results[] is where as-yet undefined fields are appended.
Linux already has a creation time field, it's called otime (there is no "b" in
"creation"), and you will find scattered fragments of that all over the kernel
(foremost, fs/jfs/, now btrfs, and I also notice sysvipc having something with
that name).
> struct xstat_time {
> unsigned long long tv_sec, tv_nsec;
> };
If it helps getting rid of the ugly suseconds_t in userspace ;-)
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 101+ messages in thread
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
2010-07-15 20:35 ` Arnd Bergmann
[not found] ` <201007152235.22373.arnd-r2nGTMty4D4@public.gmane.org>
@ 2010-07-19 14:05 ` David Howells
2010-07-19 15:17 ` Linus Torvalds
` (2 subsequent siblings)
5 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-19 14:05 UTC (permalink / raw)
To: Christoph Hellwig
Cc: dhowells, viro, linux-fsdevel, linux-nfs, linux-cifs,
linux-kernel, samba-technical, linux-ext4, drepper, torvalds
Christoph Hellwig <hch@infradead.org> wrote:
> Adding Uli to the Cc list to make sure this system call is useful
> for glibc / can be exported by it. Otherwise it's rather pointless
> to add it.
>
> > (6) BSD stat compatibility: Including more fields from the BSD stat such
> > as creation time (st_btime) and inode generation number (st_gen)
> > [Jeremy Allison, Bernd Schubert]
>
> How is this different from (1) and (4)?
A matter of intent, really, and who proposed it.
> > (7) Extra coherency data may be useful in making backups [Andreas Dilger].
>
> What do you mean with that?
There are extra dates and version numbers potentially available. This may be
useful in making backups. Ask Andreas.
> > (8) Allow the filesystem to indicate what it can/cannot provide: A
> > filesystem can now say it doesn't support a standard stat feature if
> > that isn't available.
>
> What for?
So that you can decide not to use it. Some of our filesystems fabricate things
that they don't actually store.
> > (9) Make the fields a consistent size on all arches, and make them large.
>
> Why making them large for the sake of it? We'll need massive changes
> all through libc and applications to ever make use of this. So please
> coordinate the types used with Uli.
Otherwise we end up with #ifdefs and duplicated fields of different sizes
within stat structs, and fields of "long" types which vary in size, depending
on the environment.
I just want to make sure that:
- st_ino is stored as 64-bit
- st_size and st_blocks are stored 64-bit
- st.{a,b,c,m}time.tv_sec are stored 64-bit
We could probably stand to make st_blksize 32-bit. I'd quite like to leave
st_gen as 64-bits and I definitely want to leave st_data_version as 64-bits.
> > The following structures are defined for the use of these new system calls:
> >
> > struct xstat_parameters {
> > unsigned long long request_mask;
> > };
>
> Just pass this as a single flag by value. And just make it an unsigned
> long to make the calling convention a lot simpler.
Already done.
> > struct xstat_dev {
> > unsigned int major, minor;
> > };
> >
> > struct xstat_time {
> > unsigned long long tv_sec, tv_nsec;
> > };
>
> No point in adding special types here that aren't genericly useful.
> Also this is the first and only system call using split major/minor
> values for the dev_t. All this just creates more churn than it helps.
I can perhaps agree on the device numbers, though some filesystems we have can
store numbers that can't be represented by dev_t. I think, however, everything
we have can be handled by a 32:32 split. The numbers could then be encoded as
desired in userspace.
The problem with using extant time structs is they use "long" or "unsigned
long". And I specifically want to get away from that, since it might be
32-bits or it might be 64-bits.
> >
> > struct xstat {
> > unsigned long long st_result_mask;
>
> Just st_mask?
Perhaps, but it contrasts nicely with request_mask, and makes it easier to
document.
> > unsigned long long st_data_version;
>
> st version?
Acceptable.
> > unsigned long long st_inode_flags;
>
>
>
> > The defined bits in request_mask and st_result_mask are:
> >
> > XSTAT_REQUEST_MODE Want/got st_mode
> > XSTAT_REQUEST_NLINK Want/got st_nlink
> > XSTAT_REQUEST_UID Want/got st_uid
> > XSTAT_REQUEST_GID Want/got st_gid
> > XSTAT_REQUEST_RDEV Want/got st_rdev
> > XSTAT_REQUEST_ATIME Want/got st_atime
> > XSTAT_REQUEST_MTIME Want/got st_mtime
> > XSTAT_REQUEST_CTIME Want/got st_ctime
> > XSTAT_REQUEST_INO Want/got st_ino
> > XSTAT_REQUEST_SIZE Want/got st_size
> > XSTAT_REQUEST_BLOCKS Want/got st_blocks
> > XSTAT_REQUEST__BASIC_STATS The stuff in the normal stat struct
> > XSTAT_REQUEST_BTIME Want/got st_btime
> > XSTAT_REQUEST_GEN Want/got st_gen
> > XSTAT_REQUEST_DATA_VERSION Want/got st_data_version
> > XSTAT_REQUEST_INODE_FLAGS Want/got st_inode_flags
> > XSTAT_REQUEST__EXTENDED_STATS The stuff in the xstat struct
> > XSTAT_REQUEST__ALL_STATS The defined set of requestables
>
> What's the point of the REQUEST in the name?
Well, they are.
> Also no double underscores inside the identifier. Instead adding a _MASK
> postfix for masks would make it a lot more clear.
Perhaps.
> > The defined bits in st_inode_flags are the usual FS_xxx_FL flags in the
> > LSW, plus some extra flags in the MSW:
> >
> > FS_SPECIAL_FL Special kernel file, such as found in procfs
> > FS_AUTOMOUNT_FL Specific automount point
> > FS_AUTOMOUNT_ANY_FL Free-form automount directory
> > FS_REMOTE_FL File is remote
> > FS_ENCRYPTED_FL File is encrypted
> > FS_SYSTEM_FL File is marked system (DOS/NTFS/CIFS)
> > FS_TEMPORARY_FL File is temporary (NTFS/CIFS)
> > FS_OFFLINE_FL File is offline (CIFS)
>
> Please don't overload the FL_ namespace even more. It's already a
> complete mess given that it overloads the extN on-disk namespace.
> You're much better off just adding a clean new namespace.
Yeah. I've been thinking that's probably the better thing to do.
> > The system calls are:
> >
> > ssize_t ret = xstat(int dfd,
> > const char *filename,
> > unsigned flags,
> > const struct xstat_parameters *params,
> > struct xstat *buffer,
> > size_t buflen);
>
> If you already have a buflen parameter there is absolute no need for
> the extra results field. Just define new fields at the end and include
> them if the bufsize is big enough and it's in the mask of requested
> fields.
Or, as someone else has already said, return -E2BIG if the result won't fit.
> > The request_mask should be set by the caller to specify extra results that
> > the caller may desire. These come in a number of classes:
> >
> > (0) dev, blksize.
> >
> > These are local data and are always available.
> >
> > (1) mode, nlinks, uid, gid, [amc]time, ino, size, blocks.
> >
> > These will be returned whether the caller asks for them or not. The
> > corresponding bits in result_mask will be set to indicate their
> > presence.
> >
> > If the caller didn't ask for them, then they may be approximated. For
> > example, NFS won't waste any time updating them from the server,
> > unless as a byproduct of updating something requested.
>
> Please don't introduce tons of special cases. Instead use a simple rule
> like:
>
> - a filesystem must return all attributes requests, or return an
> error if it can't.
> - a filesystem may return additional attributes, the caller can detect
> this by looking at st_mask.
>
> plus possibly a list of attributes the filesystem must be able to
> provide if requests. I don't see a reason to make that mask different
> from the attributes required by Posix.
Firstly: Lightweight stat: I want to say that the filesystem may return data
that is out of date if it isn't asked for specifically, but the filesystem has
a copy available. But I'm not sure that this should apply to non-standard
fields.
Secondly: It doesn't matter what POSIX wants; not all filesystems we support
have everything available. Where something that's standard is not available,
we have the opportunity to indicate this, whilst still providing a fabricated
result, so that the user can take note of this fact if they choose to, whilst
totally ignoring the indication if they prefer, and just using the fabrication.
Davod
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
` (2 preceding siblings ...)
2010-07-19 14:05 ` David Howells
@ 2010-07-19 15:17 ` Linus Torvalds
[not found] ` <AANLkTikuzYqYpGHcubb7QVciZW0dNFjOG82qIwy5M4gO-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-22 12:14 ` David Howells
5 siblings, 0 replies; 101+ messages in thread
From: Linus Torvalds @ 2010-07-19 15:17 UTC (permalink / raw)
To: David Howells
Cc: viro, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
On Wed, Jul 14, 2010 at 7:17 PM, David Howells <dhowells@redhat.com> wrote:
>
> ssize_t ret = xstat(int dfd,
> const char *filename,
> unsigned flags,
> const struct xstat_parameters *params,
> struct xstat *buffer,
> size_t buflen);
Ugh. So I think this is pretty disgusting. For a few reasons:
- that whole xstat buffer handling is just a mess. I think you
already fixed the "xstat_parameters" crud and just made it a simple
unsigned long and a direct argument, but the "buffer+buflen" thing is
still disgusting.
Why not just leave a few empty fields at the end, and make the rule
be: "We don't just add random crap, so don't expect it to grow widely
in the future".
- you use "long long" all over the place. Don't do that. If you want
a fixed size, say so, and use "u64/s64". That's the _real_ fixed size,
and "long long" just _happens_ to be the same size on all current
architectures.
Put another way: "long" just _happened_ to be 32 bits way back when
on pretty much all targets. That's where all the 64-bit compatibility
mess came from. Don't make the same mistake. Besides, if the point is
to make things be the same, _document_ that point by using a type that
is explicitly sized.
- why create that new kind of xstat() that realistically absolutely
nobody will use outside of some very special cases, and that has no
real advantages for 99.9% of all people?
You could make it a "atomic stat+open" by replacing the useless
"size" return value with a "fd" return value, add a flag saying "we're
also interested in opening it" (in the same result set flags), and
instead of that stupid "buflen" input, give the "mode" input that open
needs.
Tadaa! You now have something that more people might be interested
in, if only because it avoids a system call and might be a performance
win. Who knows. Ask the Wine people what strange
open-function-from-hell they are interested in.
> ssize_t ret = fxstat(unsigned fd,
Quite frankly, my gut feel is that once you do "xstat(dfd, filename,
...)" then it's damn stupid to do a separate "fxstat()", when you
might as well say that "xtstat(dfd, NULL, ...)" is the same as
"fxstat(fd, ...)"
Now, the difference between adding one or two system calls may not be
huge, but just from a cleanliness angle, I really don't see the point
of having another fstat variant when the extended xstat() already very
naturally supports the thing. And let's face it, using a NULL path
pointer just makes sense if you don't have a path. You already passed
it a target file descriptor in the dfd.
Anyway, I didn't look at whether the new xstat fields made any sense,
but I hated the interface enough that I can't be bothered to. Don't
make up baroque new things that will never be used. Make a better
argument for why anybody would use them despite the lack of
standardization etc. And make sure they are as simple as possible
(which is why I hate that "buflen" thing etc).
Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 101+ messages in thread[parent not found: <AANLkTikuzYqYpGHcubb7QVciZW0dNFjOG82qIwy5M4gO-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>]
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
[not found] ` <AANLkTikuzYqYpGHcubb7QVciZW0dNFjOG82qIwy5M4gO-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2010-07-19 16:15 ` David Howells
[not found] ` <10783.1279556132-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
[not found] ` <AANLkTinVns77R7yCCh-lydd0eQufdAF9O2OaWmCL7uSn-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
0 siblings, 2 replies; 101+ messages in thread
From: David Howells @ 2010-07-19 16:15 UTC (permalink / raw)
To: Linus Torvalds
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
Linus Torvalds <torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org> wrote:
> - that whole xstat buffer handling is just a mess. I think you
> already fixed the "xstat_parameters" crud and just made it a simple
> unsigned long and a direct argument,
I was thinking more of an unsigned int argument, since it can't have more than
32 flags in it if it is also to work on 32-bit arches.
> but the "buffer+buflen" thing is still disgusting.
>
> Why not just leave a few empty fields at the end, and make the rule
> be: "We don't just add random crap, so don't expect it to grow widely
> in the future".
Because it gets allocated on the kernel stack. It's already 160 bytes, and
expanding it will eat more kernel stack space. Now, I can offset that by: (a)
embedding it in struct kstat so that we allocate less stack space in xstat()
overall, and (b) allocating kstat/xstat structs with kmalloc() rather than on
the stack in all the stat syscalls.
> - you use "long long" all over the place. Don't do that. If you want
> a fixed size, say so, and use "u64/s64". That's the _real_ fixed size,
> and "long long" just _happens_ to be the same size on all current
> architectures.
I was following struct stat/stat64 in arch/x86/include/asm/stat.h which do the
same. Also, if this is going to be seen by userspace, isn't it better to use
uint32_t and suchlike?
> - why create that new kind of xstat() that realistically absolutely
> nobody will use outside of some very special cases, and that has no
> real advantages for 99.9% of all people?
The new information is useful for some cases. Samba for example. At least
two of the fields I'm adding are also made available through BSD's stat()
call, and will automatically be used for some things by autoconf magic if they
become available.
I'm still trying to get a handle on what people think will be truly useful. I
can see things *could* be useful, particularly to GUI file managers and ls,
but not everyone is of the same opinion.
Perhaps you or others can offer answers to the following questions as these
might help:
(1) Should I offer information that's effectively free to come by, but could
be got through:
(a) An extra statfs() call - such as whether a file is remote, whether
it's some kernel special file? Or what the volume label is for this
file?
(b) An extra getxattr() call - such as a file's security label.
(c) An extra ioctl() call - such as FS_IOC_GETFLAGS.
(2) Should I offer information that's appropriate to non-UNIX filesystems
such as FAT, NTFS or CIFS. Some of this may map onto other fields, such
as FS_IOC_GETFLAGS.
(3) Should I offer information about which results that I've returned are
actually useful, as opposed to being fabricated on the spot? Such as
UID/GID in FAT or blocks in UBIFS. This may be of use to df or a GUI.
For instance, a GUI, seeing that UID/GID aren't useful, could ask the
filesystem to provide information about what it considers to be valid
ownership information.
> You could make it a "atomic stat+open" by replacing the useless
> "size" return value with a "fd" return value, add a flag saying "we're
> also interested in opening it" (in the same result set flags), and
> instead of that stupid "buflen" input, give the "mode" input that open
> needs.
Which would be used by even fewer people, I suspect. However, it's certainly
an interesting idea. I suspect it doesn't gain much over open()+fstat()
though, given that you'd still have to do most of the work of fstat() after
doing the open() thing anyway.
Also, I'm not sure how much use the atomicity is, given that the file may have
changed state between the gathering of the stat data and userspace getting to
do anything with it.
> > ssize_t ret = fxstat(unsigned fd,
>
> Quite frankly, my gut feel is that once you do "xstat(dfd, filename,
> ...)" then it's damn stupid to do a separate "fxstat()", when you
> might as well say that "xtstat(dfd, NULL, ...)" is the same as
> "fxstat(fd, ...)"
This has been suggested and denounced as stupid already. That said, I agree
with you.
> Now, the difference between adding one or two system calls may not be
> huge, but just from a cleanliness angle, I really don't see the point
> of having another fstat variant when the extended xstat() already very
> naturally supports the thing. And let's face it, using a NULL path
> pointer just makes sense if you don't have a path. You already passed
> it a target file descriptor in the dfd.
Agreed.
David
^ permalink raw reply [flat|nested] 101+ messages in thread
* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
` (4 preceding siblings ...)
[not found] ` <AANLkTikuzYqYpGHcubb7QVciZW0dNFjOG82qIwy5M4gO-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2010-07-22 12:14 ` David Howells
2010-07-22 12:17 ` Volker Lendecke
5 siblings, 1 reply; 101+ messages in thread
From: David Howells @ 2010-07-22 12:14 UTC (permalink / raw)
To: Jan Engelhardt
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
viro, linux-fsdevel, linux-ext4
Jan Engelhardt <jengelh@medozas.de> wrote:
> Linux already has a creation time field, it's called otime (there is no "b"
> in "creation"), and you will find scattered fragments of that all over the
> kernel (foremost, fs/jfs/, now btrfs, and I also notice sysvipc having
> something with that name).
It is? It's called crtime in Ext4. st_btime, however, would be compatible
with BSD's stat, and Samba would just use it by way of autoconf magic if it
appeared.
David
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available [ver #6]
2010-07-22 12:14 ` David Howells
@ 2010-07-22 12:17 ` Volker Lendecke
[not found] ` <E1Obuiy-00C9jr-Al-dqLtpHMqGvUyWpdLl23E4A@public.gmane.org>
0 siblings, 1 reply; 101+ messages in thread
From: Volker Lendecke @ 2010-07-22 12:17 UTC (permalink / raw)
To: David Howells
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel,
Jan Engelhardt, viro, linux-fsdevel, linux-ext4
On Thu, Jul 22, 2010 at 01:14:47PM +0100, David Howells wrote:
> Jan Engelhardt <jengelh@medozas.de> wrote:
>
> > Linux already has a creation time field, it's called otime (there is no "b"
> > in "creation"), and you will find scattered fragments of that all over the
> > kernel (foremost, fs/jfs/, now btrfs, and I also notice sysvipc having
> > something with that name).
>
> It is? It's called crtime in Ext4. st_btime, however, would be compatible
> with BSD's stat, and Samba would just use it by way of autoconf magic if it
> appeared.
Samba has the following check:
# recent FreeBSD, NetBSD have creation timestamps called birthtime:
AC_CHECK_MEMBERS([struct stat.st_birthtimespec.tv_nsec])
AC_CHECK_MEMBERS([struct stat.st_birthtime], AC_CHECK_MEMBERS([struct stat.st_birthtimensec]))
and the supporting code around that. "birth" might also be
where the "b" comes from :-)
Volker
^ permalink raw reply [flat|nested] 101+ messages in thread
* [PATCH 03/18] AFS: Use i_generation not i_version for the vnode uniquifier [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
2010-07-15 2:17 ` [PATCH 01/18] Mark arguments to certain syscalls as being const " David Howells
2010-07-15 2:17 ` [PATCH 02/18] xstat: Add a pair of system calls to make extended file stats available " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 04/18] xstat: AFS: Return extended attributes " David Howells
` (14 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: dhowells, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
Store the AFS vnode uniquifier in the i_generation field, not the i_version
field of the inode struct. i_version can then be given the AFS data version
number.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/dir.c | 8 ++++----
fs/afs/fsclient.c | 3 ++-
fs/afs/inode.c | 10 +++++-----
3 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index b42d5cc..afb9ff8 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -542,11 +542,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
dentry->d_op = &afs_fs_dentry_operations;
d_add(dentry, inode);
- _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
+ _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }",
fid.vnode,
fid.unique,
dentry->d_inode->i_ino,
- (unsigned long long)dentry->d_inode->i_version);
+ dentry->d_inode->i_generation);
return NULL;
}
@@ -626,10 +626,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
* been deleted and replaced, and the original vnode ID has
* been reused */
if (fid.unique != vnode->fid.unique) {
- _debug("%s: file deleted (uq %u -> %u I:%llu)",
+ _debug("%s: file deleted (uq %u -> %u I:%u)",
dentry->d_name.name, fid.unique,
vnode->fid.unique,
- (unsigned long long)dentry->d_inode->i_version);
+ dentry->d_inode->i_generation);
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
spin_unlock(&vnode->lock);
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4bd0218..346e328 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -89,7 +89,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
i_size_write(&vnode->vfs_inode, size);
vnode->vfs_inode.i_uid = status->owner;
vnode->vfs_inode.i_gid = status->group;
- vnode->vfs_inode.i_version = vnode->fid.unique;
+ vnode->vfs_inode.i_generation = vnode->fid.unique;
vnode->vfs_inode.i_nlink = status->nlink;
mode = vnode->vfs_inode.i_mode;
@@ -102,6 +102,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server;
vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime;
vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime;
+ vnode->vfs_inode.i_version = data_version;
}
expected_version = status->data_version;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index d00b312..ee3190a 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -73,7 +73,8 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
inode->i_ctime.tv_nsec = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime;
inode->i_blocks = 0;
- inode->i_version = vnode->fid.unique;
+ inode->i_generation = vnode->fid.unique;
+ inode->i_version = vnode->status.data_version;
inode->i_mapping->a_ops = &afs_fs_aops;
/* check to see whether a symbolic link is really a mountpoint */
@@ -98,7 +99,7 @@ static int afs_iget5_test(struct inode *inode, void *opaque)
struct afs_iget_data *data = opaque;
return inode->i_ino == data->fid.vnode &&
- inode->i_version == data->fid.unique;
+ inode->i_generation == data->fid.unique;
}
/*
@@ -110,7 +111,7 @@ static int afs_iget5_set(struct inode *inode, void *opaque)
struct afs_vnode *vnode = AFS_FS_I(inode);
inode->i_ino = data->fid.vnode;
- inode->i_version = data->fid.unique;
+ inode->i_generation = data->fid.unique;
vnode->fid = data->fid;
vnode->volume = data->volume;
@@ -306,8 +307,7 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
inode = dentry->d_inode;
- _enter("{ ino=%lu v=%llu }", inode->i_ino,
- (unsigned long long)inode->i_version);
+ _enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
generic_fillattr(inode, stat);
return 0;
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 04/18] xstat: AFS: Return extended attributes [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (2 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 03/18] AFS: Use i_generation not i_version for the vnode uniquifier " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 05/18] xstat: eCryptFS: " David Howells
` (13 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Return extended attributes from the AFS filesystem. This includes the
following:
(1) The vnode uniquifier as st_gen.
(2) The data version number as st_data_version.
(3) FS_AUTOMOUNT_FL on mountpoint directories.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/inode.c | 13 ++++++++-----
1 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index ee3190a..02f115f 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -300,16 +300,19 @@ 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_mask |= XSTAT_REQUEST_GEN | XSTAT_REQUEST_DATA_VERSION;
+ stat->gen = inode->i_generation;
+ stat->data_version = inode->i_version;
+ if (test_bit(AFS_VNODE_MOUNTPOINT, &AFS_FS_I(inode)->flags))
+ stat->inode_flags |= FS_AUTOMOUNT_FL;
return 0;
}
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 05/18] xstat: eCryptFS: Return extended attributes [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (3 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 04/18] xstat: AFS: Return extended attributes " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 06/18] xstat: Ext4: " David Howells
` (12 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Return extended attributes from the eCryptFS filesystem, dredged up from the
lower filesystem.
Possibly eCryptFS should also set FS_COMPR_FL on its compressed files.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/ecryptfs/inode.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 31ef525..41bc407 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -994,8 +994,10 @@ int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat lower_stat;
int rc;
- rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry),
- ecryptfs_dentry_to_lower(dentry), &lower_stat);
+ lower_stat.query_flags = stat->query_flags;
+ lower_stat.request_mask = stat->request_mask | XSTAT_REQUEST_BLOCKS;
+ rc = vfs_xgetattr(ecryptfs_dentry_to_lower_mnt(dentry),
+ ecryptfs_dentry_to_lower(dentry), &lower_stat);
if (!rc) {
generic_fillattr(dentry->d_inode, stat);
stat->blocks = lower_stat.blocks;
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 06/18] xstat: Ext4: Return extended attributes [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (4 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 05/18] xstat: eCryptFS: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 07/18] xstat: NFS: " David Howells
` (11 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Return extended attributes from the Ext4 filesystem. This includes the
following:
(1) The inode creation time (i_crtime) as i_btime.
(2) The inode i_generation as i_gen if not the root directory.
(3) The inode i_version as st_data_version if a file with I_VERSION set or a
directory.
(4) FS_xxx_FL flags as for FS_IOC_GETFLAGS.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/ext4/ext4.h | 2 ++
fs/ext4/file.c | 2 +-
fs/ext4/inode.c | 32 +++++++++++++++++++++++++++++---
fs/ext4/namei.c | 2 ++
fs/ext4/symlink.c | 2 ++
5 files changed, 36 insertions(+), 4 deletions(-)
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..822a4ad 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5550,12 +5550,38 @@ 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;
+ struct ext4_inode_info *ei = EXT4_I(inode);
- inode = dentry->d_inode;
generic_fillattr(inode, stat);
+ stat->result_mask |= XSTAT_REQUEST_BTIME;
+ stat->btime.tv_sec = EXT4_I(inode)->i_crtime.tv_sec;
+ stat->btime.tv_nsec = EXT4_I(inode)->i_crtime.tv_nsec;
+
+ if (inode->i_ino != EXT4_ROOT_INO) {
+ stat->result_mask |= XSTAT_REQUEST_GEN;
+ stat->gen = inode->i_generation;
+ }
+ if (S_ISDIR(inode->i_mode) || test_opt(inode->i_sb, I_VERSION)) {
+ stat->result_mask |= XSTAT_REQUEST_DATA_VERSION;
+ stat->data_version = inode->i_version;
+ }
+
+ ext4_get_inode_flags(ei);
+ stat->inode_flags |= ei->i_flags & EXT4_FL_USER_VISIBLE;
+ stat->result_mask |= XSTAT_REQUEST_INODE_FLAGS;
+ 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,
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 07/18] xstat: NFS: Return extended attributes [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (5 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 06/18] xstat: Ext4: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 08/18] xstat: CIFS: " David Howells
` (10 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Return extended attributes from the NFS filesystem. This includes the
following:
(1) The change attribute as st_data_version if NFSv4.
(2) FS_AUTOMOUNT_FL on referral/submount directories.
Furthermore, what nfs_getattr() does can be controlled as follows:
(1) If AT_FORCE_ATTR_SYNC is indicated, or mtime, ctime or data_version (NFSv4
only) are requested then the outstanding writes will be written to the
server first.
(2) The inode's attributes may be synchronised with the server:
(a) If AT_FORCE_ATTR_SYNC is indicated or if atime is requested (and atime
updating is not suppressed by a mount flag) then the attributes will
be reread unconditionally.
(b) If the data version or any of basic stats are requested then the
attributes will be reread if the cached attributes have expired.
(c) Otherwise the cached attributes will be used - even if expired -
without reference to the server.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/nfs/inode.c | 46 ++++++++++++++++++++++++++++++++++------------
1 files changed, 34 insertions(+), 12 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 099b351..8c6de96 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -495,11 +495,21 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
+ unsigned force = stat->query_flags & AT_FORCE_ATTR_SYNC;
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
int err;
- /* Flush out writes to the server in order to update c/mtime. */
- if (S_ISREG(inode->i_mode)) {
+ if (NFS_SERVER(inode)->nfs_client->rpc_ops->version < 4)
+ stat->request_mask &= ~XSTAT_REQUEST_DATA_VERSION;
+
+ /* Flush out writes to the server in order to update c/mtime
+ * or data version if the user wants them */
+ if ((force || stat->request_mask & (XSTAT_REQUEST_MTIME |
+ XSTAT_REQUEST_CTIME |
+ XSTAT_REQUEST_DATA_VERSION
+ )) &&
+ S_ISREG(inode->i_mode)
+ ) {
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto out;
@@ -514,18 +524,30 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
* - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
* no point in checking those.
*/
- if ((mnt->mnt_flags & MNT_NOATIME) ||
- ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
+ if (!(stat->request_mask & XSTAT_REQUEST_ATIME) ||
+ (mnt->mnt_flags & MNT_NOATIME) ||
+ ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
need_atime = 0;
- if (need_atime)
- err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
- else
- err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
- if (!err) {
- generic_fillattr(inode, stat);
- stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
+ if (force || stat->request_mask & (XSTAT_REQUEST__BASIC_STATS |
+ XSTAT_REQUEST_DATA_VERSION)
+ ) {
+ if (force || need_atime)
+ err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ else
+ err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ if (err)
+ goto out;
}
+
+ generic_fillattr(inode, stat);
+ stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
+
+ if (stat->request_mask & XSTAT_REQUEST_DATA_VERSION) {
+ stat->data_version = NFS_I(inode)->change_attr;
+ stat->result_mask |= XSTAT_REQUEST_DATA_VERSION;
+ }
+
out:
return err;
}
@@ -770,7 +792,7 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
-
+
if (mapping->nrpages != 0) {
int ret = invalidate_inode_pages2(mapping);
if (ret < 0)
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 08/18] xstat: CIFS: Return extended attributes [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (6 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 07/18] xstat: NFS: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL " David Howells
` (9 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: dhowells, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
Return extended attributes from the CIFS filesystem. This includes the
following:
(1) Return the file creation time as btime. We assume that the creation time
won't change over the life of the inode.
(2) FS_AUTOMOUNT_FL on referral/submount directories.
(3) Deasserting XSTAT_REQUEST_INO in st_result_mask if we made up the inode
number and didn't get it from the server.
(4) Map various Windows file attributes to FS_xxx_FL flags in st_inode_flags,
fetching them from the server if we don't have them yet or don't have a
current copy.
Furthermore, what cifs_getattr() does can be controlled as follows:
(1) If AT_FORCE_ATTR_SYNC is indicated, or if the inode flags or creation time
are requested but not yet collected, then the attributes will be reread
unconditionally.
(2) If the basic stats are requested or if the inode flags are requested and
have been collected previously, then the attributes will be reread if out
of date.
(3) Otherwise the cached attributes will be used - even if expired - without
reference to the server.
Note that cifs_revalidate_dentry() will issue an extra operation to get the
FILE_ALL_INFO in addition to the FILE_UNIX_BASIC_INFO if it needs to collect
creation time and attributes on behalf of cifs_getattr().
[NOTE: THIS PATCH IS UNTESTED!]
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/cifs/cifsfs.h | 2 +
fs/cifs/cifsglob.h | 5 +++
fs/cifs/dir.c | 2 +
fs/cifs/inode.c | 76 ++++++++++++++++++++++++++++++++++++++++++++--------
4 files changed, 71 insertions(+), 14 deletions(-)
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index a7eb65c..50bf70b 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -62,7 +62,7 @@ extern int cifs_rmdir(struct inode *, struct dentry *);
extern int cifs_rename(struct inode *, struct dentry *, struct inode *,
struct dentry *);
extern int cifs_revalidate_file(struct file *filp);
-extern int cifs_revalidate_dentry(struct dentry *);
+extern int cifs_revalidate_dentry(struct dentry *, bool, bool);
extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int cifs_setattr(struct dentry *, struct iattr *);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index a88479c..f12e78d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -396,6 +396,9 @@ struct cifsInodeInfo {
bool clientCanCacheAll:1; /* read and writebehind oplock */
bool delete_pending:1; /* DELETE_ON_CLOSE is set */
bool invalid_mapping:1; /* pagecache is invalid */
+ bool cifsAttrs_valid:1; /* stored cifs attributes are valid */
+ bool btime_valid:1; /* stored creation time is valid */
+ struct timespec btime; /* creation time */
u64 server_eof; /* current file size on server */
u64 uniqueid; /* server inode number */
struct inode vfs_inode;
@@ -508,6 +511,7 @@ struct dfs_info3_param {
#define CIFS_FATTR_DELETE_PENDING 0x2
#define CIFS_FATTR_NEED_REVAL 0x4
#define CIFS_FATTR_INO_COLLISION 0x8
+#define CIFS_FATTR_WINATTRS_VALID 0x10 /* T if cf_btime and cf_cifsattrs valid */
struct cifs_fattr {
u32 cf_flags;
@@ -524,6 +528,7 @@ struct cifs_fattr {
struct timespec cf_atime;
struct timespec cf_mtime;
struct timespec cf_ctime;
+ struct timespec cf_btime;
};
static inline void free_dfs_info_param(struct dfs_info3_param *param)
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index e7ae78b..65da30e 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -778,7 +778,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
int isValid = 1;
if (direntry->d_inode) {
- if (cifs_revalidate_dentry(direntry))
+ if (cifs_revalidate_dentry(direntry, false, false))
return 0;
} else {
cFYI(1, "neg dentry 0x%p name = %s",
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6f0683c..ff4a62f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -136,7 +136,11 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM))
inode->i_mode = fattr->cf_mode;
- cifs_i->cifsAttrs = fattr->cf_cifsattrs;
+ if (fattr->cf_flags & CIFS_FATTR_WINATTRS_VALID) {
+ cifs_i->cifsAttrs = fattr->cf_cifsattrs;
+ cifs_i->btime = fattr->cf_btime;
+ cifs_i->btime_valid = true;
+ }
if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
cifs_i->time = 0;
@@ -468,6 +472,7 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
struct cifs_sb_info *cifs_sb, bool adjust_tz)
{
memset(fattr, 0, sizeof(*fattr));
+ fattr->cf_flags = CIFS_FATTR_WINATTRS_VALID;
fattr->cf_cifsattrs = le32_to_cpu(info->Attributes);
if (info->DeletePending)
fattr->cf_flags |= CIFS_FATTR_DELETE_PENDING;
@@ -479,6 +484,7 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime);
+ fattr->cf_btime = cifs_NTtimeToUnix(info->CreationTime);
if (adjust_tz) {
fattr->cf_ctime.tv_sec += cifs_sb->tcon->ses->server->timeAdj;
@@ -1591,7 +1597,8 @@ check_inval:
}
/* revalidate a dentry's inode attributes */
-int cifs_revalidate_dentry(struct dentry *dentry)
+int cifs_revalidate_dentry(struct dentry *dentry, bool want_extra_bits,
+ bool force)
{
int xid;
int rc = 0;
@@ -1604,7 +1611,7 @@ int cifs_revalidate_dentry(struct dentry *dentry)
xid = GetXid();
- if (!cifs_inode_needs_reval(inode))
+ if (!force && !cifs_inode_needs_reval(inode))
goto check_inval;
/* can not safely grab the rename sem here if rename calls revalidate
@@ -1619,9 +1626,12 @@ int cifs_revalidate_dentry(struct dentry *dentry)
"jiffies %ld", full_path, inode, inode->i_count.counter,
dentry, dentry->d_time, jiffies);
- if (CIFS_SB(sb)->tcon->unix_ext)
+ if (CIFS_SB(sb)->tcon->unix_ext) {
rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
- else
+ if (rc != 0)
+ goto check_inval;
+ }
+ if (!CIFS_SB(sb)->tcon->unix_ext || want_extra_bits)
rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
xid, NULL);
@@ -1637,13 +1647,55 @@ check_inval:
int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
- int err = cifs_revalidate_dentry(dentry);
- if (!err) {
- generic_fillattr(dentry->d_inode, stat);
- stat->blksize = CIFS_MAX_MSGSIZE;
- stat->ino = CIFS_I(dentry->d_inode)->uniqueid;
- }
- return err;
+ struct cifsInodeInfo *cifs_i = CIFS_I(dentry->d_inode);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
+ unsigned force = stat->query_flags & AT_FORCE_ATTR_SYNC;
+ bool want_extra_bits = false;
+ u64 iflag;
+ u32 attrs;
+ int err;
+
+ if (stat->request_mask & XSTAT_REQUEST_BTIME && !cifs_i->btime_valid) {
+ want_extra_bits = true;
+ force = true;
+ }
+
+ if (stat->request_mask & XSTAT_REQUEST_INODE_FLAGS) {
+ want_extra_bits = true;
+ if (!cifs_i->cifsAttrs_valid)
+ force = true;
+ }
+
+ if (force || stat->request_mask & XSTAT_REQUEST__BASIC_STATS) {
+ err = cifs_revalidate_dentry(dentry, want_extra_bits, force);
+ if (err)
+ return err;
+ }
+
+ generic_fillattr(&cifs_i->vfs_inode, stat);
+ stat->blksize = CIFS_MAX_MSGSIZE;
+
+ /* we don't promise an inode number if we made one up */
+ stat->ino = cifs_i->uniqueid;
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM))
+ stat->result_mask &= ~XSTAT_REQUEST_INO;
+ if (cifs_i->btime_valid) {
+ stat->btime = cifs_i->btime;
+ stat->result_mask |= XSTAT_REQUEST_BTIME;
+ }
+ attrs = cifs_i->cifsAttrs;
+ iflag = 0;
+ if (attrs & ATTR_READONLY) iflag |= FS_IMMUTABLE_FL;
+ if (attrs & ATTR_HIDDEN) iflag |= FS_HIDDEN_FL;
+ if (attrs & ATTR_SYSTEM) iflag |= FS_SYSTEM_FL;
+ if (attrs & ATTR_ARCHIVE) iflag |= FS_ARCHIVE_FL;
+ if (attrs & ATTR_TEMPORARY) iflag |= FS_TEMPORARY_FL;
+ if (attrs & ATTR_REPARSE) iflag |= FS_REPARSE_POINT_FL;
+ if (attrs & ATTR_COMPRESSED) iflag |= FS_COMPR_FL;
+ if (attrs & ATTR_OFFLINE) iflag |= FS_OFFLINE_FL;
+ if (attrs & ATTR_ENCRYPTED) iflag |= FS_ENCRYPTED_FL;
+ stat->inode_flags |= iflag;
+ return 0;
}
static int cifs_truncate_page(struct address_space *mapping, loff_t from)
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (7 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 08/18] xstat: CIFS: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-18 8:49 ` Christoph Hellwig
` (2 more replies)
2010-07-15 2:17 ` [PATCH 10/18] xstat: Make network filesystems return FS_REMOTE_FL " David Howells
` (8 subsequent siblings)
17 siblings, 3 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Make special system filesystems return FS_SPECIAL_FL in st_inode_flags to
xstat().
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/ia64/kernel/perfmon.c | 7 ++++---
arch/powerpc/platforms/cell/spufs/inode.c | 1 +
arch/s390/hypfs/inode.c | 1 +
drivers/infiniband/hw/ipath/ipath_fs.c | 1 +
drivers/infiniband/hw/qib/qib_fs.c | 1 +
drivers/isdn/capi/capifs.c | 1 +
drivers/misc/ibmasm/ibmasmfs.c | 1 +
drivers/mtd/mtdchar.c | 1 +
drivers/oprofile/oprofilefs.c | 1 +
drivers/usb/core/inode.c | 1 +
drivers/usb/gadget/f_fs.c | 1 +
drivers/usb/gadget/inode.c | 1 +
drivers/xen/xenfs/super.c | 1 +
fs/anon_inodes.c | 1 +
fs/binfmt_misc.c | 1 +
fs/configfs/mount.c | 1 +
fs/debugfs/inode.c | 1 +
fs/fuse/control.c | 1 +
fs/hostfs/hostfs_kern.c | 1 +
fs/nfsd/nfsctl.c | 1 +
fs/ocfs2/dlmfs/dlmfs.c | 1 +
fs/openpromfs/inode.c | 1 +
fs/pipe.c | 1 +
fs/proc/root.c | 1 +
fs/sysfs/mount.c | 1 +
ipc/mqueue.c | 1 +
kernel/cgroup.c | 1 +
kernel/cpuset.c | 1 +
net/socket.c | 1 +
net/sunrpc/rpc_pipe.c | 1 +
security/inode.c | 1 +
security/selinux/selinuxfs.c | 1 +
security/smack/smackfs.c | 1 +
33 files changed, 36 insertions(+), 3 deletions(-)
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index ab985f7..bc96df7 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -626,9 +626,10 @@ pfmfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name,
}
static struct file_system_type pfm_fs_type = {
- .name = "pfmfs",
- .get_sb = pfmfs_get_sb,
- .kill_sb = kill_anon_super,
+ .name = "pfmfs",
+ .inode_flags = FS_SPECIAL_FL,
+ .get_sb = pfmfs_get_sb,
+ .kill_sb = kill_anon_super,
};
DEFINE_PER_CPU(unsigned long, pfm_syst_info);
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index e5e5f82..f7d7c84 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -808,6 +808,7 @@ spufs_get_sb(struct file_system_type *fstype, int flags,
static struct file_system_type spufs_type = {
.owner = THIS_MODULE,
.name = "spufs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = spufs_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 6b120f0..01060c6 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -454,6 +454,7 @@ static const struct file_operations hypfs_file_ops = {
static struct file_system_type hypfs_type = {
.owner = THIS_MODULE,
.name = "s390_hypfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = hypfs_get_super,
.kill_sb = hypfs_kill_super
};
diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c
index 2fca708..e5bb001 100644
--- a/drivers/infiniband/hw/ipath/ipath_fs.c
+++ b/drivers/infiniband/hw/ipath/ipath_fs.c
@@ -407,6 +407,7 @@ bail:
static struct file_system_type ipathfs_fs_type = {
.owner = THIS_MODULE,
.name = "ipathfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = ipathfs_get_sb,
.kill_sb = ipathfs_kill_super,
};
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index 844954b..b888a49 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -601,6 +601,7 @@ int qibfs_remove(struct qib_devdata *dd)
static struct file_system_type qibfs_fs_type = {
.owner = THIS_MODULE,
.name = "ipathfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = qibfs_get_sb,
.kill_sb = qibfs_kill_super,
};
diff --git a/drivers/isdn/capi/capifs.c b/drivers/isdn/capi/capifs.c
index 2b83850..1208e4c 100644
--- a/drivers/isdn/capi/capifs.c
+++ b/drivers/isdn/capi/capifs.c
@@ -134,6 +134,7 @@ static int capifs_get_sb(struct file_system_type *fs_type,
static struct file_system_type capifs_fs_type = {
.owner = THIS_MODULE,
.name = "capifs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = capifs_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index 8844a3f..0767280 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -108,6 +108,7 @@ static const struct file_operations *ibmasmfs_dir_ops = &simple_dir_operations;
static struct file_system_type ibmasmfs_type = {
.owner = THIS_MODULE,
.name = "ibmasmfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = ibmasmfs_get_super,
.kill_sb = kill_litter_super,
};
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 91c8013..acb4ad7 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -986,6 +986,7 @@ static int mtd_inodefs_get_sb(struct file_system_type *fs_type, int flags,
static struct file_system_type mtd_inodefs_type = {
.name = "mtd_inodefs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = mtd_inodefs_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index 2766a6d..cf3dab6 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -279,6 +279,7 @@ static int oprofilefs_get_sb(struct file_system_type *fs_type,
static struct file_system_type oprofilefs_type = {
.owner = THIS_MODULE,
.name = "oprofilefs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = oprofilefs_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index 1a27618..0d942f0 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -586,6 +586,7 @@ static int usb_get_sb(struct file_system_type *fs_type,
static struct file_system_type usb_fs_type = {
.owner = THIS_MODULE,
.name = "usbfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = usb_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index d69eccf..63d8f91 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1221,6 +1221,7 @@ ffs_fs_kill_sb(struct super_block *sb)
static struct file_system_type ffs_fs_type = {
.owner = THIS_MODULE,
.name = "functionfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = ffs_fs_get_sb,
.kill_sb = ffs_fs_kill_sb,
};
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index de8a838..cb304b8 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -2127,6 +2127,7 @@ gadgetfs_kill_sb (struct super_block *sb)
static struct file_system_type gadgetfs_type = {
.owner = THIS_MODULE,
.name = shortname,
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = gadgetfs_get_sb,
.kill_sb = gadgetfs_kill_sb,
};
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 8924d93..d1029bf 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -59,6 +59,7 @@ static int xenfs_get_sb(struct file_system_type *fs_type,
static struct file_system_type xenfs_type = {
.owner = THIS_MODULE,
.name = "xenfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = xenfs_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index e4b75d6..8820975 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -45,6 +45,7 @@ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen)
static struct file_system_type anon_inode_fs_type = {
.name = "anon_inodefs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = anon_inodefs_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index c4e8353..df727ea 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -715,6 +715,7 @@ static struct linux_binfmt misc_format = {
static struct file_system_type bm_fs_type = {
.owner = THIS_MODULE,
.name = "binfmt_misc",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = bm_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 8c8d642..11107f4 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -113,6 +113,7 @@ static int configfs_get_sb(struct file_system_type *fs_type,
static struct file_system_type configfs_fs_type = {
.owner = THIS_MODULE,
.name = "configfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = configfs_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 30a87b3..84f09a1 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -144,6 +144,7 @@ static int debug_get_sb(struct file_system_type *fs_type,
static struct file_system_type debug_fs_type = {
.owner = THIS_MODULE,
.name = "debugfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = debug_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 3773fd6..798da59 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -341,6 +341,7 @@ static void fuse_ctl_kill_sb(struct super_block *sb)
static struct file_system_type fuse_ctl_fs_type = {
.owner = THIS_MODULE,
.name = "fusectl",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = fuse_ctl_get_sb,
.kill_sb = fuse_ctl_kill_sb,
};
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 87ac189..07a9973 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -1037,6 +1037,7 @@ static int hostfs_read_sb(struct file_system_type *type,
static struct file_system_type hostfs_type = {
.owner = THIS_MODULE,
.name = "hostfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = hostfs_read_sb,
.kill_sb = kill_anon_super,
.fs_flags = 0,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 508941c..4e6cf14 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1397,6 +1397,7 @@ static int nfsd_get_sb(struct file_system_type *fs_type,
static struct file_system_type nfsd_fs_type = {
.owner = THIS_MODULE,
.name = "nfsd",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = nfsd_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index b83d610..0bba39f 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -649,6 +649,7 @@ static int dlmfs_get_sb(struct file_system_type *fs_type,
static struct file_system_type dlmfs_fs_type = {
.owner = THIS_MODULE,
.name = "ocfs2_dlmfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = dlmfs_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index ffcd04f..8bbc7ce 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -424,6 +424,7 @@ static int openprom_get_sb(struct file_system_type *fs_type,
static struct file_system_type openprom_fs_type = {
.owner = THIS_MODULE,
.name = "openpromfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = openprom_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/fs/pipe.c b/fs/pipe.c
index 279eef9..247efd1 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1254,6 +1254,7 @@ static int pipefs_get_sb(struct file_system_type *fs_type,
static struct file_system_type pipe_fs_type = {
.name = "pipefs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = pipefs_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 4258384..9c95a19 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -97,6 +97,7 @@ static void proc_kill_sb(struct super_block *sb)
static struct file_system_type proc_fs_type = {
.name = "proc",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = proc_get_sb,
.kill_sb = proc_kill_sb,
};
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 281c0c9..ec2ea3b 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -147,6 +147,7 @@ static void sysfs_kill_sb(struct super_block *sb)
static struct file_system_type sysfs_fs_type = {
.name = "sysfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = sysfs_get_sb,
.kill_sb = sysfs_kill_sb,
};
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index c93fd3f..bba10cf 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1232,6 +1232,7 @@ static const struct super_operations mqueue_super_ops = {
static struct file_system_type mqueue_fs_type = {
.name = "mqueue",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = mqueue_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3ac6f5b..71c81b4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1619,6 +1619,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
static struct file_system_type cgroup_fs_type = {
.name = "cgroup",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = cgroup_get_sb,
.kill_sb = cgroup_kill_sb,
};
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 02b9611..d5e5c56 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -250,6 +250,7 @@ static int cpuset_get_sb(struct file_system_type *fs_type,
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = cpuset_get_sb,
};
diff --git a/net/socket.c b/net/socket.c
index 367d547..0aaf9f6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -326,6 +326,7 @@ static struct vfsmount *sock_mnt __read_mostly;
static struct file_system_type sock_fs_type = {
.name = "sockfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = sockfs_get_sb,
.kill_sb = kill_anon_super,
};
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 95ccbcf..1e1d477 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1033,6 +1033,7 @@ rpc_get_sb(struct file_system_type *fs_type,
static struct file_system_type rpc_pipe_fs_type = {
.owner = THIS_MODULE,
.name = "rpc_pipefs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = rpc_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/security/inode.c b/security/inode.c
index 1c812e8..7a904bb 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -139,6 +139,7 @@ static int get_sb(struct file_system_type *fs_type,
static struct file_system_type fs_type = {
.owner = THIS_MODULE,
.name = "securityfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 0293843..9c4bc22 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -1706,6 +1706,7 @@ static int sel_get_sb(struct file_system_type *fs_type,
static struct file_system_type sel_fs_type = {
.name = "selinuxfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = sel_get_sb,
.kill_sb = kill_litter_super,
};
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index a2b72d7..56a8cc1 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -1325,6 +1325,7 @@ static int smk_get_sb(struct file_system_type *fs_type,
static struct file_system_type smk_fs_type = {
.name = "smackfs",
+ .inode_flags = FS_SPECIAL_FL,
.get_sb = smk_get_sb,
.kill_sb = kill_litter_super,
};
^ permalink raw reply related [flat|nested] 101+ messages in thread* Re: [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL [ver #6]
2010-07-15 2:17 ` [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL " David Howells
@ 2010-07-18 8:49 ` Christoph Hellwig
2010-07-19 14:09 ` David Howells
[not found] ` <8426.1279548573-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2 siblings, 0 replies; 101+ messages in thread
From: Christoph Hellwig @ 2010-07-18 8:49 UTC (permalink / raw)
To: David Howells
Cc: viro, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
special is not a very useful identifier. Also what you are returning
is per-filesystem data, not per-file. This needs to go into statfs,
not into stat. We're about to introduce flags for statfs, so try
to do it ontop of those.
The same thing applies to the remote flag in the next patch.
^ permalink raw reply [flat|nested] 101+ messages in thread* Re: [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL [ver #6]
2010-07-15 2:17 ` [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL " David Howells
2010-07-18 8:49 ` Christoph Hellwig
@ 2010-07-19 14:09 ` David Howells
[not found] ` <8426.1279548573-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-19 14:09 UTC (permalink / raw)
To: Christoph Hellwig
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
viro, linux-fsdevel, linux-ext4
Christoph Hellwig <hch@infradead.org> wrote:
> special is not a very useful identifier. Also what you are returning
> is per-filesystem data, not per-file. This needs to go into statfs,
> not into stat. We're about to introduce flags for statfs, so try
> to do it ontop of those.
>
> The same thing applies to the remote flag in the next patch.
Which means that you have to do two calls (xstat+statfs) to find this
information that we can return pretty much for free here, though you can cache
it based on st_dev, I suppose.
Also, not all the flags are per-filesystem. The following are:
FS_SPECIAL_FL /* Special file as found in procfs/sysfs */
FS_REMOTE_FL /* File is remote */
but the rest aren't:
FS_AUTOMOUNT_FL /* Specific automount point */
FS_AUTOMOUNT_ANY_FL /* Unspecific automount directory */
FS_ENCRYPTED_FL /* File is encrypted */
FS_HIDDEN_FL /* File is marked hidden (DOS+) */
FS_SYSTEM_FL /* File is marked system (DOS+) */
FS_ARCHIVE_FL /* File is marked archive (DOS+) */
FS_TEMPORARY_FL /* File is temporary (NTFS/CIFS) */
FS_OFFLINE_FL /* File is offline (CIFS) */
FS_REPARSE_POINT_FL /* Reparse point (NTFS/CIFS) */
David
^ permalink raw reply [flat|nested] 101+ messages in thread[parent not found: <8426.1279548573-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]
* Re: [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL [ver #6]
[not found] ` <8426.1279548573-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
@ 2010-07-27 13:41 ` David Howells
0 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-27 13:41 UTC (permalink / raw)
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA, Christoph Hellwig,
viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
> Also, not all the flags are per-filesystem. The following are:
>
> FS_SPECIAL_FL /* Special file as found in procfs/sysfs */
> FS_REMOTE_FL /* File is remote */
Actually, that last is not true; FS_REMOTE_FL is per-file, not per-fs. You
can have a filesystem that has fabricated files and remote files. For
instance, with kAFS at some point you will be go into /afs, do a lookup for a
directory that doesn't exist, but whose name represents a cell+volume, the
filesystem will fabricate a local directory and then attempt to mount a remote
directory on to it.
David
^ permalink raw reply [flat|nested] 101+ messages in thread
* [PATCH 10/18] xstat: Make network filesystems return FS_REMOTE_FL [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (8 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 09/18] xstat: Make special system filesystems return FS_SPECIAL_FL " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 11/18] xstat: Make automounter filesystems return FS_AUTOMOUNT_FL " David Howells
` (7 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Make network filesystems return FS_REMOTE_FL in st_inode_flags to xstat().
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/super.c | 1 +
fs/ceph/super.c | 1 +
fs/cifs/cifsfs.c | 1 +
fs/coda/inode.c | 1 +
fs/ncpfs/inode.c | 1 +
fs/nfs/super.c | 7 +++++++
fs/smbfs/inode.c | 1 +
7 files changed, 13 insertions(+), 0 deletions(-)
diff --git a/fs/afs/super.c b/fs/afs/super.c
index e932e5a..daaa3d4 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -40,6 +40,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
struct file_system_type afs_fs_type = {
.owner = THIS_MODULE,
.name = "afs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = afs_get_sb,
.kill_sb = kill_anon_super,
.fs_flags = 0,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index fa87f51..f486ac8 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1019,6 +1019,7 @@ static void ceph_kill_sb(struct super_block *s)
static struct file_system_type ceph_fs_type = {
.owner = THIS_MODULE,
.name = "ceph",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = ceph_get_sb,
.kill_sb = ceph_kill_sb,
.fs_flags = FS_RENAME_DOES_D_MOVE,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ef9a773..eb2c517 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -586,6 +586,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
struct file_system_type cifs_fs_type = {
.owner = THIS_MODULE,
.name = "cifs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = cifs_get_sb,
.kill_sb = kill_anon_super,
/* .fs_flags */
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index d97f993..cb05427 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -308,6 +308,7 @@ static int coda_get_sb(struct file_system_type *fs_type,
struct file_system_type coda_fs_type = {
.owner = THIS_MODULE,
.name = "coda",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = coda_get_sb,
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index fa33851..c5892a1 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -1018,6 +1018,7 @@ static int ncp_get_sb(struct file_system_type *fs_type,
static struct file_system_type ncp_fs_type = {
.owner = THIS_MODULE,
.name = "ncpfs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = ncp_get_sb,
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f9df16d..2553683 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -251,6 +251,7 @@ static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
static struct file_system_type nfs_fs_type = {
.owner = THIS_MODULE,
.name = "nfs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs_get_sb,
.kill_sb = nfs_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -259,6 +260,7 @@ static struct file_system_type nfs_fs_type = {
struct file_system_type nfs_xdev_fs_type = {
.owner = THIS_MODULE,
.name = "nfs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs_xdev_get_sb,
.kill_sb = nfs_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -297,6 +299,7 @@ static void nfs4_kill_super(struct super_block *sb);
static struct file_system_type nfs4_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs4_get_sb,
.kill_sb = nfs4_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -305,6 +308,7 @@ static struct file_system_type nfs4_fs_type = {
static struct file_system_type nfs4_remote_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs4_remote_get_sb,
.kill_sb = nfs4_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -313,6 +317,7 @@ static struct file_system_type nfs4_remote_fs_type = {
struct file_system_type nfs4_xdev_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs4_xdev_get_sb,
.kill_sb = nfs4_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -321,6 +326,7 @@ struct file_system_type nfs4_xdev_fs_type = {
static struct file_system_type nfs4_remote_referral_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs4_remote_referral_get_sb,
.kill_sb = nfs4_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
@@ -329,6 +335,7 @@ static struct file_system_type nfs4_remote_referral_fs_type = {
struct file_system_type nfs4_referral_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = nfs4_referral_get_sb,
.kill_sb = nfs4_kill_super,
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index 9551cb6..e47d86a 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -800,6 +800,7 @@ static int smb_get_sb(struct file_system_type *fs_type,
static struct file_system_type smb_fs_type = {
.owner = THIS_MODULE,
.name = "smbfs",
+ .inode_flags = FS_REMOTE_FL,
.get_sb = smb_get_sb,
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 11/18] xstat: Make automounter filesystems return FS_AUTOMOUNT_FL [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (9 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 10/18] xstat: Make network filesystems return FS_REMOTE_FL " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 12/18] xstat: Add a dentry op to handle automounting rather than abusing follow_link() " David Howells
` (6 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Make automounter filesystems return FS_AUTOMOUNT_FL in st_inode_flags to
xstat().
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/autofs/init.c | 1 +
fs/autofs4/init.c | 1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/autofs/init.c b/fs/autofs/init.c
index cea5219..2c06d4b 100644
--- a/fs/autofs/init.c
+++ b/fs/autofs/init.c
@@ -23,6 +23,7 @@ static int autofs_get_sb(struct file_system_type *fs_type,
static struct file_system_type autofs_fs_type = {
.owner = THIS_MODULE,
.name = "autofs",
+ .inode_flags = FS_AUTOMOUNT_FL,
.get_sb = autofs_get_sb,
.kill_sb = autofs_kill_sb,
};
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index 9722e4b..43df431 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -23,6 +23,7 @@ static int autofs_get_sb(struct file_system_type *fs_type,
static struct file_system_type autofs_fs_type = {
.owner = THIS_MODULE,
.name = "autofs",
+ .inode_flags = FS_AUTOMOUNT_FL,
.get_sb = autofs_get_sb,
.kill_sb = autofs4_kill_sb,
};
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 12/18] xstat: Add a dentry op to handle automounting rather than abusing follow_link() [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (10 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 11/18] xstat: Make automounter filesystems return FS_AUTOMOUNT_FL " David Howells
@ 2010-07-15 2:17 ` David Howells
[not found] ` <20100715021723.5544.85730.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
[not found] ` <20100718085048.GC27794-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2010-07-15 2:17 ` [PATCH 13/18] xstat: AFS: Use d_automount() " David Howells
` (5 subsequent siblings)
17 siblings, 2 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Add a dentry op (d_automount) to handle automounting directories rather than
abusing the follow_link() inode operation. The operation is keyed off a new
inode flag (S_AUTOMOUNT).
This makes it easier to add an AT_ flag to suppress terminal segment automount
during pathwalk. It should also remove the need for the kludge code in the
pathwalk algorithm to handle directories with follow_link() semantics.
I've only changed __follow_mount() to handle automount points, but it might be
necessary to change follow_mount() too. The latter is only used from
follow_dotdot(), but any automounts on ".." should be pinned whilst we're using
a child of it.
Note that autofs4's use of follow_mount() will need examining if this patch is
committed.
Signed-off-by: David Howells <dhowells@redhat.com>
---
Documentation/filesystems/Locking | 2 +
Documentation/filesystems/vfs.txt | 13 ++++++
fs/namei.c | 85 +++++++++++++++++++++++++++++--------
fs/stat.c | 2 +
include/linux/dcache.h | 5 ++
include/linux/fs.h | 2 +
6 files changed, 91 insertions(+), 18 deletions(-)
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 96d4293..ccbfa98 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -16,6 +16,7 @@ prototypes:
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
+ struct vfsmount *(*d_automount)(struct path *path);
locking rules:
none have BKL
@@ -27,6 +28,7 @@ d_delete: yes no yes no
d_release: no no no yes
d_iput: no no no yes
d_dname: no no no no
+d_automount: no no no yes
--------------------------- inode_operations ---------------------------
prototypes:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 94677e7..31a9e8f 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -851,6 +851,7 @@ struct dentry_operations {
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
+ struct vfsmount *(*d_automount)(struct path *);
};
d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -885,6 +886,18 @@ struct dentry_operations {
at the end of the buffer, and returns a pointer to the first char.
dynamic_dname() helper function is provided to take care of this.
+ d_automount: called when an automount dentry is to be traversed (optional).
+ This should create a new VFS mount record, mount it on the directory
+ and return the record to the caller. The caller is supplied with a
+ path parameter giving the automount directory to describe the automount
+ target and the parent VFS mount record to provide inheritable mount
+ parameters. NULL should be returned if someone else managed to make
+ the automount first. If the automount failed, then an error code
+ should be returned.
+
+ This function is only used if S_AUTOMOUNT is set on the inode to which
+ the dentry refers.
+
Example :
static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
diff --git a/fs/namei.c b/fs/namei.c
index 868d0cb..fcec3c6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -617,24 +617,71 @@ int follow_up(struct path *path)
return 1;
}
+/*
+ * Perform an automount
+ */
+static int follow_automount(struct path *path, int res)
+{
+ struct vfsmount *mnt;
+
+ if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
+ return -EREMOTE;
+
+ current->total_link_count++;
+ if (current->total_link_count >= 40)
+ return -ELOOP;
+
+ mnt = path->dentry->d_op->d_automount(path);
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+ if (!mnt) /* mount collision */
+ return 0;
+
+ if (mnt->mnt_sb == path->mnt->mnt_sb &&
+ mnt->mnt_root == path->dentry) {
+ mntput(mnt);
+ return -ELOOP;
+ }
+
+ dput(path->dentry);
+ if (res)
+ mntput(path->mnt);
+ path->mnt = mnt;
+ path->dentry = dget(mnt->mnt_root);
+ return 0;
+}
+
/* no need for dcache_lock, as serialization is taken care in
* namespace.c
*/
-static int __follow_mount(struct path *path)
+static int __follow_mount(struct path *path, unsigned nofollow)
{
- int res = 0;
- while (d_mountpoint(path->dentry)) {
- struct vfsmount *mounted = lookup_mnt(path);
- if (!mounted)
+ struct vfsmount *mounted;
+ int ret, res = 0;
+ for (;;) {
+ while (d_mountpoint(path->dentry)) {
+ if (nofollow)
+ return -ELOOP;
+ mounted = lookup_mnt(path);
+ if (!mounted)
+ break;
+ dput(path->dentry);
+ if (res)
+ mntput(path->mnt);
+ path->mnt = mounted;
+ path->dentry = dget(mounted->mnt_root);
+ res = 1;
+ }
+ if (!d_automount_point(path->dentry))
break;
- dput(path->dentry);
- if (res)
- mntput(path->mnt);
- path->mnt = mounted;
- path->dentry = dget(mounted->mnt_root);
+ if (nofollow)
+ return -ELOOP;
+ ret = follow_automount(path, res);
+ if (ret < 0)
+ return ret;
res = 1;
}
- return res;
+ return 0;
}
static void follow_mount(struct path *path)
@@ -702,6 +749,8 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent;
struct inode *dir;
+ int ret;
+
/*
* See if the low-level filesystem might want
* to use its own hash..
@@ -720,8 +769,10 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
done:
path->mnt = mnt;
path->dentry = dentry;
- __follow_mount(path);
- return 0;
+ ret = __follow_mount(path, 0);
+ if (unlikely(ret < 0))
+ path_put(path);
+ return ret;
need_lookup:
parent = nd->path.dentry;
@@ -1721,11 +1772,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
if (open_flag & O_EXCL)
goto exit_dput;
- if (__follow_mount(path)) {
- error = -ELOOP;
- if (open_flag & O_NOFOLLOW)
- goto exit_dput;
- }
+ error = __follow_mount(path, open_flag & O_NOFOLLOW);
+ if (error < 0)
+ goto exit_dput;
error = -ENOENT;
if (!path->dentry->d_inode)
diff --git a/fs/stat.c b/fs/stat.c
index 89d72fc..bb0f538 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -43,6 +43,8 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
stat->blocks = inode->i_blocks;
stat->blksize = (1 << inode->i_blkbits);
stat->inode_flags = inode->i_sb->s_type->inode_flags;
+ if (IS_AUTOMOUNT(inode))
+ stat->inode_flags |= FS_AUTOMOUNT_FL;
stat->result_mask |= XSTAT_REQUEST__BASIC_STATS & ~XSTAT_REQUEST_RDEV;
if (unlikely(S_ISBLK(stat->mode) || S_ISCHR(stat->mode)))
stat->result_mask |= XSTAT_REQUEST_RDEV;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index eebb617..5380bff 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -139,6 +139,7 @@ struct dentry_operations {
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
+ struct vfsmount *(*d_automount)(struct path *);
};
/* the dentry parameter passed to d_hash and d_compare is the parent
@@ -157,6 +158,7 @@ d_compare: no yes yes no
d_delete: no yes no no
d_release: no no no yes
d_iput: no no no yes
+d_automount: no no no yes
*/
/* d_flags entries */
@@ -389,6 +391,9 @@ static inline int d_mountpoint(struct dentry *dentry)
return dentry->d_mounted;
}
+#define d_automount_point(dentry) \
+ (dentry->d_inode && IS_AUTOMOUNT(dentry->d_inode))
+
extern struct vfsmount *lookup_mnt(struct path *);
extern struct dentry *lookup_create(struct nameidata *nd, int is_dir);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 951c36b..579ad9d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -235,6 +235,7 @@ struct inodes_stat_t {
#define S_NOCMTIME 128 /* Do not update file c/mtime */
#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE 512 /* Inode is fs-internal */
+#define S_AUTOMOUNT 1024 /* Automount/referral quasi-directory */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -269,6 +270,7 @@ struct inodes_stat_t {
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
+#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
/* the read-only stuff doesn't really belong here, but any other place is
probably as bad and I don't want to create yet another include file. */
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 13/18] xstat: AFS: Use d_automount() rather than abusing follow_link() [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (11 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 12/18] xstat: Add a dentry op to handle automounting rather than abusing follow_link() " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 14/18] xstat: NFS: " David Howells
` (4 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Make AFS use the new d_automount() dentry operation rather than abusing
follow_link() on directories.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/dir.c | 1 +
fs/afs/internal.h | 1 +
fs/afs/mntpt.c | 46 +++++++++++++++-------------------------------
3 files changed, 17 insertions(+), 31 deletions(-)
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index afb9ff8..d2dd137 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -65,6 +65,7 @@ static const struct dentry_operations afs_fs_dentry_operations = {
.d_revalidate = afs_d_revalidate,
.d_delete = afs_d_delete,
.d_release = afs_d_release,
+ .d_automount = afs_d_automount,
};
#define AFS_DIR_HASHTBL_SIZE 128
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5f679b7..2c700dc 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -583,6 +583,7 @@ extern int afs_abort_to_error(u32);
extern const struct inode_operations afs_mntpt_inode_operations;
extern const struct file_operations afs_mntpt_file_operations;
+extern struct vfsmount *afs_d_automount(struct path *);
extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
extern void afs_mntpt_kill_timer(void);
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index a9e2303..ea9cfee 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -24,7 +24,6 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
struct nameidata *nd);
static int afs_mntpt_open(struct inode *inode, struct file *file);
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd);
static void afs_mntpt_expiry_timed_out(struct work_struct *work);
const struct file_operations afs_mntpt_file_operations = {
@@ -33,7 +32,6 @@ const struct file_operations afs_mntpt_file_operations = {
const struct inode_operations afs_mntpt_inode_operations = {
.lookup = afs_mntpt_lookup,
- .follow_link = afs_mntpt_follow_link,
.readlink = page_readlink,
.getattr = afs_getattr,
};
@@ -82,6 +80,7 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
_debug("symlink is a mountpoint");
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+ vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
spin_unlock(&vnode->lock);
}
@@ -205,52 +204,37 @@ error_no_devname:
}
/*
- * follow a link from a mountpoint directory, thus causing it to be mounted
+ * handle an automount point
*/
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *afs_d_automount(struct path *path)
{
struct vfsmount *newmnt;
int err;
- _enter("%p{%s},{%s:%p{%s},}",
- dentry,
- dentry->d_name.name,
- nd->path.mnt->mnt_devname,
- dentry,
- nd->path.dentry->d_name.name);
-
- dput(nd->path.dentry);
- nd->path.dentry = dget(dentry);
+ _enter("{%s,%s}", path->mnt->mnt_devname, path->dentry->d_name.name);
- newmnt = afs_mntpt_do_automount(nd->path.dentry);
- if (IS_ERR(newmnt)) {
- path_put(&nd->path);
- return (void *)newmnt;
- }
+ newmnt = afs_mntpt_do_automount(path->dentry);
+ if (IS_ERR(newmnt))
+ return newmnt;
mntget(newmnt);
- err = do_add_mount(newmnt, &nd->path, MNT_SHRINKABLE, &afs_vfsmounts);
+ err = do_add_mount(newmnt, path, MNT_SHRINKABLE, &afs_vfsmounts);
switch (err) {
case 0:
- path_put(&nd->path);
- nd->path.mnt = newmnt;
- nd->path.dentry = dget(newmnt->mnt_root);
schedule_delayed_work(&afs_mntpt_expiry_timer,
afs_mntpt_expiry_timeout * HZ);
- break;
+ _leave(" = %p {%s}", newmnt, newmnt->mnt_devname);
+ return newmnt;
case -EBUSY:
/* someone else made a mount here whilst we were busy */
- while (d_mountpoint(nd->path.dentry) &&
- follow_down(&nd->path))
- ;
- err = 0;
+ mntput(newmnt);
+ _leave(" = NULL [EBUSY]");
+ return NULL;
default:
mntput(newmnt);
- break;
+ _leave(" = %d", err);
+ return ERR_PTR(err);
}
-
- _leave(" = %d", err);
- return ERR_PTR(err);
}
/*
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 14/18] xstat: NFS: Use d_automount() rather than abusing follow_link() [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (12 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 13/18] xstat: AFS: Use d_automount() " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 15/18] xstat: CIFS: " David Howells
` (3 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: linux-cifs, linux-nfs, samba-technical, linux-kernel, dhowells,
linux-fsdevel, linux-ext4
Make NFS use the new d_automount() dentry operation rather than abusing
follow_link() on directories.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/nfs/dir.c | 2 +
fs/nfs/inode.c | 1 +
fs/nfs/internal.h | 1 +
fs/nfs/namespace.c | 87 ++++++++++++++++++++++++----------------------------
4 files changed, 44 insertions(+), 47 deletions(-)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 782b431..d7e5810 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -927,6 +927,7 @@ const struct dentry_operations nfs_dentry_operations = {
.d_revalidate = nfs_lookup_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
+ .d_automount = nfs_d_automount,
};
static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
@@ -1002,6 +1003,7 @@ const struct dentry_operations nfs4_dentry_operations = {
.d_revalidate = nfs_open_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
+ .d_automount = nfs_d_automount,
};
/*
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 8c6de96..f9737bd 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -296,6 +296,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
inode->i_op = &nfs_mountpoint_inode_operations;
inode->i_fop = NULL;
set_bit(NFS_INO_MOUNTPOINT, &nfsi->flags);
+ inode->i_flags |= S_AUTOMOUNT;
}
} else if (S_ISLNK(inode->i_mode))
inode->i_op = &nfs_symlink_inode_operations;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d8bd619..48de6f8 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -238,6 +238,7 @@ extern char *nfs_path(const char *base,
const struct dentry *droot,
const struct dentry *dentry,
char *buffer, ssize_t buflen);
+extern struct vfsmount *nfs_d_automount(struct path *path);
/* getroot.c */
extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index db6aa36..bf80079 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -88,9 +88,8 @@ Elong:
}
/*
- * nfs_follow_mountpoint - handle crossing a mountpoint on the server
- * @dentry - dentry of mountpoint
- * @nd - nameidata info
+ * nfs_d_automount - Handle crossing a mountpoint on the server
+ * @path - The mountpoint
*
* When we encounter a mountpoint on the server, we want to set up
* a mountpoint on the client too, to prevent inode numbers from
@@ -100,87 +99,81 @@ Elong:
* situation, and that different filesystems may want to use
* different security flavours.
*/
-static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *nfs_d_automount(struct path *path)
{
struct vfsmount *mnt;
- struct nfs_server *server = NFS_SERVER(dentry->d_inode);
+ struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
struct dentry *parent;
struct nfs_fh *fh = NULL;
struct nfs_fattr *fattr = NULL;
int err;
- dprintk("--> nfs_follow_mountpoint()\n");
+ dprintk("--> nfs_d_automount()\n");
- err = -ESTALE;
- if (IS_ROOT(dentry))
- goto out_err;
+ mnt = ERR_PTR(-ESTALE);
+ if (IS_ROOT(path->dentry))
+ goto out_nofree;
- err = -ENOMEM;
+ mnt = ERR_PTR(-ENOMEM);
fh = nfs_alloc_fhandle();
fattr = nfs_alloc_fattr();
if (fh == NULL || fattr == NULL)
- goto out_err;
+ goto out;
dprintk("%s: enter\n", __func__);
- dput(nd->path.dentry);
- nd->path.dentry = dget(dentry);
- /* Look it up again */
- parent = dget_parent(nd->path.dentry);
+ /* Look it up again to get its attributes */
+ parent = dget_parent(path->dentry);
err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
- &nd->path.dentry->d_name,
+ &path->dentry->d_name,
fh, fattr);
dput(parent);
- if (err != 0)
- goto out_err;
+ if (err != 0) {
+ mnt = ERR_PTR(err);
+ goto out;
+ }
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
- mnt = nfs_do_refmount(nd->path.mnt, nd->path.dentry);
+ mnt = nfs_do_refmount(path->mnt, path->dentry);
else
- mnt = nfs_do_submount(nd->path.mnt, nd->path.dentry, fh,
- fattr);
- err = PTR_ERR(mnt);
+ mnt = nfs_do_submount(path->mnt, path->dentry, fh, fattr);
if (IS_ERR(mnt))
- goto out_err;
+ goto out;
mntget(mnt);
- err = do_add_mount(mnt, &nd->path, nd->path.mnt->mnt_flags|MNT_SHRINKABLE,
+ err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE,
&nfs_automount_list);
- if (err < 0) {
+ switch (err) {
+ case 0:
+ dprintk("%s: done, success\n", __func__);
+ schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+ break;
+ case -EBUSY:
+ /* someone else made a mount here whilst we were busy */
mntput(mnt);
- if (err == -EBUSY)
- goto out_follow;
- goto out_err;
+ dprintk("%s: done, collision\n", __func__);
+ mnt = NULL;
+ break;
+ default:
+ mntput(mnt);
+ dprintk("%s: done, error %d\n", __func__, err);
+ mnt = ERR_PTR(err);
+ break;
}
- path_put(&nd->path);
- nd->path.mnt = mnt;
- nd->path.dentry = dget(mnt->mnt_root);
- schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+
out:
nfs_free_fattr(fattr);
nfs_free_fhandle(fh);
- dprintk("%s: done, returned %d\n", __func__, err);
-
- dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
- return ERR_PTR(err);
-out_err:
- path_put(&nd->path);
- goto out;
-out_follow:
- while (d_mountpoint(nd->path.dentry) &&
- follow_down(&nd->path))
- ;
- err = 0;
- goto out;
+out_nofree:
+ dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+ return mnt;
}
const struct inode_operations nfs_mountpoint_inode_operations = {
- .follow_link = nfs_follow_mountpoint,
.getattr = nfs_getattr,
};
const struct inode_operations nfs_referral_inode_operations = {
- .follow_link = nfs_follow_mountpoint,
};
static void nfs_expire_automounts(struct work_struct *work)
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 15/18] xstat: CIFS: Use d_automount() rather than abusing follow_link() [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (13 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 14/18] xstat: NFS: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 16/18] xstat: Remove the automount through follow_link() kludge code from pathwalk " David Howells
` (2 subsequent siblings)
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: dhowells, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
Make CIFS use the new d_automount() dentry operation rather than abusing
follow_link() on directories.
[NOTE: THIS IS UNTESTED!]
[Question: Why does cifs_dfs_do_refmount() when the caller has already done
that and could pass the result through?]
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Steve French <sfrench@samba.org>
---
fs/cifs/cifs_dfs_ref.c | 145 +++++++++++++++++++++++-------------------------
fs/cifs/cifsfs.h | 6 ++
fs/cifs/dir.c | 2 +
fs/cifs/inode.c | 8 ++-
4 files changed, 83 insertions(+), 78 deletions(-)
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 4516867..500b952 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -230,8 +230,8 @@ compose_mount_options_err:
}
-static struct vfsmount *cifs_dfs_do_refmount(const struct vfsmount *mnt_parent,
- struct dentry *dentry, const struct dfs_info3_param *ref)
+static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
+ const struct dfs_info3_param *ref)
{
struct cifs_sb_info *cifs_sb;
struct vfsmount *mnt;
@@ -239,12 +239,12 @@ static struct vfsmount *cifs_dfs_do_refmount(const struct vfsmount *mnt_parent,
char *devname = NULL;
char *fullpath;
- cifs_sb = CIFS_SB(dentry->d_inode->i_sb);
+ cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
/*
* this function gives us a path with a double backslash prefix. We
* require a single backslash for DFS.
*/
- fullpath = build_path_from_dentry(dentry);
+ fullpath = build_path_from_dentry(mntpt);
if (!fullpath)
return ERR_PTR(-ENOMEM);
@@ -262,35 +262,6 @@ static struct vfsmount *cifs_dfs_do_refmount(const struct vfsmount *mnt_parent,
}
-static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
- struct list_head *mntlist)
-{
- /* stolen from afs code */
- int err;
-
- mntget(newmnt);
- err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags | MNT_SHRINKABLE, mntlist);
- switch (err) {
- case 0:
- path_put(&nd->path);
- nd->path.mnt = newmnt;
- nd->path.dentry = dget(newmnt->mnt_root);
- schedule_delayed_work(&cifs_dfs_automount_task,
- cifs_dfs_mountpoint_expiry_timeout);
- break;
- case -EBUSY:
- /* someone else made a mount here whilst we were busy */
- while (d_mountpoint(nd->path.dentry) &&
- follow_down(&nd->path))
- ;
- err = 0;
- default:
- mntput(newmnt);
- break;
- }
- return err;
-}
-
static void dump_referral(const struct dfs_info3_param *ref)
{
cFYI(1, "DFS: ref path: %s", ref->path_name);
@@ -300,34 +271,30 @@ static void dump_referral(const struct dfs_info3_param *ref)
ref->path_consumed);
}
-
-static void*
-cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+/*
+ * Create a vfsmount that we can automount
+ */
+static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
{
struct dfs_info3_param *referrals = NULL;
unsigned int num_referrals = 0;
struct cifs_sb_info *cifs_sb;
struct cifsSesInfo *ses;
- char *full_path = NULL;
+ char *full_path;
int xid, i;
- int rc = 0;
- struct vfsmount *mnt = ERR_PTR(-ENOENT);
+ int rc;
+ struct vfsmount *mnt;
cFYI(1, "in %s", __func__);
- BUG_ON(IS_ROOT(dentry));
+ BUG_ON(IS_ROOT(mntpt));
xid = GetXid();
- dput(nd->path.dentry);
- nd->path.dentry = dget(dentry);
-
- cifs_sb = CIFS_SB(dentry->d_inode->i_sb);
+ cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
+ mnt = ERR_PTR(-EINVAL);
ses = cifs_sb->tcon->ses;
-
- if (!ses) {
- rc = -EINVAL;
- goto out_err;
- }
+ if (!ses)
+ goto free_xid;
/*
* The MSDFS spec states that paths in DFS referral requests and
@@ -335,56 +302,84 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
* the double backslashes usually used in the UNC. This function
* gives us the latter, so we must adjust the result.
*/
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
- goto out_err;
- }
+ mnt = ERR_PTR(-ENOMEM);
+ full_path = build_path_from_dentry(mntpt);
+ if (full_path == NULL)
+ goto free_xid;
rc = get_dfs_path(xid, ses , full_path + 1, cifs_sb->local_nls,
&num_referrals, &referrals,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ mnt = ERR_PTR(-ENOENT);
for (i = 0; i < num_referrals; i++) {
int len;
- dump_referral(referrals+i);
+ dump_referral(referrals + i);
/* connect to a node */
len = strlen(referrals[i].node_name);
if (len < 2) {
cERROR(1, "%s: Net Address path too short: %s",
__func__, referrals[i].node_name);
- rc = -EINVAL;
- goto out_err;
+ mnt = ERR_PTR(-EINVAL);
+ break;
}
- mnt = cifs_dfs_do_refmount(nd->path.mnt,
- nd->path.dentry, referrals + i);
+ mnt = cifs_dfs_do_refmount(mntpt, referrals + i);
cFYI(1, "%s: cifs_dfs_do_refmount:%s , mnt:%p", __func__,
referrals[i].node_name, mnt);
-
- /* complete mount procedure if we accured submount */
if (!IS_ERR(mnt))
- break;
+ goto success;
}
- /* we need it cause for() above could exit without valid submount */
- rc = PTR_ERR(mnt);
- if (IS_ERR(mnt))
- goto out_err;
-
- rc = add_mount_helper(mnt, nd, &cifs_dfs_automount_list);
+ /* no valid submounts were found; return error from get_dfs_path() by
+ * preference */
+ if (rc != 0)
+ mnt = ERR_PTR(rc);
-out:
- FreeXid(xid);
+success:
free_dfs_info_array(referrals, num_referrals);
kfree(full_path);
+free_xid:
+ FreeXid(xid);
cFYI(1, "leaving %s" , __func__);
return ERR_PTR(rc);
-out_err:
- path_put(&nd->path);
- goto out;
+}
+
+/*
+ * Attempt to automount the referral
+ */
+struct vfsmount *cifs_dfs_d_automount(struct path *path)
+{
+ struct vfsmount *newmnt;
+ int err;
+
+ cFYI(1, "in %s", __func__);
+
+ newmnt = cifs_dfs_do_automount(path->dentry);
+ if (IS_ERR(newmnt)) {
+ cFYI(1, "leaving %s [automount failed]" , __func__);
+ return newmnt;
+ }
+
+ mntget(newmnt);
+ err = do_add_mount(newmnt, path, MNT_SHRINKABLE,
+ &cifs_dfs_automount_list);
+ switch (err) {
+ case 0:
+ schedule_delayed_work(&cifs_dfs_automount_task,
+ cifs_dfs_mountpoint_expiry_timeout);
+ cFYI(1, "leaving %s [ok]" , __func__);
+ return newmnt;
+ case -EBUSY:
+ /* someone else made a mount here whilst we were busy */
+ mntput(newmnt);
+ cFYI(1, "leaving %s [EBUSY]" , __func__);
+ return NULL;
+ default:
+ mntput(newmnt);
+ cFYI(1, "leaving %s [error %d]" , __func__, err);
+ return ERR_PTR(err);
+ }
}
const struct inode_operations cifs_dfs_referral_inode_operations = {
- .follow_link = cifs_dfs_follow_mountpoint,
};
-
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 50bf70b..fb50a4a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -95,6 +95,12 @@ extern int cifs_readdir(struct file *file, void *direntry, filldir_t filldir);
extern const struct dentry_operations cifs_dentry_ops;
extern const struct dentry_operations cifs_ci_dentry_ops;
+#ifdef CONFIG_CIFS_DFS_UPCALL
+extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
+#else
+#define cifs_dfs_d_automount NULL
+#endif
+
/* Functions related to symlinks */
extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
extern void cifs_put_link(struct dentry *direntry,
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 65da30e..73fd652 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -804,6 +804,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
const struct dentry_operations cifs_dentry_ops = {
.d_revalidate = cifs_d_revalidate,
+ .d_automount = cifs_dfs_d_automount,
/* d_delete: cifs_d_delete, */ /* not needed except for debugging */
};
@@ -844,4 +845,5 @@ const struct dentry_operations cifs_ci_dentry_ops = {
.d_revalidate = cifs_d_revalidate,
.d_hash = cifs_ci_hash,
.d_compare = cifs_ci_compare,
+ .d_automount = cifs_dfs_d_automount,
};
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index ff4a62f..12d95f4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -31,7 +31,7 @@
#include "cifs_fs_sb.h"
-static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
+static void cifs_set_ops(struct inode *inode)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -59,7 +59,7 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
break;
case S_IFDIR:
#ifdef CONFIG_CIFS_DFS_UPCALL
- if (is_dfs_referral) {
+ if (IS_AUTOMOUNT(inode)) {
inode->i_op = &cifs_dfs_referral_inode_operations;
} else {
#else /* NO DFS support, treat as a directory */
@@ -170,7 +170,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
}
spin_unlock(&inode->i_lock);
- cifs_set_ops(inode, fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL);
+ if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
+ inode->i_flags |= S_AUTOMOUNT;
+ cifs_set_ops(inode);
}
void
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 16/18] xstat: Remove the automount through follow_link() kludge code from pathwalk [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (14 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 15/18] xstat: CIFS: " David Howells
@ 2010-07-15 2:17 ` David Howells
2010-07-15 2:17 ` [PATCH 17/18] xstat: Add an AT_NO_AUTOMOUNT flag to suppress terminal automount " David Howells
[not found] ` <20100715021709.5544.64506.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: dhowells, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
Remove the automount through follow_link() kludge code from pathwalk in favour
of using d_automount().
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/namei.c | 17 +++--------------
1 files changed, 3 insertions(+), 14 deletions(-)
diff --git a/fs/namei.c b/fs/namei.c
index fcec3c6..86068a2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -845,17 +845,6 @@ fail:
}
/*
- * This is a temporary kludge to deal with "automount" symlinks; proper
- * solution is to trigger them on follow_mount(), so that do_lookup()
- * would DTRT. To be killed before 2.6.34-final.
- */
-static inline int follow_on_final(struct inode *inode, unsigned lookup_flags)
-{
- return inode && unlikely(inode->i_op->follow_link) &&
- ((lookup_flags & LOOKUP_FOLLOW) || S_ISDIR(inode->i_mode));
-}
-
-/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
@@ -975,7 +964,8 @@ last_component:
if (err)
break;
inode = next.dentry->d_inode;
- if (follow_on_final(inode, lookup_flags)) {
+ if (inode && unlikely(inode->i_op->follow_link) &&
+ (lookup_flags & LOOKUP_FOLLOW)) {
err = do_follow_link(&next, nd);
if (err)
goto return_err;
@@ -1888,8 +1878,7 @@ reval:
struct inode *inode = path.dentry->d_inode;
void *cookie;
error = -ELOOP;
- /* S_ISDIR part is a temporary automount kludge */
- if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(inode->i_mode))
+ if (!(nd.flags & LOOKUP_FOLLOW))
goto exit_dput;
if (count++ == 32)
goto exit_dput;
^ permalink raw reply related [flat|nested] 101+ messages in thread* [PATCH 17/18] xstat: Add an AT_NO_AUTOMOUNT flag to suppress terminal automount [ver #6]
2010-07-15 2:17 [PATCH 00/18] Extended file stat functions [ver #6] David Howells
` (15 preceding siblings ...)
2010-07-15 2:17 ` [PATCH 16/18] xstat: Remove the automount through follow_link() kludge code from pathwalk " David Howells
@ 2010-07-15 2:17 ` David Howells
[not found] ` <20100715021709.5544.64506.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
17 siblings, 0 replies; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro
Cc: dhowells, linux-fsdevel, linux-nfs, linux-cifs, linux-kernel,
samba-technical, linux-ext4
Add an AT_NO_AUTOMOUNT flag to suppress terminal automounting of directories
with follow_link semantics. This can be used by fstatat()/xstat() users to
permit the gathering of attributes on an automount point and also prevent
mass-automounting of a directory of automount points by ls.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/namei.c | 15 ++++++++++-----
fs/stat.c | 4 +++-
include/linux/fcntl.h | 1 +
include/linux/namei.h | 2 ++
4 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/fs/namei.c b/fs/namei.c
index 86068a2..056427e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -654,7 +654,8 @@ static int follow_automount(struct path *path, int res)
/* no need for dcache_lock, as serialization is taken care in
* namespace.c
*/
-static int __follow_mount(struct path *path, unsigned nofollow)
+static int __follow_mount(struct path *path, unsigned nofollow,
+ struct nameidata *nd)
{
struct vfsmount *mounted;
int ret, res = 0;
@@ -674,8 +675,12 @@ static int __follow_mount(struct path *path, unsigned nofollow)
}
if (!d_automount_point(path->dentry))
break;
- if (nofollow)
- return -ELOOP;
+ if (!(nd->flags & LOOKUP_CONTINUE)) {
+ if (nofollow)
+ return -ELOOP;
+ if (nd->flags & LOOKUP_NO_AUTOMOUNT)
+ break;
+ }
ret = follow_automount(path, res);
if (ret < 0)
return ret;
@@ -769,7 +774,7 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
done:
path->mnt = mnt;
path->dentry = dentry;
- ret = __follow_mount(path, 0);
+ ret = __follow_mount(path, 0, nd);
if (unlikely(ret < 0))
path_put(path);
return ret;
@@ -1762,7 +1767,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
if (open_flag & O_EXCL)
goto exit_dput;
- error = __follow_mount(path, open_flag & O_NOFOLLOW);
+ error = __follow_mount(path, open_flag & O_NOFOLLOW, nd);
if (error < 0)
goto exit_dput;
diff --git a/fs/stat.c b/fs/stat.c
index bb0f538..3f2ab5f 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -182,11 +182,13 @@ int vfs_xstat(int dfd, const char __user *filename, int flags,
struct path path;
int error, lookup_flags;
- if (flags & ~(AT_SYMLINK_NOFOLLOW | KSTAT_QUERY_FLAGS))
+ if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+ KSTAT_QUERY_FLAGS))
return -EINVAL;
stat->query_flags = flags & KSTAT_QUERY_FLAGS;
lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+ lookup_flags |= (flags & AT_NO_AUTOMOUNT) ? LOOKUP_NO_AUTOMOUNT : 0;
error = user_path_at(dfd, filename, lookup_flags, &path);
if (!error) {
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index bcf8083..768b0fd 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -46,6 +46,7 @@
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
#define AT_FORCE_ATTR_SYNC 0x800 /* Force the attributes to be sync'd with the server */
+#define AT_NO_AUTOMOUNT 0x1000 /* Suppress terminal automount traversal */
#ifdef __KERNEL__
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 05b441d..1e1febf 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -43,12 +43,14 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
* - internal "there are more path components" flag
* - locked when lookup done with dcache_lock held
* - dentry cache is untrusted; force a real lookup
+ * - suppress terminal automount
*/
#define LOOKUP_FOLLOW 1
#define LOOKUP_DIRECTORY 2
#define LOOKUP_CONTINUE 4
#define LOOKUP_PARENT 16
#define LOOKUP_REVAL 64
+#define LOOKUP_NO_AUTOMOUNT 128
/*
* Intent data
*/
^ permalink raw reply related [flat|nested] 101+ messages in thread[parent not found: <20100715021709.5544.64506.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>]
* [PATCH 18/18] xstat: Provide a mechanism to gather extra results for [f]xstat() [ver #6]
[not found] ` <20100715021709.5544.64506.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
@ 2010-07-15 2:17 ` David Howells
[not found] ` <20100715021730.5544.68442.stgit-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
0 siblings, 1 reply; 101+ messages in thread
From: David Howells @ 2010-07-15 2:17 UTC (permalink / raw)
To: viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn
Cc: dhowells-H+wXaHxf7aLQT0dZR+AlfA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-cifs-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
samba-technical-w/Ol4Ecudpl8XjKLYN78aQ,
linux-ext4-u79uwXL29TY76Z2rM5mHXA
Provide a mechanism in the kernel by which extra results beyond those allocated
space in the xstat struct can be returned to userspace.
[I'm not sure this is the best way to do this; it's a bit unwieldy. However,
I'd rather not overburden struct kstat with fields for every extra result we
might want to return as it's allocated on the stack in various places.
Possibly the pass_result of struct xstat_extra_result could be placed in
struct kstat to be used if pass_result is non-NULL, and struct kstat could be
passed to container_of().]
This is modelled on the filldir approach used to read directory entries. This
allows kernel routines (such as NFSD) to access this information too.
A new inode operation (getattr_extra) is provided that interested filesystems
need to implement. If this is not provided, then it is assumed that no extra
results will be returned.
The getattr_extra() routine is passed a token to represent the request:
struct xstat_extra_result {
u64 request_mask;
struct kstat *stat;
xstat_extra_result_t pass_result;
};
The three fields in this struct are: the request_mask (with bits not
representing extra results edited out); the pointer to the kstat structure as
passed to getattr() (stat->query_flags may be useful); and a pointer to a
function to which each individual result should be passed.
The requests can be handled in order with something like the following:
u64 request_mask = token->request_mask;
do {
int request = __ffs64(request_mask);
request_mask &= ~(1ULL << request);
switch (request) {
case ilog2(XSTAT_REQUEST_FOO): {
struct xstat_foo foo;
ret = myfs_get_foo(inode, token, &foo);
if (!ret)
token->pass_result(token, request,
&foo, sizeof(foo));
break;
}
default:
ret = 0;
break;
}
} while (ret == 0 && request_mask);
The caller should probably embed token in something so that they can retrieve
it in the pass_result() function with container_of().
Signed-off-by: David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
fs/stat.c | 115 ++++++++++++++++++++++++++++++++++++++++----------
include/linux/fs.h | 12 ++++-
include/linux/stat.h | 27 ++++++++++++
3 files changed, 129 insertions(+), 25 deletions(-)
diff --git a/fs/stat.c b/fs/stat.c
index 3f2ab5f..65efbaa 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -113,6 +113,25 @@ int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
}
EXPORT_SYMBOL(vfs_getattr);
+/*
+ * Get the extra stat results
+ */
+static int vfs_get_xstat_extra_results(struct path *path,
+ struct xstat_extra_result *extra)
+{
+ struct vfsmount *mnt = path->mnt;
+ struct dentry *dentry = path->dentry;
+ struct inode *inode = dentry->d_inode;
+
+ if (extra && inode->i_op->getattr_extra) {
+ extra->request_mask =
+ extra->stat->request_mask & XSTAT_REQUEST__EXTRA_STATS;
+ if (extra->request_mask)
+ return inode->i_op->getattr_extra(mnt, dentry, extra);
+ }
+ return 0;
+}
+
/**
* vfs_fxstat - Get extended attributes by file descriptor
* @fd: The file descriptor refering to the file of interest
@@ -126,7 +145,8 @@ EXPORT_SYMBOL(vfs_getattr);
*
* 0 will be returned on success, and a -ve error code if unsuccessful.
*/
-int vfs_fxstat(unsigned int fd, struct kstat *stat)
+int vfs_fxstat(unsigned int fd, struct kstat *stat,
+ struct xstat_extra_result *extra)
{
struct file *f = fget(fd);
int error = -EBADF;
@@ -135,6 +155,8 @@ int vfs_fxstat(unsigned int fd, struct kstat *stat)
return -EINVAL;
if (f) {
error = vfs_xgetattr(f->f_path.mnt, f->f_path.dentry, stat);
+ if (!error)
+ error = vfs_get_xstat_extra_results(&f->f_path, extra);
fput(f);
}
return error;
@@ -155,7 +177,7 @@ int vfs_fstat(unsigned int fd, struct kstat *stat)
{
stat->query_flags = 0;
stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
- return vfs_fxstat(fd, stat);
+ return vfs_fxstat(fd, stat, NULL);
}
EXPORT_SYMBOL(vfs_fstat);
@@ -177,7 +199,7 @@ EXPORT_SYMBOL(vfs_fstat);
* 0 will be returned on success, and a -ve error code if unsuccessful.
*/
int vfs_xstat(int dfd, const char __user *filename, int flags,
- struct kstat *stat)
+ struct kstat *stat, struct xstat_extra_result *extra)
{
struct path path;
int error, lookup_flags;
@@ -193,6 +215,8 @@ int vfs_xstat(int dfd, const char __user *filename, int flags,
error = user_path_at(dfd, filename, lookup_flags, &path);
if (!error) {
error = vfs_xgetattr(path.mnt, path.dentry, stat);
+ if (!error)
+ error = vfs_get_xstat_extra_results(&path, extra);
path_put(&path);
}
return error;
@@ -217,7 +241,7 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
int flags)
{
stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
- return vfs_xstat(dfd, filename, flags, stat);
+ return vfs_xstat(dfd, filename, flags, stat, NULL);
}
EXPORT_SYMBOL(vfs_fstatat);
@@ -236,7 +260,7 @@ EXPORT_SYMBOL(vfs_fstatat);
int vfs_stat(const char __user *filename, struct kstat *stat)
{
stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
- return vfs_xstat(AT_FDCWD, filename, 0, stat);
+ return vfs_xstat(AT_FDCWD, filename, 0, stat, NULL);
}
EXPORT_SYMBOL(vfs_stat);
@@ -254,7 +278,7 @@ EXPORT_SYMBOL(vfs_stat);
*/
int vfs_lstat(const char __user *name, struct kstat *stat)
{
- return vfs_xstat(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW, stat);
+ return vfs_xstat(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW, stat, NULL);
}
EXPORT_SYMBOL(vfs_lstat);
@@ -562,25 +586,70 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
}
#endif /* __ARCH_WANT_STAT64 */
+struct xstat_extra_result_token {
+ struct xstat_extra_result extra;
+ void __user *buffer;
+ size_t buf_remain;
+ size_t result_size;
+};
+
+/*
+ * copy extra results to userspace
+ */
+static int xstat_pass_result(struct xstat_extra_result *extra,
+ unsigned request, const void *result,
+ size_t len)
+{
+ struct xstat_extra_result_token *token =
+ container_of(extra, struct xstat_extra_result_token, extra);
+
+ /* we shouldn't see anything that wasn't asked for */
+ BUG_ON(!((token->extra.request_mask >> request) & 1));
+
+ token->extra.stat->result_mask |= 1ULL << request;
+ token->result_size += len;
+ if (token->buffer) {
+ if (len > token->buf_remain)
+ return -E2BIG;
+ if (copy_to_user(token->buffer, result, len) != 0)
+ return -EFAULT;
+ token->buffer += len;
+ token->buf_remain -= len;
+ }
+ return 0;
+}
+
/*
* Get the xstat parameters if supplied
*/
static int xstat_get_params(struct xstat_parameters __user *_params,
- struct kstat *stat)
+ struct xstat __user *buffer, size_t bufsize,
+ struct kstat *stat,
+ struct xstat_extra_result_token *token)
{
struct xstat_parameters params;
memset(stat, 0xde, sizeof(*stat)); // DEBUGGING
+ if (!buffer && bufsize > 0)
+ return -EINVAL;
+ if (bufsize > 0 && bufsize < sizeof(struct xstat))
+ return -E2BIG;
+
+ stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
+ stat->result_mask = 0;
if (_params) {
if (copy_from_user(¶ms, _params, sizeof(params)) != 0)
return -EFAULT;
stat->request_mask =
params.request_mask & XSTAT_REQUEST__ALL_STATS;
- } else {
- stat->request_mask = XSTAT_REQUEST__BASIC_STATS;
}
- stat->result_mask = 0;
+
+ token->extra.stat = stat;
+ token->extra.pass_result = xstat_pass_result;
+ token->buffer = buffer ? buffer->st_extra_results : NULL;
+ token->result_size = sizeof(struct xstat);
+ token->buf_remain = bufsize > 0 ? bufsize - sizeof(struct xstat) : 0;
return 0;
}
@@ -597,14 +666,14 @@ static int xstat_get_params(struct xstat_parameters __user *_params,
* data written into the buffer (or -EFAULT).
*/
static long xstat_set_result(struct kstat *stat,
- struct xstat __user *buffer, size_t bufsize)
+ struct xstat __user *buffer, size_t bufsize,
+ struct xstat_extra_result_token *token)
{
struct xstat tmp;
- size_t result_size = sizeof(tmp);
if (bufsize == 0)
- return result_size;
- if (bufsize < result_size)
+ return token->result_size;
+ if (bufsize < token->result_size)
return -E2BIG;
/* transfer the fixed results */
@@ -640,9 +709,9 @@ static long xstat_set_result(struct kstat *stat,
if (tmp.st_result_mask & XSTAT_REQUEST_INODE_FLAGS)
tmp.st_inode_flags = stat->inode_flags;
- if (copy_to_user(buffer, &tmp, result_size) != 0)
+ if (copy_to_user(buffer, &tmp, sizeof(tmp)) != 0)
return -EFAULT;
- return result_size;
+ return token->result_size;
}
/*
@@ -653,16 +722,17 @@ SYSCALL_DEFINE6(xstat,
struct xstat_parameters __user *, params,
struct xstat __user *, buffer, size_t, bufsize)
{
+ struct xstat_extra_result_token token;
struct kstat stat;
int error;
- error = xstat_get_params(params, &stat);
+ error = xstat_get_params(params, buffer, bufsize, &stat, &token);
if (error != 0)
return error;
- error = vfs_xstat(dfd, filename, atflag, &stat);
+ error = vfs_xstat(dfd, filename, atflag, &stat, &token.extra);
if (error)
return error;
- return xstat_set_result(&stat, buffer, bufsize);
+ return xstat_set_result(&stat, buffer, bufsize, &token);
}
/*
@@ -672,18 +742,19 @@ SYSCALL_DEFINE5(fxstat, unsigned int, fd, unsigned int, flags,
struct xstat_parameters __user *, params,
struct xstat __user *, buffer, size_t, bufsize)
{
+ struct xstat_extra_result_token token;
struct kstat stat;
int error;
- error = xstat_get_params(params, &stat);
+ error = xstat_get_params(params, buffer, bufsize, &stat, &token);
if (error < 0)
return error;
stat.query_flags = flags;
- error = vfs_fxstat(fd, &stat);
+ error = vfs_fxstat(fd, &stat, &token.extra);
if (error)
return error;
- return xstat_set_result(&stat, buffer, bufsize);
+ return xstat_set_result(&stat, buffer, bufsize, &token);
}
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 579ad9d..ae87289 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1531,7 +1531,9 @@ struct inode_operations {
int (*permission) (struct inode *, int);
int (*check_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
+ int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
+ int (*getattr_extra) (struct vfsmount *, struct dentry *,
+ struct xstat_extra_result *);
int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
@@ -2345,6 +2347,8 @@ extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int vfs_xgetattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int vfs_xgetattr_extra(struct vfsmount *, struct dentry *, struct kstat *,
+ xstat_extra_result_t, void *);
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);
@@ -2357,8 +2361,10 @@ 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_xstat(int, const char __user *, int, struct kstat *);
-extern int vfs_xfstat(unsigned int, struct kstat *);
+extern int vfs_xstat(int, const char __user *, int, struct kstat *,
+ struct xstat_extra_result *);
+extern int vfs_xfstat(unsigned int, struct kstat *,
+ struct xstat_extra_result *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 41a3c22..ec000ff 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -109,6 +109,7 @@ struct xstat_parameters {
#define XSTAT_REQUEST_INODE_FLAGS 0x00004000ULL /* want/got st_inode_flags */
#define XSTAT_REQUEST__EXTENDED_STATS 0x00007fffULL /* the stuff in the xstat struct */
#define XSTAT_REQUEST__ALL_STATS 0x00007fffULL /* the defined set of requestables */
+#define XSTAT_REQUEST__EXTRA_STATS (XSTAT_REQUEST__ALL_STATS & ~XSTAT_REQUEST__EXTENDED_STATS)
};
struct xstat_dev {
@@ -167,6 +168,32 @@ struct xstat {
#include <linux/types.h>
#include <linux/time.h>
+/**
+ * xstat_extra_result_t - Function to call to return extra stat results
+ * @token: The token given to the caller
+ * @request: The bit number of the request
+ * @result: The result data to include
+ * @len: The length of the result data
+ *
+ * Request is the bit number from one of the bits that may be set in
+ * (kstat->request_mask & XSTAT_REQUEST__EXTRA_STATS).
+ *
+ * The results must be passed in ascending order of bit number.
+ */
+struct xstat_extra_result;
+typedef int (*xstat_extra_result_t)(struct xstat_extra_result *token,
+ unsigned request, const void *result,
+ size_t len);
+
+struct xstat_extra_result {
+ u64 request_mask;
+ struct kstat *stat;
+ xstat_extra_result_t pass_result;
+};
+
+/*
+ * Linux's internal stat record, obtained by vfs_[x]getattr()
+ */
struct kstat {
u64 request_mask; /* what fields the user asked for */
u64 result_mask; /* what fields the user got */
^ permalink raw reply related [flat|nested] 101+ messages in thread