introduce sys_syncfs to sync a single file system

It is frequently useful to sync a single file system, instead of all
mounted file systems via sync(2):

 - On machines with many mounts, it is not at all uncommon for some of
   them to hang (e.g. unresponsive NFS server).  sync(2) will get stuck on
   those and may never get to the one you do care about (e.g., /).
 - Some applications write lots of data to the file system and then
   want to make sure it is flushed to disk.  Calling fsync(2) on each
   file introduces unnecessary ordering constraints that result in a large
   amount of sub-optimal writeback/flush/commit behavior by the file
   system.

There are currently two ways (that I know of) to sync a single super_block:

 - BLKFLSBUF ioctl on the block device: That also invalidates the bdev
   mapping, which isn't usually desirable, and doesn't work for non-block
   file systems.
 - 'mount -o remount,rw' will call sync_filesystem as an artifact of the
   current implemention.  Relying on this little-known side effect for
   something like data safety sounds foolish.

Both of these approaches require root privileges, which some applications
do not have (nor should they need?) given that sync(2) is an unprivileged
operation.

This patch introduces a new system call syncfs(2) that takes an fd and
syncs only the file system it references.  Maybe someday we can

 $ sync /some/path

and not get

 sync: ignoring all arguments

The syscall is motivated by comments by Al and Christoph at the last LSF.
syncfs(2) seems like an appropriate name given statfs(2).

A similar ioctl was also proposed a while back, see
	http://marc.info/?l=linux-fsdevel&m=127970513829285&w=2

Signed-off-by: Sage Weil <sage@newdream.net>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

7 files changed, 34 insertions, 2 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 430312ba6e3..849a9d23c71 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -847,4 +847,5 @@ ia32_sys_call_table:
 	.quad sys_name_to_handle_at
 	.quad compat_sys_open_by_handle_at
 	.quad compat_sys_clock_adjtime
+	.quad sys_syncfs
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index ffaf183c619..a755ef5e597 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -349,10 +349,11 @@
 #define __NR_name_to_handle_at	341
 #define __NR_open_by_handle_at  342
 #define __NR_clock_adjtime	343
+#define __NR_syncfs             344
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 344
+#define NR_syscalls 345
 
 #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 5466bea670e..160fa76bd57 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -675,6 +675,8 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
 __SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
 #define __NR_clock_adjtime			305
 __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
+#define __NR_syncfs                             306
+__SYSCALL(__NR_syncfs, sys_syncfs)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 5f181742e8f..abce34d5c79 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -343,3 +343,4 @@ ENTRY(sys_call_table)
 	.long sys_name_to_handle_at
 	.long sys_open_by_handle_at
 	.long sys_clock_adjtime
+	.long sys_syncfs
diff --git a/fs/sync.c b/fs/sync.c
index ba76b9623e7..92ca208777d 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/namei.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
@@ -128,6 +129,29 @@ void emergency_sync(void)
 	}
 }
 
+/*
+ * sync a single super
+ */
+SYSCALL_DEFINE1(syncfs, int, fd)
+{
+	struct file *file;
+	struct super_block *sb;
+	int ret;
+	int fput_needed;
+
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+	sb = file->f_dentry->d_sb;
+
+	down_read(&sb->s_umount);
+	ret = sync_filesystem(sb);
+	up_read(&sb->s_umount);
+
+	fput_light(file, fput_needed);
+	return ret;
+}
+
 /**
  * vfs_fsync_range - helper to sync a range of data & metadata to disk
  * @file:		file to sync
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index d94f447c667..176b825add5 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -652,9 +652,11 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
 __SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
 #define __NR_clock_adjtime 266
 __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
+#define __NR_syncfs 264
+__SYSCALL(__NR_syncfs, sys_syncfs)
 
 #undef __NR_syscalls
-#define __NR_syscalls 267
+#define __NR_syscalls 268
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1f5c18e6f4f..83ecc1749ef 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -825,6 +825,7 @@ asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags
 asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags,
 				  u64 mask, int fd,
 				  const char  __user *pathname);
+asmlinkage long sys_syncfs(int fd);
 
 int kernel_execve(const char *filename, const char *const argv[], const char *const envp[]);