[PATCH] saner handling of auto_acct_off() and DQUOT_OFF() in umount

The way we currently deal with quota and process accounting that might
keep vfsmount busy at umount time is inherently broken; we try to turn
them off just in case (not quite correctly, at that) and

  a) pray umount doesn't fail (otherwise they'll stay turned off)
  b) pray nobody doesn anything funny just as we turn quota off

Moreover, LSM provides hooks for doing the same sort of broken logics.

The proper way to deal with that is to introduce the second kind of
reference to vfsmount.  Semantics:

 - when the last normal reference is dropped, all special ones are
   converted to normal ones and if there had been any, cleanup is done.
 - normal reference can be cloned into a special one
 - special reference can be converted to normal one; that's a no-op if
   we'd already passed the point of no return (i.e.  mntput() had
   converted special references to normal and started cleanup).

The way it works: e.g. starting process accounting converts the vfsmount
reference pinned by the opened file into special one and turns it back
to normal when it gets shut down; acct_auto_close() is done when no
normal references are left.  That way it does *not* obstruct umount(2)
and it silently gets turned off when the last normal reference to
vfsmount is gone.  Which is exactly what we want...

The same should be done by LSM module that holds some internal
references to vfsmount and wants to shut them down on umount - it should
make them special and security_sb_umount_close() will be called exactly
when the last normal reference to vfsmount is gone.

quota handling is even simpler - we don't use normal file IO anymore, so
there's no need to hold vfsmounts at all.  DQUOT_OFF() is done from
deactivate_super(), where it really belongs.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 62 insertions, 30 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 2e3f4a47e7d0..6312d6bd43e3 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -54,6 +54,7 @@
 #include <linux/jiffies.h>
 #include <linux/times.h>
 #include <linux/syscalls.h>
+#include <linux/mount.h>
 #include <asm/uaccess.h>
 #include <asm/div64.h>
 #include <linux/blkdev.h> /* sector_div */
@@ -192,6 +193,7 @@ static void acct_file_reopen(struct file *file)
 		add_timer(&acct_globals.timer);
 	}
 	if (old_acct) {
+		mnt_unpin(old_acct->f_vfsmnt);
 		spin_unlock(&acct_globals.lock);
 		do_acct_process(0, old_acct);
 		filp_close(old_acct, NULL);
@@ -199,6 +201,42 @@ static void acct_file_reopen(struct file *file)
 	}
 }
 
+static int acct_on(char *name)
+{
+	struct file *file;
+	int error;
+
+	/* Difference from BSD - they don't do O_APPEND */
+	file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	if (!S_ISREG(file->f_dentry->d_inode->i_mode)) {
+		filp_close(file, NULL);
+		return -EACCES;
+	}
+
+	if (!file->f_op->write) {
+		filp_close(file, NULL);
+		return -EIO;
+	}
+
+	error = security_acct(file);
+	if (error) {
+		filp_close(file, NULL);
+		return error;
+	}
+
+	spin_lock(&acct_globals.lock);
+	mnt_pin(file->f_vfsmnt);
+	acct_file_reopen(file);
+	spin_unlock(&acct_globals.lock);
+
+	mntput(file->f_vfsmnt);	/* it's pinned, now give up active reference */
+
+	return 0;
+}
+
 /**
  * sys_acct - enable/disable process accounting
  * @name: file name for accounting records or NULL to shutdown accounting
@@ -212,47 +250,41 @@ static void acct_file_reopen(struct file *file)
  */
 asmlinkage long sys_acct(const char __user *name)
 {
-	struct file *file = NULL;
-	char *tmp;
 	int error;
 
 	if (!capable(CAP_SYS_PACCT))
 		return -EPERM;
 
 	if (name) {
-		tmp = getname(name);
-		if (IS_ERR(tmp)) {
+		char *tmp = getname(name);
+		if (IS_ERR(tmp))
 			return (PTR_ERR(tmp));
-		}
-		/* Difference from BSD - they don't do O_APPEND */
-		file = filp_open(tmp, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+		error = acct_on(tmp);
 		putname(tmp);
-		if (IS_ERR(file)) {
-			return (PTR_ERR(file));
-		}
-		if (!S_ISREG(file->f_dentry->d_inode->i_mode)) {
-			filp_close(file, NULL);
-			return (-EACCES);
-		}
-
-		if (!file->f_op->write) {
-			filp_close(file, NULL);
-			return (-EIO);
+	} else {
+		error = security_acct(NULL);
+		if (!error) {
+			spin_lock(&acct_globals.lock);
+			acct_file_reopen(NULL);
+			spin_unlock(&acct_globals.lock);
 		}
 	}
+	return error;
+}
 
-	error = security_acct(file);
-	if (error) {
-		if (file)
-			filp_close(file, NULL);
-		return error;
-	}
-
+/**
+ * acct_auto_close - turn off a filesystem's accounting if it is on
+ * @m: vfsmount being shut down
+ *
+ * If the accounting is turned on for a file in the subtree pointed to
+ * to by m, turn accounting off.  Done when m is about to die.
+ */
+void acct_auto_close_mnt(struct vfsmount *m)
+{
 	spin_lock(&acct_globals.lock);
-	acct_file_reopen(file);
+	if (acct_globals.file && acct_globals.file->f_vfsmnt == m)
+		acct_file_reopen(NULL);
 	spin_unlock(&acct_globals.lock);
-
-	return (0);
 }
 
 /**
@@ -266,8 +298,8 @@ void acct_auto_close(struct super_block *sb)
 {
 	spin_lock(&acct_globals.lock);
 	if (acct_globals.file &&
-	    acct_globals.file->f_dentry->d_inode->i_sb == sb) {
-		acct_file_reopen((struct file *)NULL);
+	    acct_globals.file->f_vfsmnt->mnt_sb == sb) {
+		acct_file_reopen(NULL);
 	}
 	spin_unlock(&acct_globals.lock);
 }