sysctl: merge equal proc_sys_read and proc_sys_write

Many (most of) sysctls do not have a per-container sense.  E.g.
kernel.print_fatal_signals, vm.panic_on_oom, net.core.netdev_budget and so on
and so forth.  Besides, tuning then from inside a container is not even
secure.  On the other hand, hiding them completely from the container's tasks
sometimes causes user-space to stop working.

When developing net sysctl, the common practice was to duplicate a table and
drop the write bits in table->mode, but this approach was not very elegant,
lead to excessive memory consumption and was not suitable in general.

Here's the alternative solution.  To facilitate the per-container sysctls
ctl_table_root-s were introduced.  Each root contains a list of
ctl_table_header-s that are visible to different namespaces.  The idea of this
set is to add the permissions() callback on the ctl_table_root to allow ctl
root limit permissions to the same ctl_table-s.

The main user of this functionality is the net-namespaces code, but later this
will (should) be used by more and more namespaces, containers and control
groups.

Actually, this idea's core is in a single hunk in the third patch.  First two
patches are cleanups for sysctl code, while the third one mostly extends the
arguments set of some sysctl functions.

This patch:

These ->read and ->write callbacks act in a very similar way, so merge these
paths to reduce the number of places to patch later and shrink the .text size
(a bit).

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: "David S. Miller" <davem@davemloft.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexey Dobriyan <adobriyan@sw.ru>
Cc: Denis V. Lunev <den@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 11 insertions, 39 deletions

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 614c34b..5e31585 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -165,8 +165,8 @@ out:
 	return err;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
+		size_t count, loff_t *ppos, int write)
 {
 	struct dentry *dentry = filp->f_dentry;
 	struct ctl_table_header *head;
@@ -190,12 +190,12 @@ static ssize_t proc_sys_read(struct file *filp, char __user *buf,
 	 * and won't be until we finish.
 	 */
 	error = -EPERM;
-	if (sysctl_perm(table, MAY_READ))
+	if (sysctl_perm(table, write ? MAY_WRITE : MAY_READ))
 		goto out;
 
 	/* careful: calling conventions are nasty here */
 	res = count;
-	error = table->proc_handler(table, 0, filp, buf, &res, ppos);
+	error = table->proc_handler(table, write, filp, buf, &res, ppos);
 	if (!error)
 		error = res;
 out:
@@ -204,44 +204,16 @@ out:
 	return error;
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+static ssize_t proc_sys_read(struct file *filp, char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	struct dentry *dentry = filp->f_dentry;
-	struct ctl_table_header *head;
-	struct ctl_table *table;
-	ssize_t error;
-	size_t res;
-
-	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-	/* Has the sysctl entry disappeared on us? */
-	error = -ENOENT;
-	if (!table)
-		goto out;
-
-	/* Has the sysctl entry been replaced by a directory? */
-	error = -EISDIR;
-	if (!table->proc_handler)
-		goto out;
-
-	/*
-	 * At this point we know that the sysctl was not unregistered
-	 * and won't be until we finish.
-	 */
-	error = -EPERM;
-	if (sysctl_perm(table, MAY_WRITE))
-		goto out;
-
-	/* careful: calling conventions are nasty here */
-	res = count;
-	error = table->proc_handler(table, 1, filp, (char __user *)buf,
-				    &res, ppos);
-	if (!error)
-		error = res;
-out:
-	sysctl_head_finish(head);
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+}
 
-	return error;
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
 }