ipc: Store mqueue sysctls in the ipc namespace

Right now, the mqueue sysctls take ipc namespaces into account in a
rather hacky way. This works in most cases, but does not respect the
user namespace.

Within the user namespace, the user cannot change the /proc/sys/fs/mqueue/*
parametres. This poses a problem in the rootless containers.

To solve this I changed the implementation of the mqueue sysctls just
like some other sysctls.

So far, the changes do not provide additional access to files. This will
be done in a future patch.

v3:
* Don't implemenet set_permissions to keep the current behavior.

v2:
* Fixed compilation problem if CONFIG_POSIX_MQUEUE_SYSCTL is not
  specified.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/b0ccbb2489119f1f20c737cf1930c3a9c4e4243a.1644862280.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

3 files changed, 76 insertions, 61 deletions

diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 72a92a08c848..fbf6a8b93a26 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -9,39 +9,9 @@
 #include <linux/ipc_namespace.h>
 #include <linux/sysctl.h>
 
-#ifdef CONFIG_PROC_SYSCTL
-static void *get_mq(struct ctl_table *table)
-{
-	char *which = table->data;
-	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
-	which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
-	return which;
-}
-
-static int proc_mq_dointvec(struct ctl_table *table, int write,
-			    void *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table mq_table;
-	memcpy(&mq_table, table, sizeof(mq_table));
-	mq_table.data = get_mq(table);
-
-	return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
-}
-
-static int proc_mq_dointvec_minmax(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table mq_table;
-	memcpy(&mq_table, table, sizeof(mq_table));
-	mq_table.data = get_mq(table);
-
-	return proc_dointvec_minmax(&mq_table, write, buffer,
-					lenp, ppos);
-}
-#else
-#define proc_mq_dointvec NULL
-#define proc_mq_dointvec_minmax NULL
-#endif
+#include <linux/stat.h>
+#include <linux/capability.h>
+#include <linux/slab.h>
 
 static int msg_max_limit_min = MIN_MSGMAX;
 static int msg_max_limit_max = HARD_MSGMAX;
@@ -55,14 +25,14 @@ static struct ctl_table mq_sysctls[] = {
 		.data		= &init_ipc_ns.mq_queues_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "msg_max",
 		.data		= &init_ipc_ns.mq_msg_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &msg_max_limit_min,
 		.extra2		= &msg_max_limit_max,
 	},
@@ -71,7 +41,7 @@ static struct ctl_table mq_sysctls[] = {
 		.data		= &init_ipc_ns.mq_msgsize_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &msg_maxsize_limit_min,
 		.extra2		= &msg_maxsize_limit_max,
 	},
@@ -80,7 +50,7 @@ static struct ctl_table mq_sysctls[] = {
 		.data		= &init_ipc_ns.mq_msg_default,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &msg_max_limit_min,
 		.extra2		= &msg_max_limit_max,
 	},
@@ -89,32 +59,73 @@ static struct ctl_table mq_sysctls[] = {
 		.data		= &init_ipc_ns.mq_msgsize_default,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_mq_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &msg_maxsize_limit_min,
 		.extra2		= &msg_maxsize_limit_max,
 	},
 	{}
 };
 
-static struct ctl_table mq_sysctl_dir[] = {
-	{
-		.procname	= "mqueue",
-		.mode		= 0555,
-		.child		= mq_sysctls,
-	},
-	{}
-};
+static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
+{
+	return &current->nsproxy->ipc_ns->mq_set;
+}
 
-static struct ctl_table mq_sysctl_root[] = {
-	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= mq_sysctl_dir,
-	},
-	{}
+static int set_is_seen(struct ctl_table_set *set)
+{
+	return &current->nsproxy->ipc_ns->mq_set == set;
+}
+
+static struct ctl_table_root set_root = {
+	.lookup = set_lookup,
 };
 
-struct ctl_table_header *mq_register_sysctl_table(void)
+bool setup_mq_sysctls(struct ipc_namespace *ns)
 {
-	return register_sysctl_table(mq_sysctl_root);
+	struct ctl_table *tbl;
+
+	setup_sysctl_set(&ns->mq_set, &set_root, set_is_seen);
+
+	tbl = kmemdup(mq_sysctls, sizeof(mq_sysctls), GFP_KERNEL);
+	if (tbl) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(mq_sysctls); i++) {
+			if (tbl[i].data == &init_ipc_ns.mq_queues_max)
+				tbl[i].data = &ns->mq_queues_max;
+
+			else if (tbl[i].data == &init_ipc_ns.mq_msg_max)
+				tbl[i].data = &ns->mq_msg_max;
+
+			else if (tbl[i].data == &init_ipc_ns.mq_msgsize_max)
+				tbl[i].data = &ns->mq_msgsize_max;
+
+			else if (tbl[i].data == &init_ipc_ns.mq_msg_default)
+				tbl[i].data = &ns->mq_msg_default;
+
+			else if (tbl[i].data == &init_ipc_ns.mq_msgsize_default)
+				tbl[i].data = &ns->mq_msgsize_default;
+			else
+				tbl[i].data = NULL;
+		}
+
+		ns->mq_sysctls = __register_sysctl_table(&ns->mq_set, "fs/mqueue", tbl);
+	}
+	if (!ns->mq_sysctls) {
+		kfree(tbl);
+		retire_sysctl_set(&ns->mq_set);
+		return false;
+	}
+
+	return true;
+}
+
+void retire_mq_sysctls(struct ipc_namespace *ns)
+{
+	struct ctl_table *tbl;
+
+	tbl = ns->mq_sysctls->ctl_table_arg;
+	unregister_sysctl_table(ns->mq_sysctls);
+	retire_sysctl_set(&ns->mq_set);
+	kfree(tbl);
 }
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 5becca9be867..1b4a3be71636 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -163,8 +163,6 @@ static void remove_notification(struct mqueue_inode_info *info);
 
 static struct kmem_cache *mqueue_inode_cachep;
 
-static struct ctl_table_header *mq_sysctl_table;
-
 static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
 {
 	return container_of(inode, struct mqueue_inode_info, vfs_inode);
@@ -1713,8 +1711,10 @@ static int __init init_mqueue_fs(void)
 	if (mqueue_inode_cachep == NULL)
 		return -ENOMEM;
 
-	/* ignore failures - they are not fatal */
-	mq_sysctl_table = mq_register_sysctl_table();
+	if (!setup_mq_sysctls(&init_ipc_ns)) {
+		pr_warn("sysctl registration failed\n");
+		return -ENOMEM;
+	}
 
 	error = register_filesystem(&mqueue_fs_type);
 	if (error)
@@ -1731,8 +1731,6 @@ static int __init init_mqueue_fs(void)
 out_filesystem:
 	unregister_filesystem(&mqueue_fs_type);
 out_sysctl:
-	if (mq_sysctl_table)
-		unregister_sysctl_table(mq_sysctl_table);
 	kmem_cache_destroy(mqueue_inode_cachep);
 	return error;
 }
diff --git a/ipc/namespace.c b/ipc/namespace.c
index ae83f0f2651b..f760243ca685 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -59,6 +59,10 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	if (err)
 		goto fail_put;
 
+	err = -ENOMEM;
+	if (!setup_mq_sysctls(ns))
+		goto fail_put;
+
 	sem_init_ns(ns);
 	msg_init_ns(ns);
 	shm_init_ns(ns);
@@ -125,6 +129,8 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
 
+	retire_mq_sysctls(ns);
+
 	dec_ipc_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);