Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Alexey Gladkov <legion@kernel.org>
To:     LKML <linux-kernel@vger.kernel.org>,
        Linux Containers <containers@lists.linux.dev>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Christian Brauner <brauner@kernel.org>,
        "Eric W . Biederman" <ebiederm@xmission.com>,
        Kees Cook <keescook@chromium.org>,
        Manfred Spraul <manfred@colorfullife.com>
Subject: [PATCH v1 2/3] sysctl: Allow to change limits for posix messages queues
Date:   Tue, 16 Aug 2022 17:42:44 +0200
Message-Id: <0e095acd72553868925b116d778357eb019796a2.1660664258.git.legion@kernel.org>
In-Reply-To: <cover.1660664258.git.legion@kernel.org>
References: <87wnc1i2wo.fsf@email.froward.int.ebiederm.org> <cover.1660664258.git.legion@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

All parameters of posix messages queues (queues_max/msg_max/msgsize_max)
end up being limited by RLIMIT_MSGQUEUE. The code in mqueue_get_inode is
where that limiting happens.

The RLIMIT_MSGQUEUE is bound to the user namespace and is counted
hierarchically.

We can allow root in the user namespace to modify the posix messages
queues parameters.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 ipc/mq_sysctl.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index fbf6a8b93a26..39dcf086b7c2 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -12,6 +12,7 @@
 #include <linux/stat.h>
 #include <linux/capability.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 
 static int msg_max_limit_min = MIN_MSGMAX;
 static int msg_max_limit_max = HARD_MSGMAX;
@@ -76,8 +77,43 @@ static int set_is_seen(struct ctl_table_set *set)
 	return &current->nsproxy->ipc_ns->mq_set == set;
 }
 
+static int mq_permissions(struct ctl_table_header *head, struct ctl_table *table)
+{
+	struct ipc_namespace *ns =
+		container_of(head->set, struct ipc_namespace, mq_set);
+
+	if (ns->user_ns != &init_user_ns) {
+		kuid_t ns_root_uid = make_kuid(ns->user_ns, 0);
+		kgid_t ns_root_gid = make_kgid(ns->user_ns, 0);
+
+		if (uid_valid(ns_root_uid) && uid_eq(current_euid(), ns_root_uid))
+			return  table->mode >> 6;
+
+		if (gid_valid(ns_root_gid) && in_egroup_p(ns_root_gid))
+			return table->mode >> 3;
+	}
+
+	return table->mode;
+}
+
+static void mq_set_ownership(struct ctl_table_header *head,
+			     struct ctl_table *table,
+			     kuid_t *uid, kgid_t *gid)
+{
+	struct ipc_namespace *ns =
+		container_of(head->set, struct ipc_namespace, mq_set);
+
+	kuid_t ns_root_uid = make_kuid(ns->user_ns, 0);
+	kgid_t ns_root_gid = make_kgid(ns->user_ns, 0);
+
+	*uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID;
+	*gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID;
+}
+
 static struct ctl_table_root set_root = {
 	.lookup = set_lookup,
+	.permissions = mq_permissions,
+	.set_ownership = mq_set_ownership,
 };
 
 bool setup_mq_sysctls(struct ipc_namespace *ns)
-- 
2.33.4