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 v3 1/3] sysctl: Allow change system v ipc sysctls inside ipc namespace
Date:   Wed, 21 Sep 2022 12:41:47 +0200
Message-Id: <e2d84d3ec0172cfff759e6065da84ce0cc2736f8.1663756794.git.legion@kernel.org>
In-Reply-To: <cover.1663756794.git.legion@kernel.org>
References: <202209211737.0Bu0F40t-lkp@intel.com> <cover.1663756794.git.legion@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Rootless containers are not allowed to modify kernel IPC parameters.

All default limits are set to such high values that in fact there are no
limits at all. All limits are not inherited and are initialized to
default values when a new ipc_namespace is created.

For new ipc_namespace:

size_t       ipc_ns.shm_ctlmax = SHMMAX; // (ULONG_MAX - (1UL << 24))
size_t       ipc_ns.shm_ctlall = SHMALL; // (ULONG_MAX - (1UL << 24))
int          ipc_ns.shm_ctlmni = IPCMNI; // (1 << 15)
int          ipc_ns.shm_rmid_forced = 0;
unsigned int ipc_ns.msg_ctlmax = MSGMAX; // 8192
unsigned int ipc_ns.msg_ctlmni = MSGMNI; // 32000
unsigned int ipc_ns.msg_ctlmnb = MSGMNB; // 16384

The shm_tot (total amount of shared pages) has also ceased to be
global, it is located in ipc_namespace and is not inherited from
anywhere.

In such conditions, it cannot be said that these limits limit anything.
The real limiter for them is cgroups.

If we allow rootless containers to change these parameters, then it can
only be reduced.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 ipc/ipc_sysctl.c | 36 ++++++++++++++++++++++++++++++++++--
 1 file changed, 34 insertions(+), 2 deletions(-)

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index ef313ecfb53a..31282e0a630d 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -190,25 +190,57 @@ static int set_is_seen(struct ctl_table_set *set)
 	return &current->nsproxy->ipc_ns->ipc_set == set;
 }
 
+static void ipc_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, ipc_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 int ipc_permissions(struct ctl_table_header *head, struct ctl_table *table)
 {
 	int mode = table->mode;
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
-	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+	struct ipc_namespace *ns =
+		container_of(head->set, struct ipc_namespace, ipc_set);
 
 	if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) ||
 	     (table->data == &ns->ids[IPC_MSG_IDS].next_id) ||
 	     (table->data == &ns->ids[IPC_SHM_IDS].next_id)) &&
 	    checkpoint_restore_ns_capable(ns->user_ns))
 		mode = 0666;
+	else
 #endif
-	return mode;
+	{
+		kuid_t ns_root_uid;
+		kgid_t ns_root_gid;
+
+		ipc_set_ownership(head, table, &ns_root_uid, &ns_root_gid);
+
+		if (uid_eq(current_euid(), ns_root_uid))
+			mode >>= 6;
+
+		else if (in_egroup_p(ns_root_gid))
+			mode >>= 3;
+	}
+
+	mode &= 7;
+
+	return (mode << 6) | (mode << 3) | mode;
 }
 
 static struct ctl_table_root set_root = {
 	.lookup = set_lookup,
 	.permissions = ipc_permissions,
+	.set_ownership = ipc_set_ownership,
 };
 
 bool setup_ipc_sysctls(struct ipc_namespace *ns)
-- 
2.33.4