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;
Date:   Tue, 27 Jun 2023 12:00:58 +0000
In-Reply-To: <20230627120058.2214509-1-matteorizzo@google.com>
Mime-Version: 1.0
References: <20230627120058.2214509-1-matteorizzo@google.com>
Message-ID: <20230627120058.2214509-2-matteorizzo@google.com>
Subject: [PATCH 1/1] Add a new sysctl to disable io_uring system-wide
From:   Matteo Rizzo <matteorizzo@google.com>
To:     linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
        io-uring@vger.kernel.org
Cc:     matteorizzo@google.com, jordyzomer@google.com, evn@google.com,
        poprdi@google.com, corbet@lwn.net, axboe@kernel.dk,
        asml.silence@gmail.com, akpm@linux-foundation.org,
        keescook@chromium.org, rostedt@goodmis.org,
        dave.hansen@linux.intel.com, ribalda@chromium.org,
        chenhuacai@kernel.org, steve@sk2.org, gpiccoli@igalia.com,
        ldufour@linux.ibm.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Introduce a new sysctl (io_uring_disabled) which can be either 0 or 1.
When 0 (the default), all processes are allowed to create io_uring
instances, which is the current behavior. When 1, all calls to
io_uring_setup fail with -EPERM.

Signed-off-by: Matteo Rizzo <matteorizzo@google.com>
---
 Documentation/admin-guide/sysctl/kernel.rst | 14 ++++++++++++
 io_uring/io_uring.c                         | 24 +++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index d85d90f5d000..3c53a238332a 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -450,6 +450,20 @@ this allows system administrators to override the
 ``IA64_THREAD_UAC_NOPRINT`` ``prctl`` and avoid logs being flooded.
 
 
+io_uring_disabled
+=========================
+
+Prevents all processes from creating new io_uring instances. Enabling this
+shrinks the kernel's attack surface.
+
+= =============================================================
+0 All processes can create io_uring instances as normal. This is the default
+  setting.
+1 io_uring is disabled. io_uring_setup always fails with -EPERM. Existing
+  io_uring instances can still be used.
+= =============================================================
+
+
 kexec_load_disabled
 ===================
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 1b53a2ab0a27..0496ae7017f7 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -153,6 +153,22 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx);
 
 struct kmem_cache *req_cachep;
 
+static int __read_mostly sysctl_io_uring_disabled;
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kernel_io_uring_disabled_table[] = {
+	{
+		.procname	= "io_uring_disabled",
+		.data		= &sysctl_io_uring_disabled,
+		.maxlen		= sizeof(sysctl_io_uring_disabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{},
+};
+#endif
+
 struct sock *io_uring_get_socket(struct file *file)
 {
 #if defined(CONFIG_UNIX)
@@ -4003,6 +4019,9 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 		struct io_uring_params __user *, params)
 {
+	if (sysctl_io_uring_disabled)
+		return -EPERM;
+
 	return io_uring_setup(entries, params);
 }
 
@@ -4577,6 +4596,11 @@ static int __init io_uring_init(void)
 
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
 				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
+
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("kernel", kernel_io_uring_disabled_table);
+#endif
+
 	return 0;
 };
 __initcall(io_uring_init);
-- 
2.41.0.162.gfafddb0af9-goog