[PATCH v3 1/1] io_uring: add a sysctl to disable io_uring system-wide

[Matteo Rizzo]

Introduce a new sysctl (io_uring_disabled) which can be either 0, 1,
or 2. 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 unless the calling process has
CAP_SYS_ADMIN. When 2, calls to io_uring_setup fail with -EPERM
regardless of privilege.

Signed-off-by: Matteo Rizzo <matteorizzo@xxxxxxxxxx>
Reviewed-by: Jeff Moyer <jmoyer@xxxxxxxxxx>
Reviewed-by: Gabriel Krisman Bertazi <krisman@xxxxxxx>
---
 Documentation/admin-guide/sysctl/kernel.rst | 19 +++++++++++++
 io_uring/io_uring.c                         | 31 +++++++++++++++++++++
 2 files changed, 50 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 3800fab1619b..ee65f7aeb0cf 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -450,6 +450,25 @@ 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 creation is disabled for unprivileged processes.
+  io_uring_setup fails with -EPERM unless the calling process is
+  privileged (CAP_SYS_ADMIN). Existing io_uring instances can
+  still be used.
+2 io_uring creation is disabled for all processes. 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 e8096d502a7c..5410f5576980 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -152,6 +152,22 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
 
 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_TWO,
+	},
+	{},
+};
+#endif
+
 struct sock *io_uring_get_socket(struct file *file)
 {
 #if defined(CONFIG_UNIX)
@@ -4015,9 +4031,19 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	return io_uring_create(entries, &p, params);
 }
 
+static inline bool io_uring_allowed(void)
+{
+	int disabled = READ_ONCE(sysctl_io_uring_disabled);
+
+	return disabled == 0 || (disabled == 1 && capable(CAP_SYS_ADMIN));
+}
+
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 		struct io_uring_params __user *, params)
 {
+	if (!io_uring_allowed())
+		return -EPERM;
+
 	return io_uring_setup(entries, params);
 }
 
@@ -4592,6 +4618,11 @@ 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);
-- 
2.41.0.255.g8b1d071c50-goog