io_uring: add a sysctl to disable io_uring system-wide
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.
BUG=b/293017665
TEST=presubmit
RELEASE_NOTE=None
cos-patch: bug
Signed-off-by: Matteo Rizzo <matteorizzo@google.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Reviewed-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/r/20230630151003.3622786-2-matteorizzo@google.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Change-Id: I0536bc6e6443ddacadf463fcb78e708a34d88fe5
Reviewed-on: https://cos-review.googlesource.com/c/third_party/kernel/+/55596
Tested-by: Cusky Presubmit Bot <presubmit@cos-infra-prod.iam.gserviceaccount.com>
Reviewed-by: Arnav Kansal <rnv@google.com>
Main-Branch-Verified: Cusky Presubmit Bot <presubmit@cos-infra-prod.iam.gserviceaccount.com>
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 48b91c4..2b1fdf4 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -442,6 +442,25 @@
``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 cbfc9bb..25cab91 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1115,6 +1115,21 @@
static struct kmem_cache *req_cachep;
static const struct file_operations io_uring_fops;
+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)
{
@@ -10663,9 +10678,19 @@
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);
}
@@ -11295,6 +11320,11 @@
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT);
+
+#ifdef CONFIG_SYSCTL
+ register_sysctl_init("kernel", kernel_io_uring_disabled_table);
+#endif
+
return 0;
};
__initcall(io_uring_init);