From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 11 May 2021 22:35:17 +0200
Subject: bpf: Add kconfig knob for disabling unpriv bpf by default
Patch-mainline: v5.13-rc4
Git-commit: 08389d888287c3823f80b0216766b71e17f0aba5
References: jsc#SLE-22573
Add a kconfig knob which allows for unprivileged bpf to be disabled by default.
If set, the knob sets /proc/sys/kernel/unprivileged_bpf_disabled to value of 2.
This still allows a transition of 2 -> {0,1} through an admin. Similarly,
this also still keeps 1 -> {1} behavior intact, so that once set to permanently
disabled, it cannot be undone aside from a reboot.
We've also added extra2 with max of 2 for the procfs handler, so that an admin
still has a chance to toggle between 0 <-> 2.
Either way, as an additional alternative, applications can make use of CAP_BPF
that we added a while ago.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/74ec548079189e4e4dffaeb42b8987bb3c852eee.1620765074.git.daniel@iogearbox.net
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
---
syu: Drop documentation and patches init/Kconfig instead of kernel/bpf/Kconfig
since b24abcff918a ("bpf, kconfig: Add consolidated menu entry for bpf with
core options") is not backported.
---
init/Kconfig | 10 ++++++++++
kernel/bpf/syscall.c | 3 ++-
kernel/sysctl.c | 29 +++++++++++++++++++++++++----
3 files changed, 37 insertions(+), 5 deletions(-)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1708,6 +1708,16 @@ config BPF_JIT_ALWAYS_ON
Enables BPF JIT and removes BPF interpreter to avoid
speculative execution of BPF instructions by the interpreter
+config BPF_UNPRIV_DEFAULT_OFF
+ bool "Disable unprivileged BPF by default"
+ depends on BPF_SYSCALL
+ help
+ Disables unprivileged BPF by default by setting the corresponding
+ /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can
+ still reenable it by setting it to 0 later on, or permanently
+ disable it by setting it to 1 (from which no other transition to
+ 0 is possible anymore).
+
config USERFAULTFD
bool "Enable userfaultfd() system call"
select ANON_INODES
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -37,7 +37,8 @@ static DEFINE_SPINLOCK(prog_idr_lock);
static DEFINE_IDR(map_idr);
static DEFINE_SPINLOCK(map_idr_lock);
-int sysctl_unprivileged_bpf_disabled __read_mostly;
+int sysctl_unprivileged_bpf_disabled __read_mostly =
+ IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0;
static const struct bpf_map_ops * const bpf_map_types[] = {
#define BPF_PROG_TYPE(_id, _ops)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -306,6 +306,28 @@ static int min_extfrag_threshold;
static int max_extfrag_threshold = 1000;
#endif
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
+static int bpf_unpriv_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret, unpriv_enable = *(int *)table->data;
+ bool locked_state = unpriv_enable == 1;
+ struct ctl_table tmp = *table;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ tmp.data = &unpriv_enable;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret) {
+ if (locked_state && unpriv_enable != 1)
+ return -EPERM;
+ *(int *)table->data = unpriv_enable;
+ }
+ return ret;
+}
+#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */
+
static struct ctl_table kern_table[] = {
{
.procname = "sched_child_runs_first",
@@ -1212,10 +1234,9 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_unprivileged_bpf_disabled,
.maxlen = sizeof(sysctl_unprivileged_bpf_disabled),
.mode = 0644,
- /* only handle a transition from default "0" to "1" */
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- .extra2 = &one,
+ .proc_handler = bpf_unpriv_handler,
+ .extra1 = &zero,
+ .extra2 = &two,
},
#endif
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)