bpf: Add kconfig knob for disabling unpriv bpf by default

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

Documentation/admin-guide/sysctl/kernel.rst

@@ -1457,11 +1457,22 @@ unprivileged_bpf_disabled
 =========================
 
 Writing 1 to this entry will disable unprivileged calls to ``bpf()``;
-once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return
-``-EPERM``.
+once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF``
+will return ``-EPERM``. Once set to 1, this can't be cleared from the
+running kernel anymore.
 
-Once set, this can't be cleared.
+Writing 2 to this entry will also disable unprivileged calls to ``bpf()``,
+however, an admin can still change this setting later on, if needed, by
+writing 0 or 1 to this entry.
 
+If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this
+entry will default to 2 instead of 0.
+
+= =============================================================
+0 Unprivileged calls to ``bpf()`` are enabled
+1 Unprivileged calls to ``bpf()`` are disabled without recovery
+2 Unprivileged calls to ``bpf()`` are disabled
+= =============================================================
 
 watchdog
 ========

kernel/bpf/Kconfig

@@ -61,6 +61,16 @@ config BPF_JIT_DEFAULT_ON
 	def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON
 	depends on HAVE_EBPF_JIT && BPF_JIT
 
+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).
+
 source "kernel/bpf/preload/Kconfig"
 
 config BPF_LSM

kernel/bpf/syscall.c

@@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock);
 static DEFINE_IDR(link_idr);
 static DEFINE_SPINLOCK(link_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, _name, prog_ctx_type, kern_ctx_type)

kernel/sysctl.c

@@ -225,7 +225,27 @@ static int bpf_stats_handler(struct ctl_table *table, int write,
 	mutex_unlock(&bpf_stats_enabled_mutex);
 	return ret;
 }
-#endif
+
+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 */
 
 /*
  * /proc/sys support
@@ -2600,10 +2620,9 @@ 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		= SYSCTL_ONE,
-		.extra2		= SYSCTL_ONE,
+		.proc_handler	= bpf_unpriv_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "bpf_stats_enabled",