bpf: restrict access to core bpf sysctls

Given BPF reaches far beyond just networking these days, it was
never intended to allow setting and in some cases reading those
knobs out of a user namespace root running without CAP_SYS_ADMIN,
thus tighten such access.

Also the bpf_jit_enable = 2 debugging mode should only be allowed
if kptr_restrict is not set since it otherwise can leak addresses
to the kernel log. Dump a note to the kernel log that this is for
debugging JITs only when enabled.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 6d39b4c..f2d0462 100644 (file)
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -251,6 +251,46 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
        return proc_dostring(&fake_table, write, buffer, lenp, ppos);
 }
 
+#ifdef CONFIG_BPF_JIT
+static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
+                                          void __user *buffer, size_t *lenp,
+                                          loff_t *ppos)
+{
+       int ret, jit_enable = *(int *)table->data;
+       struct ctl_table tmp = *table;
+
+       if (write && !capable(CAP_SYS_ADMIN))
+               return -EPERM;
+
+       tmp.data = &jit_enable;
+       ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+       if (write && !ret) {
+               if (jit_enable < 2 ||
+                   (jit_enable == 2 && bpf_dump_raw_ok())) {
+                       *(int *)table->data = jit_enable;
+                       if (jit_enable == 2)
+                               pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
+               } else {
+                       ret = -EPERM;
+               }
+       }
+       return ret;
+}
+
+# ifdef CONFIG_HAVE_EBPF_JIT
+static int
+proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+                                   void __user *buffer, size_t *lenp,
+                                   loff_t *ppos)
+{
+       if (!capable(CAP_SYS_ADMIN))
+               return -EPERM;
+
+       return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+# endif
+#endif
+
 static struct ctl_table net_core_table[] = {
 #ifdef CONFIG_NET
        {
@@ -326,7 +366,7 @@ static struct ctl_table net_core_table[] = {
                .data           = &bpf_jit_enable,
                .maxlen         = sizeof(int),
                .mode           = 0644,
-               .proc_handler   = proc_dointvec_minmax,
+               .proc_handler   = proc_dointvec_minmax_bpf_enable,
 # ifdef CONFIG_BPF_JIT_ALWAYS_ON
                .extra1         = &one,
                .extra2         = &one,
@@ -341,7 +381,7 @@ static struct ctl_table net_core_table[] = {
                .data           = &bpf_jit_harden,
                .maxlen         = sizeof(int),
                .mode           = 0600,
-               .proc_handler   = proc_dointvec_minmax,
+               .proc_handler   = proc_dointvec_minmax_bpf_restricted,
                .extra1         = &zero,
                .extra2         = &two,
        },
@@ -350,7 +390,7 @@ static struct ctl_table net_core_table[] = {
                .data           = &bpf_jit_kallsyms,
                .maxlen         = sizeof(int),
                .mode           = 0600,
-               .proc_handler   = proc_dointvec_minmax,
+               .proc_handler   = proc_dointvec_minmax_bpf_restricted,
                .extra1         = &zero,
                .extra2         = &one,
        },