From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 20 Jan 2018 01:24:34 +0100
Subject: bpf: restrict access to core bpf sysctls
Patch-mainline: v4.16-rc1
Git-commit: 2e4a30983b0f9b19b59e38bbf7427d7fdd480d98
References: bsc#1109837

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>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 net/core/sysctl_net_core.c |   46 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 3 deletions(-)

--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -250,6 +250,46 @@ static int proc_do_rss_key(struct ctl_ta
 	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
 	{
@@ -325,7 +365,7 @@ 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,
@@ -340,7 +380,7 @@ 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,
 	},
@@ -349,7 +389,7 @@ 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,
 	},