[PATCH bpf 1/2] bpf, kconfig: Add consolidated menu entry for bpf with core options

[PATCH bpf 1/2] bpf, kconfig: Add consolidated menu entry for bpf with core options

[Daniel Borkmann]

Right now, all core BPF related options are scattered in different Kconfig
locations mainly due to historic reasons. Moving forward, lets add a proper
subsystem entry under ...

  General setup  --->
    BPF subsystem  --->

... in order to have all knobs in a single location and thus ease BPF related
configuration. Networking related bits such as sockmap are out of scope for
the general setup and therefore better suited to remain in net/Kconfig.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 init/Kconfig       | 41 +-----------------------
 kernel/bpf/Kconfig | 78 ++++++++++++++++++++++++++++++++++++++++++++++
 net/Kconfig        | 27 ----------------
 3 files changed, 79 insertions(+), 67 deletions(-)
 create mode 100644 kernel/bpf/Kconfig

diff --git a/init/Kconfig b/init/Kconfig
index ca559ccdaa32..2282a6842dc6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -439,6 +439,7 @@ config AUDITSYSCALL
 
 source "kernel/irq/Kconfig"
 source "kernel/time/Kconfig"
+source "kernel/bpf/Kconfig"
 source "kernel/Kconfig.preempt"
 
 menu "CPU/Task time and stats accounting"
@@ -1705,46 +1706,6 @@ config KALLSYMS_BASE_RELATIVE
 
 # syscall, maps, verifier
 
-config BPF_LSM
-	bool "LSM Instrumentation with BPF"
-	depends on BPF_EVENTS
-	depends on BPF_SYSCALL
-	depends on SECURITY
-	depends on BPF_JIT
-	help
-	  Enables instrumentation of the security hooks with eBPF programs for
-	  implementing dynamic MAC and Audit Policies.
-
-	  If you are unsure how to answer this question, answer N.
-
-config BPF_SYSCALL
-	bool "Enable bpf() system call"
-	select BPF
-	select IRQ_WORK
-	select TASKS_TRACE_RCU
-	select BINARY_PRINTF
-	select NET_SOCK_MSG if INET
-	default n
-	help
-	  Enable the bpf() system call that allows to manipulate eBPF
-	  programs and maps via file descriptors.
-
-config ARCH_WANT_DEFAULT_BPF_JIT
-	bool
-
-config BPF_JIT_ALWAYS_ON
-	bool "Permanently enable BPF JIT and remove BPF interpreter"
-	depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT
-	help
-	  Enables BPF JIT and removes BPF interpreter to avoid
-	  speculative execution of BPF instructions by the interpreter
-
-config BPF_JIT_DEFAULT_ON
-	def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON
-	depends on HAVE_EBPF_JIT && BPF_JIT
-
-source "kernel/bpf/preload/Kconfig"
-
 config USERFAULTFD
 	bool "Enable userfaultfd() system call"
 	depends on MMU
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
new file mode 100644
index 000000000000..b4edaefc6255
--- /dev/null
+++ b/kernel/bpf/Kconfig
@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# BPF interpreter that, for example, classic socket filters depend on.
+config BPF
+	bool
+
+# Used by archs to tell that they support BPF JIT compiler plus which
+# flavour. Only one of the two can be selected for a specific arch since
+# eBPF JIT supersedes the cBPF JIT.
+
+# Classic BPF JIT (cBPF)
+config HAVE_CBPF_JIT
+	bool
+
+# Extended BPF JIT (eBPF)
+config HAVE_EBPF_JIT
+	bool
+
+# Used by archs to tell that they want the BPF JIT compiler enabled by
+# default for kernels that were compiled with BPF JIT support.
+config ARCH_WANT_DEFAULT_BPF_JIT
+	bool
+
+menu "BPF subsystem"
+
+config BPF_SYSCALL
+	bool "Enable bpf() system call"
+	select BPF
+	select IRQ_WORK
+	select TASKS_TRACE_RCU
+	select BINARY_PRINTF
+	select NET_SOCK_MSG if INET
+	default n
+	help
+	  Enable the bpf() system call that allows to manipulate BPF programs
+	  and maps via file descriptors.
+
+config BPF_JIT
+	bool "Enable BPF Just In Time compiler"
+	depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
+	depends on MODULES
+	help
+	  BPF programs are normally handled by a BPF interpreter. This option
+	  allows the kernel to generate native code when a program is loaded
+	  into the kernel. This will significantly speed-up processing of BPF
+	  programs.
+
+	  Note, an admin should enable this feature changing:
+	  /proc/sys/net/core/bpf_jit_enable
+	  /proc/sys/net/core/bpf_jit_harden   (optional)
+	  /proc/sys/net/core/bpf_jit_kallsyms (optional)
+
+config BPF_JIT_ALWAYS_ON
+	bool "Permanently enable BPF JIT and remove BPF interpreter"
+	depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT
+	help
+	  Enables BPF JIT and removes BPF interpreter to avoid speculative
+	  execution of BPF instructions by the interpreter.
+
+config BPF_JIT_DEFAULT_ON
+	def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON
+	depends on HAVE_EBPF_JIT && BPF_JIT
+
+source "kernel/bpf/preload/Kconfig"
+
+config BPF_LSM
+	bool "Enable BPF LSM Instrumentation"
+	depends on BPF_EVENTS
+	depends on BPF_SYSCALL
+	depends on SECURITY
+	depends on BPF_JIT
+	help
+	  Enables instrumentation of the security hooks with BPF programs for
+	  implementing dynamic MAC and Audit Policies.
+
+	  If you are unsure how to answer this question, answer N.
+
+endmenu # "BPF subsystem"
diff --git a/net/Kconfig b/net/Kconfig
index f5ee7c65e6b4..c7392c449b25 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -302,21 +302,6 @@ config BQL
 	select DQL
 	default y
 
-config BPF_JIT
-	bool "enable BPF Just In Time compiler"
-	depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
-	depends on MODULES
-	help
-	  Berkeley Packet Filter filtering capabilities are normally handled
-	  by an interpreter. This option allows kernel to generate a native
-	  code when filter is loaded in memory. This should speedup
-	  packet sniffing (libpcap/tcpdump).
-
-	  Note, admin should enable this feature changing:
-	  /proc/sys/net/core/bpf_jit_enable
-	  /proc/sys/net/core/bpf_jit_harden   (optional)
-	  /proc/sys/net/core/bpf_jit_kallsyms (optional)
-
 config BPF_STREAM_PARSER
 	bool "enable BPF STREAM_PARSER"
 	depends on INET
@@ -470,15 +455,3 @@ config ETHTOOL_NETLINK
 	  e.g. notification messages.
 
 endif   # if NET
-
-# Used by archs to tell that they support BPF JIT compiler plus which flavour.
-# Only one of the two can be selected for a specific arch since eBPF JIT supersedes
-# the cBPF JIT.
-
-# Classic BPF JIT (cBPF)
-config HAVE_CBPF_JIT
-	bool
-
-# Extended BPF JIT (eBPF)
-config HAVE_EBPF_JIT
-	bool
-- 
2.21.0

[PATCH bpf 2/2] bpf: Add kconfig knob for disabling unpriv bpf by default

[Daniel Borkmann]

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>
---
 Documentation/admin-guide/sysctl/kernel.rst | 17 +++++++++---
 kernel/bpf/Kconfig                          | 10 +++++++
 kernel/bpf/syscall.c                        |  3 ++-
 kernel/sysctl.c                             | 29 +++++++++++++++++----
 4 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 1d56a6b73a4e..24ab20d7a50a 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/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
 ========
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index b4edaefc6255..26b591e23f16 100644
--- a/kernel/bpf/Kconfig
+++ b/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
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 941ca06d9dfa..ea04b0deb5ce 100644
--- a/kernel/bpf/syscall.c
+++ b/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)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f91d327273c1..6df7c81f7cdd 100644
--- a/kernel/sysctl.c
+++ b/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",
-- 
2.21.0