Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 07e7f7cc authored by Daniel Borkmann's avatar Daniel Borkmann Committed by Greg Kroah-Hartman
Browse files

bpf: Add kconfig knob for disabling unpriv bpf by default 



commit 08389d888287c3823f80b0216766b71e17f0aba5 upstream.

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: default avatarDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/74ec548079189e4e4dffaeb42b8987bb3c852eee.1620765074.git.daniel@iogearbox.net


[fllinden@amazon.com: backported to 4.19]
Signed-off-by: default avatarFrank van der Linden <fllinden@amazon.com>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent cf9de6a3

Documentation/sysctl/kernel.txt

+21 −0
Original line number Diff line number Diff line
@@ -94,6 +94,7 @@ show up in /proc/sys/kernel: 
- sysctl_writes_strict

- tainted

- threads-max

- unprivileged_bpf_disabled

- unknown_nmi_panic

- watchdog

- watchdog_thresh
@@ -1041,6 +1042,26 @@ available RAM pages threads-max is reduced accordingly. 


==============================================================



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 set to 1, this can't be cleared from the running kernel

anymore.



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



==============================================================



unknown_nmi_panic:



The value in this file affects behavior of handling NMI. When the

init/Kconfig

+10 −0
Original line number Diff line number Diff line
@@ -1474,6 +1474,16 @@ 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

kernel/bpf/syscall.c

+2 −1
Original line number Diff line number Diff line
@@ -48,7 +48,8 @@ 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)

kernel/sysctl.c

+25 −4
Original line number Diff line number Diff line
@@ -250,6 +250,28 @@ static int sysrq_sysctl_handler(struct ctl_table *table, int write, 


#endif



#ifdef CONFIG_BPF_SYSCALL

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



static struct ctl_table kern_table[];

static struct ctl_table vm_table[];

static struct ctl_table fs_table[];
@@ -1220,10 +1242,9 @@ 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)