Commit b617cfc8 authored by Thomas Gleixner's avatar Thomas Gleixner
Browse files

prctl: Add speculation control prctls 



Add two new prctls to control aspects of speculation related vulnerabilites
and their mitigations to provide finer grained control over performance
impacting mitigations.

PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
which is selected with arg2 of prctl(2). The return value uses bit 0-2 with
the following meaning:

Bit  Define           Description
0    PR_SPEC_PRCTL    Mitigation can be controlled per task by
                      PR_SET_SPECULATION_CTRL
1    PR_SPEC_ENABLE   The speculation feature is enabled, mitigation is
                      disabled
2    PR_SPEC_DISABLE  The speculation feature is disabled, mitigation is
                      enabled

If all bits are 0 the CPU is not affected by the speculation misfeature.

If PR_SPEC_PRCTL is set, then the per task control of the mitigation is
available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
misfeature will fail.

PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
is selected by arg2 of prctl(2) per task. arg3 is used to hand in the
control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.

The common return values are:

EINVAL  prctl is not implemented by the architecture or the unused prctl()
        arguments are not 0
ENODEV  arg2 is selecting a not supported speculation misfeature

PR_SET_SPECULATION_CTRL has these additional return values:

ERANGE  arg3 is incorrect, i.e. it's not either PR_SPEC_ENABLE or PR_SPEC_DISABLE
ENXIO   prctl control of the selected speculation misfeature is disabled

The first supported controlable speculation misfeature is
PR_SPEC_STORE_BYPASS. Add the define so this can be shared between
architectures.

Based on an initial patch from Tim Chen and mostly rewritten.

Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Reviewed-by: default avatarIngo Molnar <mingo@kernel.org>
Reviewed-by: default avatarKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
parent 28a27752

Documentation/userspace-api/index.rst

+1 −0
Original line number Diff line number Diff line
@@ -19,6 +19,7 @@ place where this information is gathered. 
   no_new_privs

   seccomp_filter

   unshare

   spec_ctrl



.. only::  subproject and html

Documentation/userspace-api/spec_ctrl.rst

0 → 100644
+86 −0
Original line number Diff line number Diff line 
===================

Speculation Control

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



Quite some CPUs have speculation related misfeatures which are in fact

vulnerabilites causing data leaks in various forms even accross privilege

domains.



The kernel provides mitigation for such vulnerabilities in various

forms. Some of these mitigations are compile time configurable and some on

the kernel command line.



There is also a class of mitigations which are very expensive, but they can

be restricted to a certain set of processes or tasks in controlled

environments. The mechanism to control these mitigations is via

:manpage:`prctl(2)`.



There are two prctl options which are related to this:



 * PR_GET_SPECULATION_CTRL



 * PR_SET_SPECULATION_CTRL



PR_GET_SPECULATION_CTRL

-----------------------



PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature

which is selected with arg2 of prctl(2). The return value uses bits 0-2 with

the following meaning:



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

Bit  Define           Description

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

0    PR_SPEC_PRCTL    Mitigation can be controlled per task by

                      PR_SET_SPECULATION_CTRL

1    PR_SPEC_ENABLE   The speculation feature is enabled, mitigation is

                      disabled

2    PR_SPEC_DISABLE  The speculation feature is disabled, mitigation is

                      enabled

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



If all bits are 0 the CPU is not affected by the speculation misfeature.



If PR_SPEC_PRCTL is set, then the per task control of the mitigation is

available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation

misfeature will fail.



PR_SET_SPECULATION_CTRL

-----------------------

PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which

is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand

in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.



Common error codes

------------------

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

Value   Meaning

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

EINVAL  The prctl is not implemented by the architecture or unused

        prctl(2) arguments are not 0



ENODEV  arg2 is selecting a not supported speculation misfeature

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



PR_SET_SPECULATION_CTRL error codes

-----------------------------------

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

Value   Meaning

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

0       Success



ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor

        PR_SPEC_DISABLE



ENXIO   Control of the selected speculation misfeature is not possible.

        See PR_GET_SPECULATION_CTRL.

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



Speculation misfeature controls

-------------------------------

- PR_SPEC_STORE_BYPASS: Speculative Store Bypass



  Invocations:

   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);

   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);

   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);

include/linux/nospec.h

+5 −0
Original line number Diff line number Diff line
@@ -55,4 +55,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, 
									\

	(typeof(_i)) (_i & _mask);					\

})



/* Speculation control prctl */

int arch_prctl_spec_ctrl_get(unsigned long which);

int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl);



#endif /* _LINUX_NOSPEC_H */

include/uapi/linux/prctl.h

+11 −0
Original line number Diff line number Diff line
@@ -207,4 +207,15 @@ struct prctl_mm_map { 
# define PR_SVE_VL_LEN_MASK		0xffff

# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */



/* Per task speculation control */

#define PR_GET_SPECULATION_CTRL		52

#define PR_SET_SPECULATION_CTRL		53

/* Speculation control variants */

# define PR_SPEC_STORE_BYPASS		0

/* Return and control values for PR_SET/GET_SPECULATION_CTRL */

# define PR_SPEC_NOT_AFFECTED		0

# define PR_SPEC_PRCTL			(1UL << 0)

# define PR_SPEC_ENABLE			(1UL << 1)

# define PR_SPEC_DISABLE		(1UL << 2)



#endif /* _LINUX_PRCTL_H */

kernel/sys.c

+22 −0
Original line number Diff line number Diff line
@@ -61,6 +61,8 @@ 
#include <linux/uidgid.h>

#include <linux/cred.h>



#include <linux/nospec.h>



#include <linux/kmsg_dump.h>

/* Move somewhere else to avoid recompiling? */

#include <generated/utsrelease.h>
@@ -2242,6 +2244,16 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data) 
	return 1;

}



int __weak arch_prctl_spec_ctrl_get(unsigned long which)

{

	return -EINVAL;

}



int __weak arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl)

{

	return -EINVAL;

}



SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,

		unsigned long, arg4, unsigned long, arg5)

{
@@ -2450,6 +2462,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, 
	case PR_SVE_GET_VL:

		error = SVE_GET_VL();

		break;

	case PR_GET_SPECULATION_CTRL:

		if (arg3 || arg4 || arg5)

			return -EINVAL;

		error = arch_prctl_spec_ctrl_get(arg2);

		break;

	case PR_SET_SPECULATION_CTRL:

		if (arg4 || arg5)

			return -EINVAL;

		error = arch_prctl_spec_ctrl_set(arg2, arg3);

		break;

	default:

		error = -EINVAL;

		break;

CRA Git | Maintained and supported by SUSTech CRA and CCSE