prctl: Add speculation control prctls

commit b617cfc858161140d69cc0b5cc211996b557a1c7 upstream

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: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa@csail.mit.edu>
Reviewed-by: Matt Helsley (VMware) <matt.helsley@gmail.com>
Reviewed-by: Alexey Makhalov <amakhalov@vmware.com>
Reviewed-by: Bo Gan <ganb@vmware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 122 insertions, 0 deletions

diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt
new file mode 100644
index 000000000000..ddbebcd01208
--- /dev/null
+++ b/Documentation/spec_ctrl.txt
@@ -0,0 +1,86 @@
+===================
+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);
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index e791ebc65c9c..700bb8a4e4ea 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -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 */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index a8d0759a9e40..3b316be71c56 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -197,4 +197,15 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* 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 */
diff --git a/kernel/sys.c b/kernel/sys.c
index 6624919ef0e7..d80c33f9aff7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2075,6 +2075,16 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
 }
 #endif
 
+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)
 {
@@ -2269,6 +2279,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_FP_MODE:
 		error = GET_FP_MODE(me);
 		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;