Blob Blame Raw
From 73958cc1f78cfc69f3b1ec26a3406b3c45f6d202 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 9 Apr 2018 09:52:45 +0100
Subject: [PATCH 01/24] Add the ability to lock down access to the running
 kernel image

Provide a single call to allow kernel code to determine whether the system
should be locked down, thereby disallowing various accesses that might
allow the running kernel image to be changed, including:

 - /dev/mem and similar
 - Loading of unauthorised modules
 - Fiddling with MSR registers
 - Suspend to disk managed by the kernel
 - Use of device DMA

Two kernel configuration options are provided:

 (*) CONFIG_LOCK_DOWN_KERNEL

     This makes lockdown available and applies it to all the points that
     need to be locked down if the mode is set.  Lockdown mode can be
     enabled by providing:

	lockdown=1

     on the command line.

 (*) CONFIG_LOCK_DOWN_MANDATORY

     This forces lockdown on at compile time, overriding the command line
     option.

init_lockdown() is used as a hook from which lockdown can be managed in
future.  It has to be called from arch setup code before things like ACPI
are enabled.

Note that, with the other changes in this series, if lockdown mode is
enabled, the kernel will not be able to use certain drivers as the ability
to manually configure hardware parameters would then be prohibited.  This
primarily applies to ISA hardware devices.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 arch/x86/kernel/setup.c |  2 ++
 include/linux/kernel.h  | 32 ++++++++++++++++++++++++
 security/Kconfig        | 23 ++++++++++++++++-
 security/Makefile       |  3 +++
 security/lock_down.c    | 65 +++++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 124 insertions(+), 1 deletion(-)
 create mode 100644 security/lock_down.c

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6285697b6e56..566f0f447053 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -996,6 +996,8 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_init();

+	init_lockdown();
+
 	dmi_scan_machine();
 	dmi_memdev_walk();
 	dmi_set_dump_stack_arch_desc();
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4ae1dfd9bf05..7d085cca9cee 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -306,6 +306,38 @@ static inline void refcount_error_report(struct pt_regs *regs, const char *err)
 { }
 #endif

+#ifdef CONFIG_LOCK_DOWN_KERNEL
+extern void __init init_lockdown(void);
+extern bool __kernel_is_locked_down(const char *what, bool first);
+
+#ifndef CONFIG_LOCK_DOWN_MANDATORY
+#define kernel_is_locked_down(what)					\
+	({								\
+		static bool message_given;				\
+		bool locked_down = __kernel_is_locked_down(what, !message_given); \
+		message_given = true;					\
+		locked_down;						\
+	})
+#else
+#define kernel_is_locked_down(what)					\
+	({								\
+		static bool message_given;				\
+		__kernel_is_locked_down(what, !message_given);		\
+		message_given = true;					\
+		true;							\
+	})
+#endif
+#else
+static inline void __init init_lockdown(void)
+{
+}
+static inline bool __kernel_is_locked_down(const char *what, bool first)
+{
+	return false;
+}
+#define kernel_is_locked_down(what) ({ false; })
+#endif
+
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
 int __must_check _kstrtol(const char *s, unsigned int base, long *res);
diff --git a/security/Kconfig b/security/Kconfig
index c4302067a3ad..a68e5bdebad5 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -231,6 +231,28 @@ config STATIC_USERMODEHELPER_PATH
 	  If you wish for all usermode helper programs to be disabled,
 	  specify an empty string here (i.e. "").

+config LOCK_DOWN_KERNEL
+	bool "Allow the kernel to be 'locked down'"
+	help
+	  Allow the kernel to be locked down.  Locking down the kernel turns
+	  off various features that might otherwise allow access to the kernel
+	  image (eg. setting MSR registers).
+
+	  Note, however, that locking down your kernel will prevent some
+	  drivers from functioning because allowing manual configuration of
+	  hardware parameters is forbidden, lest a device be used to access the
+	  kernel by DMA.  This mostly applies to ISA devices.
+
+	  The kernel lockdown can be triggered by adding lockdown=1 to the
+	  kernel command line.
+
+config LOCK_DOWN_MANDATORY
+	bool "Make kernel lockdown mandatory"
+	depends on LOCK_DOWN_KERNEL
+	help
+	  Makes the lockdown non-negotiable.  It is always on and cannot be
+	  disabled.
+
 source "security/selinux/Kconfig"
 source "security/smack/Kconfig"
 source "security/tomoyo/Kconfig"
@@ -278,4 +300,3 @@ config DEFAULT_SECURITY
 	default "" if DEFAULT_SECURITY_DAC

 endmenu
-
diff --git a/security/Makefile b/security/Makefile
index 4d2d3782ddef..507ac8c520ce 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -30,3 +30,6 @@ obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
 # Object integrity file lists
 subdir-$(CONFIG_INTEGRITY)		+= integrity
 obj-$(CONFIG_INTEGRITY)			+= integrity/
+
+# Allow the kernel to be locked down
+obj-$(CONFIG_LOCK_DOWN_KERNEL)		+= lock_down.o
diff --git a/security/lock_down.c b/security/lock_down.c
new file mode 100644
index 000000000000..f35ffdd096ad
--- /dev/null
+++ b/security/lock_down.c
@@ -0,0 +1,65 @@
+/* Lock down the kernel
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/sched.h>
+
+#ifndef CONFIG_LOCK_DOWN_MANDATORY
+static __ro_after_init bool kernel_locked_down;
+#else
+#define kernel_locked_down true
+#endif
+
+/*
+ * Put the kernel into lock-down mode.
+ */
+static void __init lock_kernel_down(const char *where)
+{
+#ifndef CONFIG_LOCK_DOWN_MANDATORY
+	if (!kernel_locked_down) {
+		kernel_locked_down = true;
+		pr_notice("Kernel is locked down from %s; see man kernel_lockdown.7\n",
+			  where);
+	}
+#endif
+}
+
+static int __init lockdown_param(char *ignored)
+{
+	lock_kernel_down("command line");
+	return 0;
+}
+
+early_param("lockdown", lockdown_param);
+
+/*
+ * Lock the kernel down from very early in the arch setup.  This must happen
+ * prior to things like ACPI being initialised.
+ */
+void __init init_lockdown(void)
+{
+#ifdef CONFIG_LOCK_DOWN_MANDATORY
+	pr_notice("Kernel is locked down from config; see man kernel_lockdown.7\n");
+#endif
+}
+
+/**
+ * kernel_is_locked_down - Find out if the kernel is locked down
+ * @what: Tag to use in notice generated if lockdown is in effect
+ */
+bool __kernel_is_locked_down(const char *what, bool first)
+{
+	if (what && first && kernel_locked_down)
+		pr_notice("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
+			  current->comm, what);
+	return kernel_locked_down;
+}
+EXPORT_SYMBOL(__kernel_is_locked_down);
-- 
2.14.3

From 13dada34d9aa56ac4ee5438c7ebefde2d30d5542 Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@redhat.com>
Date: Mon, 9 Apr 2018 09:52:45 +0100
Subject: [PATCH 02/24] Add a SysRq option to lift kernel lockdown

Make an option to provide a sysrq key that will lift the kernel lockdown,
thereby allowing the running kernel image to be accessed and modified.

On x86 this is triggered with SysRq+x, but this key may not be available on
all arches, so it is set by setting LOCKDOWN_LIFT_KEY in asm/setup.h.
Since this macro must be defined in an arch to be able to use this facility
for that arch, the Kconfig option is restricted to arches that support it.

Signed-off-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: x86@kernel.org
---
 arch/x86/include/asm/setup.h |  2 ++
 drivers/input/misc/uinput.c  |  1 +
 drivers/tty/sysrq.c          | 19 ++++++++++++------
 include/linux/input.h        |  5 +++++
 include/linux/sysrq.h        |  8 +++++++-
 kernel/debug/kdb/kdb_main.c  |  2 +-
 security/Kconfig             | 11 +++++++++++
 security/lock_down.c         | 47 ++++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 87 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ae13bc974416..3108e297d87d 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -9,6 +9,8 @@
 #include <linux/linkage.h>
 #include <asm/page_types.h>

+#define LOCKDOWN_LIFT_KEY 'x'
+
 #ifdef __i386__

 #include <linux/pfn.h>
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 96a887f33698..027c730631cc 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -365,6 +365,7 @@ static int uinput_create_device(struct uinput_device *udev)
 		dev->flush = uinput_dev_flush;
 	}

+	dev->flags |= INPUTDEV_FLAGS_SYNTHETIC;
 	dev->event = uinput_dev_event;

 	input_set_drvdata(udev->dev, udev);
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 6364890575ec..ffeb3aa86cd1 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -487,6 +487,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	/* x: May be registered on mips for TLB dump */
 	/* x: May be registered on ppc/powerpc for xmon */
 	/* x: May be registered on sparc64 for global PMU dump */
+	/* x: May be registered on x86_64 for disabling secure boot */
 	NULL,				/* x */
 	/* y: May be registered on sparc64 for global register dump */
 	NULL,				/* y */
@@ -530,7 +531,7 @@ static void __sysrq_put_key_op(int key, struct sysrq_key_op *op_p)
                 sysrq_key_table[i] = op_p;
 }

-void __handle_sysrq(int key, bool check_mask)
+void __handle_sysrq(int key, unsigned int from)
 {
 	struct sysrq_key_op *op_p;
 	int orig_log_level;
@@ -550,11 +551,15 @@ void __handle_sysrq(int key, bool check_mask)

         op_p = __sysrq_get_key_op(key);
         if (op_p) {
+		/* Ban synthetic events from some sysrq functionality */
+		if ((from == SYSRQ_FROM_PROC || from == SYSRQ_FROM_SYNTHETIC) &&
+		    op_p->enable_mask & SYSRQ_DISABLE_USERSPACE)
+			printk("This sysrq operation is disabled from userspace.\n");
 		/*
 		 * Should we check for enabled operations (/proc/sysrq-trigger
 		 * should not) and is the invoked operation enabled?
 		 */
-		if (!check_mask || sysrq_on_mask(op_p->enable_mask)) {
+		if (from == SYSRQ_FROM_KERNEL || sysrq_on_mask(op_p->enable_mask)) {
 			pr_cont("%s\n", op_p->action_msg);
 			console_loglevel = orig_log_level;
 			op_p->handler(key);
@@ -586,7 +591,7 @@ void __handle_sysrq(int key, bool check_mask)
 void handle_sysrq(int key)
 {
 	if (sysrq_on())
-		__handle_sysrq(key, true);
+		__handle_sysrq(key, SYSRQ_FROM_KERNEL);
 }
 EXPORT_SYMBOL(handle_sysrq);

@@ -667,7 +672,7 @@ static void sysrq_do_reset(struct timer_list *t)
 static void sysrq_handle_reset_request(struct sysrq_state *state)
 {
 	if (state->reset_requested)
-		__handle_sysrq(sysrq_xlate[KEY_B], false);
+		__handle_sysrq(sysrq_xlate[KEY_B], SYSRQ_FROM_KERNEL);

 	if (sysrq_reset_downtime_ms)
 		mod_timer(&state->keyreset_timer,
@@ -818,8 +823,10 @@ static bool sysrq_handle_keypress(struct sysrq_state *sysrq,

 	default:
 		if (sysrq->active && value && value != 2) {
+			int from = sysrq->handle.dev->flags & INPUTDEV_FLAGS_SYNTHETIC ?
+					SYSRQ_FROM_SYNTHETIC : 0;
 			sysrq->need_reinject = false;
-			__handle_sysrq(sysrq_xlate[code], true);
+			__handle_sysrq(sysrq_xlate[code], from);
 		}
 		break;
 	}
@@ -1102,7 +1109,7 @@ static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,

 		if (get_user(c, buf))
 			return -EFAULT;
-		__handle_sysrq(c, false);
+		__handle_sysrq(c, SYSRQ_FROM_PROC);
 	}

 	return count;
diff --git a/include/linux/input.h b/include/linux/input.h
index 7c7516eb7d76..38cd0ea72c37 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -42,6 +42,7 @@ struct input_value {
  * @phys: physical path to the device in the system hierarchy
  * @uniq: unique identification code for the device (if device has it)
  * @id: id of the device (struct input_id)
+ * @flags: input device flags (SYNTHETIC, etc.)
  * @propbit: bitmap of device properties and quirks
  * @evbit: bitmap of types of events supported by the device (EV_KEY,
  *	EV_REL, etc.)
@@ -124,6 +125,8 @@ struct input_dev {
 	const char *uniq;
 	struct input_id id;

+	unsigned int flags;
+
 	unsigned long propbit[BITS_TO_LONGS(INPUT_PROP_CNT)];

 	unsigned long evbit[BITS_TO_LONGS(EV_CNT)];
@@ -190,6 +193,8 @@ struct input_dev {
 };
 #define to_input_dev(d) container_of(d, struct input_dev, dev)

+#define	INPUTDEV_FLAGS_SYNTHETIC	0x000000001
+
 /*
  * Verify that we are in sync with input_device_id mod_devicetable.h #defines
  */
diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
index 8c71874e8485..7de1f08b60a9 100644
--- a/include/linux/sysrq.h
+++ b/include/linux/sysrq.h
@@ -29,6 +29,8 @@
 #define SYSRQ_ENABLE_BOOT	0x0080
 #define SYSRQ_ENABLE_RTNICE	0x0100

+#define SYSRQ_DISABLE_USERSPACE	0x00010000
+
 struct sysrq_key_op {
 	void (*handler)(int);
 	char *help_msg;
@@ -43,8 +45,12 @@ struct sysrq_key_op {
  * are available -- else NULL's).
  */

+#define SYSRQ_FROM_KERNEL	0x0001
+#define SYSRQ_FROM_PROC		0x0002
+#define SYSRQ_FROM_SYNTHETIC	0x0004
+
 void handle_sysrq(int key);
-void __handle_sysrq(int key, bool check_mask);
+void __handle_sysrq(int key, unsigned int from);
 int register_sysrq_key(int key, struct sysrq_key_op *op);
 int unregister_sysrq_key(int key, struct sysrq_key_op *op);
 struct sysrq_key_op *__sysrq_get_key_op(int key);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index dbb0781a0533..aae9a0f44058 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1970,7 +1970,7 @@ static int kdb_sr(int argc, const char **argv)
 		return KDB_ARGCOUNT;

 	kdb_trap_printk++;
-	__handle_sysrq(*argv[1], check_mask);
+	__handle_sysrq(*argv[1], check_mask ? SYSRQ_FROM_KERNEL : 0);
 	kdb_trap_printk--;

 	return 0;
diff --git a/security/Kconfig b/security/Kconfig
index a68e5bdebad5..46967ee77dfd 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -253,6 +253,17 @@ config LOCK_DOWN_MANDATORY
 	  Makes the lockdown non-negotiable.  It is always on and cannot be
 	  disabled.

+config ALLOW_LOCKDOWN_LIFT_BY_SYSRQ
+	bool "Allow the kernel lockdown to be lifted by SysRq"
+	depends on LOCK_DOWN_KERNEL
+	depends on !LOCK_DOWN_MANDATORY
+	depends on MAGIC_SYSRQ
+	depends on X86
+	help
+	  Allow the lockdown on a kernel to be lifted, by pressing a SysRq key
+	  combination on a wired keyboard.  On x86, this is SysRq+x.
+
+
 source "security/selinux/Kconfig"
 source "security/smack/Kconfig"
 source "security/tomoyo/Kconfig"
diff --git a/security/lock_down.c b/security/lock_down.c
index f35ffdd096ad..2615669dbf03 100644
--- a/security/lock_down.c
+++ b/security/lock_down.c
@@ -11,9 +11,15 @@

 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sysrq.h>
+#include <asm/setup.h>

 #ifndef CONFIG_LOCK_DOWN_MANDATORY
+#ifdef CONFIG_ALLOW_LOCKDOWN_LIFT_BY_SYSRQ
+static __read_mostly bool kernel_locked_down;
+#else
 static __ro_after_init bool kernel_locked_down;
+#endif
 #else
 #define kernel_locked_down true
 #endif
@@ -63,3 +69,44 @@ bool __kernel_is_locked_down(const char *what, bool first)
 	return kernel_locked_down;
 }
 EXPORT_SYMBOL(__kernel_is_locked_down);
+
+#ifdef CONFIG_ALLOW_LOCKDOWN_LIFT_BY_SYSRQ
+
+/*
+ * Take the kernel out of lockdown mode.
+ */
+static void lift_kernel_lockdown(void)
+{
+	pr_notice("Lifting lockdown\n");
+	kernel_locked_down = false;
+}
+
+/*
+ * Allow lockdown to be lifted by pressing something like SysRq+x (and not by
+ * echoing the appropriate letter into the sysrq-trigger file).
+ */
+static void sysrq_handle_lockdown_lift(int key)
+{
+	if (kernel_locked_down)
+		lift_kernel_lockdown();
+}
+
+static struct sysrq_key_op lockdown_lift_sysrq_op = {
+	.handler	= sysrq_handle_lockdown_lift,
+	.help_msg	= "unSB(x)",
+	.action_msg	= "Disabling Secure Boot restrictions",
+	.enable_mask	= SYSRQ_DISABLE_USERSPACE,
+};
+
+static int __init lockdown_lift_sysrq(void)
+{
+	if (kernel_locked_down) {
+		lockdown_lift_sysrq_op.help_msg[5] = LOCKDOWN_LIFT_KEY;
+		register_sysrq_key(LOCKDOWN_LIFT_KEY, &lockdown_lift_sysrq_op);
+	}
+	return 0;
+}
+
+late_initcall(lockdown_lift_sysrq);
+
+#endif /* CONFIG_ALLOW_LOCKDOWN_LIFT_BY_SYSRQ */
-- 
2.14.3

From 7948946e19294e7560c81b177b2788d21ed79f59 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:46 +0100
Subject: [PATCH 05/24] Restrict /dev/{mem,kmem,port} when the kernel is locked
 down

Allowing users to read and write to core kernel memory makes it possible
for the kernel to be subverted, avoiding module loading restrictions, and
also to steal cryptographic information.

Disallow /dev/mem and /dev/kmem from being opened this when the kernel has
been locked down to prevent this.

Also disallow /dev/port from being opened to prevent raw ioport access and
thus DMA from being used to accomplish the same thing.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
---
 drivers/char/mem.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index ffeb60d3434c..b2fca26e5765 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -784,6 +784,8 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)

 static int open_port(struct inode *inode, struct file *filp)
 {
+	if (kernel_is_locked_down("/dev/mem,kmem,port"))
+		return -EPERM;
 	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
 }

-- 
2.14.3

From a19b6b9637f114388cc7087176860eee962cac79 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:46 +0100
Subject: [PATCH 06/24] kexec_load: Disable at runtime if the kernel is locked
 down

The kexec_load() syscall permits the loading and execution of arbitrary
code in ring 0, which is something that lock-down is meant to prevent. It
makes sense to disable kexec_load() in this situation.

This does not affect kexec_file_load() syscall which can check for a
signature on the image to be booted.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dave Young <dyoung@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
Reviewed-by: James Morris <james.l.morris@oracle.com>
cc: kexec@lists.infradead.org
---
 kernel/kexec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 68559808fdfa..041d505070e1 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -202,6 +202,13 @@ static inline int kexec_load_check(unsigned long nr_segments,
 	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
 		return -EPERM;
 
+	/*
+	 * kexec can be used to circumvent module loading restrictions, so
+	 * prevent loading in that case
+	 */
+	if (kernel_is_locked_down("kexec of unsigned images"))
+		return -EPERM;
+
 	/* Permit LSMs and IMA to fail the kexec */
 	result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
 	if (result < 0)
-- 
2.17.1

From aed8ee965258e3926be6aaeb57aef8a9a03c9989 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@fedoraproject.org>
Date: Mon, 9 Apr 2018 09:52:47 +0100
Subject: [PATCH 07/24] hibernate: Disable when the kernel is locked down

There is currently no way to verify the resume image when returning
from hibernate.  This might compromise the signed modules trust model,
so until we can work with signed hibernate images we disable it when the
kernel is locked down.

Signed-off-by: Josh Boyer <jwboyer@fedoraproject.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: linux-pm@vger.kernel.org
---
 kernel/power/hibernate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 5454cc639a8d..629f158f5a0c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -70,7 +70,7 @@ static const struct platform_hibernation_ops *hibernation_ops;

 bool hibernation_available(void)
 {
-	return (nohibernate == 0);
+	return nohibernate == 0 && !kernel_is_locked_down("Hibernation");
 }

 /**
-- 
2.14.3

From 8732c1663d7c0305ae01ba5a1ee4d2299b7b4612 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:47 +0100
Subject: [PATCH 08/24] uswsusp: Disable when the kernel is locked down

uswsusp allows a user process to dump and then restore kernel state, which
makes it possible to modify the running kernel.  Disable this if the kernel
is locked down.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
Reviewed-by: James Morris <james.l.morris@oracle.com>
cc: linux-pm@vger.kernel.org
---
 kernel/power/user.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/power/user.c b/kernel/power/user.c
index 75c959de4b29..959b336d8eca 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -52,6 +52,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	if (!hibernation_available())
 		return -EPERM;

+	if (kernel_is_locked_down("/dev/snapshot"))
+		return -EPERM;
+
 	lock_system_sleep();

 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
-- 
2.14.3

From 4f5f0aae410d1929872eec346954c85e3a85f4f3 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:48 +0100
Subject: [PATCH 09/24] PCI: Lock down BAR access when the kernel is locked
 down

Any hardware that can potentially generate DMA has to be locked down in
order to avoid it being possible for an attacker to modify kernel code,
allowing them to circumvent disabled module loading or module signing.
Default to paranoid - in future we can potentially relax this for
sufficiently IOMMU-isolated devices.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: linux-pci@vger.kernel.org
---
 drivers/pci/pci-sysfs.c | 9 +++++++++
 drivers/pci/proc.c      | 9 ++++++++-
 drivers/pci/syscall.c   | 3 ++-
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 366d93af051d..1e149ec006a4 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -903,6 +903,9 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj,
 	loff_t init_off = off;
 	u8 *data = (u8 *) buf;

+	if (kernel_is_locked_down("Direct PCI access"))
+		return -EPERM;
+
 	if (off > dev->cfg_size)
 		return 0;
 	if (off + count > dev->cfg_size) {
@@ -1165,6 +1168,9 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	enum pci_mmap_state mmap_type;
 	struct resource *res = &pdev->resource[bar];

+	if (kernel_is_locked_down("Direct PCI access"))
+		return -EPERM;
+
 	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
 		return -EINVAL;

@@ -1240,6 +1246,9 @@ static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
 				     struct bin_attribute *attr, char *buf,
 				     loff_t off, size_t count)
 {
+	if (kernel_is_locked_down("Direct PCI access"))
+		return -EPERM;
+
 	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
 }

diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 1ee8927a0635..469445a9019b 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -117,6 +117,9 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf,
 	int size = dev->cfg_size;
 	int cnt;

+	if (kernel_is_locked_down("Direct PCI access"))
+		return -EPERM;
+
 	if (pos >= size)
 		return 0;
 	if (nbytes >= size)
@@ -196,6 +199,9 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 #endif /* HAVE_PCI_MMAP */
 	int ret = 0;

+	if (kernel_is_locked_down("Direct PCI access"))
+		return -EPERM;
+
 	switch (cmd) {
 	case PCIIOC_CONTROLLER:
 		ret = pci_domain_nr(dev->bus);
@@ -237,7 +243,8 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	struct pci_filp_private *fpriv = file->private_data;
 	int i, ret, write_combine = 0, res_bit = IORESOURCE_MEM;

-	if (!capable(CAP_SYS_RAWIO))
+	if (!capable(CAP_SYS_RAWIO) ||
+	    kernel_is_locked_down("Direct PCI access"))
 		return -EPERM;

 	if (fpriv->mmap_state == pci_mmap_io) {
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index d96626c614f5..b8a08d3166a1 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -90,7 +90,8 @@ SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
 	u32 dword;
 	int err = 0;

-	if (!capable(CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN) ||
+	    kernel_is_locked_down("Direct PCI access"))
 		return -EPERM;

 	dev = pci_get_domain_bus_and_slot(0, bus, dfn);
-- 
2.14.3

From 677537cdec42804f1936b57ffaa6181f633bc015 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:48 +0100
Subject: [PATCH 10/24] x86: Lock down IO port access when the kernel is locked
 down

IO port access would permit users to gain access to PCI configuration
registers, which in turn (on a lot of hardware) give access to MMIO
register space. This would potentially permit root to trigger arbitrary
DMA, so lock it down by default.

This also implicitly locks down the KDADDIO, KDDELIO, KDENABIO and
KDDISABIO console ioctls.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: x86@kernel.org
---
 arch/x86/kernel/ioport.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 0fe1c8782208..abc702a6ae9c 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -31,7 +31,8 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)

 	if ((from + num <= from) || (from + num > IO_BITMAP_BITS))
 		return -EINVAL;
-	if (turn_on && !capable(CAP_SYS_RAWIO))
+	if (turn_on && (!capable(CAP_SYS_RAWIO) ||
+			kernel_is_locked_down("ioperm")))
 		return -EPERM;

 	/*
@@ -126,7 +127,8 @@ SYSCALL_DEFINE1(iopl, unsigned int, level)
 		return -EINVAL;
 	/* Trying to gain more privileges? */
 	if (level > old) {
-		if (!capable(CAP_SYS_RAWIO))
+		if (!capable(CAP_SYS_RAWIO) ||
+		    kernel_is_locked_down("iopl"))
 			return -EPERM;
 	}
 	regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
-- 
2.14.3

From f005be07fababf8c698a556fe465871ad168c9d9 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:48 +0100
Subject: [PATCH 11/24] x86/msr: Restrict MSR access when the kernel is locked
 down

Writing to MSRs should not be allowed if the kernel is locked down, since
it could lead to execution of arbitrary code in kernel mode.  Based on a
patch by Kees Cook.

MSR accesses are logged for the purposes of building up a whitelist as per
Alan Cox's suggestion.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: x86@kernel.org
---
 arch/x86/kernel/msr.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index ef688804f80d..dfb61d358196 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -84,6 +84,11 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
 	int err = 0;
 	ssize_t bytes = 0;

+	if (kernel_is_locked_down("Direct MSR access")) {
+		pr_info("Direct access to MSR %x\n", reg);
+		return -EPERM;
+	}
+
 	if (count % 8)
 		return -EINVAL;	/* Invalid chunk size */

@@ -135,6 +140,11 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg)
 			err = -EFAULT;
 			break;
 		}
+		if (kernel_is_locked_down("Direct MSR access")) {
+			pr_info("Direct access to MSR %x\n", regs[1]); /* Display %ecx */
+			err = -EPERM;
+			break;
+		}
 		err = wrmsr_safe_regs_on_cpu(cpu, regs);
 		if (err)
 			break;
-- 
2.14.3

From 0a48b7c936757dda851ab2d3ecde7f6a79de7a5b Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Mon, 9 Apr 2018 09:52:48 +0100
Subject: [PATCH 12/24] ACPI: Limit access to custom_method when the kernel is
 locked down

custom_method effectively allows arbitrary access to system memory, making
it possible for an attacker to circumvent restrictions on module loading.
Disable it if the kernel is locked down.

Signed-off-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/custom_method.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/acpi/custom_method.c b/drivers/acpi/custom_method.c
index e967c1173ba3..a07fbe999eb6 100644
--- a/drivers/acpi/custom_method.c
+++ b/drivers/acpi/custom_method.c
@@ -29,6 +29,9 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf,
 	struct acpi_table_header table;
 	acpi_status status;

+	if (kernel_is_locked_down("ACPI custom methods"))
+		return -EPERM;
+
 	if (!(*ppos)) {
 		/* parse the table header to get the table length */
 		if (count <= sizeof(struct acpi_table_header))
-- 
2.14.3

From 2ed74b084366d7dba7b4a611ba13d99b82c4e11e Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Mon, 9 Apr 2018 09:52:49 +0100
Subject: [PATCH 13/24] acpi: Ignore acpi_rsdp kernel param when the kernel has
 been locked down

This option allows userspace to pass the RSDP address to the kernel, which
makes it possible for a user to modify the workings of hardware .  Reject
the option when the kernel is locked down.

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: Dave Young <dyoung@redhat.com>
cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/osl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 7ca41bf023c9..34e4ce7939f4 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -192,7 +192,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void)
 	acpi_physical_address pa;

 #ifdef CONFIG_KEXEC
-	if (acpi_rsdp)
+	if (acpi_rsdp && !kernel_is_locked_down("ACPI RSDP specification"))
 		return acpi_rsdp;
 #endif
 	pa = acpi_arch_get_root_pointer();
-- 
2.14.3

From 7fb2ddf683c23cc4b227d7d75a5d039970ca910e Mon Sep 17 00:00:00 2001
From: Linn Crosetto <linn@hpe.com>
Date: Mon, 9 Apr 2018 09:52:49 +0100
Subject: [PATCH 14/24] acpi: Disable ACPI table override if the kernel is
 locked down

From the kernel documentation (initrd_table_override.txt):

  If the ACPI_INITRD_TABLE_OVERRIDE compile option is true, it is possible
  to override nearly any ACPI table provided by the BIOS with an
  instrumented, modified one.

When securelevel is set, the kernel should disallow any unauthenticated
changes to kernel space.  ACPI tables contain code invoked by the kernel,
so do not allow ACPI tables to be overridden if the kernel is locked down.

Signed-off-by: Linn Crosetto <linn@hpe.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/tables.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 849c4fb19b03..6c5ee7e66842 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -527,6 +527,11 @@ void __init acpi_table_upgrade(void)
 	if (table_nr == 0)
 		return;

+	if (kernel_is_locked_down("ACPI table override")) {
+		pr_notice("kernel is locked down, ignoring table override\n");
+		return;
+	}
+
 	acpi_tables_addr =
 		memblock_find_in_range(0, ACPI_TABLE_UPGRADE_MAX_PHYS,
 				       all_tables_size, PAGE_SIZE);
-- 
2.14.3

From d1ff6505c76cec9438217f2c284f024a1ac2ac59 Mon Sep 17 00:00:00 2001
From: Linn Crosetto <linn@hpe.com>
Date: Mon, 9 Apr 2018 09:52:50 +0100
Subject: [PATCH 15/24] acpi: Disable APEI error injection if the kernel is
 locked down

ACPI provides an error injection mechanism, EINJ, for debugging and testing
the ACPI Platform Error Interface (APEI) and other RAS features.  If
supported by the firmware, ACPI specification 5.0 and later provide for a
way to specify a physical memory address to which to inject the error.

Injecting errors through EINJ can produce errors which to the platform are
indistinguishable from real hardware errors.  This can have undesirable
side-effects, such as causing the platform to mark hardware as needing
replacement.

While it does not provide a method to load unauthenticated privileged code,
the effect of these errors may persist across reboots and affect trust in
the underlying hardware, so disable error injection through EINJ if
the kernel is locked down.

Signed-off-by: Linn Crosetto <linn@hpe.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: "Lee, Chun-Yi" <jlee@suse.com>
cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/apei/einj.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index b38737c83a24..6d71e1e97b20 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -518,6 +518,9 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	int rc;
 	u64 base_addr, size;

+	if (kernel_is_locked_down("ACPI error injection"))
+		return -EPERM;
+
 	/* If user manually set "flags", make sure it is legal */
 	if (flags && (flags &
 		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
-- 
2.14.3

From 3153be0328e3a752aacab95d503fbd460f517402 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:37 +0100
Subject: [PATCH 16/24] Prohibit PCMCIA CIS storage when the kernel is locked
 down

Prohibit replacement of the PCMCIA Card Information Structure when the
kernel is locked down.

Suggested-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-pcmcia@lists.infradead.org
---
 drivers/pcmcia/cistpl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c
index 102646fedb56..e46c948d7246 100644
--- a/drivers/pcmcia/cistpl.c
+++ b/drivers/pcmcia/cistpl.c
@@ -1578,6 +1578,9 @@ static ssize_t pccard_store_cis(struct file *filp, struct kobject *kobj,
 	struct pcmcia_socket *s;
 	int error;

+	if (kernel_is_locked_down("Direct PCMCIA CIS storage"))
+		return -EPERM;
+
 	s = to_socket(container_of(kobj, struct device, kobj));

 	if (off)
-- 
2.14.3

From 9fedc1427e8589edf2e16a481f8588711adba69a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:37 +0100
Subject: [PATCH 17/24] Lock down TIOCSSERIAL

Lock down TIOCSSERIAL as that can be used to change the ioport and irq
settings on a serial port.  This only appears to be an issue for the serial
drivers that use the core serial code.  All other drivers seem to either
ignore attempts to change port/irq or give an error.

Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jiri Slaby <jslaby@suse.com>
---
 drivers/tty/serial/serial_core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0466f9f08a91..360f8e4416c4 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -829,6 +829,12 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 	new_flags = (__force upf_t)new_info->flags;
 	old_custom_divisor = uport->custom_divisor;

+	if ((change_port || change_irq) &&
+	    kernel_is_locked_down("Using TIOCSSERIAL to change device addresses, irqs and dma channels")) {
+		retval = -EPERM;
+		goto exit;
+	}
+
 	if (!capable(CAP_SYS_ADMIN)) {
 		retval = -EPERM;
 		if (change_irq || change_port ||
-- 
2.14.3

From f8fd52e2b077ce5a993807f8fc6e27a17cf4d19f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:37 +0100
Subject: [PATCH 18/24] Lock down module params that specify hardware
 parameters (eg. ioport)

Provided an annotation for module parameters that specify hardware
parameters (such as io ports, iomem addresses, irqs, dma channels, fixed
dma buffers and other types).

Suggested-by: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 kernel/params.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/kernel/params.c b/kernel/params.c
index cc9108c2a1fd..2c08c4aa376b 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -108,13 +108,19 @@ bool parameq(const char *a, const char *b)
 	return parameqn(a, b, strlen(a)+1);
 }

-static void param_check_unsafe(const struct kernel_param *kp)
+static bool param_check_unsafe(const struct kernel_param *kp,
+			       const char *doing)
 {
 	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
 		pr_notice("Setting dangerous option %s - tainting kernel\n",
 			  kp->name);
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
 	}
+
+	if (kp->flags & KERNEL_PARAM_FL_HWPARAM &&
+	    kernel_is_locked_down("Command line-specified device addresses, irqs and dma channels"))
+		return false;
+	return true;
 }

 static int parse_one(char *param,
@@ -144,8 +150,10 @@ static int parse_one(char *param,
 			pr_debug("handling %s with %p\n", param,
 				params[i].ops->set);
 			kernel_param_lock(params[i].mod);
-			param_check_unsafe(&params[i]);
-			err = params[i].ops->set(val, &params[i]);
+			if (param_check_unsafe(&params[i], doing))
+				err = params[i].ops->set(val, &params[i]);
+			else
+				err = -EPERM;
 			kernel_param_unlock(params[i].mod);
 			return err;
 		}
@@ -553,6 +561,12 @@ static ssize_t param_attr_show(struct module_attribute *mattr,
 	return count;
 }

+#ifdef CONFIG_MODULES
+#define mod_name(mod) (mod)->name
+#else
+#define mod_name(mod) "unknown"
+#endif
+
 /* sysfs always hands a nul-terminated string in buf.  We rely on that. */
 static ssize_t param_attr_store(struct module_attribute *mattr,
 				struct module_kobject *mk,
@@ -565,8 +579,10 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
 		return -EPERM;

 	kernel_param_lock(mk->mod);
-	param_check_unsafe(attribute->param);
-	err = attribute->param->ops->set(buf, attribute->param);
+	if (param_check_unsafe(attribute->param, mod_name(mk->mod)))
+		err = attribute->param->ops->set(buf, attribute->param);
+	else
+		err = -EPERM;
 	kernel_param_unlock(mk->mod);
 	if (!err)
 		return len;
-- 
2.14.3

From 9c88e2ab392f5ac9c80529e43175fe65d00cdb67 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:38 +0100
Subject: [PATCH 19/24] x86/mmiotrace: Lock down the testmmiotrace module

The testmmiotrace module shouldn't be permitted when the kernel is locked
down as it can be used to arbitrarily read and write MMIO space.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Howells <dhowells@redhat.com
cc: Thomas Gleixner <tglx@linutronix.de>
cc: Steven Rostedt <rostedt@goodmis.org>
cc: Ingo Molnar <mingo@kernel.org>
cc: "H. Peter Anvin" <hpa@zytor.com>
cc: x86@kernel.org
---
 arch/x86/mm/testmmiotrace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index f6ae6830b341..bbaad357f5d7 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -115,6 +115,9 @@ static int __init init(void)
 {
 	unsigned long size = (read_far) ? (8 << 20) : (16 << 10);

+	if (kernel_is_locked_down("MMIO trace testing"))
+		return -EPERM;
+
 	if (mmio_address == 0) {
 		pr_err("you have to use the module argument mmio_address.\n");
 		pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n");
-- 
2.14.3

From 256e20401f9f5dd19028d4220095897a15daa67c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:38 +0100
Subject: [PATCH 20/24] Lock down /proc/kcore

Disallow access to /proc/kcore when the kernel is locked down to prevent
access to cryptographic data.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: James Morris <james.l.morris@oracle.com>
---
 fs/proc/kcore.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d1e82761de81..cdebdee81719 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -546,6 +546,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)

 static int open_kcore(struct inode *inode, struct file *filp)
 {
+	if (kernel_is_locked_down("/proc/kcore"))
+		return -EPERM;
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;

-- 
2.14.3

From f68ca24bc8d8a64cf30e59a595fad0e6782e933f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:38 +0100
Subject: [PATCH 21/24] Lock down kprobes

Disallow the creation of kprobes when the kernel is locked down by
preventing their registration.  This prevents kprobes from being used to
access kernel memory, either to make modifications or to steal crypto data.

Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 kernel/kprobes.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 102160ff5c66..4f5757732553 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1561,6 +1561,9 @@ int register_kprobe(struct kprobe *p)
 	struct module *probed_mod;
 	kprobe_opcode_t *addr;

+	if (kernel_is_locked_down("Use of kprobes"))
+		return -EPERM;
+
 	/* Adjust probe address from symbol */
 	addr = kprobe_addr(p);
 	if (IS_ERR(addr))
-- 
2.14.3

From d44a6ae3a7cad5cd9b01f7b0a48b3c788af968e8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:38 +0100
Subject: [PATCH 23/24] Lock down perf

Disallow the use of certain perf facilities that might allow userspace to
access kernel data.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 kernel/events/core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc1c330c6bd6..1922f2e0980a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10407,6 +10407,11 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}

+	if ((attr.sample_type & PERF_SAMPLE_REGS_INTR) &&
+	    kernel_is_locked_down("PERF_SAMPLE_REGS_INTR"))
+		/* REGS_INTR can leak data, lockdown must prevent this */
+		return -EPERM;
+
 	/* Only privileged users can get physical addresses */
 	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) &&
 	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-- 
2.14.3

From fe5091f97838c8c64b891280bcd30367e71cd5c3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Apr 2018 14:45:38 +0100
Subject: [PATCH 24/24] debugfs: Restrict debugfs when the kernel is locked
 down

Disallow opening of debugfs files that might be used to muck around when
the kernel is locked down as various drivers give raw access to hardware
through debugfs.  Given the effort of auditing all 2000 or so files and
manually fixing each one as necessary, I've chosen to apply a heuristic
instead.  The following changes are made:

 (1) chmod and chown are disallowed on debugfs objects (though the root dir
     can be modified by mount and remount, but I'm not worried about that).

 (2) When the kernel is locked down, only files with the following criteria
     are permitted to be opened:

	- The file must have mode 00444
	- The file must not have ioctl methods
	- The file must not have mmap

 (3) When the kernel is locked down, files may only be opened for reading.

Normal device interaction should be done through configfs, sysfs or a
miscdev, not debugfs.

Note that this makes it unnecessary to specifically lock down show_dsts(),
show_devs() and show_call() in the asus-wmi driver.

I would actually prefer to lock down all files by default and have the
the files unlocked by the creator.  This is tricky to manage correctly,
though, as there are 19 creation functions and ~1600 call sites (some of
them in loops scanning tables).

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Andy Shevchenko <andy.shevchenko@gmail.com>
cc: acpi4asus-user@lists.sourceforge.net
cc: platform-driver-x86@vger.kernel.org
cc: Matthew Garrett <mjg59@srcf.ucam.org>
cc: Thomas Gleixner <tglx@linutronix.de>
---
 fs/debugfs/file.c  | 28 ++++++++++++++++++++++++++++
 fs/debugfs/inode.c | 30 ++++++++++++++++++++++++++++--
 2 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 1f99678ff5d3..51cb894c21f2 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -136,6 +136,25 @@ void debugfs_file_put(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_file_put);

+/*
+ * Only permit access to world-readable files when the kernel is locked down.
+ * We also need to exclude any file that has ways to write or alter it as root
+ * can bypass the permissions check.
+ */
+static bool debugfs_is_locked_down(struct inode *inode,
+				   struct file *filp,
+				   const struct file_operations *real_fops)
+{
+	if ((inode->i_mode & 07777) == 0444 &&
+	    !(filp->f_mode & FMODE_WRITE) &&
+	    !real_fops->unlocked_ioctl &&
+	    !real_fops->compat_ioctl &&
+	    !real_fops->mmap)
+		return false;
+
+	return kernel_is_locked_down("debugfs");
+}
+
 static int open_proxy_open(struct inode *inode, struct file *filp)
 {
 	struct dentry *dentry = F_DENTRY(filp);
@@ -147,6 +166,11 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;

 	real_fops = debugfs_real_fops(filp);
+
+	r = -EPERM;
+	if (debugfs_is_locked_down(inode, filp, real_fops))
+		goto out;
+
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {
 		/* Huh? Module did not clean up after itself at exit? */
@@ -272,6 +296,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;

 	real_fops = debugfs_real_fops(filp);
+	r = -EPERM;
+	if (debugfs_is_locked_down(inode, filp, real_fops))
+		goto out;
+
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {
 		/* Huh? Module did not cleanup after itself at exit? */
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 13b01351dd1c..4daec17b8215 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -32,6 +32,31 @@ static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
 static bool debugfs_registered;

+/*
+ * Don't allow access attributes to be changed whilst the kernel is locked down
+ * so that we can use the file mode as part of a heuristic to determine whether
+ * to lock down individual files.
+ */
+static int debugfs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+	if ((ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) &&
+	    kernel_is_locked_down("debugfs"))
+		return -EPERM;
+	return simple_setattr(dentry, ia);
+}
+
+static const struct inode_operations debugfs_file_inode_operations = {
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_symlink_inode_operations = {
+	.get_link	= simple_get_link,
+	.setattr	= debugfs_setattr,
+};
+
 static struct inode *debugfs_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -356,6 +381,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	inode->i_mode = mode;
 	inode->i_private = data;

+	inode->i_op = &debugfs_file_inode_operations;
 	inode->i_fop = proxy_fops;
 	dentry->d_fsdata = (void *)((unsigned long)real_fops |
 				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
@@ -515,7 +541,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 		return failed_creating(dentry);
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	inode->i_op = &simple_dir_inode_operations;
+	inode->i_op = &debugfs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;

 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -608,7 +634,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 		return failed_creating(dentry);
 	}
 	inode->i_mode = S_IFLNK | S_IRWXUGO;
-	inode->i_op = &simple_symlink_inode_operations;
+	inode->i_op = &debugfs_symlink_inode_operations;
 	inode->i_link = link;
 	d_instantiate(dentry, inode);
 	return end_creating(dentry);
-- 
2.14.3

From patchwork Wed Nov 21 12:05:10 2018
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Vasily Gorbik <gor@linux.ibm.com>
X-Patchwork-Id: 1015495
Return-Path: <SRS0=ejdu=OA=vger.kernel.org=linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id AF80FC04EBA
	for <linux-kernel@archiver.kernel.org>; Wed, 21 Nov 2018 12:05:25 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [209.132.180.67])
	by mail.kernel.org (Postfix) with ESMTP id 80EA921479
	for <linux-kernel@archiver.kernel.org>; Wed, 21 Nov 2018 12:05:25 +0000 (UTC)
DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 80EA921479
Authentication-Results: mail.kernel.org;
 dmarc=fail (p=none dis=none) header.from=linux.ibm.com
Authentication-Results: mail.kernel.org;
 spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1730155AbeKUWjb (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Wed, 21 Nov 2018 17:39:31 -0500
Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:33574 "EHLO
        mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL)
        by vger.kernel.org with ESMTP id S1729128AbeKUWjb (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Wed, 21 Nov 2018 17:39:31 -0500
Received: from pps.filterd (m0098420.ppops.net [127.0.0.1])
        by mx0b-001b2d01.pphosted.com (8.16.0.22/8.16.0.22) with SMTP id
 wALBx6kw056071
        for <linux-kernel@vger.kernel.org>; Wed, 21 Nov 2018 07:05:22 -0500
Received: from e06smtp02.uk.ibm.com (e06smtp02.uk.ibm.com [195.75.94.98])
        by mx0b-001b2d01.pphosted.com with ESMTP id 2nw5p847fp-1
        (version=TLSv1.2 cipher=AES256-GCM-SHA384 bits=256 verify=NOT)
        for <linux-kernel@vger.kernel.org>; Wed, 21 Nov 2018 07:05:22 -0500
Received: from localhost
        by e06smtp02.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use
 Only! Violators will be prosecuted
        for <linux-kernel@vger.kernel.org> from <gor@linux.ibm.com>;
        Wed, 21 Nov 2018 12:05:20 -0000
Received: from b06cxnps4075.portsmouth.uk.ibm.com (9.149.109.197)
        by e06smtp02.uk.ibm.com (192.168.101.132) with IBM ESMTP SMTP Gateway:
 Authorized Use Only! Violators will be prosecuted;
        (version=TLSv1/SSLv3 cipher=AES256-GCM-SHA384 bits=256/256)
        Wed, 21 Nov 2018 12:05:17 -0000
Received: from b06wcsmtp001.portsmouth.uk.ibm.com
 (b06wcsmtp001.portsmouth.uk.ibm.com [9.149.105.160])
        by b06cxnps4075.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with
 ESMTP id wALC5GXF60817580
        (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256
 verify=FAIL);
        Wed, 21 Nov 2018 12:05:16 GMT
Received: from b06wcsmtp001.portsmouth.uk.ibm.com (unknown [127.0.0.1])
        by IMSVA (Postfix) with ESMTP id 4EB1CA4060;
        Wed, 21 Nov 2018 12:05:16 +0000 (GMT)
Received: from b06wcsmtp001.portsmouth.uk.ibm.com (unknown [127.0.0.1])
        by IMSVA (Postfix) with ESMTP id 0C844A405F;
        Wed, 21 Nov 2018 12:05:16 +0000 (GMT)
Received: from localhost (unknown [9.152.212.229])
        by b06wcsmtp001.portsmouth.uk.ibm.com (Postfix) with ESMTPS;
        Wed, 21 Nov 2018 12:05:15 +0000 (GMT)
Date: Wed, 21 Nov 2018 13:05:10 +0100
From: Vasily Gorbik <gor@linux.ibm.com>
To: David Howells <dhowells@redhat.com>,
        James Morris <jmorris@namei.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        linux-kernel@vger.kernel.org, linux-security-module@vger.kernel.org
Subject: [PATCH next-lockdown 1/1] debugfs: avoid EPERM when no open file
 operation defined
References: <4136.1522452584@warthog.procyon.org.uk>
 <cover.thread-bfac1b.your-ad-here.call-01542799656-ext-6093@work.hours>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: 
 <cover.thread-bfac1b.your-ad-here.call-01542799656-ext-6093@work.hours>
X-TM-AS-GCONF: 00
x-cbid: 18112112-0008-0000-0000-000002963F3F
X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused
x-cbparentid: 18112112-0009-0000-0000-000022006F52
Message-Id: 
 <patch-1.thread-bfac1b.git-bfac1b60354c.your-ad-here.call-01542799656-ext-6093@work.hours>
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,,
 definitions=2018-11-21_05:,,
 signatures=0
X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0
 priorityscore=1501
 malwarescore=0 suspectscore=1 phishscore=0 bulkscore=0 spamscore=0
 clxscore=1015 lowpriorityscore=0 mlxscore=0 impostorscore=0
 mlxlogscore=999 adultscore=0 classifier=spam adjust=0 reason=mlx
 scancount=1 engine=8.0.1-1810050000 definitions=main-1811210107
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

With "debugfs: Restrict debugfs when the kernel is locked down"
return code "r" is unconditionally set to -EPERM, which stays like that
until function return if no "open" file operation defined, effectivelly
resulting in "Operation not permitted" for all such files despite kernel
lock down status or CONFIG_LOCK_DOWN_KERNEL being enabled.

In particular this breaks 2 debugfs files on s390:
/sys/kernel/debug/s390_hypfs/diag_304
/sys/kernel/debug/s390_hypfs/diag_204

To address that set EPERM return code only when debugfs_is_locked_down
returns true.

Fixes: 3fc322605158 ("debugfs: Restrict debugfs when the kernel is locked down")
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 fs/debugfs/file.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 51cb894c21f2..89c86faaa02a 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -167,9 +167,10 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 
 	real_fops = debugfs_real_fops(filp);
 
-	r = -EPERM;
-	if (debugfs_is_locked_down(inode, filp, real_fops))
+	if (debugfs_is_locked_down(inode, filp, real_fops)) {
+		r = -EPERM;
 		goto out;
+	}
 
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {
@@ -296,9 +297,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;
 
 	real_fops = debugfs_real_fops(filp);
-	r = -EPERM;
-	if (debugfs_is_locked_down(inode, filp, real_fops))
+	if (debugfs_is_locked_down(inode, filp, real_fops)) {
+		r = -EPERM;
 		goto out;
+	}
 
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {