kexec: introduce sysctl parameters kexec_load_limit_*

kexec allows replacing the current kernel with a different one.  This is
usually a source of concerns for sysadmins that want to harden a system.

Linux already provides a way to disable loading new kexec kernel via
kexec_load_disabled, but that control is very coard, it is all or nothing
and does not make distinction between a panic kexec and a normal kexec.

This patch introduces new sysctl parameters, with finer tuning to specify
how many times a kexec kernel can be loaded.  The sysadmin can set
different limits for kexec panic and kexec reboot kernels.  The value can
be modified at runtime via sysctl, but only with a stricter value.

With these new parameters on place, a system with loadpin and verity
enabled, using the following kernel parameters:
sysctl.kexec_load_limit_reboot=0 sysct.kexec_load_limit_panic=1 can have a
good warranty that if initrd tries to load a panic kernel, a malitious
user will have small chances to replace that kernel with a different one,
even if they can trigger timeouts on the disk where the panic kernel
lives.

Link: https://lkml.kernel.org/r/20221114-disable-kexec-reset-v6-3-6a8531a09b9a@chromium.org
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Philipp Rudo <prudo@redhat.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 114 insertions, 8 deletions

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index b53c0235cb43..4b7bfea28cd7 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -464,6 +464,24 @@ allowing a system to set up (and later use) an image without it being
 altered.
 Generally used together with the `modules_disabled`_ sysctl.
 
+kexec_load_limit_panic
+======================
+
+This parameter specifies a limit to the number of times the syscalls
+``kexec_load`` and ``kexec_file_load`` can be called with a crash
+image. It can only be set with a more restrictive value than the
+current one.
+
+== ======================================================
+-1 Unlimited calls to kexec. This is the default setting.
+N  Number of calls left.
+== ======================================================
+
+kexec_load_limit_reboot
+=======================
+
+Similar functionality as ``kexec_load_limit_panic``, but for a normal
+image.
 
 kptr_restrict
 =============
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index f18a3c9e813b..6883c5922701 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -404,7 +404,7 @@ extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
 
-bool kexec_load_permitted(void);
+bool kexec_load_permitted(int kexec_image_type);
 
 #ifndef kexec_flush_icache_page
 #define kexec_flush_icache_page(page)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ce1bca874a8d..92d301f98776 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -190,10 +190,12 @@ out_unlock:
 static inline int kexec_load_check(unsigned long nr_segments,
 				   unsigned long flags)
 {
+	int image_type = (flags & KEXEC_ON_CRASH) ?
+			 KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT;
 	int result;
 
 	/* We only trust the superuser with rebooting the system. */
-	if (!kexec_load_permitted())
+	if (!kexec_load_permitted(image_type))
 		return -EPERM;
 
 	/* Permit LSMs and IMA to fail the kexec */
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index d51ebbaeb1b2..ab140098c3ad 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -920,10 +920,64 @@ int kimage_load_segment(struct kimage *image,
 	return result;
 }
 
+struct kexec_load_limit {
+	/* Mutex protects the limit count. */
+	struct mutex mutex;
+	int limit;
+};
+
+static struct kexec_load_limit load_limit_reboot = {
+	.mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex),
+	.limit = -1,
+};
+
+static struct kexec_load_limit load_limit_panic = {
+	.mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex),
+	.limit = -1,
+};
+
 struct kimage *kexec_image;
 struct kimage *kexec_crash_image;
 static int kexec_load_disabled;
+
 #ifdef CONFIG_SYSCTL
+static int kexec_limit_handler(struct ctl_table *table, int write,
+			       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct kexec_load_limit *limit = table->data;
+	int val;
+	struct ctl_table tmp = {
+		.data = &val,
+		.maxlen = sizeof(val),
+		.mode = table->mode,
+	};
+	int ret;
+
+	if (write) {
+		ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+		if (ret)
+			return ret;
+
+		if (val < 0)
+			return -EINVAL;
+
+		mutex_lock(&limit->mutex);
+		if (limit->limit != -1 && val >= limit->limit)
+			ret = -EINVAL;
+		else
+			limit->limit = val;
+		mutex_unlock(&limit->mutex);
+
+		return ret;
+	}
+
+	mutex_lock(&limit->mutex);
+	val = limit->limit;
+	mutex_unlock(&limit->mutex);
+
+	return proc_dointvec(&tmp, write, buffer, lenp, ppos);
+}
+
 static struct ctl_table kexec_core_sysctls[] = {
 	{
 		.procname	= "kexec_load_disabled",
@@ -935,6 +989,18 @@ static struct ctl_table kexec_core_sysctls[] = {
 		.extra1		= SYSCTL_ONE,
 		.extra2		= SYSCTL_ONE,
 	},
+	{
+		.procname	= "kexec_load_limit_panic",
+		.data		= &load_limit_panic,
+		.mode		= 0644,
+		.proc_handler	= kexec_limit_handler,
+	},
+	{
+		.procname	= "kexec_load_limit_reboot",
+		.data		= &load_limit_reboot,
+		.mode		= 0644,
+		.proc_handler	= kexec_limit_handler,
+	},
 	{ }
 };
 
@@ -946,13 +1012,30 @@ static int __init kexec_core_sysctl_init(void)
 late_initcall(kexec_core_sysctl_init);
 #endif
 
-bool kexec_load_permitted(void)
+bool kexec_load_permitted(int kexec_image_type)
 {
+	struct kexec_load_limit *limit;
+
 	/*
 	 * Only the superuser can use the kexec syscall and if it has not
 	 * been disabled.
 	 */
-	return capable(CAP_SYS_BOOT) && !kexec_load_disabled;
+	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
+		return false;
+
+	/* Check limit counter and decrease it.*/
+	limit = (kexec_image_type == KEXEC_TYPE_CRASH) ?
+		&load_limit_panic : &load_limit_reboot;
+	mutex_lock(&limit->mutex);
+	if (!limit->limit) {
+		mutex_unlock(&limit->mutex);
+		return false;
+	}
+	if (limit->limit != -1)
+		limit->limit--;
+	mutex_unlock(&limit->mutex);
+
+	return true;
 }
 
 /*
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index c897eb4b8c8c..f1a0e4e3fb5c 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -326,11 +326,13 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 		unsigned long, cmdline_len, const char __user *, cmdline_ptr,
 		unsigned long, flags)
 {
-	int ret = 0, i;
+	int image_type = (flags & KEXEC_FILE_ON_CRASH) ?
+			 KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT;
 	struct kimage **dest_image, *image;
+	int ret = 0, i;
 
 	/* We only trust the superuser with rebooting the system. */
-	if (!kexec_load_permitted())
+	if (!kexec_load_permitted(image_type))
 		return -EPERM;
 
 	/* Make sure we have a legal set of flags */
@@ -342,11 +344,12 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (!kexec_trylock())
 		return -EBUSY;
 
-	dest_image = &kexec_image;
-	if (flags & KEXEC_FILE_ON_CRASH) {
+	if (image_type == KEXEC_TYPE_CRASH) {
 		dest_image = &kexec_crash_image;
 		if (kexec_crash_image)
 			arch_kexec_unprotect_crashkres();
+	} else {
+		dest_image = &kexec_image;
 	}
 
 	if (flags & KEXEC_FILE_UNLOAD)