[PATCH 2/2] x86/ldt: allow to disable modify_ldt at runtime

[Willy Tarreau]

For distros who prefer not to take the risk of completely disabling the
modify_ldt syscall using CONFIG_MODIFY_LDT_SYSCALL, this patch adds a
sysctl to enable, temporarily disable, or permanently disable it at
runtime, and proposes to temporarily disable it by default. This can be
a safe alternative. A message is logged if an attempt was stopped so that
it's easy to spot if/when it is needed.

Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 Documentation/sysctl/kernel.txt | 16 ++++++++++++++++
 arch/x86/Kconfig                | 17 +++++++++++++++++
 arch/x86/kernel/ldt.c           | 15 +++++++++++++++
 kernel/sysctl.c                 | 14 ++++++++++++++
 4 files changed, 62 insertions(+)

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 6fccb69..55648b9 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -41,6 +41,7 @@ show up in /proc/sys/kernel:
 - kptr_restrict
 - kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
+- modify_ldt                  [ X86 only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
 - modules_disabled
 - msg_next_id		      [ sysv ipc ]
@@ -391,6 +392,21 @@ This flag controls the L2 cache of G3 processor boards. If
 
 ==============================================================
 
+modify_ldt: (X86 only)
+
+Enables (1), disables (0) or permanently disables (-1) the modify_ldt syscall.
+Modifying the LDT (Local Descriptor Table) may be needed to run a 16-bit or
+segmented code such as Dosemu or Wine. This is done via a system call which is
+not needed to run portable applications, and which can sometimes be abused to
+exploit some weaknesses of the architecture, opening new vulnerabilities.
+
+This sysctl allows one to increase the system's security by disabling the
+system call, or to restore compatibility with specific applications when it
+was already disabled. When permanently disabled, it is not possible to change
+the value anymore until the next system reboot.
+
+==============================================================
+
 modules_disabled:
 
 A toggle value indicating if modules are allowed to be loaded
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index beabf30..88d10a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2069,6 +2069,23 @@ config MODIFY_LDT_SYSCALL
 	  surface.  Disabling it removes the modify_ldt(2) system call.
 
 	  Saying 'N' here may make sense for embedded or server kernels.
+	  If really unsure, say 'Y', you'll be able to disable it at runtime.
+
+config DEFAULT_MODIFY_LDT_SYSCALL
+	bool "Allow userspace to modify the LDT by default"
+	depends on MODIFY_LDT_SYSCALL
+	default y
+	---help---
+	  Modifying the LDT (Local Descriptor Table) may be needed to run a
+	  16-bit or segmented code such as Dosemu or Wine. This is done via
+	  a system call which is not needed to run portable applications,
+	  and which can sometimes be abused to exploit some weaknesses of
+	  the architecture, opening new vulnerabilities.
+
+	  For this reason this option allows one to enable or disable the
+	  feature at runtime. It is recommended to say 'N' here to leave
+	  the system protected, and to enable it at runtime only if needed
+	  by setting the sys.kernel.modify_ldt sysctl.
 
 source "kernel/livepatch/Kconfig"
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 2bcc052..420fc8f 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/ratelimit.h>
 #include <linux/smp.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -21,6 +22,11 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+int sysctl_modify_ldt __read_mostly =
+	IS_ENABLED(CONFIG_DEFAULT_MODIFY_LDT_SYSCALL);
+#endif
+
 /* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
@@ -276,6 +282,15 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr,
 {
 	int ret = -ENOSYS;
 
+	if (sysctl_modify_ldt <= 0) {
+		printk_ratelimited(KERN_INFO
+			"Denied a call to modify_ldt() from %s[%d] (uid: %d)."
+			" Adjust sysctl if this was not an exploit attempt.\n",
+			current->comm, task_pid_nr(current),
+			from_kuid_munged(current_user_ns(), current_uid()));
+		return ret;
+	}
+
 	switch (func) {
 	case 0:
 		ret = read_ldt(ptr, bytecount);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 86c95a8..ec1170d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -111,6 +111,9 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+extern int sysctl_modify_ldt;
+#endif
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -963,6 +966,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	{
+		.procname	= "modify_ldt",
+		.data		= &sysctl_modify_ldt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax_negperm,
+		.extra1		= &neg_one,
+		.extra2		= &one,
+	},
+#endif
 #endif
 #if defined(CONFIG_MMU)
 	{
-- 
1.7.12.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/