x86/vsyscall: Add a new vsyscall=xonly mode

With vsyscall emulation on, a readable vsyscall page is still exposed that
contains syscall instructions that validly implement the vsyscalls.

This is required because certain dynamic binary instrumentation tools
attempt to read the call targets of call instructions in the instrumented
code.  If the instrumented code uses vsyscalls, then the vsyscall page needs
to contain readable code.

Unfortunately, leaving readable memory at a deterministic address can be
used to help various ASLR bypasses, so some hardening value can be gained
by disallowing vsyscall reads.

Given how rarely the vsyscall page needs to be readable, add a mechanism to
make the vsyscall page be execute only.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Kernel Hardening <kernel-hardening@lists.openwall.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/r/d17655777c21bc09a7af1bbcf74e6f2b69a51152.1561610354.git.luto@kernel.org

Documentation/admin-guide/kernel-parameters.txt

@@ -5100,7 +5100,12 @@
 			targets for exploits that can control RIP.
 
 			emulate     [default] Vsyscalls turn into traps and are
-			            emulated reasonably safely.
+			            emulated reasonably safely.  The vsyscall
+				    page is readable.
+
+			xonly       Vsyscalls turn into traps and are
+			            emulated reasonably safely.  The vsyscall
+				    page is not readable.
 
 			none        Vsyscalls don't work at all.  This makes
 			            them quite hard to use for exploits but

arch/x86/Kconfig

@@ -2293,23 +2293,38 @@ choice
 	  it can be used to assist security vulnerability exploitation.
 
 	  This setting can be changed at boot time via the kernel command
-	  line parameter vsyscall=[emulate|none].
+	  line parameter vsyscall=[emulate|xonly|none].
 
 	  On a system with recent enough glibc (2.14 or newer) and no
 	  static binaries, you can say None without a performance penalty
 	  to improve security.
 
-	  If unsure, select "Emulate".
+	  If unsure, select "Emulate execution only".
 
 	config LEGACY_VSYSCALL_EMULATE
-		bool "Emulate"
+		bool "Full emulation"
 		help
-		  The kernel traps and emulates calls into the fixed
-		  vsyscall address mapping. This makes the mapping
-		  non-executable, but it still contains known contents,
-		  which could be used in certain rare security vulnerability
-		  exploits. This configuration is recommended when userspace
-		  still uses the vsyscall area.
+		  The kernel traps and emulates calls into the fixed vsyscall
+		  address mapping. This makes the mapping non-executable, but
+		  it still contains readable known contents, which could be
+		  used in certain rare security vulnerability exploits. This
+		  configuration is recommended when using legacy userspace
+		  that still uses vsyscalls along with legacy binary
+		  instrumentation tools that require code to be readable.
+
+		  An example of this type of legacy userspace is running
+		  Pin on an old binary that still uses vsyscalls.
+
+	config LEGACY_VSYSCALL_XONLY
+		bool "Emulate execution only"
+		help
+		  The kernel traps and emulates calls into the fixed vsyscall
+		  address mapping and does not allow reads.  This
+		  configuration is recommended when userspace might use the
+		  legacy vsyscall area but support for legacy binary
+		  instrumentation of legacy code is not needed.  It mitigates
+		  certain uses of the vsyscall area as an ASLR-bypassing
+		  buffer.
 
 	config LEGACY_VSYSCALL_NONE
 		bool "None"

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -42,9 +42,11 @@
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
-static enum { EMULATE, NONE } vsyscall_mode =
+static enum { EMULATE, XONLY, NONE } vsyscall_mode =
 #ifdef CONFIG_LEGACY_VSYSCALL_NONE
 	NONE;
+#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
+	XONLY;
 #else
 	EMULATE;
 #endif
@@ -54,6 +56,8 @@ static int __init vsyscall_setup(char *str)
 	if (str) {
 		if (!strcmp("emulate", str))
 			vsyscall_mode = EMULATE;
+		else if (!strcmp("xonly", str))
+			vsyscall_mode = XONLY;
 		else if (!strcmp("none", str))
 			vsyscall_mode = NONE;
 		else
@@ -357,12 +361,20 @@ void __init map_vsyscall(void)
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE) {
+	/*
+	 * For full emulation, the page needs to exist for real.  In
+	 * execute-only mode, there is no PTE at all backing the vsyscall
+	 * page.
+	 */
+	if (vsyscall_mode == EMULATE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     PAGE_KERNEL_VVAR);
 		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
 	}
 
+	if (vsyscall_mode == XONLY)
+		gate_vma.vm_flags = VM_EXEC;
+
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);
 }