@@ -5084,7 +5084,12 @@
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
@@ -2288,23 +2288,35 @@ 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 legacy using userspace
+ that still uses vsyscalls along with legacy binary
+ instrumentation tools that require code to be readable.
+
+ 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"
@@ -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
@@ -284,13 +288,20 @@ static const char *gate_vma_name(struct vm_area_struct *vma)
static const struct vm_operations_struct gate_vma_ops = {
.name = gate_vma_name,
};
-static struct vm_area_struct gate_vma = {
+static struct vm_area_struct rx_gate_vma = {
.vm_start = VSYSCALL_ADDR,
.vm_end = VSYSCALL_ADDR + PAGE_SIZE,
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC,
.vm_ops = &gate_vma_ops,
};
+static struct vm_area_struct xo_gate_vma = {
+ .vm_start = VSYSCALL_ADDR,
+ .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
+ .vm_page_prot = PAGE_READONLY_EXEC,
+ .vm_flags = VM_EXEC,
+ .vm_ops = &gate_vma_ops,
+};
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
@@ -300,7 +311,7 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
#endif
if (vsyscall_mode == NONE)
return NULL;
- return &gate_vma;
+ return vsyscall_mode == XONLY ? &xo_gate_vma : &rx_gate_vma;
}
int in_gate_area(struct mm_struct *mm, unsigned long addr)
@@ -357,7 +368,7 @@ void __init map_vsyscall(void)
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- if (vsyscall_mode != NONE) {
+ if (vsyscall_mode == EMULATE) {
__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
PAGE_KERNEL_VVAR);
set_vsyscall_pgtable_user_bits(swapper_pg_dir);
With vsyscall emulation on, we still expose a readable vsyscall page that contains syscall instructions that validly implement the vsyscalls. We need this 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 vsyscal page needs to contain readable code. Unfortunately, leaving readable memory at a deterministic address can be used to help various ASLR bypasses, so we gain some hardening value if we disallow vsyscall reads. Given how rarely the vsyscall page needs to be readable, add a mechanism to make the vsyscall page be execute only. Cc: Kees Cook <keescook@chromium.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Kernel Hardening <kernel-hardening@lists.openwall.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andy Lutomirski <luto@kernel.org> --- .../admin-guide/kernel-parameters.txt | 7 ++++- arch/x86/Kconfig | 30 +++++++++++++------ arch/x86/entry/vsyscall/vsyscall_64.c | 19 +++++++++--- 3 files changed, 42 insertions(+), 14 deletions(-)