The syscall table base is a user controlled function pointer in kernel
space. Use array_index_nospec() to prevent any out of bounds
speculation. While retpoline prevents speculating into a userspace
directed target it does not stop the pointer de-reference, the concern
is leaking memory relative to the syscall table base, by observing
instruction cache behavior.
Reported-by: Linus Torvalds <torva...@linux-foundation.org>
Cc: Thomas Gleixner <t...@linutronix.de>
Cc: Ingo Molnar <mi...@redhat.com>
Cc: "H. Peter Anvin" <h...@zytor.com>
Cc: x...@kernel.org
Cc: Andy Lutomirski <l...@kernel.org>
Signed-off-by: Dan Williams <dan.j.willi...@intel.com>
---
arch/x86/entry/common.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 03505ffbe1b6..390abbc4c915 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -21,6 +21,7 @@
#include <linux/export.h>
#include <linux/context_tracking.h>
#include <linux/user-return-notifier.h>
+#include <linux/nospec.h>
#include <linux/uprobes.h>
#include <linux/livepatch.h>
#include <linux/syscalls.h>
@@ -284,7 +285,8 @@ __visible void do_syscall_64(struct pt_regs *regs)
* regs->orig_ax, which changes the behavior of some syscalls.
*/
if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) {
- regs->ax = sys_call_table[nr & __SYSCALL_MASK](
+ nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls);
+ regs->ax = sys_call_table[nr](
regs->di, regs->si, regs->dx,
regs->r10, regs->r8, regs->r9);
}
@@ -320,6 +322,7 @@ static __always_inline void do_syscall_32_irqs_on(struct
pt_regs *regs)
}
if (likely(nr < IA32_NR_syscalls)) {
+ nr = array_index_nospec(nr, IA32_NR_syscalls);
/*
* It's possible that a 32-bit syscall implementation
* takes a 64-bit parameter but nonetheless assumes that
