x86/syscall: Sanitize syscall table de-references under speculation

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 <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Andy Lutomirski <luto@kernel.org>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727417984.33451.1216731042505722161.stgit@dwillia2-desk3.amr.corp.intel.com

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 9908134..21dbdf0 100644 (file)
--- 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>
@@ -282,7 +283,8 @@ __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);
        }
@@ -318,6 +320,7 @@ 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