x86/entry/64: Introduce the PUSH_AND_CLEAN_REGS macro

Those instances where ALLOC_PT_GPREGS_ON_STACK is called just before
SAVE_AND_CLEAR_REGS can trivially be replaced by PUSH_AND_CLEAN_REGS.
This macro uses PUSH instead of MOV and should therefore be faster, at
least on newer CPUs.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dan.j.williams@intel.com
Link: http://lkml.kernel.org/r/20180211104949.12992-5-linux@dominikbrodowski.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 38 insertions, 4 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index a05cbb81268d..57b1b87a04f0 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -137,6 +137,42 @@ For 32-bit we have the following conventions - kernel is built with
         UNWIND_HINT_REGS offset=\offset
         .endm
 
+        .macro PUSH_AND_CLEAR_REGS
+        /*
+         * Push registers and sanitize registers of values that a
+         * speculation attack might otherwise want to exploit. The
+         * lower registers are likely clobbered well before they
+         * could be put to use in a speculative execution gadget.
+         * Interleave XOR with PUSH for better uop scheduling:
+         */
+        pushq   %rdi            /* pt_regs->di */
+        pushq   %rsi            /* pt_regs->si */
+        pushq   %rdx            /* pt_regs->dx */
+        pushq   %rcx            /* pt_regs->cx */
+        pushq   %rax            /* pt_regs->ax */
+        pushq   %r8             /* pt_regs->r8 */
+        xorq    %r8, %r8        /* nospec   r8 */
+        pushq   %r9             /* pt_regs->r9 */
+        xorq    %r9, %r9        /* nospec   r9 */
+        pushq   %r10            /* pt_regs->r10 */
+        xorq    %r10, %r10      /* nospec   r10 */
+        pushq   %r11            /* pt_regs->r11 */
+        xorq    %r11, %r11      /* nospec   r11*/
+        pushq   %rbx            /* pt_regs->rbx */
+        xorl    %ebx, %ebx      /* nospec   rbx*/
+        pushq   %rbp            /* pt_regs->rbp */
+        xorl    %ebp, %ebp      /* nospec   rbp*/
+        pushq   %r12            /* pt_regs->r12 */
+        xorq    %r12, %r12      /* nospec   r12*/
+        pushq   %r13            /* pt_regs->r13 */
+        xorq    %r13, %r13      /* nospec   r13*/
+        pushq   %r14            /* pt_regs->r14 */
+        xorq    %r14, %r14      /* nospec   r14*/
+        pushq   %r15            /* pt_regs->r15 */
+        xorq    %r15, %r15      /* nospec   r15*/
+        UNWIND_HINT_REGS
+        .endm
+
         .macro POP_REGS pop_rdi=1 skip_r11rcx=0
         popq %r15
         popq %r14
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 07692b44800d..cf4a9ae558f3 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -564,8 +564,7 @@ END(irq_entries_start)
         call    switch_to_thread_stack
 1:
 
-        ALLOC_PT_GPREGS_ON_STACK
-        SAVE_AND_CLEAR_REGS
+        PUSH_AND_CLEAR_REGS
         ENCODE_FRAME_POINTER
 
         testb   $3, CS(%rsp)
@@ -1112,8 +1111,7 @@ ENTRY(xen_failsafe_callback)
         addq    $0x30, %rsp
         UNWIND_HINT_IRET_REGS
         pushq   $-1 /* orig_ax = -1 => not a system call */
-        ALLOC_PT_GPREGS_ON_STACK
-        SAVE_AND_CLEAR_REGS
+        PUSH_AND_CLEAR_REGS
         ENCODE_FRAME_POINTER
         jmp     error_exit
 END(xen_failsafe_callback)