[PATCH v1 1/1] tools/nolibc: i386: Fix a stack misalign bug on _start

[Ammar Faizi]

The ABI mandates that the %esp register must be a multiple of 16 when
executing a call instruction.

Commit 2ab446336b17 simplified the _start function, but it didn't take
care of the %esp alignment, causing SIGSEGV on SSE and AVX programs that
use aligned move instruction (e.g., movdqa, movaps, and vmovdqa).

Ensure the %esp is a multiple of 16 when executing the call instruction.

Cc: Zhangjin Wu <falcon@xxxxxxxxxxx>
Fixes: 2ab446336b17aad362c6decee29b4efd83a01979 ("tools/nolibc: i386: shrink _start with _start_c")
Reported-by: Nicholas Rosenberg <inori@xxxxxxxx>
Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>
---
 tools/include/nolibc/arch-i386.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
index 64415b9fac77f996..4edf238eeac67aa2 100644
--- a/tools/include/nolibc/arch-i386.h
+++ b/tools/include/nolibc/arch-i386.h
@@ -167,7 +167,8 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_
 	__asm__ volatile (
 		"xor  %ebp, %ebp\n"       /* zero the stack frame                                */
 		"mov  %esp, %eax\n"       /* save stack pointer to %eax, as arg1 of _start_c     */
-		"and  $-16, %esp\n"       /* last pushed argument must be 16-byte aligned        */
+		"and  $-16, %esp\n"       /* align stack to 16 bytes                             */
+		"sub  $12, %esp\n"        /* last pushed argument must be 16-byte aligned        */
 		"push %eax\n"             /* push arg1 on stack to support plain stack modes too */
 		"call _start_c\n"         /* transfer to c runtime                               */
 		"hlt\n"                   /* ensure it does not return                           */
-- 
Ammar Faizi