tools/nolibc: i386: fix initial stack alignment

commit ebbe0d8a44 upstream.

After re-checking in the spec and comparing stack offsets with glibc,
The last pushed argument must be 16-byte aligned (i.e. aligned before the
call) so that in the callee esp+4 is multiple of 16, so the principle is
the 32-bit equivalent to what Ammar fixed for x86_64. It's possible that
32-bit code using SSE2 or MMX could have been affected. In addition the
frame pointer ought to be zero at the deepest level.

Link: https://gitlab.com/x86-psABIs/i386-ABI/-/wikis/Intel386-psABI
Cc: Ammar Faizi <ammar.faizi@students.amikom.ac.id>
Cc: stable@vger.kernel.org
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

tools/include/nolibc/nolibc.h

@@ -606,13 +606,21 @@ struct sys_stat_struct {
 })
 
 /* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
 asm(".section .text\n"
     ".global _start\n"
     "_start:\n"
     "pop %eax\n"                // argc   (first arg, %eax)
     "mov %esp, %ebx\n"          // argv[] (second arg, %ebx)
     "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
-    "and $-16, %esp\n"          // x86 ABI : esp must be 16-byte aligned when
+    "xor %ebp, %ebp\n"          // zero the stack frame
+    "and $-16, %esp\n"          // x86 ABI : esp must be 16-byte aligned before
+    "sub $4, %esp\n"            // the call instruction (args are aligned)
     "push %ecx\n"               // push all registers on the stack so that we
     "push %ebx\n"               // support both regparm and plain stack modes
     "push %eax\n"