From 937ed91c712273131de6d2a02caafd3ee84e0c72 Mon Sep 17 00:00:00 2001
From: Ammar Faizi <ammar.faizi@students.amikom.ac.id>
Date: Sun, 24 Oct 2021 19:28:14 +0200
Subject: [PATCH] tools/nolibc: x86-64: Fix startup code bug
Git-commit: 937ed91c712273131de6d2a02caafd3ee84e0c72
Patch-mainline: v5.17-rc1
References: git-fixes

Before this patch, the `_start` function looks like this:
```
0000000000001170 <_start>:
    1170:	pop    %rdi
    1171:	mov    %rsp,%rsi
    1174:	lea    0x8(%rsi,%rdi,8),%rdx
    1179:	and    $0xfffffffffffffff0,%rsp
    117d:	sub    $0x8,%rsp
    1181:	call   1000 <main>
    1186:	movzbq %al,%rdi
    118a:	mov    $0x3c,%rax
    1191:	syscall
    1193:	hlt
    1194:	data16 cs nopw 0x0(%rax,%rax,1)
    119f:	nop
```
Note the "and" to %rsp with $-16, it makes the %rsp be 16-byte aligned,
but then there is a "sub" with $0x8 which makes the %rsp no longer
16-byte aligned, then it calls main. That's the bug!

What actually the x86-64 System V ABI mandates is that right before the
"call", the %rsp must be 16-byte aligned, not after the "call". So the
"sub" with $0x8 here breaks the alignment. Remove it.

An example where this rule matters is when the callee needs to align
its stack at 16-byte for aligned move instruction, like `movdqa` and
`movaps`. If the callee can't align its stack properly, it will result
in segmentation fault.

x86-64 System V ABI also mandates the deepest stack frame should be
zero. Just to be safe, let's zero the %rbp on startup as the content
of %rbp may be unspecified when the program starts. Now it looks like
This: 
```
0000000000001170 <_start>:
    1170:	pop    %rdi
    1171:	mov    %rsp,%rsi
    1174:	lea    0x8(%rsi,%rdi,8),%rdx
    1179:	xor    %ebp,%ebp                # zero the %rbp
    117b:	and    $0xfffffffffffffff0,%rsp # align the %rsp
    117f:	call   1000 <main>
    1184:	movzbq %al,%rdi
    1188:	mov    $0x3c,%rax
    118f:	syscall
    1191:	hlt
    1192:	data16 cs nopw 0x0(%rax,%rax,1)
    119d:	nopl   (%rax)
```

Cc: Bedirhan KURT <windowz414@gnuweeb.org>
Cc: Louvian Lyndal <louvianlyndal@gmail.com>
Reported-by: Peter Cordes <peter@cordes.ca>
Signed-off-by: Ammar Faizi <ammar.faizi@students.amikom.ac.id>
[wt: I did this on purpose due to a misunderstanding of the spec, other     archs will thus have to be rechecked, particularly i386]
Cc: stable@vger.kernel.org
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 tools/include/nolibc/nolibc.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
index 3430667b0d24..96b6d56acb57 100644
--- a/tools/include/nolibc/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -399,14 +399,20 @@ struct stat {
 })
 
 /* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
 asm(".section .text\n"
     ".global _start\n"
     "_start:\n"
     "pop %rdi\n"                // argc   (first arg, %rdi)
     "mov %rsp, %rsi\n"          // argv[] (second arg, %rsi)
     "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
-    "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned when
-    "sub $8, %rsp\n"            // entering the callee
+    "xor %ebp, %ebp\n"          // zero the stack frame
+    "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned before call
     "call main\n"               // main() returns the status code, we'll exit with it.
     "movzb %al, %rdi\n"         // retrieve exit code from 8 lower bits
     "mov $60, %rax\n"           // NR_exit == 60
-- 
2.35.3