From: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Tue, 7 Jun 2022 04:11:28 +0000 (-0700)
Subject: x86: Add COND_VZEROUPPER that can replace vzeroupper if no `ret`
X-Git-Tag: glibc-2.36~181
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=dd5c483b2598f411428df4d8864c15c4b8a3cd68;p=thirdparty%2Fglibc.git

x86: Add COND_VZEROUPPER that can replace vzeroupper if no `ret`

The RTM vzeroupper mitigation has no way of replacing inline
vzeroupper not before a return.

This can be useful when hoisting a vzeroupper to save code size
for example:

```
L(foo):
	cmpl	%eax, %edx
	jz	L(bar)
	tzcntl	%eax, %eax
	addq	%rdi, %rax
	VZEROUPPER_RETURN

L(bar):
	xorl	%eax, %eax
	VZEROUPPER_RETURN
```

Can become:

```
L(foo):
	COND_VZEROUPPER
	cmpl	%eax, %edx
	jz	L(bar)
	tzcntl	%eax, %eax
	addq	%rdi, %rax
	ret

L(bar):
	xorl	%eax, %eax
	ret
```

This code does not change any existing functionality.

There is no difference in the objdump of libc.so before and after this
patch.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
---

diff --git a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
index 3f531dd47fc..6ca9f5e6bae 100644
--- a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
+++ b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
@@ -20,6 +20,7 @@
 #ifndef _AVX_RTM_VECS_H
 #define _AVX_RTM_VECS_H			1
 
+#define COND_VZEROUPPER			COND_VZEROUPPER_XTEST
 #define ZERO_UPPER_VEC_REGISTERS_RETURN	\
 	ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST
 
diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
index f14d50786d2..4f512d5566b 100644
--- a/sysdeps/x86_64/sysdep.h
+++ b/sysdeps/x86_64/sysdep.h
@@ -106,6 +106,24 @@ lose:									      \
 	vzeroupper;						\
 	ret
 
+/* Can be used to replace vzeroupper that is not directly before a
+   return.  This is useful when hoisting a vzeroupper from multiple
+   return paths to decrease the total number of vzerouppers and code
+   size.  */
+#define COND_VZEROUPPER_XTEST							\
+    xtest;							\
+    jz 1f;							\
+    vzeroall;							\
+    jmp 2f;							\
+1:							\
+    vzeroupper;							\
+2:
+
+/* In RTM define this as COND_VZEROUPPER_XTEST.  */
+#ifndef COND_VZEROUPPER
+# define COND_VZEROUPPER vzeroupper
+#endif
+
 /* Zero upper vector registers and return.  */
 #ifndef ZERO_UPPER_VEC_REGISTERS_RETURN
 # define ZERO_UPPER_VEC_REGISTERS_RETURN \