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>
#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
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 \