Intel's Silvermont/Knights Landing architecture treats them as full ALU
operations, rather than zeroing idoms.
No functional change, and no change in code volume (only changing the bit
selection in the REX prefix).
Signed-off-by: Andrew Cooper <andrew.coop...@citrix.com>
---
CC: Jan Beulich <jbeul...@suse.com>
If anyone is interested, <20180211104949.12992-5-li...@dominikbrodowski.net>
is the LKML discusson on the subject. It is most likely that this is a
deliberate simplification in the Knights* architecture because compilers
follow optimisation instructions of "use xors for zeroing" and "use 32bit
operations in preference to 64bit ones wherever possible".
---
xen/include/asm-x86/asm_defns.h | 32 ++++++++++++++++----------------
1 file changed, 16 insertions(+), 16 deletions(-)
diff --git a/xen/include/asm-x86/asm_defns.h b/xen/include/asm-x86/asm_defns.h
index aee14ba..6fc13d3 100644
--- a/xen/include/asm-x86/asm_defns.h
+++ b/xen/include/asm-x86/asm_defns.h
@@ -269,10 +269,10 @@ static always_inline void stac(void)
movq %r10,UREGS_r10(%rsp)
movq %r11,UREGS_r11(%rsp)
.endif
- xor %r8, %r8
- xor %r9, %r9
- xor %r10, %r10
- xor %r11, %r11
+ xor %r8d, %r8d
+ xor %r9d, %r9d
+ xor %r10d, %r10d
+ xor %r11d, %r11d
movq %rbx,UREGS_rbx(%rsp)
xor %ebx, %ebx
movq %rbp,UREGS_rbp(%rsp)
@@ -289,10 +289,10 @@ static always_inline void stac(void)
movq %r14,UREGS_r14(%rsp)
movq %r15,UREGS_r15(%rsp)
.endif
- xor %r12, %r12
- xor %r13, %r13
- xor %r14, %r14
- xor %r15, %r15
+ xor %r12d, %r12d
+ xor %r13d, %r13d
+ xor %r14d, %r14d
+ xor %r15d, %r15d
.endm
#define LOAD_ONE_REG(reg, compat) \
@@ -317,10 +317,10 @@ static always_inline void stac(void)
movq UREGS_r13(%rsp), %r13
movq UREGS_r12(%rsp), %r12
.else
- xor %r15, %r15
- xor %r14, %r14
- xor %r13, %r13
- xor %r12, %r12
+ xor %r15d, %r15d
+ xor %r14d, %r14d
+ xor %r13d, %r13d
+ xor %r12d, %r12d
.endif
LOAD_ONE_REG(bp, \compat)
LOAD_ONE_REG(bx, \compat)
@@ -330,10 +330,10 @@ static always_inline void stac(void)
movq UREGS_r9(%rsp),%r9
movq UREGS_r8(%rsp),%r8
.else
- xor %r11, %r11
- xor %r10, %r10
- xor %r9, %r9
- xor %r8, %r8
+ xor %r11d, %r11d
+ xor %r10d, %r10d
+ xor %r9d, %r9d
+ xor %r8d, %r8d
.endif
LOAD_ONE_REG(ax, \compat)
LOAD_ONE_REG(cx, \compat)
--
2.1.4
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
