[PATCH v2] x86-64: use 32-bit XOR to zero registers

From: Jan Beulich
Date: Mon Jul 02 2018 - 06:32:07 EST

Some Intel CPUs don't recognize 64-bit XORs as zeroing idioms. Zeroing
idioms don't require execution bandwidth, as they're being taken care
of in the frontend (through register renaming). Use 32-bit XORs instead.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
v2: Explain what zeroing idioms are/do in the description.
---
arch/x86/crypto/aegis128-aesni-asm.S | 2 +-
arch/x86/crypto/aegis128l-aesni-asm.S | 2 +-
arch/x86/crypto/aegis256-aesni-asm.S | 2 +-
arch/x86/crypto/aesni-intel_asm.S | 8 ++++----
arch/x86/crypto/aesni-intel_avx-x86_64.S | 4 ++--
arch/x86/crypto/morus1280-avx2-asm.S | 2 +-
arch/x86/crypto/morus1280-sse2-asm.S | 2 +-
arch/x86/crypto/morus640-sse2-asm.S | 2 +-
arch/x86/crypto/sha1_ssse3_asm.S | 2 +-
arch/x86/kernel/head_64.S | 2 +-
arch/x86/kernel/paravirt_patch_64.c | 2 +-
arch/x86/lib/memcpy_64.S | 2 +-
arch/x86/power/hibernate_asm_64.S | 2 +-
13 files changed, 17 insertions(+), 17 deletions(-)

--- 4.18-rc3/arch/x86/crypto/aegis128-aesni-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/aegis128-aesni-asm.S
@@ -75,7 +75,7 @@
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG

mov LEN, %r8
--- 4.18-rc3/arch/x86/crypto/aegis128l-aesni-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -66,7 +66,7 @@
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG0, MSG0
pxor MSG1, MSG1

--- 4.18-rc3/arch/x86/crypto/aegis256-aesni-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/aegis256-aesni-asm.S
@@ -59,7 +59,7 @@
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG

mov LEN, %r8
--- 4.18-rc3/arch/x86/crypto/aesni-intel_asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/aesni-intel_asm.S
@@ -258,7 +258,7 @@ ALL_F: .octa 0xffffffffffffffffffff
.macro GCM_INIT Iv SUBKEY AAD AADLEN
mov \AADLEN, %r11
mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
- xor %r11, %r11
+ xor %r11d, %r11d
mov %r11, InLen(%arg2) # ctx_data.in_length = 0
mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
@@ -286,7 +286,7 @@ ALL_F: .octa 0xffffffffffffffffffff
movdqu HashKey(%arg2), %xmm13
add %arg5, InLen(%arg2)

- xor %r11, %r11 # initialise the data pointer offset as zero
+ xor %r11d, %r11d # initialise the data pointer offset as zero
PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation

sub %r11, %arg5 # sub partial block data used
@@ -702,7 +702,7 @@ _no_extra_mask_1_\@:

# GHASH computation for the last <16 Byte block
GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %rax,%rax
+ xor %eax, %eax

mov %rax, PBlockLen(%arg2)
jmp _dec_done_\@
@@ -737,7 +737,7 @@ _no_extra_mask_2_\@:

# GHASH computation for the last <16 Byte block
GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %rax,%rax
+ xor %eax, %eax

mov %rax, PBlockLen(%arg2)
jmp _encode_done_\@
--- 4.18-rc3/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -463,7 +463,7 @@ _get_AAD_rest_final\@:

_get_AAD_done\@:
# initialize the data pointer offset as zero
- xor %r11, %r11
+ xor %r11d, %r11d

# start AES for num_initial_blocks blocks
mov arg5, %rax # rax = *Y0
@@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@:

_get_AAD_done\@:
# initialize the data pointer offset as zero
- xor %r11, %r11
+ xor %r11d, %r11d

# start AES for num_initial_blocks blocks
mov arg5, %rax # rax = *Y0
--- 4.18-rc3/arch/x86/crypto/morus1280-avx2-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/morus1280-avx2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero)
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
vpxor MSG, MSG, MSG

mov %rcx, %r8
--- 4.18-rc3/arch/x86/crypto/morus1280-sse2-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/morus1280-sse2-asm.S
@@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero)
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG_LO, MSG_LO
pxor MSG_HI, MSG_HI

--- 4.18-rc3/arch/x86/crypto/morus640-sse2-asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/morus640-sse2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero)
* %r9
*/
__load_partial:
- xor %r9, %r9
+ xor %r9d, %r9d
pxor MSG, MSG

mov %rcx, %r8
--- 4.18-rc3/arch/x86/crypto/sha1_ssse3_asm.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/crypto/sha1_ssse3_asm.S
@@ -96,7 +96,7 @@
# cleanup workspace
mov $8, %ecx
mov %rsp, %rdi
- xor %rax, %rax
+ xor %eax, %eax
rep stosq

mov %rbp, %rsp # deallocate workspace
--- 4.18-rc3/arch/x86/kernel/head_64.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/kernel/head_64.S
@@ -235,7 +235,7 @@ ENTRY(secondary_startup_64)
* address given in m16:64.
*/
pushq $.Lafter_lret # put return address on stack for unwinder
- xorq %rbp, %rbp # clear frame pointer
+ xorl %ebp, %ebp # clear frame pointer
movq initial_code(%rip), %rax
pushq $__KERNEL_CS # set correct cs
pushq %rax # target address in negative space
--- 4.18-rc3/arch/x86/kernel/paravirt_patch_64.c
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/kernel/paravirt_patch_64.c
@@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");

#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
#endif

unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
--- 4.18-rc3/arch/x86/lib/memcpy_64.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/lib/memcpy_64.S
@@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe)

/* Copy successful. Return zero */
.L_done_memcpy_trap:
- xorq %rax, %rax
+ xorl %eax, %eax
ret
ENDPROC(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
--- 4.18-rc3/arch/x86/power/hibernate_asm_64.S
+++ 4.18-rc3-x86_64-32bit-XOR/arch/x86/power/hibernate_asm_64.S
@@ -137,7 +137,7 @@ ENTRY(restore_registers)
/* Saved in save_processor_state. */
lgdt saved_context_gdt_desc(%rax)

- xorq %rax, %rax
+ xorl %eax, %eax

/* tell the hibernation core that we've just restored the memory */
movq %rax, in_suspend(%rip)