crypto: aesni - Use TEST %reg,%reg instead of CMP $0,%reg

CMP $0,%reg can't set overflow flag, so we can use shorter TEST %reg,%reg
instruction when only zero and sign flags are checked (E,L,LE,G,GE conditions).

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 1852b19..d1436c3 100644 (file)
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -318,7 +318,7 @@ _initial_blocks_\@:
 
        # Main loop - Encrypt/Decrypt remaining blocks
 
-       cmp     $0, %r13
+       test    %r13, %r13
        je      _zero_cipher_left_\@
        sub     $64, %r13
        je      _four_cipher_left_\@
@@ -437,7 +437,7 @@ _multiple_of_16_bytes_\@:
 
        mov PBlockLen(%arg2), %r12
 
-       cmp $0, %r12
+       test %r12, %r12
        je _partial_done\@
 
        GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
@@ -474,7 +474,7 @@ _T_8_\@:
        add     $8, %r10
        sub     $8, %r11
        psrldq  $8, %xmm0
-       cmp     $0, %r11
+       test    %r11, %r11
        je      _return_T_done_\@
 _T_4_\@:
        movd    %xmm0, %eax
@@ -482,7 +482,7 @@ _T_4_\@:
        add     $4, %r10
        sub     $4, %r11
        psrldq  $4, %xmm0
-       cmp     $0, %r11
+       test    %r11, %r11
        je      _return_T_done_\@
 _T_123_\@:
        movd    %xmm0, %eax
@@ -619,7 +619,7 @@ _get_AAD_blocks\@:
 
        /* read the last <16B of AAD */
 _get_AAD_rest\@:
-       cmp        $0, %r11
+       test       %r11, %r11
        je         _get_AAD_done\@
 
        READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7
@@ -640,7 +640,7 @@ _get_AAD_done\@:
 .macro PARTIAL_BLOCK CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
        AAD_HASH operation
        mov     PBlockLen(%arg2), %r13
-       cmp     $0, %r13
+       test    %r13, %r13
        je      _partial_block_done_\@  # Leave Macro if no partial blocks
        # Read in input data without over reading
        cmp     $16, \PLAIN_CYPH_LEN
@@ -692,7 +692,7 @@ _no_extra_mask_1_\@:
        pshufb  %xmm2, %xmm3
        pxor    %xmm3, \AAD_HASH
 
-       cmp     $0, %r10
+       test    %r10, %r10
        jl      _partial_incomplete_1_\@
 
        # GHASH computation for the last <16 Byte block
@@ -727,7 +727,7 @@ _no_extra_mask_2_\@:
        pshufb  %xmm2, %xmm9
        pxor    %xmm9, \AAD_HASH
 
-       cmp     $0, %r10
+       test    %r10, %r10
        jl      _partial_incomplete_2_\@
 
        # GHASH computation for the last <16 Byte block
@@ -747,7 +747,7 @@ _encode_done_\@:
        pshufb  %xmm2, %xmm9
 .endif
        # output encrypted Bytes
-       cmp     $0, %r10
+       test    %r10, %r10
        jl      _partial_fill_\@
        mov     %r13, %r12
        mov     $16, %r13
@@ -2720,7 +2720,7 @@ SYM_FUNC_END(aesni_ctr_enc)
  */
 SYM_FUNC_START(aesni_xts_crypt8)
        FRAME_BEGIN
-       cmpb $0, %cl
+       testb %cl, %cl
        movl $0, %ecx
        movl $240, %r10d
        leaq _aesni_enc4, %r11

diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 5fee479..2cf8e94 100644 (file)
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -369,7 +369,7 @@ _initial_num_blocks_is_0\@:
 
 
 _initial_blocks_encrypted\@:
-        cmp     $0, %r13
+        test    %r13, %r13
         je      _zero_cipher_left\@
 
         sub     $128, %r13
@@ -528,7 +528,7 @@ _multiple_of_16_bytes\@:
         vmovdqu HashKey(arg2), %xmm13
 
         mov PBlockLen(arg2), %r12
-        cmp $0, %r12
+        test %r12, %r12
         je _partial_done\@
 
        #GHASH computation for the last <16 Byte block
@@ -573,7 +573,7 @@ _T_8\@:
         add     $8, %r10
         sub     $8, %r11
         vpsrldq $8, %xmm9, %xmm9
-        cmp     $0, %r11
+        test    %r11, %r11
         je     _return_T_done\@
 _T_4\@:
         vmovd   %xmm9, %eax
@@ -581,7 +581,7 @@ _T_4\@:
         add     $4, %r10
         sub     $4, %r11
         vpsrldq     $4, %xmm9, %xmm9
-        cmp     $0, %r11
+        test    %r11, %r11
         je     _return_T_done\@
 _T_123\@:
         vmovd     %xmm9, %eax
@@ -625,7 +625,7 @@ _get_AAD_blocks\@:
        cmp     $16, %r11
        jge     _get_AAD_blocks\@
        vmovdqu \T8, \T7
-       cmp     $0, %r11
+       test    %r11, %r11
        je      _get_AAD_done\@
 
        vpxor   \T7, \T7, \T7
@@ -644,7 +644,7 @@ _get_AAD_rest8\@:
        vpxor   \T1, \T7, \T7
        jmp     _get_AAD_rest8\@
 _get_AAD_rest4\@:
-       cmp     $0, %r11
+       test    %r11, %r11
        jle      _get_AAD_rest0\@
        mov     (%r10), %eax
        movq    %rax, \T1
@@ -749,7 +749,7 @@ _done_read_partial_block_\@:
 .macro PARTIAL_BLOCK GHASH_MUL CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
         AAD_HASH ENC_DEC
         mov    PBlockLen(arg2), %r13
-        cmp    $0, %r13
+        test   %r13, %r13
         je     _partial_block_done_\@  # Leave Macro if no partial blocks
         # Read in input data without over reading
         cmp    $16, \PLAIN_CYPH_LEN
@@ -801,7 +801,7 @@ _no_extra_mask_1_\@:
         vpshufb        %xmm2, %xmm3, %xmm3
         vpxor  %xmm3, \AAD_HASH, \AAD_HASH
 
-        cmp    $0, %r10
+        test   %r10, %r10
         jl     _partial_incomplete_1_\@
 
         # GHASH computation for the last <16 Byte block
@@ -836,7 +836,7 @@ _no_extra_mask_2_\@:
         vpshufb %xmm2, %xmm9, %xmm9
         vpxor  %xmm9, \AAD_HASH, \AAD_HASH
 
-        cmp    $0, %r10
+        test   %r10, %r10
         jl     _partial_incomplete_2_\@
 
         # GHASH computation for the last <16 Byte block
@@ -856,7 +856,7 @@ _encode_done_\@:
         vpshufb        %xmm2, %xmm9, %xmm9
 .endif
         # output encrypted Bytes
-        cmp    $0, %r10
+        test   %r10, %r10
         jl     _partial_fill_\@
         mov    %r13, %r12
         mov    $16, %r13