accelerated: Re-generate assembly sources

Re-generate assembly sources from the updated openssl submodule.

Signed-off-by: Anderson Toshiyuki Sasaki <ansasaki@redhat.com>

diff --git a/lib/accelerated/aarch64/elf/aes-aarch64.s b/lib/accelerated/aarch64/elf/aes-aarch64.s
index ab227a8c147c9fb97f197b3806ef45c39b9396f8..b9b4b4b6e4cd94e8fb260ddfdca34a55753b92a2 100644 (file)
--- a/lib/accelerated/aarch64/elf/aes-aarch64.s
+++ b/lib/accelerated/aarch64/elf/aes-aarch64.s
@@ -147,7 +147,12 @@ aes_v8_set_encrypt_key:
 .Loop192:
  tbl v6.16b,{v4.16b},v2.16b
  ext v5.16b,v0.16b,v3.16b,#12
+
+
+
+
  st1 {v4.8b},[x2],#8
+
  aese v6.16b,v0.16b
  subs w1,w1,#1
 
@@ -618,6 +623,9 @@ aes_v8_ctr32_encrypt_blocks:
  ldr w5,[x3,#240]
 
  ldr w8, [x4, #12]
+
+
+
  ld1 {v0.4s},[x4]
 
  ld1 {v16.4s,v17.4s},[x3]

diff --git a/lib/accelerated/aarch64/elf/sha1-armv8.s b/lib/accelerated/aarch64/elf/sha1-armv8.s
index 4b65cf6ea8280058ae503ec29dc6004367e76dd6..0de5de02f25af2ccd1cbe059dfbff3aacf2c4506 100644 (file)
--- a/lib/accelerated/aarch64/elf/sha1-armv8.s
+++ b/lib/accelerated/aarch64/elf/sha1-armv8.s
@@ -47,6 +47,7 @@
 .text
 
 
+.hidden _gnutls_arm_cpuid_s
 .globl sha1_block_data_order
 .type sha1_block_data_order,%function
 .align 6
@@ -1262,5 +1263,4 @@ sha1_block_armv8:
 .byte 83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align 2
 .align 2
-.comm _gnutls_arm_cpuid_s,4,4
 .section .note.GNU-stack,"",%progbits

diff --git a/lib/accelerated/aarch64/elf/sha256-armv8.s b/lib/accelerated/aarch64/elf/sha256-armv8.s
index bc3f146c6853eecc4f8a4fc5cbf3d2b83ee277d1..2d13b5e4276b61884825085321c3882ae2a88286 100644 (file)
--- a/lib/accelerated/aarch64/elf/sha256-armv8.s
+++ b/lib/accelerated/aarch64/elf/sha256-armv8.s
@@ -49,6 +49,7 @@
 .text
 
 
+.hidden _gnutls_arm_cpuid_s
 .globl sha256_block_data_order
 .type sha256_block_data_order,%function
 .align 6
@@ -2050,6 +2051,4 @@ sha256_block_neon:
  add sp,sp,#16*4+16
  ret
 .size sha256_block_neon,.-sha256_block_neon
-
-.comm _gnutls_arm_cpuid_s,4,4
 .section .note.GNU-stack,"",%progbits

diff --git a/lib/accelerated/aarch64/elf/sha512-armv8.s b/lib/accelerated/aarch64/elf/sha512-armv8.s
index b036c2a121560ebad92311d3890d4a3fae30d640..13384fc827488ef69e32e265f254198e51694a56 100644 (file)
--- a/lib/accelerated/aarch64/elf/sha512-armv8.s
+++ b/lib/accelerated/aarch64/elf/sha512-armv8.s
@@ -49,6 +49,7 @@
 .text
 
 
+.hidden _gnutls_arm_cpuid_s
 .globl sha512_block_data_order
 .type sha512_block_data_order,%function
 .align 6
@@ -1604,7 +1605,4 @@ sha512_block_armv8:
  ldr x29,[sp],#16
  ret
 .size sha512_block_armv8,.-sha512_block_armv8
-
-
-.comm _gnutls_arm_cpuid_s,4,4
 .section .note.GNU-stack,"",%progbits

diff --git a/lib/accelerated/aarch64/macosx/aes-aarch64.s b/lib/accelerated/aarch64/macosx/aes-aarch64.s
index 7acabf3f255b2925d237c2bac4f247f7892e8a35..4b55f88071acc38b1dcba49baf846073349945a6 100644 (file)
--- a/lib/accelerated/aarch64/macosx/aes-aarch64.s
+++ b/lib/accelerated/aarch64/macosx/aes-aarch64.s
@@ -147,7 +147,12 @@ L192:
 Loop192:
  tbl v6.16b,{v4.16b},v2.16b
  ext v5.16b,v0.16b,v3.16b,#12
+
+
+
+
  st1 {v4.8b},[x2],#8
+
  aese v6.16b,v0.16b
  subs w1,w1,#1
 
@@ -618,6 +623,9 @@ _aes_v8_ctr32_encrypt_blocks:
  ldr w5,[x3,#240]
 
  ldr w8, [x4, #12]
+
+
+
  ld1 {v0.4s},[x4]
 
  ld1 {v16.4s,v17.4s},[x3]

diff --git a/lib/accelerated/aarch64/macosx/sha1-armv8.s b/lib/accelerated/aarch64/macosx/sha1-armv8.s
index 8e1e12edf600cc21d1c8250a0659e4087521dd6c..9b2bdf2d85cadc38c65c237e13281d6f7544164c 100644 (file)
--- a/lib/accelerated/aarch64/macosx/sha1-armv8.s
+++ b/lib/accelerated/aarch64/macosx/sha1-armv8.s
@@ -47,6 +47,7 @@
 .text
 
 
+.private_extern __gnutls_arm_cpuid_s
 .globl _sha1_block_data_order
 
 .align 6
@@ -1262,4 +1263,3 @@ L_gnutls_arm_cpuid_s:
 .byte 83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align 2
 .align 2
-.comm __gnutls_arm_cpuid_s,4,4

diff --git a/lib/accelerated/aarch64/macosx/sha256-armv8.s b/lib/accelerated/aarch64/macosx/sha256-armv8.s
index fc6424975ccbcf9b39eabc64dc876a62257c6a34..3ee6befc664a8172bc0157827a2621a97476c4bd 100644 (file)
--- a/lib/accelerated/aarch64/macosx/sha256-armv8.s
+++ b/lib/accelerated/aarch64/macosx/sha256-armv8.s
@@ -49,6 +49,7 @@
 .text
 
 
+.private_extern __gnutls_arm_cpuid_s
 .globl _sha256_block_data_order
 
 .align 6
@@ -2049,6 +2050,3 @@ L_00_48:
  ldr x29,[x29]
  add sp,sp,#16*4+16
  ret
-
-
-.comm __gnutls_arm_cpuid_s,4,4

diff --git a/lib/accelerated/aarch64/macosx/sha512-armv8.s b/lib/accelerated/aarch64/macosx/sha512-armv8.s
index 43af71fa48c3279700fe8dfa3e498e5e03726855..8c3abda83bd9f7ecc101c2f918b3134f8fcaf686 100644 (file)
--- a/lib/accelerated/aarch64/macosx/sha512-armv8.s
+++ b/lib/accelerated/aarch64/macosx/sha512-armv8.s
@@ -49,6 +49,7 @@
 .text
 
 
+.private_extern __gnutls_arm_cpuid_s
 .globl _sha512_block_data_order
 
 .align 6
@@ -1603,7 +1604,3 @@ Loop_hw:
 
  ldr x29,[sp],#16
  ret
-
-
-
-.comm __gnutls_arm_cpuid_s,4,4

diff --git a/lib/accelerated/x86/coff/aesni-gcm-x86_64.s b/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
index 7988004cb04b90e3f14005b7e3c7939c3c768759..ab4e37c0432ab891398a03a49ab2ecfd49b1463f 100644 (file)
--- a/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
@@ -42,6 +42,7 @@
 .def   _aesni_ctr32_ghash_6x;  .scl 3; .type 32;       .endef
 .p2align       5
 _aesni_ctr32_ghash_6x:
+
        vmovdqu 32(%r11),%xmm2
        subq    $6,%rdx
        vpxor   %xmm4,%xmm4,%xmm4
@@ -350,6 +351,7 @@ _aesni_ctr32_ghash_6x:
 
        .byte   0xf3,0xc3
 
+
 .globl aesni_gcm_decrypt
 .def   aesni_gcm_decrypt;      .scl 2; .type 32;       .endef
 .p2align       5
@@ -490,6 +492,7 @@ aesni_gcm_decrypt:
 .def   _aesni_ctr32_6x;        .scl 3; .type 32;       .endef
 .p2align       5
 _aesni_ctr32_6x:
+
        vmovdqu 0-128(%rcx),%xmm4
        vmovdqu 32(%r11),%xmm2
        leaq    -1(%rbp),%r13
@@ -578,6 +581,7 @@ _aesni_ctr32_6x:
        jmp     .Loop_ctr32
 
 
+
 .globl aesni_gcm_encrypt
 .def   aesni_gcm_encrypt;      .scl 2; .type 32;       .endef
 .p2align       5

diff --git a/lib/accelerated/x86/coff/aesni-x86_64.s b/lib/accelerated/x86/coff/aesni-x86_64.s
index 4e8de065f21a54d6c15303155e1fbedcf82cc814..3a07713e4e84d95626e863f03c3fe7deb37d36a2 100644 (file)
--- a/lib/accelerated/x86/coff/aesni-x86_64.s
+++ b/lib/accelerated/x86/coff/aesni-x86_64.s
@@ -939,6 +939,7 @@ aesni_ccm64_encrypt_blocks:
        movq    40(%rsp),%r8
        movq    48(%rsp),%r9
 
+
        leaq    -88(%rsp),%rsp
        movaps  %xmm6,(%rsp)
        movaps  %xmm7,16(%rsp)
@@ -1015,6 +1016,7 @@ aesni_ccm64_encrypt_blocks:
        movq    8(%rsp),%rdi
        movq    16(%rsp),%rsi
        .byte   0xf3,0xc3
+
 .LSEH_end_aesni_ccm64_encrypt_blocks:
 .globl aesni_ccm64_decrypt_blocks
 .def   aesni_ccm64_decrypt_blocks;     .scl 2; .type 32;       .endef
@@ -1031,6 +1033,7 @@ aesni_ccm64_decrypt_blocks:
        movq    40(%rsp),%r8
        movq    48(%rsp),%r9
 
+
        leaq    -88(%rsp),%rsp
        movaps  %xmm6,(%rsp)
        movaps  %xmm7,16(%rsp)
@@ -1141,6 +1144,7 @@ aesni_ccm64_decrypt_blocks:
        movq    8(%rsp),%rdi
        movq    16(%rsp),%rsi
        .byte   0xf3,0xc3
+
 .LSEH_end_aesni_ccm64_decrypt_blocks:
 .globl aesni_ctr32_encrypt_blocks
 .def   aesni_ctr32_encrypt_blocks;     .scl 2; .type 32;       .endef
@@ -3046,6 +3050,7 @@ aesni_ocb_encrypt:
 .def   __ocb_encrypt6; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_encrypt6:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3145,9 +3150,11 @@ __ocb_encrypt6:
        .byte   0xf3,0xc3
 
 
+
 .def   __ocb_encrypt4; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_encrypt4:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3214,9 +3221,11 @@ __ocb_encrypt4:
        .byte   0xf3,0xc3
 
 
+
 .def   __ocb_encrypt1; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_encrypt1:
+
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm2,%xmm8
@@ -3249,6 +3258,7 @@ __ocb_encrypt1:
        .byte   0xf3,0xc3
 
 
+
 .globl aesni_ocb_decrypt
 .def   aesni_ocb_decrypt;      .scl 2; .type 32;       .endef
 .p2align       5
@@ -3519,6 +3529,7 @@ aesni_ocb_decrypt:
 .def   __ocb_decrypt6; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_decrypt6:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3612,9 +3623,11 @@ __ocb_decrypt6:
        .byte   0xf3,0xc3
 
 
+
 .def   __ocb_decrypt4; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_decrypt4:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3677,9 +3690,11 @@ __ocb_decrypt4:
        .byte   0xf3,0xc3
 
 
+
 .def   __ocb_decrypt1; .scl 3; .type 32;       .endef
 .p2align       5
 __ocb_decrypt1:
+
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm7,%xmm2
@@ -3710,6 +3725,7 @@ __ocb_decrypt1:
 .byte  102,15,56,223,215
        .byte   0xf3,0xc3
 
+
 .globl aesni_cbc_encrypt
 .def   aesni_cbc_encrypt;      .scl 2; .type 32;       .endef
 .p2align       4
@@ -4687,7 +4703,6 @@ __aesni_set_encrypt_key:
        addq    $8,%rsp
 
        .byte   0xf3,0xc3
-
 .LSEH_end_set_encrypt_key:
 
 .p2align       4
@@ -4760,6 +4775,7 @@ __aesni_set_encrypt_key:
        .byte   0xf3,0xc3
 
 
+
 .p2align       6
 .Lbswap_mask:
 .byte  15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0

diff --git a/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
index cdfc88254ef0a6f92ff5f60727c7e51ae4f23e5b..79f841f1ac0cb7ad6802c6a4537c764109962b96 100644 (file)
--- a/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
@@ -1490,10 +1490,10 @@ _shaext_shortcut:
        movaps  -8-16(%rax),%xmm9
        movq    %rax,%rsp
 .Lepilogue_shaext:
-
        movq    8(%rsp),%rdi
        movq    16(%rsp),%rsi
        .byte   0xf3,0xc3
+
 .LSEH_end_sha1_block_data_order_shaext:
 .def   sha1_block_data_order_ssse3;    .scl 3; .type 32;       .endef
 .p2align       4

diff --git a/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
index d2fc1957eae8f3c9d48b88580db1ce97f55e10ae..78fae2a6239253d61d5e9762e38687c9dd69a31b 100644 (file)
--- a/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
@@ -1832,6 +1832,7 @@ sha256_block_data_order_shaext:
        movq    %r8,%rdx
 
 _shaext_shortcut:
+
        leaq    -88(%rsp),%rsp
        movaps  %xmm6,-8-80(%rax)
        movaps  %xmm7,-8-64(%rax)
@@ -2050,6 +2051,7 @@ _shaext_shortcut:
        movq    8(%rsp),%rdi
        movq    16(%rsp),%rsi
        .byte   0xf3,0xc3
+
 .LSEH_end_sha256_block_data_order_shaext:
 .def   sha256_block_data_order_ssse3;  .scl 3; .type 32;       .endef
 .p2align       6
@@ -5501,6 +5503,8 @@ sha256_block_data_order_avx2:
 
        leaq    448(%rsp),%rsp
 
+
+
        addl    0(%rdi),%eax
        addl    4(%rdi),%ebx
        addl    8(%rdi),%ecx
@@ -5526,15 +5530,17 @@ sha256_block_data_order_avx2:
        jbe     .Loop_avx2
        leaq    (%rsp),%rbp
 
+
+
+
 .Ldone_avx2:
-       leaq    (%rbp),%rsp
-       movq    88(%rsp),%rsi
+       movq    88(%rbp),%rsi
 
        vzeroupper
-       movaps  64+32(%rsp),%xmm6
-       movaps  64+48(%rsp),%xmm7
-       movaps  64+64(%rsp),%xmm8
-       movaps  64+80(%rsp),%xmm9
+       movaps  64+32(%rbp),%xmm6
+       movaps  64+48(%rbp),%xmm7
+       movaps  64+64(%rbp),%xmm8
+       movaps  64+80(%rbp),%xmm9
        movq    -48(%rsi),%r15
 
        movq    -40(%rsi),%r14

diff --git a/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
index 419fa2a9803366509b8b36e1a85f6810d3565a0c..836e0cf66e48b173b9bb02682756d0b8f8586c6b 100644 (file)
--- a/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
@@ -5494,6 +5494,8 @@ sha512_block_data_order_avx2:
 
        leaq    1152(%rsp),%rsp
 
+
+
        addq    0(%rdi),%rax
        addq    8(%rdi),%rbx
        addq    16(%rdi),%rcx
@@ -5519,17 +5521,19 @@ sha512_block_data_order_avx2:
        jbe     .Loop_avx2
        leaq    (%rsp),%rbp
 
+
+
+
 .Ldone_avx2:
-       leaq    (%rbp),%rsp
-       movq    152(%rsp),%rsi
+       movq    152(%rbp),%rsi
 
        vzeroupper
-       movaps  128+32(%rsp),%xmm6
-       movaps  128+48(%rsp),%xmm7
-       movaps  128+64(%rsp),%xmm8
-       movaps  128+80(%rsp),%xmm9
-       movaps  128+96(%rsp),%xmm10
-       movaps  128+112(%rsp),%xmm11
+       movaps  128+32(%rbp),%xmm6
+       movaps  128+48(%rbp),%xmm7
+       movaps  128+64(%rbp),%xmm8
+       movaps  128+80(%rbp),%xmm9
+       movaps  128+96(%rbp),%xmm10
+       movaps  128+112(%rbp),%xmm11
        movq    -48(%rsi),%r15
 
        movq    -40(%rsi),%r14

diff --git a/lib/accelerated/x86/elf/aesni-gcm-x86_64.s b/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
index e26d18d69fa1bbeb24b1503d0c3e8127a32f49a4..461dd026b96a82ee96f7e25a1697b7d4604b4598 100644 (file)
--- a/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
@@ -42,6 +42,7 @@
 .type  _aesni_ctr32_ghash_6x,@function
 .align 32
 _aesni_ctr32_ghash_6x:
+.cfi_startproc 
        vmovdqu 32(%r11),%xmm2
        subq    $6,%rdx
        vpxor   %xmm4,%xmm4,%xmm4
@@ -349,6 +350,7 @@ _aesni_ctr32_ghash_6x:
        vpxor   %xmm4,%xmm8,%xmm8
 
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  _aesni_ctr32_ghash_6x,.-_aesni_ctr32_ghash_6x
 .globl aesni_gcm_decrypt
 .type  aesni_gcm_decrypt,@function
@@ -455,6 +457,7 @@ aesni_gcm_decrypt:
 .type  _aesni_ctr32_6x,@function
 .align 32
 _aesni_ctr32_6x:
+.cfi_startproc 
        vmovdqu 0-128(%rcx),%xmm4
        vmovdqu 32(%r11),%xmm2
        leaq    -1(%rbp),%r13
@@ -541,6 +544,7 @@ _aesni_ctr32_6x:
        vpshufb %xmm0,%xmm1,%xmm1
        vpxor   %xmm4,%xmm14,%xmm14
        jmp     .Loop_ctr32
+.cfi_endproc   
 .size  _aesni_ctr32_6x,.-_aesni_ctr32_6x
 
 .globl aesni_gcm_encrypt

diff --git a/lib/accelerated/x86/elf/aesni-x86_64.s b/lib/accelerated/x86/elf/aesni-x86_64.s
index 43cf4e68defaae6b23414d70537a2ff3aa7314a4..acc7c2c55502ae887f1524c450ab7440fde08cc8 100644 (file)
--- a/lib/accelerated/x86/elf/aesni-x86_64.s
+++ b/lib/accelerated/x86/elf/aesni-x86_64.s
@@ -900,6 +900,7 @@ aesni_ecb_encrypt:
 .type  aesni_ccm64_encrypt_blocks,@function
 .align 16
 aesni_ccm64_encrypt_blocks:
+.cfi_startproc 
        movl    240(%rcx),%eax
        movdqu  (%r8),%xmm6
        movdqa  .Lincrement64(%rip),%xmm9
@@ -958,11 +959,13 @@ aesni_ccm64_encrypt_blocks:
        pxor    %xmm8,%xmm8
        pxor    %xmm6,%xmm6
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  aesni_ccm64_encrypt_blocks,.-aesni_ccm64_encrypt_blocks
 .globl aesni_ccm64_decrypt_blocks
 .type  aesni_ccm64_decrypt_blocks,@function
 .align 16
 aesni_ccm64_decrypt_blocks:
+.cfi_startproc 
        movl    240(%rcx),%eax
        movups  (%r8),%xmm6
        movdqu  (%r9),%xmm3
@@ -1055,6 +1058,7 @@ aesni_ccm64_decrypt_blocks:
        pxor    %xmm8,%xmm8
        pxor    %xmm6,%xmm6
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  aesni_ccm64_decrypt_blocks,.-aesni_ccm64_decrypt_blocks
 .globl aesni_ctr32_encrypt_blocks
 .type  aesni_ctr32_encrypt_blocks,@function
@@ -2829,6 +2833,7 @@ aesni_ocb_encrypt:
 .type  __ocb_encrypt6,@function
 .align 32
 __ocb_encrypt6:
+.cfi_startproc 
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -2926,11 +2931,13 @@ __ocb_encrypt6:
 .byte  102,65,15,56,221,246
 .byte  102,65,15,56,221,255
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_encrypt6,.-__ocb_encrypt6
 
 .type  __ocb_encrypt4,@function
 .align 32
 __ocb_encrypt4:
+.cfi_startproc 
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -2995,11 +3002,13 @@ __ocb_encrypt4:
 .byte  102,65,15,56,221,228
 .byte  102,65,15,56,221,237
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_encrypt4,.-__ocb_encrypt4
 
 .type  __ocb_encrypt1,@function
 .align 32
 __ocb_encrypt1:
+.cfi_startproc 
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm2,%xmm8
@@ -3030,6 +3039,7 @@ __ocb_encrypt1:
 
 .byte  102,15,56,221,215
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_encrypt1,.-__ocb_encrypt1
 
 .globl aesni_ocb_decrypt
@@ -3272,6 +3282,7 @@ aesni_ocb_decrypt:
 .type  __ocb_decrypt6,@function
 .align 32
 __ocb_decrypt6:
+.cfi_startproc 
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3363,11 +3374,13 @@ __ocb_decrypt6:
 .byte  102,65,15,56,223,246
 .byte  102,65,15,56,223,255
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_decrypt6,.-__ocb_decrypt6
 
 .type  __ocb_decrypt4,@function
 .align 32
 __ocb_decrypt4:
+.cfi_startproc 
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3428,11 +3441,13 @@ __ocb_decrypt4:
 .byte  102,65,15,56,223,228
 .byte  102,65,15,56,223,237
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_decrypt4,.-__ocb_decrypt4
 
 .type  __ocb_decrypt1,@function
 .align 32
 __ocb_decrypt1:
+.cfi_startproc 
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm7,%xmm2
@@ -3462,6 +3477,7 @@ __ocb_decrypt1:
 
 .byte  102,15,56,223,215
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  __ocb_decrypt1,.-__ocb_decrypt1
 .globl aesni_cbc_encrypt
 .type  aesni_cbc_encrypt,@function
@@ -4400,7 +4416,6 @@ __aesni_set_encrypt_key:
        addq    $8,%rsp
 .cfi_adjust_cfa_offset -8
        .byte   0xf3,0xc3
-.cfi_endproc   
 .LSEH_end_set_encrypt_key:
 
 .align 16
@@ -4471,6 +4486,7 @@ __aesni_set_encrypt_key:
        shufps  $170,%xmm1,%xmm1
        xorps   %xmm1,%xmm2
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  aesni_set_encrypt_key,.-aesni_set_encrypt_key
 .size  __aesni_set_encrypt_key,.-__aesni_set_encrypt_key
 .align 64

diff --git a/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
index 1e6546e11e60fef80add577a2211e484cfd99ebf..d34f34497c3532969ec613835d77b972b4927f92 100644 (file)
--- a/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
@@ -1460,8 +1460,8 @@ _shaext_shortcut:
        pshufd  $27,%xmm1,%xmm1
        movdqu  %xmm0,(%rdi)
        movd    %xmm1,16(%rdi)
-.cfi_endproc   
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  sha1_block_data_order_shaext,.-sha1_block_data_order_shaext
 .type  sha1_block_data_order_ssse3,@function
 .align 16

diff --git a/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
index 4b08e0c85e55c16910838c1e6cb0edcb59e5ff30..d196c6a7935b3a0be09c5e536a93213ad3643f38 100644 (file)
--- a/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
@@ -1814,6 +1814,7 @@ K256:
 .align 64
 sha256_block_data_order_shaext:
 _shaext_shortcut:
+.cfi_startproc 
        leaq    K256+128(%rip),%rcx
        movdqu  (%rdi),%xmm1
        movdqu  16(%rdi),%xmm2
@@ -2016,6 +2017,7 @@ _shaext_shortcut:
        movdqu  %xmm1,(%rdi)
        movdqu  %xmm2,16(%rdi)
        .byte   0xf3,0xc3
+.cfi_endproc   
 .size  sha256_block_data_order_shaext,.-sha256_block_data_order_shaext
 .type  sha256_block_data_order_ssse3,@function
 .align 64
@@ -4277,7 +4279,15 @@ sha256_block_data_order_avx2:
        vmovdqa %ymm4,0(%rsp)
        xorl    %r14d,%r14d
        vmovdqa %ymm5,32(%rsp)
+
+       movq    88(%rsp),%rdi
+.cfi_def_cfa   %rdi,8
        leaq    -64(%rsp),%rsp
+
+
+
+       movq    %rdi,-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        movl    %ebx,%edi
        vmovdqa %ymm6,0(%rsp)
        xorl    %ecx,%edi
@@ -4289,6 +4299,12 @@ sha256_block_data_order_avx2:
 .align 16
 .Lavx2_00_47:
        leaq    -64(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x38,0x06,0x23,0x08
+
+       pushq   64-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+       leaq    8(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        vpalignr        $4,%ymm0,%ymm1,%ymm4
        addl    0+128(%rsp),%r11d
        andl    %r8d,%r12d
@@ -4544,6 +4560,12 @@ sha256_block_data_order_avx2:
        movl    %r9d,%r12d
        vmovdqa %ymm6,32(%rsp)
        leaq    -64(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x38,0x06,0x23,0x08
+
+       pushq   64-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+       leaq    8(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        vpalignr        $4,%ymm2,%ymm3,%ymm4
        addl    0+128(%rsp),%r11d
        andl    %r8d,%r12d
@@ -5419,6 +5441,8 @@ sha256_block_data_order_avx2:
 
        leaq    448(%rsp),%rsp
 
+.cfi_escape    0x0f,0x06,0x77,0xd8,0x00,0x06,0x23,0x08
+
        addl    0(%rdi),%eax
        addl    4(%rdi),%ebx
        addl    8(%rdi),%ecx
@@ -5444,9 +5468,11 @@ sha256_block_data_order_avx2:
        jbe     .Loop_avx2
        leaq    (%rsp),%rbp
 
+
+.cfi_escape    0x0f,0x06,0x76,0xd8,0x00,0x06,0x23,0x08
+
 .Ldone_avx2:
-       leaq    (%rbp),%rsp
-       movq    88(%rsp),%rsi
+       movq    88(%rbp),%rsi
 .cfi_def_cfa   %rsi,8
        vzeroupper
        movq    -48(%rsi),%r15

diff --git a/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
index e384d7e9e8337cf897be5ca677f1f3e87e8a52c8..446c06a3e65075401ab0483284e307f589b98e09 100644 (file)
--- a/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
@@ -4204,7 +4204,15 @@ sha512_block_data_order_avx2:
        vmovdqa %ymm10,64(%rsp)
        vpaddq  64(%rbp),%ymm6,%ymm10
        vmovdqa %ymm11,96(%rsp)
+
+       movq    152(%rsp),%rdi
+.cfi_def_cfa   %rdi,8
        leaq    -128(%rsp),%rsp
+
+
+
+       movq    %rdi,-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        vpaddq  96(%rbp),%ymm7,%ymm11
        vmovdqa %ymm8,0(%rsp)
        xorq    %r14,%r14
@@ -4220,6 +4228,12 @@ sha512_block_data_order_avx2:
 .align 16
 .Lavx2_00_47:
        leaq    -128(%rsp),%rsp
+.cfi_escape    0x0f,0x06,0x77,0xf8,0x00,0x06,0x23,0x08
+
+       pushq   128-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+       leaq    8(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        vpalignr        $8,%ymm0,%ymm1,%ymm8
        addq    0+256(%rsp),%r11
        andq    %r8,%r12
@@ -4513,6 +4527,12 @@ sha512_block_data_order_avx2:
        movq    %r9,%r12
        vmovdqa %ymm10,96(%rsp)
        leaq    -128(%rsp),%rsp
+.cfi_escape    0x0f,0x06,0x77,0xf8,0x00,0x06,0x23,0x08
+
+       pushq   128-8(%rsp)
+.cfi_escape    0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+       leaq    8(%rsp),%rsp
+.cfi_escape    0x0f,0x05,0x77,0x78,0x06,0x23,0x08
        vpalignr        $8,%ymm4,%ymm5,%ymm8
        addq    0+256(%rsp),%r11
        andq    %r8,%r12
@@ -5426,6 +5446,8 @@ sha512_block_data_order_avx2:
 
        leaq    1152(%rsp),%rsp
 
+.cfi_escape    0x0f,0x06,0x77,0x98,0x01,0x06,0x23,0x08
+
        addq    0(%rdi),%rax
        addq    8(%rdi),%rbx
        addq    16(%rdi),%rcx
@@ -5451,9 +5473,11 @@ sha512_block_data_order_avx2:
        jbe     .Loop_avx2
        leaq    (%rsp),%rbp
 
+
+.cfi_escape    0x0f,0x06,0x76,0x98,0x01,0x06,0x23,0x08
+
 .Ldone_avx2:
-       leaq    (%rbp),%rsp
-       movq    152(%rsp),%rsi
+       movq    152(%rbp),%rsi
 .cfi_def_cfa   %rsi,8
        vzeroupper
        movq    -48(%rsi),%r15

diff --git a/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s b/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
index d540930b5b2c3f01c0963e7c6ebe034be68a4e86..1d323b166aa494f9ee52c0d866233439e4f06b33 100644 (file)
--- a/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
@@ -42,6 +42,7 @@
 
 .p2align       5
 _aesni_ctr32_ghash_6x:
+
        vmovdqu 32(%r11),%xmm2
        subq    $6,%rdx
        vpxor   %xmm4,%xmm4,%xmm4
@@ -350,6 +351,7 @@ L$6x_done:
 
        .byte   0xf3,0xc3
 
+
 .globl _aesni_gcm_decrypt
 
 .p2align       5
@@ -455,6 +457,7 @@ L$gcm_dec_abort:
 
 .p2align       5
 _aesni_ctr32_6x:
+
        vmovdqu 0-128(%rcx),%xmm4
        vmovdqu 32(%r11),%xmm2
        leaq    -1(%rbp),%r13
@@ -543,6 +546,7 @@ L$handle_ctr32_2:
        jmp     L$oop_ctr32
 
 
+
 .globl _aesni_gcm_encrypt
 
 .p2align       5

diff --git a/lib/accelerated/x86/macosx/aesni-x86_64.s b/lib/accelerated/x86/macosx/aesni-x86_64.s
index f6145f166b5c928b3f9233fca2c2962421fe6ea0..3601d543861b82339ff41944df014353821fc9af 100644 (file)
--- a/lib/accelerated/x86/macosx/aesni-x86_64.s
+++ b/lib/accelerated/x86/macosx/aesni-x86_64.s
@@ -900,6 +900,7 @@ L$ecb_ret:
 
 .p2align       4
 _aesni_ccm64_encrypt_blocks:
+
        movl    240(%rcx),%eax
        movdqu  (%r8),%xmm6
        movdqa  L$increment64(%rip),%xmm9
@@ -959,10 +960,12 @@ L$ccm64_enc2_loop:
        pxor    %xmm6,%xmm6
        .byte   0xf3,0xc3
 
+
 .globl _aesni_ccm64_decrypt_blocks
 
 .p2align       4
 _aesni_ccm64_decrypt_blocks:
+
        movl    240(%rcx),%eax
        movups  (%r8),%xmm6
        movdqu  (%r9),%xmm3
@@ -1056,6 +1059,7 @@ L$oop_enc1_6:
        pxor    %xmm6,%xmm6
        .byte   0xf3,0xc3
 
+
 .globl _aesni_ctr32_encrypt_blocks
 
 .p2align       4
@@ -2824,6 +2828,7 @@ L$ocb_enc_epilogue:
 
 .p2align       5
 __ocb_encrypt6:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -2924,8 +2929,10 @@ L$ocb_enc_loop6:
 
 
 
+
 .p2align       5
 __ocb_encrypt4:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -2993,8 +3000,10 @@ L$ocb_enc_loop4:
 
 
 
+
 .p2align       5
 __ocb_encrypt1:
+
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm2,%xmm8
@@ -3027,6 +3036,7 @@ L$ocb_enc_loop1:
        .byte   0xf3,0xc3
 
 
+
 .globl _aesni_ocb_decrypt
 
 .p2align       5
@@ -3262,6 +3272,7 @@ L$ocb_dec_epilogue:
 
 .p2align       5
 __ocb_decrypt6:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3356,8 +3367,10 @@ L$ocb_dec_loop6:
 
 
 
+
 .p2align       5
 __ocb_decrypt4:
+
        pxor    %xmm9,%xmm15
        movdqu  (%rbx,%r12,1),%xmm11
        movdqa  %xmm10,%xmm12
@@ -3421,8 +3434,10 @@ L$ocb_dec_loop4:
 
 
 
+
 .p2align       5
 __ocb_decrypt1:
+
        pxor    %xmm15,%xmm7
        pxor    %xmm9,%xmm7
        pxor    %xmm7,%xmm2
@@ -3453,6 +3468,7 @@ L$ocb_dec_loop1:
 .byte  102,15,56,223,215
        .byte   0xf3,0xc3
 
+
 .globl _aesni_cbc_encrypt
 
 .p2align       4
@@ -4390,7 +4406,6 @@ L$enc_key_ret:
        addq    $8,%rsp
 
        .byte   0xf3,0xc3
-
 L$SEH_end_set_encrypt_key:
 
 .p2align       4
@@ -4463,6 +4478,7 @@ L$key_expansion_256b:
        .byte   0xf3,0xc3
 
 
+
 .p2align       6
 L$bswap_mask:
 .byte  15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0

diff --git a/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
index a576acc25fb030c7002c71ddf3c66910ef84fa47..7b5d9dfc9e9b3d6aa98c5a35995602727e2c10dc 100644 (file)
--- a/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
@@ -1460,10 +1460,10 @@ L$oop_shaext:
        pshufd  $27,%xmm1,%xmm1
        movdqu  %xmm0,(%rdi)
        movd    %xmm1,16(%rdi)
-
        .byte   0xf3,0xc3
 
 
+
 .p2align       4
 sha1_block_data_order_ssse3:
 _ssse3_shortcut:

diff --git a/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
index fd0c2473591aeb4698f545e699ddf40ede36c2db..9fed36b9c80fe6dc0423238c5d88a0f2e4ce807b 100644 (file)
--- a/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
@@ -1814,6 +1814,7 @@ K256:
 .p2align       6
 sha256_block_data_order_shaext:
 _shaext_shortcut:
+
        leaq    K256+128(%rip),%rcx
        movdqu  (%rdi),%xmm1
        movdqu  16(%rdi),%xmm2
@@ -2018,6 +2019,7 @@ L$oop_shaext:
        .byte   0xf3,0xc3
 
 
+
 .p2align       6
 sha256_block_data_order_ssse3:
 
@@ -4277,7 +4279,15 @@ L$oop_avx2:
        vmovdqa %ymm4,0(%rsp)
        xorl    %r14d,%r14d
        vmovdqa %ymm5,32(%rsp)
+
+       movq    88(%rsp),%rdi
+
        leaq    -64(%rsp),%rsp
+
+
+
+       movq    %rdi,-8(%rsp)
+
        movl    %ebx,%edi
        vmovdqa %ymm6,0(%rsp)
        xorl    %ecx,%edi
@@ -4289,6 +4299,12 @@ L$oop_avx2:
 .p2align       4
 L$avx2_00_47:
        leaq    -64(%rsp),%rsp
+
+
+       pushq   64-8(%rsp)
+
+       leaq    8(%rsp),%rsp
+
        vpalignr        $4,%ymm0,%ymm1,%ymm4
        addl    0+128(%rsp),%r11d
        andl    %r8d,%r12d
@@ -4544,6 +4560,12 @@ L$avx2_00_47:
        movl    %r9d,%r12d
        vmovdqa %ymm6,32(%rsp)
        leaq    -64(%rsp),%rsp
+
+
+       pushq   64-8(%rsp)
+
+       leaq    8(%rsp),%rsp
+
        vpalignr        $4,%ymm2,%ymm3,%ymm4
        addl    0+128(%rsp),%r11d
        andl    %r8d,%r12d
@@ -5419,6 +5441,8 @@ L$ower_avx2:
 
        leaq    448(%rsp),%rsp
 
+
+
        addl    0(%rdi),%eax
        addl    4(%rdi),%ebx
        addl    8(%rdi),%ecx
@@ -5444,9 +5468,11 @@ L$ower_avx2:
        jbe     L$oop_avx2
        leaq    (%rsp),%rbp
 
+
+
+
 L$done_avx2:
-       leaq    (%rbp),%rsp
-       movq    88(%rsp),%rsi
+       movq    88(%rbp),%rsi
 
        vzeroupper
        movq    -48(%rsi),%r15

diff --git a/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
index 8bf161601e54a4547564c096e94fd84e1d880c03..e78d90f2d351aa0cc41d1584e7d510b6aeb67efa 100644 (file)
--- a/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
@@ -4204,7 +4204,15 @@ L$oop_avx2:
        vmovdqa %ymm10,64(%rsp)
        vpaddq  64(%rbp),%ymm6,%ymm10
        vmovdqa %ymm11,96(%rsp)
+
+       movq    152(%rsp),%rdi
+
        leaq    -128(%rsp),%rsp
+
+
+
+       movq    %rdi,-8(%rsp)
+
        vpaddq  96(%rbp),%ymm7,%ymm11
        vmovdqa %ymm8,0(%rsp)
        xorq    %r14,%r14
@@ -4220,6 +4228,12 @@ L$oop_avx2:
 .p2align       4
 L$avx2_00_47:
        leaq    -128(%rsp),%rsp
+
+
+       pushq   128-8(%rsp)
+
+       leaq    8(%rsp),%rsp
+
        vpalignr        $8,%ymm0,%ymm1,%ymm8
        addq    0+256(%rsp),%r11
        andq    %r8,%r12
@@ -4513,6 +4527,12 @@ L$avx2_00_47:
        movq    %r9,%r12
        vmovdqa %ymm10,96(%rsp)
        leaq    -128(%rsp),%rsp
+
+
+       pushq   128-8(%rsp)
+
+       leaq    8(%rsp),%rsp
+
        vpalignr        $8,%ymm4,%ymm5,%ymm8
        addq    0+256(%rsp),%r11
        andq    %r8,%r12
@@ -5426,6 +5446,8 @@ L$ower_avx2:
 
        leaq    1152(%rsp),%rsp
 
+
+
        addq    0(%rdi),%rax
        addq    8(%rdi),%rbx
        addq    16(%rdi),%rcx
@@ -5451,9 +5473,11 @@ L$ower_avx2:
        jbe     L$oop_avx2
        leaq    (%rsp),%rbp
 
+
+
+
 L$done_avx2:
-       leaq    (%rbp),%rsp
-       movq    152(%rsp),%rsi
+       movq    152(%rbp),%rsi
 
        vzeroupper
        movq    -48(%rsi),%r15