diff --git a/secure/lib/libcrypto/arch/amd64/aes-x86_64.S b/secure/lib/libcrypto/arch/amd64/aes-x86_64.S new file mode 100644 --- /dev/null +++ b/secure/lib/libcrypto/arch/amd64/aes-x86_64.S @@ -0,0 +1,2680 @@ +/* Do not modify. This file is auto-generated from aes-x86_64.pl. */ +.text +.type _x86_64_AES_encrypt,@function +.align 16 +_x86_64_AES_encrypt: +.cfi_startproc + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx + + movl 240(%r15),%r13d + subl $1,%r13d + jmp .Lenc_loop +.align 16 +.Lenc_loop: + + movzbl %al,%esi + movzbl %bl,%edi + movzbl %cl,%ebp + movl 0(%r14,%rsi,8),%r10d + movl 0(%r14,%rdi,8),%r11d + movl 0(%r14,%rbp,8),%r12d + + movzbl %bh,%esi + movzbl %ch,%edi + movzbl %dl,%ebp + xorl 3(%r14,%rsi,8),%r10d + xorl 3(%r14,%rdi,8),%r11d + movl 0(%r14,%rbp,8),%r8d + + movzbl %dh,%esi + shrl $16,%ecx + movzbl %ah,%ebp + xorl 3(%r14,%rsi,8),%r12d + shrl $16,%edx + xorl 3(%r14,%rbp,8),%r8d + + shrl $16,%ebx + leaq 16(%r15),%r15 + shrl $16,%eax + + movzbl %cl,%esi + movzbl %dl,%edi + movzbl %al,%ebp + xorl 2(%r14,%rsi,8),%r10d + xorl 2(%r14,%rdi,8),%r11d + xorl 2(%r14,%rbp,8),%r12d + + movzbl %dh,%esi + movzbl %ah,%edi + movzbl %bl,%ebp + xorl 1(%r14,%rsi,8),%r10d + xorl 1(%r14,%rdi,8),%r11d + xorl 2(%r14,%rbp,8),%r8d + + movl 12(%r15),%edx + movzbl %bh,%edi + movzbl %ch,%ebp + movl 0(%r15),%eax + xorl 1(%r14,%rdi,8),%r12d + xorl 1(%r14,%rbp,8),%r8d + + movl 4(%r15),%ebx + movl 8(%r15),%ecx + xorl %r10d,%eax + xorl %r11d,%ebx + xorl %r12d,%ecx + xorl %r8d,%edx + subl $1,%r13d + jnz .Lenc_loop + movzbl %al,%esi + movzbl %bl,%edi + movzbl %cl,%ebp + movzbl 2(%r14,%rsi,8),%r10d + movzbl 2(%r14,%rdi,8),%r11d + movzbl 2(%r14,%rbp,8),%r12d + + movzbl %dl,%esi + movzbl %bh,%edi + movzbl %ch,%ebp + movzbl 2(%r14,%rsi,8),%r8d + movl 0(%r14,%rdi,8),%edi + movl 0(%r14,%rbp,8),%ebp + + andl $0x0000ff00,%edi + andl $0x0000ff00,%ebp + + xorl %edi,%r10d + xorl %ebp,%r11d + shrl $16,%ecx + + movzbl %dh,%esi + movzbl %ah,%edi + shrl $16,%edx + movl 0(%r14,%rsi,8),%esi + movl 0(%r14,%rdi,8),%edi + + andl $0x0000ff00,%esi + andl $0x0000ff00,%edi + shrl $16,%ebx + xorl %esi,%r12d + xorl %edi,%r8d + shrl $16,%eax + + movzbl %cl,%esi + movzbl %dl,%edi + movzbl %al,%ebp + movl 0(%r14,%rsi,8),%esi + movl 0(%r14,%rdi,8),%edi + movl 0(%r14,%rbp,8),%ebp + + andl $0x00ff0000,%esi + andl $0x00ff0000,%edi + andl $0x00ff0000,%ebp + + xorl %esi,%r10d + xorl %edi,%r11d + xorl %ebp,%r12d + + movzbl %bl,%esi + movzbl %dh,%edi + movzbl %ah,%ebp + movl 0(%r14,%rsi,8),%esi + movl 2(%r14,%rdi,8),%edi + movl 2(%r14,%rbp,8),%ebp + + andl $0x00ff0000,%esi + andl $0xff000000,%edi + andl $0xff000000,%ebp + + xorl %esi,%r8d + xorl %edi,%r10d + xorl %ebp,%r11d + + movzbl %bh,%esi + movzbl %ch,%edi + movl 16+12(%r15),%edx + movl 2(%r14,%rsi,8),%esi + movl 2(%r14,%rdi,8),%edi + movl 16+0(%r15),%eax + + andl $0xff000000,%esi + andl $0xff000000,%edi + + xorl %esi,%r12d + xorl %edi,%r8d + + movl 16+4(%r15),%ebx + movl 16+8(%r15),%ecx + xorl %r10d,%eax + xorl %r11d,%ebx + xorl %r12d,%ecx + xorl %r8d,%edx +.byte 0xf3,0xc3 +.cfi_endproc +.size _x86_64_AES_encrypt,.-_x86_64_AES_encrypt +.type _x86_64_AES_encrypt_compact,@function +.align 16 +_x86_64_AES_encrypt_compact: +.cfi_startproc + leaq 128(%r14),%r8 + movl 0-128(%r8),%edi + movl 32-128(%r8),%ebp + movl 64-128(%r8),%r10d + movl 96-128(%r8),%r11d + movl 128-128(%r8),%edi + movl 160-128(%r8),%ebp + movl 192-128(%r8),%r10d + movl 224-128(%r8),%r11d + jmp .Lenc_loop_compact +.align 16 +.Lenc_loop_compact: + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx + leaq 16(%r15),%r15 + movzbl %al,%r10d + movzbl %bl,%r11d + movzbl %cl,%r12d + movzbl %dl,%r8d + movzbl %bh,%esi + movzbl %ch,%edi + shrl $16,%ecx + movzbl %dh,%ebp + movzbl (%r14,%r10,1),%r10d + movzbl (%r14,%r11,1),%r11d + movzbl (%r14,%r12,1),%r12d + movzbl (%r14,%r8,1),%r8d + + movzbl (%r14,%rsi,1),%r9d + movzbl %ah,%esi + movzbl (%r14,%rdi,1),%r13d + movzbl %cl,%edi + movzbl (%r14,%rbp,1),%ebp + movzbl (%r14,%rsi,1),%esi + + shll $8,%r9d + shrl $16,%edx + shll $8,%r13d + xorl %r9d,%r10d + shrl $16,%eax + movzbl %dl,%r9d + shrl $16,%ebx + xorl %r13d,%r11d + shll $8,%ebp + movzbl %al,%r13d + movzbl (%r14,%rdi,1),%edi + xorl %ebp,%r12d + + shll $8,%esi + movzbl %bl,%ebp + shll $16,%edi + xorl %esi,%r8d + movzbl (%r14,%r9,1),%r9d + movzbl %dh,%esi + movzbl (%r14,%r13,1),%r13d + xorl %edi,%r10d + + shrl $8,%ecx + movzbl %ah,%edi + shll $16,%r9d + shrl $8,%ebx + shll $16,%r13d + xorl %r9d,%r11d + movzbl (%r14,%rbp,1),%ebp + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%edi + movzbl (%r14,%rcx,1),%edx + movzbl (%r14,%rbx,1),%ecx + + shll $16,%ebp + xorl %r13d,%r12d + shll $24,%esi + xorl %ebp,%r8d + shll $24,%edi + xorl %esi,%r10d + shll $24,%edx + xorl %edi,%r11d + shll $24,%ecx + movl %r10d,%eax + movl %r11d,%ebx + xorl %r12d,%ecx + xorl %r8d,%edx + cmpq 16(%rsp),%r15 + je .Lenc_compact_done + movl $0x80808080,%r10d + movl $0x80808080,%r11d + andl %eax,%r10d + andl %ebx,%r11d + movl %r10d,%esi + movl %r11d,%edi + shrl $7,%r10d + leal (%rax,%rax,1),%r8d + shrl $7,%r11d + leal (%rbx,%rbx,1),%r9d + subl %r10d,%esi + subl %r11d,%edi + andl $0xfefefefe,%r8d + andl $0xfefefefe,%r9d + andl $0x1b1b1b1b,%esi + andl $0x1b1b1b1b,%edi + movl %eax,%r10d + movl %ebx,%r11d + xorl %esi,%r8d + xorl %edi,%r9d + + xorl %r8d,%eax + xorl %r9d,%ebx + movl $0x80808080,%r12d + roll $24,%eax + movl $0x80808080,%ebp + roll $24,%ebx + andl %ecx,%r12d + andl %edx,%ebp + xorl %r8d,%eax + xorl %r9d,%ebx + movl %r12d,%esi + rorl $16,%r10d + movl %ebp,%edi + rorl $16,%r11d + leal (%rcx,%rcx,1),%r8d + shrl $7,%r12d + xorl %r10d,%eax + shrl $7,%ebp + xorl %r11d,%ebx + rorl $8,%r10d + leal (%rdx,%rdx,1),%r9d + rorl $8,%r11d + subl %r12d,%esi + subl %ebp,%edi + xorl %r10d,%eax + xorl %r11d,%ebx + + andl $0xfefefefe,%r8d + andl $0xfefefefe,%r9d + andl $0x1b1b1b1b,%esi + andl $0x1b1b1b1b,%edi + movl %ecx,%r12d + movl %edx,%ebp + xorl %esi,%r8d + xorl %edi,%r9d + + rorl $16,%r12d + xorl %r8d,%ecx + rorl $16,%ebp + xorl %r9d,%edx + roll $24,%ecx + movl 0(%r14),%esi + roll $24,%edx + xorl %r8d,%ecx + movl 64(%r14),%edi + xorl %r9d,%edx + movl 128(%r14),%r8d + xorl %r12d,%ecx + rorl $8,%r12d + xorl %ebp,%edx + rorl $8,%ebp + xorl %r12d,%ecx + movl 192(%r14),%r9d + xorl %ebp,%edx + jmp .Lenc_loop_compact +.align 16 +.Lenc_compact_done: + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx +.byte 0xf3,0xc3 +.cfi_endproc +.size _x86_64_AES_encrypt_compact,.-_x86_64_AES_encrypt_compact +.globl AES_encrypt +.type AES_encrypt,@function +.align 16 +.globl asm_AES_encrypt +.hidden asm_AES_encrypt +asm_AES_encrypt: +AES_encrypt: +.cfi_startproc +.byte 243,15,30,250 + movq %rsp,%rax +.cfi_def_cfa_register %rax + pushq %rbx +.cfi_offset %rbx,-16 + pushq %rbp +.cfi_offset %rbp,-24 + pushq %r12 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_offset %r15,-56 + + + leaq -63(%rdx),%rcx + andq $-64,%rsp + subq %rsp,%rcx + negq %rcx + andq $0x3c0,%rcx + subq %rcx,%rsp + subq $32,%rsp + + movq %rsi,16(%rsp) + movq %rax,24(%rsp) +.cfi_escape 0x0f,0x05,0x77,0x18,0x06,0x23,0x08 +.Lenc_prologue: + + movq %rdx,%r15 + movl 240(%r15),%r13d + + movl 0(%rdi),%eax + movl 4(%rdi),%ebx + movl 8(%rdi),%ecx + movl 12(%rdi),%edx + + shll $4,%r13d + leaq (%r15,%r13,1),%rbp + movq %r15,(%rsp) + movq %rbp,8(%rsp) + + + leaq .LAES_Te+2048(%rip),%r14 + leaq 768(%rsp),%rbp + subq %r14,%rbp + andq $0x300,%rbp + leaq (%r14,%rbp,1),%r14 + + call _x86_64_AES_encrypt_compact + + movq 16(%rsp),%r9 + movq 24(%rsp),%rsi +.cfi_def_cfa %rsi,8 + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + movq -48(%rsi),%r15 +.cfi_restore %r15 + movq -40(%rsi),%r14 +.cfi_restore %r14 + movq -32(%rsi),%r13 +.cfi_restore %r13 + movq -24(%rsi),%r12 +.cfi_restore %r12 + movq -16(%rsi),%rbp +.cfi_restore %rbp + movq -8(%rsi),%rbx +.cfi_restore %rbx + leaq (%rsi),%rsp +.cfi_def_cfa_register %rsp +.Lenc_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size AES_encrypt,.-AES_encrypt +.type _x86_64_AES_decrypt,@function +.align 16 +_x86_64_AES_decrypt: +.cfi_startproc + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx + + movl 240(%r15),%r13d + subl $1,%r13d + jmp .Ldec_loop +.align 16 +.Ldec_loop: + + movzbl %al,%esi + movzbl %bl,%edi + movzbl %cl,%ebp + movl 0(%r14,%rsi,8),%r10d + movl 0(%r14,%rdi,8),%r11d + movl 0(%r14,%rbp,8),%r12d + + movzbl %dh,%esi + movzbl %ah,%edi + movzbl %dl,%ebp + xorl 3(%r14,%rsi,8),%r10d + xorl 3(%r14,%rdi,8),%r11d + movl 0(%r14,%rbp,8),%r8d + + movzbl %bh,%esi + shrl $16,%eax + movzbl %ch,%ebp + xorl 3(%r14,%rsi,8),%r12d + shrl $16,%edx + xorl 3(%r14,%rbp,8),%r8d + + shrl $16,%ebx + leaq 16(%r15),%r15 + shrl $16,%ecx + + movzbl %cl,%esi + movzbl %dl,%edi + movzbl %al,%ebp + xorl 2(%r14,%rsi,8),%r10d + xorl 2(%r14,%rdi,8),%r11d + xorl 2(%r14,%rbp,8),%r12d + + movzbl %bh,%esi + movzbl %ch,%edi + movzbl %bl,%ebp + xorl 1(%r14,%rsi,8),%r10d + xorl 1(%r14,%rdi,8),%r11d + xorl 2(%r14,%rbp,8),%r8d + + movzbl %dh,%esi + movl 12(%r15),%edx + movzbl %ah,%ebp + xorl 1(%r14,%rsi,8),%r12d + movl 0(%r15),%eax + xorl 1(%r14,%rbp,8),%r8d + + xorl %r10d,%eax + movl 4(%r15),%ebx + movl 8(%r15),%ecx + xorl %r12d,%ecx + xorl %r11d,%ebx + xorl %r8d,%edx + subl $1,%r13d + jnz .Ldec_loop + leaq 2048(%r14),%r14 + movzbl %al,%esi + movzbl %bl,%edi + movzbl %cl,%ebp + movzbl (%r14,%rsi,1),%r10d + movzbl (%r14,%rdi,1),%r11d + movzbl (%r14,%rbp,1),%r12d + + movzbl %dl,%esi + movzbl %dh,%edi + movzbl %ah,%ebp + movzbl (%r14,%rsi,1),%r8d + movzbl (%r14,%rdi,1),%edi + movzbl (%r14,%rbp,1),%ebp + + shll $8,%edi + shll $8,%ebp + + xorl %edi,%r10d + xorl %ebp,%r11d + shrl $16,%edx + + movzbl %bh,%esi + movzbl %ch,%edi + shrl $16,%eax + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%edi + + shll $8,%esi + shll $8,%edi + shrl $16,%ebx + xorl %esi,%r12d + xorl %edi,%r8d + shrl $16,%ecx + + movzbl %cl,%esi + movzbl %dl,%edi + movzbl %al,%ebp + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%edi + movzbl (%r14,%rbp,1),%ebp + + shll $16,%esi + shll $16,%edi + shll $16,%ebp + + xorl %esi,%r10d + xorl %edi,%r11d + xorl %ebp,%r12d + + movzbl %bl,%esi + movzbl %bh,%edi + movzbl %ch,%ebp + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%edi + movzbl (%r14,%rbp,1),%ebp + + shll $16,%esi + shll $24,%edi + shll $24,%ebp + + xorl %esi,%r8d + xorl %edi,%r10d + xorl %ebp,%r11d + + movzbl %dh,%esi + movzbl %ah,%edi + movl 16+12(%r15),%edx + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%edi + movl 16+0(%r15),%eax + + shll $24,%esi + shll $24,%edi + + xorl %esi,%r12d + xorl %edi,%r8d + + movl 16+4(%r15),%ebx + movl 16+8(%r15),%ecx + leaq -2048(%r14),%r14 + xorl %r10d,%eax + xorl %r11d,%ebx + xorl %r12d,%ecx + xorl %r8d,%edx +.byte 0xf3,0xc3 +.cfi_endproc +.size _x86_64_AES_decrypt,.-_x86_64_AES_decrypt +.type _x86_64_AES_decrypt_compact,@function +.align 16 +_x86_64_AES_decrypt_compact: +.cfi_startproc + leaq 128(%r14),%r8 + movl 0-128(%r8),%edi + movl 32-128(%r8),%ebp + movl 64-128(%r8),%r10d + movl 96-128(%r8),%r11d + movl 128-128(%r8),%edi + movl 160-128(%r8),%ebp + movl 192-128(%r8),%r10d + movl 224-128(%r8),%r11d + jmp .Ldec_loop_compact + +.align 16 +.Ldec_loop_compact: + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx + leaq 16(%r15),%r15 + movzbl %al,%r10d + movzbl %bl,%r11d + movzbl %cl,%r12d + movzbl %dl,%r8d + movzbl %dh,%esi + movzbl %ah,%edi + shrl $16,%edx + movzbl %bh,%ebp + movzbl (%r14,%r10,1),%r10d + movzbl (%r14,%r11,1),%r11d + movzbl (%r14,%r12,1),%r12d + movzbl (%r14,%r8,1),%r8d + + movzbl (%r14,%rsi,1),%r9d + movzbl %ch,%esi + movzbl (%r14,%rdi,1),%r13d + movzbl (%r14,%rbp,1),%ebp + movzbl (%r14,%rsi,1),%esi + + shrl $16,%ecx + shll $8,%r13d + shll $8,%r9d + movzbl %cl,%edi + shrl $16,%eax + xorl %r9d,%r10d + shrl $16,%ebx + movzbl %dl,%r9d + + shll $8,%ebp + xorl %r13d,%r11d + shll $8,%esi + movzbl %al,%r13d + movzbl (%r14,%rdi,1),%edi + xorl %ebp,%r12d + movzbl %bl,%ebp + + shll $16,%edi + xorl %esi,%r8d + movzbl (%r14,%r9,1),%r9d + movzbl %bh,%esi + movzbl (%r14,%rbp,1),%ebp + xorl %edi,%r10d + movzbl (%r14,%r13,1),%r13d + movzbl %ch,%edi + + shll $16,%ebp + shll $16,%r9d + shll $16,%r13d + xorl %ebp,%r8d + movzbl %dh,%ebp + xorl %r9d,%r11d + shrl $8,%eax + xorl %r13d,%r12d + + movzbl (%r14,%rsi,1),%esi + movzbl (%r14,%rdi,1),%ebx + movzbl (%r14,%rbp,1),%ecx + movzbl (%r14,%rax,1),%edx + + movl %r10d,%eax + shll $24,%esi + shll $24,%ebx + shll $24,%ecx + xorl %esi,%eax + shll $24,%edx + xorl %r11d,%ebx + xorl %r12d,%ecx + xorl %r8d,%edx + cmpq 16(%rsp),%r15 + je .Ldec_compact_done + + movq 256+0(%r14),%rsi + shlq $32,%rbx + shlq $32,%rdx + movq 256+8(%r14),%rdi + orq %rbx,%rax + orq %rdx,%rcx + movq 256+16(%r14),%rbp + movq %rsi,%r9 + movq %rsi,%r12 + andq %rax,%r9 + andq %rcx,%r12 + movq %r9,%rbx + movq %r12,%rdx + shrq $7,%r9 + leaq (%rax,%rax,1),%r8 + shrq $7,%r12 + leaq (%rcx,%rcx,1),%r11 + subq %r9,%rbx + subq %r12,%rdx + andq %rdi,%r8 + andq %rdi,%r11 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r8 + xorq %rdx,%r11 + movq %rsi,%r10 + movq %rsi,%r13 + + andq %r8,%r10 + andq %r11,%r13 + movq %r10,%rbx + movq %r13,%rdx + shrq $7,%r10 + leaq (%r8,%r8,1),%r9 + shrq $7,%r13 + leaq (%r11,%r11,1),%r12 + subq %r10,%rbx + subq %r13,%rdx + andq %rdi,%r9 + andq %rdi,%r12 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r9 + xorq %rdx,%r12 + movq %rsi,%r10 + movq %rsi,%r13 + + andq %r9,%r10 + andq %r12,%r13 + movq %r10,%rbx + movq %r13,%rdx + shrq $7,%r10 + xorq %rax,%r8 + shrq $7,%r13 + xorq %rcx,%r11 + subq %r10,%rbx + subq %r13,%rdx + leaq (%r9,%r9,1),%r10 + leaq (%r12,%r12,1),%r13 + xorq %rax,%r9 + xorq %rcx,%r12 + andq %rdi,%r10 + andq %rdi,%r13 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r10 + xorq %rdx,%r13 + + xorq %r10,%rax + xorq %r13,%rcx + xorq %r10,%r8 + xorq %r13,%r11 + movq %rax,%rbx + movq %rcx,%rdx + xorq %r10,%r9 + shrq $32,%rbx + xorq %r13,%r12 + shrq $32,%rdx + xorq %r8,%r10 + roll $8,%eax + xorq %r11,%r13 + roll $8,%ecx + xorq %r9,%r10 + roll $8,%ebx + xorq %r12,%r13 + + roll $8,%edx + xorl %r10d,%eax + shrq $32,%r10 + xorl %r13d,%ecx + shrq $32,%r13 + xorl %r10d,%ebx + xorl %r13d,%edx + + movq %r8,%r10 + roll $24,%r8d + movq %r11,%r13 + roll $24,%r11d + shrq $32,%r10 + xorl %r8d,%eax + shrq $32,%r13 + xorl %r11d,%ecx + roll $24,%r10d + movq %r9,%r8 + roll $24,%r13d + movq %r12,%r11 + shrq $32,%r8 + xorl %r10d,%ebx + shrq $32,%r11 + xorl %r13d,%edx + + movq 0(%r14),%rsi + roll $16,%r9d + movq 64(%r14),%rdi + roll $16,%r12d + movq 128(%r14),%rbp + roll $16,%r8d + movq 192(%r14),%r10 + xorl %r9d,%eax + roll $16,%r11d + xorl %r12d,%ecx + movq 256(%r14),%r13 + xorl %r8d,%ebx + xorl %r11d,%edx + jmp .Ldec_loop_compact +.align 16 +.Ldec_compact_done: + xorl 0(%r15),%eax + xorl 4(%r15),%ebx + xorl 8(%r15),%ecx + xorl 12(%r15),%edx +.byte 0xf3,0xc3 +.cfi_endproc +.size _x86_64_AES_decrypt_compact,.-_x86_64_AES_decrypt_compact +.globl AES_decrypt +.type AES_decrypt,@function +.align 16 +.globl asm_AES_decrypt +.hidden asm_AES_decrypt +asm_AES_decrypt: +AES_decrypt: +.cfi_startproc +.byte 243,15,30,250 + movq %rsp,%rax +.cfi_def_cfa_register %rax + pushq %rbx +.cfi_offset %rbx,-16 + pushq %rbp +.cfi_offset %rbp,-24 + pushq %r12 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_offset %r15,-56 + + + leaq -63(%rdx),%rcx + andq $-64,%rsp + subq %rsp,%rcx + negq %rcx + andq $0x3c0,%rcx + subq %rcx,%rsp + subq $32,%rsp + + movq %rsi,16(%rsp) + movq %rax,24(%rsp) +.cfi_escape 0x0f,0x05,0x77,0x18,0x06,0x23,0x08 +.Ldec_prologue: + + movq %rdx,%r15 + movl 240(%r15),%r13d + + movl 0(%rdi),%eax + movl 4(%rdi),%ebx + movl 8(%rdi),%ecx + movl 12(%rdi),%edx + + shll $4,%r13d + leaq (%r15,%r13,1),%rbp + movq %r15,(%rsp) + movq %rbp,8(%rsp) + + + leaq .LAES_Td+2048(%rip),%r14 + leaq 768(%rsp),%rbp + subq %r14,%rbp + andq $0x300,%rbp + leaq (%r14,%rbp,1),%r14 + shrq $3,%rbp + addq %rbp,%r14 + + call _x86_64_AES_decrypt_compact + + movq 16(%rsp),%r9 + movq 24(%rsp),%rsi +.cfi_def_cfa %rsi,8 + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + movq -48(%rsi),%r15 +.cfi_restore %r15 + movq -40(%rsi),%r14 +.cfi_restore %r14 + movq -32(%rsi),%r13 +.cfi_restore %r13 + movq -24(%rsi),%r12 +.cfi_restore %r12 + movq -16(%rsi),%rbp +.cfi_restore %rbp + movq -8(%rsi),%rbx +.cfi_restore %rbx + leaq (%rsi),%rsp +.cfi_def_cfa_register %rsp +.Ldec_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size AES_decrypt,.-AES_decrypt +.globl AES_set_encrypt_key +.type AES_set_encrypt_key,@function +.align 16 +AES_set_encrypt_key: +.cfi_startproc +.byte 243,15,30,250 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-16 + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + subq $8,%rsp +.cfi_adjust_cfa_offset 8 +.Lenc_key_prologue: + + call _x86_64_AES_set_encrypt_key + + movq 40(%rsp),%rbp +.cfi_restore %rbp + movq 48(%rsp),%rbx +.cfi_restore %rbx + addq $56,%rsp +.cfi_adjust_cfa_offset -56 +.Lenc_key_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size AES_set_encrypt_key,.-AES_set_encrypt_key + +.type _x86_64_AES_set_encrypt_key,@function +.align 16 +_x86_64_AES_set_encrypt_key: +.cfi_startproc + movl %esi,%ecx + movq %rdi,%rsi + movq %rdx,%rdi + + testq $-1,%rsi + jz .Lbadpointer + testq $-1,%rdi + jz .Lbadpointer + + leaq .LAES_Te(%rip),%rbp + leaq 2048+128(%rbp),%rbp + + + movl 0-128(%rbp),%eax + movl 32-128(%rbp),%ebx + movl 64-128(%rbp),%r8d + movl 96-128(%rbp),%edx + movl 128-128(%rbp),%eax + movl 160-128(%rbp),%ebx + movl 192-128(%rbp),%r8d + movl 224-128(%rbp),%edx + + cmpl $128,%ecx + je .L10rounds + cmpl $192,%ecx + je .L12rounds + cmpl $256,%ecx + je .L14rounds + movq $-2,%rax + jmp .Lexit + +.L10rounds: + movq 0(%rsi),%rax + movq 8(%rsi),%rdx + movq %rax,0(%rdi) + movq %rdx,8(%rdi) + + shrq $32,%rdx + xorl %ecx,%ecx + jmp .L10shortcut +.align 4 +.L10loop: + movl 0(%rdi),%eax + movl 12(%rdi),%edx +.L10shortcut: + movzbl %dl,%esi + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + + xorl 1024-128(%rbp,%rcx,4),%eax + movl %eax,16(%rdi) + xorl 4(%rdi),%eax + movl %eax,20(%rdi) + xorl 8(%rdi),%eax + movl %eax,24(%rdi) + xorl 12(%rdi),%eax + movl %eax,28(%rdi) + addl $1,%ecx + leaq 16(%rdi),%rdi + cmpl $10,%ecx + jl .L10loop + + movl $10,80(%rdi) + xorq %rax,%rax + jmp .Lexit + +.L12rounds: + movq 0(%rsi),%rax + movq 8(%rsi),%rbx + movq 16(%rsi),%rdx + movq %rax,0(%rdi) + movq %rbx,8(%rdi) + movq %rdx,16(%rdi) + + shrq $32,%rdx + xorl %ecx,%ecx + jmp .L12shortcut +.align 4 +.L12loop: + movl 0(%rdi),%eax + movl 20(%rdi),%edx +.L12shortcut: + movzbl %dl,%esi + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + + xorl 1024-128(%rbp,%rcx,4),%eax + movl %eax,24(%rdi) + xorl 4(%rdi),%eax + movl %eax,28(%rdi) + xorl 8(%rdi),%eax + movl %eax,32(%rdi) + xorl 12(%rdi),%eax + movl %eax,36(%rdi) + + cmpl $7,%ecx + je .L12break + addl $1,%ecx + + xorl 16(%rdi),%eax + movl %eax,40(%rdi) + xorl 20(%rdi),%eax + movl %eax,44(%rdi) + + leaq 24(%rdi),%rdi + jmp .L12loop +.L12break: + movl $12,72(%rdi) + xorq %rax,%rax + jmp .Lexit + +.L14rounds: + movq 0(%rsi),%rax + movq 8(%rsi),%rbx + movq 16(%rsi),%rcx + movq 24(%rsi),%rdx + movq %rax,0(%rdi) + movq %rbx,8(%rdi) + movq %rcx,16(%rdi) + movq %rdx,24(%rdi) + + shrq $32,%rdx + xorl %ecx,%ecx + jmp .L14shortcut +.align 4 +.L14loop: + movl 0(%rdi),%eax + movl 28(%rdi),%edx +.L14shortcut: + movzbl %dl,%esi + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + + xorl 1024-128(%rbp,%rcx,4),%eax + movl %eax,32(%rdi) + xorl 4(%rdi),%eax + movl %eax,36(%rdi) + xorl 8(%rdi),%eax + movl %eax,40(%rdi) + xorl 12(%rdi),%eax + movl %eax,44(%rdi) + + cmpl $6,%ecx + je .L14break + addl $1,%ecx + + movl %eax,%edx + movl 16(%rdi),%eax + movzbl %dl,%esi + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shrl $16,%edx + shll $8,%ebx + movzbl %dl,%esi + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + movzbl %dh,%esi + shll $16,%ebx + xorl %ebx,%eax + + movzbl -128(%rbp,%rsi,1),%ebx + shll $24,%ebx + xorl %ebx,%eax + + movl %eax,48(%rdi) + xorl 20(%rdi),%eax + movl %eax,52(%rdi) + xorl 24(%rdi),%eax + movl %eax,56(%rdi) + xorl 28(%rdi),%eax + movl %eax,60(%rdi) + + leaq 32(%rdi),%rdi + jmp .L14loop +.L14break: + movl $14,48(%rdi) + xorq %rax,%rax + jmp .Lexit + +.Lbadpointer: + movq $-1,%rax +.Lexit: +.byte 0xf3,0xc3 +.cfi_endproc +.size _x86_64_AES_set_encrypt_key,.-_x86_64_AES_set_encrypt_key +.globl AES_set_decrypt_key +.type AES_set_decrypt_key,@function +.align 16 +AES_set_decrypt_key: +.cfi_startproc +.byte 243,15,30,250 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-16 + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + pushq %rdx +.cfi_adjust_cfa_offset 8 +.Ldec_key_prologue: + + call _x86_64_AES_set_encrypt_key + movq (%rsp),%r8 + cmpl $0,%eax + jne .Labort + + movl 240(%r8),%r14d + xorq %rdi,%rdi + leaq (%rdi,%r14,4),%rcx + movq %r8,%rsi + leaq (%r8,%rcx,4),%rdi +.align 4 +.Linvert: + movq 0(%rsi),%rax + movq 8(%rsi),%rbx + movq 0(%rdi),%rcx + movq 8(%rdi),%rdx + movq %rax,0(%rdi) + movq %rbx,8(%rdi) + movq %rcx,0(%rsi) + movq %rdx,8(%rsi) + leaq 16(%rsi),%rsi + leaq -16(%rdi),%rdi + cmpq %rsi,%rdi + jne .Linvert + + leaq .LAES_Te+2048+1024(%rip),%rax + + movq 40(%rax),%rsi + movq 48(%rax),%rdi + movq 56(%rax),%rbp + + movq %r8,%r15 + subl $1,%r14d +.align 4 +.Lpermute: + leaq 16(%r15),%r15 + movq 0(%r15),%rax + movq 8(%r15),%rcx + movq %rsi,%r9 + movq %rsi,%r12 + andq %rax,%r9 + andq %rcx,%r12 + movq %r9,%rbx + movq %r12,%rdx + shrq $7,%r9 + leaq (%rax,%rax,1),%r8 + shrq $7,%r12 + leaq (%rcx,%rcx,1),%r11 + subq %r9,%rbx + subq %r12,%rdx + andq %rdi,%r8 + andq %rdi,%r11 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r8 + xorq %rdx,%r11 + movq %rsi,%r10 + movq %rsi,%r13 + + andq %r8,%r10 + andq %r11,%r13 + movq %r10,%rbx + movq %r13,%rdx + shrq $7,%r10 + leaq (%r8,%r8,1),%r9 + shrq $7,%r13 + leaq (%r11,%r11,1),%r12 + subq %r10,%rbx + subq %r13,%rdx + andq %rdi,%r9 + andq %rdi,%r12 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r9 + xorq %rdx,%r12 + movq %rsi,%r10 + movq %rsi,%r13 + + andq %r9,%r10 + andq %r12,%r13 + movq %r10,%rbx + movq %r13,%rdx + shrq $7,%r10 + xorq %rax,%r8 + shrq $7,%r13 + xorq %rcx,%r11 + subq %r10,%rbx + subq %r13,%rdx + leaq (%r9,%r9,1),%r10 + leaq (%r12,%r12,1),%r13 + xorq %rax,%r9 + xorq %rcx,%r12 + andq %rdi,%r10 + andq %rdi,%r13 + andq %rbp,%rbx + andq %rbp,%rdx + xorq %rbx,%r10 + xorq %rdx,%r13 + + xorq %r10,%rax + xorq %r13,%rcx + xorq %r10,%r8 + xorq %r13,%r11 + movq %rax,%rbx + movq %rcx,%rdx + xorq %r10,%r9 + shrq $32,%rbx + xorq %r13,%r12 + shrq $32,%rdx + xorq %r8,%r10 + roll $8,%eax + xorq %r11,%r13 + roll $8,%ecx + xorq %r9,%r10 + roll $8,%ebx + xorq %r12,%r13 + + roll $8,%edx + xorl %r10d,%eax + shrq $32,%r10 + xorl %r13d,%ecx + shrq $32,%r13 + xorl %r10d,%ebx + xorl %r13d,%edx + + movq %r8,%r10 + roll $24,%r8d + movq %r11,%r13 + roll $24,%r11d + shrq $32,%r10 + xorl %r8d,%eax + shrq $32,%r13 + xorl %r11d,%ecx + roll $24,%r10d + movq %r9,%r8 + roll $24,%r13d + movq %r12,%r11 + shrq $32,%r8 + xorl %r10d,%ebx + shrq $32,%r11 + xorl %r13d,%edx + + + roll $16,%r9d + + roll $16,%r12d + + roll $16,%r8d + + xorl %r9d,%eax + roll $16,%r11d + xorl %r12d,%ecx + + xorl %r8d,%ebx + xorl %r11d,%edx + movl %eax,0(%r15) + movl %ebx,4(%r15) + movl %ecx,8(%r15) + movl %edx,12(%r15) + subl $1,%r14d + jnz .Lpermute + + xorq %rax,%rax +.Labort: + movq 8(%rsp),%r15 +.cfi_restore %r15 + movq 16(%rsp),%r14 +.cfi_restore %r14 + movq 24(%rsp),%r13 +.cfi_restore %r13 + movq 32(%rsp),%r12 +.cfi_restore %r12 + movq 40(%rsp),%rbp +.cfi_restore %rbp + movq 48(%rsp),%rbx +.cfi_restore %rbx + addq $56,%rsp +.cfi_adjust_cfa_offset -56 +.Ldec_key_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size AES_set_decrypt_key,.-AES_set_decrypt_key +.globl AES_cbc_encrypt +.type AES_cbc_encrypt,@function +.align 16 + +.globl asm_AES_cbc_encrypt +.hidden asm_AES_cbc_encrypt +asm_AES_cbc_encrypt: +AES_cbc_encrypt: +.cfi_startproc +.byte 243,15,30,250 + cmpq $0,%rdx + je .Lcbc_epilogue + pushfq + + +.cfi_adjust_cfa_offset 8 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-24 + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-32 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-40 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-48 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-56 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-64 +.Lcbc_prologue: + + cld + movl %r9d,%r9d + + leaq .LAES_Te(%rip),%r14 + leaq .LAES_Td(%rip),%r10 + cmpq $0,%r9 + cmoveq %r10,%r14 + +.cfi_remember_state + movl OPENSSL_ia32cap_P(%rip),%r10d + cmpq $512,%rdx + jb .Lcbc_slow_prologue + testq $15,%rdx + jnz .Lcbc_slow_prologue + btl $28,%r10d + jc .Lcbc_slow_prologue + + + leaq -88-248(%rsp),%r15 + andq $-64,%r15 + + + movq %r14,%r10 + leaq 2304(%r14),%r11 + movq %r15,%r12 + andq $0xFFF,%r10 + andq $0xFFF,%r11 + andq $0xFFF,%r12 + + cmpq %r11,%r12 + jb .Lcbc_te_break_out + subq %r11,%r12 + subq %r12,%r15 + jmp .Lcbc_te_ok +.Lcbc_te_break_out: + subq %r10,%r12 + andq $0xFFF,%r12 + addq $320,%r12 + subq %r12,%r15 +.align 4 +.Lcbc_te_ok: + + xchgq %rsp,%r15 +.cfi_def_cfa_register %r15 + + movq %r15,16(%rsp) +.cfi_escape 0x0f,0x05,0x77,0x10,0x06,0x23,0x40 +.Lcbc_fast_body: + movq %rdi,24(%rsp) + movq %rsi,32(%rsp) + movq %rdx,40(%rsp) + movq %rcx,48(%rsp) + movq %r8,56(%rsp) + movl $0,80+240(%rsp) + movq %r8,%rbp + movq %r9,%rbx + movq %rsi,%r9 + movq %rdi,%r8 + movq %rcx,%r15 + + movl 240(%r15),%eax + + movq %r15,%r10 + subq %r14,%r10 + andq $0xfff,%r10 + cmpq $2304,%r10 + jb .Lcbc_do_ecopy + cmpq $4096-248,%r10 + jb .Lcbc_skip_ecopy +.align 4 +.Lcbc_do_ecopy: + movq %r15,%rsi + leaq 80(%rsp),%rdi + leaq 80(%rsp),%r15 + movl $30,%ecx +.long 0x90A548F3 + movl %eax,(%rdi) +.Lcbc_skip_ecopy: + movq %r15,0(%rsp) + + movl $18,%ecx +.align 4 +.Lcbc_prefetch_te: + movq 0(%r14),%r10 + movq 32(%r14),%r11 + movq 64(%r14),%r12 + movq 96(%r14),%r13 + leaq 128(%r14),%r14 + subl $1,%ecx + jnz .Lcbc_prefetch_te + leaq -2304(%r14),%r14 + + cmpq $0,%rbx + je .LFAST_DECRYPT + + + movl 0(%rbp),%eax + movl 4(%rbp),%ebx + movl 8(%rbp),%ecx + movl 12(%rbp),%edx + +.align 4 +.Lcbc_fast_enc_loop: + xorl 0(%r8),%eax + xorl 4(%r8),%ebx + xorl 8(%r8),%ecx + xorl 12(%r8),%edx + movq 0(%rsp),%r15 + movq %r8,24(%rsp) + + call _x86_64_AES_encrypt + + movq 24(%rsp),%r8 + movq 40(%rsp),%r10 + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + leaq 16(%r8),%r8 + leaq 16(%r9),%r9 + subq $16,%r10 + testq $-16,%r10 + movq %r10,40(%rsp) + jnz .Lcbc_fast_enc_loop + movq 56(%rsp),%rbp + movl %eax,0(%rbp) + movl %ebx,4(%rbp) + movl %ecx,8(%rbp) + movl %edx,12(%rbp) + + jmp .Lcbc_fast_cleanup + + +.align 16 +.LFAST_DECRYPT: + cmpq %r8,%r9 + je .Lcbc_fast_dec_in_place + + movq %rbp,64(%rsp) +.align 4 +.Lcbc_fast_dec_loop: + movl 0(%r8),%eax + movl 4(%r8),%ebx + movl 8(%r8),%ecx + movl 12(%r8),%edx + movq 0(%rsp),%r15 + movq %r8,24(%rsp) + + call _x86_64_AES_decrypt + + movq 64(%rsp),%rbp + movq 24(%rsp),%r8 + movq 40(%rsp),%r10 + xorl 0(%rbp),%eax + xorl 4(%rbp),%ebx + xorl 8(%rbp),%ecx + xorl 12(%rbp),%edx + movq %r8,%rbp + + subq $16,%r10 + movq %r10,40(%rsp) + movq %rbp,64(%rsp) + + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + leaq 16(%r8),%r8 + leaq 16(%r9),%r9 + jnz .Lcbc_fast_dec_loop + movq 56(%rsp),%r12 + movq 0(%rbp),%r10 + movq 8(%rbp),%r11 + movq %r10,0(%r12) + movq %r11,8(%r12) + jmp .Lcbc_fast_cleanup + +.align 16 +.Lcbc_fast_dec_in_place: + movq 0(%rbp),%r10 + movq 8(%rbp),%r11 + movq %r10,0+64(%rsp) + movq %r11,8+64(%rsp) +.align 4 +.Lcbc_fast_dec_in_place_loop: + movl 0(%r8),%eax + movl 4(%r8),%ebx + movl 8(%r8),%ecx + movl 12(%r8),%edx + movq 0(%rsp),%r15 + movq %r8,24(%rsp) + + call _x86_64_AES_decrypt + + movq 24(%rsp),%r8 + movq 40(%rsp),%r10 + xorl 0+64(%rsp),%eax + xorl 4+64(%rsp),%ebx + xorl 8+64(%rsp),%ecx + xorl 12+64(%rsp),%edx + + movq 0(%r8),%r11 + movq 8(%r8),%r12 + subq $16,%r10 + jz .Lcbc_fast_dec_in_place_done + + movq %r11,0+64(%rsp) + movq %r12,8+64(%rsp) + + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + leaq 16(%r8),%r8 + leaq 16(%r9),%r9 + movq %r10,40(%rsp) + jmp .Lcbc_fast_dec_in_place_loop +.Lcbc_fast_dec_in_place_done: + movq 56(%rsp),%rdi + movq %r11,0(%rdi) + movq %r12,8(%rdi) + + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + +.align 4 +.Lcbc_fast_cleanup: + cmpl $0,80+240(%rsp) + leaq 80(%rsp),%rdi + je .Lcbc_exit + movl $30,%ecx + xorq %rax,%rax +.long 0x90AB48F3 + + jmp .Lcbc_exit + + +.align 16 +.Lcbc_slow_prologue: +.cfi_restore_state + + leaq -88(%rsp),%rbp + andq $-64,%rbp + + leaq -88-63(%rcx),%r10 + subq %rbp,%r10 + negq %r10 + andq $0x3c0,%r10 + subq %r10,%rbp + + xchgq %rsp,%rbp +.cfi_def_cfa_register %rbp + + movq %rbp,16(%rsp) +.cfi_escape 0x0f,0x05,0x77,0x10,0x06,0x23,0x40 +.Lcbc_slow_body: + + + + + movq %r8,56(%rsp) + movq %r8,%rbp + movq %r9,%rbx + movq %rsi,%r9 + movq %rdi,%r8 + movq %rcx,%r15 + movq %rdx,%r10 + + movl 240(%r15),%eax + movq %r15,0(%rsp) + shll $4,%eax + leaq (%r15,%rax,1),%rax + movq %rax,8(%rsp) + + + leaq 2048(%r14),%r14 + leaq 768-8(%rsp),%rax + subq %r14,%rax + andq $0x300,%rax + leaq (%r14,%rax,1),%r14 + + cmpq $0,%rbx + je .LSLOW_DECRYPT + + + testq $-16,%r10 + movl 0(%rbp),%eax + movl 4(%rbp),%ebx + movl 8(%rbp),%ecx + movl 12(%rbp),%edx + jz .Lcbc_slow_enc_tail + +.align 4 +.Lcbc_slow_enc_loop: + xorl 0(%r8),%eax + xorl 4(%r8),%ebx + xorl 8(%r8),%ecx + xorl 12(%r8),%edx + movq 0(%rsp),%r15 + movq %r8,24(%rsp) + movq %r9,32(%rsp) + movq %r10,40(%rsp) + + call _x86_64_AES_encrypt_compact + + movq 24(%rsp),%r8 + movq 32(%rsp),%r9 + movq 40(%rsp),%r10 + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + leaq 16(%r8),%r8 + leaq 16(%r9),%r9 + subq $16,%r10 + testq $-16,%r10 + jnz .Lcbc_slow_enc_loop + testq $15,%r10 + jnz .Lcbc_slow_enc_tail + movq 56(%rsp),%rbp + movl %eax,0(%rbp) + movl %ebx,4(%rbp) + movl %ecx,8(%rbp) + movl %edx,12(%rbp) + + jmp .Lcbc_exit + +.align 4 +.Lcbc_slow_enc_tail: + movq %rax,%r11 + movq %rcx,%r12 + movq %r10,%rcx + movq %r8,%rsi + movq %r9,%rdi +.long 0x9066A4F3 + movq $16,%rcx + subq %r10,%rcx + xorq %rax,%rax +.long 0x9066AAF3 + movq %r9,%r8 + movq $16,%r10 + movq %r11,%rax + movq %r12,%rcx + jmp .Lcbc_slow_enc_loop + +.align 16 +.LSLOW_DECRYPT: + shrq $3,%rax + addq %rax,%r14 + + movq 0(%rbp),%r11 + movq 8(%rbp),%r12 + movq %r11,0+64(%rsp) + movq %r12,8+64(%rsp) + +.align 4 +.Lcbc_slow_dec_loop: + movl 0(%r8),%eax + movl 4(%r8),%ebx + movl 8(%r8),%ecx + movl 12(%r8),%edx + movq 0(%rsp),%r15 + movq %r8,24(%rsp) + movq %r9,32(%rsp) + movq %r10,40(%rsp) + + call _x86_64_AES_decrypt_compact + + movq 24(%rsp),%r8 + movq 32(%rsp),%r9 + movq 40(%rsp),%r10 + xorl 0+64(%rsp),%eax + xorl 4+64(%rsp),%ebx + xorl 8+64(%rsp),%ecx + xorl 12+64(%rsp),%edx + + movq 0(%r8),%r11 + movq 8(%r8),%r12 + subq $16,%r10 + jc .Lcbc_slow_dec_partial + jz .Lcbc_slow_dec_done + + movq %r11,0+64(%rsp) + movq %r12,8+64(%rsp) + + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + leaq 16(%r8),%r8 + leaq 16(%r9),%r9 + jmp .Lcbc_slow_dec_loop +.Lcbc_slow_dec_done: + movq 56(%rsp),%rdi + movq %r11,0(%rdi) + movq %r12,8(%rdi) + + movl %eax,0(%r9) + movl %ebx,4(%r9) + movl %ecx,8(%r9) + movl %edx,12(%r9) + + jmp .Lcbc_exit + +.align 4 +.Lcbc_slow_dec_partial: + movq 56(%rsp),%rdi + movq %r11,0(%rdi) + movq %r12,8(%rdi) + + movl %eax,0+64(%rsp) + movl %ebx,4+64(%rsp) + movl %ecx,8+64(%rsp) + movl %edx,12+64(%rsp) + + movq %r9,%rdi + leaq 64(%rsp),%rsi + leaq 16(%r10),%rcx +.long 0x9066A4F3 + jmp .Lcbc_exit + +.align 16 +.Lcbc_exit: + movq 16(%rsp),%rsi +.cfi_def_cfa %rsi,64 + movq (%rsi),%r15 +.cfi_restore %r15 + movq 8(%rsi),%r14 +.cfi_restore %r14 + movq 16(%rsi),%r13 +.cfi_restore %r13 + movq 24(%rsi),%r12 +.cfi_restore %r12 + movq 32(%rsi),%rbp +.cfi_restore %rbp + movq 40(%rsi),%rbx +.cfi_restore %rbx + leaq 48(%rsi),%rsp +.cfi_def_cfa %rsp,16 +.Lcbc_popfq: + popfq + + +.cfi_adjust_cfa_offset -8 +.Lcbc_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size AES_cbc_encrypt,.-AES_cbc_encrypt +.align 64 +.LAES_Te: +.long 0xa56363c6,0xa56363c6 +.long 0x847c7cf8,0x847c7cf8 +.long 0x997777ee,0x997777ee +.long 0x8d7b7bf6,0x8d7b7bf6 +.long 0x0df2f2ff,0x0df2f2ff +.long 0xbd6b6bd6,0xbd6b6bd6 +.long 0xb16f6fde,0xb16f6fde +.long 0x54c5c591,0x54c5c591 +.long 0x50303060,0x50303060 +.long 0x03010102,0x03010102 +.long 0xa96767ce,0xa96767ce +.long 0x7d2b2b56,0x7d2b2b56 +.long 0x19fefee7,0x19fefee7 +.long 0x62d7d7b5,0x62d7d7b5 +.long 0xe6abab4d,0xe6abab4d +.long 0x9a7676ec,0x9a7676ec +.long 0x45caca8f,0x45caca8f +.long 0x9d82821f,0x9d82821f +.long 0x40c9c989,0x40c9c989 +.long 0x877d7dfa,0x877d7dfa +.long 0x15fafaef,0x15fafaef +.long 0xeb5959b2,0xeb5959b2 +.long 0xc947478e,0xc947478e +.long 0x0bf0f0fb,0x0bf0f0fb +.long 0xecadad41,0xecadad41 +.long 0x67d4d4b3,0x67d4d4b3 +.long 0xfda2a25f,0xfda2a25f +.long 0xeaafaf45,0xeaafaf45 +.long 0xbf9c9c23,0xbf9c9c23 +.long 0xf7a4a453,0xf7a4a453 +.long 0x967272e4,0x967272e4 +.long 0x5bc0c09b,0x5bc0c09b +.long 0xc2b7b775,0xc2b7b775 +.long 0x1cfdfde1,0x1cfdfde1 +.long 0xae93933d,0xae93933d +.long 0x6a26264c,0x6a26264c +.long 0x5a36366c,0x5a36366c +.long 0x413f3f7e,0x413f3f7e +.long 0x02f7f7f5,0x02f7f7f5 +.long 0x4fcccc83,0x4fcccc83 +.long 0x5c343468,0x5c343468 +.long 0xf4a5a551,0xf4a5a551 +.long 0x34e5e5d1,0x34e5e5d1 +.long 0x08f1f1f9,0x08f1f1f9 +.long 0x937171e2,0x937171e2 +.long 0x73d8d8ab,0x73d8d8ab +.long 0x53313162,0x53313162 +.long 0x3f15152a,0x3f15152a +.long 0x0c040408,0x0c040408 +.long 0x52c7c795,0x52c7c795 +.long 0x65232346,0x65232346 +.long 0x5ec3c39d,0x5ec3c39d +.long 0x28181830,0x28181830 +.long 0xa1969637,0xa1969637 +.long 0x0f05050a,0x0f05050a +.long 0xb59a9a2f,0xb59a9a2f +.long 0x0907070e,0x0907070e +.long 0x36121224,0x36121224 +.long 0x9b80801b,0x9b80801b +.long 0x3de2e2df,0x3de2e2df +.long 0x26ebebcd,0x26ebebcd +.long 0x6927274e,0x6927274e +.long 0xcdb2b27f,0xcdb2b27f +.long 0x9f7575ea,0x9f7575ea +.long 0x1b090912,0x1b090912 +.long 0x9e83831d,0x9e83831d +.long 0x742c2c58,0x742c2c58 +.long 0x2e1a1a34,0x2e1a1a34 +.long 0x2d1b1b36,0x2d1b1b36 +.long 0xb26e6edc,0xb26e6edc +.long 0xee5a5ab4,0xee5a5ab4 +.long 0xfba0a05b,0xfba0a05b +.long 0xf65252a4,0xf65252a4 +.long 0x4d3b3b76,0x4d3b3b76 +.long 0x61d6d6b7,0x61d6d6b7 +.long 0xceb3b37d,0xceb3b37d +.long 0x7b292952,0x7b292952 +.long 0x3ee3e3dd,0x3ee3e3dd +.long 0x712f2f5e,0x712f2f5e +.long 0x97848413,0x97848413 +.long 0xf55353a6,0xf55353a6 +.long 0x68d1d1b9,0x68d1d1b9 +.long 0x00000000,0x00000000 +.long 0x2cededc1,0x2cededc1 +.long 0x60202040,0x60202040 +.long 0x1ffcfce3,0x1ffcfce3 +.long 0xc8b1b179,0xc8b1b179 +.long 0xed5b5bb6,0xed5b5bb6 +.long 0xbe6a6ad4,0xbe6a6ad4 +.long 0x46cbcb8d,0x46cbcb8d +.long 0xd9bebe67,0xd9bebe67 +.long 0x4b393972,0x4b393972 +.long 0xde4a4a94,0xde4a4a94 +.long 0xd44c4c98,0xd44c4c98 +.long 0xe85858b0,0xe85858b0 +.long 0x4acfcf85,0x4acfcf85 +.long 0x6bd0d0bb,0x6bd0d0bb +.long 0x2aefefc5,0x2aefefc5 +.long 0xe5aaaa4f,0xe5aaaa4f +.long 0x16fbfbed,0x16fbfbed +.long 0xc5434386,0xc5434386 +.long 0xd74d4d9a,0xd74d4d9a +.long 0x55333366,0x55333366 +.long 0x94858511,0x94858511 +.long 0xcf45458a,0xcf45458a +.long 0x10f9f9e9,0x10f9f9e9 +.long 0x06020204,0x06020204 +.long 0x817f7ffe,0x817f7ffe +.long 0xf05050a0,0xf05050a0 +.long 0x443c3c78,0x443c3c78 +.long 0xba9f9f25,0xba9f9f25 +.long 0xe3a8a84b,0xe3a8a84b +.long 0xf35151a2,0xf35151a2 +.long 0xfea3a35d,0xfea3a35d +.long 0xc0404080,0xc0404080 +.long 0x8a8f8f05,0x8a8f8f05 +.long 0xad92923f,0xad92923f +.long 0xbc9d9d21,0xbc9d9d21 +.long 0x48383870,0x48383870 +.long 0x04f5f5f1,0x04f5f5f1 +.long 0xdfbcbc63,0xdfbcbc63 +.long 0xc1b6b677,0xc1b6b677 +.long 0x75dadaaf,0x75dadaaf +.long 0x63212142,0x63212142 +.long 0x30101020,0x30101020 +.long 0x1affffe5,0x1affffe5 +.long 0x0ef3f3fd,0x0ef3f3fd +.long 0x6dd2d2bf,0x6dd2d2bf +.long 0x4ccdcd81,0x4ccdcd81 +.long 0x140c0c18,0x140c0c18 +.long 0x35131326,0x35131326 +.long 0x2fececc3,0x2fececc3 +.long 0xe15f5fbe,0xe15f5fbe +.long 0xa2979735,0xa2979735 +.long 0xcc444488,0xcc444488 +.long 0x3917172e,0x3917172e +.long 0x57c4c493,0x57c4c493 +.long 0xf2a7a755,0xf2a7a755 +.long 0x827e7efc,0x827e7efc +.long 0x473d3d7a,0x473d3d7a +.long 0xac6464c8,0xac6464c8 +.long 0xe75d5dba,0xe75d5dba +.long 0x2b191932,0x2b191932 +.long 0x957373e6,0x957373e6 +.long 0xa06060c0,0xa06060c0 +.long 0x98818119,0x98818119 +.long 0xd14f4f9e,0xd14f4f9e +.long 0x7fdcdca3,0x7fdcdca3 +.long 0x66222244,0x66222244 +.long 0x7e2a2a54,0x7e2a2a54 +.long 0xab90903b,0xab90903b +.long 0x8388880b,0x8388880b +.long 0xca46468c,0xca46468c +.long 0x29eeeec7,0x29eeeec7 +.long 0xd3b8b86b,0xd3b8b86b +.long 0x3c141428,0x3c141428 +.long 0x79dedea7,0x79dedea7 +.long 0xe25e5ebc,0xe25e5ebc +.long 0x1d0b0b16,0x1d0b0b16 +.long 0x76dbdbad,0x76dbdbad +.long 0x3be0e0db,0x3be0e0db +.long 0x56323264,0x56323264 +.long 0x4e3a3a74,0x4e3a3a74 +.long 0x1e0a0a14,0x1e0a0a14 +.long 0xdb494992,0xdb494992 +.long 0x0a06060c,0x0a06060c +.long 0x6c242448,0x6c242448 +.long 0xe45c5cb8,0xe45c5cb8 +.long 0x5dc2c29f,0x5dc2c29f +.long 0x6ed3d3bd,0x6ed3d3bd +.long 0xefacac43,0xefacac43 +.long 0xa66262c4,0xa66262c4 +.long 0xa8919139,0xa8919139 +.long 0xa4959531,0xa4959531 +.long 0x37e4e4d3,0x37e4e4d3 +.long 0x8b7979f2,0x8b7979f2 +.long 0x32e7e7d5,0x32e7e7d5 +.long 0x43c8c88b,0x43c8c88b +.long 0x5937376e,0x5937376e +.long 0xb76d6dda,0xb76d6dda +.long 0x8c8d8d01,0x8c8d8d01 +.long 0x64d5d5b1,0x64d5d5b1 +.long 0xd24e4e9c,0xd24e4e9c +.long 0xe0a9a949,0xe0a9a949 +.long 0xb46c6cd8,0xb46c6cd8 +.long 0xfa5656ac,0xfa5656ac +.long 0x07f4f4f3,0x07f4f4f3 +.long 0x25eaeacf,0x25eaeacf +.long 0xaf6565ca,0xaf6565ca +.long 0x8e7a7af4,0x8e7a7af4 +.long 0xe9aeae47,0xe9aeae47 +.long 0x18080810,0x18080810 +.long 0xd5baba6f,0xd5baba6f +.long 0x887878f0,0x887878f0 +.long 0x6f25254a,0x6f25254a +.long 0x722e2e5c,0x722e2e5c +.long 0x241c1c38,0x241c1c38 +.long 0xf1a6a657,0xf1a6a657 +.long 0xc7b4b473,0xc7b4b473 +.long 0x51c6c697,0x51c6c697 +.long 0x23e8e8cb,0x23e8e8cb +.long 0x7cdddda1,0x7cdddda1 +.long 0x9c7474e8,0x9c7474e8 +.long 0x211f1f3e,0x211f1f3e +.long 0xdd4b4b96,0xdd4b4b96 +.long 0xdcbdbd61,0xdcbdbd61 +.long 0x868b8b0d,0x868b8b0d +.long 0x858a8a0f,0x858a8a0f +.long 0x907070e0,0x907070e0 +.long 0x423e3e7c,0x423e3e7c +.long 0xc4b5b571,0xc4b5b571 +.long 0xaa6666cc,0xaa6666cc +.long 0xd8484890,0xd8484890 +.long 0x05030306,0x05030306 +.long 0x01f6f6f7,0x01f6f6f7 +.long 0x120e0e1c,0x120e0e1c +.long 0xa36161c2,0xa36161c2 +.long 0x5f35356a,0x5f35356a +.long 0xf95757ae,0xf95757ae +.long 0xd0b9b969,0xd0b9b969 +.long 0x91868617,0x91868617 +.long 0x58c1c199,0x58c1c199 +.long 0x271d1d3a,0x271d1d3a +.long 0xb99e9e27,0xb99e9e27 +.long 0x38e1e1d9,0x38e1e1d9 +.long 0x13f8f8eb,0x13f8f8eb +.long 0xb398982b,0xb398982b +.long 0x33111122,0x33111122 +.long 0xbb6969d2,0xbb6969d2 +.long 0x70d9d9a9,0x70d9d9a9 +.long 0x898e8e07,0x898e8e07 +.long 0xa7949433,0xa7949433 +.long 0xb69b9b2d,0xb69b9b2d +.long 0x221e1e3c,0x221e1e3c +.long 0x92878715,0x92878715 +.long 0x20e9e9c9,0x20e9e9c9 +.long 0x49cece87,0x49cece87 +.long 0xff5555aa,0xff5555aa +.long 0x78282850,0x78282850 +.long 0x7adfdfa5,0x7adfdfa5 +.long 0x8f8c8c03,0x8f8c8c03 +.long 0xf8a1a159,0xf8a1a159 +.long 0x80898909,0x80898909 +.long 0x170d0d1a,0x170d0d1a +.long 0xdabfbf65,0xdabfbf65 +.long 0x31e6e6d7,0x31e6e6d7 +.long 0xc6424284,0xc6424284 +.long 0xb86868d0,0xb86868d0 +.long 0xc3414182,0xc3414182 +.long 0xb0999929,0xb0999929 +.long 0x772d2d5a,0x772d2d5a +.long 0x110f0f1e,0x110f0f1e +.long 0xcbb0b07b,0xcbb0b07b +.long 0xfc5454a8,0xfc5454a8 +.long 0xd6bbbb6d,0xd6bbbb6d +.long 0x3a16162c,0x3a16162c +.byte 0x63,0x7c,0x77,0x7b,0xf2,0x6b,0x6f,0xc5 +.byte 0x30,0x01,0x67,0x2b,0xfe,0xd7,0xab,0x76 +.byte 0xca,0x82,0xc9,0x7d,0xfa,0x59,0x47,0xf0 +.byte 0xad,0xd4,0xa2,0xaf,0x9c,0xa4,0x72,0xc0 +.byte 0xb7,0xfd,0x93,0x26,0x36,0x3f,0xf7,0xcc +.byte 0x34,0xa5,0xe5,0xf1,0x71,0xd8,0x31,0x15 +.byte 0x04,0xc7,0x23,0xc3,0x18,0x96,0x05,0x9a +.byte 0x07,0x12,0x80,0xe2,0xeb,0x27,0xb2,0x75 +.byte 0x09,0x83,0x2c,0x1a,0x1b,0x6e,0x5a,0xa0 +.byte 0x52,0x3b,0xd6,0xb3,0x29,0xe3,0x2f,0x84 +.byte 0x53,0xd1,0x00,0xed,0x20,0xfc,0xb1,0x5b +.byte 0x6a,0xcb,0xbe,0x39,0x4a,0x4c,0x58,0xcf +.byte 0xd0,0xef,0xaa,0xfb,0x43,0x4d,0x33,0x85 +.byte 0x45,0xf9,0x02,0x7f,0x50,0x3c,0x9f,0xa8 +.byte 0x51,0xa3,0x40,0x8f,0x92,0x9d,0x38,0xf5 +.byte 0xbc,0xb6,0xda,0x21,0x10,0xff,0xf3,0xd2 +.byte 0xcd,0x0c,0x13,0xec,0x5f,0x97,0x44,0x17 +.byte 0xc4,0xa7,0x7e,0x3d,0x64,0x5d,0x19,0x73 +.byte 0x60,0x81,0x4f,0xdc,0x22,0x2a,0x90,0x88 +.byte 0x46,0xee,0xb8,0x14,0xde,0x5e,0x0b,0xdb +.byte 0xe0,0x32,0x3a,0x0a,0x49,0x06,0x24,0x5c +.byte 0xc2,0xd3,0xac,0x62,0x91,0x95,0xe4,0x79 +.byte 0xe7,0xc8,0x37,0x6d,0x8d,0xd5,0x4e,0xa9 +.byte 0x6c,0x56,0xf4,0xea,0x65,0x7a,0xae,0x08 +.byte 0xba,0x78,0x25,0x2e,0x1c,0xa6,0xb4,0xc6 +.byte 0xe8,0xdd,0x74,0x1f,0x4b,0xbd,0x8b,0x8a +.byte 0x70,0x3e,0xb5,0x66,0x48,0x03,0xf6,0x0e +.byte 0x61,0x35,0x57,0xb9,0x86,0xc1,0x1d,0x9e +.byte 0xe1,0xf8,0x98,0x11,0x69,0xd9,0x8e,0x94 +.byte 0x9b,0x1e,0x87,0xe9,0xce,0x55,0x28,0xdf +.byte 0x8c,0xa1,0x89,0x0d,0xbf,0xe6,0x42,0x68 +.byte 0x41,0x99,0x2d,0x0f,0xb0,0x54,0xbb,0x16 +.byte 0x63,0x7c,0x77,0x7b,0xf2,0x6b,0x6f,0xc5 +.byte 0x30,0x01,0x67,0x2b,0xfe,0xd7,0xab,0x76 +.byte 0xca,0x82,0xc9,0x7d,0xfa,0x59,0x47,0xf0 +.byte 0xad,0xd4,0xa2,0xaf,0x9c,0xa4,0x72,0xc0 +.byte 0xb7,0xfd,0x93,0x26,0x36,0x3f,0xf7,0xcc +.byte 0x34,0xa5,0xe5,0xf1,0x71,0xd8,0x31,0x15 +.byte 0x04,0xc7,0x23,0xc3,0x18,0x96,0x05,0x9a +.byte 0x07,0x12,0x80,0xe2,0xeb,0x27,0xb2,0x75 +.byte 0x09,0x83,0x2c,0x1a,0x1b,0x6e,0x5a,0xa0 +.byte 0x52,0x3b,0xd6,0xb3,0x29,0xe3,0x2f,0x84 +.byte 0x53,0xd1,0x00,0xed,0x20,0xfc,0xb1,0x5b +.byte 0x6a,0xcb,0xbe,0x39,0x4a,0x4c,0x58,0xcf +.byte 0xd0,0xef,0xaa,0xfb,0x43,0x4d,0x33,0x85 +.byte 0x45,0xf9,0x02,0x7f,0x50,0x3c,0x9f,0xa8 +.byte 0x51,0xa3,0x40,0x8f,0x92,0x9d,0x38,0xf5 +.byte 0xbc,0xb6,0xda,0x21,0x10,0xff,0xf3,0xd2 +.byte 0xcd,0x0c,0x13,0xec,0x5f,0x97,0x44,0x17 +.byte 0xc4,0xa7,0x7e,0x3d,0x64,0x5d,0x19,0x73 +.byte 0x60,0x81,0x4f,0xdc,0x22,0x2a,0x90,0x88 +.byte 0x46,0xee,0xb8,0x14,0xde,0x5e,0x0b,0xdb +.byte 0xe0,0x32,0x3a,0x0a,0x49,0x06,0x24,0x5c +.byte 0xc2,0xd3,0xac,0x62,0x91,0x95,0xe4,0x79 +.byte 0xe7,0xc8,0x37,0x6d,0x8d,0xd5,0x4e,0xa9 +.byte 0x6c,0x56,0xf4,0xea,0x65,0x7a,0xae,0x08 +.byte 0xba,0x78,0x25,0x2e,0x1c,0xa6,0xb4,0xc6 +.byte 0xe8,0xdd,0x74,0x1f,0x4b,0xbd,0x8b,0x8a +.byte 0x70,0x3e,0xb5,0x66,0x48,0x03,0xf6,0x0e +.byte 0x61,0x35,0x57,0xb9,0x86,0xc1,0x1d,0x9e +.byte 0xe1,0xf8,0x98,0x11,0x69,0xd9,0x8e,0x94 +.byte 0x9b,0x1e,0x87,0xe9,0xce,0x55,0x28,0xdf +.byte 0x8c,0xa1,0x89,0x0d,0xbf,0xe6,0x42,0x68 +.byte 0x41,0x99,0x2d,0x0f,0xb0,0x54,0xbb,0x16 +.byte 0x63,0x7c,0x77,0x7b,0xf2,0x6b,0x6f,0xc5 +.byte 0x30,0x01,0x67,0x2b,0xfe,0xd7,0xab,0x76 +.byte 0xca,0x82,0xc9,0x7d,0xfa,0x59,0x47,0xf0 +.byte 0xad,0xd4,0xa2,0xaf,0x9c,0xa4,0x72,0xc0 +.byte 0xb7,0xfd,0x93,0x26,0x36,0x3f,0xf7,0xcc +.byte 0x34,0xa5,0xe5,0xf1,0x71,0xd8,0x31,0x15 +.byte 0x04,0xc7,0x23,0xc3,0x18,0x96,0x05,0x9a +.byte 0x07,0x12,0x80,0xe2,0xeb,0x27,0xb2,0x75 +.byte 0x09,0x83,0x2c,0x1a,0x1b,0x6e,0x5a,0xa0 +.byte 0x52,0x3b,0xd6,0xb3,0x29,0xe3,0x2f,0x84 +.byte 0x53,0xd1,0x00,0xed,0x20,0xfc,0xb1,0x5b +.byte 0x6a,0xcb,0xbe,0x39,0x4a,0x4c,0x58,0xcf +.byte 0xd0,0xef,0xaa,0xfb,0x43,0x4d,0x33,0x85 +.byte 0x45,0xf9,0x02,0x7f,0x50,0x3c,0x9f,0xa8 +.byte 0x51,0xa3,0x40,0x8f,0x92,0x9d,0x38,0xf5 +.byte 0xbc,0xb6,0xda,0x21,0x10,0xff,0xf3,0xd2 +.byte 0xcd,0x0c,0x13,0xec,0x5f,0x97,0x44,0x17 +.byte 0xc4,0xa7,0x7e,0x3d,0x64,0x5d,0x19,0x73 +.byte 0x60,0x81,0x4f,0xdc,0x22,0x2a,0x90,0x88 +.byte 0x46,0xee,0xb8,0x14,0xde,0x5e,0x0b,0xdb +.byte 0xe0,0x32,0x3a,0x0a,0x49,0x06,0x24,0x5c +.byte 0xc2,0xd3,0xac,0x62,0x91,0x95,0xe4,0x79 +.byte 0xe7,0xc8,0x37,0x6d,0x8d,0xd5,0x4e,0xa9 +.byte 0x6c,0x56,0xf4,0xea,0x65,0x7a,0xae,0x08 +.byte 0xba,0x78,0x25,0x2e,0x1c,0xa6,0xb4,0xc6 +.byte 0xe8,0xdd,0x74,0x1f,0x4b,0xbd,0x8b,0x8a +.byte 0x70,0x3e,0xb5,0x66,0x48,0x03,0xf6,0x0e +.byte 0x61,0x35,0x57,0xb9,0x86,0xc1,0x1d,0x9e +.byte 0xe1,0xf8,0x98,0x11,0x69,0xd9,0x8e,0x94 +.byte 0x9b,0x1e,0x87,0xe9,0xce,0x55,0x28,0xdf +.byte 0x8c,0xa1,0x89,0x0d,0xbf,0xe6,0x42,0x68 +.byte 0x41,0x99,0x2d,0x0f,0xb0,0x54,0xbb,0x16 +.byte 0x63,0x7c,0x77,0x7b,0xf2,0x6b,0x6f,0xc5 +.byte 0x30,0x01,0x67,0x2b,0xfe,0xd7,0xab,0x76 +.byte 0xca,0x82,0xc9,0x7d,0xfa,0x59,0x47,0xf0 +.byte 0xad,0xd4,0xa2,0xaf,0x9c,0xa4,0x72,0xc0 +.byte 0xb7,0xfd,0x93,0x26,0x36,0x3f,0xf7,0xcc +.byte 0x34,0xa5,0xe5,0xf1,0x71,0xd8,0x31,0x15 +.byte 0x04,0xc7,0x23,0xc3,0x18,0x96,0x05,0x9a +.byte 0x07,0x12,0x80,0xe2,0xeb,0x27,0xb2,0x75 +.byte 0x09,0x83,0x2c,0x1a,0x1b,0x6e,0x5a,0xa0 +.byte 0x52,0x3b,0xd6,0xb3,0x29,0xe3,0x2f,0x84 +.byte 0x53,0xd1,0x00,0xed,0x20,0xfc,0xb1,0x5b +.byte 0x6a,0xcb,0xbe,0x39,0x4a,0x4c,0x58,0xcf +.byte 0xd0,0xef,0xaa,0xfb,0x43,0x4d,0x33,0x85 +.byte 0x45,0xf9,0x02,0x7f,0x50,0x3c,0x9f,0xa8 +.byte 0x51,0xa3,0x40,0x8f,0x92,0x9d,0x38,0xf5 +.byte 0xbc,0xb6,0xda,0x21,0x10,0xff,0xf3,0xd2 +.byte 0xcd,0x0c,0x13,0xec,0x5f,0x97,0x44,0x17 +.byte 0xc4,0xa7,0x7e,0x3d,0x64,0x5d,0x19,0x73 +.byte 0x60,0x81,0x4f,0xdc,0x22,0x2a,0x90,0x88 +.byte 0x46,0xee,0xb8,0x14,0xde,0x5e,0x0b,0xdb +.byte 0xe0,0x32,0x3a,0x0a,0x49,0x06,0x24,0x5c +.byte 0xc2,0xd3,0xac,0x62,0x91,0x95,0xe4,0x79 +.byte 0xe7,0xc8,0x37,0x6d,0x8d,0xd5,0x4e,0xa9 +.byte 0x6c,0x56,0xf4,0xea,0x65,0x7a,0xae,0x08 +.byte 0xba,0x78,0x25,0x2e,0x1c,0xa6,0xb4,0xc6 +.byte 0xe8,0xdd,0x74,0x1f,0x4b,0xbd,0x8b,0x8a +.byte 0x70,0x3e,0xb5,0x66,0x48,0x03,0xf6,0x0e +.byte 0x61,0x35,0x57,0xb9,0x86,0xc1,0x1d,0x9e +.byte 0xe1,0xf8,0x98,0x11,0x69,0xd9,0x8e,0x94 +.byte 0x9b,0x1e,0x87,0xe9,0xce,0x55,0x28,0xdf +.byte 0x8c,0xa1,0x89,0x0d,0xbf,0xe6,0x42,0x68 +.byte 0x41,0x99,0x2d,0x0f,0xb0,0x54,0xbb,0x16 +.long 0x00000001, 0x00000002, 0x00000004, 0x00000008 +.long 0x00000010, 0x00000020, 0x00000040, 0x00000080 +.long 0x0000001b, 0x00000036, 0x80808080, 0x80808080 +.long 0xfefefefe, 0xfefefefe, 0x1b1b1b1b, 0x1b1b1b1b +.align 64 +.LAES_Td: +.long 0x50a7f451,0x50a7f451 +.long 0x5365417e,0x5365417e +.long 0xc3a4171a,0xc3a4171a +.long 0x965e273a,0x965e273a +.long 0xcb6bab3b,0xcb6bab3b +.long 0xf1459d1f,0xf1459d1f +.long 0xab58faac,0xab58faac +.long 0x9303e34b,0x9303e34b +.long 0x55fa3020,0x55fa3020 +.long 0xf66d76ad,0xf66d76ad +.long 0x9176cc88,0x9176cc88 +.long 0x254c02f5,0x254c02f5 +.long 0xfcd7e54f,0xfcd7e54f +.long 0xd7cb2ac5,0xd7cb2ac5 +.long 0x80443526,0x80443526 +.long 0x8fa362b5,0x8fa362b5 +.long 0x495ab1de,0x495ab1de +.long 0x671bba25,0x671bba25 +.long 0x980eea45,0x980eea45 +.long 0xe1c0fe5d,0xe1c0fe5d +.long 0x02752fc3,0x02752fc3 +.long 0x12f04c81,0x12f04c81 +.long 0xa397468d,0xa397468d +.long 0xc6f9d36b,0xc6f9d36b +.long 0xe75f8f03,0xe75f8f03 +.long 0x959c9215,0x959c9215 +.long 0xeb7a6dbf,0xeb7a6dbf +.long 0xda595295,0xda595295 +.long 0x2d83bed4,0x2d83bed4 +.long 0xd3217458,0xd3217458 +.long 0x2969e049,0x2969e049 +.long 0x44c8c98e,0x44c8c98e +.long 0x6a89c275,0x6a89c275 +.long 0x78798ef4,0x78798ef4 +.long 0x6b3e5899,0x6b3e5899 +.long 0xdd71b927,0xdd71b927 +.long 0xb64fe1be,0xb64fe1be +.long 0x17ad88f0,0x17ad88f0 +.long 0x66ac20c9,0x66ac20c9 +.long 0xb43ace7d,0xb43ace7d +.long 0x184adf63,0x184adf63 +.long 0x82311ae5,0x82311ae5 +.long 0x60335197,0x60335197 +.long 0x457f5362,0x457f5362 +.long 0xe07764b1,0xe07764b1 +.long 0x84ae6bbb,0x84ae6bbb +.long 0x1ca081fe,0x1ca081fe +.long 0x942b08f9,0x942b08f9 +.long 0x58684870,0x58684870 +.long 0x19fd458f,0x19fd458f +.long 0x876cde94,0x876cde94 +.long 0xb7f87b52,0xb7f87b52 +.long 0x23d373ab,0x23d373ab +.long 0xe2024b72,0xe2024b72 +.long 0x578f1fe3,0x578f1fe3 +.long 0x2aab5566,0x2aab5566 +.long 0x0728ebb2,0x0728ebb2 +.long 0x03c2b52f,0x03c2b52f +.long 0x9a7bc586,0x9a7bc586 +.long 0xa50837d3,0xa50837d3 +.long 0xf2872830,0xf2872830 +.long 0xb2a5bf23,0xb2a5bf23 +.long 0xba6a0302,0xba6a0302 +.long 0x5c8216ed,0x5c8216ed +.long 0x2b1ccf8a,0x2b1ccf8a +.long 0x92b479a7,0x92b479a7 +.long 0xf0f207f3,0xf0f207f3 +.long 0xa1e2694e,0xa1e2694e +.long 0xcdf4da65,0xcdf4da65 +.long 0xd5be0506,0xd5be0506 +.long 0x1f6234d1,0x1f6234d1 +.long 0x8afea6c4,0x8afea6c4 +.long 0x9d532e34,0x9d532e34 +.long 0xa055f3a2,0xa055f3a2 +.long 0x32e18a05,0x32e18a05 +.long 0x75ebf6a4,0x75ebf6a4 +.long 0x39ec830b,0x39ec830b +.long 0xaaef6040,0xaaef6040 +.long 0x069f715e,0x069f715e +.long 0x51106ebd,0x51106ebd +.long 0xf98a213e,0xf98a213e +.long 0x3d06dd96,0x3d06dd96 +.long 0xae053edd,0xae053edd +.long 0x46bde64d,0x46bde64d +.long 0xb58d5491,0xb58d5491 +.long 0x055dc471,0x055dc471 +.long 0x6fd40604,0x6fd40604 +.long 0xff155060,0xff155060 +.long 0x24fb9819,0x24fb9819 +.long 0x97e9bdd6,0x97e9bdd6 +.long 0xcc434089,0xcc434089 +.long 0x779ed967,0x779ed967 +.long 0xbd42e8b0,0xbd42e8b0 +.long 0x888b8907,0x888b8907 +.long 0x385b19e7,0x385b19e7 +.long 0xdbeec879,0xdbeec879 +.long 0x470a7ca1,0x470a7ca1 +.long 0xe90f427c,0xe90f427c +.long 0xc91e84f8,0xc91e84f8 +.long 0x00000000,0x00000000 +.long 0x83868009,0x83868009 +.long 0x48ed2b32,0x48ed2b32 +.long 0xac70111e,0xac70111e +.long 0x4e725a6c,0x4e725a6c +.long 0xfbff0efd,0xfbff0efd +.long 0x5638850f,0x5638850f +.long 0x1ed5ae3d,0x1ed5ae3d +.long 0x27392d36,0x27392d36 +.long 0x64d90f0a,0x64d90f0a +.long 0x21a65c68,0x21a65c68 +.long 0xd1545b9b,0xd1545b9b +.long 0x3a2e3624,0x3a2e3624 +.long 0xb1670a0c,0xb1670a0c +.long 0x0fe75793,0x0fe75793 +.long 0xd296eeb4,0xd296eeb4 +.long 0x9e919b1b,0x9e919b1b +.long 0x4fc5c080,0x4fc5c080 +.long 0xa220dc61,0xa220dc61 +.long 0x694b775a,0x694b775a +.long 0x161a121c,0x161a121c +.long 0x0aba93e2,0x0aba93e2 +.long 0xe52aa0c0,0xe52aa0c0 +.long 0x43e0223c,0x43e0223c +.long 0x1d171b12,0x1d171b12 +.long 0x0b0d090e,0x0b0d090e +.long 0xadc78bf2,0xadc78bf2 +.long 0xb9a8b62d,0xb9a8b62d +.long 0xc8a91e14,0xc8a91e14 +.long 0x8519f157,0x8519f157 +.long 0x4c0775af,0x4c0775af +.long 0xbbdd99ee,0xbbdd99ee +.long 0xfd607fa3,0xfd607fa3 +.long 0x9f2601f7,0x9f2601f7 +.long 0xbcf5725c,0xbcf5725c +.long 0xc53b6644,0xc53b6644 +.long 0x347efb5b,0x347efb5b +.long 0x7629438b,0x7629438b +.long 0xdcc623cb,0xdcc623cb +.long 0x68fcedb6,0x68fcedb6 +.long 0x63f1e4b8,0x63f1e4b8 +.long 0xcadc31d7,0xcadc31d7 +.long 0x10856342,0x10856342 +.long 0x40229713,0x40229713 +.long 0x2011c684,0x2011c684 +.long 0x7d244a85,0x7d244a85 +.long 0xf83dbbd2,0xf83dbbd2 +.long 0x1132f9ae,0x1132f9ae +.long 0x6da129c7,0x6da129c7 +.long 0x4b2f9e1d,0x4b2f9e1d +.long 0xf330b2dc,0xf330b2dc +.long 0xec52860d,0xec52860d +.long 0xd0e3c177,0xd0e3c177 +.long 0x6c16b32b,0x6c16b32b +.long 0x99b970a9,0x99b970a9 +.long 0xfa489411,0xfa489411 +.long 0x2264e947,0x2264e947 +.long 0xc48cfca8,0xc48cfca8 +.long 0x1a3ff0a0,0x1a3ff0a0 +.long 0xd82c7d56,0xd82c7d56 +.long 0xef903322,0xef903322 +.long 0xc74e4987,0xc74e4987 +.long 0xc1d138d9,0xc1d138d9 +.long 0xfea2ca8c,0xfea2ca8c +.long 0x360bd498,0x360bd498 +.long 0xcf81f5a6,0xcf81f5a6 +.long 0x28de7aa5,0x28de7aa5 +.long 0x268eb7da,0x268eb7da +.long 0xa4bfad3f,0xa4bfad3f +.long 0xe49d3a2c,0xe49d3a2c +.long 0x0d927850,0x0d927850 +.long 0x9bcc5f6a,0x9bcc5f6a +.long 0x62467e54,0x62467e54 +.long 0xc2138df6,0xc2138df6 +.long 0xe8b8d890,0xe8b8d890 +.long 0x5ef7392e,0x5ef7392e +.long 0xf5afc382,0xf5afc382 +.long 0xbe805d9f,0xbe805d9f +.long 0x7c93d069,0x7c93d069 +.long 0xa92dd56f,0xa92dd56f +.long 0xb31225cf,0xb31225cf +.long 0x3b99acc8,0x3b99acc8 +.long 0xa77d1810,0xa77d1810 +.long 0x6e639ce8,0x6e639ce8 +.long 0x7bbb3bdb,0x7bbb3bdb +.long 0x097826cd,0x097826cd +.long 0xf418596e,0xf418596e +.long 0x01b79aec,0x01b79aec +.long 0xa89a4f83,0xa89a4f83 +.long 0x656e95e6,0x656e95e6 +.long 0x7ee6ffaa,0x7ee6ffaa +.long 0x08cfbc21,0x08cfbc21 +.long 0xe6e815ef,0xe6e815ef +.long 0xd99be7ba,0xd99be7ba +.long 0xce366f4a,0xce366f4a +.long 0xd4099fea,0xd4099fea +.long 0xd67cb029,0xd67cb029 +.long 0xafb2a431,0xafb2a431 +.long 0x31233f2a,0x31233f2a +.long 0x3094a5c6,0x3094a5c6 +.long 0xc066a235,0xc066a235 +.long 0x37bc4e74,0x37bc4e74 +.long 0xa6ca82fc,0xa6ca82fc +.long 0xb0d090e0,0xb0d090e0 +.long 0x15d8a733,0x15d8a733 +.long 0x4a9804f1,0x4a9804f1 +.long 0xf7daec41,0xf7daec41 +.long 0x0e50cd7f,0x0e50cd7f +.long 0x2ff69117,0x2ff69117 +.long 0x8dd64d76,0x8dd64d76 +.long 0x4db0ef43,0x4db0ef43 +.long 0x544daacc,0x544daacc +.long 0xdf0496e4,0xdf0496e4 +.long 0xe3b5d19e,0xe3b5d19e +.long 0x1b886a4c,0x1b886a4c +.long 0xb81f2cc1,0xb81f2cc1 +.long 0x7f516546,0x7f516546 +.long 0x04ea5e9d,0x04ea5e9d +.long 0x5d358c01,0x5d358c01 +.long 0x737487fa,0x737487fa +.long 0x2e410bfb,0x2e410bfb +.long 0x5a1d67b3,0x5a1d67b3 +.long 0x52d2db92,0x52d2db92 +.long 0x335610e9,0x335610e9 +.long 0x1347d66d,0x1347d66d +.long 0x8c61d79a,0x8c61d79a +.long 0x7a0ca137,0x7a0ca137 +.long 0x8e14f859,0x8e14f859 +.long 0x893c13eb,0x893c13eb +.long 0xee27a9ce,0xee27a9ce +.long 0x35c961b7,0x35c961b7 +.long 0xede51ce1,0xede51ce1 +.long 0x3cb1477a,0x3cb1477a +.long 0x59dfd29c,0x59dfd29c +.long 0x3f73f255,0x3f73f255 +.long 0x79ce1418,0x79ce1418 +.long 0xbf37c773,0xbf37c773 +.long 0xeacdf753,0xeacdf753 +.long 0x5baafd5f,0x5baafd5f +.long 0x146f3ddf,0x146f3ddf +.long 0x86db4478,0x86db4478 +.long 0x81f3afca,0x81f3afca +.long 0x3ec468b9,0x3ec468b9 +.long 0x2c342438,0x2c342438 +.long 0x5f40a3c2,0x5f40a3c2 +.long 0x72c31d16,0x72c31d16 +.long 0x0c25e2bc,0x0c25e2bc +.long 0x8b493c28,0x8b493c28 +.long 0x41950dff,0x41950dff +.long 0x7101a839,0x7101a839 +.long 0xdeb30c08,0xdeb30c08 +.long 0x9ce4b4d8,0x9ce4b4d8 +.long 0x90c15664,0x90c15664 +.long 0x6184cb7b,0x6184cb7b +.long 0x70b632d5,0x70b632d5 +.long 0x745c6c48,0x745c6c48 +.long 0x4257b8d0,0x4257b8d0 +.byte 0x52,0x09,0x6a,0xd5,0x30,0x36,0xa5,0x38 +.byte 0xbf,0x40,0xa3,0x9e,0x81,0xf3,0xd7,0xfb +.byte 0x7c,0xe3,0x39,0x82,0x9b,0x2f,0xff,0x87 +.byte 0x34,0x8e,0x43,0x44,0xc4,0xde,0xe9,0xcb +.byte 0x54,0x7b,0x94,0x32,0xa6,0xc2,0x23,0x3d +.byte 0xee,0x4c,0x95,0x0b,0x42,0xfa,0xc3,0x4e +.byte 0x08,0x2e,0xa1,0x66,0x28,0xd9,0x24,0xb2 +.byte 0x76,0x5b,0xa2,0x49,0x6d,0x8b,0xd1,0x25 +.byte 0x72,0xf8,0xf6,0x64,0x86,0x68,0x98,0x16 +.byte 0xd4,0xa4,0x5c,0xcc,0x5d,0x65,0xb6,0x92 +.byte 0x6c,0x70,0x48,0x50,0xfd,0xed,0xb9,0xda +.byte 0x5e,0x15,0x46,0x57,0xa7,0x8d,0x9d,0x84 +.byte 0x90,0xd8,0xab,0x00,0x8c,0xbc,0xd3,0x0a +.byte 0xf7,0xe4,0x58,0x05,0xb8,0xb3,0x45,0x06 +.byte 0xd0,0x2c,0x1e,0x8f,0xca,0x3f,0x0f,0x02 +.byte 0xc1,0xaf,0xbd,0x03,0x01,0x13,0x8a,0x6b +.byte 0x3a,0x91,0x11,0x41,0x4f,0x67,0xdc,0xea +.byte 0x97,0xf2,0xcf,0xce,0xf0,0xb4,0xe6,0x73 +.byte 0x96,0xac,0x74,0x22,0xe7,0xad,0x35,0x85 +.byte 0xe2,0xf9,0x37,0xe8,0x1c,0x75,0xdf,0x6e +.byte 0x47,0xf1,0x1a,0x71,0x1d,0x29,0xc5,0x89 +.byte 0x6f,0xb7,0x62,0x0e,0xaa,0x18,0xbe,0x1b +.byte 0xfc,0x56,0x3e,0x4b,0xc6,0xd2,0x79,0x20 +.byte 0x9a,0xdb,0xc0,0xfe,0x78,0xcd,0x5a,0xf4 +.byte 0x1f,0xdd,0xa8,0x33,0x88,0x07,0xc7,0x31 +.byte 0xb1,0x12,0x10,0x59,0x27,0x80,0xec,0x5f +.byte 0x60,0x51,0x7f,0xa9,0x19,0xb5,0x4a,0x0d +.byte 0x2d,0xe5,0x7a,0x9f,0x93,0xc9,0x9c,0xef +.byte 0xa0,0xe0,0x3b,0x4d,0xae,0x2a,0xf5,0xb0 +.byte 0xc8,0xeb,0xbb,0x3c,0x83,0x53,0x99,0x61 +.byte 0x17,0x2b,0x04,0x7e,0xba,0x77,0xd6,0x26 +.byte 0xe1,0x69,0x14,0x63,0x55,0x21,0x0c,0x7d +.long 0x80808080, 0x80808080, 0xfefefefe, 0xfefefefe +.long 0x1b1b1b1b, 0x1b1b1b1b, 0, 0 +.byte 0x52,0x09,0x6a,0xd5,0x30,0x36,0xa5,0x38 +.byte 0xbf,0x40,0xa3,0x9e,0x81,0xf3,0xd7,0xfb +.byte 0x7c,0xe3,0x39,0x82,0x9b,0x2f,0xff,0x87 +.byte 0x34,0x8e,0x43,0x44,0xc4,0xde,0xe9,0xcb +.byte 0x54,0x7b,0x94,0x32,0xa6,0xc2,0x23,0x3d +.byte 0xee,0x4c,0x95,0x0b,0x42,0xfa,0xc3,0x4e +.byte 0x08,0x2e,0xa1,0x66,0x28,0xd9,0x24,0xb2 +.byte 0x76,0x5b,0xa2,0x49,0x6d,0x8b,0xd1,0x25 +.byte 0x72,0xf8,0xf6,0x64,0x86,0x68,0x98,0x16 +.byte 0xd4,0xa4,0x5c,0xcc,0x5d,0x65,0xb6,0x92 +.byte 0x6c,0x70,0x48,0x50,0xfd,0xed,0xb9,0xda +.byte 0x5e,0x15,0x46,0x57,0xa7,0x8d,0x9d,0x84 +.byte 0x90,0xd8,0xab,0x00,0x8c,0xbc,0xd3,0x0a +.byte 0xf7,0xe4,0x58,0x05,0xb8,0xb3,0x45,0x06 +.byte 0xd0,0x2c,0x1e,0x8f,0xca,0x3f,0x0f,0x02 +.byte 0xc1,0xaf,0xbd,0x03,0x01,0x13,0x8a,0x6b +.byte 0x3a,0x91,0x11,0x41,0x4f,0x67,0xdc,0xea +.byte 0x97,0xf2,0xcf,0xce,0xf0,0xb4,0xe6,0x73 +.byte 0x96,0xac,0x74,0x22,0xe7,0xad,0x35,0x85 +.byte 0xe2,0xf9,0x37,0xe8,0x1c,0x75,0xdf,0x6e +.byte 0x47,0xf1,0x1a,0x71,0x1d,0x29,0xc5,0x89 +.byte 0x6f,0xb7,0x62,0x0e,0xaa,0x18,0xbe,0x1b +.byte 0xfc,0x56,0x3e,0x4b,0xc6,0xd2,0x79,0x20 +.byte 0x9a,0xdb,0xc0,0xfe,0x78,0xcd,0x5a,0xf4 +.byte 0x1f,0xdd,0xa8,0x33,0x88,0x07,0xc7,0x31 +.byte 0xb1,0x12,0x10,0x59,0x27,0x80,0xec,0x5f +.byte 0x60,0x51,0x7f,0xa9,0x19,0xb5,0x4a,0x0d +.byte 0x2d,0xe5,0x7a,0x9f,0x93,0xc9,0x9c,0xef +.byte 0xa0,0xe0,0x3b,0x4d,0xae,0x2a,0xf5,0xb0 +.byte 0xc8,0xeb,0xbb,0x3c,0x83,0x53,0x99,0x61 +.byte 0x17,0x2b,0x04,0x7e,0xba,0x77,0xd6,0x26 +.byte 0xe1,0x69,0x14,0x63,0x55,0x21,0x0c,0x7d +.long 0x80808080, 0x80808080, 0xfefefefe, 0xfefefefe +.long 0x1b1b1b1b, 0x1b1b1b1b, 0, 0 +.byte 0x52,0x09,0x6a,0xd5,0x30,0x36,0xa5,0x38 +.byte 0xbf,0x40,0xa3,0x9e,0x81,0xf3,0xd7,0xfb +.byte 0x7c,0xe3,0x39,0x82,0x9b,0x2f,0xff,0x87 +.byte 0x34,0x8e,0x43,0x44,0xc4,0xde,0xe9,0xcb +.byte 0x54,0x7b,0x94,0x32,0xa6,0xc2,0x23,0x3d +.byte 0xee,0x4c,0x95,0x0b,0x42,0xfa,0xc3,0x4e +.byte 0x08,0x2e,0xa1,0x66,0x28,0xd9,0x24,0xb2 +.byte 0x76,0x5b,0xa2,0x49,0x6d,0x8b,0xd1,0x25 +.byte 0x72,0xf8,0xf6,0x64,0x86,0x68,0x98,0x16 +.byte 0xd4,0xa4,0x5c,0xcc,0x5d,0x65,0xb6,0x92 +.byte 0x6c,0x70,0x48,0x50,0xfd,0xed,0xb9,0xda +.byte 0x5e,0x15,0x46,0x57,0xa7,0x8d,0x9d,0x84 +.byte 0x90,0xd8,0xab,0x00,0x8c,0xbc,0xd3,0x0a +.byte 0xf7,0xe4,0x58,0x05,0xb8,0xb3,0x45,0x06 +.byte 0xd0,0x2c,0x1e,0x8f,0xca,0x3f,0x0f,0x02 +.byte 0xc1,0xaf,0xbd,0x03,0x01,0x13,0x8a,0x6b +.byte 0x3a,0x91,0x11,0x41,0x4f,0x67,0xdc,0xea +.byte 0x97,0xf2,0xcf,0xce,0xf0,0xb4,0xe6,0x73 +.byte 0x96,0xac,0x74,0x22,0xe7,0xad,0x35,0x85 +.byte 0xe2,0xf9,0x37,0xe8,0x1c,0x75,0xdf,0x6e +.byte 0x47,0xf1,0x1a,0x71,0x1d,0x29,0xc5,0x89 +.byte 0x6f,0xb7,0x62,0x0e,0xaa,0x18,0xbe,0x1b +.byte 0xfc,0x56,0x3e,0x4b,0xc6,0xd2,0x79,0x20 +.byte 0x9a,0xdb,0xc0,0xfe,0x78,0xcd,0x5a,0xf4 +.byte 0x1f,0xdd,0xa8,0x33,0x88,0x07,0xc7,0x31 +.byte 0xb1,0x12,0x10,0x59,0x27,0x80,0xec,0x5f +.byte 0x60,0x51,0x7f,0xa9,0x19,0xb5,0x4a,0x0d +.byte 0x2d,0xe5,0x7a,0x9f,0x93,0xc9,0x9c,0xef +.byte 0xa0,0xe0,0x3b,0x4d,0xae,0x2a,0xf5,0xb0 +.byte 0xc8,0xeb,0xbb,0x3c,0x83,0x53,0x99,0x61 +.byte 0x17,0x2b,0x04,0x7e,0xba,0x77,0xd6,0x26 +.byte 0xe1,0x69,0x14,0x63,0x55,0x21,0x0c,0x7d +.long 0x80808080, 0x80808080, 0xfefefefe, 0xfefefefe +.long 0x1b1b1b1b, 0x1b1b1b1b, 0, 0 +.byte 0x52,0x09,0x6a,0xd5,0x30,0x36,0xa5,0x38 +.byte 0xbf,0x40,0xa3,0x9e,0x81,0xf3,0xd7,0xfb +.byte 0x7c,0xe3,0x39,0x82,0x9b,0x2f,0xff,0x87 +.byte 0x34,0x8e,0x43,0x44,0xc4,0xde,0xe9,0xcb +.byte 0x54,0x7b,0x94,0x32,0xa6,0xc2,0x23,0x3d +.byte 0xee,0x4c,0x95,0x0b,0x42,0xfa,0xc3,0x4e +.byte 0x08,0x2e,0xa1,0x66,0x28,0xd9,0x24,0xb2 +.byte 0x76,0x5b,0xa2,0x49,0x6d,0x8b,0xd1,0x25 +.byte 0x72,0xf8,0xf6,0x64,0x86,0x68,0x98,0x16 +.byte 0xd4,0xa4,0x5c,0xcc,0x5d,0x65,0xb6,0x92 +.byte 0x6c,0x70,0x48,0x50,0xfd,0xed,0xb9,0xda +.byte 0x5e,0x15,0x46,0x57,0xa7,0x8d,0x9d,0x84 +.byte 0x90,0xd8,0xab,0x00,0x8c,0xbc,0xd3,0x0a +.byte 0xf7,0xe4,0x58,0x05,0xb8,0xb3,0x45,0x06 +.byte 0xd0,0x2c,0x1e,0x8f,0xca,0x3f,0x0f,0x02 +.byte 0xc1,0xaf,0xbd,0x03,0x01,0x13,0x8a,0x6b +.byte 0x3a,0x91,0x11,0x41,0x4f,0x67,0xdc,0xea +.byte 0x97,0xf2,0xcf,0xce,0xf0,0xb4,0xe6,0x73 +.byte 0x96,0xac,0x74,0x22,0xe7,0xad,0x35,0x85 +.byte 0xe2,0xf9,0x37,0xe8,0x1c,0x75,0xdf,0x6e +.byte 0x47,0xf1,0x1a,0x71,0x1d,0x29,0xc5,0x89 +.byte 0x6f,0xb7,0x62,0x0e,0xaa,0x18,0xbe,0x1b +.byte 0xfc,0x56,0x3e,0x4b,0xc6,0xd2,0x79,0x20 +.byte 0x9a,0xdb,0xc0,0xfe,0x78,0xcd,0x5a,0xf4 +.byte 0x1f,0xdd,0xa8,0x33,0x88,0x07,0xc7,0x31 +.byte 0xb1,0x12,0x10,0x59,0x27,0x80,0xec,0x5f +.byte 0x60,0x51,0x7f,0xa9,0x19,0xb5,0x4a,0x0d +.byte 0x2d,0xe5,0x7a,0x9f,0x93,0xc9,0x9c,0xef +.byte 0xa0,0xe0,0x3b,0x4d,0xae,0x2a,0xf5,0xb0 +.byte 0xc8,0xeb,0xbb,0x3c,0x83,0x53,0x99,0x61 +.byte 0x17,0x2b,0x04,0x7e,0xba,0x77,0xd6,0x26 +.byte 0xe1,0x69,0x14,0x63,0x55,0x21,0x0c,0x7d +.long 0x80808080, 0x80808080, 0xfefefefe, 0xfefefefe +.long 0x1b1b1b1b, 0x1b1b1b1b, 0, 0 +.byte 65,69,83,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 +.align 64 + .section ".note.gnu.property", "a" + .p2align 3 + .long 1f - 0f + .long 4f - 1f + .long 5 +0: + # "GNU" encoded with .byte, since .asciz isn't supported + # on Solaris. + .byte 0x47 + .byte 0x4e + .byte 0x55 + .byte 0 +1: + .p2align 3 + .long 0xc0000002 + .long 3f - 2f +2: + .long 3 +3: + .p2align 3 +4: diff --git a/secure/lib/libcrypto/arch/amd64/bsaes-x86_64.S b/secure/lib/libcrypto/arch/amd64/bsaes-x86_64.S new file mode 100644 --- /dev/null +++ b/secure/lib/libcrypto/arch/amd64/bsaes-x86_64.S @@ -0,0 +1,2619 @@ +/* Do not modify. This file is auto-generated from bsaes-x86_64.pl. */ +.text + + + + +.type _bsaes_encrypt8,@function +.align 64 +_bsaes_encrypt8: +.cfi_startproc + leaq .LBS0(%rip),%r11 + + movdqa (%rax),%xmm8 + leaq 16(%rax),%rax + movdqa 80(%r11),%xmm7 + pxor %xmm8,%xmm15 + pxor %xmm8,%xmm0 + pxor %xmm8,%xmm1 + pxor %xmm8,%xmm2 +.byte 102,68,15,56,0,255 +.byte 102,15,56,0,199 + pxor %xmm8,%xmm3 + pxor %xmm8,%xmm4 +.byte 102,15,56,0,207 +.byte 102,15,56,0,215 + pxor %xmm8,%xmm5 + pxor %xmm8,%xmm6 +.byte 102,15,56,0,223 +.byte 102,15,56,0,231 +.byte 102,15,56,0,239 +.byte 102,15,56,0,247 +_bsaes_encrypt8_bitslice: + movdqa 0(%r11),%xmm7 + movdqa 16(%r11),%xmm8 + movdqa %xmm5,%xmm9 + psrlq $1,%xmm5 + movdqa %xmm3,%xmm10 + psrlq $1,%xmm3 + pxor %xmm6,%xmm5 + pxor %xmm4,%xmm3 + pand %xmm7,%xmm5 + pand %xmm7,%xmm3 + pxor %xmm5,%xmm6 + psllq $1,%xmm5 + pxor %xmm3,%xmm4 + psllq $1,%xmm3 + pxor %xmm9,%xmm5 + pxor %xmm10,%xmm3 + movdqa %xmm1,%xmm9 + psrlq $1,%xmm1 + movdqa %xmm15,%xmm10 + psrlq $1,%xmm15 + pxor %xmm2,%xmm1 + pxor %xmm0,%xmm15 + pand %xmm7,%xmm1 + pand %xmm7,%xmm15 + pxor %xmm1,%xmm2 + psllq $1,%xmm1 + pxor %xmm15,%xmm0 + psllq $1,%xmm15 + pxor %xmm9,%xmm1 + pxor %xmm10,%xmm15 + movdqa 32(%r11),%xmm7 + movdqa %xmm4,%xmm9 + psrlq $2,%xmm4 + movdqa %xmm3,%xmm10 + psrlq $2,%xmm3 + pxor %xmm6,%xmm4 + pxor %xmm5,%xmm3 + pand %xmm8,%xmm4 + pand %xmm8,%xmm3 + pxor %xmm4,%xmm6 + psllq $2,%xmm4 + pxor %xmm3,%xmm5 + psllq $2,%xmm3 + pxor %xmm9,%xmm4 + pxor %xmm10,%xmm3 + movdqa %xmm0,%xmm9 + psrlq $2,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $2,%xmm15 + pxor %xmm2,%xmm0 + pxor %xmm1,%xmm15 + pand %xmm8,%xmm0 + pand %xmm8,%xmm15 + pxor %xmm0,%xmm2 + psllq $2,%xmm0 + pxor %xmm15,%xmm1 + psllq $2,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa %xmm2,%xmm9 + psrlq $4,%xmm2 + movdqa %xmm1,%xmm10 + psrlq $4,%xmm1 + pxor %xmm6,%xmm2 + pxor %xmm5,%xmm1 + pand %xmm7,%xmm2 + pand %xmm7,%xmm1 + pxor %xmm2,%xmm6 + psllq $4,%xmm2 + pxor %xmm1,%xmm5 + psllq $4,%xmm1 + pxor %xmm9,%xmm2 + pxor %xmm10,%xmm1 + movdqa %xmm0,%xmm9 + psrlq $4,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $4,%xmm15 + pxor %xmm4,%xmm0 + pxor %xmm3,%xmm15 + pand %xmm7,%xmm0 + pand %xmm7,%xmm15 + pxor %xmm0,%xmm4 + psllq $4,%xmm0 + pxor %xmm15,%xmm3 + psllq $4,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + decl %r10d + jmp .Lenc_sbox +.align 16 +.Lenc_loop: + pxor 0(%rax),%xmm15 + pxor 16(%rax),%xmm0 + pxor 32(%rax),%xmm1 + pxor 48(%rax),%xmm2 +.byte 102,68,15,56,0,255 +.byte 102,15,56,0,199 + pxor 64(%rax),%xmm3 + pxor 80(%rax),%xmm4 +.byte 102,15,56,0,207 +.byte 102,15,56,0,215 + pxor 96(%rax),%xmm5 + pxor 112(%rax),%xmm6 +.byte 102,15,56,0,223 +.byte 102,15,56,0,231 +.byte 102,15,56,0,239 +.byte 102,15,56,0,247 + leaq 128(%rax),%rax +.Lenc_sbox: + pxor %xmm5,%xmm4 + pxor %xmm0,%xmm1 + pxor %xmm15,%xmm2 + pxor %xmm1,%xmm5 + pxor %xmm15,%xmm4 + + pxor %xmm2,%xmm5 + pxor %xmm6,%xmm2 + pxor %xmm4,%xmm6 + pxor %xmm3,%xmm2 + pxor %xmm4,%xmm3 + pxor %xmm0,%xmm2 + + pxor %xmm6,%xmm1 + pxor %xmm4,%xmm0 + movdqa %xmm6,%xmm10 + movdqa %xmm0,%xmm9 + movdqa %xmm4,%xmm8 + movdqa %xmm1,%xmm12 + movdqa %xmm5,%xmm11 + + pxor %xmm3,%xmm10 + pxor %xmm1,%xmm9 + pxor %xmm2,%xmm8 + movdqa %xmm10,%xmm13 + pxor %xmm3,%xmm12 + movdqa %xmm9,%xmm7 + pxor %xmm15,%xmm11 + movdqa %xmm10,%xmm14 + + por %xmm8,%xmm9 + por %xmm11,%xmm10 + pxor %xmm7,%xmm14 + pand %xmm11,%xmm13 + pxor %xmm8,%xmm11 + pand %xmm8,%xmm7 + pand %xmm11,%xmm14 + movdqa %xmm2,%xmm11 + pxor %xmm15,%xmm11 + pand %xmm11,%xmm12 + pxor %xmm12,%xmm10 + pxor %xmm12,%xmm9 + movdqa %xmm6,%xmm12 + movdqa %xmm4,%xmm11 + pxor %xmm0,%xmm12 + pxor %xmm5,%xmm11 + movdqa %xmm12,%xmm8 + pand %xmm11,%xmm12 + por %xmm11,%xmm8 + pxor %xmm12,%xmm7 + pxor %xmm14,%xmm10 + pxor %xmm13,%xmm9 + pxor %xmm14,%xmm8 + movdqa %xmm1,%xmm11 + pxor %xmm13,%xmm7 + movdqa %xmm3,%xmm12 + pxor %xmm13,%xmm8 + movdqa %xmm0,%xmm13 + pand %xmm2,%xmm11 + movdqa %xmm6,%xmm14 + pand %xmm15,%xmm12 + pand %xmm4,%xmm13 + por %xmm5,%xmm14 + pxor %xmm11,%xmm10 + pxor %xmm12,%xmm9 + pxor %xmm13,%xmm8 + pxor %xmm14,%xmm7 + + + + + + movdqa %xmm10,%xmm11 + pand %xmm8,%xmm10 + pxor %xmm9,%xmm11 + + movdqa %xmm7,%xmm13 + movdqa %xmm11,%xmm14 + pxor %xmm10,%xmm13 + pand %xmm13,%xmm14 + + movdqa %xmm8,%xmm12 + pxor %xmm9,%xmm14 + pxor %xmm7,%xmm12 + + pxor %xmm9,%xmm10 + + pand %xmm10,%xmm12 + + movdqa %xmm13,%xmm9 + pxor %xmm7,%xmm12 + + pxor %xmm12,%xmm9 + pxor %xmm12,%xmm8 + + pand %xmm7,%xmm9 + + pxor %xmm9,%xmm13 + pxor %xmm9,%xmm8 + + pand %xmm14,%xmm13 + + pxor %xmm11,%xmm13 + movdqa %xmm5,%xmm11 + movdqa %xmm4,%xmm7 + movdqa %xmm14,%xmm9 + pxor %xmm13,%xmm9 + pand %xmm5,%xmm9 + pxor %xmm4,%xmm5 + pand %xmm14,%xmm4 + pand %xmm13,%xmm5 + pxor %xmm4,%xmm5 + pxor %xmm9,%xmm4 + pxor %xmm15,%xmm11 + pxor %xmm2,%xmm7 + pxor %xmm12,%xmm14 + pxor %xmm8,%xmm13 + movdqa %xmm14,%xmm10 + movdqa %xmm12,%xmm9 + pxor %xmm13,%xmm10 + pxor %xmm8,%xmm9 + pand %xmm11,%xmm10 + pand %xmm15,%xmm9 + pxor %xmm7,%xmm11 + pxor %xmm2,%xmm15 + pand %xmm14,%xmm7 + pand %xmm12,%xmm2 + pand %xmm13,%xmm11 + pand %xmm8,%xmm15 + pxor %xmm11,%xmm7 + pxor %xmm2,%xmm15 + pxor %xmm10,%xmm11 + pxor %xmm9,%xmm2 + pxor %xmm11,%xmm5 + pxor %xmm11,%xmm15 + pxor %xmm7,%xmm4 + pxor %xmm7,%xmm2 + + movdqa %xmm6,%xmm11 + movdqa %xmm0,%xmm7 + pxor %xmm3,%xmm11 + pxor %xmm1,%xmm7 + movdqa %xmm14,%xmm10 + movdqa %xmm12,%xmm9 + pxor %xmm13,%xmm10 + pxor %xmm8,%xmm9 + pand %xmm11,%xmm10 + pand %xmm3,%xmm9 + pxor %xmm7,%xmm11 + pxor %xmm1,%xmm3 + pand %xmm14,%xmm7 + pand %xmm12,%xmm1 + pand %xmm13,%xmm11 + pand %xmm8,%xmm3 + pxor %xmm11,%xmm7 + pxor %xmm1,%xmm3 + pxor %xmm10,%xmm11 + pxor %xmm9,%xmm1 + pxor %xmm12,%xmm14 + pxor %xmm8,%xmm13 + movdqa %xmm14,%xmm10 + pxor %xmm13,%xmm10 + pand %xmm6,%xmm10 + pxor %xmm0,%xmm6 + pand %xmm14,%xmm0 + pand %xmm13,%xmm6 + pxor %xmm0,%xmm6 + pxor %xmm10,%xmm0 + pxor %xmm11,%xmm6 + pxor %xmm11,%xmm3 + pxor %xmm7,%xmm0 + pxor %xmm7,%xmm1 + pxor %xmm15,%xmm6 + pxor %xmm5,%xmm0 + pxor %xmm6,%xmm3 + pxor %xmm15,%xmm5 + pxor %xmm0,%xmm15 + + pxor %xmm4,%xmm0 + pxor %xmm1,%xmm4 + pxor %xmm2,%xmm1 + pxor %xmm4,%xmm2 + pxor %xmm4,%xmm3 + + pxor %xmm2,%xmm5 + decl %r10d + jl .Lenc_done + pshufd $0x93,%xmm15,%xmm7 + pshufd $0x93,%xmm0,%xmm8 + pxor %xmm7,%xmm15 + pshufd $0x93,%xmm3,%xmm9 + pxor %xmm8,%xmm0 + pshufd $0x93,%xmm5,%xmm10 + pxor %xmm9,%xmm3 + pshufd $0x93,%xmm2,%xmm11 + pxor %xmm10,%xmm5 + pshufd $0x93,%xmm6,%xmm12 + pxor %xmm11,%xmm2 + pshufd $0x93,%xmm1,%xmm13 + pxor %xmm12,%xmm6 + pshufd $0x93,%xmm4,%xmm14 + pxor %xmm13,%xmm1 + pxor %xmm14,%xmm4 + + pxor %xmm15,%xmm8 + pxor %xmm4,%xmm7 + pxor %xmm4,%xmm8 + pshufd $0x4E,%xmm15,%xmm15 + pxor %xmm0,%xmm9 + pshufd $0x4E,%xmm0,%xmm0 + pxor %xmm2,%xmm12 + pxor %xmm7,%xmm15 + pxor %xmm6,%xmm13 + pxor %xmm8,%xmm0 + pxor %xmm5,%xmm11 + pshufd $0x4E,%xmm2,%xmm7 + pxor %xmm1,%xmm14 + pshufd $0x4E,%xmm6,%xmm8 + pxor %xmm3,%xmm10 + pshufd $0x4E,%xmm5,%xmm2 + pxor %xmm4,%xmm10 + pshufd $0x4E,%xmm4,%xmm6 + pxor %xmm4,%xmm11 + pshufd $0x4E,%xmm1,%xmm5 + pxor %xmm11,%xmm7 + pshufd $0x4E,%xmm3,%xmm1 + pxor %xmm12,%xmm8 + pxor %xmm10,%xmm2 + pxor %xmm14,%xmm6 + pxor %xmm13,%xmm5 + movdqa %xmm7,%xmm3 + pxor %xmm9,%xmm1 + movdqa %xmm8,%xmm4 + movdqa 48(%r11),%xmm7 + jnz .Lenc_loop + movdqa 64(%r11),%xmm7 + jmp .Lenc_loop +.align 16 +.Lenc_done: + movdqa 0(%r11),%xmm7 + movdqa 16(%r11),%xmm8 + movdqa %xmm1,%xmm9 + psrlq $1,%xmm1 + movdqa %xmm2,%xmm10 + psrlq $1,%xmm2 + pxor %xmm4,%xmm1 + pxor %xmm6,%xmm2 + pand %xmm7,%xmm1 + pand %xmm7,%xmm2 + pxor %xmm1,%xmm4 + psllq $1,%xmm1 + pxor %xmm2,%xmm6 + psllq $1,%xmm2 + pxor %xmm9,%xmm1 + pxor %xmm10,%xmm2 + movdqa %xmm3,%xmm9 + psrlq $1,%xmm3 + movdqa %xmm15,%xmm10 + psrlq $1,%xmm15 + pxor %xmm5,%xmm3 + pxor %xmm0,%xmm15 + pand %xmm7,%xmm3 + pand %xmm7,%xmm15 + pxor %xmm3,%xmm5 + psllq $1,%xmm3 + pxor %xmm15,%xmm0 + psllq $1,%xmm15 + pxor %xmm9,%xmm3 + pxor %xmm10,%xmm15 + movdqa 32(%r11),%xmm7 + movdqa %xmm6,%xmm9 + psrlq $2,%xmm6 + movdqa %xmm2,%xmm10 + psrlq $2,%xmm2 + pxor %xmm4,%xmm6 + pxor %xmm1,%xmm2 + pand %xmm8,%xmm6 + pand %xmm8,%xmm2 + pxor %xmm6,%xmm4 + psllq $2,%xmm6 + pxor %xmm2,%xmm1 + psllq $2,%xmm2 + pxor %xmm9,%xmm6 + pxor %xmm10,%xmm2 + movdqa %xmm0,%xmm9 + psrlq $2,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $2,%xmm15 + pxor %xmm5,%xmm0 + pxor %xmm3,%xmm15 + pand %xmm8,%xmm0 + pand %xmm8,%xmm15 + pxor %xmm0,%xmm5 + psllq $2,%xmm0 + pxor %xmm15,%xmm3 + psllq $2,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa %xmm5,%xmm9 + psrlq $4,%xmm5 + movdqa %xmm3,%xmm10 + psrlq $4,%xmm3 + pxor %xmm4,%xmm5 + pxor %xmm1,%xmm3 + pand %xmm7,%xmm5 + pand %xmm7,%xmm3 + pxor %xmm5,%xmm4 + psllq $4,%xmm5 + pxor %xmm3,%xmm1 + psllq $4,%xmm3 + pxor %xmm9,%xmm5 + pxor %xmm10,%xmm3 + movdqa %xmm0,%xmm9 + psrlq $4,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $4,%xmm15 + pxor %xmm6,%xmm0 + pxor %xmm2,%xmm15 + pand %xmm7,%xmm0 + pand %xmm7,%xmm15 + pxor %xmm0,%xmm6 + psllq $4,%xmm0 + pxor %xmm15,%xmm2 + psllq $4,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa (%rax),%xmm7 + pxor %xmm7,%xmm3 + pxor %xmm7,%xmm5 + pxor %xmm7,%xmm2 + pxor %xmm7,%xmm6 + pxor %xmm7,%xmm1 + pxor %xmm7,%xmm4 + pxor %xmm7,%xmm15 + pxor %xmm7,%xmm0 + .byte 0xf3,0xc3 +.cfi_endproc +.size _bsaes_encrypt8,.-_bsaes_encrypt8 + +.type _bsaes_decrypt8,@function +.align 64 +_bsaes_decrypt8: +.cfi_startproc + leaq .LBS0(%rip),%r11 + + movdqa (%rax),%xmm8 + leaq 16(%rax),%rax + movdqa -48(%r11),%xmm7 + pxor %xmm8,%xmm15 + pxor %xmm8,%xmm0 + pxor %xmm8,%xmm1 + pxor %xmm8,%xmm2 +.byte 102,68,15,56,0,255 +.byte 102,15,56,0,199 + pxor %xmm8,%xmm3 + pxor %xmm8,%xmm4 +.byte 102,15,56,0,207 +.byte 102,15,56,0,215 + pxor %xmm8,%xmm5 + pxor %xmm8,%xmm6 +.byte 102,15,56,0,223 +.byte 102,15,56,0,231 +.byte 102,15,56,0,239 +.byte 102,15,56,0,247 + movdqa 0(%r11),%xmm7 + movdqa 16(%r11),%xmm8 + movdqa %xmm5,%xmm9 + psrlq $1,%xmm5 + movdqa %xmm3,%xmm10 + psrlq $1,%xmm3 + pxor %xmm6,%xmm5 + pxor %xmm4,%xmm3 + pand %xmm7,%xmm5 + pand %xmm7,%xmm3 + pxor %xmm5,%xmm6 + psllq $1,%xmm5 + pxor %xmm3,%xmm4 + psllq $1,%xmm3 + pxor %xmm9,%xmm5 + pxor %xmm10,%xmm3 + movdqa %xmm1,%xmm9 + psrlq $1,%xmm1 + movdqa %xmm15,%xmm10 + psrlq $1,%xmm15 + pxor %xmm2,%xmm1 + pxor %xmm0,%xmm15 + pand %xmm7,%xmm1 + pand %xmm7,%xmm15 + pxor %xmm1,%xmm2 + psllq $1,%xmm1 + pxor %xmm15,%xmm0 + psllq $1,%xmm15 + pxor %xmm9,%xmm1 + pxor %xmm10,%xmm15 + movdqa 32(%r11),%xmm7 + movdqa %xmm4,%xmm9 + psrlq $2,%xmm4 + movdqa %xmm3,%xmm10 + psrlq $2,%xmm3 + pxor %xmm6,%xmm4 + pxor %xmm5,%xmm3 + pand %xmm8,%xmm4 + pand %xmm8,%xmm3 + pxor %xmm4,%xmm6 + psllq $2,%xmm4 + pxor %xmm3,%xmm5 + psllq $2,%xmm3 + pxor %xmm9,%xmm4 + pxor %xmm10,%xmm3 + movdqa %xmm0,%xmm9 + psrlq $2,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $2,%xmm15 + pxor %xmm2,%xmm0 + pxor %xmm1,%xmm15 + pand %xmm8,%xmm0 + pand %xmm8,%xmm15 + pxor %xmm0,%xmm2 + psllq $2,%xmm0 + pxor %xmm15,%xmm1 + psllq $2,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa %xmm2,%xmm9 + psrlq $4,%xmm2 + movdqa %xmm1,%xmm10 + psrlq $4,%xmm1 + pxor %xmm6,%xmm2 + pxor %xmm5,%xmm1 + pand %xmm7,%xmm2 + pand %xmm7,%xmm1 + pxor %xmm2,%xmm6 + psllq $4,%xmm2 + pxor %xmm1,%xmm5 + psllq $4,%xmm1 + pxor %xmm9,%xmm2 + pxor %xmm10,%xmm1 + movdqa %xmm0,%xmm9 + psrlq $4,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $4,%xmm15 + pxor %xmm4,%xmm0 + pxor %xmm3,%xmm15 + pand %xmm7,%xmm0 + pand %xmm7,%xmm15 + pxor %xmm0,%xmm4 + psllq $4,%xmm0 + pxor %xmm15,%xmm3 + psllq $4,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + decl %r10d + jmp .Ldec_sbox +.align 16 +.Ldec_loop: + pxor 0(%rax),%xmm15 + pxor 16(%rax),%xmm0 + pxor 32(%rax),%xmm1 + pxor 48(%rax),%xmm2 +.byte 102,68,15,56,0,255 +.byte 102,15,56,0,199 + pxor 64(%rax),%xmm3 + pxor 80(%rax),%xmm4 +.byte 102,15,56,0,207 +.byte 102,15,56,0,215 + pxor 96(%rax),%xmm5 + pxor 112(%rax),%xmm6 +.byte 102,15,56,0,223 +.byte 102,15,56,0,231 +.byte 102,15,56,0,239 +.byte 102,15,56,0,247 + leaq 128(%rax),%rax +.Ldec_sbox: + pxor %xmm3,%xmm2 + + pxor %xmm6,%xmm3 + pxor %xmm6,%xmm1 + pxor %xmm3,%xmm5 + pxor %xmm5,%xmm6 + pxor %xmm6,%xmm0 + + pxor %xmm0,%xmm15 + pxor %xmm4,%xmm1 + pxor %xmm15,%xmm2 + pxor %xmm15,%xmm4 + pxor %xmm2,%xmm0 + movdqa %xmm2,%xmm10 + movdqa %xmm6,%xmm9 + movdqa %xmm0,%xmm8 + movdqa %xmm3,%xmm12 + movdqa %xmm4,%xmm11 + + pxor %xmm15,%xmm10 + pxor %xmm3,%xmm9 + pxor %xmm5,%xmm8 + movdqa %xmm10,%xmm13 + pxor %xmm15,%xmm12 + movdqa %xmm9,%xmm7 + pxor %xmm1,%xmm11 + movdqa %xmm10,%xmm14 + + por %xmm8,%xmm9 + por %xmm11,%xmm10 + pxor %xmm7,%xmm14 + pand %xmm11,%xmm13 + pxor %xmm8,%xmm11 + pand %xmm8,%xmm7 + pand %xmm11,%xmm14 + movdqa %xmm5,%xmm11 + pxor %xmm1,%xmm11 + pand %xmm11,%xmm12 + pxor %xmm12,%xmm10 + pxor %xmm12,%xmm9 + movdqa %xmm2,%xmm12 + movdqa %xmm0,%xmm11 + pxor %xmm6,%xmm12 + pxor %xmm4,%xmm11 + movdqa %xmm12,%xmm8 + pand %xmm11,%xmm12 + por %xmm11,%xmm8 + pxor %xmm12,%xmm7 + pxor %xmm14,%xmm10 + pxor %xmm13,%xmm9 + pxor %xmm14,%xmm8 + movdqa %xmm3,%xmm11 + pxor %xmm13,%xmm7 + movdqa %xmm15,%xmm12 + pxor %xmm13,%xmm8 + movdqa %xmm6,%xmm13 + pand %xmm5,%xmm11 + movdqa %xmm2,%xmm14 + pand %xmm1,%xmm12 + pand %xmm0,%xmm13 + por %xmm4,%xmm14 + pxor %xmm11,%xmm10 + pxor %xmm12,%xmm9 + pxor %xmm13,%xmm8 + pxor %xmm14,%xmm7 + + + + + + movdqa %xmm10,%xmm11 + pand %xmm8,%xmm10 + pxor %xmm9,%xmm11 + + movdqa %xmm7,%xmm13 + movdqa %xmm11,%xmm14 + pxor %xmm10,%xmm13 + pand %xmm13,%xmm14 + + movdqa %xmm8,%xmm12 + pxor %xmm9,%xmm14 + pxor %xmm7,%xmm12 + + pxor %xmm9,%xmm10 + + pand %xmm10,%xmm12 + + movdqa %xmm13,%xmm9 + pxor %xmm7,%xmm12 + + pxor %xmm12,%xmm9 + pxor %xmm12,%xmm8 + + pand %xmm7,%xmm9 + + pxor %xmm9,%xmm13 + pxor %xmm9,%xmm8 + + pand %xmm14,%xmm13 + + pxor %xmm11,%xmm13 + movdqa %xmm4,%xmm11 + movdqa %xmm0,%xmm7 + movdqa %xmm14,%xmm9 + pxor %xmm13,%xmm9 + pand %xmm4,%xmm9 + pxor %xmm0,%xmm4 + pand %xmm14,%xmm0 + pand %xmm13,%xmm4 + pxor %xmm0,%xmm4 + pxor %xmm9,%xmm0 + pxor %xmm1,%xmm11 + pxor %xmm5,%xmm7 + pxor %xmm12,%xmm14 + pxor %xmm8,%xmm13 + movdqa %xmm14,%xmm10 + movdqa %xmm12,%xmm9 + pxor %xmm13,%xmm10 + pxor %xmm8,%xmm9 + pand %xmm11,%xmm10 + pand %xmm1,%xmm9 + pxor %xmm7,%xmm11 + pxor %xmm5,%xmm1 + pand %xmm14,%xmm7 + pand %xmm12,%xmm5 + pand %xmm13,%xmm11 + pand %xmm8,%xmm1 + pxor %xmm11,%xmm7 + pxor %xmm5,%xmm1 + pxor %xmm10,%xmm11 + pxor %xmm9,%xmm5 + pxor %xmm11,%xmm4 + pxor %xmm11,%xmm1 + pxor %xmm7,%xmm0 + pxor %xmm7,%xmm5 + + movdqa %xmm2,%xmm11 + movdqa %xmm6,%xmm7 + pxor %xmm15,%xmm11 + pxor %xmm3,%xmm7 + movdqa %xmm14,%xmm10 + movdqa %xmm12,%xmm9 + pxor %xmm13,%xmm10 + pxor %xmm8,%xmm9 + pand %xmm11,%xmm10 + pand %xmm15,%xmm9 + pxor %xmm7,%xmm11 + pxor %xmm3,%xmm15 + pand %xmm14,%xmm7 + pand %xmm12,%xmm3 + pand %xmm13,%xmm11 + pand %xmm8,%xmm15 + pxor %xmm11,%xmm7 + pxor %xmm3,%xmm15 + pxor %xmm10,%xmm11 + pxor %xmm9,%xmm3 + pxor %xmm12,%xmm14 + pxor %xmm8,%xmm13 + movdqa %xmm14,%xmm10 + pxor %xmm13,%xmm10 + pand %xmm2,%xmm10 + pxor %xmm6,%xmm2 + pand %xmm14,%xmm6 + pand %xmm13,%xmm2 + pxor %xmm6,%xmm2 + pxor %xmm10,%xmm6 + pxor %xmm11,%xmm2 + pxor %xmm11,%xmm15 + pxor %xmm7,%xmm6 + pxor %xmm7,%xmm3 + pxor %xmm6,%xmm0 + pxor %xmm4,%xmm5 + + pxor %xmm0,%xmm3 + pxor %xmm6,%xmm1 + pxor %xmm6,%xmm4 + pxor %xmm1,%xmm3 + pxor %xmm15,%xmm6 + pxor %xmm4,%xmm3 + pxor %xmm5,%xmm2 + pxor %xmm0,%xmm5 + pxor %xmm3,%xmm2 + + pxor %xmm15,%xmm3 + pxor %xmm2,%xmm6 + decl %r10d + jl .Ldec_done + + pshufd $0x4E,%xmm15,%xmm7 + pshufd $0x4E,%xmm2,%xmm13 + pxor %xmm15,%xmm7 + pshufd $0x4E,%xmm4,%xmm14 + pxor %xmm2,%xmm13 + pshufd $0x4E,%xmm0,%xmm8 + pxor %xmm4,%xmm14 + pshufd $0x4E,%xmm5,%xmm9 + pxor %xmm0,%xmm8 + pshufd $0x4E,%xmm3,%xmm10 + pxor %xmm5,%xmm9 + pxor %xmm13,%xmm15 + pxor %xmm13,%xmm0 + pshufd $0x4E,%xmm1,%xmm11 + pxor %xmm3,%xmm10 + pxor %xmm7,%xmm5 + pxor %xmm8,%xmm3 + pshufd $0x4E,%xmm6,%xmm12 + pxor %xmm1,%xmm11 + pxor %xmm14,%xmm0 + pxor %xmm9,%xmm1 + pxor %xmm6,%xmm12 + + pxor %xmm14,%xmm5 + pxor %xmm13,%xmm3 + pxor %xmm13,%xmm1 + pxor %xmm10,%xmm6 + pxor %xmm11,%xmm2 + pxor %xmm14,%xmm1 + pxor %xmm14,%xmm6 + pxor %xmm12,%xmm4 + pshufd $0x93,%xmm15,%xmm7 + pshufd $0x93,%xmm0,%xmm8 + pxor %xmm7,%xmm15 + pshufd $0x93,%xmm5,%xmm9 + pxor %xmm8,%xmm0 + pshufd $0x93,%xmm3,%xmm10 + pxor %xmm9,%xmm5 + pshufd $0x93,%xmm1,%xmm11 + pxor %xmm10,%xmm3 + pshufd $0x93,%xmm6,%xmm12 + pxor %xmm11,%xmm1 + pshufd $0x93,%xmm2,%xmm13 + pxor %xmm12,%xmm6 + pshufd $0x93,%xmm4,%xmm14 + pxor %xmm13,%xmm2 + pxor %xmm14,%xmm4 + + pxor %xmm15,%xmm8 + pxor %xmm4,%xmm7 + pxor %xmm4,%xmm8 + pshufd $0x4E,%xmm15,%xmm15 + pxor %xmm0,%xmm9 + pshufd $0x4E,%xmm0,%xmm0 + pxor %xmm1,%xmm12 + pxor %xmm7,%xmm15 + pxor %xmm6,%xmm13 + pxor %xmm8,%xmm0 + pxor %xmm3,%xmm11 + pshufd $0x4E,%xmm1,%xmm7 + pxor %xmm2,%xmm14 + pshufd $0x4E,%xmm6,%xmm8 + pxor %xmm5,%xmm10 + pshufd $0x4E,%xmm3,%xmm1 + pxor %xmm4,%xmm10 + pshufd $0x4E,%xmm4,%xmm6 + pxor %xmm4,%xmm11 + pshufd $0x4E,%xmm2,%xmm3 + pxor %xmm11,%xmm7 + pshufd $0x4E,%xmm5,%xmm2 + pxor %xmm12,%xmm8 + pxor %xmm1,%xmm10 + pxor %xmm14,%xmm6 + pxor %xmm3,%xmm13 + movdqa %xmm7,%xmm3 + pxor %xmm9,%xmm2 + movdqa %xmm13,%xmm5 + movdqa %xmm8,%xmm4 + movdqa %xmm2,%xmm1 + movdqa %xmm10,%xmm2 + movdqa -16(%r11),%xmm7 + jnz .Ldec_loop + movdqa -32(%r11),%xmm7 + jmp .Ldec_loop +.align 16 +.Ldec_done: + movdqa 0(%r11),%xmm7 + movdqa 16(%r11),%xmm8 + movdqa %xmm2,%xmm9 + psrlq $1,%xmm2 + movdqa %xmm1,%xmm10 + psrlq $1,%xmm1 + pxor %xmm4,%xmm2 + pxor %xmm6,%xmm1 + pand %xmm7,%xmm2 + pand %xmm7,%xmm1 + pxor %xmm2,%xmm4 + psllq $1,%xmm2 + pxor %xmm1,%xmm6 + psllq $1,%xmm1 + pxor %xmm9,%xmm2 + pxor %xmm10,%xmm1 + movdqa %xmm5,%xmm9 + psrlq $1,%xmm5 + movdqa %xmm15,%xmm10 + psrlq $1,%xmm15 + pxor %xmm3,%xmm5 + pxor %xmm0,%xmm15 + pand %xmm7,%xmm5 + pand %xmm7,%xmm15 + pxor %xmm5,%xmm3 + psllq $1,%xmm5 + pxor %xmm15,%xmm0 + psllq $1,%xmm15 + pxor %xmm9,%xmm5 + pxor %xmm10,%xmm15 + movdqa 32(%r11),%xmm7 + movdqa %xmm6,%xmm9 + psrlq $2,%xmm6 + movdqa %xmm1,%xmm10 + psrlq $2,%xmm1 + pxor %xmm4,%xmm6 + pxor %xmm2,%xmm1 + pand %xmm8,%xmm6 + pand %xmm8,%xmm1 + pxor %xmm6,%xmm4 + psllq $2,%xmm6 + pxor %xmm1,%xmm2 + psllq $2,%xmm1 + pxor %xmm9,%xmm6 + pxor %xmm10,%xmm1 + movdqa %xmm0,%xmm9 + psrlq $2,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $2,%xmm15 + pxor %xmm3,%xmm0 + pxor %xmm5,%xmm15 + pand %xmm8,%xmm0 + pand %xmm8,%xmm15 + pxor %xmm0,%xmm3 + psllq $2,%xmm0 + pxor %xmm15,%xmm5 + psllq $2,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa %xmm3,%xmm9 + psrlq $4,%xmm3 + movdqa %xmm5,%xmm10 + psrlq $4,%xmm5 + pxor %xmm4,%xmm3 + pxor %xmm2,%xmm5 + pand %xmm7,%xmm3 + pand %xmm7,%xmm5 + pxor %xmm3,%xmm4 + psllq $4,%xmm3 + pxor %xmm5,%xmm2 + psllq $4,%xmm5 + pxor %xmm9,%xmm3 + pxor %xmm10,%xmm5 + movdqa %xmm0,%xmm9 + psrlq $4,%xmm0 + movdqa %xmm15,%xmm10 + psrlq $4,%xmm15 + pxor %xmm6,%xmm0 + pxor %xmm1,%xmm15 + pand %xmm7,%xmm0 + pand %xmm7,%xmm15 + pxor %xmm0,%xmm6 + psllq $4,%xmm0 + pxor %xmm15,%xmm1 + psllq $4,%xmm15 + pxor %xmm9,%xmm0 + pxor %xmm10,%xmm15 + movdqa (%rax),%xmm7 + pxor %xmm7,%xmm5 + pxor %xmm7,%xmm3 + pxor %xmm7,%xmm1 + pxor %xmm7,%xmm6 + pxor %xmm7,%xmm2 + pxor %xmm7,%xmm4 + pxor %xmm7,%xmm15 + pxor %xmm7,%xmm0 + .byte 0xf3,0xc3 +.cfi_endproc +.size _bsaes_decrypt8,.-_bsaes_decrypt8 +.type _bsaes_key_convert,@function +.align 16 +_bsaes_key_convert: +.cfi_startproc + leaq .Lmasks(%rip),%r11 + movdqu (%rcx),%xmm7 + leaq 16(%rcx),%rcx + movdqa 0(%r11),%xmm0 + movdqa 16(%r11),%xmm1 + movdqa 32(%r11),%xmm2 + movdqa 48(%r11),%xmm3 + movdqa 64(%r11),%xmm4 + pcmpeqd %xmm5,%xmm5 + + movdqu (%rcx),%xmm6 + movdqa %xmm7,(%rax) + leaq 16(%rax),%rax + decl %r10d + jmp .Lkey_loop +.align 16 +.Lkey_loop: +.byte 102,15,56,0,244 + + movdqa %xmm0,%xmm8 + movdqa %xmm1,%xmm9 + + pand %xmm6,%xmm8 + pand %xmm6,%xmm9 + movdqa %xmm2,%xmm10 + pcmpeqb %xmm0,%xmm8 + psllq $4,%xmm0 + movdqa %xmm3,%xmm11 + pcmpeqb %xmm1,%xmm9 + psllq $4,%xmm1 + + pand %xmm6,%xmm10 + pand %xmm6,%xmm11 + movdqa %xmm0,%xmm12 + pcmpeqb %xmm2,%xmm10 + psllq $4,%xmm2 + movdqa %xmm1,%xmm13 + pcmpeqb %xmm3,%xmm11 + psllq $4,%xmm3 + + movdqa %xmm2,%xmm14 + movdqa %xmm3,%xmm15 + pxor %xmm5,%xmm8 + pxor %xmm5,%xmm9 + + pand %xmm6,%xmm12 + pand %xmm6,%xmm13 + movdqa %xmm8,0(%rax) + pcmpeqb %xmm0,%xmm12 + psrlq $4,%xmm0 + movdqa %xmm9,16(%rax) + pcmpeqb %xmm1,%xmm13 + psrlq $4,%xmm1 + leaq 16(%rcx),%rcx + + pand %xmm6,%xmm14 + pand %xmm6,%xmm15 + movdqa %xmm10,32(%rax) + pcmpeqb %xmm2,%xmm14 + psrlq $4,%xmm2 + movdqa %xmm11,48(%rax) + pcmpeqb %xmm3,%xmm15 + psrlq $4,%xmm3 + movdqu (%rcx),%xmm6 + + pxor %xmm5,%xmm13 + pxor %xmm5,%xmm14 + movdqa %xmm12,64(%rax) + movdqa %xmm13,80(%rax) + movdqa %xmm14,96(%rax) + movdqa %xmm15,112(%rax) + leaq 128(%rax),%rax + decl %r10d + jnz .Lkey_loop + + movdqa 80(%r11),%xmm7 + + .byte 0xf3,0xc3 +.cfi_endproc +.size _bsaes_key_convert,.-_bsaes_key_convert + +.globl ossl_bsaes_cbc_encrypt +.type ossl_bsaes_cbc_encrypt,@function +.align 16 +ossl_bsaes_cbc_encrypt: +.cfi_startproc +.byte 243,15,30,250 + cmpl $0,%r9d + jne asm_AES_cbc_encrypt + cmpq $128,%rdx + jb asm_AES_cbc_encrypt + + movq %rsp,%rax +.Lcbc_dec_prologue: + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-16 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + leaq -72(%rsp),%rsp +.cfi_adjust_cfa_offset 0x48 + movq %rsp,%rbp +.cfi_def_cfa_register %rbp + movl 240(%rcx),%eax + movq %rdi,%r12 + movq %rsi,%r13 + movq %rdx,%r14 + movq %rcx,%r15 + movq %r8,%rbx + shrq $4,%r14 + + movl %eax,%edx + shlq $7,%rax + subq $96,%rax + subq %rax,%rsp + + movq %rsp,%rax + movq %r15,%rcx + movl %edx,%r10d + call _bsaes_key_convert + pxor (%rsp),%xmm7 + movdqa %xmm6,(%rax) + movdqa %xmm7,(%rsp) + + movdqu (%rbx),%xmm14 + subq $8,%r14 +.Lcbc_dec_loop: + movdqu 0(%r12),%xmm15 + movdqu 16(%r12),%xmm0 + movdqu 32(%r12),%xmm1 + movdqu 48(%r12),%xmm2 + movdqu 64(%r12),%xmm3 + movdqu 80(%r12),%xmm4 + movq %rsp,%rax + movdqu 96(%r12),%xmm5 + movl %edx,%r10d + movdqu 112(%r12),%xmm6 + movdqa %xmm14,32(%rbp) + + call _bsaes_decrypt8 + + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm5 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm3 + movdqu 64(%r12),%xmm11 + pxor %xmm10,%xmm1 + movdqu 80(%r12),%xmm12 + pxor %xmm11,%xmm6 + movdqu 96(%r12),%xmm13 + pxor %xmm12,%xmm2 + movdqu 112(%r12),%xmm14 + pxor %xmm13,%xmm4 + movdqu %xmm15,0(%r13) + leaq 128(%r12),%r12 + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + movdqu %xmm1,64(%r13) + movdqu %xmm6,80(%r13) + movdqu %xmm2,96(%r13) + movdqu %xmm4,112(%r13) + leaq 128(%r13),%r13 + subq $8,%r14 + jnc .Lcbc_dec_loop + + addq $8,%r14 + jz .Lcbc_dec_done + + movdqu 0(%r12),%xmm15 + movq %rsp,%rax + movl %edx,%r10d + cmpq $2,%r14 + jb .Lcbc_dec_one + movdqu 16(%r12),%xmm0 + je .Lcbc_dec_two + movdqu 32(%r12),%xmm1 + cmpq $4,%r14 + jb .Lcbc_dec_three + movdqu 48(%r12),%xmm2 + je .Lcbc_dec_four + movdqu 64(%r12),%xmm3 + cmpq $6,%r14 + jb .Lcbc_dec_five + movdqu 80(%r12),%xmm4 + je .Lcbc_dec_six + movdqu 96(%r12),%xmm5 + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm5 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm3 + movdqu 64(%r12),%xmm11 + pxor %xmm10,%xmm1 + movdqu 80(%r12),%xmm12 + pxor %xmm11,%xmm6 + movdqu 96(%r12),%xmm14 + pxor %xmm12,%xmm2 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + movdqu %xmm1,64(%r13) + movdqu %xmm6,80(%r13) + movdqu %xmm2,96(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_six: + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm5 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm3 + movdqu 64(%r12),%xmm11 + pxor %xmm10,%xmm1 + movdqu 80(%r12),%xmm14 + pxor %xmm11,%xmm6 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + movdqu %xmm1,64(%r13) + movdqu %xmm6,80(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_five: + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm5 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm3 + movdqu 64(%r12),%xmm14 + pxor %xmm10,%xmm1 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + movdqu %xmm1,64(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_four: + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm5 + movdqu 48(%r12),%xmm14 + pxor %xmm9,%xmm3 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_three: + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm0 + movdqu 32(%r12),%xmm14 + pxor %xmm8,%xmm5 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_two: + movdqa %xmm14,32(%rbp) + call _bsaes_decrypt8 + pxor 32(%rbp),%xmm15 + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm14 + pxor %xmm7,%xmm0 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + jmp .Lcbc_dec_done +.align 16 +.Lcbc_dec_one: + leaq (%r12),%rdi + leaq 32(%rbp),%rsi + leaq (%r15),%rdx + call asm_AES_decrypt + pxor 32(%rbp),%xmm14 + movdqu %xmm14,(%r13) + movdqa %xmm15,%xmm14 + +.Lcbc_dec_done: + movdqu %xmm14,(%rbx) + leaq (%rsp),%rax + pxor %xmm0,%xmm0 +.Lcbc_dec_bzero: + movdqa %xmm0,0(%rax) + movdqa %xmm0,16(%rax) + leaq 32(%rax),%rax + cmpq %rax,%rbp + ja .Lcbc_dec_bzero + + leaq 120(%rbp),%rax +.cfi_def_cfa %rax,8 + movq -48(%rax),%r15 +.cfi_restore %r15 + movq -40(%rax),%r14 +.cfi_restore %r14 + movq -32(%rax),%r13 +.cfi_restore %r13 + movq -24(%rax),%r12 +.cfi_restore %r12 + movq -16(%rax),%rbx +.cfi_restore %rbx + movq -8(%rax),%rbp +.cfi_restore %rbp + leaq (%rax),%rsp +.cfi_def_cfa_register %rsp +.Lcbc_dec_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size ossl_bsaes_cbc_encrypt,.-ossl_bsaes_cbc_encrypt + +.globl ossl_bsaes_ctr32_encrypt_blocks +.type ossl_bsaes_ctr32_encrypt_blocks,@function +.align 16 +ossl_bsaes_ctr32_encrypt_blocks: +.cfi_startproc +.byte 243,15,30,250 + movq %rsp,%rax +.Lctr_enc_prologue: + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-16 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + leaq -72(%rsp),%rsp +.cfi_adjust_cfa_offset 0x48 + movq %rsp,%rbp +.cfi_def_cfa_register %rbp + movdqu (%r8),%xmm0 + movl 240(%rcx),%eax + movq %rdi,%r12 + movq %rsi,%r13 + movq %rdx,%r14 + movq %rcx,%r15 + movdqa %xmm0,32(%rbp) + cmpq $8,%rdx + jb .Lctr_enc_short + + movl %eax,%ebx + shlq $7,%rax + subq $96,%rax + subq %rax,%rsp + + movq %rsp,%rax + movq %r15,%rcx + movl %ebx,%r10d + call _bsaes_key_convert + pxor %xmm6,%xmm7 + movdqa %xmm7,(%rax) + + movdqa (%rsp),%xmm8 + leaq .LADD1(%rip),%r11 + movdqa 32(%rbp),%xmm15 + movdqa -32(%r11),%xmm7 +.byte 102,68,15,56,0,199 +.byte 102,68,15,56,0,255 + movdqa %xmm8,(%rsp) + jmp .Lctr_enc_loop +.align 16 +.Lctr_enc_loop: + movdqa %xmm15,32(%rbp) + movdqa %xmm15,%xmm0 + movdqa %xmm15,%xmm1 + paddd 0(%r11),%xmm0 + movdqa %xmm15,%xmm2 + paddd 16(%r11),%xmm1 + movdqa %xmm15,%xmm3 + paddd 32(%r11),%xmm2 + movdqa %xmm15,%xmm4 + paddd 48(%r11),%xmm3 + movdqa %xmm15,%xmm5 + paddd 64(%r11),%xmm4 + movdqa %xmm15,%xmm6 + paddd 80(%r11),%xmm5 + paddd 96(%r11),%xmm6 + + + + movdqa (%rsp),%xmm8 + leaq 16(%rsp),%rax + movdqa -16(%r11),%xmm7 + pxor %xmm8,%xmm15 + pxor %xmm8,%xmm0 + pxor %xmm8,%xmm1 + pxor %xmm8,%xmm2 +.byte 102,68,15,56,0,255 +.byte 102,15,56,0,199 + pxor %xmm8,%xmm3 + pxor %xmm8,%xmm4 +.byte 102,15,56,0,207 +.byte 102,15,56,0,215 + pxor %xmm8,%xmm5 + pxor %xmm8,%xmm6 +.byte 102,15,56,0,223 +.byte 102,15,56,0,231 +.byte 102,15,56,0,239 +.byte 102,15,56,0,247 + leaq .LBS0(%rip),%r11 + movl %ebx,%r10d + + call _bsaes_encrypt8_bitslice + + subq $8,%r14 + jc .Lctr_enc_loop_done + + movdqu 0(%r12),%xmm7 + movdqu 16(%r12),%xmm8 + movdqu 32(%r12),%xmm9 + movdqu 48(%r12),%xmm10 + movdqu 64(%r12),%xmm11 + movdqu 80(%r12),%xmm12 + movdqu 96(%r12),%xmm13 + movdqu 112(%r12),%xmm14 + leaq 128(%r12),%r12 + pxor %xmm15,%xmm7 + movdqa 32(%rbp),%xmm15 + pxor %xmm8,%xmm0 + movdqu %xmm7,0(%r13) + pxor %xmm9,%xmm3 + movdqu %xmm0,16(%r13) + pxor %xmm10,%xmm5 + movdqu %xmm3,32(%r13) + pxor %xmm11,%xmm2 + movdqu %xmm5,48(%r13) + pxor %xmm12,%xmm6 + movdqu %xmm2,64(%r13) + pxor %xmm13,%xmm1 + movdqu %xmm6,80(%r13) + pxor %xmm14,%xmm4 + movdqu %xmm1,96(%r13) + leaq .LADD1(%rip),%r11 + movdqu %xmm4,112(%r13) + leaq 128(%r13),%r13 + paddd 112(%r11),%xmm15 + jnz .Lctr_enc_loop + + jmp .Lctr_enc_done +.align 16 +.Lctr_enc_loop_done: + addq $8,%r14 + movdqu 0(%r12),%xmm7 + pxor %xmm7,%xmm15 + movdqu %xmm15,0(%r13) + cmpq $2,%r14 + jb .Lctr_enc_done + movdqu 16(%r12),%xmm8 + pxor %xmm8,%xmm0 + movdqu %xmm0,16(%r13) + je .Lctr_enc_done + movdqu 32(%r12),%xmm9 + pxor %xmm9,%xmm3 + movdqu %xmm3,32(%r13) + cmpq $4,%r14 + jb .Lctr_enc_done + movdqu 48(%r12),%xmm10 + pxor %xmm10,%xmm5 + movdqu %xmm5,48(%r13) + je .Lctr_enc_done + movdqu 64(%r12),%xmm11 + pxor %xmm11,%xmm2 + movdqu %xmm2,64(%r13) + cmpq $6,%r14 + jb .Lctr_enc_done + movdqu 80(%r12),%xmm12 + pxor %xmm12,%xmm6 + movdqu %xmm6,80(%r13) + je .Lctr_enc_done + movdqu 96(%r12),%xmm13 + pxor %xmm13,%xmm1 + movdqu %xmm1,96(%r13) + jmp .Lctr_enc_done + +.align 16 +.Lctr_enc_short: + leaq 32(%rbp),%rdi + leaq 48(%rbp),%rsi + leaq (%r15),%rdx + call asm_AES_encrypt + movdqu (%r12),%xmm0 + leaq 16(%r12),%r12 + movl 44(%rbp),%eax + bswapl %eax + pxor 48(%rbp),%xmm0 + incl %eax + movdqu %xmm0,(%r13) + bswapl %eax + leaq 16(%r13),%r13 + movl %eax,44(%rsp) + decq %r14 + jnz .Lctr_enc_short + +.Lctr_enc_done: + leaq (%rsp),%rax + pxor %xmm0,%xmm0 +.Lctr_enc_bzero: + movdqa %xmm0,0(%rax) + movdqa %xmm0,16(%rax) + leaq 32(%rax),%rax + cmpq %rax,%rbp + ja .Lctr_enc_bzero + + leaq 120(%rbp),%rax +.cfi_def_cfa %rax,8 + movq -48(%rax),%r15 +.cfi_restore %r15 + movq -40(%rax),%r14 +.cfi_restore %r14 + movq -32(%rax),%r13 +.cfi_restore %r13 + movq -24(%rax),%r12 +.cfi_restore %r12 + movq -16(%rax),%rbx +.cfi_restore %rbx + movq -8(%rax),%rbp +.cfi_restore %rbp + leaq (%rax),%rsp +.cfi_def_cfa_register %rsp +.Lctr_enc_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size ossl_bsaes_ctr32_encrypt_blocks,.-ossl_bsaes_ctr32_encrypt_blocks +.globl ossl_bsaes_xts_encrypt +.type ossl_bsaes_xts_encrypt,@function +.align 16 +ossl_bsaes_xts_encrypt: +.cfi_startproc + movq %rsp,%rax +.Lxts_enc_prologue: + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-16 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + leaq -72(%rsp),%rsp +.cfi_adjust_cfa_offset 0x48 + movq %rsp,%rbp +.cfi_def_cfa_register %rbp + movq %rdi,%r12 + movq %rsi,%r13 + movq %rdx,%r14 + movq %rcx,%r15 + + leaq (%r9),%rdi + leaq 32(%rbp),%rsi + leaq (%r8),%rdx + call asm_AES_encrypt + + movl 240(%r15),%eax + movq %r14,%rbx + + movl %eax,%edx + shlq $7,%rax + subq $96,%rax + subq %rax,%rsp + + movq %rsp,%rax + movq %r15,%rcx + movl %edx,%r10d + call _bsaes_key_convert + pxor %xmm6,%xmm7 + movdqa %xmm7,(%rax) + + andq $-16,%r14 + subq $0x80,%rsp + movdqa 32(%rbp),%xmm6 + + pxor %xmm14,%xmm14 + movdqa .Lxts_magic(%rip),%xmm12 + pcmpgtd %xmm6,%xmm14 + + subq $0x80,%r14 + jc .Lxts_enc_short + jmp .Lxts_enc_loop + +.align 16 +.Lxts_enc_loop: + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm15 + movdqa %xmm6,0(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm0 + movdqa %xmm6,16(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 0(%r12),%xmm7 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm1 + movdqa %xmm6,32(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm15 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm2 + movdqa %xmm6,48(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm0 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm3 + movdqa %xmm6,64(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm4 + movdqa %xmm6,80(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 64(%r12),%xmm11 + pxor %xmm10,%xmm2 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm5 + movdqa %xmm6,96(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 80(%r12),%xmm12 + pxor %xmm11,%xmm3 + movdqu 96(%r12),%xmm13 + pxor %xmm12,%xmm4 + movdqu 112(%r12),%xmm14 + leaq 128(%r12),%r12 + movdqa %xmm6,112(%rsp) + pxor %xmm13,%xmm5 + leaq 128(%rsp),%rax + pxor %xmm14,%xmm6 + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm5 + movdqu %xmm3,32(%r13) + pxor 64(%rsp),%xmm2 + movdqu %xmm5,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm2,64(%r13) + pxor 96(%rsp),%xmm1 + movdqu %xmm6,80(%r13) + pxor 112(%rsp),%xmm4 + movdqu %xmm1,96(%r13) + movdqu %xmm4,112(%r13) + leaq 128(%r13),%r13 + + movdqa 112(%rsp),%xmm6 + pxor %xmm14,%xmm14 + movdqa .Lxts_magic(%rip),%xmm12 + pcmpgtd %xmm6,%xmm14 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + + subq $0x80,%r14 + jnc .Lxts_enc_loop + +.Lxts_enc_short: + addq $0x80,%r14 + jz .Lxts_enc_done + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm15 + movdqa %xmm6,0(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm0 + movdqa %xmm6,16(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 0(%r12),%xmm7 + cmpq $16,%r14 + je .Lxts_enc_1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm1 + movdqa %xmm6,32(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 16(%r12),%xmm8 + cmpq $32,%r14 + je .Lxts_enc_2 + pxor %xmm7,%xmm15 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm2 + movdqa %xmm6,48(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 32(%r12),%xmm9 + cmpq $48,%r14 + je .Lxts_enc_3 + pxor %xmm8,%xmm0 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm3 + movdqa %xmm6,64(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 48(%r12),%xmm10 + cmpq $64,%r14 + je .Lxts_enc_4 + pxor %xmm9,%xmm1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm4 + movdqa %xmm6,80(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 64(%r12),%xmm11 + cmpq $80,%r14 + je .Lxts_enc_5 + pxor %xmm10,%xmm2 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm5 + movdqa %xmm6,96(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 80(%r12),%xmm12 + cmpq $96,%r14 + je .Lxts_enc_6 + pxor %xmm11,%xmm3 + movdqu 96(%r12),%xmm13 + pxor %xmm12,%xmm4 + movdqa %xmm6,112(%rsp) + leaq 112(%r12),%r12 + pxor %xmm13,%xmm5 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm5 + movdqu %xmm3,32(%r13) + pxor 64(%rsp),%xmm2 + movdqu %xmm5,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm2,64(%r13) + pxor 96(%rsp),%xmm1 + movdqu %xmm6,80(%r13) + movdqu %xmm1,96(%r13) + leaq 112(%r13),%r13 + + movdqa 112(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_6: + pxor %xmm11,%xmm3 + leaq 96(%r12),%r12 + pxor %xmm12,%xmm4 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm5 + movdqu %xmm3,32(%r13) + pxor 64(%rsp),%xmm2 + movdqu %xmm5,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm2,64(%r13) + movdqu %xmm6,80(%r13) + leaq 96(%r13),%r13 + + movdqa 96(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_5: + pxor %xmm10,%xmm2 + leaq 80(%r12),%r12 + pxor %xmm11,%xmm3 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm5 + movdqu %xmm3,32(%r13) + pxor 64(%rsp),%xmm2 + movdqu %xmm5,48(%r13) + movdqu %xmm2,64(%r13) + leaq 80(%r13),%r13 + + movdqa 80(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_4: + pxor %xmm9,%xmm1 + leaq 64(%r12),%r12 + pxor %xmm10,%xmm2 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm5 + movdqu %xmm3,32(%r13) + movdqu %xmm5,48(%r13) + leaq 64(%r13),%r13 + + movdqa 64(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_3: + pxor %xmm8,%xmm0 + leaq 48(%r12),%r12 + pxor %xmm9,%xmm1 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm3 + movdqu %xmm0,16(%r13) + movdqu %xmm3,32(%r13) + leaq 48(%r13),%r13 + + movdqa 48(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_2: + pxor %xmm7,%xmm15 + leaq 32(%r12),%r12 + pxor %xmm8,%xmm0 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_encrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + leaq 32(%r13),%r13 + + movdqa 32(%rsp),%xmm6 + jmp .Lxts_enc_done +.align 16 +.Lxts_enc_1: + pxor %xmm15,%xmm7 + leaq 16(%r12),%r12 + movdqa %xmm7,32(%rbp) + leaq 32(%rbp),%rdi + leaq 32(%rbp),%rsi + leaq (%r15),%rdx + call asm_AES_encrypt + pxor 32(%rbp),%xmm15 + + + + + + movdqu %xmm15,0(%r13) + leaq 16(%r13),%r13 + + movdqa 16(%rsp),%xmm6 + +.Lxts_enc_done: + andl $15,%ebx + jz .Lxts_enc_ret + movq %r13,%rdx + +.Lxts_enc_steal: + movzbl (%r12),%eax + movzbl -16(%rdx),%ecx + leaq 1(%r12),%r12 + movb %al,-16(%rdx) + movb %cl,0(%rdx) + leaq 1(%rdx),%rdx + subl $1,%ebx + jnz .Lxts_enc_steal + + movdqu -16(%r13),%xmm15 + leaq 32(%rbp),%rdi + pxor %xmm6,%xmm15 + leaq 32(%rbp),%rsi + movdqa %xmm15,32(%rbp) + leaq (%r15),%rdx + call asm_AES_encrypt + pxor 32(%rbp),%xmm6 + movdqu %xmm6,-16(%r13) + +.Lxts_enc_ret: + leaq (%rsp),%rax + pxor %xmm0,%xmm0 +.Lxts_enc_bzero: + movdqa %xmm0,0(%rax) + movdqa %xmm0,16(%rax) + leaq 32(%rax),%rax + cmpq %rax,%rbp + ja .Lxts_enc_bzero + + leaq 120(%rbp),%rax +.cfi_def_cfa %rax,8 + movq -48(%rax),%r15 +.cfi_restore %r15 + movq -40(%rax),%r14 +.cfi_restore %r14 + movq -32(%rax),%r13 +.cfi_restore %r13 + movq -24(%rax),%r12 +.cfi_restore %r12 + movq -16(%rax),%rbx +.cfi_restore %rbx + movq -8(%rax),%rbp +.cfi_restore %rbp + leaq (%rax),%rsp +.cfi_def_cfa_register %rsp +.Lxts_enc_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size ossl_bsaes_xts_encrypt,.-ossl_bsaes_xts_encrypt + +.globl ossl_bsaes_xts_decrypt +.type ossl_bsaes_xts_decrypt,@function +.align 16 +ossl_bsaes_xts_decrypt: +.cfi_startproc + movq %rsp,%rax +.Lxts_dec_prologue: + pushq %rbp +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbp,-16 + pushq %rbx +.cfi_adjust_cfa_offset 8 +.cfi_offset %rbx,-24 + pushq %r12 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r12,-32 + pushq %r13 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r13,-40 + pushq %r14 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r14,-48 + pushq %r15 +.cfi_adjust_cfa_offset 8 +.cfi_offset %r15,-56 + leaq -72(%rsp),%rsp +.cfi_adjust_cfa_offset 0x48 + movq %rsp,%rbp + movq %rdi,%r12 + movq %rsi,%r13 + movq %rdx,%r14 + movq %rcx,%r15 + + leaq (%r9),%rdi + leaq 32(%rbp),%rsi + leaq (%r8),%rdx + call asm_AES_encrypt + + movl 240(%r15),%eax + movq %r14,%rbx + + movl %eax,%edx + shlq $7,%rax + subq $96,%rax + subq %rax,%rsp + + movq %rsp,%rax + movq %r15,%rcx + movl %edx,%r10d + call _bsaes_key_convert + pxor (%rsp),%xmm7 + movdqa %xmm6,(%rax) + movdqa %xmm7,(%rsp) + + xorl %eax,%eax + andq $-16,%r14 + testl $15,%ebx + setnz %al + shlq $4,%rax + subq %rax,%r14 + + subq $0x80,%rsp + movdqa 32(%rbp),%xmm6 + + pxor %xmm14,%xmm14 + movdqa .Lxts_magic(%rip),%xmm12 + pcmpgtd %xmm6,%xmm14 + + subq $0x80,%r14 + jc .Lxts_dec_short + jmp .Lxts_dec_loop + +.align 16 +.Lxts_dec_loop: + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm15 + movdqa %xmm6,0(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm0 + movdqa %xmm6,16(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 0(%r12),%xmm7 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm1 + movdqa %xmm6,32(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 16(%r12),%xmm8 + pxor %xmm7,%xmm15 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm2 + movdqa %xmm6,48(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 32(%r12),%xmm9 + pxor %xmm8,%xmm0 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm3 + movdqa %xmm6,64(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 48(%r12),%xmm10 + pxor %xmm9,%xmm1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm4 + movdqa %xmm6,80(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 64(%r12),%xmm11 + pxor %xmm10,%xmm2 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm5 + movdqa %xmm6,96(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 80(%r12),%xmm12 + pxor %xmm11,%xmm3 + movdqu 96(%r12),%xmm13 + pxor %xmm12,%xmm4 + movdqu 112(%r12),%xmm14 + leaq 128(%r12),%r12 + movdqa %xmm6,112(%rsp) + pxor %xmm13,%xmm5 + leaq 128(%rsp),%rax + pxor %xmm14,%xmm6 + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm3 + movdqu %xmm5,32(%r13) + pxor 64(%rsp),%xmm1 + movdqu %xmm3,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm1,64(%r13) + pxor 96(%rsp),%xmm2 + movdqu %xmm6,80(%r13) + pxor 112(%rsp),%xmm4 + movdqu %xmm2,96(%r13) + movdqu %xmm4,112(%r13) + leaq 128(%r13),%r13 + + movdqa 112(%rsp),%xmm6 + pxor %xmm14,%xmm14 + movdqa .Lxts_magic(%rip),%xmm12 + pcmpgtd %xmm6,%xmm14 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + + subq $0x80,%r14 + jnc .Lxts_dec_loop + +.Lxts_dec_short: + addq $0x80,%r14 + jz .Lxts_dec_done + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm15 + movdqa %xmm6,0(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm0 + movdqa %xmm6,16(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 0(%r12),%xmm7 + cmpq $16,%r14 + je .Lxts_dec_1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm1 + movdqa %xmm6,32(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 16(%r12),%xmm8 + cmpq $32,%r14 + je .Lxts_dec_2 + pxor %xmm7,%xmm15 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm2 + movdqa %xmm6,48(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 32(%r12),%xmm9 + cmpq $48,%r14 + je .Lxts_dec_3 + pxor %xmm8,%xmm0 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm3 + movdqa %xmm6,64(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 48(%r12),%xmm10 + cmpq $64,%r14 + je .Lxts_dec_4 + pxor %xmm9,%xmm1 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm4 + movdqa %xmm6,80(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 64(%r12),%xmm11 + cmpq $80,%r14 + je .Lxts_dec_5 + pxor %xmm10,%xmm2 + pshufd $0x13,%xmm14,%xmm13 + pxor %xmm14,%xmm14 + movdqa %xmm6,%xmm5 + movdqa %xmm6,96(%rsp) + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + pcmpgtd %xmm6,%xmm14 + pxor %xmm13,%xmm6 + movdqu 80(%r12),%xmm12 + cmpq $96,%r14 + je .Lxts_dec_6 + pxor %xmm11,%xmm3 + movdqu 96(%r12),%xmm13 + pxor %xmm12,%xmm4 + movdqa %xmm6,112(%rsp) + leaq 112(%r12),%r12 + pxor %xmm13,%xmm5 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm3 + movdqu %xmm5,32(%r13) + pxor 64(%rsp),%xmm1 + movdqu %xmm3,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm1,64(%r13) + pxor 96(%rsp),%xmm2 + movdqu %xmm6,80(%r13) + movdqu %xmm2,96(%r13) + leaq 112(%r13),%r13 + + movdqa 112(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_6: + pxor %xmm11,%xmm3 + leaq 96(%r12),%r12 + pxor %xmm12,%xmm4 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm3 + movdqu %xmm5,32(%r13) + pxor 64(%rsp),%xmm1 + movdqu %xmm3,48(%r13) + pxor 80(%rsp),%xmm6 + movdqu %xmm1,64(%r13) + movdqu %xmm6,80(%r13) + leaq 96(%r13),%r13 + + movdqa 96(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_5: + pxor %xmm10,%xmm2 + leaq 80(%r12),%r12 + pxor %xmm11,%xmm3 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm3 + movdqu %xmm5,32(%r13) + pxor 64(%rsp),%xmm1 + movdqu %xmm3,48(%r13) + movdqu %xmm1,64(%r13) + leaq 80(%r13),%r13 + + movdqa 80(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_4: + pxor %xmm9,%xmm1 + leaq 64(%r12),%r12 + pxor %xmm10,%xmm2 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + pxor 48(%rsp),%xmm3 + movdqu %xmm5,32(%r13) + movdqu %xmm3,48(%r13) + leaq 64(%r13),%r13 + + movdqa 64(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_3: + pxor %xmm8,%xmm0 + leaq 48(%r12),%r12 + pxor %xmm9,%xmm1 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + pxor 32(%rsp),%xmm5 + movdqu %xmm0,16(%r13) + movdqu %xmm5,32(%r13) + leaq 48(%r13),%r13 + + movdqa 48(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_2: + pxor %xmm7,%xmm15 + leaq 32(%r12),%r12 + pxor %xmm8,%xmm0 + leaq 128(%rsp),%rax + movl %edx,%r10d + + call _bsaes_decrypt8 + + pxor 0(%rsp),%xmm15 + pxor 16(%rsp),%xmm0 + movdqu %xmm15,0(%r13) + movdqu %xmm0,16(%r13) + leaq 32(%r13),%r13 + + movdqa 32(%rsp),%xmm6 + jmp .Lxts_dec_done +.align 16 +.Lxts_dec_1: + pxor %xmm15,%xmm7 + leaq 16(%r12),%r12 + movdqa %xmm7,32(%rbp) + leaq 32(%rbp),%rdi + leaq 32(%rbp),%rsi + leaq (%r15),%rdx + call asm_AES_decrypt + pxor 32(%rbp),%xmm15 + + + + + + movdqu %xmm15,0(%r13) + leaq 16(%r13),%r13 + + movdqa 16(%rsp),%xmm6 + +.Lxts_dec_done: + andl $15,%ebx + jz .Lxts_dec_ret + + pxor %xmm14,%xmm14 + movdqa .Lxts_magic(%rip),%xmm12 + pcmpgtd %xmm6,%xmm14 + pshufd $0x13,%xmm14,%xmm13 + movdqa %xmm6,%xmm5 + paddq %xmm6,%xmm6 + pand %xmm12,%xmm13 + movdqu (%r12),%xmm15 + pxor %xmm13,%xmm6 + + leaq 32(%rbp),%rdi + pxor %xmm6,%xmm15 + leaq 32(%rbp),%rsi + movdqa %xmm15,32(%rbp) + leaq (%r15),%rdx + call asm_AES_decrypt + pxor 32(%rbp),%xmm6 + movq %r13,%rdx + movdqu %xmm6,(%r13) + +.Lxts_dec_steal: + movzbl 16(%r12),%eax + movzbl (%rdx),%ecx + leaq 1(%r12),%r12 + movb %al,(%rdx) + movb %cl,16(%rdx) + leaq 1(%rdx),%rdx + subl $1,%ebx + jnz .Lxts_dec_steal + + movdqu (%r13),%xmm15 + leaq 32(%rbp),%rdi + pxor %xmm5,%xmm15 + leaq 32(%rbp),%rsi + movdqa %xmm15,32(%rbp) + leaq (%r15),%rdx + call asm_AES_decrypt + pxor 32(%rbp),%xmm5 + movdqu %xmm5,(%r13) + +.Lxts_dec_ret: + leaq (%rsp),%rax + pxor %xmm0,%xmm0 +.Lxts_dec_bzero: + movdqa %xmm0,0(%rax) + movdqa %xmm0,16(%rax) + leaq 32(%rax),%rax + cmpq %rax,%rbp + ja .Lxts_dec_bzero + + leaq 120(%rbp),%rax +.cfi_def_cfa %rax,8 + movq -48(%rax),%r15 +.cfi_restore %r15 + movq -40(%rax),%r14 +.cfi_restore %r14 + movq -32(%rax),%r13 +.cfi_restore %r13 + movq -24(%rax),%r12 +.cfi_restore %r12 + movq -16(%rax),%rbx +.cfi_restore %rbx + movq -8(%rax),%rbp +.cfi_restore %rbp + leaq (%rax),%rsp +.cfi_def_cfa_register %rsp +.Lxts_dec_epilogue: + .byte 0xf3,0xc3 +.cfi_endproc +.size ossl_bsaes_xts_decrypt,.-ossl_bsaes_xts_decrypt +.type _bsaes_const,@object +.align 64 +_bsaes_const: +.LM0ISR: +.quad 0x0a0e0206070b0f03, 0x0004080c0d010509 +.LISRM0: +.quad 0x01040b0e0205080f, 0x0306090c00070a0d +.LISR: +.quad 0x0504070602010003, 0x0f0e0d0c080b0a09 +.LBS0: +.quad 0x5555555555555555, 0x5555555555555555 +.LBS1: +.quad 0x3333333333333333, 0x3333333333333333 +.LBS2: +.quad 0x0f0f0f0f0f0f0f0f, 0x0f0f0f0f0f0f0f0f +.LSR: +.quad 0x0504070600030201, 0x0f0e0d0c0a09080b +.LSRM0: +.quad 0x0304090e00050a0f, 0x01060b0c0207080d +.LM0SR: +.quad 0x0a0e02060f03070b, 0x0004080c05090d01 +.LSWPUP: +.quad 0x0706050403020100, 0x0c0d0e0f0b0a0908 +.LSWPUPM0SR: +.quad 0x0a0d02060c03070b, 0x0004080f05090e01 +.LADD1: +.quad 0x0000000000000000, 0x0000000100000000 +.LADD2: +.quad 0x0000000000000000, 0x0000000200000000 +.LADD3: +.quad 0x0000000000000000, 0x0000000300000000 +.LADD4: +.quad 0x0000000000000000, 0x0000000400000000 +.LADD5: +.quad 0x0000000000000000, 0x0000000500000000 +.LADD6: +.quad 0x0000000000000000, 0x0000000600000000 +.LADD7: +.quad 0x0000000000000000, 0x0000000700000000 +.LADD8: +.quad 0x0000000000000000, 0x0000000800000000 +.Lxts_magic: +.long 0x87,0,1,0 +.Lmasks: +.quad 0x0101010101010101, 0x0101010101010101 +.quad 0x0202020202020202, 0x0202020202020202 +.quad 0x0404040404040404, 0x0404040404040404 +.quad 0x0808080808080808, 0x0808080808080808 +.LM0: +.quad 0x02060a0e03070b0f, 0x0004080c0105090d +.L63: +.quad 0x6363636363636363, 0x6363636363636363 +.byte 66,105,116,45,115,108,105,99,101,100,32,65,69,83,32,102,111,114,32,120,56,54,95,54,52,47,83,83,83,69,51,44,32,69,109,105,108,105,97,32,75,195,164,115,112,101,114,44,32,80,101,116,101,114,32,83,99,104,119,97,98,101,44,32,65,110,100,121,32,80,111,108,121,97,107,111,118,0 +.align 64 +.size _bsaes_const,.-_bsaes_const + .section ".note.gnu.property", "a" + .p2align 3 + .long 1f - 0f + .long 4f - 1f + .long 5 +0: + # "GNU" encoded with .byte, since .asciz isn't supported + # on Solaris. + .byte 0x47 + .byte 0x4e + .byte 0x55 + .byte 0 +1: + .p2align 3 + .long 0xc0000002 + .long 3f - 2f +2: + .long 3 +3: + .p2align 3 +4: diff --git a/secure/lib/libcrypto/arch/i386/aes-586.S b/secure/lib/libcrypto/arch/i386/aes-586.S new file mode 100644 --- /dev/null +++ b/secure/lib/libcrypto/arch/i386/aes-586.S @@ -0,0 +1,6644 @@ +/* Do not modify. This file is auto-generated from aes-586.pl. */ +#ifdef PIC +.text +.type _x86_AES_encrypt_compact,@function +.align 16 +_x86_AES_encrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi +.align 16 +.L000loop: + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movzbl -128(%ebp,%esi,1),%esi + movzbl %ch,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ah,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $8,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movzbl -128(%ebp,%ecx,1),%ecx + shll $24,%ecx + xorl %ecx,%edx + movl %esi,%ecx + + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %ecx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %ecx,%edi + xorl %esi,%ecx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%ecx + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%ecx + andl %edx,%ebp + leal (%edx,%edx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %edx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %edx,%edi + xorl %esi,%edx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%edx + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%edx + andl %eax,%ebp + leal (%eax,%eax,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %eax,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %eax,%edi + xorl %esi,%eax + rorl $24,%edi + xorl %ebp,%esi + roll $24,%eax + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%eax + andl %ebx,%ebp + leal (%ebx,%ebx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %ebx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %ebx,%edi + xorl %esi,%ebx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%ebx + xorl %edi,%esi + xorl %esi,%ebx + movl 20(%esp),%edi + movl 28(%esp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L000loop + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movzbl -128(%ebp,%esi,1),%esi + movzbl %ch,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + + movl 20(%esp),%edi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ah,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $8,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movzbl -128(%ebp,%ecx,1),%ecx + shll $24,%ecx + xorl %ecx,%edx + movl %esi,%ecx + + xorl 16(%edi),%eax + xorl 20(%edi),%ebx + xorl 24(%edi),%ecx + xorl 28(%edi),%edx + ret +.size _x86_AES_encrypt_compact,.-_x86_AES_encrypt_compact +.type _sse_AES_encrypt_compact,@function +.align 16 +_sse_AES_encrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl $454761243,%eax + movl %eax,8(%esp) + movl %eax,12(%esp) + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx +.align 16 +.L001loop: + pshufw $8,%mm0,%mm1 + pshufw $13,%mm4,%mm5 + movd %mm1,%eax + movd %mm5,%ebx + movl %edi,20(%esp) + movzbl %al,%esi + movzbl %ah,%edx + pshufw $13,%mm0,%mm2 + movzbl -128(%ebp,%esi,1),%ecx + movzbl %bl,%edi + movzbl -128(%ebp,%edx,1),%edx + shrl $16,%eax + shll $8,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $16,%esi + pshufw $8,%mm4,%mm6 + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $24,%esi + shrl $16,%ebx + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $8,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + movd %mm2,%eax + movd %ecx,%mm0 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %ah,%edi + shll $16,%ecx + movd %mm6,%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + shll $8,%esi + shrl $16,%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shrl $16,%eax + movd %ecx,%mm1 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %ah,%edi + shll $16,%ecx + andl $255,%eax + orl %esi,%ecx + punpckldq %mm1,%mm0 + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + andl $255,%ebx + movzbl -128(%ebp,%eax,1),%eax + orl %esi,%ecx + shll $16,%eax + movzbl -128(%ebp,%edi,1),%esi + orl %eax,%edx + shll $8,%esi + movzbl -128(%ebp,%ebx,1),%ebx + orl %esi,%ecx + orl %ebx,%edx + movl 20(%esp),%edi + movd %ecx,%mm4 + movd %edx,%mm5 + punpckldq %mm5,%mm4 + addl $16,%edi + cmpl 24(%esp),%edi + ja .L002out + movq 8(%esp),%mm2 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + movq %mm0,%mm1 + movq %mm4,%mm5 + pcmpgtb %mm0,%mm3 + pcmpgtb %mm4,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + pshufw $177,%mm0,%mm2 + pshufw $177,%mm4,%mm6 + paddb %mm0,%mm0 + paddb %mm4,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pshufw $177,%mm2,%mm3 + pshufw $177,%mm6,%mm7 + pxor %mm0,%mm1 + pxor %mm4,%mm5 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq %mm3,%mm2 + movq %mm7,%mm6 + pslld $8,%mm3 + pslld $8,%mm7 + psrld $24,%mm2 + psrld $24,%mm6 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq %mm1,%mm3 + movq %mm5,%mm7 + movq (%edi),%mm2 + movq 8(%edi),%mm6 + psrld $8,%mm1 + psrld $8,%mm5 + movl -128(%ebp),%eax + pslld $24,%mm3 + pslld $24,%mm7 + movl -64(%ebp),%ebx + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movl (%ebp),%ecx + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movl 64(%ebp),%edx + pxor %mm2,%mm0 + pxor %mm6,%mm4 + jmp .L001loop +.align 16 +.L002out: + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + ret +.size _sse_AES_encrypt_compact,.-_sse_AES_encrypt_compact +.type _x86_AES_encrypt,@function +.align 16 +_x86_AES_encrypt: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) +.align 16 +.L003loop: + movl %eax,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %bh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movl (%ebp,%esi,8),%esi + movzbl %ch,%edi + xorl 3(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movl (%ebp,%esi,8),%esi + movzbl %dh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movzbl %bh,%edi + xorl 1(%ebp,%edi,8),%esi + + movl 20(%esp),%edi + movl (%ebp,%edx,8),%edx + movzbl %ah,%eax + xorl 3(%ebp,%eax,8),%edx + movl 4(%esp),%eax + andl $255,%ebx + xorl 2(%ebp,%ebx,8),%edx + movl 8(%esp),%ebx + xorl 1(%ebp,%ecx,8),%edx + movl %esi,%ecx + + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L003loop + movl %eax,%esi + andl $255,%esi + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %bh,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %ch,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %dh,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movzbl %bh,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movl 2(%ebp,%edx,8),%edx + andl $255,%edx + movzbl %ah,%eax + movl (%ebp,%eax,8),%eax + andl $65280,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movl (%ebp,%ebx,8),%ebx + andl $16711680,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movl 2(%ebp,%ecx,8),%ecx + andl $4278190080,%ecx + xorl %ecx,%edx + movl %esi,%ecx + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + ret +.align 64 +.LAES_Te: +.long 2774754246,2774754246 +.long 2222750968,2222750968 +.long 2574743534,2574743534 +.long 2373680118,2373680118 +.long 234025727,234025727 +.long 3177933782,3177933782 +.long 2976870366,2976870366 +.long 1422247313,1422247313 +.long 1345335392,1345335392 +.long 50397442,50397442 +.long 2842126286,2842126286 +.long 2099981142,2099981142 +.long 436141799,436141799 +.long 1658312629,1658312629 +.long 3870010189,3870010189 +.long 2591454956,2591454956 +.long 1170918031,1170918031 +.long 2642575903,2642575903 +.long 1086966153,1086966153 +.long 2273148410,2273148410 +.long 368769775,368769775 +.long 3948501426,3948501426 +.long 3376891790,3376891790 +.long 200339707,200339707 +.long 3970805057,3970805057 +.long 1742001331,1742001331 +.long 4255294047,4255294047 +.long 3937382213,3937382213 +.long 3214711843,3214711843 +.long 4154762323,4154762323 +.long 2524082916,2524082916 +.long 1539358875,1539358875 +.long 3266819957,3266819957 +.long 486407649,486407649 +.long 2928907069,2928907069 +.long 1780885068,1780885068 +.long 1513502316,1513502316 +.long 1094664062,1094664062 +.long 49805301,49805301 +.long 1338821763,1338821763 +.long 1546925160,1546925160 +.long 4104496465,4104496465 +.long 887481809,887481809 +.long 150073849,150073849 +.long 2473685474,2473685474 +.long 1943591083,1943591083 +.long 1395732834,1395732834 +.long 1058346282,1058346282 +.long 201589768,201589768 +.long 1388824469,1388824469 +.long 1696801606,1696801606 +.long 1589887901,1589887901 +.long 672667696,672667696 +.long 2711000631,2711000631 +.long 251987210,251987210 +.long 3046808111,3046808111 +.long 151455502,151455502 +.long 907153956,907153956 +.long 2608889883,2608889883 +.long 1038279391,1038279391 +.long 652995533,652995533 +.long 1764173646,1764173646 +.long 3451040383,3451040383 +.long 2675275242,2675275242 +.long 453576978,453576978 +.long 2659418909,2659418909 +.long 1949051992,1949051992 +.long 773462580,773462580 +.long 756751158,756751158 +.long 2993581788,2993581788 +.long 3998898868,3998898868 +.long 4221608027,4221608027 +.long 4132590244,4132590244 +.long 1295727478,1295727478 +.long 1641469623,1641469623 +.long 3467883389,3467883389 +.long 2066295122,2066295122 +.long 1055122397,1055122397 +.long 1898917726,1898917726 +.long 2542044179,2542044179 +.long 4115878822,4115878822 +.long 1758581177,1758581177 +.long 0,0 +.long 753790401,753790401 +.long 1612718144,1612718144 +.long 536673507,536673507 +.long 3367088505,3367088505 +.long 3982187446,3982187446 +.long 3194645204,3194645204 +.long 1187761037,1187761037 +.long 3653156455,3653156455 +.long 1262041458,1262041458 +.long 3729410708,3729410708 +.long 3561770136,3561770136 +.long 3898103984,3898103984 +.long 1255133061,1255133061 +.long 1808847035,1808847035 +.long 720367557,720367557 +.long 3853167183,3853167183 +.long 385612781,385612781 +.long 3309519750,3309519750 +.long 3612167578,3612167578 +.long 1429418854,1429418854 +.long 2491778321,2491778321 +.long 3477423498,3477423498 +.long 284817897,284817897 +.long 100794884,100794884 +.long 2172616702,2172616702 +.long 4031795360,4031795360 +.long 1144798328,1144798328 +.long 3131023141,3131023141 +.long 3819481163,3819481163 +.long 4082192802,4082192802 +.long 4272137053,4272137053 +.long 3225436288,3225436288 +.long 2324664069,2324664069 +.long 2912064063,2912064063 +.long 3164445985,3164445985 +.long 1211644016,1211644016 +.long 83228145,83228145 +.long 3753688163,3753688163 +.long 3249976951,3249976951 +.long 1977277103,1977277103 +.long 1663115586,1663115586 +.long 806359072,806359072 +.long 452984805,452984805 +.long 250868733,250868733 +.long 1842533055,1842533055 +.long 1288555905,1288555905 +.long 336333848,336333848 +.long 890442534,890442534 +.long 804056259,804056259 +.long 3781124030,3781124030 +.long 2727843637,2727843637 +.long 3427026056,3427026056 +.long 957814574,957814574 +.long 1472513171,1472513171 +.long 4071073621,4071073621 +.long 2189328124,2189328124 +.long 1195195770,1195195770 +.long 2892260552,2892260552 +.long 3881655738,3881655738 +.long 723065138,723065138 +.long 2507371494,2507371494 +.long 2690670784,2690670784 +.long 2558624025,2558624025 +.long 3511635870,3511635870 +.long 2145180835,2145180835 +.long 1713513028,1713513028 +.long 2116692564,2116692564 +.long 2878378043,2878378043 +.long 2206763019,2206763019 +.long 3393603212,3393603212 +.long 703524551,703524551 +.long 3552098411,3552098411 +.long 1007948840,1007948840 +.long 2044649127,2044649127 +.long 3797835452,3797835452 +.long 487262998,487262998 +.long 1994120109,1994120109 +.long 1004593371,1004593371 +.long 1446130276,1446130276 +.long 1312438900,1312438900 +.long 503974420,503974420 +.long 3679013266,3679013266 +.long 168166924,168166924 +.long 1814307912,1814307912 +.long 3831258296,3831258296 +.long 1573044895,1573044895 +.long 1859376061,1859376061 +.long 4021070915,4021070915 +.long 2791465668,2791465668 +.long 2828112185,2828112185 +.long 2761266481,2761266481 +.long 937747667,937747667 +.long 2339994098,2339994098 +.long 854058965,854058965 +.long 1137232011,1137232011 +.long 1496790894,1496790894 +.long 3077402074,3077402074 +.long 2358086913,2358086913 +.long 1691735473,1691735473 +.long 3528347292,3528347292 +.long 3769215305,3769215305 +.long 3027004632,3027004632 +.long 4199962284,4199962284 +.long 133494003,133494003 +.long 636152527,636152527 +.long 2942657994,2942657994 +.long 2390391540,2390391540 +.long 3920539207,3920539207 +.long 403179536,403179536 +.long 3585784431,3585784431 +.long 2289596656,2289596656 +.long 1864705354,1864705354 +.long 1915629148,1915629148 +.long 605822008,605822008 +.long 4054230615,4054230615 +.long 3350508659,3350508659 +.long 1371981463,1371981463 +.long 602466507,602466507 +.long 2094914977,2094914977 +.long 2624877800,2624877800 +.long 555687742,555687742 +.long 3712699286,3712699286 +.long 3703422305,3703422305 +.long 2257292045,2257292045 +.long 2240449039,2240449039 +.long 2423288032,2423288032 +.long 1111375484,1111375484 +.long 3300242801,3300242801 +.long 2858837708,2858837708 +.long 3628615824,3628615824 +.long 84083462,84083462 +.long 32962295,32962295 +.long 302911004,302911004 +.long 2741068226,2741068226 +.long 1597322602,1597322602 +.long 4183250862,4183250862 +.long 3501832553,3501832553 +.long 2441512471,2441512471 +.long 1489093017,1489093017 +.long 656219450,656219450 +.long 3114180135,3114180135 +.long 954327513,954327513 +.long 335083755,335083755 +.long 3013122091,3013122091 +.long 856756514,856756514 +.long 3144247762,3144247762 +.long 1893325225,1893325225 +.long 2307821063,2307821063 +.long 2811532339,2811532339 +.long 3063651117,3063651117 +.long 572399164,572399164 +.long 2458355477,2458355477 +.long 552200649,552200649 +.long 1238290055,1238290055 +.long 4283782570,4283782570 +.long 2015897680,2015897680 +.long 2061492133,2061492133 +.long 2408352771,2408352771 +.long 4171342169,4171342169 +.long 2156497161,2156497161 +.long 386731290,386731290 +.long 3669999461,3669999461 +.long 837215959,837215959 +.long 3326231172,3326231172 +.long 3093850320,3093850320 +.long 3275833730,3275833730 +.long 2962856233,2962856233 +.long 1999449434,1999449434 +.long 286199582,286199582 +.long 3417354363,3417354363 +.long 4233385128,4233385128 +.long 3602627437,3602627437 +.long 974525996,974525996 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.long 1,2,4,8 +.long 16,32,64,128 +.long 27,54,0,0 +.long 0,0,0,0 +.size _x86_AES_encrypt,.-_x86_AES_encrypt +.globl AES_encrypt +.type AES_encrypt,@function +.align 16 +AES_encrypt: +.L_AES_encrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 20(%esp),%esi + movl 28(%esp),%edi + movl %esp,%eax + subl $36,%esp + andl $-64,%esp + leal -127(%edi),%ebx + subl %esp,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esp + addl $4,%esp + movl %eax,28(%esp) + call .L004pic_point +.L004pic_point: + popl %ebp + leal OPENSSL_ia32cap_P-.L004pic_point(%ebp),%eax + leal .LAES_Te-.L004pic_point(%ebp),%ebp + leal 764(%esp),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + btl $25,(%eax) + jnc .L005x86 + movq (%esi),%mm0 + movq 8(%esi),%mm4 + call _sse_AES_encrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.align 16 +.L005x86: + movl %ebp,24(%esp) + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + call _x86_AES_encrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_encrypt,.-.L_AES_encrypt_begin +.type _x86_AES_decrypt_compact,@function +.align 16 +_x86_AES_decrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi +.align 16 +.L006loop: + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl -128(%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + shrl $24,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%eax + subl %edi,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %esi,%eax + movl $2155905152,%edi + andl %eax,%edi + movl %edi,%esi + shrl $7,%edi + leal (%eax,%eax,1),%ebx + subl %edi,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %ecx,%eax + xorl %esi,%ebx + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %ecx,%ebx + roll $8,%ecx + xorl %esi,%ebp + xorl %eax,%ecx + xorl %ebp,%eax + xorl %ebx,%ecx + xorl %ebp,%ebx + roll $24,%eax + xorl %ebp,%ecx + roll $16,%ebx + xorl %eax,%ecx + roll $8,%ebp + xorl %ebx,%ecx + movl 4(%esp),%eax + xorl %ebp,%ecx + movl %ecx,12(%esp) + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebx + subl %edi,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %esi,%ebx + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %edx,%ebx + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %edx,%ecx + roll $8,%edx + xorl %esi,%ebp + xorl %ebx,%edx + xorl %ebp,%ebx + xorl %ecx,%edx + xorl %ebp,%ecx + roll $24,%ebx + xorl %ebp,%edx + roll $16,%ecx + xorl %ebx,%edx + roll $8,%ebp + xorl %ecx,%edx + movl 8(%esp),%ebx + xorl %ebp,%edx + movl %edx,16(%esp) + movl $2155905152,%edi + andl %eax,%edi + movl %edi,%esi + shrl $7,%edi + leal (%eax,%eax,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%edx + subl %edi,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %eax,%ecx + xorl %esi,%edx + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %eax,%edx + roll $8,%eax + xorl %esi,%ebp + xorl %ecx,%eax + xorl %ebp,%ecx + xorl %edx,%eax + xorl %ebp,%edx + roll $24,%ecx + xorl %ebp,%eax + roll $16,%edx + xorl %ecx,%eax + roll $8,%ebp + xorl %edx,%eax + xorl %ebp,%eax + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%edx + subl %edi,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %ebx,%ecx + xorl %esi,%edx + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %ebx,%edx + roll $8,%ebx + xorl %esi,%ebp + xorl %ecx,%ebx + xorl %ebp,%ecx + xorl %edx,%ebx + xorl %ebp,%edx + roll $24,%ecx + xorl %ebp,%ebx + roll $16,%edx + xorl %ecx,%ebx + roll $8,%ebp + xorl %edx,%ebx + movl 12(%esp),%ecx + xorl %ebp,%ebx + movl 16(%esp),%edx + movl 20(%esp),%edi + movl 28(%esp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L006loop + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl -128(%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + shrl $24,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl 4(%esp),%eax + xorl 16(%edi),%eax + xorl 20(%edi),%ebx + xorl 24(%edi),%ecx + xorl 28(%edi),%edx + ret +.size _x86_AES_decrypt_compact,.-_x86_AES_decrypt_compact +.type _sse_AES_decrypt_compact,@function +.align 16 +_sse_AES_decrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl $454761243,%eax + movl %eax,8(%esp) + movl %eax,12(%esp) + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx +.align 16 +.L007loop: + pshufw $12,%mm0,%mm1 + pshufw $9,%mm4,%mm5 + movd %mm1,%eax + movd %mm5,%ebx + movl %edi,20(%esp) + movzbl %al,%esi + movzbl %ah,%edx + pshufw $6,%mm0,%mm2 + movzbl -128(%ebp,%esi,1),%ecx + movzbl %bl,%edi + movzbl -128(%ebp,%edx,1),%edx + shrl $16,%eax + shll $8,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $16,%esi + pshufw $3,%mm4,%mm6 + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $24,%esi + shrl $16,%ebx + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $8,%esi + movd %mm2,%eax + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + shll $16,%esi + movd %mm6,%ebx + movd %ecx,%mm0 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %al,%edi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $16,%esi + shrl $16,%eax + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shrl $16,%ebx + shll $8,%esi + movd %edx,%mm1 + movzbl -128(%ebp,%edi,1),%edx + movzbl %bh,%edi + shll $24,%edx + andl $255,%ebx + orl %esi,%edx + punpckldq %mm1,%mm0 + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $8,%esi + movzbl %ah,%eax + movzbl -128(%ebp,%ebx,1),%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + orl %ebx,%edx + shll $16,%esi + movzbl -128(%ebp,%eax,1),%eax + orl %esi,%edx + shll $24,%eax + orl %eax,%ecx + movl 20(%esp),%edi + movd %edx,%mm4 + movd %ecx,%mm5 + punpckldq %mm5,%mm4 + addl $16,%edi + cmpl 24(%esp),%edi + ja .L008out + movq %mm0,%mm3 + movq %mm4,%mm7 + pshufw $228,%mm0,%mm2 + pshufw $228,%mm4,%mm6 + movq %mm0,%mm1 + movq %mm4,%mm5 + pshufw $177,%mm0,%mm0 + pshufw $177,%mm4,%mm4 + pslld $8,%mm2 + pslld $8,%mm6 + psrld $8,%mm3 + psrld $8,%mm7 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pslld $16,%mm2 + pslld $16,%mm6 + psrld $16,%mm3 + psrld $16,%mm7 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movq 8(%esp),%mm3 + pxor %mm2,%mm2 + pxor %mm6,%mm6 + pcmpgtb %mm1,%mm2 + pcmpgtb %mm5,%mm6 + pand %mm3,%mm2 + pand %mm3,%mm6 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm2,%mm1 + pxor %mm6,%mm5 + movq %mm1,%mm3 + movq %mm5,%mm7 + movq %mm1,%mm2 + movq %mm5,%mm6 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pslld $24,%mm3 + pslld $24,%mm7 + psrld $8,%mm2 + psrld $8,%mm6 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq 8(%esp),%mm2 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + pcmpgtb %mm1,%mm3 + pcmpgtb %mm5,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm3,%mm1 + pxor %mm7,%mm5 + pshufw $177,%mm1,%mm3 + pshufw $177,%mm5,%mm7 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + pcmpgtb %mm1,%mm3 + pcmpgtb %mm5,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm3,%mm1 + pxor %mm7,%mm5 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movq %mm1,%mm3 + movq %mm5,%mm7 + pshufw $177,%mm1,%mm2 + pshufw $177,%mm5,%mm6 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pslld $8,%mm1 + pslld $8,%mm5 + psrld $8,%mm3 + psrld $8,%mm7 + movq (%edi),%mm2 + movq 8(%edi),%mm6 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movl -128(%ebp),%eax + pslld $16,%mm1 + pslld $16,%mm5 + movl -64(%ebp),%ebx + psrld $16,%mm3 + psrld $16,%mm7 + movl (%ebp),%ecx + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movl 64(%ebp),%edx + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + jmp .L007loop +.align 16 +.L008out: + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + ret +.size _sse_AES_decrypt_compact,.-_sse_AES_decrypt_compact +.type _x86_AES_decrypt,@function +.align 16 +_x86_AES_decrypt: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) +.align 16 +.L009loop: + movl %eax,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %dh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %ebx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %ah,%edi + xorl 3(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %bh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + + movl 20(%esp),%edi + andl $255,%edx + movl (%ebp,%edx,8),%edx + movzbl %ch,%ecx + xorl 3(%ebp,%ecx,8),%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + xorl 2(%ebp,%ebx,8),%edx + movl 8(%esp),%ebx + shrl $24,%eax + xorl 1(%ebp,%eax,8),%edx + movl 4(%esp),%eax + + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L009loop + leal 2176(%ebp),%ebp + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi + leal -128(%ebp),%ebp + movl %eax,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movzbl (%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl (%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl (%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + shrl $24,%eax + movzbl (%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl 4(%esp),%eax + leal -2048(%ebp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + ret +.align 64 +.LAES_Td: +.long 1353184337,1353184337 +.long 1399144830,1399144830 +.long 3282310938,3282310938 +.long 2522752826,2522752826 +.long 3412831035,3412831035 +.long 4047871263,4047871263 +.long 2874735276,2874735276 +.long 2466505547,2466505547 +.long 1442459680,1442459680 +.long 4134368941,4134368941 +.long 2440481928,2440481928 +.long 625738485,625738485 +.long 4242007375,4242007375 +.long 3620416197,3620416197 +.long 2151953702,2151953702 +.long 2409849525,2409849525 +.long 1230680542,1230680542 +.long 1729870373,1729870373 +.long 2551114309,2551114309 +.long 3787521629,3787521629 +.long 41234371,41234371 +.long 317738113,317738113 +.long 2744600205,2744600205 +.long 3338261355,3338261355 +.long 3881799427,3881799427 +.long 2510066197,2510066197 +.long 3950669247,3950669247 +.long 3663286933,3663286933 +.long 763608788,763608788 +.long 3542185048,3542185048 +.long 694804553,694804553 +.long 1154009486,1154009486 +.long 1787413109,1787413109 +.long 2021232372,2021232372 +.long 1799248025,1799248025 +.long 3715217703,3715217703 +.long 3058688446,3058688446 +.long 397248752,397248752 +.long 1722556617,1722556617 +.long 3023752829,3023752829 +.long 407560035,407560035 +.long 2184256229,2184256229 +.long 1613975959,1613975959 +.long 1165972322,1165972322 +.long 3765920945,3765920945 +.long 2226023355,2226023355 +.long 480281086,480281086 +.long 2485848313,2485848313 +.long 1483229296,1483229296 +.long 436028815,436028815 +.long 2272059028,2272059028 +.long 3086515026,3086515026 +.long 601060267,601060267 +.long 3791801202,3791801202 +.long 1468997603,1468997603 +.long 715871590,715871590 +.long 120122290,120122290 +.long 63092015,63092015 +.long 2591802758,2591802758 +.long 2768779219,2768779219 +.long 4068943920,4068943920 +.long 2997206819,2997206819 +.long 3127509762,3127509762 +.long 1552029421,1552029421 +.long 723308426,723308426 +.long 2461301159,2461301159 +.long 4042393587,4042393587 +.long 2715969870,2715969870 +.long 3455375973,3455375973 +.long 3586000134,3586000134 +.long 526529745,526529745 +.long 2331944644,2331944644 +.long 2639474228,2639474228 +.long 2689987490,2689987490 +.long 853641733,853641733 +.long 1978398372,1978398372 +.long 971801355,971801355 +.long 2867814464,2867814464 +.long 111112542,111112542 +.long 1360031421,1360031421 +.long 4186579262,4186579262 +.long 1023860118,1023860118 +.long 2919579357,2919579357 +.long 1186850381,1186850381 +.long 3045938321,3045938321 +.long 90031217,90031217 +.long 1876166148,1876166148 +.long 4279586912,4279586912 +.long 620468249,620468249 +.long 2548678102,2548678102 +.long 3426959497,3426959497 +.long 2006899047,2006899047 +.long 3175278768,3175278768 +.long 2290845959,2290845959 +.long 945494503,945494503 +.long 3689859193,3689859193 +.long 1191869601,1191869601 +.long 3910091388,3910091388 +.long 3374220536,3374220536 +.long 0,0 +.long 2206629897,2206629897 +.long 1223502642,1223502642 +.long 2893025566,2893025566 +.long 1316117100,1316117100 +.long 4227796733,4227796733 +.long 1446544655,1446544655 +.long 517320253,517320253 +.long 658058550,658058550 +.long 1691946762,1691946762 +.long 564550760,564550760 +.long 3511966619,3511966619 +.long 976107044,976107044 +.long 2976320012,2976320012 +.long 266819475,266819475 +.long 3533106868,3533106868 +.long 2660342555,2660342555 +.long 1338359936,1338359936 +.long 2720062561,2720062561 +.long 1766553434,1766553434 +.long 370807324,370807324 +.long 179999714,179999714 +.long 3844776128,3844776128 +.long 1138762300,1138762300 +.long 488053522,488053522 +.long 185403662,185403662 +.long 2915535858,2915535858 +.long 3114841645,3114841645 +.long 3366526484,3366526484 +.long 2233069911,2233069911 +.long 1275557295,1275557295 +.long 3151862254,3151862254 +.long 4250959779,4250959779 +.long 2670068215,2670068215 +.long 3170202204,3170202204 +.long 3309004356,3309004356 +.long 880737115,880737115 +.long 1982415755,1982415755 +.long 3703972811,3703972811 +.long 1761406390,1761406390 +.long 1676797112,1676797112 +.long 3403428311,3403428311 +.long 277177154,277177154 +.long 1076008723,1076008723 +.long 538035844,538035844 +.long 2099530373,2099530373 +.long 4164795346,4164795346 +.long 288553390,288553390 +.long 1839278535,1839278535 +.long 1261411869,1261411869 +.long 4080055004,4080055004 +.long 3964831245,3964831245 +.long 3504587127,3504587127 +.long 1813426987,1813426987 +.long 2579067049,2579067049 +.long 4199060497,4199060497 +.long 577038663,577038663 +.long 3297574056,3297574056 +.long 440397984,440397984 +.long 3626794326,3626794326 +.long 4019204898,4019204898 +.long 3343796615,3343796615 +.long 3251714265,3251714265 +.long 4272081548,4272081548 +.long 906744984,906744984 +.long 3481400742,3481400742 +.long 685669029,685669029 +.long 646887386,646887386 +.long 2764025151,2764025151 +.long 3835509292,3835509292 +.long 227702864,227702864 +.long 2613862250,2613862250 +.long 1648787028,1648787028 +.long 3256061430,3256061430 +.long 3904428176,3904428176 +.long 1593260334,1593260334 +.long 4121936770,4121936770 +.long 3196083615,3196083615 +.long 2090061929,2090061929 +.long 2838353263,2838353263 +.long 3004310991,3004310991 +.long 999926984,999926984 +.long 2809993232,2809993232 +.long 1852021992,1852021992 +.long 2075868123,2075868123 +.long 158869197,158869197 +.long 4095236462,4095236462 +.long 28809964,28809964 +.long 2828685187,2828685187 +.long 1701746150,1701746150 +.long 2129067946,2129067946 +.long 147831841,147831841 +.long 3873969647,3873969647 +.long 3650873274,3650873274 +.long 3459673930,3459673930 +.long 3557400554,3557400554 +.long 3598495785,3598495785 +.long 2947720241,2947720241 +.long 824393514,824393514 +.long 815048134,815048134 +.long 3227951669,3227951669 +.long 935087732,935087732 +.long 2798289660,2798289660 +.long 2966458592,2966458592 +.long 366520115,366520115 +.long 1251476721,1251476721 +.long 4158319681,4158319681 +.long 240176511,240176511 +.long 804688151,804688151 +.long 2379631990,2379631990 +.long 1303441219,1303441219 +.long 1414376140,1414376140 +.long 3741619940,3741619940 +.long 3820343710,3820343710 +.long 461924940,461924940 +.long 3089050817,3089050817 +.long 2136040774,2136040774 +.long 82468509,82468509 +.long 1563790337,1563790337 +.long 1937016826,1937016826 +.long 776014843,776014843 +.long 1511876531,1511876531 +.long 1389550482,1389550482 +.long 861278441,861278441 +.long 323475053,323475053 +.long 2355222426,2355222426 +.long 2047648055,2047648055 +.long 2383738969,2383738969 +.long 2302415851,2302415851 +.long 3995576782,3995576782 +.long 902390199,902390199 +.long 3991215329,3991215329 +.long 1018251130,1018251130 +.long 1507840668,1507840668 +.long 1064563285,1064563285 +.long 2043548696,2043548696 +.long 3208103795,3208103795 +.long 3939366739,3939366739 +.long 1537932639,1537932639 +.long 342834655,342834655 +.long 2262516856,2262516856 +.long 2180231114,2180231114 +.long 1053059257,1053059257 +.long 741614648,741614648 +.long 1598071746,1598071746 +.long 1925389590,1925389590 +.long 203809468,203809468 +.long 2336832552,2336832552 +.long 1100287487,1100287487 +.long 1895934009,1895934009 +.long 3736275976,3736275976 +.long 2632234200,2632234200 +.long 2428589668,2428589668 +.long 1636092795,1636092795 +.long 1890988757,1890988757 +.long 1952214088,1952214088 +.long 1113045200,1113045200 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.size _x86_AES_decrypt,.-_x86_AES_decrypt +.globl AES_decrypt +.type AES_decrypt,@function +.align 16 +AES_decrypt: +.L_AES_decrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 20(%esp),%esi + movl 28(%esp),%edi + movl %esp,%eax + subl $36,%esp + andl $-64,%esp + leal -127(%edi),%ebx + subl %esp,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esp + addl $4,%esp + movl %eax,28(%esp) + call .L010pic_point +.L010pic_point: + popl %ebp + leal OPENSSL_ia32cap_P-.L010pic_point(%ebp),%eax + leal .LAES_Td-.L010pic_point(%ebp),%ebp + leal 764(%esp),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + btl $25,(%eax) + jnc .L011x86 + movq (%esi),%mm0 + movq 8(%esi),%mm4 + call _sse_AES_decrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.align 16 +.L011x86: + movl %ebp,24(%esp) + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + call _x86_AES_decrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_decrypt,.-.L_AES_decrypt_begin +.globl AES_cbc_encrypt +.type AES_cbc_encrypt,@function +.align 16 +AES_cbc_encrypt: +.L_AES_cbc_encrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 28(%esp),%ecx + cmpl $0,%ecx + je .L012drop_out + call .L013pic_point +.L013pic_point: + popl %ebp + leal OPENSSL_ia32cap_P-.L013pic_point(%ebp),%eax + cmpl $0,40(%esp) + leal .LAES_Te-.L013pic_point(%ebp),%ebp + jne .L014picked_te + leal .LAES_Td-.LAES_Te(%ebp),%ebp +.L014picked_te: + pushfl + cld + cmpl $512,%ecx + jb .L015slow_way + testl $15,%ecx + jnz .L015slow_way + btl $28,(%eax) + jc .L015slow_way + leal -324(%esp),%esi + andl $-64,%esi + movl %ebp,%eax + leal 2304(%ebp),%ebx + movl %esi,%edx + andl $4095,%eax + andl $4095,%ebx + andl $4095,%edx + cmpl %ebx,%edx + jb .L016tbl_break_out + subl %ebx,%edx + subl %edx,%esi + jmp .L017tbl_ok +.align 4 +.L016tbl_break_out: + subl %eax,%edx + andl $4095,%edx + addl $384,%edx + subl %edx,%esi +.align 4 +.L017tbl_ok: + leal 24(%esp),%edx + xchgl %esi,%esp + addl $4,%esp + movl %ebp,24(%esp) + movl %esi,28(%esp) + movl (%edx),%eax + movl 4(%edx),%ebx + movl 12(%edx),%edi + movl 16(%edx),%esi + movl 20(%edx),%edx + movl %eax,32(%esp) + movl %ebx,36(%esp) + movl %ecx,40(%esp) + movl %edi,44(%esp) + movl %esi,48(%esp) + movl $0,316(%esp) + movl %edi,%ebx + movl $61,%ecx + subl %ebp,%ebx + movl %edi,%esi + andl $4095,%ebx + leal 76(%esp),%edi + cmpl $2304,%ebx + jb .L018do_copy + cmpl $3852,%ebx + jb .L019skip_copy +.align 4 +.L018do_copy: + movl %edi,44(%esp) +.long 2784229001 +.L019skip_copy: + movl $16,%edi +.align 4 +.L020prefetch_tbl: + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%esi + leal 128(%ebp),%ebp + subl $1,%edi + jnz .L020prefetch_tbl + subl $2048,%ebp + movl 32(%esp),%esi + movl 48(%esp),%edi + cmpl $0,%edx + je .L021fast_decrypt + movl (%edi),%eax + movl 4(%edi),%ebx +.align 16 +.L022fast_enc_loop: + movl 8(%edi),%ecx + movl 12(%edi),%edx + xorl (%esi),%eax + xorl 4(%esi),%ebx + xorl 8(%esi),%ecx + xorl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_encrypt + movl 32(%esp),%esi + movl 36(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + leal 16(%esi),%esi + movl 40(%esp),%ecx + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L022fast_enc_loop + movl 48(%esp),%esi + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + cmpl $0,316(%esp) + movl 44(%esp),%edi + je .L023skip_ezero + movl $60,%ecx + xorl %eax,%eax +.align 4 +.long 2884892297 +.L023skip_ezero: + movl 28(%esp),%esp + popfl +.L012drop_out: + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L021fast_decrypt: + cmpl 36(%esp),%esi + je .L024fast_dec_in_place + movl %edi,52(%esp) +.align 4 +.align 16 +.L025fast_dec_loop: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_decrypt + movl 52(%esp),%edi + movl 40(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 36(%esp),%edi + movl 32(%esp),%esi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + movl %esi,52(%esp) + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edi + movl %edi,36(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L025fast_dec_loop + movl 52(%esp),%edi + movl 48(%esp),%esi + movl (%edi),%eax + movl 4(%edi),%ebx + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + jmp .L026fast_dec_out +.align 16 +.L024fast_dec_in_place: +.L027fast_dec_in_place_loop: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + leal 60(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 44(%esp),%edi + call _x86_AES_decrypt + movl 48(%esp),%edi + movl 36(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + leal 16(%esi),%esi + movl %esi,36(%esp) + leal 60(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 32(%esp),%esi + movl 40(%esp),%ecx + leal 16(%esi),%esi + movl %esi,32(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L027fast_dec_in_place_loop +.align 4 +.L026fast_dec_out: + cmpl $0,316(%esp) + movl 44(%esp),%edi + je .L028skip_dzero + movl $60,%ecx + xorl %eax,%eax +.align 4 +.long 2884892297 +.L028skip_dzero: + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L015slow_way: + movl (%eax),%eax + movl 36(%esp),%edi + leal -80(%esp),%esi + andl $-64,%esi + leal -143(%edi),%ebx + subl %esi,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esi + leal 768(%esi),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + leal 24(%esp),%edx + xchgl %esi,%esp + addl $4,%esp + movl %ebp,24(%esp) + movl %esi,28(%esp) + movl %eax,52(%esp) + movl (%edx),%eax + movl 4(%edx),%ebx + movl 16(%edx),%esi + movl 20(%edx),%edx + movl %eax,32(%esp) + movl %ebx,36(%esp) + movl %ecx,40(%esp) + movl %edi,44(%esp) + movl %esi,48(%esp) + movl %esi,%edi + movl %eax,%esi + cmpl $0,%edx + je .L029slow_decrypt + cmpl $16,%ecx + movl %ebx,%edx + jb .L030slow_enc_tail + btl $25,52(%esp) + jnc .L031slow_enc_x86 + movq (%edi),%mm0 + movq 8(%edi),%mm4 +.align 16 +.L032slow_enc_loop_sse: + pxor (%esi),%mm0 + pxor 8(%esi),%mm4 + movl 44(%esp),%edi + call _sse_AES_encrypt_compact + movl 32(%esp),%esi + movl 36(%esp),%edi + movl 40(%esp),%ecx + movq %mm0,(%edi) + movq %mm4,8(%edi) + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + cmpl $16,%ecx + movl %ecx,40(%esp) + jae .L032slow_enc_loop_sse + testl $15,%ecx + jnz .L030slow_enc_tail + movl 48(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L031slow_enc_x86: + movl (%edi),%eax + movl 4(%edi),%ebx +.align 4 +.L033slow_enc_loop_x86: + movl 8(%edi),%ecx + movl 12(%edi),%edx + xorl (%esi),%eax + xorl 4(%esi),%ebx + xorl 8(%esi),%ecx + xorl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_encrypt_compact + movl 32(%esp),%esi + movl 36(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + cmpl $16,%ecx + movl %ecx,40(%esp) + jae .L033slow_enc_loop_x86 + testl $15,%ecx + jnz .L030slow_enc_tail + movl 48(%esp),%esi + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L030slow_enc_tail: + emms + movl %edx,%edi + movl $16,%ebx + subl %ecx,%ebx + cmpl %esi,%edi + je .L034enc_in_place +.align 4 +.long 2767451785 + jmp .L035enc_skip_in_place +.L034enc_in_place: + leal (%edi,%ecx,1),%edi +.L035enc_skip_in_place: + movl %ebx,%ecx + xorl %eax,%eax +.align 4 +.long 2868115081 + movl 48(%esp),%edi + movl %edx,%esi + movl (%edi),%eax + movl 4(%edi),%ebx + movl $16,40(%esp) + jmp .L033slow_enc_loop_x86 +.align 16 +.L029slow_decrypt: + btl $25,52(%esp) + jnc .L036slow_dec_loop_x86 +.align 4 +.L037slow_dec_loop_sse: + movq (%esi),%mm0 + movq 8(%esi),%mm4 + movl 44(%esp),%edi + call _sse_AES_decrypt_compact + movl 32(%esp),%esi + leal 60(%esp),%eax + movl 36(%esp),%ebx + movl 40(%esp),%ecx + movl 48(%esp),%edi + movq (%esi),%mm1 + movq 8(%esi),%mm5 + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movq %mm1,(%edi) + movq %mm5,8(%edi) + subl $16,%ecx + jc .L038slow_dec_partial_sse + movq %mm0,(%ebx) + movq %mm4,8(%ebx) + leal 16(%ebx),%ebx + movl %ebx,36(%esp) + leal 16(%esi),%esi + movl %esi,32(%esp) + movl %ecx,40(%esp) + jnz .L037slow_dec_loop_sse + emms + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L038slow_dec_partial_sse: + movq %mm0,(%eax) + movq %mm4,8(%eax) + emms + addl $16,%ecx + movl %ebx,%edi + movl %eax,%esi +.align 4 +.long 2767451785 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L036slow_dec_loop_x86: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + leal 60(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 44(%esp),%edi + call _x86_AES_decrypt_compact + movl 48(%esp),%edi + movl 40(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + subl $16,%esi + jc .L039slow_dec_partial_x86 + movl %esi,40(%esp) + movl 36(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + leal 16(%esi),%esi + movl %esi,36(%esp) + leal 60(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 32(%esp),%esi + leal 16(%esi),%esi + movl %esi,32(%esp) + jnz .L036slow_dec_loop_x86 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L039slow_dec_partial_x86: + leal 60(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + movl 32(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + movl 36(%esp),%edi + leal 60(%esp),%esi +.align 4 +.long 2767451785 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_cbc_encrypt,.-.L_AES_cbc_encrypt_begin +.type _x86_AES_set_encrypt_key,@function +.align 16 +_x86_AES_set_encrypt_key: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 24(%esp),%esi + movl 32(%esp),%edi + testl $-1,%esi + jz .L040badpointer + testl $-1,%edi + jz .L040badpointer + call .L041pic_point +.L041pic_point: + popl %ebp + leal .LAES_Te-.L041pic_point(%ebp),%ebp + leal 2176(%ebp),%ebp + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx + movl 28(%esp),%ecx + cmpl $128,%ecx + je .L04210rounds + cmpl $192,%ecx + je .L04312rounds + cmpl $256,%ecx + je .L04414rounds + movl $-2,%eax + jmp .L045exit +.L04210rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + xorl %ecx,%ecx + jmp .L04610shortcut +.align 4 +.L04710loop: + movl (%edi),%eax + movl 12(%edi),%edx +.L04610shortcut: + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,16(%edi) + xorl 4(%edi),%eax + movl %eax,20(%edi) + xorl 8(%edi),%eax + movl %eax,24(%edi) + xorl 12(%edi),%eax + movl %eax,28(%edi) + incl %ecx + addl $16,%edi + cmpl $10,%ecx + jl .L04710loop + movl $10,80(%edi) + xorl %eax,%eax + jmp .L045exit +.L04312rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 16(%esi),%ecx + movl 20(%esi),%edx + movl %ecx,16(%edi) + movl %edx,20(%edi) + xorl %ecx,%ecx + jmp .L04812shortcut +.align 4 +.L04912loop: + movl (%edi),%eax + movl 20(%edi),%edx +.L04812shortcut: + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,24(%edi) + xorl 4(%edi),%eax + movl %eax,28(%edi) + xorl 8(%edi),%eax + movl %eax,32(%edi) + xorl 12(%edi),%eax + movl %eax,36(%edi) + cmpl $7,%ecx + je .L05012break + incl %ecx + xorl 16(%edi),%eax + movl %eax,40(%edi) + xorl 20(%edi),%eax + movl %eax,44(%edi) + addl $24,%edi + jmp .L04912loop +.L05012break: + movl $12,72(%edi) + xorl %eax,%eax + jmp .L045exit +.L04414rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 16(%esi),%eax + movl 20(%esi),%ebx + movl 24(%esi),%ecx + movl 28(%esi),%edx + movl %eax,16(%edi) + movl %ebx,20(%edi) + movl %ecx,24(%edi) + movl %edx,28(%edi) + xorl %ecx,%ecx + jmp .L05114shortcut +.align 4 +.L05214loop: + movl 28(%edi),%edx +.L05114shortcut: + movl (%edi),%eax + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,32(%edi) + xorl 4(%edi),%eax + movl %eax,36(%edi) + xorl 8(%edi),%eax + movl %eax,40(%edi) + xorl 12(%edi),%eax + movl %eax,44(%edi) + cmpl $6,%ecx + je .L05314break + incl %ecx + movl %eax,%edx + movl 16(%edi),%eax + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + shll $8,%ebx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $16,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $24,%ebx + xorl %ebx,%eax + movl %eax,48(%edi) + xorl 20(%edi),%eax + movl %eax,52(%edi) + xorl 24(%edi),%eax + movl %eax,56(%edi) + xorl 28(%edi),%eax + movl %eax,60(%edi) + addl $32,%edi + jmp .L05214loop +.L05314break: + movl $14,48(%edi) + xorl %eax,%eax + jmp .L045exit +.L040badpointer: + movl $-1,%eax +.L045exit: + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size _x86_AES_set_encrypt_key,.-_x86_AES_set_encrypt_key +.globl AES_set_encrypt_key +.type AES_set_encrypt_key,@function +.align 16 +AES_set_encrypt_key: +.L_AES_set_encrypt_key_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + call _x86_AES_set_encrypt_key + ret +.size AES_set_encrypt_key,.-.L_AES_set_encrypt_key_begin +.globl AES_set_decrypt_key +.type AES_set_decrypt_key,@function +.align 16 +AES_set_decrypt_key: +.L_AES_set_decrypt_key_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + call _x86_AES_set_encrypt_key + cmpl $0,%eax + je .L054proceed + ret +.L054proceed: + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 28(%esp),%esi + movl 240(%esi),%ecx + leal (,%ecx,4),%ecx + leal (%esi,%ecx,4),%edi +.align 4 +.L055invert: + movl (%esi),%eax + movl 4(%esi),%ebx + movl (%edi),%ecx + movl 4(%edi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,(%esi) + movl %edx,4(%esi) + movl 8(%esi),%eax + movl 12(%esi),%ebx + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,8(%edi) + movl %ebx,12(%edi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + addl $16,%esi + subl $16,%edi + cmpl %edi,%esi + jne .L055invert + movl 28(%esp),%edi + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,28(%esp) + movl 16(%edi),%eax +.align 4 +.L056permute: + addl $16,%edi + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %esi,%ebx + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %eax,%ebx + xorl %esi,%ecx + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + xorl %eax,%ecx + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + roll $8,%eax + xorl %esi,%edx + movl 4(%edi),%ebp + xorl %ebx,%eax + xorl %edx,%ebx + xorl %ecx,%eax + roll $24,%ebx + xorl %edx,%ecx + xorl %edx,%eax + roll $16,%ecx + xorl %ebx,%eax + roll $8,%edx + xorl %ecx,%eax + movl %ebp,%ebx + xorl %edx,%eax + movl %eax,(%edi) + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %ebx,%ecx + xorl %esi,%edx + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + xorl %ebx,%edx + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + roll $8,%ebx + xorl %esi,%eax + movl 8(%edi),%ebp + xorl %ecx,%ebx + xorl %eax,%ecx + xorl %edx,%ebx + roll $24,%ecx + xorl %eax,%edx + xorl %eax,%ebx + roll $16,%edx + xorl %ecx,%ebx + roll $8,%eax + xorl %edx,%ebx + movl %ebp,%ecx + xorl %eax,%ebx + movl %ebx,4(%edi) + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %esi,%edx + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %ecx,%edx + xorl %esi,%eax + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + xorl %ecx,%eax + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + roll $8,%ecx + xorl %esi,%ebx + movl 12(%edi),%ebp + xorl %edx,%ecx + xorl %ebx,%edx + xorl %eax,%ecx + roll $24,%edx + xorl %ebx,%eax + xorl %ebx,%ecx + roll $16,%eax + xorl %edx,%ecx + roll $8,%ebx + xorl %eax,%ecx + movl %ebp,%edx + xorl %ebx,%ecx + movl %ecx,8(%edi) + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %esi,%eax + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %edx,%eax + xorl %esi,%ebx + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + xorl %edx,%ebx + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + roll $8,%edx + xorl %esi,%ecx + movl 16(%edi),%ebp + xorl %eax,%edx + xorl %ecx,%eax + xorl %ebx,%edx + roll $24,%eax + xorl %ecx,%ebx + xorl %ecx,%edx + roll $16,%ebx + xorl %eax,%edx + roll $8,%ecx + xorl %ebx,%edx + movl %ebp,%eax + xorl %ecx,%edx + movl %edx,12(%edi) + cmpl 28(%esp),%edi + jb .L056permute + xorl %eax,%eax + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_set_decrypt_key,.-.L_AES_set_decrypt_key_begin +.byte 65,69,83,32,102,111,114,32,120,56,54,44,32,67,82,89 +.byte 80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114 +.byte 111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 +.comm OPENSSL_ia32cap_P,16,4 + + .section ".note.gnu.property", "a" + .p2align 2 + .long 1f - 0f + .long 4f - 1f + .long 5 +0: + .asciz "GNU" +1: + .p2align 2 + .long 0xc0000002 + .long 3f - 2f +2: + .long 3 +3: + .p2align 2 +4: +#else +.text +.type _x86_AES_encrypt_compact,@function +.align 16 +_x86_AES_encrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi +.align 16 +.L000loop: + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movzbl -128(%ebp,%esi,1),%esi + movzbl %ch,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ah,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $8,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movzbl -128(%ebp,%ecx,1),%ecx + shll $24,%ecx + xorl %ecx,%edx + movl %esi,%ecx + + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %ecx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %ecx,%edi + xorl %esi,%ecx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%ecx + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%ecx + andl %edx,%ebp + leal (%edx,%edx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %edx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %edx,%edi + xorl %esi,%edx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%edx + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%edx + andl %eax,%ebp + leal (%eax,%eax,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %eax,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %eax,%edi + xorl %esi,%eax + rorl $24,%edi + xorl %ebp,%esi + roll $24,%eax + xorl %edi,%esi + movl $2155905152,%ebp + xorl %esi,%eax + andl %ebx,%ebp + leal (%ebx,%ebx,1),%edi + movl %ebp,%esi + shrl $7,%ebp + andl $4278124286,%edi + subl %ebp,%esi + movl %ebx,%ebp + andl $454761243,%esi + rorl $16,%ebp + xorl %edi,%esi + movl %ebx,%edi + xorl %esi,%ebx + rorl $24,%edi + xorl %ebp,%esi + roll $24,%ebx + xorl %edi,%esi + xorl %esi,%ebx + movl 20(%esp),%edi + movl 28(%esp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L000loop + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movzbl -128(%ebp,%esi,1),%esi + movzbl %ch,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + + movl 20(%esp),%edi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ah,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $8,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movzbl -128(%ebp,%ecx,1),%ecx + shll $24,%ecx + xorl %ecx,%edx + movl %esi,%ecx + + xorl 16(%edi),%eax + xorl 20(%edi),%ebx + xorl 24(%edi),%ecx + xorl 28(%edi),%edx + ret +.size _x86_AES_encrypt_compact,.-_x86_AES_encrypt_compact +.type _sse_AES_encrypt_compact,@function +.align 16 +_sse_AES_encrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl $454761243,%eax + movl %eax,8(%esp) + movl %eax,12(%esp) + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx +.align 16 +.L001loop: + pshufw $8,%mm0,%mm1 + pshufw $13,%mm4,%mm5 + movd %mm1,%eax + movd %mm5,%ebx + movl %edi,20(%esp) + movzbl %al,%esi + movzbl %ah,%edx + pshufw $13,%mm0,%mm2 + movzbl -128(%ebp,%esi,1),%ecx + movzbl %bl,%edi + movzbl -128(%ebp,%edx,1),%edx + shrl $16,%eax + shll $8,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $16,%esi + pshufw $8,%mm4,%mm6 + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $24,%esi + shrl $16,%ebx + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $8,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + movd %mm2,%eax + movd %ecx,%mm0 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %ah,%edi + shll $16,%ecx + movd %mm6,%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + shll $8,%esi + shrl $16,%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shrl $16,%eax + movd %ecx,%mm1 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %ah,%edi + shll $16,%ecx + andl $255,%eax + orl %esi,%ecx + punpckldq %mm1,%mm0 + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + andl $255,%ebx + movzbl -128(%ebp,%eax,1),%eax + orl %esi,%ecx + shll $16,%eax + movzbl -128(%ebp,%edi,1),%esi + orl %eax,%edx + shll $8,%esi + movzbl -128(%ebp,%ebx,1),%ebx + orl %esi,%ecx + orl %ebx,%edx + movl 20(%esp),%edi + movd %ecx,%mm4 + movd %edx,%mm5 + punpckldq %mm5,%mm4 + addl $16,%edi + cmpl 24(%esp),%edi + ja .L002out + movq 8(%esp),%mm2 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + movq %mm0,%mm1 + movq %mm4,%mm5 + pcmpgtb %mm0,%mm3 + pcmpgtb %mm4,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + pshufw $177,%mm0,%mm2 + pshufw $177,%mm4,%mm6 + paddb %mm0,%mm0 + paddb %mm4,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pshufw $177,%mm2,%mm3 + pshufw $177,%mm6,%mm7 + pxor %mm0,%mm1 + pxor %mm4,%mm5 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq %mm3,%mm2 + movq %mm7,%mm6 + pslld $8,%mm3 + pslld $8,%mm7 + psrld $24,%mm2 + psrld $24,%mm6 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq %mm1,%mm3 + movq %mm5,%mm7 + movq (%edi),%mm2 + movq 8(%edi),%mm6 + psrld $8,%mm1 + psrld $8,%mm5 + movl -128(%ebp),%eax + pslld $24,%mm3 + pslld $24,%mm7 + movl -64(%ebp),%ebx + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movl (%ebp),%ecx + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movl 64(%ebp),%edx + pxor %mm2,%mm0 + pxor %mm6,%mm4 + jmp .L001loop +.align 16 +.L002out: + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + ret +.size _sse_AES_encrypt_compact,.-_sse_AES_encrypt_compact +.type _x86_AES_encrypt,@function +.align 16 +_x86_AES_encrypt: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) +.align 16 +.L003loop: + movl %eax,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %bh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movl (%ebp,%esi,8),%esi + movzbl %ch,%edi + xorl 3(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movl (%ebp,%esi,8),%esi + movzbl %dh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movzbl %bh,%edi + xorl 1(%ebp,%edi,8),%esi + + movl 20(%esp),%edi + movl (%ebp,%edx,8),%edx + movzbl %ah,%eax + xorl 3(%ebp,%eax,8),%edx + movl 4(%esp),%eax + andl $255,%ebx + xorl 2(%ebp,%ebx,8),%edx + movl 8(%esp),%ebx + xorl 1(%ebp,%ecx,8),%edx + movl %esi,%ecx + + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L003loop + movl %eax,%esi + andl $255,%esi + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %bh,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + shrl $16,%ebx + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %ch,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $24,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + shrl $24,%ecx + movl 2(%ebp,%esi,8),%esi + andl $255,%esi + movzbl %dh,%edi + movl (%ebp,%edi,8),%edi + andl $65280,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edx + andl $255,%edi + movl (%ebp,%edi,8),%edi + andl $16711680,%edi + xorl %edi,%esi + movzbl %bh,%edi + movl 2(%ebp,%edi,8),%edi + andl $4278190080,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movl 2(%ebp,%edx,8),%edx + andl $255,%edx + movzbl %ah,%eax + movl (%ebp,%eax,8),%eax + andl $65280,%eax + xorl %eax,%edx + movl 4(%esp),%eax + andl $255,%ebx + movl (%ebp,%ebx,8),%ebx + andl $16711680,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + movl 2(%ebp,%ecx,8),%ecx + andl $4278190080,%ecx + xorl %ecx,%edx + movl %esi,%ecx + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + ret +.align 64 +.LAES_Te: +.long 2774754246,2774754246 +.long 2222750968,2222750968 +.long 2574743534,2574743534 +.long 2373680118,2373680118 +.long 234025727,234025727 +.long 3177933782,3177933782 +.long 2976870366,2976870366 +.long 1422247313,1422247313 +.long 1345335392,1345335392 +.long 50397442,50397442 +.long 2842126286,2842126286 +.long 2099981142,2099981142 +.long 436141799,436141799 +.long 1658312629,1658312629 +.long 3870010189,3870010189 +.long 2591454956,2591454956 +.long 1170918031,1170918031 +.long 2642575903,2642575903 +.long 1086966153,1086966153 +.long 2273148410,2273148410 +.long 368769775,368769775 +.long 3948501426,3948501426 +.long 3376891790,3376891790 +.long 200339707,200339707 +.long 3970805057,3970805057 +.long 1742001331,1742001331 +.long 4255294047,4255294047 +.long 3937382213,3937382213 +.long 3214711843,3214711843 +.long 4154762323,4154762323 +.long 2524082916,2524082916 +.long 1539358875,1539358875 +.long 3266819957,3266819957 +.long 486407649,486407649 +.long 2928907069,2928907069 +.long 1780885068,1780885068 +.long 1513502316,1513502316 +.long 1094664062,1094664062 +.long 49805301,49805301 +.long 1338821763,1338821763 +.long 1546925160,1546925160 +.long 4104496465,4104496465 +.long 887481809,887481809 +.long 150073849,150073849 +.long 2473685474,2473685474 +.long 1943591083,1943591083 +.long 1395732834,1395732834 +.long 1058346282,1058346282 +.long 201589768,201589768 +.long 1388824469,1388824469 +.long 1696801606,1696801606 +.long 1589887901,1589887901 +.long 672667696,672667696 +.long 2711000631,2711000631 +.long 251987210,251987210 +.long 3046808111,3046808111 +.long 151455502,151455502 +.long 907153956,907153956 +.long 2608889883,2608889883 +.long 1038279391,1038279391 +.long 652995533,652995533 +.long 1764173646,1764173646 +.long 3451040383,3451040383 +.long 2675275242,2675275242 +.long 453576978,453576978 +.long 2659418909,2659418909 +.long 1949051992,1949051992 +.long 773462580,773462580 +.long 756751158,756751158 +.long 2993581788,2993581788 +.long 3998898868,3998898868 +.long 4221608027,4221608027 +.long 4132590244,4132590244 +.long 1295727478,1295727478 +.long 1641469623,1641469623 +.long 3467883389,3467883389 +.long 2066295122,2066295122 +.long 1055122397,1055122397 +.long 1898917726,1898917726 +.long 2542044179,2542044179 +.long 4115878822,4115878822 +.long 1758581177,1758581177 +.long 0,0 +.long 753790401,753790401 +.long 1612718144,1612718144 +.long 536673507,536673507 +.long 3367088505,3367088505 +.long 3982187446,3982187446 +.long 3194645204,3194645204 +.long 1187761037,1187761037 +.long 3653156455,3653156455 +.long 1262041458,1262041458 +.long 3729410708,3729410708 +.long 3561770136,3561770136 +.long 3898103984,3898103984 +.long 1255133061,1255133061 +.long 1808847035,1808847035 +.long 720367557,720367557 +.long 3853167183,3853167183 +.long 385612781,385612781 +.long 3309519750,3309519750 +.long 3612167578,3612167578 +.long 1429418854,1429418854 +.long 2491778321,2491778321 +.long 3477423498,3477423498 +.long 284817897,284817897 +.long 100794884,100794884 +.long 2172616702,2172616702 +.long 4031795360,4031795360 +.long 1144798328,1144798328 +.long 3131023141,3131023141 +.long 3819481163,3819481163 +.long 4082192802,4082192802 +.long 4272137053,4272137053 +.long 3225436288,3225436288 +.long 2324664069,2324664069 +.long 2912064063,2912064063 +.long 3164445985,3164445985 +.long 1211644016,1211644016 +.long 83228145,83228145 +.long 3753688163,3753688163 +.long 3249976951,3249976951 +.long 1977277103,1977277103 +.long 1663115586,1663115586 +.long 806359072,806359072 +.long 452984805,452984805 +.long 250868733,250868733 +.long 1842533055,1842533055 +.long 1288555905,1288555905 +.long 336333848,336333848 +.long 890442534,890442534 +.long 804056259,804056259 +.long 3781124030,3781124030 +.long 2727843637,2727843637 +.long 3427026056,3427026056 +.long 957814574,957814574 +.long 1472513171,1472513171 +.long 4071073621,4071073621 +.long 2189328124,2189328124 +.long 1195195770,1195195770 +.long 2892260552,2892260552 +.long 3881655738,3881655738 +.long 723065138,723065138 +.long 2507371494,2507371494 +.long 2690670784,2690670784 +.long 2558624025,2558624025 +.long 3511635870,3511635870 +.long 2145180835,2145180835 +.long 1713513028,1713513028 +.long 2116692564,2116692564 +.long 2878378043,2878378043 +.long 2206763019,2206763019 +.long 3393603212,3393603212 +.long 703524551,703524551 +.long 3552098411,3552098411 +.long 1007948840,1007948840 +.long 2044649127,2044649127 +.long 3797835452,3797835452 +.long 487262998,487262998 +.long 1994120109,1994120109 +.long 1004593371,1004593371 +.long 1446130276,1446130276 +.long 1312438900,1312438900 +.long 503974420,503974420 +.long 3679013266,3679013266 +.long 168166924,168166924 +.long 1814307912,1814307912 +.long 3831258296,3831258296 +.long 1573044895,1573044895 +.long 1859376061,1859376061 +.long 4021070915,4021070915 +.long 2791465668,2791465668 +.long 2828112185,2828112185 +.long 2761266481,2761266481 +.long 937747667,937747667 +.long 2339994098,2339994098 +.long 854058965,854058965 +.long 1137232011,1137232011 +.long 1496790894,1496790894 +.long 3077402074,3077402074 +.long 2358086913,2358086913 +.long 1691735473,1691735473 +.long 3528347292,3528347292 +.long 3769215305,3769215305 +.long 3027004632,3027004632 +.long 4199962284,4199962284 +.long 133494003,133494003 +.long 636152527,636152527 +.long 2942657994,2942657994 +.long 2390391540,2390391540 +.long 3920539207,3920539207 +.long 403179536,403179536 +.long 3585784431,3585784431 +.long 2289596656,2289596656 +.long 1864705354,1864705354 +.long 1915629148,1915629148 +.long 605822008,605822008 +.long 4054230615,4054230615 +.long 3350508659,3350508659 +.long 1371981463,1371981463 +.long 602466507,602466507 +.long 2094914977,2094914977 +.long 2624877800,2624877800 +.long 555687742,555687742 +.long 3712699286,3712699286 +.long 3703422305,3703422305 +.long 2257292045,2257292045 +.long 2240449039,2240449039 +.long 2423288032,2423288032 +.long 1111375484,1111375484 +.long 3300242801,3300242801 +.long 2858837708,2858837708 +.long 3628615824,3628615824 +.long 84083462,84083462 +.long 32962295,32962295 +.long 302911004,302911004 +.long 2741068226,2741068226 +.long 1597322602,1597322602 +.long 4183250862,4183250862 +.long 3501832553,3501832553 +.long 2441512471,2441512471 +.long 1489093017,1489093017 +.long 656219450,656219450 +.long 3114180135,3114180135 +.long 954327513,954327513 +.long 335083755,335083755 +.long 3013122091,3013122091 +.long 856756514,856756514 +.long 3144247762,3144247762 +.long 1893325225,1893325225 +.long 2307821063,2307821063 +.long 2811532339,2811532339 +.long 3063651117,3063651117 +.long 572399164,572399164 +.long 2458355477,2458355477 +.long 552200649,552200649 +.long 1238290055,1238290055 +.long 4283782570,4283782570 +.long 2015897680,2015897680 +.long 2061492133,2061492133 +.long 2408352771,2408352771 +.long 4171342169,4171342169 +.long 2156497161,2156497161 +.long 386731290,386731290 +.long 3669999461,3669999461 +.long 837215959,837215959 +.long 3326231172,3326231172 +.long 3093850320,3093850320 +.long 3275833730,3275833730 +.long 2962856233,2962856233 +.long 1999449434,1999449434 +.long 286199582,286199582 +.long 3417354363,3417354363 +.long 4233385128,4233385128 +.long 3602627437,3602627437 +.long 974525996,974525996 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.byte 99,124,119,123,242,107,111,197 +.byte 48,1,103,43,254,215,171,118 +.byte 202,130,201,125,250,89,71,240 +.byte 173,212,162,175,156,164,114,192 +.byte 183,253,147,38,54,63,247,204 +.byte 52,165,229,241,113,216,49,21 +.byte 4,199,35,195,24,150,5,154 +.byte 7,18,128,226,235,39,178,117 +.byte 9,131,44,26,27,110,90,160 +.byte 82,59,214,179,41,227,47,132 +.byte 83,209,0,237,32,252,177,91 +.byte 106,203,190,57,74,76,88,207 +.byte 208,239,170,251,67,77,51,133 +.byte 69,249,2,127,80,60,159,168 +.byte 81,163,64,143,146,157,56,245 +.byte 188,182,218,33,16,255,243,210 +.byte 205,12,19,236,95,151,68,23 +.byte 196,167,126,61,100,93,25,115 +.byte 96,129,79,220,34,42,144,136 +.byte 70,238,184,20,222,94,11,219 +.byte 224,50,58,10,73,6,36,92 +.byte 194,211,172,98,145,149,228,121 +.byte 231,200,55,109,141,213,78,169 +.byte 108,86,244,234,101,122,174,8 +.byte 186,120,37,46,28,166,180,198 +.byte 232,221,116,31,75,189,139,138 +.byte 112,62,181,102,72,3,246,14 +.byte 97,53,87,185,134,193,29,158 +.byte 225,248,152,17,105,217,142,148 +.byte 155,30,135,233,206,85,40,223 +.byte 140,161,137,13,191,230,66,104 +.byte 65,153,45,15,176,84,187,22 +.long 1,2,4,8 +.long 16,32,64,128 +.long 27,54,0,0 +.long 0,0,0,0 +.size _x86_AES_encrypt,.-_x86_AES_encrypt +.globl AES_encrypt +.type AES_encrypt,@function +.align 16 +AES_encrypt: +.L_AES_encrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 20(%esp),%esi + movl 28(%esp),%edi + movl %esp,%eax + subl $36,%esp + andl $-64,%esp + leal -127(%edi),%ebx + subl %esp,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esp + addl $4,%esp + movl %eax,28(%esp) + call .L004pic_point +.L004pic_point: + popl %ebp + leal OPENSSL_ia32cap_P,%eax + leal .LAES_Te-.L004pic_point(%ebp),%ebp + leal 764(%esp),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + btl $25,(%eax) + jnc .L005x86 + movq (%esi),%mm0 + movq 8(%esi),%mm4 + call _sse_AES_encrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.align 16 +.L005x86: + movl %ebp,24(%esp) + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + call _x86_AES_encrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_encrypt,.-.L_AES_encrypt_begin +.type _x86_AES_decrypt_compact,@function +.align 16 +_x86_AES_decrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi +.align 16 +.L006loop: + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl -128(%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + shrl $24,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%eax + subl %edi,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %esi,%eax + movl $2155905152,%edi + andl %eax,%edi + movl %edi,%esi + shrl $7,%edi + leal (%eax,%eax,1),%ebx + subl %edi,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %ecx,%eax + xorl %esi,%ebx + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %ecx,%ebx + roll $8,%ecx + xorl %esi,%ebp + xorl %eax,%ecx + xorl %ebp,%eax + xorl %ebx,%ecx + xorl %ebp,%ebx + roll $24,%eax + xorl %ebp,%ecx + roll $16,%ebx + xorl %eax,%ecx + roll $8,%ebp + xorl %ebx,%ecx + movl 4(%esp),%eax + xorl %ebp,%ecx + movl %ecx,12(%esp) + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebx + subl %edi,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %esi,%ebx + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %edx,%ebx + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %edx,%ecx + roll $8,%edx + xorl %esi,%ebp + xorl %ebx,%edx + xorl %ebp,%ebx + xorl %ecx,%edx + xorl %ebp,%ecx + roll $24,%ebx + xorl %ebp,%edx + roll $16,%ecx + xorl %ebx,%edx + roll $8,%ebp + xorl %ecx,%edx + movl 8(%esp),%ebx + xorl %ebp,%edx + movl %edx,16(%esp) + movl $2155905152,%edi + andl %eax,%edi + movl %edi,%esi + shrl $7,%edi + leal (%eax,%eax,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%edx + subl %edi,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %eax,%ecx + xorl %esi,%edx + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %eax,%edx + roll $8,%eax + xorl %esi,%ebp + xorl %ecx,%eax + xorl %ebp,%ecx + xorl %edx,%eax + xorl %ebp,%edx + roll $24,%ecx + xorl %ebp,%eax + roll $16,%edx + xorl %ecx,%eax + roll $8,%ebp + xorl %edx,%eax + xorl %ebp,%eax + movl $2155905152,%edi + andl %ebx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ebx,%ebx,1),%ecx + subl %edi,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%edi + andl %ecx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%ecx,%ecx,1),%edx + subl %edi,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %ebx,%ecx + xorl %esi,%edx + movl $2155905152,%edi + andl %edx,%edi + movl %edi,%esi + shrl $7,%edi + leal (%edx,%edx,1),%ebp + subl %edi,%esi + andl $4278124286,%ebp + andl $454761243,%esi + xorl %ebx,%edx + roll $8,%ebx + xorl %esi,%ebp + xorl %ecx,%ebx + xorl %ebp,%ecx + xorl %edx,%ebx + xorl %ebp,%edx + roll $24,%ecx + xorl %ebp,%ebx + roll $16,%edx + xorl %ecx,%ebx + roll $8,%ebp + xorl %edx,%ebx + movl 12(%esp),%ecx + xorl %ebp,%ebx + movl 16(%esp),%edx + movl 20(%esp),%edi + movl 28(%esp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L006loop + movl %eax,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl -128(%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl -128(%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movzbl -128(%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl -128(%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl -128(%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + shrl $24,%eax + movzbl -128(%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl 4(%esp),%eax + xorl 16(%edi),%eax + xorl 20(%edi),%ebx + xorl 24(%edi),%ecx + xorl 28(%edi),%edx + ret +.size _x86_AES_decrypt_compact,.-_x86_AES_decrypt_compact +.type _sse_AES_decrypt_compact,@function +.align 16 +_sse_AES_decrypt_compact: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) + movl $454761243,%eax + movl %eax,8(%esp) + movl %eax,12(%esp) + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx +.align 16 +.L007loop: + pshufw $12,%mm0,%mm1 + pshufw $9,%mm4,%mm5 + movd %mm1,%eax + movd %mm5,%ebx + movl %edi,20(%esp) + movzbl %al,%esi + movzbl %ah,%edx + pshufw $6,%mm0,%mm2 + movzbl -128(%ebp,%esi,1),%ecx + movzbl %bl,%edi + movzbl -128(%ebp,%edx,1),%edx + shrl $16,%eax + shll $8,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $16,%esi + pshufw $3,%mm4,%mm6 + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $24,%esi + shrl $16,%ebx + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shll $24,%esi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $8,%esi + movd %mm2,%eax + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + shll $16,%esi + movd %mm6,%ebx + movd %ecx,%mm0 + movzbl -128(%ebp,%edi,1),%ecx + movzbl %al,%edi + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bl,%edi + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %ah,%edi + shll $16,%esi + shrl $16,%eax + orl %esi,%edx + movzbl -128(%ebp,%edi,1),%esi + movzbl %bh,%edi + shrl $16,%ebx + shll $8,%esi + movd %edx,%mm1 + movzbl -128(%ebp,%edi,1),%edx + movzbl %bh,%edi + shll $24,%edx + andl $255,%ebx + orl %esi,%edx + punpckldq %mm1,%mm0 + movzbl -128(%ebp,%edi,1),%esi + movzbl %al,%edi + shll $8,%esi + movzbl %ah,%eax + movzbl -128(%ebp,%ebx,1),%ebx + orl %esi,%ecx + movzbl -128(%ebp,%edi,1),%esi + orl %ebx,%edx + shll $16,%esi + movzbl -128(%ebp,%eax,1),%eax + orl %esi,%edx + shll $24,%eax + orl %eax,%ecx + movl 20(%esp),%edi + movd %edx,%mm4 + movd %ecx,%mm5 + punpckldq %mm5,%mm4 + addl $16,%edi + cmpl 24(%esp),%edi + ja .L008out + movq %mm0,%mm3 + movq %mm4,%mm7 + pshufw $228,%mm0,%mm2 + pshufw $228,%mm4,%mm6 + movq %mm0,%mm1 + movq %mm4,%mm5 + pshufw $177,%mm0,%mm0 + pshufw $177,%mm4,%mm4 + pslld $8,%mm2 + pslld $8,%mm6 + psrld $8,%mm3 + psrld $8,%mm7 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pslld $16,%mm2 + pslld $16,%mm6 + psrld $16,%mm3 + psrld $16,%mm7 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movq 8(%esp),%mm3 + pxor %mm2,%mm2 + pxor %mm6,%mm6 + pcmpgtb %mm1,%mm2 + pcmpgtb %mm5,%mm6 + pand %mm3,%mm2 + pand %mm3,%mm6 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm2,%mm1 + pxor %mm6,%mm5 + movq %mm1,%mm3 + movq %mm5,%mm7 + movq %mm1,%mm2 + movq %mm5,%mm6 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pslld $24,%mm3 + pslld $24,%mm7 + psrld $8,%mm2 + psrld $8,%mm6 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + movq 8(%esp),%mm2 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + pcmpgtb %mm1,%mm3 + pcmpgtb %mm5,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm3,%mm1 + pxor %mm7,%mm5 + pshufw $177,%mm1,%mm3 + pshufw $177,%mm5,%mm7 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm3,%mm3 + pxor %mm7,%mm7 + pcmpgtb %mm1,%mm3 + pcmpgtb %mm5,%mm7 + pand %mm2,%mm3 + pand %mm2,%mm7 + paddb %mm1,%mm1 + paddb %mm5,%mm5 + pxor %mm3,%mm1 + pxor %mm7,%mm5 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movq %mm1,%mm3 + movq %mm5,%mm7 + pshufw $177,%mm1,%mm2 + pshufw $177,%mm5,%mm6 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + pslld $8,%mm1 + pslld $8,%mm5 + psrld $8,%mm3 + psrld $8,%mm7 + movq (%edi),%mm2 + movq 8(%edi),%mm6 + pxor %mm1,%mm0 + pxor %mm5,%mm4 + pxor %mm3,%mm0 + pxor %mm7,%mm4 + movl -128(%ebp),%eax + pslld $16,%mm1 + pslld $16,%mm5 + movl -64(%ebp),%ebx + psrld $16,%mm3 + psrld $16,%mm7 + movl (%ebp),%ecx + pxor %mm1,%mm0 + pxor %mm5,%mm4 + movl 64(%ebp),%edx + pxor %mm3,%mm0 + pxor %mm7,%mm4 + pxor %mm2,%mm0 + pxor %mm6,%mm4 + jmp .L007loop +.align 16 +.L008out: + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + ret +.size _sse_AES_decrypt_compact,.-_sse_AES_decrypt_compact +.type _x86_AES_decrypt,@function +.align 16 +_x86_AES_decrypt: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + movl %edi,20(%esp) + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,24(%esp) +.align 16 +.L009loop: + movl %eax,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %dh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %ebx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,4(%esp) + + movl %ebx,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %ah,%edi + xorl 3(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %ecx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + movl %esi,8(%esp) + + movl %ecx,%esi + andl $255,%esi + movl (%ebp,%esi,8),%esi + movzbl %bh,%edi + xorl 3(%ebp,%edi,8),%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + xorl 2(%ebp,%edi,8),%esi + movl %edx,%edi + shrl $24,%edi + xorl 1(%ebp,%edi,8),%esi + + movl 20(%esp),%edi + andl $255,%edx + movl (%ebp,%edx,8),%edx + movzbl %ch,%ecx + xorl 3(%ebp,%ecx,8),%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + xorl 2(%ebp,%ebx,8),%edx + movl 8(%esp),%ebx + shrl $24,%eax + xorl 1(%ebp,%eax,8),%edx + movl 4(%esp),%eax + + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + cmpl 24(%esp),%edi + movl %edi,20(%esp) + jb .L009loop + leal 2176(%ebp),%ebp + movl -128(%ebp),%edi + movl -96(%ebp),%esi + movl -64(%ebp),%edi + movl -32(%ebp),%esi + movl (%ebp),%edi + movl 32(%ebp),%esi + movl 64(%ebp),%edi + movl 96(%ebp),%esi + leal -128(%ebp),%ebp + movl %eax,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %dh,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ebx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,4(%esp) + movl %ebx,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %ah,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %ecx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl %esi,8(%esp) + movl %ecx,%esi + andl $255,%esi + movzbl (%ebp,%esi,1),%esi + movzbl %bh,%edi + movzbl (%ebp,%edi,1),%edi + shll $8,%edi + xorl %edi,%esi + movl %eax,%edi + shrl $16,%edi + andl $255,%edi + movzbl (%ebp,%edi,1),%edi + shll $16,%edi + xorl %edi,%esi + movl %edx,%edi + shrl $24,%edi + movzbl (%ebp,%edi,1),%edi + shll $24,%edi + xorl %edi,%esi + movl 20(%esp),%edi + andl $255,%edx + movzbl (%ebp,%edx,1),%edx + movzbl %ch,%ecx + movzbl (%ebp,%ecx,1),%ecx + shll $8,%ecx + xorl %ecx,%edx + movl %esi,%ecx + shrl $16,%ebx + andl $255,%ebx + movzbl (%ebp,%ebx,1),%ebx + shll $16,%ebx + xorl %ebx,%edx + movl 8(%esp),%ebx + shrl $24,%eax + movzbl (%ebp,%eax,1),%eax + shll $24,%eax + xorl %eax,%edx + movl 4(%esp),%eax + leal -2048(%ebp),%ebp + addl $16,%edi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + ret +.align 64 +.LAES_Td: +.long 1353184337,1353184337 +.long 1399144830,1399144830 +.long 3282310938,3282310938 +.long 2522752826,2522752826 +.long 3412831035,3412831035 +.long 4047871263,4047871263 +.long 2874735276,2874735276 +.long 2466505547,2466505547 +.long 1442459680,1442459680 +.long 4134368941,4134368941 +.long 2440481928,2440481928 +.long 625738485,625738485 +.long 4242007375,4242007375 +.long 3620416197,3620416197 +.long 2151953702,2151953702 +.long 2409849525,2409849525 +.long 1230680542,1230680542 +.long 1729870373,1729870373 +.long 2551114309,2551114309 +.long 3787521629,3787521629 +.long 41234371,41234371 +.long 317738113,317738113 +.long 2744600205,2744600205 +.long 3338261355,3338261355 +.long 3881799427,3881799427 +.long 2510066197,2510066197 +.long 3950669247,3950669247 +.long 3663286933,3663286933 +.long 763608788,763608788 +.long 3542185048,3542185048 +.long 694804553,694804553 +.long 1154009486,1154009486 +.long 1787413109,1787413109 +.long 2021232372,2021232372 +.long 1799248025,1799248025 +.long 3715217703,3715217703 +.long 3058688446,3058688446 +.long 397248752,397248752 +.long 1722556617,1722556617 +.long 3023752829,3023752829 +.long 407560035,407560035 +.long 2184256229,2184256229 +.long 1613975959,1613975959 +.long 1165972322,1165972322 +.long 3765920945,3765920945 +.long 2226023355,2226023355 +.long 480281086,480281086 +.long 2485848313,2485848313 +.long 1483229296,1483229296 +.long 436028815,436028815 +.long 2272059028,2272059028 +.long 3086515026,3086515026 +.long 601060267,601060267 +.long 3791801202,3791801202 +.long 1468997603,1468997603 +.long 715871590,715871590 +.long 120122290,120122290 +.long 63092015,63092015 +.long 2591802758,2591802758 +.long 2768779219,2768779219 +.long 4068943920,4068943920 +.long 2997206819,2997206819 +.long 3127509762,3127509762 +.long 1552029421,1552029421 +.long 723308426,723308426 +.long 2461301159,2461301159 +.long 4042393587,4042393587 +.long 2715969870,2715969870 +.long 3455375973,3455375973 +.long 3586000134,3586000134 +.long 526529745,526529745 +.long 2331944644,2331944644 +.long 2639474228,2639474228 +.long 2689987490,2689987490 +.long 853641733,853641733 +.long 1978398372,1978398372 +.long 971801355,971801355 +.long 2867814464,2867814464 +.long 111112542,111112542 +.long 1360031421,1360031421 +.long 4186579262,4186579262 +.long 1023860118,1023860118 +.long 2919579357,2919579357 +.long 1186850381,1186850381 +.long 3045938321,3045938321 +.long 90031217,90031217 +.long 1876166148,1876166148 +.long 4279586912,4279586912 +.long 620468249,620468249 +.long 2548678102,2548678102 +.long 3426959497,3426959497 +.long 2006899047,2006899047 +.long 3175278768,3175278768 +.long 2290845959,2290845959 +.long 945494503,945494503 +.long 3689859193,3689859193 +.long 1191869601,1191869601 +.long 3910091388,3910091388 +.long 3374220536,3374220536 +.long 0,0 +.long 2206629897,2206629897 +.long 1223502642,1223502642 +.long 2893025566,2893025566 +.long 1316117100,1316117100 +.long 4227796733,4227796733 +.long 1446544655,1446544655 +.long 517320253,517320253 +.long 658058550,658058550 +.long 1691946762,1691946762 +.long 564550760,564550760 +.long 3511966619,3511966619 +.long 976107044,976107044 +.long 2976320012,2976320012 +.long 266819475,266819475 +.long 3533106868,3533106868 +.long 2660342555,2660342555 +.long 1338359936,1338359936 +.long 2720062561,2720062561 +.long 1766553434,1766553434 +.long 370807324,370807324 +.long 179999714,179999714 +.long 3844776128,3844776128 +.long 1138762300,1138762300 +.long 488053522,488053522 +.long 185403662,185403662 +.long 2915535858,2915535858 +.long 3114841645,3114841645 +.long 3366526484,3366526484 +.long 2233069911,2233069911 +.long 1275557295,1275557295 +.long 3151862254,3151862254 +.long 4250959779,4250959779 +.long 2670068215,2670068215 +.long 3170202204,3170202204 +.long 3309004356,3309004356 +.long 880737115,880737115 +.long 1982415755,1982415755 +.long 3703972811,3703972811 +.long 1761406390,1761406390 +.long 1676797112,1676797112 +.long 3403428311,3403428311 +.long 277177154,277177154 +.long 1076008723,1076008723 +.long 538035844,538035844 +.long 2099530373,2099530373 +.long 4164795346,4164795346 +.long 288553390,288553390 +.long 1839278535,1839278535 +.long 1261411869,1261411869 +.long 4080055004,4080055004 +.long 3964831245,3964831245 +.long 3504587127,3504587127 +.long 1813426987,1813426987 +.long 2579067049,2579067049 +.long 4199060497,4199060497 +.long 577038663,577038663 +.long 3297574056,3297574056 +.long 440397984,440397984 +.long 3626794326,3626794326 +.long 4019204898,4019204898 +.long 3343796615,3343796615 +.long 3251714265,3251714265 +.long 4272081548,4272081548 +.long 906744984,906744984 +.long 3481400742,3481400742 +.long 685669029,685669029 +.long 646887386,646887386 +.long 2764025151,2764025151 +.long 3835509292,3835509292 +.long 227702864,227702864 +.long 2613862250,2613862250 +.long 1648787028,1648787028 +.long 3256061430,3256061430 +.long 3904428176,3904428176 +.long 1593260334,1593260334 +.long 4121936770,4121936770 +.long 3196083615,3196083615 +.long 2090061929,2090061929 +.long 2838353263,2838353263 +.long 3004310991,3004310991 +.long 999926984,999926984 +.long 2809993232,2809993232 +.long 1852021992,1852021992 +.long 2075868123,2075868123 +.long 158869197,158869197 +.long 4095236462,4095236462 +.long 28809964,28809964 +.long 2828685187,2828685187 +.long 1701746150,1701746150 +.long 2129067946,2129067946 +.long 147831841,147831841 +.long 3873969647,3873969647 +.long 3650873274,3650873274 +.long 3459673930,3459673930 +.long 3557400554,3557400554 +.long 3598495785,3598495785 +.long 2947720241,2947720241 +.long 824393514,824393514 +.long 815048134,815048134 +.long 3227951669,3227951669 +.long 935087732,935087732 +.long 2798289660,2798289660 +.long 2966458592,2966458592 +.long 366520115,366520115 +.long 1251476721,1251476721 +.long 4158319681,4158319681 +.long 240176511,240176511 +.long 804688151,804688151 +.long 2379631990,2379631990 +.long 1303441219,1303441219 +.long 1414376140,1414376140 +.long 3741619940,3741619940 +.long 3820343710,3820343710 +.long 461924940,461924940 +.long 3089050817,3089050817 +.long 2136040774,2136040774 +.long 82468509,82468509 +.long 1563790337,1563790337 +.long 1937016826,1937016826 +.long 776014843,776014843 +.long 1511876531,1511876531 +.long 1389550482,1389550482 +.long 861278441,861278441 +.long 323475053,323475053 +.long 2355222426,2355222426 +.long 2047648055,2047648055 +.long 2383738969,2383738969 +.long 2302415851,2302415851 +.long 3995576782,3995576782 +.long 902390199,902390199 +.long 3991215329,3991215329 +.long 1018251130,1018251130 +.long 1507840668,1507840668 +.long 1064563285,1064563285 +.long 2043548696,2043548696 +.long 3208103795,3208103795 +.long 3939366739,3939366739 +.long 1537932639,1537932639 +.long 342834655,342834655 +.long 2262516856,2262516856 +.long 2180231114,2180231114 +.long 1053059257,1053059257 +.long 741614648,741614648 +.long 1598071746,1598071746 +.long 1925389590,1925389590 +.long 203809468,203809468 +.long 2336832552,2336832552 +.long 1100287487,1100287487 +.long 1895934009,1895934009 +.long 3736275976,3736275976 +.long 2632234200,2632234200 +.long 2428589668,2428589668 +.long 1636092795,1636092795 +.long 1890988757,1890988757 +.long 1952214088,1952214088 +.long 1113045200,1113045200 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.byte 82,9,106,213,48,54,165,56 +.byte 191,64,163,158,129,243,215,251 +.byte 124,227,57,130,155,47,255,135 +.byte 52,142,67,68,196,222,233,203 +.byte 84,123,148,50,166,194,35,61 +.byte 238,76,149,11,66,250,195,78 +.byte 8,46,161,102,40,217,36,178 +.byte 118,91,162,73,109,139,209,37 +.byte 114,248,246,100,134,104,152,22 +.byte 212,164,92,204,93,101,182,146 +.byte 108,112,72,80,253,237,185,218 +.byte 94,21,70,87,167,141,157,132 +.byte 144,216,171,0,140,188,211,10 +.byte 247,228,88,5,184,179,69,6 +.byte 208,44,30,143,202,63,15,2 +.byte 193,175,189,3,1,19,138,107 +.byte 58,145,17,65,79,103,220,234 +.byte 151,242,207,206,240,180,230,115 +.byte 150,172,116,34,231,173,53,133 +.byte 226,249,55,232,28,117,223,110 +.byte 71,241,26,113,29,41,197,137 +.byte 111,183,98,14,170,24,190,27 +.byte 252,86,62,75,198,210,121,32 +.byte 154,219,192,254,120,205,90,244 +.byte 31,221,168,51,136,7,199,49 +.byte 177,18,16,89,39,128,236,95 +.byte 96,81,127,169,25,181,74,13 +.byte 45,229,122,159,147,201,156,239 +.byte 160,224,59,77,174,42,245,176 +.byte 200,235,187,60,131,83,153,97 +.byte 23,43,4,126,186,119,214,38 +.byte 225,105,20,99,85,33,12,125 +.size _x86_AES_decrypt,.-_x86_AES_decrypt +.globl AES_decrypt +.type AES_decrypt,@function +.align 16 +AES_decrypt: +.L_AES_decrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 20(%esp),%esi + movl 28(%esp),%edi + movl %esp,%eax + subl $36,%esp + andl $-64,%esp + leal -127(%edi),%ebx + subl %esp,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esp + addl $4,%esp + movl %eax,28(%esp) + call .L010pic_point +.L010pic_point: + popl %ebp + leal OPENSSL_ia32cap_P,%eax + leal .LAES_Td-.L010pic_point(%ebp),%ebp + leal 764(%esp),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + btl $25,(%eax) + jnc .L011x86 + movq (%esi),%mm0 + movq 8(%esi),%mm4 + call _sse_AES_decrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.align 16 +.L011x86: + movl %ebp,24(%esp) + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + call _x86_AES_decrypt_compact + movl 28(%esp),%esp + movl 24(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_decrypt,.-.L_AES_decrypt_begin +.globl AES_cbc_encrypt +.type AES_cbc_encrypt,@function +.align 16 +AES_cbc_encrypt: +.L_AES_cbc_encrypt_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 28(%esp),%ecx + cmpl $0,%ecx + je .L012drop_out + call .L013pic_point +.L013pic_point: + popl %ebp + leal OPENSSL_ia32cap_P,%eax + cmpl $0,40(%esp) + leal .LAES_Te-.L013pic_point(%ebp),%ebp + jne .L014picked_te + leal .LAES_Td-.LAES_Te(%ebp),%ebp +.L014picked_te: + pushfl + cld + cmpl $512,%ecx + jb .L015slow_way + testl $15,%ecx + jnz .L015slow_way + btl $28,(%eax) + jc .L015slow_way + leal -324(%esp),%esi + andl $-64,%esi + movl %ebp,%eax + leal 2304(%ebp),%ebx + movl %esi,%edx + andl $4095,%eax + andl $4095,%ebx + andl $4095,%edx + cmpl %ebx,%edx + jb .L016tbl_break_out + subl %ebx,%edx + subl %edx,%esi + jmp .L017tbl_ok +.align 4 +.L016tbl_break_out: + subl %eax,%edx + andl $4095,%edx + addl $384,%edx + subl %edx,%esi +.align 4 +.L017tbl_ok: + leal 24(%esp),%edx + xchgl %esi,%esp + addl $4,%esp + movl %ebp,24(%esp) + movl %esi,28(%esp) + movl (%edx),%eax + movl 4(%edx),%ebx + movl 12(%edx),%edi + movl 16(%edx),%esi + movl 20(%edx),%edx + movl %eax,32(%esp) + movl %ebx,36(%esp) + movl %ecx,40(%esp) + movl %edi,44(%esp) + movl %esi,48(%esp) + movl $0,316(%esp) + movl %edi,%ebx + movl $61,%ecx + subl %ebp,%ebx + movl %edi,%esi + andl $4095,%ebx + leal 76(%esp),%edi + cmpl $2304,%ebx + jb .L018do_copy + cmpl $3852,%ebx + jb .L019skip_copy +.align 4 +.L018do_copy: + movl %edi,44(%esp) +.long 2784229001 +.L019skip_copy: + movl $16,%edi +.align 4 +.L020prefetch_tbl: + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%esi + leal 128(%ebp),%ebp + subl $1,%edi + jnz .L020prefetch_tbl + subl $2048,%ebp + movl 32(%esp),%esi + movl 48(%esp),%edi + cmpl $0,%edx + je .L021fast_decrypt + movl (%edi),%eax + movl 4(%edi),%ebx +.align 16 +.L022fast_enc_loop: + movl 8(%edi),%ecx + movl 12(%edi),%edx + xorl (%esi),%eax + xorl 4(%esi),%ebx + xorl 8(%esi),%ecx + xorl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_encrypt + movl 32(%esp),%esi + movl 36(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + leal 16(%esi),%esi + movl 40(%esp),%ecx + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L022fast_enc_loop + movl 48(%esp),%esi + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + cmpl $0,316(%esp) + movl 44(%esp),%edi + je .L023skip_ezero + movl $60,%ecx + xorl %eax,%eax +.align 4 +.long 2884892297 +.L023skip_ezero: + movl 28(%esp),%esp + popfl +.L012drop_out: + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L021fast_decrypt: + cmpl 36(%esp),%esi + je .L024fast_dec_in_place + movl %edi,52(%esp) +.align 4 +.align 16 +.L025fast_dec_loop: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_decrypt + movl 52(%esp),%edi + movl 40(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl 36(%esp),%edi + movl 32(%esp),%esi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + movl %esi,52(%esp) + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edi + movl %edi,36(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L025fast_dec_loop + movl 52(%esp),%edi + movl 48(%esp),%esi + movl (%edi),%eax + movl 4(%edi),%ebx + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + jmp .L026fast_dec_out +.align 16 +.L024fast_dec_in_place: +.L027fast_dec_in_place_loop: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + leal 60(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 44(%esp),%edi + call _x86_AES_decrypt + movl 48(%esp),%edi + movl 36(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + leal 16(%esi),%esi + movl %esi,36(%esp) + leal 60(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 32(%esp),%esi + movl 40(%esp),%ecx + leal 16(%esi),%esi + movl %esi,32(%esp) + subl $16,%ecx + movl %ecx,40(%esp) + jnz .L027fast_dec_in_place_loop +.align 4 +.L026fast_dec_out: + cmpl $0,316(%esp) + movl 44(%esp),%edi + je .L028skip_dzero + movl $60,%ecx + xorl %eax,%eax +.align 4 +.long 2884892297 +.L028skip_dzero: + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L015slow_way: + movl (%eax),%eax + movl 36(%esp),%edi + leal -80(%esp),%esi + andl $-64,%esi + leal -143(%edi),%ebx + subl %esi,%ebx + negl %ebx + andl $960,%ebx + subl %ebx,%esi + leal 768(%esi),%ebx + subl %ebp,%ebx + andl $768,%ebx + leal 2176(%ebp,%ebx,1),%ebp + leal 24(%esp),%edx + xchgl %esi,%esp + addl $4,%esp + movl %ebp,24(%esp) + movl %esi,28(%esp) + movl %eax,52(%esp) + movl (%edx),%eax + movl 4(%edx),%ebx + movl 16(%edx),%esi + movl 20(%edx),%edx + movl %eax,32(%esp) + movl %ebx,36(%esp) + movl %ecx,40(%esp) + movl %edi,44(%esp) + movl %esi,48(%esp) + movl %esi,%edi + movl %eax,%esi + cmpl $0,%edx + je .L029slow_decrypt + cmpl $16,%ecx + movl %ebx,%edx + jb .L030slow_enc_tail + btl $25,52(%esp) + jnc .L031slow_enc_x86 + movq (%edi),%mm0 + movq 8(%edi),%mm4 +.align 16 +.L032slow_enc_loop_sse: + pxor (%esi),%mm0 + pxor 8(%esi),%mm4 + movl 44(%esp),%edi + call _sse_AES_encrypt_compact + movl 32(%esp),%esi + movl 36(%esp),%edi + movl 40(%esp),%ecx + movq %mm0,(%edi) + movq %mm4,8(%edi) + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + cmpl $16,%ecx + movl %ecx,40(%esp) + jae .L032slow_enc_loop_sse + testl $15,%ecx + jnz .L030slow_enc_tail + movl 48(%esp),%esi + movq %mm0,(%esi) + movq %mm4,8(%esi) + emms + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L031slow_enc_x86: + movl (%edi),%eax + movl 4(%edi),%ebx +.align 4 +.L033slow_enc_loop_x86: + movl 8(%edi),%ecx + movl 12(%edi),%edx + xorl (%esi),%eax + xorl 4(%esi),%ebx + xorl 8(%esi),%ecx + xorl 12(%esi),%edx + movl 44(%esp),%edi + call _x86_AES_encrypt_compact + movl 32(%esp),%esi + movl 36(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + leal 16(%esi),%esi + movl %esi,32(%esp) + leal 16(%edi),%edx + movl %edx,36(%esp) + subl $16,%ecx + cmpl $16,%ecx + movl %ecx,40(%esp) + jae .L033slow_enc_loop_x86 + testl $15,%ecx + jnz .L030slow_enc_tail + movl 48(%esp),%esi + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L030slow_enc_tail: + emms + movl %edx,%edi + movl $16,%ebx + subl %ecx,%ebx + cmpl %esi,%edi + je .L034enc_in_place +.align 4 +.long 2767451785 + jmp .L035enc_skip_in_place +.L034enc_in_place: + leal (%edi,%ecx,1),%edi +.L035enc_skip_in_place: + movl %ebx,%ecx + xorl %eax,%eax +.align 4 +.long 2868115081 + movl 48(%esp),%edi + movl %edx,%esi + movl (%edi),%eax + movl 4(%edi),%ebx + movl $16,40(%esp) + jmp .L033slow_enc_loop_x86 +.align 16 +.L029slow_decrypt: + btl $25,52(%esp) + jnc .L036slow_dec_loop_x86 +.align 4 +.L037slow_dec_loop_sse: + movq (%esi),%mm0 + movq 8(%esi),%mm4 + movl 44(%esp),%edi + call _sse_AES_decrypt_compact + movl 32(%esp),%esi + leal 60(%esp),%eax + movl 36(%esp),%ebx + movl 40(%esp),%ecx + movl 48(%esp),%edi + movq (%esi),%mm1 + movq 8(%esi),%mm5 + pxor (%edi),%mm0 + pxor 8(%edi),%mm4 + movq %mm1,(%edi) + movq %mm5,8(%edi) + subl $16,%ecx + jc .L038slow_dec_partial_sse + movq %mm0,(%ebx) + movq %mm4,8(%ebx) + leal 16(%ebx),%ebx + movl %ebx,36(%esp) + leal 16(%esi),%esi + movl %esi,32(%esp) + movl %ecx,40(%esp) + jnz .L037slow_dec_loop_sse + emms + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L038slow_dec_partial_sse: + movq %mm0,(%eax) + movq %mm4,8(%eax) + emms + addl $16,%ecx + movl %ebx,%edi + movl %eax,%esi +.align 4 +.long 2767451785 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L036slow_dec_loop_x86: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + leal 60(%esp),%edi + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 44(%esp),%edi + call _x86_AES_decrypt_compact + movl 48(%esp),%edi + movl 40(%esp),%esi + xorl (%edi),%eax + xorl 4(%edi),%ebx + xorl 8(%edi),%ecx + xorl 12(%edi),%edx + subl $16,%esi + jc .L039slow_dec_partial_x86 + movl %esi,40(%esp) + movl 36(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + leal 16(%esi),%esi + movl %esi,36(%esp) + leal 60(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 32(%esp),%esi + leal 16(%esi),%esi + movl %esi,32(%esp) + jnz .L036slow_dec_loop_x86 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret + pushfl +.align 16 +.L039slow_dec_partial_x86: + leal 60(%esp),%esi + movl %eax,(%esi) + movl %ebx,4(%esi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + movl 32(%esp),%esi + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 40(%esp),%ecx + movl 36(%esp),%edi + leal 60(%esp),%esi +.align 4 +.long 2767451785 + movl 28(%esp),%esp + popfl + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_cbc_encrypt,.-.L_AES_cbc_encrypt_begin +.type _x86_AES_set_encrypt_key,@function +.align 16 +_x86_AES_set_encrypt_key: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 24(%esp),%esi + movl 32(%esp),%edi + testl $-1,%esi + jz .L040badpointer + testl $-1,%edi + jz .L040badpointer + call .L041pic_point +.L041pic_point: + popl %ebp + leal .LAES_Te-.L041pic_point(%ebp),%ebp + leal 2176(%ebp),%ebp + movl -128(%ebp),%eax + movl -96(%ebp),%ebx + movl -64(%ebp),%ecx + movl -32(%ebp),%edx + movl (%ebp),%eax + movl 32(%ebp),%ebx + movl 64(%ebp),%ecx + movl 96(%ebp),%edx + movl 28(%esp),%ecx + cmpl $128,%ecx + je .L04210rounds + cmpl $192,%ecx + je .L04312rounds + cmpl $256,%ecx + je .L04414rounds + movl $-2,%eax + jmp .L045exit +.L04210rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + xorl %ecx,%ecx + jmp .L04610shortcut +.align 4 +.L04710loop: + movl (%edi),%eax + movl 12(%edi),%edx +.L04610shortcut: + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,16(%edi) + xorl 4(%edi),%eax + movl %eax,20(%edi) + xorl 8(%edi),%eax + movl %eax,24(%edi) + xorl 12(%edi),%eax + movl %eax,28(%edi) + incl %ecx + addl $16,%edi + cmpl $10,%ecx + jl .L04710loop + movl $10,80(%edi) + xorl %eax,%eax + jmp .L045exit +.L04312rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 16(%esi),%ecx + movl 20(%esi),%edx + movl %ecx,16(%edi) + movl %edx,20(%edi) + xorl %ecx,%ecx + jmp .L04812shortcut +.align 4 +.L04912loop: + movl (%edi),%eax + movl 20(%edi),%edx +.L04812shortcut: + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,24(%edi) + xorl 4(%edi),%eax + movl %eax,28(%edi) + xorl 8(%edi),%eax + movl %eax,32(%edi) + xorl 12(%edi),%eax + movl %eax,36(%edi) + cmpl $7,%ecx + je .L05012break + incl %ecx + xorl 16(%edi),%eax + movl %eax,40(%edi) + xorl 20(%edi),%eax + movl %eax,44(%edi) + addl $24,%edi + jmp .L04912loop +.L05012break: + movl $12,72(%edi) + xorl %eax,%eax + jmp .L045exit +.L04414rounds: + movl (%esi),%eax + movl 4(%esi),%ebx + movl 8(%esi),%ecx + movl 12(%esi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,8(%edi) + movl %edx,12(%edi) + movl 16(%esi),%eax + movl 20(%esi),%ebx + movl 24(%esi),%ecx + movl 28(%esi),%edx + movl %eax,16(%edi) + movl %ebx,20(%edi) + movl %ecx,24(%edi) + movl %edx,28(%edi) + xorl %ecx,%ecx + jmp .L05114shortcut +.align 4 +.L05214loop: + movl 28(%edi),%edx +.L05114shortcut: + movl (%edi),%eax + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $24,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $8,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $16,%ebx + xorl %ebx,%eax + xorl 896(%ebp,%ecx,4),%eax + movl %eax,32(%edi) + xorl 4(%edi),%eax + movl %eax,36(%edi) + xorl 8(%edi),%eax + movl %eax,40(%edi) + xorl 12(%edi),%eax + movl %eax,44(%edi) + cmpl $6,%ecx + je .L05314break + incl %ecx + movl %eax,%edx + movl 16(%edi),%eax + movzbl %dl,%esi + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shrl $16,%edx + shll $8,%ebx + movzbl %dl,%esi + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + movzbl %dh,%esi + shll $16,%ebx + xorl %ebx,%eax + movzbl -128(%ebp,%esi,1),%ebx + shll $24,%ebx + xorl %ebx,%eax + movl %eax,48(%edi) + xorl 20(%edi),%eax + movl %eax,52(%edi) + xorl 24(%edi),%eax + movl %eax,56(%edi) + xorl 28(%edi),%eax + movl %eax,60(%edi) + addl $32,%edi + jmp .L05214loop +.L05314break: + movl $14,48(%edi) + xorl %eax,%eax + jmp .L045exit +.L040badpointer: + movl $-1,%eax +.L045exit: + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size _x86_AES_set_encrypt_key,.-_x86_AES_set_encrypt_key +.globl AES_set_encrypt_key +.type AES_set_encrypt_key,@function +.align 16 +AES_set_encrypt_key: +.L_AES_set_encrypt_key_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + call _x86_AES_set_encrypt_key + ret +.size AES_set_encrypt_key,.-.L_AES_set_encrypt_key_begin +.globl AES_set_decrypt_key +.type AES_set_decrypt_key,@function +.align 16 +AES_set_decrypt_key: +.L_AES_set_decrypt_key_begin: + #ifdef __CET__ + +.byte 243,15,30,251 + #endif + + call _x86_AES_set_encrypt_key + cmpl $0,%eax + je .L054proceed + ret +.L054proceed: + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi + movl 28(%esp),%esi + movl 240(%esi),%ecx + leal (,%ecx,4),%ecx + leal (%esi,%ecx,4),%edi +.align 4 +.L055invert: + movl (%esi),%eax + movl 4(%esi),%ebx + movl (%edi),%ecx + movl 4(%edi),%edx + movl %eax,(%edi) + movl %ebx,4(%edi) + movl %ecx,(%esi) + movl %edx,4(%esi) + movl 8(%esi),%eax + movl 12(%esi),%ebx + movl 8(%edi),%ecx + movl 12(%edi),%edx + movl %eax,8(%edi) + movl %ebx,12(%edi) + movl %ecx,8(%esi) + movl %edx,12(%esi) + addl $16,%esi + subl $16,%edi + cmpl %edi,%esi + jne .L055invert + movl 28(%esp),%edi + movl 240(%edi),%esi + leal -2(%esi,%esi,1),%esi + leal (%edi,%esi,8),%esi + movl %esi,28(%esp) + movl 16(%edi),%eax +.align 4 +.L056permute: + addl $16,%edi + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %esi,%ebx + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %eax,%ebx + xorl %esi,%ecx + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + xorl %eax,%ecx + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + roll $8,%eax + xorl %esi,%edx + movl 4(%edi),%ebp + xorl %ebx,%eax + xorl %edx,%ebx + xorl %ecx,%eax + roll $24,%ebx + xorl %edx,%ecx + xorl %edx,%eax + roll $16,%ecx + xorl %ebx,%eax + roll $8,%edx + xorl %ecx,%eax + movl %ebp,%ebx + xorl %edx,%eax + movl %eax,(%edi) + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + xorl %esi,%ecx + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %ebx,%ecx + xorl %esi,%edx + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + xorl %ebx,%edx + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + roll $8,%ebx + xorl %esi,%eax + movl 8(%edi),%ebp + xorl %ecx,%ebx + xorl %eax,%ecx + xorl %edx,%ebx + roll $24,%ecx + xorl %eax,%edx + xorl %eax,%ebx + roll $16,%edx + xorl %ecx,%ebx + roll $8,%eax + xorl %edx,%ebx + movl %ebp,%ecx + xorl %eax,%ebx + movl %ebx,4(%edi) + movl $2155905152,%ebp + andl %ecx,%ebp + leal (%ecx,%ecx,1),%edx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%edx + andl $454761243,%esi + xorl %esi,%edx + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %ecx,%edx + xorl %esi,%eax + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + xorl %ecx,%eax + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + roll $8,%ecx + xorl %esi,%ebx + movl 12(%edi),%ebp + xorl %edx,%ecx + xorl %ebx,%edx + xorl %eax,%ecx + roll $24,%edx + xorl %ebx,%eax + xorl %ebx,%ecx + roll $16,%eax + xorl %edx,%ecx + roll $8,%ebx + xorl %eax,%ecx + movl %ebp,%edx + xorl %ebx,%ecx + movl %ecx,8(%edi) + movl $2155905152,%ebp + andl %edx,%ebp + leal (%edx,%edx,1),%eax + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%eax + andl $454761243,%esi + xorl %esi,%eax + movl $2155905152,%ebp + andl %eax,%ebp + leal (%eax,%eax,1),%ebx + movl %ebp,%esi + shrl $7,%ebp + subl %ebp,%esi + andl $4278124286,%ebx + andl $454761243,%esi + xorl %edx,%eax + xorl %esi,%ebx + movl $2155905152,%ebp + andl %ebx,%ebp + leal (%ebx,%ebx,1),%ecx + movl %ebp,%esi + shrl $7,%ebp + xorl %edx,%ebx + subl %ebp,%esi + andl $4278124286,%ecx + andl $454761243,%esi + roll $8,%edx + xorl %esi,%ecx + movl 16(%edi),%ebp + xorl %eax,%edx + xorl %ecx,%eax + xorl %ebx,%edx + roll $24,%eax + xorl %ecx,%ebx + xorl %ecx,%edx + roll $16,%ebx + xorl %eax,%edx + roll $8,%ecx + xorl %ebx,%edx + movl %ebp,%eax + xorl %ecx,%edx + movl %edx,12(%edi) + cmpl 28(%esp),%edi + jb .L056permute + xorl %eax,%eax + popl %edi + popl %esi + popl %ebx + popl %ebp + ret +.size AES_set_decrypt_key,.-.L_AES_set_decrypt_key_begin +.byte 65,69,83,32,102,111,114,32,120,56,54,44,32,67,82,89 +.byte 80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114 +.byte 111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 +.comm OPENSSL_ia32cap_P,16,4 + + .section ".note.gnu.property", "a" + .p2align 2 + .long 1f - 0f + .long 4f - 1f + .long 5 +0: + .asciz "GNU" +1: + .p2align 2 + .long 0xc0000002 + .long 3f - 2f +2: + .long 3 +3: + .p2align 2 +4: +#endif