diff options
Diffstat (limited to 'module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S')
| -rw-r--r-- | module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S | 24 |
1 files changed, 20 insertions, 4 deletions
diff --git a/module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S b/module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S index ed9f660fce5b..dc71ae2c1c89 100644 --- a/module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S +++ b/module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S @@ -55,6 +55,7 @@ .type _aesni_ctr32_ghash_6x,@function .align 32 _aesni_ctr32_ghash_6x: +.cfi_startproc vmovdqu 32(%r11),%xmm2 subq $6,%rdx vpxor %xmm4,%xmm4,%xmm4 @@ -363,12 +364,14 @@ _aesni_ctr32_ghash_6x: vpxor %xmm4,%xmm8,%xmm8 .byte 0xf3,0xc3 +.cfi_endproc .size _aesni_ctr32_ghash_6x,.-_aesni_ctr32_ghash_6x #endif /* ifdef HAVE_MOVBE */ .type _aesni_ctr32_ghash_no_movbe_6x,@function .align 32 _aesni_ctr32_ghash_no_movbe_6x: +.cfi_startproc vmovdqu 32(%r11),%xmm2 subq $6,%rdx vpxor %xmm4,%xmm4,%xmm4 @@ -689,6 +692,7 @@ _aesni_ctr32_ghash_no_movbe_6x: vpxor %xmm4,%xmm8,%xmm8 .byte 0xf3,0xc3 +.cfi_endproc .size _aesni_ctr32_ghash_no_movbe_6x,.-_aesni_ctr32_ghash_no_movbe_6x .globl aesni_gcm_decrypt @@ -714,6 +718,8 @@ aesni_gcm_decrypt: .cfi_offset %r14,-48 pushq %r15 .cfi_offset %r15,-56 + pushq %r9 +.cfi_offset %r9,-64 vzeroupper vmovdqu (%r8),%xmm1 @@ -726,7 +732,8 @@ aesni_gcm_decrypt: andq $-128,%rsp vmovdqu (%r11),%xmm0 leaq 128(%rcx),%rcx - leaq 32+32(%r9),%r9 + movq 32(%r9),%r9 + leaq 32(%r9),%r9 movl 504-128(%rcx),%ebp // ICP has a larger offset for rounds. vpshufb %xmm0,%xmm8,%xmm8 @@ -782,7 +789,9 @@ aesni_gcm_decrypt: vmovups %xmm14,-16(%rsi) vpshufb (%r11),%xmm8,%xmm8 - vmovdqu %xmm8,-64(%r9) + movq -56(%rax),%r9 +.cfi_restore %r9 + vmovdqu %xmm8,(%r9) vzeroupper movq -48(%rax),%r15 @@ -807,6 +816,7 @@ aesni_gcm_decrypt: .type _aesni_ctr32_6x,@function .align 32 _aesni_ctr32_6x: +.cfi_startproc vmovdqu 0-128(%rcx),%xmm4 vmovdqu 32(%r11),%xmm2 leaq -2(%rbp),%r13 // ICP uses 10,12,14 not 9,11,13 for rounds. @@ -893,6 +903,7 @@ _aesni_ctr32_6x: vpshufb %xmm0,%xmm1,%xmm1 vpxor %xmm4,%xmm14,%xmm14 jmp .Loop_ctr32 +.cfi_endproc .size _aesni_ctr32_6x,.-_aesni_ctr32_6x .globl aesni_gcm_encrypt @@ -918,6 +929,8 @@ aesni_gcm_encrypt: .cfi_offset %r14,-48 pushq %r15 .cfi_offset %r15,-56 + pushq %r9 +.cfi_offset %r9,-64 vzeroupper vmovdqu (%r8),%xmm1 @@ -960,7 +973,8 @@ aesni_gcm_encrypt: call _aesni_ctr32_6x vmovdqu (%r9),%xmm8 - leaq 32+32(%r9),%r9 + movq 32(%r9),%r9 + leaq 32(%r9),%r9 subq $12,%rdx movq $192,%r10 vpshufb %xmm0,%xmm8,%xmm8 @@ -1151,7 +1165,9 @@ aesni_gcm_encrypt: vpxor %xmm7,%xmm2,%xmm2 vpxor %xmm2,%xmm8,%xmm8 vpshufb (%r11),%xmm8,%xmm8 - vmovdqu %xmm8,-64(%r9) + movq -56(%rax),%r9 +.cfi_restore %r9 + vmovdqu %xmm8,(%r9) vzeroupper movq -48(%rax),%r15 |