.text
-##define the fields of the gcm aes context
-#{
-# u8 expanded_keys[16*11] store expanded keys
-# u8 shifted_hkey_1[16] store HashKey <<1 mod poly here
-# u8 shifted_hkey_2[16] store HashKey^2 <<1 mod poly here
-# u8 shifted_hkey_3[16] store HashKey^3 <<1 mod poly here
-# u8 shifted_hkey_4[16] store HashKey^4 <<1 mod poly here
-# u8 shifted_hkey_5[16] store HashKey^5 <<1 mod poly here
-# u8 shifted_hkey_6[16] store HashKey^6 <<1 mod poly here
-# u8 shifted_hkey_7[16] store HashKey^7 <<1 mod poly here
-# u8 shifted_hkey_8[16] store HashKey^8 <<1 mod poly here
-# u8 shifted_hkey_1_k[16] store XOR HashKey <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_2_k[16] store XOR HashKey^2 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_3_k[16] store XOR HashKey^3 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_4_k[16] store XOR HashKey^4 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_5_k[16] store XOR HashKey^5 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_6_k[16] store XOR HashKey^6 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_7_k[16] store XOR HashKey^7 <<1 mod poly here (for Karatsuba purposes)
-# u8 shifted_hkey_8_k[16] store XOR HashKey^8 <<1 mod poly here (for Karatsuba purposes)
-#} gcm_ctx#
-
-HashKey = 16*11 # store HashKey <<1 mod poly here
-HashKey_2 = 16*12 # store HashKey^2 <<1 mod poly here
-HashKey_3 = 16*13 # store HashKey^3 <<1 mod poly here
-HashKey_4 = 16*14 # store HashKey^4 <<1 mod poly here
-HashKey_5 = 16*15 # store HashKey^5 <<1 mod poly here
-HashKey_6 = 16*16 # store HashKey^6 <<1 mod poly here
-HashKey_7 = 16*17 # store HashKey^7 <<1 mod poly here
-HashKey_8 = 16*18 # store HashKey^8 <<1 mod poly here
-HashKey_k = 16*19 # store XOR of HashKey <<1 mod poly here (for Karatsuba purposes)
-HashKey_2_k = 16*20 # store XOR of HashKey^2 <<1 mod poly here (for Karatsuba purposes)
-HashKey_3_k = 16*21 # store XOR of HashKey^3 <<1 mod poly here (for Karatsuba purposes)
-HashKey_4_k = 16*22 # store XOR of HashKey^4 <<1 mod poly here (for Karatsuba purposes)
-HashKey_5_k = 16*23 # store XOR of HashKey^5 <<1 mod poly here (for Karatsuba purposes)
-HashKey_6_k = 16*24 # store XOR of HashKey^6 <<1 mod poly here (for Karatsuba purposes)
-HashKey_7_k = 16*25 # store XOR of HashKey^7 <<1 mod poly here (for Karatsuba purposes)
-HashKey_8_k = 16*26 # store XOR of HashKey^8 <<1 mod poly here (for Karatsuba purposes)
+#define AadHash 16*0
+#define AadLen 16*1
+#define InLen (16*1)+8
+#define PBlockEncKey 16*2
+#define OrigIV 16*3
+#define CurCount 16*4
+#define PBlockLen 16*5
+
+HashKey = 16*6 # store HashKey <<1 mod poly here
+HashKey_2 = 16*7 # store HashKey^2 <<1 mod poly here
+HashKey_3 = 16*8 # store HashKey^3 <<1 mod poly here
+HashKey_4 = 16*9 # store HashKey^4 <<1 mod poly here
+HashKey_5 = 16*10 # store HashKey^5 <<1 mod poly here
+HashKey_6 = 16*11 # store HashKey^6 <<1 mod poly here
+HashKey_7 = 16*12 # store HashKey^7 <<1 mod poly here
+HashKey_8 = 16*13 # store HashKey^8 <<1 mod poly here
+HashKey_k = 16*14 # store XOR of HashKey <<1 mod poly here (for Karatsuba purposes)
+HashKey_2_k = 16*15 # store XOR of HashKey^2 <<1 mod poly here (for Karatsuba purposes)
+HashKey_3_k = 16*16 # store XOR of HashKey^3 <<1 mod poly here (for Karatsuba purposes)
+HashKey_4_k = 16*17 # store XOR of HashKey^4 <<1 mod poly here (for Karatsuba purposes)
+HashKey_5_k = 16*18 # store XOR of HashKey^5 <<1 mod poly here (for Karatsuba purposes)
+HashKey_6_k = 16*19 # store XOR of HashKey^6 <<1 mod poly here (for Karatsuba purposes)
+HashKey_7_k = 16*20 # store XOR of HashKey^7 <<1 mod poly here (for Karatsuba purposes)
+HashKey_8_k = 16*21 # store XOR of HashKey^8 <<1 mod poly here (for Karatsuba purposes)
#define arg1 %rdi
#define arg2 %rsi
#define arg7 STACK_OFFSET+8*1(%r14)
#define arg8 STACK_OFFSET+8*2(%r14)
#define arg9 STACK_OFFSET+8*3(%r14)
+#define arg10 STACK_OFFSET+8*4(%r14)
+#define keysize 2*15*16(arg1)
i = 0
j = 0
# Utility Macros
################################
+.macro FUNC_SAVE
+ #the number of pushes must equal STACK_OFFSET
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ mov %rsp, %r14
+
+
+
+ sub $VARIABLE_OFFSET, %rsp
+ and $~63, %rsp # align rsp to 64 bytes
+.endm
+
+.macro FUNC_RESTORE
+ mov %r14, %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+.endm
+
# Encryption of a single block
-.macro ENCRYPT_SINGLE_BLOCK XMM0
+.macro ENCRYPT_SINGLE_BLOCK REP XMM0
vpxor (arg1), \XMM0, \XMM0
- i = 1
- setreg
-.rep 9
+ i = 1
+ setreg
+.rep \REP
vaesenc 16*i(arg1), \XMM0, \XMM0
- i = (i+1)
- setreg
+ i = (i+1)
+ setreg
.endr
- vaesenclast 16*10(arg1), \XMM0, \XMM0
+ vaesenclast 16*i(arg1), \XMM0, \XMM0
.endm
-#ifdef CONFIG_AS_AVX
-###############################################################################
-# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
-# Input: A and B (128-bits each, bit-reflected)
-# Output: C = A*B*x mod poly, (i.e. >>1 )
-# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
-# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
-###############################################################################
-.macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
+# combined for GCM encrypt and decrypt functions
+# clobbering all xmm registers
+# clobbering r10, r11, r12, r13, r14, r15
+.macro GCM_ENC_DEC INITIAL_BLOCKS GHASH_8_ENCRYPT_8_PARALLEL GHASH_LAST_8 GHASH_MUL ENC_DEC REP
+ vmovdqu AadHash(arg2), %xmm8
+ vmovdqu HashKey(arg2), %xmm13 # xmm13 = HashKey
+ add arg5, InLen(arg2)
- vpshufd $0b01001110, \GH, \T2
- vpshufd $0b01001110, \HK, \T3
- vpxor \GH , \T2, \T2 # T2 = (a1+a0)
- vpxor \HK , \T3, \T3 # T3 = (b1+b0)
+ # initialize the data pointer offset as zero
+ xor %r11d, %r11d
- vpclmulqdq $0x11, \HK, \GH, \T1 # T1 = a1*b1
- vpclmulqdq $0x00, \HK, \GH, \GH # GH = a0*b0
- vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
- vpxor \GH, \T2,\T2
- vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
+ PARTIAL_BLOCK \GHASH_MUL, arg3, arg4, arg5, %r11, %xmm8, \ENC_DEC
+ sub %r11, arg5
- vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
- vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
- vpxor \T3, \GH, \GH
- vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
+ mov arg5, %r13 # save the number of bytes of plaintext/ciphertext
+ and $-16, %r13 # r13 = r13 - (r13 mod 16)
- #first phase of the reduction
- vpslld $31, \GH, \T2 # packed right shifting << 31
- vpslld $30, \GH, \T3 # packed right shifting shift << 30
- vpslld $25, \GH, \T4 # packed right shifting shift << 25
+ mov %r13, %r12
+ shr $4, %r12
+ and $7, %r12
+ jz _initial_num_blocks_is_0\@
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
+ cmp $7, %r12
+ je _initial_num_blocks_is_7\@
+ cmp $6, %r12
+ je _initial_num_blocks_is_6\@
+ cmp $5, %r12
+ je _initial_num_blocks_is_5\@
+ cmp $4, %r12
+ je _initial_num_blocks_is_4\@
+ cmp $3, %r12
+ je _initial_num_blocks_is_3\@
+ cmp $2, %r12
+ je _initial_num_blocks_is_2\@
- vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
+ jmp _initial_num_blocks_is_1\@
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \GH, \GH # first phase of the reduction complete
+_initial_num_blocks_is_7\@:
+ \INITIAL_BLOCKS \REP, 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*7, %r13
+ jmp _initial_blocks_encrypted\@
- #second phase of the reduction
+_initial_num_blocks_is_6\@:
+ \INITIAL_BLOCKS \REP, 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*6, %r13
+ jmp _initial_blocks_encrypted\@
- vpsrld $1,\GH, \T2 # packed left shifting >> 1
- vpsrld $2,\GH, \T3 # packed left shifting >> 2
- vpsrld $7,\GH, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
+_initial_num_blocks_is_5\@:
+ \INITIAL_BLOCKS \REP, 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*5, %r13
+ jmp _initial_blocks_encrypted\@
- vpxor \T5, \T2, \T2
- vpxor \T2, \GH, \GH
- vpxor \T1, \GH, \GH # the result is in GH
+_initial_num_blocks_is_4\@:
+ \INITIAL_BLOCKS \REP, 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*4, %r13
+ jmp _initial_blocks_encrypted\@
+_initial_num_blocks_is_3\@:
+ \INITIAL_BLOCKS \REP, 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*3, %r13
+ jmp _initial_blocks_encrypted\@
-.endm
+_initial_num_blocks_is_2\@:
+ \INITIAL_BLOCKS \REP, 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*2, %r13
+ jmp _initial_blocks_encrypted\@
-.macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
+_initial_num_blocks_is_1\@:
+ \INITIAL_BLOCKS \REP, 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*1, %r13
+ jmp _initial_blocks_encrypted\@
- # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vmovdqa \HK, \T5
+_initial_num_blocks_is_0\@:
+ \INITIAL_BLOCKS \REP, 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_k(arg1)
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
- vmovdqa \T5, HashKey_2(arg1) # [HashKey_2] = HashKey^2<<1 mod poly
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_2_k(arg1)
+_initial_blocks_encrypted\@:
+ cmp $0, %r13
+ je _zero_cipher_left\@
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
- vmovdqa \T5, HashKey_3(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_3_k(arg1)
+ sub $128, %r13
+ je _eight_cipher_left\@
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
- vmovdqa \T5, HashKey_4(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_4_k(arg1)
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
- vmovdqa \T5, HashKey_5(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_5_k(arg1)
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
- vmovdqa \T5, HashKey_6(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_6_k(arg1)
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
- vmovdqa \T5, HashKey_7(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_7_k(arg1)
+ vmovd %xmm9, %r15d
+ and $255, %r15d
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
- vmovdqa \T5, HashKey_8(arg1)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqa \T1, HashKey_8_k(arg1)
-.endm
+_encrypt_by_8_new\@:
+ cmp $(255-8), %r15d
+ jg _encrypt_by_8\@
-## if a = number of total plaintext bytes
-## b = floor(a/16)
-## num_initial_blocks = b mod 4#
-## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
-## r10, r11, r12, rax are clobbered
-## arg1, arg2, arg3, r14 are used as a pointer only, not modified
-.macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
- i = (8-\num_initial_blocks)
- j = 0
- setreg
- mov arg6, %r10 # r10 = AAD
- mov arg7, %r12 # r12 = aadLen
+ add $8, %r15b
+ \GHASH_8_ENCRYPT_8_PARALLEL \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ jmp _eight_cipher_left\@
- mov %r12, %r11
+_encrypt_by_8\@:
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $8, %r15b
+ \GHASH_8_ENCRYPT_8_PARALLEL \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
- vpxor reg_j, reg_j, reg_j
- vpxor reg_i, reg_i, reg_i
- cmp $16, %r11
- jl _get_AAD_rest8\@
-_get_AAD_blocks\@:
- vmovdqu (%r10), reg_i
- vpshufb SHUF_MASK(%rip), reg_i, reg_i
- vpxor reg_i, reg_j, reg_j
- GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6
- add $16, %r10
- sub $16, %r12
- sub $16, %r11
- cmp $16, %r11
- jge _get_AAD_blocks\@
- vmovdqu reg_j, reg_i
- cmp $0, %r11
- je _get_AAD_done\@
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- vpxor reg_i, reg_i, reg_i
- /* read the last <16B of AAD. since we have at least 4B of
- data right after the AAD (the ICV, and maybe some CT), we can
- read 4B/8B blocks safely, and then get rid of the extra stuff */
-_get_AAD_rest8\@:
- cmp $4, %r11
- jle _get_AAD_rest4\@
- movq (%r10), \T1
- add $8, %r10
- sub $8, %r11
- vpslldq $8, \T1, \T1
- vpsrldq $8, reg_i, reg_i
- vpxor \T1, reg_i, reg_i
- jmp _get_AAD_rest8\@
-_get_AAD_rest4\@:
- cmp $0, %r11
- jle _get_AAD_rest0\@
- mov (%r10), %eax
- movq %rax, \T1
- add $4, %r10
- sub $4, %r11
- vpslldq $12, \T1, \T1
- vpsrldq $4, reg_i, reg_i
- vpxor \T1, reg_i, reg_i
-_get_AAD_rest0\@:
- /* finalize: shift out the extra bytes we read, and align
- left. since pslldq can only shift by an immediate, we use
- vpshufb and an array of shuffle masks */
- movq %r12, %r11
- salq $4, %r11
- movdqu aad_shift_arr(%r11), \T1
- vpshufb \T1, reg_i, reg_i
-_get_AAD_rest_final\@:
- vpshufb SHUF_MASK(%rip), reg_i, reg_i
- vpxor reg_j, reg_i, reg_i
- GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6
-_get_AAD_done\@:
- # initialize the data pointer offset as zero
- xor %r11d, %r11d
- # start AES for num_initial_blocks blocks
- mov arg5, %rax # rax = *Y0
- vmovdqu (%rax), \CTR # CTR = Y0
- vpshufb SHUF_MASK(%rip), \CTR, \CTR
+_eight_cipher_left\@:
+ \GHASH_LAST_8 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, reg_i
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
- i = (i+1)
- setreg
-.endr
+_zero_cipher_left\@:
+ vmovdqu %xmm14, AadHash(arg2)
+ vmovdqu %xmm9, CurCount(arg2)
- vmovdqa (arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpxor \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
+ # check for 0 length
+ mov arg5, %r13
+ and $15, %r13 # r13 = (arg5 mod 16)
- j = 1
- setreg
-.rep 9
- vmovdqa 16*j(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenc \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
+ je _multiple_of_16_bytes\@
- j = (j+1)
- setreg
-.endr
+ # handle the last <16 Byte block separately
+ mov %r13, PBlockLen(arg2)
- vmovdqa 16*10(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenclast \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
+ vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
+ vmovdqu %xmm9, CurCount(arg2)
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vmovdqu (arg3, %r11), \T1
- vpxor \T1, reg_i, reg_i
- vmovdqu reg_i, (arg2 , %r11) # write back ciphertext for num_initial_blocks blocks
- add $16, %r11
-.if \ENC_DEC == DEC
- vmovdqa \T1, reg_i
-.endif
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
- i = (i+1)
- setreg
-.endr
+ ENCRYPT_SINGLE_BLOCK \REP, %xmm9 # E(K, Yn)
+ vmovdqu %xmm9, PBlockEncKey(arg2)
+ cmp $16, arg5
+ jge _large_enough_update\@
- i = (8-\num_initial_blocks)
- j = (9-\num_initial_blocks)
- setreg
+ lea (arg4,%r11,1), %r10
+ mov %r13, %r12
-.rep \num_initial_blocks
- vpxor reg_i, reg_j, reg_j
- GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- # XMM8 has the combined result here
+ READ_PARTIAL_BLOCK %r10 %r12 %xmm1
- vmovdqa \XMM8, TMP1(%rsp)
- vmovdqa \XMM8, \T3
+ lea SHIFT_MASK+16(%rip), %r12
+ sub %r13, %r12 # adjust the shuffle mask pointer to be
+ # able to shift 16-r13 bytes (r13 is the
+ # number of bytes in plaintext mod 16)
- cmp $128, %r13
- jl _initial_blocks_done\@ # no need for precomputed constants
+ jmp _final_ghash_mul\@
-###############################################################################
-# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM1
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+_large_enough_update\@:
+ sub $16, %r11
+ add %r13, %r11
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM2
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ # receive the last <16 Byte block
+ vmovdqu (arg4, %r11, 1), %xmm1
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM3
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ sub %r13, %r11
+ add $16, %r11
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM4
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ lea SHIFT_MASK+16(%rip), %r12
+ # adjust the shuffle mask pointer to be able to shift 16-r13 bytes
+ # (r13 is the number of bytes in plaintext mod 16)
+ sub %r13, %r12
+ # get the appropriate shuffle mask
+ vmovdqu (%r12), %xmm2
+ # shift right 16-r13 bytes
+ vpshufb %xmm2, %xmm1, %xmm1
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM5
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+_final_ghash_mul\@:
+ .if \ENC_DEC == DEC
+ vmovdqa %xmm1, %xmm2
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
+ # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm2, %xmm2
+ vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm14, %xmm14
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM6
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vmovdqu %xmm14, AadHash(arg2)
+ .else
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
+ # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ vpxor %xmm9, %xmm14, %xmm14
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM7
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vmovdqu %xmm14, AadHash(arg2)
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
+ .endif
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM8
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
- vmovdqa (arg1), \T_key
- vpxor \T_key, \XMM1, \XMM1
- vpxor \T_key, \XMM2, \XMM2
- vpxor \T_key, \XMM3, \XMM3
- vpxor \T_key, \XMM4, \XMM4
- vpxor \T_key, \XMM5, \XMM5
- vpxor \T_key, \XMM6, \XMM6
- vpxor \T_key, \XMM7, \XMM7
- vpxor \T_key, \XMM8, \XMM8
+ #############################
+ # output r13 Bytes
+ vmovq %xmm9, %rax
+ cmp $8, %r13
+ jle _less_than_8_bytes_left\@
- i = 1
- setreg
-.rep 9 # do 9 rounds
- vmovdqa 16*i(arg1), \T_key
- vaesenc \T_key, \XMM1, \XMM1
- vaesenc \T_key, \XMM2, \XMM2
- vaesenc \T_key, \XMM3, \XMM3
- vaesenc \T_key, \XMM4, \XMM4
- vaesenc \T_key, \XMM5, \XMM5
- vaesenc \T_key, \XMM6, \XMM6
- vaesenc \T_key, \XMM7, \XMM7
- vaesenc \T_key, \XMM8, \XMM8
- i = (i+1)
- setreg
-.endr
+ mov %rax, (arg3 , %r11)
+ add $8, %r11
+ vpsrldq $8, %xmm9, %xmm9
+ vmovq %xmm9, %rax
+ sub $8, %r13
+_less_than_8_bytes_left\@:
+ movb %al, (arg3 , %r11)
+ add $1, %r11
+ shr $8, %rax
+ sub $1, %r13
+ jne _less_than_8_bytes_left\@
+ #############################
- vmovdqa 16*i(arg1), \T_key
- vaesenclast \T_key, \XMM1, \XMM1
- vaesenclast \T_key, \XMM2, \XMM2
- vaesenclast \T_key, \XMM3, \XMM3
- vaesenclast \T_key, \XMM4, \XMM4
- vaesenclast \T_key, \XMM5, \XMM5
- vaesenclast \T_key, \XMM6, \XMM6
- vaesenclast \T_key, \XMM7, \XMM7
- vaesenclast \T_key, \XMM8, \XMM8
+_multiple_of_16_bytes\@:
+.endm
- vmovdqu (arg3, %r11), \T1
- vpxor \T1, \XMM1, \XMM1
- vmovdqu \XMM1, (arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM1
- .endif
- vmovdqu 16*1(arg3, %r11), \T1
- vpxor \T1, \XMM2, \XMM2
- vmovdqu \XMM2, 16*1(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM2
- .endif
+# GCM_COMPLETE Finishes update of tag of last partial block
+# Output: Authorization Tag (AUTH_TAG)
+# Clobbers rax, r10-r12, and xmm0, xmm1, xmm5-xmm15
+.macro GCM_COMPLETE GHASH_MUL REP AUTH_TAG AUTH_TAG_LEN
+ vmovdqu AadHash(arg2), %xmm14
+ vmovdqu HashKey(arg2), %xmm13
- vmovdqu 16*2(arg3, %r11), \T1
- vpxor \T1, \XMM3, \XMM3
- vmovdqu \XMM3, 16*2(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM3
- .endif
+ mov PBlockLen(arg2), %r12
+ cmp $0, %r12
+ je _partial_done\@
- vmovdqu 16*3(arg3, %r11), \T1
- vpxor \T1, \XMM4, \XMM4
- vmovdqu \XMM4, 16*3(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM4
- .endif
+ #GHASH computation for the last <16 Byte block
+ \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- vmovdqu 16*4(arg3, %r11), \T1
- vpxor \T1, \XMM5, \XMM5
- vmovdqu \XMM5, 16*4(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM5
- .endif
+_partial_done\@:
+ mov AadLen(arg2), %r12 # r12 = aadLen (number of bytes)
+ shl $3, %r12 # convert into number of bits
+ vmovd %r12d, %xmm15 # len(A) in xmm15
- vmovdqu 16*5(arg3, %r11), \T1
- vpxor \T1, \XMM6, \XMM6
- vmovdqu \XMM6, 16*5(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM6
- .endif
+ mov InLen(arg2), %r12
+ shl $3, %r12 # len(C) in bits (*128)
+ vmovq %r12, %xmm1
+ vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
+ vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
- vmovdqu 16*6(arg3, %r11), \T1
- vpxor \T1, \XMM7, \XMM7
- vmovdqu \XMM7, 16*6(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM7
- .endif
+ vpxor %xmm15, %xmm14, %xmm14
+ \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
+ vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
- vmovdqu 16*7(arg3, %r11), \T1
- vpxor \T1, \XMM8, \XMM8
- vmovdqu \XMM8, 16*7(arg2 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM8
- .endif
+ vmovdqu OrigIV(arg2), %xmm9
- add $128, %r11
+ ENCRYPT_SINGLE_BLOCK \REP, %xmm9 # E(K, Y0)
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with the corresponding ciphertext
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+ vpxor %xmm14, %xmm9, %xmm9
-###############################################################################
-_initial_blocks_done\@:
-.endm
+_return_T\@:
+ mov \AUTH_TAG, %r10 # r10 = authTag
+ mov \AUTH_TAG_LEN, %r11 # r11 = auth_tag_len
-# encrypt 8 blocks at a time
-# ghash the 8 previously encrypted ciphertext blocks
-# arg1, arg2, arg3 are used as pointers only, not modified
-# r11 is the data offset value
-.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
+ cmp $16, %r11
+ je _T_16\@
- vmovdqa \XMM1, \T2
- vmovdqa \XMM2, TMP2(%rsp)
- vmovdqa \XMM3, TMP3(%rsp)
- vmovdqa \XMM4, TMP4(%rsp)
- vmovdqa \XMM5, TMP5(%rsp)
- vmovdqa \XMM6, TMP6(%rsp)
- vmovdqa \XMM7, TMP7(%rsp)
- vmovdqa \XMM8, TMP8(%rsp)
+ cmp $8, %r11
+ jl _T_4\@
-.if \loop_idx == in_order
- vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONE(%rip), \XMM1, \XMM2
- vpaddd ONE(%rip), \XMM2, \XMM3
- vpaddd ONE(%rip), \XMM3, \XMM4
- vpaddd ONE(%rip), \XMM4, \XMM5
- vpaddd ONE(%rip), \XMM5, \XMM6
- vpaddd ONE(%rip), \XMM6, \XMM7
- vpaddd ONE(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
+_T_8\@:
+ vmovq %xmm9, %rax
+ mov %rax, (%r10)
+ add $8, %r10
+ sub $8, %r11
+ vpsrldq $8, %xmm9, %xmm9
+ cmp $0, %r11
+ je _return_T_done\@
+_T_4\@:
+ vmovd %xmm9, %eax
+ mov %eax, (%r10)
+ add $4, %r10
+ sub $4, %r11
+ vpsrldq $4, %xmm9, %xmm9
+ cmp $0, %r11
+ je _return_T_done\@
+_T_123\@:
+ vmovd %xmm9, %eax
+ cmp $2, %r11
+ jl _T_1\@
+ mov %ax, (%r10)
+ cmp $2, %r11
+ je _return_T_done\@
+ add $2, %r10
+ sar $16, %eax
+_T_1\@:
+ mov %al, (%r10)
+ jmp _return_T_done\@
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-.else
- vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONEf(%rip), \XMM1, \XMM2
- vpaddd ONEf(%rip), \XMM2, \XMM3
- vpaddd ONEf(%rip), \XMM3, \XMM4
- vpaddd ONEf(%rip), \XMM4, \XMM5
- vpaddd ONEf(%rip), \XMM5, \XMM6
- vpaddd ONEf(%rip), \XMM6, \XMM7
- vpaddd ONEf(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
-.endif
+_T_16\@:
+ vmovdqu %xmm9, (%r10)
+_return_T_done\@:
+.endm
- #######################################################################
-
- vmovdqu (arg1), \T1
- vpxor \T1, \XMM1, \XMM1
- vpxor \T1, \XMM2, \XMM2
- vpxor \T1, \XMM3, \XMM3
- vpxor \T1, \XMM4, \XMM4
- vpxor \T1, \XMM5, \XMM5
- vpxor \T1, \XMM6, \XMM6
- vpxor \T1, \XMM7, \XMM7
- vpxor \T1, \XMM8, \XMM8
-
- #######################################################################
-
+.macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
+ mov \AAD, %r10 # r10 = AAD
+ mov \AADLEN, %r12 # r12 = aadLen
+ mov %r12, %r11
- vmovdqu 16*1(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
+ vpxor \T8, \T8, \T8
+ vpxor \T7, \T7, \T7
+ cmp $16, %r11
+ jl _get_AAD_rest8\@
+_get_AAD_blocks\@:
+ vmovdqu (%r10), \T7
+ vpshufb SHUF_MASK(%rip), \T7, \T7
+ vpxor \T7, \T8, \T8
+ \GHASH_MUL \T8, \T2, \T1, \T3, \T4, \T5, \T6
+ add $16, %r10
+ sub $16, %r12
+ sub $16, %r11
+ cmp $16, %r11
+ jge _get_AAD_blocks\@
+ vmovdqu \T8, \T7
+ cmp $0, %r11
+ je _get_AAD_done\@
- vmovdqu 16*2(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
+ vpxor \T7, \T7, \T7
+ /* read the last <16B of AAD. since we have at least 4B of
+ data right after the AAD (the ICV, and maybe some CT), we can
+ read 4B/8B blocks safely, and then get rid of the extra stuff */
+_get_AAD_rest8\@:
+ cmp $4, %r11
+ jle _get_AAD_rest4\@
+ movq (%r10), \T1
+ add $8, %r10
+ sub $8, %r11
+ vpslldq $8, \T1, \T1
+ vpsrldq $8, \T7, \T7
+ vpxor \T1, \T7, \T7
+ jmp _get_AAD_rest8\@
+_get_AAD_rest4\@:
+ cmp $0, %r11
+ jle _get_AAD_rest0\@
+ mov (%r10), %eax
+ movq %rax, \T1
+ add $4, %r10
+ sub $4, %r11
+ vpslldq $12, \T1, \T1
+ vpsrldq $4, \T7, \T7
+ vpxor \T1, \T7, \T7
+_get_AAD_rest0\@:
+ /* finalize: shift out the extra bytes we read, and align
+ left. since pslldq can only shift by an immediate, we use
+ vpshufb and an array of shuffle masks */
+ movq %r12, %r11
+ salq $4, %r11
+ vmovdqu aad_shift_arr(%r11), \T1
+ vpshufb \T1, \T7, \T7
+_get_AAD_rest_final\@:
+ vpshufb SHUF_MASK(%rip), \T7, \T7
+ vpxor \T8, \T7, \T7
+ \GHASH_MUL \T7, \T2, \T1, \T3, \T4, \T5, \T6
- #######################################################################
+_get_AAD_done\@:
+ vmovdqu \T7, AadHash(arg2)
+.endm
- vmovdqa HashKey_8(arg1), \T5
- vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
- vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
+.macro INIT GHASH_MUL PRECOMPUTE
+ mov arg6, %r11
+ mov %r11, AadLen(arg2) # ctx_data.aad_length = aad_length
+ xor %r11d, %r11d
+ mov %r11, InLen(arg2) # ctx_data.in_length = 0
- vpshufd $0b01001110, \T2, \T6
- vpxor \T2, \T6, \T6
+ mov %r11, PBlockLen(arg2) # ctx_data.partial_block_length = 0
+ mov %r11, PBlockEncKey(arg2) # ctx_data.partial_block_enc_key = 0
+ mov arg3, %rax
+ movdqu (%rax), %xmm0
+ movdqu %xmm0, OrigIV(arg2) # ctx_data.orig_IV = iv
- vmovdqa HashKey_8_k(arg1), \T5
- vpclmulqdq $0x00, \T5, \T6, \T6
+ vpshufb SHUF_MASK(%rip), %xmm0, %xmm0
+ movdqu %xmm0, CurCount(arg2) # ctx_data.current_counter = iv
- vmovdqu 16*3(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP2(%rsp), \T1
- vmovdqa HashKey_7(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_7_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*4(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
+ vmovdqu (arg4), %xmm6 # xmm6 = HashKey
+ vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
+ ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
+ vmovdqa %xmm6, %xmm2
+ vpsllq $1, %xmm6, %xmm6
+ vpsrlq $63, %xmm2, %xmm2
+ vmovdqa %xmm2, %xmm1
+ vpslldq $8, %xmm2, %xmm2
+ vpsrldq $8, %xmm1, %xmm1
+ vpor %xmm2, %xmm6, %xmm6
+ #reduction
+ vpshufd $0b00100100, %xmm1, %xmm2
+ vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
+ vpand POLY(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
#######################################################################
+ vmovdqu %xmm6, HashKey(arg2) # store HashKey<<1 mod poly
- vmovdqa TMP3(%rsp), \T1
- vmovdqa HashKey_6(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_6_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*5(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP4(%rsp), \T1
- vmovdqa HashKey_5(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_5_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*6(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- vmovdqa TMP5(%rsp), \T1
- vmovdqa HashKey_4(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_4_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
+ CALC_AAD_HASH \GHASH_MUL, arg5, arg6, %xmm2, %xmm6, %xmm3, %xmm4, %xmm5, %xmm7, %xmm1, %xmm0
- vmovdqu 16*7(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP6(%rsp), \T1
- vmovdqa HashKey_3(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_3_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
+ \PRECOMPUTE %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
+.endm
- vmovdqu 16*8(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
+# Reads DLEN bytes starting at DPTR and stores in XMMDst
+# where 0 < DLEN < 16
+# Clobbers %rax, DLEN
+.macro READ_PARTIAL_BLOCK DPTR DLEN XMMDst
+ vpxor \XMMDst, \XMMDst, \XMMDst
+
+ cmp $8, \DLEN
+ jl _read_lt8_\@
+ mov (\DPTR), %rax
+ vpinsrq $0, %rax, \XMMDst, \XMMDst
+ sub $8, \DLEN
+ jz _done_read_partial_block_\@
+ xor %eax, %eax
+_read_next_byte_\@:
+ shl $8, %rax
+ mov 7(\DPTR, \DLEN, 1), %al
+ dec \DLEN
+ jnz _read_next_byte_\@
+ vpinsrq $1, %rax, \XMMDst, \XMMDst
+ jmp _done_read_partial_block_\@
+_read_lt8_\@:
+ xor %eax, %eax
+_read_next_byte_lt8_\@:
+ shl $8, %rax
+ mov -1(\DPTR, \DLEN, 1), %al
+ dec \DLEN
+ jnz _read_next_byte_lt8_\@
+ vpinsrq $0, %rax, \XMMDst, \XMMDst
+_done_read_partial_block_\@:
+.endm
- vmovdqa TMP7(%rsp), \T1
- vmovdqa HashKey_2(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
+# PARTIAL_BLOCK: Handles encryption/decryption and the tag partial blocks
+# between update calls.
+# Requires the input data be at least 1 byte long due to READ_PARTIAL_BLOCK
+# Outputs encrypted bytes, and updates hash and partial info in gcm_data_context
+# Clobbers rax, r10, r12, r13, xmm0-6, xmm9-13
+.macro PARTIAL_BLOCK GHASH_MUL CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
+ AAD_HASH ENC_DEC
+ mov PBlockLen(arg2), %r13
+ cmp $0, %r13
+ je _partial_block_done_\@ # Leave Macro if no partial blocks
+ # Read in input data without over reading
+ cmp $16, \PLAIN_CYPH_LEN
+ jl _fewer_than_16_bytes_\@
+ vmovdqu (\PLAIN_CYPH_IN), %xmm1 # If more than 16 bytes, just fill xmm
+ jmp _data_read_\@
+
+_fewer_than_16_bytes_\@:
+ lea (\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
+ mov \PLAIN_CYPH_LEN, %r12
+ READ_PARTIAL_BLOCK %r10 %r12 %xmm1
+
+ mov PBlockLen(arg2), %r13
+
+_data_read_\@: # Finished reading in data
+
+ vmovdqu PBlockEncKey(arg2), %xmm9
+ vmovdqu HashKey(arg2), %xmm13
+
+ lea SHIFT_MASK(%rip), %r12
+
+ # adjust the shuffle mask pointer to be able to shift r13 bytes
+ # r16-r13 is the number of bytes in plaintext mod 16)
+ add %r13, %r12
+ vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
+ vpshufb %xmm2, %xmm9, %xmm9 # shift right r13 bytes
+
+.if \ENC_DEC == DEC
+ vmovdqa %xmm1, %xmm3
+ pxor %xmm1, %xmm9 # Cyphertext XOR E(K, Yn)
+
+ mov \PLAIN_CYPH_LEN, %r10
+ add %r13, %r10
+ # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
+ sub $16, %r10
+ # Determine if if partial block is not being filled and
+ # shift mask accordingly
+ jge _no_extra_mask_1_\@
+ sub %r10, %r12
+_no_extra_mask_1_\@:
+
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1
+ # get the appropriate mask to mask out bottom r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out bottom r13 bytes of xmm9
+
+ vpand %xmm1, %xmm3, %xmm3
+ vmovdqa SHUF_MASK(%rip), %xmm10
+ vpshufb %xmm10, %xmm3, %xmm3
+ vpshufb %xmm2, %xmm3, %xmm3
+ vpxor %xmm3, \AAD_HASH, \AAD_HASH
+
+ cmp $0, %r10
+ jl _partial_incomplete_1_\@
+
+ # GHASH computation for the last <16 Byte block
+ \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ xor %eax,%eax
+
+ mov %rax, PBlockLen(arg2)
+ jmp _dec_done_\@
+_partial_incomplete_1_\@:
+ add \PLAIN_CYPH_LEN, PBlockLen(arg2)
+_dec_done_\@:
+ vmovdqu \AAD_HASH, AadHash(arg2)
+.else
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+
+ mov \PLAIN_CYPH_LEN, %r10
+ add %r13, %r10
+ # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
+ sub $16, %r10
+ # Determine if if partial block is not being filled and
+ # shift mask accordingly
+ jge _no_extra_mask_2_\@
+ sub %r10, %r12
+_no_extra_mask_2_\@:
+
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1
+ # get the appropriate mask to mask out bottom r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9
+
+ vmovdqa SHUF_MASK(%rip), %xmm1
+ vpshufb %xmm1, %xmm9, %xmm9
+ vpshufb %xmm2, %xmm9, %xmm9
+ vpxor %xmm9, \AAD_HASH, \AAD_HASH
+
+ cmp $0, %r10
+ jl _partial_incomplete_2_\@
+
+ # GHASH computation for the last <16 Byte block
+ \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ xor %eax,%eax
+
+ mov %rax, PBlockLen(arg2)
+ jmp _encode_done_\@
+_partial_incomplete_2_\@:
+ add \PLAIN_CYPH_LEN, PBlockLen(arg2)
+_encode_done_\@:
+ vmovdqu \AAD_HASH, AadHash(arg2)
+
+ vmovdqa SHUF_MASK(%rip), %xmm10
+ # shuffle xmm9 back to output as ciphertext
+ vpshufb %xmm10, %xmm9, %xmm9
+ vpshufb %xmm2, %xmm9, %xmm9
+.endif
+ # output encrypted Bytes
+ cmp $0, %r10
+ jl _partial_fill_\@
+ mov %r13, %r12
+ mov $16, %r13
+ # Set r13 to be the number of bytes to write out
+ sub %r12, %r13
+ jmp _count_set_\@
+_partial_fill_\@:
+ mov \PLAIN_CYPH_LEN, %r13
+_count_set_\@:
+ vmovdqa %xmm9, %xmm0
+ vmovq %xmm0, %rax
+ cmp $8, %r13
+ jle _less_than_8_bytes_left_\@
+
+ mov %rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
+ add $8, \DATA_OFFSET
+ psrldq $8, %xmm0
+ vmovq %xmm0, %rax
+ sub $8, %r13
+_less_than_8_bytes_left_\@:
+ movb %al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
+ add $1, \DATA_OFFSET
+ shr $8, %rax
+ sub $1, %r13
+ jne _less_than_8_bytes_left_\@
+_partial_block_done_\@:
+.endm # PARTIAL_BLOCK
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_2_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
+#ifdef CONFIG_AS_AVX
+###############################################################################
+# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
+# Input: A and B (128-bits each, bit-reflected)
+# Output: C = A*B*x mod poly, (i.e. >>1 )
+# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
+# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
+###############################################################################
+.macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
- #######################################################################
+ vpshufd $0b01001110, \GH, \T2
+ vpshufd $0b01001110, \HK, \T3
+ vpxor \GH , \T2, \T2 # T2 = (a1+a0)
+ vpxor \HK , \T3, \T3 # T3 = (b1+b0)
- vmovdqu 16*9(arg1), \T5
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
+ vpclmulqdq $0x11, \HK, \GH, \T1 # T1 = a1*b1
+ vpclmulqdq $0x00, \HK, \GH, \GH # GH = a0*b0
+ vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
+ vpxor \GH, \T2,\T2
+ vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
- vmovdqa TMP8(%rsp), \T1
- vmovdqa HashKey(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
+ vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
+ vpxor \T3, \GH, \GH
+ vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqa HashKey_k(arg1), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
+ #first phase of the reduction
+ vpslld $31, \GH, \T2 # packed right shifting << 31
+ vpslld $30, \GH, \T3 # packed right shifting shift << 30
+ vpslld $25, \GH, \T4 # packed right shifting shift << 25
- vpxor \T4, \T6, \T6
- vpxor \T7, \T6, \T6
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
- vmovdqu 16*10(arg1), \T5
+ vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
- i = 0
- j = 1
- setreg
-.rep 8
- vpxor 16*i(arg3, %r11), \T5, \T2
- .if \ENC_DEC == ENC
- vaesenclast \T2, reg_j, reg_j
- .else
- vaesenclast \T2, reg_j, \T3
- vmovdqu 16*i(arg3, %r11), reg_j
- vmovdqu \T3, 16*i(arg2, %r11)
- .endif
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- #######################################################################
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \GH, \GH # first phase of the reduction complete
+ #second phase of the reduction
- vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
- vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
- vpxor \T3, \T7, \T7
- vpxor \T4, \T6, \T6 # accumulate the results in T6:T7
+ vpsrld $1,\GH, \T2 # packed left shifting >> 1
+ vpsrld $2,\GH, \T3 # packed left shifting >> 2
+ vpsrld $7,\GH, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+ vpxor \T5, \T2, \T2
+ vpxor \T2, \GH, \GH
+ vpxor \T1, \GH, \GH # the result is in GH
- #######################################################################
- #first phase of the reduction
- #######################################################################
- vpslld $31, \T7, \T2 # packed right shifting << 31
- vpslld $30, \T7, \T3 # packed right shifting shift << 30
- vpslld $25, \T7, \T4 # packed right shifting shift << 25
+.endm
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
+.macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
- vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
+ # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vmovdqa \HK, \T5
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
- .if \ENC_DEC == ENC
- vmovdqu \XMM1, 16*0(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM2, 16*1(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM3, 16*2(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM4, 16*3(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM5, 16*4(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM6, 16*5(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM7, 16*6(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM8, 16*7(arg2,%r11) # Write to the Ciphertext buffer
- .endif
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_k(arg2)
- #######################################################################
- #second phase of the reduction
- vpsrld $1, \T7, \T2 # packed left shifting >> 1
- vpsrld $2, \T7, \T3 # packed left shifting >> 2
- vpsrld $7, \T7, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
+ vmovdqu \T5, HashKey_2(arg2) # [HashKey_2] = HashKey^2<<1 mod poly
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_2_k(arg2)
- vpxor \T1, \T2, \T2
- vpxor \T2, \T7, \T7
- vpxor \T7, \T6, \T6 # the result is in T6
- #######################################################################
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
+ vmovdqu \T5, HashKey_3(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_3_k(arg2)
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
+ vmovdqu \T5, HashKey_4(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_4_k(arg2)
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
+ vmovdqu \T5, HashKey_5(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_5_k(arg2)
- vpxor \T6, \XMM1, \XMM1
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
+ vmovdqu \T5, HashKey_6(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_6_k(arg2)
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
+ vmovdqu \T5, HashKey_7(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_7_k(arg2)
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
+ vmovdqu \T5, HashKey_8(arg2)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqu \T1, HashKey_8_k(arg2)
.endm
+## if a = number of total plaintext bytes
+## b = floor(a/16)
+## num_initial_blocks = b mod 4#
+## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
+## r10, r11, r12, rax are clobbered
+## arg1, arg3, arg4, r14 are used as a pointer only, not modified
-# GHASH the last 4 ciphertext blocks.
-.macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
+.macro INITIAL_BLOCKS_AVX REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
+ i = (8-\num_initial_blocks)
+ setreg
+ vmovdqu AadHash(arg2), reg_i
- ## Karatsuba Method
+ # start AES for num_initial_blocks blocks
+ vmovdqu CurCount(arg2), \CTR
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, reg_i
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
+ i = (i+1)
+ setreg
+.endr
- vpshufd $0b01001110, \XMM1, \T2
- vpxor \XMM1, \T2, \T2
- vmovdqa HashKey_8(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM1, \T6
- vpclmulqdq $0x00, \T5, \XMM1, \T7
+ vmovdqa (arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpxor \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
- vmovdqa HashKey_8_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \XMM1
+ j = 1
+ setreg
+.rep \REP
+ vmovdqa 16*j(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenc \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
- ######################
+ j = (j+1)
+ setreg
+.endr
- vpshufd $0b01001110, \XMM2, \T2
- vpxor \XMM2, \T2, \T2
- vmovdqa HashKey_7(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM2, \T4
- vpxor \T4, \T6, \T6
+ vmovdqa 16*j(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenclast \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
- vpclmulqdq $0x00, \T5, \XMM2, \T4
- vpxor \T4, \T7, \T7
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vmovdqu (arg4, %r11), \T1
+ vpxor \T1, reg_i, reg_i
+ vmovdqu reg_i, (arg3 , %r11) # write back ciphertext for num_initial_blocks blocks
+ add $16, %r11
+.if \ENC_DEC == DEC
+ vmovdqa \T1, reg_i
+.endif
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
+ i = (i+1)
+ setreg
+.endr
- vmovdqa HashKey_7_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
- ######################
+ i = (8-\num_initial_blocks)
+ j = (9-\num_initial_blocks)
+ setreg
- vpshufd $0b01001110, \XMM3, \T2
- vpxor \XMM3, \T2, \T2
- vmovdqa HashKey_6(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM3, \T4
- vpxor \T4, \T6, \T6
+.rep \num_initial_blocks
+ vpxor reg_i, reg_j, reg_j
+ GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ # XMM8 has the combined result here
- vpclmulqdq $0x00, \T5, \XMM3, \T4
- vpxor \T4, \T7, \T7
+ vmovdqa \XMM8, TMP1(%rsp)
+ vmovdqa \XMM8, \T3
- vmovdqa HashKey_6_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
+ cmp $128, %r13
+ jl _initial_blocks_done\@ # no need for precomputed constants
- ######################
+###############################################################################
+# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM1
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufd $0b01001110, \XMM4, \T2
- vpxor \XMM4, \T2, \T2
- vmovdqa HashKey_5(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM4, \T4
- vpxor \T4, \T6, \T6
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM2
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpclmulqdq $0x00, \T5, \XMM4, \T4
- vpxor \T4, \T7, \T7
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM3
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vmovdqa HashKey_5_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM4
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- ######################
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM5
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufd $0b01001110, \XMM5, \T2
- vpxor \XMM5, \T2, \T2
- vmovdqa HashKey_4(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM5, \T4
- vpxor \T4, \T6, \T6
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM6
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpclmulqdq $0x00, \T5, \XMM5, \T4
- vpxor \T4, \T7, \T7
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM7
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vmovdqa HashKey_4_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM8
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
- ######################
+ vmovdqa (arg1), \T_key
+ vpxor \T_key, \XMM1, \XMM1
+ vpxor \T_key, \XMM2, \XMM2
+ vpxor \T_key, \XMM3, \XMM3
+ vpxor \T_key, \XMM4, \XMM4
+ vpxor \T_key, \XMM5, \XMM5
+ vpxor \T_key, \XMM6, \XMM6
+ vpxor \T_key, \XMM7, \XMM7
+ vpxor \T_key, \XMM8, \XMM8
- vpshufd $0b01001110, \XMM6, \T2
- vpxor \XMM6, \T2, \T2
- vmovdqa HashKey_3(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM6, \T4
- vpxor \T4, \T6, \T6
+ i = 1
+ setreg
+.rep \REP # do REP rounds
+ vmovdqa 16*i(arg1), \T_key
+ vaesenc \T_key, \XMM1, \XMM1
+ vaesenc \T_key, \XMM2, \XMM2
+ vaesenc \T_key, \XMM3, \XMM3
+ vaesenc \T_key, \XMM4, \XMM4
+ vaesenc \T_key, \XMM5, \XMM5
+ vaesenc \T_key, \XMM6, \XMM6
+ vaesenc \T_key, \XMM7, \XMM7
+ vaesenc \T_key, \XMM8, \XMM8
+ i = (i+1)
+ setreg
+.endr
- vpclmulqdq $0x00, \T5, \XMM6, \T4
- vpxor \T4, \T7, \T7
+ vmovdqa 16*i(arg1), \T_key
+ vaesenclast \T_key, \XMM1, \XMM1
+ vaesenclast \T_key, \XMM2, \XMM2
+ vaesenclast \T_key, \XMM3, \XMM3
+ vaesenclast \T_key, \XMM4, \XMM4
+ vaesenclast \T_key, \XMM5, \XMM5
+ vaesenclast \T_key, \XMM6, \XMM6
+ vaesenclast \T_key, \XMM7, \XMM7
+ vaesenclast \T_key, \XMM8, \XMM8
- vmovdqa HashKey_3_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
+ vmovdqu (arg4, %r11), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vmovdqu \XMM1, (arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM1
+ .endif
- ######################
+ vmovdqu 16*1(arg4, %r11), \T1
+ vpxor \T1, \XMM2, \XMM2
+ vmovdqu \XMM2, 16*1(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM2
+ .endif
- vpshufd $0b01001110, \XMM7, \T2
- vpxor \XMM7, \T2, \T2
- vmovdqa HashKey_2(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM7, \T4
- vpxor \T4, \T6, \T6
+ vmovdqu 16*2(arg4, %r11), \T1
+ vpxor \T1, \XMM3, \XMM3
+ vmovdqu \XMM3, 16*2(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM3
+ .endif
- vpclmulqdq $0x00, \T5, \XMM7, \T4
- vpxor \T4, \T7, \T7
+ vmovdqu 16*3(arg4, %r11), \T1
+ vpxor \T1, \XMM4, \XMM4
+ vmovdqu \XMM4, 16*3(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM4
+ .endif
- vmovdqa HashKey_2_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
+ vmovdqu 16*4(arg4, %r11), \T1
+ vpxor \T1, \XMM5, \XMM5
+ vmovdqu \XMM5, 16*4(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM5
+ .endif
- ######################
+ vmovdqu 16*5(arg4, %r11), \T1
+ vpxor \T1, \XMM6, \XMM6
+ vmovdqu \XMM6, 16*5(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM6
+ .endif
- vpshufd $0b01001110, \XMM8, \T2
- vpxor \XMM8, \T2, \T2
- vmovdqa HashKey(arg1), \T5
- vpclmulqdq $0x11, \T5, \XMM8, \T4
- vpxor \T4, \T6, \T6
+ vmovdqu 16*6(arg4, %r11), \T1
+ vpxor \T1, \XMM7, \XMM7
+ vmovdqu \XMM7, 16*6(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM7
+ .endif
+
+ vmovdqu 16*7(arg4, %r11), \T1
+ vpxor \T1, \XMM8, \XMM8
+ vmovdqu \XMM8, 16*7(arg3 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM8
+ .endif
+
+ add $128, %r11
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with the corresponding ciphertext
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
- vpclmulqdq $0x00, \T5, \XMM8, \T4
- vpxor \T4, \T7, \T7
+###############################################################################
- vmovdqa HashKey_k(arg1), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
+_initial_blocks_done\@:
- vpxor \T2, \XMM1, \XMM1
- vpxor \T6, \XMM1, \XMM1
- vpxor \T7, \XMM1, \T2
+.endm
+# encrypt 8 blocks at a time
+# ghash the 8 previously encrypted ciphertext blocks
+# arg1, arg3, arg4 are used as pointers only, not modified
+# r11 is the data offset value
+.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
+ vmovdqa \XMM1, \T2
+ vmovdqa \XMM2, TMP2(%rsp)
+ vmovdqa \XMM3, TMP3(%rsp)
+ vmovdqa \XMM4, TMP4(%rsp)
+ vmovdqa \XMM5, TMP5(%rsp)
+ vmovdqa \XMM6, TMP6(%rsp)
+ vmovdqa \XMM7, TMP7(%rsp)
+ vmovdqa \XMM8, TMP8(%rsp)
+.if \loop_idx == in_order
+ vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONE(%rip), \XMM1, \XMM2
+ vpaddd ONE(%rip), \XMM2, \XMM3
+ vpaddd ONE(%rip), \XMM3, \XMM4
+ vpaddd ONE(%rip), \XMM4, \XMM5
+ vpaddd ONE(%rip), \XMM5, \XMM6
+ vpaddd ONE(%rip), \XMM6, \XMM7
+ vpaddd ONE(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
- vpslldq $8, \T2, \T4
- vpsrldq $8, \T2, \T2
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+.else
+ vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONEf(%rip), \XMM1, \XMM2
+ vpaddd ONEf(%rip), \XMM2, \XMM3
+ vpaddd ONEf(%rip), \XMM3, \XMM4
+ vpaddd ONEf(%rip), \XMM4, \XMM5
+ vpaddd ONEf(%rip), \XMM5, \XMM6
+ vpaddd ONEf(%rip), \XMM6, \XMM7
+ vpaddd ONEf(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
+.endif
- vpxor \T4, \T7, \T7
- vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
- # the accumulated carry-less multiplications
#######################################################################
- #first phase of the reduction
- vpslld $31, \T7, \T2 # packed right shifting << 31
- vpslld $30, \T7, \T3 # packed right shifting shift << 30
- vpslld $25, \T7, \T4 # packed right shifting shift << 25
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
+ vmovdqu (arg1), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vpxor \T1, \XMM2, \XMM2
+ vpxor \T1, \XMM3, \XMM3
+ vpxor \T1, \XMM4, \XMM4
+ vpxor \T1, \XMM5, \XMM5
+ vpxor \T1, \XMM6, \XMM6
+ vpxor \T1, \XMM7, \XMM7
+ vpxor \T1, \XMM8, \XMM8
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
#######################################################################
- #second phase of the reduction
- vpsrld $1, \T7, \T2 # packed left shifting >> 1
- vpsrld $2, \T7, \T3 # packed left shifting >> 2
- vpsrld $7, \T7, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
- vpxor \T1, \T2, \T2
- vpxor \T2, \T7, \T7
- vpxor \T7, \T6, \T6 # the result is in T6
-.endm
+ vmovdqu 16*1(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
-# combined for GCM encrypt and decrypt functions
-# clobbering all xmm registers
-# clobbering r10, r11, r12, r13, r14, r15
-.macro GCM_ENC_DEC_AVX ENC_DEC
+ vmovdqu 16*2(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
- #the number of pushes must equal STACK_OFFSET
- push %r12
- push %r13
- push %r14
- push %r15
- mov %rsp, %r14
+ #######################################################################
+ vmovdqu HashKey_8(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
+ vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
+ vpshufd $0b01001110, \T2, \T6
+ vpxor \T2, \T6, \T6
+ vmovdqu HashKey_8_k(arg2), \T5
+ vpclmulqdq $0x00, \T5, \T6, \T6
- sub $VARIABLE_OFFSET, %rsp
- and $~63, %rsp # align rsp to 64 bytes
+ vmovdqu 16*3(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+ vmovdqa TMP2(%rsp), \T1
+ vmovdqu HashKey_7(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
- vmovdqu HashKey(arg1), %xmm13 # xmm13 = HashKey
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_7_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
- mov arg4, %r13 # save the number of bytes of plaintext/ciphertext
- and $-16, %r13 # r13 = r13 - (r13 mod 16)
+ vmovdqu 16*4(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
- mov %r13, %r12
- shr $4, %r12
- and $7, %r12
- jz _initial_num_blocks_is_0\@
+ #######################################################################
- cmp $7, %r12
- je _initial_num_blocks_is_7\@
- cmp $6, %r12
- je _initial_num_blocks_is_6\@
- cmp $5, %r12
- je _initial_num_blocks_is_5\@
- cmp $4, %r12
- je _initial_num_blocks_is_4\@
- cmp $3, %r12
- je _initial_num_blocks_is_3\@
- cmp $2, %r12
- je _initial_num_blocks_is_2\@
+ vmovdqa TMP3(%rsp), \T1
+ vmovdqu HashKey_6(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
- jmp _initial_num_blocks_is_1\@
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_6_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
-_initial_num_blocks_is_7\@:
- INITIAL_BLOCKS_AVX 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*7, %r13
- jmp _initial_blocks_encrypted\@
+ vmovdqu 16*5(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
-_initial_num_blocks_is_6\@:
- INITIAL_BLOCKS_AVX 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*6, %r13
- jmp _initial_blocks_encrypted\@
+ vmovdqa TMP4(%rsp), \T1
+ vmovdqu HashKey_5(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
-_initial_num_blocks_is_5\@:
- INITIAL_BLOCKS_AVX 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*5, %r13
- jmp _initial_blocks_encrypted\@
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_5_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
-_initial_num_blocks_is_4\@:
- INITIAL_BLOCKS_AVX 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*4, %r13
- jmp _initial_blocks_encrypted\@
+ vmovdqu 16*6(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
-_initial_num_blocks_is_3\@:
- INITIAL_BLOCKS_AVX 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*3, %r13
- jmp _initial_blocks_encrypted\@
-_initial_num_blocks_is_2\@:
- INITIAL_BLOCKS_AVX 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*2, %r13
- jmp _initial_blocks_encrypted\@
+ vmovdqa TMP5(%rsp), \T1
+ vmovdqu HashKey_4(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
-_initial_num_blocks_is_1\@:
- INITIAL_BLOCKS_AVX 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*1, %r13
- jmp _initial_blocks_encrypted\@
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_4_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
-_initial_num_blocks_is_0\@:
- INITIAL_BLOCKS_AVX 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ vmovdqu 16*7(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+ vmovdqa TMP6(%rsp), \T1
+ vmovdqu HashKey_3(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
-_initial_blocks_encrypted\@:
- cmp $0, %r13
- je _zero_cipher_left\@
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_3_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
- sub $128, %r13
- je _eight_cipher_left\@
+ vmovdqu 16*8(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+ vmovdqa TMP7(%rsp), \T1
+ vmovdqu HashKey_2(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_2_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
- vmovd %xmm9, %r15d
- and $255, %r15d
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ #######################################################################
+ vmovdqu 16*9(arg1), \T5
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
-_encrypt_by_8_new\@:
- cmp $(255-8), %r15d
- jg _encrypt_by_8\@
+ vmovdqa TMP8(%rsp), \T1
+ vmovdqu HashKey(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqu HashKey_k(arg2), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+ vpxor \T4, \T6, \T6
+ vpxor \T7, \T6, \T6
- add $8, %r15b
- GHASH_8_ENCRYPT_8_PARALLEL_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
- add $128, %r11
- sub $128, %r13
- jne _encrypt_by_8_new\@
+ vmovdqu 16*10(arg1), \T5
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- jmp _eight_cipher_left\@
+ i = 11
+ setreg
+.rep (\REP-9)
+
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
+
+ vmovdqu 16*i(arg1), \T5
+ i = i + 1
+ setreg
+.endr
-_encrypt_by_8\@:
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $8, %r15b
- GHASH_8_ENCRYPT_8_PARALLEL_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $128, %r11
- sub $128, %r13
- jne _encrypt_by_8_new\@
+ i = 0
+ j = 1
+ setreg
+.rep 8
+ vpxor 16*i(arg4, %r11), \T5, \T2
+ .if \ENC_DEC == ENC
+ vaesenclast \T2, reg_j, reg_j
+ .else
+ vaesenclast \T2, reg_j, \T3
+ vmovdqu 16*i(arg4, %r11), reg_j
+ vmovdqu \T3, 16*i(arg3, %r11)
+ .endif
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ #######################################################################
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
+ vpxor \T3, \T7, \T7
+ vpxor \T4, \T6, \T6 # accumulate the results in T6:T7
-_eight_cipher_left\@:
- GHASH_LAST_8_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
+ #######################################################################
+ #first phase of the reduction
+ #######################################################################
+ vpslld $31, \T7, \T2 # packed right shifting << 31
+ vpslld $30, \T7, \T3 # packed right shifting shift << 30
+ vpslld $25, \T7, \T4 # packed right shifting shift << 25
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
-_zero_cipher_left\@:
- cmp $16, arg4
- jl _only_less_than_16\@
+ vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
- mov arg4, %r13
- and $15, %r13 # r13 = (arg4 mod 16)
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+ .if \ENC_DEC == ENC
+ vmovdqu \XMM1, 16*0(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM2, 16*1(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM3, 16*2(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM4, 16*3(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM5, 16*4(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM6, 16*5(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM7, 16*6(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM8, 16*7(arg3,%r11) # Write to the Ciphertext buffer
+ .endif
- je _multiple_of_16_bytes\@
+ #######################################################################
+ #second phase of the reduction
+ vpsrld $1, \T7, \T2 # packed left shifting >> 1
+ vpsrld $2, \T7, \T3 # packed left shifting >> 2
+ vpsrld $7, \T7, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
- # handle the last <16 Byte block seperately
+ vpxor \T1, \T2, \T2
+ vpxor \T2, \T7, \T7
+ vpxor \T7, \T6, \T6 # the result is in T6
+ #######################################################################
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
- vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
- sub $16, %r11
- add %r13, %r11
- vmovdqu (arg3, %r11), %xmm1 # receive the last <16 Byte block
+ vpxor \T6, \XMM1, \XMM1
- lea SHIFT_MASK+16(%rip), %r12
- sub %r13, %r12 # adjust the shuffle mask pointer to be
- # able to shift 16-r13 bytes (r13 is the
- # number of bytes in plaintext mod 16)
- vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
- vpshufb %xmm2, %xmm1, %xmm1 # shift right 16-r13 bytes
- jmp _final_ghash_mul\@
-_only_less_than_16\@:
- # check for 0 length
- mov arg4, %r13
- and $15, %r13 # r13 = (arg4 mod 16)
- je _multiple_of_16_bytes\@
+.endm
- # handle the last <16 Byte block seperately
+# GHASH the last 4 ciphertext blocks.
+.macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
- vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+ ## Karatsuba Method
- lea SHIFT_MASK+16(%rip), %r12
- sub %r13, %r12 # adjust the shuffle mask pointer to be
- # able to shift 16-r13 bytes (r13 is the
- # number of bytes in plaintext mod 16)
+ vpshufd $0b01001110, \XMM1, \T2
+ vpxor \XMM1, \T2, \T2
+ vmovdqu HashKey_8(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM1, \T6
+ vpclmulqdq $0x00, \T5, \XMM1, \T7
-_get_last_16_byte_loop\@:
- movb (arg3, %r11), %al
- movb %al, TMP1 (%rsp , %r11)
- add $1, %r11
- cmp %r13, %r11
- jne _get_last_16_byte_loop\@
+ vmovdqu HashKey_8_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \XMM1
- vmovdqu TMP1(%rsp), %xmm1
+ ######################
- sub $16, %r11
+ vpshufd $0b01001110, \XMM2, \T2
+ vpxor \XMM2, \T2, \T2
+ vmovdqu HashKey_7(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM2, \T4
+ vpxor \T4, \T6, \T6
-_final_ghash_mul\@:
- .if \ENC_DEC == DEC
- vmovdqa %xmm1, %xmm2
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
- # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm2, %xmm2
- vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- sub %r13, %r11
- add $16, %r11
- .else
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
- # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- vpxor %xmm9, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- sub %r13, %r11
- add $16, %r11
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
- .endif
+ vpclmulqdq $0x00, \T5, \XMM2, \T4
+ vpxor \T4, \T7, \T7
+ vmovdqu HashKey_7_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
- #############################
- # output r13 Bytes
- vmovq %xmm9, %rax
- cmp $8, %r13
- jle _less_than_8_bytes_left\@
+ ######################
- mov %rax, (arg2 , %r11)
- add $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- vmovq %xmm9, %rax
- sub $8, %r13
+ vpshufd $0b01001110, \XMM3, \T2
+ vpxor \XMM3, \T2, \T2
+ vmovdqu HashKey_6(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM3, \T4
+ vpxor \T4, \T6, \T6
-_less_than_8_bytes_left\@:
- movb %al, (arg2 , %r11)
- add $1, %r11
- shr $8, %rax
- sub $1, %r13
- jne _less_than_8_bytes_left\@
- #############################
+ vpclmulqdq $0x00, \T5, \XMM3, \T4
+ vpxor \T4, \T7, \T7
-_multiple_of_16_bytes\@:
- mov arg7, %r12 # r12 = aadLen (number of bytes)
- shl $3, %r12 # convert into number of bits
- vmovd %r12d, %xmm15 # len(A) in xmm15
+ vmovdqu HashKey_6_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
- shl $3, arg4 # len(C) in bits (*128)
- vmovq arg4, %xmm1
- vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
- vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
+ ######################
- vpxor %xmm15, %xmm14, %xmm14
- GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
- vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
+ vpshufd $0b01001110, \XMM4, \T2
+ vpxor \XMM4, \T2, \T2
+ vmovdqu HashKey_5(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM4, \T4
+ vpxor \T4, \T6, \T6
- mov arg5, %rax # rax = *Y0
- vmovdqu (%rax), %xmm9 # xmm9 = Y0
+ vpclmulqdq $0x00, \T5, \XMM4, \T4
+ vpxor \T4, \T7, \T7
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Y0)
+ vmovdqu HashKey_5_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
- vpxor %xmm14, %xmm9, %xmm9
+ ######################
+ vpshufd $0b01001110, \XMM5, \T2
+ vpxor \XMM5, \T2, \T2
+ vmovdqu HashKey_4(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM5, \T4
+ vpxor \T4, \T6, \T6
+ vpclmulqdq $0x00, \T5, \XMM5, \T4
+ vpxor \T4, \T7, \T7
-_return_T\@:
- mov arg8, %r10 # r10 = authTag
- mov arg9, %r11 # r11 = auth_tag_len
+ vmovdqu HashKey_4_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
- cmp $16, %r11
- je _T_16\@
+ ######################
- cmp $8, %r11
- jl _T_4\@
+ vpshufd $0b01001110, \XMM6, \T2
+ vpxor \XMM6, \T2, \T2
+ vmovdqu HashKey_3(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM6, \T4
+ vpxor \T4, \T6, \T6
-_T_8\@:
- vmovq %xmm9, %rax
- mov %rax, (%r10)
- add $8, %r10
- sub $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- cmp $0, %r11
- je _return_T_done\@
-_T_4\@:
- vmovd %xmm9, %eax
- mov %eax, (%r10)
- add $4, %r10
- sub $4, %r11
- vpsrldq $4, %xmm9, %xmm9
- cmp $0, %r11
- je _return_T_done\@
-_T_123\@:
- vmovd %xmm9, %eax
- cmp $2, %r11
- jl _T_1\@
- mov %ax, (%r10)
- cmp $2, %r11
- je _return_T_done\@
- add $2, %r10
- sar $16, %eax
-_T_1\@:
- mov %al, (%r10)
- jmp _return_T_done\@
+ vpclmulqdq $0x00, \T5, \XMM6, \T4
+ vpxor \T4, \T7, \T7
-_T_16\@:
- vmovdqu %xmm9, (%r10)
+ vmovdqu HashKey_3_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
-_return_T_done\@:
- mov %r14, %rsp
+ ######################
- pop %r15
- pop %r14
- pop %r13
- pop %r12
-.endm
+ vpshufd $0b01001110, \XMM7, \T2
+ vpxor \XMM7, \T2, \T2
+ vmovdqu HashKey_2(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM7, \T4
+ vpxor \T4, \T6, \T6
+ vpclmulqdq $0x00, \T5, \XMM7, \T4
+ vpxor \T4, \T7, \T7
-#############################################################
-#void aesni_gcm_precomp_avx_gen2
-# (gcm_data *my_ctx_data,
-# u8 *hash_subkey)# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
-#############################################################
-ENTRY(aesni_gcm_precomp_avx_gen2)
- #the number of pushes must equal STACK_OFFSET
- push %r12
- push %r13
- push %r14
- push %r15
+ vmovdqu HashKey_2_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
- mov %rsp, %r14
+ ######################
+
+ vpshufd $0b01001110, \XMM8, \T2
+ vpxor \XMM8, \T2, \T2
+ vmovdqu HashKey(arg2), \T5
+ vpclmulqdq $0x11, \T5, \XMM8, \T4
+ vpxor \T4, \T6, \T6
+ vpclmulqdq $0x00, \T5, \XMM8, \T4
+ vpxor \T4, \T7, \T7
+ vmovdqu HashKey_k(arg2), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
- sub $VARIABLE_OFFSET, %rsp
- and $~63, %rsp # align rsp to 64 bytes
+ vpxor \T2, \XMM1, \XMM1
+ vpxor \T6, \XMM1, \XMM1
+ vpxor \T7, \XMM1, \T2
- vmovdqu (arg2), %xmm6 # xmm6 = HashKey
- vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
- ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
- vmovdqa %xmm6, %xmm2
- vpsllq $1, %xmm6, %xmm6
- vpsrlq $63, %xmm2, %xmm2
- vmovdqa %xmm2, %xmm1
- vpslldq $8, %xmm2, %xmm2
- vpsrldq $8, %xmm1, %xmm1
- vpor %xmm2, %xmm6, %xmm6
- #reduction
- vpshufd $0b00100100, %xmm1, %xmm2
- vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
- vpand POLY(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
+
+
+ vpslldq $8, \T2, \T4
+ vpsrldq $8, \T2, \T2
+
+ vpxor \T4, \T7, \T7
+ vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
+ # the accumulated carry-less multiplications
+
#######################################################################
- vmovdqa %xmm6, HashKey(arg1) # store HashKey<<1 mod poly
+ #first phase of the reduction
+ vpslld $31, \T7, \T2 # packed right shifting << 31
+ vpslld $30, \T7, \T3 # packed right shifting shift << 30
+ vpslld $25, \T7, \T4 # packed right shifting shift << 25
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
- PRECOMPUTE_AVX %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
+ vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
- mov %r14, %rsp
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- ret
-ENDPROC(aesni_gcm_precomp_avx_gen2)
-###############################################################################
-#void aesni_gcm_enc_avx_gen2(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
-# const u8 *in, /* Plaintext input */
-# u64 plaintext_len, /* Length of data in Bytes for encryption. */
+ #second phase of the reduction
+ vpsrld $1, \T7, \T2 # packed left shifting >> 1
+ vpsrld $2, \T7, \T3 # packed left shifting >> 2
+ vpsrld $7, \T7, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpxor \T1, \T2, \T2
+ vpxor \T2, \T7, \T7
+ vpxor \T7, \T6, \T6 # the result is in T6
+
+.endm
+
+#############################################################
+#void aesni_gcm_precomp_avx_gen2
+# (gcm_data *my_ctx_data,
+# gcm_context_data *data,
+# u8 *hash_subkey# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
# u8 *iv, /* Pre-counter block j0: 4 byte salt
# (from Security Association) concatenated with 8 byte
# Initialisation Vector (from IPSec ESP Payload)
# concatenated with 0x00000001. 16-byte aligned pointer. */
# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
-# u8 *auth_tag, /* Authenticated Tag output. */
-# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
-# Valid values are 16 (most likely), 12 or 8. */
+# u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+#############################################################
+ENTRY(aesni_gcm_init_avx_gen2)
+ FUNC_SAVE
+ INIT GHASH_MUL_AVX, PRECOMPUTE_AVX
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_init_avx_gen2)
+
###############################################################################
-ENTRY(aesni_gcm_enc_avx_gen2)
- GCM_ENC_DEC_AVX ENC
- ret
-ENDPROC(aesni_gcm_enc_avx_gen2)
+#void aesni_gcm_enc_update_avx_gen2(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
+# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
+# const u8 *in, /* Plaintext input */
+# u64 plaintext_len) /* Length of data in Bytes for encryption. */
+###############################################################################
+ENTRY(aesni_gcm_enc_update_avx_gen2)
+ FUNC_SAVE
+ mov keysize, %eax
+ cmp $32, %eax
+ je key_256_enc_update
+ cmp $16, %eax
+ je key_128_enc_update
+ # must be 192
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 11
+ FUNC_RESTORE
+ ret
+key_128_enc_update:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 9
+ FUNC_RESTORE
+ ret
+key_256_enc_update:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_enc_update_avx_gen2)
###############################################################################
-#void aesni_gcm_dec_avx_gen2(
+#void aesni_gcm_dec_update_avx_gen2(
# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
# const u8 *in, /* Ciphertext input */
-# u64 plaintext_len, /* Length of data in Bytes for encryption. */
-# u8 *iv, /* Pre-counter block j0: 4 byte salt
-# (from Security Association) concatenated with 8 byte
-# Initialisation Vector (from IPSec ESP Payload)
-# concatenated with 0x00000001. 16-byte aligned pointer. */
-# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u64 plaintext_len) /* Length of data in Bytes for encryption. */
+###############################################################################
+ENTRY(aesni_gcm_dec_update_avx_gen2)
+ FUNC_SAVE
+ mov keysize,%eax
+ cmp $32, %eax
+ je key_256_dec_update
+ cmp $16, %eax
+ je key_128_dec_update
+ # must be 192
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 11
+ FUNC_RESTORE
+ ret
+key_128_dec_update:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 9
+ FUNC_RESTORE
+ ret
+key_256_dec_update:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_dec_update_avx_gen2)
+
+###############################################################################
+#void aesni_gcm_finalize_avx_gen2(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
# u8 *auth_tag, /* Authenticated Tag output. */
# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
# Valid values are 16 (most likely), 12 or 8. */
###############################################################################
-ENTRY(aesni_gcm_dec_avx_gen2)
- GCM_ENC_DEC_AVX DEC
- ret
-ENDPROC(aesni_gcm_dec_avx_gen2)
+ENTRY(aesni_gcm_finalize_avx_gen2)
+ FUNC_SAVE
+ mov keysize,%eax
+ cmp $32, %eax
+ je key_256_finalize
+ cmp $16, %eax
+ je key_128_finalize
+ # must be 192
+ GCM_COMPLETE GHASH_MUL_AVX, 11, arg3, arg4
+ FUNC_RESTORE
+ ret
+key_128_finalize:
+ GCM_COMPLETE GHASH_MUL_AVX, 9, arg3, arg4
+ FUNC_RESTORE
+ ret
+key_256_finalize:
+ GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_finalize_avx_gen2)
+
#endif /* CONFIG_AS_AVX */
#ifdef CONFIG_AS_AVX2
# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
vmovdqa \HK, \T5
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
- vmovdqa \T5, HashKey_2(arg1) # [HashKey_2] = HashKey^2<<1 mod poly
+ vmovdqu \T5, HashKey_2(arg2) # [HashKey_2] = HashKey^2<<1 mod poly
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
- vmovdqa \T5, HashKey_3(arg1)
+ vmovdqu \T5, HashKey_3(arg2)
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
- vmovdqa \T5, HashKey_4(arg1)
+ vmovdqu \T5, HashKey_4(arg2)
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
- vmovdqa \T5, HashKey_5(arg1)
+ vmovdqu \T5, HashKey_5(arg2)
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
- vmovdqa \T5, HashKey_6(arg1)
+ vmovdqu \T5, HashKey_6(arg2)
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
- vmovdqa \T5, HashKey_7(arg1)
+ vmovdqu \T5, HashKey_7(arg2)
GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
- vmovdqa \T5, HashKey_8(arg1)
+ vmovdqu \T5, HashKey_8(arg2)
.endm
-
## if a = number of total plaintext bytes
## b = floor(a/16)
## num_initial_blocks = b mod 4#
## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
## r10, r11, r12, rax are clobbered
-## arg1, arg2, arg3, r14 are used as a pointer only, not modified
+## arg1, arg3, arg4, r14 are used as a pointer only, not modified
-.macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
+.macro INITIAL_BLOCKS_AVX2 REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
i = (8-\num_initial_blocks)
- j = 0
setreg
-
- mov arg6, %r10 # r10 = AAD
- mov arg7, %r12 # r12 = aadLen
-
-
- mov %r12, %r11
-
- vpxor reg_j, reg_j, reg_j
- vpxor reg_i, reg_i, reg_i
-
- cmp $16, %r11
- jl _get_AAD_rest8\@
-_get_AAD_blocks\@:
- vmovdqu (%r10), reg_i
- vpshufb SHUF_MASK(%rip), reg_i, reg_i
- vpxor reg_i, reg_j, reg_j
- GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6
- add $16, %r10
- sub $16, %r12
- sub $16, %r11
- cmp $16, %r11
- jge _get_AAD_blocks\@
- vmovdqu reg_j, reg_i
- cmp $0, %r11
- je _get_AAD_done\@
-
- vpxor reg_i, reg_i, reg_i
-
- /* read the last <16B of AAD. since we have at least 4B of
- data right after the AAD (the ICV, and maybe some CT), we can
- read 4B/8B blocks safely, and then get rid of the extra stuff */
-_get_AAD_rest8\@:
- cmp $4, %r11
- jle _get_AAD_rest4\@
- movq (%r10), \T1
- add $8, %r10
- sub $8, %r11
- vpslldq $8, \T1, \T1
- vpsrldq $8, reg_i, reg_i
- vpxor \T1, reg_i, reg_i
- jmp _get_AAD_rest8\@
-_get_AAD_rest4\@:
- cmp $0, %r11
- jle _get_AAD_rest0\@
- mov (%r10), %eax
- movq %rax, \T1
- add $4, %r10
- sub $4, %r11
- vpslldq $12, \T1, \T1
- vpsrldq $4, reg_i, reg_i
- vpxor \T1, reg_i, reg_i
-_get_AAD_rest0\@:
- /* finalize: shift out the extra bytes we read, and align
- left. since pslldq can only shift by an immediate, we use
- vpshufb and an array of shuffle masks */
- movq %r12, %r11
- salq $4, %r11
- movdqu aad_shift_arr(%r11), \T1
- vpshufb \T1, reg_i, reg_i
-_get_AAD_rest_final\@:
- vpshufb SHUF_MASK(%rip), reg_i, reg_i
- vpxor reg_j, reg_i, reg_i
- GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6
-
-_get_AAD_done\@:
- # initialize the data pointer offset as zero
- xor %r11d, %r11d
+ vmovdqu AadHash(arg2), reg_i
# start AES for num_initial_blocks blocks
- mov arg5, %rax # rax = *Y0
- vmovdqu (%rax), \CTR # CTR = Y0
- vpshufb SHUF_MASK(%rip), \CTR, \CTR
-
+ vmovdqu CurCount(arg2), \CTR
i = (9-\num_initial_blocks)
setreg
j = 1
setreg
-.rep 9
+.rep \REP
vmovdqa 16*j(arg1), \T_key
i = (9-\num_initial_blocks)
setreg
.endr
- vmovdqa 16*10(arg1), \T_key
+ vmovdqa 16*j(arg1), \T_key
i = (9-\num_initial_blocks)
setreg
.rep \num_initial_blocks
i = (9-\num_initial_blocks)
setreg
.rep \num_initial_blocks
- vmovdqu (arg3, %r11), \T1
+ vmovdqu (arg4, %r11), \T1
vpxor \T1, reg_i, reg_i
- vmovdqu reg_i, (arg2 , %r11) # write back ciphertext for
+ vmovdqu reg_i, (arg3 , %r11) # write back ciphertext for
# num_initial_blocks blocks
add $16, %r11
.if \ENC_DEC == DEC
i = 1
setreg
-.rep 9 # do 9 rounds
+.rep \REP # do REP rounds
vmovdqa 16*i(arg1), \T_key
vaesenc \T_key, \XMM1, \XMM1
vaesenc \T_key, \XMM2, \XMM2
vaesenclast \T_key, \XMM7, \XMM7
vaesenclast \T_key, \XMM8, \XMM8
- vmovdqu (arg3, %r11), \T1
+ vmovdqu (arg4, %r11), \T1
vpxor \T1, \XMM1, \XMM1
- vmovdqu \XMM1, (arg2 , %r11)
+ vmovdqu \XMM1, (arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM1
.endif
- vmovdqu 16*1(arg3, %r11), \T1
+ vmovdqu 16*1(arg4, %r11), \T1
vpxor \T1, \XMM2, \XMM2
- vmovdqu \XMM2, 16*1(arg2 , %r11)
+ vmovdqu \XMM2, 16*1(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM2
.endif
- vmovdqu 16*2(arg3, %r11), \T1
+ vmovdqu 16*2(arg4, %r11), \T1
vpxor \T1, \XMM3, \XMM3
- vmovdqu \XMM3, 16*2(arg2 , %r11)
+ vmovdqu \XMM3, 16*2(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM3
.endif
- vmovdqu 16*3(arg3, %r11), \T1
+ vmovdqu 16*3(arg4, %r11), \T1
vpxor \T1, \XMM4, \XMM4
- vmovdqu \XMM4, 16*3(arg2 , %r11)
+ vmovdqu \XMM4, 16*3(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM4
.endif
- vmovdqu 16*4(arg3, %r11), \T1
+ vmovdqu 16*4(arg4, %r11), \T1
vpxor \T1, \XMM5, \XMM5
- vmovdqu \XMM5, 16*4(arg2 , %r11)
+ vmovdqu \XMM5, 16*4(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM5
.endif
- vmovdqu 16*5(arg3, %r11), \T1
+ vmovdqu 16*5(arg4, %r11), \T1
vpxor \T1, \XMM6, \XMM6
- vmovdqu \XMM6, 16*5(arg2 , %r11)
+ vmovdqu \XMM6, 16*5(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM6
.endif
- vmovdqu 16*6(arg3, %r11), \T1
+ vmovdqu 16*6(arg4, %r11), \T1
vpxor \T1, \XMM7, \XMM7
- vmovdqu \XMM7, 16*6(arg2 , %r11)
+ vmovdqu \XMM7, 16*6(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM7
.endif
- vmovdqu 16*7(arg3, %r11), \T1
+ vmovdqu 16*7(arg4, %r11), \T1
vpxor \T1, \XMM8, \XMM8
- vmovdqu \XMM8, 16*7(arg2 , %r11)
+ vmovdqu \XMM8, 16*7(arg3 , %r11)
.if \ENC_DEC == DEC
vmovdqa \T1, \XMM8
.endif
# encrypt 8 blocks at a time
# ghash the 8 previously encrypted ciphertext blocks
-# arg1, arg2, arg3 are used as pointers only, not modified
+# arg1, arg3, arg4 are used as pointers only, not modified
# r11 is the data offset value
-.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
+.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
vmovdqa \XMM1, \T2
vmovdqa \XMM2, TMP2(%rsp)
- vmovdqu 16*1(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqu 16*2(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- #######################################################################
-
- vmovdqa HashKey_8(arg1), \T5
- vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
- vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
- vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
- vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
- vpxor \T5, \T6, \T6
-
- vmovdqu 16*3(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP2(%rsp), \T1
- vmovdqa HashKey_7(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*4(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- #######################################################################
-
- vmovdqa TMP3(%rsp), \T1
- vmovdqa HashKey_6(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*5(arg1), \T1
+ vmovdqu 16*1(arg1), \T1
vaesenc \T1, \XMM1, \XMM1
vaesenc \T1, \XMM2, \XMM2
vaesenc \T1, \XMM3, \XMM3
vaesenc \T1, \XMM7, \XMM7
vaesenc \T1, \XMM8, \XMM8
- vmovdqa TMP4(%rsp), \T1
- vmovdqa HashKey_5(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*6(arg1), \T1
+ vmovdqu 16*2(arg1), \T1
vaesenc \T1, \XMM1, \XMM1
vaesenc \T1, \XMM2, \XMM2
vaesenc \T1, \XMM3, \XMM3
vaesenc \T1, \XMM8, \XMM8
- vmovdqa TMP5(%rsp), \T1
- vmovdqa HashKey_4(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
+ #######################################################################
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
+ vmovdqu HashKey_8(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
+ vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
+ vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
+ vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
+ vpxor \T5, \T6, \T6
- vmovdqu 16*7(arg1), \T1
+ vmovdqu 16*3(arg1), \T1
vaesenc \T1, \XMM1, \XMM1
vaesenc \T1, \XMM2, \XMM2
vaesenc \T1, \XMM3, \XMM3
vaesenc \T1, \XMM7, \XMM7
vaesenc \T1, \XMM8, \XMM8
- vmovdqa TMP6(%rsp), \T1
- vmovdqa HashKey_3(arg1), \T5
+ vmovdqa TMP2(%rsp), \T1
+ vmovdqu HashKey_7(arg2), \T5
vpclmulqdq $0x11, \T5, \T1, \T3
vpxor \T3, \T4, \T4
vpclmulqdq $0x10, \T5, \T1, \T3
vpxor \T3, \T6, \T6
- vmovdqu 16*8(arg1), \T1
+ vmovdqu 16*4(arg1), \T1
vaesenc \T1, \XMM1, \XMM1
vaesenc \T1, \XMM2, \XMM2
vaesenc \T1, \XMM3, \XMM3
vaesenc \T1, \XMM7, \XMM7
vaesenc \T1, \XMM8, \XMM8
- vmovdqa TMP7(%rsp), \T1
- vmovdqa HashKey_2(arg1), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
-
#######################################################################
- vmovdqu 16*9(arg1), \T5
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
-
- vmovdqa TMP8(%rsp), \T1
- vmovdqa HashKey(arg1), \T5
+ vmovdqa TMP3(%rsp), \T1
+ vmovdqu HashKey_6(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
vpclmulqdq $0x00, \T5, \T1, \T3
vpxor \T3, \T7, \T7
vpclmulqdq $0x10, \T5, \T1, \T3
vpxor \T3, \T6, \T6
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T1
-
-
- vmovdqu 16*10(arg1), \T5
-
- i = 0
- j = 1
- setreg
-.rep 8
- vpxor 16*i(arg3, %r11), \T5, \T2
- .if \ENC_DEC == ENC
- vaesenclast \T2, reg_j, reg_j
- .else
- vaesenclast \T2, reg_j, \T3
- vmovdqu 16*i(arg3, %r11), reg_j
- vmovdqu \T3, 16*i(arg2, %r11)
- .endif
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- #######################################################################
-
-
- vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
- vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
- vpxor \T3, \T7, \T7
- vpxor \T6, \T1, \T1 # accumulate the results in T1:T7
-
-
-
- #######################################################################
- #first phase of the reduction
- vmovdqa POLY2(%rip), \T3
-
- vpclmulqdq $0x01, \T7, \T3, \T2
- vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
-
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
- .if \ENC_DEC == ENC
- vmovdqu \XMM1, 16*0(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM2, 16*1(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM3, 16*2(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM4, 16*3(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM5, 16*4(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM6, 16*5(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM7, 16*6(arg2,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM8, 16*7(arg2,%r11) # Write to the Ciphertext buffer
- .endif
-
- #######################################################################
- #second phase of the reduction
- vpclmulqdq $0x00, \T7, \T3, \T2
- vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
-
- vpclmulqdq $0x10, \T7, \T3, \T4
- vpslldq $4, \T4, \T4 # shift-L xmm0 1 DW (Shift-L 1-DW to obtain result with no shifts)
-
- vpxor \T2, \T4, \T4 # second phase of the reduction complete
- #######################################################################
- vpxor \T4, \T1, \T1 # the result is in T1
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
-
- vpxor \T1, \XMM1, \XMM1
-
-
-
-.endm
-
-
-# GHASH the last 4 ciphertext blocks.
-.macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
-
- ## Karatsuba Method
-
- vmovdqa HashKey_8(arg1), \T5
-
- vpshufd $0b01001110, \XMM1, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM1, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM1, \T6
- vpclmulqdq $0x00, \T5, \XMM1, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \XMM1
-
- ######################
-
- vmovdqa HashKey_7(arg1), \T5
- vpshufd $0b01001110, \XMM2, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM2, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM2, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM2, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqa HashKey_6(arg1), \T5
- vpshufd $0b01001110, \XMM3, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM3, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM3, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM3, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqa HashKey_5(arg1), \T5
- vpshufd $0b01001110, \XMM4, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM4, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM4, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM4, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqa HashKey_4(arg1), \T5
- vpshufd $0b01001110, \XMM5, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM5, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM5, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM5, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqa HashKey_3(arg1), \T5
- vpshufd $0b01001110, \XMM6, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM6, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM6, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM6, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqa HashKey_2(arg1), \T5
- vpshufd $0b01001110, \XMM7, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM7, \T2, \T2
- vpxor \T5, \T3, \T3
+ vmovdqu 16*5(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
- vpclmulqdq $0x11, \T5, \XMM7, \T4
- vpxor \T4, \T6, \T6
+ vmovdqa TMP4(%rsp), \T1
+ vmovdqu HashKey_5(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \XMM7, \T4
- vpxor \T4, \T7, \T7
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
- vpclmulqdq $0x00, \T3, \T2, \T2
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- vpxor \T2, \XMM1, \XMM1
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- ######################
+ vmovdqu 16*6(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
- vmovdqa HashKey(arg1), \T5
- vpshufd $0b01001110, \XMM8, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM8, \T2, \T2
- vpxor \T5, \T3, \T3
- vpclmulqdq $0x11, \T5, \XMM8, \T4
- vpxor \T4, \T6, \T6
+ vmovdqa TMP5(%rsp), \T1
+ vmovdqu HashKey_4(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \XMM8, \T4
- vpxor \T4, \T7, \T7
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
- vpclmulqdq $0x00, \T3, \T2, \T2
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- vpxor \T2, \XMM1, \XMM1
- vpxor \T6, \XMM1, \XMM1
- vpxor \T7, \XMM1, \T2
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+ vmovdqu 16*7(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+ vmovdqa TMP6(%rsp), \T1
+ vmovdqu HashKey_3(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
- vpslldq $8, \T2, \T4
- vpsrldq $8, \T2, \T2
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- vpxor \T4, \T7, \T7
- vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
- # accumulated carry-less multiplications
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- #######################################################################
- #first phase of the reduction
- vmovdqa POLY2(%rip), \T3
+ vmovdqu 16*8(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
- vpclmulqdq $0x01, \T7, \T3, \T2
- vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
+ vmovdqa TMP7(%rsp), \T1
+ vmovdqu HashKey_2(arg2), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- #second phase of the reduction
- vpclmulqdq $0x00, \T7, \T3, \T2
- vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
- vpclmulqdq $0x10, \T7, \T3, \T4
- vpslldq $4, \T4, \T4 # shift-L T4 1 DW (Shift-L 1-DW to obtain result with no shifts)
- vpxor \T2, \T4, \T4 # second phase of the reduction complete
#######################################################################
- vpxor \T4, \T6, \T6 # the result is in T6
-.endm
-
-
-# combined for GCM encrypt and decrypt functions
-# clobbering all xmm registers
-# clobbering r10, r11, r12, r13, r14, r15
-.macro GCM_ENC_DEC_AVX2 ENC_DEC
+ vmovdqu 16*9(arg1), \T5
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
- #the number of pushes must equal STACK_OFFSET
- push %r12
- push %r13
- push %r14
- push %r15
+ vmovdqa TMP8(%rsp), \T1
+ vmovdqu HashKey(arg2), \T5
- mov %rsp, %r14
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T1
- sub $VARIABLE_OFFSET, %rsp
- and $~63, %rsp # align rsp to 64 bytes
+ vmovdqu 16*10(arg1), \T5
- vmovdqu HashKey(arg1), %xmm13 # xmm13 = HashKey
+ i = 11
+ setreg
+.rep (\REP-9)
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
+
+ vmovdqu 16*i(arg1), \T5
+ i = i + 1
+ setreg
+.endr
- mov arg4, %r13 # save the number of bytes of plaintext/ciphertext
- and $-16, %r13 # r13 = r13 - (r13 mod 16)
+ i = 0
+ j = 1
+ setreg
+.rep 8
+ vpxor 16*i(arg4, %r11), \T5, \T2
+ .if \ENC_DEC == ENC
+ vaesenclast \T2, reg_j, reg_j
+ .else
+ vaesenclast \T2, reg_j, \T3
+ vmovdqu 16*i(arg4, %r11), reg_j
+ vmovdqu \T3, 16*i(arg3, %r11)
+ .endif
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ #######################################################################
- mov %r13, %r12
- shr $4, %r12
- and $7, %r12
- jz _initial_num_blocks_is_0\@
- cmp $7, %r12
- je _initial_num_blocks_is_7\@
- cmp $6, %r12
- je _initial_num_blocks_is_6\@
- cmp $5, %r12
- je _initial_num_blocks_is_5\@
- cmp $4, %r12
- je _initial_num_blocks_is_4\@
- cmp $3, %r12
- je _initial_num_blocks_is_3\@
- cmp $2, %r12
- je _initial_num_blocks_is_2\@
+ vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
+ vpxor \T3, \T7, \T7
+ vpxor \T6, \T1, \T1 # accumulate the results in T1:T7
- jmp _initial_num_blocks_is_1\@
-_initial_num_blocks_is_7\@:
- INITIAL_BLOCKS_AVX2 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*7, %r13
- jmp _initial_blocks_encrypted\@
-_initial_num_blocks_is_6\@:
- INITIAL_BLOCKS_AVX2 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*6, %r13
- jmp _initial_blocks_encrypted\@
+ #######################################################################
+ #first phase of the reduction
+ vmovdqa POLY2(%rip), \T3
-_initial_num_blocks_is_5\@:
- INITIAL_BLOCKS_AVX2 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*5, %r13
- jmp _initial_blocks_encrypted\@
+ vpclmulqdq $0x01, \T7, \T3, \T2
+ vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
-_initial_num_blocks_is_4\@:
- INITIAL_BLOCKS_AVX2 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*4, %r13
- jmp _initial_blocks_encrypted\@
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+ .if \ENC_DEC == ENC
+ vmovdqu \XMM1, 16*0(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM2, 16*1(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM3, 16*2(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM4, 16*3(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM5, 16*4(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM6, 16*5(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM7, 16*6(arg3,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM8, 16*7(arg3,%r11) # Write to the Ciphertext buffer
+ .endif
-_initial_num_blocks_is_3\@:
- INITIAL_BLOCKS_AVX2 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*3, %r13
- jmp _initial_blocks_encrypted\@
+ #######################################################################
+ #second phase of the reduction
+ vpclmulqdq $0x00, \T7, \T3, \T2
+ vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
-_initial_num_blocks_is_2\@:
- INITIAL_BLOCKS_AVX2 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*2, %r13
- jmp _initial_blocks_encrypted\@
+ vpclmulqdq $0x10, \T7, \T3, \T4
+ vpslldq $4, \T4, \T4 # shift-L xmm0 1 DW (Shift-L 1-DW to obtain result with no shifts)
-_initial_num_blocks_is_1\@:
- INITIAL_BLOCKS_AVX2 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*1, %r13
- jmp _initial_blocks_encrypted\@
+ vpxor \T2, \T4, \T4 # second phase of the reduction complete
+ #######################################################################
+ vpxor \T4, \T1, \T1 # the result is in T1
-_initial_num_blocks_is_0\@:
- INITIAL_BLOCKS_AVX2 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-_initial_blocks_encrypted\@:
- cmp $0, %r13
- je _zero_cipher_left\@
+ vpxor \T1, \XMM1, \XMM1
- sub $128, %r13
- je _eight_cipher_left\@
+.endm
- vmovd %xmm9, %r15d
- and $255, %r15d
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+# GHASH the last 4 ciphertext blocks.
+.macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
+ ## Karatsuba Method
-_encrypt_by_8_new\@:
- cmp $(255-8), %r15d
- jg _encrypt_by_8\@
+ vmovdqu HashKey_8(arg2), \T5
+ vpshufd $0b01001110, \XMM1, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM1, \T2, \T2
+ vpxor \T5, \T3, \T3
+ vpclmulqdq $0x11, \T5, \XMM1, \T6
+ vpclmulqdq $0x00, \T5, \XMM1, \T7
- add $8, %r15b
- GHASH_8_ENCRYPT_8_PARALLEL_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
- add $128, %r11
- sub $128, %r13
- jne _encrypt_by_8_new\@
+ vpclmulqdq $0x00, \T3, \T2, \XMM1
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- jmp _eight_cipher_left\@
+ ######################
-_encrypt_by_8\@:
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $8, %r15b
- GHASH_8_ENCRYPT_8_PARALLEL_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $128, %r11
- sub $128, %r13
- jne _encrypt_by_8_new\@
+ vmovdqu HashKey_7(arg2), \T5
+ vpshufd $0b01001110, \XMM2, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM2, \T2, \T2
+ vpxor \T5, \T3, \T3
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ vpclmulqdq $0x11, \T5, \XMM2, \T4
+ vpxor \T4, \T6, \T6
+ vpclmulqdq $0x00, \T5, \XMM2, \T4
+ vpxor \T4, \T7, \T7
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
-_eight_cipher_left\@:
- GHASH_LAST_8_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
+ ######################
+ vmovdqu HashKey_6(arg2), \T5
+ vpshufd $0b01001110, \XMM3, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM3, \T2, \T2
+ vpxor \T5, \T3, \T3
-_zero_cipher_left\@:
- cmp $16, arg4
- jl _only_less_than_16\@
+ vpclmulqdq $0x11, \T5, \XMM3, \T4
+ vpxor \T4, \T6, \T6
- mov arg4, %r13
- and $15, %r13 # r13 = (arg4 mod 16)
+ vpclmulqdq $0x00, \T5, \XMM3, \T4
+ vpxor \T4, \T7, \T7
- je _multiple_of_16_bytes\@
+ vpclmulqdq $0x00, \T3, \T2, \T2
- # handle the last <16 Byte block seperately
+ vpxor \T2, \XMM1, \XMM1
+ ######################
- vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+ vmovdqu HashKey_5(arg2), \T5
+ vpshufd $0b01001110, \XMM4, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM4, \T2, \T2
+ vpxor \T5, \T3, \T3
- sub $16, %r11
- add %r13, %r11
- vmovdqu (arg3, %r11), %xmm1 # receive the last <16 Byte block
+ vpclmulqdq $0x11, \T5, \XMM4, \T4
+ vpxor \T4, \T6, \T6
- lea SHIFT_MASK+16(%rip), %r12
- sub %r13, %r12 # adjust the shuffle mask pointer
- # to be able to shift 16-r13 bytes
- # (r13 is the number of bytes in plaintext mod 16)
- vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
- vpshufb %xmm2, %xmm1, %xmm1 # shift right 16-r13 bytes
- jmp _final_ghash_mul\@
-
-_only_less_than_16\@:
- # check for 0 length
- mov arg4, %r13
- and $15, %r13 # r13 = (arg4 mod 16)
+ vpclmulqdq $0x00, \T5, \XMM4, \T4
+ vpxor \T4, \T7, \T7
- je _multiple_of_16_bytes\@
+ vpclmulqdq $0x00, \T3, \T2, \T2
- # handle the last <16 Byte block seperately
+ vpxor \T2, \XMM1, \XMM1
+ ######################
- vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+ vmovdqu HashKey_4(arg2), \T5
+ vpshufd $0b01001110, \XMM5, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM5, \T2, \T2
+ vpxor \T5, \T3, \T3
+ vpclmulqdq $0x11, \T5, \XMM5, \T4
+ vpxor \T4, \T6, \T6
- lea SHIFT_MASK+16(%rip), %r12
- sub %r13, %r12 # adjust the shuffle mask pointer to be
- # able to shift 16-r13 bytes (r13 is the
- # number of bytes in plaintext mod 16)
+ vpclmulqdq $0x00, \T5, \XMM5, \T4
+ vpxor \T4, \T7, \T7
-_get_last_16_byte_loop\@:
- movb (arg3, %r11), %al
- movb %al, TMP1 (%rsp , %r11)
- add $1, %r11
- cmp %r13, %r11
- jne _get_last_16_byte_loop\@
+ vpclmulqdq $0x00, \T3, \T2, \T2
- vmovdqu TMP1(%rsp), %xmm1
+ vpxor \T2, \XMM1, \XMM1
- sub $16, %r11
+ ######################
-_final_ghash_mul\@:
- .if \ENC_DEC == DEC
- vmovdqa %xmm1, %xmm2
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm2, %xmm2
- vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- sub %r13, %r11
- add $16, %r11
- .else
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- vpxor %xmm9, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- sub %r13, %r11
- add $16, %r11
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
- .endif
+ vmovdqu HashKey_3(arg2), \T5
+ vpshufd $0b01001110, \XMM6, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM6, \T2, \T2
+ vpxor \T5, \T3, \T3
+ vpclmulqdq $0x11, \T5, \XMM6, \T4
+ vpxor \T4, \T6, \T6
- #############################
- # output r13 Bytes
- vmovq %xmm9, %rax
- cmp $8, %r13
- jle _less_than_8_bytes_left\@
+ vpclmulqdq $0x00, \T5, \XMM6, \T4
+ vpxor \T4, \T7, \T7
- mov %rax, (arg2 , %r11)
- add $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- vmovq %xmm9, %rax
- sub $8, %r13
+ vpclmulqdq $0x00, \T3, \T2, \T2
-_less_than_8_bytes_left\@:
- movb %al, (arg2 , %r11)
- add $1, %r11
- shr $8, %rax
- sub $1, %r13
- jne _less_than_8_bytes_left\@
- #############################
+ vpxor \T2, \XMM1, \XMM1
-_multiple_of_16_bytes\@:
- mov arg7, %r12 # r12 = aadLen (number of bytes)
- shl $3, %r12 # convert into number of bits
- vmovd %r12d, %xmm15 # len(A) in xmm15
+ ######################
- shl $3, arg4 # len(C) in bits (*128)
- vmovq arg4, %xmm1
- vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
- vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
+ vmovdqu HashKey_2(arg2), \T5
+ vpshufd $0b01001110, \XMM7, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM7, \T2, \T2
+ vpxor \T5, \T3, \T3
- vpxor %xmm15, %xmm14, %xmm14
- GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
- vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
+ vpclmulqdq $0x11, \T5, \XMM7, \T4
+ vpxor \T4, \T6, \T6
- mov arg5, %rax # rax = *Y0
- vmovdqu (%rax), %xmm9 # xmm9 = Y0
+ vpclmulqdq $0x00, \T5, \XMM7, \T4
+ vpxor \T4, \T7, \T7
- ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Y0)
+ vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor %xmm14, %xmm9, %xmm9
+ vpxor \T2, \XMM1, \XMM1
+ ######################
+ vmovdqu HashKey(arg2), \T5
+ vpshufd $0b01001110, \XMM8, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM8, \T2, \T2
+ vpxor \T5, \T3, \T3
-_return_T\@:
- mov arg8, %r10 # r10 = authTag
- mov arg9, %r11 # r11 = auth_tag_len
+ vpclmulqdq $0x11, \T5, \XMM8, \T4
+ vpxor \T4, \T6, \T6
- cmp $16, %r11
- je _T_16\@
+ vpclmulqdq $0x00, \T5, \XMM8, \T4
+ vpxor \T4, \T7, \T7
- cmp $8, %r11
- jl _T_4\@
+ vpclmulqdq $0x00, \T3, \T2, \T2
-_T_8\@:
- vmovq %xmm9, %rax
- mov %rax, (%r10)
- add $8, %r10
- sub $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- cmp $0, %r11
- je _return_T_done\@
-_T_4\@:
- vmovd %xmm9, %eax
- mov %eax, (%r10)
- add $4, %r10
- sub $4, %r11
- vpsrldq $4, %xmm9, %xmm9
- cmp $0, %r11
- je _return_T_done\@
-_T_123\@:
- vmovd %xmm9, %eax
- cmp $2, %r11
- jl _T_1\@
- mov %ax, (%r10)
- cmp $2, %r11
- je _return_T_done\@
- add $2, %r10
- sar $16, %eax
-_T_1\@:
- mov %al, (%r10)
- jmp _return_T_done\@
+ vpxor \T2, \XMM1, \XMM1
+ vpxor \T6, \XMM1, \XMM1
+ vpxor \T7, \XMM1, \T2
-_T_16\@:
- vmovdqu %xmm9, (%r10)
-_return_T_done\@:
- mov %r14, %rsp
- pop %r15
- pop %r14
- pop %r13
- pop %r12
-.endm
+ vpslldq $8, \T2, \T4
+ vpsrldq $8, \T2, \T2
-#############################################################
-#void aesni_gcm_precomp_avx_gen4
-# (gcm_data *my_ctx_data,
-# u8 *hash_subkey)# /* H, the Hash sub key input.
-# Data starts on a 16-byte boundary. */
-#############################################################
-ENTRY(aesni_gcm_precomp_avx_gen4)
- #the number of pushes must equal STACK_OFFSET
- push %r12
- push %r13
- push %r14
- push %r15
+ vpxor \T4, \T7, \T7
+ vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
+ # accumulated carry-less multiplications
- mov %rsp, %r14
+ #######################################################################
+ #first phase of the reduction
+ vmovdqa POLY2(%rip), \T3
+ vpclmulqdq $0x01, \T7, \T3, \T2
+ vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
+
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
- sub $VARIABLE_OFFSET, %rsp
- and $~63, %rsp # align rsp to 64 bytes
+ #second phase of the reduction
+ vpclmulqdq $0x00, \T7, \T3, \T2
+ vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
- vmovdqu (arg2), %xmm6 # xmm6 = HashKey
+ vpclmulqdq $0x10, \T7, \T3, \T4
+ vpslldq $4, \T4, \T4 # shift-L T4 1 DW (Shift-L 1-DW to obtain result with no shifts)
- vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
- ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
- vmovdqa %xmm6, %xmm2
- vpsllq $1, %xmm6, %xmm6
- vpsrlq $63, %xmm2, %xmm2
- vmovdqa %xmm2, %xmm1
- vpslldq $8, %xmm2, %xmm2
- vpsrldq $8, %xmm1, %xmm1
- vpor %xmm2, %xmm6, %xmm6
- #reduction
- vpshufd $0b00100100, %xmm1, %xmm2
- vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
- vpand POLY(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
+ vpxor \T2, \T4, \T4 # second phase of the reduction complete
#######################################################################
- vmovdqa %xmm6, HashKey(arg1) # store HashKey<<1 mod poly
-
+ vpxor \T4, \T6, \T6 # the result is in T6
+.endm
- PRECOMPUTE_AVX2 %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
- mov %r14, %rsp
- pop %r15
- pop %r14
- pop %r13
- pop %r12
+#############################################################
+#void aesni_gcm_init_avx_gen4
+# (gcm_data *my_ctx_data,
+# gcm_context_data *data,
+# u8 *iv, /* Pre-counter block j0: 4 byte salt
+# (from Security Association) concatenated with 8 byte
+# Initialisation Vector (from IPSec ESP Payload)
+# concatenated with 0x00000001. 16-byte aligned pointer. */
+# u8 *hash_subkey# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
+# const u8 *aad, /* Additional Authentication Data (AAD)*/
+# u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+#############################################################
+ENTRY(aesni_gcm_init_avx_gen4)
+ FUNC_SAVE
+ INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2
+ FUNC_RESTORE
ret
-ENDPROC(aesni_gcm_precomp_avx_gen4)
-
+ENDPROC(aesni_gcm_init_avx_gen4)
###############################################################################
#void aesni_gcm_enc_avx_gen4(
# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
# const u8 *in, /* Plaintext input */
-# u64 plaintext_len, /* Length of data in Bytes for encryption. */
-# u8 *iv, /* Pre-counter block j0: 4 byte salt
-# (from Security Association) concatenated with 8 byte
-# Initialisation Vector (from IPSec ESP Payload)
-# concatenated with 0x00000001. 16-byte aligned pointer. */
-# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
-# u8 *auth_tag, /* Authenticated Tag output. */
-# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
-# Valid values are 16 (most likely), 12 or 8. */
+# u64 plaintext_len) /* Length of data in Bytes for encryption. */
###############################################################################
-ENTRY(aesni_gcm_enc_avx_gen4)
- GCM_ENC_DEC_AVX2 ENC
+ENTRY(aesni_gcm_enc_update_avx_gen4)
+ FUNC_SAVE
+ mov keysize,%eax
+ cmp $32, %eax
+ je key_256_enc_update4
+ cmp $16, %eax
+ je key_128_enc_update4
+ # must be 192
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 11
+ FUNC_RESTORE
+ ret
+key_128_enc_update4:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 9
+ FUNC_RESTORE
ret
-ENDPROC(aesni_gcm_enc_avx_gen4)
+key_256_enc_update4:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_enc_update_avx_gen4)
###############################################################################
-#void aesni_gcm_dec_avx_gen4(
+#void aesni_gcm_dec_update_avx_gen4(
# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
# const u8 *in, /* Ciphertext input */
-# u64 plaintext_len, /* Length of data in Bytes for encryption. */
-# u8 *iv, /* Pre-counter block j0: 4 byte salt
-# (from Security Association) concatenated with 8 byte
-# Initialisation Vector (from IPSec ESP Payload)
-# concatenated with 0x00000001. 16-byte aligned pointer. */
-# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u64 plaintext_len) /* Length of data in Bytes for encryption. */
+###############################################################################
+ENTRY(aesni_gcm_dec_update_avx_gen4)
+ FUNC_SAVE
+ mov keysize,%eax
+ cmp $32, %eax
+ je key_256_dec_update4
+ cmp $16, %eax
+ je key_128_dec_update4
+ # must be 192
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 11
+ FUNC_RESTORE
+ ret
+key_128_dec_update4:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 9
+ FUNC_RESTORE
+ ret
+key_256_dec_update4:
+ GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_dec_update_avx_gen4)
+
+###############################################################################
+#void aesni_gcm_finalize_avx_gen4(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# gcm_context_data *data,
# u8 *auth_tag, /* Authenticated Tag output. */
# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
-# Valid values are 16 (most likely), 12 or 8. */
+# Valid values are 16 (most likely), 12 or 8. */
###############################################################################
-ENTRY(aesni_gcm_dec_avx_gen4)
- GCM_ENC_DEC_AVX2 DEC
- ret
-ENDPROC(aesni_gcm_dec_avx_gen4)
+ENTRY(aesni_gcm_finalize_avx_gen4)
+ FUNC_SAVE
+ mov keysize,%eax
+ cmp $32, %eax
+ je key_256_finalize4
+ cmp $16, %eax
+ je key_128_finalize4
+ # must be 192
+ GCM_COMPLETE GHASH_MUL_AVX2, 11, arg3, arg4
+ FUNC_RESTORE
+ ret
+key_128_finalize4:
+ GCM_COMPLETE GHASH_MUL_AVX2, 9, arg3, arg4
+ FUNC_RESTORE
+ ret
+key_256_finalize4:
+ GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4
+ FUNC_RESTORE
+ ret
+ENDPROC(aesni_gcm_finalize_avx_gen4)
#endif /* CONFIG_AS_AVX2 */