diff options
Diffstat (limited to 'arch/x86/crypto/aesni-intel_asm.S')
-rw-r--r-- | arch/x86/crypto/aesni-intel_asm.S | 1404 |
1 files changed, 688 insertions, 716 deletions
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 12e8484a8ee7..cb2deb61c5d9 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -94,23 +94,30 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define STACK_OFFSET 8*3 -#define HashKey 16*0 // store HashKey <<1 mod poly here -#define HashKey_2 16*1 // store HashKey^2 <<1 mod poly here -#define HashKey_3 16*2 // store HashKey^3 <<1 mod poly here -#define HashKey_4 16*3 // store HashKey^4 <<1 mod poly here -#define HashKey_k 16*4 // store XOR of High 64 bits and Low 64 + +#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 +#define HashKey 16*6 // store HashKey <<1 mod poly here +#define HashKey_2 16*7 // store HashKey^2 <<1 mod poly here +#define HashKey_3 16*8 // store HashKey^3 <<1 mod poly here +#define HashKey_4 16*9 // store HashKey^4 <<1 mod poly here +#define HashKey_k 16*10 // store XOR of High 64 bits and Low 64 // bits of HashKey <<1 mod poly here //(for Karatsuba purposes) -#define HashKey_2_k 16*5 // store XOR of High 64 bits and Low 64 +#define HashKey_2_k 16*11 // store XOR of High 64 bits and Low 64 // bits of HashKey^2 <<1 mod poly here // (for Karatsuba purposes) -#define HashKey_3_k 16*6 // store XOR of High 64 bits and Low 64 +#define HashKey_3_k 16*12 // store XOR of High 64 bits and Low 64 // bits of HashKey^3 <<1 mod poly here // (for Karatsuba purposes) -#define HashKey_4_k 16*7 // store XOR of High 64 bits and Low 64 +#define HashKey_4_k 16*13 // store XOR of High 64 bits and Low 64 // bits of HashKey^4 <<1 mod poly here // (for Karatsuba purposes) -#define VARIABLE_OFFSET 16*8 #define arg1 rdi #define arg2 rsi @@ -118,10 +125,11 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define arg4 rcx #define arg5 r8 #define arg6 r9 -#define arg7 STACK_OFFSET+8(%r14) -#define arg8 STACK_OFFSET+16(%r14) -#define arg9 STACK_OFFSET+24(%r14) -#define arg10 STACK_OFFSET+32(%r14) +#define arg7 STACK_OFFSET+8(%rsp) +#define arg8 STACK_OFFSET+16(%rsp) +#define arg9 STACK_OFFSET+24(%rsp) +#define arg10 STACK_OFFSET+32(%rsp) +#define arg11 STACK_OFFSET+40(%rsp) #define keysize 2*15*16(%arg1) #endif @@ -171,6 +179,332 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define TKEYP T1 #endif +.macro FUNC_SAVE + push %r12 + push %r13 + push %r14 +# +# states of %xmm registers %xmm6:%xmm15 not saved +# all %xmm registers are clobbered +# +.endm + + +.macro FUNC_RESTORE + pop %r14 + pop %r13 + pop %r12 +.endm + +# Precompute hashkeys. +# Input: Hash subkey. +# Output: HashKeys stored in gcm_context_data. Only needs to be called +# once per key. +# clobbers r12, and tmp xmm registers. +.macro PRECOMPUTE SUBKEY TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 TMP7 + mov \SUBKEY, %r12 + movdqu (%r12), \TMP3 + movdqa SHUF_MASK(%rip), \TMP2 + PSHUFB_XMM \TMP2, \TMP3 + + # precompute HashKey<<1 mod poly from the HashKey (required for GHASH) + + movdqa \TMP3, \TMP2 + psllq $1, \TMP3 + psrlq $63, \TMP2 + movdqa \TMP2, \TMP1 + pslldq $8, \TMP2 + psrldq $8, \TMP1 + por \TMP2, \TMP3 + + # reduce HashKey<<1 + + pshufd $0x24, \TMP1, \TMP2 + pcmpeqd TWOONE(%rip), \TMP2 + pand POLY(%rip), \TMP2 + pxor \TMP2, \TMP3 + movdqu \TMP3, HashKey(%arg2) + + movdqa \TMP3, \TMP5 + pshufd $78, \TMP3, \TMP1 + pxor \TMP3, \TMP1 + movdqu \TMP1, HashKey_k(%arg2) + + GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 +# TMP5 = HashKey^2<<1 (mod poly) + movdqu \TMP5, HashKey_2(%arg2) +# HashKey_2 = HashKey^2<<1 (mod poly) + pshufd $78, \TMP5, \TMP1 + pxor \TMP5, \TMP1 + movdqu \TMP1, HashKey_2_k(%arg2) + + GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 +# TMP5 = HashKey^3<<1 (mod poly) + movdqu \TMP5, HashKey_3(%arg2) + pshufd $78, \TMP5, \TMP1 + pxor \TMP5, \TMP1 + movdqu \TMP1, HashKey_3_k(%arg2) + + GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 +# TMP5 = HashKey^3<<1 (mod poly) + movdqu \TMP5, HashKey_4(%arg2) + pshufd $78, \TMP5, \TMP1 + pxor \TMP5, \TMP1 + movdqu \TMP1, HashKey_4_k(%arg2) +.endm + +# GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding. +# Clobbers rax, r10-r13 and xmm0-xmm6, %xmm13 +.macro GCM_INIT Iv SUBKEY AAD AADLEN + mov \AADLEN, %r11 + mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length + xor %r11d, %r11d + mov %r11, InLen(%arg2) # ctx_data.in_length = 0 + mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0 + mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0 + mov \Iv, %rax + movdqu (%rax), %xmm0 + movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv + + movdqa SHUF_MASK(%rip), %xmm2 + PSHUFB_XMM %xmm2, %xmm0 + movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv + + PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + movdqu HashKey(%arg2), %xmm13 + + CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ + %xmm4, %xmm5, %xmm6 +.endm + +# GCM_ENC_DEC Encodes/Decodes given data. Assumes that the passed gcm_context +# struct has been initialized by GCM_INIT. +# Requires the input data be at least 1 byte long because of READ_PARTIAL_BLOCK +# Clobbers rax, r10-r13, and xmm0-xmm15 +.macro GCM_ENC_DEC operation + movdqu AadHash(%arg2), %xmm8 + movdqu HashKey(%arg2), %xmm13 + add %arg5, InLen(%arg2) + + xor %r11d, %r11d # initialise the data pointer offset as zero + PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation + + sub %r11, %arg5 # sub partial block data used + mov %arg5, %r13 # save the number of bytes + + and $-16, %r13 # %r13 = %r13 - (%r13 mod 16) + mov %r13, %r12 + # Encrypt/Decrypt first few blocks + + and $(3<<4), %r12 + jz _initial_num_blocks_is_0_\@ + cmp $(2<<4), %r12 + jb _initial_num_blocks_is_1_\@ + je _initial_num_blocks_is_2_\@ +_initial_num_blocks_is_3_\@: + INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ +%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, \operation + sub $48, %r13 + jmp _initial_blocks_\@ +_initial_num_blocks_is_2_\@: + INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ +%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, \operation + sub $32, %r13 + jmp _initial_blocks_\@ +_initial_num_blocks_is_1_\@: + INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ +%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, \operation + sub $16, %r13 + jmp _initial_blocks_\@ +_initial_num_blocks_is_0_\@: + INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ +%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, \operation +_initial_blocks_\@: + + # Main loop - Encrypt/Decrypt remaining blocks + + cmp $0, %r13 + je _zero_cipher_left_\@ + sub $64, %r13 + je _four_cipher_left_\@ +_crypt_by_4_\@: + GHASH_4_ENCRYPT_4_PARALLEL_\operation %xmm9, %xmm10, %xmm11, %xmm12, \ + %xmm13, %xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, \ + %xmm7, %xmm8, enc + add $64, %r11 + sub $64, %r13 + jne _crypt_by_4_\@ +_four_cipher_left_\@: + GHASH_LAST_4 %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \ +%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8 +_zero_cipher_left_\@: + movdqu %xmm8, AadHash(%arg2) + movdqu %xmm0, CurCount(%arg2) + + mov %arg5, %r13 + and $15, %r13 # %r13 = arg5 (mod 16) + je _multiple_of_16_bytes_\@ + + mov %r13, PBlockLen(%arg2) + + # Handle the last <16 Byte block separately + paddd ONE(%rip), %xmm0 # INCR CNT to get Yn + movdqu %xmm0, CurCount(%arg2) + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10, %xmm0 + + ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn) + movdqu %xmm0, PBlockEncKey(%arg2) + + cmp $16, %arg5 + jge _large_enough_update_\@ + + lea (%arg4,%r11,1), %r10 + mov %r13, %r12 + READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1 + jmp _data_read_\@ + +_large_enough_update_\@: + sub $16, %r11 + add %r13, %r11 + + # receive the last <16 Byte block + movdqu (%arg4, %r11, 1), %xmm1 + + sub %r13, %r11 + add $16, %r11 + + 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 + movdqu (%r12), %xmm2 + # shift right 16-r13 bytes + PSHUFB_XMM %xmm2, %xmm1 + +_data_read_\@: + lea ALL_F+16(%rip), %r12 + sub %r13, %r12 + +.ifc \operation, dec + movdqa %xmm1, %xmm2 +.endif + pxor %xmm1, %xmm0 # XOR Encrypt(K, Yn) + movdqu (%r12), %xmm1 + # get the appropriate mask to mask out top 16-r13 bytes of xmm0 + pand %xmm1, %xmm0 # mask out top 16-r13 bytes of xmm0 +.ifc \operation, dec + pand %xmm1, %xmm2 + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10 ,%xmm2 + + pxor %xmm2, %xmm8 +.else + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10,%xmm0 + + pxor %xmm0, %xmm8 +.endif + + movdqu %xmm8, AadHash(%arg2) +.ifc \operation, enc + # GHASH computation for the last <16 byte block + movdqa SHUF_MASK(%rip), %xmm10 + # shuffle xmm0 back to output as ciphertext + PSHUFB_XMM %xmm10, %xmm0 +.endif + + # Output %r13 bytes + MOVQ_R64_XMM %xmm0, %rax + cmp $8, %r13 + jle _less_than_8_bytes_left_\@ + mov %rax, (%arg3 , %r11, 1) + add $8, %r11 + psrldq $8, %xmm0 + MOVQ_R64_XMM %xmm0, %rax + sub $8, %r13 +_less_than_8_bytes_left_\@: + mov %al, (%arg3, %r11, 1) + add $1, %r11 + shr $8, %rax + sub $1, %r13 + jne _less_than_8_bytes_left_\@ +_multiple_of_16_bytes_\@: +.endm + +# 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 AUTHTAG AUTHTAGLEN + movdqu AadHash(%arg2), %xmm8 + movdqu HashKey(%arg2), %xmm13 + + mov PBlockLen(%arg2), %r12 + + cmp $0, %r12 + je _partial_done\@ + + GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 + +_partial_done\@: + mov AadLen(%arg2), %r12 # %r13 = aadLen (number of bytes) + shl $3, %r12 # convert into number of bits + movd %r12d, %xmm15 # len(A) in %xmm15 + mov InLen(%arg2), %r12 + shl $3, %r12 # len(C) in bits (*128) + MOVQ_R64_XMM %r12, %xmm1 + + pslldq $8, %xmm15 # %xmm15 = len(A)||0x0000000000000000 + pxor %xmm1, %xmm15 # %xmm15 = len(A)||len(C) + pxor %xmm15, %xmm8 + GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 + # final GHASH computation + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10, %xmm8 + + movdqu OrigIV(%arg2), %xmm0 # %xmm0 = Y0 + ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Y0) + pxor %xmm8, %xmm0 +_return_T_\@: + mov \AUTHTAG, %r10 # %r10 = authTag + mov \AUTHTAGLEN, %r11 # %r11 = auth_tag_len + cmp $16, %r11 + je _T_16_\@ + cmp $8, %r11 + jl _T_4_\@ +_T_8_\@: + MOVQ_R64_XMM %xmm0, %rax + mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 + psrldq $8, %xmm0 + cmp $0, %r11 + je _return_T_done_\@ +_T_4_\@: + movd %xmm0, %eax + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + psrldq $4, %xmm0 + cmp $0, %r11 + je _return_T_done_\@ +_T_123_\@: + movd %xmm0, %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_\@ +_T_16_\@: + movdqu %xmm0, (%r10) +_return_T_done_\@: +.endm #ifdef __x86_64__ /* GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0) @@ -264,232 +598,188 @@ _read_next_byte_lt8_\@: _done_read_partial_block_\@: .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, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers -* are clobbered -* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified -*/ - - -.macro INITIAL_BLOCKS_DEC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \ -XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation - MOVADQ SHUF_MASK(%rip), %xmm14 - mov arg7, %r10 # %r10 = AAD - mov arg8, %r11 # %r11 = aadLen - pxor %xmm\i, %xmm\i - pxor \XMM2, \XMM2 +# CALC_AAD_HASH: Calculates the hash of the data which will not be encrypted. +# clobbers r10-11, xmm14 +.macro CALC_AAD_HASH HASHKEY AAD AADLEN TMP1 TMP2 TMP3 TMP4 TMP5 \ + TMP6 TMP7 + MOVADQ SHUF_MASK(%rip), %xmm14 + mov \AAD, %r10 # %r10 = AAD + mov \AADLEN, %r11 # %r11 = aadLen + pxor \TMP7, \TMP7 + pxor \TMP6, \TMP6 cmp $16, %r11 - jl _get_AAD_rest\num_initial_blocks\operation -_get_AAD_blocks\num_initial_blocks\operation: - movdqu (%r10), %xmm\i - PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data - pxor %xmm\i, \XMM2 - GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + jl _get_AAD_rest\@ +_get_AAD_blocks\@: + movdqu (%r10), \TMP7 + PSHUFB_XMM %xmm14, \TMP7 # byte-reflect the AAD data + pxor \TMP7, \TMP6 + GHASH_MUL \TMP6, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5 add $16, %r10 sub $16, %r11 cmp $16, %r11 - jge _get_AAD_blocks\num_initial_blocks\operation + jge _get_AAD_blocks\@ - movdqu \XMM2, %xmm\i + movdqu \TMP6, \TMP7 /* read the last <16B of AAD */ -_get_AAD_rest\num_initial_blocks\operation: +_get_AAD_rest\@: cmp $0, %r11 - je _get_AAD_done\num_initial_blocks\operation - - READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i - PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data - pxor \XMM2, %xmm\i - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + je _get_AAD_done\@ -_get_AAD_done\num_initial_blocks\operation: - xor %r11, %r11 # initialise the data pointer offset as zero - # start AES for num_initial_blocks blocks - - mov %arg5, %rax # %rax = *Y0 - movdqu (%rax), \XMM0 # XMM0 = Y0 - PSHUFB_XMM %xmm14, \XMM0 + READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7 + PSHUFB_XMM %xmm14, \TMP7 # byte-reflect the AAD data + pxor \TMP6, \TMP7 + GHASH_MUL \TMP7, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5 + movdqu \TMP7, \TMP6 -.if (\i == 5) || (\i == 6) || (\i == 7) - MOVADQ ONE(%RIP),\TMP1 - MOVADQ (%arg1),\TMP2 -.irpc index, \i_seq - paddd \TMP1, \XMM0 # INCR Y0 - movdqa \XMM0, %xmm\index - PSHUFB_XMM %xmm14, %xmm\index # perform a 16 byte swap - pxor \TMP2, %xmm\index -.endr - lea 0x10(%arg1),%r10 - mov keysize,%eax - shr $2,%eax # 128->4, 192->6, 256->8 - add $5,%eax # 128->9, 192->11, 256->13 - -aes_loop_initial_dec\num_initial_blocks: - MOVADQ (%r10),\TMP1 -.irpc index, \i_seq - AESENC \TMP1, %xmm\index -.endr - add $16,%r10 - sub $1,%eax - jnz aes_loop_initial_dec\num_initial_blocks - - MOVADQ (%r10), \TMP1 -.irpc index, \i_seq - AESENCLAST \TMP1, %xmm\index # Last Round -.endr -.irpc index, \i_seq - movdqu (%arg3 , %r11, 1), \TMP1 - pxor \TMP1, %xmm\index - movdqu %xmm\index, (%arg2 , %r11, 1) - # write back plaintext/ciphertext for num_initial_blocks - add $16, %r11 - - movdqa \TMP1, %xmm\index - PSHUFB_XMM %xmm14, %xmm\index - # prepare plaintext/ciphertext for GHASH computation -.endr -.endif - - # apply GHASH on num_initial_blocks blocks +_get_AAD_done\@: + movdqu \TMP6, AadHash(%arg2) +.endm -.if \i == 5 - pxor %xmm5, %xmm6 - GHASH_MUL %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 - pxor %xmm6, %xmm7 - GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 - pxor %xmm7, %xmm8 - GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 -.elseif \i == 6 - pxor %xmm6, %xmm7 - GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 - pxor %xmm7, %xmm8 - GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 -.elseif \i == 7 - pxor %xmm7, %xmm8 - GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 +# 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 CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \ + AAD_HASH operation + 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_\@ + movups (\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 %xmm0 %xmm1 + + mov PBlockLen(%arg2), %r13 + +_data_read_\@: # Finished reading in data + + movdqu PBlockEncKey(%arg2), %xmm9 + movdqu 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 + movdqu (%r12), %xmm2 # get the appropriate shuffle mask + PSHUFB_XMM %xmm2, %xmm9 # shift right r13 bytes + +.ifc \operation, dec + movdqa %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_\@: + + movdqu ALL_F-SHIFT_MASK(%r12), %xmm1 + # get the appropriate mask to mask out bottom r13 bytes of xmm9 + pand %xmm1, %xmm9 # mask out bottom r13 bytes of xmm9 + + pand %xmm1, %xmm3 + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10, %xmm3 + PSHUFB_XMM %xmm2, %xmm3 + pxor %xmm3, \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_\@: + movdqu \AAD_HASH, AadHash(%arg2) +.else + pxor %xmm1, %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_\@: + + movdqu ALL_F-SHIFT_MASK(%r12), %xmm1 + # get the appropriate mask to mask out bottom r13 bytes of xmm9 + pand %xmm1, %xmm9 + + movdqa SHUF_MASK(%rip), %xmm1 + PSHUFB_XMM %xmm1, %xmm9 + PSHUFB_XMM %xmm2, %xmm9 + pxor %xmm9, \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_\@: + movdqu \AAD_HASH, AadHash(%arg2) + + movdqa SHUF_MASK(%rip), %xmm10 + # shuffle xmm9 back to output as ciphertext + PSHUFB_XMM %xmm10, %xmm9 + PSHUFB_XMM %xmm2, %xmm9 .endif - cmp $64, %r13 - jl _initial_blocks_done\num_initial_blocks\operation - # no need for precomputed values -/* -* -* Precomputations for HashKey parallel with encryption of first 4 blocks. -* Haskey_i_k holds XORed values of the low and high parts of the Haskey_i -*/ - MOVADQ ONE(%rip), \TMP1 - paddd \TMP1, \XMM0 # INCR Y0 - MOVADQ \XMM0, \XMM1 - PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap - - paddd \TMP1, \XMM0 # INCR Y0 - MOVADQ \XMM0, \XMM2 - PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap - - paddd \TMP1, \XMM0 # INCR Y0 - MOVADQ \XMM0, \XMM3 - PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap - - paddd \TMP1, \XMM0 # INCR Y0 - MOVADQ \XMM0, \XMM4 - PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap - - MOVADQ 0(%arg1),\TMP1 - pxor \TMP1, \XMM1 - pxor \TMP1, \XMM2 - pxor \TMP1, \XMM3 - pxor \TMP1, \XMM4 - movdqa \TMP3, \TMP5 - pshufd $78, \TMP3, \TMP1 - pxor \TMP3, \TMP1 - movdqa \TMP1, HashKey_k(%rsp) - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^2<<1 (mod poly) - movdqa \TMP5, HashKey_2(%rsp) -# HashKey_2 = HashKey^2<<1 (mod poly) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_2_k(%rsp) -.irpc index, 1234 # do 4 rounds - movaps 0x10*\index(%arg1), \TMP1 - AESENC \TMP1, \XMM1 - AESENC \TMP1, \XMM2 - AESENC \TMP1, \XMM3 - AESENC \TMP1, \XMM4 -.endr - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_3(%rsp) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_3_k(%rsp) -.irpc index, 56789 # do next 5 rounds - movaps 0x10*\index(%arg1), \TMP1 - AESENC \TMP1, \XMM1 - AESENC \TMP1, \XMM2 - AESENC \TMP1, \XMM3 - AESENC \TMP1, \XMM4 -.endr - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_4(%rsp) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_4_k(%rsp) - lea 0xa0(%arg1),%r10 - mov keysize,%eax - shr $2,%eax # 128->4, 192->6, 256->8 - sub $4,%eax # 128->0, 192->2, 256->4 - jz aes_loop_pre_dec_done\num_initial_blocks - -aes_loop_pre_dec\num_initial_blocks: - MOVADQ (%r10),\TMP2 -.irpc index, 1234 - AESENC \TMP2, %xmm\index -.endr - add $16,%r10 - sub $1,%eax - jnz aes_loop_pre_dec\num_initial_blocks - -aes_loop_pre_dec_done\num_initial_blocks: - MOVADQ (%r10), \TMP2 - AESENCLAST \TMP2, \XMM1 - AESENCLAST \TMP2, \XMM2 - AESENCLAST \TMP2, \XMM3 - AESENCLAST \TMP2, \XMM4 - movdqu 16*0(%arg3 , %r11 , 1), \TMP1 - pxor \TMP1, \XMM1 - movdqu \XMM1, 16*0(%arg2 , %r11 , 1) - movdqa \TMP1, \XMM1 - movdqu 16*1(%arg3 , %r11 , 1), \TMP1 - pxor \TMP1, \XMM2 - movdqu \XMM2, 16*1(%arg2 , %r11 , 1) - movdqa \TMP1, \XMM2 - movdqu 16*2(%arg3 , %r11 , 1), \TMP1 - pxor \TMP1, \XMM3 - movdqu \XMM3, 16*2(%arg2 , %r11 , 1) - movdqa \TMP1, \XMM3 - movdqu 16*3(%arg3 , %r11 , 1), \TMP1 - pxor \TMP1, \XMM4 - movdqu \XMM4, 16*3(%arg2 , %r11 , 1) - movdqa \TMP1, \XMM4 - add $64, %r11 - PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap - pxor \XMMDst, \XMM1 -# combine GHASHed value with the corresponding ciphertext - PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap - PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap - PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap - -_initial_blocks_done\num_initial_blocks\operation: - -.endm + # 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_\@: + movdqa %xmm9, %xmm0 + MOVQ_R64_XMM %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 + MOVQ_R64_XMM %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 /* * if a = number of total plaintext bytes @@ -499,49 +789,19 @@ _initial_blocks_done\num_initial_blocks\operation: * the ciphertext * %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers * are clobbered -* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified +* arg1, %arg2, %arg3 are used as a pointer only, not modified */ -.macro INITIAL_BLOCKS_ENC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \ -XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation - MOVADQ SHUF_MASK(%rip), %xmm14 - mov arg7, %r10 # %r10 = AAD - mov arg8, %r11 # %r11 = aadLen - pxor %xmm\i, %xmm\i - pxor \XMM2, \XMM2 +.macro INITIAL_BLOCKS_ENC_DEC TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \ + XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation + MOVADQ SHUF_MASK(%rip), %xmm14 - cmp $16, %r11 - jl _get_AAD_rest\num_initial_blocks\operation -_get_AAD_blocks\num_initial_blocks\operation: - movdqu (%r10), %xmm\i - PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data - pxor %xmm\i, \XMM2 - GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 - add $16, %r10 - sub $16, %r11 - cmp $16, %r11 - jge _get_AAD_blocks\num_initial_blocks\operation + movdqu AadHash(%arg2), %xmm\i # XMM0 = Y0 - movdqu \XMM2, %xmm\i - - /* read the last <16B of AAD */ -_get_AAD_rest\num_initial_blocks\operation: - cmp $0, %r11 - je _get_AAD_done\num_initial_blocks\operation - - READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i - PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data - pxor \XMM2, %xmm\i - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 - -_get_AAD_done\num_initial_blocks\operation: - xor %r11, %r11 # initialise the data pointer offset as zero # start AES for num_initial_blocks blocks - mov %arg5, %rax # %rax = *Y0 - movdqu (%rax), \XMM0 # XMM0 = Y0 - PSHUFB_XMM %xmm14, \XMM0 + movdqu CurCount(%arg2), \XMM0 # XMM0 = Y0 .if (\i == 5) || (\i == 6) || (\i == 7) @@ -549,7 +809,11 @@ _get_AAD_done\num_initial_blocks\operation: MOVADQ 0(%arg1),\TMP2 .irpc index, \i_seq paddd \TMP1, \XMM0 # INCR Y0 +.ifc \operation, dec + movdqa \XMM0, %xmm\index +.else MOVADQ \XMM0, %xmm\index +.endif PSHUFB_XMM %xmm14, %xmm\index # perform a 16 byte swap pxor \TMP2, %xmm\index .endr @@ -558,25 +822,29 @@ _get_AAD_done\num_initial_blocks\operation: shr $2,%eax # 128->4, 192->6, 256->8 add $5,%eax # 128->9, 192->11, 256->13 -aes_loop_initial_enc\num_initial_blocks: +aes_loop_initial_\@: MOVADQ (%r10),\TMP1 .irpc index, \i_seq AESENC \TMP1, %xmm\index .endr add $16,%r10 sub $1,%eax - jnz aes_loop_initial_enc\num_initial_blocks + jnz aes_loop_initial_\@ MOVADQ (%r10), \TMP1 .irpc index, \i_seq AESENCLAST \TMP1, %xmm\index # Last Round .endr .irpc index, \i_seq - movdqu (%arg3 , %r11, 1), \TMP1 + movdqu (%arg4 , %r11, 1), \TMP1 pxor \TMP1, %xmm\index - movdqu %xmm\index, (%arg2 , %r11, 1) + movdqu %xmm\index, (%arg3 , %r11, 1) # write back plaintext/ciphertext for num_initial_blocks add $16, %r11 + +.ifc \operation, dec + movdqa \TMP1, %xmm\index +.endif PSHUFB_XMM %xmm14, %xmm\index # prepare plaintext/ciphertext for GHASH computation @@ -602,7 +870,7 @@ aes_loop_initial_enc\num_initial_blocks: GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 .endif cmp $64, %r13 - jl _initial_blocks_done\num_initial_blocks\operation + jl _initial_blocks_done\@ # no need for precomputed values /* * @@ -631,17 +899,6 @@ aes_loop_initial_enc\num_initial_blocks: pxor \TMP1, \XMM2 pxor \TMP1, \XMM3 pxor \TMP1, \XMM4 - movdqa \TMP3, \TMP5 - pshufd $78, \TMP3, \TMP1 - pxor \TMP3, \TMP1 - movdqa \TMP1, HashKey_k(%rsp) - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^2<<1 (mod poly) - movdqa \TMP5, HashKey_2(%rsp) -# HashKey_2 = HashKey^2<<1 (mod poly) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_2_k(%rsp) .irpc index, 1234 # do 4 rounds movaps 0x10*\index(%arg1), \TMP1 AESENC \TMP1, \XMM1 @@ -649,12 +906,6 @@ aes_loop_initial_enc\num_initial_blocks: AESENC \TMP1, \XMM3 AESENC \TMP1, \XMM4 .endr - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_3(%rsp) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_3_k(%rsp) .irpc index, 56789 # do next 5 rounds movaps 0x10*\index(%arg1), \TMP1 AESENC \TMP1, \XMM1 @@ -662,45 +913,56 @@ aes_loop_initial_enc\num_initial_blocks: AESENC \TMP1, \XMM3 AESENC \TMP1, \XMM4 .endr - GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 -# TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_4(%rsp) - pshufd $78, \TMP5, \TMP1 - pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_4_k(%rsp) lea 0xa0(%arg1),%r10 mov keysize,%eax shr $2,%eax # 128->4, 192->6, 256->8 sub $4,%eax # 128->0, 192->2, 256->4 - jz aes_loop_pre_enc_done\num_initial_blocks + jz aes_loop_pre_done\@ -aes_loop_pre_enc\num_initial_blocks: +aes_loop_pre_\@: MOVADQ (%r10),\TMP2 .irpc index, 1234 AESENC \TMP2, %xmm\index .endr add $16,%r10 sub $1,%eax - jnz aes_loop_pre_enc\num_initial_blocks + jnz aes_loop_pre_\@ -aes_loop_pre_enc_done\num_initial_blocks: +aes_loop_pre_done\@: MOVADQ (%r10), \TMP2 AESENCLAST \TMP2, \XMM1 AESENCLAST \TMP2, \XMM2 AESENCLAST \TMP2, \XMM3 AESENCLAST \TMP2, \XMM4 - movdqu 16*0(%arg3 , %r11 , 1), \TMP1 + movdqu 16*0(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM1 - movdqu 16*1(%arg3 , %r11 , 1), \TMP1 +.ifc \operation, dec + movdqu \XMM1, 16*0(%arg3 , %r11 , 1) + movdqa \TMP1, \XMM1 +.endif + movdqu 16*1(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM2 - movdqu 16*2(%arg3 , %r11 , 1), \TMP1 +.ifc \operation, dec + movdqu \XMM2, 16*1(%arg3 , %r11 , 1) + movdqa \TMP1, \XMM2 +.endif + movdqu 16*2(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM3 - movdqu 16*3(%arg3 , %r11 , 1), \TMP1 +.ifc \operation, dec + movdqu \XMM3, 16*2(%arg3 , %r11 , 1) + movdqa \TMP1, \XMM3 +.endif + movdqu 16*3(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM4 - movdqu \XMM1, 16*0(%arg2 , %r11 , 1) - movdqu \XMM2, 16*1(%arg2 , %r11 , 1) - movdqu \XMM3, 16*2(%arg2 , %r11 , 1) - movdqu \XMM4, 16*3(%arg2 , %r11 , 1) +.ifc \operation, dec + movdqu \XMM4, 16*3(%arg3 , %r11 , 1) + movdqa \TMP1, \XMM4 +.else + movdqu \XMM1, 16*0(%arg3 , %r11 , 1) + movdqu \XMM2, 16*1(%arg3 , %r11 , 1) + movdqu \XMM3, 16*2(%arg3 , %r11 , 1) + movdqu \XMM4, 16*3(%arg3 , %r11 , 1) +.endif add $64, %r11 PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap @@ -710,14 +972,14 @@ aes_loop_pre_enc_done\num_initial_blocks: PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap -_initial_blocks_done\num_initial_blocks\operation: +_initial_blocks_done\@: .endm /* * encrypt 4 blocks at a time * ghash the 4 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_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \ @@ -735,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%rsp), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -754,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%rsp), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -769,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%rsp), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -782,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%rsp), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -796,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%rsp ), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -812,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%rsp), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -830,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%rsp), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -842,37 +1104,37 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation mov keysize,%eax shr $2,%eax # 128->4, 192->6, 256->8 sub $4,%eax # 128->0, 192->2, 256->4 - jz aes_loop_par_enc_done + jz aes_loop_par_enc_done\@ -aes_loop_par_enc: +aes_loop_par_enc\@: MOVADQ (%r10),\TMP3 .irpc index, 1234 AESENC \TMP3, %xmm\index .endr add $16,%r10 sub $1,%eax - jnz aes_loop_par_enc + jnz aes_loop_par_enc\@ -aes_loop_par_enc_done: +aes_loop_par_enc_done\@: MOVADQ (%r10), \TMP3 AESENCLAST \TMP3, \XMM1 # Round 10 AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%rsp), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) - movdqu (%arg3,%r11,1), \TMP3 + movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK - movdqu 16(%arg3,%r11,1), \TMP3 + movdqu 16(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM2 # Ciphertext/Plaintext XOR EK - movdqu 32(%arg3,%r11,1), \TMP3 + movdqu 32(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM3 # Ciphertext/Plaintext XOR EK - movdqu 48(%arg3,%r11,1), \TMP3 + movdqu 48(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM4 # Ciphertext/Plaintext XOR EK - movdqu \XMM1, (%arg2,%r11,1) # Write to the ciphertext buffer - movdqu \XMM2, 16(%arg2,%r11,1) # Write to the ciphertext buffer - movdqu \XMM3, 32(%arg2,%r11,1) # Write to the ciphertext buffer - movdqu \XMM4, 48(%arg2,%r11,1) # Write to the ciphertext buffer + movdqu \XMM1, (%arg3,%r11,1) # Write to the ciphertext buffer + movdqu \XMM2, 16(%arg3,%r11,1) # Write to the ciphertext buffer + movdqu \XMM3, 32(%arg3,%r11,1) # Write to the ciphertext buffer + movdqu \XMM4, 48(%arg3,%r11,1) # Write to the ciphertext buffer PSHUFB_XMM %xmm15, \XMM1 # perform a 16 byte swap PSHUFB_XMM %xmm15, \XMM2 # perform a 16 byte swap PSHUFB_XMM %xmm15, \XMM3 # perform a 16 byte swap @@ -925,7 +1187,7 @@ aes_loop_par_enc_done: /* * decrypt 4 blocks at a time * ghash the 4 previously decrypted 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_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \ @@ -943,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%rsp), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -962,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%rsp), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -977,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%rsp), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -990,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%rsp), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -1004,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%rsp ), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -1020,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%rsp), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -1038,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%rsp), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -1050,40 +1312,40 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation mov keysize,%eax shr $2,%eax # 128->4, 192->6, 256->8 sub $4,%eax # 128->0, 192->2, 256->4 - jz aes_loop_par_dec_done + jz aes_loop_par_dec_done\@ -aes_loop_par_dec: +aes_loop_par_dec\@: MOVADQ (%r10),\TMP3 .irpc index, 1234 AESENC \TMP3, %xmm\index .endr add $16,%r10 sub $1,%eax - jnz aes_loop_par_dec + jnz aes_loop_par_dec\@ -aes_loop_par_dec_done: +aes_loop_par_dec_done\@: MOVADQ (%r10), \TMP3 AESENCLAST \TMP3, \XMM1 # last round AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%rsp), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) - movdqu (%arg3,%r11,1), \TMP3 + movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK - movdqu \XMM1, (%arg2,%r11,1) # Write to plaintext buffer + movdqu \XMM1, (%arg3,%r11,1) # Write to plaintext buffer movdqa \TMP3, \XMM1 - movdqu 16(%arg3,%r11,1), \TMP3 + movdqu 16(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM2 # Ciphertext/Plaintext XOR EK - movdqu \XMM2, 16(%arg2,%r11,1) # Write to plaintext buffer + movdqu \XMM2, 16(%arg3,%r11,1) # Write to plaintext buffer movdqa \TMP3, \XMM2 - movdqu 32(%arg3,%r11,1), \TMP3 + movdqu 32(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM3 # Ciphertext/Plaintext XOR EK - movdqu \XMM3, 32(%arg2,%r11,1) # Write to plaintext buffer + movdqu \XMM3, 32(%arg3,%r11,1) # Write to plaintext buffer movdqa \TMP3, \XMM3 - movdqu 48(%arg3,%r11,1), \TMP3 + movdqu 48(%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM4 # Ciphertext/Plaintext XOR EK - movdqu \XMM4, 48(%arg2,%r11,1) # Write to plaintext buffer + movdqu \XMM4, 48(%arg3,%r11,1) # Write to plaintext buffer movdqa \TMP3, \XMM4 PSHUFB_XMM %xmm15, \XMM1 # perform a 16 byte swap PSHUFB_XMM %xmm15, \XMM2 # perform a 16 byte swap @@ -1143,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM1, \TMP6 pshufd $78, \XMM1, \TMP2 pxor \XMM1, \TMP2 - movdqa HashKey_4(%rsp), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP6 # TMP6 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM1 # XMM1 = a0*b0 - movdqa HashKey_4_k(%rsp), \TMP4 + movdqu HashKey_4_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqa \XMM1, \XMMDst movdqa \TMP2, \XMM1 # result in TMP6, XMMDst, XMM1 @@ -1156,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM2, \TMP1 pshufd $78, \XMM2, \TMP2 pxor \XMM2, \TMP2 - movdqa HashKey_3(%rsp), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM2 # XMM2 = a0*b0 - movdqa HashKey_3_k(%rsp), \TMP4 + movdqu HashKey_3_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM2, \XMMDst @@ -1171,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM3, \TMP1 pshufd $78, \XMM3, \TMP2 pxor \XMM3, \TMP2 - movdqa HashKey_2(%rsp), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM3 # XMM3 = a0*b0 - movdqa HashKey_2_k(%rsp), \TMP4 + movdqu HashKey_2_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM3, \XMMDst @@ -1184,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM4, \TMP1 pshufd $78, \XMM4, \TMP2 pxor \XMM4, \TMP2 - movdqa HashKey(%rsp), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM4 # XMM4 = a0*b0 - movdqa HashKey_k(%rsp), \TMP4 + movdqu HashKey_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM4, \XMMDst @@ -1256,6 +1518,8 @@ _esb_loop_\@: .endm /***************************************************************************** * void aesni_gcm_dec(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data +* // Context data * u8 *out, // Plaintext output. Encrypt in-place is allowed. * const u8 *in, // Ciphertext input * u64 plaintext_len, // Length of data in bytes for decryption. @@ -1333,195 +1597,20 @@ _esb_loop_\@: * *****************************************************************************/ ENTRY(aesni_gcm_dec) - push %r12 - push %r13 - push %r14 - mov %rsp, %r14 -/* -* states of %xmm registers %xmm6:%xmm15 not saved -* all %xmm registers are clobbered -*/ - sub $VARIABLE_OFFSET, %rsp - and $~63, %rsp # align rsp to 64 bytes - mov %arg6, %r12 - movdqu (%r12), %xmm13 # %xmm13 = HashKey - movdqa SHUF_MASK(%rip), %xmm2 - PSHUFB_XMM %xmm2, %xmm13 - - -# Precompute HashKey<<1 (mod poly) from the hash key (required for GHASH) - - movdqa %xmm13, %xmm2 - psllq $1, %xmm13 - psrlq $63, %xmm2 - movdqa %xmm2, %xmm1 - pslldq $8, %xmm2 - psrldq $8, %xmm1 - por %xmm2, %xmm13 - - # Reduction - - pshufd $0x24, %xmm1, %xmm2 - pcmpeqd TWOONE(%rip), %xmm2 - pand POLY(%rip), %xmm2 - pxor %xmm2, %xmm13 # %xmm13 holds the HashKey<<1 (mod poly) - - - # Decrypt first few blocks - - movdqa %xmm13, HashKey(%rsp) # store HashKey<<1 (mod poly) - mov %arg4, %r13 # save the number of bytes of plaintext/ciphertext - and $-16, %r13 # %r13 = %r13 - (%r13 mod 16) - mov %r13, %r12 - and $(3<<4), %r12 - jz _initial_num_blocks_is_0_decrypt - cmp $(2<<4), %r12 - jb _initial_num_blocks_is_1_decrypt - je _initial_num_blocks_is_2_decrypt -_initial_num_blocks_is_3_decrypt: - INITIAL_BLOCKS_DEC 3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, dec - sub $48, %r13 - jmp _initial_blocks_decrypted -_initial_num_blocks_is_2_decrypt: - INITIAL_BLOCKS_DEC 2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, dec - sub $32, %r13 - jmp _initial_blocks_decrypted -_initial_num_blocks_is_1_decrypt: - INITIAL_BLOCKS_DEC 1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, dec - sub $16, %r13 - jmp _initial_blocks_decrypted -_initial_num_blocks_is_0_decrypt: - INITIAL_BLOCKS_DEC 0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, dec -_initial_blocks_decrypted: - cmp $0, %r13 - je _zero_cipher_left_decrypt - sub $64, %r13 - je _four_cipher_left_decrypt -_decrypt_by_4: - GHASH_4_ENCRYPT_4_PARALLEL_DEC %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \ -%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, dec - add $64, %r11 - sub $64, %r13 - jne _decrypt_by_4 -_four_cipher_left_decrypt: - GHASH_LAST_4 %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \ -%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8 -_zero_cipher_left_decrypt: - mov %arg4, %r13 - and $15, %r13 # %r13 = arg4 (mod 16) - je _multiple_of_16_bytes_decrypt - - # Handle the last <16 byte block separately - - paddd ONE(%rip), %xmm0 # increment CNT to get Yn - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10, %xmm0 - - ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Yn) - - lea (%arg3,%r11,1), %r10 - mov %r13, %r12 - READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1 - - lea ALL_F+16(%rip), %r12 - sub %r13, %r12 - movdqa %xmm1, %xmm2 - pxor %xmm1, %xmm0 # Ciphertext XOR E(K, Yn) - movdqu (%r12), %xmm1 - # get the appropriate mask to mask out top 16-%r13 bytes of %xmm0 - pand %xmm1, %xmm0 # mask out top 16-%r13 bytes of %xmm0 - pand %xmm1, %xmm2 - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10 ,%xmm2 - - pxor %xmm2, %xmm8 - GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 - - # output %r13 bytes - MOVQ_R64_XMM %xmm0, %rax - cmp $8, %r13 - jle _less_than_8_bytes_left_decrypt - mov %rax, (%arg2 , %r11, 1) - add $8, %r11 - psrldq $8, %xmm0 - MOVQ_R64_XMM %xmm0, %rax - sub $8, %r13 -_less_than_8_bytes_left_decrypt: - mov %al, (%arg2, %r11, 1) - add $1, %r11 - shr $8, %rax - sub $1, %r13 - jne _less_than_8_bytes_left_decrypt -_multiple_of_16_bytes_decrypt: - mov arg8, %r12 # %r13 = aadLen (number of bytes) - shl $3, %r12 # convert into number of bits - movd %r12d, %xmm15 # len(A) in %xmm15 - shl $3, %arg4 # len(C) in bits (*128) - MOVQ_R64_XMM %arg4, %xmm1 - pslldq $8, %xmm15 # %xmm15 = len(A)||0x0000000000000000 - pxor %xmm1, %xmm15 # %xmm15 = len(A)||len(C) - pxor %xmm15, %xmm8 - GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 - # final GHASH computation - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10, %xmm8 + FUNC_SAVE - mov %arg5, %rax # %rax = *Y0 - movdqu (%rax), %xmm0 # %xmm0 = Y0 - ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Y0) - pxor %xmm8, %xmm0 -_return_T_decrypt: - mov arg9, %r10 # %r10 = authTag - mov arg10, %r11 # %r11 = auth_tag_len - cmp $16, %r11 - je _T_16_decrypt - cmp $8, %r11 - jl _T_4_decrypt -_T_8_decrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) - add $8, %r10 - sub $8, %r11 - psrldq $8, %xmm0 - cmp $0, %r11 - je _return_T_done_decrypt -_T_4_decrypt: - movd %xmm0, %eax - mov %eax, (%r10) - add $4, %r10 - sub $4, %r11 - psrldq $4, %xmm0 - cmp $0, %r11 - je _return_T_done_decrypt -_T_123_decrypt: - movd %xmm0, %eax - cmp $2, %r11 - jl _T_1_decrypt - mov %ax, (%r10) - cmp $2, %r11 - je _return_T_done_decrypt - add $2, %r10 - sar $16, %eax -_T_1_decrypt: - mov %al, (%r10) - jmp _return_T_done_decrypt -_T_16_decrypt: - movdqu %xmm0, (%r10) -_return_T_done_decrypt: - mov %r14, %rsp - pop %r14 - pop %r13 - pop %r12 + GCM_INIT %arg6, arg7, arg8, arg9 + GCM_ENC_DEC dec + GCM_COMPLETE arg10, arg11 + FUNC_RESTORE ret ENDPROC(aesni_gcm_dec) /***************************************************************************** * void aesni_gcm_enc(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data +* // Context 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. @@ -1596,195 +1685,78 @@ ENDPROC(aesni_gcm_dec) * poly = x^128 + x^127 + x^126 + x^121 + 1 ***************************************************************************/ ENTRY(aesni_gcm_enc) - push %r12 - push %r13 - push %r14 - mov %rsp, %r14 -# -# states of %xmm registers %xmm6:%xmm15 not saved -# all %xmm registers are clobbered -# - sub $VARIABLE_OFFSET, %rsp - and $~63, %rsp - mov %arg6, %r12 - movdqu (%r12), %xmm13 - movdqa SHUF_MASK(%rip), %xmm2 - PSHUFB_XMM %xmm2, %xmm13 - - -# precompute HashKey<<1 mod poly from the HashKey (required for GHASH) - - movdqa %xmm13, %xmm2 - psllq $1, %xmm13 - psrlq $63, %xmm2 - movdqa %xmm2, %xmm1 - pslldq $8, %xmm2 - psrldq $8, %xmm1 - por %xmm2, %xmm13 - - # reduce HashKey<<1 - - pshufd $0x24, %xmm1, %xmm2 - pcmpeqd TWOONE(%rip), %xmm2 - pand POLY(%rip), %xmm2 - pxor %xmm2, %xmm13 - movdqa %xmm13, HashKey(%rsp) - mov %arg4, %r13 # %xmm13 holds HashKey<<1 (mod poly) - and $-16, %r13 - mov %r13, %r12 + FUNC_SAVE - # Encrypt first few blocks + GCM_INIT %arg6, arg7, arg8, arg9 + GCM_ENC_DEC enc - and $(3<<4), %r12 - jz _initial_num_blocks_is_0_encrypt - cmp $(2<<4), %r12 - jb _initial_num_blocks_is_1_encrypt - je _initial_num_blocks_is_2_encrypt -_initial_num_blocks_is_3_encrypt: - INITIAL_BLOCKS_ENC 3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, enc - sub $48, %r13 - jmp _initial_blocks_encrypted -_initial_num_blocks_is_2_encrypt: - INITIAL_BLOCKS_ENC 2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, enc - sub $32, %r13 - jmp _initial_blocks_encrypted -_initial_num_blocks_is_1_encrypt: - INITIAL_BLOCKS_ENC 1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, enc - sub $16, %r13 - jmp _initial_blocks_encrypted -_initial_num_blocks_is_0_encrypt: - INITIAL_BLOCKS_ENC 0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \ -%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, enc -_initial_blocks_encrypted: - - # Main loop - Encrypt remaining blocks - - cmp $0, %r13 - je _zero_cipher_left_encrypt - sub $64, %r13 - je _four_cipher_left_encrypt -_encrypt_by_4_encrypt: - GHASH_4_ENCRYPT_4_PARALLEL_ENC %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \ -%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, enc - add $64, %r11 - sub $64, %r13 - jne _encrypt_by_4_encrypt -_four_cipher_left_encrypt: - GHASH_LAST_4 %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \ -%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8 -_zero_cipher_left_encrypt: - mov %arg4, %r13 - and $15, %r13 # %r13 = arg4 (mod 16) - je _multiple_of_16_bytes_encrypt - - # Handle the last <16 Byte block separately - paddd ONE(%rip), %xmm0 # INCR CNT to get Yn - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10, %xmm0 - - ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn) - - lea (%arg3,%r11,1), %r10 - mov %r13, %r12 - READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1 - - lea ALL_F+16(%rip), %r12 - sub %r13, %r12 - pxor %xmm1, %xmm0 # Plaintext XOR Encrypt(K, Yn) - movdqu (%r12), %xmm1 - # get the appropriate mask to mask out top 16-r13 bytes of xmm0 - pand %xmm1, %xmm0 # mask out top 16-r13 bytes of xmm0 - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10,%xmm0 + GCM_COMPLETE arg10, arg11 + FUNC_RESTORE + ret +ENDPROC(aesni_gcm_enc) - pxor %xmm0, %xmm8 - GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 - # GHASH computation for the last <16 byte block - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10, %xmm0 +/***************************************************************************** +* void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data, +* // context 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. +*/ +ENTRY(aesni_gcm_init) + FUNC_SAVE + GCM_INIT %arg3, %arg4,%arg5, %arg6 + FUNC_RESTORE + ret +ENDPROC(aesni_gcm_init) - # shuffle xmm0 back to output as ciphertext +/***************************************************************************** +* void aesni_gcm_enc_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data, +* // context 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) + FUNC_SAVE + GCM_ENC_DEC enc + FUNC_RESTORE + ret +ENDPROC(aesni_gcm_enc_update) - # Output %r13 bytes - MOVQ_R64_XMM %xmm0, %rax - cmp $8, %r13 - jle _less_than_8_bytes_left_encrypt - mov %rax, (%arg2 , %r11, 1) - add $8, %r11 - psrldq $8, %xmm0 - MOVQ_R64_XMM %xmm0, %rax - sub $8, %r13 -_less_than_8_bytes_left_encrypt: - mov %al, (%arg2, %r11, 1) - add $1, %r11 - shr $8, %rax - sub $1, %r13 - jne _less_than_8_bytes_left_encrypt -_multiple_of_16_bytes_encrypt: - mov arg8, %r12 # %r12 = addLen (number of bytes) - shl $3, %r12 - movd %r12d, %xmm15 # len(A) in %xmm15 - shl $3, %arg4 # len(C) in bits (*128) - MOVQ_R64_XMM %arg4, %xmm1 - pslldq $8, %xmm15 # %xmm15 = len(A)||0x0000000000000000 - pxor %xmm1, %xmm15 # %xmm15 = len(A)||len(C) - pxor %xmm15, %xmm8 - GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6 - # final GHASH computation - movdqa SHUF_MASK(%rip), %xmm10 - PSHUFB_XMM %xmm10, %xmm8 # perform a 16 byte swap +/***************************************************************************** +* void aesni_gcm_dec_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data, +* // context 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_dec_update) + FUNC_SAVE + GCM_ENC_DEC dec + FUNC_RESTORE + ret +ENDPROC(aesni_gcm_dec_update) - mov %arg5, %rax # %rax = *Y0 - movdqu (%rax), %xmm0 # %xmm0 = Y0 - ENCRYPT_SINGLE_BLOCK %xmm0, %xmm15 # Encrypt(K, Y0) - pxor %xmm8, %xmm0 -_return_T_encrypt: - mov arg9, %r10 # %r10 = authTag - mov arg10, %r11 # %r11 = auth_tag_len - cmp $16, %r11 - je _T_16_encrypt - cmp $8, %r11 - jl _T_4_encrypt -_T_8_encrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) - add $8, %r10 - sub $8, %r11 - psrldq $8, %xmm0 - cmp $0, %r11 - je _return_T_done_encrypt -_T_4_encrypt: - movd %xmm0, %eax - mov %eax, (%r10) - add $4, %r10 - sub $4, %r11 - psrldq $4, %xmm0 - cmp $0, %r11 - je _return_T_done_encrypt -_T_123_encrypt: - movd %xmm0, %eax - cmp $2, %r11 - jl _T_1_encrypt - mov %ax, (%r10) - cmp $2, %r11 - je _return_T_done_encrypt - add $2, %r10 - sar $16, %eax -_T_1_encrypt: - mov %al, (%r10) - jmp _return_T_done_encrypt -_T_16_encrypt: - movdqu %xmm0, (%r10) -_return_T_done_encrypt: - mov %r14, %rsp - pop %r14 - pop %r13 - pop %r12 +/***************************************************************************** +* void aesni_gcm_finalize(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. +* struct gcm_context_data *data, +* // context 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_finalize) + FUNC_SAVE + GCM_COMPLETE %arg3 %arg4 + FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc) +ENDPROC(aesni_gcm_finalize) #endif |