diff options
author | Dave Watson <davejwatson@fb.com> | 2018-02-14 20:39:23 +0300 |
---|---|---|
committer | Herbert Xu <herbert@gondor.apana.org.au> | 2018-02-22 17:16:47 +0300 |
commit | 9ee4a5df220919c0b62165cb2813d63a7bdcb83d (patch) | |
tree | 4a1e8fdf26a1c87c89e71ba908baff9c16d7f06c /arch/x86/crypto/aesni-intel_asm.S | |
parent | ba45833e3e76aac409b7ebc3a428515a1b53ebda (diff) | |
download | linux-9ee4a5df220919c0b62165cb2813d63a7bdcb83d.tar.xz |
crypto: aesni - Introduce gcm_context_data
Introduce a gcm_context_data struct that will be used to pass
context data between scatter/gather update calls. It is passed
as the second argument (after crypto keys), other args are
renumbered.
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto/aesni-intel_asm.S')
-rw-r--r-- | arch/x86/crypto/aesni-intel_asm.S | 115 |
1 files changed, 64 insertions, 51 deletions
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 796d1a52cf03..8c73ab61b5da 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -112,6 +112,14 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff // (for Karatsuba purposes) #define VARIABLE_OFFSET 16*8 +#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 arg1 rdi #define arg2 rsi #define arg3 rdx @@ -122,6 +130,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define arg8 STACK_OFFSET+16(%r14) #define arg9 STACK_OFFSET+24(%r14) #define arg10 STACK_OFFSET+32(%r14) +#define arg11 STACK_OFFSET+40(%r14) #define keysize 2*15*16(%arg1) #endif @@ -196,9 +205,9 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff # GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding. # Clobbers rax, r10-r13 and xmm0-xmm6, %xmm13 .macro GCM_INIT - mov %arg6, %r12 + mov arg7, %r12 movdqu (%r12), %xmm13 - movdqa SHUF_MASK(%rip), %xmm2 + movdqa SHUF_MASK(%rip), %xmm2 PSHUFB_XMM %xmm2, %xmm13 # precompute HashKey<<1 mod poly from the HashKey (required for GHASH) @@ -218,7 +227,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff pand POLY(%rip), %xmm2 pxor %xmm2, %xmm13 movdqa %xmm13, HashKey(%rsp) - mov %arg4, %r13 # %xmm13 holds HashKey<<1 (mod poly) + mov %arg5, %r13 # %xmm13 holds HashKey<<1 (mod poly) and $-16, %r13 mov %r13, %r12 .endm @@ -272,18 +281,18 @@ _four_cipher_left_\@: GHASH_LAST_4 %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \ %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8 _zero_cipher_left_\@: - mov %arg4, %r13 - and $15, %r13 # %r13 = arg4 (mod 16) + mov %arg5, %r13 + and $15, %r13 # %r13 = arg5 (mod 16) je _multiple_of_16_bytes_\@ # Handle the last <16 Byte block separately paddd ONE(%rip), %xmm0 # INCR CNT to get Yn - movdqa SHUF_MASK(%rip), %xmm10 + movdqa SHUF_MASK(%rip), %xmm10 PSHUFB_XMM %xmm10, %xmm0 ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn) - lea (%arg3,%r11,1), %r10 + lea (%arg4,%r11,1), %r10 mov %r13, %r12 READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1 @@ -321,13 +330,13 @@ _zero_cipher_left_\@: MOVQ_R64_XMM %xmm0, %rax cmp $8, %r13 jle _less_than_8_bytes_left_\@ - mov %rax, (%arg2 , %r11, 1) + 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, (%arg2, %r11, 1) + mov %al, (%arg3, %r11, 1) add $1, %r11 shr $8, %rax sub $1, %r13 @@ -339,11 +348,11 @@ _multiple_of_16_bytes_\@: # Output: Authorization Tag (AUTH_TAG) # Clobbers rax, r10-r12, and xmm0, xmm1, xmm5-xmm15 .macro GCM_COMPLETE - mov arg8, %r12 # %r13 = aadLen (number of bytes) + mov arg9, %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 + shl $3, %arg5 # len(C) in bits (*128) + MOVQ_R64_XMM %arg5, %xmm1 pslldq $8, %xmm15 # %xmm15 = len(A)||0x0000000000000000 pxor %xmm1, %xmm15 # %xmm15 = len(A)||len(C) pxor %xmm15, %xmm8 @@ -352,13 +361,13 @@ _multiple_of_16_bytes_\@: movdqa SHUF_MASK(%rip), %xmm10 PSHUFB_XMM %xmm10, %xmm8 - mov %arg5, %rax # %rax = *Y0 + mov %arg6, %rax # %rax = *Y0 movdqu (%rax), %xmm0 # %xmm0 = Y0 ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Y0) pxor %xmm8, %xmm0 _return_T_\@: - mov arg9, %r10 # %r10 = authTag - mov arg10, %r11 # %r11 = auth_tag_len + mov arg10, %r10 # %r10 = authTag + mov arg11, %r11 # %r11 = auth_tag_len cmp $16, %r11 je _T_16_\@ cmp $8, %r11 @@ -496,15 +505,15 @@ _done_read_partial_block_\@: * 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, %arg3, %arg4, %r14 are used as a pointer only, not modified */ .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 - mov arg7, %r10 # %r10 = AAD - mov arg8, %r11 # %r11 = aadLen + mov arg8, %r10 # %r10 = AAD + mov arg9, %r11 # %r11 = aadLen pxor %xmm\i, %xmm\i pxor \XMM2, \XMM2 @@ -536,7 +545,7 @@ _get_AAD_done\@: xor %r11, %r11 # initialise the data pointer offset as zero # start AES for num_initial_blocks blocks - mov %arg5, %rax # %rax = *Y0 + mov %arg6, %rax # %rax = *Y0 movdqu (%rax), \XMM0 # XMM0 = Y0 PSHUFB_XMM %xmm14, \XMM0 @@ -573,9 +582,9 @@ aes_loop_initial_\@: 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 @@ -694,34 +703,34 @@ aes_loop_pre_done\@: 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 .ifc \operation, dec - movdqu \XMM1, 16*0(%arg2 , %r11 , 1) + movdqu \XMM1, 16*0(%arg3 , %r11 , 1) movdqa \TMP1, \XMM1 .endif - movdqu 16*1(%arg3 , %r11 , 1), \TMP1 + movdqu 16*1(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM2 .ifc \operation, dec - movdqu \XMM2, 16*1(%arg2 , %r11 , 1) + movdqu \XMM2, 16*1(%arg3 , %r11 , 1) movdqa \TMP1, \XMM2 .endif - movdqu 16*2(%arg3 , %r11 , 1), \TMP1 + movdqu 16*2(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM3 .ifc \operation, dec - movdqu \XMM3, 16*2(%arg2 , %r11 , 1) + movdqu \XMM3, 16*2(%arg3 , %r11 , 1) movdqa \TMP1, \XMM3 .endif - movdqu 16*3(%arg3 , %r11 , 1), \TMP1 + movdqu 16*3(%arg4 , %r11 , 1), \TMP1 pxor \TMP1, \XMM4 .ifc \operation, dec - movdqu \XMM4, 16*3(%arg2 , %r11 , 1) + movdqu \XMM4, 16*3(%arg3 , %r11 , 1) movdqa \TMP1, \XMM4 .else - 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) + 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 @@ -739,7 +748,7 @@ _initial_blocks_done\@: /* * 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 \ @@ -883,18 +892,18 @@ aes_loop_par_enc_done: AESENCLAST \TMP3, \XMM4 movdqa HashKey_k(%rsp), \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 @@ -947,7 +956,7 @@ 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 \ @@ -1091,21 +1100,21 @@ aes_loop_par_dec_done: AESENCLAST \TMP3, \XMM4 movdqa HashKey_k(%rsp), \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 @@ -1278,6 +1287,8 @@ _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. @@ -1367,6 +1378,8 @@ 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. |