From: Dave Watson Subject: [PATCH v2 07/14] x86/crypto: aesni: Split AAD hash calculation to separate macro Date: Wed, 14 Feb 2018 09:39:36 -0800 Message-ID: <20180214173936.GA62048@davejwatson-mba> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: "David S. Miller" , Hannes Frederic Sowa , Tim Chen , Sabrina Dubroca , , Stephan Mueller , Ilya Lesokhin To: Herbert Xu , Junaid Shahid , Steffen Klassert , Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-crypto.vger.kernel.org AAD hash only needs to be calculated once for each scatter/gather operation. Move it to its own macro, and call it from GCM_INIT instead of INITIAL_BLOCKS. Signed-off-by: Dave Watson --- arch/x86/crypto/aesni-intel_asm.S | 71 ++++++++++++++++++++++++--------------- 1 file changed, 43 insertions(+), 28 deletions(-) diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 6c5a80d..58bbfac 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -229,6 +229,10 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff mov %arg5, %r13 # %xmm13 holds HashKey<<1 (mod poly) and $-16, %r13 mov %r13, %r12 + + CALC_AAD_HASH %xmm13 %xmm0 %xmm1 %xmm2 %xmm3 %xmm4 \ + %xmm5 %xmm6 + mov %r13, %r12 .endm # GCM_ENC_DEC Encodes/Decodes given data. Assumes that the passed gcm_context @@ -496,51 +500,62 @@ _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, %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 arg8, %r10 # %r10 = AAD - mov arg9, %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 TMP1 TMP2 TMP3 TMP4 TMP5 \ + TMP6 TMP7 + MOVADQ SHUF_MASK(%rip), %xmm14 + mov arg8, %r10 # %r10 = AAD + mov arg9, %r11 # %r11 = aadLen + pxor \TMP7, \TMP7 + pxor \TMP6, \TMP6 cmp $16, %r11 jl _get_AAD_rest\@ _get_AAD_blocks\@: - 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 + 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\@ - movdqu \XMM2, %xmm\i + movdqu \TMP6, \TMP7 /* read the last <16B of AAD */ _get_AAD_rest\@: cmp $0, %r11 je _get_AAD_done\@ - 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 + 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 _get_AAD_done\@: + movdqu \TMP6, AadHash(%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, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers +* are clobbered +* arg1, %arg2, %arg3, %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 + + movdqu AadHash(%arg2), %xmm\i # XMM0 = Y0 + xor %r11, %r11 # initialise the data pointer offset as zero # start AES for num_initial_blocks blocks -- 2.9.5