The asm macros are all set up now, introduce entry points.
GCM_INIT and GCM_COMPLETE have arguments supplied, so that
the new scatter/gather entry points don't have to take all the
arguments, and only the ones they need.
Signed-off-by: Dave Watson <davejwat...@fb.com>
---
arch/x86/crypto/aesni-intel_asm.S | 116 ++++++++++++++++++++++++++++---------
arch/x86/crypto/aesni-intel_glue.c | 16 +++++
2 files changed, 106 insertions(+), 26 deletions(-)
diff --git a/arch/x86/crypto/aesni-intel_asm.S
b/arch/x86/crypto/aesni-intel_asm.S
index b941952..311b2de 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -200,8 +200,8 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
# Output: HashKeys stored in gcm_context_data. Only needs to be called
# once per key.
# clobbers r12, and tmp xmm registers.
-.macro PRECOMPUTE TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 TMP7
- mov arg7, %r12
+.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
@@ -254,14 +254,14 @@ 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 arg9, %r11
+.macro GCM_INIT Iv SUBKEY AAD AADLEN
+ mov \AADLEN, %r11
mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
xor %r11, %r11
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 %arg6, %rax
+ mov \Iv, %rax
movdqu (%rax), %xmm0
movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv
@@ -269,11 +269,11 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
PSHUFB_XMM %xmm2, %xmm0
movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
- PRECOMPUTE %xmm1 %xmm2 %xmm3 %xmm4 %xmm5 %xmm6 %xmm7
+ PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
movdqa HashKey(%arg2), %xmm13
- CALC_AAD_HASH %xmm13 %xmm0 %xmm1 %xmm2 %xmm3 %xmm4 \
- %xmm5 %xmm6
+ 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
@@ -435,7 +435,7 @@ _multiple_of_16_bytes_\@:
# 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
+.macro GCM_COMPLETE AUTHTAG AUTHTAGLEN
movdqu AadHash(%arg2), %xmm8
movdqu HashKey(%arg2), %xmm13
@@ -466,8 +466,8 @@ _partial_done\@:
ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Y0)
pxor %xmm8, %xmm0
_return_T_\@:
- mov arg10, %r10 # %r10 = authTag
- mov arg11, %r11 # %r11 = auth_tag_len
+ mov \AUTHTAG, %r10 # %r10 = authTag
+ mov \AUTHTAGLEN, %r11 # %r11 = auth_tag_len
cmp $16, %r11
je _T_16_\@
cmp $8, %r11
@@ -599,11 +599,11 @@ _done_read_partial_block_\@:
# 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 \
+.macro CALC_AAD_HASH HASHKEY AAD AADLEN TMP1 TMP2 TMP3 TMP4 TMP5 \
TMP6 TMP7
MOVADQ SHUF_MASK(%rip), %xmm14
- mov arg8, %r10 # %r10 = AAD
- mov arg9, %r11 # %r11 = aadLen
+ mov \AAD, %r10 # %r10 = AAD
+ mov \AADLEN, %r11 # %r11 = aadLen
pxor \TMP7, \TMP7
pxor \TMP6, \TMP6
@@ -1103,18 +1103,18 @@ 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
@@ -1311,18 +1311,18 @@ 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
@@ -1598,9 +1598,9 @@ _esb_loop_\@:
ENTRY(aesni_gcm_dec)
FUNC_SAVE
- GCM_INIT
+ GCM_INIT %arg6, arg7, arg8, arg9
GCM_ENC_DEC dec
- GCM_COMPLETE
+ GCM_COMPLETE arg10, arg11
FUNC_RESTORE
ret
ENDPROC(aesni_gcm_dec)
@@ -1686,13 +1686,77 @@ ENDPROC(aesni_gcm_dec)
ENTRY(aesni_gcm_enc)
FUNC_SAVE
- GCM_INIT
+ GCM_INIT %arg6, arg7, arg8, arg9
GCM_ENC_DEC enc
- GCM_COMPLETE
+
+ GCM_COMPLETE arg10, arg11
FUNC_RESTORE
ret
ENDPROC(aesni_gcm_enc)
+/*****************************************************************************
+* 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)
+
+/*****************************************************************************
+* 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)
+
+/*****************************************************************************
+* 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)
+
+/*****************************************************************************
+* 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_finalize)
+
#endif
diff --git a/arch/x86/crypto/aesni-intel_glue.c
b/arch/x86/crypto/aesni-intel_glue.c
index 4dd5b9b..de986f9 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -161,6 +161,22 @@ asmlinkage void aesni_gcm_dec(void *ctx,
u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
u8 *auth_tag, unsigned long auth_tag_len);
+/* Scatter / Gather routines, with args similar to above */
+asmlinkage void aesni_gcm_init(void *ctx,
+ struct gcm_context_data *gdata,
+ u8 *iv,
+ u8 *hash_subkey, const u8 *aad,
+ unsigned long aad_len);
+asmlinkage void aesni_gcm_enc_update(void *ctx,
+ struct gcm_context_data *gdata, u8 *out,
+ const u8 *in, unsigned long plaintext_len);
+asmlinkage void aesni_gcm_dec_update(void *ctx,
+ struct gcm_context_data *gdata, u8 *out,
+ const u8 *in,
+ unsigned long ciphertext_len);
+asmlinkage void aesni_gcm_finalize(void *ctx,
+ struct gcm_context_data *gdata,
+ u8 *auth_tag, unsigned long auth_tag_len);
#ifdef CONFIG_AS_AVX
asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
--
2.9.5
