@@ -1875,7 +1875,7 @@ ENDPROC(aesni_gcm_enc)
.align 4
_key_expansion_128:
-_key_expansion_256a:
+SYM_FUNC_START_LOCAL(_key_expansion_256a)
pshufd $0b11111111, %xmm1, %xmm1
shufps $0b00010000, %xmm0, %xmm4
pxor %xmm4, %xmm0
@@ -1886,10 +1886,9 @@ _key_expansion_256a:
add $0x10, TKEYP
ret
ENDPROC(_key_expansion_128)
-ENDPROC(_key_expansion_256a)
+SYM_FUNC_END(_key_expansion_256a)
-.align 4
-_key_expansion_192a:
+SYM_FUNC_START_LOCAL(_key_expansion_192a)
pshufd $0b01010101, %xmm1, %xmm1
shufps $0b00010000, %xmm0, %xmm4
pxor %xmm4, %xmm0
@@ -1911,10 +1910,9 @@ _key_expansion_192a:
movaps %xmm1, 0x10(TKEYP)
add $0x20, TKEYP
ret
-ENDPROC(_key_expansion_192a)
+SYM_FUNC_END(_key_expansion_192a)
-.align 4
-_key_expansion_192b:
+SYM_FUNC_START_LOCAL(_key_expansion_192b)
pshufd $0b01010101, %xmm1, %xmm1
shufps $0b00010000, %xmm0, %xmm4
pxor %xmm4, %xmm0
@@ -1931,10 +1929,9 @@ _key_expansion_192b:
movaps %xmm0, (TKEYP)
add $0x10, TKEYP
ret
-ENDPROC(_key_expansion_192b)
+SYM_FUNC_END(_key_expansion_192b)
-.align 4
-_key_expansion_256b:
+SYM_FUNC_START_LOCAL(_key_expansion_256b)
pshufd $0b10101010, %xmm1, %xmm1
shufps $0b00010000, %xmm2, %xmm4
pxor %xmm4, %xmm2
@@ -1944,7 +1941,7 @@ _key_expansion_256b:
movaps %xmm2, (TKEYP)
add $0x10, TKEYP
ret
-ENDPROC(_key_expansion_256b)
+SYM_FUNC_END(_key_expansion_256b)
/*
* int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
@@ -2097,8 +2094,7 @@ ENDPROC(aesni_enc)
* KEY
* TKEYP (T1)
*/
-.align 4
-_aesni_enc1:
+SYM_FUNC_START_LOCAL(_aesni_enc1)
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE # round 0
@@ -2141,7 +2137,7 @@ _aesni_enc1:
movaps 0x70(TKEYP), KEY
AESENCLAST KEY STATE
ret
-ENDPROC(_aesni_enc1)
+SYM_FUNC_END(_aesni_enc1)
/*
* _aesni_enc4: internal ABI
@@ -2161,8 +2157,7 @@ ENDPROC(_aesni_enc1)
* KEY
* TKEYP (T1)
*/
-.align 4
-_aesni_enc4:
+SYM_FUNC_START_LOCAL(_aesni_enc4)
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE1 # round 0
@@ -2250,7 +2245,7 @@ _aesni_enc4:
AESENCLAST KEY STATE3
AESENCLAST KEY STATE4
ret
-ENDPROC(_aesni_enc4)
+SYM_FUNC_END(_aesni_enc4)
/*
* void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -2289,8 +2284,7 @@ ENDPROC(aesni_dec)
* KEY
* TKEYP (T1)
*/
-.align 4
-_aesni_dec1:
+SYM_FUNC_START_LOCAL(_aesni_dec1)
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE # round 0
@@ -2333,7 +2327,7 @@ _aesni_dec1:
movaps 0x70(TKEYP), KEY
AESDECLAST KEY STATE
ret
-ENDPROC(_aesni_dec1)
+SYM_FUNC_END(_aesni_dec1)
/*
* _aesni_dec4: internal ABI
@@ -2353,8 +2347,7 @@ ENDPROC(_aesni_dec1)
* KEY
* TKEYP (T1)
*/
-.align 4
-_aesni_dec4:
+SYM_FUNC_START_LOCAL(_aesni_dec4)
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE1 # round 0
@@ -2442,7 +2435,7 @@ _aesni_dec4:
AESDECLAST KEY STATE3
AESDECLAST KEY STATE4
ret
-ENDPROC(_aesni_dec4)
+SYM_FUNC_END(_aesni_dec4)
/*
* void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2720,8 +2713,7 @@ ENDPROC(aesni_cbc_dec)
* INC: == 1, in little endian
* BSWAP_MASK == endian swapping mask
*/
-.align 4
-_aesni_inc_init:
+SYM_FUNC_START_LOCAL(_aesni_inc_init)
movaps .Lbswap_mask, BSWAP_MASK
movaps IV, CTR
PSHUFB_XMM BSWAP_MASK CTR
@@ -2729,7 +2721,7 @@ _aesni_inc_init:
MOVQ_R64_XMM TCTR_LOW INC
MOVQ_R64_XMM CTR TCTR_LOW
ret
-ENDPROC(_aesni_inc_init)
+SYM_FUNC_END(_aesni_inc_init)
/*
* _aesni_inc: internal ABI
@@ -2746,8 +2738,7 @@ ENDPROC(_aesni_inc_init)
* CTR: == output IV, in little endian
* TCTR_LOW: == lower qword of CTR
*/
-.align 4
-_aesni_inc:
+SYM_FUNC_START_LOCAL(_aesni_inc)
paddq INC, CTR
add $1, TCTR_LOW
jnc .Linc_low
@@ -2758,7 +2749,7 @@ _aesni_inc:
movaps CTR, IV
PSHUFB_XMM BSWAP_MASK IV
ret
-ENDPROC(_aesni_inc)
+SYM_FUNC_END(_aesni_inc)
/*
* void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -188,20 +188,20 @@
* larger and would only be 0.5% faster (on sandy-bridge).
*/
.align 8
-roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
%xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
%rcx, (%r9));
ret;
-ENDPROC(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
.align 8
-roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3,
%xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
%rax, (%r9));
ret;
-ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
/*
* IN/OUT:
@@ -721,7 +721,7 @@ ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
.text
.align 8
-__camellia_enc_blk16:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
/* input:
* %rdi: ctx, CTX
* %rax: temporary storage, 256 bytes
@@ -805,10 +805,10 @@ __camellia_enc_blk16:
%xmm15, %rax, %rcx, 24);
jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk16)
+SYM_FUNC_END(__camellia_enc_blk16)
.align 8
-__camellia_dec_blk16:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
/* input:
* %rdi: ctx, CTX
* %rax: temporary storage, 256 bytes
@@ -890,7 +890,7 @@ __camellia_dec_blk16:
((key_table + (24) * 8) + 4)(CTX));
jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk16)
+SYM_FUNC_END(__camellia_dec_blk16)
ENTRY(camellia_ecb_enc_16way)
/* input:
@@ -1119,7 +1119,7 @@ ENDPROC(camellia_ctr_16way)
vpxor tmp, iv, iv;
.align 8
-camellia_xts_crypt_16way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -1253,7 +1253,7 @@ camellia_xts_crypt_16way:
FRAME_END
ret;
-ENDPROC(camellia_xts_crypt_16way)
+SYM_FUNC_END(camellia_xts_crypt_16way)
ENTRY(camellia_xts_enc_16way)
/* input:
@@ -227,20 +227,20 @@
* larger and would only marginally faster.
*/
.align 8
-roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
%ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
%rcx, (%r9));
ret;
-ENDPROC(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
.align 8
-roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
%ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
%rax, (%r9));
ret;
-ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
/*
* IN/OUT:
@@ -764,7 +764,7 @@ ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
.text
.align 8
-__camellia_enc_blk32:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
/* input:
* %rdi: ctx, CTX
* %rax: temporary storage, 512 bytes
@@ -848,10 +848,10 @@ __camellia_enc_blk32:
%ymm15, %rax, %rcx, 24);
jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk32)
+SYM_FUNC_END(__camellia_enc_blk32)
.align 8
-__camellia_dec_blk32:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
/* input:
* %rdi: ctx, CTX
* %rax: temporary storage, 512 bytes
@@ -933,7 +933,7 @@ __camellia_dec_blk32:
((key_table + (24) * 8) + 4)(CTX));
jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk32)
+SYM_FUNC_END(__camellia_dec_blk32)
ENTRY(camellia_ecb_enc_32way)
/* input:
@@ -1226,7 +1226,7 @@ ENDPROC(camellia_ctr_32way)
vpxor tmp1, iv, iv;
.align 8
-camellia_xts_crypt_32way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (32 blocks)
@@ -1371,7 +1371,7 @@ camellia_xts_crypt_32way:
FRAME_END
ret;
-ENDPROC(camellia_xts_crypt_32way)
+SYM_FUNC_END(camellia_xts_crypt_32way)
ENTRY(camellia_xts_enc_32way)
/* input:
@@ -224,7 +224,7 @@
.text
.align 16
-__cast5_enc_blk16:
+SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
/* input:
* %rdi: ctx
* RL1: blocks 1 and 2
@@ -295,10 +295,10 @@ __cast5_enc_blk16:
outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
ret;
-ENDPROC(__cast5_enc_blk16)
+SYM_FUNC_END(__cast5_enc_blk16)
.align 16
-__cast5_dec_blk16:
+SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
/* input:
* %rdi: ctx
* RL1: encrypted blocks 1 and 2
@@ -372,7 +372,7 @@ __cast5_dec_blk16:
.L__skip_dec:
vpsrldq $4, RKR, RKR;
jmp .L__dec_tail;
-ENDPROC(__cast5_dec_blk16)
+SYM_FUNC_END(__cast5_dec_blk16)
ENTRY(cast5_ecb_enc_16way)
/* input:
@@ -262,7 +262,7 @@
.text
.align 8
-__cast6_enc_blk8:
+SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
/* input:
* %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -307,10 +307,10 @@ __cast6_enc_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
ret;
-ENDPROC(__cast6_enc_blk8)
+SYM_FUNC_END(__cast6_enc_blk8)
.align 8
-__cast6_dec_blk8:
+SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
/* input:
* %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -354,7 +354,7 @@ __cast6_dec_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
ret;
-ENDPROC(__cast6_dec_blk8)
+SYM_FUNC_END(__cast6_dec_blk8)
ENTRY(cast6_ecb_enc_8way)
/* input:
@@ -47,7 +47,7 @@
* T2
* T3
*/
-__clmul_gf128mul_ble:
+SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
movaps DATA, T1
pshufd $0b01001110, DATA, T2
pshufd $0b01001110, SHASH, T3
@@ -90,7 +90,7 @@ __clmul_gf128mul_ble:
pxor T2, T1
pxor T1, DATA
ret
-ENDPROC(__clmul_gf128mul_ble)
+SYM_FUNC_END(__clmul_gf128mul_ble)
/* void clmul_ghash_mul(char *dst, const u128 *shash) */
ENTRY(clmul_ghash_mul)
@@ -570,7 +570,7 @@
transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
.align 8
-__serpent_enc_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
/* input:
* %rdi: ctx, CTX
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -621,10 +621,10 @@ __serpent_enc_blk8_avx:
write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
-ENDPROC(__serpent_enc_blk8_avx)
+SYM_FUNC_END(__serpent_enc_blk8_avx)
.align 8
-__serpent_dec_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
/* input:
* %rdi: ctx, CTX
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -675,7 +675,7 @@ __serpent_dec_blk8_avx:
write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
-ENDPROC(__serpent_dec_blk8_avx)
+SYM_FUNC_END(__serpent_dec_blk8_avx)
ENTRY(serpent_ecb_enc_8way_avx)
/* input:
@@ -566,7 +566,7 @@
transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
.align 8
-__serpent_enc_blk16:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
/* input:
* %rdi: ctx, CTX
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: plaintext
@@ -617,10 +617,10 @@ __serpent_enc_blk16:
write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
-ENDPROC(__serpent_enc_blk16)
+SYM_FUNC_END(__serpent_enc_blk16)
.align 8
-__serpent_dec_blk16:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
/* input:
* %rdi: ctx, CTX
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: ciphertext
@@ -671,7 +671,7 @@ __serpent_dec_blk16:
write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
-ENDPROC(__serpent_dec_blk16)
+SYM_FUNC_END(__serpent_dec_blk16)
ENTRY(serpent_ecb_enc_16way)
/* input:
@@ -249,7 +249,7 @@
vpxor x3, wkey, x3;
.align 8
-__twofish_enc_blk8:
+SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
/* input:
* %rdi: ctx, CTX
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -288,10 +288,10 @@ __twofish_enc_blk8:
outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
ret;
-ENDPROC(__twofish_enc_blk8)
+SYM_FUNC_END(__twofish_enc_blk8)
.align 8
-__twofish_dec_blk8:
+SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
/* input:
* %rdi: ctx, CTX
* RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2: encrypted blocks
@@ -328,7 +328,7 @@ __twofish_dec_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
ret;
-ENDPROC(__twofish_dec_blk8)
+SYM_FUNC_END(__twofish_dec_blk8)
ENTRY(twofish_ecb_enc_8way)
/* input:
Use the newly added SYM_FUNC_START_LOCAL to annotate starts of all functions which do not have ".globl" annotation, but their ends are annotated by ENDPROC. This is needed to balance ENDPROC for tools that are about to generate debuginfo. To be symmetric, we also convert their ENDPROCs to the new SYM_FUNC_END. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <x86@kernel.org> Cc: <linux-crypto@vger.kernel.org> --- arch/x86/crypto/aesni-intel_asm.S | 49 ++++++++++++---------------- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 20 ++++++------ arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 20 ++++++------ arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 8 ++--- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 8 ++--- arch/x86/crypto/ghash-clmulni-intel_asm.S | 4 +-- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 8 ++--- arch/x86/crypto/serpent-avx2-asm_64.S | 8 ++--- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 8 ++--- 9 files changed, 62 insertions(+), 71 deletions(-)