@@ -80,7 +80,46 @@
vzr .req v13
-ENTRY(crc_t10dif_pmull)
+ .macro fold64, p, reg1, reg2
+ ldp q11, q12, [arg2], #0x20
+
+ __pmull_\p v8, \reg1, v10, 2
+ __pmull_\p \reg1, \reg1, v10
+
+CPU_LE( rev64 v11.16b, v11.16b )
+CPU_LE( rev64 v12.16b, v12.16b )
+
+ __pmull_\p v9, \reg2, v10, 2
+ __pmull_\p \reg2, \reg2, v10
+
+CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
+CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
+
+ eor \reg1\().16b, \reg1\().16b, v8.16b
+ eor \reg2\().16b, \reg2\().16b, v9.16b
+ eor \reg1\().16b, \reg1\().16b, v11.16b
+ eor \reg2\().16b, \reg2\().16b, v12.16b
+ .endm
+
+ .macro fold16, p, reg, rk
+ __pmull_\p v8, \reg, v10
+ __pmull_\p \reg, \reg, v10, 2
+ .ifnb \rk
+ ldr_l q10, \rk, x8
+ .endif
+ eor v7.16b, v7.16b, v8.16b
+ eor v7.16b, v7.16b, \reg\().16b
+ .endm
+
+ .macro __pmull_p64, rd, rn, rm, n
+ .ifb \n
+ pmull \rd\().1q, \rn\().1d, \rm\().1d
+ .else
+ pmull2 \rd\().1q, \rn\().2d, \rm\().2d
+ .endif
+ .endm
+
+ .macro crc_t10dif_pmull, p
frame_push 3, 128
mov arg1_low32, w0
@@ -96,7 +135,7 @@ ENTRY(crc_t10dif_pmull)
cmp arg3, #256
// for sizes less than 128, we can't fold 64B at a time...
- b.lt _less_than_128
+ b.lt .L_less_than_128_\@
// load the initial crc value
// crc value does not need to be byte-reflected, but it needs
@@ -147,41 +186,19 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// buffer. The _fold_64_B_loop will fold 64B at a time
// until we have 64+y Bytes of buffer
-
// fold 64B at a time. This section of the code folds 4 vector
// registers in parallel
-_fold_64_B_loop:
-
- .macro fold64, reg1, reg2
- ldp q11, q12, [arg2], #0x20
-
- pmull2 v8.1q, \reg1\().2d, v10.2d
- pmull \reg1\().1q, \reg1\().1d, v10.1d
-
-CPU_LE( rev64 v11.16b, v11.16b )
-CPU_LE( rev64 v12.16b, v12.16b )
-
- pmull2 v9.1q, \reg2\().2d, v10.2d
- pmull \reg2\().1q, \reg2\().1d, v10.1d
-
-CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
-CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
-
- eor \reg1\().16b, \reg1\().16b, v8.16b
- eor \reg2\().16b, \reg2\().16b, v9.16b
- eor \reg1\().16b, \reg1\().16b, v11.16b
- eor \reg2\().16b, \reg2\().16b, v12.16b
- .endm
+.L_fold_64_B_loop_\@:
- fold64 v0, v1
- fold64 v2, v3
- fold64 v4, v5
- fold64 v6, v7
+ fold64 \p, v0, v1
+ fold64 \p, v2, v3
+ fold64 \p, v4, v5
+ fold64 \p, v6, v7
subs arg3, arg3, #128
// check if there is another 64B in the buffer to be able to fold
- b.lt _fold_64_B_end
+ b.lt .L_fold_64_B_end_\@
if_will_cond_yield_neon
stp q0, q1, [sp, #.Lframe_local_offset]
@@ -197,9 +214,9 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
movi vzr.16b, #0 // init zero register
endif_yield_neon
- b _fold_64_B_loop
+ b .L_fold_64_B_loop_\@
-_fold_64_B_end:
+.L_fold_64_B_end_\@:
// at this point, the buffer pointer is pointing at the last y Bytes
// of the buffer the 64B of folded data is in 4 of the vector
// registers: v0, v1, v2, v3
@@ -209,37 +226,27 @@ _fold_64_B_end:
ldr_l q10, rk9, x8
- .macro fold16, reg, rk
- pmull v8.1q, \reg\().1d, v10.1d
- pmull2 \reg\().1q, \reg\().2d, v10.2d
- .ifnb \rk
- ldr_l q10, \rk, x8
- .endif
- eor v7.16b, v7.16b, v8.16b
- eor v7.16b, v7.16b, \reg\().16b
- .endm
-
- fold16 v0, rk11
- fold16 v1, rk13
- fold16 v2, rk15
- fold16 v3, rk17
- fold16 v4, rk19
- fold16 v5, rk1
- fold16 v6
+ fold16 \p, v0, rk11
+ fold16 \p, v1, rk13
+ fold16 \p, v2, rk15
+ fold16 \p, v3, rk17
+ fold16 \p, v4, rk19
+ fold16 \p, v5, rk1
+ fold16 \p, v6
// instead of 64, we add 48 to the loop counter to save 1 instruction
// from the loop instead of a cmp instruction, we use the negative
// flag with the jl instruction
adds arg3, arg3, #(128-16)
- b.lt _final_reduction_for_128
+ b.lt .L_final_reduction_for_128_\@
// now we have 16+y bytes left to reduce. 16 Bytes is in register v7
// and the rest is in memory. We can fold 16 bytes at a time if y>=16
// continue folding 16B at a time
-_16B_reduction_loop:
- pmull v8.1q, v7.1d, v10.1d
- pmull2 v7.1q, v7.2d, v10.2d
+.L_16B_reduction_loop_\@:
+ __pmull_\p v8, v7, v10
+ __pmull_\p v7, v7, v10, 2
eor v7.16b, v7.16b, v8.16b
ldr q0, [arg2], #16
@@ -251,22 +258,22 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
// instead of a cmp instruction, we utilize the flags with the
// jge instruction equivalent of: cmp arg3, 16-16
// check if there is any more 16B in the buffer to be able to fold
- b.ge _16B_reduction_loop
+ b.ge .L_16B_reduction_loop_\@
// now we have 16+z bytes left to reduce, where 0<= z < 16.
// first, we reduce the data in the xmm7 register
-_final_reduction_for_128:
+.L_final_reduction_for_128_\@:
// check if any more data to fold. If not, compute the CRC of
// the final 128 bits
adds arg3, arg3, #16
- b.eq _128_done
+ b.eq .L_128_done_\@
// here we are getting data that is less than 16 bytes.
// since we know that there was data before the pointer, we can
// offset the input pointer before the actual point, to receive
// exactly 16 bytes. after that the registers need to be adjusted.
-_get_last_two_regs:
+.L_get_last_two_regs_\@:
add arg2, arg2, arg3
ldr q1, [arg2, #-16]
CPU_LE( rev64 v1.16b, v1.16b )
@@ -291,47 +298,46 @@ CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 )
bsl v0.16b, v2.16b, v1.16b
// fold 16 Bytes
- pmull v8.1q, v7.1d, v10.1d
- pmull2 v7.1q, v7.2d, v10.2d
+ __pmull_\p v8, v7, v10
+ __pmull_\p v7, v7, v10, 2
eor v7.16b, v7.16b, v8.16b
eor v7.16b, v7.16b, v0.16b
-_128_done:
+.L_128_done_\@:
// compute crc of a 128-bit value
ldr_l q10, rk5, x8 // rk5 and rk6 in xmm10
// 64b fold
ext v0.16b, vzr.16b, v7.16b, #8
mov v7.d[0], v7.d[1]
- pmull v7.1q, v7.1d, v10.1d
+ __pmull_\p v7, v7, v10
eor v7.16b, v7.16b, v0.16b
// 32b fold
ext v0.16b, v7.16b, vzr.16b, #4
mov v7.s[3], vzr.s[0]
- pmull2 v0.1q, v0.2d, v10.2d
+ __pmull_\p v0, v0, v10, 2
eor v7.16b, v7.16b, v0.16b
// barrett reduction
-_barrett:
ldr_l q10, rk7, x8
mov v0.d[0], v7.d[1]
- pmull v0.1q, v0.1d, v10.1d
+ __pmull_\p v0, v0, v10
ext v0.16b, vzr.16b, v0.16b, #12
- pmull2 v0.1q, v0.2d, v10.2d
+ __pmull_\p v0, v0, v10, 2
ext v0.16b, vzr.16b, v0.16b, #12
eor v7.16b, v7.16b, v0.16b
mov w0, v7.s[1]
-_cleanup:
+.L_cleanup_\@:
// scale the result back to 16 bits
lsr x0, x0, #16
frame_pop
ret
-_less_than_128:
- cbz arg3, _cleanup
+.L_less_than_128_\@:
+ cbz arg3, .L_cleanup_\@
movi v0.16b, #0
mov v0.s[3], arg1_low32 // get the initial crc value
@@ -342,20 +348,20 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
eor v7.16b, v7.16b, v0.16b // xor the initial crc value
cmp arg3, #16
- b.eq _128_done // exactly 16 left
- b.lt _less_than_16_left
+ b.eq .L_128_done_\@ // exactly 16 left
+ b.lt .L_less_than_16_left_\@
ldr_l q10, rk1, x8 // rk1 and rk2 in xmm10
// update the counter. subtract 32 instead of 16 to save one
// instruction from the loop
subs arg3, arg3, #32
- b.ge _16B_reduction_loop
+ b.ge .L_16B_reduction_loop_\@
add arg3, arg3, #16
- b _get_last_two_regs
+ b .L_get_last_two_regs_\@
-_less_than_16_left:
+.L_less_than_16_left_\@:
// shl r9, 4
adr_l x0, tbl_shf_table + 16
sub x0, x0, arg3
@@ -363,8 +369,12 @@ _less_than_16_left:
movi v9.16b, #0x80
eor v0.16b, v0.16b, v9.16b
tbl v7.16b, {v7.16b}, v0.16b
- b _128_done
-ENDPROC(crc_t10dif_pmull)
+ b .L_128_done_\@
+ .endm
+
+ENTRY(crc_t10dif_pmull_p64)
+ crc_t10dif_pmull p64
+ENDPROC(crc_t10dif_pmull_p64)
// precomputed constants
// these constants are precomputed from the poly:
@@ -22,7 +22,9 @@
#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
-asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 buf[], u64 len);
+asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 buf[], u64 len);
+
+static u16 (*crc_t10dif_pmull)(u16 init_crc, const u8 buf[], u64 len);
static int crct10dif_init(struct shash_desc *desc)
{
@@ -85,6 +87,8 @@ static struct shash_alg crc_t10dif_alg = {
static int __init crc_t10dif_mod_init(void)
{
+ crc_t10dif_pmull = crc_t10dif_pmull_p64;
+
return crypto_register_shash(&crc_t10dif_alg);
}
Reorganize the CRC-T10DIF asm routine so we can easily instantiate an alternative version based on 8x8 polynomial multiplication in a subsequent patch. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/crct10dif-ce-core.S | 160 +++++++++++--------- arch/arm64/crypto/crct10dif-ce-glue.c | 6 +- 2 files changed, 90 insertions(+), 76 deletions(-)