@@ -144,11 +144,6 @@ CPU_LE( vrev64.8 q12, q12 )
veor.8 \dst_reg, \dst_reg, \src_reg
.endm
- .macro __adrl, out, sym
- movw \out, #:lower16:\sym
- movt \out, #:upper16:\sym
- .endm
-
//
// u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
//
@@ -160,7 +155,7 @@ ENTRY(crc_t10dif_pmull)
cmp len, #256
blt .Lless_than_256_bytes
- __adrl fold_consts_ptr, .Lfold_across_128_bytes_consts
+ mov_l fold_consts_ptr, .Lfold_across_128_bytes_consts
// Load the first 128 data bytes. Byte swapping is necessary to make
// the bit order match the polynomial coefficient order.
@@ -262,7 +257,7 @@ CPU_LE( vrev64.8 q0, q0 )
vswp q0l, q0h
// q1 = high order part of second chunk: q7 left-shifted by 'len' bytes.
- __adrl r3, .Lbyteshift_table + 16
+ mov_l r3, .Lbyteshift_table + 16
sub r3, r3, len
vld1.8 {q2}, [r3]
vtbl.8 q1l, {q7l-q7h}, q2l
@@ -324,7 +319,7 @@ CPU_LE( vrev64.8 q0, q0 )
.Lless_than_256_bytes:
// Checksumming a buffer of length 16...255 bytes
- __adrl fold_consts_ptr, .Lfold_across_16_bytes_consts
+ mov_l fold_consts_ptr, .Lfold_across_16_bytes_consts
// Load the first 16 data bytes.
vld1.64 {q7}, [buf]!