diff options
Diffstat (limited to 'arch/arm64/crypto/crct10dif-ce-core.S')
| -rw-r--r-- | arch/arm64/crypto/crct10dif-ce-core.S | 54 |
1 files changed, 16 insertions, 38 deletions
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S index e545b42e6a46..5604de61d06d 100644 --- a/arch/arm64/crypto/crct10dif-ce-core.S +++ b/arch/arm64/crypto/crct10dif-ce-core.S @@ -66,12 +66,12 @@ #include <asm/assembler.h> .text - .cpu generic+crypto + .arch armv8-a+crypto - init_crc .req w19 - buf .req x20 - len .req x21 - fold_consts_ptr .req x22 + init_crc .req w0 + buf .req x1 + len .req x2 + fold_consts_ptr .req x3 fold_consts .req v10 @@ -131,7 +131,7 @@ tbl bd4.16b, {\bd\().16b}, perm4.16b .endm -__pmull_p8_core: +SYM_FUNC_START_LOCAL(__pmull_p8_core) .L__pmull_p8_core: ext t4.8b, ad.8b, ad.8b, #1 // A1 ext t5.8b, ad.8b, ad.8b, #2 // A2 @@ -194,7 +194,7 @@ __pmull_p8_core: eor t4.16b, t4.16b, t5.16b eor t6.16b, t6.16b, t3.16b ret -ENDPROC(__pmull_p8_core) +SYM_FUNC_END(__pmull_p8_core) .macro __pmull_p8, rq, ad, bd, i .ifnc \bd, fold_consts @@ -257,12 +257,6 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) .endm .macro crc_t10dif_pmull, p - frame_push 4, 128 - - mov init_crc, w0 - mov buf, x1 - mov len, x2 - __pmull_init_\p // For sizes less than 256 bytes, we can't fold 128 bytes at a time. @@ -317,26 +311,7 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) fold_32_bytes \p, v6, v7 subs len, len, #128 - b.lt .Lfold_128_bytes_loop_done_\@ - - if_will_cond_yield_neon - stp q0, q1, [sp, #.Lframe_local_offset] - stp q2, q3, [sp, #.Lframe_local_offset + 32] - stp q4, q5, [sp, #.Lframe_local_offset + 64] - stp q6, q7, [sp, #.Lframe_local_offset + 96] - do_cond_yield_neon - ldp q0, q1, [sp, #.Lframe_local_offset] - ldp q2, q3, [sp, #.Lframe_local_offset + 32] - ldp q4, q5, [sp, #.Lframe_local_offset + 64] - ldp q6, q7, [sp, #.Lframe_local_offset + 96] - ld1 {fold_consts.2d}, [fold_consts_ptr] - __pmull_init_\p - __pmull_pre_\p fold_consts - endif_yield_neon - - b .Lfold_128_bytes_loop_\@ - -.Lfold_128_bytes_loop_done_\@: + b.ge .Lfold_128_bytes_loop_\@ // Now fold the 112 bytes in v0-v6 into the 16 bytes in v7. @@ -453,7 +428,9 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0. umov w0, v0.h[0] + .ifc \p, p8 frame_pop + .endif ret .Lless_than_256_bytes_\@: @@ -488,9 +465,10 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) // // Assumes len >= 16. // -ENTRY(crc_t10dif_pmull_p8) - crc_t10dif_pmull p8 -ENDPROC(crc_t10dif_pmull_p8) +SYM_FUNC_START(crc_t10dif_pmull_p8) + frame_push 1 + crc_t10dif_pmull p8 +SYM_FUNC_END(crc_t10dif_pmull_p8) .align 5 // @@ -498,9 +476,9 @@ ENDPROC(crc_t10dif_pmull_p8) // // Assumes len >= 16. // -ENTRY(crc_t10dif_pmull_p64) +SYM_FUNC_START(crc_t10dif_pmull_p64) crc_t10dif_pmull p64 -ENDPROC(crc_t10dif_pmull_p64) +SYM_FUNC_END(crc_t10dif_pmull_p64) .section ".rodata", "a" .align 4 |