crypto: arm64/aes-neonbs - remove NEON yield calls

There is no need for elaborate yield handling in the bit-sliced NEON
implementation of AES, given that skciphers are naturally bounded by the
size of the chunks returned by the skcipher_walk API. So remove the
yield calls from the asm code.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 63a52ad9a75c03deab976e09e5a709135f71102f..a3405b8c344b5b24c71c831931cb69921f39990a 100644 (file)
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -613,7 +613,6 @@ SYM_FUNC_END(aesbs_decrypt8)
        st1             {\o7\().16b}, [x19], #16
 
        cbz             x23, 1f
-       cond_yield_neon
        b               99b
 
 1:     frame_pop
@@ -715,7 +714,6 @@ SYM_FUNC_START(aesbs_cbc_decrypt)
 1:     st1             {v24.16b}, [x24]                // store IV
 
        cbz             x23, 2f
-       cond_yield_neon
        b               99b
 
 2:     frame_pop
@@ -801,7 +799,7 @@ SYM_FUNC_END(__xts_crypt8)
        mov             x23, x4
        mov             x24, x5
 
-0:     movi            v30.2s, #0x1
+       movi            v30.2s, #0x1
        movi            v25.2s, #0x87
        uzp1            v30.4s, v30.4s, v25.4s
        ld1             {v25.16b}, [x24]
@@ -846,7 +844,6 @@ SYM_FUNC_END(__xts_crypt8)
        cbz             x23, 1f
        st1             {v25.16b}, [x24]
 
-       cond_yield_neon 0b
        b               99b
 
 1:     st1             {v25.16b}, [x24]
@@ -889,7 +886,7 @@ SYM_FUNC_START(aesbs_ctr_encrypt)
        cset            x26, ne
        add             x23, x23, x26           // do one extra block if final
 
-98:    ldp             x7, x8, [x24]
+       ldp             x7, x8, [x24]
        ld1             {v0.16b}, [x24]
 CPU_LE(        rev             x7, x7          )
 CPU_LE(        rev             x8, x8          )
@@ -967,7 +964,6 @@ CPU_LE(     rev             x8, x8          )
        st1             {v0.16b}, [x24]
        cbz             x23, .Lctr_done
 
-       cond_yield_neon 98b
        b               99b
 
 .Lctr_done: