crypto: arm64/crct10dif-ce - yield NEON after every block of input

Avoid excessive scheduling delays under a preemptible kernel by
yielding the NEON after every block of input.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index f179c01..663ea71 100644 (file)
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -74,13 +74,19 @@
        .text
        .cpu            generic+crypto
 
-       arg1_low32      .req    w0
-       arg2            .req    x1
-       arg3            .req    x2
+       arg1_low32      .req    w19
+       arg2            .req    x20
+       arg3            .req    x21
 
        vzr             .req    v13
 
 ENTRY(crc_t10dif_pmull)
+       frame_push      3, 128
+
+       mov             arg1_low32, w0
+       mov             arg2, x1
+       mov             arg3, x2
+
        movi            vzr.16b, #0             // init zero register
 
        // adjust the 16-bit initial_crc value, scale it to 32 bits
@@ -175,8 +181,25 @@ CPU_LE(    ext             v12.16b, v12.16b, v12.16b, #8   )
        subs            arg3, arg3, #128
 
        // check if there is another 64B in the buffer to be able to fold
-       b.ge            _fold_64_B_loop
+       b.lt            _fold_64_B_end
+
+       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]
+       ldr_l           q10, rk3, x8
+       movi            vzr.16b, #0             // init zero register
+       endif_yield_neon
+
+       b               _fold_64_B_loop
 
+_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
@@ -304,6 +327,7 @@ _barrett:
 _cleanup:
        // scale the result back to 16 bits
        lsr             x0, x0, #16
+       frame_pop
        ret
 
 _less_than_128: