crypto: arm64/sha1-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/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 46049850727de821b516a5a12f12a195d460f091..78eb35fb505608826c0aeaba39120494e9831bb5 100644 (file)
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -69,30 +69,36 @@
         *                        int blocks)
         */
 ENTRY(sha1_ce_transform)
+       frame_push      3
+
+       mov             x19, x0
+       mov             x20, x1
+       mov             x21, x2
+
        /* load round constants */
-       loadrc          k0.4s, 0x5a827999, w6
+0:     loadrc          k0.4s, 0x5a827999, w6
        loadrc          k1.4s, 0x6ed9eba1, w6
        loadrc          k2.4s, 0x8f1bbcdc, w6
        loadrc          k3.4s, 0xca62c1d6, w6
 
        /* load state */
-       ld1             {dgav.4s}, [x0]
-       ldr             dgb, [x0, #16]
+       ld1             {dgav.4s}, [x19]
+       ldr             dgb, [x19, #16]
 
        /* load sha1_ce_state::finalize */
        ldr_l           w4, sha1_ce_offsetof_finalize, x4
-       ldr             w4, [x0, x4]
+       ldr             w4, [x19, x4]
 
        /* load input */
-0:     ld1             {v8.4s-v11.4s}, [x1], #64
-       sub             w2, w2, #1
+1:     ld1             {v8.4s-v11.4s}, [x20], #64
+       sub             w21, w21, #1
 
 CPU_LE(        rev32           v8.16b, v8.16b          )
 CPU_LE(        rev32           v9.16b, v9.16b          )
 CPU_LE(        rev32           v10.16b, v10.16b        )
 CPU_LE(        rev32           v11.16b, v11.16b        )
 
-1:     add             t0.4s, v8.4s, k0.4s
+2:     add             t0.4s, v8.4s, k0.4s
        mov             dg0v.16b, dgav.16b
 
        add_update      c, ev, k0,  8,  9, 10, 11, dgb
@@ -123,16 +129,25 @@ CPU_LE(   rev32           v11.16b, v11.16b        )
        add             dgbv.2s, dgbv.2s, dg1v.2s
        add             dgav.4s, dgav.4s, dg0v.4s
 
-       cbnz            w2, 0b
+       cbz             w21, 3f
+
+       if_will_cond_yield_neon
+       st1             {dgav.4s}, [x19]
+       str             dgb, [x19, #16]
+       do_cond_yield_neon
+       b               0b
+       endif_yield_neon
+
+       b               1b
 
        /*
         * Final block: add padding and total bit count.
         * Skip if the input size was not a round multiple of the block size,
         * the padding is handled by the C code in that case.
         */
-       cbz             x4, 3f
+3:     cbz             x4, 4f
        ldr_l           w4, sha1_ce_offsetof_count, x4
-       ldr             x4, [x0, x4]
+       ldr             x4, [x19, x4]
        movi            v9.2d, #0
        mov             x8, #0x80000000
        movi            v10.2d, #0
@@ -141,10 +156,11 @@ CPU_LE(   rev32           v11.16b, v11.16b        )
        mov             x4, #0
        mov             v11.d[0], xzr
        mov             v11.d[1], x7
-       b               1b
+       b               2b
 
        /* store new state */
-3:     st1             {dgav.4s}, [x0]
-       str             dgb, [x0, #16]
+4:     st1             {dgav.4s}, [x19]
+       str             dgb, [x19, #16]
+       frame_pop
        ret
 ENDPROC(sha1_ce_transform)