From 7c50136a8aba8784f07fb66a950cc61a7f3d2ee3 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 30 Apr 2018 18:18:26 +0200 Subject: crypto: arm64/aes-ghash - 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 Signed-off-by: Herbert Xu --- arch/arm64/crypto/ghash-ce-core.S | 113 +++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 33 deletions(-) (limited to 'arch/arm64/crypto/ghash-ce-core.S') diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index 11ebf1ae248a..dcffb9e77589 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -213,22 +213,31 @@ .endm .macro __pmull_ghash, pn - ld1 {SHASH.2d}, [x3] - ld1 {XL.2d}, [x1] + frame_push 5 + + mov x19, x0 + mov x20, x1 + mov x21, x2 + mov x22, x3 + mov x23, x4 + +0: ld1 {SHASH.2d}, [x22] + ld1 {XL.2d}, [x20] ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 eor SHASH2.16b, SHASH2.16b, SHASH.16b __pmull_pre_\pn /* do the head block first, if supplied */ - cbz x4, 0f - ld1 {T1.2d}, [x4] - b 1f + cbz x23, 1f + ld1 {T1.2d}, [x23] + mov x23, xzr + b 2f -0: ld1 {T1.2d}, [x2], #16 - sub w0, w0, #1 +1: ld1 {T1.2d}, [x21], #16 + sub w19, w19, #1 -1: /* multiply XL by SHASH in GF(2^128) */ +2: /* multiply XL by SHASH in GF(2^128) */ CPU_LE( rev64 T1.16b, T1.16b ) ext T2.16b, XL.16b, XL.16b, #8 @@ -250,9 +259,18 @@ CPU_LE( rev64 T1.16b, T1.16b ) eor T2.16b, T2.16b, XH.16b eor XL.16b, XL.16b, T2.16b - cbnz w0, 0b + cbz w19, 3f + + if_will_cond_yield_neon + st1 {XL.2d}, [x20] + do_cond_yield_neon + b 0b + endif_yield_neon + + b 1b - st1 {XL.2d}, [x1] +3: st1 {XL.2d}, [x20] + frame_pop ret .endm @@ -304,38 +322,55 @@ ENDPROC(pmull_ghash_update_p8) .endm .macro pmull_gcm_do_crypt, enc - ld1 {SHASH.2d}, [x4] - ld1 {XL.2d}, [x1] - ldr x8, [x5, #8] // load lower counter + frame_push 10 + + mov x19, x0 + mov x20, x1 + mov x21, x2 + mov x22, x3 + mov x23, x4 + mov x24, x5 + mov x25, x6 + mov x26, x7 + .if \enc == 1 + ldr x27, [sp, #96] // first stacked arg + .endif + + ldr x28, [x24, #8] // load lower counter +CPU_LE( rev x28, x28 ) + +0: mov x0, x25 + load_round_keys w26, x0 + ld1 {SHASH.2d}, [x23] + ld1 {XL.2d}, [x20] movi MASK.16b, #0xe1 ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 -CPU_LE( rev x8, x8 ) shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, SHASH.16b .if \enc == 1 - ld1 {KS.16b}, [x7] + ld1 {KS.16b}, [x27] .endif -0: ld1 {CTR.8b}, [x5] // load upper counter - ld1 {INP.16b}, [x3], #16 - rev x9, x8 - add x8, x8, #1 - sub w0, w0, #1 +1: ld1 {CTR.8b}, [x24] // load upper counter + ld1 {INP.16b}, [x22], #16 + rev x9, x28 + add x28, x28, #1 + sub w19, w19, #1 ins CTR.d[1], x9 // set lower counter .if \enc == 1 eor INP.16b, INP.16b, KS.16b // encrypt input - st1 {INP.16b}, [x2], #16 + st1 {INP.16b}, [x21], #16 .endif rev64 T1.16b, INP.16b - cmp w6, #12 - b.ge 2f // AES-192/256? + cmp w26, #12 + b.ge 4f // AES-192/256? -1: enc_round CTR, v21 +2: enc_round CTR, v21 ext T2.16b, XL.16b, XL.16b, #8 ext IN1.16b, T1.16b, T1.16b, #8 @@ -390,27 +425,39 @@ CPU_LE( rev x8, x8 ) .if \enc == 0 eor INP.16b, INP.16b, KS.16b - st1 {INP.16b}, [x2], #16 + st1 {INP.16b}, [x21], #16 .endif - cbnz w0, 0b + cbz w19, 3f -CPU_LE( rev x8, x8 ) - st1 {XL.2d}, [x1] - str x8, [x5, #8] // store lower counter + if_will_cond_yield_neon + st1 {XL.2d}, [x20] + .if \enc == 1 + st1 {KS.16b}, [x27] + .endif + do_cond_yield_neon + b 0b + endif_yield_neon + b 1b + +3: st1 {XL.2d}, [x20] .if \enc == 1 - st1 {KS.16b}, [x7] + st1 {KS.16b}, [x27] .endif +CPU_LE( rev x28, x28 ) + str x28, [x24, #8] // store lower counter + + frame_pop ret -2: b.eq 3f // AES-192? +4: b.eq 5f // AES-192? enc_round CTR, v17 enc_round CTR, v18 -3: enc_round CTR, v19 +5: enc_round CTR, v19 enc_round CTR, v20 - b 1b + b 2b .endm /* -- cgit v1.2.3