From: Ard Biesheuvel <ard.biesheuvel@linaro.org> To: linux-crypto@vger.kernel.org Cc: Mark Rutland <mark.rutland@arm.com>, herbert@gondor.apana.org.au, Ard Biesheuvel <ard.biesheuvel@linaro.org>, Peter Zijlstra <peterz@infradead.org>, Catalin Marinas <catalin.marinas@arm.com>, Sebastian Andrzej Siewior <bigeasy@linutronix.de>, Will Deacon <will.deacon@arm.com>, Russell King - ARM Linux <linux@armlinux.org.uk>, Steven Rostedt <rostedt@goodmis.org>, Thomas Gleixner <tglx@linutronix.de>, Dave Martin <Dave.Martin@arm.com>, linux-arm-kernel@lists.infradead.org, linux-rt-users@vger.kernel.org Subject: [PATCH v5 20/23] crypto: arm64/sha3-ce - yield NEON after every block of input Date: Sat, 10 Mar 2018 15:22:05 +0000 [thread overview] Message-ID: <20180310152208.10369-21-ard.biesheuvel@linaro.org> (raw) In-Reply-To: <20180310152208.10369-1-ard.biesheuvel@linaro.org> Avoid excessive scheduling delays under a preemptible kernel by conditionally yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/sha3-ce-core.S | 77 +++++++++++++------- 1 file changed, 50 insertions(+), 27 deletions(-) diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S index 332ad7530690..a7d587fa54f6 100644 --- a/arch/arm64/crypto/sha3-ce-core.S +++ b/arch/arm64/crypto/sha3-ce-core.S @@ -41,9 +41,16 @@ */ .text ENTRY(sha3_ce_transform) - /* load state */ - add x8, x0, #32 - ld1 { v0.1d- v3.1d}, [x0] + frame_push 4 + + mov x19, x0 + mov x20, x1 + mov x21, x2 + mov x22, x3 + +0: /* load state */ + add x8, x19, #32 + ld1 { v0.1d- v3.1d}, [x19] ld1 { v4.1d- v7.1d}, [x8], #32 ld1 { v8.1d-v11.1d}, [x8], #32 ld1 {v12.1d-v15.1d}, [x8], #32 @@ -51,13 +58,13 @@ ENTRY(sha3_ce_transform) ld1 {v20.1d-v23.1d}, [x8], #32 ld1 {v24.1d}, [x8] -0: sub w2, w2, #1 +1: sub w21, w21, #1 mov w8, #24 adr_l x9, .Lsha3_rcon /* load input */ - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b-v31.8b}, [x1], #24 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b-v31.8b}, [x20], #24 eor v0.8b, v0.8b, v25.8b eor v1.8b, v1.8b, v26.8b eor v2.8b, v2.8b, v27.8b @@ -66,10 +73,10 @@ ENTRY(sha3_ce_transform) eor v5.8b, v5.8b, v30.8b eor v6.8b, v6.8b, v31.8b - tbnz x3, #6, 2f // SHA3-512 + tbnz x22, #6, 3f // SHA3-512 - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b-v30.8b}, [x1], #16 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b-v30.8b}, [x20], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b eor v9.8b, v9.8b, v27.8b @@ -77,34 +84,34 @@ ENTRY(sha3_ce_transform) eor v11.8b, v11.8b, v29.8b eor v12.8b, v12.8b, v30.8b - tbnz x3, #4, 1f // SHA3-384 or SHA3-224 + tbnz x22, #4, 2f // SHA3-384 or SHA3-224 // SHA3-256 - ld1 {v25.8b-v28.8b}, [x1], #32 + ld1 {v25.8b-v28.8b}, [x20], #32 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b - b 3f + b 4f -1: tbz x3, #2, 3f // bit 2 cleared? SHA-384 +2: tbz x22, #2, 4f // bit 2 cleared? SHA-384 // SHA3-224 - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b}, [x1], #8 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b}, [x20], #8 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b eor v17.8b, v17.8b, v29.8b - b 3f + b 4f // SHA3-512 -2: ld1 {v25.8b-v26.8b}, [x1], #16 +3: ld1 {v25.8b-v26.8b}, [x20], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b -3: sub w8, w8, #1 +4: sub w8, w8, #1 eor3 v29.16b, v4.16b, v9.16b, v14.16b eor3 v26.16b, v1.16b, v6.16b, v11.16b @@ -183,17 +190,33 @@ ENTRY(sha3_ce_transform) eor v0.16b, v0.16b, v31.16b - cbnz w8, 3b - cbnz w2, 0b + cbnz w8, 4b + cbz w21, 5f + + if_will_cond_yield_neon + add x8, x19, #32 + st1 { v0.1d- v3.1d}, [x19] + st1 { v4.1d- v7.1d}, [x8], #32 + st1 { v8.1d-v11.1d}, [x8], #32 + st1 {v12.1d-v15.1d}, [x8], #32 + st1 {v16.1d-v19.1d}, [x8], #32 + st1 {v20.1d-v23.1d}, [x8], #32 + st1 {v24.1d}, [x8] + do_cond_yield_neon + b 0b + endif_yield_neon + + b 1b /* save state */ - st1 { v0.1d- v3.1d}, [x0], #32 - st1 { v4.1d- v7.1d}, [x0], #32 - st1 { v8.1d-v11.1d}, [x0], #32 - st1 {v12.1d-v15.1d}, [x0], #32 - st1 {v16.1d-v19.1d}, [x0], #32 - st1 {v20.1d-v23.1d}, [x0], #32 - st1 {v24.1d}, [x0] +5: st1 { v0.1d- v3.1d}, [x19], #32 + st1 { v4.1d- v7.1d}, [x19], #32 + st1 { v8.1d-v11.1d}, [x19], #32 + st1 {v12.1d-v15.1d}, [x19], #32 + st1 {v16.1d-v19.1d}, [x19], #32 + st1 {v20.1d-v23.1d}, [x19], #32 + st1 {v24.1d}, [x19] + frame_pop ret ENDPROC(sha3_ce_transform) -- 2.15.1
WARNING: multiple messages have this Message-ID (diff)
From: ard.biesheuvel@linaro.org (Ard Biesheuvel) To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v5 20/23] crypto: arm64/sha3-ce - yield NEON after every block of input Date: Sat, 10 Mar 2018 15:22:05 +0000 [thread overview] Message-ID: <20180310152208.10369-21-ard.biesheuvel@linaro.org> (raw) In-Reply-To: <20180310152208.10369-1-ard.biesheuvel@linaro.org> Avoid excessive scheduling delays under a preemptible kernel by conditionally yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/sha3-ce-core.S | 77 +++++++++++++------- 1 file changed, 50 insertions(+), 27 deletions(-) diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S index 332ad7530690..a7d587fa54f6 100644 --- a/arch/arm64/crypto/sha3-ce-core.S +++ b/arch/arm64/crypto/sha3-ce-core.S @@ -41,9 +41,16 @@ */ .text ENTRY(sha3_ce_transform) - /* load state */ - add x8, x0, #32 - ld1 { v0.1d- v3.1d}, [x0] + frame_push 4 + + mov x19, x0 + mov x20, x1 + mov x21, x2 + mov x22, x3 + +0: /* load state */ + add x8, x19, #32 + ld1 { v0.1d- v3.1d}, [x19] ld1 { v4.1d- v7.1d}, [x8], #32 ld1 { v8.1d-v11.1d}, [x8], #32 ld1 {v12.1d-v15.1d}, [x8], #32 @@ -51,13 +58,13 @@ ENTRY(sha3_ce_transform) ld1 {v20.1d-v23.1d}, [x8], #32 ld1 {v24.1d}, [x8] -0: sub w2, w2, #1 +1: sub w21, w21, #1 mov w8, #24 adr_l x9, .Lsha3_rcon /* load input */ - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b-v31.8b}, [x1], #24 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b-v31.8b}, [x20], #24 eor v0.8b, v0.8b, v25.8b eor v1.8b, v1.8b, v26.8b eor v2.8b, v2.8b, v27.8b @@ -66,10 +73,10 @@ ENTRY(sha3_ce_transform) eor v5.8b, v5.8b, v30.8b eor v6.8b, v6.8b, v31.8b - tbnz x3, #6, 2f // SHA3-512 + tbnz x22, #6, 3f // SHA3-512 - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b-v30.8b}, [x1], #16 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b-v30.8b}, [x20], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b eor v9.8b, v9.8b, v27.8b @@ -77,34 +84,34 @@ ENTRY(sha3_ce_transform) eor v11.8b, v11.8b, v29.8b eor v12.8b, v12.8b, v30.8b - tbnz x3, #4, 1f // SHA3-384 or SHA3-224 + tbnz x22, #4, 2f // SHA3-384 or SHA3-224 // SHA3-256 - ld1 {v25.8b-v28.8b}, [x1], #32 + ld1 {v25.8b-v28.8b}, [x20], #32 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b - b 3f + b 4f -1: tbz x3, #2, 3f // bit 2 cleared? SHA-384 +2: tbz x22, #2, 4f // bit 2 cleared? SHA-384 // SHA3-224 - ld1 {v25.8b-v28.8b}, [x1], #32 - ld1 {v29.8b}, [x1], #8 + ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v29.8b}, [x20], #8 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b eor v17.8b, v17.8b, v29.8b - b 3f + b 4f // SHA3-512 -2: ld1 {v25.8b-v26.8b}, [x1], #16 +3: ld1 {v25.8b-v26.8b}, [x20], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b -3: sub w8, w8, #1 +4: sub w8, w8, #1 eor3 v29.16b, v4.16b, v9.16b, v14.16b eor3 v26.16b, v1.16b, v6.16b, v11.16b @@ -183,17 +190,33 @@ ENTRY(sha3_ce_transform) eor v0.16b, v0.16b, v31.16b - cbnz w8, 3b - cbnz w2, 0b + cbnz w8, 4b + cbz w21, 5f + + if_will_cond_yield_neon + add x8, x19, #32 + st1 { v0.1d- v3.1d}, [x19] + st1 { v4.1d- v7.1d}, [x8], #32 + st1 { v8.1d-v11.1d}, [x8], #32 + st1 {v12.1d-v15.1d}, [x8], #32 + st1 {v16.1d-v19.1d}, [x8], #32 + st1 {v20.1d-v23.1d}, [x8], #32 + st1 {v24.1d}, [x8] + do_cond_yield_neon + b 0b + endif_yield_neon + + b 1b /* save state */ - st1 { v0.1d- v3.1d}, [x0], #32 - st1 { v4.1d- v7.1d}, [x0], #32 - st1 { v8.1d-v11.1d}, [x0], #32 - st1 {v12.1d-v15.1d}, [x0], #32 - st1 {v16.1d-v19.1d}, [x0], #32 - st1 {v20.1d-v23.1d}, [x0], #32 - st1 {v24.1d}, [x0] +5: st1 { v0.1d- v3.1d}, [x19], #32 + st1 { v4.1d- v7.1d}, [x19], #32 + st1 { v8.1d-v11.1d}, [x19], #32 + st1 {v12.1d-v15.1d}, [x19], #32 + st1 {v16.1d-v19.1d}, [x19], #32 + st1 {v20.1d-v23.1d}, [x19], #32 + st1 {v24.1d}, [x19] + frame_pop ret ENDPROC(sha3_ce_transform) -- 2.15.1
next prev parent reply other threads:[~2018-03-10 15:22 UTC|newest] Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-03-10 15:21 [PATCH v5 00/23] crypto: arm64 - play nice with CONFIG_PREEMPT Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 01/23] crypto: testmgr - add a new test case for CRC-T10DIF Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 02/23] crypto: arm64/aes-ce-ccm - move kernel mode neon en/disable into loop Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 03/23] crypto: arm64/aes-blk " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 04/23] crypto: arm64/aes-bs " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 05/23] crypto: arm64/chacha20 " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 06/23] crypto: arm64/aes-blk - remove configurable interleave Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 07/23] crypto: arm64/aes-blk - add 4 way interleave to CBC encrypt path Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 08/23] crypto: arm64/aes-blk - add 4 way interleave to CBC-MAC " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 09/23] crypto: arm64/sha256-neon - play nice with CONFIG_PREEMPT kernels Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 10/23] arm64: assembler: add utility macros to push/pop stack frames Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 11/23] arm64: assembler: add macros to conditionally yield the NEON under PREEMPT Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 12/23] crypto: arm64/sha1-ce - yield NEON after every block of input Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 13/23] crypto: arm64/sha2-ce " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:21 ` [PATCH v5 14/23] crypto: arm64/aes-ccm " Ard Biesheuvel 2018-03-10 15:21 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 15/23] crypto: arm64/aes-blk " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 16/23] crypto: arm64/aes-bs " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 17/23] crypto: arm64/aes-ghash " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 18/23] crypto: arm64/crc32-ce " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 19/23] crypto: arm64/crct10dif-ce " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel [this message] 2018-03-10 15:22 ` [PATCH v5 20/23] crypto: arm64/sha3-ce " Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 21/23] crypto: arm64/sha512-ce " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 22/23] crypto: arm64/sm3-ce " Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-10 15:22 ` [PATCH v5 23/23] DO NOT MERGE Ard Biesheuvel 2018-03-10 15:22 ` Ard Biesheuvel 2018-03-11 5:16 ` [PATCH v5 00/23] crypto: arm64 - play nice with CONFIG_PREEMPT Vakul Garg 2018-03-11 5:16 ` Vakul Garg 2018-03-11 8:55 ` Ard Biesheuvel 2018-03-11 8:55 ` Ard Biesheuvel 2018-03-16 15:57 ` Herbert Xu 2018-03-16 15:57 ` Herbert Xu 2018-03-19 15:31 ` Ard Biesheuvel 2018-03-19 15:31 ` Ard Biesheuvel 2018-03-19 23:36 ` Herbert Xu 2018-03-19 23:36 ` Herbert Xu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20180310152208.10369-21-ard.biesheuvel@linaro.org \ --to=ard.biesheuvel@linaro.org \ --cc=Dave.Martin@arm.com \ --cc=bigeasy@linutronix.de \ --cc=catalin.marinas@arm.com \ --cc=herbert@gondor.apana.org.au \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-crypto@vger.kernel.org \ --cc=linux-rt-users@vger.kernel.org \ --cc=linux@armlinux.org.uk \ --cc=mark.rutland@arm.com \ --cc=peterz@infradead.org \ --cc=rostedt@goodmis.org \ --cc=tglx@linutronix.de \ --cc=will.deacon@arm.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.