Received: by 2002:a05:7412:31a9:b0:e2:908c:2ebd with SMTP id et41csp2920568rdb; Tue, 12 Sep 2023 17:08:58 -0700 (PDT) X-Google-Smtp-Source: AGHT+IGRVT59Sr2ed/lqUDHkCj1utjx9+k3RAS93N3LGR+3rme9ich2gqAQt8CITOHO0t0OlhmEE X-Received: by 2002:a05:6a00:852:b0:68a:5197:619f with SMTP id q18-20020a056a00085200b0068a5197619fmr1487602pfk.31.1694563737814; Tue, 12 Sep 2023 17:08:57 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1694563737; cv=none; d=google.com; s=arc-20160816; b=x5aOUykbYxPznsnPvFVvQCx/rpauMkYOxpEt6cU/MWbGodTfUFlw5xlL5+vnnbrNsv s8AwzCGCscKPr9dKHmHI/yA0lcOtVVJiFV1MngqzZIz5LK6Xl61uhQi9KNwDAj7v8ZYk Z8C58qVJ3vK3oAwfR4TzeeAXznlnSXOU2ROYGXQPTXU0coHqflOLhni6A+w7vkazgxRS b9tW3i2qWOeH3AdZcUQ2ndR/XENABNpl48z9tHSJOmAZZSJfyQLvIEf2Qbpl5p5iiiVe 73RFo0giqAhbEDBOVP7eIKWHgZrrH+NBH970+g4pdUmjOzoVuuBJ/9UcBf4lnX1F47Hj Jdig== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:cc:to:subject :message-id:date:from:in-reply-to:references:mime-version :dkim-signature; bh=GhbwcGjh9waE2xmi4ypz1ufZ0VvBoJLRFjEGLC9R+hI=; fh=QMwngwPg2LVBpjV0a5twaAy0Rq+IPtvcRCu7zrbEKWg=; b=Zte3KCv3ubWpcxRRZRiuTwJT1J9qWMB6qemmbW+4w0GdlqQidP5y+gScvVSH1VwGhP ppJXcoxgv+nrRGRonoEE74M5ozpDyOs9r0ReYr9SYYQVdjUFOo0s3XIIOoQCqQSjIp/U gUUX0b1f1ty4vbeYsfTqU3aR0v5FfEYJB1sJoZdW3g+OrKVuYItF91aoUGlVdau1A4KQ dVsGi370fI9ti/YG/LWCes6gQpXGDU5tMMqmJ3RfY9OEidEgqkDEpHzXIg5+nu3GibPS ooq4j1QKycBayRcN9U0J33+A2SrfxlJGVezZhIB5iUxdSnx9EUsiWoXLpZg0lYKg0Qsh BWcw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@kernel.org header.s=k20201202 header.b=schTMMJE; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.36 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=kernel.org Return-Path: Received: from pete.vger.email (pete.vger.email. [23.128.96.36]) by mx.google.com with ESMTPS id g190-20020a636bc7000000b00577a519621bsi2224372pgc.231.2023.09.12.17.08.51 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 12 Sep 2023 17:08:57 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.36 as permitted sender) client-ip=23.128.96.36; Authentication-Results: mx.google.com; dkim=pass header.i=@kernel.org header.s=k20201202 header.b=schTMMJE; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.36 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=kernel.org Received: from out1.vger.email (depot.vger.email [IPv6:2620:137:e000::3:0]) by pete.vger.email (Postfix) with ESMTP id 2C27E8186509; Tue, 12 Sep 2023 17:07:21 -0700 (PDT) X-Virus-Status: Clean X-Virus-Scanned: clamav-milter 0.103.10 at pete.vger.email Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231704AbjIMAHQ (ORCPT + 99 others); Tue, 12 Sep 2023 20:07:16 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59236 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229589AbjIMAHP (ORCPT ); Tue, 12 Sep 2023 20:07:15 -0400 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D414B10E6 for ; Tue, 12 Sep 2023 17:07:11 -0700 (PDT) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 751FAC433C9 for ; Wed, 13 Sep 2023 00:07:11 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1694563631; bh=VlNGzwkcnkJZZXfSRX8hKY5qTg4+EZPM0eItVOjG+20=; h=References:In-Reply-To:From:Date:Subject:To:Cc:From; b=schTMMJEfg+jjXT9+frPlcDC5efg7e3IPfn6Ck6UpB5H4fGqx8yNncINIeFJiFA32 7eNIYOSyWrBWn+irAiiBzOraXk4+tOlKst92rJe8jquI150N0UJZqr7VhDWnmbKAK7 fWITfUKCuKEX5MGfr4sox7esR6etPJPeeMutQ3v3r4iNU1BMcAUtYnOwAVkJ5HhHuV BHx56lrDWQH7o5N6VZ8tTtz/ouiDE2THZwthVzz8KA9lZT9iHo8e2UHxyn3+KKt4KM HcXTvpZgpwA2n/lcccD6CH5QVqWz8XCjyDb4GaXeEYxUYIxR3DG57xl8akB09afKoC 2SHX014YjzgQw== Received: by mail-lj1-f180.google.com with SMTP id 38308e7fff4ca-2bd6611873aso99789271fa.1 for ; Tue, 12 Sep 2023 17:07:11 -0700 (PDT) X-Gm-Message-State: AOJu0YxawEAocqtg5w3WeJ+rjfs459uFqOvwdl2pCd7H1HsPyBxhfMKM c5a/C7YOaMspVn9HHvzzl10CcTgi8dS93Aed+54= X-Received: by 2002:a2e:501d:0:b0:2bf:b770:ac2e with SMTP id e29-20020a2e501d000000b002bfb770ac2emr295798ljb.33.1694563629560; Tue, 12 Sep 2023 17:07:09 -0700 (PDT) MIME-Version: 1.0 References: <20230912072740.2544-1-jszhang@kernel.org> In-Reply-To: From: Guo Ren Date: Wed, 13 Sep 2023 08:06:56 +0800 X-Gmail-Original-Message-ID: Message-ID: Subject: Re: [PATCH] riscv: errata: thead: use riscv_nonstd_cache_ops for CMO To: Jessica Clarke Cc: Jisheng Zhang , Arnd Bergmann , Paul Walmsley , Palmer Dabbelt , Albert Ou , linux-riscv , linux-kernel@vger.kernel.org Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (pete.vger.email [0.0.0.0]); Tue, 12 Sep 2023 17:07:21 -0700 (PDT) X-Spam-Status: No, score=-1.2 required=5.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS autolearn=unavailable autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on pete.vger.email On Wed, Sep 13, 2023 at 3:00=E2=80=AFAM Jessica Clarke = wrote: > > On 12 Sep 2023, at 11:53, Guo Ren wrote: > > > > On Tue, Sep 12, 2023 at 03:27:40PM +0800, Jisheng Zhang wrote: > >> Previously, we use alternative mechanism to dynamically patch > >> the CMO operations for THEAD C906/C910 during boot for performance > >> reason. But as pointed out by Arnd, "there is already a significant > >> cost in accessing the invalidated cache lines afterwards, which is > >> likely going to be much higher than the cost of an indirect branch". > >> And indeed, there's no performance difference with GMAC and EMMC per > >> my test on Sipeed Lichee Pi 4A board. > >> > >> Use riscv_nonstd_cache_ops for THEAD C906/C910 CMO to simplify > >> the alternative code, and to acchieve Arnd's goal -- "I think > >> moving the THEAD ops at the same level as all nonstandard operations > >> makes sense, but I'd still leave CMO as an explicit fast path that > >> avoids the indirect branch. This seems like the right thing to do both > >> for readability and for platforms on which the indirect branch has a > >> noticeable overhead." > >> > >> Signed-off-by: Jisheng Zhang > >> --- > >> arch/riscv/Kconfig.errata | 1 + > >> arch/riscv/errata/thead/errata.c | 76 +++++++++++++++++++++++++++- > >> arch/riscv/include/asm/errata_list.h | 50 +++--------------- > >> 3 files changed, 81 insertions(+), 46 deletions(-) > >> > >> diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata > >> index 566bcefeab50..d7972914f9de 100644 > >> --- a/arch/riscv/Kconfig.errata > >> +++ b/arch/riscv/Kconfig.errata > >> @@ -78,6 +78,7 @@ config ERRATA_THEAD_CMO > >> bool "Apply T-Head cache management errata" > >> depends on ERRATA_THEAD && MMU > >> select RISCV_DMA_NONCOHERENT > >> + select RISCV_NONSTANDARD_CACHE_OPS > >> default y > >> help > >> This will apply the cache management errata to handle the > >> diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thea= d/errata.c > >> index 0554ed4bf087..1c320abfe446 100644 > >> --- a/arch/riscv/errata/thead/errata.c > >> +++ b/arch/riscv/errata/thead/errata.c > >> @@ -12,8 +12,10 @@ > >> #include > >> #include > >> #include > >> +#include > >> #include > >> #include > >> +#include > >> #include > >> #include > >> > >> @@ -33,6 +35,75 @@ static bool errata_probe_pbmt(unsigned int stage, > >> return false; > >> } > >> > >> +/* > >> + * dcache.ipa rs1 (invalidate, physical address) > >> + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> + * 0000001 01010 rs1 000 00000 0001011 > >> + * dache.iva rs1 (invalida, virtual address) > >> + * 0000001 00110 rs1 000 00000 0001011 > > Remove dache.iva rs1 ... > > > >> + * > >> + * dcache.cpa rs1 (clean, physical address) > >> + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> + * 0000001 01001 rs1 000 00000 0001011 > > Remove dcache.cpa rs1 ... > > > >> + * dcache.cva rs1 (clean, virtual address) > >> + * 0000001 00101 rs1 000 00000 0001011 > > Remove dcache.cva rs1 ... > > > >> + * > >> + * dcache.cipa rs1 (clean then invalidate, physical address) > >> + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> + * 0000001 01011 rs1 000 00000 0001011 > >> + * dcache.civa rs1 (... virtual address) > >> + * 0000001 00111 rs1 000 00000 0001011 > > Remove dcache.civa rs1 ... > > > >> + * > >> + * sync.s (make sure all cache operations finished) > >> + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> + * 0000000 11001 00000 000 00000 0001011 > >> + */ > >> +#define THEAD_inval_A0 ".long 0x0265000b" > >> +#define THEAD_clean_A0 ".long 0x0255000b" > >> +#define THEAD_flush_A0 ".long 0x0275000b" > >> +#define THEAD_SYNC_S ".long 0x0190000b" > >> + > >> +#define THEAD_CMO_OP(_op, _start, _size, _cachesize) \ > >> +asm volatile("mv a0, %1\n\t" \ > >> + "j 2f\n\t" \ > >> + "3:\n\t" \ > >> + THEAD_##_op##_A0 "\n\t" \ > >> + "add a0, a0, %0\n\t" \ > >> + "2:\n\t" \ > >> + "bltu a0, %2, 3b\n\t" \ > >> + THEAD_SYNC_S \ > >> + : : "r"(_cachesize), \ > >> + "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \ > >> + "r"((unsigned long)(_start) + (_size)) \ > >> + : "a0") > >> + > >> +static void thead_errata_cache_inv(phys_addr_t paddr, size_t size) > >> +{ > >> + void *vaddr =3D phys_to_virt(paddr); > > No need to phys_to_virt, and we could use paddr directly (dcache.ipa > > rs1). > > > >> + > >> + THEAD_CMO_OP(inval, vaddr, size, riscv_cbom_block_size); > >> +} > >> + > >> +static void thead_errata_cache_wback(phys_addr_t paddr, size_t size) > >> +{ > >> + void *vaddr =3D phys_to_virt(paddr); > >> + > >> + THEAD_CMO_OP(clean, vaddr, size, riscv_cbom_block_size); > >> +} > > Please remove the thead_errata_cache_wback because T-HEAD processors > > would prioritize using an invalid cacheline instead of evicting an > > existing cacheline. When we do dcache clean, the following operations > > are to let other interconnect masters read. So, keeping wback_inv for > > T-HEAD processors is the best choice, and maybe some other processors' > > vendor has a different idea, but please use the wback_inv instead of > > wback_only for the T-HEAD processors. > > Unless you can demonstrate that your cores have significantly worse > performance when using wback instead of wback_inv I do not think the > non-standard implementation should deviate from the semantics of the > standard one. There are efforts to unify the implemented semantics of > the operations across architectures and this would obstruct those. I'm afraid I have to disagree with the view that this obstructs "unifying the implemented semantics of the operations across architectures." static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops =3D { - .wback =3D &thead_errata_cache_wback, + .wback =3D &thead_errata_cache_wback_inv, .inv =3D &thead_errata_cache_inv, .wback_inv =3D &thead_errata_cache_wback_inv, I don't see how the above patch obstructs unifying. On the contrary, it decreases the custom function, which could help unify. Could you give the least respect for the vendor's choice? > > Jess > > >> + > >> +static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t si= ze) > >> +{ > >> + void *vaddr =3D phys_to_virt(paddr); > > Ditto. > > > >> + > >> + THEAD_CMO_OP(flush, vaddr, size, riscv_cbom_block_size); > >> +} > >> + > >> +static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops =3D { > >> + .wback =3D &thead_errata_cache_wback, > > Please .wback =3D &thead_errata_cache_wback_inv, > > > > > >> + .inv =3D &thead_errata_cache_inv, > >> + .wback_inv =3D &thead_errata_cache_wback_inv, > >> +}; > >> + > >> static bool errata_probe_cmo(unsigned int stage, > >> unsigned long arch_id, unsigned long impid) > >> { > >> @@ -48,6 +119,8 @@ static bool errata_probe_cmo(unsigned int stage, > >> if (stage =3D=3D RISCV_ALTERNATIVES_BOOT) { > >> riscv_cbom_block_size =3D L1_CACHE_BYTES; > >> riscv_noncoherent_supported(); > >> + if (IS_ENABLED(CONFIG_RISCV_NONSTANDARD_CACHE_OPS)) > >> + riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops); > >> } > >> > >> return true; > >> @@ -77,8 +150,7 @@ static u32 thead_errata_probe(unsigned int stage, > >> if (errata_probe_pbmt(stage, archid, impid)) > >> cpu_req_errata |=3D BIT(ERRATA_THEAD_PBMT); > >> > >> - if (errata_probe_cmo(stage, archid, impid)) > >> - cpu_req_errata |=3D BIT(ERRATA_THEAD_CMO); > >> + errata_probe_cmo(stage, archid, impid); > >> > >> if (errata_probe_pmu(stage, archid, impid)) > >> cpu_req_errata |=3D BIT(ERRATA_THEAD_PMU); > >> diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include= /asm/errata_list.h > >> index b55b434f0059..ea33288f8a25 100644 > >> --- a/arch/riscv/include/asm/errata_list.h > >> +++ b/arch/riscv/include/asm/errata_list.h > >> @@ -24,9 +24,8 @@ > >> > >> #ifdef CONFIG_ERRATA_THEAD > >> #define ERRATA_THEAD_PBMT 0 > >> -#define ERRATA_THEAD_CMO 1 > >> -#define ERRATA_THEAD_PMU 2 > >> -#define ERRATA_THEAD_NUMBER 3 > >> +#define ERRATA_THEAD_PMU 1 > >> +#define ERRATA_THEAD_NUMBER 2 > >> #endif > >> > >> #ifdef __ASSEMBLY__ > >> @@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE( \ > >> #define ALT_THEAD_PMA(_val) > >> #endif > >> > >> -/* > >> - * dcache.ipa rs1 (invalidate, physical address) > >> - * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> - * 0000001 01010 rs1 000 00000 0001011 > >> - * dache.iva rs1 (invalida, virtual address) > >> - * 0000001 00110 rs1 000 00000 0001011 > >> - * > >> - * dcache.cpa rs1 (clean, physical address) > >> - * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> - * 0000001 01001 rs1 000 00000 0001011 > >> - * dcache.cva rs1 (clean, virtual address) > >> - * 0000001 00101 rs1 000 00000 0001011 > >> - * > >> - * dcache.cipa rs1 (clean then invalidate, physical address) > >> - * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> - * 0000001 01011 rs1 000 00000 0001011 > >> - * dcache.civa rs1 (... virtual address) > >> - * 0000001 00111 rs1 000 00000 0001011 > >> - * > >> - * sync.s (make sure all cache operations finished) > >> - * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | > >> - * 0000000 11001 00000 000 00000 0001011 > >> - */ > >> -#define THEAD_inval_A0 ".long 0x0265000b" > >> -#define THEAD_clean_A0 ".long 0x0255000b" > >> -#define THEAD_flush_A0 ".long 0x0275000b" > >> -#define THEAD_SYNC_S ".long 0x0190000b" > >> - > >> #define ALT_CMO_OP(_op, _start, _size, _cachesize) \ > >> -asm volatile(ALTERNATIVE_2( \ > >> - __nops(6), \ > >> +asm volatile(ALTERNATIVE( \ > >> + __nops(5), \ > >> "mv a0, %1\n\t" \ > >> "j 2f\n\t" \ > >> "3:\n\t" \ > >> CBO_##_op(a0) \ > >> "add a0, a0, %0\n\t" \ > >> "2:\n\t" \ > >> - "bltu a0, %2, 3b\n\t" \ > >> - "nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM, \ > >> - "mv a0, %1\n\t" \ > >> - "j 2f\n\t" \ > >> - "3:\n\t" \ > >> - THEAD_##_op##_A0 "\n\t" \ > >> - "add a0, a0, %0\n\t" \ > >> - "2:\n\t" \ > >> - "bltu a0, %2, 3b\n\t" \ > >> - THEAD_SYNC_S, THEAD_VENDOR_ID, \ > >> - ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO) \ > >> + "bltu a0, %2, 3b\n\t", \ > >> + 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM) \ > >> : : "r"(_cachesize), \ > >> "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \ > >> "r"((unsigned long)(_start) + (_size)) \ > >> -- > >> 2.40.1 > >> > >> > >> _______________________________________________ > >> linux-riscv mailing list > >> linux-riscv@lists.infradead.org > >> http://lists.infradead.org/mailman/listinfo/linux-riscv > >> > > > > _______________________________________________ > > linux-riscv mailing list > > linux-riscv@lists.infradead.org > > http://lists.infradead.org/mailman/listinfo/linux-riscv > > --=20 Best Regards Guo Ren