From patchwork Thu Oct 12 14:37:45 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jisheng Zhang X-Patchwork-Id: 13419348 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 0E6D2CDB47E for ; Thu, 12 Oct 2023 14:50:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-Id:Date:Subject:Cc:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=IAs5I8h7JoXw8kjcLfkfxjwKCeQDyqSDNlta/tIcS2w=; b=Yf9gK3QU+oh5I/ wNMJ3dgMVoml/gysczKKGdjZKfyfdgnKw1Ud7lIkmMZmcxZ5qZC3Oeua8y3pa8gHQd/LEd6esspW9 Mie4AFGp0GkPEjbfIzY0iq5GkzdgNqPXvuVLbnvzVLF7+aaDzWBDWJS38k2mL+Yj1r12kHxWBF8lF FvsnxaILw9gvBffTJFs01tJYhEqLB+EBHGCbDeDFFbWreK+GnrndRUuGhV640faTFA0DOGK96s6vM ukwlGx3c31fSwHcDPF8fMlP7ThxL4swW5w1skV6XL3nLOLEbDCV7K7OZaYtMLvey8dUcO4WSp0cTv ZpNcudReiYTN34pT8htQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qqx0o-001DVl-0E; Thu, 12 Oct 2023 14:50:06 +0000 Received: from sin.source.kernel.org ([145.40.73.55]) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qqx0j-001DU0-38 for linux-riscv@lists.infradead.org; Thu, 12 Oct 2023 14:50:04 +0000 Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sin.source.kernel.org (Postfix) with ESMTP id 1623ECE26A5; Thu, 12 Oct 2023 14:50:00 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9E5A5C433C7; Thu, 12 Oct 2023 14:49:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1697122198; bh=p/CDJgMvaNR4UZQdx7MrqZ6c6bwx0gbu1EVlg3gF2aw=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=u6NLMOmSr/gmSq8XDPliu/QE5ORuQaHVGQIvp43kIjOnPVaeHng2Uh3Y0NRveSvUG gtgaWby5zaKUKRPtBMS4BzMnReBKNuZjEX3oo4zah7E7nr3k23YOi/MaKRQIG5sLEL EDxiQ4rrXp4Kk4lmbQ7BeJL7tS1CvpLuPOXmE4m3o37SPisVZqvbzB9nsdPcKs6vKV ylE1L3dEYJaBkgibn8r4qAk/pWGlDPeNfMcCy859LuUS21mlNW0BCKOmEdmND4IHfZ NP7l8JRqfbJGquYqCbBvCFL4mAx6aKIES012RkHHXWphH8fIMOdP/85H+AT5GW40pF VH/f/NZW4VE0g== From: Jisheng Zhang To: Paul Walmsley , Palmer Dabbelt , Albert Ou Cc: Guo Ren , linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org, Emil Renner Berthing , Conor Dooley Subject: [PATCH v4 1/2] riscv: errata: thead: use riscv_nonstd_cache_ops for CMO Date: Thu, 12 Oct 2023 22:37:45 +0800 Message-Id: <20231012143746.454-2-jszhang@kernel.org> X-Mailer: git-send-email 2.40.0 In-Reply-To: <20231012143746.454-1-jszhang@kernel.org> References: <20231012143746.454-1-jszhang@kernel.org> MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231012_075002_397177_56274E9E X-CRM114-Status: GOOD ( 14.33 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org 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 Tested-by: Emil Renner Berthing Reviewed-by: Conor Dooley --- arch/riscv/Kconfig.errata | 1 + arch/riscv/errata/thead/errata.c | 75 +++++++++++++++++++++++++++- arch/riscv/include/asm/errata_list.h | 50 +++---------------- 3 files changed, 80 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/thead/errata.c index 0554ed4bf087..3fefeb1b456e 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 + * dcache.iva rs1 (invalidate, 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 (clean then invalidate, 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 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 = phys_to_virt(paddr); + + 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 = phys_to_virt(paddr); + + THEAD_CMO_OP(clean, vaddr, size, riscv_cbom_block_size); +} + +static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size) +{ + void *vaddr = phys_to_virt(paddr); + + THEAD_CMO_OP(flush, vaddr, size, riscv_cbom_block_size); +} + +static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = { + .wback = &thead_errata_cache_wback, + .inv = &thead_errata_cache_inv, + .wback_inv = &thead_errata_cache_wback_inv, +}; + static bool errata_probe_cmo(unsigned int stage, unsigned long arch_id, unsigned long impid) { @@ -48,6 +119,7 @@ static bool errata_probe_cmo(unsigned int stage, if (stage == RISCV_ALTERNATIVES_BOOT) { riscv_cbom_block_size = L1_CACHE_BYTES; riscv_noncoherent_supported(); + riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops); } return true; @@ -77,8 +149,7 @@ static u32 thead_errata_probe(unsigned int stage, if (errata_probe_pbmt(stage, archid, impid)) cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); - if (errata_probe_cmo(stage, archid, impid)) - cpu_req_errata |= BIT(ERRATA_THEAD_CMO); + errata_probe_cmo(stage, archid, impid); if (errata_probe_pmu(stage, archid, impid)) cpu_req_errata |= 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)) \