From patchwork Thu Oct 19 13:59:40 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yu-Chien Peter Lin X-Patchwork-Id: 13429261 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 9572ACDB483 for ; Thu, 19 Oct 2023 14:03:49 +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: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:In-Reply-To:References: List-Owner; bh=ZHZjJRuemTyFldL1UFhw5u4yhobYKOK4IK+AMoSqzLM=; b=KTOESzYeDqvKph LUKaxpoxZHPcznX4cvPNbvJmOoO2cgb6mgo72CrZtE0OMFcSdEiT5RYHyi1Hz+FxID8cpDp2MwWdB wspSPuZQ/ZgoV6fCYbmiD0Tt0c48BKgUnFJzZWLhrh+OJIQ/UnUp6BTIIxcSAmhFaMAcDC3qW9CCU WnauaqiTNpDxnXrS/UNT2515IwC8482HeTkAiXNEnosV9jWUfPeJNkp67sk+Oenhbm2b1ifCEMCmh 3rqKLRCXRrAn+6VoWkfZomJcooU9MEhihk4OOLpWHMYtjZCykQYYIN2wvUpAqEiJqvzr+ZZXPjFQ0 SUy9uiK3jJo05DD24uGQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qtTcT-0000Li-01; Thu, 19 Oct 2023 14:03:25 +0000 Received: from 60-248-80-70.hinet-ip.hinet.net ([60.248.80.70] helo=Atcsqr.andestech.com) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qtTcG-0000F8-10; Thu, 19 Oct 2023 14:03:14 +0000 Received: from mail.andestech.com (ATCPCS16.andestech.com [10.0.1.222]) by Atcsqr.andestech.com with ESMTP id 39JE2iEt029473; Thu, 19 Oct 2023 22:02:44 +0800 (+08) (envelope-from peterlin@andestech.com) Received: from swlinux02.andestech.com (10.0.15.183) by ATCPCS16.andestech.com (10.0.1.222) with Microsoft SMTP Server id 14.3.498.0; Thu, 19 Oct 2023 22:02:41 +0800 From: Yu Chien Peter Lin To: , , , , , , , , , CC: , , , , , "Yu Chien Peter Lin" Subject: [PATCH v2 06/10] perf: RISC-V: Eliminate redundant IRQ enable/disable operations Date: Thu, 19 Oct 2023 21:59:40 +0800 Message-ID: <20231019135940.3658613-1-peterlin@andestech.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 X-Originating-IP: [10.0.15.183] X-DNSRBL: X-MAIL: Atcsqr.andestech.com 39JE2iEt029473 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231019_070312_791836_CE71300B X-CRM114-Status: UNSURE ( 8.09 ) X-CRM114-Notice: Please train this message. X-BeenThere: linux-arm-kernel@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-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org The IRQ enable/disable operations are already performed by the IRQ chip functions riscv_intc_irq_unmask()/riscv_intc_irq_mask() during enable_percpu_irq()/disable_percpu_irq(). We can just do it once. Signed-off-by: Yu Chien Peter Lin --- This patch allows us to drop unnecessary ALT_SBI_PMU_OVF_{DISABLE,ENABLE} in the last PATCH3 [1]. [1] https://patchwork.kernel.org/project/linux-riscv/patch/20230907021635.1002738-4-peterlin@andestech.com/ Changes v1 -> v2: - New patch --- drivers/perf/riscv_pmu_sbi.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 96c7f670c8f0..f340db9ce1e2 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -778,7 +778,6 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) if (riscv_pmu_use_irq) { cpu_hw_evt->irq = riscv_pmu_irq; csr_clear(CSR_IP, BIT(riscv_pmu_irq_num)); - csr_set(CSR_IE, BIT(riscv_pmu_irq_num)); enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE); } @@ -789,7 +788,6 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node) { if (riscv_pmu_use_irq) { disable_percpu_irq(riscv_pmu_irq); - csr_clear(CSR_IE, BIT(riscv_pmu_irq_num)); } /* Disable all counters access for user mode now */ From patchwork Thu Oct 19 14:01:19 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yu-Chien Peter Lin X-Patchwork-Id: 13429275 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 E781CCDB465 for ; Thu, 19 Oct 2023 14:05:27 +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: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:In-Reply-To:References: List-Owner; bh=121ErxycZ714pL0vBsOCCWkp2ng15fEP3yBb/xEmoLE=; b=mQRN1tP0ywK9GV SST3QRVM5sN+gq1+Nkf4rQLHUleEEjG7GG2WeeTyNy/9di5ujisUlgM6BFnUr8aPI3c+IkaS+SJxG Ui8e1Di0OCjUBCU/rMIksEelIWxQ7Waev0VxDpWOdtN87YDIzKajyC6/pc4RXw5K+LXzlRJFPP169 v6gyQaMl4Jp0nSc1Ex2nwGGy24p5Xuq7VActvG4Qn+tWGLoEwF8LrzRZHJoMvi7oZgpd9y6nAliMt voDN1uA8xFsKYwMeUazgN+5Pmi7VcrvxcXgnoA6yn/7Tshr0YUcHGmqCdx5djSC1UekRvEatg2QwW CNzhGBzRQdoR6Gl5v+KQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qtTdy-0000sn-27; Thu, 19 Oct 2023 14:04:58 +0000 Received: from 60-248-80-70.hinet-ip.hinet.net ([60.248.80.70] helo=Atcsqr.andestech.com) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qtTdu-0000qY-2z; Thu, 19 Oct 2023 14:04:57 +0000 Received: from mail.andestech.com (ATCPCS16.andestech.com [10.0.1.222]) by Atcsqr.andestech.com with ESMTP id 39JE4KY5031507; Thu, 19 Oct 2023 22:04:20 +0800 (+08) (envelope-from peterlin@andestech.com) Received: from swlinux02.andestech.com (10.0.15.183) by ATCPCS16.andestech.com (10.0.1.222) with Microsoft SMTP Server id 14.3.498.0; Thu, 19 Oct 2023 22:04:19 +0800 From: Yu Chien Peter Lin To: , , , , , , , , , , , , , , , , , , , , , CC: , , , Subject: [RFC PATCH v2 07/10] perf: RISC-V: Move T-Head PMU to CPU feature alternative framework Date: Thu, 19 Oct 2023 22:01:19 +0800 Message-ID: <20231019140119.3659651-1-peterlin@andestech.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 X-Originating-IP: [10.0.15.183] X-DNSRBL: X-MAIL: Atcsqr.andestech.com 39JE4KY5031507 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231019_070455_400955_D866A201 X-CRM114-Status: GOOD ( 18.82 ) X-BeenThere: linux-arm-kernel@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-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org The custom PMU extension was developed to support perf event sampling prior to the ratification of Sscofpmf. Instead of utilizing the standard bits and CSR of Sscofpmf, a set of custom CSRs is added. So we may consider it as a CPU feature rather than an erratum. T-Head cores need to append "xtheadpmu" to the riscv,isa-extensions for each cpu node in device tree, and enable CONFIG_THEAD_CUSTOM_PMU for proper functioning as of this commit. Signed-off-by: Yu Chien Peter Lin --- Hi All, This is in preparation for introducing other PMU alternative. We follow Conor's suggestion [1] to use cpu feature alternative framework rather than errta, if you want to stick with errata alternative or have other issues, please let me know. Thanks. [1] https://patchwork.kernel.org/project/linux-riscv/patch/20230907021635.1002738-4-peterlin@andestech.com/#25503860 Changes v1 -> v2: - New patch --- arch/riscv/Kconfig.errata | 13 ------------- arch/riscv/errata/thead/errata.c | 19 ------------------- arch/riscv/include/asm/errata_list.h | 15 +-------------- arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/kernel/cpufeature.c | 1 + drivers/perf/Kconfig | 13 +++++++++++++ drivers/perf/riscv_pmu_sbi.c | 16 ++++++++++++++-- 7 files changed, 30 insertions(+), 48 deletions(-) diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 566bcefeab50..35dfb19d6a29 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -85,17 +85,4 @@ config ERRATA_THEAD_CMO If you don't know what to do here, say "Y". -config ERRATA_THEAD_PMU - bool "Apply T-Head PMU errata" - depends on ERRATA_THEAD && RISCV_PMU_SBI - default y - help - The T-Head C9xx cores implement a PMU overflow extension very - similar to the core SSCOFPMF extension. - - This will apply the overflow errata to handle the non-standard - behaviour via the regular SBI PMU driver and interface. - - If you don't know what to do here, say "Y". - endmenu # "CPU errata selection" diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 0554ed4bf087..5de5f7209132 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -53,22 +53,6 @@ static bool errata_probe_cmo(unsigned int stage, return true; } -static bool errata_probe_pmu(unsigned int stage, - unsigned long arch_id, unsigned long impid) -{ - if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PMU)) - return false; - - /* target-c9xx cores report arch_id and impid as 0 */ - if (arch_id != 0 || impid != 0) - return false; - - if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) - return false; - - return true; -} - static u32 thead_errata_probe(unsigned int stage, unsigned long archid, unsigned long impid) { @@ -80,9 +64,6 @@ static u32 thead_errata_probe(unsigned int stage, if (errata_probe_cmo(stage, archid, impid)) cpu_req_errata |= BIT(ERRATA_THEAD_CMO); - if (errata_probe_pmu(stage, archid, impid)) - cpu_req_errata |= BIT(ERRATA_THEAD_PMU); - return cpu_req_errata; } diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index c190393aa9db..1b5354a50d55 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -25,8 +25,7 @@ #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_NUMBER 2 #endif #ifdef __ASSEMBLY__ @@ -147,18 +146,6 @@ asm volatile(ALTERNATIVE_2( \ "r"((unsigned long)(_start) + (_size)) \ : "a0") -#define THEAD_C9XX_RV_IRQ_PMU 17 -#define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5 - -#define ALT_SBI_PMU_OVERFLOW(__ovl) \ -asm volatile(ALTERNATIVE( \ - "csrr %0, " __stringify(CSR_SSCOUNTOVF), \ - "csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF), \ - THEAD_VENDOR_ID, ERRATA_THEAD_PMU, \ - CONFIG_ERRATA_THEAD_PMU) \ - : "=r" (__ovl) : \ - : "memory") - #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index b7b58258f6c7..d3082391c901 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -58,6 +58,7 @@ #define RISCV_ISA_EXT_ZICSR 40 #define RISCV_ISA_EXT_ZIFENCEI 41 #define RISCV_ISA_EXT_ZIHPM 42 +#define RISCV_ISA_EXT_XTHEADPMU 43 #define RISCV_ISA_EXT_MAX 64 diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 1cfbba65d11a..4a3fb017026c 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -181,6 +181,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), + __RISCV_ISA_EXT_DATA(xtheadpmu, RISCV_ISA_EXT_XTHEADPMU), }; const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 273d67ecf6d2..c71b6f16bdfa 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -86,6 +86,19 @@ config RISCV_PMU_SBI full perf feature support i.e. counter overflow, privilege mode filtering, counter configuration. +config THEAD_CUSTOM_PMU + bool "T-Head custom PMU support" + depends on RISCV_ALTERNATIVE && RISCV_PMU_SBI + default y + help + The T-Head C9xx cores implement a PMU overflow extension very + similar to the core SSCOFPMF extension. + + This will patch the overflow CSR and handle the non-standard + behaviour via the regular SBI PMU driver and interface. + + If you don't know what to do here, say "Y". + config ARM_PMU_ACPI depends on ARM_PMU && ACPI def_bool y diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index f340db9ce1e2..790fc20fe094 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -20,10 +20,21 @@ #include #include -#include #include #include +#define THEAD_C9XX_RV_IRQ_PMU 17 +#define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5 + +#define ALT_SBI_PMU_OVERFLOW(__ovl) \ +asm volatile(ALTERNATIVE( \ + "csrr %0, " __stringify(CSR_SSCOUNTOVF), \ + "csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF), \ + 0, RISCV_ISA_EXT_XTHEADPMU, \ + CONFIG_THEAD_CUSTOM_PMU) \ + : "=r" (__ovl) : \ + : "memory") + #define SYSCTL_NO_USER_ACCESS 0 #define SYSCTL_USER_ACCESS 1 #define SYSCTL_LEGACY 2 @@ -805,7 +816,8 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde if (riscv_isa_extension_available(NULL, SSCOFPMF)) { riscv_pmu_irq_num = RV_IRQ_PMU; riscv_pmu_use_irq = true; - } else if (IS_ENABLED(CONFIG_ERRATA_THEAD_PMU) && + } else if (riscv_isa_extension_available(NULL, XTHEADPMU) && + IS_ENABLED(CONFIG_THEAD_CUSTOM_PMU) && riscv_cached_mvendorid(0) == THEAD_VENDOR_ID && riscv_cached_marchid(0) == 0 && riscv_cached_mimpid(0) == 0) { From patchwork Thu Oct 19 14:01:56 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yu-Chien Peter Lin X-Patchwork-Id: 13429276 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 901B1CDB465 for ; Thu, 19 Oct 2023 14:06:00 +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: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:In-Reply-To:References: List-Owner; bh=P8jnWI8qu7WEryYHOKsp75maAOrzaUTowcwXv4nnes4=; b=n5OlHrEKduDOfW /4HY9SiXZGSSP+HeC/Yd48J2kWdhPgLBAyIMqgkcKQsY9GdFQcseImfSMa1Jz8JR18eYtHFyZPZlh u0u1C/apFo49GltLBnBn5pUMTJ6qiBjEa3yg6+CWRBRJWy4hO6gVqZCUe7eJKkejm44HOneKAZBeH J+biX+2QorhG743/nHv0Xx+TElTmkoxUe8Bo9Fd2fGXoQ4nbBCF0qEcV4oZ+1gaFmIE+7jcLLHplX mSqLIJHVH2lJi1ZW1+MhaGQEU+nzG8IT929gMpqy++wwt85WFEu6BsoHUF2MObuLT2QcTMIF1GFPS zfYZXxENcx6ZuBDPqtsg==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qtTeZ-00017c-0T; Thu, 19 Oct 2023 14:05:35 +0000 Received: from 60-248-80-70.hinet-ip.hinet.net ([60.248.80.70] helo=Atcsqr.andestech.com) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qtTeU-00015V-2i; Thu, 19 Oct 2023 14:05:32 +0000 Received: from mail.andestech.com (ATCPCS16.andestech.com [10.0.1.222]) by Atcsqr.andestech.com with ESMTP id 39JE50qp032111; Thu, 19 Oct 2023 22:05:00 +0800 (+08) (envelope-from peterlin@andestech.com) Received: from swlinux02.andestech.com (10.0.15.183) by ATCPCS16.andestech.com (10.0.1.222) with Microsoft SMTP Server id 14.3.498.0; Thu, 19 Oct 2023 22:04:57 +0800 From: Yu Chien Peter Lin To: , , , , , , , , , , , , , , , , CC: , , , , , "Leo Yu-Chi Liang" Subject: [RFC PATCH v2 08/10] perf: RISC-V: Introduce Andes PMU for perf event sampling Date: Thu, 19 Oct 2023 22:01:56 +0800 Message-ID: <20231019140156.3660000-1-peterlin@andestech.com> X-Mailer: git-send-email 2.34.1 MIME-Version: 1.0 X-Originating-IP: [10.0.15.183] X-DNSRBL: X-MAIL: Atcsqr.andestech.com 39JE50qp032111 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231019_070531_320865_F874CDDB X-CRM114-Status: GOOD ( 18.75 ) X-BeenThere: linux-arm-kernel@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-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org The Andes PMU extension provides the same mechanism as Sscofpmf, allowing us to reuse the SBI PMU driver to support event sampling and mode filtering. To make use of this custom PMU extension, "xandespmu" needs to be appended to the riscv,isa-extensions for each cpu node in device-tree, and enable CONFIG_ANDES_CUSTOM_PMU. Signed-off-by: Yu Chien Peter Lin Reviewed-by: Charles Ci-Jyun Wu Reviewed-by: Leo Yu-Chi Liang Co-developed-by: Locus Wei-Han Chen Signed-off-by: Locus Wei-Han Chen --- Changes v1 -> v2: - New patch --- arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/kernel/cpufeature.c | 1 + drivers/perf/Kconfig | 14 ++++++++++++++ drivers/perf/riscv_pmu_sbi.c | 35 +++++++++++++++++++++++++++++----- 4 files changed, 46 insertions(+), 5 deletions(-) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index d3082391c901..eecfe95d5050 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -59,6 +59,7 @@ #define RISCV_ISA_EXT_ZIFENCEI 41 #define RISCV_ISA_EXT_ZIHPM 42 #define RISCV_ISA_EXT_XTHEADPMU 43 +#define RISCV_ISA_EXT_XANDESPMU 44 #define RISCV_ISA_EXT_MAX 64 diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 4a3fb017026c..a8e71c6dfb3e 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -182,6 +182,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), __RISCV_ISA_EXT_DATA(xtheadpmu, RISCV_ISA_EXT_XTHEADPMU), + __RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_EXT_XANDESPMU), }; const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index c71b6f16bdfa..c1a490829d15 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -86,6 +86,20 @@ config RISCV_PMU_SBI full perf feature support i.e. counter overflow, privilege mode filtering, counter configuration. +config ANDES_CUSTOM_PMU + bool "Andes custom PMU support" + depends on RISCV_ALTERNATIVE && RISCV_PMU_SBI + default y + help + The Andes cores implement a PMU overflow extension very + similar to the core SSCOFPMF extension. + + This will patch the overflow/pending CSR and handle the + non-standard behaviour via the regular SBI PMU driver and + interface. + + If you don't know what to do here, say "Y". + config THEAD_CUSTOM_PMU bool "T-Head custom PMU support" depends on RISCV_ALTERNATIVE && RISCV_PMU_SBI diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 790fc20fe094..e0de1a5fa0ba 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -26,15 +27,31 @@ #define THEAD_C9XX_RV_IRQ_PMU 17 #define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5 +#define ANDES_RV_IRQ_PMU 18 +#define ANDES_CSR_SCOUNTEROF 0x9d4 +#define ANDES_CSR_SLIP 0x9c5 + #define ALT_SBI_PMU_OVERFLOW(__ovl) \ -asm volatile(ALTERNATIVE( \ +asm volatile(ALTERNATIVE_2( \ "csrr %0, " __stringify(CSR_SSCOUNTOVF), \ "csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF), \ 0, RISCV_ISA_EXT_XTHEADPMU, \ - CONFIG_THEAD_CUSTOM_PMU) \ + CONFIG_THEAD_CUSTOM_PMU, \ + "csrr %0, " __stringify(ANDES_CSR_SCOUNTEROF), \ + 0, RISCV_ISA_EXT_XANDESPMU, \ + CONFIG_ANDES_CUSTOM_PMU) \ : "=r" (__ovl) : \ : "memory") +#define ALT_SBI_PMU_OVF_CLEAR_PENDING(__irq_mask) \ +asm volatile(ALTERNATIVE( \ + "csrc " __stringify(CSR_IP) ", %0\n\t", \ + "csrc " __stringify(ANDES_CSR_SLIP) ", %0\n\t", \ + 0, RISCV_ISA_EXT_XANDESPMU, \ + CONFIG_ANDES_CUSTOM_PMU) \ + : : "r"(__irq_mask) \ + : "memory") + #define SYSCTL_NO_USER_ACCESS 0 #define SYSCTL_USER_ACCESS 1 #define SYSCTL_LEGACY 2 @@ -72,6 +89,7 @@ static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS; static union sbi_pmu_ctr_info *pmu_ctr_list; static bool riscv_pmu_use_irq; static unsigned int riscv_pmu_irq_num; +static unsigned int riscv_pmu_irq_mask; static unsigned int riscv_pmu_irq; /* Cache the available counters in a bitmask */ @@ -702,7 +720,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS); event = cpu_hw_evt->events[fidx]; if (!event) { - csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); + ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); return IRQ_NONE; } @@ -716,7 +734,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) * Overflow interrupt pending bit should only be cleared after stopping * all the counters to avoid any race condition. */ - csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); + ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); /* No overflow bit is set */ if (!overflow) @@ -788,7 +806,7 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) if (riscv_pmu_use_irq) { cpu_hw_evt->irq = riscv_pmu_irq; - csr_clear(CSR_IP, BIT(riscv_pmu_irq_num)); + ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask); enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE); } @@ -823,8 +841,15 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde riscv_cached_mimpid(0) == 0) { riscv_pmu_irq_num = THEAD_C9XX_RV_IRQ_PMU; riscv_pmu_use_irq = true; + } else if (riscv_isa_extension_available(NULL, XANDESPMU) && + IS_ENABLED(CONFIG_ANDES_CUSTOM_PMU) && + riscv_cached_mvendorid(0) == ANDES_VENDOR_ID) { + riscv_pmu_irq_num = ANDES_SLI_CAUSE_BASE + ANDES_RV_IRQ_PMU; + riscv_pmu_use_irq = true; } + riscv_pmu_irq_mask = BIT(riscv_pmu_irq_num % BITS_PER_LONG); + if (!riscv_pmu_use_irq) return -EOPNOTSUPP;