From patchwork Fri Aug 19 16:25:46 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jeremy Linton X-Patchwork-Id: 598523 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id C3CB8C28B2B for ; Fri, 19 Aug 2022 17:07:38 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1350329AbiHSRHg (ORCPT ); Fri, 19 Aug 2022 13:07:36 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:38458 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1350747AbiHSRGx (ORCPT ); Fri, 19 Aug 2022 13:06:53 -0400 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id D603113CFB3; Fri, 19 Aug 2022 09:27:29 -0700 (PDT) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id A04991042; Fri, 19 Aug 2022 09:26:25 -0700 (PDT) Received: from mammon-tx2.austin.arm.com (mammon-tx2.austin.arm.com [10.118.28.62]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id A0B323F66F; Fri, 19 Aug 2022 09:26:23 -0700 (PDT) From: Jeremy Linton To: linux-acpi@vger.kernel.org Cc: rafael@kernel.org, lenb@kernel.org, viresh.kumar@linaro.org, robert.moore@intel.com, punit.agrawal@bytedance.com, lukasz.luba@arm.com, ionela.voinescu@arm.com, pierre.gondois@arm.com, linux-kernel@vger.kernel.org, devel@acpica.org, linux-pm@vger.kernel.org, Jeremy Linton Subject: [PATCH v4 1/2] ACPI: CPPC: Disable FIE if registers in PCC regions Date: Fri, 19 Aug 2022 11:25:46 -0500 Message-Id: <20220819162547.141333-2-jeremy.linton@arm.com> X-Mailer: git-send-email 2.35.3 In-Reply-To: <20220819162547.141333-1-jeremy.linton@arm.com> References: <20220819162547.141333-1-jeremy.linton@arm.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-acpi@vger.kernel.org PCC regions utilize a mailbox to set/retrieve register values used by the CPPC code. This is fine as long as the operations are infrequent. With the FIE code enabled though the overhead can range from 2-11% of system CPU overhead (ex: as measured by top) on Arm based machines. So, before enabling FIE assure none of the registers used by cppc_get_perf_ctrs() are in the PCC region. Furthermore lets also enable a module parameter which can also disable it at boot or module reload. Signed-off-by: Jeremy Linton --- drivers/acpi/cppc_acpi.c | 41 ++++++++++++++++++++++++++++++++++ drivers/cpufreq/cppc_cpufreq.c | 31 +++++++++++++++++++++---- include/acpi/cppc_acpi.h | 5 +++++ 3 files changed, 73 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 1e15a9f25ae9..c840bf606b30 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1240,6 +1240,47 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) } EXPORT_SYMBOL_GPL(cppc_get_perf_caps); +/** + * cppc_perf_ctrs_in_pcc - Check if any perf counters are in a PCC region. + * + * CPPC has flexibility about how counters describing CPU perf are delivered. + * One of the choices is PCC regions, which can have a high access latency. This + * routine allows callers of cppc_get_perf_ctrs() to know this ahead of time. + * + * Return: true if any of the counters are in PCC regions, false otherwise + */ +bool cppc_perf_ctrs_in_pcc(void) +{ + int cpu; + + for_each_present_cpu(cpu) { + struct cpc_register_resource *ref_perf_reg; + struct cpc_desc *cpc_desc; + + cpc_desc = per_cpu(cpc_desc_ptr, cpu); + + if (CPC_IN_PCC(&cpc_desc->cpc_regs[DELIVERED_CTR]) || + CPC_IN_PCC(&cpc_desc->cpc_regs[REFERENCE_CTR]) || + CPC_IN_PCC(&cpc_desc->cpc_regs[CTR_WRAP_TIME])) + return true; + + + ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF]; + + /* + * If reference perf register is not supported then we should + * use the nominal perf value + */ + if (!CPC_SUPPORTED(ref_perf_reg)) + ref_perf_reg = &cpc_desc->cpc_regs[NOMINAL_PERF]; + + if (CPC_IN_PCC(ref_perf_reg)) + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(cppc_perf_ctrs_in_pcc); + /** * cppc_get_perf_ctrs - Read a CPU's performance feedback counters. * @cpunum: CPU from which to read counters. diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 24eaf0ec344d..32fcb0bf74a4 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -63,7 +63,15 @@ static struct cppc_workaround_oem_info wa_info[] = { static struct cpufreq_driver cppc_cpufreq_driver; +static enum { + FIE_UNSET = -1, + FIE_ENABLED, + FIE_DISABLED +} fie_disabled = FIE_UNSET; + #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE +module_param(fie_disabled, int, 0444); +MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); /* Frequency invariance support */ struct cppc_freq_invariance { @@ -158,7 +166,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu, ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; for_each_cpu(cpu, policy->cpus) { @@ -199,7 +207,7 @@ static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; /* policy->cpus will be empty here, use related_cpus instead */ @@ -229,7 +237,21 @@ static void __init cppc_freq_invariance_init(void) }; int ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + switch (fie_disabled) { + /* honor user request */ + case FIE_DISABLED: + case FIE_ENABLED: + break; + case FIE_UNSET: + default: + fie_disabled = FIE_ENABLED; + if (cppc_perf_ctrs_in_pcc()) { + pr_info("FIE not enabled on systems with registers in PCC\n"); + fie_disabled = FIE_DISABLED; + } + break; + } + if (fie_disabled) return; kworker_fie = kthread_create_worker(0, "cppc_fie"); @@ -247,7 +269,7 @@ static void __init cppc_freq_invariance_init(void) static void cppc_freq_invariance_exit(void) { - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; kthread_destroy_worker(kworker_fie); @@ -936,6 +958,7 @@ static void cppc_check_hisi_workaround(void) wa_info[i].oem_revision == tbl->oem_revision) { /* Overwrite the get() callback */ cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate; + fie_disabled = FIE_DISABLED; break; } } diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index f73d357ecdf5..c5614444031f 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -140,6 +140,7 @@ extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs); extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); +extern bool cppc_perf_ctrs_in_pcc(void); extern bool acpi_cpc_valid(void); extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); @@ -173,6 +174,10 @@ static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps) { return -ENOTSUPP; } +static inline bool cppc_perf_ctrs_in_pcc(void) +{ + return false; +} static inline bool acpi_cpc_valid(void) { return false; From patchwork Fri Aug 19 16:25:47 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jeremy Linton X-Patchwork-Id: 598749 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F3240C32771 for ; Fri, 19 Aug 2022 17:07:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1350938AbiHSRHi (ORCPT ); Fri, 19 Aug 2022 13:07:38 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41716 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1350779AbiHSRGy (ORCPT ); Fri, 19 Aug 2022 13:06:54 -0400 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 1D697CCE26; Fri, 19 Aug 2022 09:27:29 -0700 (PDT) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id D9071175A; Fri, 19 Aug 2022 09:26:25 -0700 (PDT) Received: from mammon-tx2.austin.arm.com (mammon-tx2.austin.arm.com [10.118.28.62]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id D06D23F66F; Fri, 19 Aug 2022 09:26:23 -0700 (PDT) From: Jeremy Linton To: linux-acpi@vger.kernel.org Cc: rafael@kernel.org, lenb@kernel.org, viresh.kumar@linaro.org, robert.moore@intel.com, punit.agrawal@bytedance.com, lukasz.luba@arm.com, ionela.voinescu@arm.com, pierre.gondois@arm.com, linux-kernel@vger.kernel.org, devel@acpica.org, linux-pm@vger.kernel.org, Jeremy Linton Subject: [PATCH v4 2/2] cpufreq: CPPC: Change FIE default Date: Fri, 19 Aug 2022 11:25:47 -0500 Message-Id: <20220819162547.141333-3-jeremy.linton@arm.com> X-Mailer: git-send-email 2.35.3 In-Reply-To: <20220819162547.141333-1-jeremy.linton@arm.com> References: <20220819162547.141333-1-jeremy.linton@arm.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-acpi@vger.kernel.org FIE is mostly implemented as PCC mailboxes on arm machines. This was enabled by default without any data suggesting that it does anything but hurt system performance. Lets change the default to 'n' until hardware appears which clearly benefits. Signed-off-by: Jeremy Linton Reviewed-by: Lukasz Luba --- drivers/cpufreq/Kconfig.arm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 954749afb5fe..ad66d8f15db0 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -22,7 +22,7 @@ config ACPI_CPPC_CPUFREQ config ACPI_CPPC_CPUFREQ_FIE bool "Frequency Invariance support for CPPC cpufreq driver" depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY - default y + default n help This extends frequency invariance support in the CPPC cpufreq driver, by using CPPC delivered and reference performance counters.