From patchwork Mon Dec 7 16:28:25 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Rafael J. Wysocki" X-Patchwork-Id: 339396 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 87E66C1B087 for ; Mon, 7 Dec 2020 16:41:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 51F92206C1 for ; Mon, 7 Dec 2020 16:41:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727009AbgLGQke (ORCPT ); Mon, 7 Dec 2020 11:40:34 -0500 Received: from cloudserver094114.home.pl ([79.96.170.134]:50168 "EHLO cloudserver094114.home.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727673AbgLGQke (ORCPT ); Mon, 7 Dec 2020 11:40:34 -0500 Received: from 89-64-79-106.dynamic.chello.pl (89.64.79.106) (HELO kreacher.localnet) by serwer1319399.home.pl (79.96.170.134) with SMTP (IdeaSmtpServer 0.83.530) id db8c3b154aa71968; Mon, 7 Dec 2020 17:39:51 +0100 From: "Rafael J. Wysocki" To: Linux PM Cc: LKML , Viresh Kumar , Srinivas Pandruvada , Peter Zijlstra , Doug Smythies , Giovanni Gherdovich Subject: [PATCH v1 1/4] cpufreq: schedutil: Add util to struct sg_cpu Date: Mon, 07 Dec 2020 17:28:25 +0100 Message-ID: <2344038.BgO4qI7qUv@kreacher> In-Reply-To: <20360841.iInq7taT2Z@kreacher> References: <20360841.iInq7taT2Z@kreacher> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org From: Rafael J. Wysocki Instead of passing util and max between functions while computing the utilization and capacity, store the former in struct sg_cpu (along with the latter and bw_dl). This will allow the current utilization value to be compared with the one obtained previously (which is requisite for some code changes to follow this one), but also it makes the code look slightly more consistent and clean. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- kernel/sched/cpufreq_schedutil.c | 42 ++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 22 deletions(-) Index: linux-pm/kernel/sched/cpufreq_schedutil.c =================================================================== --- linux-pm.orig/kernel/sched/cpufreq_schedutil.c +++ linux-pm/kernel/sched/cpufreq_schedutil.c @@ -53,6 +53,7 @@ struct sugov_cpu { unsigned int iowait_boost; u64 last_update; + unsigned long util; unsigned long bw_dl; unsigned long max; @@ -276,16 +277,15 @@ unsigned long schedutil_cpu_util(int cpu return min(max, util); } -static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - unsigned long util = cpu_util_cfs(rq); unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->max = max; sg_cpu->bw_dl = cpu_bw_dl(rq); - - return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL); + sg_cpu->util = schedutil_cpu_util(sg_cpu->cpu, cpu_util_cfs(rq), max, + FREQUENCY_UTIL, NULL); } /** @@ -362,8 +362,6 @@ static void sugov_iowait_boost(struct su * sugov_iowait_apply() - Apply the IO boost to a CPU. * @sg_cpu: the sugov data for the cpu to boost * @time: the update time from the caller - * @util: the utilization to (eventually) boost - * @max: the maximum value the utilization can be boosted to * * A CPU running a task which woken up after an IO operation can have its * utilization boosted to speed up the completion of those IO operations. @@ -377,18 +375,17 @@ static void sugov_iowait_boost(struct su * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, - unsigned long util, unsigned long max) +static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) { unsigned long boost; /* No boost currently required */ if (!sg_cpu->iowait_boost) - return util; + return; /* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return util; + return; if (!sg_cpu->iowait_boost_pending) { /* @@ -397,18 +394,19 @@ static unsigned long sugov_iowait_apply( sg_cpu->iowait_boost >>= 1; if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) { sg_cpu->iowait_boost = 0; - return util; + return; } } sg_cpu->iowait_boost_pending = false; /* - * @util is already in capacity scale; convert iowait_boost + * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; - return max(boost, util); + boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; + if (sg_cpu->util < boost) + sg_cpu->util = boost; } #ifdef CONFIG_NO_HZ_COMMON @@ -439,9 +437,8 @@ static void sugov_update_single(struct u { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); struct sugov_policy *sg_policy = sg_cpu->sg_policy; - unsigned long util, max; - unsigned int next_f; unsigned int cached_freq = sg_policy->cached_raw_freq; + unsigned int next_f; sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -451,10 +448,10 @@ static void sugov_update_single(struct u if (!sugov_should_update_freq(sg_policy, time)) return; - util = sugov_get_util(sg_cpu); - max = sg_cpu->max; - util = sugov_iowait_apply(sg_cpu, time, util, max); - next_f = get_next_freq(sg_policy, util, max); + sugov_get_util(sg_cpu); + sugov_iowait_apply(sg_cpu, time); + + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. @@ -491,9 +488,10 @@ static unsigned int sugov_next_freq_shar struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; - j_util = sugov_get_util(j_sg_cpu); + sugov_get_util(j_sg_cpu); + sugov_iowait_apply(j_sg_cpu, time); + j_util = j_sg_cpu->util; j_max = j_sg_cpu->max; - j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max); if (j_util * max > j_max * util) { util = j_util; From patchwork Mon Dec 14 20:08:00 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Rafael J. Wysocki" X-Patchwork-Id: 343764 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 511C1C2BB40 for ; Mon, 14 Dec 2020 20:17:20 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 274D9207A2 for ; Mon, 14 Dec 2020 20:17:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2502716AbgLNUKl (ORCPT ); Mon, 14 Dec 2020 15:10:41 -0500 Received: from cloudserver094114.home.pl ([79.96.170.134]:43956 "EHLO cloudserver094114.home.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2502801AbgLNUKc (ORCPT ); Mon, 14 Dec 2020 15:10:32 -0500 Received: from 89-77-60-66.dynamic.chello.pl (89.77.60.66) (HELO kreacher.localnet) by serwer1319399.home.pl (79.96.170.134) with SMTP (IdeaSmtpServer 0.83.530) id a63a85a8384da918; Mon, 14 Dec 2020 21:09:39 +0100 From: "Rafael J. Wysocki" To: Linux PM Cc: LKML , Viresh Kumar , Srinivas Pandruvada , Peter Zijlstra , Doug Smythies , Giovanni Gherdovich Subject: [PATCH v2 2/3] cpufreq: Add special-purpose fast-switching callback for drivers Date: Mon, 14 Dec 2020 21:08:00 +0100 Message-ID: <10727653.HtF45dgyQg@kreacher> In-Reply-To: <3827230.0GnL3RTcl1@kreacher> References: <20360841.iInq7taT2Z@kreacher> <3827230.0GnL3RTcl1@kreacher> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org From: Rafael J. Wysocki First off, some cpufreq drivers (eg. intel_pstate) can pass hints beyond the current target frequency to the hardware and there are no provisions for doing that in the cpufreq framework. In particular, today the driver has to assume that it should not allow the frequency to fall below the one requested by the governor (or the required capacity may not be provided) which may not be the case and which may lead to excessive energy usage in some scenarios. Second, the hints passed by these drivers to the hardware need not be in terms of the frequency, so representing the utilization numbers coming from the scheduler as frequency before passing them to those drivers is not really useful. Address the two points above by adding a special-purpose replacement for the ->fast_switch callback, called ->adjust_perf, allowing the governor to pass abstract performance level (rather than frequency) values for the minimum (required) and target (desired) performance along with the CPU capacity to compare them to. Also update the schedutil governor to use the new callback instead of ->fast_switch if present and if the utilization mertics are frequency-invariant (that is requisite for the direct mapping between the utilization and the CPU performance levels to be a reasonable approximation). Signed-off-by: Rafael J. Wysocki --- v1 -> v2: - Do not share optimization code between the freq and perf paths. - Fall back from perf to freq if scale invariance is not supported. Changes with respect to the RFC: - Don't pass "busy" to ->adjust_perf(). - Use a special 'update_util' hook for the ->adjust_perf() case in schedutil (this still requires an additional branch because of the shared common code between this case and the "frequency" one, but IMV this version is cleaner nevertheless). --- drivers/cpufreq/cpufreq.c | 40 ++++++++++++++++++++++ include/linux/cpufreq.h | 14 ++++++++ include/linux/sched/cpufreq.h | 5 ++ kernel/sched/cpufreq_schedutil.c | 68 +++++++++++++++++++++++++++++++++------ 4 files changed, 117 insertions(+), 10 deletions(-) Index: linux-pm/include/linux/cpufreq.h =================================================================== --- linux-pm.orig/include/linux/cpufreq.h +++ linux-pm/include/linux/cpufreq.h @@ -320,6 +320,15 @@ struct cpufreq_driver { unsigned int index); unsigned int (*fast_switch)(struct cpufreq_policy *policy, unsigned int target_freq); + /* + * ->fast_switch() replacement for drivers that use an internal + * representation of performance levels and can pass hints other than + * the target performance level to the hardware. + */ + void (*adjust_perf)(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity); /* * Caches and returns the lowest driver-supported frequency greater than @@ -588,6 +597,11 @@ struct cpufreq_governor { /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); +void cpufreq_driver_adjust_perf(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity); +bool cpufreq_driver_has_adjust_perf(void); int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); Index: linux-pm/drivers/cpufreq/cpufreq.c =================================================================== --- linux-pm.orig/drivers/cpufreq/cpufreq.c +++ linux-pm/drivers/cpufreq/cpufreq.c @@ -2097,6 +2097,46 @@ unsigned int cpufreq_driver_fast_switch( } EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); +/** + * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go. + * @cpu: Target CPU. + * @min_perf: Minimum (required) performance level (units of @capacity). + * @target_perf: Terget (desired) performance level (units of @capacity). + * @capacity: Capacity of the target CPU. + * + * Carry out a fast performance level switch of @cpu without sleeping. + * + * The driver's ->adjust_perf() callback invoked by this function must be + * suitable for being called from within RCU-sched read-side critical sections + * and it is expected to select a suitable performance level equal to or above + * @min_perf and preferably equal to or below @target_perf. + * + * This function must not be called if policy->fast_switch_enabled is unset. + * + * Governors calling this function must guarantee that it will never be invoked + * twice in parallel for the same CPU and that it will never be called in + * parallel with either ->target() or ->target_index() or ->fast_switch() for + * the same CPU. + */ +void cpufreq_driver_adjust_perf(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity) +{ + cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity); +} + +/** + * cpufreq_driver_has_adjust_perf - Check "direct fast switch" callback. + * + * Return 'true' if the ->adjust_perf callback is present for the + * current driver or 'false' otherwise. + */ +bool cpufreq_driver_has_adjust_perf(void) +{ + return !!cpufreq_driver->adjust_perf; +} + /* Must set freqs->new to intermediate frequency */ static int __target_intermediate(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, int index) Index: linux-pm/kernel/sched/cpufreq_schedutil.c =================================================================== --- linux-pm.orig/kernel/sched/cpufreq_schedutil.c +++ linux-pm/kernel/sched/cpufreq_schedutil.c @@ -432,13 +432,10 @@ static inline void ignore_dl_rate_limit( sg_policy->limits_changed = true; } -static void sugov_update_single(struct update_util_data *hook, u64 time, - unsigned int flags) +static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, + u64 time, unsigned int flags) { - struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); struct sugov_policy *sg_policy = sg_cpu->sg_policy; - unsigned int cached_freq = sg_policy->cached_raw_freq; - unsigned int next_f; sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -446,11 +443,25 @@ static void sugov_update_single(struct u ignore_dl_rate_limit(sg_cpu, sg_policy); if (!sugov_should_update_freq(sg_policy, time)) - return; + return false; sugov_get_util(sg_cpu); sugov_iowait_apply(sg_cpu, time); + return true; +} + +static void sugov_update_single_freq(struct update_util_data *hook, u64 time, + unsigned int flags) +{ + struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); + struct sugov_policy *sg_policy = sg_cpu->sg_policy; + unsigned int cached_freq = sg_policy->cached_raw_freq; + unsigned int next_f; + + if (!sugov_update_single_common(sg_cpu, time, flags)) + return; + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); /* * Do not reduce the frequency if the CPU has not been idle @@ -477,6 +488,38 @@ static void sugov_update_single(struct u } } +static void sugov_update_single_perf(struct update_util_data *hook, u64 time, + unsigned int flags) +{ + struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); + unsigned long prev_util = sg_cpu->util; + + /* + * Fall back to the "frequency" path if frequency invariance is not + * supported, because the direct mapping between the utilization and + * the performance levels depends on the frequency invariance. + */ + if (!arch_scale_freq_invariant()) { + sugov_update_single_freq(hook, time, flags); + return; + } + + if (!sugov_update_single_common(sg_cpu, time, flags)) + return; + + /* + * Do not reduce the target performance level if the CPU has not been + * idle recently, as the reduction is likely to be premature then. + */ + if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) + sg_cpu->util = prev_util; + + cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), + map_util_perf(sg_cpu->util), sg_cpu->max); + + sg_cpu->sg_policy->last_freq_update_time = time; +} + static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; @@ -815,6 +858,7 @@ static void sugov_exit(struct cpufreq_po static int sugov_start(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; + void (*uu)(struct update_util_data *data, u64 time, unsigned int flags); unsigned int cpu; sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; @@ -834,13 +878,17 @@ static int sugov_start(struct cpufreq_po sg_cpu->sg_policy = sg_policy; } + if (policy_is_shared(policy)) + uu = sugov_update_shared; + else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf()) + uu = sugov_update_single_perf; + else + uu = sugov_update_single_freq; + for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - policy_is_shared(policy) ? - sugov_update_shared : - sugov_update_single); + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu); } return 0; } Index: linux-pm/include/linux/sched/cpufreq.h =================================================================== --- linux-pm.orig/include/linux/sched/cpufreq.h +++ linux-pm/include/linux/sched/cpufreq.h @@ -28,6 +28,11 @@ static inline unsigned long map_util_fre { return (freq + (freq >> 2)) * util / cap; } + +static inline unsigned long map_util_perf(unsigned long util) +{ + return util + (util >> 2); +} #endif /* CONFIG_CPU_FREQ */ #endif /* _LINUX_SCHED_CPUFREQ_H */ From patchwork Mon Dec 7 16:35:52 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Rafael J. Wysocki" X-Patchwork-Id: 339397 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3F550C0018C for ; Mon, 7 Dec 2020 16:41:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1BFB3206C1 for ; Mon, 7 Dec 2020 16:41:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727739AbgLGQkd (ORCPT ); Mon, 7 Dec 2020 11:40:33 -0500 Received: from cloudserver094114.home.pl ([79.96.170.134]:63842 "EHLO cloudserver094114.home.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727135AbgLGQkc (ORCPT ); Mon, 7 Dec 2020 11:40:32 -0500 Received: from 89-64-79-106.dynamic.chello.pl (89.64.79.106) (HELO kreacher.localnet) by serwer1319399.home.pl (79.96.170.134) with SMTP (IdeaSmtpServer 0.83.530) id a3622490ce2847ea; Mon, 7 Dec 2020 17:39:49 +0100 From: "Rafael J. Wysocki" To: Linux PM Cc: LKML , Viresh Kumar , Srinivas Pandruvada , Peter Zijlstra , Doug Smythies , Giovanni Gherdovich Subject: [PATCH v1 3/4] cpufreq: Add special-purpose fast-switching callback for drivers Date: Mon, 07 Dec 2020 17:35:52 +0100 Message-ID: <146138074.tjdImvNTH2@kreacher> In-Reply-To: <20360841.iInq7taT2Z@kreacher> References: <20360841.iInq7taT2Z@kreacher> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org From: Rafael J. Wysocki First off, some cpufreq drivers (eg. intel_pstate) can pass hints beyond the current target frequency to the hardware and there are no provisions for doing that in the cpufreq framework. In particular, today the driver has to assume that it should not allow the frequency to fall below the one requested by the governor (or the required capacity may not be provided) which may not be the case and which may lead to excessive energy usage in some scenarios. Second, the hints passed by these drivers to the hardware need not be in terms of the frequency, so representing the utilization numbers coming from the scheduler as frequency before passing them to those drivers is not really useful. Address the two points above by adding a special-purpose replacement for the ->fast_switch callback, called ->adjust_perf, allowing the governor to pass abstract performance level (rather than frequency) values for the minimum (required) and target (desired) performance along with the CPU capacity to compare them to. Also update the schedutil governor to use the new callback instead of ->fast_switch if present. Signed-off-by: Rafael J. Wysocki --- Changes with respect to the RFC: - Don't pass "busy" to ->adjust_perf(). - Use a special 'update_util' hook for the ->adjust_perf() case in schedutil (this still requires an additional branch because of the shared common code between this case and the "frequency" one, but IMV this version is cleaner nevertheless). --- drivers/cpufreq/cpufreq.c | 40 ++++++++++++++++++++++++++++++++ include/linux/cpufreq.h | 14 +++++++++++ include/linux/sched/cpufreq.h | 5 ++++ kernel/sched/cpufreq_schedutil.c | 48 +++++++++++++++++++++++++++++++-------- 4 files changed, 98 insertions(+), 9 deletions(-) Index: linux-pm/include/linux/cpufreq.h =================================================================== --- linux-pm.orig/include/linux/cpufreq.h +++ linux-pm/include/linux/cpufreq.h @@ -320,6 +320,15 @@ struct cpufreq_driver { unsigned int index); unsigned int (*fast_switch)(struct cpufreq_policy *policy, unsigned int target_freq); + /* + * ->fast_switch() replacement for drivers that use an internal + * representation of performance levels and can pass hints other than + * the target performance level to the hardware. + */ + void (*adjust_perf)(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity); /* * Caches and returns the lowest driver-supported frequency greater than @@ -588,6 +597,11 @@ struct cpufreq_governor { /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); +void cpufreq_driver_adjust_perf(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity); +bool cpufreq_driver_has_adjust_perf(void); int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); Index: linux-pm/drivers/cpufreq/cpufreq.c =================================================================== --- linux-pm.orig/drivers/cpufreq/cpufreq.c +++ linux-pm/drivers/cpufreq/cpufreq.c @@ -2097,6 +2097,46 @@ unsigned int cpufreq_driver_fast_switch( } EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); +/** + * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go. + * @cpu: Target CPU. + * @min_perf: Minimum (required) performance level (units of @capacity). + * @target_perf: Terget (desired) performance level (units of @capacity). + * @capacity: Capacity of the target CPU. + * + * Carry out a fast performance level switch of @cpu without sleeping. + * + * The driver's ->adjust_perf() callback invoked by this function must be + * suitable for being called from within RCU-sched read-side critical sections + * and it is expected to select a suitable performance level equal to or above + * @min_perf and preferably equal to or below @target_perf. + * + * This function must not be called if policy->fast_switch_enabled is unset. + * + * Governors calling this function must guarantee that it will never be invoked + * twice in parallel for the same CPU and that it will never be called in + * parallel with either ->target() or ->target_index() or ->fast_switch() for + * the same CPU. + */ +void cpufreq_driver_adjust_perf(unsigned int cpu, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity) +{ + cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity); +} + +/** + * cpufreq_driver_has_adjust_perf - Check "direct fast switch" callback. + * + * Return 'true' if the ->adjust_perf callback is present for the + * current driver or 'false' otherwise. + */ +bool cpufreq_driver_has_adjust_perf(void) +{ + return !!cpufreq_driver->adjust_perf; +} + /* Must set freqs->new to intermediate frequency */ static int __target_intermediate(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, int index) Index: linux-pm/kernel/sched/cpufreq_schedutil.c =================================================================== --- linux-pm.orig/kernel/sched/cpufreq_schedutil.c +++ linux-pm/kernel/sched/cpufreq_schedutil.c @@ -432,13 +432,11 @@ static inline void ignore_dl_rate_limit( sg_policy->limits_changed = true; } -static void sugov_update_single(struct update_util_data *hook, u64 time, - unsigned int flags) +static bool sugov_update_single_common(struct sugov_cpu *sg_cpu, u64 time, + unsigned int flags) { - struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long prev_util = sg_cpu->util; - unsigned int next_f; sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -446,7 +444,7 @@ static void sugov_update_single(struct u ignore_dl_rate_limit(sg_cpu, sg_policy); if (!sugov_should_update_freq(sg_policy, time)) - return; + return false; sugov_get_util(sg_cpu); sugov_iowait_apply(sg_cpu, time); @@ -458,6 +456,19 @@ static void sugov_update_single(struct u if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) sg_cpu->util = prev_util; + return true; +} + +static void sugov_update_single_freq(struct update_util_data *hook, u64 time, + unsigned int flags) +{ + struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); + struct sugov_policy *sg_policy = sg_cpu->sg_policy; + unsigned int next_f; + + if (!sugov_update_single_common(sg_cpu, time, flags)) + return; + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); /* @@ -474,6 +485,20 @@ static void sugov_update_single(struct u } } +static void sugov_update_single_perf(struct update_util_data *hook, u64 time, + unsigned int flags) +{ + struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); + + if (!sugov_update_single_common(sg_cpu, time, flags)) + return; + + cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), + map_util_perf(sg_cpu->util), sg_cpu->max); + + sg_cpu->sg_policy->last_freq_update_time = time; +} + static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; @@ -812,6 +837,7 @@ static void sugov_exit(struct cpufreq_po static int sugov_start(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; + void (*uu)(struct update_util_data *data, u64 time, unsigned int flags); unsigned int cpu; sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; @@ -831,13 +857,17 @@ static int sugov_start(struct cpufreq_po sg_cpu->sg_policy = sg_policy; } + if (policy_is_shared(policy)) + uu = sugov_update_shared; + else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf()) + uu = sugov_update_single_perf; + else + uu = sugov_update_single_freq; + for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - policy_is_shared(policy) ? - sugov_update_shared : - sugov_update_single); + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu); } return 0; } Index: linux-pm/include/linux/sched/cpufreq.h =================================================================== --- linux-pm.orig/include/linux/sched/cpufreq.h +++ linux-pm/include/linux/sched/cpufreq.h @@ -28,6 +28,11 @@ static inline unsigned long map_util_fre { return (freq + (freq >> 2)) * util / cap; } + +static inline unsigned long map_util_perf(unsigned long util) +{ + return util + (util >> 2); +} #endif /* CONFIG_CPU_FREQ */ #endif /* _LINUX_SCHED_CPUFREQ_H */ From patchwork Mon Dec 7 16:38:58 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Rafael J. Wysocki" X-Patchwork-Id: 339398 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.7 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 503E0C4361B for ; Mon, 7 Dec 2020 16:40:32 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1E5F123877 for ; Mon, 7 Dec 2020 16:40:32 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726938AbgLGQkb (ORCPT ); Mon, 7 Dec 2020 11:40:31 -0500 Received: from cloudserver094114.home.pl ([79.96.170.134]:61978 "EHLO cloudserver094114.home.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726698AbgLGQkb (ORCPT ); Mon, 7 Dec 2020 11:40:31 -0500 Received: from 89-64-79-106.dynamic.chello.pl (89.64.79.106) (HELO kreacher.localnet) by serwer1319399.home.pl (79.96.170.134) with SMTP (IdeaSmtpServer 0.83.530) id aa4a46705c8d1b84; Mon, 7 Dec 2020 17:39:48 +0100 From: "Rafael J. Wysocki" To: Linux PM Cc: LKML , Viresh Kumar , Srinivas Pandruvada , Peter Zijlstra , Doug Smythies , Giovanni Gherdovich Subject: [PATCH v1 4/4] cpufreq: intel_pstate: Implement the ->adjust_perf() callback Date: Mon, 07 Dec 2020 17:38:58 +0100 Message-ID: <3342398.tGQZsKHvNY@kreacher> In-Reply-To: <20360841.iInq7taT2Z@kreacher> References: <20360841.iInq7taT2Z@kreacher> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org From: Rafael J. Wysocki Make intel_pstate expose the ->adjust_perf() callback when it operates in the passive mode with HWP enabled which causes the schedutil governor to use that callback instead of ->fast_switch(). The minimum and target performance-level values passed by the governor to ->adjust_perf() are converted to HWP.REQ.MIN and HWP.REQ.DESIRED, respectively, which allows the processor to adjust its configuration to maximize energy-efficiency while providing sufficient capacity. Signed-off-by: Rafael J. Wysocki --- Changes with respect to the RFC: - Drop the code related to the dropped "busy" argument of ->adjust_perf(). - Update the changelog accordingly. --- drivers/cpufreq/intel_pstate.c | 70 +++++++++++++++++++++++++++++++++-------- 1 file changed, 58 insertions(+), 12 deletions(-) Index: linux-pm/drivers/cpufreq/intel_pstate.c =================================================================== --- linux-pm.orig/drivers/cpufreq/intel_pstate.c +++ linux-pm/drivers/cpufreq/intel_pstate.c @@ -2526,20 +2526,19 @@ static void intel_cpufreq_trace(struct c fp_toint(cpu->iowait_boost * 100)); } -static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, - bool strict, bool fast_switch) +static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 min, u32 max, + u32 desired, bool fast_switch) { u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev; value &= ~HWP_MIN_PERF(~0L); - value |= HWP_MIN_PERF(target_pstate); + value |= HWP_MIN_PERF(min); - /* - * The entire MSR needs to be updated in order to update the HWP min - * field in it, so opportunistically update the max too if needed. - */ value &= ~HWP_MAX_PERF(~0L); - value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio); + value |= HWP_MAX_PERF(max); + + value &= ~HWP_DESIRED_PERF(~0L); + value |= HWP_DESIRED_PERF(desired); if (value == prev) return; @@ -2569,11 +2568,15 @@ static int intel_cpufreq_update_pstate(s int old_pstate = cpu->pstate.current_pstate; target_pstate = intel_pstate_prepare_request(cpu, target_pstate); - if (hwp_active) - intel_cpufreq_adjust_hwp(cpu, target_pstate, - policy->strict_target, fast_switch); - else if (target_pstate != old_pstate) + if (hwp_active) { + int max_pstate = policy->strict_target ? + target_pstate : cpu->max_perf_ratio; + + intel_cpufreq_adjust_hwp(cpu, target_pstate, max_pstate, 0, + fast_switch); + } else if (target_pstate != old_pstate) { intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch); + } cpu->pstate.current_pstate = target_pstate; @@ -2634,6 +2637,47 @@ static unsigned int intel_cpufreq_fast_s return target_pstate * cpu->pstate.scaling; } +static void intel_cpufreq_adjust_perf(unsigned int cpunum, + unsigned long min_perf, + unsigned long target_perf, + unsigned long capacity) +{ + struct cpudata *cpu = all_cpu_data[cpunum]; + int old_pstate = cpu->pstate.current_pstate; + int cap_pstate, min_pstate, max_pstate, target_pstate; + + update_turbo_state(); + cap_pstate = global.turbo_disabled ? cpu->pstate.max_pstate : + cpu->pstate.turbo_pstate; + + /* Optimization: Avoid unnecessary divisions. */ + + target_pstate = cap_pstate; + if (target_perf < capacity) + target_pstate = DIV_ROUND_UP(cap_pstate * target_perf, capacity); + + min_pstate = cap_pstate; + if (min_perf < capacity) + min_pstate = DIV_ROUND_UP(cap_pstate * min_perf, capacity); + + if (min_pstate < cpu->pstate.min_pstate) + min_pstate = cpu->pstate.min_pstate; + + if (min_pstate < cpu->min_perf_ratio) + min_pstate = cpu->min_perf_ratio; + + max_pstate = min(cap_pstate, cpu->max_perf_ratio); + if (max_pstate < min_pstate) + max_pstate = min_pstate; + + target_pstate = clamp_t(int, target_pstate, min_pstate, max_pstate); + + intel_cpufreq_adjust_hwp(cpu, min_pstate, max_pstate, target_pstate, true); + + cpu->pstate.current_pstate = target_pstate; + intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate); +} + static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) { int max_state, turbo_max, min_freq, max_freq, ret; @@ -3032,6 +3076,8 @@ static int __init intel_pstate_init(void intel_pstate.attr = hwp_cpufreq_attrs; intel_cpufreq.attr = hwp_cpufreq_attrs; intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS; + intel_cpufreq.fast_switch = NULL; + intel_cpufreq.adjust_perf = intel_cpufreq_adjust_perf; if (!default_driver) default_driver = &intel_pstate;