From patchwork Thu Feb 22 13:56:59 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pierre Gondois X-Patchwork-Id: 13567382 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 796B5138489; Thu, 22 Feb 2024 13:57:14 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610236; cv=none; b=Q2WJWjPTXYy7aWyYeqQTezxPUJ6kIS22tImRbtXw8xjMUbuZkFJdfwz+/jEMV5tEBeOST619KMUlTdYrjJsA3OGqJVKicXamaeCRWtX6DmFAP9RGiSfJ/efD1r0A+Yx5+D6ez9T5Zck6IgHOOJEGBcUhZIj1BexLjuq7Gc2Vu0w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610236; c=relaxed/simple; bh=vTobQSrduSBuA1TUKnn4ttuDr4UZ3tWYTkDtSYmJZBg=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=GCBlaNH8u7abyeMtBXyLreqg3Tu1SE10Qe0S49I9BtKQrYyO44fuOFKdxr+N5HiU/1vHuzJTNnLOPG9dGoFeEZDe+n3PqxXpQ5k9fLokbL88SoJr5/CsGA45WzYGrTvFOv/+EshHRULhPP8iks5KVkwZQBpJdl12POC70QnNWKw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 51ED01007; Thu, 22 Feb 2024 05:57:52 -0800 (PST) Received: from e126645.arm.com (unknown [10.57.50.6]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 6B5C83F762; Thu, 22 Feb 2024 05:57:11 -0800 (PST) From: Pierre Gondois To: linux-kernel@vger.kernel.org Cc: Cristian Marussi , Christian Loehle , Ionela Voinescu , Sudeep Holla , Dietmar Eggemann , Pierre Gondois , "Rafael J. Wysocki" , Viresh Kumar , linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org Subject: [PATCH 1/3] firmware: arm_scmi: Populate perf commands rate_limit Date: Thu, 22 Feb 2024 14:56:59 +0100 Message-Id: <20240222135702.2005635-2-pierre.gondois@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20240222135702.2005635-1-pierre.gondois@arm.com> References: <20240222135702.2005635-1-pierre.gondois@arm.com> Precedence: bulk X-Mailing-List: linux-pm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Arm SCMI spec. v3.2, s4.5.3.4 PERFORMANCE_DOMAIN_ATTRIBUTES defines a per-domain rate_limit for performance requests: """ Rate Limit in microseconds, indicating the minimum time required between successive requests. A value of 0 indicates that this field is not supported by the platform. This field does not apply to FastChannels. """" The field is first defined in SCMI v1.0. Add support to fetch this value and advertise it through a rate_limit_get() callback. Signed-off-by: Pierre Gondois Reviewed-by: Cristian Marussi Acked-by: Sudeep Holla --- drivers/firmware/arm_scmi/perf.c | 21 +++++++++++++++++++++ include/linux/scmi_protocol.h | 4 ++++ 2 files changed, 25 insertions(+) diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 211e8e0aef2c..37c80376bd0a 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -153,6 +153,7 @@ struct perf_dom_info { bool perf_fastchannels; bool level_indexing_mode; u32 opp_count; + u32 rate_limit_us; u32 sustained_freq_khz; u32 sustained_perf_level; unsigned long mult_factor; @@ -266,6 +267,8 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, if (PROTOCOL_REV_MAJOR(version) >= 0x4) dom_info->level_indexing_mode = SUPPORTS_LEVEL_INDEXING(flags); + dom_info->rate_limit_us = le32_to_cpu(attr->rate_limit_us) & + GENMASK(19, 0); dom_info->sustained_freq_khz = le32_to_cpu(attr->sustained_freq_khz); dom_info->sustained_perf_level = @@ -855,6 +858,23 @@ scmi_dvfs_transition_latency_get(const struct scmi_protocol_handle *ph, return dom->opp[dom->opp_count - 1].trans_latency_us * 1000; } +static int +scmi_dvfs_rate_limit_get(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit) +{ + struct perf_dom_info *dom; + + if (!rate_limit) + return -EINVAL; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); + + *rate_limit = dom->rate_limit_us; + return 0; +} + static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain, unsigned long freq, bool poll) { @@ -970,6 +990,7 @@ static const struct scmi_perf_proto_ops perf_proto_ops = { .level_set = scmi_perf_level_set, .level_get = scmi_perf_level_get, .transition_latency_get = scmi_dvfs_transition_latency_get, + .rate_limit_get = scmi_dvfs_rate_limit_get, .device_opps_add = scmi_dvfs_device_opps_add, .freq_set = scmi_dvfs_freq_set, .freq_get = scmi_dvfs_freq_get, diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index f2f05fb42d28..acd956ffcb84 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -128,6 +128,8 @@ struct scmi_perf_domain_info { * @level_set: sets the performance level of a domain * @level_get: gets the performance level of a domain * @transition_latency_get: gets the DVFS transition latency for a given device + * @rate_limit_get: gets the minimum time (us) required between successive + * requests * @device_opps_add: adds all the OPPs for a given device * @freq_set: sets the frequency for a given device using sustained frequency * to sustained performance level mapping @@ -154,6 +156,8 @@ struct scmi_perf_proto_ops { u32 *level, bool poll); int (*transition_latency_get)(const struct scmi_protocol_handle *ph, u32 domain); + int (*rate_limit_get)(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit); int (*device_opps_add)(const struct scmi_protocol_handle *ph, struct device *dev, u32 domain); int (*freq_set)(const struct scmi_protocol_handle *ph, u32 domain, From patchwork Thu Feb 22 13:57:00 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pierre Gondois X-Patchwork-Id: 13567383 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 00BC81474A6; Thu, 22 Feb 2024 13:57:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610239; cv=none; b=SvOTPgl4BKeyOPUP/ze1mCmrX3ae34cWekTeAcfrjufREXAaQlt2mxltbo4BHK64Fg/9ddprukMOtmsEoLygXXe60RGfKy6JZVqva666xxiDN/2qoLlKPovem2hawAD5Vp5TYL9mhKsOx1RzWOTqRazcUnZced0ucEYIuqWp9Q0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610239; c=relaxed/simple; bh=1qnYusaNpig0INkVHatCtHGPaVx9Aabdn3o6JWMH1vQ=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=KrO+NWikbwHRFolyCZ6msXTfzyjDACArTk7bjCEvmc2up/D0LzGSLlfivtnCUPqdmPd3KUkzDr8S9ipNFD2eqKRFw+VmQJSbtBmiRN4vtBrd36CWonwgA7v9IKOnXnJslH/iHARNMf6KT4SKlRYoGzkURuB4CrGg9EeVaAQ+eOY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 E0D0ADA7; Thu, 22 Feb 2024 05:57:55 -0800 (PST) Received: from e126645.arm.com (unknown [10.57.50.6]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 18EB93F762; Thu, 22 Feb 2024 05:57:14 -0800 (PST) From: Pierre Gondois To: linux-kernel@vger.kernel.org Cc: Cristian Marussi , Christian Loehle , Ionela Voinescu , Sudeep Holla , Dietmar Eggemann , Pierre Gondois , "Rafael J. Wysocki" , Viresh Kumar , linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org Subject: [PATCH 2/3] firmware: arm_scmi: Populate fast channel rate_limit Date: Thu, 22 Feb 2024 14:57:00 +0100 Message-Id: <20240222135702.2005635-3-pierre.gondois@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20240222135702.2005635-1-pierre.gondois@arm.com> References: <20240222135702.2005635-1-pierre.gondois@arm.com> Precedence: bulk X-Mailing-List: linux-pm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Arm SCMI spec. v3.2, s4.5.3.12 PERFORMANCE_DESCRIBE_FASTCHANNEL defines a per-domain rate_limit for performance requests: """ Rate Limit in microseconds, indicating the minimum time required between successive requests. A value of 0 indicates that this field is not applicable or supported on the platform. """" The field is first defined in SCMI v2.0. Add support to fetch this value and advertise it through a fast_switch_rate_limit() callback. Signed-off-by: Pierre Gondois Reviewed-by: Cristian Marussi Acked-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 5 ++++- drivers/firmware/arm_scmi/perf.c | 32 +++++++++++++++++++++++---- drivers/firmware/arm_scmi/powercap.c | 12 ++++++---- drivers/firmware/arm_scmi/protocols.h | 4 +++- include/linux/scmi_protocol.h | 4 ++++ 5 files changed, 47 insertions(+), 10 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 3ea64b22cf0d..1d38ecfafc59 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1617,7 +1617,7 @@ static void scmi_common_fastchannel_init(const struct scmi_protocol_handle *ph, u8 describe_id, u32 message_id, u32 valid_size, u32 domain, void __iomem **p_addr, - struct scmi_fc_db_info **p_db) + struct scmi_fc_db_info **p_db, u32 *rate_limit) { int ret; u32 flags; @@ -1661,6 +1661,9 @@ scmi_common_fastchannel_init(const struct scmi_protocol_handle *ph, goto err_xfer; } + if (rate_limit) + *rate_limit = le32_to_cpu(resp->rate_limit) & GENMASK(19, 0); + phys_addr = le32_to_cpu(resp->chan_addr_low); phys_addr |= (u64)le32_to_cpu(resp->chan_addr_high) << 32; addr = devm_ioremap(ph->dev, phys_addr, size); diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 37c80376bd0a..fbcbd703198a 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -789,23 +789,27 @@ static void scmi_perf_domain_init_fc(const struct scmi_protocol_handle *ph, ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL, PERF_LEVEL_GET, 4, dom->id, - &fc[PERF_FC_LEVEL].get_addr, NULL); + &fc[PERF_FC_LEVEL].get_addr, NULL, + &fc[PERF_FC_LEVEL].rate_limit); ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL, PERF_LIMITS_GET, 8, dom->id, - &fc[PERF_FC_LIMIT].get_addr, NULL); + &fc[PERF_FC_LIMIT].get_addr, NULL, + &fc[PERF_FC_LIMIT].rate_limit); if (dom->info.set_perf) ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL, PERF_LEVEL_SET, 4, dom->id, &fc[PERF_FC_LEVEL].set_addr, - &fc[PERF_FC_LEVEL].set_db); + &fc[PERF_FC_LEVEL].set_db, + &fc[PERF_FC_LEVEL].rate_limit); if (dom->set_limits) ph->hops->fastchannel_init(ph, PERF_DESCRIBE_FASTCHANNEL, PERF_LIMITS_SET, 8, dom->id, &fc[PERF_FC_LIMIT].set_addr, - &fc[PERF_FC_LIMIT].set_db); + &fc[PERF_FC_LIMIT].set_db, + &fc[PERF_FC_LIMIT].rate_limit); dom->fc_info = fc; } @@ -974,6 +978,25 @@ static bool scmi_fast_switch_possible(const struct scmi_protocol_handle *ph, return dom->fc_info && dom->fc_info[PERF_FC_LEVEL].set_addr; } +static int scmi_fast_switch_rate_limit(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit) +{ + struct perf_dom_info *dom; + + if (!rate_limit) + return -EINVAL; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); + + if (!dom->fc_info) + return -EINVAL; + + *rate_limit = dom->fc_info[PERF_FC_LEVEL].rate_limit; + return 0; +} + static enum scmi_power_scale scmi_power_scale_get(const struct scmi_protocol_handle *ph) { @@ -996,6 +1019,7 @@ static const struct scmi_perf_proto_ops perf_proto_ops = { .freq_get = scmi_dvfs_freq_get, .est_power_get = scmi_dvfs_est_power_get, .fast_switch_possible = scmi_fast_switch_possible, + .fast_switch_rate_limit = scmi_fast_switch_rate_limit, .power_scale_get = scmi_power_scale_get, }; diff --git a/drivers/firmware/arm_scmi/powercap.c b/drivers/firmware/arm_scmi/powercap.c index a4c6cd4716fe..604184c044ff 100644 --- a/drivers/firmware/arm_scmi/powercap.c +++ b/drivers/firmware/arm_scmi/powercap.c @@ -703,20 +703,24 @@ static void scmi_powercap_domain_init_fc(const struct scmi_protocol_handle *ph, ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL, POWERCAP_CAP_SET, 4, domain, &fc[POWERCAP_FC_CAP].set_addr, - &fc[POWERCAP_FC_CAP].set_db); + &fc[POWERCAP_FC_CAP].set_db, + &fc[POWERCAP_FC_CAP].rate_limit); ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL, POWERCAP_CAP_GET, 4, domain, - &fc[POWERCAP_FC_CAP].get_addr, NULL); + &fc[POWERCAP_FC_CAP].get_addr, NULL, + &fc[POWERCAP_FC_CAP].rate_limit); ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL, POWERCAP_PAI_SET, 4, domain, &fc[POWERCAP_FC_PAI].set_addr, - &fc[POWERCAP_FC_PAI].set_db); + &fc[POWERCAP_FC_PAI].set_db, + &fc[POWERCAP_FC_PAI].rate_limit); ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL, POWERCAP_PAI_GET, 4, domain, - &fc[POWERCAP_FC_PAI].get_addr, NULL); + &fc[POWERCAP_FC_PAI].get_addr, NULL, + &fc[POWERCAP_PAI_GET].rate_limit); *p_fc = fc; } diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h index e683c26f24eb..8b5d9ce4a33a 100644 --- a/drivers/firmware/arm_scmi/protocols.h +++ b/drivers/firmware/arm_scmi/protocols.h @@ -234,6 +234,7 @@ struct scmi_fc_info { void __iomem *set_addr; void __iomem *get_addr; struct scmi_fc_db_info *set_db; + u32 rate_limit; }; /** @@ -268,7 +269,8 @@ struct scmi_proto_helpers_ops { u8 describe_id, u32 message_id, u32 valid_size, u32 domain, void __iomem **p_addr, - struct scmi_fc_db_info **p_db); + struct scmi_fc_db_info **p_db, + u32 *rate_limit); void (*fastchannel_db_ring)(struct scmi_fc_db_info *db); }; diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index acd956ffcb84..fafedb3b6604 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -139,6 +139,8 @@ struct scmi_perf_domain_info { * at a given frequency * @fast_switch_possible: indicates if fast DVFS switching is possible or not * for a given device + * @fast_switch_rate_limit: gets the minimum time (us) required between + * successive fast_switching requests * @power_scale_mw_get: indicates if the power values provided are in milliWatts * or in some other (abstract) scale */ @@ -168,6 +170,8 @@ struct scmi_perf_proto_ops { unsigned long *rate, unsigned long *power); bool (*fast_switch_possible)(const struct scmi_protocol_handle *ph, u32 domain); + int (*fast_switch_rate_limit)(const struct scmi_protocol_handle *ph, + u32 domain, u32 *rate_limit); enum scmi_power_scale (*power_scale_get)(const struct scmi_protocol_handle *ph); }; From patchwork Thu Feb 22 13:57:01 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pierre Gondois X-Patchwork-Id: 13567384 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 4F35A1474C1; Thu, 22 Feb 2024 13:57:21 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610242; cv=none; b=KYJzgxKiO2MBQ1aAAeTSzukZ8Q1OpNVpkzNALYAhLnRM0t6YEYxWkLFXtE56x3qbwKGhUZnQyY8JROm0ue26pTzF9xz3hR7eUQeZHkFezgeqzlM5KxWwEnYiRVvXuuH+VQsAe5Jr93QyWgCNj9UtRWVysmMaQmepUMnw6atKdu0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1708610242; c=relaxed/simple; bh=+gm91ZtyDofHjM2c3cnsnbGIdaQIAtNdEWIE4qR/lL4=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=TSlJEyo3bWGclTIMNMLE8SMll0EAk/cP4wF0ZZ+d+RvbClSCxy6lRKn9fW1t9SaXwrrr/0BDe7GkbBnYj7tRfRtTynJKapn6enbR8gh6r6P3NVU4vsVVteYJslHtPW+wailNrZ4+V9XwUc7dar+HwtYS/aOkfgxdf77SYZg/ZvA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 4934B1007; Thu, 22 Feb 2024 05:57:59 -0800 (PST) Received: from e126645.arm.com (unknown [10.57.50.6]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 946493F762; Thu, 22 Feb 2024 05:57:18 -0800 (PST) From: Pierre Gondois To: linux-kernel@vger.kernel.org Cc: Cristian Marussi , Christian Loehle , Ionela Voinescu , Sudeep Holla , Dietmar Eggemann , Pierre Gondois , "Rafael J. Wysocki" , Viresh Kumar , linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org Subject: [PATCH 3/3] cpufreq: scmi: Set transition_delay_us Date: Thu, 22 Feb 2024 14:57:01 +0100 Message-Id: <20240222135702.2005635-4-pierre.gondois@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20240222135702.2005635-1-pierre.gondois@arm.com> References: <20240222135702.2005635-1-pierre.gondois@arm.com> Precedence: bulk X-Mailing-List: linux-pm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Make use of the newly added callbacks: - rate_limit_get() - fast_switch_rate_limit() to populate policies's `transition_delay_us`, defined as the 'Preferred average time interval between consecutive invocations of the driver to set the frequency for this policy.' Signed-off-by: Pierre Gondois --- drivers/cpufreq/scmi-cpufreq.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 4ee23f4ebf4a..0b483bd0d3ca 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -144,6 +144,29 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power, return 0; } +static int +scmi_get_rate_limit(u32 domain, bool has_fast_switch) +{ + int ret, rate_limit; + + if (has_fast_switch) { + /* + * Fast channels are used whenever available, + * so use their rate_limit value if populated. + */ + ret = perf_ops->fast_switch_rate_limit(ph, domain, + &rate_limit); + if (!ret && rate_limit) + return rate_limit; + } + + ret = perf_ops->rate_limit_get(ph, domain, &rate_limit); + if (ret) + return 0; + + return rate_limit; +} + static int scmi_cpufreq_init(struct cpufreq_policy *policy) { int ret, nr_opp, domain; @@ -250,6 +273,9 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = perf_ops->fast_switch_possible(ph, domain); + policy->transition_delay_us = + scmi_get_rate_limit(domain, policy->fast_switch_possible); + return 0; out_free_opp: