From 0612d928b7ff8c87043115f74f08cb4af1f0c4cf Mon Sep 17 00:00:00 2001 From: Adam Skladowski Date: Mon, 15 Aug 2022 12:09:42 +0200 Subject: [PATCH 01/16] cpufreq: Add SM6115 to cpufreq-dt-platdev blocklist The Qualcomm SM6115 platform uses the qcom-cpufreq-hw driver, so add it to the cpufreq-dt-platdev driver's blocklist. Signed-off-by: Adam Skladowski Signed-off-by: Viresh Kumar --- drivers/cpufreq/cpufreq-dt-platdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 2c96de3f2d83c..6ac3800db4508 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -146,6 +146,7 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "qcom,sc8180x", }, { .compatible = "qcom,sc8280xp", }, { .compatible = "qcom,sdm845", }, + { .compatible = "qcom,sm6115", }, { .compatible = "qcom,sm6350", }, { .compatible = "qcom,sm8150", }, { .compatible = "qcom,sm8250", }, From 6d5afdc97ea71958287364a1f1d07e59ef151b11 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 16 Aug 2022 14:06:29 +0100 Subject: [PATCH 02/16] cpufreq: schedutil: Move max CPU capacity to sugov_policy There is no need to keep the max CPU capacity in the per_cpu instance. Furthermore, there is no need to check and update that variable (sg_cpu->max) every time in the frequency change request, which is part of hot path. Instead use struct sugov_policy to store that information. Initialize the max CPU capacity during the setup and start callback. We can do that since all CPUs in the same frequency domain have the same max capacity (capacity setup and thermal pressure are based on that). Acked-by: Viresh Kumar Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/sched/cpufreq_schedutil.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 1207c78f85c11..9161d1136d01c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -25,6 +25,9 @@ struct sugov_policy { unsigned int next_freq; unsigned int cached_raw_freq; + /* max CPU capacity, which is equal for all CPUs in freq. domain */ + unsigned long max; + /* The next fields are only needed if fast switch cannot be used: */ struct irq_work irq_work; struct kthread_work work; @@ -48,7 +51,6 @@ struct sugov_cpu { unsigned long util; unsigned long bw_dl; - unsigned long max; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -158,7 +160,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->bw_dl = cpu_bw_dl(rq); sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), FREQUENCY_UTIL, NULL); @@ -253,6 +254,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, */ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) { + struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long boost; /* No boost currently required */ @@ -280,7 +282,8 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; + boost = sg_cpu->iowait_boost * sg_policy->max; + boost >>= SCHED_CAPACITY_SHIFT; boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; @@ -337,7 +340,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, if (!sugov_update_single_common(sg_cpu, time, flags)) return; - next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max); /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. @@ -373,6 +376,7 @@ 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); + struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long prev_util = sg_cpu->util; /* @@ -399,7 +403,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, 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); + map_util_perf(sg_cpu->util), + sg_policy->max); sg_cpu->sg_policy->last_freq_update_time = time; } @@ -408,25 +413,19 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned long util = 0, max = 1; + unsigned long util = 0; unsigned int j; for_each_cpu(j, policy->cpus) { struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); - unsigned long j_util, j_max; 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; - if (j_util * max > j_max * util) { - util = j_util; - max = j_max; - } + util = max(j_sg_cpu->util, util); } - return get_next_freq(sg_policy, util, max); + return get_next_freq(sg_policy, util, sg_policy->max); } static void @@ -752,7 +751,7 @@ 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; + unsigned int cpu = cpumask_first(policy->cpus); sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; sg_policy->last_freq_update_time = 0; @@ -760,6 +759,7 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->work_in_progress = false; sg_policy->limits_changed = false; sg_policy->cached_raw_freq = 0; + sg_policy->max = arch_scale_cpu_capacity(cpu); sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); From 3359d52755e5bf1268d96ce7e9d6e8c1b4700225 Mon Sep 17 00:00:00 2001 From: Zhang Jianhua Date: Tue, 30 Aug 2022 16:07:32 +0800 Subject: [PATCH 03/16] cpufreq: bmips-cpufreq: Use module_init and add module_exit - Use module_init instead of device_initcall. - Add a function for module_exit to unregister driver. Signed-off-by: Zhang Jianhua Signed-off-by: Viresh Kumar --- drivers/cpufreq/bmips-cpufreq.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c index f7c23fa468f0b..39221a9a187a7 100644 --- a/drivers/cpufreq/bmips-cpufreq.c +++ b/drivers/cpufreq/bmips-cpufreq.c @@ -156,7 +156,7 @@ static struct cpufreq_driver bmips_cpufreq_driver = { .name = BMIPS_CPUFREQ_PREFIX, }; -static int __init bmips_cpufreq_probe(void) +static int __init bmips_cpufreq_driver_init(void) { struct cpufreq_compat *cc; struct device_node *np; @@ -176,7 +176,13 @@ static int __init bmips_cpufreq_probe(void) return cpufreq_register_driver(&bmips_cpufreq_driver); } -device_initcall(bmips_cpufreq_probe); +module_init(bmips_cpufreq_driver_init); + +static void __exit bmips_cpufreq_driver_exit(void) +{ + cpufreq_unregister_driver(&bmips_cpufreq_driver); +} +module_exit(bmips_cpufreq_driver_exit); MODULE_AUTHOR("Markus Mayer "); MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs"); From 4f59540c3cd00a9a361b2cf2ac475edd83fd4f93 Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 15 Aug 2022 00:35:43 +0800 Subject: [PATCH 04/16] cpufreq: amd-pstate: simplify cpudata pointer assignment move the cpudata assignment to cpudata declaration which will simplify the functions. No functional change intended. Reviewed-by: Huang Rui Acked-by: Viresh Kumar Signed-off-by: Perry Yuan Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9ac75c1cde9c2..2c17623218eca 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -555,9 +555,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) { - struct amd_cpudata *cpudata; - - cpudata = policy->driver_data; + struct amd_cpudata *cpudata = policy->driver_data; freq_qos_remove_request(&cpudata->req[1]); freq_qos_remove_request(&cpudata->req[0]); @@ -599,9 +597,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy, char *buf) { int max_freq; - struct amd_cpudata *cpudata; - - cpudata = policy->driver_data; + struct amd_cpudata *cpudata = policy->driver_data; max_freq = amd_get_max_freq(cpudata); if (max_freq < 0) @@ -614,9 +610,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli char *buf) { int freq; - struct amd_cpudata *cpudata; - - cpudata = policy->driver_data; + struct amd_cpudata *cpudata = policy->driver_data; freq = amd_get_lowest_nonlinear_freq(cpudata); if (freq < 0) From d8bee41db83ea207792889df323bb46ee4ebab24 Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 15 Aug 2022 00:35:44 +0800 Subject: [PATCH 05/16] cpufreq: amd-pstate: fix white-space Remove the white space and correct mixed-up indentation Acked-by: Viresh Kumar Signed-off-by: Perry Yuan Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 2c17623218eca..ec02929aaa986 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -120,7 +120,7 @@ struct amd_cpudata { struct amd_aperf_mperf cur; struct amd_aperf_mperf prev; - u64 freq; + u64 freq; bool boost_supported; }; @@ -656,7 +656,7 @@ static struct cpufreq_driver amd_pstate_driver = { .resume = amd_pstate_cpu_resume, .set_boost = amd_pstate_set_boost, .name = "amd-pstate", - .attr = amd_pstate_attr, + .attr = amd_pstate_attr, }; static int __init amd_pstate_init(void) From b185c5053c65b7704ead4537e4d4d9b33dc398dc Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 15 Aug 2022 00:35:45 +0800 Subject: [PATCH 06/16] cpufreq: amd_pstate: fix wrong lowest perf fetch Fix the wrong lowest perf value reading which is used for new des_perf calculation by governor requested, the incorrect min_perf will get incorrect des_perf to be set , that will cause the system frequency changing unexpectedly. Reviewed-by: Huang Rui Acked-by: Viresh Kumar Signed-off-by: Perry Yuan Signed-off-by: Su Jinzhou Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index ec02929aaa986..a47a1a2fdd067 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -312,7 +312,7 @@ static int amd_pstate_target(struct cpufreq_policy *policy, return -ENODEV; cap_perf = READ_ONCE(cpudata->highest_perf); - min_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); max_perf = cap_perf; freqs.old = policy->cur; From 0e9a86386bca646d3b0fc50e5e15eedb1eb620b3 Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 15 Aug 2022 00:35:46 +0800 Subject: [PATCH 07/16] cpufreq: amd_pstate: map desired perf into pstate scope for powersave governor The patch will fix the invalid desired perf value for powersave governor. This issue is found when testing on one AMD EPYC system, the actual des_perf is smaller than the min_perf value, that is invalid value. because the min_perf is the lowest_perf system can support in idle state. Reviewed-by: Huang Rui Signed-off-by: Perry Yuan Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index a47a1a2fdd067..fd563a002fd03 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -269,6 +269,7 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, u64 prev = READ_ONCE(cpudata->cppc_req_cached); u64 value = prev; + des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); value &= ~AMD_CPPC_MIN_PERF(~0L); value |= AMD_CPPC_MIN_PERF(min_perf); @@ -357,8 +358,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (max_perf < min_perf) max_perf = min_perf; - des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); - amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true); } From ca08e46d4215e85eb3cef2481255431d98da56da Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Mon, 15 Aug 2022 00:35:47 +0800 Subject: [PATCH 08/16] cpufreq: amd-pstate: update pstate frequency transition delay time Change the default transition latency to be 20ms that is more reasonable transition delay for AMD processors in non-EPP driver mode. Update transition delay time to 1ms, in the AMD CPU autonomous mode and non-autonomous mode, CPPC firmware will decide frequency at 1ms timescale based on the workload utilization. Acked-by: Viresh Kumar Signed-off-by: Perry Yuan Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index fd563a002fd03..33fbd6a94c43a 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -46,8 +46,8 @@ #include #include "amd-pstate-trace.h" -#define AMD_PSTATE_TRANSITION_LATENCY 0x20000 -#define AMD_PSTATE_TRANSITION_DELAY 500 +#define AMD_PSTATE_TRANSITION_LATENCY 20000 +#define AMD_PSTATE_TRANSITION_DELAY 1000 /* * TODO: We need more time to fine tune processors with shared memory solution From ddf958f39741a1dda74020ac8a0f226cb5aa017b Mon Sep 17 00:00:00 2001 From: ye xingchen Date: Wed, 31 Aug 2022 03:32:13 +0000 Subject: [PATCH 09/16] cpufreq: tegra194: Remove the unneeded result variable Return the value returned by smp_call_function_single() directly instead of storing it in another redundant variable. Reported-by: Zeal Robot Signed-off-by: ye xingchen [ Viresh: Minor update to commit log ] Signed-off-by: Viresh Kumar --- drivers/cpufreq/tegra194-cpufreq.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 1216046cf4c2e..7e143c06972ef 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -314,11 +314,7 @@ static void tegra194_get_cpu_ndiv_sysreg(void *ndiv) static int tegra194_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv) { - int ret; - - ret = smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true); - - return ret; + return smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true); } static void tegra194_set_cpu_ndiv_sysreg(void *data) From bedadcfb011fef55273bd686e8893fdd8911dcdb Mon Sep 17 00:00:00 2001 From: Perry Yuan Date: Tue, 30 Aug 2022 09:56:00 +0800 Subject: [PATCH 10/16] cpufreq: amd-pstate: Fix initial highest_perf value To avoid some new AMD processors use wrong highest perf when amd pstate driver loaded, this fix will query the highest perf from MSR register MSR_AMD_CPPC_CAP1 and cppc_acpi interface firstly, then compare with the highest perf value got by calling amd_get_highest_perf() function. The lower value will be the correct highest perf we need to use. Otherwise the CPU max MHz will be incorrect if the amd_get_highest_perf() did not cover the new process family and model ID. Like this lscpu info, the max frequency is incorrect. Vendor ID: AuthenticAMD Socket(s): 1 Stepping: 2 CPU max MHz: 5410.0000 CPU min MHz: 400.0000 BogoMIPS: 5600.54 Fixes: 3743d55b289c2 (x86, sched: Fix the AMD CPPC maximum performance value on certain AMD Ryzen generations) Acked-by: Huang Rui Signed-off-by: Perry Yuan Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/amd-pstate.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 33fbd6a94c43a..bf0ed8e54fdff 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -152,6 +152,7 @@ static inline int amd_pstate_enable(bool enable) static int pstate_init_perf(struct amd_cpudata *cpudata) { u64 cap1; + u32 highest_perf; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); @@ -163,7 +164,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) * * CPPC entry doesn't indicate the highest performance in some ASICs. */ - WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf()); + highest_perf = amd_get_highest_perf(); + if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) + highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); + + WRITE_ONCE(cpudata->highest_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); @@ -175,12 +180,17 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) static int cppc_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; + u32 highest_perf; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf()); + highest_perf = amd_get_highest_perf(); + if (highest_perf > cppc_perf.highest_perf) + highest_perf = cppc_perf.highest_perf; + + WRITE_ONCE(cpudata->highest_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, From 71bb5c82aaaea007167f3ba68d3a669c74d7d55d Mon Sep 17 00:00:00 2001 From: Doug Smythies Date: Tue, 6 Sep 2022 13:28:57 -0700 Subject: [PATCH 11/16] cpufreq: intel_pstate: Add Tigerlake support in no-HWP mode Users may disable HWP in firmware, in which case intel_pstate wouldn't load unless the CPU model is explicitly supported. Add TIGERLAKE to the list of CPUs that can register intel_pstate while not advertising the HWP capability. Without this change, an TIGERLAKE in no-HWP mode could only use the acpi_cpufreq frequency scaling driver. See also commits: d8de7a44e11f: cpufreq: intel_pstate: Add Skylake servers support fbdc21e9b038: cpufreq: intel_pstate: Add Icelake servers support in no-HWP mode 706c5328851d: cpufreq: intel_pstate: Add Cometlake support in no-HWP mode Reported by: M. Cargi Ari Signed-off-by: Doug Smythies Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 57cdb36798854..fc3ebeb0bbe59 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2416,6 +2416,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { X86_MATCH(SKYLAKE_X, core_funcs), X86_MATCH(COMETLAKE, core_funcs), X86_MATCH(ICELAKE_X, core_funcs), + X86_MATCH(TIGERLAKE, core_funcs), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); From 91dc90fdb8b8199519a3aac9c46a433b02223c5b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 21 Sep 2022 12:30:38 +0530 Subject: [PATCH 12/16] cpufreq: qcom-cpufreq-hw: Fix uninitialized throttled_freq warning Commit 6240aaad75e1 was supposed to drop the reference count to the OPP, instead it avoided more stuff if the OPP isn't found. This isn't entirely correct. We already have a frequency value available, we just couldn't align it with an OPP in case of IS_ERR(opp). Lets continue with updating thermal pressure, etc, even if we aren't able to find an OPP here. This fixes warning generated by the 'smatch' tool. Fixes: 6240aaad75e1 ("cpufreq: qcom-hw: fix the opp entries refcounting") Cc: v5.18+ # v5.18+ Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Neil Armstrong Signed-off-by: Viresh Kumar --- drivers/cpufreq/qcom-cpufreq-hw.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index d5ef3c66c7625..bb32659820ceb 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -316,14 +316,14 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) if (IS_ERR(opp)) { dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp); } else { - throttled_freq = freq_hz / HZ_PER_KHZ; - - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); - dev_pm_opp_put(opp); } + throttled_freq = freq_hz / HZ_PER_KHZ; + + /* Update thermal pressure (the boost frequencies are accepted) */ + arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + /* * In the unlikely case policy is unregistered do not enable * polling or h/w interrupt From 676886010707fc656e2b407b2849883fbb63717e Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Tue, 20 Sep 2022 16:36:46 +0530 Subject: [PATCH 13/16] cpufreq: tegra194: Add support for Tegra239 Adding support for Tegra239 SoC which has eight cores in a single cluster. Also, moving num_clusters to SoC data to avoid over allocating memory for four clusters always. Signed-off-by: Sumit Gupta Acked-by: Thierry Reding Signed-off-by: Viresh Kumar --- drivers/cpufreq/tegra194-cpufreq.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 7e143c06972ef..cfc1b225f8115 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -38,14 +38,6 @@ /* cpufreq transisition latency */ #define TEGRA_CPUFREQ_TRANSITION_LATENCY (300 * 1000) /* unit in nanoseconds */ -enum cluster { - CLUSTER0, - CLUSTER1, - CLUSTER2, - CLUSTER3, - MAX_CLUSTERS, -}; - struct tegra_cpu_ctr { u32 cpu; u32 coreclk_cnt, last_coreclk_cnt; @@ -67,12 +59,12 @@ struct tegra_cpufreq_ops { struct tegra_cpufreq_soc { struct tegra_cpufreq_ops *ops; int maxcpus_per_cluster; + unsigned int num_clusters; phys_addr_t actmon_cntr_base; }; struct tegra194_cpufreq_data { void __iomem *regs; - size_t num_clusters; struct cpufreq_frequency_table **tables; const struct tegra_cpufreq_soc *soc; }; @@ -166,6 +158,14 @@ static const struct tegra_cpufreq_soc tegra234_cpufreq_soc = { .ops = &tegra234_cpufreq_ops, .actmon_cntr_base = 0x9000, .maxcpus_per_cluster = 4, + .num_clusters = 3, +}; + +const struct tegra_cpufreq_soc tegra239_cpufreq_soc = { + .ops = &tegra234_cpufreq_ops, + .actmon_cntr_base = 0x4000, + .maxcpus_per_cluster = 8, + .num_clusters = 1, }; static void tegra194_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid) @@ -378,7 +378,7 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy) data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid); - if (clusterid >= data->num_clusters || !data->tables[clusterid]) + if (clusterid >= data->soc->num_clusters || !data->tables[clusterid]) return -EINVAL; start_cpu = rounddown(policy->cpu, maxcpus_per_cluster); @@ -429,6 +429,7 @@ static struct tegra_cpufreq_ops tegra194_cpufreq_ops = { static const struct tegra_cpufreq_soc tegra194_cpufreq_soc = { .ops = &tegra194_cpufreq_ops, .maxcpus_per_cluster = 2, + .num_clusters = 4, }; static void tegra194_cpufreq_free_resources(void) @@ -521,15 +522,14 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev) soc = of_device_get_match_data(&pdev->dev); - if (soc->ops && soc->maxcpus_per_cluster) { + if (soc->ops && soc->maxcpus_per_cluster && soc->num_clusters) { data->soc = soc; } else { dev_err(&pdev->dev, "soc data missing\n"); return -EINVAL; } - data->num_clusters = MAX_CLUSTERS; - data->tables = devm_kcalloc(&pdev->dev, data->num_clusters, + data->tables = devm_kcalloc(&pdev->dev, data->soc->num_clusters, sizeof(*data->tables), GFP_KERNEL); if (!data->tables) return -ENOMEM; @@ -554,7 +554,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev) goto put_bpmp; } - for (i = 0; i < data->num_clusters; i++) { + for (i = 0; i < data->soc->num_clusters; i++) { data->tables[i] = init_freq_table(pdev, bpmp, i); if (IS_ERR(data->tables[i])) { err = PTR_ERR(data->tables[i]); @@ -586,6 +586,7 @@ static int tegra194_cpufreq_remove(struct platform_device *pdev) static const struct of_device_id tegra194_cpufreq_of_match[] = { { .compatible = "nvidia,tegra194-ccplex", .data = &tegra194_cpufreq_soc }, { .compatible = "nvidia,tegra234-ccplex-cluster", .data = &tegra234_cpufreq_soc }, + { .compatible = "nvidia,tegra239-ccplex-cluster", .data = &tegra239_cpufreq_soc }, { /* sentinel */ } }; From f991b117120569838676b9512f6e7d755fdfc12b Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 23 Sep 2022 22:50:16 +0800 Subject: [PATCH 14/16] cpufreq: tegra194: change tegra239_cpufreq_soc to static tegra239_cpufreq_soc is only used in tegra194-cpufreq.c now, change it to static. Fixes: 676886010707 ("cpufreq: tegra194: Add support for Tegra239") Signed-off-by: Yang Yingliang Signed-off-by: Viresh Kumar --- drivers/cpufreq/tegra194-cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index cfc1b225f8115..c2004cae3f021 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -161,7 +161,7 @@ static const struct tegra_cpufreq_soc tegra234_cpufreq_soc = { .num_clusters = 3, }; -const struct tegra_cpufreq_soc tegra239_cpufreq_soc = { +static const struct tegra_cpufreq_soc tegra239_cpufreq_soc = { .ops = &tegra234_cpufreq_ops, .actmon_cntr_base = 0x4000, .maxcpus_per_cluster = 8, From f7968c22bd427f98bacccc44f11523ba6b498e7d Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sat, 24 Sep 2022 17:21:59 +0800 Subject: [PATCH 15/16] cpufreq: Add __init annotation to module init funcs Add missing __init annotation to module init funcs. Signed-off-by: Xiu Jianfeng Signed-off-by: Viresh Kumar --- drivers/cpufreq/highbank-cpufreq.c | 2 +- drivers/cpufreq/sti-cpufreq.c | 2 +- drivers/cpufreq/ti-cpufreq.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c index ac57cddc5f2fe..a458647011434 100644 --- a/drivers/cpufreq/highbank-cpufreq.c +++ b/drivers/cpufreq/highbank-cpufreq.c @@ -55,7 +55,7 @@ static struct notifier_block hb_cpufreq_clk_nb = { .notifier_call = hb_cpufreq_clk_notify, }; -static int hb_cpufreq_driver_init(void) +static int __init hb_cpufreq_driver_init(void) { struct platform_device_info devinfo = { .name = "cpufreq-dt", }; struct device *cpu_dev; diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index a67df90848c2e..1a63aeea87112 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -252,7 +252,7 @@ static int sti_cpufreq_fetch_syscon_registers(void) return 0; } -static int sti_cpufreq_init(void) +static int __init sti_cpufreq_init(void) { int ret; diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index df85a77d476b4..f64180dd2005b 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -398,7 +398,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev) return ret; } -static int ti_cpufreq_init(void) +static int __init ti_cpufreq_init(void) { const struct of_device_id *match; From c4c0efb06f17fa4a37ad99e7752b18a5405c76dc Mon Sep 17 00:00:00 2001 From: Xuewen Yan Date: Mon, 26 Sep 2022 16:34:05 +0800 Subject: [PATCH 16/16] cpufreq: qcom-cpufreq-hw: Add cpufreq qos for LMh Before update thermal pressure, the max cpufreq should be limited. Add QOS control for Lmh throttle cpufreq. Signed-off-by: Xuewen Yan Signed-off-by: Viresh Kumar --- drivers/cpufreq/qcom-cpufreq-hw.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index bb32659820ceb..833589bc95e40 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -56,6 +57,8 @@ struct qcom_cpufreq_data { struct cpufreq_policy *policy; bool per_core_dcvs; + + struct freq_qos_request throttle_freq_req; }; static unsigned long cpu_hw_rate, xo_rate; @@ -321,6 +324,8 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) throttled_freq = freq_hz / HZ_PER_KHZ; + freq_qos_update_request(&data->throttle_freq_req, throttled_freq); + /* Update thermal pressure (the boost frequencies are accepted) */ arch_update_thermal_pressure(policy->related_cpus, throttled_freq); @@ -413,6 +418,14 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) if (data->throttle_irq < 0) return data->throttle_irq; + ret = freq_qos_add_request(&policy->constraints, + &data->throttle_freq_req, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to add freq constraint (%d)\n", ret); + return ret; + } + data->cancel_throttle = false; data->policy = policy; @@ -479,6 +492,7 @@ static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) if (data->throttle_irq <= 0) return; + freq_qos_remove_request(&data->throttle_freq_req); free_irq(data->throttle_irq, data); }