Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.31 as permitted sender) client-ip=23.128.96.31;
From:   Zeng Heng <zengheng4@huawei.com>
To:     <broonie@kernel.org>, <joey.gouly@arm.com>, <will@kernel.org>,
        <amit.kachhap@arm.com>, <rafael@kernel.org>,
        <catalin.marinas@arm.com>, <james.morse@arm.com>,
        <mark.rutland@arm.com>, <maz@kernel.org>,
        <viresh.kumar@linaro.org>, <sumitg@nvidia.com>,
        <yang@os.amperecomputing.com>
CC:     <linux-kernel@vger.kernel.org>, <linux-pm@vger.kernel.org>,
        <linux-arm-kernel@lists.infradead.org>,
        <wangxiongfeng2@huawei.com>, <xiexiuqi@huawei.com>
Subject: [PATCH 2/3] cpufreq: CPPC: Keep the target core awake when reading its cpufreq rate
Date:   Wed, 25 Oct 2023 17:38:46 +0800
Message-ID: <20231025093847.3740104-3-zengheng4@huawei.com>
In-Reply-To: <20231025093847.3740104-1-zengheng4@huawei.com>
References: <20231025093847.3740104-1-zengheng4@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

As ARM AMU's document says, all counters are subject to any changes
in clock frequency, including clock stopping caused by the WFI and WFE
instructions.

Therefore, using smp_call_on_cpu() to trigger target CPU to
read self's AMU counters, which ensures the counters are working
properly while cstate feature is enabled.

Reported-by: Sumit Gupta <sumitg@nvidia.com>
Link: https://lore.kernel.org/all/20230418113459.12860-7-sumitg@nvidia.com/
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
---
 drivers/cpufreq/cppc_cpufreq.c | 39 ++++++++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 9 deletions(-)

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index fe08ca419b3d..321a9dc9484d 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -90,6 +90,12 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t1);
 
+struct fb_ctr_pair {
+	u32 cpu;
+	struct cppc_perf_fb_ctrs fb_ctrs_t0;
+	struct cppc_perf_fb_ctrs fb_ctrs_t1;
+};
+
 /**
  * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
  * @work: The work item.
@@ -840,9 +846,24 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	return (reference_perf * delta_delivered) / delta_reference;
 }
 
+static int cppc_get_perf_ctrs_pair(void *val)
+{
+	struct fb_ctr_pair *fb_ctrs = val;
+	int cpu = fb_ctrs->cpu;
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs->fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	return cppc_get_perf_ctrs(cpu, &fb_ctrs->fb_ctrs_t1);
+}
+
 static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
+	struct fb_ctr_pair fb_ctrs = { .cpu = cpu, };
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct cppc_cpudata *cpu_data = policy->driver_data;
 	u64 delivered_perf;
@@ -850,18 +871,18 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 
 	cpufreq_cpu_put(policy);
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
-	if (ret)
-		return 0;
-
-	udelay(2); /* 2usec delay between sampling */
+	if (cpu_has_amu_feat(cpu))
+		ret = smp_call_on_cpu(cpu, cppc_get_perf_ctrs_pair,
+				      &fb_ctrs, false);
+	else
+		ret = cppc_get_perf_ctrs_pair(&fb_ctrs);
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1);
 	if (ret)
 		return 0;
 
-	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
-					       &fb_ctrs_t1);
+	delivered_perf = cppc_perf_from_fbctrs(cpu_data,
+					      &fb_ctrs.fb_ctrs_t0,
+					      &fb_ctrs.fb_ctrs_t1);
 
 	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
 }
-- 
2.25.1