cpufreq: amd-pstate: Add more tracepoint for AMD P-State module

Add frequency, mperf, aperf and tsc in the trace. This can be used
to debug and tune the performance of AMD P-state driver.

Use the time difference between amd_pstate_update to calculate CPU
frequency. There could be sleep in arch_freq_get_on_cpu, so do not
use it here.

Signed-off-by: Jinzhou Su <[e-mail]>
Co-developed-by: Huang Rui <[e-mail]>
Signed-off-by: Huang Rui <[e-mail]>
Signed-off-by: Rafael J. Wysocki <[e-mail]>

drivers/cpufreq/amd-pstate-trace.h

···
 	TP_PROTO(unsigned long min_perf,
 		 unsigned long target_perf,
 		 unsigned long capacity,
+		 u64 freq,
+		 u64 mperf,
+		 u64 aperf,
+		 u64 tsc,
 		 unsigned int cpu_id,
 		 bool changed,
 		 bool fast_switch
···
 	TP_ARGS(min_perf,
 		target_perf,
 		capacity,
+		freq,
+		mperf,
+		aperf,
+		tsc,
 		cpu_id,
 		changed,
 		fast_switch
···
 		__field(unsigned long, min_perf)
 		__field(unsigned long, target_perf)
 		__field(unsigned long, capacity)
+		__field(unsigned long long, freq)
+		__field(unsigned long long, mperf)
+		__field(unsigned long long, aperf)
+		__field(unsigned long long, tsc)
 		__field(unsigned int, cpu_id)
 		__field(bool, changed)
 		__field(bool, fast_switch)
···
 		__entry->min_perf = min_perf;
 		__entry->target_perf = target_perf;
 		__entry->capacity = capacity;
+		__entry->freq = freq;
+		__entry->mperf = mperf;
+		__entry->aperf = aperf;
+		__entry->tsc = tsc;
 		__entry->cpu_id = cpu_id;
 		__entry->changed = changed;
 		__entry->fast_switch = fast_switch;
 		),
 
-	TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu cpu_id=%u changed=%s fast_switch=%s",
+	TP_printk("amd_min_perf=%lu amd_des_perf=%lu amd_max_perf=%lu freq=%llu mperf=%llu aperf=%llu tsc=%llu cpu_id=%u changed=%s fast_switch=%s",
 		  (unsigned long)__entry->min_perf,
 		  (unsigned long)__entry->target_perf,
 		  (unsigned long)__entry->capacity,
+		  (unsigned long long)__entry->freq,
+		  (unsigned long long)__entry->mperf,
+		  (unsigned long long)__entry->aperf,
+		  (unsigned long long)__entry->tsc,
 		  (unsigned int)__entry->cpu_id,
 		  (__entry->changed) ? "true" : "false",
 		  (__entry->fast_switch) ? "true" : "false"

drivers/cpufreq/amd-pstate.c

···
 static struct cpufreq_driver amd_pstate_driver;
 
 /**
+ * struct  amd_aperf_mperf
+ * @aperf: actual performance frequency clock count
+ * @mperf: maximum performance frequency clock count
+ * @tsc:   time stamp counter
+ */
+struct amd_aperf_mperf {
+	u64 aperf;
+	u64 mperf;
+	u64 tsc;
+};
+
+/**
  * struct amd_cpudata - private CPU data for AMD P-State
  * @cpu: CPU number
  * @req: constraint request to apply
···
  * @min_freq: the frequency that mapped to lowest_perf
  * @nominal_freq: the frequency that mapped to nominal_perf
  * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf
+ * @cur: Difference of Aperf/Mperf/tsc count between last and current sample
+ * @prev: Last Aperf/Mperf/tsc count value read from register
+ * @freq: current cpu frequency value
  * @boost_supported: check whether the Processor or SBIOS supports boost mode
  *
  * The amd_cpudata is key private data for each CPU thread in AMD P-State, and
···
 	u32	nominal_freq;
 	u32	lowest_nonlinear_freq;
 
+	struct amd_aperf_mperf cur;
+	struct amd_aperf_mperf prev;
+
+	u64 freq;
 	bool	boost_supported;
 };
 
···
 					    max_perf, fast_switch);
 }
 
+static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
+{
+	u64 aperf, mperf, tsc;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	rdmsrl(MSR_IA32_APERF, aperf);
+	rdmsrl(MSR_IA32_MPERF, mperf);
+	tsc = rdtsc();
+
+	if (cpudata->prev.mperf == mperf || cpudata->prev.tsc == tsc) {
+		local_irq_restore(flags);
+		return false;
+	}
+
+	local_irq_restore(flags);
+
+	cpudata->cur.aperf = aperf;
+	cpudata->cur.mperf = mperf;
+	cpudata->cur.tsc =  tsc;
+	cpudata->cur.aperf -= cpudata->prev.aperf;
+	cpudata->cur.mperf -= cpudata->prev.mperf;
+	cpudata->cur.tsc -= cpudata->prev.tsc;
+
+	cpudata->prev.aperf = aperf;
+	cpudata->prev.mperf = mperf;
+	cpudata->prev.tsc = tsc;
+
+	cpudata->freq = div64_u64((cpudata->cur.aperf * cpu_khz), cpudata->cur.mperf);
+
+	return true;
+}
+
 static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 			      u32 des_perf, u32 max_perf, bool fast_switch)
 {
···
 	value &= ~AMD_CPPC_MAX_PERF(~0L);
 	value |= AMD_CPPC_MAX_PERF(max_perf);
 
-	trace_amd_pstate_perf(min_perf, des_perf, max_perf,
-			      cpudata->cpu, (value != prev), fast_switch);
+	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
+		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
+			cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc,
+				cpudata->cpu, (value != prev), fast_switch);
+	}
 
 	if (value == prev)
 		return;