Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Mostly simple overlapping changes.

For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 87 insertions, 21 deletions

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 1b2f28f69a81..4852d9efe74e 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -80,11 +80,17 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 {
 	struct cppc_cpudata *cpu;
 	struct cpufreq_freqs freqs;
+	u32 desired_perf;
 	int ret = 0;
 
 	cpu = all_cpu_data[policy->cpu];
 
-	cpu->perf_ctrls.desired_perf = (u64)target_freq * policy->max / cppc_dmi_max_khz;
+	desired_perf = (u64)target_freq * cpu->perf_caps.highest_perf / cppc_dmi_max_khz;
+	/* Return if it is exactly the same perf */
+	if (desired_perf == cpu->perf_ctrls.desired_perf)
+		return ret;
+
+	cpu->perf_ctrls.desired_perf = desired_perf;
 	freqs.old = policy->cur;
 	freqs.new = target_freq;
 
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 18da4f8051d3..13475890d792 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -17,6 +17,7 @@
 struct cs_policy_dbs_info {
 	struct policy_dbs_info policy_dbs;
 	unsigned int down_skip;
+	unsigned int requested_freq;
 };
 
 static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
@@ -61,6 +62,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 {
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	unsigned int requested_freq = dbs_info->requested_freq;
 	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int load = dbs_update(policy);
@@ -72,10 +74,16 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 	if (cs_tuners->freq_step == 0)
 		goto out;
 
+	/*
+	 * If requested_freq is out of range, it is likely that the limits
+	 * changed in the meantime, so fall back to current frequency in that
+	 * case.
+	 */
+	if (requested_freq > policy->max || requested_freq < policy->min)
+		requested_freq = policy->cur;
+
 	/* Check for frequency increase */
 	if (load > dbs_data->up_threshold) {
-		unsigned int requested_freq = policy->cur;
-
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
@@ -83,8 +91,11 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 			goto out;
 
 		requested_freq += get_freq_target(cs_tuners, policy);
+		if (requested_freq > policy->max)
+			requested_freq = policy->max;
 
 		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H);
+		dbs_info->requested_freq = requested_freq;
 		goto out;
 	}
 
@@ -95,7 +106,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 
 	/* Check for frequency decrease */
 	if (load < cs_tuners->down_threshold) {
-		unsigned int freq_target, requested_freq = policy->cur;
+		unsigned int freq_target;
 		/*
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
@@ -109,6 +120,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 			requested_freq = policy->min;
 
 		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L);
+		dbs_info->requested_freq = requested_freq;
 	}
 
  out:
@@ -287,6 +299,7 @@ static void cs_start(struct cpufreq_policy *policy)
 	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
 
 	dbs_info->down_skip = 0;
+	dbs_info->requested_freq = policy->cur;
 }
 
 static struct dbs_governor cs_governor = {
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 806f2039571e..4737520ec823 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct _pid {
 /**
  * struct cpudata -	Per CPU instance data storage
  * @cpu:		CPU number for this instance data
+ * @policy:		CPUFreq policy value
  * @update_util:	CPUFreq utility callback information
  * @update_util_set:	CPUFreq utility callback is set
  * @iowait_boost:	iowait-related boost fraction
@@ -201,6 +202,7 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
+	unsigned int policy;
 	struct update_util_data update_util;
 	bool   update_util_set;
 
@@ -225,7 +227,7 @@ struct cpudata {
 static struct cpudata **all_cpu_data;
 
 /**
- * struct pid_adjust_policy - Stores static PID configuration data
+ * struct pstate_adjust_policy - Stores static PID configuration data
  * @sample_rate_ms:	PID calculation sample rate in ms
  * @sample_rate_ns:	Sample rate calculation in ns
  * @deadband:		PID deadband
@@ -562,12 +564,12 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask)
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	u64 value, cap;
 
-	rdmsrl(MSR_HWP_CAPABILITIES, cap);
-	hw_min = HWP_LOWEST_PERF(cap);
-	hw_max = HWP_HIGHEST_PERF(cap);
-	range = hw_max - hw_min;
-
 	for_each_cpu(cpu, cpumask) {
+		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+		hw_min = HWP_LOWEST_PERF(cap);
+		hw_max = HWP_HIGHEST_PERF(cap);
+		range = hw_max - hw_min;
+
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 		adj_range = limits->min_perf_pct * range / 100;
 		min = hw_min + adj_range;
@@ -1142,10 +1144,8 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
-	int pstate = cpu->pstate.min_pstate;
-
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	cpu->pstate.current_pstate = pstate;
 	/*
@@ -1157,6 +1157,20 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 		      pstate_funcs.get_val(cpu, pstate));
 }
 
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
+static void intel_pstate_max_within_limits(struct cpudata *cpu)
+{
+	int min_pstate, max_pstate;
+
+	update_turbo_state();
+	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+	intel_pstate_set_pstate(cpu, max_pstate);
+}
+
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
@@ -1232,6 +1246,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
 	int32_t busy_frac, boost;
+	int target, avg_pstate;
 
 	busy_frac = div_fp(sample->mperf, sample->tsc);
 
@@ -1242,7 +1257,26 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 		busy_frac = boost;
 
 	sample->busy_scaled = busy_frac * 100;
-	return get_avg_pstate(cpu) - pid_calc(&cpu->pid, sample->busy_scaled);
+
+	target = limits->no_turbo || limits->turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+	target += target >> 2;
+	target = mul_fp(target, busy_frac);
+	if (target < cpu->pstate.min_pstate)
+		target = cpu->pstate.min_pstate;
+
+	/*
+	 * If the average P-state during the previous cycle was higher than the
+	 * current target, add 50% of the difference to the target to reduce
+	 * possible performance oscillations and offset possible performance
+	 * loss related to moving the workload from one CPU to another within
+	 * a package/module.
+	 */
+	avg_pstate = get_avg_pstate(cpu);
+	if (avg_pstate > target)
+		target += (avg_pstate - target) >> 1;
+
+	return target;
 }
 
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
@@ -1251,10 +1285,11 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	u64 duration_ns;
 
 	/*
-	 * perf_scaled is the average performance during the last sampling
-	 * period scaled by the ratio of the maximum P-state to the P-state
-	 * requested last time (in percent).  That measures the system's
-	 * response to the previous P-state selection.
+	 * perf_scaled is the ratio of the average P-state during the last
+	 * sampling period to the P-state requested last time (in percent).
+	 *
+	 * That measures the system's response to the previous P-state
+	 * selection.
 	 */
 	max_pstate = cpu->pstate.max_pstate_physical;
 	current_pstate = cpu->pstate.current_pstate;
@@ -1304,7 +1339,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
 	from = cpu->pstate.current_pstate;
 
-	target_pstate = pstate_funcs.get_target_pstate(cpu);
+	target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
+		cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
 
 	intel_pstate_update_pstate(cpu, target_pstate);
 
@@ -1470,7 +1506,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
 		 policy->cpuinfo.max_freq, policy->max);
 
-	cpu = all_cpu_data[0];
+	cpu = all_cpu_data[policy->cpu];
+	cpu->policy = policy->policy;
+
 	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
@@ -1478,7 +1516,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		policy->max = policy->cpuinfo.max_freq;
 	}
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
 		if (policy->max >= policy->cpuinfo.max_freq) {
 			pr_debug("set performance\n");
@@ -1514,6 +1552,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		/*
+		 * NOHZ_FULL CPUs need this as the governor callback may not
+		 * be invoked on them.
+		 */
+		intel_pstate_clear_update_util_hook(policy->cpu);
+		intel_pstate_max_within_limits(cpu);
+	}
+
 	intel_pstate_set_update_util_hook(policy->cpu);
 
 	intel_pstate_hwp_set_policy(policy);