Merge tag 'pm+acpi-3.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull ACPI and power management updates from Rafael Wysocki:
 "This is material that didn't make it to my 3.18-rc1 pull request for
  various reasons, mostly related to timing and travel (LinuxCon EU /
  LPC) plus a couple of fixes for recent bugs.

  The only really new thing here is the PM QoS class for memory
  bandwidth, but it is simple enough and users of it will be added in
  the next cycle.  One major change in behavior is that platform devices
  enumerated by ACPI will use 32-bit DMA mask by default.  Also included
  is an ACPICA update to a new upstream release, but that's mostly
  cleanups, changes in tools and similar.  The rest is fixes and
  cleanups mostly.

  Specifics:

   - Fix for a recent PCI power management change that overlooked the
     fact that some IRQ chips might not be able to configure PCIe PME
     for system wakeup from Lucas Stach.

   - Fix for a bug introduced in 3.17 where acpi_device_wakeup() is
     called with a wrong ordering of arguments from Zhang Rui.

   - A bunch of intel_pstate driver fixes (all -stable candidates) from
     Dirk Brandewie, Gabriele Mazzotta and Pali Rohár.

   - Fixes for a rather long-standing problem with the OOM killer and
     the freezer that frozen processes killed by the OOM do not actually
     release any memory until they are thawed, so OOM-killing them is
     rather pointless, with a couple of cleanups on top (Michal Hocko,
     Cong Wang, Rafael J Wysocki).

   - ACPICA update to upstream release 20140926, inlcuding mostly
     cleanups reducing differences between the upstream ACPICA and the
     kernel code, tools changes (acpidump, acpiexec) and support for the
     _DDN object (Bob Moore, Lv Zheng).

   - New PM QoS class for memory bandwidth from Tomeu Vizoso.

   - Default 32-bit DMA mask for platform devices enumerated by ACPI
     (this change is mostly needed for some drivers development in
     progress targeted at 3.19) from Heikki Krogerus.

   - ACPI EC driver cleanups, mostly related to debugging, from Lv
     Zheng.

   - cpufreq-dt driver updates from Thomas Petazzoni.

   - powernv cpuidle driver update from Preeti U Murthy"

* tag 'pm+acpi-3.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (34 commits)
  intel_pstate: Correct BYT VID values.
  intel_pstate: Fix BYT frequency reporting
  intel_pstate: Don't lose sysfs settings during cpu offline
  cpufreq: intel_pstate: Reflect current no_turbo state correctly
  cpufreq: expose scaling_cur_freq sysfs file for set_policy() drivers
  cpufreq: intel_pstate: Fix setting max_perf_pct in performance policy
  PCI / PM: handle failure to enable wakeup on PCIe PME
  ACPI: invoke acpi_device_wakeup() with correct parameters
  PM / freezer: Clean up code after recent fixes
  PM: convert do_each_thread to for_each_process_thread
  OOM, PM: OOM killed task shouldn't escape PM suspend
  freezer: remove obsolete comments in __thaw_task()
  freezer: Do not freeze tasks killed by OOM killer
  ACPI / platform: provide default DMA mask
  cpuidle: powernv: Populate cpuidle state details by querying the device-tree
  cpufreq: cpufreq-dt: adjust message related to regulators
  cpufreq: cpufreq-dt: extend with platform_data
  cpufreq: allow driver-specific data
  ACPI / EC: Cleanup coding style.
  ACPI / EC: Refine event/query debugging messages.
  ...

1 files changed, 88 insertions, 22 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 0668b389c516..27bb6d3877ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -52,6 +52,17 @@ static inline int32_t div_fp(int32_t x, int32_t y)
 	return div_s64((int64_t)x << FRAC_BITS, y);
 }
 
+static inline int ceiling_fp(int32_t x)
+{
+	int mask, ret;
+
+	ret = fp_toint(x);
+	mask = (1 << FRAC_BITS) - 1;
+	if (x & mask)
+		ret += 1;
+	return ret;
+}
+
 struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
@@ -64,6 +75,7 @@ struct pstate_data {
 	int	current_pstate;
 	int	min_pstate;
 	int	max_pstate;
+	int	scaling;
 	int	turbo_pstate;
 };
 
@@ -113,6 +125,7 @@ struct pstate_funcs {
 	int (*get_max)(void);
 	int (*get_min)(void);
 	int (*get_turbo)(void);
+	int (*get_scaling)(void);
 	void (*set)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
 };
@@ -138,6 +151,7 @@ struct perf_limits {
 
 static struct perf_limits limits = {
 	.no_turbo = 0,
+	.turbo_disabled = 0,
 	.max_perf_pct = 100,
 	.max_perf = int_tofp(1),
 	.min_perf_pct = 0,
@@ -218,6 +232,18 @@ static inline void intel_pstate_reset_all_pid(void)
 	}
 }
 
+static inline void update_turbo_state(void)
+{
+	u64 misc_en;
+	struct cpudata *cpu;
+
+	cpu = all_cpu_data[0];
+	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
+	limits.turbo_disabled =
+		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
+		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
+}
+
 /************************** debugfs begin ************************/
 static int pid_param_set(void *data, u64 val)
 {
@@ -274,6 +300,20 @@ static void __init intel_pstate_debug_expose_params(void)
 		return sprintf(buf, "%u\n", limits.object);		\
 	}
 
+static ssize_t show_no_turbo(struct kobject *kobj,
+			     struct attribute *attr, char *buf)
+{
+	ssize_t ret;
+
+	update_turbo_state();
+	if (limits.turbo_disabled)
+		ret = sprintf(buf, "%u\n", limits.turbo_disabled);
+	else
+		ret = sprintf(buf, "%u\n", limits.no_turbo);
+
+	return ret;
+}
+
 static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 			      const char *buf, size_t count)
 {
@@ -283,11 +323,14 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	limits.no_turbo = clamp_t(int, input, 0 , 1);
+
+	update_turbo_state();
 	if (limits.turbo_disabled) {
 		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
-		limits.no_turbo = limits.turbo_disabled;
+		return -EPERM;
 	}
+	limits.no_turbo = clamp_t(int, input, 0, 1);
+
 	return count;
 }
 
@@ -323,7 +366,6 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-show_one(no_turbo, no_turbo);
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
@@ -394,7 +436,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 		cpudata->vid.ratio);
 
 	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
-	vid = fp_toint(vid_fp);
+	vid = ceiling_fp(vid_fp);
 
 	if (pstate > cpudata->pstate.max_pstate)
 		vid = cpudata->vid.turbo;
@@ -404,6 +446,22 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
+#define BYT_BCLK_FREQS 5
+static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
+
+static int byt_get_scaling(void)
+{
+	u64 value;
+	int i;
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0x3;
+
+	BUG_ON(i > BYT_BCLK_FREQS);
+
+	return byt_freq_table[i] * 100;
+}
+
 static void byt_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
@@ -449,6 +507,11 @@ static int core_get_turbo_pstate(void)
 	return ret;
 }
 
+static inline int core_get_scaling(void)
+{
+	return 100000;
+}
+
 static void core_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
@@ -473,6 +536,7 @@ static struct cpu_defaults core_params = {
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = core_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
@@ -491,6 +555,7 @@ static struct cpu_defaults byt_params = {
 		.get_min = byt_get_min_pstate,
 		.get_turbo = byt_get_turbo_pstate,
 		.set = byt_set_pstate,
+		.get_scaling = byt_get_scaling,
 		.get_vid = byt_get_vid,
 	},
 };
@@ -501,7 +566,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	int max_perf_adj;
 	int min_perf;
 
-	if (limits.no_turbo)
+	if (limits.no_turbo || limits.turbo_disabled)
 		max_perf = cpu->pstate.max_pstate;
 
 	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
@@ -516,6 +581,8 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	int max_perf, min_perf;
 
+	update_turbo_state();
+
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
 	pstate = clamp_t(int, pstate, min_perf, max_perf);
@@ -523,7 +590,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-	trace_cpu_frequency(pstate * 100000, cpu->cpu);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
 
@@ -535,6 +602,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate = pstate_funcs.get_max();
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+	cpu->pstate.scaling = pstate_funcs.get_scaling();
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
@@ -550,7 +618,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
 
 	sample->freq = fp_toint(
-		mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
+		mul_fp(int_tofp(
+			cpu->pstate.max_pstate * cpu->pstate.scaling / 100),
+			core_pct));
 
 	sample->core_pct_busy = (int32_t)core_pct;
 }
@@ -671,7 +741,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
 
-	all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
+	if (!all_cpu_data[cpunum])
+		all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata),
+					       GFP_KERNEL);
 	if (!all_cpu_data[cpunum])
 		return -ENOMEM;
 
@@ -714,9 +786,10 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits.min_perf_pct = 100;
 		limits.min_perf = int_tofp(1);
+		limits.max_policy_pct = 100;
 		limits.max_perf_pct = 100;
 		limits.max_perf = int_tofp(1);
-		limits.no_turbo = limits.turbo_disabled;
+		limits.no_turbo = 0;
 		return 0;
 	}
 	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
@@ -751,15 +824,12 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 
 	del_timer_sync(&all_cpu_data[cpu_num]->timer);
 	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
-	kfree(all_cpu_data[cpu_num]);
-	all_cpu_data[cpu_num] = NULL;
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
 	int rc;
-	u64 misc_en;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -767,23 +837,18 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
-	if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
-	    cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) {
-		limits.turbo_disabled = 1;
-		limits.no_turbo = 1;
-	}
 	if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	policy->min = cpu->pstate.min_pstate * 100000;
-	policy->max = cpu->pstate.turbo_pstate * 100000;
+	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
-	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
+	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->cpuinfo.max_freq =
+		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
@@ -841,6 +906,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_max   = funcs->get_max;
 	pstate_funcs.get_min   = funcs->get_min;
 	pstate_funcs.get_turbo = funcs->get_turbo;
+	pstate_funcs.get_scaling = funcs->get_scaling;
 	pstate_funcs.set       = funcs->set;
 	pstate_funcs.get_vid   = funcs->get_vid;
 }