Merge tag 'pm+acpi-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull ACPI and power management fixes from Rafael Wysocki:

 - Two cpuidle initialization fixes from Konrad Rzeszutek Wilk.

 - cpufreq regression fixes for AMD processors from Borislav Petkov,
   Stefan Bader, and Matthew Garrett.

 - ACPI cpufreq fix from Thomas Schlichter.

 - cpufreq and devfreq fixes related to incorrect usage of operating
   performance points (OPP) framework and RCU from Nishanth Menon.

 - APEI workaround for incorrect BIOS information from Lans Zhang.

* tag 'pm+acpi-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: Add module aliases for acpi-cpufreq
  ACPI: Check MSR valid bit before using P-state frequencies
  PM / devfreq: exynos4_bus: honor RCU lock usage
  PM / devfreq: add locking documentation for recommended_opp
  cpufreq: cpufreq-cpu0: use RCU locks around usage of OPP
  cpufreq: OMAP: use RCU locks around usage of OPP
  ACPI, APEI: Fixup incorrect 64-bit access width firmware bug
  ACPI / processor: Get power info before updating the C-states
  powernow-k8: Add a kconfig dependency on acpi-cpufreq
  ACPI / cpuidle: Fix NULL pointer issues when cpuidle is disabled
  intel_idle: Don't register CPU notifier if we are not running.

10 files changed, 103 insertions, 30 deletions

diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 00a783661d0b..46f80e2c92f7 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -590,6 +590,9 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
         if (bit_width == 32 && bit_offset == 0 && (*paddr & 0x03) == 0 &&
             *access_bit_width < 32)
                 *access_bit_width = 32;
+        else if (bit_width == 64 && bit_offset == 0 && (*paddr & 0x07) == 0 &&
+            *access_bit_width < 64)
+                *access_bit_width = 64;
 
         if ((bit_width + bit_offset) > *access_bit_width) {
                 pr_warning(FW_BUG APEI_PFX
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f1a5da44591d..ed9a1cc690be 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -958,6 +958,9 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr)
                 return -EINVAL;
         }
 
+        if (!dev)
+                return -EINVAL;
+
         dev->cpu = pr->id;
 
         if (max_cstate == 0)
@@ -1149,6 +1152,7 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
                 }
 
                 /* Populate Updated C-state information */
+                acpi_processor_get_power_info(pr);
                 acpi_processor_setup_cpuidle_states(pr);
 
                 /* Enable all cpuidle devices */
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 836bfe069042..53e7ac9403a7 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -340,6 +340,13 @@ static void amd_fixup_frequency(struct acpi_processor_px *px, int i)
         if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
             || boot_cpu_data.x86 == 0x11) {
                 rdmsr(MSR_AMD_PSTATE_DEF_BASE + index, lo, hi);
+                /*
+                 * MSR C001_0064+:
+                 * Bit 63: PstateEn. Read-write. If set, the P-state is valid.
+                 */
+                if (!(hi & BIT(31)))
+                        return;
+
                 fid = lo & 0x3f;
                 did = (lo >> 6) & 7;
                 if (boot_cpu_data.x86 == 0x10)
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 934854ae5eb4..7227cd734042 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -106,7 +106,7 @@ config X86_POWERNOW_K7_ACPI
 config X86_POWERNOW_K8
         tristate "AMD Opteron/Athlon64 PowerNow!"
         select CPU_FREQ_TABLE
-        depends on ACPI && ACPI_PROCESSOR
+        depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
         help
           This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
           Support for K10 and newer processors is now in acpi-cpufreq.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0d048f6a2b23..7b0d49d78c61 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -1030,4 +1030,11 @@ MODULE_PARM_DESC(acpi_pstate_strict,
 late_initcall(acpi_cpufreq_init);
 module_exit(acpi_cpufreq_exit);
 
+static const struct x86_cpu_id acpi_cpufreq_ids[] = {
+        X86_FEATURE_MATCH(X86_FEATURE_ACPI),
+        X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
+        {}
+};
+MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
+
 MODULE_ALIAS("acpi");
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 52bf36d599f5..debc5a7c8db6 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -71,12 +71,15 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
         }
 
         if (cpu_reg) {
+                rcu_read_lock();
                 opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
                 if (IS_ERR(opp)) {
+                        rcu_read_unlock();
                         pr_err("failed to find OPP for %ld\n", freq_Hz);
                         return PTR_ERR(opp);
                 }
                 volt = opp_get_voltage(opp);
+                rcu_read_unlock();
                 tol = volt * voltage_tolerance / 100;
                 volt_old = regulator_get_voltage(cpu_reg);
         }
@@ -236,12 +239,14 @@ static int cpu0_cpufreq_driver_init(void)
                  */
                 for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
                         ;
+                rcu_read_lock();
                 opp = opp_find_freq_exact(cpu_dev,
                                 freq_table[0].frequency * 1000, true);
                 min_uV = opp_get_voltage(opp);
                 opp = opp_find_freq_exact(cpu_dev,
                                 freq_table[i-1].frequency * 1000, true);
                 max_uV = opp_get_voltage(opp);
+                rcu_read_unlock();
                 ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
                 if (ret > 0)
                         transition_latency += ret * 1000;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 1f3417a8322d..97102b05843f 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -110,13 +110,16 @@ static int omap_target(struct cpufreq_policy *policy,
         freq = ret;
 
         if (mpu_reg) {
+                rcu_read_lock();
                 opp = opp_find_freq_ceil(mpu_dev, &freq);
                 if (IS_ERR(opp)) {
+                        rcu_read_unlock();
                         dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
                                 __func__, freqs.new);
                         return -EINVAL;
                 }
                 volt = opp_get_voltage(opp);
+                rcu_read_unlock();
                 tol = volt * OPP_TOLERANCE / 100;
                 volt_old = regulator_get_voltage(mpu_reg);
         }
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 53766f39aadd..3b367973a802 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -994,6 +994,11 @@ module_exit(devfreq_exit);
  * @freq:       The frequency given to target function
  * @flags:      Flags handed from devfreq framework.
  *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
 struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq,
                                     u32 flags)
diff --git a/drivers/devfreq/exynos4_bus.c b/drivers/devfreq/exynos4_bus.c
index 80c745e83082..46d94e9e95b5 100644
--- a/drivers/devfreq/exynos4_bus.c
+++ b/drivers/devfreq/exynos4_bus.c
@@ -73,6 +73,16 @@ enum busclk_level_idx {
 #define EX4210_LV_NUM   (LV_2 + 1)
 #define EX4x12_LV_NUM   (LV_4 + 1)
 
+/**
+ * struct busfreq_opp_info - opp information for bus
+ * @rate:       Frequency in hertz
+ * @volt:       Voltage in microvolts corresponding to this OPP
+ */
+struct busfreq_opp_info {
+        unsigned long rate;
+        unsigned long volt;
+};
+
 struct busfreq_data {
         enum exynos4_busf_type type;
         struct device *dev;
@@ -80,7 +90,7 @@ struct busfreq_data {
         bool disabled;
         struct regulator *vdd_int;
         struct regulator *vdd_mif; /* Exynos4412/4212 only */
-        struct opp *curr_opp;
+        struct busfreq_opp_info curr_oppinfo;
         struct exynos4_ppmu dmc[2];
 
         struct notifier_block pm_notifier;
@@ -296,13 +306,14 @@ static unsigned int exynos4x12_clkdiv_sclkip[][3] = {
 };
 
 
-static int exynos4210_set_busclk(struct busfreq_data *data, struct opp *opp)
+static int exynos4210_set_busclk(struct busfreq_data *data,
+                                 struct busfreq_opp_info *oppi)
 {
         unsigned int index;
         unsigned int tmp;
 
         for (index = LV_0; index < EX4210_LV_NUM; index++)
-                if (opp_get_freq(opp) == exynos4210_busclk_table[index].clk)
+                if (oppi->rate == exynos4210_busclk_table[index].clk)
                         break;
 
         if (index == EX4210_LV_NUM)
@@ -361,13 +372,14 @@ static int exynos4210_set_busclk(struct busfreq_data *data, struct opp *opp)
         return 0;
 }
 
-static int exynos4x12_set_busclk(struct busfreq_data *data, struct opp *opp)
+static int exynos4x12_set_busclk(struct busfreq_data *data,
+                                 struct busfreq_opp_info *oppi)
 {
         unsigned int index;
         unsigned int tmp;
 
         for (index = LV_0; index < EX4x12_LV_NUM; index++)
-                if (opp_get_freq(opp) == exynos4x12_mifclk_table[index].clk)
+                if (oppi->rate == exynos4x12_mifclk_table[index].clk)
                         break;
 
         if (index == EX4x12_LV_NUM)
@@ -576,11 +588,12 @@ static int exynos4x12_get_intspec(unsigned long mifclk)
         return -EINVAL;
 }
 
-static int exynos4_bus_setvolt(struct busfreq_data *data, struct opp *opp,
-                               struct opp *oldopp)
+static int exynos4_bus_setvolt(struct busfreq_data *data,
+                               struct busfreq_opp_info *oppi,
+                               struct busfreq_opp_info *oldoppi)
 {
         int err = 0, tmp;
-        unsigned long volt = opp_get_voltage(opp);
+        unsigned long volt = oppi->volt;
 
         switch (data->type) {
         case TYPE_BUSF_EXYNOS4210:
@@ -595,11 +608,11 @@ static int exynos4_bus_setvolt(struct busfreq_data *data, struct opp *opp,
                 if (err)
                         break;
 
-                tmp = exynos4x12_get_intspec(opp_get_freq(opp));
+                tmp = exynos4x12_get_intspec(oppi->rate);
                 if (tmp < 0) {
                         err = tmp;
                         regulator_set_voltage(data->vdd_mif,
-                                              opp_get_voltage(oldopp),
+                                              oldoppi->volt,
                                               MAX_SAFEVOLT);
                         break;
                 }
@@ -609,7 +622,7 @@ static int exynos4_bus_setvolt(struct busfreq_data *data, struct opp *opp,
                 /*  Try to recover */
                 if (err)
                         regulator_set_voltage(data->vdd_mif,
-                                              opp_get_voltage(oldopp),
+                                              oldoppi->volt,
                                               MAX_SAFEVOLT);
                 break;
         default:
@@ -626,17 +639,26 @@ static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
         struct platform_device *pdev = container_of(dev, struct platform_device,
                                                     dev);
         struct busfreq_data *data = platform_get_drvdata(pdev);
-        struct opp *opp = devfreq_recommended_opp(dev, _freq, flags);
-        unsigned long freq = opp_get_freq(opp);
-        unsigned long old_freq = opp_get_freq(data->curr_opp);
+        struct opp *opp;
+        unsigned long freq;
+        unsigned long old_freq = data->curr_oppinfo.rate;
+        struct busfreq_opp_info new_oppinfo;
 
-        if (IS_ERR(opp))
+        rcu_read_lock();
+        opp = devfreq_recommended_opp(dev, _freq, flags);
+        if (IS_ERR(opp)) {
+                rcu_read_unlock();
                 return PTR_ERR(opp);
+        }
+        new_oppinfo.rate = opp_get_freq(opp);
+        new_oppinfo.volt = opp_get_voltage(opp);
+        rcu_read_unlock();
+        freq = new_oppinfo.rate;
 
         if (old_freq == freq)
                 return 0;
 
-        dev_dbg(dev, "targetting %lukHz %luuV\n", freq, opp_get_voltage(opp));
+        dev_dbg(dev, "targetting %lukHz %luuV\n", freq, new_oppinfo.volt);
 
         mutex_lock(&data->lock);
 
@@ -644,17 +666,18 @@ static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
                 goto out;
 
         if (old_freq < freq)
-                err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+                err = exynos4_bus_setvolt(data, &new_oppinfo,
+                                          &data->curr_oppinfo);
         if (err)
                 goto out;
 
         if (old_freq != freq) {
                 switch (data->type) {
                 case TYPE_BUSF_EXYNOS4210:
-                        err = exynos4210_set_busclk(data, opp);
+                        err = exynos4210_set_busclk(data, &new_oppinfo);
                         break;
                 case TYPE_BUSF_EXYNOS4x12:
-                        err = exynos4x12_set_busclk(data, opp);
+                        err = exynos4x12_set_busclk(data, &new_oppinfo);
                         break;
                 default:
                         err = -EINVAL;
@@ -664,11 +687,12 @@ static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
                 goto out;
 
         if (old_freq > freq)
-                err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+                err = exynos4_bus_setvolt(data, &new_oppinfo,
+                                          &data->curr_oppinfo);
         if (err)
                 goto out;
 
-        data->curr_opp = opp;
+        data->curr_oppinfo = new_oppinfo;
 out:
         mutex_unlock(&data->lock);
         return err;
@@ -702,7 +726,7 @@ static int exynos4_bus_get_dev_status(struct device *dev,
 
         exynos4_read_ppmu(data);
         busier_dmc = exynos4_get_busier_dmc(data);
-        stat->current_frequency = opp_get_freq(data->curr_opp);
+        stat->current_frequency = data->curr_oppinfo.rate;
 
         if (busier_dmc)
                 addr = S5P_VA_DMC1;
@@ -933,6 +957,7 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
         struct busfreq_data *data = container_of(this, struct busfreq_data,
                                                  pm_notifier);
         struct opp *opp;
+        struct busfreq_opp_info new_oppinfo;
         unsigned long maxfreq = ULONG_MAX;
         int err = 0;
 
@@ -943,18 +968,29 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
 
                 data->disabled = true;
 
+                rcu_read_lock();
                 opp = opp_find_freq_floor(data->dev, &maxfreq);
+                if (IS_ERR(opp)) {
+                        rcu_read_unlock();
+                        dev_err(data->dev, "%s: unable to find a min freq\n",
+                                __func__);
+                        return PTR_ERR(opp);
+                }
+                new_oppinfo.rate = opp_get_freq(opp);
+                new_oppinfo.volt = opp_get_voltage(opp);
+                rcu_read_unlock();
 
-                err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+                err = exynos4_bus_setvolt(data, &new_oppinfo,
+                                          &data->curr_oppinfo);
                 if (err)
                         goto unlock;
 
                 switch (data->type) {
                 case TYPE_BUSF_EXYNOS4210:
-                        err = exynos4210_set_busclk(data, opp);
+                        err = exynos4210_set_busclk(data, &new_oppinfo);
                         break;
                 case TYPE_BUSF_EXYNOS4x12:
-                        err = exynos4x12_set_busclk(data, opp);
+                        err = exynos4x12_set_busclk(data, &new_oppinfo);
                         break;
                 default:
                         err = -EINVAL;
@@ -962,7 +998,7 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
                 if (err)
                         goto unlock;
 
-                data->curr_opp = opp;
+                data->curr_oppinfo = new_oppinfo;
 unlock:
                 mutex_unlock(&data->lock);
                 if (err)
@@ -1027,13 +1063,17 @@ static int exynos4_busfreq_probe(struct platform_device *pdev)
                 }
         }
 
+        rcu_read_lock();
         opp = opp_find_freq_floor(dev, &exynos4_devfreq_profile.initial_freq);
         if (IS_ERR(opp)) {
+                rcu_read_unlock();
                 dev_err(dev, "Invalid initial frequency %lu kHz.\n",
                         exynos4_devfreq_profile.initial_freq);
                 return PTR_ERR(opp);
         }
-        data->curr_opp = opp;
+        data->curr_oppinfo.rate = opp_get_freq(opp);
+        data->curr_oppinfo.volt = opp_get_voltage(opp);
+        rcu_read_unlock();
 
         platform_set_drvdata(pdev, data);
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 4ba384f1ab54..2df9414a72f7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -448,8 +448,6 @@ static int intel_idle_probe(void)
         else
                 on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 
-        register_cpu_notifier(&cpu_hotplug_notifier);
-
         pr_debug(PREFIX "v" INTEL_IDLE_VERSION
                 " model 0x%X\n", boot_cpu_data.x86_model);
 
@@ -612,6 +610,7 @@ static int __init intel_idle_init(void)
                         return retval;
                 }
         }
+        register_cpu_notifier(&cpu_hotplug_notifier);
 
         return 0;
 }