Merge branch 'linus' into release

Conflicts:
	drivers/acpi/debug.c

Signed-off-by: Len Brown <len.brown@intel.com>

3 files changed, 184 insertions, 66 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 18cc42562250..ed41562909fe 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -51,7 +51,7 @@
 static DEFINE_MUTEX(mce_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
-        rcu_dereference_check((p), \
+        rcu_dereference_index_check((p), \
                               rcu_read_lock_sched_held() || \
                               lockdep_is_held(&mce_read_mutex))
 
@@ -107,8 +107,8 @@ EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
 static int default_decode_mce(struct notifier_block *nb, unsigned long val,
                                void *data)
 {
-        pr_emerg("No human readable MCE decoding support on this CPU type.\n");
-        pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+        pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
+        pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
 
         return NOTIFY_STOP;
 }
@@ -211,11 +211,11 @@ void mce_log(struct mce *mce)
 
 static void print_mce(struct mce *m)
 {
-        pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
+        pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
                m->extcpu, m->mcgstatus, m->bank, m->status);
 
         if (m->ip) {
-                pr_emerg("RIP%s %02x:<%016Lx> ",
+                pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
                         !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
                                 m->cs, m->ip);
 
@@ -224,14 +224,14 @@ static void print_mce(struct mce *m)
                 pr_cont("\n");
         }
 
-        pr_emerg("TSC %llx ", m->tsc);
+        pr_emerg(HW_ERR "TSC %llx ", m->tsc);
         if (m->addr)
                 pr_cont("ADDR %llx ", m->addr);
         if (m->misc)
                 pr_cont("MISC %llx ", m->misc);
 
         pr_cont("\n");
-        pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+        pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
                 m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
 
         /*
@@ -241,16 +241,6 @@ static void print_mce(struct mce *m)
         atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
 }
 
-static void print_mce_head(void)
-{
-        pr_emerg("\nHARDWARE ERROR\n");
-}
-
-static void print_mce_tail(void)
-{
-        pr_emerg("This is not a software problem!\n");
-}
-
 #define PANIC_TIMEOUT 5 /* 5 seconds */
 
 static atomic_t mce_paniced;
@@ -291,7 +281,6 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
                 if (atomic_inc_return(&mce_fake_paniced) > 1)
                         return;
         }
-        print_mce_head();
         /* First print corrected ones that are still unlogged */
         for (i = 0; i < MCE_LOG_LEN; i++) {
                 struct mce *m = &mcelog.entry[i];
@@ -322,16 +311,15 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
                         apei_err = apei_write_mce(final);
         }
         if (cpu_missing)
-                printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
-        print_mce_tail();
+                pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n");
         if (exp)
-                printk(KERN_EMERG "Machine check: %s\n", exp);
+                pr_emerg(HW_ERR "Machine check: %s\n", exp);
         if (!fake_panic) {
                 if (panic_timeout == 0)
                         panic_timeout = mce_panic_timeout;
                 panic(msg);
         } else
-                printk(KERN_EMERG "Fake kernel panic: %s\n", msg);
+                pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
 }
 
 /* Support code for software error injection */
@@ -600,6 +588,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
                  */
                 if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
                         mce_log(&m);
+                        atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
                         add_taint(TAINT_MACHINE_CHECK);
                 }
 
@@ -1220,7 +1209,7 @@ int mce_notify_irq(void)
                         schedule_work(&mce_trigger_work);
 
                 if (__ratelimit(&ratelimit))
-                        printk(KERN_INFO "Machine check events logged\n");
+                        pr_info(HW_ERR "Machine check events logged\n");
 
                 return 1;
         }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 62b48e40920a..6fcd0936194f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -95,19 +95,20 @@ static void cmci_discover(int banks, int boot)
                 rdmsrl(MSR_IA32_MCx_CTL2(i), val);
 
                 /* Already owned by someone else? */
-                if (val & CMCI_EN) {
+                if (val & MCI_CTL2_CMCI_EN) {
                         if (test_and_clear_bit(i, owned) && !boot)
                                 print_update("SHD", &hdr, i);
                         __clear_bit(i, __get_cpu_var(mce_poll_banks));
                         continue;
                 }
 
-                val |= CMCI_EN | CMCI_THRESHOLD;
+                val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+                val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD;
                 wrmsrl(MSR_IA32_MCx_CTL2(i), val);
                 rdmsrl(MSR_IA32_MCx_CTL2(i), val);
 
                 /* Did the enable bit stick? -- the bank supports CMCI */
-                if (val & CMCI_EN) {
+                if (val & MCI_CTL2_CMCI_EN) {
                         if (!test_and_set_bit(i, owned) && !boot)
                                 print_update("CMCI", &hdr, i);
                         __clear_bit(i, __get_cpu_var(mce_poll_banks));
@@ -155,7 +156,7 @@ void cmci_clear(void)
                         continue;
                 /* Disable CMCI */
                 rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-                val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK);
+                val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK);
                 wrmsrl(MSR_IA32_MCx_CTL2(i), val);
                 __clear_bit(i, __get_cpu_var(mce_banks_owned));
         }
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index e1a0a3bf9716..c2a8b26d4fea 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -34,15 +34,25 @@
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL          (300 * HZ)
 
+#define THERMAL_THROTTLING_EVENT        0
+#define POWER_LIMIT_EVENT               1
+
 /*
- * Current thermal throttling state:
+ * Current thermal event state:
  */
-struct thermal_state {
-        bool                    is_throttled;
-
+struct _thermal_state {
+        bool                    new_event;
+        int                     event;
         u64                     next_check;
-        unsigned long           throttle_count;
-        unsigned long           last_throttle_count;
+        unsigned long           count;
+        unsigned long           last_count;
+};
+
+struct thermal_state {
+        struct _thermal_state core_throttle;
+        struct _thermal_state core_power_limit;
+        struct _thermal_state package_throttle;
+        struct _thermal_state package_power_limit;
 };
 
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
@@ -53,11 +63,13 @@ static u32 lvtthmr_init __read_mostly;
 
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)                         \
-        static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)
+        static SYSDEV_ATTR(_name, 0444,                                 \
+                           therm_throt_sysdev_show_##_name,             \
+                                   NULL)                                \
 
-#define define_therm_throt_sysdev_show_func(name)                       \
+#define define_therm_throt_sysdev_show_func(event, name)                \
                                                                         \
-static ssize_t therm_throt_sysdev_show_##name(                          \
+static ssize_t therm_throt_sysdev_show_##event##_##name(                \
                         struct sys_device *dev,                         \
                         struct sysdev_attribute *attr,                  \
                         char *buf)                                      \
@@ -66,30 +78,42 @@ static ssize_t therm_throt_sysdev_show_##name(				\
         ssize_t ret;                                                    \
                                                                         \
         preempt_disable();      /* CPU hotplug */                       \
-        if (cpu_online(cpu))                                            \
+        if (cpu_online(cpu)) {                                          \
                 ret = sprintf(buf, "%lu\n",                             \
-                              per_cpu(thermal_state, cpu).name);        \
-        else                                                            \
+                              per_cpu(thermal_state, cpu).event.name);  \
+        } else                                                          \
                 ret = 0;                                                \
         preempt_enable();                                               \
                                                                         \
         return ret;                                                     \
 }
 
-define_therm_throt_sysdev_show_func(throttle_count);
-define_therm_throt_sysdev_one_ro(throttle_count);
+define_therm_throt_sysdev_show_func(core_throttle, count);
+define_therm_throt_sysdev_one_ro(core_throttle_count);
+
+define_therm_throt_sysdev_show_func(core_power_limit, count);
+define_therm_throt_sysdev_one_ro(core_power_limit_count);
+
+define_therm_throt_sysdev_show_func(package_throttle, count);
+define_therm_throt_sysdev_one_ro(package_throttle_count);
+
+define_therm_throt_sysdev_show_func(package_power_limit, count);
+define_therm_throt_sysdev_one_ro(package_power_limit_count);
 
 static struct attribute *thermal_throttle_attrs[] = {
-        &attr_throttle_count.attr,
+        &attr_core_throttle_count.attr,
         NULL
 };
 
-static struct attribute_group thermal_throttle_attr_group = {
+static struct attribute_group thermal_attr_group = {
         .attrs  = thermal_throttle_attrs,
         .name   = "thermal_throttle"
 };
 #endif /* CONFIG_SYSFS */
 
+#define CORE_LEVEL      0
+#define PACKAGE_LEVEL   1
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -106,39 +130,70 @@ static struct attribute_group thermal_throttle_attr_group = {
  *          1 : Event should be logged further, and a message has been
  *              printed to the syslog.
  */
-static int therm_throt_process(bool is_throttled)
+static int therm_throt_process(bool new_event, int event, int level)
 {
-        struct thermal_state *state;
-        unsigned int this_cpu;
-        bool was_throttled;
+        struct _thermal_state *state;
+        unsigned int this_cpu = smp_processor_id();
+        bool old_event;
         u64 now;
+        struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
 
-        this_cpu = smp_processor_id();
         now = get_jiffies_64();
-        state = &per_cpu(thermal_state, this_cpu);
+        if (level == CORE_LEVEL) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        state = &pstate->core_throttle;
+                else if (event == POWER_LIMIT_EVENT)
+                        state = &pstate->core_power_limit;
+                else
+                         return 0;
+        } else if (level == PACKAGE_LEVEL) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        state = &pstate->package_throttle;
+                else if (event == POWER_LIMIT_EVENT)
+                        state = &pstate->package_power_limit;
+                else
+                        return 0;
+        } else
+                return 0;
 
-        was_throttled = state->is_throttled;
-        state->is_throttled = is_throttled;
+        old_event = state->new_event;
+        state->new_event = new_event;
 
-        if (is_throttled)
-                state->throttle_count++;
+        if (new_event)
+                state->count++;
 
         if (time_before64(now, state->next_check) &&
-                        state->throttle_count != state->last_throttle_count)
+                        state->count != state->last_count)
                 return 0;
 
         state->next_check = now + CHECK_INTERVAL;
-        state->last_throttle_count = state->throttle_count;
+        state->last_count = state->count;
 
         /* if we just entered the thermal event */
-        if (is_throttled) {
-                printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count);
+        if (new_event) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package",
+                                state->count);
+                else
+                        printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package",
+                                state->count);
 
                 add_taint(TAINT_MACHINE_CHECK);
                 return 1;
         }
-        if (was_throttled) {
-                printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu);
+        if (old_event) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        printk(KERN_INFO "CPU%d: %s temperature/speed normal\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package");
+                else
+                        printk(KERN_INFO "CPU%d: %s power limit normal\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package");
                 return 1;
         }
 
@@ -149,13 +204,32 @@ static int therm_throt_process(bool is_throttled)
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
 {
-        return sysfs_create_group(&sys_dev->kobj,
-                                  &thermal_throttle_attr_group);
+        int err;
+        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+
+        err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
+        if (err)
+                return err;
+
+        if (cpu_has(c, X86_FEATURE_PLN))
+                err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                              &attr_core_power_limit_count.attr,
+                                              thermal_attr_group.name);
+        if (cpu_has(c, X86_FEATURE_PTS))
+                err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                              &attr_package_throttle_count.attr,
+                                              thermal_attr_group.name);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                        &attr_package_power_limit_count.attr,
+                                        thermal_attr_group.name);
+
+        return err;
 }
 
 static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
 {
-        sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
+        sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
 }
 
 /* Mutex protecting device creation against CPU hotplug: */
@@ -226,14 +300,50 @@ device_initcall(thermal_throttle_init_device);
 
 #endif /* CONFIG_SYSFS */
 
+/*
+ * Set up the most two significant bit to notify mce log that this thermal
+ * event type.
+ * This is a temp solution. May be changed in the future with mce log
+ * infrasture.
+ */
+#define CORE_THROTTLED          (0)
+#define CORE_POWER_LIMIT        ((__u64)1 << 62)
+#define PACKAGE_THROTTLED       ((__u64)2 << 62)
+#define PACKAGE_POWER_LIMIT     ((__u64)3 << 62)
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
         __u64 msr_val;
+        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
         rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
-        if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0))
-                mce_log_therm_throt_event(msr_val);
+
+        if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+                                THERMAL_THROTTLING_EVENT,
+                                CORE_LEVEL) != 0)
+                mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
+
+        if (cpu_has(c, X86_FEATURE_PLN))
+                if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
+                                        POWER_LIMIT_EVENT,
+                                        CORE_LEVEL) != 0)
+                        mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
+
+        if (cpu_has(c, X86_FEATURE_PTS)) {
+                rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+                if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
+                                        THERMAL_THROTTLING_EVENT,
+                                        PACKAGE_LEVEL) != 0)
+                        mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        if (therm_throt_process(msr_val &
+                                        PACKAGE_THERM_STATUS_POWER_LIMIT,
+                                        POWER_LIMIT_EVENT,
+                                        PACKAGE_LEVEL) != 0)
+                                mce_log_therm_throt_event(PACKAGE_POWER_LIMIT
+                                                          | msr_val);
+        }
 }
 
 static void unexpected_thermal_interrupt(void)
@@ -335,8 +445,26 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
         apic_write(APIC_LVTTHMR, h);
 
         rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
-        wrmsr(MSR_IA32_THERM_INTERRUPT,
-                l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+        if (cpu_has(c, X86_FEATURE_PLN))
+                wrmsr(MSR_IA32_THERM_INTERRUPT,
+                      l | (THERM_INT_LOW_ENABLE
+                        | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h);
+        else
+                wrmsr(MSR_IA32_THERM_INTERRUPT,
+                      l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+
+        if (cpu_has(c, X86_FEATURE_PTS)) {
+                rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+                              l | (PACKAGE_THERM_INT_LOW_ENABLE
+                                | PACKAGE_THERM_INT_HIGH_ENABLE
+                                | PACKAGE_THERM_INT_PLN_ENABLE), h);
+                else
+                        wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+                              l | (PACKAGE_THERM_INT_LOW_ENABLE
+                                | PACKAGE_THERM_INT_HIGH_ENABLE), h);
+        }
 
         smp_thermal_vector = intel_thermal_interrupt;