7 files changed, 49 insertions, 42 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0beba0d1468d..bb83b1c397aa 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -154,6 +154,7 @@
  * CPUID levels like 0x6, 0xA etc
  */
 #define X86_FEATURE_IDA         (7*32+ 0) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT        (7*32+ 1) /* Always Running APIC Timer */
 
 /* Virtualization flags: Linux defined */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 098ec84b8c00..f2870920f246 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -431,6 +431,12 @@ static void __cpuinit setup_APIC_timer(void)
 {
         struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
+        if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
+                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
+                /* Make LAPIC timer preferrable over percpu HPET */
+                lapic_clockevent.rating = 150;
+        }
+
         memcpy(levt, &lapic_clockevent, sizeof(*levt));
         levt->cpumask = cpumask_of(smp_processor_id());
 
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 8220ae69849d..c965e5212714 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 
         static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
                 { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
+                { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
                 { 0, 0, 0, 0 }
         };
 
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 19f6b9d27e83..3e3cd3db7a0c 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -68,6 +68,7 @@ struct acpi_cpufreq_data {
         unsigned int max_freq;
         unsigned int resume;
         unsigned int cpu_feature;
+        u64 saved_aperf, saved_mperf;
 };
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
@@ -152,7 +153,8 @@ struct drv_cmd {
         u32 val;
 };
 
-static long do_drv_read(void *_cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
 {
         struct drv_cmd *cmd = _cmd;
         u32 h;
@@ -169,10 +171,10 @@ static long do_drv_read(void *_cmd)
         default:
                 break;
         }
-        return 0;
 }
 
-static long do_drv_write(void *_cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
         struct drv_cmd *cmd = _cmd;
         u32 lo, hi;
@@ -191,23 +193,18 @@ static long do_drv_write(void *_cmd)
         default:
                 break;
         }
-        return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
         cmd->val = 0;
 
-        work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+        smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-        unsigned int i;
-
-        for_each_cpu(i, cmd->mask) {
-                work_on_cpu(i, do_drv_write, cmd);
-        }
+        smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -241,28 +238,23 @@ static u32 get_cur_val(const struct cpumask *mask)
         return cmd.val;
 }
 
-struct perf_cur {
+struct perf_pair {
         union {
                 struct {
                         u32 lo;
                         u32 hi;
                 } split;
                 u64 whole;
-        } aperf_cur, mperf_cur;
+        } aperf, mperf;
 };
 
-
-static long read_measured_perf_ctrs(void *_cur)
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
 {
-        struct perf_cur *cur = _cur;
-
-        rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi);
-        rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi);
-
-        wrmsr(MSR_IA32_APERF, 0, 0);
-        wrmsr(MSR_IA32_MPERF, 0, 0);
+        struct perf_pair *cur = _cur;
 
-        return 0;
+        rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
+        rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
 }
 
 /*
@@ -281,52 +273,57 @@ static long read_measured_perf_ctrs(void *_cur)
 static unsigned int get_measured_perf(struct cpufreq_policy *policy,
                                       unsigned int cpu)
 {
-        struct perf_cur cur;
+        struct perf_pair readin, cur;
         unsigned int perf_percent;
         unsigned int retval;
 
-        if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur))
+        if (smp_call_function_single(cpu, read_measured_perf_ctrs, &cur, 1))
                 return 0;
 
+        cur.aperf.whole = readin.aperf.whole -
+                                per_cpu(drv_data, cpu)->saved_aperf;
+        cur.mperf.whole = readin.mperf.whole -
+                                per_cpu(drv_data, cpu)->saved_mperf;
+        per_cpu(drv_data, cpu)->saved_aperf = readin.aperf.whole;
+        per_cpu(drv_data, cpu)->saved_mperf = readin.mperf.whole;
+
 #ifdef __i386__
         /*
          * We dont want to do 64 bit divide with 32 bit kernel
          * Get an approximate value. Return failure in case we cannot get
          * an approximate value.
          */
-        if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) {
+        if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) {
                 int shift_count;
                 u32 h;
 
-                h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi);
+                h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi);
                 shift_count = fls(h);
 
-                cur.aperf_cur.whole >>= shift_count;
-                cur.mperf_cur.whole >>= shift_count;
+                cur.aperf.whole >>= shift_count;
+                cur.mperf.whole >>= shift_count;
         }
 
-        if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) {
+        if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) {
                 int shift_count = 7;
-                cur.aperf_cur.split.lo >>= shift_count;
-                cur.mperf_cur.split.lo >>= shift_count;
+                cur.aperf.split.lo >>= shift_count;
+                cur.mperf.split.lo >>= shift_count;
         }
 
-        if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo)
-                perf_percent = (cur.aperf_cur.split.lo * 100) /
-                                cur.mperf_cur.split.lo;
+        if (cur.aperf.split.lo && cur.mperf.split.lo)
+                perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo;
         else
                 perf_percent = 0;
 
 #else
-        if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) {
+        if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) {
                 int shift_count = 7;
-                cur.aperf_cur.whole >>= shift_count;
-                cur.mperf_cur.whole >>= shift_count;
+                cur.aperf.whole >>= shift_count;
+                cur.mperf.whole >>= shift_count;
         }
 
-        if (cur.aperf_cur.whole && cur.mperf_cur.whole)
-                perf_percent = (cur.aperf_cur.whole * 100) /
-                                cur.mperf_cur.whole;
+        if (cur.aperf.whole && cur.mperf.whole)
+                perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole;
         else
                 perf_percent = 0;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index 0bd48e65a0ca..ce2ed3e4aad9 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -33,7 +33,6 @@
 #include <linux/timex.h>
 #include <linux/io.h>
 #include <linux/acpi.h>
-#include <linux/kernel.h>
 
 #include <asm/msr.h>
 #include <acpi/processor.h>
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 70a10ca100f6..18dfa30795c9 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <trace/syscall.h>
+
 #include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index fe9345c967de..23b7c8f017e2 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,7 +21,6 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
-#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -35,6 +34,8 @@
 #include <asm/proto.h>
 #include <asm/ds.h>
 
+#include <trace/syscall.h>
+
 #include "tls.h"
 
 enum x86_regset {