summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/elanfreq.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/gx-suspmod.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/longrun.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/p4-clockmod.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k6.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-ich.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-lib.c1
-rw-r--r--arch/x86/kernel/cpu/cpufreq/speedstep-smi.c1
-rw-r--r--arch/x86/kernel/cpu/intel.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c16
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c5
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c1
-rw-r--r--arch/x86/kernel/cpu/mtrr/if.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event.c267
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c142
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c95
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c18
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c2
23 files changed, 325 insertions, 238 deletions
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 1b1920fa7c8..459168083b7 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,6 +33,7 @@
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
+#include <linux/slab.h>
#include <trace/events/power.h>
#include <linux/acpi.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index 006b278b0d5..c587db472a7 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -20,7 +20,6 @@
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/cpufreq.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
index ac27ec2264d..16e3483be9e 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
@@ -80,6 +80,7 @@
#include <linux/cpufreq.h>
#include <linux/pci.h>
#include <linux/errno.h>
+#include <linux/slab.h>
#include <asm/processor-cyrix.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index da5f70fcb76..e7b559d74c5 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -9,7 +9,6 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/cpufreq.h>
#include <linux/timex.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 86961519372..7b8a8ba67b0 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -25,7 +25,6 @@
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/cpufreq.h>
-#include <linux/slab.h>
#include <linux/cpumask.h>
#include <linux/timex.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index ff36d2979a9..ce7cde713e7 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -30,6 +30,7 @@
#include <linux/sched.h>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
+#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
index cb01dac267d..b3379d6a5c5 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
@@ -13,7 +13,6 @@
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/ioport.h>
-#include <linux/slab.h>
#include <linux/timex.h>
#include <linux/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 8d672ef162c..9b1ff37de46 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -20,6 +20,7 @@
#include <linux/sched.h> /* current */
#include <linux/delay.h>
#include <linux/compiler.h>
+#include <linux/gfp.h>
#include <asm/msr.h>
#include <asm/processor.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 2ce8e0b5cc5..561758e9518 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -23,7 +23,6 @@
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/pci.h>
-#include <linux/slab.h>
#include <linux/sched.h>
#include "speedstep-lib.h"
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
index ad0083abfa2..a94ec6be69f 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
@@ -13,7 +13,6 @@
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
-#include <linux/slab.h>
#include <asm/msr.h>
#include <asm/tsc.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index 04d73c114e4..8abd869baab 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -17,7 +17,6 @@
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
-#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/io.h>
#include <asm/ist.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 879666f4d87..7e1cca13af3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -70,7 +70,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- sched_clock_stable = 1;
+ if (!check_tsc_unstable())
+ sched_clock_stable = 1;
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 73734baa50f..e7dbde7bfed 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -22,6 +22,7 @@
#include <linux/kdebug.h>
#include <linux/cpu.h>
#include <linux/sched.h>
+#include <linux/gfp.h>
#include <asm/mce.h>
#include <asm/apic.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 28cba46bf32..8a6f0afa767 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -26,6 +26,7 @@
#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/types.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/poll.h>
@@ -46,6 +47,13 @@
#include "mce-internal.h"
+static DEFINE_MUTEX(mce_read_mutex);
+
+#define rcu_dereference_check_mce(p) \
+ rcu_dereference_check((p), \
+ rcu_read_lock_sched_held() || \
+ lockdep_is_held(&mce_read_mutex))
+
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
@@ -158,7 +166,7 @@ void mce_log(struct mce *mce)
mce->finished = 0;
wmb();
for (;;) {
- entry = rcu_dereference(mcelog.next);
+ entry = rcu_dereference_check_mce(mcelog.next);
for (;;) {
/*
* When the buffer fills up discard new entries.
@@ -1485,8 +1493,6 @@ static void collect_tscs(void *data)
rdtscll(cpu_tsc[smp_processor_id()]);
}
-static DEFINE_MUTEX(mce_read_mutex);
-
static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
loff_t *off)
{
@@ -1500,7 +1506,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
return -ENOMEM;
mutex_lock(&mce_read_mutex);
- next = rcu_dereference(mcelog.next);
+ next = rcu_dereference_check_mce(mcelog.next);
/* Only supports full reads right now */
if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
@@ -1565,7 +1571,7 @@ timeout:
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference(mcelog.next))
+ if (rcu_dereference_check_mce(mcelog.next))
return POLLIN | POLLRDNORM;
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index cda932ca3ad..224392d8fe8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -21,6 +21,7 @@
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sysfs.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/smp.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 7c785634af2..62b48e40920 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -5,6 +5,7 @@
* Author: Andi Kleen
*/
+#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
@@ -95,7 +96,7 @@ static void cmci_discover(int banks, int boot)
/* Already owned by someone else? */
if (val & CMCI_EN) {
- if (test_and_clear_bit(i, owned) || boot)
+ if (test_and_clear_bit(i, owned) && !boot)
print_update("SHD", &hdr, i);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
continue;
@@ -107,7 +108,7 @@ static void cmci_discover(int banks, int boot)
/* Did the enable bit stick? -- the bank supports CMCI */
if (val & CMCI_EN) {
- if (!test_and_set_bit(i, owned) || boot)
+ if (!test_and_set_bit(i, owned) && !boot)
print_update("CMCI", &hdr, i);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
} else {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9aa5dc76ff4..fd31a441c61 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -6,7 +6,6 @@
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/io.h>
#include <linux/mm.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index e006e56f699..79289632cb2 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -5,6 +5,7 @@
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/string.h>
+#include <linux/slab.h>
#include <linux/init.h>
#define LINE_SIZE 80
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b1fbdeecf6c..db5bdc8addf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -21,6 +21,7 @@
#include <linux/kdebug.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
+#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
@@ -28,6 +29,7 @@
#include <asm/apic.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
+#include <asm/compat.h>
static u64 perf_event_mask __read_mostly;
@@ -73,10 +75,10 @@ struct debug_store {
struct event_constraint {
union {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- u64 idxmsk64[1];
+ u64 idxmsk64;
};
- int code;
- int cmask;
+ u64 code;
+ u64 cmask;
int weight;
};
@@ -103,7 +105,7 @@ struct cpu_hw_events {
};
#define __EVENT_CONSTRAINT(c, n, m, w) {\
- { .idxmsk64[0] = (n) }, \
+ { .idxmsk64 = (n) }, \
.code = (c), \
.cmask = (m), \
.weight = (w), \
@@ -116,7 +118,7 @@ struct cpu_hw_events {
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
#define FIXED_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK)
+ EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
#define EVENT_CONSTRAINT_END \
EVENT_CONSTRAINT(0, 0, 0)
@@ -133,8 +135,8 @@ struct x86_pmu {
int (*handle_irq)(struct pt_regs *);
void (*disable_all)(void);
void (*enable_all)(void);
- void (*enable)(struct hw_perf_event *, int);
- void (*disable)(struct hw_perf_event *, int);
+ void (*enable)(struct perf_event *);
+ void (*disable)(struct perf_event *);
unsigned eventsel;
unsigned perfctr;
u64 (*event_map)(int);
@@ -157,6 +159,11 @@ struct x86_pmu {
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
+
+ int (*cpu_prepare)(int cpu);
+ void (*cpu_starting)(int cpu);
+ void (*cpu_dying)(int cpu);
+ void (*cpu_dead)(int cpu);
};
static struct x86_pmu x86_pmu __read_mostly;
@@ -165,8 +172,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.enabled = 1,
};
-static int x86_perf_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc, int idx);
+static int x86_perf_event_set_period(struct perf_event *event);
/*
* Generalized hw caching related hw_event table, filled
@@ -189,11 +195,12 @@ static u64 __read_mostly hw_cache_event_ids
* Returns the delta events processed.
*/
static u64
-x86_perf_event_update(struct perf_event *event,
- struct hw_perf_event *hwc, int idx)
+x86_perf_event_update(struct perf_event *event)
{
+ struct hw_perf_event *hwc = &event->hw;
int shift = 64 - x86_pmu.event_bits;
u64 prev_raw_count, new_raw_count;
+ int idx = hwc->idx;
s64 delta;
if (idx == X86_PMC_IDX_FIXED_BTS)
@@ -293,7 +300,7 @@ static inline bool bts_available(void)
return x86_pmu.enable_bts != NULL;
}
-static inline void init_debug_store_on_cpu(int cpu)
+static void init_debug_store_on_cpu(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -305,7 +312,7 @@ static inline void init_debug_store_on_cpu(int cpu)
(u32)((u64)(unsigned long)ds >> 32));
}
-static inline void fini_debug_store_on_cpu(int cpu)
+static void fini_debug_store_on_cpu(int cpu)
{
if (!per_cpu(cpu_hw_events, cpu).ds)
return;
@@ -503,6 +510,9 @@ static int __hw_perf_event_init(struct perf_event *event)
*/
if (attr->type == PERF_TYPE_RAW) {
hwc->config |= x86_pmu.raw_event(attr->config);
+ if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
+ perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
return 0;
}
@@ -553,9 +563,9 @@ static void x86_pmu_disable_all(void)
if (!test_bit(idx, cpuc->active_mask))
continue;
rdmsrl(x86_pmu.eventsel + idx, val);
- if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+ if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
continue;
- val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(x86_pmu.eventsel + idx, val);
}
}
@@ -590,7 +600,7 @@ static void x86_pmu_enable_all(void)
continue;
val = event->hw.config;
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val |= ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(x86_pmu.eventsel + idx, val);
}
}
@@ -612,8 +622,8 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
for (i = 0; i < n; i++) {
- constraints[i] =
- x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+ c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+ constraints[i] = c;
}
/*
@@ -635,7 +645,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
if (test_bit(hwc->idx, used_mask))
break;
- set_bit(hwc->idx, used_mask);
+ __set_bit(hwc->idx, used_mask);
if (assign)
assign[i] = hwc->idx;
}
@@ -684,7 +694,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
if (j == X86_PMC_IDX_MAX)
break;
- set_bit(j, used_mask);
+ __set_bit(j, used_mask);
if (assign)
assign[i] = j;
@@ -777,6 +787,7 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
hwc->last_tag == cpuc->tags[i];
}
+static int x86_pmu_start(struct perf_event *event);
static void x86_pmu_stop(struct perf_event *event);
void hw_perf_enable(void)
@@ -793,6 +804,7 @@ void hw_perf_enable(void)
return;
if (cpuc->n_added) {
+ int n_running = cpuc->n_events - cpuc->n_added;
/*
* apply assignment obtained either from
* hw_perf_group_sched_in() or x86_pmu_enable()
@@ -800,8 +812,7 @@ void hw_perf_enable(void)
* step1: save events moving to new counters
* step2: reprogram moved events into new counters
*/
- for (i = 0; i < cpuc->n_events; i++) {
-
+ for (i = 0; i < n_running; i++) {
event = cpuc->event_list[i];
hwc = &event->hw;
@@ -816,29 +827,18 @@ void hw_perf_enable(void)
continue;
x86_pmu_stop(event);
-
- hwc->idx = -1;
}
for (i = 0; i < cpuc->n_events; i++) {
-
event = cpuc->event_list[i];
hwc = &event->hw;
- if (hwc->idx == -1) {
+ if (!match_prev_assignment(hwc, cpuc, i))
x86_assign_hw_event(event, cpuc, i);
- x86_perf_event_set_period(event, hwc, hwc->idx);
- }
- /*
- * need to mark as active because x86_pmu_disable()
- * clear active_mask and events[] yet it preserves
- * idx
- */
- set_bit(hwc->idx, cpuc->active_mask);
- cpuc->events[hwc->idx] = event;
+ else if (i < n_running)
+ continue;
- x86_pmu.enable(hwc, hwc->idx);
- perf_event_update_userpage(event);
+ x86_pmu_start(event);
}
cpuc->n_added = 0;
perf_events_lapic_init();
@@ -850,15 +850,16 @@ void hw_perf_enable(void)
x86_pmu.enable_all();
}
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
{
- (void)checking_wrmsrl(hwc->config_base + idx,
- hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
+ (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
}
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct perf_event *event)
{
- (void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
+ struct hw_perf_event *hwc = &event->hw;
+ (void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -868,12 +869,12 @@ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
* To be called with the event disabled in hw:
*/
static int
-x86_perf_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc, int idx)
+x86_perf_event_set_period(struct perf_event *event)
{
+ struct hw_perf_event *hwc = &event->hw;
s64 left = atomic64_read(&hwc->period_left);
s64 period = hwc->sample_period;
- int err, ret = 0;
+ int err, ret = 0, idx = hwc->idx;
if (idx == X86_PMC_IDX_FIXED_BTS)
return 0;
@@ -919,11 +920,11 @@ x86_perf_event_set_period(struct perf_event *event,
return ret;
}
-static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (cpuc->enabled)
- __x86_pmu_enable_event(hwc, idx);
+ __x86_pmu_enable_event(&event->hw);
}
/*
@@ -959,34 +960,32 @@ static int x86_pmu_enable(struct perf_event *event)
memcpy(cpuc->assign, assign, n*sizeof(int));
cpuc->n_events = n;
- cpuc->n_added = n - n0;
+ cpuc->n_added += n - n0;
return 0;
}
static int x86_pmu_start(struct perf_event *event)
{
- struct hw_perf_event *hwc = &event->hw;
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ int idx = event->hw.idx;
- if (hwc->idx == -1)
+ if (idx == -1)
return -EAGAIN;
- x86_perf_event_set_period(event, hwc, hwc->idx);
- x86_pmu.enable(hwc, hwc->idx);
+ x86_perf_event_set_period(event);
+ cpuc->events[idx] = event;
+ __set_bit(idx, cpuc->active_mask);
+ x86_pmu.enable(event);
+ perf_event_update_userpage(event);
return 0;
}
static void x86_pmu_unthrottle(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct hw_perf_event *hwc = &event->hw;
-
- if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX ||
- cpuc->events[hwc->idx] != event))
- return;
-
- x86_pmu.enable(hwc, hwc->idx);
+ int ret = x86_pmu_start(event);
+ WARN_ON_ONCE(ret);
}
void perf_event_print_debug(void)
@@ -1046,18 +1045,16 @@ static void x86_pmu_stop(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
- /*
- * Must be done before we disable, otherwise the nmi handler
- * could reenable again:
- */
- clear_bit(idx, cpuc->active_mask);
- x86_pmu.disable(hwc, idx);
+ if (!__test_and_clear_bit(idx, cpuc->active_mask))
+ return;
+
+ x86_pmu.disable(event);
/*
* Drain the remaining delta count out of a event
* that we are disabling:
*/
- x86_perf_event_update(event, hwc, idx);
+ x86_perf_event_update(event);
cpuc->events[idx] = NULL;
}
@@ -1094,8 +1091,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
int idx, handled = 0;
u64 val;
- data.addr = 0;
- data.raw = NULL;
+ perf_sample_data_init(&data, 0);
cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1106,7 +1102,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
event = cpuc->events[idx];
hwc = &event->hw;
- val = x86_perf_event_update(event, hwc, idx);
+ val = x86_perf_event_update(event);
if (val & (1ULL << (x86_pmu.event_bits - 1)))
continue;
@@ -1116,11 +1112,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
handled = 1;
data.period = event->hw.last_period;
- if (!x86_perf_event_set_period(event, hwc, idx))
+ if (!x86_perf_event_set_period(event))
continue;
if (perf_event_overflow(event, 1, &data, regs))
- x86_pmu.disable(hwc, idx);
+ x86_pmu_stop(event);
}
if (handled)
@@ -1307,7 +1303,7 @@ int hw_perf_group_sched_in(struct perf_event *leader,
memcpy(cpuc->assign, assign, n0*sizeof(int));
cpuc->n_events = n0;
- cpuc->n_added = n1;
+ cpuc->n_added += n1;
ctx->nr_active += n1;
/*
@@ -1335,6 +1331,41 @@ undo:
#include "perf_event_p6.c"
#include "perf_event_intel.c"
+static int __cpuinit
+x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+ int ret = NOTIFY_OK;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ if (x86_pmu.cpu_prepare)
+ ret = x86_pmu.cpu_prepare(cpu);
+ break;
+
+ case CPU_STARTING:
+ if (x86_pmu.cpu_starting)
+ x86_pmu.cpu_starting(cpu);
+ break;
+
+ case CPU_DYING:
+ if (x86_pmu.cpu_dying)
+ x86_pmu.cpu_dying(cpu);
+ break;
+
+ case CPU_UP_CANCELED:
+ case CPU_DEAD:
+ if (x86_pmu.cpu_dead)
+ x86_pmu.cpu_dead(cpu);
+ break;
+
+ default:
+ break;
+ }
+
+ return ret;
+}
+
static void __init pmu_check_apic(void)
{
if (cpu_has_apic)
@@ -1347,6 +1378,7 @@ static void __init pmu_check_apic(void)
void __init init_hw_perf_events(void)
{
+ struct event_constraint *c;
int err;
pr_info("Performance Events: ");
@@ -1395,6 +1427,16 @@ void __init init_hw_perf_events(void)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
0, x86_pmu.num_events);
+ if (x86_pmu.event_constraints) {
+ for_each_event_constraint(c, x86_pmu.event_constraints) {
+ if (c->cmask != INTEL_ARCH_FIXED_MASK)
+ continue;
+
+ c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
+ c->weight += x86_pmu.num_events;
+ }
+ }
+
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.event_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_events);
@@ -1402,11 +1444,13 @@ void __init init_hw_perf_events(void)
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed);
pr_info("... event mask: %016Lx\n", perf_event_mask);
+
+ perf_cpu_notifier(x86_pmu_notifier);
}
static inline void x86_pmu_read(struct perf_event *event)
{
- x86_perf_event_update(event, &event->hw, event->hw.idx);
+ x86_perf_event_update(event);
}
static const struct pmu pmu = {
@@ -1588,14 +1632,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
return len;
}
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
- unsigned long bytes;
+ /* 32-bit process in 64-bit kernel. */
+ struct stack_frame_ia32 frame;
+ const void __user *fp;
- bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+ if (!test_thread_flag(TIF_IA32))
+ return 0;
- return bytes == sizeof(*frame);
+ fp = compat_ptr(regs->bp);
+ while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ unsigned long bytes;
+ frame.next_frame = 0;
+ frame.return_address = 0;
+
+ bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (bytes != sizeof(frame))
+ break;
+
+ if (fp < compat_ptr(regs->sp))
+ break;
+
+ callchain_store(entry, frame.return_address);
+ fp = compat_ptr(frame.next_frame);
+ }
+ return 1;
+}
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+ return 0;
}
+#endif
static void
perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1611,11 +1683,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
callchain_store(entry, PERF_CONTEXT_USER);
callchain_store(entry, regs->ip);
+ if (perf_callchain_user32(regs, entry))
+ return;
+
while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
- if (!copy_stack_frame(fp, &frame))
+ bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (bytes != sizeof(frame))
break;
if ((unsigned long)fp < regs->sp)
@@ -1662,28 +1739,14 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
return entry;
}
-void hw_perf_event_setup_online(int cpu)
-{
- init_debug_store_on_cpu(cpu);
-
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- amd_pmu_cpu_online(cpu);
- break;
- default:
- return;
- }
-}
-
-void hw_perf_event_setup_offline(int cpu)
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
{
- init_debug_store_on_cpu(cpu);
-
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- amd_pmu_cpu_offline(cpu);
- break;
- default:
- return;
- }
+ regs->ip = ip;
+ /*
+ * perf_arch_fetch_caller_regs adds another call, we need to increment
+ * the skip level
+ */
+ regs->bp = rewind_frame_pointer(skip + 1);
+ regs->cs = __KERNEL_CS;
+ local_save_flags(regs->flags);
}
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 8f3dbfda3c4..db6f7d4056e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
return (hwc->config & 0xe0) == 0xe0;
}
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+ struct amd_nb *nb = cpuc->amd_nb;
+
+ return nb && nb->nb_id != -1;
+}
+
static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
/*
* only care about NB events
*/
- if (!(nb && amd_is_nb_event(hwc)))
+ if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
return;
/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
/*
* if not NB event or no NB, then no constraints
*/
- if (!(nb && amd_is_nb_event(hwc)))
+ if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
return &unconstrained;
/*
@@ -271,28 +278,6 @@ done:
return &emptyconstraint;
}
-static __initconst struct x86_pmu amd_pmu = {
- .name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
- .enable_all = x86_pmu_enable_all,
- .enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
- .eventsel = MSR_K7_EVNTSEL0,
- .perfctr = MSR_K7_PERFCTR0,
- .event_map = amd_pmu_event_map,
- .raw_event = amd_pmu_raw_event,
- .max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_events = 4,
- .event_bits = 48,
- .event_mask = (1ULL << 48) - 1,
- .apic = 1,
- /* use highest bit to detect overflow */
- .max_period = (1ULL << 47) - 1,
- .get_event_constraints = amd_get_event_constraints,
- .put_event_constraints = amd_put_event_constraints
-};
-
static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
{
struct amd_nb *nb;
@@ -309,57 +294,61 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
* initialize all possible NB constraints
*/
for (i = 0; i < x86_pmu.num_events; i++) {
- set_bit(i, nb->event_constraints[i].idxmsk);
+ __set_bit(i, nb->event_constraints[i].idxmsk);
nb->event_constraints[i].weight = 1;
}
return nb;
}
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
{
- struct cpu_hw_events *cpu1, *cpu2;
- struct amd_nb *nb = NULL;
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+ WARN_ON_ONCE(cpuc->amd_nb);
+
+ if (boot_cpu_data.x86_max_cores < 2)
+ return NOTIFY_OK;
+
+ cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+ if (!cpuc->amd_nb)
+ return NOTIFY_BAD;
+
+ return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
+{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ struct amd_nb *nb;
int i, nb_id;
if (boot_cpu_data.x86_max_cores < 2)
return;
- /*
- * function may be called too early in the
- * boot process, in which case nb_id is bogus
- */
nb_id = amd_get_nb_id(cpu);
- if (nb_id == BAD_APICID)
- return;
-
- cpu1 = &per_cpu(cpu_hw_events, cpu);
- cpu1->amd_nb = NULL;
+ WARN_ON_ONCE(nb_id == BAD_APICID);
raw_spin_lock(&amd_nb_lock);
for_each_online_cpu(i) {
- cpu2 = &per_cpu(cpu_hw_events, i);
- nb = cpu2->amd_nb;
- if (!nb)
+ nb = per_cpu(cpu_hw_events, i).amd_nb;
+ if (WARN_ON_ONCE(!nb))
continue;
- if (nb->nb_id == nb_id)
- goto found;
- }
- nb = amd_alloc_nb(cpu, nb_id);
- if (!nb) {
- pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
- raw_spin_unlock(&amd_nb_lock);
- return;
+ if (nb->nb_id == nb_id) {
+ kfree(cpuc->amd_nb);
+ cpuc->amd_nb = nb;
+ break;
+ }
}
-found:
- nb->refcnt++;
- cpu1->amd_nb = nb;
+
+ cpuc->amd_nb->nb_id = nb_id;
+ cpuc->amd_nb->refcnt++;
raw_spin_unlock(&amd_nb_lock);
}
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
{
struct cpu_hw_events *cpuhw;
@@ -370,14 +359,44 @@ static void amd_pmu_cpu_offline(int cpu)
raw_spin_lock(&amd_nb_lock);
- if (--cpuhw->amd_nb->refcnt == 0)
- kfree(cpuhw->amd_nb);
+ if (cpuhw->amd_nb) {
+ struct amd_nb *nb = cpuhw->amd_nb;
+
+ if (nb->nb_id == -1 || --nb->refcnt == 0)
+ kfree(nb);
- cpuhw->amd_nb = NULL;
+ cpuhw->amd_nb = NULL;
+ }
raw_spin_unlock(&amd_nb_lock);
}
+static __initconst struct x86_pmu amd_pmu = {
+ .name = "AMD",
+ .handle_irq = x86_pmu_handle_irq,
+ .disable_all = x86_pmu_disable_all,
+ .enable_all = x86_pmu_enable_all,
+ .enable = x86_pmu_enable_event,
+ .disable = x86_pmu_disable_event,
+ .eventsel = MSR_K7_EVNTSEL0,
+ .perfctr = MSR_K7_PERFCTR0,
+ .event_map = amd_pmu_event_map,
+ .raw_event = amd_pmu_raw_event,
+ .max_events = ARRAY_SIZE(amd_perfmon_event_map),
+ .num_events = 4,
+ .event_bits = 48,
+ .event_mask = (1ULL << 48) - 1,
+ .apic = 1,
+ /* use highest bit to detect overflow */
+ .max_period = (1ULL << 47) - 1,
+ .get_event_constraints = amd_get_event_constraints,
+ .put_event_constraints = amd_put_event_constraints,
+
+ .cpu_prepare = amd_pmu_cpu_prepare,
+ .cpu_starting = amd_pmu_cpu_starting,
+ .cpu_dead = amd_pmu_cpu_dead,
+};
+
static __init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
@@ -390,11 +409,6 @@ static __init int amd_pmu_init(void)
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
- /*
- * explicitly initialize the boot cpu, other cpus will get
- * the cpu hotplug callbacks from smp_init()
- */
- amd_pmu_cpu_online(smp_processor_id());
return 0;
}
@@ -405,12 +419,4 @@ static int amd_pmu_init(void)
return 0;
}
-static void amd_pmu_cpu_online(int cpu)
-{
-}
-
-static void amd_pmu_cpu_offline(int cpu)
-{
-}
-
#endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 977e7544738..9c794ac8783 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,7 +1,7 @@
#ifdef CONFIG_CPU_SUP_INTEL
/*
- * Intel PerfMon v3. Used on Core2 and later.
+ * Intel PerfMon, used on Core and later.
*/
static const u64 intel_perfmon_event_map[] =
{
@@ -27,8 +27,14 @@ static struct event_constraint intel_core_event_constraints[] =
static struct event_constraint intel_core2_event_constraints[] =
{
- FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
- FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /*
+ * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event
+ * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed
+ * ratio between these counters.
+ */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -37,14 +43,16 @@ static struct event_constraint intel_core2_event_constraints[] =
INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* ITLB_MISS_RETIRED (T30-9) */
INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_nehalem_event_constraints[] =
{
- FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
- FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
@@ -58,8 +66,9 @@ static struct event_constraint intel_nehalem_event_constraints[] =
static struct event_constraint intel_westmere_event_constraints[] =
{
- FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
- FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
@@ -68,8 +77,9 @@ static struct event_constraint intel_westmere_event_constraints[] =
static struct event_constraint intel_gen_event_constraints[] =
{
- FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
- FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
EVENT_CONSTRAINT_END
};
@@ -538,9 +548,9 @@ static inline void intel_pmu_ack_status(u64 ack)
}
static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
- int idx = __idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - X86_PMC_IDX_FIXED;
u64 ctrl_val, mask;
mask = 0xfULL << (idx * 4);
@@ -580,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void)
ds->bts_index = ds->bts_buffer_base;
+ perf_sample_data_init(&data, 0);
data.period = event->hw.last_period;
- data.addr = 0;
- data.raw = NULL;
regs.ip = 0;
/*
@@ -612,26 +621,28 @@ static void intel_pmu_drain_bts_buffer(void)
}
static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+intel_pmu_disable_event(struct perf_event *event)
{
- if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
intel_pmu_drain_bts_buffer();
return;
}
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_disable_fixed(hwc, idx);
+ intel_pmu_disable_fixed(hwc);
return;
}
- x86_pmu_disable_event(hwc, idx);
+ x86_pmu_disable_event(event);
}
static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
- int idx = __idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - X86_PMC_IDX_FIXED;
u64 ctrl_val, bits, mask;
int err;
@@ -661,9 +672,11 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
err = checking_wrmsrl(hwc->config_base, ctrl_val);
}
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void intel_pmu_enable_event(struct perf_event *event)
{
- if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
if (!__get_cpu_var(cpu_hw_events).enabled)
return;
@@ -672,11 +685,11 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
}
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_enable_fixed(hwc, idx);
+ intel_pmu_enable_fixed(hwc);
return;
}
- __x86_pmu_enable_event(hwc, idx);
+ __x86_pmu_enable_event(hwc);
}
/*
@@ -685,14 +698,8 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
*/
static int intel_pmu_save_and_restart(struct perf_event *event)
{
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
- int ret;
-
- x86_perf_event_update(event, hwc, idx);
- ret = x86_perf_event_set_period(event, hwc, idx);
-
- return ret;
+ x86_perf_event_update(event);
+ return x86_perf_event_set_period(event);
}
static void intel_pmu_reset(void)
@@ -732,16 +739,15 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
int bit, loops;
u64 ack, status;
- data.addr = 0;
- data.raw = NULL;
+ perf_sample_data_init(&data, 0);
cpuc = &__get_cpu_var(cpu_hw_events);
- perf_disable();
+ intel_pmu_disable_all();
intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
if (!status) {
- perf_enable();
+ intel_pmu_enable_all();
return 0;
}
@@ -751,8 +757,7 @@ again:
WARN_ONCE(1, "perfevents: irq loop stuck!\n");
perf_event_print_debug();
intel_pmu_reset();
- perf_enable();
- return 1;
+ goto done;
}
inc_irq_stat(apic_perf_irqs);
@@ -760,7 +765,6 @@ again:
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
- clear_bit(bit, (unsigned long *) &status);
if (!test_bit(bit, cpuc->active_mask))
continue;
@@ -770,7 +774,7 @@ again:
data.period = event->hw.last_period;
if (perf_event_overflow(event, 1, &data, regs))
- intel_pmu_disable_event(&event->hw, bit);
+ x86_pmu_stop(event);
}
intel_pmu_ack_status(ack);
@@ -782,8 +786,8 @@ again:
if (status)
goto again;
- perf_enable();
-
+done:
+ intel_pmu_enable_all();
return 1;
}
@@ -862,7 +866,10 @@ static __initconst struct x86_pmu intel_pmu = {
.max_period = (1ULL << 31) - 1,
.enable_bts = intel_pmu_enable_bts,
.disable_bts = intel_pmu_disable_bts,
- .get_event_constraints = intel_get_event_constraints
+ .get_event_constraints = intel_get_event_constraints,
+
+ .cpu_starting = init_debug_store_on_cpu,
+ .cpu_dying = fini_debug_store_on_cpu,
};
static __init int intel_pmu_init(void)
@@ -929,13 +936,14 @@ static __init int intel_pmu_init(void)
case 26: /* 45 nm nehalem, "Bloomfield" */
case 30: /* 45 nm nehalem, "Lynnfield" */
+ case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
x86_pmu.event_constraints = intel_nehalem_event_constraints;
pr_cont("Nehalem/Corei7 events, ");
break;
- case 28:
+ case 28: /* Atom */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -951,6 +959,7 @@ static __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_westmere_event_constraints;
pr_cont("Westmere events, ");
break;
+
default:
/*
* default constraints for v2 and up
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 1ca5ba078af..a330485d14d 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -62,7 +62,7 @@ static void p6_pmu_disable_all(void)
/* p6 only has one enable register */
rdmsrl(MSR_P6_EVNTSEL0, val);
- val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(MSR_P6_EVNTSEL0, val);
}
@@ -72,32 +72,34 @@ static void p6_pmu_enable_all(void)
/* p6 only has one enable register */
rdmsrl(MSR_P6_EVNTSEL0, val);
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val |= ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(MSR_P6_EVNTSEL0, val);
}
static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+p6_pmu_disable_event(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
u64 val = P6_NOP_EVENT;
if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + idx, val);
+ (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
}
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void p6_pmu_enable_event(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
u64 val;
val = hwc->config;
if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + idx, val);
+ (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
}
static __initconst struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 74f4e85a572..fb329e9f849 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -680,7 +680,7 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
cpu_nmi_set_wd_enabled();
apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsr(evntsel_msr, evntsel, 0);
intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
return 1;