Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (35 commits)
  perf: Fix unexported generic perf_arch_fetch_caller_regs
  perf record: Don't try to find buildids in a zero sized file
  perf: export perf_trace_regs and perf_arch_fetch_caller_regs
  perf, x86: Fix hw_perf_enable() event assignment
  perf, ppc: Fix compile error due to new cpu notifiers
  perf: Make the install relative to DESTDIR if specified
  kprobes: Calculate the index correctly when freeing the out-of-line execution slot
  perf tools: Fix sparse CPU numbering related bugs
  perf_event: Fix oops triggered by cpu offline/online
  perf: Drop the obsolete profile naming for trace events
  perf: Take a hot regs snapshot for trace events
  perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot
  perf/x86-64: Use frame pointer to walk on irq and process stacks
  lockdep: Move lock events under lockdep recursion protection
  perf report: Print the map table just after samples for which no map was found
  perf report: Add multiple event support
  perf session: Change perf_session post processing functions to take histogram tree
  perf session: Add storage for seperating event types in report
  perf session: Change add_hist_entry to take the tree root instead of session
  perf record: Add ID and to recorded event data when recording multiple events
  ...

39 files changed, 741 insertions, 398 deletions

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 5120bd44f69a..08460a2e9f41 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1287,7 +1287,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
                 irq_exit();
 }
 
-void hw_perf_event_setup(int cpu)
+static void power_pmu_setup(int cpu)
 {
         struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
@@ -1297,6 +1297,23 @@ void hw_perf_event_setup(int cpu)
         cpuhw->mmcr[0] = MMCR0_FC;
 }
 
+static int __cpuinit
+power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (long)hcpu;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                power_pmu_setup(cpu);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
 int register_power_pmu(struct power_pmu *pmu)
 {
         if (ppmu)
@@ -1314,5 +1331,7 @@ int register_power_pmu(struct power_pmu *pmu)
                 freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+        perf_cpu_notifier(power_pmu_notifier);
+
         return 0;
 }
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7ff0943e7a08..9f253e9cce01 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -275,13 +275,30 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
         return &pmu;
 }
 
-void hw_perf_event_setup(int cpu)
+static void sh_pmu_setup(int cpu)
 {
         struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
         memset(cpuhw, 0, sizeof(struct cpu_hw_events));
 }
 
+static int __cpuinit
+sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (long)hcpu;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                sh_pmu_setup(cpu);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
 void hw_perf_enable(void)
 {
         if (!sh_pmu_initialized())
@@ -308,5 +325,6 @@ int register_sh_pmu(struct sh_pmu *pmu)
 
         WARN_ON(pmu->num_events > MAX_HWEVENTS);
 
+        perf_cpu_notifier(sh_pmu_notifier);
         return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 42aafd11e170..60398a0d947c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -133,8 +133,8 @@ 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 +157,11 @@ struct x86_pmu {
         void            (*put_event_constraints)(struct cpu_hw_events *cpuc,
                                                  struct perf_event *event);
         struct event_constraint *event_constraints;
+
+        void            (*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 +170,7 @@ 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 +193,12 @@ 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 +298,7 @@ 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 +310,7 @@ 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;
@@ -638,7 +643,7 @@ 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;
         }
@@ -687,7 +692,7 @@ 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;
@@ -780,6 +785,7 @@ 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)
@@ -796,6 +802,7 @@ 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()
@@ -803,8 +810,7 @@ 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;
 
@@ -819,29 +825,18 @@ 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();
@@ -853,15 +848,16 @@ 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,
+        (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);
@@ -871,12 +867,12 @@ 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;
@@ -922,11 +918,11 @@ 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);
 }
 
 /*
@@ -962,34 +958,32 @@ 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)
@@ -1049,18 +1043,16 @@ 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;
 }
@@ -1108,7 +1100,7 @@ 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;
 
@@ -1118,11 +1110,11 @@ 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)
@@ -1309,7 +1301,7 @@ 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;
 
         /*
@@ -1337,6 +1329,39 @@ 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;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                if (x86_pmu.cpu_prepare)
+                        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_DEAD:
+                if (x86_pmu.cpu_dead)
+                        x86_pmu.cpu_dead(cpu);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
 static void __init pmu_check_apic(void)
 {
         if (cpu_has_apic)
@@ -1415,11 +1440,13 @@ 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 = {
@@ -1675,28 +1702,16 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return entry;
 }
 
-void hw_perf_event_setup_online(int cpu)
+#ifdef CONFIG_EVENT_TRACING
+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_online(cpu);
-                break;
-        default:
-                return;
-        }
-}
-
-void hw_perf_event_setup_offline(int cpu)
-{
-        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);
 }
+#endif
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 8f3dbfda3c4f..573458f1caf2 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -271,28 +271,6 @@ 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;
@@ -309,7 +287,7 @@ 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;
@@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu)
         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_online,
+        .cpu_dead               = amd_pmu_cpu_offline,
+};
+
 static __init int amd_pmu_init(void)
 {
         /* Performance-monitoring supported from K7 and later: */
@@ -390,11 +393,6 @@ 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 +403,4 @@ 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 44b60c852107..84bfde64a337 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -548,9 +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);
@@ -621,26 +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;
 
@@ -670,9 +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;
 
@@ -681,11 +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);
 }
 
 /*
@@ -694,14 +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)
@@ -745,11 +743,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
         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;
         }
 
@@ -759,8 +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);
@@ -768,7 +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;
 
@@ -778,7 +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);
@@ -790,8 +786,8 @@ again:
         if (status)
                 goto again;
 
-        perf_enable();
-
+done:
+        intel_pmu_enable_all();
         return 1;
 }
 
@@ -870,7 +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)
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a4e67b99d91c..a330485d14da 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -77,27 +77,29 @@ static void p6_pmu_enable_all(void)
 }
 
 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_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_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/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 4fd1420faffa..29e5f7c845b2 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,4 +29,19 @@ struct stack_frame {
         struct stack_frame *next_frame;
         unsigned long return_address;
 };
+
+static inline unsigned long rewind_frame_pointer(int n)
+{
+        struct stack_frame *frame;
+
+        get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+        while (n--)
+                frame = frame->next_frame;
 #endif
+
+        return (unsigned long)frame;
+}
+
+#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d5e2a2ebb627..272c9f1f05f3 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -208,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                         if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
                                 if (ops->stack(data, "IRQ") < 0)
                                         break;
-                                bp = print_context_stack(tinfo, stack, bp,
+                                bp = ops->walk_stack(tinfo, stack, bp,
                                         ops, data, irq_stack_end, &graph);
                                 /*
                                  * We link to the next stack (which would be
@@ -229,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
         /*
          * This handles the process stack:
          */
-        bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+        bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
         put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6b7c444ab8f6..c0f4b364c711 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -131,12 +131,12 @@ struct ftrace_event_call {
         void                    *mod;
         void                    *data;
 
-        int                     profile_count;
-        int                     (*profile_enable)(struct ftrace_event_call *);
-        void                    (*profile_disable)(struct ftrace_event_call *);
+        int                     perf_refcount;
+        int                     (*perf_event_enable)(struct ftrace_event_call *);
+        void                    (*perf_event_disable)(struct ftrace_event_call *);
 };
 
-#define FTRACE_MAX_PROFILE_SIZE 2048
+#define PERF_MAX_TRACE_SIZE     2048
 
 #define MAX_FILTER_PRED         32
 #define MAX_FILTER_STR_VAL      256     /* Should handle KSYM_SYMBOL_LEN */
@@ -187,22 +187,25 @@ do {									\
 
 #ifdef CONFIG_PERF_EVENTS
 struct perf_event;
-extern int ftrace_profile_enable(int event_id);
-extern void ftrace_profile_disable(int event_id);
+
+DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+
+extern int perf_trace_enable(int event_id);
+extern void perf_trace_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
                                      char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *
-ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
                          unsigned long *irq_flags);
 
 static inline void
-ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-                       u64 count, unsigned long irq_flags)
+perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+                       u64 count, unsigned long irq_flags, struct pt_regs *regs)
 {
         struct trace_entry *entry = raw_data;
 
-        perf_tp_event(entry->type, addr, count, raw_data, size);
+        perf_tp_event(entry->type, addr, count, raw_data, size, regs);
         perf_swevent_put_recursion_context(rctx);
         local_irq_restore(irq_flags);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6f8cd7da1a01..95477038a72a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -452,6 +452,8 @@ enum perf_callchain_context {
 #include <linux/fs.h>
 #include <linux/pid_namespace.h>
 #include <linux/workqueue.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
 #include <asm/atomic.h>
 
 #define PERF_MAX_STACK_DEPTH            255
@@ -847,6 +849,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
                 __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+{
+        unsigned long ip;
+
+        memset(regs, 0, sizeof(*regs));
+
+        switch (skip) {
+        case 1 :
+                ip = CALLER_ADDR0;
+                break;
+        case 2 :
+                ip = CALLER_ADDR1;
+                break;
+        case 3 :
+                ip = CALLER_ADDR2;
+                break;
+        case 4:
+                ip = CALLER_ADDR3;
+                break;
+        /* No need to support further for now */
+        default:
+                ip = 0;
+        }
+
+        return perf_arch_fetch_caller_regs(regs, ip, skip);
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
@@ -880,7 +920,8 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+                          int entry_size, struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -936,5 +977,21 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_output_put(handle, x) \
         perf_output_copy((handle), &(x), sizeof(x))
 
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+#define perf_cpu_notifier(fn)                                   \
+do {                                                            \
+        static struct notifier_block fn##_nb __cpuinitdata =    \
+                { .notifier_call = fn, .priority = 20 };        \
+        fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,             \
+                (void *)(unsigned long)smp_processor_id());     \
+        fn(&fn##_nb, (unsigned long)CPU_STARTING,               \
+                (void *)(unsigned long)smp_processor_id());     \
+        fn(&fn##_nb, (unsigned long)CPU_ONLINE,                 \
+                (void *)(unsigned long)smp_processor_id());     \
+        register_cpu_notifier(&fn##_nb);                        \
+} while (0)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 44f2ad0e8825..f994ae58a002 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -105,18 +105,18 @@ struct perf_event_attr;
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)                                    \
-        .profile_enable = prof_sysenter_enable,                                \
-        .profile_disable = prof_sysenter_disable,
+#define TRACE_SYS_ENTER_PERF_INIT(sname)                                       \
+        .perf_event_enable = perf_sysenter_enable,                             \
+        .perf_event_disable = perf_sysenter_disable,
 
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)                                     \
-        .profile_enable = prof_sysexit_enable,                                 \
-        .profile_disable = prof_sysexit_disable,
+#define TRACE_SYS_EXIT_PERF_INIT(sname)                                        \
+        .perf_event_enable = perf_sysexit_enable,                              \
+        .perf_event_disable = perf_sysexit_disable,
 #else
-#define TRACE_SYS_ENTER_PROFILE(sname)
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
-#define TRACE_SYS_EXIT_PROFILE(sname)
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#define TRACE_SYS_ENTER_PERF(sname)
+#define TRACE_SYS_ENTER_PERF_INIT(sname)
+#define TRACE_SYS_EXIT_PERF(sname)
+#define TRACE_SYS_EXIT_PERF_INIT(sname)
 #endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -153,7 +153,7 @@ struct perf_event_attr;
                 .regfunc                = reg_event_syscall_enter,      \
                 .unregfunc              = unreg_event_syscall_enter,    \
                 .data                   = (void *)&__syscall_meta_##sname,\
-                TRACE_SYS_ENTER_PROFILE_INIT(sname)                     \
+                TRACE_SYS_ENTER_PERF_INIT(sname)                        \
         }
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)                                 \
@@ -175,7 +175,7 @@ struct perf_event_attr;
                 .regfunc                = reg_event_syscall_exit,       \
                 .unregfunc              = unreg_event_syscall_exit,     \
                 .data                   = (void *)&__syscall_meta_##sname,\
-                TRACE_SYS_EXIT_PROFILE_INIT(sname)                      \
+                TRACE_SYS_EXIT_PERF_INIT(sname)                 \
         }
 
 #define SYSCALL_METADATA(sname, nb)                             \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 601ad7744247..ea6f9d4a20e9 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -401,18 +401,18 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args)                       \
                                                                         \
-static void ftrace_profile_##name(proto);                               \
+static void perf_trace_##name(proto);                                   \
                                                                         \
 static notrace int                                                      \
-ftrace_profile_enable_##name(struct ftrace_event_call *unused)          \
+perf_trace_enable_##name(struct ftrace_event_call *unused)              \
 {                                                                       \
-        return register_trace_##name(ftrace_profile_##name);            \
+        return register_trace_##name(perf_trace_##name);                \
 }                                                                       \
                                                                         \
 static notrace void                                                     \
-ftrace_profile_disable_##name(struct ftrace_event_call *unused)         \
+perf_trace_disable_##name(struct ftrace_event_call *unused)             \
 {                                                                       \
-        unregister_trace_##name(ftrace_profile_##name);                 \
+        unregister_trace_##name(perf_trace_##name);                     \
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -507,12 +507,12 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define _TRACE_PROFILE_INIT(call)                                       \
-        .profile_enable = ftrace_profile_enable_##call,                 \
-        .profile_disable = ftrace_profile_disable_##call,
+#define _TRACE_PERF_INIT(call)                                          \
+        .perf_event_enable = perf_trace_enable_##call,                  \
+        .perf_event_disable = perf_trace_disable_##call,
 
 #else
-#define _TRACE_PROFILE_INIT(call)
+#define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
@@ -638,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .unregfunc              = ftrace_raw_unreg_event_##call,        \
         .print_fmt              = print_fmt_##template,                 \
         .define_fields          = ftrace_define_fields_##template,      \
-        _TRACE_PROFILE_INIT(call)                                       \
+        _TRACE_PERF_INIT(call)                                  \
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -657,18 +657,18 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .unregfunc              = ftrace_raw_unreg_event_##call,        \
         .print_fmt              = print_fmt_##call,                     \
         .define_fields          = ftrace_define_fields_##template,      \
-        _TRACE_PROFILE_INIT(call)                                       \
+        _TRACE_PERF_INIT(call)                                  \
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Define the insertion callback to profile events
+ * Define the insertion callback to perf events
  *
  * The job is very similar to ftrace_raw_event_<call> except that we don't
  * insert in the ring buffer but in a perf counter.
  *
- * static void ftrace_profile_<call>(proto)
+ * static void ftrace_perf_<call>(proto)
  * {
  *      struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *      struct ftrace_event_call *event_call = &event_<call>;
@@ -757,13 +757,14 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)  \
 static notrace void                                                     \
-ftrace_profile_templ_##call(struct ftrace_event_call *event_call,       \
+perf_trace_templ_##call(struct ftrace_event_call *event_call,           \
                             proto)                                      \
 {                                                                       \
         struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
         struct ftrace_raw_##call *entry;                                \
         u64 __addr = 0, __count = 1;                                    \
         unsigned long irq_flags;                                        \
+        struct pt_regs *__regs;                                         \
         int __entry_size;                                               \
         int __data_size;                                                \
         int rctx;                                                       \
@@ -773,10 +774,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
                              sizeof(u64));                              \
         __entry_size -= sizeof(u32);                                    \
                                                                         \
-        if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,           \
+        if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,               \
                       "profile buffer not large enough"))               \
                 return;                                                 \
-        entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(    \
+        entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(     \
                 __entry_size, event_call->id, &rctx, &irq_flags);       \
         if (!entry)                                                     \
                 return;                                                 \
@@ -784,17 +785,20 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
                                                                         \
         { assign; }                                                     \
                                                                         \
-        ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,       \
-                               __count, irq_flags);                     \
+        __regs = &__get_cpu_var(perf_trace_regs);                       \
+        perf_fetch_caller_regs(__regs, 2);                              \
+                                                                        \
+        perf_trace_buf_submit(entry, __entry_size, rctx, __addr,        \
+                               __count, irq_flags, __regs);             \
 }
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)               \
-static notrace void ftrace_profile_##call(proto)                \
+static notrace void perf_trace_##call(proto)                    \
 {                                                               \
         struct ftrace_event_call *event_call = &event_##call;   \
                                                                 \
-        ftrace_profile_templ_##template(event_call, args);      \
+        perf_trace_templ_##template(event_call, args);          \
 }
 
 #undef DEFINE_EVENT_PRINT
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 0387100752f0..e5e5f48dbfb3 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
-int prof_sysenter_enable(struct ftrace_event_call *call);
-void prof_sysenter_disable(struct ftrace_event_call *call);
-int prof_sysexit_enable(struct ftrace_event_call *call);
-void prof_sysexit_disable(struct ftrace_event_call *call);
+int perf_sysenter_enable(struct ftrace_event_call *call);
+void perf_sysenter_disable(struct ftrace_event_call *call);
+int perf_sysexit_enable(struct ftrace_event_call *call);
+void perf_sysexit_disable(struct ftrace_event_call *call);
 #endif
 
 #endif /* _TRACE_SYSCALL_H */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index fa034d29cf73..0ed46f3e51e9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -259,7 +259,8 @@ static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
         struct kprobe_insn_page *kip;
 
         list_for_each_entry(kip, &c->pages, list) {
-                long idx = ((long)slot - (long)kip->insns) / c->insn_size;
+                long idx = ((long)slot - (long)kip->insns) /
+                                (c->insn_size * sizeof(kprobe_opcode_t));
                 if (idx >= 0 && idx < slots_per_page(c)) {
                         WARN_ON(kip->slot_used[idx] != SLOT_USED);
                         if (dirty) {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 681bc2e1e187..c927a549db2c 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3211,8 +3211,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
         unsigned long flags;
 
-        trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -3220,6 +3218,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         check_flags(flags);
 
         current->lockdep_recursion = 1;
+        trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
         __lock_acquire(lock, subclass, trylock, read, check,
                        irqs_disabled_flags(flags), nest_lock, ip, 0);
         current->lockdep_recursion = 0;
@@ -3232,14 +3231,13 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
         unsigned long flags;
 
-        trace_lock_release(lock, nested, ip);
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
         raw_local_irq_save(flags);
         check_flags(flags);
         current->lockdep_recursion = 1;
+        trace_lock_release(lock, nested, ip);
         __lock_release(lock, nested, ip);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
@@ -3413,8 +3411,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
         unsigned long flags;
 
-        trace_lock_contended(lock, ip);
-
         if (unlikely(!lock_stat))
                 return;
 
@@ -3424,6 +3420,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
         raw_local_irq_save(flags);
         check_flags(flags);
         current->lockdep_recursion = 1;
+        trace_lock_contended(lock, ip);
         __lock_contended(lock, ip);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 4393b9e73740..574ee58a3046 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -81,10 +81,6 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
 void __weak hw_perf_disable(void)               { barrier(); }
 void __weak hw_perf_enable(void)                { barrier(); }
 
-void __weak hw_perf_event_setup(int cpu)        { barrier(); }
-void __weak hw_perf_event_setup_online(int cpu) { barrier(); }
-void __weak hw_perf_event_setup_offline(int cpu)        { barrier(); }
-
 int __weak
 hw_perf_group_sched_in(struct perf_event *group_leader,
                struct perf_cpu_context *cpuctx,
@@ -97,25 +93,15 @@ void __weak perf_event_print_debug(void)	{ }
 
 static DEFINE_PER_CPU(int, perf_disable_count);
 
-void __perf_disable(void)
-{
-        __get_cpu_var(perf_disable_count)++;
-}
-
-bool __perf_enable(void)
-{
-        return !--__get_cpu_var(perf_disable_count);
-}
-
 void perf_disable(void)
 {
-        __perf_disable();
-        hw_perf_disable();
+        if (!__get_cpu_var(perf_disable_count)++)
+                hw_perf_disable();
 }
 
 void perf_enable(void)
 {
-        if (__perf_enable())
+        if (!--__get_cpu_var(perf_disable_count))
                 hw_perf_enable();
 }
 
@@ -1538,12 +1524,15 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
                  */
                 if (interrupts == MAX_INTERRUPTS) {
                         perf_log_throttle(event, 1);
+                        perf_disable();
                         event->pmu->unthrottle(event);
+                        perf_enable();
                 }
 
                 if (!event->attr.freq || !event->attr.sample_freq)
                         continue;
 
+                perf_disable();
                 event->pmu->read(event);
                 now = atomic64_read(&event->count);
                 delta = now - hwc->freq_count_stamp;
@@ -1551,6 +1540,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
                 if (delta > 0)
                         perf_adjust_period(event, TICK_NSEC, delta);
+                perf_enable();
         }
         raw_spin_unlock(&ctx->lock);
 }
@@ -1560,9 +1550,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
  */
 static void rotate_ctx(struct perf_event_context *ctx)
 {
-        if (!ctx->nr_events)
-                return;
-
         raw_spin_lock(&ctx->lock);
 
         /* Rotate the first entry last of non-pinned groups */
@@ -1575,19 +1562,28 @@ void perf_event_task_tick(struct task_struct *curr)
 {
         struct perf_cpu_context *cpuctx;
         struct perf_event_context *ctx;
+        int rotate = 0;
 
         if (!atomic_read(&nr_events))
                 return;
 
         cpuctx = &__get_cpu_var(perf_cpu_context);
-        ctx = curr->perf_event_ctxp;
+        if (cpuctx->ctx.nr_events &&
+            cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
+                rotate = 1;
 
-        perf_disable();
+        ctx = curr->perf_event_ctxp;
+        if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active)
+                rotate = 1;
 
         perf_ctx_adjust_freq(&cpuctx->ctx);
         if (ctx)
                 perf_ctx_adjust_freq(ctx);
 
+        if (!rotate)
+                return;
+
+        perf_disable();
         cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
         if (ctx)
                 task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1599,7 +1595,6 @@ void perf_event_task_tick(struct task_struct *curr)
         cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
         if (ctx)
                 task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-
         perf_enable();
 }
 
@@ -2791,6 +2786,13 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return NULL;
 }
 
+#ifdef CONFIG_EVENT_TRACING
+__weak
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
+{
+}
+#endif
+
 /*
  * Output
  */
@@ -4318,9 +4320,8 @@ static const struct pmu perf_ops_task_clock = {
 #ifdef CONFIG_EVENT_TRACING
 
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
-                          int entry_size)
+                   int entry_size, struct pt_regs *regs)
 {
-        struct pt_regs *regs = get_irq_regs();
         struct perf_sample_data data;
         struct perf_raw_record raw = {
                 .size = entry_size,
@@ -4330,12 +4331,9 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
         perf_sample_data_init(&data, addr);
         data.raw = &raw;
 
-        if (!regs)
-                regs = task_pt_regs(current);
-
         /* Trace events already protected against recursion */
         do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
-                                &data, regs);
+                         &data, regs);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
@@ -4351,7 +4349,7 @@ static int perf_tp_event_match(struct perf_event *event,
 
 static void tp_perf_event_destroy(struct perf_event *event)
 {
-        ftrace_profile_disable(event->attr.config);
+        perf_trace_disable(event->attr.config);
 }
 
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
@@ -4365,7 +4363,7 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
                         !capable(CAP_SYS_ADMIN))
                 return ERR_PTR(-EPERM);
 
-        if (ftrace_profile_enable(event->attr.config))
+        if (perf_trace_enable(event->attr.config))
                 return NULL;
 
         event->destroy = tp_perf_event_destroy;
@@ -5372,18 +5370,26 @@ int perf_event_init_task(struct task_struct *child)
         return ret;
 }
 
+static void __init perf_event_init_all_cpus(void)
+{
+        int cpu;
+        struct perf_cpu_context *cpuctx;
+
+        for_each_possible_cpu(cpu) {
+                cpuctx = &per_cpu(perf_cpu_context, cpu);
+                __perf_event_init_context(&cpuctx->ctx, NULL);
+        }
+}
+
 static void __cpuinit perf_event_init_cpu(int cpu)
 {
         struct perf_cpu_context *cpuctx;
 
         cpuctx = &per_cpu(perf_cpu_context, cpu);
-        __perf_event_init_context(&cpuctx->ctx, NULL);
 
         spin_lock(&perf_resource_lock);
         cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
         spin_unlock(&perf_resource_lock);
-
-        hw_perf_event_setup(cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -5423,20 +5429,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
                 perf_event_init_cpu(cpu);
                 break;
 
-        case CPU_ONLINE:
-        case CPU_ONLINE_FROZEN:
-                hw_perf_event_setup_online(cpu);
-                break;
-
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN:
                 perf_event_exit_cpu(cpu);
                 break;
 
-        case CPU_DEAD:
-                hw_perf_event_setup_offline(cpu);
-                break;
-
         default:
                 break;
         }
@@ -5454,6 +5451,7 @@ static struct notifier_block __cpuinitdata perf_cpu_nb = {
 
 void __init perf_event_init(void)
 {
+        perf_event_init_all_cpus();
         perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
                         (void *)(long)smp_processor_id());
         perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d00c6fe23f54..78edc6490038 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
-obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_perf.c
index c1cc3ab633de..81f691eb3a30 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,32 +1,36 @@
 /*
- * trace event based perf counter profiling
+ * trace event based perf event profiling/tracing
  *
  * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include "trace.h"
 
+DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
+EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
+
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
+typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
 
 /* Count the events in use (per event id, not per instance) */
-static int      total_profile_count;
+static int      total_ref_count;
 
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+static int perf_trace_event_enable(struct ftrace_event_call *event)
 {
         char *buf;
         int ret = -ENOMEM;
 
-        if (event->profile_count++ > 0)
+        if (event->perf_refcount++ > 0)
                 return 0;
 
-        if (!total_profile_count) {
+        if (!total_ref_count) {
                 buf = (char *)alloc_percpu(perf_trace_t);
                 if (!buf)
                         goto fail_buf;
@@ -40,35 +44,35 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
                 rcu_assign_pointer(perf_trace_buf_nmi, buf);
         }
 
-        ret = event->profile_enable(event);
+        ret = event->perf_event_enable(event);
         if (!ret) {
-                total_profile_count++;
+                total_ref_count++;
                 return 0;
         }
 
 fail_buf_nmi:
-        if (!total_profile_count) {
+        if (!total_ref_count) {
                 free_percpu(perf_trace_buf_nmi);
                 free_percpu(perf_trace_buf);
                 perf_trace_buf_nmi = NULL;
                 perf_trace_buf = NULL;
         }
 fail_buf:
-        event->profile_count--;
+        event->perf_refcount--;
 
         return ret;
 }
 
-int ftrace_profile_enable(int event_id)
+int perf_trace_enable(int event_id)
 {
         struct ftrace_event_call *event;
         int ret = -EINVAL;
 
         mutex_lock(&event_mutex);
         list_for_each_entry(event, &ftrace_events, list) {
-                if (event->id == event_id && event->profile_enable &&
+                if (event->id == event_id && event->perf_event_enable &&
                     try_module_get(event->mod)) {
-                        ret = ftrace_profile_enable_event(event);
+                        ret = perf_trace_event_enable(event);
                         break;
                 }
         }
@@ -77,16 +81,16 @@ int ftrace_profile_enable(int event_id)
         return ret;
 }
 
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+static void perf_trace_event_disable(struct ftrace_event_call *event)
 {
         char *buf, *nmi_buf;
 
-        if (--event->profile_count > 0)
+        if (--event->perf_refcount > 0)
                 return;
 
-        event->profile_disable(event);
+        event->perf_event_disable(event);
 
-        if (!--total_profile_count) {
+        if (!--total_ref_count) {
                 buf = perf_trace_buf;
                 rcu_assign_pointer(perf_trace_buf, NULL);
 
@@ -104,14 +108,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
         }
 }
 
-void ftrace_profile_disable(int event_id)
+void perf_trace_disable(int event_id)
 {
         struct ftrace_event_call *event;
 
         mutex_lock(&event_mutex);
         list_for_each_entry(event, &ftrace_events, list) {
                 if (event->id == event_id) {
-                        ftrace_profile_disable_event(event);
+                        perf_trace_event_disable(event);
                         module_put(event->mod);
                         break;
                 }
@@ -119,8 +123,8 @@ void ftrace_profile_disable(int event_id)
         mutex_unlock(&event_mutex);
 }
 
-__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
-                                        int *rctxp, unsigned long *irq_flags)
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+                                       int *rctxp, unsigned long *irq_flags)
 {
         struct trace_entry *entry;
         char *trace_buf, *raw_data;
@@ -161,4 +165,4 @@ err_recursion:
         local_irq_restore(*irq_flags);
         return NULL;
 }
-EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3f972ad98d04..beab8bf2f310 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -938,7 +938,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
                 trace_create_file("enable", 0644, call->dir, call,
                                   enable);
 
-        if (call->id && call->profile_enable)
+        if (call->id && call->perf_event_enable)
                 trace_create_file("id", 0444, call->dir, call,
                                   id);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 505c92273b1a..1251e367bae9 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1214,7 +1214,7 @@ static int set_print_fmt(struct trace_probe *tp)
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static __kprobes void kprobe_profile_func(struct kprobe *kp,
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
                                          struct pt_regs *regs)
 {
         struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
@@ -1227,11 +1227,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
         __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
         size = ALIGN(__size + sizeof(u32), sizeof(u64));
         size -= sizeof(u32);
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
                      "profile buffer not large enough"))
                 return;
 
-        entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+        entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
         if (!entry)
                 return;
 
@@ -1240,11 +1240,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
         for (i = 0; i < tp->nr_args; i++)
                 entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-        ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags);
+        perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
 }
 
 /* Kretprobe profile handler */
-static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
                                             struct pt_regs *regs)
 {
         struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
@@ -1257,11 +1257,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
         __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
         size = ALIGN(__size + sizeof(u32), sizeof(u64));
         size -= sizeof(u32);
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
                      "profile buffer not large enough"))
                 return;
 
-        entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+        entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
         if (!entry)
                 return;
 
@@ -1271,10 +1271,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
         for (i = 0; i < tp->nr_args; i++)
                 entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-        ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags);
+        perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+                               irq_flags, regs);
 }
 
-static int probe_profile_enable(struct ftrace_event_call *call)
+static int probe_perf_enable(struct ftrace_event_call *call)
 {
         struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1286,7 +1287,7 @@ static int probe_profile_enable(struct ftrace_event_call *call)
                 return enable_kprobe(&tp->rp.kp);
 }
 
-static void probe_profile_disable(struct ftrace_event_call *call)
+static void probe_perf_disable(struct ftrace_event_call *call)
 {
         struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1311,7 +1312,7 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
                 kprobe_trace_func(kp, regs);
 #ifdef CONFIG_PERF_EVENTS
         if (tp->flags & TP_FLAG_PROFILE)
-                kprobe_profile_func(kp, regs);
+                kprobe_perf_func(kp, regs);
 #endif
         return 0;       /* We don't tweek kernel, so just return 0 */
 }
@@ -1325,7 +1326,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
                 kretprobe_trace_func(ri, regs);
 #ifdef CONFIG_PERF_EVENTS
         if (tp->flags & TP_FLAG_PROFILE)
-                kretprobe_profile_func(ri, regs);
+                kretprobe_perf_func(ri, regs);
 #endif
         return 0;       /* We don't tweek kernel, so just return 0 */
 }
@@ -1358,8 +1359,8 @@ static int register_probe_event(struct trace_probe *tp)
         call->unregfunc = probe_event_disable;
 
 #ifdef CONFIG_PERF_EVENTS
-        call->profile_enable = probe_profile_enable;
-        call->profile_disable = probe_profile_disable;
+        call->perf_event_enable = probe_perf_enable;
+        call->perf_event_disable = probe_perf_disable;
 #endif
         call->data = tp;
         ret = trace_add_event_call(call);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index cba47d7935cc..33c2a5b769dc 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -428,12 +428,12 @@ core_initcall(init_ftrace_syscalls);
 
 #ifdef CONFIG_PERF_EVENTS
 
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
 
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(struct pt_regs *regs, long id)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
@@ -443,7 +443,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         int size;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -455,11 +455,11 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         size = ALIGN(size + sizeof(u32), sizeof(u64));
         size -= sizeof(u32);
 
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                      "profile buffer not large enough"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                      "perf buffer not large enough"))
                 return;
 
-        rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size,
+        rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
                                 sys_data->enter_event->id, &rctx, &flags);
         if (!rec)
                 return;
@@ -467,10 +467,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         rec->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                                (unsigned long *)&rec->args);
-        ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysenter_enable(struct ftrace_event_call *call)
+int perf_sysenter_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
@@ -478,34 +478,34 @@ int prof_sysenter_enable(struct ftrace_event_call *call)
         num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_enter)
-                ret = register_trace_sys_enter(prof_syscall_enter);
+        if (!sys_perf_refcount_enter)
+                ret = register_trace_sys_enter(perf_syscall_enter);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall entry trace point");
         } else {
-                set_bit(num, enabled_prof_enter_syscalls);
-                sys_prof_refcount_enter++;
+                set_bit(num, enabled_perf_enter_syscalls);
+                sys_perf_refcount_enter++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void prof_sysenter_disable(struct ftrace_event_call *call)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
         int num;
 
         num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_enter--;
-        clear_bit(num, enabled_prof_enter_syscalls);
-        if (!sys_prof_refcount_enter)
-                unregister_trace_sys_enter(prof_syscall_enter);
+        sys_perf_refcount_enter--;
+        clear_bit(num, enabled_perf_enter_syscalls);
+        if (!sys_perf_refcount_enter)
+                unregister_trace_sys_enter(perf_syscall_enter);
         mutex_unlock(&syscall_trace_lock);
 }
 
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_exit *rec;
@@ -515,7 +515,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
         int size;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -530,11 +530,11 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
          * Impossible, but be paranoid with the future
          * How to put this check outside runtime?
          */
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                "exit event has grown above profile buffer size"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                "exit event has grown above perf buffer size"))
                 return;
 
-        rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size,
+        rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
                                 sys_data->exit_event->id, &rctx, &flags);
         if (!rec)
                 return;
@@ -542,10 +542,10 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
         rec->nr = syscall_nr;
         rec->ret = syscall_get_return_value(current, regs);
 
-        ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysexit_enable(struct ftrace_event_call *call)
+int perf_sysexit_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
@@ -553,30 +553,30 @@ int prof_sysexit_enable(struct ftrace_event_call *call)
         num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_exit)
-                ret = register_trace_sys_exit(prof_syscall_exit);
+        if (!sys_perf_refcount_exit)
+                ret = register_trace_sys_exit(perf_syscall_exit);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall exit trace point");
         } else {
-                set_bit(num, enabled_prof_exit_syscalls);
-                sys_prof_refcount_exit++;
+                set_bit(num, enabled_perf_exit_syscalls);
+                sys_perf_refcount_exit++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void prof_sysexit_disable(struct ftrace_event_call *call)
+void perf_sysexit_disable(struct ftrace_event_call *call)
 {
         int num;
 
         num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_exit--;
-        clear_bit(num, enabled_prof_exit_syscalls);
-        if (!sys_prof_refcount_exit)
-                unregister_trace_sys_exit(prof_syscall_exit);
+        sys_perf_refcount_exit--;
+        clear_bit(num, enabled_perf_exit_syscalls);
+        if (!sys_perf_refcount_exit)
+                unregister_trace_sys_exit(perf_syscall_exit);
         mutex_unlock(&syscall_trace_lock);
 }
 
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bdd3b7ecad0a..bd498d496952 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -24,7 +24,10 @@ DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
 DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
 DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
 
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
 prefix?=$(HOME)
+endif
 bindir?=$(prefix)/bin
 htmldir?=$(prefix)/share/doc/perf-doc
 pdfdir?=$(prefix)/share/doc/perf-doc
@@ -32,7 +35,6 @@ mandir?=$(prefix)/share/man
 man1dir=$(mandir)/man1
 man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
-# DESTDIR=
 
 ASCIIDOC=asciidoc
 ASCIIDOC_EXTRA = --unsafe
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 2d537382c686..8a8f52db7e38 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -216,7 +216,10 @@ STRIP ?= strip
 # runtime figures out where they are based on the path to the executable.
 # This can help installing the suite in a relocatable way.
 
+# Make the path relative to DESTDIR, not to prefix
+ifndef DESTDIR
 prefix = $(HOME)
+endif
 bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
 mandir = share/man
@@ -233,7 +236,6 @@ sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
 lib = lib
-# DESTDIR=
 
 export prefix bindir sharedir sysconfdir
 
@@ -387,6 +389,7 @@ LIB_H += util/thread.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
+LIB_H += util/cpumap.h
 
 LIB_OBJS += util/abspath.o
 LIB_OBJS += util/alias.o
@@ -433,6 +436,7 @@ LIB_OBJS += util/sort.o
 LIB_OBJS += util/hist.o
 LIB_OBJS += util/probe-event.o
 LIB_OBJS += util/util.o
+LIB_OBJS += util/cpumap.o
 
 BUILTIN_OBJS += builtin-annotate.o
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5ec5de995872..6ad7148451c5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -116,7 +116,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
                 return 0;
         }
 
-        he = __perf_session__add_hist_entry(self, al, NULL, count, &hit);
+        he = __perf_session__add_hist_entry(&self->hists, al, NULL, count, &hit);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -564,8 +564,8 @@ static int __cmd_annotate(void)
         if (verbose > 2)
                 dsos__fprintf(stdout);
 
-        perf_session__collapse_resort(session);
-        perf_session__output_resort(session, session->event_total[0]);
+        perf_session__collapse_resort(&session->hists);
+        perf_session__output_resort(&session->hists, session->event_total[0]);
         perf_session__find_annotations(session);
 out_delete:
         perf_session__delete(session);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 18b3f505f9db..1ea15d8aeed1 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -26,7 +26,8 @@ static int perf_session__add_hist_entry(struct perf_session *self,
                                         struct addr_location *al, u64 count)
 {
         bool hit;
-        struct hist_entry *he = __perf_session__add_hist_entry(self, al, NULL,
+        struct hist_entry *he = __perf_session__add_hist_entry(&self->hists,
+                                                               al, NULL,
                                                                count, &hit);
         if (he == NULL)
                 return -ENOMEM;
@@ -114,7 +115,7 @@ static void perf_session__resort_hist_entries(struct perf_session *self)
 
 static void perf_session__set_hist_entries_positions(struct perf_session *self)
 {
-        perf_session__output_resort(self, self->events_stats.total);
+        perf_session__output_resort(&self->hists, self->events_stats.total);
         perf_session__resort_hist_entries(self);
 }
 
@@ -166,13 +167,15 @@ static int __cmd_diff(void)
                         goto out_delete;
         }
 
-        perf_session__output_resort(session[1], session[1]->events_stats.total);
+        perf_session__output_resort(&session[1]->hists,
+                                    session[1]->events_stats.total);
         if (show_displacement)
                 perf_session__set_hist_entries_positions(session[0]);
 
         perf_session__match_hists(session[0], session[1]);
-        perf_session__fprintf_hists(session[1], session[0],
-                                    show_displacement, stdout);
+        perf_session__fprintf_hists(&session[1]->hists, session[0],
+                                    show_displacement, stdout,
+                                    session[1]->events_stats.total);
 out_delete:
         for (i = 0; i < 2; ++i)
                 perf_session__delete(session[i]);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 771533ced6a8..3b8b6387c47c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -22,6 +22,7 @@
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/cpumap.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -244,6 +245,9 @@ static void create_counter(int counter, int cpu, pid_t pid)
 
         attr->sample_type       |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
+        if (nr_counters > 1)
+                attr->sample_type |= PERF_SAMPLE_ID;
+
         if (freq) {
                 attr->sample_type       |= PERF_SAMPLE_PERIOD;
                 attr->freq              = 1;
@@ -391,6 +395,9 @@ static int process_buildids(void)
 {
         u64 size = lseek(output, 0, SEEK_CUR);
 
+        if (size == 0)
+                return 0;
+
         session->fd = output;
         return __perf_session__process_events(session, post_processing_offset,
                                               size - post_processing_offset,
@@ -418,9 +425,6 @@ static int __cmd_record(int argc, const char **argv)
         char buf;
 
         page_size = sysconf(_SC_PAGE_SIZE);
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert(nr_cpus >= 0);
 
         atexit(sig_atexit);
         signal(SIGCHLD, sig_handler);
@@ -544,8 +548,9 @@ static int __cmd_record(int argc, const char **argv)
         if ((!system_wide && !inherit) || profile_cpu != -1) {
                 open_counters(profile_cpu, target_pid);
         } else {
+                nr_cpus = read_cpu_map();
                 for (i = 0; i < nr_cpus; i++)
-                        open_counters(i, target_pid);
+                        open_counters(cpumap[i], target_pid);
         }
 
         if (file_new) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cfc655d40bb7..f815de25d0fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -45,28 +45,71 @@ static char		*pretty_printing_style = default_pretty_printing_style;
 
 static char             callchain_default_opt[] = "fractal,0.5";
 
+static struct event_stat_id *get_stats(struct perf_session *self,
+                                       u64 event_stream, u32 type, u64 config)
+{
+        struct rb_node **p = &self->stats_by_id.rb_node;
+        struct rb_node *parent = NULL;
+        struct event_stat_id *iter, *new;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct event_stat_id, rb_node);
+                if (iter->config == config)
+                        return iter;
+
+
+                if (config > iter->config)
+                        p = &(*p)->rb_right;
+                else
+                        p = &(*p)->rb_left;
+        }
+
+        new = malloc(sizeof(struct event_stat_id));
+        if (new == NULL)
+                return NULL;
+        memset(new, 0, sizeof(struct event_stat_id));
+        new->event_stream = event_stream;
+        new->config = config;
+        new->type = type;
+        rb_link_node(&new->rb_node, parent, p);
+        rb_insert_color(&new->rb_node, &self->stats_by_id);
+        return new;
+}
+
 static int perf_session__add_hist_entry(struct perf_session *self,
                                         struct addr_location *al,
-                                        struct ip_callchain *chain, u64 count)
+                                        struct sample_data *data)
 {
         struct symbol **syms = NULL, *parent = NULL;
         bool hit;
         struct hist_entry *he;
+        struct event_stat_id *stats;
+        struct perf_event_attr *attr;
 
-        if ((sort__has_parent || symbol_conf.use_callchain) && chain)
+        if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain)
                 syms = perf_session__resolve_callchain(self, al->thread,
-                                                       chain, &parent);
-        he = __perf_session__add_hist_entry(self, al, parent, count, &hit);
+                                                       data->callchain, &parent);
+
+        attr = perf_header__find_attr(data->id, &self->header);
+        if (attr)
+                stats = get_stats(self, data->id, attr->type, attr->config);
+        else
+                stats = get_stats(self, data->id, 0, 0);
+        if (stats == NULL)
+                return -ENOMEM;
+        he = __perf_session__add_hist_entry(&stats->hists, al, parent,
+                                            data->period, &hit);
         if (he == NULL)
                 return -ENOMEM;
 
         if (hit)
-                he->count += count;
+                he->count += data->period;
 
         if (symbol_conf.use_callchain) {
                 if (!hit)
                         callchain_init(&he->callchain);
-                append_chain(&he->callchain, chain, syms);
+                append_chain(&he->callchain, data->callchain, syms);
                 free(syms);
         }
 
@@ -86,10 +129,30 @@ static int validate_chain(struct ip_callchain *chain, event_t *event)
         return 0;
 }
 
+static int add_event_total(struct perf_session *session,
+                           struct sample_data *data,
+                           struct perf_event_attr *attr)
+{
+        struct event_stat_id *stats;
+
+        if (attr)
+                stats = get_stats(session, data->id, attr->type, attr->config);
+        else
+                stats = get_stats(session, data->id, 0, 0);
+
+        if (!stats)
+                return -ENOMEM;
+
+        stats->stats.total += data->period;
+        session->events_stats.total += data->period;
+        return 0;
+}
+
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct sample_data data = { .period = 1, };
         struct addr_location al;
+        struct perf_event_attr *attr;
 
         event__parse_sample(event, session->sample_type, &data);
 
@@ -123,12 +186,18 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         if (al.filtered || (hide_unresolved && al.sym == NULL))
                 return 0;
 
-        if (perf_session__add_hist_entry(session, &al, data.callchain, data.period)) {
+        if (perf_session__add_hist_entry(session, &al, &data)) {
                 pr_debug("problem incrementing symbol count, skipping event\n");
                 return -1;
         }
 
-        session->events_stats.total += data.period;
+        attr = perf_header__find_attr(data.id, &session->header);
+
+        if (add_event_total(session, &data, attr)) {
+                pr_debug("problem adding event count\n");
+                return -1;
+        }
+
         return 0;
 }
 
@@ -197,6 +266,7 @@ static int __cmd_report(void)
 {
         int ret = -EINVAL;
         struct perf_session *session;
+        struct rb_node *next;
 
         session = perf_session__new(input_name, O_RDONLY, force);
         if (session == NULL)
@@ -224,10 +294,28 @@ static int __cmd_report(void)
         if (verbose > 2)
                 dsos__fprintf(stdout);
 
-        perf_session__collapse_resort(session);
-        perf_session__output_resort(session, session->events_stats.total);
-        fprintf(stdout, "# Samples: %Ld\n#\n", session->events_stats.total);
-        perf_session__fprintf_hists(session, NULL, false, stdout);
+        next = rb_first(&session->stats_by_id);
+        while (next) {
+                struct event_stat_id *stats;
+
+                stats = rb_entry(next, struct event_stat_id, rb_node);
+                perf_session__collapse_resort(&stats->hists);
+                perf_session__output_resort(&stats->hists, stats->stats.total);
+                if (rb_first(&session->stats_by_id) ==
+                    rb_last(&session->stats_by_id))
+                        fprintf(stdout, "# Samples: %Ld\n#\n",
+                                stats->stats.total);
+                else
+                        fprintf(stdout, "# Samples: %Ld %s\n#\n",
+                                stats->stats.total,
+                                __event_name(stats->type, stats->config));
+
+                perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
+                                            stats->stats.total);
+                fprintf(stdout, "\n\n");
+                next = rb_next(&stats->rb_node);
+        }
+
         if (sort_order == default_sort_order &&
             parent_pattern == default_parent_pattern)
                 fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e8c85d5aec41..95db31cff6fd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,6 +45,7 @@
 #include "util/event.h"
 #include "util/debug.h"
 #include "util/header.h"
+#include "util/cpumap.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -151,7 +152,7 @@ static void create_perf_stat_counter(int counter, int pid)
                 unsigned int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
-                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpu, -1, 0);
+                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
                         if (fd[cpu][counter] < 0 && verbose)
                                 fprintf(stderr, ERR_PERF_OPEN, counter,
                                         fd[cpu][counter], strerror(errno));
@@ -519,9 +520,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
                 nr_counters = ARRAY_SIZE(default_attrs);
         }
 
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert((int)nr_cpus >= 0);
+        if (system_wide)
+                nr_cpus = read_cpu_map();
+        else
+                nr_cpus = 1;
 
         /*
          * We dont want to block the signals - that would cause
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 31f2e597800c..0b719e3dde05 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -28,6 +28,7 @@
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
 #include "util/parse-events.h"
+#include "util/cpumap.h"
 
 #include "util/debug.h"
 
@@ -1123,7 +1124,7 @@ static void start_counter(int i, int counter)
 
         cpu = profile_cpu;
         if (target_pid == -1 && profile_cpu == -1)
-                cpu = i;
+                cpu = cpumap[i];
 
         attr = attrs + counter;
 
@@ -1347,12 +1348,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 attrs[counter].sample_period = default_interval;
         }
 
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert(nr_cpus >= 0);
-
         if (target_pid != -1 || profile_cpu != -1)
                 nr_cpus = 1;
+        else
+                nr_cpus = read_cpu_map();
 
         get_term_dimensions(&winsize);
         if (print_entries == 0) {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
new file mode 100644
index 000000000000..4e01490e51e5
--- /dev/null
+++ b/tools/perf/util/cpumap.c
@@ -0,0 +1,59 @@
+#include "util.h"
+#include "../perf.h"
+#include "cpumap.h"
+#include <assert.h>
+#include <stdio.h>
+
+int cpumap[MAX_NR_CPUS];
+
+static int default_cpu_map(void)
+{
+        int nr_cpus, i;
+
+        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+        assert(nr_cpus <= MAX_NR_CPUS);
+        assert((int)nr_cpus >= 0);
+
+        for (i = 0; i < nr_cpus; ++i)
+                cpumap[i] = i;
+
+        return nr_cpus;
+}
+
+int read_cpu_map(void)
+{
+        FILE *onlnf;
+        int nr_cpus = 0;
+        int n, cpu, prev;
+        char sep;
+
+        onlnf = fopen("/sys/devices/system/cpu/online", "r");
+        if (!onlnf)
+                return default_cpu_map();
+
+        sep = 0;
+        prev = -1;
+        for (;;) {
+                n = fscanf(onlnf, "%u%c", &cpu, &sep);
+                if (n <= 0)
+                        break;
+                if (prev >= 0) {
+                        assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+                        while (++prev < cpu)
+                                cpumap[nr_cpus++] = prev;
+                }
+                assert (nr_cpus < MAX_NR_CPUS);
+                cpumap[nr_cpus++] = cpu;
+                if (n == 2 && sep == '-')
+                        prev = cpu;
+                else
+                        prev = -1;
+                if (n == 1 || sep == '\n')
+                        break;
+        }
+        fclose(onlnf);
+        if (nr_cpus > 0)
+                return nr_cpus;
+
+        return default_cpu_map();
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
new file mode 100644
index 000000000000..86c78bb33098
--- /dev/null
+++ b/tools/perf/util/cpumap.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_CPUMAP_H
+#define __PERF_CPUMAP_H
+
+extern int read_cpu_map(void);
+extern int cpumap[];
+
+#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 50a7132887f5..a33b94952e34 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -99,6 +99,15 @@ struct events_stats {
         u64 lost;
 };
 
+struct event_stat_id {
+        struct rb_node          rb_node;
+        struct rb_root          hists;
+        struct events_stats     stats;
+        u64                     config;
+        u64                     event_stream;
+        u32                     type;
+};
+
 void event__print_totals(void);
 
 struct perf_session;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 44408c2621cf..2be33c7dbf03 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -12,12 +12,12 @@ struct callchain_param	callchain_param = {
  * histogram, sorted on item, collects counts
  */
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
                                                   struct addr_location *al,
                                                   struct symbol *sym_parent,
                                                   u64 count, bool *hit)
 {
-        struct rb_node **p = &self->hists.rb_node;
+        struct rb_node **p = &hists->rb_node;
         struct rb_node *parent = NULL;
         struct hist_entry *he;
         struct hist_entry entry = {
@@ -53,7 +53,7 @@ struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
                 return NULL;
         *he = entry;
         rb_link_node(&he->rb_node, parent, p);
-        rb_insert_color(&he->rb_node, &self->hists);
+        rb_insert_color(&he->rb_node, hists);
         *hit = false;
         return he;
 }
@@ -130,7 +130,7 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
         rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__collapse_resort(struct perf_session *self)
+void perf_session__collapse_resort(struct rb_root *hists)
 {
         struct rb_root tmp;
         struct rb_node *next;
@@ -140,17 +140,17 @@ void perf_session__collapse_resort(struct perf_session *self)
                 return;
 
         tmp = RB_ROOT;
-        next = rb_first(&self->hists);
+        next = rb_first(hists);
 
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node);
                 next = rb_next(&n->rb_node);
 
-                rb_erase(&n->rb_node, &self->hists);
+                rb_erase(&n->rb_node, hists);
                 collapse__insert_entry(&tmp, n);
         }
 
-        self->hists = tmp;
+        *hists = tmp;
 }
 
 /*
@@ -183,7 +183,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
         rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples)
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
 {
         struct rb_root tmp;
         struct rb_node *next;
@@ -194,18 +194,18 @@ void perf_session__output_resort(struct perf_session *self, u64 total_samples)
                 total_samples * (callchain_param.min_percent / 100);
 
         tmp = RB_ROOT;
-        next = rb_first(&self->hists);
+        next = rb_first(hists);
 
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node);
                 next = rb_next(&n->rb_node);
 
-                rb_erase(&n->rb_node, &self->hists);
+                rb_erase(&n->rb_node, hists);
                 perf_session__insert_output_hist_entry(&tmp, n,
                                                        min_callchain_hits);
         }
 
-        self->hists = tmp;
+        *hists = tmp;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -456,10 +456,10 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 }
 
 static size_t hist_entry__fprintf(struct hist_entry *self,
-                                  struct perf_session *session,
                                   struct perf_session *pair_session,
                                   bool show_displacement,
-                                  long displacement, FILE *fp)
+                                  long displacement, FILE *fp,
+                                  u64 session_total)
 {
         struct sort_entry *se;
         u64 count, total;
@@ -474,7 +474,7 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
                 total = pair_session->events_stats.total;
         } else {
                 count = self->count;
-                total = session->events_stats.total;
+                total = session_total;
         }
 
         if (total)
@@ -496,8 +496,8 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 
                 if (total > 0)
                         old_percent = (count * 100.0) / total;
-                if (session->events_stats.total > 0)
-                        new_percent = (self->count * 100.0) / session->events_stats.total;
+                if (session_total > 0)
+                        new_percent = (self->count * 100.0) / session_total;
 
                 diff = new_percent - old_percent;
 
@@ -544,16 +544,17 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
                         left_margin -= thread__comm_len(self->thread);
                 }
 
-                hist_entry_callchain__fprintf(fp, self, session->events_stats.total,
+                hist_entry_callchain__fprintf(fp, self, session_total,
                                               left_margin);
         }
 
         return ret;
 }
 
-size_t perf_session__fprintf_hists(struct perf_session *self,
+size_t perf_session__fprintf_hists(struct rb_root *hists,
                                    struct perf_session *pair,
-                                   bool show_displacement, FILE *fp)
+                                   bool show_displacement, FILE *fp,
+                                   u64 session_total)
 {
         struct sort_entry *se;
         struct rb_node *nd;
@@ -641,7 +642,7 @@ size_t perf_session__fprintf_hists(struct perf_session *self,
         fprintf(fp, "\n#\n");
 
 print_entries:
-        for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
                 if (show_displacement) {
@@ -652,8 +653,13 @@ print_entries:
                                 displacement = 0;
                         ++position;
                 }
-                ret += hist_entry__fprintf(h, self, pair, show_displacement,
-                                           displacement, fp);
+                ret += hist_entry__fprintf(h, pair, show_displacement,
+                                           displacement, fp, session_total);
+                if (h->map == NULL && verbose > 1) {
+                        __map_groups__fprintf_maps(&h->thread->mg,
+                                                   MAP__FUNCTION, fp);
+                        fprintf(fp, "%.10s end\n", graph_dotted_line);
+                }
         }
 
         free(rem_sq_bracket);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index e5f99b24048b..16f360cce5bf 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,8 +10,9 @@ struct perf_session;
 struct hist_entry;
 struct addr_location;
 struct symbol;
+struct rb_root;
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
                                                   struct addr_location *al,
                                                   struct symbol *parent,
                                                   u64 count, bool *hit);
@@ -19,9 +20,10 @@ extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples);
-void perf_session__collapse_resort(struct perf_session *self);
-size_t perf_session__fprintf_hists(struct perf_session *self,
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
+void perf_session__collapse_resort(struct rb_root *hists);
+size_t perf_session__fprintf_hists(struct rb_root *hists,
                                    struct perf_session *pair,
-                                   bool show_displacement, FILE *fp);
+                                   bool show_displacement, FILE *fp,
+                                   u64 session_total);
 #endif  /* __PERF_HIST_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index e77dc886760e..1e6c65ebbd80 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -169,7 +169,7 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 {
         Dwarf_Files *files;
         size_t nfiles, i;
-        const char *src;
+        const char *src = NULL;
         int ret;
 
         if (!fname)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0de7258e70a5..eed1cb889008 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -70,6 +70,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 
         memcpy(self->filename, filename, len);
         self->threads = RB_ROOT;
+        self->stats_by_id = RB_ROOT;
         self->last_match = NULL;
         self->mmap_window = 32;
         self->cwd = NULL;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 31950fcd8a4d..5c33417eebb3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -20,6 +20,7 @@ struct perf_session {
         struct thread           *last_match;
         struct map              *vmlinux_maps[MAP__NR_TYPES];
         struct events_stats     events_stats;
+        struct rb_root          stats_by_id;
         unsigned long           event_total[PERF_RECORD_MAX];
         unsigned long           unknown_events;
         struct rb_root          hists;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 21b92162282b..fa968312ee7d 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -79,8 +79,8 @@ int thread__comm_len(struct thread *self)
         return self->comm_len;
 }
 
-static size_t __map_groups__fprintf_maps(struct map_groups *self,
-                                         enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+                                  enum map_type type, FILE *fp)
 {
         size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
         struct rb_node *nd;
@@ -89,7 +89,7 @@ static size_t __map_groups__fprintf_maps(struct map_groups *self,
                 struct map *pos = rb_entry(nd, struct map, rb_node);
                 printed += fprintf(fp, "Map:");
                 printed += map__fprintf(pos, fp);
-                if (verbose > 1) {
+                if (verbose > 2) {
                         printed += dso__fprintf(pos->dso, type, fp);
                         printed += fprintf(fp, "--\n");
                 }
@@ -183,8 +183,8 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
         return th;
 }
 
-static void map_groups__remove_overlappings(struct map_groups *self,
-                                            struct map *map)
+static int map_groups__fixup_overlappings(struct map_groups *self,
+                                          struct map *map)
 {
         struct rb_root *root = &self->maps[map->type];
         struct rb_node *next = rb_first(root);
@@ -209,7 +209,36 @@ static void map_groups__remove_overlappings(struct map_groups *self,
                  * list.
                  */
                 list_add_tail(&pos->node, &self->removed_maps[map->type]);
+                /*
+                 * Now check if we need to create new maps for areas not
+                 * overlapped by the new map:
+                 */
+                if (map->start > pos->start) {
+                        struct map *before = map__clone(pos);
+
+                        if (before == NULL)
+                                return -ENOMEM;
+
+                        before->end = map->start - 1;
+                        map_groups__insert(self, before);
+                        if (verbose >= 2)
+                                map__fprintf(before, stderr);
+                }
+
+                if (map->end < pos->end) {
+                        struct map *after = map__clone(pos);
+
+                        if (after == NULL)
+                                return -ENOMEM;
+
+                        after->start = map->end + 1;
+                        map_groups__insert(self, after);
+                        if (verbose >= 2)
+                                map__fprintf(after, stderr);
+                }
         }
+
+        return 0;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -254,7 +283,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 
 void thread__insert_map(struct thread *self, struct map *map)
 {
-        map_groups__remove_overlappings(&self->mg, map);
+        map_groups__fixup_overlappings(&self->mg, map);
         map_groups__insert(&self->mg, map);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 0a28f39de545..dcf70303e58e 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,9 @@ struct map_groups {
         struct list_head        removed_maps[MAP__NR_TYPES];
 };
 
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+                                  enum map_type type, FILE *fp);
+
 struct thread {
         struct rb_node          rb_node;
         struct map_groups       mg;