39 files changed, 206 insertions, 187 deletions

diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/alpha/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/arm/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index c45768614c8a..5b7cfafc0720 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -164,20 +164,20 @@ armpmu_event_set_period(struct perf_event *event,
                         struct hw_perf_event *hwc,
                         int idx)
 {
-        s64 left = atomic64_read(&hwc->period_left);
+        s64 left = local64_read(&hwc->period_left);
         s64 period = hwc->sample_period;
         int ret = 0;
 
         if (unlikely(left <= -period)) {
                 left = period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
 
         if (unlikely(left <= 0)) {
                 left += period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
@@ -185,7 +185,7 @@ armpmu_event_set_period(struct perf_event *event,
         if (left > (s64)armpmu->max_period)
                 left = armpmu->max_period;
 
-        atomic64_set(&hwc->prev_count, (u64)-left);
+        local64_set(&hwc->prev_count, (u64)-left);
 
         armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
 
@@ -204,18 +204,18 @@ armpmu_event_update(struct perf_event *event,
         s64 delta;
 
 again:
-        prev_raw_count = atomic64_read(&hwc->prev_count);
+        prev_raw_count = local64_read(&hwc->prev_count);
         new_raw_count = armpmu->read_counter(idx);
 
-        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
                              new_raw_count) != prev_raw_count)
                 goto again;
 
         delta = (new_raw_count << shift) - (prev_raw_count << shift);
         delta >>= shift;
 
-        atomic64_add(delta, &event->count);
-        atomic64_sub(delta, &hwc->period_left);
+        local64_add(delta, &event->count);
+        local64_sub(delta, &hwc->period_left);
 
         return new_raw_count;
 }
@@ -478,7 +478,7 @@ __hw_perf_event_init(struct perf_event *event)
         if (!hwc->sample_period) {
                 hwc->sample_period  = armpmu->max_period;
                 hwc->last_period    = hwc->sample_period;
-                atomic64_set(&hwc->period_left, hwc->sample_period);
+                local64_set(&hwc->period_left, hwc->sample_period);
         }
 
         err = 0;
diff --git a/arch/avr32/include/asm/local64.h b/arch/avr32/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/avr32/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/blackfin/include/asm/local64.h b/arch/blackfin/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/blackfin/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/cris/include/asm/local64.h b/arch/cris/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/cris/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/frv/include/asm/local64.h b/arch/frv/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/frv/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/frv/kernel/local64.h b/arch/frv/kernel/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/frv/kernel/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/h8300/include/asm/local64.h b/arch/h8300/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/h8300/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/ia64/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/m32r/include/asm/local64.h b/arch/m32r/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/m32r/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/m68k/include/asm/local64.h b/arch/m68k/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/m68k/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/microblaze/include/asm/local64.h b/arch/microblaze/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/microblaze/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/mips/include/asm/local64.h b/arch/mips/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/mips/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/mn10300/include/asm/local64.h b/arch/mn10300/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/mn10300/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/parisc/include/asm/local64.h b/arch/parisc/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/parisc/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/powerpc/include/asm/local64.h b/arch/powerpc/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/powerpc/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index e6d4ce69b126..5c16b891d501 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -21,3 +21,15 @@
 #ifdef CONFIG_FSL_EMB_PERF_EVENT
 #include <asm/perf_event_fsl_emb.h>
 #endif
+
+#ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+
+#define perf_arch_fetch_caller_regs(regs, __ip)                 \
+        do {                                                    \
+                (regs)->nip = __ip;                             \
+                (regs)->gpr[1] = *(unsigned long *)__get_SP();  \
+                asm volatile("mfmsr %0" : "=r" ((regs)->msr));  \
+        } while (0)
+#endif
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 22e507c8a556..2d29752cbe16 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7)
 _GLOBAL(__restore_cpu_power7)
         /* place holder */
         blr
-
-/*
- * Get a minimal set of registers for our caller's nth caller.
- * r3 = regs pointer, r5 = n.
- *
- * We only get R1 (stack pointer), NIP (next instruction pointer)
- * and LR (link register).  These are all we can get in the
- * general case without doing complicated stack unwinding, but
- * fortunately they are enough to do a stack backtrace, which
- * is all we need them for.
- */
-_GLOBAL(perf_arch_fetch_caller_regs)
-        mr      r6,r1
-        cmpwi   r5,0
-        mflr    r4
-        ble     2f
-        mtctr   r5
-1:      PPC_LL  r6,0(r6)
-        bdnz    1b
-        PPC_LL  r4,PPC_LR_STKOFF(r6)
-2:      PPC_LL  r7,0(r6)
-        PPC_LL  r7,PPC_LR_STKOFF(r7)
-        PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3)
-        PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3)
-        PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3)
-        blr
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 43b83c35cf54..af1d9a7c65d1 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -410,15 +410,15 @@ static void power_pmu_read(struct perf_event *event)
          * Therefore we treat them like NMIs.
          */
         do {
-                prev = atomic64_read(&event->hw.prev_count);
+                prev = local64_read(&event->hw.prev_count);
                 barrier();
                 val = read_pmc(event->hw.idx);
-        } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
+        } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
         /* The counters are only 32 bits wide */
         delta = (val - prev) & 0xfffffffful;
-        atomic64_add(delta, &event->count);
-        atomic64_sub(delta, &event->hw.period_left);
+        local64_add(delta, &event->count);
+        local64_sub(delta, &event->hw.period_left);
 }
 
 /*
@@ -444,10 +444,10 @@ static void freeze_limited_counters(struct cpu_hw_events *cpuhw,
                 if (!event->hw.idx)
                         continue;
                 val = (event->hw.idx == 5) ? pmc5 : pmc6;
-                prev = atomic64_read(&event->hw.prev_count);
+                prev = local64_read(&event->hw.prev_count);
                 event->hw.idx = 0;
                 delta = (val - prev) & 0xfffffffful;
-                atomic64_add(delta, &event->count);
+                local64_add(delta, &event->count);
         }
 }
 
@@ -462,7 +462,7 @@ static void thaw_limited_counters(struct cpu_hw_events *cpuhw,
                 event = cpuhw->limited_counter[i];
                 event->hw.idx = cpuhw->limited_hwidx[i];
                 val = (event->hw.idx == 5) ? pmc5 : pmc6;
-                atomic64_set(&event->hw.prev_count, val);
+                local64_set(&event->hw.prev_count, val);
                 perf_event_update_userpage(event);
         }
 }
@@ -666,11 +666,11 @@ void hw_perf_enable(void)
                 }
                 val = 0;
                 if (event->hw.sample_period) {
-                        left = atomic64_read(&event->hw.period_left);
+                        left = local64_read(&event->hw.period_left);
                         if (left < 0x80000000L)
                                 val = 0x80000000L - left;
                 }
-                atomic64_set(&event->hw.prev_count, val);
+                local64_set(&event->hw.prev_count, val);
                 event->hw.idx = idx;
                 write_pmc(idx, val);
                 perf_event_update_userpage(event);
@@ -754,7 +754,7 @@ static int power_pmu_enable(struct perf_event *event)
          * skip the schedulability test here, it will be peformed
          * at commit time(->commit_txn) as a whole
          */
-        if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuhw->group_flag & PERF_EVENT_TXN)
                 goto nocheck;
 
         if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
@@ -842,8 +842,8 @@ static void power_pmu_unthrottle(struct perf_event *event)
         if (left < 0x80000000L)
                 val = 0x80000000L - left;
         write_pmc(event->hw.idx, val);
-        atomic64_set(&event->hw.prev_count, val);
-        atomic64_set(&event->hw.period_left, left);
+        local64_set(&event->hw.prev_count, val);
+        local64_set(&event->hw.period_left, left);
         perf_event_update_userpage(event);
         perf_enable();
         local_irq_restore(flags);
@@ -858,7 +858,7 @@ void power_pmu_start_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-        cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuhw->group_flag |= PERF_EVENT_TXN;
         cpuhw->n_txn_start = cpuhw->n_events;
 }
 
@@ -871,7 +871,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-        cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        cpuhw->group_flag &= ~PERF_EVENT_TXN;
 }
 
 /*
@@ -897,6 +897,7 @@ int power_pmu_commit_txn(const struct pmu *pmu)
         for (i = cpuhw->n_txn_start; i < n; ++i)
                 cpuhw->event[i]->hw.config = cpuhw->events[i];
 
+        cpuhw->group_flag &= ~PERF_EVENT_TXN;
         return 0;
 }
 
@@ -1108,7 +1109,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
         event->hw.config = events[n];
         event->hw.event_base = cflags[n];
         event->hw.last_period = event->hw.sample_period;
-        atomic64_set(&event->hw.period_left, event->hw.last_period);
+        local64_set(&event->hw.period_left, event->hw.last_period);
 
         /*
          * See if we need to reserve the PMU.
@@ -1146,16 +1147,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
         int record = 0;
 
         /* we don't have to worry about interrupts here */
-        prev = atomic64_read(&event->hw.prev_count);
+        prev = local64_read(&event->hw.prev_count);
         delta = (val - prev) & 0xfffffffful;
-        atomic64_add(delta, &event->count);
+        local64_add(delta, &event->count);
 
         /*
          * See if the total period for this event has expired,
          * and update for the next period.
          */
         val = 0;
-        left = atomic64_read(&event->hw.period_left) - delta;
+        left = local64_read(&event->hw.period_left) - delta;
         if (period) {
                 if (left <= 0) {
                         left += period;
@@ -1193,8 +1194,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
         }
 
         write_pmc(event->hw.idx, val);
-        atomic64_set(&event->hw.prev_count, val);
-        atomic64_set(&event->hw.period_left, left);
+        local64_set(&event->hw.prev_count, val);
+        local64_set(&event->hw.period_left, left);
         perf_event_update_userpage(event);
 }
 
diff --git a/arch/s390/include/asm/local64.h b/arch/s390/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/s390/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/score/include/asm/local64.h b/arch/score/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/score/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/sh/include/asm/local64.h b/arch/sh/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/sh/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 81b6de41ae5d..7a3dc3567258 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -185,10 +185,10 @@ static void sh_perf_event_update(struct perf_event *event,
          * this is the simplest approach for maintaining consistency.
          */
 again:
-        prev_raw_count = atomic64_read(&hwc->prev_count);
+        prev_raw_count = local64_read(&hwc->prev_count);
         new_raw_count = sh_pmu->read(idx);
 
-        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
                              new_raw_count) != prev_raw_count)
                 goto again;
 
@@ -203,7 +203,7 @@ again:
         delta = (new_raw_count << shift) - (prev_raw_count << shift);
         delta >>= shift;
 
-        atomic64_add(delta, &event->count);
+        local64_add(delta, &event->count);
 }
 
 static void sh_pmu_disable(struct perf_event *event)
diff --git a/arch/sparc/include/asm/local64.h b/arch/sparc/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/sparc/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index 7e2669894ce8..74c4e0cd889c 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -6,7 +6,15 @@ extern void set_perf_event_pending(void);
 #define PERF_EVENT_INDEX_OFFSET 0
 
 #ifdef CONFIG_PERF_EVENTS
+#include <asm/ptrace.h>
+
 extern void init_hw_perf_events(void);
+
+extern void
+__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+#define perf_arch_fetch_caller_regs(pt_regs, ip)        \
+        __perf_arch_fetch_caller_regs(pt_regs, ip, 1);
 #else
 static inline void init_hw_perf_events(void)    { }
 #endif
diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 92090cc9e829..682fee06a16b 100644
--- a/arch/sparc/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
@@ -47,9 +47,9 @@ stack_trace_flush:
         .size           stack_trace_flush,.-stack_trace_flush
 
 #ifdef CONFIG_PERF_EVENTS
-        .globl          perf_arch_fetch_caller_regs
-        .type           perf_arch_fetch_caller_regs,#function
-perf_arch_fetch_caller_regs:
+        .globl          __perf_arch_fetch_caller_regs
+        .type           __perf_arch_fetch_caller_regs,#function
+__perf_arch_fetch_caller_regs:
         /* We always read the %pstate into %o5 since we will use
          * that to construct a fake %tstate to store into the regs.
          */
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 0ec92c8861dd..8a6660da8e08 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -572,18 +572,18 @@ static u64 sparc_perf_event_update(struct perf_event *event,
         s64 delta;
 
 again:
-        prev_raw_count = atomic64_read(&hwc->prev_count);
+        prev_raw_count = local64_read(&hwc->prev_count);
         new_raw_count = read_pmc(idx);
 
-        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
                              new_raw_count) != prev_raw_count)
                 goto again;
 
         delta = (new_raw_count << shift) - (prev_raw_count << shift);
         delta >>= shift;
 
-        atomic64_add(delta, &event->count);
-        atomic64_sub(delta, &hwc->period_left);
+        local64_add(delta, &event->count);
+        local64_sub(delta, &hwc->period_left);
 
         return new_raw_count;
 }
@@ -591,27 +591,27 @@ again:
 static int sparc_perf_event_set_period(struct perf_event *event,
                                        struct hw_perf_event *hwc, int idx)
 {
-        s64 left = atomic64_read(&hwc->period_left);
+        s64 left = local64_read(&hwc->period_left);
         s64 period = hwc->sample_period;
         int ret = 0;
 
         if (unlikely(left <= -period)) {
                 left = period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
 
         if (unlikely(left <= 0)) {
                 left += period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
         if (left > MAX_PERIOD)
                 left = MAX_PERIOD;
 
-        atomic64_set(&hwc->prev_count, (u64)-left);
+        local64_set(&hwc->prev_count, (u64)-left);
 
         write_pmc(idx, (u64)(-left) & 0xffffffff);
 
@@ -1005,7 +1005,7 @@ static int sparc_pmu_enable(struct perf_event *event)
          * skip the schedulability test here, it will be peformed
          * at commit time(->commit_txn) as a whole
          */
-        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuc->group_flag & PERF_EVENT_TXN)
                 goto nocheck;
 
         if (check_excludes(cpuc->event, n0, 1))
@@ -1087,7 +1087,7 @@ static int __hw_perf_event_init(struct perf_event *event)
         if (!hwc->sample_period) {
                 hwc->sample_period = MAX_PERIOD;
                 hwc->last_period = hwc->sample_period;
-                atomic64_set(&hwc->period_left, hwc->sample_period);
+                local64_set(&hwc->period_left, hwc->sample_period);
         }
 
         return 0;
@@ -1102,7 +1102,7 @@ static void sparc_pmu_start_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-        cpuhw->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
 /*
@@ -1114,7 +1114,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-        cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        cpuhw->group_flag &= ~PERF_EVENT_TXN;
 }
 
 /*
@@ -1137,6 +1137,7 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu)
         if (sparc_check_constraints(cpuc->event, cpuc->events, n))
                 return -EAGAIN;
 
+        cpuc->group_flag &= ~PERF_EVENT_TXN;
         return 0;
 }
 
diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/x86/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 254883d0c7e0..6e742cc4251b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -68,8 +68,9 @@ union cpuid10_eax {
 
 union cpuid10_edx {
         struct {
-                unsigned int num_counters_fixed:4;
-                unsigned int reserved:28;
+                unsigned int num_counters_fixed:5;
+                unsigned int bit_width_fixed:8;
+                unsigned int reserved:19;
         } split;
         unsigned int full;
 };
@@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)   perf_misc_flags(regs)
 
+#include <asm/stacktrace.h>
+
+/*
+ * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
+ * and the comment with PERF_EFLAGS_EXACT.
+ */
+#define perf_arch_fetch_caller_regs(regs, __ip)         {       \
+        (regs)->ip = (__ip);                                    \
+        (regs)->bp = caller_frame_pointer();                    \
+        (regs)->cs = __KERNEL_CS;                               \
+        regs->flags = 0;                                        \
+}
+
 #else
 static inline void init_hw_perf_events(void)            { }
 static inline void perf_events_lapic_init(void) { }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 4dab78edbad9..2b16a2ad23dc 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -1,6 +1,13 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
 #ifndef _ASM_X86_STACKTRACE_H
 #define _ASM_X86_STACKTRACE_H
 
+#include <linux/uaccess.h>
+
 extern int kstack_depth_to_print;
 
 struct thread_info;
@@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data);
 
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+        struct stack_frame *next_frame;
+        unsigned long return_address;
+};
+
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
+static inline unsigned long caller_frame_pointer(void)
+{
+        struct stack_frame *frame;
+
+        get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+        frame = frame->next_frame;
+#endif
+
+        return (unsigned long)frame;
+}
+
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5db5b7d65a18..f2da20fda02d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -220,6 +220,7 @@ struct x86_pmu {
                                                  struct perf_event *event);
         struct event_constraint *event_constraints;
         void            (*quirks)(void);
+        int             perfctr_second_write;
 
         int             (*cpu_prepare)(int cpu);
         void            (*cpu_starting)(int cpu);
@@ -295,10 +296,10 @@ x86_perf_event_update(struct perf_event *event)
          * count to the generic event atomically:
          */
 again:
-        prev_raw_count = atomic64_read(&hwc->prev_count);
+        prev_raw_count = local64_read(&hwc->prev_count);
         rdmsrl(hwc->event_base + idx, new_raw_count);
 
-        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
                                         new_raw_count) != prev_raw_count)
                 goto again;
 
@@ -313,8 +314,8 @@ again:
         delta = (new_raw_count << shift) - (prev_raw_count << shift);
         delta >>= shift;
 
-        atomic64_add(delta, &event->count);
-        atomic64_sub(delta, &hwc->period_left);
+        local64_add(delta, &event->count);
+        local64_sub(delta, &hwc->period_left);
 
         return new_raw_count;
 }
@@ -438,7 +439,7 @@ static int x86_setup_perfctr(struct perf_event *event)
         if (!hwc->sample_period) {
                 hwc->sample_period = x86_pmu.max_period;
                 hwc->last_period = hwc->sample_period;
-                atomic64_set(&hwc->period_left, hwc->sample_period);
+                local64_set(&hwc->period_left, hwc->sample_period);
         } else {
                 /*
                  * If we have a PMU initialized but no APIC
@@ -885,7 +886,7 @@ static int
 x86_perf_event_set_period(struct perf_event *event)
 {
         struct hw_perf_event *hwc = &event->hw;
-        s64 left = atomic64_read(&hwc->period_left);
+        s64 left = local64_read(&hwc->period_left);
         s64 period = hwc->sample_period;
         int ret = 0, idx = hwc->idx;
 
@@ -897,14 +898,14 @@ x86_perf_event_set_period(struct perf_event *event)
          */
         if (unlikely(left <= -period)) {
                 left = period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
 
         if (unlikely(left <= 0)) {
                 left += period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
@@ -923,10 +924,19 @@ x86_perf_event_set_period(struct perf_event *event)
          * The hw event starts counting from this event offset,
          * mark it to be able to extra future deltas:
          */
-        atomic64_set(&hwc->prev_count, (u64)-left);
+        local64_set(&hwc->prev_count, (u64)-left);
 
-        wrmsrl(hwc->event_base + idx,
+        wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+
+        /*
+         * Due to erratum on certan cpu we need
+         * a second write to be sure the register
+         * is updated properly
+         */
+        if (x86_pmu.perfctr_second_write) {
+                wrmsrl(hwc->event_base + idx,
                         (u64)(-left) & x86_pmu.cntval_mask);
+        }
 
         perf_event_update_userpage(event);
 
@@ -969,7 +979,7 @@ static int x86_pmu_enable(struct perf_event *event)
          * skip the schedulability test here, it will be peformed
          * at commit time(->commit_txn) as a whole
          */
-        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuc->group_flag & PERF_EVENT_TXN)
                 goto out;
 
         ret = x86_pmu.schedule_events(cpuc, n, assign);
@@ -1096,7 +1106,7 @@ static void x86_pmu_disable(struct perf_event *event)
          * The events never got scheduled and ->cancel_txn will truncate
          * the event_list.
          */
-        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuc->group_flag & PERF_EVENT_TXN)
                 return;
 
         x86_pmu_stop(event);
@@ -1388,7 +1398,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-        cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuc->group_flag |= PERF_EVENT_TXN;
         cpuc->n_txn = 0;
 }
 
@@ -1401,7 +1411,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-        cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        cpuc->group_flag &= ~PERF_EVENT_TXN;
         /*
          * Truncate the collected events.
          */
@@ -1435,11 +1445,7 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
          */
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
-        /*
-         * Clear out the txn count so that ->cancel_txn() which gets
-         * run after ->commit_txn() doesn't undo things.
-         */
-        cpuc->n_txn = 0;
+        cpuc->group_flag &= ~PERF_EVENT_TXN;
 
         return 0;
 }
@@ -1607,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = {
         .walk_stack             = print_context_stack_bp,
 };
 
-#include "../dumpstack.h"
-
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
@@ -1730,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return entry;
 }
 
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-        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;
-        /*
-         * We abuse bit 3 to pass exact information, see perf_misc_flags
-         * and the comment with PERF_EFLAGS_EXACT.
-         */
-        regs->flags = 0;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
         unsigned long ip;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ae85d69644d1..9286e736a70a 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -829,6 +829,15 @@ static __initconst const struct x86_pmu p4_pmu = {
         .max_period             = (1ULL << 39) - 1,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
+        /*
+         * This handles erratum N15 in intel doc 249199-029,
+         * the counter may not be updated correctly on write
+         * so we need a second write operation to do the trick
+         * (the official workaround didn't work)
+         *
+         * the former idea is taken from OProfile code
+         */
+        .perfctr_second_write   = 1,
 };
 
 static __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c89a386930b7..6e8752c1bd52 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,7 +18,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
deleted file mode 100644
index e1a93be4fd44..000000000000
--- a/arch/x86/kernel/dumpstack.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
- */
-
-#ifndef DUMPSTACK_H
-#define DUMPSTACK_H
-
-#ifdef CONFIG_X86_32
-#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-#else
-#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-#endif
-
-#include <linux/uaccess.h>
-
-extern void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp, char *log_lvl);
-
-extern void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *sp, unsigned long bp, char *log_lvl);
-
-extern unsigned int code_bytes;
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-        struct stack_frame *next_frame;
-        unsigned long return_address;
-};
-
-struct stack_frame_ia32 {
-    u32 next_frame;
-    u32 return_address;
-};
-
-static inline unsigned long rewind_frame_pointer(int n)
-{
-        struct stack_frame *frame;
-
-        get_bp(frame);
-
-#ifdef CONFIG_FRAME_POINTER
-        while (n--) {
-                if (probe_kernel_address(&frame->next_frame, frame))
-                        break;
-        }
-#endif
-
-        return (unsigned long)frame;
-}
-
-#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 11540a189d93..0f6376ffa2d9 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,8 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
-
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 272c9f1f05f3..57a21f11c791 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,7 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 #define N_EXCEPTION_STACKS_END \
                 (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 922eefbb3f6c..b53c525368a7 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name)
         return 0;
 }
 
-static void save_stack_address(void *data, unsigned long addr, int reliable)
+static void
+__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
 {
         struct stack_trace *trace = data;
+#ifdef CONFIG_FRAME_POINTER
         if (!reliable)
                 return;
+#endif
+        if (nosched && in_sched_functions(addr))
+                return;
         if (trace->skip > 0) {
                 trace->skip--;
                 return;
@@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable)
                 trace->entries[trace->nr_entries++] = addr;
 }
 
+static void save_stack_address(void *data, unsigned long addr, int reliable)
+{
+        return __save_stack_address(data, addr, reliable, false);
+}
+
 static void
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
-        struct stack_trace *trace = (struct stack_trace *)data;
-        if (!reliable)
-                return;
-        if (in_sched_functions(addr))
-                return;
-        if (trace->skip > 0) {
-                trace->skip--;
-                return;
-        }
-        if (trace->nr_entries < trace->max_entries)
-                trace->entries[trace->nr_entries++] = addr;
+        return __save_stack_address(data, addr, reliable, true);
 }
 
 static const struct stacktrace_ops save_stack_ops = {
@@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
-struct stack_frame {
+struct stack_frame_user {
         const void __user       *next_fp;
         unsigned long           ret_addr;
 };
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+static int
+copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 {
         int ret;
 
@@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
                 trace->entries[trace->nr_entries++] = regs->ip;
 
         while (trace->nr_entries < trace->max_entries) {
-                struct stack_frame frame;
+                struct stack_frame_user frame;
 
                 frame.next_fp = NULL;
                 frame.ret_addr = 0;
diff --git a/arch/xtensa/include/asm/local64.h b/arch/xtensa/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/xtensa/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>