113 files changed, 1268 insertions, 1884 deletions

diff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace
deleted file mode 100644
index 5e6a92a02d85..000000000000
--- a/Documentation/ABI/testing/debugfs-kmemtrace
+++ /dev/null
@@ -1,71 +0,0 @@
-What:           /sys/kernel/debug/kmemtrace/
-Date:           July 2008
-Contact:        Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-Description:
-
-In kmemtrace-enabled kernels, the following files are created:
-
-/sys/kernel/debug/kmemtrace/
-        cpu<n>          (0400)  Per-CPU tracing data, see below. (binary)
-        total_overruns  (0400)  Total number of bytes which were dropped from
-                                cpu<n> files because of full buffer condition,
-                                non-binary. (text)
-        abi_version     (0400)  Kernel's kmemtrace ABI version. (text)
-
-Each per-CPU file should be read according to the relay interface. That is,
-the reader should set affinity to that specific CPU and, as currently done by
-the userspace application (though there are other methods), use poll() with
-an infinite timeout before every read(). Otherwise, erroneous data may be
-read. The binary data has the following _core_ format:
-
-        Event ID        (1 byte)        Unsigned integer, one of:
-                0 - represents an allocation (KMEMTRACE_EVENT_ALLOC)
-                1 - represents a freeing of previously allocated memory
-                    (KMEMTRACE_EVENT_FREE)
-        Type ID         (1 byte)        Unsigned integer, one of:
-                0 - this is a kmalloc() / kfree()
-                1 - this is a kmem_cache_alloc() / kmem_cache_free()
-                2 - this is a __get_free_pages() et al.
-        Event size      (2 bytes)       Unsigned integer representing the
-                                        size of this event. Used to extend
-                                        kmemtrace. Discard the bytes you
-                                        don't know about.
-        Sequence number (4 bytes)       Signed integer used to reorder data
-                                        logged on SMP machines. Wraparound
-                                        must be taken into account, although
-                                        it is unlikely.
-        Caller address  (8 bytes)       Return address to the caller.
-        Pointer to mem  (8 bytes)       Pointer to target memory area. Can be
-                                        NULL, but not all such calls might be
-                                        recorded.
-
-In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow:
-
-        Requested bytes (8 bytes)       Total number of requested bytes,
-                                        unsigned, must not be zero.
-        Allocated bytes (8 bytes)       Total number of actually allocated
-                                        bytes, unsigned, must not be lower
-                                        than requested bytes.
-        Requested flags (4 bytes)       GFP flags supplied by the caller.
-        Target CPU      (4 bytes)       Signed integer, valid for event id 1.
-                                        If equal to -1, target CPU is the same
-                                        as origin CPU, but the reverse might
-                                        not be true.
-
-The data is made available in the same endianness the machine has.
-
-Other event ids and type ids may be defined and added. Other fields may be
-added by increasing event size, but see below for details.
-Every modification to the ABI, including new id definitions, are followed
-by bumping the ABI version by one.
-
-Adding new data to the packet (features) is done at the end of the mandatory
-data:
-        Feature size    (2 byte)
-        Feature ID      (1 byte)
-        Feature data    (Feature size - 3 bytes)
-
-
-Users:
-        kmemtrace-user - git://repo.or.cz/kmemtrace-user.git
-
diff --git a/Documentation/trace/kmemtrace.txt b/Documentation/trace/kmemtrace.txt
deleted file mode 100644
index 6308735e58ca..000000000000
--- a/Documentation/trace/kmemtrace.txt
+++ /dev/null
@@ -1,126 +0,0 @@
-                        kmemtrace - Kernel Memory Tracer
-
-                          by Eduard - Gabriel Munteanu
-                             <eduard.munteanu@linux360.ro>
-
-I. Introduction
-===============
-
-kmemtrace helps kernel developers figure out two things:
-1) how different allocators (SLAB, SLUB etc.) perform
-2) how kernel code allocates memory and how much
-
-To do this, we trace every allocation and export information to the userspace
-through the relay interface. We export things such as the number of requested
-bytes, the number of bytes actually allocated (i.e. including internal
-fragmentation), whether this is a slab allocation or a plain kmalloc() and so
-on.
-
-The actual analysis is performed by a userspace tool (see section III for
-details on where to get it from). It logs the data exported by the kernel,
-processes it and (as of writing this) can provide the following information:
-- the total amount of memory allocated and fragmentation per call-site
-- the amount of memory allocated and fragmentation per allocation
-- total memory allocated and fragmentation in the collected dataset
-- number of cross-CPU allocation and frees (makes sense in NUMA environments)
-
-Moreover, it can potentially find inconsistent and erroneous behavior in
-kernel code, such as using slab free functions on kmalloc'ed memory or
-allocating less memory than requested (but not truly failed allocations).
-
-kmemtrace also makes provisions for tracing on some arch and analysing the
-data on another.
-
-II. Design and goals
-====================
-
-kmemtrace was designed to handle rather large amounts of data. Thus, it uses
-the relay interface to export whatever is logged to userspace, which then
-stores it. Analysis and reporting is done asynchronously, that is, after the
-data is collected and stored. By design, it allows one to log and analyse
-on different machines and different arches.
-
-As of writing this, the ABI is not considered stable, though it might not
-change much. However, no guarantees are made about compatibility yet. When
-deemed stable, the ABI should still allow easy extension while maintaining
-backward compatibility. This is described further in Documentation/ABI.
-
-Summary of design goals:
-        - allow logging and analysis to be done across different machines
-        - be fast and anticipate usage in high-load environments (*)
-        - be reasonably extensible
-        - make it possible for GNU/Linux distributions to have kmemtrace
-        included in their repositories
-
-(*) - one of the reasons Pekka Enberg's original userspace data analysis
-    tool's code was rewritten from Perl to C (although this is more than a
-    simple conversion)
-
-
-III. Quick usage guide
-======================
-
-1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable
-CONFIG_KMEMTRACE).
-
-2) Get the userspace tool and build it:
-$ git clone git://repo.or.cz/kmemtrace-user.git         # current repository
-$ cd kmemtrace-user/
-$ ./autogen.sh
-$ ./configure
-$ make
-
-3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the
-'single' runlevel (so that relay buffers don't fill up easily), and run
-kmemtrace:
-# '$' does not mean user, but root here.
-$ mount -t debugfs none /sys/kernel/debug
-$ mount -t proc none /proc
-$ cd path/to/kmemtrace-user/
-$ ./kmemtraced
-Wait a bit, then stop it with CTRL+C.
-$ cat /sys/kernel/debug/kmemtrace/total_overruns        # Check if we didn't
-                                                        # overrun, should
-                                                        # be zero.
-$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to
-                check its correctness]
-$ ./kmemtrace-report
-
-Now you should have a nice and short summary of how the allocator performs.
-
-IV. FAQ and known issues
-========================
-
-Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix
-this? Should I worry?
-A: If it's non-zero, this affects kmemtrace's accuracy, depending on how
-large the number is. You can fix it by supplying a higher
-'kmemtrace.subbufs=N' kernel parameter.
----
-
-Q: kmemtrace_check reports errors, how do I fix this? Should I worry?
-A: This is a bug and should be reported. It can occur for a variety of
-reasons:
-        - possible bugs in relay code
-        - possible misuse of relay by kmemtrace
-        - timestamps being collected unorderly
-Or you may fix it yourself and send us a patch.
----
-
-Q: kmemtrace_report shows many errors, how do I fix this? Should I worry?
-A: This is a known issue and I'm working on it. These might be true errors
-in kernel code, which may have inconsistent behavior (e.g. allocating memory
-with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed
-out this behavior may work with SLAB, but may fail with other allocators.
-
-It may also be due to lack of tracing in some unusual allocator functions.
-
-We don't want bug reports regarding this issue yet.
----
-
-V. See also
-===========
-
-Documentation/kernel-parameters.txt
-Documentation/ABI/testing/debugfs-kmemtrace
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 6d119c98b89b..b7ae5fb9f8bc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3368,13 +3368,6 @@ F:	include/linux/kmemleak.h
 F:      mm/kmemleak.c
 F:      mm/kmemleak-test.c
 
-KMEMTRACE
-M:      Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-S:      Maintained
-F:      Documentation/trace/kmemtrace.txt
-F:      include/linux/kmemtrace.h
-F:      kernel/trace/kmemtrace.c
-
 KPROBES
 M:      Ananth N Mavinakayanahalli <ananth@in.ibm.com>
 M:      Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
diff --git a/Makefile b/Makefile
index d49d96c35ce5..865718f4bcea 100644
--- a/Makefile
+++ b/Makefile
@@ -414,7 +414,7 @@ endif
 no-dot-config-targets := clean mrproper distclean \
                          cscope TAGS tags help %docs check% \
                          include/linux/version.h headers_% \
-                         kernelrelease kernelversion
+                         kernelrelease kernelversion %src-pkg
 
 config-targets := 0
 mixed-targets  := 0
@@ -1228,6 +1228,8 @@ distclean: mrproper
 # rpm target kept for backward compatibility
 package-dir     := $(srctree)/scripts/package
 
+%src-pkg: FORCE
+        $(Q)$(MAKE) $(build)=$(package-dir) $@
 %pkg: include/config/kernel.release FORCE
         $(Q)$(MAKE) $(build)=$(package-dir) $@
 rpm: include/config/kernel.release FORCE
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>
diff --git a/fs/exec.c b/fs/exec.c
index e19de6a80339..97d91a03fb13 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -653,6 +653,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
         else
                 stack_base = vma->vm_start - stack_expand;
 #endif
+        current->mm->start_stack = bprm->p;
         ret = expand_stack(vma, stack_base);
         if (ret)
                 ret = -EFAULT;
diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h
new file mode 100644
index 000000000000..02ac760c1a8b
--- /dev/null
+++ b/include/asm-generic/local64.h
@@ -0,0 +1,96 @@
+#ifndef _ASM_GENERIC_LOCAL64_H
+#define _ASM_GENERIC_LOCAL64_H
+
+#include <linux/percpu.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic64_t.  Which is
+ * rather pointless.  The whole point behind local64_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local64_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+#if BITS_PER_LONG == 64
+
+#include <asm/local.h>
+
+typedef struct {
+        local_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i) { LOCAL_INIT(i) }
+
+#define local64_read(l)         local_read(&(l)->a)
+#define local64_set(l,i)        local_set((&(l)->a),(i))
+#define local64_inc(l)          local_inc(&(l)->a)
+#define local64_dec(l)          local_dec(&(l)->a)
+#define local64_add(i,l)        local_add((i),(&(l)->a))
+#define local64_sub(i,l)        local_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) local_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) local_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) local_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)   local_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)      local_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)        local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)        local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)      local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)      local64_set((l), local64_read(l) - (i))
+
+#else /* BITS_PER_LONG != 64 */
+
+#include <asm/atomic.h>
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct {
+        atomic64_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i) { ATOMIC_LONG_INIT(i) }
+
+#define local64_read(l)         atomic64_read(&(l)->a)
+#define local64_set(l,i)        atomic64_set((&(l)->a),(i))
+#define local64_inc(l)          atomic64_inc(&(l)->a)
+#define local64_dec(l)          atomic64_dec(&(l)->a)
+#define local64_add(i,l)        atomic64_add((i),(&(l)->a))
+#define local64_sub(i,l)        atomic64_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)   atomic64_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)      atomic64_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)        local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)        local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)      local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)      local64_set((l), local64_read(l) - (i))
+
+#endif /* BITS_PER_LONG != 64 */
+
+#endif /* _ASM_GENERIC_LOCAL64_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 3167f2df4126..0af31cd335d6 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -257,8 +257,7 @@ static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
                        u64 count, struct pt_regs *regs, void *head)
 {
-        perf_tp_event(addr, count, raw_data, size, regs, head);
-        perf_swevent_put_recursion_context(rctx);
+        perf_tp_event(addr, count, raw_data, size, regs, head, rctx);
 }
 #endif
 
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
deleted file mode 100644
index b616d3930c3b..000000000000
--- a/include/linux/kmemtrace.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <trace/events/kmem.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5d0266d94985..63b5aa5dce69 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -214,8 +214,9 @@ struct perf_event_attr {
                                  *  See also PERF_RECORD_MISC_EXACT_IP
                                  */
                                 precise_ip     :  2, /* skid constraint       */
+                                mmap_data      :  1, /* non-exec mmap data    */
 
-                                __reserved_1   : 47;
+                                __reserved_1   : 46;
 
         union {
                 __u32           wakeup_events;    /* wakeup every n events */
@@ -461,6 +462,7 @@ enum perf_callchain_context {
 
 #ifdef CONFIG_PERF_EVENTS
 # include <asm/perf_event.h>
+# include <asm/local64.h>
 #endif
 
 struct perf_guest_info_callbacks {
@@ -535,10 +537,10 @@ struct hw_perf_event {
                 struct arch_hw_breakpoint       info;
 #endif
         };
-        atomic64_t                      prev_count;
+        local64_t                       prev_count;
         u64                             sample_period;
         u64                             last_period;
-        atomic64_t                      period_left;
+        local64_t                       period_left;
         u64                             interrupts;
 
         u64                             freq_time_stamp;
@@ -548,7 +550,10 @@ struct hw_perf_event {
 
 struct perf_event;
 
-#define PERF_EVENT_TXN_STARTED 1
+/*
+ * Common implementation detail of pmu::{start,commit,cancel}_txn
+ */
+#define PERF_EVENT_TXN 0x1
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -562,14 +567,28 @@ struct pmu {
         void (*unthrottle)              (struct perf_event *event);
 
         /*
-         * group events scheduling is treated as a transaction,
-         * add group events as a whole and perform one schedulability test.
-         * If test fails, roll back the whole group
+         * Group events scheduling is treated as a transaction, add group
+         * events as a whole and perform one schedulability test. If the test
+         * fails, roll back the whole group
          */
 
+        /*
+         * Start the transaction, after this ->enable() doesn't need
+         * to do schedulability tests.
+         */
         void (*start_txn)       (const struct pmu *pmu);
-        void (*cancel_txn)      (const struct pmu *pmu);
+        /*
+         * If ->start_txn() disabled the ->enable() schedulability test
+         * then ->commit_txn() is required to perform one. On success
+         * the transaction is closed. On error the transaction is kept
+         * open until ->cancel_txn() is called.
+         */
         int  (*commit_txn)      (const struct pmu *pmu);
+        /*
+         * Will cancel the transaction, assumes ->disable() is called for
+         * each successfull ->enable() during the transaction.
+         */
+        void (*cancel_txn)      (const struct pmu *pmu);
 };
 
 /**
@@ -584,7 +603,9 @@ enum perf_event_active_state {
 
 struct file;
 
-struct perf_mmap_data {
+#define PERF_BUFFER_WRITABLE            0x01
+
+struct perf_buffer {
         atomic_t                        refcount;
         struct rcu_head                 rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
@@ -650,7 +671,8 @@ struct perf_event {
 
         enum perf_event_active_state    state;
         unsigned int                    attach_state;
-        atomic64_t                      count;
+        local64_t                       count;
+        atomic64_t                      child_count;
 
         /*
          * These are the total time in nanoseconds that the event
@@ -709,7 +731,7 @@ struct perf_event {
         atomic_t                        mmap_count;
         int                             mmap_locked;
         struct user_struct              *mmap_user;
-        struct perf_mmap_data           *data;
+        struct perf_buffer              *buffer;
 
         /* poll related */
         wait_queue_head_t               waitq;
@@ -807,7 +829,7 @@ struct perf_cpu_context {
 
 struct perf_output_handle {
         struct perf_event               *event;
-        struct perf_mmap_data           *data;
+        struct perf_buffer              *buffer;
         unsigned long                   wakeup;
         unsigned long                   size;
         void                            *addr;
@@ -910,8 +932,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-extern void
-perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+#ifndef perf_arch_fetch_caller_regs
+static inline void
+perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { }
+#endif
 
 /*
  * Take a snapshot of the regs. Skip ip and frame pointer to
@@ -921,31 +945,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
  * - bp for callchains
  * - eflags, for future purposes, just in case
  */
-static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
-        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);
+        perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
 static inline void
@@ -955,21 +959,14 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
                 struct pt_regs hot_regs;
 
                 if (!regs) {
-                        perf_fetch_caller_regs(&hot_regs, 1);
+                        perf_fetch_caller_regs(&hot_regs);
                         regs = &hot_regs;
                 }
                 __perf_sw_event(event_id, nr, nmi, regs, addr);
         }
 }
 
-extern void __perf_event_mmap(struct vm_area_struct *vma);
-
-static inline void perf_event_mmap(struct vm_area_struct *vma)
-{
-        if (vma->vm_flags & VM_EXEC)
-                __perf_event_mmap(vma);
-}
-
+extern void perf_event_mmap(struct vm_area_struct *vma);
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -1001,7 +998,7 @@ static inline bool perf_paranoid_kernel(void)
 extern void perf_event_init(void);
 extern void perf_tp_event(u64 addr, u64 count, void *record,
                           int entry_size, struct pt_regs *regs,
-                          struct hlist_head *head);
+                          struct hlist_head *head, int rctx);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 1812dac8c496..1acfa73ce2ac 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,8 @@
 #include <asm/page.h>           /* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>          /* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <linux/kmemtrace.h>
+
+#include <trace/events/kmem.h>
 
 #ifndef ARCH_KMALLOC_MINALIGN
 /*
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 4ba59cfc1f75..6447a723ecb1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,9 +10,10 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <linux/kmemtrace.h>
 #include <linux/kmemleak.h>
 
+#include <trace/events/kmem.h>
+
 enum stat_item {
         ALLOC_FASTPATH,         /* Allocation from cpu slab */
         ALLOC_SLOWPATH,         /* Allocation by getting a new cpu slab */
diff --git a/include/trace/boot.h b/include/trace/boot.h
deleted file mode 100644
index 088ea089e31d..000000000000
--- a/include/trace/boot.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _LINUX_TRACE_BOOT_H
-#define _LINUX_TRACE_BOOT_H
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/init.h>
-
-/*
- * Structure which defines the trace of an initcall
- * while it is called.
- * You don't have to fill the func field since it is
- * only used internally by the tracer.
- */
-struct boot_trace_call {
-        pid_t                   caller;
-        char                    func[KSYM_SYMBOL_LEN];
-};
-
-/*
- * Structure which defines the trace of an initcall
- * while it returns.
- */
-struct boot_trace_ret {
-        char                    func[KSYM_SYMBOL_LEN];
-        int                             result;
-        unsigned long long      duration;               /* nsecs */
-};
-
-#ifdef CONFIG_BOOT_TRACER
-/* Append the traces on the ring-buffer */
-extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
-extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
-
-/* Tells the tracer that smp_pre_initcall is finished.
- * So we can start the tracing
- */
-extern void start_boot_trace(void);
-
-/* Resume the tracing of other necessary events
- * such as sched switches
- */
-extern void enable_boot_trace(void);
-
-/* Suspend this tracing. Actually, only sched_switches tracing have
- * to be suspended. Initcalls doesn't need it.)
- */
-extern void disable_boot_trace(void);
-#else
-static inline
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
-
-static inline
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
-
-static inline void start_boot_trace(void) { }
-static inline void enable_boot_trace(void) { }
-static inline void disable_boot_trace(void) { }
-#endif /* CONFIG_BOOT_TRACER */
-
-#endif /* __LINUX_TRACE_BOOT_H */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 5a64905d7278..fc013a8201e9 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -705,7 +705,7 @@ perf_trace_##call(void *__data, proto)					\
         int __data_size;                                                \
         int rctx;                                                       \
                                                                         \
-        perf_fetch_caller_regs(&__regs, 1);                             \
+        perf_fetch_caller_regs(&__regs);                                \
                                                                         \
         __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
         __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
diff --git a/init/main.c b/init/main.c
index 3bdb152f412f..e2a2bf3a169f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -66,11 +66,9 @@
 #include <linux/ftrace.h>
 #include <linux/async.h>
 #include <linux/kmemcheck.h>
-#include <linux/kmemtrace.h>
 #include <linux/sfi.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
-#include <trace/boot.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -653,7 +651,6 @@ asmlinkage void __init start_kernel(void)
 #endif
         page_cgroup_init();
         enable_debug_pagealloc();
-        kmemtrace_init();
         kmemleak_init();
         debug_objects_mem_init();
         idr_init_cache();
@@ -715,38 +712,33 @@ int initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
 static char msgbuf[64];
-static struct boot_trace_call call;
-static struct boot_trace_ret ret;
 
 int do_one_initcall(initcall_t fn)
 {
         int count = preempt_count();
         ktime_t calltime, delta, rettime;
+        unsigned long long duration;
+        int ret;
 
         if (initcall_debug) {
-                call.caller = task_pid_nr(current);
-                printk("calling  %pF @ %i\n", fn, call.caller);
+                printk("calling  %pF @ %i\n", fn, task_pid_nr(current));
                 calltime = ktime_get();
-                trace_boot_call(&call, fn);
-                enable_boot_trace();
         }
 
-        ret.result = fn();
+        ret = fn();
 
         if (initcall_debug) {
-                disable_boot_trace();
                 rettime = ktime_get();
                 delta = ktime_sub(rettime, calltime);
-                ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
-                trace_boot_ret(&ret, fn);
-                printk("initcall %pF returned %d after %Ld usecs\n", fn,
-                        ret.result, ret.duration);
+                duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+                printk("initcall %pF returned %d after %lld usecs\n", fn,
+                        ret, duration);
         }
 
         msgbuf[0] = 0;
 
-        if (ret.result && ret.result != -ENODEV && initcall_debug)
-                sprintf(msgbuf, "error code %d ", ret.result);
+        if (ret && ret != -ENODEV && initcall_debug)
+                sprintf(msgbuf, "error code %d ", ret);
 
         if (preempt_count() != count) {
                 strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
@@ -760,7 +752,7 @@ int do_one_initcall(initcall_t fn)
                 printk("initcall %pF returned with %s\n", fn, msgbuf);
         }
 
-        return ret.result;
+        return ret;
 }
 
 
@@ -880,7 +872,6 @@ static int __init kernel_init(void * unused)
         smp_prepare_cpus(setup_max_cpus);
 
         do_pre_smp_initcalls();
-        start_boot_trace();
 
         smp_init();
         sched_init_smp();
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index ff86c558af4c..c772a3d4000d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -675,7 +675,6 @@ group_sched_in(struct perf_event *group_event,
         struct perf_event *event, *partial_group = NULL;
         const struct pmu *pmu = group_event->pmu;
         bool txn = false;
-        int ret;
 
         if (group_event->state == PERF_EVENT_STATE_OFF)
                 return 0;
@@ -703,14 +702,8 @@ group_sched_in(struct perf_event *group_event,
                 }
         }
 
-        if (!txn)
-                return 0;
-
-        ret = pmu->commit_txn(pmu);
-        if (!ret) {
-                pmu->cancel_txn(pmu);
+        if (!txn || !pmu->commit_txn(pmu))
                 return 0;
-        }
 
 group_error:
         /*
@@ -1155,9 +1148,9 @@ static void __perf_event_sync_stat(struct perf_event *event,
          * In order to keep per-task stats reliable we need to flip the event
          * values when we flip the contexts.
          */
-        value = atomic64_read(&next_event->count);
-        value = atomic64_xchg(&event->count, value);
-        atomic64_set(&next_event->count, value);
+        value = local64_read(&next_event->count);
+        value = local64_xchg(&event->count, value);
+        local64_set(&next_event->count, value);
 
         swap(event->total_time_enabled, next_event->total_time_enabled);
         swap(event->total_time_running, next_event->total_time_running);
@@ -1547,10 +1540,10 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 
         hwc->sample_period = sample_period;
 
-        if (atomic64_read(&hwc->period_left) > 8*sample_period) {
+        if (local64_read(&hwc->period_left) > 8*sample_period) {
                 perf_disable();
                 perf_event_stop(event);
-                atomic64_set(&hwc->period_left, 0);
+                local64_set(&hwc->period_left, 0);
                 perf_event_start(event);
                 perf_enable();
         }
@@ -1591,7 +1584,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
                 perf_disable();
                 event->pmu->read(event);
-                now = atomic64_read(&event->count);
+                now = local64_read(&event->count);
                 delta = now - hwc->freq_count_stamp;
                 hwc->freq_count_stamp = now;
 
@@ -1743,6 +1736,11 @@ static void __perf_event_read(void *info)
         event->pmu->read(event);
 }
 
+static inline u64 perf_event_count(struct perf_event *event)
+{
+        return local64_read(&event->count) + atomic64_read(&event->child_count);
+}
+
 static u64 perf_event_read(struct perf_event *event)
 {
         /*
@@ -1762,7 +1760,7 @@ static u64 perf_event_read(struct perf_event *event)
                 raw_spin_unlock_irqrestore(&ctx->lock, flags);
         }
 
-        return atomic64_read(&event->count);
+        return perf_event_count(event);
 }
 
 /*
@@ -1883,7 +1881,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void perf_pending_sync(struct perf_event *event);
-static void perf_mmap_data_put(struct perf_mmap_data *data);
+static void perf_buffer_put(struct perf_buffer *buffer);
 
 static void free_event(struct perf_event *event)
 {
@@ -1891,7 +1889,7 @@ static void free_event(struct perf_event *event)
 
         if (!event->parent) {
                 atomic_dec(&nr_events);
-                if (event->attr.mmap)
+                if (event->attr.mmap || event->attr.mmap_data)
                         atomic_dec(&nr_mmap_events);
                 if (event->attr.comm)
                         atomic_dec(&nr_comm_events);
@@ -1899,9 +1897,9 @@ static void free_event(struct perf_event *event)
                         atomic_dec(&nr_task_events);
         }
 
-        if (event->data) {
-                perf_mmap_data_put(event->data);
-                event->data = NULL;
+        if (event->buffer) {
+                perf_buffer_put(event->buffer);
+                event->buffer = NULL;
         }
 
         if (event->destroy)
@@ -2126,13 +2124,13 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 static unsigned int perf_poll(struct file *file, poll_table *wait)
 {
         struct perf_event *event = file->private_data;
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         unsigned int events = POLL_HUP;
 
         rcu_read_lock();
-        data = rcu_dereference(event->data);
-        if (data)
-                events = atomic_xchg(&data->poll, 0);
+        buffer = rcu_dereference(event->buffer);
+        if (buffer)
+                events = atomic_xchg(&buffer->poll, 0);
         rcu_read_unlock();
 
         poll_wait(file, &event->waitq, wait);
@@ -2143,7 +2141,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 static void perf_event_reset(struct perf_event *event)
 {
         (void)perf_event_read(event);
-        atomic64_set(&event->count, 0);
+        local64_set(&event->count, 0);
         perf_event_update_userpage(event);
 }
 
@@ -2342,14 +2340,14 @@ static int perf_event_index(struct perf_event *event)
 void perf_event_update_userpage(struct perf_event *event)
 {
         struct perf_event_mmap_page *userpg;
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
 
         rcu_read_lock();
-        data = rcu_dereference(event->data);
-        if (!data)
+        buffer = rcu_dereference(event->buffer);
+        if (!buffer)
                 goto unlock;
 
-        userpg = data->user_page;
+        userpg = buffer->user_page;
 
         /*
          * Disable preemption so as to not let the corresponding user-space
@@ -2359,9 +2357,9 @@ void perf_event_update_userpage(struct perf_event *event)
         ++userpg->lock;
         barrier();
         userpg->index = perf_event_index(event);
-        userpg->offset = atomic64_read(&event->count);
+        userpg->offset = perf_event_count(event);
         if (event->state == PERF_EVENT_STATE_ACTIVE)
-                userpg->offset -= atomic64_read(&event->hw.prev_count);
+                userpg->offset -= local64_read(&event->hw.prev_count);
 
         userpg->time_enabled = event->total_time_enabled +
                         atomic64_read(&event->child_total_time_enabled);
@@ -2376,6 +2374,25 @@ unlock:
         rcu_read_unlock();
 }
 
+static unsigned long perf_data_size(struct perf_buffer *buffer);
+
+static void
+perf_buffer_init(struct perf_buffer *buffer, long watermark, int flags)
+{
+        long max_size = perf_data_size(buffer);
+
+        if (watermark)
+                buffer->watermark = min(max_size, watermark);
+
+        if (!buffer->watermark)
+                buffer->watermark = max_size / 2;
+
+        if (flags & PERF_BUFFER_WRITABLE)
+                buffer->writable = 1;
+
+        atomic_set(&buffer->refcount, 1);
+}
+
 #ifndef CONFIG_PERF_USE_VMALLOC
 
 /*
@@ -2383,15 +2400,15 @@ unlock:
  */
 
 static struct page *
-perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff)
 {
-        if (pgoff > data->nr_pages)
+        if (pgoff > buffer->nr_pages)
                 return NULL;
 
         if (pgoff == 0)
-                return virt_to_page(data->user_page);
+                return virt_to_page(buffer->user_page);
 
-        return virt_to_page(data->data_pages[pgoff - 1]);
+        return virt_to_page(buffer->data_pages[pgoff - 1]);
 }
 
 static void *perf_mmap_alloc_page(int cpu)
@@ -2407,42 +2424,44 @@ static void *perf_mmap_alloc_page(int cpu)
         return page_address(page);
 }
 
-static struct perf_mmap_data *
-perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+static struct perf_buffer *
+perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         unsigned long size;
         int i;
 
-        size = sizeof(struct perf_mmap_data);
+        size = sizeof(struct perf_buffer);
         size += nr_pages * sizeof(void *);
 
-        data = kzalloc(size, GFP_KERNEL);
-        if (!data)
+        buffer = kzalloc(size, GFP_KERNEL);
+        if (!buffer)
                 goto fail;
 
-        data->user_page = perf_mmap_alloc_page(event->cpu);
-        if (!data->user_page)
+        buffer->user_page = perf_mmap_alloc_page(cpu);
+        if (!buffer->user_page)
                 goto fail_user_page;
 
         for (i = 0; i < nr_pages; i++) {
-                data->data_pages[i] = perf_mmap_alloc_page(event->cpu);
-                if (!data->data_pages[i])
+                buffer->data_pages[i] = perf_mmap_alloc_page(cpu);
+                if (!buffer->data_pages[i])
                         goto fail_data_pages;
         }
 
-        data->nr_pages = nr_pages;
+        buffer->nr_pages = nr_pages;
+
+        perf_buffer_init(buffer, watermark, flags);
 
-        return data;
+        return buffer;
 
 fail_data_pages:
         for (i--; i >= 0; i--)
-                free_page((unsigned long)data->data_pages[i]);
+                free_page((unsigned long)buffer->data_pages[i]);
 
-        free_page((unsigned long)data->user_page);
+        free_page((unsigned long)buffer->user_page);
 
 fail_user_page:
-        kfree(data);
+        kfree(buffer);
 
 fail:
         return NULL;
@@ -2456,17 +2475,17 @@ static void perf_mmap_free_page(unsigned long addr)
         __free_page(page);
 }
 
-static void perf_mmap_data_free(struct perf_mmap_data *data)
+static void perf_buffer_free(struct perf_buffer *buffer)
 {
         int i;
 
-        perf_mmap_free_page((unsigned long)data->user_page);
-        for (i = 0; i < data->nr_pages; i++)
-                perf_mmap_free_page((unsigned long)data->data_pages[i]);
-        kfree(data);
+        perf_mmap_free_page((unsigned long)buffer->user_page);
+        for (i = 0; i < buffer->nr_pages; i++)
+                perf_mmap_free_page((unsigned long)buffer->data_pages[i]);
+        kfree(buffer);
 }
 
-static inline int page_order(struct perf_mmap_data *data)
+static inline int page_order(struct perf_buffer *buffer)
 {
         return 0;
 }
@@ -2479,18 +2498,18 @@ static inline int page_order(struct perf_mmap_data *data)
  * Required for architectures that have d-cache aliasing issues.
  */
 
-static inline int page_order(struct perf_mmap_data *data)
+static inline int page_order(struct perf_buffer *buffer)
 {
-        return data->page_order;
+        return buffer->page_order;
 }
 
 static struct page *
-perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff)
 {
-        if (pgoff > (1UL << page_order(data)))
+        if (pgoff > (1UL << page_order(buffer)))
                 return NULL;
 
-        return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE);
+        return vmalloc_to_page((void *)buffer->user_page + pgoff * PAGE_SIZE);
 }
 
 static void perf_mmap_unmark_page(void *addr)
@@ -2500,57 +2519,59 @@ static void perf_mmap_unmark_page(void *addr)
         page->mapping = NULL;
 }
 
-static void perf_mmap_data_free_work(struct work_struct *work)
+static void perf_buffer_free_work(struct work_struct *work)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         void *base;
         int i, nr;
 
-        data = container_of(work, struct perf_mmap_data, work);
-        nr = 1 << page_order(data);
+        buffer = container_of(work, struct perf_buffer, work);
+        nr = 1 << page_order(buffer);
 
-        base = data->user_page;
+        base = buffer->user_page;
         for (i = 0; i < nr + 1; i++)
                 perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
         vfree(base);
-        kfree(data);
+        kfree(buffer);
 }
 
-static void perf_mmap_data_free(struct perf_mmap_data *data)
+static void perf_buffer_free(struct perf_buffer *buffer)
 {
-        schedule_work(&data->work);
+        schedule_work(&buffer->work);
 }
 
-static struct perf_mmap_data *
-perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+static struct perf_buffer *
+perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         unsigned long size;
         void *all_buf;
 
-        size = sizeof(struct perf_mmap_data);
+        size = sizeof(struct perf_buffer);
         size += sizeof(void *);
 
-        data = kzalloc(size, GFP_KERNEL);
-        if (!data)
+        buffer = kzalloc(size, GFP_KERNEL);
+        if (!buffer)
                 goto fail;
 
-        INIT_WORK(&data->work, perf_mmap_data_free_work);
+        INIT_WORK(&buffer->work, perf_buffer_free_work);
 
         all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
         if (!all_buf)
                 goto fail_all_buf;
 
-        data->user_page = all_buf;
-        data->data_pages[0] = all_buf + PAGE_SIZE;
-        data->page_order = ilog2(nr_pages);
-        data->nr_pages = 1;
+        buffer->user_page = all_buf;
+        buffer->data_pages[0] = all_buf + PAGE_SIZE;
+        buffer->page_order = ilog2(nr_pages);
+        buffer->nr_pages = 1;
+
+        perf_buffer_init(buffer, watermark, flags);
 
-        return data;
+        return buffer;
 
 fail_all_buf:
-        kfree(data);
+        kfree(buffer);
 
 fail:
         return NULL;
@@ -2558,15 +2579,15 @@ fail:
 
 #endif
 
-static unsigned long perf_data_size(struct perf_mmap_data *data)
+static unsigned long perf_data_size(struct perf_buffer *buffer)
 {
-        return data->nr_pages << (PAGE_SHIFT + page_order(data));
+        return buffer->nr_pages << (PAGE_SHIFT + page_order(buffer));
 }
 
 static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
         struct perf_event *event = vma->vm_file->private_data;
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         int ret = VM_FAULT_SIGBUS;
 
         if (vmf->flags & FAULT_FLAG_MKWRITE) {
@@ -2576,14 +2597,14 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
         }
 
         rcu_read_lock();
-        data = rcu_dereference(event->data);
-        if (!data)
+        buffer = rcu_dereference(event->buffer);
+        if (!buffer)
                 goto unlock;
 
         if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
                 goto unlock;
 
-        vmf->page = perf_mmap_to_page(data, vmf->pgoff);
+        vmf->page = perf_mmap_to_page(buffer, vmf->pgoff);
         if (!vmf->page)
                 goto unlock;
 
@@ -2598,52 +2619,35 @@ unlock:
         return ret;
 }
 
-static void
-perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
-{
-        long max_size = perf_data_size(data);
-
-        if (event->attr.watermark) {
-                data->watermark = min_t(long, max_size,
-                                        event->attr.wakeup_watermark);
-        }
-
-        if (!data->watermark)
-                data->watermark = max_size / 2;
-
-        atomic_set(&data->refcount, 1);
-        rcu_assign_pointer(event->data, data);
-}
-
-static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
+static void perf_buffer_free_rcu(struct rcu_head *rcu_head)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
 
-        data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
-        perf_mmap_data_free(data);
+        buffer = container_of(rcu_head, struct perf_buffer, rcu_head);
+        perf_buffer_free(buffer);
 }
 
-static struct perf_mmap_data *perf_mmap_data_get(struct perf_event *event)
+static struct perf_buffer *perf_buffer_get(struct perf_event *event)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
 
         rcu_read_lock();
-        data = rcu_dereference(event->data);
-        if (data) {
-                if (!atomic_inc_not_zero(&data->refcount))
-                        data = NULL;
+        buffer = rcu_dereference(event->buffer);
+        if (buffer) {
+                if (!atomic_inc_not_zero(&buffer->refcount))
+                        buffer = NULL;
         }
         rcu_read_unlock();
 
-        return data;
+        return buffer;
 }
 
-static void perf_mmap_data_put(struct perf_mmap_data *data)
+static void perf_buffer_put(struct perf_buffer *buffer)
 {
-        if (!atomic_dec_and_test(&data->refcount))
+        if (!atomic_dec_and_test(&buffer->refcount))
                 return;
 
-        call_rcu(&data->rcu_head, perf_mmap_data_free_rcu);
+        call_rcu(&buffer->rcu_head, perf_buffer_free_rcu);
 }
 
 static void perf_mmap_open(struct vm_area_struct *vma)
@@ -2658,16 +2662,16 @@ static void perf_mmap_close(struct vm_area_struct *vma)
         struct perf_event *event = vma->vm_file->private_data;
 
         if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-                unsigned long size = perf_data_size(event->data);
+                unsigned long size = perf_data_size(event->buffer);
                 struct user_struct *user = event->mmap_user;
-                struct perf_mmap_data *data = event->data;
+                struct perf_buffer *buffer = event->buffer;
 
                 atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
                 vma->vm_mm->locked_vm -= event->mmap_locked;
-                rcu_assign_pointer(event->data, NULL);
+                rcu_assign_pointer(event->buffer, NULL);
                 mutex_unlock(&event->mmap_mutex);
 
-                perf_mmap_data_put(data);
+                perf_buffer_put(buffer);
                 free_uid(user);
         }
 }
@@ -2685,11 +2689,11 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
         unsigned long user_locked, user_lock_limit;
         struct user_struct *user = current_user();
         unsigned long locked, lock_limit;
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         unsigned long vma_size;
         unsigned long nr_pages;
         long user_extra, extra;
-        int ret = 0;
+        int ret = 0, flags = 0;
 
         /*
          * Don't allow mmap() of inherited per-task counters. This would
@@ -2706,7 +2710,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
         nr_pages = (vma_size / PAGE_SIZE) - 1;
 
         /*
-         * If we have data pages ensure they're a power-of-two number, so we
+         * If we have buffer pages ensure they're a power-of-two number, so we
          * can do bitmasks instead of modulo.
          */
         if (nr_pages != 0 && !is_power_of_2(nr_pages))
@@ -2720,9 +2724,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
         WARN_ON_ONCE(event->ctx->parent_ctx);
         mutex_lock(&event->mmap_mutex);
-        if (event->data) {
-                if (event->data->nr_pages == nr_pages)
-                        atomic_inc(&event->data->refcount);
+        if (event->buffer) {
+                if (event->buffer->nr_pages == nr_pages)
+                        atomic_inc(&event->buffer->refcount);
                 else
                         ret = -EINVAL;
                 goto unlock;
@@ -2752,17 +2756,18 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
                 goto unlock;
         }
 
-        WARN_ON(event->data);
+        WARN_ON(event->buffer);
+
+        if (vma->vm_flags & VM_WRITE)
+                flags |= PERF_BUFFER_WRITABLE;
 
-        data = perf_mmap_data_alloc(event, nr_pages);
-        if (!data) {
+        buffer = perf_buffer_alloc(nr_pages, event->attr.wakeup_watermark,
+                                   event->cpu, flags);
+        if (!buffer) {
                 ret = -ENOMEM;
                 goto unlock;
         }
-
-        perf_mmap_data_init(event, data);
-        if (vma->vm_flags & VM_WRITE)
-                event->data->writable = 1;
+        rcu_assign_pointer(event->buffer, buffer);
 
         atomic_long_add(user_extra, &user->locked_vm);
         event->mmap_locked = extra;
@@ -2941,11 +2946,6 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return NULL;
 }
 
-__weak
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-}
-
 
 /*
  * We assume there is only KVM supporting the callbacks.
@@ -2971,15 +2971,15 @@ EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
 /*
  * Output
  */
-static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
+static bool perf_output_space(struct perf_buffer *buffer, unsigned long tail,
                               unsigned long offset, unsigned long head)
 {
         unsigned long mask;
 
-        if (!data->writable)
+        if (!buffer->writable)
                 return true;
 
-        mask = perf_data_size(data) - 1;
+        mask = perf_data_size(buffer) - 1;
 
         offset = (offset - tail) & mask;
         head   = (head   - tail) & mask;
@@ -2992,7 +2992,7 @@ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
 
 static void perf_output_wakeup(struct perf_output_handle *handle)
 {
-        atomic_set(&handle->data->poll, POLL_IN);
+        atomic_set(&handle->buffer->poll, POLL_IN);
 
         if (handle->nmi) {
                 handle->event->pending_wakeup = 1;
@@ -3012,45 +3012,45 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
  */
 static void perf_output_get_handle(struct perf_output_handle *handle)
 {
-        struct perf_mmap_data *data = handle->data;
+        struct perf_buffer *buffer = handle->buffer;
 
         preempt_disable();
-        local_inc(&data->nest);
-        handle->wakeup = local_read(&data->wakeup);
+        local_inc(&buffer->nest);
+        handle->wakeup = local_read(&buffer->wakeup);
 }
 
 static void perf_output_put_handle(struct perf_output_handle *handle)
 {
-        struct perf_mmap_data *data = handle->data;
+        struct perf_buffer *buffer = handle->buffer;
         unsigned long head;
 
 again:
-        head = local_read(&data->head);
+        head = local_read(&buffer->head);
 
         /*
          * IRQ/NMI can happen here, which means we can miss a head update.
          */
 
-        if (!local_dec_and_test(&data->nest))
+        if (!local_dec_and_test(&buffer->nest))
                 goto out;
 
         /*
          * Publish the known good head. Rely on the full barrier implied
-         * by atomic_dec_and_test() order the data->head read and this
+         * by atomic_dec_and_test() order the buffer->head read and this
          * write.
          */
-        data->user_page->data_head = head;
+        buffer->user_page->data_head = head;
 
         /*
          * Now check if we missed an update, rely on the (compiler)
-         * barrier in atomic_dec_and_test() to re-read data->head.
+         * barrier in atomic_dec_and_test() to re-read buffer->head.
          */
-        if (unlikely(head != local_read(&data->head))) {
-                local_inc(&data->nest);
+        if (unlikely(head != local_read(&buffer->head))) {
+                local_inc(&buffer->nest);
                 goto again;
         }
 
-        if (handle->wakeup != local_read(&data->wakeup))
+        if (handle->wakeup != local_read(&buffer->wakeup))
                 perf_output_wakeup(handle);
 
  out:
@@ -3070,12 +3070,12 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
                 buf += size;
                 handle->size -= size;
                 if (!handle->size) {
-                        struct perf_mmap_data *data = handle->data;
+                        struct perf_buffer *buffer = handle->buffer;
 
                         handle->page++;
-                        handle->page &= data->nr_pages - 1;
-                        handle->addr = data->data_pages[handle->page];
-                        handle->size = PAGE_SIZE << page_order(data);
+                        handle->page &= buffer->nr_pages - 1;
+                        handle->addr = buffer->data_pages[handle->page];
+                        handle->size = PAGE_SIZE << page_order(buffer);
                 }
         } while (len);
 }
@@ -3084,7 +3084,7 @@ int perf_output_begin(struct perf_output_handle *handle,
                       struct perf_event *event, unsigned int size,
                       int nmi, int sample)
 {
-        struct perf_mmap_data *data;
+        struct perf_buffer *buffer;
         unsigned long tail, offset, head;
         int have_lost;
         struct {
@@ -3100,19 +3100,19 @@ int perf_output_begin(struct perf_output_handle *handle,
         if (event->parent)
                 event = event->parent;
 
-        data = rcu_dereference(event->data);
-        if (!data)
+        buffer = rcu_dereference(event->buffer);
+        if (!buffer)
                 goto out;
 
-        handle->data    = data;
+        handle->buffer  = buffer;
         handle->event   = event;
         handle->nmi     = nmi;
         handle->sample  = sample;
 
-        if (!data->nr_pages)
+        if (!buffer->nr_pages)
                 goto out;
 
-        have_lost = local_read(&data->lost);
+        have_lost = local_read(&buffer->lost);
         if (have_lost)
                 size += sizeof(lost_event);
 
@@ -3124,30 +3124,30 @@ int perf_output_begin(struct perf_output_handle *handle,
                  * tail pointer. So that all reads will be completed before the
                  * write is issued.
                  */
-                tail = ACCESS_ONCE(data->user_page->data_tail);
+                tail = ACCESS_ONCE(buffer->user_page->data_tail);
                 smp_rmb();
-                offset = head = local_read(&data->head);
+                offset = head = local_read(&buffer->head);
                 head += size;
-                if (unlikely(!perf_output_space(data, tail, offset, head)))
+                if (unlikely(!perf_output_space(buffer, tail, offset, head)))
                         goto fail;
-        } while (local_cmpxchg(&data->head, offset, head) != offset);
+        } while (local_cmpxchg(&buffer->head, offset, head) != offset);
 
-        if (head - local_read(&data->wakeup) > data->watermark)
-                local_add(data->watermark, &data->wakeup);
+        if (head - local_read(&buffer->wakeup) > buffer->watermark)
+                local_add(buffer->watermark, &buffer->wakeup);
 
-        handle->page = offset >> (PAGE_SHIFT + page_order(data));
-        handle->page &= data->nr_pages - 1;
-        handle->size = offset & ((PAGE_SIZE << page_order(data)) - 1);
-        handle->addr = data->data_pages[handle->page];
+        handle->page = offset >> (PAGE_SHIFT + page_order(buffer));
+        handle->page &= buffer->nr_pages - 1;
+        handle->size = offset & ((PAGE_SIZE << page_order(buffer)) - 1);
+        handle->addr = buffer->data_pages[handle->page];
         handle->addr += handle->size;
-        handle->size = (PAGE_SIZE << page_order(data)) - handle->size;
+        handle->size = (PAGE_SIZE << page_order(buffer)) - handle->size;
 
         if (have_lost) {
                 lost_event.header.type = PERF_RECORD_LOST;
                 lost_event.header.misc = 0;
                 lost_event.header.size = sizeof(lost_event);
                 lost_event.id          = event->id;
-                lost_event.lost        = local_xchg(&data->lost, 0);
+                lost_event.lost        = local_xchg(&buffer->lost, 0);
 
                 perf_output_put(handle, lost_event);
         }
@@ -3155,7 +3155,7 @@ int perf_output_begin(struct perf_output_handle *handle,
         return 0;
 
 fail:
-        local_inc(&data->lost);
+        local_inc(&buffer->lost);
         perf_output_put_handle(handle);
 out:
         rcu_read_unlock();
@@ -3166,15 +3166,15 @@ out:
 void perf_output_end(struct perf_output_handle *handle)
 {
         struct perf_event *event = handle->event;
-        struct perf_mmap_data *data = handle->data;
+        struct perf_buffer *buffer = handle->buffer;
 
         int wakeup_events = event->attr.wakeup_events;
 
         if (handle->sample && wakeup_events) {
-                int events = local_inc_return(&data->events);
+                int events = local_inc_return(&buffer->events);
                 if (events >= wakeup_events) {
-                        local_sub(wakeup_events, &data->events);
-                        local_inc(&data->wakeup);
+                        local_sub(wakeup_events, &buffer->events);
+                        local_inc(&buffer->wakeup);
                 }
         }
 
@@ -3211,7 +3211,7 @@ static void perf_output_read_one(struct perf_output_handle *handle,
         u64 values[4];
         int n = 0;
 
-        values[n++] = atomic64_read(&event->count);
+        values[n++] = perf_event_count(event);
         if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
                 values[n++] = event->total_time_enabled +
                         atomic64_read(&event->child_total_time_enabled);
@@ -3248,7 +3248,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
         if (leader != event)
                 leader->pmu->read(leader);
 
-        values[n++] = atomic64_read(&leader->count);
+        values[n++] = perf_event_count(leader);
         if (read_format & PERF_FORMAT_ID)
                 values[n++] = primary_event_id(leader);
 
@@ -3260,7 +3260,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
                 if (sub != event)
                         sub->pmu->read(sub);
 
-                values[n++] = atomic64_read(&sub->count);
+                values[n++] = perf_event_count(sub);
                 if (read_format & PERF_FORMAT_ID)
                         values[n++] = primary_event_id(sub);
 
@@ -3491,7 +3491,7 @@ perf_event_read_event(struct perf_event *event,
 /*
  * task tracking -- fork/exit
  *
- * enabled by: attr.comm | attr.mmap | attr.task
+ * enabled by: attr.comm | attr.mmap | attr.mmap_data | attr.task
  */
 
 struct perf_task_event {
@@ -3541,7 +3541,8 @@ static int perf_event_task_match(struct perf_event *event)
         if (event->cpu != -1 && event->cpu != smp_processor_id())
                 return 0;
 
-        if (event->attr.comm || event->attr.mmap || event->attr.task)
+        if (event->attr.comm || event->attr.mmap ||
+            event->attr.mmap_data || event->attr.task)
                 return 1;
 
         return 0;
@@ -3766,7 +3767,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 }
 
 static int perf_event_mmap_match(struct perf_event *event,
-                                   struct perf_mmap_event *mmap_event)
+                                   struct perf_mmap_event *mmap_event,
+                                   int executable)
 {
         if (event->state < PERF_EVENT_STATE_INACTIVE)
                 return 0;
@@ -3774,19 +3776,21 @@ static int perf_event_mmap_match(struct perf_event *event,
         if (event->cpu != -1 && event->cpu != smp_processor_id())
                 return 0;
 
-        if (event->attr.mmap)
+        if ((!executable && event->attr.mmap_data) ||
+            (executable && event->attr.mmap))
                 return 1;
 
         return 0;
 }
 
 static void perf_event_mmap_ctx(struct perf_event_context *ctx,
-                                  struct perf_mmap_event *mmap_event)
+                                  struct perf_mmap_event *mmap_event,
+                                  int executable)
 {
         struct perf_event *event;
 
         list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_event_mmap_match(event, mmap_event))
+                if (perf_event_mmap_match(event, mmap_event, executable))
                         perf_event_mmap_output(event, mmap_event);
         }
 }
@@ -3830,6 +3834,14 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
                 if (!vma->vm_mm) {
                         name = strncpy(tmp, "[vdso]", sizeof(tmp));
                         goto got_name;
+                } else if (vma->vm_start <= vma->vm_mm->start_brk &&
+                                vma->vm_end >= vma->vm_mm->brk) {
+                        name = strncpy(tmp, "[heap]", sizeof(tmp));
+                        goto got_name;
+                } else if (vma->vm_start <= vma->vm_mm->start_stack &&
+                                vma->vm_end >= vma->vm_mm->start_stack) {
+                        name = strncpy(tmp, "[stack]", sizeof(tmp));
+                        goto got_name;
                 }
 
                 name = strncpy(tmp, "//anon", sizeof(tmp));
@@ -3846,17 +3858,17 @@ got_name:
 
         rcu_read_lock();
         cpuctx = &get_cpu_var(perf_cpu_context);
-        perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
+        perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC);
         ctx = rcu_dereference(current->perf_event_ctxp);
         if (ctx)
-                perf_event_mmap_ctx(ctx, mmap_event);
+                perf_event_mmap_ctx(ctx, mmap_event, vma->vm_flags & VM_EXEC);
         put_cpu_var(perf_cpu_context);
         rcu_read_unlock();
 
         kfree(buf);
 }
 
-void __perf_event_mmap(struct vm_area_struct *vma)
+void perf_event_mmap(struct vm_area_struct *vma)
 {
         struct perf_mmap_event mmap_event;
 
@@ -4018,14 +4030,14 @@ static u64 perf_swevent_set_period(struct perf_event *event)
         hwc->last_period = hwc->sample_period;
 
 again:
-        old = val = atomic64_read(&hwc->period_left);
+        old = val = local64_read(&hwc->period_left);
         if (val < 0)
                 return 0;
 
         nr = div64_u64(period + val, period);
         offset = nr * period;
         val -= offset;
-        if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
+        if (local64_cmpxchg(&hwc->period_left, old, val) != old)
                 goto again;
 
         return nr;
@@ -4064,7 +4076,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
 {
         struct hw_perf_event *hwc = &event->hw;
 
-        atomic64_add(nr, &event->count);
+        local64_add(nr, &event->count);
 
         if (!regs)
                 return;
@@ -4075,7 +4087,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
         if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
                 return perf_swevent_overflow(event, 1, nmi, data, regs);
 
-        if (atomic64_add_negative(nr, &hwc->period_left))
+        if (local64_add_negative(nr, &hwc->period_left))
                 return;
 
         perf_swevent_overflow(event, 0, nmi, data, regs);
@@ -4213,14 +4225,12 @@ int perf_swevent_get_recursion_context(void)
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
-void perf_swevent_put_recursion_context(int rctx)
+void inline perf_swevent_put_recursion_context(int rctx)
 {
         struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
         barrier();
         cpuctx->recursion[rctx]--;
 }
-EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
-
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
                             struct pt_regs *regs, u64 addr)
@@ -4368,8 +4378,8 @@ static void cpu_clock_perf_event_update(struct perf_event *event)
         u64 now;
 
         now = cpu_clock(cpu);
-        prev = atomic64_xchg(&event->hw.prev_count, now);
-        atomic64_add(now - prev, &event->count);
+        prev = local64_xchg(&event->hw.prev_count, now);
+        local64_add(now - prev, &event->count);
 }
 
 static int cpu_clock_perf_event_enable(struct perf_event *event)
@@ -4377,7 +4387,7 @@ static int cpu_clock_perf_event_enable(struct perf_event *event)
         struct hw_perf_event *hwc = &event->hw;
         int cpu = raw_smp_processor_id();
 
-        atomic64_set(&hwc->prev_count, cpu_clock(cpu));
+        local64_set(&hwc->prev_count, cpu_clock(cpu));
         perf_swevent_start_hrtimer(event);
 
         return 0;
@@ -4409,9 +4419,9 @@ static void task_clock_perf_event_update(struct perf_event *event, u64 now)
         u64 prev;
         s64 delta;
 
-        prev = atomic64_xchg(&event->hw.prev_count, now);
+        prev = local64_xchg(&event->hw.prev_count, now);
         delta = now - prev;
-        atomic64_add(delta, &event->count);
+        local64_add(delta, &event->count);
 }
 
 static int task_clock_perf_event_enable(struct perf_event *event)
@@ -4421,7 +4431,7 @@ static int task_clock_perf_event_enable(struct perf_event *event)
 
         now = event->ctx->time;
 
-        atomic64_set(&hwc->prev_count, now);
+        local64_set(&hwc->prev_count, now);
 
         perf_swevent_start_hrtimer(event);
 
@@ -4601,7 +4611,7 @@ static int perf_tp_event_match(struct perf_event *event,
 }
 
 void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
-                   struct pt_regs *regs, struct hlist_head *head)
+                   struct pt_regs *regs, struct hlist_head *head, int rctx)
 {
         struct perf_sample_data data;
         struct perf_event *event;
@@ -4615,12 +4625,12 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
         perf_sample_data_init(&data, addr);
         data.raw = &raw;
 
-        rcu_read_lock();
         hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
                 if (perf_tp_event_match(event, &data, regs))
                         perf_swevent_add(event, count, 1, &data, regs);
         }
-        rcu_read_unlock();
+
+        perf_swevent_put_recursion_context(rctx);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
@@ -4864,7 +4874,7 @@ perf_event_alloc(struct perf_event_attr *attr,
                 hwc->sample_period = 1;
         hwc->last_period = hwc->sample_period;
 
-        atomic64_set(&hwc->period_left, hwc->sample_period);
+        local64_set(&hwc->period_left, hwc->sample_period);
 
         /*
          * we currently do not support PERF_FORMAT_GROUP on inherited events
@@ -4913,7 +4923,7 @@ done:
 
         if (!event->parent) {
                 atomic_inc(&nr_events);
-                if (event->attr.mmap)
+                if (event->attr.mmap || event->attr.mmap_data)
                         atomic_inc(&nr_mmap_events);
                 if (event->attr.comm)
                         atomic_inc(&nr_comm_events);
@@ -5007,7 +5017,7 @@ err_size:
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-        struct perf_mmap_data *data = NULL, *old_data = NULL;
+        struct perf_buffer *buffer = NULL, *old_buffer = NULL;
         int ret = -EINVAL;
 
         if (!output_event)
@@ -5037,19 +5047,19 @@ set:
 
         if (output_event) {
                 /* get the buffer we want to redirect to */
-                data = perf_mmap_data_get(output_event);
-                if (!data)
+                buffer = perf_buffer_get(output_event);
+                if (!buffer)
                         goto unlock;
         }
 
-        old_data = event->data;
-        rcu_assign_pointer(event->data, data);
+        old_buffer = event->buffer;
+        rcu_assign_pointer(event->buffer, buffer);
         ret = 0;
 unlock:
         mutex_unlock(&event->mmap_mutex);
 
-        if (old_data)
-                perf_mmap_data_put(old_data);
+        if (old_buffer)
+                perf_buffer_put(old_buffer);
 out:
         return ret;
 }
@@ -5298,7 +5308,7 @@ inherit_event(struct perf_event *parent_event,
                 hwc->sample_period = sample_period;
                 hwc->last_period   = sample_period;
 
-                atomic64_set(&hwc->period_left, sample_period);
+                local64_set(&hwc->period_left, sample_period);
         }
 
         child_event->overflow_handler = parent_event->overflow_handler;
@@ -5359,12 +5369,12 @@ static void sync_child_event(struct perf_event *child_event,
         if (child_event->attr.inherit_stat)
                 perf_event_read_event(child_event, child);
 
-        child_val = atomic64_read(&child_event->count);
+        child_val = perf_event_count(child_event);
 
         /*
          * Add back the child's count to the parent's count:
          */
-        atomic64_add(child_val, &parent_event->count);
+        atomic64_add(child_val, &parent_event->child_count);
         atomic64_add(child_event->total_time_enabled,
                      &parent_event->child_total_time_enabled);
         atomic64_add(child_event->total_time_running,
diff --git a/kernel/sched.c b/kernel/sched.c
index f8b8996228dd..3c5d34a4e932 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3717,7 +3717,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched preempt_schedule(void)
+asmlinkage void __sched notrace preempt_schedule(void)
 {
         struct thread_info *ti = current_thread_info();
 
@@ -3729,9 +3729,9 @@ asmlinkage void __sched preempt_schedule(void)
                 return;
 
         do {
-                add_preempt_count(PREEMPT_ACTIVE);
+                add_preempt_count_notrace(PREEMPT_ACTIVE);
                 schedule();
-                sub_preempt_count(PREEMPT_ACTIVE);
+                sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
                 /*
                  * Check again in case we missed a preemption opportunity
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8b1797c4545b..f669092fdead 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -229,23 +229,6 @@ config FTRACE_SYSCALLS
         help
           Basic tracer to catch the syscall entry and exit events.
 
-config BOOT_TRACER
-        bool "Trace boot initcalls"
-        select GENERIC_TRACER
-        select CONTEXT_SWITCH_TRACER
-        help
-          This tracer helps developers to optimize boot times: it records
-          the timings of the initcalls and traces key events and the identity
-          of tasks that can cause boot delays, such as context-switches.
-
-          Its aim is to be parsed by the scripts/bootgraph.pl tool to
-          produce pretty graphics about boot inefficiencies, giving a visual
-          representation of the delays during initcalls - but the raw
-          /debug/tracing/trace text output is readable too.
-
-          You must pass in initcall_debug and ftrace=initcall to the kernel
-          command line to enable this on bootup.
-
 config TRACE_BRANCH_PROFILING
         bool
         select GENERIC_TRACER
@@ -371,26 +354,6 @@ config STACK_TRACER
 
           Say N if unsure.
 
-config KMEMTRACE
-        bool "Trace SLAB allocations"
-        select GENERIC_TRACER
-        help
-          kmemtrace provides tracing for slab allocator functions, such as
-          kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected
-          data is then fed to the userspace application in order to analyse
-          allocation hotspots, internal fragmentation and so on, making it
-          possible to see how well an allocator performs, as well as debug
-          and profile kernel code.
-
-          This requires an userspace application to use. See
-          Documentation/trace/kmemtrace.txt for more information.
-
-          Saying Y will make the kernel somewhat larger and slower. However,
-          if you disable kmemtrace at run-time or boot-time, the performance
-          impact is minimal (depending on the arch the kernel is built for).
-
-          If unsure, say N.
-
 config WORKQUEUE_TRACER
         bool "Trace workqueues"
         select GENERIC_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index ffb1a5b0550e..469a1c7555a5 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -38,10 +38,8 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
-obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
 ifeq ($(CONFIG_BLOCK),y)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6d2cb14f9449..0d88ce9b9fb8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1883,7 +1883,6 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
         struct hlist_head *hhd;
         struct hlist_node *n;
         unsigned long key;
-        int resched;
 
         key = hash_long(ip, FTRACE_HASH_BITS);
 
@@ -1897,12 +1896,12 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
          * period. This syncs the hash iteration and freeing of items
          * on the hash. rcu_read_lock is too dangerous here.
          */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         hlist_for_each_entry_rcu(entry, n, hhd, node) {
                 if (entry->ip == ip)
                         entry->ops->func(ip, parent_ip, &entry->data);
         }
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
deleted file mode 100644
index bbfc1bb1660b..000000000000
--- a/kernel/trace/kmemtrace.c
+++ /dev/null
@@ -1,529 +0,0 @@
-/*
- * Memory allocator tracing
- *
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- */
-
-#include <linux/tracepoint.h>
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/dcache.h>
-#include <linux/fs.h>
-
-#include <linux/kmemtrace.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-/* Select an alternative, minimalistic output than the original one */
-#define TRACE_KMEM_OPT_MINIMAL  0x1
-
-static struct tracer_opt kmem_opts[] = {
-        /* Default disable the minimalistic output */
-        { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
-        { }
-};
-
-static struct tracer_flags kmem_tracer_flags = {
-        .val                    = 0,
-        .opts                   = kmem_opts
-};
-
-static struct trace_array *kmemtrace_array;
-
-/* Trace allocations */
-static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
-                                   unsigned long call_site,
-                                   const void *ptr,
-                                   size_t bytes_req,
-                                   size_t bytes_alloc,
-                                   gfp_t gfp_flags,
-                                   int node)
-{
-        struct ftrace_event_call *call = &event_kmem_alloc;
-        struct trace_array *tr = kmemtrace_array;
-        struct kmemtrace_alloc_entry *entry;
-        struct ring_buffer_event *event;
-
-        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
-        if (!event)
-                return;
-
-        entry = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, 0);
-
-        entry->ent.type         = TRACE_KMEM_ALLOC;
-        entry->type_id          = type_id;
-        entry->call_site        = call_site;
-        entry->ptr              = ptr;
-        entry->bytes_req        = bytes_req;
-        entry->bytes_alloc      = bytes_alloc;
-        entry->gfp_flags        = gfp_flags;
-        entry->node             = node;
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-
-        trace_wake_up();
-}
-
-static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
-                                  unsigned long call_site,
-                                  const void *ptr)
-{
-        struct ftrace_event_call *call = &event_kmem_free;
-        struct trace_array *tr = kmemtrace_array;
-        struct kmemtrace_free_entry *entry;
-        struct ring_buffer_event *event;
-
-        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, 0);
-
-        entry->ent.type         = TRACE_KMEM_FREE;
-        entry->type_id          = type_id;
-        entry->call_site        = call_site;
-        entry->ptr              = ptr;
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-
-        trace_wake_up();
-}
-
-static void kmemtrace_kmalloc(void *ignore,
-                              unsigned long call_site,
-                              const void *ptr,
-                              size_t bytes_req,
-                              size_t bytes_alloc,
-                              gfp_t gfp_flags)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, -1);
-}
-
-static void kmemtrace_kmem_cache_alloc(void *ignore,
-                                       unsigned long call_site,
-                                       const void *ptr,
-                                       size_t bytes_req,
-                                       size_t bytes_alloc,
-                                       gfp_t gfp_flags)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, -1);
-}
-
-static void kmemtrace_kmalloc_node(void *ignore,
-                                   unsigned long call_site,
-                                   const void *ptr,
-                                   size_t bytes_req,
-                                   size_t bytes_alloc,
-                                   gfp_t gfp_flags,
-                                   int node)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, node);
-}
-
-static void kmemtrace_kmem_cache_alloc_node(void *ignore,
-                                            unsigned long call_site,
-                                            const void *ptr,
-                                            size_t bytes_req,
-                                            size_t bytes_alloc,
-                                            gfp_t gfp_flags,
-                                            int node)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, node);
-}
-
-static void
-kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr)
-{
-        kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
-}
-
-static void kmemtrace_kmem_cache_free(void *ignore,
-                                      unsigned long call_site, const void *ptr)
-{
-        kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
-}
-
-static int kmemtrace_start_probes(void)
-{
-        int err;
-
-        err = register_trace_kmalloc(kmemtrace_kmalloc, NULL);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
-        if (err)
-                return err;
-        err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
-        if (err)
-                return err;
-        err = register_trace_kfree(kmemtrace_kfree, NULL);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
-
-        return err;
-}
-
-static void kmemtrace_stop_probes(void)
-{
-        unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
-        unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
-        unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
-        unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
-        unregister_trace_kfree(kmemtrace_kfree, NULL);
-        unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
-}
-
-static int kmem_trace_init(struct trace_array *tr)
-{
-        kmemtrace_array = tr;
-
-        tracing_reset_online_cpus(tr);
-
-        kmemtrace_start_probes();
-
-        return 0;
-}
-
-static void kmem_trace_reset(struct trace_array *tr)
-{
-        kmemtrace_stop_probes();
-}
-
-static void kmemtrace_headers(struct seq_file *s)
-{
-        /* Don't need headers for the original kmemtrace output */
-        if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
-                return;
-
-        seq_printf(s, "#\n");
-        seq_printf(s, "# ALLOC  TYPE  REQ   GIVEN  FLAGS     "
-                        "      POINTER         NODE    CALLER\n");
-        seq_printf(s, "# FREE   |      |     |       |       "
-                        "       |   |            |        |\n");
-        seq_printf(s, "# |\n\n");
-}
-
-/*
- * The following functions give the original output from kmemtrace,
- * plus the origin CPU, since reordering occurs in-kernel now.
- */
-
-#define KMEMTRACE_USER_ALLOC    0
-#define KMEMTRACE_USER_FREE     1
-
-struct kmemtrace_user_event {
-        u8                      event_id;
-        u8                      type_id;
-        u16                     event_size;
-        u32                     cpu;
-        u64                     timestamp;
-        unsigned long           call_site;
-        unsigned long           ptr;
-};
-
-struct kmemtrace_user_event_alloc {
-        size_t                  bytes_req;
-        size_t                  bytes_alloc;
-        unsigned                gfp_flags;
-        int                     node;
-};
-
-static enum print_line_t
-kmemtrace_print_alloc(struct trace_iterator *iter, int flags,
-                      struct trace_event *event)
-{
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_alloc_entry *entry;
-        int ret;
-
-        trace_assign_type(entry, iter->ent);
-
-        ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
-            "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
-            entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
-            (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
-            (unsigned long)entry->gfp_flags, entry->node);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags,
-                     struct trace_event *event)
-{
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_free_entry *entry;
-        int ret;
-
-        trace_assign_type(entry, iter->ent);
-
-        ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
-                               entry->type_id, (void *)entry->call_site,
-                               (unsigned long)entry->ptr);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
-                           struct trace_event *event)
-{
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_alloc_entry *entry;
-        struct kmemtrace_user_event *ev;
-        struct kmemtrace_user_event_alloc *ev_alloc;
-
-        trace_assign_type(entry, iter->ent);
-
-        ev = trace_seq_reserve(s, sizeof(*ev));
-        if (!ev)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev->event_id            = KMEMTRACE_USER_ALLOC;
-        ev->type_id             = entry->type_id;
-        ev->event_size          = sizeof(*ev) + sizeof(*ev_alloc);
-        ev->cpu                 = iter->cpu;
-        ev->timestamp           = iter->ts;
-        ev->call_site           = entry->call_site;
-        ev->ptr                 = (unsigned long)entry->ptr;
-
-        ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
-        if (!ev_alloc)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev_alloc->bytes_req     = entry->bytes_req;
-        ev_alloc->bytes_alloc   = entry->bytes_alloc;
-        ev_alloc->gfp_flags     = entry->gfp_flags;
-        ev_alloc->node          = entry->node;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter, int flags,
-                          struct trace_event *event)
-{
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_free_entry *entry;
-        struct kmemtrace_user_event *ev;
-
-        trace_assign_type(entry, iter->ent);
-
-        ev = trace_seq_reserve(s, sizeof(*ev));
-        if (!ev)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev->event_id            = KMEMTRACE_USER_FREE;
-        ev->type_id             = entry->type_id;
-        ev->event_size          = sizeof(*ev);
-        ev->cpu                 = iter->cpu;
-        ev->timestamp           = iter->ts;
-        ev->call_site           = entry->call_site;
-        ev->ptr                 = (unsigned long)entry->ptr;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-/* The two other following provide a more minimalistic output */
-static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter)
-{
-        struct kmemtrace_alloc_entry *entry;
-        struct trace_seq *s = &iter->seq;
-        int ret;
-
-        trace_assign_type(entry, iter->ent);
-
-        /* Alloc entry */
-        ret = trace_seq_printf(s, "  +      ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Type */
-        switch (entry->type_id) {
-        case KMEMTRACE_TYPE_KMALLOC:
-                ret = trace_seq_printf(s, "K   ");
-                break;
-        case KMEMTRACE_TYPE_CACHE:
-                ret = trace_seq_printf(s, "C   ");
-                break;
-        case KMEMTRACE_TYPE_PAGES:
-                ret = trace_seq_printf(s, "P   ");
-                break;
-        default:
-                ret = trace_seq_printf(s, "?   ");
-        }
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Requested */
-        ret = trace_seq_printf(s, "%4zu   ", entry->bytes_req);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Allocated */
-        ret = trace_seq_printf(s, "%4zu   ", entry->bytes_alloc);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Flags
-         * TODO: would be better to see the name of the GFP flag names
-         */
-        ret = trace_seq_printf(s, "%08x   ", entry->gfp_flags);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Pointer to allocated */
-        ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Node and call site*/
-        ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
-                                                 (void *)entry->call_site);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter)
-{
-        struct kmemtrace_free_entry *entry;
-        struct trace_seq *s = &iter->seq;
-        int ret;
-
-        trace_assign_type(entry, iter->ent);
-
-        /* Free entry */
-        ret = trace_seq_printf(s, "  -      ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Type */
-        switch (entry->type_id) {
-        case KMEMTRACE_TYPE_KMALLOC:
-                ret = trace_seq_printf(s, "K     ");
-                break;
-        case KMEMTRACE_TYPE_CACHE:
-                ret = trace_seq_printf(s, "C     ");
-                break;
-        case KMEMTRACE_TYPE_PAGES:
-                ret = trace_seq_printf(s, "P     ");
-                break;
-        default:
-                ret = trace_seq_printf(s, "?     ");
-        }
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Skip requested/allocated/flags */
-        ret = trace_seq_printf(s, "                       ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Pointer to allocated */
-        ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Skip node and print call site*/
-        ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-
-        if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
-                return TRACE_TYPE_UNHANDLED;
-
-        switch (entry->type) {
-        case TRACE_KMEM_ALLOC:
-                return kmemtrace_print_alloc_compress(iter);
-        case TRACE_KMEM_FREE:
-                return kmemtrace_print_free_compress(iter);
-        default:
-                return TRACE_TYPE_UNHANDLED;
-        }
-}
-
-static struct trace_event_functions kmem_trace_alloc_funcs = {
-        .trace                  = kmemtrace_print_alloc,
-        .binary                 = kmemtrace_print_alloc_user,
-};
-
-static struct trace_event kmem_trace_alloc = {
-        .type                   = TRACE_KMEM_ALLOC,
-        .funcs                  = &kmem_trace_alloc_funcs,
-};
-
-static struct trace_event_functions kmem_trace_free_funcs = {
-        .trace                  = kmemtrace_print_free,
-        .binary                 = kmemtrace_print_free_user,
-};
-
-static struct trace_event kmem_trace_free = {
-        .type                   = TRACE_KMEM_FREE,
-        .funcs                  = &kmem_trace_free_funcs,
-};
-
-static struct tracer kmem_tracer __read_mostly = {
-        .name                   = "kmemtrace",
-        .init                   = kmem_trace_init,
-        .reset                  = kmem_trace_reset,
-        .print_line             = kmemtrace_print_line,
-        .print_header           = kmemtrace_headers,
-        .flags                  = &kmem_tracer_flags
-};
-
-void kmemtrace_init(void)
-{
-        /* earliest opportunity to start kmem tracing */
-}
-
-static int __init init_kmem_tracer(void)
-{
-        if (!register_ftrace_event(&kmem_trace_alloc)) {
-                pr_warning("Warning: could not register kmem events\n");
-                return 1;
-        }
-
-        if (!register_ftrace_event(&kmem_trace_free)) {
-                pr_warning("Warning: could not register kmem events\n");
-                return 1;
-        }
-
-        if (register_tracer(&kmem_tracer) != 0) {
-                pr_warning("Warning: could not register the kmem tracer\n");
-                return 1;
-        }
-
-        return 0;
-}
-device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1da7b6ea8b85..28d0615a513f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2242,8 +2242,6 @@ static void trace_recursive_unlock(void)
 
 #endif
 
-static DEFINE_PER_CPU(int, rb_need_resched);
-
 /**
  * ring_buffer_lock_reserve - reserve a part of the buffer
  * @buffer: the ring buffer to reserve from
@@ -2264,13 +2262,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
-        int cpu, resched;
+        int cpu;
 
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return NULL;
 
         /* If we are tracing schedule, we don't want to recurse */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
 
         if (atomic_read(&buffer->record_disabled))
                 goto out_nocheck;
@@ -2295,21 +2293,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
         if (!event)
                 goto out;
 
-        /*
-         * Need to store resched state on this cpu.
-         * Only the first needs to.
-         */
-
-        if (preempt_count() == 1)
-                per_cpu(rb_need_resched, cpu) = resched;
-
         return event;
 
  out:
         trace_recursive_unlock();
 
  out_nocheck:
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
         return NULL;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
@@ -2355,13 +2345,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
         trace_recursive_unlock();
 
-        /*
-         * Only the last preempt count needs to restore preemption.
-         */
-        if (preempt_count() == 1)
-                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-        else
-                preempt_enable_no_resched_notrace();
+        preempt_enable_notrace();
 
         return 0;
 }
@@ -2469,13 +2453,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 
         trace_recursive_unlock();
 
-        /*
-         * Only the last preempt count needs to restore preemption.
-         */
-        if (preempt_count() == 1)
-                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-        else
-                preempt_enable_no_resched_notrace();
+        preempt_enable_notrace();
 
 }
 EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
@@ -2501,12 +2479,12 @@ int ring_buffer_write(struct ring_buffer *buffer,
         struct ring_buffer_event *event;
         void *body;
         int ret = -EBUSY;
-        int cpu, resched;
+        int cpu;
 
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return -EBUSY;
 
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
 
         if (atomic_read(&buffer->record_disabled))
                 goto out;
@@ -2536,7 +2514,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         ret = 0;
  out:
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 
         return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 086d36316805..8683dec6946b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1404,7 +1404,6 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
         struct bprint_entry *entry;
         unsigned long flags;
         int disable;
-        int resched;
         int cpu, len = 0, size, pc;
 
         if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -1414,7 +1413,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
         pause_graph_tracing();
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
 
@@ -1452,7 +1451,7 @@ out_unlock:
 
 out:
         atomic_dec_return(&data->disabled);
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
         unpause_graph_tracing();
 
         return len;
@@ -4597,9 +4596,6 @@ __init static int tracer_alloc_buffers(void)
 
         register_tracer(&nop_trace);
         current_trace = &nop_trace;
-#ifdef CONFIG_BOOT_TRACER
-        register_tracer(&boot_tracer);
-#endif
         /* All seems OK, enable tracing */
         tracing_disabled = 0;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2cd96399463f..01ce088c1cdf 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,10 +9,7 @@
 #include <linux/mmiotrace.h>
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
-#include <trace/boot.h>
-#include <linux/kmemtrace.h>
 #include <linux/hw_breakpoint.h>
-
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
 
@@ -29,26 +26,15 @@ enum trace_type {
         TRACE_MMIO_RW,
         TRACE_MMIO_MAP,
         TRACE_BRANCH,
-        TRACE_BOOT_CALL,
-        TRACE_BOOT_RET,
         TRACE_GRAPH_RET,
         TRACE_GRAPH_ENT,
         TRACE_USER_STACK,
-        TRACE_KMEM_ALLOC,
-        TRACE_KMEM_FREE,
         TRACE_BLK,
         TRACE_KSYM,
 
         __TRACE_LAST_TYPE,
 };
 
-enum kmemtrace_type_id {
-        KMEMTRACE_TYPE_KMALLOC = 0,     /* kmalloc() or kfree(). */
-        KMEMTRACE_TYPE_CACHE,           /* kmem_cache_*(). */
-        KMEMTRACE_TYPE_PAGES,           /* __get_free_pages() and friends. */
-};
-
-extern struct tracer boot_tracer;
 
 #undef __field
 #define __field(type, item)             type    item;
@@ -209,17 +195,11 @@ extern void __ftrace_bad_type(void);
                           TRACE_MMIO_RW);                               \
                 IF_ASSIGN(var, ent, struct trace_mmiotrace_map,         \
                           TRACE_MMIO_MAP);                              \
-                IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
-                IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
                 IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
                 IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,      \
                           TRACE_GRAPH_ENT);             \
                 IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,      \
                           TRACE_GRAPH_RET);             \
-                IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,       \
-                          TRACE_KMEM_ALLOC);    \
-                IF_ASSIGN(var, ent, struct kmemtrace_free_entry,        \
-                          TRACE_KMEM_FREE);     \
                 IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
                 __ftrace_bad_type();                                    \
         } while (0)
@@ -628,54 +608,6 @@ enum trace_iterator_flags {
 
 extern struct tracer nop_trace;
 
-/**
- * ftrace_preempt_disable - disable preemption scheduler safe
- *
- * When tracing can happen inside the scheduler, there exists
- * cases that the tracing might happen before the need_resched
- * flag is checked. If this happens and the tracer calls
- * preempt_enable (after a disable), a schedule might take place
- * causing an infinite recursion.
- *
- * To prevent this, we read the need_resched flag before
- * disabling preemption. When we want to enable preemption we
- * check the flag, if it is set, then we call preempt_enable_no_resched.
- * Otherwise, we call preempt_enable.
- *
- * The rational for doing the above is that if need_resched is set
- * and we have yet to reschedule, we are either in an atomic location
- * (where we do not need to check for scheduling) or we are inside
- * the scheduler and do not want to resched.
- */
-static inline int ftrace_preempt_disable(void)
-{
-        int resched;
-
-        resched = need_resched();
-        preempt_disable_notrace();
-
-        return resched;
-}
-
-/**
- * ftrace_preempt_enable - enable preemption scheduler safe
- * @resched: the return value from ftrace_preempt_disable
- *
- * This is a scheduler safe way to enable preemption and not miss
- * any preemption checks. The disabled saved the state of preemption.
- * If resched is set, then we are either inside an atomic or
- * are inside the scheduler (we would have already scheduled
- * otherwise). In this case, we do not want to call normal
- * preempt_enable, but preempt_enable_no_resched instead.
- */
-static inline void ftrace_preempt_enable(int resched)
-{
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
-}
-
 #ifdef CONFIG_BRANCH_TRACER
 extern int enable_branch_tracing(struct trace_array *tr);
 extern void disable_branch_tracing(void);
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
deleted file mode 100644
index c21d5f3956ad..000000000000
--- a/kernel/trace/trace_boot.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * ring buffer based initcalls tracer
- *
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- *
- */
-
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/kallsyms.h>
-#include <linux/time.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-static struct trace_array *boot_trace;
-static bool pre_initcalls_finished;
-
-/* Tells the boot tracer that the pre_smp_initcalls are finished.
- * So we are ready .
- * It doesn't enable sched events tracing however.
- * You have to call enable_boot_trace to do so.
- */
-void start_boot_trace(void)
-{
-        pre_initcalls_finished = true;
-}
-
-void enable_boot_trace(void)
-{
-        if (boot_trace && pre_initcalls_finished)
-                tracing_start_sched_switch_record();
-}
-
-void disable_boot_trace(void)
-{
-        if (boot_trace && pre_initcalls_finished)
-                tracing_stop_sched_switch_record();
-}
-
-static int boot_trace_init(struct trace_array *tr)
-{
-        boot_trace = tr;
-
-        if (!tr)
-                return 0;
-
-        tracing_reset_online_cpus(tr);
-
-        tracing_sched_switch_assign_trace(tr);
-        return 0;
-}
-
-static enum print_line_t
-initcall_call_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *s = &iter->seq;
-        struct trace_boot_call *field;
-        struct boot_trace_call *call;
-        u64 ts;
-        unsigned long nsec_rem;
-        int ret;
-
-        trace_assign_type(field, entry);
-        call = &field->boot_call;
-        ts = iter->ts;
-        nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-        ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
-                        (unsigned long)ts, nsec_rem, call->func, call->caller);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        else
-                return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-initcall_ret_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *s = &iter->seq;
-        struct trace_boot_ret *field;
-        struct boot_trace_ret *init_ret;
-        u64 ts;
-        unsigned long nsec_rem;
-        int ret;
-
-        trace_assign_type(field, entry);
-        init_ret = &field->boot_ret;
-        ts = iter->ts;
-        nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-        ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
-                        "returned %d after %llu msecs\n",
-                        (unsigned long) ts,
-                        nsec_rem,
-                        init_ret->func, init_ret->result, init_ret->duration);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        else
-                return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-
-        switch (entry->type) {
-        case TRACE_BOOT_CALL:
-                return initcall_call_print_line(iter);
-        case TRACE_BOOT_RET:
-                return initcall_ret_print_line(iter);
-        default:
-                return TRACE_TYPE_UNHANDLED;
-        }
-}
-
-struct tracer boot_tracer __read_mostly =
-{
-        .name           = "initcall",
-        .init           = boot_trace_init,
-        .reset          = tracing_reset_online_cpus,
-        .print_line     = initcall_print_line,
-};
-
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
-{
-        struct ftrace_event_call *call = &event_boot_call;
-        struct ring_buffer_event *event;
-        struct ring_buffer *buffer;
-        struct trace_boot_call *entry;
-        struct trace_array *tr = boot_trace;
-
-        if (!tr || !pre_initcalls_finished)
-                return;
-
-        /* Get its name now since this function could
-         * disappear because it is in the .init section.
-         */
-        sprint_symbol(bt->func, (unsigned long)fn);
-        preempt_disable();
-
-        buffer = tr->buffer;
-        event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->boot_call = *bt;
-        if (!filter_check_discard(call, entry, buffer, event))
-                trace_buffer_unlock_commit(buffer, event, 0, 0);
- out:
-        preempt_enable();
-}
-
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
-{
-        struct ftrace_event_call *call = &event_boot_ret;
-        struct ring_buffer_event *event;
-        struct ring_buffer *buffer;
-        struct trace_boot_ret *entry;
-        struct trace_array *tr = boot_trace;
-
-        if (!tr || !pre_initcalls_finished)
-                return;
-
-        sprint_symbol(bt->func, (unsigned long)fn);
-        preempt_disable();
-
-        buffer = tr->buffer;
-        event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->boot_ret = *bt;
-        if (!filter_check_discard(call, entry, buffer, event))
-                trace_buffer_unlock_commit(buffer, event, 0, 0);
- out:
-        preempt_enable();
-}
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 9d589d8dcd1a..52fda6c04ac3 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -32,16 +32,15 @@
 u64 notrace trace_clock_local(void)
 {
         u64 clock;
-        int resched;
 
         /*
          * sched_clock() is an architecture implemented, fast, scalable,
          * lockless clock. It is not guaranteed to be coherent across
          * CPUs, nor across CPU idle events.
          */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         clock = sched_clock();
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 
         return clock;
 }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index dc008c1240da..13abc157dbaf 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -271,33 +271,6 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
                  __entry->map_id, __entry->opcode)
 );
 
-FTRACE_ENTRY(boot_call, trace_boot_call,
-
-        TRACE_BOOT_CALL,
-
-        F_STRUCT(
-                __field_struct( struct boot_trace_call, boot_call       )
-                __field_desc(   pid_t,  boot_call,      caller          )
-                __array_desc(   char,   boot_call,      func,   KSYM_SYMBOL_LEN)
-        ),
-
-        F_printk("%d  %s", __entry->caller, __entry->func)
-);
-
-FTRACE_ENTRY(boot_ret, trace_boot_ret,
-
-        TRACE_BOOT_RET,
-
-        F_STRUCT(
-                __field_struct( struct boot_trace_ret,  boot_ret        )
-                __array_desc(   char,   boot_ret,       func,   KSYM_SYMBOL_LEN)
-                __field_desc(   int,    boot_ret,       result          )
-                __field_desc(   unsigned long, boot_ret, duration       )
-        ),
-
-        F_printk("%s %d %lx",
-                 __entry->func, __entry->result, __entry->duration)
-);
 
 #define TRACE_FUNC_SIZE 30
 #define TRACE_FILE_SIZE 20
@@ -318,41 +291,6 @@ FTRACE_ENTRY(branch, trace_branch,
                  __entry->func, __entry->file, __entry->correct)
 );
 
-FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
-
-        TRACE_KMEM_ALLOC,
-
-        F_STRUCT(
-                __field(        enum kmemtrace_type_id, type_id         )
-                __field(        unsigned long,          call_site       )
-                __field(        const void *,           ptr             )
-                __field(        size_t,                 bytes_req       )
-                __field(        size_t,                 bytes_alloc     )
-                __field(        gfp_t,                  gfp_flags       )
-                __field(        int,                    node            )
-        ),
-
-        F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
-                 " flags:%x node:%d",
-                 __entry->type_id, __entry->call_site, __entry->ptr,
-                 __entry->bytes_req, __entry->bytes_alloc,
-                 __entry->gfp_flags, __entry->node)
-);
-
-FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
-
-        TRACE_KMEM_FREE,
-
-        F_STRUCT(
-                __field(        enum kmemtrace_type_id, type_id         )
-                __field(        unsigned long,          call_site       )
-                __field(        const void *,           ptr             )
-        ),
-
-        F_printk("type:%u call_site:%lx ptr:%p",
-                 __entry->type_id, __entry->call_site, __entry->ptr)
-);
-
 FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
 
         TRACE_KSYM,
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e6f65887842c..4799d7047eb0 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,8 +9,6 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
-
 static char *perf_trace_buf[4];
 
 /*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 53cffc0b0801..a594f9a7ee3d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1524,12 +1524,11 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
         struct ftrace_entry *entry;
         unsigned long flags;
         long disabled;
-        int resched;
         int cpu;
         int pc;
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         cpu = raw_smp_processor_id();
         disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
 
@@ -1551,7 +1550,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 
  out:
         atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __initdata  =
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index b3f3776b0cd6..16aee4d44e8f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -54,14 +54,14 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
-        int cpu, resched;
+        int cpu;
         int pc;
 
         if (unlikely(!ftrace_function_enabled))
                 return;
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         local_save_flags(flags);
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -71,7 +71,7 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
                 trace_function(tr, ip, parent_ip, flags, pc);
 
         atomic_dec(&data->disabled);
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static void
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0e73bc2ef8c5..c9fd5bd02036 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -46,7 +46,6 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
-        int resched;
         int cpu;
         int pc;
 
@@ -54,7 +53,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
                 return;
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
 
         cpu = raw_smp_processor_id();
         if (cpu != wakeup_current_cpu)
@@ -74,7 +73,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
         atomic_dec(&data->disabled);
  out_enable:
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index f4bc9b27de5f..056468eae7cf 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -110,12 +110,12 @@ static inline void check_stack(void)
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip)
 {
-        int cpu, resched;
+        int cpu;
 
         if (unlikely(!ftrace_enabled || stack_trace_disabled))
                 return;
 
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
 
         cpu = raw_smp_processor_id();
         /* no atomic needed, we only modify this variable by this cpu */
@@ -127,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
         per_cpu(trace_active, cpu)--;
         /* prevent recursion in schedule */
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index a7974a552ca9..c080956f4d8e 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -33,12 +33,13 @@ static DEFINE_MUTEX(sample_timer_lock);
  */
 static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
 
-struct stack_frame {
+struct stack_frame_user {
         const void __user       *next_fp;
         unsigned long           return_address;
 };
 
-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;
 
@@ -125,7 +126,7 @@ trace_kernel(struct pt_regs *regs, struct trace_array *tr,
 static void timer_notify(struct pt_regs *regs, int cpu)
 {
         struct trace_array_cpu *data;
-        struct stack_frame frame;
+        struct stack_frame_user frame;
         struct trace_array *tr;
         const void __user *fp;
         int is_user;
diff --git a/mm/mmap.c b/mm/mmap.c
index 456ec6f27889..e38e910cb756 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1734,8 +1734,10 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
                 grow = (address - vma->vm_end) >> PAGE_SHIFT;
 
                 error = acct_stack_growth(vma, size, grow);
-                if (!error)
+                if (!error) {
                         vma->vm_end = address;
+                        perf_event_mmap(vma);
+                }
         }
         anon_vma_unlock(vma);
         return error;
@@ -1781,6 +1783,7 @@ static int expand_downwards(struct vm_area_struct *vma,
                 if (!error) {
                         vma->vm_start = address;
                         vma->vm_pgoff -= grow;
+                        perf_event_mmap(vma);
                 }
         }
         anon_vma_unlock(vma);
@@ -2208,6 +2211,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
         vma->vm_page_prot = vm_get_page_prot(flags);
         vma_link(mm, vma, prev, rb_link, rb_parent);
 out:
+        perf_event_mmap(vma);
         mm->total_vm += len >> PAGE_SHIFT;
         if (flags & VM_LOCKED) {
                 if (!mlock_vma_pages_range(vma, addr, addr + len))
diff --git a/mm/slab.c b/mm/slab.c
index e49f8f46f46d..47360c3e5abd 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -102,7 +102,6 @@
 #include        <linux/cpu.h>
 #include        <linux/sysctl.h>
 #include        <linux/module.h>
-#include        <linux/kmemtrace.h>
 #include        <linux/rcupdate.h>
 #include        <linux/string.h>
 #include        <linux/uaccess.h>
diff --git a/mm/slob.c b/mm/slob.c
index 23631e2bb57a..a82ab5811bd9 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -66,8 +66,10 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
-#include <linux/kmemtrace.h>
 #include <linux/kmemleak.h>
+
+#include <trace/events/kmem.h>
+
 #include <asm/atomic.h>
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index 578f68f3c51f..7bb7940f4eee 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/kmemtrace.h>
 #include <linux/kmemcheck.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index 62fcc3a7f4d3..18513b0191db 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -111,13 +111,38 @@ tar%pkg: FORCE
 clean-dirs += $(objtree)/tar-install/
 
 
+# perf-pkg - generate a source tarball with perf source
+# ---------------------------------------------------------------------------
+
+perf-tar=perf-$(KERNELVERSION)
+
+quiet_cmd_perf_tar = TAR
+      cmd_perf_tar = \
+git archive --prefix=$(perf-tar)/ HEAD^{tree}                       \
+        $$(cat $(srctree)/tools/perf/MANIFEST) -o $(perf-tar).tar;  \
+mkdir -p $(perf-tar);                                               \
+git rev-parse HEAD > $(perf-tar)/HEAD;                              \
+tar rf $(perf-tar).tar $(perf-tar)/HEAD;                            \
+rm -r $(perf-tar);                                                  \
+$(if $(findstring tar-src,$@),,                                     \
+$(if $(findstring bz2,$@),bzip2,                                    \
+$(if $(findstring gz,$@),gzip,                                      \
+$(error unknown target $@)))                                       \
+        -f -9 $(perf-tar).tar)
+
+perf-%pkg: FORCE
+        $(call cmd,perf_tar)
+
 # Help text displayed when executing 'make help'
 # ---------------------------------------------------------------------------
 help: FORCE
-        @echo '  rpm-pkg         - Build both source and binary RPM kernel packages'
-        @echo '  binrpm-pkg      - Build only the binary kernel package'
-        @echo '  deb-pkg         - Build the kernel as an deb package'
-        @echo '  tar-pkg         - Build the kernel as an uncompressed tarball'
-        @echo '  targz-pkg       - Build the kernel as a gzip compressed tarball'
-        @echo '  tarbz2-pkg      - Build the kernel as a bzip2 compressed tarball'
+        @echo '  rpm-pkg             - Build both source and binary RPM kernel packages'
+        @echo '  binrpm-pkg          - Build only the binary kernel package'
+        @echo '  deb-pkg             - Build the kernel as an deb package'
+        @echo '  tar-pkg             - Build the kernel as an uncompressed tarball'
+        @echo '  targz-pkg           - Build the kernel as a gzip compressed tarball'
+        @echo '  tarbz2-pkg          - Build the kernel as a bzip2 compressed tarball'
+        @echo '  perf-tar-src-pkg    - Build $(perf-tar).tar source tarball'
+        @echo '  perf-targz-src-pkg  - Build $(perf-tar).tar.gz source tarball'
+        @echo '  perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball'
 
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index e1d60d780784..cb43289e447f 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -18,3 +18,5 @@ perf-archive
 tags
 TAGS
 cscope*
+config.mak
+config.mak.autogen
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 94a258c96a44..ea531d9d975c 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -31,6 +31,10 @@ OPTIONS
 --vmlinux=PATH::
         Specify vmlinux path which has debuginfo (Dwarf binary).
 
+-s::
+--source=PATH::
+        Specify path to kernel source.
+
 -v::
 --verbose::
         Be more verbose (show parsed arguments, etc).
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 34e255fc3e2f..3ee27dccfde9 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -103,6 +103,19 @@ OPTIONS
 --raw-samples::
 Collect raw sample records from all opened counters (default for tracepoint counters).
 
+-C::
+--cpu::
+Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), samples are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+-N::
+--no-buildid-cache::
+Do not update the builid cache. This saves some overhead in situations
+where the information in the perf.data file (which includes buildids)
+is sufficient.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 909fa766fa1c..4b3a2d46b437 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -46,6 +46,13 @@ OPTIONS
 -B::
         print large numbers with thousands' separators according to locale
 
+-C::
+--cpu=::
+Count only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode, this option is ignored. The -a option is still necessary
+to activate system-wide monitoring. Default is to count on all CPUs.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 785b9fc32a46..1f9687663f2a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -25,9 +25,11 @@ OPTIONS
 --count=<count>::
         Event period to sample.
 
--C <cpu>::
---CPU=<cpu>::
-        CPU to profile.
+-C <cpu-list>::
+--cpu=<cpu>::
+Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Default is to monitor all CPUS.
 
 -d <seconds>::
 --delay=<seconds>::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
new file mode 100644
index 000000000000..8c7fc0c8f0b8
--- /dev/null
+++ b/tools/perf/MANIFEST
@@ -0,0 +1,12 @@
+tools/perf
+include/linux/perf_event.h
+include/linux/rbtree.h
+include/linux/list.h
+include/linux/hash.h
+include/linux/stringify.h
+lib/rbtree.c
+include/linux/swab.h
+arch/*/include/asm/unistd*.h
+include/linux/poison.h
+include/linux/magic.h
+include/linux/hw_breakpoint.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3d8f31ed771d..6aa2fe323db1 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -285,14 +285,10 @@ else
         QUIET_STDERR = ">/dev/null 2>&1"
 endif
 
-BITBUCKET = "/dev/null"
+-include feature-tests.mak
 
-ifneq ($(shell sh -c "(echo '\#include <stdio.h>'; echo 'int main(void) { return puts(\"hi\"); }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
-        BITBUCKET = .perf.dev.null
-endif
-
-ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
-  CFLAGS := $(CFLAGS) -fstack-protector-all
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
+        CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
 
 
@@ -508,7 +504,8 @@ PERFLIBS = $(LIB_FILE)
 -include config.mak
 
 ifndef NO_DWARF
-ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo '\#include <version.h>'; echo '\#ifndef _ELFUTILS_PREREQ'; echo '\#error'; echo '\#endif'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+FLAGS_DWARF=$(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
+ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
         msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
         NO_DWARF := 1
 endif # Dwarf support
@@ -536,16 +533,18 @@ ifneq ($(OUTPUT),)
         BASIC_CFLAGS += -I$(OUTPUT)
 endif
 
-ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-        msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y)
+        FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS)
+        ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y)
+                msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+        else
+                msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel);
+        endif
 endif
 
-        ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-                BASIC_CFLAGS += -DLIBELF_NO_MMAP
-        endif
-else
-        msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
+ifneq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y)
+        BASIC_CFLAGS += -DLIBELF_NO_MMAP
 endif
 
 ifndef NO_DWARF
@@ -561,41 +560,47 @@ endif # NO_DWARF
 ifdef NO_NEWT
         BASIC_CFLAGS += -DNO_NEWT_SUPPORT
 else
-ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-        msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
-        BASIC_CFLAGS += -DNO_NEWT_SUPPORT
-else
-        # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
-        BASIC_CFLAGS += -I/usr/include/slang
-        EXTLIBS += -lnewt -lslang
-        LIB_OBJS += $(OUTPUT)util/newt.o
-endif
-endif # NO_NEWT
-
-ifndef NO_LIBPERL
-PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+        FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt
+        ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT)),y)
+                msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
+                BASIC_CFLAGS += -DNO_NEWT_SUPPORT
+        else
+                # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+                BASIC_CFLAGS += -I/usr/include/slang
+                EXTLIBS += -lnewt -lslang
+                LIB_OBJS += $(OUTPUT)util/newt.o
+        endif
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o $(BITBUCKET) $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+ifdef NO_LIBPERL
         BASIC_CFLAGS += -DNO_LIBPERL
 else
-        ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
-        LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
-        LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-endif
+        PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
+        PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+        PERL_EMBED_FLAGS=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
-ifndef NO_LIBPYTHON
-PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
-PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
+        ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y)
+                BASIC_CFLAGS += -DNO_LIBPERL
+        else
+                ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
+                LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
+                LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
+        endif
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+ifdef NO_LIBPYTHON
         BASIC_CFLAGS += -DNO_LIBPYTHON
 else
-        ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
-        LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-        LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+        PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
+        PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
+        FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+                BASIC_CFLAGS += -DNO_LIBPYTHON
+        else
+                ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
+                LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+                LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+        endif
 endif
 
 ifdef NO_DEMANGLE
@@ -604,20 +609,23 @@ else ifdef HAVE_CPLUS_DEMANGLE
         EXTLIBS += -liberty
         BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
 else
-        has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
-
+        FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd
+        has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD))
         ifeq ($(has_bfd),y)
                 EXTLIBS += -lbfd
         else
-                has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
+                FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
+                has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY))
                 ifeq ($(has_bfd_iberty),y)
                         EXTLIBS += -lbfd -liberty
                 else
-                        has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
+                        FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
+                        has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z))
                         ifeq ($(has_bfd_iberty_z),y)
                                 EXTLIBS += -lbfd -liberty -lz
                         else
-                                has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
+                                FLAGS_CPLUS_DEMANGLE=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -liberty
+                                has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE))
                                 ifeq ($(has_cplus_demangle),y)
                                         EXTLIBS += -liberty
                                         BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
@@ -865,7 +873,7 @@ export TAR INSTALL DESTDIR SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
-all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
+all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
 ifneq (,$X)
         $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
 endif
@@ -1195,11 +1203,6 @@ clean:
 .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
 .PHONY: .FORCE-PERF-BUILD-OPTIONS
 
-.perf.dev.null:
-                touch .perf.dev.null
-
-.INTERMEDIATE:  .perf.dev.null
-
 ### Make sure built-ins do not have dups and listed in perf.c
 #
 check-builtins::
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 96db5248e995..fd20670ce986 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -61,11 +61,9 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct addr_location al;
+        struct sample_data data;
 
-        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-                    event->ip.pid, event->ip.ip);
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index f8e3d1852029..29ad20e67919 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -78,8 +78,7 @@ static int __cmd_buildid_cache(void)
         struct str_node *pos;
         char debugdir[PATH_MAX];
 
-        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-                 DEBUG_CACHE_DIR);
+        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
         if (add_name_list_str) {
                 list = strlist__new(true, add_name_list_str);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a6e2fdc7a04e..39e6627ebb96 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -35,10 +35,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         struct addr_location al;
         struct sample_data data = { .period = 1, };
 
-        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-                    event->ip.pid, event->ip.ip);
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -47,8 +44,6 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         if (al.filtered || al.sym == NULL)
                 return 0;
 
-        event__parse_sample(event, session->sample_type, &data);
-
         if (hists__add_entry(&session->hists, &al, data.period)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 return -1;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index e4a4da32a568..54551867e7e0 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -182,6 +182,8 @@ static const struct option options[] = {
                      "Show source code lines.", opt_show_lines),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
+        OPT_STRING('s', "source", &symbol_conf.source_prefix,
+                   "directory", "path to kernel source"),
 #endif
         OPT__DRY_RUN(&probe_event_dry_run),
         OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc3435e18bde..86b1c3b6264e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,7 +49,6 @@ static int			group				=      0;
 static int                      realtime_prio                   =      0;
 static bool                     raw_samples                     =  false;
 static bool                     system_wide                     =  false;
-static int                      profile_cpu                     =     -1;
 static pid_t                    target_pid                      =     -1;
 static pid_t                    target_tid                      =     -1;
 static pid_t                    *all_tids                       =      NULL;
@@ -61,6 +60,7 @@ static bool			call_graph			=  false;
 static bool                     inherit_stat                    =  false;
 static bool                     no_samples                      =  false;
 static bool                     sample_address                  =  false;
+static bool                     no_buildid                      =  false;
 
 static long                     samples                         =      0;
 static u64                      bytes_written                   =      0;
@@ -74,6 +74,7 @@ static int			file_new			=      1;
 static off_t                    post_processing_offset;
 
 static struct perf_session      *session;
+static const char               *cpu_list;
 
 struct mmap_data {
         int                     counter;
@@ -268,12 +269,17 @@ static void create_counter(int counter, int cpu)
         if (inherit_stat)
                 attr->inherit_stat = 1;
 
-        if (sample_address)
+        if (sample_address) {
                 attr->sample_type       |= PERF_SAMPLE_ADDR;
+                attr->mmap_data = track;
+        }
 
         if (call_graph)
                 attr->sample_type       |= PERF_SAMPLE_CALLCHAIN;
 
+        if (system_wide)
+                attr->sample_type       |= PERF_SAMPLE_CPU;
+
         if (raw_samples) {
                 attr->sample_type       |= PERF_SAMPLE_TIME;
                 attr->sample_type       |= PERF_SAMPLE_RAW;
@@ -300,7 +306,7 @@ try_again:
                                 die("Permission error - are you root?\n"
                                         "\t Consider tweaking"
                                         " /proc/sys/kernel/perf_event_paranoid.\n");
-                        else if (err ==  ENODEV && profile_cpu != -1) {
+                        else if (err ==  ENODEV && cpu_list) {
                                 die("No such device - did you specify"
                                         " an out-of-range profile CPU?\n");
                         }
@@ -622,10 +628,15 @@ static int __cmd_record(int argc, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        if ((!system_wide && no_inherit) || profile_cpu != -1) {
-                open_counters(profile_cpu);
+        nr_cpus = read_cpu_map(cpu_list);
+        if (nr_cpus < 1) {
+                perror("failed to collect number of CPUs\n");
+                return -1;
+        }
+
+        if (!system_wide && no_inherit && !cpu_list) {
+                open_counters(-1);
         } else {
-                nr_cpus = read_cpu_map();
                 for (i = 0; i < nr_cpus; i++)
                         open_counters(cpumap[i]);
         }
@@ -704,7 +715,7 @@ static int __cmd_record(int argc, const char **argv)
         if (perf_guest)
                 perf_session__process_machines(session, event__synthesize_guest_os);
 
-        if (!system_wide && profile_cpu == -1)
+        if (!system_wide)
                 event__synthesize_thread(target_tid, process_synthesized_event,
                                          session);
         else
@@ -794,8 +805,8 @@ static const struct option options[] = {
                             "system-wide collection from all CPUs"),
         OPT_BOOLEAN('A', "append", &append_file,
                             "append to the output file to do incremental profiling"),
-        OPT_INTEGER('C', "profile_cpu", &profile_cpu,
-                            "CPU to profile on"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor"),
         OPT_BOOLEAN('f', "force", &force,
                         "overwrite existing data file (deprecated)"),
         OPT_U64('c', "count", &user_interval, "event period to sample"),
@@ -815,6 +826,8 @@ static const struct option options[] = {
                     "Sample addresses"),
         OPT_BOOLEAN('n', "no-samples", &no_samples,
                     "don't sample"),
+        OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid,
+                    "do not update the buildid cache"),
         OPT_END()
 };
 
@@ -825,7 +838,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
         argc = parse_options(argc, argv, options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target_pid == -1 && target_tid == -1 &&
-                !system_wide && profile_cpu == -1)
+                !system_wide && !cpu_list)
                 usage_with_options(record_usage, options);
 
         if (force && append_file) {
@@ -839,6 +852,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
         }
 
         symbol__init();
+        if (no_buildid)
+                disable_buildid_cache();
 
         if (!nr_counters) {
                 nr_counters     = 1;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 359205782964..371a3c995806 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -155,30 +155,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         struct addr_location al;
         struct perf_event_attr *attr;
 
-        event__parse_sample(event, session->sample_type, &data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-                    data.pid, data.tid, data.ip, data.period);
-
-        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-                unsigned int i;
-
-                dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
-
-                if (!ip_callchain__valid(data.callchain, event)) {
-                        pr_debug("call-chain problem with event, "
-                                 "skipping it.\n");
-                        return 0;
-                }
-
-                if (dump_trace) {
-                        for (i = 0; i < data.callchain->nr; i++)
-                                dump_printf("..... %2d: %016Lx\n",
-                                            i, data.callchain->ips[i]);
-                }
-        }
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                         event->header.type);
                 return -1;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9a39ca3c3ac4..a6b4d44f9502 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -69,7 +69,7 @@ static struct perf_event_attr default_attrs[] = {
 };
 
 static bool                     system_wide                     =  false;
-static unsigned int             nr_cpus                         =  0;
+static int                      nr_cpus                         =  0;
 static int                      run_idx                         =  0;
 
 static int                      run_count                       =  1;
@@ -82,6 +82,7 @@ static int			thread_num			=  0;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
 static bool                     big_num                         =  false;
+static const char               *cpu_list;
 
 
 static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -158,7 +159,7 @@ static int create_perf_stat_counter(int counter)
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
 
         if (system_wide) {
-                unsigned int cpu;
+                int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
                         fd[cpu][counter][0] = sys_perf_event_open(attr,
@@ -208,7 +209,7 @@ static inline int nsec_counter(int counter)
 static void read_counter(int counter)
 {
         u64 count[3], single_count[3];
-        unsigned int cpu;
+        int cpu;
         size_t res, nv;
         int scaled;
         int i, thread;
@@ -542,6 +543,8 @@ static const struct option options[] = {
                     "null run - dont start any counters"),
         OPT_BOOLEAN('B', "big-num", &big_num,
                     "print large numbers with thousands\' separators"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor in system-wide"),
         OPT_END()
 };
 
@@ -566,10 +569,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         }
 
         if (system_wide)
-                nr_cpus = read_cpu_map();
+                nr_cpus = read_cpu_map(cpu_list);
         else
                 nr_cpus = 1;
 
+        if (nr_cpus < 1)
+                usage_with_options(stat_usage, options);
+
         if (target_pid != -1) {
                 target_tid = target_pid;
                 thread_num = find_all_tid(target_pid, &all_tids);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a66f4272b994..1e8e92e317b9 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -102,6 +102,7 @@ struct sym_entry		*sym_filter_entry_sched		=   NULL;
 static int                      sym_pcnt_filter                 =      5;
 static int                      sym_counter                     =      0;
 static int                      display_weighted                =     -1;
+static const char               *cpu_list;
 
 /*
  * Symbols
@@ -982,6 +983,7 @@ static void event__process_sample(const event_t *self,
         u64 ip = self->ip.ip;
         struct sym_entry *syme;
         struct addr_location al;
+        struct sample_data data;
         struct machine *machine;
         u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -1024,7 +1026,8 @@ static void event__process_sample(const event_t *self,
         if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
                 exact_samples++;
 
-        if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
+        if (event__preprocess_sample(self, session, &al, &data,
+                                     symbol_filter) < 0 ||
             al.filtered)
                 return;
 
@@ -1351,8 +1354,8 @@ static const struct option options[] = {
                     "profile events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                             "system-wide collection from all CPUs"),
-        OPT_INTEGER('C', "CPU", &profile_cpu,
-                    "CPU to profile on"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
@@ -1428,10 +1431,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 return -ENOMEM;
 
         /* CPU and PID are mutually exclusive */
-        if (target_tid > 0 && profile_cpu != -1) {
+        if (target_tid > 0 && cpu_list) {
                 printf("WARNING: PID switch overriding CPU\n");
                 sleep(1);
-                profile_cpu = -1;
+                cpu_list = NULL;
         }
 
         if (!nr_counters)
@@ -1469,10 +1472,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 attrs[counter].sample_period = default_interval;
         }
 
-        if (target_tid != -1 || profile_cpu != -1)
+        if (target_tid != -1)
                 nr_cpus = 1;
         else
-                nr_cpus = read_cpu_map();
+                nr_cpus = read_cpu_map(cpu_list);
+
+        if (nr_cpus < 1)
+                usage_with_options(top_usage, options);
 
         get_term_dimensions(&winsize);
         if (print_entries == 0) {
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
new file mode 100644
index 000000000000..ddb68e601f0e
--- /dev/null
+++ b/tools/perf/feature-tests.mak
@@ -0,0 +1,119 @@
+define SOURCE_HELLO
+#include <stdio.h>
+int main(void)
+{
+        return puts(\"hi\");
+}
+endef
+
+ifndef NO_DWARF
+define SOURCE_DWARF
+#include <dwarf.h>
+#include <libdw.h>
+#include <version.h>
+#ifndef _ELFUTILS_PREREQ
+#error
+#endif
+
+int main(void)
+{
+        Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+        return (long)dbg;
+}
+endef
+endif
+
+define SOURCE_LIBELF
+#include <libelf.h>
+
+int main(void)
+{
+        Elf *elf = elf_begin(0, ELF_C_READ, 0);
+        return (long)elf;
+}
+endef
+
+define SOURCE_GLIBC
+#include <gnu/libc-version.h>
+
+int main(void)
+{
+        const char *version = gnu_get_libc_version();
+        return (long)version;
+}
+endef
+
+define SOURCE_ELF_MMAP
+#include <libelf.h>
+int main(void)
+{
+        Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
+        return (long)elf;
+}
+endef
+
+ifndef NO_NEWT
+define SOURCE_NEWT
+#include <newt.h>
+
+int main(void)
+{
+        newtInit();
+        newtCls();
+        return newtFinished();
+}
+endef
+endif
+
+ifndef NO_LIBPERL
+define SOURCE_PERL_EMBED
+#include <EXTERN.h>
+#include <perl.h>
+
+int main(void)
+{
+perl_alloc();
+return 0;
+}
+endef
+endif
+
+ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_EMBED
+#include <Python.h>
+
+int main(void)
+{
+        Py_Initialize();
+        return 0;
+}
+endef
+endif
+
+define SOURCE_BFD
+#include <bfd.h>
+
+int main(void)
+{
+        bfd_demangle(0, 0, 0);
+        return 0;
+}
+endef
+
+define SOURCE_CPLUS_DEMANGLE
+extern char *cplus_demangle(const char *, int);
+
+int main(void)
+{
+        cplus_demangle(0, 0);
+        return 0;
+}
+endef
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c                                            \
+        'TMP="$(TMPOUT).$$$$";                                    \
+         echo "$(1)" |                                            \
+         $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+         rm -f "$$TMP"')
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 2e7a4f417e20..677e59d62a8d 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -7,7 +7,17 @@ if [ $# -ne 0 ] ; then
         PERF_DATA=$1
 fi
 
-DEBUGDIR=~/.debug/
+#
+# PERF_BUILDID_DIR environment variable set by perf
+# path to buildid directory, default to $HOME/.debug
+#
+if [ -z $PERF_BUILDID_DIR ]; then
+        PERF_BUILDID_DIR=~/.debug/
+else
+        # append / to make substitutions work
+        PERF_BUILDID_DIR=$PERF_BUILDID_DIR/
+fi
+
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
 NOBUILDID=0000000000000000000000000000000000000000
 
@@ -22,13 +32,13 @@ MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX)
 
 cut -d ' ' -f 1 $BUILDIDS | \
 while read build_id ; do
-        linkname=$DEBUGDIR.build-id/${build_id:0:2}/${build_id:2}
+        linkname=$PERF_BUILDID_DIR.build-id/${build_id:0:2}/${build_id:2}
         filename=$(readlink -f $linkname)
-        echo ${linkname#$DEBUGDIR} >> $MANIFEST
-        echo ${filename#$DEBUGDIR} >> $MANIFEST
+        echo ${linkname#$PERF_BUILDID_DIR} >> $MANIFEST
+        echo ${filename#$PERF_BUILDID_DIR} >> $MANIFEST
 done
 
-tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
+tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
 rm -f $MANIFEST $BUILDIDS
 echo -e "Now please run:\n"
 echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6e4871191138..cdd6c03f1e14 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -458,6 +458,8 @@ int main(int argc, const char **argv)
         handle_options(&argv, &argc, NULL);
         commit_pager_choice();
         set_debugfs_path();
+        set_buildid_dir();
+
         if (argc > 0) {
                 if (!prefixcmp(argv[0], "--"))
                         argv[0] += 2;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 70c5cf87d020..5c26e2d314af 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,19 +43,17 @@ struct perf_event_ops build_id__mark_dso_hit_ops = {
 char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
 {
         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-        const char *home;
 
         if (!self->has_build_id)
                 return NULL;
 
         build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex);
-        home = getenv("HOME");
         if (bf == NULL) {
-                if (asprintf(&bf, "%s/%s/.build-id/%.2s/%s", home,
-                             DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2) < 0)
+                if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir,
+                             build_id_hex, build_id_hex + 2) < 0)
                         return NULL;
         } else
-                snprintf(bf, size, "%s/%s/.build-id/%.2s/%s", home,
-                         DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2);
+                snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
+                         build_id_hex, build_id_hex + 2);
         return bf;
 }
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 65fe664fddf6..27e9ebe4076e 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,6 +23,7 @@ extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
+extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad4aa73..e63c997d6c1b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -18,7 +18,7 @@
 #include "util.h"
 #include "callchain.h"
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
 {
         unsigned int chain_size = event->header.size;
         chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4a2723..809850fb75fb 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -60,5 +60,5 @@ int register_callchain_param(struct callchain_param *param);
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
                  struct map_symbol *syms);
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index dabe892d0e53..e02d78cae70f 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,6 +11,11 @@
 
 #define MAXNAME (256)
 
+#define DEBUG_CACHE_DIR ".debug"
+
+
+char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */
+
 static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
@@ -127,7 +132,7 @@ static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
                         break;
                 if (!iskeychar(c))
                         break;
-                name[len++] = tolower(c);
+                name[len++] = c;
                 if (len >= MAXNAME)
                         return -1;
         }
@@ -327,6 +332,13 @@ int perf_config_bool(const char *name, const char *value)
         return !!perf_config_bool_or_int(name, value, &discard);
 }
 
+const char *perf_config_dirname(const char *name, const char *value)
+{
+        if (!name)
+                return NULL;
+        return value;
+}
+
 static int perf_default_core_config(const char *var __used, const char *value __used)
 {
         /* Add other config variables here and to Documentation/config.txt. */
@@ -428,3 +440,53 @@ int config_error_nonbool(const char *var)
 {
         return error("Missing value for '%s'", var);
 }
+
+struct buildid_dir_config {
+        char *dir;
+};
+
+static int buildid_dir_command_config(const char *var, const char *value,
+                                      void *data)
+{
+        struct buildid_dir_config *c = data;
+        const char *v;
+
+        /* same dir for all commands */
+        if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
+                v = perf_config_dirname(var, value);
+                if (!v)
+                        return -1;
+                strncpy(c->dir, v, MAXPATHLEN-1);
+                c->dir[MAXPATHLEN-1] = '\0';
+        }
+        return 0;
+}
+
+static void check_buildid_dir_config(void)
+{
+        struct buildid_dir_config c;
+        c.dir = buildid_dir;
+        perf_config(buildid_dir_command_config, &c);
+}
+
+void set_buildid_dir(void)
+{
+        buildid_dir[0] = '\0';
+
+        /* try config file */
+        check_buildid_dir_config();
+
+        /* default to $HOME/.debug */
+        if (buildid_dir[0] == '\0') {
+                char *v = getenv("HOME");
+                if (v) {
+                        snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s",
+                                 v, DEBUG_CACHE_DIR);
+                } else {
+                        strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1);
+                }
+                buildid_dir[MAXPATHLEN-1] = '\0';
+        }
+        /* for communicating with external commands */
+        setenv("PERF_BUILDID_DIR", buildid_dir, 1);
+}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 4e01490e51e5..0f9b8d7a7d7e 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -20,7 +20,7 @@ static int default_cpu_map(void)
         return nr_cpus;
 }
 
-int read_cpu_map(void)
+static int read_all_cpu_map(void)
 {
         FILE *onlnf;
         int nr_cpus = 0;
@@ -57,3 +57,58 @@ int read_cpu_map(void)
 
         return default_cpu_map();
 }
+
+int read_cpu_map(const char *cpu_list)
+{
+        unsigned long start_cpu, end_cpu = 0;
+        char *p = NULL;
+        int i, nr_cpus = 0;
+
+        if (!cpu_list)
+                return read_all_cpu_map();
+
+        if (!isdigit(*cpu_list))
+                goto invalid;
+
+        while (isdigit(*cpu_list)) {
+                p = NULL;
+                start_cpu = strtoul(cpu_list, &p, 0);
+                if (start_cpu >= INT_MAX
+                    || (*p != '\0' && *p != ',' && *p != '-'))
+                        goto invalid;
+
+                if (*p == '-') {
+                        cpu_list = ++p;
+                        p = NULL;
+                        end_cpu = strtoul(cpu_list, &p, 0);
+
+                        if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
+                                goto invalid;
+
+                        if (end_cpu < start_cpu)
+                                goto invalid;
+                } else {
+                        end_cpu = start_cpu;
+                }
+
+                for (; start_cpu <= end_cpu; start_cpu++) {
+                        /* check for duplicates */
+                        for (i = 0; i < nr_cpus; i++)
+                                if (cpumap[i] == (int)start_cpu)
+                                        goto invalid;
+
+                        assert(nr_cpus < MAX_NR_CPUS);
+                        cpumap[nr_cpus++] = (int)start_cpu;
+                }
+                if (*p)
+                        ++p;
+
+                cpu_list = p;
+        }
+        if (nr_cpus > 0)
+                return nr_cpus;
+
+        return default_cpu_map();
+invalid:
+        return -1;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 86c78bb33098..3e60f56e490e 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
-extern int read_cpu_map(void);
+extern int read_cpu_map(const char *cpu_list);
 extern int cpumap[];
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 6cddff2bc970..318dab15d177 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -86,12 +86,10 @@ void trace_event(event_t *event)
                         dump_printf_color("  ", color);
                         for (j = 0; j < 15-(i & 15); j++)
                                 dump_printf_color("   ", color);
-                        for (j = 0; j < (i & 15); j++) {
-                                if (isprint(raw_event[i-15+j]))
-                                        dump_printf_color("%c", color,
-                                                          raw_event[i-15+j]);
-                                else
-                                        dump_printf_color(".", color);
+                        for (j = i & ~15; j <= i; j++) {
+                                dump_printf_color("%c", color,
+                                                isprint(raw_event[j]) ?
+                                                raw_event[j] : '.');
                         }
                         dump_printf_color("\n", color);
                 }
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1f08f008d289..a7460868124b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -655,11 +655,36 @@ static void dso__calc_col_width(struct dso *self)
 }
 
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, symbol_filter_t filter)
+                             struct addr_location *al, struct sample_data *data,
+                             symbol_filter_t filter)
 {
         u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        struct thread *thread = perf_session__findnew(session, self->ip.pid);
+        struct thread *thread;
+
+        event__parse_sample(self, session->sample_type, data);
+
+        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n",
+                    self->header.misc, data->pid, data->tid, data->ip,
+                    data->period, data->cpu);
+
+        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
+                unsigned int i;
+
+                dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
+
+                if (!ip_callchain__valid(data->callchain, self)) {
+                        pr_debug("call-chain problem with event, "
+                                 "skipping it.\n");
+                        goto out_filtered;
+                }
 
+                if (dump_trace) {
+                        for (i = 0; i < data->callchain->nr; i++)
+                                dump_printf("..... %2d: %016Lx\n",
+                                            i, data->callchain->ips[i]);
+                }
+        }
+        thread = perf_session__findnew(session, self->ip.pid);
         if (thread == NULL)
                 return -1;
 
@@ -685,6 +710,7 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
                     al->map ? al->map->dso->long_name :
                         al->level == 'H' ? "[hypervisor]" : "<not found>");
         al->sym = NULL;
+        al->cpu = data->cpu;
 
         if (al->map) {
                 if (symbol_conf.dso_list &&
@@ -724,9 +750,9 @@ out_filtered:
         return 0;
 }
 
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
+int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
 {
-        u64 *array = event->sample.array;
+        const u64 *array = event->sample.array;
 
         if (type & PERF_SAMPLE_IP) {
                 data->ip = event->ip.ip;
@@ -765,7 +791,8 @@ int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
                 u32 *p = (u32 *)array;
                 data->cpu = *p;
                 array++;
-        }
+        } else
+                data->cpu = -1;
 
         if (type & PERF_SAMPLE_PERIOD) {
                 data->period = *array;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8577085db067..887ee63bbb62 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -157,8 +157,9 @@ int event__process_task(event_t *self, struct perf_session *session);
 
 struct addr_location;
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, symbol_filter_t filter);
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data);
+                             struct addr_location *al, struct sample_data *data,
+                             symbol_filter_t filter);
+int event__parse_sample(const event_t *event, u64 type, struct sample_data *data);
 
 extern const char *event__name[];
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1f62435f96c2..d7e67b167ea3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -16,6 +16,8 @@
 #include "symbol.h"
 #include "debug.h"
 
+static bool no_buildid_cache = false;
+
 /*
  * Create new perf.data header attribute:
  */
@@ -385,8 +387,7 @@ static int perf_session__cache_build_ids(struct perf_session *self)
         int ret;
         char debugdir[PATH_MAX];
 
-        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-                 DEBUG_CACHE_DIR);
+        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
         if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
                 return -1;
@@ -471,7 +472,8 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
                 }
                 buildid_sec->size = lseek(fd, 0, SEEK_CUR) -
                                           buildid_sec->offset;
-                perf_session__cache_build_ids(session);
+                if (!no_buildid_cache)
+                        perf_session__cache_build_ids(session);
         }
 
         lseek(fd, sec_start, SEEK_SET);
@@ -1190,3 +1192,8 @@ int event__process_build_id(event_t *self,
                                  session);
         return 0;
 }
+
+void disable_buildid_cache(void)
+{
+        no_buildid_cache = true;
+}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 07f89b66b318..68d288c975de 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -70,6 +70,7 @@ struct hist_entry *__hists__add_entry(struct hists *self,
                         .map    = al->map,
                         .sym    = al->sym,
                 },
+                .cpu    = al->cpu,
                 .ip     = al->addr,
                 .level  = al->level,
                 .period = period,
@@ -1037,7 +1038,7 @@ fallback:
                  dso, dso->long_name, sym, sym->name);
 
         snprintf(command, sizeof(command),
-                 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand",
+                 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
                  map__rip_2objdump(map, sym->start),
                  map__rip_2objdump(map, sym->end),
                  filename, filename);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index d964cb199c67..baf665383498 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -37,6 +37,7 @@
 #include "event.h"
 #include "debug.h"
 #include "util.h"
+#include "symbol.h"
 #include "probe-finder.h"
 
 /* Kprobe tracer basic type is up to u64 */
@@ -57,6 +58,55 @@ static int strtailcmp(const char *s1, const char *s2)
         return 0;
 }
 
+/*
+ * Find a src file from a DWARF tag path. Prepend optional source path prefix
+ * and chop off leading directories that do not exist. Result is passed back as
+ * a newly allocated path on success.
+ * Return 0 if file was found and readable, -errno otherwise.
+ */
+static int get_real_path(const char *raw_path, char **new_path)
+{
+        if (!symbol_conf.source_prefix) {
+                if (access(raw_path, R_OK) == 0) {
+                        *new_path = strdup(raw_path);
+                        return 0;
+                } else
+                        return -errno;
+        }
+
+        *new_path = malloc((strlen(symbol_conf.source_prefix) +
+                            strlen(raw_path) + 2));
+        if (!*new_path)
+                return -ENOMEM;
+
+        for (;;) {
+                sprintf(*new_path, "%s/%s", symbol_conf.source_prefix,
+                        raw_path);
+
+                if (access(*new_path, R_OK) == 0)
+                        return 0;
+
+                switch (errno) {
+                case ENAMETOOLONG:
+                case ENOENT:
+                case EROFS:
+                case EFAULT:
+                        raw_path = strchr(++raw_path, '/');
+                        if (!raw_path) {
+                                free(*new_path);
+                                *new_path = NULL;
+                                return -ENOENT;
+                        }
+                        continue;
+
+                default:
+                        free(*new_path);
+                        *new_path = NULL;
+                        return -errno;
+                }
+        }
+}
+
 /* Line number list operations */
 
 /* Add a line to line number list */
@@ -1096,11 +1146,13 @@ end:
 static int line_range_add_line(const char *src, unsigned int lineno,
                                struct line_range *lr)
 {
+        int ret;
+
         /* Copy real path */
         if (!lr->path) {
-                lr->path = strdup(src);
-                if (lr->path == NULL)
-                        return -ENOMEM;
+                ret = get_real_path(src, &lr->path);
+                if (ret != 0)
+                        return ret;
         }
         return line_list__add_line(&lr->line_list, lineno);
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8f83a1835766..0564a5cfb12e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -27,8 +27,10 @@ static int perf_session__open(struct perf_session *self, bool force)
 
         self->fd = open(self->filename, O_RDONLY);
         if (self->fd < 0) {
-                pr_err("failed to open file: %s", self->filename);
-                if (!strcmp(self->filename, "perf.data"))
+                int err = errno;
+
+                pr_err("failed to open %s: %s", self->filename, strerror(err));
+                if (err == ENOENT && !strcmp(self->filename, "perf.data"))
                         pr_err("  (try 'perf record' first)");
                 pr_err("\n");
                 return -errno;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2316cb5a4116..c27b4b03fbc1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -13,6 +13,7 @@ enum sort_type	sort__first_dimension;
 unsigned int dsos__col_width;
 unsigned int comms__col_width;
 unsigned int threads__col_width;
+unsigned int cpus__col_width;
 static unsigned int parent_symbol__col_width;
 char * field_sep;
 
@@ -28,6 +29,8 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
                                     size_t size, unsigned int width);
 static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
                                        size_t size, unsigned int width);
+static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
+                                    size_t size, unsigned int width);
 
 struct sort_entry sort_thread = {
         .se_header      = "Command:  Pid",
@@ -63,6 +66,13 @@ struct sort_entry sort_parent = {
         .se_snprintf    = hist_entry__parent_snprintf,
         .se_width       = &parent_symbol__col_width,
 };
+ 
+struct sort_entry sort_cpu = {
+        .se_header      = "CPU",
+        .se_cmp         = sort__cpu_cmp,
+        .se_snprintf    = hist_entry__cpu_snprintf,
+        .se_width       = &cpus__col_width,
+};
 
 struct sort_dimension {
         const char              *name;
@@ -76,6 +86,7 @@ static struct sort_dimension sort_dimensions[] = {
         { .name = "dso",        .entry = &sort_dso,     },
         { .name = "symbol",     .entry = &sort_sym,     },
         { .name = "parent",     .entry = &sort_parent,  },
+        { .name = "cpu",        .entry = &sort_cpu,     },
 };
 
 int64_t cmp_null(void *l, void *r)
@@ -242,6 +253,20 @@ static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
                               self->parent ? self->parent->name : "[other]");
 }
 
+/* --sort cpu */
+
+int64_t
+sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        return right->cpu - left->cpu;
+}
+
+static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
+                                       size_t size, unsigned int width)
+{
+        return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
+}
+
 int sort_dimension__add(const char *tok)
 {
         unsigned int i;
@@ -281,6 +306,8 @@ int sort_dimension__add(const char *tok)
                                 sort__first_dimension = SORT_SYM;
                         else if (!strcmp(sd->name, "parent"))
                                 sort__first_dimension = SORT_PARENT;
+                        else if (!strcmp(sd->name, "cpu"))
+                                sort__first_dimension = SORT_CPU;
                 }
 
                 list_add_tail(&sd->entry->list, &hist_entry__sort_list);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 0d61c4082f43..560c855417e4 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -39,6 +39,7 @@ extern struct sort_entry sort_parent;
 extern unsigned int dsos__col_width;
 extern unsigned int comms__col_width;
 extern unsigned int threads__col_width;
+extern unsigned int cpus__col_width;
 extern enum sort_type sort__first_dimension;
 
 struct hist_entry {
@@ -51,6 +52,7 @@ struct hist_entry {
         struct map_symbol       ms;
         struct thread           *thread;
         u64                     ip;
+        s32                     cpu;
         u32                     nr_events;
         char                    level;
         u8                      filtered;
@@ -68,7 +70,8 @@ enum sort_type {
         SORT_COMM,
         SORT_DSO,
         SORT_SYM,
-        SORT_PARENT
+        SORT_PARENT,
+        SORT_CPU,
 };
 
 /*
@@ -104,6 +107,7 @@ extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
+int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right);
 extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
 extern int sort_dimension__add(const char *);
 void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b63e5713849f..971d0a05d6b4 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -933,6 +933,25 @@ static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type
         }
 }
 
+static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
+{
+        Elf_Scn *sec = NULL;
+        GElf_Shdr shdr;
+        size_t cnt = 1;
+
+        while ((sec = elf_nextscn(elf, sec)) != NULL) {
+                gelf_getshdr(sec, &shdr);
+
+                if ((addr >= shdr.sh_addr) &&
+                    (addr < (shdr.sh_addr + shdr.sh_size)))
+                        return cnt;
+
+                ++cnt;
+        }
+
+        return -1;
+}
+
 static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                          int fd, symbol_filter_t filter, int kmodule)
 {
@@ -944,12 +963,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
         int err = -1;
         uint32_t idx;
         GElf_Ehdr ehdr;
-        GElf_Shdr shdr;
-        Elf_Data *syms;
+        GElf_Shdr shdr, opdshdr;
+        Elf_Data *syms, *opddata = NULL;
         GElf_Sym sym;
-        Elf_Scn *sec, *sec_strndx;
+        Elf_Scn *sec, *sec_strndx, *opdsec;
         Elf *elf;
         int nr = 0;
+        size_t opdidx = 0;
 
         elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
         if (elf == NULL) {
@@ -969,6 +989,10 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                         goto out_elf_end;
         }
 
+        opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx);
+        if (opdsec)
+                opddata = elf_rawdata(opdsec, NULL);
+
         syms = elf_getdata(sec, NULL);
         if (syms == NULL)
                 goto out_elf_end;
@@ -1013,6 +1037,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                 if (!is_label && !elf_sym__is_a(&sym, map->type))
                         continue;
 
+                if (opdsec && sym.st_shndx == opdidx) {
+                        u32 offset = sym.st_value - opdshdr.sh_addr;
+                        u64 *opd = opddata->d_buf + offset;
+                        sym.st_value = *opd;
+                        sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
+                }
+
                 sec = elf_getscn(elf, sym.st_shndx);
                 if (!sec)
                         goto out_elf_end;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5e02d2c17154..80e569bbdecc 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,8 +9,6 @@
 #include <linux/rbtree.h>
 #include <stdio.h>
 
-#define DEBUG_CACHE_DIR ".debug"
-
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
 
@@ -73,6 +71,7 @@ struct symbol_conf {
                         full_paths,
                         show_cpu_utilization;
         const char      *vmlinux_name,
+                        *source_prefix,
                         *field_sep;
         const char      *default_guest_vmlinux_name,
                         *default_guest_kallsyms,
@@ -112,7 +111,8 @@ struct addr_location {
         u64           addr;
         char          level;
         bool          filtered;
-        unsigned int  cpumode;
+        u8            cpumode;
+        s32           cpu;
 };
 
 enum dso_kernel_type {
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 4e8b6b0c551c..f380fed74359 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -89,6 +89,7 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -152,6 +153,8 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
 
 extern int prefixcmp(const char *str, const char *prefix);
+extern void set_buildid_dir(void);
+extern void disable_buildid_cache(void);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {