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

Pull perf changes from Ingo Molnar:
 "There are lots of improvements, the biggest changes are:

  Main kernel side changes:

   - Improve uprobes performance by adding 'pre-filtering' support, by
     Oleg Nesterov.

   - Make some POWER7 events available in sysfs, equivalent to what was
     done on x86, from Sukadev Bhattiprolu.

   - tracing updates by Steve Rostedt - mostly misc fixes and smaller
     improvements.

   - Use perf/event tracing to report PCI Express advanced errors, by
     Tony Luck.

   - Enable northbridge performance counters on AMD family 15h, by Jacob
     Shin.

   - This tracing commit:

        tracing: Remove the extra 4 bytes of padding in events

     changes the ABI.  All involved parties (PowerTop in particular)
     seem to agree that it's safe to do now with the introduction of
     libtraceevent, but the devil is in the details ...

  Main tooling side changes:

   - Add 'event group view', from Namyung Kim:

     To use it, 'perf record' should group events when recording.  And
     then perf report parses the saved group relation from file header
     and prints them together if --group option is provided.  You can
     use the 'perf evlist' command to see event group information:

        $ perf record -e '{ref-cycles,cycles}' noploop 1
        [ perf record: Woken up 2 times to write data ]
        [ perf record: Captured and wrote 0.385 MB perf.data (~16807 samples) ]

        $ perf evlist --group
        {ref-cycles,cycles}

     With this example, default perf report will show you each event
     separately.

     You can use --group option to enable event group view:

        $ perf report --group
        ...
        # group: {ref-cycles,cycles}
        # ========
        # Samples: 7K of event 'anon group { ref-cycles, cycles }'
        # Event count (approx.): 6876107743
        #
        #         Overhead  Command      Shared Object                      Symbol
        # ................  .......  .................  ..........................
            99.84%  99.76%  noploop  noploop            [.] main
             0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
             0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
             0.03%   0.03%  noploop  [kernel.kallsyms]  [k] sched_clock_cpu
             0.02%   0.00%  noploop  [kernel.kallsyms]  [k] account_user_time
             0.01%   0.00%  noploop  [kernel.kallsyms]  [k] __alloc_pages_nodemask
             0.00%   0.00%  noploop  [kernel.kallsyms]  [k] native_write_msr_safe
             0.00%   0.11%  noploop  [kernel.kallsyms]  [k] _raw_spin_lock
             0.00%   0.06%  noploop  [kernel.kallsyms]  [k] find_get_page
             0.00%   0.02%  noploop  [kernel.kallsyms]  [k] rcu_check_callbacks
             0.00%   0.02%  noploop  [kernel.kallsyms]  [k] __current_kernel_time

     As you can see the Overhead column now contains both of ref-cycles
     and cycles and header line shows group information also - 'anon
     group { ref-cycles, cycles }'.  The output is sorted by period of
     group leader first.

   - Initial GTK+ annotate browser, from Namhyung Kim.

   - Add option for runtime switching perf data file in perf report,
     just press 's' and a menu with the valid files found in the current
     directory will be presented, from Feng Tang.

   - Add support to display whole group data for raw columns, from Jiri
     Olsa.

   - Add per processor socket count aggregation in perf stat, from
     Stephane Eranian.

   - Add interval printing in 'perf stat', from Stephane Eranian.

   - 'perf test' improvements

   - Add support for wildcards in tracepoint system name, from Jiri
     Olsa.

   - Add anonymous huge page recognition, from Joshua Zhu.

   - perf build-id cache now can show DSOs present in a perf.data file
     that are not in the cache, to integrate with build-id servers being
     put in place by organizations such as Fedora.

   - perf top now shares more of the evsel config/creation routines with
     'record', paving the way for further integration like 'top'
     snapshots, etc.

   - perf top now supports DWARF callchains.

   - Fix mmap limitations on 32-bit, fix from David Miller.

   - 'perf bench numa mem' NUMA performance measurement suite

   - ... and lots of fixes, performance improvements, cleanups and other
     improvements I failed to list - see the shortlog and git log for
     details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (270 commits)
  perf/x86/amd: Enable northbridge performance counters on AMD family 15h
  perf/hwbp: Fix cleanup in case of kzalloc failure
  perf tools: Fix build with bison 2.3 and older.
  perf tools: Limit unwind support to x86 archs
  perf annotate: Make it to be able to skip unannotatable symbols
  perf gtk/annotate: Fail early if it can't annotate
  perf gtk/annotate: Show source lines with gray color
  perf gtk/annotate: Support multiple event annotation
  perf ui/gtk: Implement basic GTK2 annotation browser
  perf annotate: Fix warning message on a missing vmlinux
  perf buildid-cache: Add --update option
  uprobes/perf: Avoid uprobe_apply() whenever possible
  uprobes/perf: Teach trace_uprobe/perf code to use UPROBE_HANDLER_REMOVE
  uprobes/perf: Teach trace_uprobe/perf code to pre-filter
  uprobes/perf: Teach trace_uprobe/perf code to track the active perf_event's
  uprobes: Introduce uprobe_apply()
  perf: Introduce hw_perf_event->tp_target and ->tp_list
  uprobes/perf: Always increment trace_uprobe->nhit
  uprobes/tracing: Kill uprobe_trace_consumer, embed uprobe_consumer into trace_uprobe
  uprobes/tracing: Introduce is_trace_uprobe_enabled()
  ...

15 files changed, 398 insertions, 180 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 36b05ed0bb3c..a2570490eab6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -39,10 +39,12 @@ config X86
 	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
+	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FENTRY if X86_64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 2d9075e863a0..93fe929d1cee 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -167,6 +167,7 @@
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
 #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -309,6 +310,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
+#define cpu_has_perfctr_nb	boot_cpu_has(X86_FEATURE_PERFCTR_NB)
 #define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9a25b522d377..86cb51e1ca96 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -44,7 +44,6 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
-#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4fabcdf1cfa7..57cb63402213 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,8 +29,13 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
-#define AMD_PERFMON_EVENTSEL_GUESTONLY			(1ULL << 40)
-#define AMD_PERFMON_EVENTSEL_HOSTONLY			(1ULL << 41)
+#define AMD64_EVENTSEL_INT_CORE_ENABLE			(1ULL << 36)
+#define AMD64_EVENTSEL_GUESTONLY			(1ULL << 40)
+#define AMD64_EVENTSEL_HOSTONLY				(1ULL << 41)
+
+#define AMD64_EVENTSEL_INT_CORE_SEL_SHIFT		37
+#define AMD64_EVENTSEL_INT_CORE_SEL_MASK		\
+	(0xFULL << AMD64_EVENTSEL_INT_CORE_SEL_SHIFT)
 
 #define AMD64_EVENTSEL_EVENT	\
 	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
@@ -46,8 +51,12 @@
 #define AMD64_RAW_EVENT_MASK		\
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
+#define AMD64_RAW_EVENT_MASK_NB		\
+	(AMD64_EVENTSEL_EVENT        |  \
+	 ARCH_PERFMON_EVENTSEL_UMASK)
 #define AMD64_NUM_COUNTERS				4
 #define AMD64_NUM_COUNTERS_CORE				6
+#define AMD64_NUM_COUNTERS_NB				4
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 433a59fb1a74..075a40255591 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -194,6 +194,8 @@
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
 #define MSR_F15H_PERF_CTR		0xc0010201
+#define MSR_F15H_NB_PERF_CTL		0xc0010240
+#define MSR_F15H_NB_PERF_CTR		0xc0010241
 
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 34e923a53762..ac3b3d002833 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -65,8 +65,7 @@ obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
-obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
+obj-y				+= kprobes/
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6774c17a5576..bf0f01aea994 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -829,7 +829,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 	} else {
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
-		hwc->event_base_rdpmc = hwc->idx;
+		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
 	}
 }
 
@@ -1310,11 +1310,6 @@ static struct attribute_group x86_pmu_format_group = {
 	.attrs = NULL,
 };
 
-struct perf_pmu_events_attr {
-	struct device_attribute attr;
-	u64 id;
-};
-
 /*
  * Remove all undefined events (x86_pmu.event_map(id) == 0)
  * out of events_attr attributes.
@@ -1348,11 +1343,9 @@ static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *at
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
 
-#define EVENT_ATTR(_name, _id)					\
-static struct perf_pmu_events_attr EVENT_VAR(_id) = {		\
-	.attr = __ATTR(_name, 0444, events_sysfs_show, NULL),	\
-	.id   =  PERF_COUNT_HW_##_id,				\
-};
+#define EVENT_ATTR(_name, _id)						\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,	\
+			events_sysfs_show)
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 115c1ea97746..7f5c75c2afdd 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -325,6 +325,8 @@ struct x86_pmu {
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	int		(*addr_offset)(int index, bool eventsel);
+	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
 	int		num_counters;
@@ -446,28 +448,21 @@ extern u64 __read_mostly hw_cache_extra_regs
 
 u64 x86_perf_event_update(struct perf_event *event);
 
-static inline int x86_pmu_addr_offset(int index)
+static inline unsigned int x86_pmu_config_addr(int index)
 {
-	int offset;
-
-	/* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */
-	alternative_io(ASM_NOP2,
-		       "shll $1, %%eax",
-		       X86_FEATURE_PERFCTR_CORE,
-		       "=a" (offset),
-		       "a"  (index));
-
-	return offset;
+	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, true) : index);
 }
 
-static inline unsigned int x86_pmu_config_addr(int index)
+static inline unsigned int x86_pmu_event_addr(int index)
 {
-	return x86_pmu.eventsel + x86_pmu_addr_offset(index);
+	return x86_pmu.perfctr + (x86_pmu.addr_offset ?
+				  x86_pmu.addr_offset(index, false) : index);
 }
 
-static inline unsigned int x86_pmu_event_addr(int index)
+static inline int x86_pmu_rdpmc_index(int index)
 {
-	return x86_pmu.perfctr + x86_pmu_addr_offset(index);
+	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
 int x86_setup_perfctr(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index c93bc4e813a0..dfdab42aed27 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -132,21 +132,102 @@ static u64 amd_pmu_event_map(int hw_event)
 	return amd_perfmon_event_map[hw_event];
 }
 
-static int amd_pmu_hw_config(struct perf_event *event)
+static struct event_constraint *amd_nb_event_constraint;
+
+/*
+ * Previously calculated offsets
+ */
+static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly;
+static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly;
+static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
+
+/*
+ * Legacy CPUs:
+ *   4 counters starting at 0xc0010000 each offset by 1
+ *
+ * CPUs with core performance counter extensions:
+ *   6 counters starting at 0xc0010200 each offset by 2
+ *
+ * CPUs with north bridge performance counter extensions:
+ *   4 additional counters starting at 0xc0010240 each offset by 2
+ *   (indexed right above either one of the above core counters)
+ */
+static inline int amd_pmu_addr_offset(int index, bool eventsel)
 {
-	int ret;
+	int offset, first, base;
 
-	/* pass precise event sampling to ibs: */
-	if (event->attr.precise_ip && get_ibs_caps())
-		return -ENOENT;
+	if (!index)
+		return index;
+
+	if (eventsel)
+		offset = event_offsets[index];
+	else
+		offset = count_offsets[index];
+
+	if (offset)
+		return offset;
+
+	if (amd_nb_event_constraint &&
+	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
+		/*
+		 * calculate the offset of NB counters with respect to
+		 * base eventsel or perfctr
+		 */
+
+		first = find_first_bit(amd_nb_event_constraint->idxmsk,
+				       X86_PMC_IDX_MAX);
+
+		if (eventsel)
+			base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel;
+		else
+			base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr;
+
+		offset = base + ((index - first) << 1);
+	} else if (!cpu_has_perfctr_core)
+		offset = index;
+	else
+		offset = index << 1;
+
+	if (eventsel)
+		event_offsets[index] = offset;
+	else
+		count_offsets[index] = offset;
+
+	return offset;
+}
+
+static inline int amd_pmu_rdpmc_index(int index)
+{
+	int ret, first;
+
+	if (!index)
+		return index;
+
+	ret = rdpmc_indexes[index];
 
-	ret = x86_pmu_hw_config(event);
 	if (ret)
 		return ret;
 
-	if (has_branch_stack(event))
-		return -EOPNOTSUPP;
+	if (amd_nb_event_constraint &&
+	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
+		/*
+		 * according to the mnual, ECX value of the NB counters is
+		 * the index of the NB counter (0, 1, 2 or 3) plus 6
+		 */
+
+		first = find_first_bit(amd_nb_event_constraint->idxmsk,
+				       X86_PMC_IDX_MAX);
+		ret = index - first + 6;
+	} else
+		ret = index;
+
+	rdpmc_indexes[index] = ret;
+
+	return ret;
+}
 
+static int amd_core_hw_config(struct perf_event *event)
+{
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
@@ -156,14 +237,37 @@ static int amd_pmu_hw_config(struct perf_event *event)
 		event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
 				      ARCH_PERFMON_EVENTSEL_OS);
 	else if (event->attr.exclude_host)
-		event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY;
+		event->hw.config |= AMD64_EVENTSEL_GUESTONLY;
 	else if (event->attr.exclude_guest)
-		event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY;
+		event->hw.config |= AMD64_EVENTSEL_HOSTONLY;
+
+	return 0;
+}
+
+/*
+ * NB counters do not support the following event select bits:
+ *   Host/Guest only
+ *   Counter mask
+ *   Invert counter mask
+ *   Edge detect
+ *   OS/User mode
+ */
+static int amd_nb_hw_config(struct perf_event *event)
+{
+	/* for NB, we only allow system wide counting mode */
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EINVAL;
+
+	if (event->attr.exclude_user || event->attr.exclude_kernel ||
+	    event->attr.exclude_host || event->attr.exclude_guest)
+		return -EINVAL;
 
-	if (event->attr.type != PERF_TYPE_RAW)
-		return 0;
+	event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
+			      ARCH_PERFMON_EVENTSEL_OS);
 
-	event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+	if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB |
+				 ARCH_PERFMON_EVENTSEL_INT))
+		return -EINVAL;
 
 	return 0;
 }
@@ -181,6 +285,11 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc)
+{
+	return amd_nb_event_constraint && amd_is_nb_event(hwc);
+}
+
 static inline int amd_has_nb(struct cpu_hw_events *cpuc)
 {
 	struct amd_nb *nb = cpuc->amd_nb;
@@ -188,20 +297,37 @@ static inline int amd_has_nb(struct cpu_hw_events *cpuc)
 	return nb && nb->nb_id != -1;
 }
 
-static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
-				      struct perf_event *event)
+static int amd_pmu_hw_config(struct perf_event *event)
+{
+	int ret;
+
+	/* pass precise event sampling to ibs: */
+	if (event->attr.precise_ip && get_ibs_caps())
+		return -ENOENT;
+
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	ret = x86_pmu_hw_config(event);
+	if (ret)
+		return ret;
+
+	if (event->attr.type == PERF_TYPE_RAW)
+		event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+
+	if (amd_is_perfctr_nb_event(&event->hw))
+		return amd_nb_hw_config(event);
+
+	return amd_core_hw_config(event);
+}
+
+static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
+					   struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
 	int i;
 
 	/*
-	 * only care about NB events
-	 */
-	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
-		return;
-
-	/*
 	 * need to scan whole list because event may not have
 	 * been assigned during scheduling
 	 *
@@ -215,6 +341,19 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	}
 }
 
+static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc)
+{
+	int core_id = cpu_data(smp_processor_id()).cpu_core_id;
+
+	/* deliver interrupts only to this core */
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) {
+		hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE;
+		hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK;
+		hwc->config |= (u64)(core_id) <<
+			AMD64_EVENTSEL_INT_CORE_SEL_SHIFT;
+	}
+}
+
  /*
   * AMD64 NorthBridge events need special treatment because
   * counter access needs to be synchronized across all cores
@@ -247,24 +386,24 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
   *
   * Given that resources are allocated (cmpxchg), they must be
   * eventually freed for others to use. This is accomplished by
-  * calling amd_put_event_constraints().
+  * calling __amd_put_nb_event_constraints()
   *
   * Non NB events are not impacted by this restriction.
   */
 static struct event_constraint *
-amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+__amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
+			       struct event_constraint *c)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
-	struct perf_event *old = NULL;
-	int max = x86_pmu.num_counters;
-	int i, j, k = -1;
+	struct perf_event *old;
+	int idx, new = -1;
 
-	/*
-	 * if not NB event or no NB, then no constraints
-	 */
-	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
-		return &unconstrained;
+	if (!c)
+		c = &unconstrained;
+
+	if (cpuc->is_fake)
+		return c;
 
 	/*
 	 * detect if already present, if so reuse
@@ -276,48 +415,36 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for (i = 0; i < max; i++) {
-		/*
-		 * keep track of first free slot
-		 */
-		if (k == -1 && !nb->owners[i])
-			k = i;
+	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+		if (new == -1 || hwc->idx == idx)
+			/* assign free slot, prefer hwc->idx */
+			old = cmpxchg(nb->owners + idx, NULL, event);
+		else if (nb->owners[idx] == event)
+			/* event already present */
+			old = event;
+		else
+			continue;
+
+		if (old && old != event)
+			continue;
+
+		/* reassign to this slot */
+		if (new != -1)
+			cmpxchg(nb->owners + new, event, NULL);
+		new = idx;
 
 		/* already present, reuse */
-		if (nb->owners[i] == event)
-			goto done;
-	}
-	/*
-	 * not present, so grab a new slot
-	 * starting either at:
-	 */
-	if (hwc->idx != -1) {
-		/* previous assignment */
-		i = hwc->idx;
-	} else if (k != -1) {
-		/* start from free slot found */
-		i = k;
-	} else {
-		/*
-		 * event not found, no slot found in
-		 * first pass, try again from the
-		 * beginning
-		 */
-		i = 0;
-	}
-	j = i;
-	do {
-		old = cmpxchg(nb->owners+i, NULL, event);
-		if (!old)
+		if (old == event)
 			break;
-		if (++i == max)
-			i = 0;
-	} while (i != j);
-done:
-	if (!old)
-		return &nb->event_constraints[i];
-
-	return &emptyconstraint;
+	}
+
+	if (new == -1)
+		return &emptyconstraint;
+
+	if (amd_is_perfctr_nb_event(hwc))
+		amd_nb_interrupt_hw_config(hwc);
+
+	return &nb->event_constraints[new];
 }
 
 static struct amd_nb *amd_alloc_nb(int cpu)
@@ -364,7 +491,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	struct amd_nb *nb;
 	int i, nb_id;
 
-	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
@@ -407,6 +534,26 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+static struct event_constraint *
+amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	/*
+	 * if not NB event or no NB, then no constraints
+	 */
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)))
+		return &unconstrained;
+
+	return __amd_get_nb_event_constraints(cpuc, event,
+					      amd_nb_event_constraint);
+}
+
+static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	if (amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))
+		__amd_put_nb_event_constraints(cpuc, event);
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7,32-35");
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -496,6 +643,9 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09,
 static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
 static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 
+static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0);
+static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0);
+
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
@@ -561,8 +711,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		/* not yet implemented */
-		return &emptyconstraint;
+		return __amd_get_nb_event_constraints(cpuc, event,
+						      amd_nb_event_constraint);
 	default:
 		return &emptyconstraint;
 	}
@@ -587,6 +737,8 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
+	.addr_offset            = amd_pmu_addr_offset,
+	.rdpmc_index		= amd_pmu_rdpmc_index,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
 	.num_counters		= AMD64_NUM_COUNTERS,
@@ -608,7 +760,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 
 static int setup_event_constraints(void)
 {
-	if (boot_cpu_data.x86 >= 0x15)
+	if (boot_cpu_data.x86 == 0x15)
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
 	return 0;
 }
@@ -638,6 +790,23 @@ static int setup_perfctr_core(void)
 	return 0;
 }
 
+static int setup_perfctr_nb(void)
+{
+	if (!cpu_has_perfctr_nb)
+		return -ENODEV;
+
+	x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB;
+
+	if (cpu_has_perfctr_core)
+		amd_nb_event_constraint = &amd_NBPMC96;
+	else
+		amd_nb_event_constraint = &amd_NBPMC74;
+
+	printk(KERN_INFO "perf: AMD northbridge performance counters detected\n");
+
+	return 0;
+}
+
 __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -648,6 +817,7 @@ __init int amd_pmu_init(void)
 
 	setup_event_constraints();
 	setup_perfctr_core();
+	setup_perfctr_nb();
 
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
@@ -678,7 +848,7 @@ void amd_pmu_disable_virt(void)
 	 * SVM is disabled the Guest-only bits still gets set and the counter
 	 * will not count anything.
 	 */
-	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
 	x86_pmu_disable_all();
diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile
new file mode 100644
index 000000000000..0d33169cc1a2
--- /dev/null
+++ b/arch/x86/kernel/kprobes/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for kernel probes
+#
+
+obj-$(CONFIG_KPROBES)		+= core.o
+obj-$(CONFIG_OPTPROBES)		+= opt.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes/common.h
index 3230b68ef29a..2e9d4b5af036 100644
--- a/arch/x86/kernel/kprobes-common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -99,4 +99,15 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 	return addr;
 }
 #endif
+
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			   struct kprobe_ctlblk *kcb);
+#else
+static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				  struct kprobe_ctlblk *kcb)
+{
+	return 0;
+}
+#endif
 #endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes/core.c
index 57916c0d3cf6..e124554598ee 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -58,7 +58,7 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
-#include "kprobes-common.h"
+#include "common.h"
 
 void jprobe_return_end(void);
 
@@ -78,7 +78,7 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 	 * Groups, and some special opcodes can not boost.
 	 * This is non-const and volatile to keep gcc from statically
 	 * optimizing it out, as variable_test_bit makes gcc think only
-	 * *(unsigned long*) is used. 
+	 * *(unsigned long*) is used.
 	 */
 static volatile u32 twobyte_is_boostable[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
@@ -117,7 +117,7 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 	struct __arch_relative_insn {
 		u8 op;
 		s32 raddr;
-	} __attribute__((packed)) *insn;
+	} __packed *insn;
 
 	insn = (struct __arch_relative_insn *)from;
 	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
@@ -541,23 +541,6 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
 	return 1;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				      struct kprobe_ctlblk *kcb)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-}
-#endif
-
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled throughout this function.
@@ -616,13 +599,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	} else if (kprobe_running()) {
 		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
-#ifdef KPROBES_CAN_USE_FTRACE
-			if (kprobe_ftrace(p)) {
-				skip_singlestep(p, regs, kcb);
-				return 1;
-			}
-#endif
-			setup_singlestep(p, regs, kcb, 0);
+			if (!skip_singlestep(p, regs, kcb))
+				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
 	} /* else: not a kprobe fault; let the kernel handle it */
@@ -1075,50 +1053,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-/* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
-{
-	struct kprobe *p;
-	struct kprobe_ctlblk *kcb;
-	unsigned long flags;
-
-	/* Disable irq for emulating a breakpoint and avoiding preempt */
-	local_irq_save(flags);
-
-	p = get_kprobe((kprobe_opcode_t *)ip);
-	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
-
-	kcb = get_kprobe_ctlblk();
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(p);
-	} else {
-		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
-		regs->ip = ip + sizeof(kprobe_opcode_t);
-
-		__this_cpu_write(current_kprobe, p);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			skip_singlestep(p, regs, kcb);
-		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe.
-		 */
-	}
-end:
-	local_irq_restore(flags);
-}
-
-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
-{
-	p->ainsn.insn = NULL;
-	p->ainsn.boostable = -1;
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
 	return arch_init_optprobes();
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
new file mode 100644
index 000000000000..23ef5c556f06
--- /dev/null
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -0,0 +1,93 @@
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+#include "common.h"
+
+static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
+{
+	/*
+	 * Emulate singlestep (and also recover regs->ip)
+	 * as if there is a 5byte nop
+	 */
+	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+	if (unlikely(p->post_handler)) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+	__this_cpu_write(current_kprobe, NULL);
+	return 1;
+}
+
+int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			      struct kprobe_ctlblk *kcb)
+{
+	if (kprobe_ftrace(p))
+		return __skip_singlestep(p, regs, kcb);
+	else
+		return 0;
+}
+
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+				     struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+	unsigned long flags;
+
+	/* Disable irq for emulating a breakpoint and avoiding preempt */
+	local_irq_save(flags);
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		goto end;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+		regs->ip = ip + sizeof(kprobe_opcode_t);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			__skip_singlestep(p, regs, kcb);
+		/*
+		 * If pre_handler returns !0, it sets regs->ip and
+		 * resets current kprobe.
+		 */
+	}
+end:
+	local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.insn = NULL;
+	p->ainsn.boostable = -1;
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes/opt.c
index c5e410eed403..76dc6f095724 100644
--- a/arch/x86/kernel/kprobes-opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -37,7 +37,7 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
-#include "kprobes-common.h"
+#include "common.h"
 
 unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index c71025b67462..0ba4cfb4f412 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -680,8 +680,10 @@ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		if (auprobe->insn[i] == 0x66)
 			continue;
 
-		if (auprobe->insn[i] == 0x90)
+		if (auprobe->insn[i] == 0x90) {
+			regs->ip += i + 1;
 			return true;
+		}
 
 		break;
 	}