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

Pull perf updates from Ingo Molnar:
 "With over 300 commits it's been a busy cycle - with most of the work
  concentrated on the tooling side (as it should).

  The main kernel side enhancements were:

   - Add per event callchain limit: Recently we introduced a sysctl to
     tune the max-stack for all events for which callchains were
     requested:

       $ sysctl kernel.perf_event_max_stack
       kernel.perf_event_max_stack = 127

     Now this patch introduces a way to configure this per event, i.e.
     this becomes possible:

       $ perf record -e sched:*/max-stack=2/ -e block:*/max-stack=10/ -a

     allowing finer tuning of how much buffer space callchains use.

     This uses an u16 from the reserved space at the end, leaving
     another u16 for future use.

     There has been interest in even finer tuning, namely to control the
     max stack for kernel and userspace callchains separately.  Further
     discussion is needed, we may for instance use the remaining u16 for
     that and when it is present, assume that the sample_max_stack
     introduced in this patch applies for the kernel, and the u16 left
     is used for limiting the userspace callchain (Arnaldo Carvalho de
     Melo)

   - Optimize AUX event (hardware assisted side-band event) delivery
     (Kan Liang)

   - Rework Intel family name macro usage (this is partially x86 arch
     work) (Dave Hansen)

   - Refine and fix Intel LBR support (David Carrillo-Cisneros)

   - Add support for Intel 'TopDown' events (Andi Kleen)

   - Intel uncore PMU driver fixes and enhancements (Kan Liang)

   - ... other misc changes.

  Here's an incomplete list of the tooling enhancements (but there's
  much more, see the shortlog and the git log for details):

   - Support cross unwinding, i.e.  collecting '--call-graph dwarf'
     perf.data files in one machine and then doing analysis in another
     machine of a different hardware architecture.  This enables, for
     instance, to do:

       $ perf record -a --call-graph dwarf

     on a x86-32 or aarch64 system and then do 'perf report' on it on a
     x86_64 workstation (He Kuang)

   - Allow reading from a backward ring buffer (one setup via
     sys_perf_event_open() with perf_event_attr.write_backward = 1)
     (Wang Nan)

   - Finish merging initial SDT (Statically Defined Traces) support, see
     cset comments for details about how it all works (Masami Hiramatsu)

   - Support attaching eBPF programs to tracepoints (Wang Nan)

   - Add demangling of symbols in programs written in the Rust language
     (David Tolnay)

   - Add support for tracepoints in the python binding, including an
     example, that sets up and parses sched:sched_switch events,
     tools/perf/python/tracepoint.py (Jiri Olsa)

   - Introduce --stdio-color to set up the color output mode selection
     in 'annotate' and 'report', allowing emit color escape sequences
     when redirecting the output of these tools (Arnaldo Carvalho de
     Melo)

   - Add 'callindent' option to 'perf script -F', to indent the Intel PT
     call stack, making this output more ftrace-like (Adrian Hunter,
     Andi Kleen)

   - Allow dumping the object files generated by llvm when processing
     eBPF scriptlet events (Wang Nan)

   - Add stackcollapse.py script to help generating flame graphs (Paolo
     Bonzini)

   - Add --ldlat option to 'perf mem' to specify load latency for loads
     event (e.g. cpu/mem-loads/ ) (Jiri Olsa)

   - Tooling support for Intel TopDown counters, recently added to the
     kernel (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (303 commits)
  perf tests: Add is_printable_array test
  perf tools: Make is_printable_array global
  perf script python: Fix string vs byte array resolving
  perf probe: Warn unmatched function filter correctly
  perf cpu_map: Add more helpers
  perf stat: Balance opening and reading events
  tools: Copy linux/{hash,poison}.h and check for drift
  perf tools: Remove include/linux/list.h from perf's MANIFEST
  tools: Copy the bitops files accessed from the kernel and check for drift
  Remove: kernel unistd*h files from perf's MANIFEST, not used
  perf tools: Remove tools/perf/util/include/linux/const.h
  perf tools: Remove tools/perf/util/include/asm/byteorder.h
  perf tools: Add missing linux/compiler.h include to perf-sys.h
  perf jit: Remove some no-op error handling
  perf jit: Add missing curly braces
  objtool: Initialize variable to silence old compiler
  objtool: Add -I$(srctree)/tools/arch/$(ARCH)/include/uapi
  perf record: Add --tail-synthesize option
  perf session: Don't warn about out of order event if write_backward is used
  perf tools: Enable overwrite settings
  ...

324 files changed, 13994 insertions, 2546 deletions

diff --git a/Makefile b/Makefile
index 66da9a3..e1a5605 100644
--- a/Makefile
+++ b/Makefile
@@ -1040,7 +1040,7 @@ ifdef CONFIG_STACK_VALIDATION
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else
-    $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev or elfutils-libelf-devel")
+    $(warning "Cannot use CONFIG_STACK_VALIDATION, please install libelf-dev, libelf-devel or elfutils-libelf-devel")
     SKIP_STACK_VALIDATION := 1
     export SKIP_STACK_VALIDATION
   endif
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index df3f60c..a2b3eb3 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -139,8 +139,8 @@ struct kvm_arch_memory_slot {
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14) 
-#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14) 
+#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
 
 /* Normal registers are mapped as coprocessor 16. */
 #define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 91eac39..dfebbde2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1622,6 +1622,29 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, cha
 }
 EXPORT_SYMBOL_GPL(events_sysfs_show);
 
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct perf_pmu_events_ht_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_ht_attr, attr);
+
+	/*
+	 * Report conditional events depending on Hyper-Threading.
+	 *
+	 * This is overly conservative as usually the HT special
+	 * handling is not needed if the other CPU thread is idle.
+	 *
+	 * Note this does not (and cannot) handle the case when thread
+	 * siblings are invisible, for example with virtualization
+	 * if they are owned by some other guest.  The user tool
+	 * has to re-read when a thread sibling gets onlined later.
+	 */
+	return sprintf(page, "%s",
+			topology_max_smt_threads() > 1 ?
+			pmu_attr->event_str_ht :
+			pmu_attr->event_str_noht);
+}
+
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9b4f9d3..0974ba1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -16,6 +16,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
+#include <asm/intel-family.h>
 #include <asm/apic.h>
 
 #include "../perf_event.h"
@@ -185,7 +186,7 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_skl_event_constraints[] = {
+static struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
@@ -204,10 +205,8 @@ struct event_constraint intel_skl_event_constraints[] = {
 };
 
 static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
-	INTEL_UEVENT_EXTRA_REG(0x01b7,
-			       MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7,
-			       MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x799ffbb6e7ull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x399ffbffe7ull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -243,14 +242,51 @@ EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
 
-struct attribute *nhm_events_attrs[] = {
+static struct attribute *nhm_events_attrs[] = {
 	EVENT_PTR(mem_ld_nhm),
 	NULL,
 };
 
-struct attribute *snb_events_attrs[] = {
+/*
+ * topdown events for Intel Core CPUs.
+ *
+ * The events are all in slots, which is a free slot in a 4 wide
+ * pipeline. Some events are already reported in slots, for cycle
+ * events we multiply by the pipeline width (4).
+ *
+ * With Hyper Threading on, topdown metrics are either summed or averaged
+ * between the threads of a core: (count_t0 + count_t1).
+ *
+ * For the average case the metric is always scaled to pipeline width,
+ * so we use factor 2 ((count_t0 + count_t1) / 2 * 4)
+ */
+
+EVENT_ATTR_STR_HT(topdown-total-slots, td_total_slots,
+	"event=0x3c,umask=0x0",			/* cpu_clk_unhalted.thread */
+	"event=0x3c,umask=0x0,any=1");		/* cpu_clk_unhalted.thread_any */
+EVENT_ATTR_STR_HT(topdown-total-slots.scale, td_total_slots_scale, "4", "2");
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued,
+	"event=0xe,umask=0x1");			/* uops_issued.any */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired,
+	"event=0xc2,umask=0x2");		/* uops_retired.retire_slots */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles,
+	"event=0x9c,umask=0x1");		/* idq_uops_not_delivered_core */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
+	"event=0xd,umask=0x3,cmask=1",		/* int_misc.recovery_cycles */
+	"event=0xd,umask=0x3,cmask=1,any=1");	/* int_misc.recovery_cycles_any */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
+	"4", "2");
+
+static struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(mem_ld_snb),
 	EVENT_PTR(mem_st_snb),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL,
 };
 
@@ -280,7 +316,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_bdw_event_constraints[] = {
+static struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
@@ -1361,6 +1397,29 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+EVENT_ATTR_STR(topdown-total-slots, td_total_slots_slm, "event=0x3c");
+EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_slm, "2");
+/* no_alloc_cycles.not_delivered */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_slm,
+	       "event=0xca,umask=0x50");
+EVENT_ATTR_STR(topdown-fetch-bubbles.scale, td_fetch_bubbles_scale_slm, "2");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_slm,
+	       "event=0xc2,umask=0x10");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_slm,
+	       "event=0xc2,umask=0x10");
+
+static struct attribute *slm_events_attrs[] = {
+	EVENT_PTR(td_total_slots_slm),
+	EVENT_PTR(td_total_slots_scale_slm),
+	EVENT_PTR(td_fetch_bubbles_slm),
+	EVENT_PTR(td_fetch_bubbles_scale_slm),
+	EVENT_PTR(td_slots_issued_slm),
+	EVENT_PTR(td_slots_retired_slm),
+	NULL
+};
+
 static struct extra_reg intel_slm_extra_regs[] __read_mostly =
 {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
@@ -3290,11 +3349,11 @@ static int intel_snb_pebs_broken(int cpu)
 	u32 rev = UINT_MAX; /* default to broken for unknown models */
 
 	switch (cpu_data(cpu).x86_model) {
-	case 42: /* SNB */
+	case INTEL_FAM6_SANDYBRIDGE:
 		rev = 0x28;
 		break;
 
-	case 45: /* SNB-EP */
+	case INTEL_FAM6_SANDYBRIDGE_X:
 		switch (cpu_data(cpu).x86_mask) {
 		case 6: rev = 0x618; break;
 		case 7: rev = 0x70c; break;
@@ -3331,6 +3390,13 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+static bool is_lbr_from(unsigned long msr)
+{
+	unsigned long lbr_from_nr = x86_pmu.lbr_from + x86_pmu.lbr_nr;
+
+	return x86_pmu.lbr_from <= msr && msr < lbr_from_nr;
+}
+
 /*
  * Under certain circumstances, access certain MSR may cause #GP.
  * The function tests if the input MSR can be safely accessed.
@@ -3351,13 +3417,24 @@ static bool check_msr(unsigned long msr, u64 mask)
 	 * Only change the bits which can be updated by wrmsrl.
 	 */
 	val_tmp = val_old ^ mask;
+
+	if (is_lbr_from(msr))
+		val_tmp = lbr_from_signext_quirk_wr(val_tmp);
+
 	if (wrmsrl_safe(msr, val_tmp) ||
 	    rdmsrl_safe(msr, &val_new))
 		return false;
 
+	/*
+	 * Quirk only affects validation in wrmsr(), so wrmsrl()'s value
+	 * should equal rdmsrl()'s even with the quirk.
+	 */
 	if (val_new != val_tmp)
 		return false;
 
+	if (is_lbr_from(msr))
+		val_old = lbr_from_signext_quirk_wr(val_old);
+
 	/* Here it's sure that the MSR can be safely accessed.
 	 * Restore the old value and return.
 	 */
@@ -3466,6 +3543,13 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL
 };
 
@@ -3537,15 +3621,15 @@ __init int intel_pmu_init(void)
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_model) {
-	case 14: /* 65nm Core "Yonah" */
+	case INTEL_FAM6_CORE_YONAH:
 		pr_cont("Core events, ");
 		break;
 
-	case 15: /* 65nm Core2 "Merom"          */
+	case INTEL_FAM6_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
-	case 22: /* 65nm Core2 "Merom-L"        */
-	case 23: /* 45nm Core2 "Penryn"         */
-	case 29: /* 45nm Core2 "Dunnington (MP) */
+	case INTEL_FAM6_CORE2_MEROM_L:
+	case INTEL_FAM6_CORE2_PENRYN:
+	case INTEL_FAM6_CORE2_DUNNINGTON:
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -3556,9 +3640,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Core2 events, ");
 		break;
 
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -3586,11 +3670,11 @@ __init int intel_pmu_init(void)
 		pr_cont("Nehalem events, ");
 		break;
 
-	case 28: /* 45nm Atom "Pineview"   */
-	case 38: /* 45nm Atom "Lincroft"   */
-	case 39: /* 32nm Atom "Penwell"    */
-	case 53: /* 32nm Atom "Cloverview" */
-	case 54: /* 32nm Atom "Cedarview"  */
+	case INTEL_FAM6_ATOM_PINEVIEW:
+	case INTEL_FAM6_ATOM_LINCROFT:
+	case INTEL_FAM6_ATOM_PENWELL:
+	case INTEL_FAM6_ATOM_CLOVERVIEW:
+	case INTEL_FAM6_ATOM_CEDARVIEW:
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -3602,9 +3686,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Atom events, ");
 		break;
 
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 76: /* 14nm Atom "Airmont"                   */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_AIRMONT:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -3616,11 +3700,12 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_slm_extra_regs;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.cpu_events = slm_events_attrs;
 		pr_cont("Silvermont events, ");
 		break;
 
-	case 92: /* 14nm Atom "Goldmont" */
-	case 95: /* 14nm Atom "Goldmont Denverton" */
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -3643,9 +3728,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Goldmont events, ");
 		break;
 
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_WESTMERE_EX:
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -3672,8 +3757,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Westmere events, ");
 		break;
 
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
 		x86_add_quirk(intel_sandybridge_quirk);
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
@@ -3686,7 +3771,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		if (boot_cpu_data.x86_model == 45)
+		if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -3708,8 +3793,8 @@ __init int intel_pmu_init(void)
 		pr_cont("SandyBridge events, ");
 		break;
 
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE_X:
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -3725,7 +3810,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
 		x86_pmu.pebs_prec_dist = true;
-		if (boot_cpu_data.x86_model == 62)
+		if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -3743,10 +3828,10 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 69: /* 22nm Haswell ULT */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_X:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
 		x86_add_quirk(intel_ht_bug);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -3770,10 +3855,10 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_X:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3806,7 +3891,7 @@ __init int intel_pmu_init(void)
 		pr_cont("Broadwell events, ");
 		break;
 
-	case 87: /* Knights Landing Xeon Phi */
+	case INTEL_FAM6_XEON_PHI_KNL:
 		memcpy(hw_cache_event_ids,
 		       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs,
@@ -3824,16 +3909,22 @@ __init int intel_pmu_init(void)
 		pr_cont("Knights Landing events, ");
 		break;
 
-	case 142: /* 14nm Kabylake Mobile */
-	case 158: /* 14nm Kabylake Desktop */
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
-	case 85: /* 14nm Skylake Server */
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 		intel_pmu_lbr_init_skl();
 
+		/* INT_MISC.RECOVERY_CYCLES has umask 1 in Skylake */
+		event_attr_td_recovery_bubbles.event_str_noht =
+			"event=0xd,umask=0x1,cmask=1";
+		event_attr_td_recovery_bubbles.event_str_ht =
+			"event=0xd,umask=0x1,cmask=1,any=1";
+
 		x86_pmu.event_constraints = intel_skl_event_constraints;
 		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_skl_extra_regs;
@@ -3914,6 +4005,8 @@ __init int intel_pmu_init(void)
 			x86_pmu.lbr_nr = 0;
 	}
 
+	if (x86_pmu.lbr_nr)
+		pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
 	/*
 	 * Access extra MSR may cause #GP under certain circumstances.
 	 * E.g. KVM doesn't support offcore event
@@ -3946,16 +4039,14 @@ __init int intel_pmu_init(void)
  */
 static __init int fixup_ht_bug(void)
 {
-	int cpu = smp_processor_id();
-	int w, c;
+	int c;
 	/*
 	 * problem not present on this CPU model, nothing to do
 	 */
 	if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
 		return 0;
 
-	w = cpumask_weight(topology_sibling_cpumask(cpu));
-	if (w > 1) {
+	if (topology_max_smt_threads() > 1) {
 		pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
 		return 0;
 	}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9ba4e41..4c7638b 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -89,6 +89,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "../perf_event.h"
 
 MODULE_LICENSE("GPL");
@@ -511,37 +512,37 @@ static const struct cstate_model slm_cstates __initconst = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
 
 static const struct x86_cpu_id intel_cstates_match[] __initconst = {
-	X86_CSTATES_MODEL(30, nhm_cstates),    /* 45nm Nehalem              */
-	X86_CSTATES_MODEL(26, nhm_cstates),    /* 45nm Nehalem-EP           */
-	X86_CSTATES_MODEL(46, nhm_cstates),    /* 45nm Nehalem-EX           */
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM,    nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EP, nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EX, nhm_cstates),
 
-	X86_CSTATES_MODEL(37, nhm_cstates),    /* 32nm Westmere             */
-	X86_CSTATES_MODEL(44, nhm_cstates),    /* 32nm Westmere-EP          */
-	X86_CSTATES_MODEL(47, nhm_cstates),    /* 32nm Westmere-EX          */
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE,    nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EP, nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EX, nhm_cstates),
 
-	X86_CSTATES_MODEL(42, snb_cstates),    /* 32nm SandyBridge          */
-	X86_CSTATES_MODEL(45, snb_cstates),    /* 32nm SandyBridge-E/EN/EP  */
+	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(58, snb_cstates),    /* 22nm IvyBridge            */
-	X86_CSTATES_MODEL(62, snb_cstates),    /* 22nm IvyBridge-EP/EX      */
+	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(60, snb_cstates),    /* 22nm Haswell Core         */
-	X86_CSTATES_MODEL(63, snb_cstates),    /* 22nm Haswell Server       */
-	X86_CSTATES_MODEL(70, snb_cstates),    /* 22nm Haswell + GT3e       */
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_CORE, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X,	   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_GT3E, snb_cstates),
 
-	X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT          */
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
 
-	X86_CSTATES_MODEL(55, slm_cstates),    /* 22nm Atom Silvermont      */
-	X86_CSTATES_MODEL(77, slm_cstates),    /* 22nm Atom Avoton/Rangely  */
-	X86_CSTATES_MODEL(76, slm_cstates),    /* 22nm Atom Airmont         */
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT,     slm_cstates),
 
-	X86_CSTATES_MODEL(61, snb_cstates),    /* 14nm Broadwell Core-M     */
-	X86_CSTATES_MODEL(86, snb_cstates),    /* 14nm Broadwell Xeon D     */
-	X86_CSTATES_MODEL(71, snb_cstates),    /* 14nm Broadwell + GT3e     */
-	X86_CSTATES_MODEL(79, snb_cstates),    /* 14nm Broadwell Server     */
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_XEON_D, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_GT3E,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X,      snb_cstates),
 
-	X86_CSTATES_MODEL(78, snb_cstates),    /* 14nm Skylake Mobile       */
-	X86_CSTATES_MODEL(94, snb_cstates),    /* 14nm Skylake Desktop      */
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 9e2b40c..707d358 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -77,9 +77,11 @@ static enum {
 	 LBR_IND_JMP	|\
 	 LBR_FAR)
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-#define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
-#define LBR_FROM_FLAG_ABORT    (1ULL << 61)
+#define LBR_FROM_FLAG_MISPRED	BIT_ULL(63)
+#define LBR_FROM_FLAG_IN_TX	BIT_ULL(62)
+#define LBR_FROM_FLAG_ABORT	BIT_ULL(61)
+
+#define LBR_FROM_SIGNEXT_2MSB	(BIT_ULL(60) | BIT_ULL(59))
 
 /*
  * x86control flow change classification
@@ -235,6 +237,97 @@ enum {
 	LBR_VALID,
 };
 
+/*
+ * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in
+ * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when
+ * TSX is not supported they have no consistent behavior:
+ *
+ *   - For wrmsr(), bits 61:62 are considered part of the sign extension.
+ *   - For HW updates (branch captures) bits 61:62 are always OFF and are not
+ *     part of the sign extension.
+ *
+ * Therefore, if:
+ *
+ *   1) LBR has TSX format
+ *   2) CPU has no TSX support enabled
+ *
+ * ... then any value passed to wrmsr() must be sign extended to 63 bits and any
+ * value from rdmsr() must be converted to have a 61 bits sign extension,
+ * ignoring the TSX flags.
+ */
+static inline bool lbr_from_signext_quirk_needed(void)
+{
+	int lbr_format = x86_pmu.intel_cap.lbr_format;
+	bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) ||
+			   boot_cpu_has(X86_FEATURE_RTM);
+
+	return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX);
+}
+
+DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
+
+/* If quirk is enabled, ensure sign extension is 63 bits: */
+inline u64 lbr_from_signext_quirk_wr(u64 val)
+{
+	if (static_branch_unlikely(&lbr_from_quirk_key)) {
+		/*
+		 * Sign extend into bits 61:62 while preserving bit 63.
+		 *
+		 * Quirk is enabled when TSX is disabled. Therefore TSX bits
+		 * in val are always OFF and must be changed to be sign
+		 * extension bits. Since bits 59:60 are guaranteed to be
+		 * part of the sign extension bits, we can just copy them
+		 * to 61:62.
+		 */
+		val |= (LBR_FROM_SIGNEXT_2MSB & val) << 2;
+	}
+	return val;
+}
+
+/*
+ * If quirk is needed, ensure sign extension is 61 bits:
+ */
+u64 lbr_from_signext_quirk_rd(u64 val)
+{
+	if (static_branch_unlikely(&lbr_from_quirk_key)) {
+		/*
+		 * Quirk is on when TSX is not enabled. Therefore TSX
+		 * flags must be read as OFF.
+		 */
+		val &= ~(LBR_FROM_FLAG_IN_TX | LBR_FROM_FLAG_ABORT);
+	}
+	return val;
+}
+
+static inline void wrlbr_from(unsigned int idx, u64 val)
+{
+	val = lbr_from_signext_quirk_wr(val);
+	wrmsrl(x86_pmu.lbr_from + idx, val);
+}
+
+static inline void wrlbr_to(unsigned int idx, u64 val)
+{
+	wrmsrl(x86_pmu.lbr_to + idx, val);
+}
+
+static inline u64 rdlbr_from(unsigned int idx)
+{
+	u64 val;
+
+	rdmsrl(x86_pmu.lbr_from + idx, val);
+
+	return lbr_from_signext_quirk_rd(val);
+}
+
+static inline u64 rdlbr_to(unsigned int idx)
+{
+	u64 val;
+
+	rdmsrl(x86_pmu.lbr_to + idx, val);
+
+	return val;
+}
+
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
 	int i;
@@ -251,8 +344,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
-		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
-		wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
+		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
+
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
@@ -262,9 +356,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
-	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
+	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
 		task_ctx->lbr_stack_state = LBR_NONE;
@@ -275,8 +369,8 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 	tos = intel_pmu_lbr_tos();
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
-		rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
-		rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
@@ -452,8 +546,8 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		u16 cycles = 0;
 		int lbr_flags = lbr_desc[lbr_format];
 
-		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
-		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
+		from = rdlbr_from(lbr_idx);
+		to   = rdlbr_to(lbr_idx);
 
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
@@ -956,7 +1050,6 @@ void __init intel_pmu_lbr_init_core(void)
 	 * SW branch filter usage:
 	 * - compensate for lack of HW filter
 	 */
-	pr_cont("4-deep LBR, ");
 }
 
 /* nehalem/westmere */
@@ -977,7 +1070,6 @@ void __init intel_pmu_lbr_init_nhm(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("16-deep LBR, ");
 }
 
 /* sandy bridge */
@@ -997,7 +1089,6 @@ void __init intel_pmu_lbr_init_snb(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("16-deep LBR, ");
 }
 
 /* haswell */
@@ -1011,7 +1102,8 @@ void intel_pmu_lbr_init_hsw(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
-	pr_cont("16-deep LBR, ");
+	if (lbr_from_signext_quirk_needed())
+		static_branch_enable(&lbr_from_quirk_key);
 }
 
 /* skylake */
@@ -1031,7 +1123,6 @@ __init void intel_pmu_lbr_init_skl(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("32-deep LBR, ");
 }
 
 /* atom */
@@ -1057,7 +1148,6 @@ void __init intel_pmu_lbr_init_atom(void)
 	 * SW branch filter usage:
 	 * - compensate for lack of HW filter
 	 */
-	pr_cont("8-deep LBR, ");
 }
 
 /* slm */
@@ -1088,6 +1178,4 @@ void intel_pmu_lbr_init_knl(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
-
-	pr_cont("8-deep LBR, ");
 }
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index e30eef4..d0c58b3 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -55,6 +55,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "../perf_event.h"
 
 MODULE_LICENSE("GPL");
@@ -786,26 +787,27 @@ static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
 };
 
 static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
-	X86_RAPL_MODEL_MATCH(42, snb_rapl_init),	/* Sandy Bridge */
-	X86_RAPL_MODEL_MATCH(45, snbep_rapl_init),	/* Sandy Bridge-EP */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,   snb_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(58, snb_rapl_init),	/* Ivy Bridge */
-	X86_RAPL_MODEL_MATCH(62, snbep_rapl_init),	/* IvyTown */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,   snb_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(60, hsw_rapl_init),	/* Haswell */
-	X86_RAPL_MODEL_MATCH(63, hsx_rapl_init),	/* Haswell-Server */
-	X86_RAPL_MODEL_MATCH(69, hsw_rapl_init),	/* Haswell-Celeron */
-	X86_RAPL_MODEL_MATCH(70, hsw_rapl_init),	/* Haswell GT3e */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X,    hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,  hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(61, hsw_rapl_init),	/* Broadwell */
-	X86_RAPL_MODEL_MATCH(71, hsw_rapl_init),	/* Broadwell-H */
-	X86_RAPL_MODEL_MATCH(79, hsx_rapl_init),	/* Broadwell-Server */
-	X86_RAPL_MODEL_MATCH(86, hsx_rapl_init),	/* Broadwell Xeon D */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE,   hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E,   hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(87, knl_rapl_init),	/* Knights Landing */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(78, skl_rapl_init),	/* Skylake */
-	X86_RAPL_MODEL_MATCH(94, skl_rapl_init),	/* Skylake H/S */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE,  skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,	 hsx_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index fce7406..59b4974 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,4 +1,5 @@
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
@@ -882,7 +883,7 @@ uncore_types_init(struct intel_uncore_type **types, bool setid)
 static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_uncore_type *type;
-	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_pmu *pmu = NULL;
 	struct intel_uncore_box *box;
 	int phys_id, pkg, ret;
 
@@ -903,20 +904,37 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+
 	/*
-	 * for performance monitoring unit with multiple boxes,
-	 * each box has a different function id.
-	 */
-	pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
-	/* Knights Landing uses a common PCI device ID for multiple instances of
-	 * an uncore PMU device type. There is only one entry per device type in
-	 * the knl_uncore_pci_ids table inspite of multiple devices present for
-	 * some device types. Hence PCI device idx would be 0 for all devices.
-	 * So increment pmu pointer to point to an unused array element.
+	 * Some platforms, e.g.  Knights Landing, use a common PCI device ID
+	 * for multiple instances of an uncore PMU device type. We should check
+	 * PCI slot and func to indicate the uncore box.
 	 */
-	if (boot_cpu_data.x86_model == 87) {
-		while (pmu->func_id >= 0)
-			pmu++;
+	if (id->driver_data & ~0xffff) {
+		struct pci_driver *pci_drv = pdev->driver;
+		const struct pci_device_id *ids = pci_drv->id_table;
+		unsigned int devfn;
+
+		while (ids && ids->vendor) {
+			if ((ids->vendor == pdev->vendor) &&
+			    (ids->device == pdev->device)) {
+				devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data),
+						  UNCORE_PCI_DEV_FUNC(ids->driver_data));
+				if (devfn == pdev->devfn) {
+					pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)];
+					break;
+				}
+			}
+			ids++;
+		}
+		if (pmu == NULL)
+			return -ENODEV;
+	} else {
+		/*
+		 * for performance monitoring unit with multiple boxes,
+		 * each box has a different function id.
+		 */
+		pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
 	}
 
 	if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
@@ -956,7 +974,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
-	struct intel_uncore_box *box = pci_get_drvdata(pdev);
+	struct intel_uncore_box *box;
 	struct intel_uncore_pmu *pmu;
 	int i, phys_id, pkg;
 
@@ -1361,30 +1379,32 @@ static const struct intel_uncore_init_fun knl_uncore_init __initconst = {
 };
 
 static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
+	.cpu_init = skl_uncore_cpu_init,
 	.pci_init = skl_uncore_pci_init,
 };
 
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
-	X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init),	/* Nehalem */
-	X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init),	/* Westmere */
-	X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(42, snb_uncore_init),	/* Sandy Bridge */
-	X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init),	/* Ivy Bridge */
-	X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init),	/* Haswell Celeron */
-	X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init),	/* Sandy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init),	/* Nehalem-EX */
-	X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init),	/* Westmere-EX aka. Xeon E7 */
-	X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init),	/* Ivy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init),	/* Haswell-EP */
-	X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init),	/* BDX-EP */
-	X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init),	/* BDX-DE */
-	X86_UNCORE_MODEL_MATCH(87, knl_uncore_init),	/* Knights Landing */
-	X86_UNCORE_MODEL_MATCH(94, skl_uncore_init),	/* SkyLake */
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,	  snb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,	  ivb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X,  snbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X,	  ivbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X,	  hswep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 79766b9..d6063e4 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -15,7 +15,11 @@
 #define UNCORE_PMC_IDX_FIXED		UNCORE_PMC_IDX_MAX_GENERIC
 #define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FIXED + 1)
 
+#define UNCORE_PCI_DEV_FULL_DATA(dev, func, type, idx)	\
+		((dev << 24) | (func << 16) | (type << 8) | idx)
 #define UNCORE_PCI_DEV_DATA(type, idx)	((type << 8) | idx)
+#define UNCORE_PCI_DEV_DEV(data)	((data >> 24) & 0xff)
+#define UNCORE_PCI_DEV_FUNC(data)	((data >> 16) & 0xff)
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
@@ -360,6 +364,7 @@ int bdw_uncore_pci_init(void);
 int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
+void skl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* perf_event_intel_uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 96531d2..97a69db 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -1,4 +1,4 @@
-/* Nehalem/SandBridge/Haswell uncore support */
+/* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */
 #include "uncore.h"
 
 /* Uncore IMC PCI IDs */
@@ -9,6 +9,7 @@
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
 #define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x190c
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -64,6 +65,10 @@
 #define NHM_UNC_PERFEVTSEL0                     0x3c0
 #define NHM_UNC_UNCORE_PMC0                     0x3b0
 
+/* SKL uncore global control */
+#define SKL_UNC_PERF_GLOBAL_CTL			0xe01
+#define SKL_UNC_GLOBAL_CTL_CORE_ALL		((1 << 5) - 1)
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -179,6 +184,60 @@ void snb_uncore_cpu_init(void)
 		snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 }
 
+static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0) {
+		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+	}
+}
+
+static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0)
+		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static struct intel_uncore_ops skl_uncore_msr_ops = {
+	.init_box	= skl_uncore_msr_init_box,
+	.exit_box	= skl_uncore_msr_exit_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type skl_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 4,
+	.num_boxes	= 5,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
+	.ops		= &skl_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
+};
+
+static struct intel_uncore_type *skl_msr_uncores[] = {
+	&skl_uncore_cbox,
+	&snb_uncore_arb,
+	NULL,
+};
+
+void skl_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = skl_msr_uncores;
+	if (skl_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		skl_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
 enum {
 	SNB_PCI_UNCORE_IMC,
 };
@@ -544,6 +603,11 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+
 	{ /* end: all zeroes */ },
 };
 
@@ -587,6 +651,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
+	IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core U */
 	{  /* end marker */ }
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 874e8bd..824e540 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2164,21 +2164,101 @@ static struct intel_uncore_type *knl_pci_uncores[] = {
 */
 
 static const struct pci_device_id knl_uncore_pci_ids[] = {
-	{ /* MC UClk */
+	{ /* MC0 UClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 0, KNL_PCI_UNCORE_MC_UCLK, 0),
 	},
-	{ /* MC DClk Channel */
+	{ /* MC1 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(11, 0, KNL_PCI_UNCORE_MC_UCLK, 1),
+	},
+	{ /* MC0 DClk CH 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 2, KNL_PCI_UNCORE_MC_DCLK, 0),
+	},
+	{ /* MC0 DClk CH 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 3, KNL_PCI_UNCORE_MC_DCLK, 1),
+	},
+	{ /* MC0 DClk CH 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 4, KNL_PCI_UNCORE_MC_DCLK, 2),
+	},
+	{ /* MC1 DClk CH 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 2, KNL_PCI_UNCORE_MC_DCLK, 3),
+	},
+	{ /* MC1 DClk CH 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 3, KNL_PCI_UNCORE_MC_DCLK, 4),
+	},
+	{ /* MC1 DClk CH 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 4, KNL_PCI_UNCORE_MC_DCLK, 5),
+	},
+	{ /* EDC0 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, KNL_PCI_UNCORE_EDC_UCLK, 0),
+	},
+	{ /* EDC1 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(16, 0, KNL_PCI_UNCORE_EDC_UCLK, 1),
+	},
+	{ /* EDC2 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(17, 0, KNL_PCI_UNCORE_EDC_UCLK, 2),
+	},
+	{ /* EDC3 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, KNL_PCI_UNCORE_EDC_UCLK, 3),
 	},
-	{ /* EDC UClk */
+	{ /* EDC4 UClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(19, 0, KNL_PCI_UNCORE_EDC_UCLK, 4),
+	},
+	{ /* EDC5 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(20, 0, KNL_PCI_UNCORE_EDC_UCLK, 5),
+	},
+	{ /* EDC6 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 0, KNL_PCI_UNCORE_EDC_UCLK, 6),
+	},
+	{ /* EDC7 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(22, 0, KNL_PCI_UNCORE_EDC_UCLK, 7),
+	},
+	{ /* EDC0 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(24, 2, KNL_PCI_UNCORE_EDC_ECLK, 0),
+	},
+	{ /* EDC1 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(25, 2, KNL_PCI_UNCORE_EDC_ECLK, 1),
+	},
+	{ /* EDC2 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(26, 2, KNL_PCI_UNCORE_EDC_ECLK, 2),
+	},
+	{ /* EDC3 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(27, 2, KNL_PCI_UNCORE_EDC_ECLK, 3),
+	},
+	{ /* EDC4 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(28, 2, KNL_PCI_UNCORE_EDC_ECLK, 4),
+	},
+	{ /* EDC5 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(29, 2, KNL_PCI_UNCORE_EDC_ECLK, 5),
+	},
+	{ /* EDC6 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(30, 2, KNL_PCI_UNCORE_EDC_ECLK, 6),
 	},
-	{ /* EDC EClk */
+	{ /* EDC7 EClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(31, 2, KNL_PCI_UNCORE_EDC_ECLK, 7),
 	},
 	{ /* M2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817),
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 85ef3c2..50b3a05 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,4 +1,5 @@
 #include <linux/perf_event.h>
+#include <asm/intel-family.h>
 
 enum perf_msr_id {
 	PERF_MSR_TSC			= 0,
@@ -34,39 +35,43 @@ static bool test_intel(int idx)
 		return false;
 
 	switch (boot_cpu_data.x86_model) {
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
-
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
-
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
-
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
-
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 69: /* 22nm Haswell ULT */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
-
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
-
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
-	case 76: /* 14nm Atom "Airmont"                   */
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
+
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE2:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_WESTMERE_EX:
+
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE_X:
+
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_X:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
+
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_X:
+
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_AIRMONT:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;
 
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8bd764d..8c4a477 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -668,6 +668,14 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 	.event_str	= str,						\
 };
 
+#define EVENT_ATTR_STR_HT(_name, v, noht, ht)				\
+static struct perf_pmu_events_ht_attr event_attr_##v = {		\
+	.attr		= __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
+	.id		= 0,						\
+	.event_str_noht	= noht,						\
+	.event_str_ht	= ht,						\
+}
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 static inline bool x86_pmu_has_lbr_callstack(void)
@@ -803,6 +811,8 @@ struct attribute **merge_attr(struct attribute **a, struct attribute **b);
 
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
 
 #ifdef CONFIG_CPU_SUP_AMD
 
@@ -892,6 +902,8 @@ void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
 
+u64 lbr_from_signext_quirk_wr(u64 val);
+
 void intel_pmu_lbr_reset(void);
 
 void intel_pmu_lbr_enable(struct perf_event *event);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 7f991bd5..e346572 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -129,6 +129,14 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
+
+extern int __max_smt_threads;
+
+static inline int topology_max_smt_threads(void)
+{
+	return __max_smt_threads;
+}
+
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
 extern int topology_phys_to_logical_pkg(unsigned int pkg);
 #else
@@ -136,6 +144,7 @@ extern int topology_phys_to_logical_pkg(unsigned int pkg);
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
+static inline int topology_max_smt_threads(void) { return 1; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fafe8b9..2ed0ec1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -105,6 +105,9 @@ static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 
+/* Maximum number of SMT threads on any online core */
+int __max_smt_threads __read_mostly;
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -493,7 +496,7 @@ void set_cpu_sibling_map(int cpu)
 	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
-	int i;
+	int i, threads;
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
@@ -550,6 +553,10 @@ void set_cpu_sibling_map(int cpu)
 		if (match_die(c, o) && !topology_same_node(c, o))
 			primarily_use_numa_for_topology();
 	}
+
+	threads = cpumask_weight(topology_sibling_cpumask(cpu));
+	if (threads > __max_smt_threads)
+		__max_smt_threads = threads;
 }
 
 /* maps the cpu to the sched domain representing multi-core */
@@ -1441,6 +1448,21 @@ __init void prefill_possible_map(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+/* Recompute SMT state for all CPUs on offline */
+static void recompute_smt_state(void)
+{
+	int max_threads, cpu;
+
+	max_threads = 0;
+	for_each_online_cpu (cpu) {
+		int threads = cpumask_weight(topology_sibling_cpumask(cpu));
+
+		if (threads > max_threads)
+			max_threads = threads;
+	}
+	__max_smt_threads = max_threads;
+}
+
 static void remove_siblinginfo(int cpu)
 {
 	int sibling;
@@ -1465,6 +1487,7 @@ static void remove_siblinginfo(int cpu)
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
+	recompute_smt_state();
 }
 
 static void remove_cpu_from_maps(int cpu)
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index 2776bec..e57f923 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -26,6 +26,7 @@
 #include <linux/seq_file.h>
 
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include <asm/pmc_core.h>
 
 #include "intel_pmc_core.h"
@@ -138,10 +139,10 @@ static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
 #endif /* CONFIG_DEBUG_FS */
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
-	{ X86_VENDOR_INTEL, 6, 0x4e, X86_FEATURE_MWAIT,
-		(kernel_ulong_t)NULL}, /* Skylake CPUID Signature */
-	{ X86_VENDOR_INTEL, 6, 0x5e, X86_FEATURE_MWAIT,
-		(kernel_ulong_t)NULL}, /* Skylake CPUID Signature */
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_MOBILE, X86_FEATURE_MWAIT,
+		(kernel_ulong_t)NULL},
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_DESKTOP, X86_FEATURE_MWAIT,
+		(kernel_ulong_t)NULL},
 	{}
 };
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1a827ce..7921f4f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -517,6 +517,11 @@ struct swevent_hlist {
 struct perf_cgroup;
 struct ring_buffer;
 
+struct pmu_event_list {
+	raw_spinlock_t		lock;
+	struct list_head	list;
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -675,6 +680,7 @@ struct perf_event {
 	int				cgrp_defer_enabled;
 #endif
 
+	struct list_head		sb_list;
 #endif /* CONFIG_PERF_EVENTS */
 };
 
@@ -1074,7 +1080,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
-extern int get_callchain_buffers(void);
+extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 
 extern int sysctl_perf_event_max_stack;
@@ -1326,6 +1332,13 @@ struct perf_pmu_events_attr {
 	const char *event_str;
 };
 
+struct perf_pmu_events_ht_attr {
+	struct device_attribute			attr;
+	u64					id;
+	const char				*event_str_ht;
+	const char				*event_str_noht;
+};
+
 ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
 			      char *page);
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 36ce552..c66a485 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -276,6 +276,9 @@ enum perf_event_read_format {
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
+ *
+ * @sample_max_stack: Max number of frame pointers in a callchain,
+ *		      should be < /proc/sys/kernel/perf_event_max_stack
  */
 struct perf_event_attr {
 
@@ -385,7 +388,8 @@ struct perf_event_attr {
 	 * Wakeup watermark for AUX area
 	 */
 	__u32	aux_watermark;
-	__u32	__reserved_2;	/* align to __u64 */
+	__u16	sample_max_stack;
+	__u16	__reserved_2;	/* align to __u64 */
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 080a2df..bf4495f 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -99,7 +99,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (err)
 		goto free_smap;
 
-	err = get_callchain_buffers();
+	err = get_callchain_buffers(sysctl_perf_event_max_stack);
 	if (err)
 		goto free_smap;
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 179ef46..e9fdb52 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -104,7 +104,7 @@ fail:
 	return -ENOMEM;
 }
 
-int get_callchain_buffers(void)
+int get_callchain_buffers(int event_max_stack)
 {
 	int err = 0;
 	int count;
@@ -121,6 +121,15 @@ int get_callchain_buffers(void)
 		/* If the allocation failed, give up */
 		if (!callchain_cpus_entries)
 			err = -ENOMEM;
+		/*
+		 * If requesting per event more than the global cap,
+		 * return a different error to help userspace figure
+		 * this out.
+		 *
+		 * And also do it here so that we have &callchain_mutex held.
+		 */
+		if (event_max_stack > sysctl_perf_event_max_stack)
+			err = -EOVERFLOW;
 		goto exit;
 	}
 
@@ -174,11 +183,12 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	bool user   = !event->attr.exclude_callchain_user;
 	/* Disallow cross-task user callchains. */
 	bool crosstask = event->ctx->task && event->ctx->task != current;
+	const u32 max_stack = event->attr.sample_max_stack;
 
 	if (!kernel && !user)
 		return NULL;
 
-	return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
+	return get_perf_callchain(regs, 0, kernel, user, max_stack, crosstask, true);
 }
 
 struct perf_callchain_entry *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 43d43a2d..79dae18 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -335,6 +335,7 @@ static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(int, perf_sched_cb_usages);
+static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -396,6 +397,13 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
 	if (ret || !write)
 		return ret;
 
+	/*
+	 * If throttling is disabled don't allow the write:
+	 */
+	if (sysctl_perf_cpu_time_max_percent == 100 ||
+	    sysctl_perf_cpu_time_max_percent == 0)
+		return -EINVAL;
+
 	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
 	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 	update_perf_cpu_limits();
@@ -3686,6 +3694,39 @@ static void free_event_rcu(struct rcu_head *head)
 static void ring_buffer_attach(struct perf_event *event,
 			       struct ring_buffer *rb);
 
+static void detach_sb_event(struct perf_event *event)
+{
+	struct pmu_event_list *pel = per_cpu_ptr(&pmu_sb_events, event->cpu);
+
+	raw_spin_lock(&pel->lock);
+	list_del_rcu(&event->sb_list);
+	raw_spin_unlock(&pel->lock);
+}
+
+static bool is_sb_event(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	if (event->parent)
+		return false;
+
+	if (event->attach_state & PERF_ATTACH_TASK)
+		return false;
+
+	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
+	    attr->comm || attr->comm_exec ||
+	    attr->task ||
+	    attr->context_switch)
+		return true;
+	return false;
+}
+
+static void unaccount_pmu_sb_event(struct perf_event *event)
+{
+	if (is_sb_event(event))
+		detach_sb_event(event);
+}
+
 static void unaccount_event_cpu(struct perf_event *event, int cpu)
 {
 	if (event->parent)
@@ -3749,6 +3790,8 @@ static void unaccount_event(struct perf_event *event)
 	}
 
 	unaccount_event_cpu(event, event->cpu);
+
+	unaccount_pmu_sb_event(event);
 }
 
 static void perf_sched_delayed(struct work_struct *work)
@@ -5875,11 +5918,11 @@ perf_event_read_event(struct perf_event *event,
 	perf_output_end(&handle);
 }
 
-typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);
+typedef void (perf_iterate_f)(struct perf_event *event, void *data);
 
 static void
-perf_event_aux_ctx(struct perf_event_context *ctx,
-		   perf_event_aux_output_cb output,
+perf_iterate_ctx(struct perf_event_context *ctx,
+		   perf_iterate_f output,
 		   void *data, bool all)
 {
 	struct perf_event *event;
@@ -5896,52 +5939,55 @@ perf_event_aux_ctx(struct perf_event_context *ctx,
 	}
 }
 
-static void
-perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
-			struct perf_event_context *task_ctx)
+static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
 {
-	rcu_read_lock();
-	preempt_disable();
-	perf_event_aux_ctx(task_ctx, output, data, false);
-	preempt_enable();
-	rcu_read_unlock();
+	struct pmu_event_list *pel = this_cpu_ptr(&pmu_sb_events);
+	struct perf_event *event;
+
+	list_for_each_entry_rcu(event, &pel->list, sb_list) {
+		if (event->state < PERF_EVENT_STATE_INACTIVE)
+			continue;
+		if (!event_filter_match(event))
+			continue;
+		output(event, data);
+	}
 }
 
+/*
+ * Iterate all events that need to receive side-band events.
+ *
+ * For new callers; ensure that account_pmu_sb_event() includes
+ * your event, otherwise it might not get delivered.
+ */
 static void
-perf_event_aux(perf_event_aux_output_cb output, void *data,
+perf_iterate_sb(perf_iterate_f output, void *data,
 	       struct perf_event_context *task_ctx)
 {
-	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
-	struct pmu *pmu;
 	int ctxn;
 
+	rcu_read_lock();
+	preempt_disable();
+
 	/*
-	 * If we have task_ctx != NULL we only notify
-	 * the task context itself. The task_ctx is set
-	 * only for EXIT events before releasing task
+	 * If we have task_ctx != NULL we only notify the task context itself.
+	 * The task_ctx is set only for EXIT events before releasing task
 	 * context.
 	 */
 	if (task_ctx) {
-		perf_event_aux_task_ctx(output, data, task_ctx);
-		return;
+		perf_iterate_ctx(task_ctx, output, data, false);
+		goto done;
 	}
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_aux_ctx(&cpuctx->ctx, output, data, false);
-		ctxn = pmu->task_ctx_nr;
-		if (ctxn < 0)
-			goto next;
+	perf_iterate_sb_cpu(output, data);
+
+	for_each_task_context_nr(ctxn) {
 		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
 		if (ctx)
-			perf_event_aux_ctx(ctx, output, data, false);
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
+			perf_iterate_ctx(ctx, output, data, false);
 	}
+done:
+	preempt_enable();
 	rcu_read_unlock();
 }
 
@@ -5990,7 +6036,7 @@ void perf_event_exec(void)
 
 		perf_event_enable_on_exec(ctxn);
 
-		perf_event_aux_ctx(ctx, perf_event_addr_filters_exec, NULL,
+		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL,
 				   true);
 	}
 	rcu_read_unlock();
@@ -6034,9 +6080,9 @@ static int __perf_pmu_output_stop(void *info)
 	};
 
 	rcu_read_lock();
-	perf_event_aux_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro, false);
+	perf_iterate_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro, false);
 	if (cpuctx->task_ctx)
-		perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop,
+		perf_iterate_ctx(cpuctx->task_ctx, __perf_event_output_stop,
 				   &ro, false);
 	rcu_read_unlock();
 
@@ -6165,7 +6211,7 @@ static void perf_event_task(struct task_struct *task,
 		},
 	};
 
-	perf_event_aux(perf_event_task_output,
+	perf_iterate_sb(perf_event_task_output,
 		       &task_event,
 		       task_ctx);
 }
@@ -6244,7 +6290,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
 
-	perf_event_aux(perf_event_comm_output,
+	perf_iterate_sb(perf_event_comm_output,
 		       comm_event,
 		       NULL);
 }
@@ -6475,7 +6521,7 @@ got_name:
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
-	perf_event_aux(perf_event_mmap_output,
+	perf_iterate_sb(perf_event_mmap_output,
 		       mmap_event,
 		       NULL);
 
@@ -6558,7 +6604,7 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma)
 		if (!ctx)
 			continue;
 
-		perf_event_aux_ctx(ctx, __perf_addr_filters_adjust, vma, true);
+		perf_iterate_ctx(ctx, __perf_addr_filters_adjust, vma, true);
 	}
 	rcu_read_unlock();
 }
@@ -6745,7 +6791,7 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
-	perf_event_aux(perf_event_switch_output,
+	perf_iterate_sb(perf_event_switch_output,
 		       &switch_event,
 		       NULL);
 }
@@ -8667,6 +8713,28 @@ unlock:
 	return pmu;
 }
 
+static void attach_sb_event(struct perf_event *event)
+{
+	struct pmu_event_list *pel = per_cpu_ptr(&pmu_sb_events, event->cpu);
+
+	raw_spin_lock(&pel->lock);
+	list_add_rcu(&event->sb_list, &pel->list);
+	raw_spin_unlock(&pel->lock);
+}
+
+/*
+ * We keep a list of all !task (and therefore per-cpu) events
+ * that need to receive side-band records.
+ *
+ * This avoids having to scan all the various PMU per-cpu contexts
+ * looking for them.
+ */
+static void account_pmu_sb_event(struct perf_event *event)
+{
+	if (is_sb_event(event))
+		attach_sb_event(event);
+}
+
 static void account_event_cpu(struct perf_event *event, int cpu)
 {
 	if (event->parent)
@@ -8747,6 +8815,8 @@ static void account_event(struct perf_event *event)
 enabled:
 
 	account_event_cpu(event, event->cpu);
+
+	account_pmu_sb_event(event);
 }
 
 /*
@@ -8895,7 +8965,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	if (!event->parent) {
 		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
-			err = get_callchain_buffers();
+			err = get_callchain_buffers(attr->sample_max_stack);
 			if (err)
 				goto err_addr_filters;
 		}
@@ -9217,6 +9287,9 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	if (!attr.sample_max_stack)
+		attr.sample_max_stack = sysctl_perf_event_max_stack;
+
 	/*
 	 * In cgroup mode, the pid argument is used to pass the fd
 	 * opened to the cgroup directory in cgroupfs. The cpu argument
@@ -9290,7 +9363,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (is_sampling_event(event)) {
 		if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
-			err = -ENOTSUPP;
+			err = -EOPNOTSUPP;
 			goto err_alloc;
 		}
 	}
@@ -10252,6 +10325,9 @@ static void __init perf_event_init_all_cpus(void)
 		swhash = &per_cpu(swevent_htable, cpu);
 		mutex_init(&swhash->hlist_mutex);
 		INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu));
+
+		INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
+		raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
 	}
 }
 
diff --git a/tools/arch/alpha/include/uapi/asm/bitsperlong.h b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..ad57f78
--- /dev/null
+++ b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_ALPHA_BITSPERLONG_H
+#define __ASM_ALPHA_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_ALPHA_BITSPERLONG_H */
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..a2b3eb3
--- /dev/null
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -0,0 +1,224 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#include <linux/types.h>
+#include <linux/psci.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_REG_SIZE(id)						\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+/* Valid for svc_regs, abt_regs, und_regs, irq_regs in struct kvm_regs */
+#define KVM_ARM_SVC_sp		svc_regs[0]
+#define KVM_ARM_SVC_lr		svc_regs[1]
+#define KVM_ARM_SVC_spsr	svc_regs[2]
+#define KVM_ARM_ABT_sp		abt_regs[0]
+#define KVM_ARM_ABT_lr		abt_regs[1]
+#define KVM_ARM_ABT_spsr	abt_regs[2]
+#define KVM_ARM_UND_sp		und_regs[0]
+#define KVM_ARM_UND_lr		und_regs[1]
+#define KVM_ARM_UND_spsr	und_regs[2]
+#define KVM_ARM_IRQ_sp		irq_regs[0]
+#define KVM_ARM_IRQ_lr		irq_regs[1]
+#define KVM_ARM_IRQ_spsr	irq_regs[2]
+
+/* Valid only for fiq_regs in struct kvm_regs */
+#define KVM_ARM_FIQ_r8		fiq_regs[0]
+#define KVM_ARM_FIQ_r9		fiq_regs[1]
+#define KVM_ARM_FIQ_r10		fiq_regs[2]
+#define KVM_ARM_FIQ_fp		fiq_regs[3]
+#define KVM_ARM_FIQ_ip		fiq_regs[4]
+#define KVM_ARM_FIQ_sp		fiq_regs[5]
+#define KVM_ARM_FIQ_lr		fiq_regs[6]
+#define KVM_ARM_FIQ_spsr	fiq_regs[7]
+
+struct kvm_regs {
+	struct pt_regs usr_regs;	/* R0_usr - R14_usr, PC, CPSR */
+	unsigned long svc_regs[3];	/* SP_svc, LR_svc, SPSR_svc */
+	unsigned long abt_regs[3];	/* SP_abt, LR_abt, SPSR_abt */
+	unsigned long und_regs[3];	/* SP_und, LR_und, SPSR_und */
+	unsigned long irq_regs[3];	/* SP_irq, LR_irq, SPSR_irq */
+	unsigned long fiq_regs[8];	/* R8_fiq - R14_fiq, SPSR_fiq */
+};
+
+/* Supported Processor Types */
+#define KVM_ARM_TARGET_CORTEX_A15	0
+#define KVM_ARM_TARGET_CORTEX_A7	1
+#define KVM_ARM_NUM_TARGETS		2
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT	0
+#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT		16
+#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2		0
+
+/* Supported VGIC address types  */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST	0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU	1
+
+#define KVM_VGIC_V2_DIST_SIZE		0x1000
+#define KVM_VGIC_V2_CPU_SIZE		0x2000
+
+#define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */
+
+struct kvm_vcpu_init {
+	__u32 target;
+	__u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+struct kvm_guest_debug_arch {
+};
+
+struct kvm_debug_exit_arch {
+};
+
+struct kvm_sync_regs {
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT	16
+#define KVM_REG_ARM_32_OPC2_MASK	0x0000000000000007
+#define KVM_REG_ARM_32_OPC2_SHIFT	0
+#define KVM_REG_ARM_OPC1_MASK		0x0000000000000078
+#define KVM_REG_ARM_OPC1_SHIFT		3
+#define KVM_REG_ARM_CRM_MASK		0x0000000000000780
+#define KVM_REG_ARM_CRM_SHIFT		7
+#define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
+#define KVM_REG_ARM_32_CRN_SHIFT	11
+
+#define ARM_CP15_REG_SHIFT_MASK(x,n) \
+	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
+
+#define __ARM_CP15_REG(op1,crn,crm,op2) \
+	(KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \
+	ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \
+	ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \
+	ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \
+	ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2))
+
+#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32)
+
+#define __ARM_CP15_REG64(op1,crm) \
+	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
+#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
+
+#define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name)	(offsetof(struct kvm_regs, name) / 4)
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX		(0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK	0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT	8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR	(0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK	0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT	0
+
+/* VFP registers: we could overload CP10 like ARM does, but that's ugly. */
+#define KVM_REG_ARM_VFP			(0x0012 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_VFP_MASK		0x000000000000FFFF
+#define KVM_REG_ARM_VFP_BASE_REG	0x0
+#define KVM_REG_ARM_VFP_FPSID		0x1000
+#define KVM_REG_ARM_VFP_FPSCR		0x1001
+#define KVM_REG_ARM_VFP_MVFR1		0x1006
+#define KVM_REG_ARM_VFP_MVFR0		0x1007
+#define KVM_REG_ARM_VFP_FPEXC		0x1008
+#define KVM_REG_ARM_VFP_FPINST		0x1009
+#define KVM_REG_ARM_VFP_FPINST2		0x100A
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT		24
+#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT		16
+#define KVM_ARM_IRQ_VCPU_MASK		0xff
+#define KVM_ARM_IRQ_NUM_SHIFT		0
+#define KVM_ARM_IRQ_NUM_MASK		0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU		0
+#define KVM_ARM_IRQ_TYPE_SPI		1
+#define KVM_ARM_IRQ_TYPE_PPI		2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ		0
+#define KVM_ARM_IRQ_CPU_FIQ		1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX		127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE		0x95c1ba5e
+#define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND		KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF		KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
+
+#endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm/include/uapi/asm/perf_regs.h b/tools/arch/arm/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..ce59448
--- /dev/null
+++ b/tools/arch/arm/include/uapi/asm/perf_regs.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_ARM_PERF_REGS_H
+#define _ASM_ARM_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM_R0,
+	PERF_REG_ARM_R1,
+	PERF_REG_ARM_R2,
+	PERF_REG_ARM_R3,
+	PERF_REG_ARM_R4,
+	PERF_REG_ARM_R5,
+	PERF_REG_ARM_R6,
+	PERF_REG_ARM_R7,
+	PERF_REG_ARM_R8,
+	PERF_REG_ARM_R9,
+	PERF_REG_ARM_R10,
+	PERF_REG_ARM_FP,
+	PERF_REG_ARM_IP,
+	PERF_REG_ARM_SP,
+	PERF_REG_ARM_LR,
+	PERF_REG_ARM_PC,
+	PERF_REG_ARM_MAX,
+};
+#endif /* _ASM_ARM_PERF_REGS_H */
diff --git a/tools/arch/arm64/include/uapi/asm/bitsperlong.h b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..fce9c29
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_BITSPERLONG_H
+#define __ASM_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif	/* __ASM_BITSPERLONG_H */
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..f209ea1
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -0,0 +1,258 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/uapi/asm/kvm.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#define KVM_SPSR_EL1	0
+#define KVM_SPSR_SVC	KVM_SPSR_EL1
+#define KVM_SPSR_ABT	1
+#define KVM_SPSR_UND	2
+#define KVM_SPSR_IRQ	3
+#define KVM_SPSR_FIQ	4
+#define KVM_NR_SPSR	5
+
+#ifndef __ASSEMBLY__
+#include <linux/psci.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_REG_SIZE(id)						\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+struct kvm_regs {
+	struct user_pt_regs regs;	/* sp = sp_el0 */
+
+	__u64	sp_el1;
+	__u64	elr_el1;
+
+	__u64	spsr[KVM_NR_SPSR];
+
+	struct user_fpsimd_state fp_regs;
+};
+
+/*
+ * Supported CPU Targets - Adding a new target type is not recommended,
+ * unless there are some special registers not supported by the
+ * genericv8 syreg table.
+ */
+#define KVM_ARM_TARGET_AEM_V8		0
+#define KVM_ARM_TARGET_FOUNDATION_V8	1
+#define KVM_ARM_TARGET_CORTEX_A57	2
+#define KVM_ARM_TARGET_XGENE_POTENZA	3
+#define KVM_ARM_TARGET_CORTEX_A53	4
+/* Generic ARM v8 target */
+#define KVM_ARM_TARGET_GENERIC_V8	5
+
+#define KVM_ARM_NUM_TARGETS		6
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT	0
+#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT		16
+#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2		0
+
+/* Supported VGIC address types  */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST	0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU	1
+
+#define KVM_VGIC_V2_DIST_SIZE		0x1000
+#define KVM_VGIC_V2_CPU_SIZE		0x2000
+
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+
+#define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
+#define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
+
+struct kvm_vcpu_init {
+	__u32 target;
+	__u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+/*
+ * See v8 ARM ARM D7.3: Debug Registers
+ *
+ * The architectural limit is 16 debug registers of each type although
+ * in practice there are usually less (see ID_AA64DFR0_EL1).
+ *
+ * Although the control registers are architecturally defined as 32
+ * bits wide we use a 64 bit structure here to keep parity with
+ * KVM_GET/SET_ONE_REG behaviour which treats all system registers as
+ * 64 bit values. It also allows for the possibility of the
+ * architecture expanding the control registers without having to
+ * change the userspace ABI.
+ */
+#define KVM_ARM_MAX_DBG_REGS 16
+struct kvm_guest_debug_arch {
+	__u64 dbg_bcr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_bvr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_wcr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
+};
+
+struct kvm_debug_exit_arch {
+	__u32 hsr;
+	__u64 far;	/* used for watchpoints */
+};
+
+/*
+ * Architecture specific defines for kvm_guest_debug->control
+ */
+
+#define KVM_GUESTDBG_USE_SW_BP		(1 << 16)
+#define KVM_GUESTDBG_USE_HW		(1 << 17)
+
+struct kvm_sync_regs {
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT	16
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name)	(offsetof(struct kvm_regs, name) / sizeof(__u32))
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX		(0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK	0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT	8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR	(0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK	0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT	0
+
+/* AArch64 system registers */
+#define KVM_REG_ARM64_SYSREG		(0x0013 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM64_SYSREG_OP0_MASK	0x000000000000c000
+#define KVM_REG_ARM64_SYSREG_OP0_SHIFT	14
+#define KVM_REG_ARM64_SYSREG_OP1_MASK	0x0000000000003800
+#define KVM_REG_ARM64_SYSREG_OP1_SHIFT	11
+#define KVM_REG_ARM64_SYSREG_CRN_MASK	0x0000000000000780
+#define KVM_REG_ARM64_SYSREG_CRN_SHIFT	7
+#define KVM_REG_ARM64_SYSREG_CRM_MASK	0x0000000000000078
+#define KVM_REG_ARM64_SYSREG_CRM_SHIFT	3
+#define KVM_REG_ARM64_SYSREG_OP2_MASK	0x0000000000000007
+#define KVM_REG_ARM64_SYSREG_OP2_SHIFT	0
+
+#define ARM64_SYS_REG_SHIFT_MASK(x,n) \
+	(((x) << KVM_REG_ARM64_SYSREG_ ## n ## _SHIFT) & \
+	KVM_REG_ARM64_SYSREG_ ## n ## _MASK)
+
+#define __ARM64_SYS_REG(op0,op1,crn,crm,op2) \
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SYSREG | \
+	ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \
+	ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \
+	ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \
+	ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \
+	ARM64_SYS_REG_SHIFT_MASK(op2, OP2))
+
+#define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
+
+#define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
+#define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL	4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
+
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL	0
+#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
+#define   KVM_ARM_VCPU_PMU_V3_INIT	1
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT		24
+#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT		16
+#define KVM_ARM_IRQ_VCPU_MASK		0xff
+#define KVM_ARM_IRQ_NUM_SHIFT		0
+#define KVM_ARM_IRQ_NUM_MASK		0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU		0
+#define KVM_ARM_IRQ_TYPE_SPI		1
+#define KVM_ARM_IRQ_TYPE_PPI		2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ		0
+#define KVM_ARM_IRQ_CPU_FIQ		1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX		127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE		0x95c1ba5e
+#define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND		KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF		KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
+
+#endif
+
+#endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..172b831
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM64_X0,
+	PERF_REG_ARM64_X1,
+	PERF_REG_ARM64_X2,
+	PERF_REG_ARM64_X3,
+	PERF_REG_ARM64_X4,
+	PERF_REG_ARM64_X5,
+	PERF_REG_ARM64_X6,
+	PERF_REG_ARM64_X7,
+	PERF_REG_ARM64_X8,
+	PERF_REG_ARM64_X9,
+	PERF_REG_ARM64_X10,
+	PERF_REG_ARM64_X11,
+	PERF_REG_ARM64_X12,
+	PERF_REG_ARM64_X13,
+	PERF_REG_ARM64_X14,
+	PERF_REG_ARM64_X15,
+	PERF_REG_ARM64_X16,
+	PERF_REG_ARM64_X17,
+	PERF_REG_ARM64_X18,
+	PERF_REG_ARM64_X19,
+	PERF_REG_ARM64_X20,
+	PERF_REG_ARM64_X21,
+	PERF_REG_ARM64_X22,
+	PERF_REG_ARM64_X23,
+	PERF_REG_ARM64_X24,
+	PERF_REG_ARM64_X25,
+	PERF_REG_ARM64_X26,
+	PERF_REG_ARM64_X27,
+	PERF_REG_ARM64_X28,
+	PERF_REG_ARM64_X29,
+	PERF_REG_ARM64_LR,
+	PERF_REG_ARM64_SP,
+	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/frv/include/uapi/asm/bitsperlong.h b/tools/arch/frv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..6dc0bb0
--- /dev/null
+++ b/tools/arch/frv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/h8300/include/asm/bitsperlong.h b/tools/arch/h8300/include/asm/bitsperlong.h
new file mode 100644
index 0000000..e140e46
--- /dev/null
+++ b/tools/arch/h8300/include/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_H8300_BITS_PER_LONG
+#define __ASM_H8300_BITS_PER_LONG
+
+#include <asm-generic/bitsperlong.h>
+
+#if !defined(__ASSEMBLY__)
+/* h8300-unknown-linux required long */
+#define __kernel_size_t __kernel_size_t
+typedef unsigned long	__kernel_size_t;
+typedef long		__kernel_ssize_t;
+typedef long		__kernel_ptrdiff_t;
+#endif
+
+#endif /* __ASM_H8300_BITS_PER_LONG */
diff --git a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..4a65815
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef __ASM_HEXAGON_BITSPERLONG_H
+#define __ASM_HEXAGON_BITSPERLONG_H
+
+#define __BITS_PER_LONG 32
+
+#include <asm-generic/bitsperlong.h>
+
+#endif
diff --git a/tools/arch/ia64/include/uapi/asm/bitsperlong.h b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..ec4db3c
--- /dev/null
+++ b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_IA64_BITSPERLONG_H
+#define __ASM_IA64_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_IA64_BITSPERLONG_H */
diff --git a/tools/arch/m32r/include/uapi/asm/bitsperlong.h b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..6dc0bb0
--- /dev/null
+++ b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..6dc0bb0
--- /dev/null
+++ b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/mips/include/uapi/asm/bitsperlong.h b/tools/arch/mips/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..3e4c10a
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_MIPS_BITSPERLONG_H
+#define __ASM_MIPS_BITSPERLONG_H
+
+#define __BITS_PER_LONG _MIPS_SZLONG
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_MIPS_BITSPERLONG_H */
diff --git a/tools/arch/mips/include/uapi/asm/kvm.h b/tools/arch/mips/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..6985eb5
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/kvm.h
@@ -0,0 +1,208 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Copyright (C) 2013 Cavium, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#ifndef __LINUX_KVM_MIPS_H
+#define __LINUX_KVM_MIPS_H
+
+#include <linux/types.h>
+
+/*
+ * KVM MIPS specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
+
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ *
+ * If Config[AT] is zero (32-bit CPU), the register contents are
+ * stored in the lower 32-bits of the struct kvm_regs fields and sign
+ * extended to 64-bits.
+ */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 hi;
+	__u64 lo;
+	__u64 pc;
+};
+
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ */
+struct kvm_fpu {
+};
+
+
+/*
+ * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various
+ * registers.  The id field is broken down as follows:
+ *
+ *  bits[63..52] - As per linux/kvm.h
+ *  bits[51..32] - Must be zero.
+ *  bits[31..16] - Register set.
+ *
+ * Register set = 0: GP registers from kvm_regs (see definitions below).
+ *
+ * Register set = 1: CP0 registers.
+ *  bits[15..8]  - Must be zero.
+ *  bits[7..3]   - Register 'rd'  index.
+ *  bits[2..0]   - Register 'sel' index.
+ *
+ * Register set = 2: KVM specific registers (see definitions below).
+ *
+ * Register set = 3: FPU / MSA registers (see definitions below).
+ *
+ * Other sets registers may be added in the future.  Each set would
+ * have its own identifier in bits[31..16].
+ */
+
+#define KVM_REG_MIPS_GP		(KVM_REG_MIPS | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_CP0	(KVM_REG_MIPS | 0x0000000000010000ULL)
+#define KVM_REG_MIPS_KVM	(KVM_REG_MIPS | 0x0000000000020000ULL)
+#define KVM_REG_MIPS_FPU	(KVM_REG_MIPS | 0x0000000000030000ULL)
+
+
+/*
+ * KVM_REG_MIPS_GP - General purpose registers from kvm_regs.
+ */
+
+#define KVM_REG_MIPS_R0		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  0)
+#define KVM_REG_MIPS_R1		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  1)
+#define KVM_REG_MIPS_R2		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  2)
+#define KVM_REG_MIPS_R3		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  3)
+#define KVM_REG_MIPS_R4		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  4)
+#define KVM_REG_MIPS_R5		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  5)
+#define KVM_REG_MIPS_R6		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  6)
+#define KVM_REG_MIPS_R7		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  7)
+#define KVM_REG_MIPS_R8		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  8)
+#define KVM_REG_MIPS_R9		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  9)
+#define KVM_REG_MIPS_R10	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10)
+#define KVM_REG_MIPS_R11	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11)
+#define KVM_REG_MIPS_R12	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12)
+#define KVM_REG_MIPS_R13	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13)
+#define KVM_REG_MIPS_R14	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14)
+#define KVM_REG_MIPS_R15	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15)
+#define KVM_REG_MIPS_R16	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16)
+#define KVM_REG_MIPS_R17	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17)
+#define KVM_REG_MIPS_R18	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18)
+#define KVM_REG_MIPS_R19	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19)
+#define KVM_REG_MIPS_R20	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20)
+#define KVM_REG_MIPS_R21	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21)
+#define KVM_REG_MIPS_R22	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22)
+#define KVM_REG_MIPS_R23	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23)
+#define KVM_REG_MIPS_R24	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24)
+#define KVM_REG_MIPS_R25	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25)
+#define KVM_REG_MIPS_R26	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26)
+#define KVM_REG_MIPS_R27	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27)
+#define KVM_REG_MIPS_R28	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28)
+#define KVM_REG_MIPS_R29	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29)
+#define KVM_REG_MIPS_R30	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30)
+#define KVM_REG_MIPS_R31	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31)
+
+#define KVM_REG_MIPS_HI		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32)
+#define KVM_REG_MIPS_LO		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33)
+#define KVM_REG_MIPS_PC		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34)
+
+
+/*
+ * KVM_REG_MIPS_KVM - KVM specific control registers.
+ */
+
+/*
+ * CP0_Count control
+ * DC:    Set 0: Master disable CP0_Count and set COUNT_RESUME to now
+ *        Set 1: Master re-enable CP0_Count with unchanged bias, handling timer
+ *               interrupts since COUNT_RESUME
+ *        This can be used to freeze the timer to get a consistent snapshot of
+ *        the CP0_Count and timer interrupt pending state, while also resuming
+ *        safely without losing time or guest timer interrupts.
+ * Other: Reserved, do not change.
+ */
+#define KVM_REG_MIPS_COUNT_CTL	    (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_MIPS_COUNT_CTL_DC	0x00000001
+
+/*
+ * CP0_Count resume monotonic nanoseconds
+ * The monotonic nanosecond time of the last set of COUNT_CTL.DC (master
+ * disable). Any reads and writes of Count related registers while
+ * COUNT_CTL.DC=1 will appear to occur at this time. When COUNT_CTL.DC is
+ * cleared again (master enable) any timer interrupts since this time will be
+ * emulated.
+ * Modifications to times in the future are rejected.
+ */
+#define KVM_REG_MIPS_COUNT_RESUME   (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1)
+/*
+ * CP0_Count rate in Hz
+ * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without
+ * discontinuities in CP0_Count.
+ */
+#define KVM_REG_MIPS_COUNT_HZ	    (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2)
+
+
+/*
+ * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers.
+ *
+ *  bits[15..8]  - Register subset (see definitions below).
+ *  bits[7..5]   - Must be zero.
+ *  bits[4..0]   - Register number within register subset.
+ */
+
+#define KVM_REG_MIPS_FPR	(KVM_REG_MIPS_FPU | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_FCR	(KVM_REG_MIPS_FPU | 0x0000000000000100ULL)
+#define KVM_REG_MIPS_MSACR	(KVM_REG_MIPS_FPU | 0x0000000000000200ULL)
+
+/*
+ * KVM_REG_MIPS_FPR - Floating point / Vector registers.
+ */
+#define KVM_REG_MIPS_FPR_32(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32  | (n))
+#define KVM_REG_MIPS_FPR_64(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64  | (n))
+#define KVM_REG_MIPS_VEC_128(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n))
+
+/*
+ * KVM_REG_MIPS_FCR - Floating point control registers.
+ */
+#define KVM_REG_MIPS_FCR_IR	(KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 |  0)
+#define KVM_REG_MIPS_FCR_CSR	(KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31)
+
+/*
+ * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers.
+ */
+#define KVM_REG_MIPS_MSA_IR	 (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 |  0)
+#define KVM_REG_MIPS_MSA_CSR	 (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 |  1)
+
+
+/*
+ * KVM MIPS specific structures and definitions
+ *
+ */
+struct kvm_debug_exit_arch {
+	__u64 epc;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
+struct kvm_mips_interrupt {
+	/* in */
+	__u32 cpu;
+	__u32 irq;
+};
+
+#endif /* __LINUX_KVM_MIPS_H */
diff --git a/tools/arch/mn10300/include/uapi/asm/bitsperlong.h b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..6dc0bb0
--- /dev/null
+++ b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/parisc/include/uapi/asm/bitsperlong.h b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..e0a23c7
--- /dev/null
+++ b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_PARISC_BITSPERLONG_H
+#define __ASM_PARISC_BITSPERLONG_H
+
+#if defined(__LP64__)
+#define __BITS_PER_LONG 64
+#define SHIFT_PER_LONG 6
+#else
+#define __BITS_PER_LONG 32
+#define SHIFT_PER_LONG 5
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_PARISC_BITSPERLONG_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..5f16590
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_POWERPC_BITSPERLONG_H
+#define __ASM_POWERPC_BITSPERLONG_H
+
+#if defined(__powerpc64__)
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_POWERPC_BITSPERLONG_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..c93cf35
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -0,0 +1,612 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __LINUX_KVM_POWERPC_H
+#define __LINUX_KVM_POWERPC_H
+
+#include <linux/types.h>
+
+/* Select powerpc specific features in <linux/kvm.h> */
+#define __KVM_HAVE_SPAPR_TCE
+#define __KVM_HAVE_PPC_SMT
+#define __KVM_HAVE_IRQCHIP
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_GUEST_DEBUG
+
+struct kvm_regs {
+	__u64 pc;
+	__u64 cr;
+	__u64 ctr;
+	__u64 lr;
+	__u64 xer;
+	__u64 msr;
+	__u64 srr0;
+	__u64 srr1;
+	__u64 pid;
+
+	__u64 sprg0;
+	__u64 sprg1;
+	__u64 sprg2;
+	__u64 sprg3;
+	__u64 sprg4;
+	__u64 sprg5;
+	__u64 sprg6;
+	__u64 sprg7;
+
+	__u64 gpr[32];
+};
+
+#define KVM_SREGS_E_IMPL_NONE	0
+#define KVM_SREGS_E_IMPL_FSL	1
+
+#define KVM_SREGS_E_FSL_PIDn	(1 << 0) /* PID1/PID2 */
+
+/*
+ * Feature bits indicate which sections of the sregs struct are valid,
+ * both in KVM_GET_SREGS and KVM_SET_SREGS.  On KVM_SET_SREGS, registers
+ * corresponding to unset feature bits will not be modified.  This allows
+ * restoring a checkpoint made without that feature, while keeping the
+ * default values of the new registers.
+ *
+ * KVM_SREGS_E_BASE contains:
+ * CSRR0/1 (refers to SRR2/3 on 40x)
+ * ESR
+ * DEAR
+ * MCSR
+ * TSR
+ * TCR
+ * DEC
+ * TB
+ * VRSAVE (USPRG0)
+ */
+#define KVM_SREGS_E_BASE		(1 << 0)
+
+/*
+ * KVM_SREGS_E_ARCH206 contains:
+ *
+ * PIR
+ * MCSRR0/1
+ * DECAR
+ * IVPR
+ */
+#define KVM_SREGS_E_ARCH206		(1 << 1)
+
+/*
+ * Contains EPCR, plus the upper half of 64-bit registers
+ * that are 32-bit on 32-bit implementations.
+ */
+#define KVM_SREGS_E_64			(1 << 2)
+
+#define KVM_SREGS_E_SPRG8		(1 << 3)
+#define KVM_SREGS_E_MCIVPR		(1 << 4)
+
+/*
+ * IVORs are used -- contains IVOR0-15, plus additional IVORs
+ * in combination with an appropriate feature bit.
+ */
+#define KVM_SREGS_E_IVOR		(1 << 5)
+
+/*
+ * Contains MAS0-4, MAS6-7, TLBnCFG, MMUCFG.
+ * Also TLBnPS if MMUCFG[MAVN] = 1.
+ */
+#define KVM_SREGS_E_ARCH206_MMU		(1 << 6)
+
+/* DBSR, DBCR, IAC, DAC, DVC */
+#define KVM_SREGS_E_DEBUG		(1 << 7)
+
+/* Enhanced debug -- DSRR0/1, SPRG9 */
+#define KVM_SREGS_E_ED			(1 << 8)
+
+/* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_SPE			(1 << 9)
+
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
+#define KVM_SREGS_EXP			(1 << 10)
+
+/* External PID (E.PD) -- EPSC/EPLC */
+#define KVM_SREGS_E_PD			(1 << 11)
+
+/* Processor Control (E.PC) -- IVOR36-37 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PC			(1 << 12)
+
+/* Page table (E.PT) -- EPTCFG */
+#define KVM_SREGS_E_PT			(1 << 13)
+
+/* Embedded Performance Monitor (E.PM) -- IVOR35 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PM			(1 << 14)
+
+/*
+ * Special updates:
+ *
+ * Some registers may change even while a vcpu is not running.
+ * To avoid losing these changes, by default these registers are
+ * not updated by KVM_SET_SREGS.  To force an update, set the bit
+ * in u.e.update_special corresponding to the register to be updated.
+ *
+ * The update_special field is zero on return from KVM_GET_SREGS.
+ *
+ * When restoring a checkpoint, the caller can set update_special
+ * to 0xffffffff to ensure that everything is restored, even new features
+ * that the caller doesn't know about.
+ */
+#define KVM_SREGS_E_UPDATE_MCSR		(1 << 0)
+#define KVM_SREGS_E_UPDATE_TSR		(1 << 1)
+#define KVM_SREGS_E_UPDATE_DEC		(1 << 2)
+#define KVM_SREGS_E_UPDATE_DBSR		(1 << 3)
+
+/*
+ * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
+ * previous KVM_GET_REGS.
+ *
+ * Unless otherwise indicated, setting any register with KVM_SET_SREGS
+ * directly sets its value.  It does not trigger any special semantics such
+ * as write-one-to-clear.  Calling KVM_SET_SREGS on an unmodified struct
+ * just received from KVM_GET_SREGS is always a no-op.
+ */
+struct kvm_sregs {
+	__u32 pvr;
+	union {
+		struct {
+			__u64 sdr1;
+			struct {
+				struct {
+					__u64 slbe;
+					__u64 slbv;
+				} slb[64];
+			} ppc64;
+			struct {
+				__u32 sr[16];
+				__u64 ibat[8];
+				__u64 dbat[8];
+			} ppc32;
+		} s;
+		struct {
+			union {
+				struct { /* KVM_SREGS_E_IMPL_FSL */
+					__u32 features; /* KVM_SREGS_E_FSL_ */
+					__u32 svr;
+					__u64 mcar;
+					__u32 hid0;
+
+					/* KVM_SREGS_E_FSL_PIDn */
+					__u32 pid1, pid2;
+				} fsl;
+				__u8 pad[256];
+			} impl;
+
+			__u32 features; /* KVM_SREGS_E_ */
+			__u32 impl_id;	/* KVM_SREGS_E_IMPL_ */
+			__u32 update_special; /* KVM_SREGS_E_UPDATE_ */
+			__u32 pir;	/* read-only */
+			__u64 sprg8;
+			__u64 sprg9;	/* E.ED */
+			__u64 csrr0;
+			__u64 dsrr0;	/* E.ED */
+			__u64 mcsrr0;
+			__u32 csrr1;
+			__u32 dsrr1;	/* E.ED */
+			__u32 mcsrr1;
+			__u32 esr;
+			__u64 dear;
+			__u64 ivpr;
+			__u64 mcivpr;
+			__u64 mcsr;	/* KVM_SREGS_E_UPDATE_MCSR */
+
+			__u32 tsr;	/* KVM_SREGS_E_UPDATE_TSR */
+			__u32 tcr;
+			__u32 decar;
+			__u32 dec;	/* KVM_SREGS_E_UPDATE_DEC */
+
+			/*
+			 * Userspace can read TB directly, but the
+			 * value reported here is consistent with "dec".
+			 *
+			 * Read-only.
+			 */
+			__u64 tb;
+
+			__u32 dbsr;	/* KVM_SREGS_E_UPDATE_DBSR */
+			__u32 dbcr[3];
+			/*
+			 * iac/dac registers are 64bit wide, while this API
+			 * interface provides only lower 32 bits on 64 bit
+			 * processors. ONE_REG interface is added for 64bit
+			 * iac/dac registers.
+			 */
+			__u32 iac[4];
+			__u32 dac[2];
+			__u32 dvc[2];
+			__u8 num_iac;	/* read-only */
+			__u8 num_dac;	/* read-only */
+			__u8 num_dvc;	/* read-only */
+			__u8 pad;
+
+			__u32 epr;	/* EXP */
+			__u32 vrsave;	/* a.k.a. USPRG0 */
+			__u32 epcr;	/* KVM_SREGS_E_64 */
+
+			__u32 mas0;
+			__u32 mas1;
+			__u64 mas2;
+			__u64 mas7_3;
+			__u32 mas4;
+			__u32 mas6;
+
+			__u32 ivor_low[16]; /* IVOR0-15 */
+			__u32 ivor_high[18]; /* IVOR32+, plus room to expand */
+
+			__u32 mmucfg;	/* read-only */
+			__u32 eptcfg;	/* E.PT, read-only */
+			__u32 tlbcfg[4];/* read-only */
+			__u32 tlbps[4]; /* read-only */
+
+			__u32 eplc, epsc; /* E.PD */
+		} e;
+		__u8 pad[1020];
+	} u;
+};
+
+struct kvm_fpu {
+	__u64 fpr[32];
+};
+
+/*
+ * Defines for h/w breakpoint, watchpoint (read, write or both) and
+ * software breakpoint.
+ * These are used as "type" in KVM_SET_GUEST_DEBUG ioctl and "status"
+ * for KVM_DEBUG_EXIT.
+ */
+#define KVMPPC_DEBUG_NONE		0x0
+#define KVMPPC_DEBUG_BREAKPOINT		(1UL << 1)
+#define KVMPPC_DEBUG_WATCH_WRITE	(1UL << 2)
+#define KVMPPC_DEBUG_WATCH_READ		(1UL << 3)
+struct kvm_debug_exit_arch {
+	__u64 address;
+	/*
+	 * exiting to userspace because of h/w breakpoint, watchpoint
+	 * (read, write or both) and software breakpoint.
+	 */
+	__u32 status;
+	__u32 reserved;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	struct {
+		/* H/W breakpoint/watchpoint address */
+		__u64 addr;
+		/*
+		 * Type denotes h/w breakpoint, read watchpoint, write
+		 * watchpoint or watchpoint (both read and write).
+		 */
+		__u32 type;
+		__u32 reserved;
+	} bp[16];
+};
+
+/* Debug related defines */
+/*
+ * kvm_guest_debug->control is a 32 bit field. The lower 16 bits are generic
+ * and upper 16 bits are architecture specific. Architecture specific defines
+ * that ioctl is for setting hardware breakpoint or software breakpoint.
+ */
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+#define KVM_INTERRUPT_SET	-1U
+#define KVM_INTERRUPT_UNSET	-2U
+#define KVM_INTERRUPT_SET_LEVEL	-3U
+
+#define KVM_CPU_440		1
+#define KVM_CPU_E500V2		2
+#define KVM_CPU_3S_32		3
+#define KVM_CPU_3S_64		4
+#define KVM_CPU_E500MC		5
+
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+	__u64 liobn;
+	__u32 window_size;
+};
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+	__u64 liobn;
+	__u32 page_shift;
+	__u32 flags;
+	__u64 offset;	/* in pages */
+	__u64 size;	/* in pages */
+};
+
+/* for KVM_ALLOCATE_RMA */
+struct kvm_allocate_rma {
+	__u64 rma_size;
+};
+
+/* for KVM_CAP_PPC_RTAS */
+struct kvm_rtas_token_args {
+	char name[120];
+	__u64 token;	/* Use a token of 0 to undefine a mapping */
+};
+
+struct kvm_book3e_206_tlb_entry {
+	__u32 mas8;
+	__u32 mas1;
+	__u64 mas2;
+	__u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+	/*
+	 * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+	 *
+	 * - The number of ways of TLB0 must be a power of two between 2 and
+	 *   16.
+	 * - TLB1 must be fully associative.
+	 * - The size of TLB0 must be a multiple of the number of ways, and
+	 *   the number of sets must be a power of two.
+	 * - The size of TLB1 may not exceed 64 entries.
+	 * - TLB0 supports 4 KiB pages.
+	 * - The page sizes supported by TLB1 are as indicated by
+	 *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+	 *   as returned by KVM_GET_SREGS.
+	 * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+	 *   and tlb_ways[] must be zero.
+	 *
+	 * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+	 *
+	 * KVM will adjust TLBnCFG based on the sizes configured here,
+	 * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+	 * set to zero.
+	 */
+	__u32 tlb_sizes[4];
+	__u32 tlb_ways[4];
+	__u32 reserved[8];
+};
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid.  Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream.  The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
+/* Per-vcpu XICS interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
+
+#define  KVM_REG_PPC_ICP_CPPR_SHIFT	56	/* current proc priority */
+#define  KVM_REG_PPC_ICP_CPPR_MASK	0xff
+#define  KVM_REG_PPC_ICP_XISR_SHIFT	32	/* interrupt status field */
+#define  KVM_REG_PPC_ICP_XISR_MASK	0xffffff
+#define  KVM_REG_PPC_ICP_MFRR_SHIFT	24	/* pending IPI priority */
+#define  KVM_REG_PPC_ICP_MFRR_MASK	0xff
+#define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
+#define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
+
+/* Device control API: PPC-specific devices */
+#define KVM_DEV_MPIC_GRP_MISC		1
+#define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
+
+#define KVM_DEV_MPIC_GRP_REGISTER	2	/* 32-bit */
+#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE	3	/* 32-bit */
+
+/* One-Reg API: PPC-specific registers */
+#define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+#define KVM_REG_PPC_IAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_PPC_IAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_PPC_IAC3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_PPC_IAC4	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_PPC_DAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_PPC_DAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_PPC_DABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_PPC_DSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9)
+#define KVM_REG_PPC_PURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa)
+#define KVM_REG_PPC_SPURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb)
+#define KVM_REG_PPC_DAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc)
+#define KVM_REG_PPC_DSISR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xd)
+#define KVM_REG_PPC_AMR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xe)
+#define KVM_REG_PPC_UAMOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xf)
+
+#define KVM_REG_PPC_MMCR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
+#define KVM_REG_PPC_MMCR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
+#define KVM_REG_PPC_MMCRA	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
+
+#define KVM_REG_PPC_PMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
+#define KVM_REG_PPC_PMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
+#define KVM_REG_PPC_PMC3	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1a)
+#define KVM_REG_PPC_PMC4	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1b)
+#define KVM_REG_PPC_PMC5	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1c)
+#define KVM_REG_PPC_PMC6	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1d)
+#define KVM_REG_PPC_PMC7	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1e)
+#define KVM_REG_PPC_PMC8	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1f)
+
+/* 32 floating-point registers */
+#define KVM_REG_PPC_FPR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x20)
+#define KVM_REG_PPC_FPR(n)	(KVM_REG_PPC_FPR0 + (n))
+#define KVM_REG_PPC_FPR31	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3f)
+
+/* 32 VMX/Altivec vector registers */
+#define KVM_REG_PPC_VR0		(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x40)
+#define KVM_REG_PPC_VR(n)	(KVM_REG_PPC_VR0 + (n))
+#define KVM_REG_PPC_VR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x5f)
+
+/* 32 double-width FP registers for VSX */
+/* High-order halves overlap with FP regs */
+#define KVM_REG_PPC_VSR0	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x60)
+#define KVM_REG_PPC_VSR(n)	(KVM_REG_PPC_VSR0 + (n))
+#define KVM_REG_PPC_VSR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x7f)
+
+/* FP and vector status/control registers */
+#define KVM_REG_PPC_FPSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x80)
+/*
+ * VSCR register is documented as a 32-bit register in the ISA, but it can
+ * only be accesses via a vector register. Expose VSCR as a 32-bit register
+ * even though the kernel represents it as a 128-bit vector.
+ */
+#define KVM_REG_PPC_VSCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x81)
+
+/* Virtual processor areas */
+/* For SLB & DTL, address in high (first) half, length in low half */
+#define KVM_REG_PPC_VPA_ADDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x82)
+#define KVM_REG_PPC_VPA_SLB	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x83)
+#define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
+
+#define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
+
+/* Timer Status Register OR/CLEAR interface */
+#define KVM_REG_PPC_OR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x87)
+#define KVM_REG_PPC_CLEAR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x88)
+#define KVM_REG_PPC_TCR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x89)
+#define KVM_REG_PPC_TSR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8a)
+
+/* Debugging: Special instruction for software breakpoint */
+#define KVM_REG_PPC_DEBUG_INST	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8b)
+
+/* MMU registers */
+#define KVM_REG_PPC_MAS0	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8c)
+#define KVM_REG_PPC_MAS1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8d)
+#define KVM_REG_PPC_MAS2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8e)
+#define KVM_REG_PPC_MAS7_3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8f)
+#define KVM_REG_PPC_MAS4	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x90)
+#define KVM_REG_PPC_MAS6	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x91)
+#define KVM_REG_PPC_MMUCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x92)
+/*
+ * TLBnCFG fields TLBnCFG_N_ENTRY and TLBnCFG_ASSOC can be changed only using
+ * KVM_CAP_SW_TLB ioctl
+ */
+#define KVM_REG_PPC_TLB0CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x93)
+#define KVM_REG_PPC_TLB1CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x94)
+#define KVM_REG_PPC_TLB2CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x95)
+#define KVM_REG_PPC_TLB3CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x96)
+#define KVM_REG_PPC_TLB0PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x97)
+#define KVM_REG_PPC_TLB1PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x98)
+#define KVM_REG_PPC_TLB2PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x99)
+#define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
+#define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_EBBRR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define KVM_REG_PPC_BESCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7)
+#define KVM_REG_PPC_TAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8)
+#define KVM_REG_PPC_DPDES	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9)
+#define KVM_REG_PPC_DAWR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa)
+#define KVM_REG_PPC_DAWRX	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab)
+#define KVM_REG_PPC_CIABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac)
+#define KVM_REG_PPC_IC		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad)
+#define KVM_REG_PPC_VTB		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae)
+#define KVM_REG_PPC_CSIGR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf)
+#define KVM_REG_PPC_TACR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0)
+#define KVM_REG_PPC_TCSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
+#define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
+#define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
+
+#define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_LPCR_64	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb5)
+#define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
+
+/* Architecture compatibility level */
+#define KVM_REG_PPC_ARCH_COMPAT	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
+
+#define KVM_REG_PPC_DABRX	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8)
+#define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9)
+#define KVM_REG_PPC_SPRG9	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
+#define KVM_REG_PPC_DBSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+
+/* Transactional Memory checkpointed state:
+ * This is all GPRs, all VSX regs and a subset of SPRs
+ */
+#define KVM_REG_PPC_TM		(KVM_REG_PPC | 0x80000000)
+/* TM GPRs */
+#define KVM_REG_PPC_TM_GPR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_PPC_TM_GPR(n)	(KVM_REG_PPC_TM_GPR0 + (n))
+#define KVM_REG_PPC_TM_GPR31	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f)
+/* TM VSX */
+#define KVM_REG_PPC_TM_VSR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20)
+#define KVM_REG_PPC_TM_VSR(n)	(KVM_REG_PPC_TM_VSR0 + (n))
+#define KVM_REG_PPC_TM_VSR63	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f)
+/* TM SPRS */
+#define KVM_REG_PPC_TM_CR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60)
+#define KVM_REG_PPC_TM_LR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61)
+#define KVM_REG_PPC_TM_CTR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62)
+#define KVM_REG_PPC_TM_FPSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63)
+#define KVM_REG_PPC_TM_AMR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64)
+#define KVM_REG_PPC_TM_PPR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65)
+#define KVM_REG_PPC_TM_VRSAVE	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66)
+#define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
+#define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
+#define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+
+/* PPC64 eXternal Interrupt Controller Specification */
+#define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+
+/* Layout of 64-bit source attribute values */
+#define  KVM_XICS_DESTINATION_SHIFT	0
+#define  KVM_XICS_DESTINATION_MASK	0xffffffffULL
+#define  KVM_XICS_PRIORITY_SHIFT	32
+#define  KVM_XICS_PRIORITY_MASK		0xff
+#define  KVM_XICS_LEVEL_SENSITIVE	(1ULL << 40)
+#define  KVM_XICS_MASKED		(1ULL << 41)
+#define  KVM_XICS_PENDING		(1ULL << 42)
+
+#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..6a93209
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -0,0 +1,50 @@
+#ifndef _UAPI_ASM_POWERPC_PERF_REGS_H
+#define _UAPI_ASM_POWERPC_PERF_REGS_H
+
+enum perf_event_powerpc_regs {
+	PERF_REG_POWERPC_R0,
+	PERF_REG_POWERPC_R1,
+	PERF_REG_POWERPC_R2,
+	PERF_REG_POWERPC_R3,
+	PERF_REG_POWERPC_R4,
+	PERF_REG_POWERPC_R5,
+	PERF_REG_POWERPC_R6,
+	PERF_REG_POWERPC_R7,
+	PERF_REG_POWERPC_R8,
+	PERF_REG_POWERPC_R9,
+	PERF_REG_POWERPC_R10,
+	PERF_REG_POWERPC_R11,
+	PERF_REG_POWERPC_R12,
+	PERF_REG_POWERPC_R13,
+	PERF_REG_POWERPC_R14,
+	PERF_REG_POWERPC_R15,
+	PERF_REG_POWERPC_R16,
+	PERF_REG_POWERPC_R17,
+	PERF_REG_POWERPC_R18,
+	PERF_REG_POWERPC_R19,
+	PERF_REG_POWERPC_R20,
+	PERF_REG_POWERPC_R21,
+	PERF_REG_POWERPC_R22,
+	PERF_REG_POWERPC_R23,
+	PERF_REG_POWERPC_R24,
+	PERF_REG_POWERPC_R25,
+	PERF_REG_POWERPC_R26,
+	PERF_REG_POWERPC_R27,
+	PERF_REG_POWERPC_R28,
+	PERF_REG_POWERPC_R29,
+	PERF_REG_POWERPC_R30,
+	PERF_REG_POWERPC_R31,
+	PERF_REG_POWERPC_NIP,
+	PERF_REG_POWERPC_MSR,
+	PERF_REG_POWERPC_ORIG_R3,
+	PERF_REG_POWERPC_CTR,
+	PERF_REG_POWERPC_LINK,
+	PERF_REG_POWERPC_XER,
+	PERF_REG_POWERPC_CCR,
+	PERF_REG_POWERPC_SOFTE,
+	PERF_REG_POWERPC_TRAP,
+	PERF_REG_POWERPC_DAR,
+	PERF_REG_POWERPC_DSISR,
+	PERF_REG_POWERPC_MAX,
+};
+#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/tools/arch/s390/include/uapi/asm/bitsperlong.h b/tools/arch/s390/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..e351ea2
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_S390_BITSPERLONG_H
+#define __ASM_S390_BITSPERLONG_H
+
+#ifndef __s390x__
+#define __BITS_PER_LONG 32
+#else
+#define __BITS_PER_LONG 64
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_S390_BITSPERLONG_H */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..3b8e99e
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -0,0 +1,192 @@
+#ifndef __LINUX_KVM_S390_H
+#define __LINUX_KVM_S390_H
+/*
+ * KVM s390 specific structures and definitions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+#include <linux/types.h>
+
+#define __KVM_S390
+#define __KVM_HAVE_GUEST_DEBUG
+
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS	1
+#define KVM_DEV_FLIC_ENQUEUE		2
+#define KVM_DEV_FLIC_CLEAR_IRQS		3
+#define KVM_DEV_FLIC_APF_ENABLE		4
+#define KVM_DEV_FLIC_APF_DISABLE_WAIT	5
+#define KVM_DEV_FLIC_ADAPTER_REGISTER	6
+#define KVM_DEV_FLIC_ADAPTER_MODIFY	7
+#define KVM_DEV_FLIC_CLEAR_IO_IRQ	8
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+#define KVM_S390_MAX_FLOAT_IRQS	266250
+#define KVM_S390_FLIC_MAX_BUFFER	0x2000000
+
+struct kvm_s390_io_adapter {
+	__u32 id;
+	__u8 isc;
+	__u8 maskable;
+	__u8 swap;
+	__u8 pad;
+};
+
+#define KVM_S390_IO_ADAPTER_MASK 1
+#define KVM_S390_IO_ADAPTER_MAP 2
+#define KVM_S390_IO_ADAPTER_UNMAP 3
+
+struct kvm_s390_io_adapter_req {
+	__u32 id;
+	__u8 type;
+	__u8 mask;
+	__u16 pad0;
+	__u64 addr;
+};
+
+/* kvm attr_group  on vm fd */
+#define KVM_S390_VM_MEM_CTRL		0
+#define KVM_S390_VM_TOD			1
+#define KVM_S390_VM_CRYPTO		2
+#define KVM_S390_VM_CPU_MODEL		3
+
+/* kvm attributes for mem_ctrl */
+#define KVM_S390_VM_MEM_ENABLE_CMMA	0
+#define KVM_S390_VM_MEM_CLR_CMMA	1
+#define KVM_S390_VM_MEM_LIMIT_SIZE	2
+
+#define KVM_S390_NO_MEM_LIMIT		U64_MAX
+
+/* kvm attributes for KVM_S390_VM_TOD */
+#define KVM_S390_VM_TOD_LOW		0
+#define KVM_S390_VM_TOD_HIGH		1
+
+/* kvm attributes for KVM_S390_VM_CPU_MODEL */
+/* processor related attributes are r/w */
+#define KVM_S390_VM_CPU_PROCESSOR	0
+struct kvm_s390_vm_cpu_processor {
+	__u64 cpuid;
+	__u16 ibc;
+	__u8  pad[6];
+	__u64 fac_list[256];
+};
+
+/* machine related attributes are r/o */
+#define KVM_S390_VM_CPU_MACHINE		1
+struct kvm_s390_vm_cpu_machine {
+	__u64 cpuid;
+	__u32 ibc;
+	__u8  pad[4];
+	__u64 fac_mask[256];
+	__u64 fac_list[256];
+};
+
+/* kvm attributes for crypto */
+#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
+#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
+#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
+#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* general purpose regs for s390 */
+	__u64 gprs[16];
+};
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	__u32 acrs[16];
+	__u64 crs[16];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u32 fpc;
+	__u64 fprs[16];
+};
+
+#define KVM_GUESTDBG_USE_HW_BP		0x00010000
+
+#define KVM_HW_BP			1
+#define KVM_HW_WP_WRITE			2
+#define KVM_SINGLESTEP			4
+
+struct kvm_debug_exit_arch {
+	__u64 addr;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+struct kvm_hw_breakpoint {
+	__u64 addr;
+	__u64 phys_addr;
+	__u64 len;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u32 nr_hw_bp;
+	__u32 pad; /* Should be set to 0 */
+	struct kvm_hw_breakpoint __user *hw_bp;
+};
+
+/* for KVM_SYNC_PFAULT and KVM_REG_S390_PFTOKEN */
+#define KVM_S390_PFAULT_TOKEN_INVALID	0xffffffffffffffffULL
+
+#define KVM_SYNC_PREFIX (1UL << 0)
+#define KVM_SYNC_GPRS   (1UL << 1)
+#define KVM_SYNC_ACRS   (1UL << 2)
+#define KVM_SYNC_CRS    (1UL << 3)
+#define KVM_SYNC_ARCH0  (1UL << 4)
+#define KVM_SYNC_PFAULT (1UL << 5)
+#define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_RICCB  (1UL << 7)
+#define KVM_SYNC_FPRS   (1UL << 8)
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+	__u64 prefix;	/* prefix register */
+	__u64 gprs[16];	/* general purpose registers */
+	__u32 acrs[16];	/* access registers */
+	__u64 crs[16];	/* control registers */
+	__u64 todpr;	/* tod programmable register [ARCH0] */
+	__u64 cputm;	/* cpu timer [ARCH0] */
+	__u64 ckc;	/* clock comparator [ARCH0] */
+	__u64 pp;	/* program parameter [ARCH0] */
+	__u64 gbea;	/* guest breaking-event address [ARCH0] */
+	__u64 pft;	/* pfault token [PFAULT] */
+	__u64 pfs;	/* pfault select [PFAULT] */
+	__u64 pfc;	/* pfault compare [PFAULT] */
+	union {
+		__u64 vrs[32][2];	/* vector registers (KVM_SYNC_VRS) */
+		__u64 fprs[16];		/* fp registers (KVM_SYNC_FPRS) */
+	};
+	__u8  reserved[512];	/* for future vector expansion */
+	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
+	__u8 padding[52];	/* riccb needs to be 64byte aligned */
+	__u8 riccb[64];		/* runtime instrumentation controls block */
+};
+
+#define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
+#define KVM_REG_S390_EPOCHDIFF	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_S390_CPU_TIMER  (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_S390_CLOCK_COMP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_S390_PFTOKEN	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_S390_PFCOMPARE	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_S390_PFSELECT	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_S390_PP		(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_S390_GBEA	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x9)
+#endif
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
new file mode 100644
index 0000000..3972827
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,25 @@
+/*
+ * Definitions for perf-kvm on s390
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_KVM_PERF_S390_H
+#define __LINUX_KVM_PERF_S390_H
+
+#include <asm/sie.h>
+
+#define DECODE_STR_LEN 40
+
+#define VCPU_ID "id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_s390_sie_enter"
+#define KVM_EXIT_TRACE "kvm:kvm_s390_sie_exit"
+#define KVM_EXIT_REASON "icptcode"
+
+#endif
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
new file mode 100644
index 0000000..8fb5d4a
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -0,0 +1,250 @@
+#ifndef _UAPI_ASM_S390_SIE_H
+#define _UAPI_ASM_S390_SIE_H
+
+#define diagnose_codes						\
+	{ 0x10, "DIAG (0x10) release pages" },			\
+	{ 0x44, "DIAG (0x44) time slice end" },			\
+	{ 0x9c, "DIAG (0x9c) time slice end directed" },	\
+	{ 0x204, "DIAG (0x204) logical-cpu utilization" },	\
+	{ 0x258, "DIAG (0x258) page-reference services" },	\
+	{ 0x288, "DIAG (0x288) watchdog functions" },		\
+	{ 0x308, "DIAG (0x308) ipl functions" },		\
+	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
+	{ 0x501, "DIAG (0x501) KVM breakpoint" }
+
+#define sigp_order_codes					\
+	{ 0x01, "SIGP sense" },					\
+	{ 0x02, "SIGP external call" },				\
+	{ 0x03, "SIGP emergency signal" },			\
+	{ 0x04, "SIGP start" },					\
+	{ 0x05, "SIGP stop" },					\
+	{ 0x06, "SIGP restart" },				\
+	{ 0x09, "SIGP stop and store status" },			\
+	{ 0x0b, "SIGP initial cpu reset" },			\
+	{ 0x0c, "SIGP cpu reset" },				\
+	{ 0x0d, "SIGP set prefix" },				\
+	{ 0x0e, "SIGP store status at address" },		\
+	{ 0x12, "SIGP set architecture" },			\
+	{ 0x13, "SIGP conditional emergency signal" },		\
+	{ 0x15, "SIGP sense running" },				\
+	{ 0x16, "SIGP set multithreading"},			\
+	{ 0x17, "SIGP store additional status ait address"}
+
+#define icpt_prog_codes						\
+	{ 0x0001, "Prog Operation" },				\
+	{ 0x0002, "Prog Privileged Operation" },		\
+	{ 0x0003, "Prog Execute" },				\
+	{ 0x0004, "Prog Protection" },				\
+	{ 0x0005, "Prog Addressing" },				\
+	{ 0x0006, "Prog Specification" },			\
+	{ 0x0007, "Prog Data" },				\
+	{ 0x0008, "Prog Fixedpoint overflow" },			\
+	{ 0x0009, "Prog Fixedpoint divide" },			\
+	{ 0x000A, "Prog Decimal overflow" },			\
+	{ 0x000B, "Prog Decimal divide" },			\
+	{ 0x000C, "Prog HFP exponent overflow" },		\
+	{ 0x000D, "Prog HFP exponent underflow" },		\
+	{ 0x000E, "Prog HFP significance" },			\
+	{ 0x000F, "Prog HFP divide" },				\
+	{ 0x0010, "Prog Segment translation" },			\
+	{ 0x0011, "Prog Page translation" },			\
+	{ 0x0012, "Prog Translation specification" },		\
+	{ 0x0013, "Prog Special operation" },			\
+	{ 0x0015, "Prog Operand" },				\
+	{ 0x0016, "Prog Trace table" },				\
+	{ 0x0017, "Prog ASNtranslation specification" },	\
+	{ 0x001C, "Prog Spaceswitch event" },			\
+	{ 0x001D, "Prog HFP square root" },			\
+	{ 0x001F, "Prog PCtranslation specification" },		\
+	{ 0x0020, "Prog AFX translation" },			\
+	{ 0x0021, "Prog ASX translation" },			\
+	{ 0x0022, "Prog LX translation" },			\
+	{ 0x0023, "Prog EX translation" },			\
+	{ 0x0024, "Prog Primary authority" },			\
+	{ 0x0025, "Prog Secondary authority" },			\
+	{ 0x0026, "Prog LFXtranslation exception" },		\
+	{ 0x0027, "Prog LSXtranslation exception" },		\
+	{ 0x0028, "Prog ALET specification" },			\
+	{ 0x0029, "Prog ALEN translation" },			\
+	{ 0x002A, "Prog ALE sequence" },			\
+	{ 0x002B, "Prog ASTE validity" },			\
+	{ 0x002C, "Prog ASTE sequence" },			\
+	{ 0x002D, "Prog Extended authority" },			\
+	{ 0x002E, "Prog LSTE sequence" },			\
+	{ 0x002F, "Prog ASTE instance" },			\
+	{ 0x0030, "Prog Stack full" },				\
+	{ 0x0031, "Prog Stack empty" },				\
+	{ 0x0032, "Prog Stack specification" },			\
+	{ 0x0033, "Prog Stack type" },				\
+	{ 0x0034, "Prog Stack operation" },			\
+	{ 0x0039, "Prog Region first translation" },		\
+	{ 0x003A, "Prog Region second translation" },		\
+	{ 0x003B, "Prog Region third translation" },		\
+	{ 0x0040, "Prog Monitor event" },			\
+	{ 0x0080, "Prog PER event" },				\
+	{ 0x0119, "Prog Crypto operation" }
+
+#define exit_code_ipa0(ipa0, opcode, mnemonic)		\
+	{ (ipa0 << 8 | opcode), #ipa0 " " mnemonic }
+#define exit_code(opcode, mnemonic)			\
+	{ opcode, mnemonic }
+
+#define icpt_insn_codes				\
+	exit_code_ipa0(0x01, 0x01, "PR"),	\
+	exit_code_ipa0(0x01, 0x04, "PTFF"),	\
+	exit_code_ipa0(0x01, 0x07, "SCKPF"),	\
+	exit_code_ipa0(0xAA, 0x00, "RINEXT"),	\
+	exit_code_ipa0(0xAA, 0x01, "RION"),	\
+	exit_code_ipa0(0xAA, 0x02, "TRIC"),	\
+	exit_code_ipa0(0xAA, 0x03, "RIOFF"),	\
+	exit_code_ipa0(0xAA, 0x04, "RIEMIT"),	\
+	exit_code_ipa0(0xB2, 0x02, "STIDP"),	\
+	exit_code_ipa0(0xB2, 0x04, "SCK"),	\
+	exit_code_ipa0(0xB2, 0x05, "STCK"),	\
+	exit_code_ipa0(0xB2, 0x06, "SCKC"),	\
+	exit_code_ipa0(0xB2, 0x07, "STCKC"),	\
+	exit_code_ipa0(0xB2, 0x08, "SPT"),	\
+	exit_code_ipa0(0xB2, 0x09, "STPT"),	\
+	exit_code_ipa0(0xB2, 0x0d, "PTLB"),	\
+	exit_code_ipa0(0xB2, 0x10, "SPX"),	\
+	exit_code_ipa0(0xB2, 0x11, "STPX"),	\
+	exit_code_ipa0(0xB2, 0x12, "STAP"),	\
+	exit_code_ipa0(0xB2, 0x14, "SIE"),	\
+	exit_code_ipa0(0xB2, 0x16, "SETR"),	\
+	exit_code_ipa0(0xB2, 0x17, "STETR"),	\
+	exit_code_ipa0(0xB2, 0x18, "PC"),	\
+	exit_code_ipa0(0xB2, 0x20, "SERVC"),	\
+	exit_code_ipa0(0xB2, 0x21, "IPTE"),	\
+	exit_code_ipa0(0xB2, 0x28, "PT"),	\
+	exit_code_ipa0(0xB2, 0x29, "ISKE"),	\
+	exit_code_ipa0(0xB2, 0x2a, "RRBE"),	\
+	exit_code_ipa0(0xB2, 0x2b, "SSKE"),	\
+	exit_code_ipa0(0xB2, 0x2c, "TB"),	\
+	exit_code_ipa0(0xB2, 0x2e, "PGIN"),	\
+	exit_code_ipa0(0xB2, 0x2f, "PGOUT"),	\
+	exit_code_ipa0(0xB2, 0x30, "CSCH"),	\
+	exit_code_ipa0(0xB2, 0x31, "HSCH"),	\
+	exit_code_ipa0(0xB2, 0x32, "MSCH"),	\
+	exit_code_ipa0(0xB2, 0x33, "SSCH"),	\
+	exit_code_ipa0(0xB2, 0x34, "STSCH"),	\
+	exit_code_ipa0(0xB2, 0x35, "TSCH"),	\
+	exit_code_ipa0(0xB2, 0x36, "TPI"),	\
+	exit_code_ipa0(0xB2, 0x37, "SAL"),	\
+	exit_code_ipa0(0xB2, 0x38, "RSCH"),	\
+	exit_code_ipa0(0xB2, 0x39, "STCRW"),	\
+	exit_code_ipa0(0xB2, 0x3a, "STCPS"),	\
+	exit_code_ipa0(0xB2, 0x3b, "RCHP"),	\
+	exit_code_ipa0(0xB2, 0x3c, "SCHM"),	\
+	exit_code_ipa0(0xB2, 0x40, "BAKR"),	\
+	exit_code_ipa0(0xB2, 0x48, "PALB"),	\
+	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
+	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
+	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
+	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
+	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\
+	exit_code_ipa0(0xB2, 0x74, "SIGA"),	\
+	exit_code_ipa0(0xB2, 0x76, "XSCH"),	\
+	exit_code_ipa0(0xB2, 0x78, "STCKE"),	\
+	exit_code_ipa0(0xB2, 0x7c, "STCKF"),	\
+	exit_code_ipa0(0xB2, 0x7d, "STSI"),	\
+	exit_code_ipa0(0xB2, 0xb0, "STFLE"),	\
+	exit_code_ipa0(0xB2, 0xb1, "STFL"),	\
+	exit_code_ipa0(0xB2, 0xb2, "LPSWE"),	\
+	exit_code_ipa0(0xB2, 0xf8, "TEND"),	\
+	exit_code_ipa0(0xB2, 0xfc, "TABORT"),	\
+	exit_code_ipa0(0xB9, 0x1e, "KMAC"),	\
+	exit_code_ipa0(0xB9, 0x28, "PCKMO"),	\
+	exit_code_ipa0(0xB9, 0x2a, "KMF"),	\
+	exit_code_ipa0(0xB9, 0x2b, "KMO"),	\
+	exit_code_ipa0(0xB9, 0x2d, "KMCTR"),	\
+	exit_code_ipa0(0xB9, 0x2e, "KM"),	\
+	exit_code_ipa0(0xB9, 0x2f, "KMC"),	\
+	exit_code_ipa0(0xB9, 0x3e, "KIMD"),	\
+	exit_code_ipa0(0xB9, 0x3f, "KLMD"),	\
+	exit_code_ipa0(0xB9, 0x8a, "CSPG"),	\
+	exit_code_ipa0(0xB9, 0x8d, "EPSW"),	\
+	exit_code_ipa0(0xB9, 0x8e, "IDTE"),	\
+	exit_code_ipa0(0xB9, 0x8f, "CRDTE"),	\
+	exit_code_ipa0(0xB9, 0x9c, "EQBS"),	\
+	exit_code_ipa0(0xB9, 0xa2, "PTF"),	\
+	exit_code_ipa0(0xB9, 0xab, "ESSA"),	\
+	exit_code_ipa0(0xB9, 0xae, "RRBM"),	\
+	exit_code_ipa0(0xB9, 0xaf, "PFMF"),	\
+	exit_code_ipa0(0xE3, 0x03, "LRAG"),	\
+	exit_code_ipa0(0xE3, 0x13, "LRAY"),	\
+	exit_code_ipa0(0xE3, 0x25, "NTSTG"),	\
+	exit_code_ipa0(0xE5, 0x00, "LASP"),	\
+	exit_code_ipa0(0xE5, 0x01, "TPROT"),	\
+	exit_code_ipa0(0xE5, 0x60, "TBEGIN"),	\
+	exit_code_ipa0(0xE5, 0x61, "TBEGINC"),	\
+	exit_code_ipa0(0xEB, 0x25, "STCTG"),	\
+	exit_code_ipa0(0xEB, 0x2f, "LCTLG"),	\
+	exit_code_ipa0(0xEB, 0x60, "LRIC"),	\
+	exit_code_ipa0(0xEB, 0x61, "STRIC"),	\
+	exit_code_ipa0(0xEB, 0x62, "MRIC"),	\
+	exit_code_ipa0(0xEB, 0x8a, "SQBS"),	\
+	exit_code_ipa0(0xC8, 0x01, "ECTG"),	\
+	exit_code(0x0a, "SVC"),			\
+	exit_code(0x80, "SSM"),			\
+	exit_code(0x82, "LPSW"),		\
+	exit_code(0x83, "DIAG"),		\
+	exit_code(0xae, "SIGP"),		\
+	exit_code(0xac, "STNSM"),		\
+	exit_code(0xad, "STOSM"),		\
+	exit_code(0xb1, "LRA"),			\
+	exit_code(0xb6, "STCTL"),		\
+	exit_code(0xb7, "LCTL"),		\
+	exit_code(0xee, "PLO")
+
+#define sie_intercept_code					\
+	{ 0x00, "Host interruption" },				\
+	{ 0x04, "Instruction" },				\
+	{ 0x08, "Program interruption" },			\
+	{ 0x0c, "Instruction and program interruption" },	\
+	{ 0x10, "External request" },				\
+	{ 0x14, "External interruption" },			\
+	{ 0x18, "I/O request" },				\
+	{ 0x1c, "Wait state" },					\
+	{ 0x20, "Validity" },					\
+	{ 0x28, "Stop request" },				\
+	{ 0x2c, "Operation exception" },			\
+	{ 0x38, "Partial-execution" },				\
+	{ 0x3c, "I/O interruption" },				\
+	{ 0x40, "I/O instruction" },				\
+	{ 0x48, "Timing subset" }
+
+/*
+ * This is the simple interceptable instructions decoder.
+ *
+ * It will be used as userspace interface and it can be used in places
+ * that does not allow to use general decoder functions,
+ * such as trace events declarations.
+ *
+ * Some userspace tools may want to parse this code
+ * and would be confused by switch(), if() and other statements,
+ * but they can understand conditional operator.
+ */
+#define INSN_DECODE_IPA0(ipa0, insn, rshift, mask)		\
+	(insn >> 56) == (ipa0) ?				\
+		((ipa0 << 8) | ((insn >> rshift) & mask)) :
+
+#define INSN_DECODE(insn) (insn >> 56)
+
+/*
+ * The macro icpt_insn_decoder() takes an intercepted instruction
+ * and returns a key, which can be used to find a mnemonic name
+ * of the instruction in the icpt_insn_codes table.
+ */
+#define icpt_insn_decoder(insn) (		\
+	INSN_DECODE_IPA0(0x01, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f)	\
+	INSN_DECODE_IPA0(0xb2, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xb9, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe3, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe5, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xeb, insn, 16, 0xff)	\
+	INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f)	\
+	INSN_DECODE(insn))
+
+#endif /* _UAPI_ASM_S390_SIE_H */
diff --git a/tools/arch/score/include/uapi/asm/bitsperlong.h b/tools/arch/score/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..86ff337
--- /dev/null
+++ b/tools/arch/score/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_SCORE_BITSPERLONG_H
+#define _ASM_SCORE_BITSPERLONG_H
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _ASM_SCORE_BITSPERLONG_H */
diff --git a/tools/arch/sparc/include/uapi/asm/bitsperlong.h b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..b62dd90
--- /dev/null
+++ b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_ALPHA_BITSPERLONG_H
+#define __ASM_ALPHA_BITSPERLONG_H
+
+#if defined(__sparc__) && defined(__arch64__)
+#define __BITS_PER_LONG 64
+#else
+#define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_ALPHA_BITSPERLONG_H */
diff --git a/tools/arch/tile/include/uapi/asm/bitsperlong.h b/tools/arch/tile/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..58c771f
--- /dev/null
+++ b/tools/arch/tile/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_BITSPERLONG_H
+#define _ASM_TILE_BITSPERLONG_H
+
+#ifdef __LP64__
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _ASM_TILE_BITSPERLONG_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
new file mode 100644
index 0000000..4a41348
--- /dev/null
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -0,0 +1,316 @@
+#ifndef _ASM_X86_CPUFEATURES_H
+#define _ASM_X86_CPUFEATURES_H
+
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#include <asm/required-features.h>
+#endif
+
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
+/*
+ * Defines x86 CPU feature bits
+ */
+#define NCAPINTS	18	/* N 32-bit words worth of info */
+#define NBUGINTS	1	/* N 32-bit bug flags */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#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 */
+#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
+#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+
+#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+
+/* Virtualization flags: Linux defined, word 8 */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+
+#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
+#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+
+/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
+#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
+
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x)		(NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
+
+
+#ifdef CONFIG_X86_32
+/*
+ * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
+ * to avoid confusion.
+ */
+#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#endif
+
+#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
new file mode 100644
index 0000000..911e935
--- /dev/null
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -0,0 +1,60 @@
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#define _ASM_X86_DISABLED_FEATURES_H
+
+/* These features, although they might be available in a CPU
+ * will not be used because the compile options to support
+ * them are not present.
+ *
+ * This code allows them to be checked and disabled at
+ * compile time without an explicit #ifdef.  Use
+ * cpu_feature_enabled().
+ */
+
+#ifdef CONFIG_X86_INTEL_MPX
+# define DISABLE_MPX	0
+#else
+# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
+#endif
+
+#ifdef CONFIG_X86_64
+# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
+# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
+# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
+# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
+#else
+# define DISABLE_VME		0
+# define DISABLE_K6_MTRR	0
+# define DISABLE_CYRIX_ARR	0
+# define DISABLE_CENTAUR_MCR	0
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+# define DISABLE_PKU		0
+# define DISABLE_OSPKE		0
+#else
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
+#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
+
+/*
+ * Make sure to add features to the correct mask
+ */
+#define DISABLED_MASK0	(DISABLE_VME)
+#define DISABLED_MASK1	0
+#define DISABLED_MASK2	0
+#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
+#define DISABLED_MASK4	0
+#define DISABLED_MASK5	0
+#define DISABLED_MASK6	0
+#define DISABLED_MASK7	0
+#define DISABLED_MASK8	0
+#define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK10	0
+#define DISABLED_MASK11	0
+#define DISABLED_MASK12	0
+#define DISABLED_MASK13	0
+#define DISABLED_MASK14	0
+#define DISABLED_MASK15	0
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+
+#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
new file mode 100644
index 0000000..4916144
--- /dev/null
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -0,0 +1,103 @@
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#define _ASM_X86_REQUIRED_FEATURES_H
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   Some requirements that are not in CPUID yet are also in the
+   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
+
+   The real information is in arch/x86/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+#ifndef CONFIG_MATH_EMULATION
+# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
+#else
+# define NEED_FPU	0
+#endif
+
+#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
+# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
+#else
+# define NEED_PAE	0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
+#else
+# define NEED_CX8	0
+#endif
+
+#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
+# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
+#else
+# define NEED_CMOV	0
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW	0
+#endif
+
+#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
+# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
+#else
+# define NEED_NOPL	0
+#endif
+
+#ifdef CONFIG_MATOM
+# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
+#else
+# define NEED_MOVBE	0
+#endif
+
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
+#define NEED_PSE	0
+#define NEED_PGE	0
+#else
+#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
+#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
+#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
+#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
+#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
+#else
+#define NEED_PSE	0
+#define NEED_MSR	0
+#define NEED_PGE	0
+#define NEED_FXSR	0
+#define NEED_XMM	0
+#define NEED_XMM2	0
+#define NEED_LM		0
+#endif
+
+#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
+			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
+			 NEED_XMM|NEED_XMM2)
+#define SSE_MASK	(NEED_XMM|NEED_XMM2)
+
+#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
+
+#define REQUIRED_MASK2	0
+#define REQUIRED_MASK3	(NEED_NOPL)
+#define REQUIRED_MASK4	(NEED_MOVBE)
+#define REQUIRED_MASK5	0
+#define REQUIRED_MASK6	0
+#define REQUIRED_MASK7	0
+#define REQUIRED_MASK8	0
+#define REQUIRED_MASK9	0
+#define REQUIRED_MASK10	0
+#define REQUIRED_MASK11	0
+#define REQUIRED_MASK12	0
+#define REQUIRED_MASK13	0
+#define REQUIRED_MASK14	0
+#define REQUIRED_MASK15	0
+#define REQUIRED_MASK16	0
+
+#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h
new file mode 100644
index 0000000..88b3f8c
--- /dev/null
+++ b/tools/arch/x86/include/asm/unistd_32.h
@@ -0,0 +1,12 @@
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 336
+#endif
+#ifndef __NR_futex
+# define __NR_futex 240
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 224
+#endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 318
+#endif
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
new file mode 100644
index 0000000..fbdb70e
--- /dev/null
+++ b/tools/arch/x86/include/asm/unistd_64.h
@@ -0,0 +1,12 @@
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 298
+#endif
+#ifndef __NR_futex
+# define __NR_futex 202
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 186
+#endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 309
+#endif
diff --git a/tools/arch/x86/include/uapi/asm/bitsperlong.h b/tools/arch/x86/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000..6e23c54
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_X86_BITSPERLONG_H
+#define __ASM_X86_BITSPERLONG_H
+
+#if defined(__x86_64__) && !defined(__ILP32__)
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_X86_BITSPERLONG_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..739c0c5
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -0,0 +1,360 @@
+#ifndef _ASM_X86_KVM_H
+#define _ASM_X86_KVM_H
+
+/*
+ * KVM x86 specific structures and definitions
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define DE_VECTOR 0
+#define DB_VECTOR 1
+#define BP_VECTOR 3
+#define OF_VECTOR 4
+#define BR_VECTOR 5
+#define UD_VECTOR 6
+#define NM_VECTOR 7
+#define DF_VECTOR 8
+#define TS_VECTOR 10
+#define NP_VECTOR 11
+#define SS_VECTOR 12
+#define GP_VECTOR 13
+#define PF_VECTOR 14
+#define MF_VECTOR 16
+#define AC_VECTOR 17
+#define MC_VECTOR 18
+#define XM_VECTOR 19
+#define VE_VECTOR 20
+
+/* Select x86 specific features in <linux/kvm.h> */
+#define __KVM_HAVE_PIT
+#define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_MSI
+#define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
+#define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
+#define __KVM_HAVE_DEBUGREGS
+#define __KVM_HAVE_XSAVE
+#define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+struct kvm_memory_alias {
+	__u32 slot;  /* this has a different namespace than memory slots */
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 target_phys_addr;
+};
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+	__u8 last_irr;	/* edge detection */
+	__u8 irr;		/* interrupt request register */
+	__u8 imr;		/* interrupt mask register */
+	__u8 isr;		/* interrupt service register */
+	__u8 priority_add;	/* highest irq priority */
+	__u8 irq_base;
+	__u8 read_reg_select;
+	__u8 poll;
+	__u8 special_mask;
+	__u8 init_state;
+	__u8 auto_eoi;
+	__u8 rotate_on_auto_eoi;
+	__u8 special_fully_nested_mode;
+	__u8 init4;		/* true if 4 byte init */
+	__u8 elcr;		/* PIIX edge/trigger selection */
+	__u8 elcr_mask;
+};
+
+#define KVM_IOAPIC_NUM_PINS  24
+struct kvm_ioapic_state {
+	__u64 base_address;
+	__u32 ioregsel;
+	__u32 id;
+	__u32 irr;
+	__u32 pad;
+	union {
+		__u64 bits;
+		struct {
+			__u8 vector;
+			__u8 delivery_mode:3;
+			__u8 dest_mode:1;
+			__u8 delivery_status:1;
+			__u8 polarity:1;
+			__u8 remote_irr:1;
+			__u8 trig_mode:1;
+			__u8 mask:1;
+			__u8 reserve:7;
+			__u8 reserved[4];
+			__u8 dest_id;
+		} fields;
+	} redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER   0
+#define KVM_IRQCHIP_PIC_SLAVE    1
+#define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
+
+#define KVM_RUN_X86_SMM		 (1 << 0)
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 rax, rbx, rcx, rdx;
+	__u64 rsi, rdi, rsp, rbp;
+	__u64 r8,  r9,  r10, r11;
+	__u64 r12, r13, r14, r15;
+	__u64 rip, rflags;
+};
+
+/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+	char regs[KVM_APIC_REG_SIZE];
+};
+
+struct kvm_segment {
+	__u64 base;
+	__u32 limit;
+	__u16 selector;
+	__u8  type;
+	__u8  present, dpl, db, s, l, g, avl;
+	__u8  unusable;
+	__u8  padding;
+};
+
+struct kvm_dtable {
+	__u64 base;
+	__u16 limit;
+	__u16 padding[3];
+};
+
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
+	struct kvm_segment cs, ds, es, fs, gs, ss;
+	struct kvm_segment tr, ldt;
+	struct kvm_dtable gdt, idt;
+	__u64 cr0, cr2, cr3, cr4, cr8;
+	__u64 efer;
+	__u64 apic_base;
+	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u8  fpr[8][16];
+	__u16 fcw;
+	__u16 fsw;
+	__u8  ftwx;  /* in fxsave format */
+	__u8  pad1;
+	__u16 last_opcode;
+	__u64 last_ip;
+	__u64 last_dp;
+	__u8  xmm[16][16];
+	__u32 mxcsr;
+	__u32 pad2;
+};
+
+struct kvm_msr_entry {
+	__u32 index;
+	__u32 reserved;
+	__u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 pad;
+
+	struct kvm_msr_entry entries[0];
+};
+
+/* for KVM_GET_MSR_INDEX_LIST */
+struct kvm_msr_list {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 indices[0];
+};
+
+
+struct kvm_cpuid_entry {
+	__u32 function;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		(1 << 0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		(1 << 1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		(1 << 2)
+
+/* for KVM_SET_CPUID2 */
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+/* for KVM_GET_PIT and KVM_SET_PIT */
+struct kvm_pit_channel_state {
+	__u32 count; /* can be 65536 */
+	__u16 latched_count;
+	__u8 count_latched;
+	__u8 status_latched;
+	__u8 status;
+	__u8 read_state;
+	__u8 write_state;
+	__u8 write_latch;
+	__u8 rw_mode;
+	__u8 mode;
+	__u8 bcd;
+	__u8 gate;
+	__s64 count_load_time;
+};
+
+struct kvm_debug_exit_arch {
+	__u32 exception;
+	__u32 pad;
+	__u64 pc;
+	__u64 dr6;
+	__u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+#define KVM_GUESTDBG_INJECT_DB		0x00040000
+#define KVM_GUESTDBG_INJECT_BP		0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u64 debugreg[8];
+};
+
+struct kvm_pit_state {
+	struct kvm_pit_channel_state channels[3];
+};
+
+#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+
+struct kvm_pit_state2 {
+	struct kvm_pit_channel_state channels[3];
+	__u32 flags;
+	__u32 reserved[9];
+};
+
+struct kvm_reinject_control {
+	__u8 pit_reinject;
+	__u8 reserved[31];
+};
+
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+#define KVM_VCPUEVENT_VALID_SMM		0x00000008
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS	0x01
+#define KVM_X86_SHADOW_INT_STI		0x02
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 shadow;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+	__u32 flags;
+	struct {
+		__u8 smm;
+		__u8 pending;
+		__u8 smm_inside_nmi;
+		__u8 latched_init;
+	} smi;
+	__u32 reserved[9];
+};
+
+/* for KVM_GET/SET_DEBUGREGS */
+struct kvm_debugregs {
+	__u64 db[4];
+	__u64 dr6;
+	__u64 dr7;
+	__u64 flags;
+	__u64 reserved[9];
+};
+
+/* for KVM_CAP_XSAVE */
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+#define KVM_MAX_XCRS	16
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+
+#endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm_perf.h b/tools/arch/x86/include/uapi/asm/kvm_perf.h
new file mode 100644
index 0000000..3bb964f
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_KVM_PERF_H
+#define _ASM_X86_KVM_PERF_H
+
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+#define DECODE_STR_LEN 20
+
+#define VCPU_ID "vcpu_id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_entry"
+#define KVM_EXIT_TRACE "kvm:kvm_exit"
+#define KVM_EXIT_REASON "exit_reason"
+
+#endif /* _ASM_X86_KVM_PERF_H */
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..3f2207b
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+	PERF_REG_X86_AX,
+	PERF_REG_X86_BX,
+	PERF_REG_X86_CX,
+	PERF_REG_X86_DX,
+	PERF_REG_X86_SI,
+	PERF_REG_X86_DI,
+	PERF_REG_X86_BP,
+	PERF_REG_X86_SP,
+	PERF_REG_X86_IP,
+	PERF_REG_X86_FLAGS,
+	PERF_REG_X86_CS,
+	PERF_REG_X86_SS,
+	PERF_REG_X86_DS,
+	PERF_REG_X86_ES,
+	PERF_REG_X86_FS,
+	PERF_REG_X86_GS,
+	PERF_REG_X86_R8,
+	PERF_REG_X86_R9,
+	PERF_REG_X86_R10,
+	PERF_REG_X86_R11,
+	PERF_REG_X86_R12,
+	PERF_REG_X86_R13,
+	PERF_REG_X86_R14,
+	PERF_REG_X86_R15,
+
+	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
new file mode 100644
index 0000000..3725e14
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -0,0 +1,178 @@
+#ifndef _UAPI__SVM_H
+#define _UAPI__SVM_H
+
+#define SVM_EXIT_READ_CR0      0x000
+#define SVM_EXIT_READ_CR2      0x002
+#define SVM_EXIT_READ_CR3      0x003
+#define SVM_EXIT_READ_CR4      0x004
+#define SVM_EXIT_READ_CR8      0x008
+#define SVM_EXIT_WRITE_CR0     0x010
+#define SVM_EXIT_WRITE_CR2     0x012
+#define SVM_EXIT_WRITE_CR3     0x013
+#define SVM_EXIT_WRITE_CR4     0x014
+#define SVM_EXIT_WRITE_CR8     0x018
+#define SVM_EXIT_READ_DR0      0x020
+#define SVM_EXIT_READ_DR1      0x021
+#define SVM_EXIT_READ_DR2      0x022
+#define SVM_EXIT_READ_DR3      0x023
+#define SVM_EXIT_READ_DR4      0x024
+#define SVM_EXIT_READ_DR5      0x025
+#define SVM_EXIT_READ_DR6      0x026
+#define SVM_EXIT_READ_DR7      0x027
+#define SVM_EXIT_WRITE_DR0     0x030
+#define SVM_EXIT_WRITE_DR1     0x031
+#define SVM_EXIT_WRITE_DR2     0x032
+#define SVM_EXIT_WRITE_DR3     0x033
+#define SVM_EXIT_WRITE_DR4     0x034
+#define SVM_EXIT_WRITE_DR5     0x035
+#define SVM_EXIT_WRITE_DR6     0x036
+#define SVM_EXIT_WRITE_DR7     0x037
+#define SVM_EXIT_EXCP_BASE     0x040
+#define SVM_EXIT_INTR          0x060
+#define SVM_EXIT_NMI           0x061
+#define SVM_EXIT_SMI           0x062
+#define SVM_EXIT_INIT          0x063
+#define SVM_EXIT_VINTR         0x064
+#define SVM_EXIT_CR0_SEL_WRITE 0x065
+#define SVM_EXIT_IDTR_READ     0x066
+#define SVM_EXIT_GDTR_READ     0x067
+#define SVM_EXIT_LDTR_READ     0x068
+#define SVM_EXIT_TR_READ       0x069
+#define SVM_EXIT_IDTR_WRITE    0x06a
+#define SVM_EXIT_GDTR_WRITE    0x06b
+#define SVM_EXIT_LDTR_WRITE    0x06c
+#define SVM_EXIT_TR_WRITE      0x06d
+#define SVM_EXIT_RDTSC         0x06e
+#define SVM_EXIT_RDPMC         0x06f
+#define SVM_EXIT_PUSHF         0x070
+#define SVM_EXIT_POPF          0x071
+#define SVM_EXIT_CPUID         0x072
+#define SVM_EXIT_RSM           0x073
+#define SVM_EXIT_IRET          0x074
+#define SVM_EXIT_SWINT         0x075
+#define SVM_EXIT_INVD          0x076
+#define SVM_EXIT_PAUSE         0x077
+#define SVM_EXIT_HLT           0x078
+#define SVM_EXIT_INVLPG        0x079
+#define SVM_EXIT_INVLPGA       0x07a
+#define SVM_EXIT_IOIO          0x07b
+#define SVM_EXIT_MSR           0x07c
+#define SVM_EXIT_TASK_SWITCH   0x07d
+#define SVM_EXIT_FERR_FREEZE   0x07e
+#define SVM_EXIT_SHUTDOWN      0x07f
+#define SVM_EXIT_VMRUN         0x080
+#define SVM_EXIT_VMMCALL       0x081
+#define SVM_EXIT_VMLOAD        0x082
+#define SVM_EXIT_VMSAVE        0x083
+#define SVM_EXIT_STGI          0x084
+#define SVM_EXIT_CLGI          0x085
+#define SVM_EXIT_SKINIT        0x086
+#define SVM_EXIT_RDTSCP        0x087
+#define SVM_EXIT_ICEBP         0x088
+#define SVM_EXIT_WBINVD        0x089
+#define SVM_EXIT_MONITOR       0x08a
+#define SVM_EXIT_MWAIT         0x08b
+#define SVM_EXIT_MWAIT_COND    0x08c
+#define SVM_EXIT_XSETBV        0x08d
+#define SVM_EXIT_NPF           0x400
+#define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
+#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
+
+#define SVM_EXIT_ERR           -1
+
+#define SVM_EXIT_REASONS \
+	{ SVM_EXIT_READ_CR0,    "read_cr0" }, \
+	{ SVM_EXIT_READ_CR2,    "read_cr2" }, \
+	{ SVM_EXIT_READ_CR3,    "read_cr3" }, \
+	{ SVM_EXIT_READ_CR4,    "read_cr4" }, \
+	{ SVM_EXIT_READ_CR8,    "read_cr8" }, \
+	{ SVM_EXIT_WRITE_CR0,   "write_cr0" }, \
+	{ SVM_EXIT_WRITE_CR2,   "write_cr2" }, \
+	{ SVM_EXIT_WRITE_CR3,   "write_cr3" }, \
+	{ SVM_EXIT_WRITE_CR4,   "write_cr4" }, \
+	{ SVM_EXIT_WRITE_CR8,   "write_cr8" }, \
+	{ SVM_EXIT_READ_DR0,    "read_dr0" }, \
+	{ SVM_EXIT_READ_DR1,    "read_dr1" }, \
+	{ SVM_EXIT_READ_DR2,    "read_dr2" }, \
+	{ SVM_EXIT_READ_DR3,    "read_dr3" }, \
+	{ SVM_EXIT_READ_DR4,    "read_dr4" }, \
+	{ SVM_EXIT_READ_DR5,    "read_dr5" }, \
+	{ SVM_EXIT_READ_DR6,    "read_dr6" }, \
+	{ SVM_EXIT_READ_DR7,    "read_dr7" }, \
+	{ SVM_EXIT_WRITE_DR0,   "write_dr0" }, \
+	{ SVM_EXIT_WRITE_DR1,   "write_dr1" }, \
+	{ SVM_EXIT_WRITE_DR2,   "write_dr2" }, \
+	{ SVM_EXIT_WRITE_DR3,   "write_dr3" }, \
+	{ SVM_EXIT_WRITE_DR4,   "write_dr4" }, \
+	{ SVM_EXIT_WRITE_DR5,   "write_dr5" }, \
+	{ SVM_EXIT_WRITE_DR6,   "write_dr6" }, \
+	{ SVM_EXIT_WRITE_DR7,   "write_dr7" }, \
+	{ SVM_EXIT_EXCP_BASE + DE_VECTOR,       "DE excp" }, \
+	{ SVM_EXIT_EXCP_BASE + DB_VECTOR,       "DB excp" }, \
+	{ SVM_EXIT_EXCP_BASE + BP_VECTOR,       "BP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + OF_VECTOR,       "OF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + BR_VECTOR,       "BR excp" }, \
+	{ SVM_EXIT_EXCP_BASE + UD_VECTOR,       "UD excp" }, \
+	{ SVM_EXIT_EXCP_BASE + NM_VECTOR,       "NM excp" }, \
+	{ SVM_EXIT_EXCP_BASE + DF_VECTOR,       "DF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + TS_VECTOR,       "TS excp" }, \
+	{ SVM_EXIT_EXCP_BASE + NP_VECTOR,       "NP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + SS_VECTOR,       "SS excp" }, \
+	{ SVM_EXIT_EXCP_BASE + GP_VECTOR,       "GP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + PF_VECTOR,       "PF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + MF_VECTOR,       "MF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + AC_VECTOR,       "AC excp" }, \
+	{ SVM_EXIT_EXCP_BASE + MC_VECTOR,       "MC excp" }, \
+	{ SVM_EXIT_EXCP_BASE + XM_VECTOR,       "XF excp" }, \
+	{ SVM_EXIT_INTR,        "interrupt" }, \
+	{ SVM_EXIT_NMI,         "nmi" }, \
+	{ SVM_EXIT_SMI,         "smi" }, \
+	{ SVM_EXIT_INIT,        "init" }, \
+	{ SVM_EXIT_VINTR,       "vintr" }, \
+	{ SVM_EXIT_CR0_SEL_WRITE, "cr0_sel_write" }, \
+	{ SVM_EXIT_IDTR_READ,   "read_idtr" }, \
+	{ SVM_EXIT_GDTR_READ,   "read_gdtr" }, \
+	{ SVM_EXIT_LDTR_READ,   "read_ldtr" }, \
+	{ SVM_EXIT_TR_READ,     "read_rt" }, \
+	{ SVM_EXIT_IDTR_WRITE,  "write_idtr" }, \
+	{ SVM_EXIT_GDTR_WRITE,  "write_gdtr" }, \
+	{ SVM_EXIT_LDTR_WRITE,  "write_ldtr" }, \
+	{ SVM_EXIT_TR_WRITE,    "write_rt" }, \
+	{ SVM_EXIT_RDTSC,       "rdtsc" }, \
+	{ SVM_EXIT_RDPMC,       "rdpmc" }, \
+	{ SVM_EXIT_PUSHF,       "pushf" }, \
+	{ SVM_EXIT_POPF,        "popf" }, \
+	{ SVM_EXIT_CPUID,       "cpuid" }, \
+	{ SVM_EXIT_RSM,         "rsm" }, \
+	{ SVM_EXIT_IRET,        "iret" }, \
+	{ SVM_EXIT_SWINT,       "swint" }, \
+	{ SVM_EXIT_INVD,        "invd" }, \
+	{ SVM_EXIT_PAUSE,       "pause" }, \
+	{ SVM_EXIT_HLT,         "hlt" }, \
+	{ SVM_EXIT_INVLPG,      "invlpg" }, \
+	{ SVM_EXIT_INVLPGA,     "invlpga" }, \
+	{ SVM_EXIT_IOIO,        "io" }, \
+	{ SVM_EXIT_MSR,         "msr" }, \
+	{ SVM_EXIT_TASK_SWITCH, "task_switch" }, \
+	{ SVM_EXIT_FERR_FREEZE, "ferr_freeze" }, \
+	{ SVM_EXIT_SHUTDOWN,    "shutdown" }, \
+	{ SVM_EXIT_VMRUN,       "vmrun" }, \
+	{ SVM_EXIT_VMMCALL,     "hypercall" }, \
+	{ SVM_EXIT_VMLOAD,      "vmload" }, \
+	{ SVM_EXIT_VMSAVE,      "vmsave" }, \
+	{ SVM_EXIT_STGI,        "stgi" }, \
+	{ SVM_EXIT_CLGI,        "clgi" }, \
+	{ SVM_EXIT_SKINIT,      "skinit" }, \
+	{ SVM_EXIT_RDTSCP,      "rdtscp" }, \
+	{ SVM_EXIT_ICEBP,       "icebp" }, \
+	{ SVM_EXIT_WBINVD,      "wbinvd" }, \
+	{ SVM_EXIT_MONITOR,     "monitor" }, \
+	{ SVM_EXIT_MWAIT,       "mwait" }, \
+	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_NPF,         "npf" }, \
+	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
+	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
+	{ SVM_EXIT_ERR,         "invalid_guest_state" }
+
+
+#endif /* _UAPI__SVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
new file mode 100644
index 0000000..5b15d94
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -0,0 +1,136 @@
+/*
+ * vmx.h: VMX Architecture related definitions
+ * Copyright (c) 2004, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * A few random additions are:
+ * Copyright (C) 2006 Qumranet
+ *    Avi Kivity <avi@qumranet.com>
+ *    Yaniv Kamay <yaniv@qumranet.com>
+ *
+ */
+#ifndef _UAPIVMX_H
+#define _UAPIVMX_H
+
+
+#define VMX_EXIT_REASONS_FAILED_VMENTRY         0x80000000
+
+#define EXIT_REASON_EXCEPTION_NMI       0
+#define EXIT_REASON_EXTERNAL_INTERRUPT  1
+#define EXIT_REASON_TRIPLE_FAULT        2
+
+#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_NMI_WINDOW          8
+#define EXIT_REASON_TASK_SWITCH         9
+#define EXIT_REASON_CPUID               10
+#define EXIT_REASON_HLT                 12
+#define EXIT_REASON_INVD                13
+#define EXIT_REASON_INVLPG              14
+#define EXIT_REASON_RDPMC               15
+#define EXIT_REASON_RDTSC               16
+#define EXIT_REASON_VMCALL              18
+#define EXIT_REASON_VMCLEAR             19
+#define EXIT_REASON_VMLAUNCH            20
+#define EXIT_REASON_VMPTRLD             21
+#define EXIT_REASON_VMPTRST             22
+#define EXIT_REASON_VMREAD              23
+#define EXIT_REASON_VMRESUME            24
+#define EXIT_REASON_VMWRITE             25
+#define EXIT_REASON_VMOFF               26
+#define EXIT_REASON_VMON                27
+#define EXIT_REASON_CR_ACCESS           28
+#define EXIT_REASON_DR_ACCESS           29
+#define EXIT_REASON_IO_INSTRUCTION      30
+#define EXIT_REASON_MSR_READ            31
+#define EXIT_REASON_MSR_WRITE           32
+#define EXIT_REASON_INVALID_STATE       33
+#define EXIT_REASON_MSR_LOAD_FAIL       34
+#define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_TRAP_FLAG   37
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION   40
+#define EXIT_REASON_MCE_DURING_VMENTRY  41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EOI_INDUCED         45
+#define EXIT_REASON_EPT_VIOLATION       48
+#define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT              50
+#define EXIT_REASON_RDTSCP              51
+#define EXIT_REASON_PREEMPTION_TIMER    52
+#define EXIT_REASON_INVVPID             53
+#define EXIT_REASON_WBINVD              54
+#define EXIT_REASON_XSETBV              55
+#define EXIT_REASON_APIC_WRITE          56
+#define EXIT_REASON_INVPCID             58
+#define EXIT_REASON_PML_FULL            62
+#define EXIT_REASON_XSAVES              63
+#define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_PCOMMIT             65
+
+#define VMX_EXIT_REASONS \
+	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
+	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
+	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
+	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
+	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
+	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
+	{ EXIT_REASON_CPUID,                 "CPUID" }, \
+	{ EXIT_REASON_HLT,                   "HLT" }, \
+	{ EXIT_REASON_INVLPG,                "INVLPG" }, \
+	{ EXIT_REASON_RDPMC,                 "RDPMC" }, \
+	{ EXIT_REASON_RDTSC,                 "RDTSC" }, \
+	{ EXIT_REASON_VMCALL,                "VMCALL" }, \
+	{ EXIT_REASON_VMCLEAR,               "VMCLEAR" }, \
+	{ EXIT_REASON_VMLAUNCH,              "VMLAUNCH" }, \
+	{ EXIT_REASON_VMPTRLD,               "VMPTRLD" }, \
+	{ EXIT_REASON_VMPTRST,               "VMPTRST" }, \
+	{ EXIT_REASON_VMREAD,                "VMREAD" }, \
+	{ EXIT_REASON_VMRESUME,              "VMRESUME" }, \
+	{ EXIT_REASON_VMWRITE,               "VMWRITE" }, \
+	{ EXIT_REASON_VMOFF,                 "VMOFF" }, \
+	{ EXIT_REASON_VMON,                  "VMON" }, \
+	{ EXIT_REASON_CR_ACCESS,             "CR_ACCESS" }, \
+	{ EXIT_REASON_DR_ACCESS,             "DR_ACCESS" }, \
+	{ EXIT_REASON_IO_INSTRUCTION,        "IO_INSTRUCTION" }, \
+	{ EXIT_REASON_MSR_READ,              "MSR_READ" }, \
+	{ EXIT_REASON_MSR_WRITE,             "MSR_WRITE" }, \
+	{ EXIT_REASON_MWAIT_INSTRUCTION,     "MWAIT_INSTRUCTION" }, \
+	{ EXIT_REASON_MONITOR_TRAP_FLAG,     "MONITOR_TRAP_FLAG" }, \
+	{ EXIT_REASON_MONITOR_INSTRUCTION,   "MONITOR_INSTRUCTION" }, \
+	{ EXIT_REASON_PAUSE_INSTRUCTION,     "PAUSE_INSTRUCTION" }, \
+	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
+	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
+	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
+	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
+	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
+	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
+	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }, \
+	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
+	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
+	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
+	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
+	{ EXIT_REASON_INVD,                  "INVD" }, \
+	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
+	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
+	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
+
+#define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
+
+#endif /* _UAPIVMX_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
new file mode 100644
index 0000000..2ec0b0abb
--- /dev/null
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -0,0 +1,297 @@
+/* Copyright 2002 Andi Kleen */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+
+/*
+ * We build a jump to memcpy_orig by default which gets NOPped out on
+ * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
+ * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
+ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
+ */
+
+.weak memcpy
+
+/*
+ * memcpy - Copy a memory block.
+ *
+ * Input:
+ *  rdi destination
+ *  rsi source
+ *  rdx count
+ *
+ * Output:
+ * rax original destination
+ */
+ENTRY(__memcpy)
+ENTRY(memcpy)
+	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
+		      "jmp memcpy_erms", X86_FEATURE_ERMS
+
+	movq %rdi, %rax
+	movq %rdx, %rcx
+	shrq $3, %rcx
+	andl $7, %edx
+	rep movsq
+	movl %edx, %ecx
+	rep movsb
+	ret
+ENDPROC(memcpy)
+ENDPROC(__memcpy)
+
+/*
+ * memcpy_erms() - enhanced fast string memcpy. This is faster and
+ * simpler than memcpy. Use memcpy_erms when possible.
+ */
+ENTRY(memcpy_erms)
+	movq %rdi, %rax
+	movq %rdx, %rcx
+	rep movsb
+	ret
+ENDPROC(memcpy_erms)
+
+ENTRY(memcpy_orig)
+	movq %rdi, %rax
+
+	cmpq $0x20, %rdx
+	jb .Lhandle_tail
+
+	/*
+	 * We check whether memory false dependence could occur,
+	 * then jump to corresponding copy mode.
+	 */
+	cmp  %dil, %sil
+	jl .Lcopy_backward
+	subq $0x20, %rdx
+.Lcopy_forward_loop:
+	subq $0x20,	%rdx
+
+	/*
+	 * Move in blocks of 4x8 bytes:
+	 */
+	movq 0*8(%rsi),	%r8
+	movq 1*8(%rsi),	%r9
+	movq 2*8(%rsi),	%r10
+	movq 3*8(%rsi),	%r11
+	leaq 4*8(%rsi),	%rsi
+
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	2*8(%rdi)
+	movq %r11,	3*8(%rdi)
+	leaq 4*8(%rdi),	%rdi
+	jae  .Lcopy_forward_loop
+	addl $0x20,	%edx
+	jmp  .Lhandle_tail
+
+.Lcopy_backward:
+	/*
+	 * Calculate copy position to tail.
+	 */
+	addq %rdx,	%rsi
+	addq %rdx,	%rdi
+	subq $0x20,	%rdx
+	/*
+	 * At most 3 ALU operations in one cycle,
+	 * so append NOPS in the same 16 bytes trunk.
+	 */
+	.p2align 4
+.Lcopy_backward_loop:
+	subq $0x20,	%rdx
+	movq -1*8(%rsi),	%r8
+	movq -2*8(%rsi),	%r9
+	movq -3*8(%rsi),	%r10
+	movq -4*8(%rsi),	%r11
+	leaq -4*8(%rsi),	%rsi
+	movq %r8,		-1*8(%rdi)
+	movq %r9,		-2*8(%rdi)
+	movq %r10,		-3*8(%rdi)
+	movq %r11,		-4*8(%rdi)
+	leaq -4*8(%rdi),	%rdi
+	jae  .Lcopy_backward_loop
+
+	/*
+	 * Calculate copy position to head.
+	 */
+	addl $0x20,	%edx
+	subq %rdx,	%rsi
+	subq %rdx,	%rdi
+.Lhandle_tail:
+	cmpl $16,	%edx
+	jb   .Lless_16bytes
+
+	/*
+	 * Move data from 16 bytes to 31 bytes.
+	 */
+	movq 0*8(%rsi), %r8
+	movq 1*8(%rsi),	%r9
+	movq -2*8(%rsi, %rdx),	%r10
+	movq -1*8(%rsi, %rdx),	%r11
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	-2*8(%rdi, %rdx)
+	movq %r11,	-1*8(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_16bytes:
+	cmpl $8,	%edx
+	jb   .Lless_8bytes
+	/*
+	 * Move data from 8 bytes to 15 bytes.
+	 */
+	movq 0*8(%rsi),	%r8
+	movq -1*8(%rsi, %rdx),	%r9
+	movq %r8,	0*8(%rdi)
+	movq %r9,	-1*8(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_8bytes:
+	cmpl $4,	%edx
+	jb   .Lless_3bytes
+
+	/*
+	 * Move data from 4 bytes to 7 bytes.
+	 */
+	movl (%rsi), %ecx
+	movl -4(%rsi, %rdx), %r8d
+	movl %ecx, (%rdi)
+	movl %r8d, -4(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_3bytes:
+	subl $1, %edx
+	jb .Lend
+	/*
+	 * Move data from 1 bytes to 3 bytes.
+	 */
+	movzbl (%rsi), %ecx
+	jz .Lstore_1byte
+	movzbq 1(%rsi), %r8
+	movzbq (%rsi, %rdx), %r9
+	movb %r8b, 1(%rdi)
+	movb %r9b, (%rdi, %rdx)
+.Lstore_1byte:
+	movb %cl, (%rdi)
+
+.Lend:
+	retq
+ENDPROC(memcpy_orig)
+
+#ifndef CONFIG_UML
+/*
+ * memcpy_mcsafe - memory copy with machine check exception handling
+ * Note that we only catch machine checks when reading the source addresses.
+ * Writes to target are posted and don't generate machine checks.
+ */
+ENTRY(memcpy_mcsafe)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_copy_leading_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_leading_bytes
+
+.L_8byte_aligned:
+	/* Figure out how many whole cache lines (64-bytes) to copy */
+	movl %edx, %ecx
+	andl $63, %edx
+	shrl $6, %ecx
+	jz .L_no_whole_cache_lines
+
+	/* Loop copying whole cache lines */
+.L_cache_w0: movq (%rsi), %r8
+.L_cache_w1: movq 1*8(%rsi), %r9
+.L_cache_w2: movq 2*8(%rsi), %r10
+.L_cache_w3: movq 3*8(%rsi), %r11
+	movq %r8, (%rdi)
+	movq %r9, 1*8(%rdi)
+	movq %r10, 2*8(%rdi)
+	movq %r11, 3*8(%rdi)
+.L_cache_w4: movq 4*8(%rsi), %r8
+.L_cache_w5: movq 5*8(%rsi), %r9
+.L_cache_w6: movq 6*8(%rsi), %r10
+.L_cache_w7: movq 7*8(%rsi), %r11
+	movq %r8, 4*8(%rdi)
+	movq %r9, 5*8(%rdi)
+	movq %r10, 6*8(%rdi)
+	movq %r11, 7*8(%rdi)
+	leaq 64(%rsi), %rsi
+	leaq 64(%rdi), %rdi
+	decl %ecx
+	jnz .L_cache_w0
+
+	/* Are there any trailing 8-byte words? */
+.L_no_whole_cache_lines:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+	/* Copy trailing words */
+.L_copy_trailing_words:
+	movq (%rsi), %r8
+	mov %r8, (%rdi)
+	leaq 8(%rsi), %rsi
+	leaq 8(%rdi), %rdi
+	decl %ecx
+	jnz .L_copy_trailing_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_copy_trailing_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_trailing_bytes
+
+	/* Copy successful. Return zero */
+.L_done_memcpy_trap:
+	xorq %rax, %rax
+	ret
+ENDPROC(memcpy_mcsafe)
+
+	.section .fixup, "ax"
+	/* Return -EFAULT for any failure */
+.L_memcpy_mcsafe_fail:
+	mov	$-EFAULT, %rax
+	ret
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+#endif
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
new file mode 100644
index 0000000..e1229ec
--- /dev/null
+++ b/tools/arch/x86/lib/memset_64.S
@@ -0,0 +1,138 @@
+/* Copyright 2002 Andi Kleen, SuSE Labs */
+
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+
+.weak memset
+
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the original function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+ENTRY(memset)
+ENTRY(__memset)
+	/*
+	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
+	 * to use it when possible. If not available, use fast string instructions.
+	 *
+	 * Otherwise, use original memset function.
+	 */
+	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
+		      "jmp memset_erms", X86_FEATURE_ERMS
+
+	movq %rdi,%r9
+	movq %rdx,%rcx
+	andl $7,%edx
+	shrq $3,%rcx
+	/* expand byte value  */
+	movzbl %sil,%esi
+	movabs $0x0101010101010101,%rax
+	imulq %rsi,%rax
+	rep stosq
+	movl %edx,%ecx
+	rep stosb
+	movq %r9,%rax
+	ret
+ENDPROC(memset)
+ENDPROC(__memset)
+
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+ENTRY(memset_erms)
+	movq %rdi,%r9
+	movb %sil,%al
+	movq %rdx,%rcx
+	rep stosb
+	movq %r9,%rax
+	ret
+ENDPROC(memset_erms)
+
+ENTRY(memset_orig)
+	movq %rdi,%r10
+
+	/* expand byte value  */
+	movzbl %sil,%ecx
+	movabs $0x0101010101010101,%rax
+	imulq  %rcx,%rax
+
+	/* align dst */
+	movl  %edi,%r9d
+	andl  $7,%r9d
+	jnz  .Lbad_alignment
+.Lafter_bad_alignment:
+
+	movq  %rdx,%rcx
+	shrq  $6,%rcx
+	jz	 .Lhandle_tail
+
+	.p2align 4
+.Lloop_64:
+	decq  %rcx
+	movq  %rax,(%rdi)
+	movq  %rax,8(%rdi)
+	movq  %rax,16(%rdi)
+	movq  %rax,24(%rdi)
+	movq  %rax,32(%rdi)
+	movq  %rax,40(%rdi)
+	movq  %rax,48(%rdi)
+	movq  %rax,56(%rdi)
+	leaq  64(%rdi),%rdi
+	jnz    .Lloop_64
+
+	/* Handle tail in loops. The loops should be faster than hard
+	   to predict jump tables. */
+	.p2align 4
+.Lhandle_tail:
+	movl	%edx,%ecx
+	andl    $63&(~7),%ecx
+	jz 		.Lhandle_7
+	shrl	$3,%ecx
+	.p2align 4
+.Lloop_8:
+	decl   %ecx
+	movq  %rax,(%rdi)
+	leaq  8(%rdi),%rdi
+	jnz    .Lloop_8
+
+.Lhandle_7:
+	andl	$7,%edx
+	jz      .Lende
+	.p2align 4
+.Lloop_1:
+	decl    %edx
+	movb 	%al,(%rdi)
+	leaq	1(%rdi),%rdi
+	jnz     .Lloop_1
+
+.Lende:
+	movq	%r10,%rax
+	ret
+
+.Lbad_alignment:
+	cmpq $7,%rdx
+	jbe	.Lhandle_7
+	movq %rax,(%rdi)	/* unaligned store */
+	movq $8,%r8
+	subq %r9,%r8
+	addq %r8,%rdi
+	subq %r8,%rdx
+	jmp .Lafter_bad_alignment
+.Lfinal:
+ENDPROC(memset_orig)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 57c8f98..a120c6b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -40,6 +40,8 @@ FEATURE_TESTS_BASIC :=			\
 	libbfd				\
 	libelf				\
 	libelf-getphdrnum		\
+	libelf-gelf_getnote		\
+	libelf-getshdrstrndx		\
 	libelf-mmap			\
 	libnuma				\
 	numa_num_possible_cpus		\
@@ -60,7 +62,8 @@ FEATURE_TESTS_BASIC :=			\
 	zlib				\
 	lzma				\
 	get_cpuid			\
-	bpf
+	bpf				\
+	sdt
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 3d88f09..a0b29a3 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -17,6 +17,8 @@ FILES=					\
 	test-cplus-demangle.bin		\
 	test-libelf.bin			\
 	test-libelf-getphdrnum.bin	\
+	test-libelf-gelf_getnote.bin	\
+	test-libelf-getshdrstrndx.bin	\
 	test-libelf-mmap.bin		\
 	test-libnuma.bin		\
 	test-numa_num_possible_cpus.bin	\
@@ -43,7 +45,8 @@ FILES=					\
 	test-zlib.bin			\
 	test-lzma.bin			\
 	test-bpf.bin			\
-	test-get_cpuid.bin
+	test-get_cpuid.bin		\
+	test-sdt.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -98,6 +101,12 @@ $(OUTPUT)test-libelf-mmap.bin:
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-libelf-gelf_getnote.bin:
+	$(BUILD) -lelf
+
+$(OUTPUT)test-libelf-getshdrstrndx.bin:
+	$(BUILD) -lelf
+
 $(OUTPUT)test-libnuma.bin:
 	$(BUILD) -lnuma
 
@@ -205,6 +214,9 @@ $(OUTPUT)test-get_cpuid.bin:
 $(OUTPUT)test-bpf.bin:
 	$(BUILD)
 
+$(OUTPUT)test-sdt.bin:
+	$(BUILD)
+
 -include $(OUTPUT)*.d
 
 ###############################
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index a282e8c..699e436 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -49,6 +49,14 @@
 # include "test-libelf-getphdrnum.c"
 #undef main
 
+#define main main_test_libelf_gelf_getnote
+# include "test-libelf-gelf_getnote.c"
+#undef main
+
+#define main main_test_libelf_getshdrstrndx
+# include "test-libelf-getshdrstrndx.c"
+#undef main
+
 #define main main_test_libunwind
 # include "test-libunwind.c"
 #undef main
@@ -137,6 +145,10 @@
 # include "test-libcrypto.c"
 #undef main
 
+#define main main_test_sdt
+# include "test-sdt.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -149,6 +161,8 @@ int main(int argc, char *argv[])
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
 	main_test_libelf_getphdrnum();
+	main_test_libelf_gelf_getnote();
+	main_test_libelf_getshdrstrndx();
 	main_test_libunwind();
 	main_test_libaudit();
 	main_test_libslang();
@@ -168,6 +182,7 @@ int main(int argc, char *argv[])
 	main_test_get_cpuid();
 	main_test_bpf();
 	main_test_libcrypto();
+	main_test_sdt();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-libelf-gelf_getnote.c b/tools/build/feature/test-libelf-gelf_getnote.c
new file mode 100644
index 0000000..d78cf4d
--- /dev/null
+++ b/tools/build/feature/test-libelf-gelf_getnote.c
@@ -0,0 +1,7 @@
+#include <stdlib.h>
+#include <gelf.h>
+
+int main(void)
+{
+	return gelf_getnote(NULL, 0, NULL, NULL, NULL);
+}
diff --git a/tools/build/feature/test-libelf-getshdrstrndx.c b/tools/build/feature/test-libelf-getshdrstrndx.c
new file mode 100644
index 0000000..f0c3b47
--- /dev/null
+++ b/tools/build/feature/test-libelf-getshdrstrndx.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+	size_t dst;
+
+	return elf_getshdrstrndx(0, &dst);
+}
diff --git a/tools/build/feature/test-sdt.c b/tools/build/feature/test-sdt.c
new file mode 100644
index 0000000..e4531a6
--- /dev/null
+++ b/tools/build/feature/test-sdt.c
@@ -0,0 +1,7 @@
+#include <sys/sdt.h>
+
+int main(void)
+{
+	DTRACE_PROBE(provider, name);
+	return 0;
+}
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
index c941750..b3accfd 100644
--- a/tools/include/asm-generic/bitops/__ffs.h
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 /**
  * __ffs - find first bit in word.
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index 494c9c6..a60a7cc 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1 +1,43 @@
-#include "../../../../include/asm-generic/bitops/__fls.h"
+#ifndef _ASM_GENERIC_BITOPS___FLS_H_
+#define _ASM_GENERIC_BITOPS___FLS_H_
+
+#include <asm/types.h>
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+	int num = BITS_PER_LONG - 1;
+
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-1))))
+		num -= 1;
+	return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
index 318bb2b..6a211f4 100644
--- a/tools/include/asm-generic/bitops/arch_hweight.h
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -1 +1,25 @@
-#include "../../../../include/asm-generic/bitops/arch_hweight.h"
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 4bccd7c3..18663f5 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
index 0afd644..0a7e066 100644
--- a/tools/include/asm-generic/bitops/const_hweight.h
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -1 +1,43 @@
-#include "../../../../include/asm-generic/bitops/const_hweight.h"
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)		\
+	((unsigned int)			\
+	 ((!!((w) & (1ULL << 0))) +	\
+	  (!!((w) & (1ULL << 1))) +	\
+	  (!!((w) & (1ULL << 2))) +	\
+	  (!!((w) & (1ULL << 3))) +	\
+	  (!!((w) & (1ULL << 4))) +	\
+	  (!!((w) & (1ULL << 5))) +	\
+	  (!!((w) & (1ULL << 6))) +	\
+	  (!!((w) & (1ULL << 7)))))
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 0e4995f..0576d1f 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1 +1,41 @@
-#include "../../../../include/asm-generic/bitops/fls.h"
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __always_inline int fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index 35bee00..b097cf8 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1 +1,36 @@
-#include "../../../../include/asm-generic/bitops/fls64.h"
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#if BITS_PER_LONG == 32
+static __always_inline int fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(h) + 32;
+	return fls(x);
+}
+#elif BITS_PER_LONG == 64
+static __always_inline int fls64(__u64 x)
+{
+	if (x == 0)
+		return 0;
+	return __fls(x) + 1;
+}
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
new file mode 100644
index 0000000..45eca51
--- /dev/null
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+#ifdef __SIZEOF_LONG__
+#define BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__)
+#else
+#define BITS_PER_LONG __WORDSIZE
+#endif
+
+#if BITS_PER_LONG != __BITS_PER_LONG
+#error Inconsistent word size. Check asm/bitsperlong.h
+#endif
+
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/include/asm/alternative-asm.h
index 3a3a0f1..2a4d1bf 100644
--- a/tools/perf/util/include/asm/alternative-asm.h
+++ b/tools/include/asm/alternative-asm.h
@@ -1,5 +1,5 @@
-#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
-#define _PERF_ASM_ALTERNATIVE_ASM_H
+#ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
+#define _TOOLS_ASM_ALTERNATIVE_ASM_H
 
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 5ad9ee1..49c929a 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -9,7 +9,9 @@
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
 #endif
 
-#define BITS_PER_LONG __WORDSIZE
+#ifndef BITS_PER_LONG
+# define BITS_PER_LONG __WORDSIZE
+#endif
 
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index fa7208a..e33fc1d 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -9,6 +9,17 @@
 # define __always_inline	inline __attribute__((always_inline))
 #endif
 
+#ifdef __ANDROID__
+/*
+ * FIXME: Big hammer to get rid of tons of:
+ *   "warning: always_inline function might not be inlinable"
+ *
+ * At least on android-ndk-r12/platforms/android-24/arch-arm
+ */
+#undef __always_inline
+#define __always_inline	inline
+#endif
+
 #define __user
 
 #ifndef __attribute_const__
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index d026c65..ad6fa21 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -1,5 +1,104 @@
-#include "../../../include/linux/hash.h"
+#ifndef _LINUX_HASH_H
+#define _LINUX_HASH_H
+/* Fast hashing routine for ints,  longs and pointers.
+   (C) 2002 Nadia Yvette Chambers, IBM */
 
-#ifndef _TOOLS_LINUX_HASH_H
-#define _TOOLS_LINUX_HASH_H
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+/*
+ * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and
+ * fs/inode.c.  It's not actually prime any more (the previous primes
+ * were actively bad for hashing), but the name remains.
+ */
+#if BITS_PER_LONG == 32
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32
+#define hash_long(val, bits) hash_32(val, bits)
+#elif BITS_PER_LONG == 64
+#define hash_long(val, bits) hash_64(val, bits)
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64
+#else
+#error Wordsize not 32 or 64
+#endif
+
+/*
+ * This hash multiplies the input by a large odd number and takes the
+ * high bits.  Since multiplication propagates changes to the most
+ * significant end only, it is essential that the high bits of the
+ * product be used for the hash value.
+ *
+ * Chuck Lever verified the effectiveness of this technique:
+ * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
+ *
+ * Although a random odd number will do, it turns out that the golden
+ * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
+ * properties.  (See Knuth vol 3, section 6.4, exercise 9.)
+ *
+ * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2,
+ * which is very slightly easier to multiply by and makes no
+ * difference to the hash distribution.
+ */
+#define GOLDEN_RATIO_32 0x61C88647
+#define GOLDEN_RATIO_64 0x61C8864680B583EBull
+
+#ifdef CONFIG_HAVE_ARCH_HASH
+/* This header may use the GOLDEN_RATIO_xx constants */
+#include <asm/hash.h>
+#endif
+
+/*
+ * The _generic versions exist only so lib/test_hash.c can compare
+ * the arch-optimized versions with the generic.
+ *
+ * Note that if you change these, any <asm/hash.h> that aren't updated
+ * to match need to have their HAVE_ARCH_* define values updated so the
+ * self-test will not false-positive.
+ */
+#ifndef HAVE_ARCH__HASH_32
+#define __hash_32 __hash_32_generic
+#endif
+static inline u32 __hash_32_generic(u32 val)
+{
+	return val * GOLDEN_RATIO_32;
+}
+
+#ifndef HAVE_ARCH_HASH_32
+#define hash_32 hash_32_generic
 #endif
+static inline u32 hash_32_generic(u32 val, unsigned int bits)
+{
+	/* High bits are more random, so use them. */
+	return __hash_32(val) >> (32 - bits);
+}
+
+#ifndef HAVE_ARCH_HASH_64
+#define hash_64 hash_64_generic
+#endif
+static __always_inline u32 hash_64_generic(u64 val, unsigned int bits)
+{
+#if BITS_PER_LONG == 64
+	/* 64x64-bit multiply is efficient on all 64-bit processors */
+	return val * GOLDEN_RATIO_64 >> (64 - bits);
+#else
+	/* Hash 64 bits using only 32x32-bit multiply. */
+	return hash_32((u32)val ^ __hash_32(val >> 32), bits);
+#endif
+}
+
+static inline u32 hash_ptr(const void *ptr, unsigned int bits)
+{
+	return hash_long((unsigned long)ptr, bits);
+}
+
+/* This really should be called fold32_ptr; it does no hashing to speak of. */
+static inline u32 hash32_ptr(const void *ptr)
+{
+	unsigned long val = (unsigned long)ptr;
+
+#if BITS_PER_LONG == 64
+	val ^= (val >> 32);
+#endif
+	return (u32)val;
+}
+
+#endif /* _LINUX_HASH_H */
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 76df535..28607db 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -2,8 +2,7 @@
 #define __TOOLS_LINUX_KERNEL_H
 
 #include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
+#include <stddef.h>
 #include <assert.h>
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
@@ -70,29 +69,8 @@
 #define cpu_to_le64(x)	(x)
 #define cpu_to_le32(x)	(x)
 
-static inline int
-vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
-{
-	int i;
-	ssize_t ssize = size;
-
-	i = vsnprintf(buf, size, fmt, args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
-
-static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
-{
-	va_list args;
-	ssize_t ssize = size;
-	int i;
-
-	va_start(args, fmt);
-	i = vsnprintf(buf, size, fmt, args);
-	va_end(args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+int scnprintf(char * buf, size_t size, const char * fmt, ...);
 
 /*
  * This looks more complex than it should be. But we need to
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
index 0c27bdf..51334ed 100644
--- a/tools/include/linux/poison.h
+++ b/tools/include/linux/poison.h
@@ -1 +1,90 @@
-#include "../../../include/linux/poison.h"
+#ifndef _LINUX_POISON_H
+#define _LINUX_POISON_H
+
+/********** include/linux/list.h **********/
+
+/*
+ * Architectures might want to move the poison pointer offset
+ * into some well-recognized area such as 0xdead000000000000,
+ * that is also not mappable by user-space exploits:
+ */
+#ifdef CONFIG_ILLEGAL_POINTER_VALUE
+# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL)
+#else
+# define POISON_POINTER_DELTA 0
+#endif
+
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
+
+/********** include/linux/timer.h **********/
+/*
+ * Magic number "tsta" to indicate a static timer initializer
+ * for the object debugging code.
+ */
+#define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
+
+/********** mm/debug-pagealloc.c **********/
+#ifdef CONFIG_PAGE_POISONING_ZERO
+#define PAGE_POISON 0x00
+#else
+#define PAGE_POISON 0xaa
+#endif
+
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING	((void *) 0x400 + POISON_POINTER_DELTA)
+
+/********** mm/slab.c **********/
+/*
+ * Magic nums for obj red zoning.
+ * Placed in the first word before and the first word after an obj.
+ */
+#define	RED_INACTIVE	0x09F911029D74E35BULL	/* when obj is inactive */
+#define	RED_ACTIVE	0xD84156C5635688C0ULL	/* when obj is active */
+
+#define SLUB_RED_INACTIVE	0xbb
+#define SLUB_RED_ACTIVE		0xcc
+
+/* ...and for poisoning */
+#define	POISON_INUSE	0x5a	/* for use-uninitialised poisoning */
+#define POISON_FREE	0x6b	/* for use-after-free poisoning */
+#define	POISON_END	0xa5	/* end-byte of poisoning */
+
+/********** arch/$ARCH/mm/init.c **********/
+#define POISON_FREE_INITMEM	0xcc
+
+/********** arch/ia64/hp/common/sba_iommu.c **********/
+/*
+ * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
+ * value of "SBAIOMMU POISON\0" for spill-over poisoning.
+ */
+
+/********** fs/jbd/journal.c **********/
+#define JBD_POISON_FREE		0x5b
+#define JBD2_POISON_FREE	0x5c
+
+/********** drivers/base/dmapool.c **********/
+#define	POOL_POISON_FREED	0xa7	/* !inuse */
+#define	POOL_POISON_ALLOCATED	0xa9	/* !initted */
+
+/********** drivers/atm/ **********/
+#define ATM_POISON_FREE		0x12
+#define ATM_POISON		0xdeadbeef
+
+/********** kernel/mutexes **********/
+#define MUTEX_DEBUG_INIT	0x11
+#define MUTEX_DEBUG_FREE	0x22
+
+/********** lib/flex_array.c **********/
+#define FLEX_ARRAY_FREE	0x6c	/* for use-after-free poisoning */
+
+/********** security/ **********/
+#define KEY_DESTROY		0xbd
+
+#endif
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index e26223f..b968794 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,8 +8,10 @@ void *memdup(const void *src, size_t len);
 
 int strtobool(const char *s, bool *res);
 
-#ifndef __UCLIBC__
+#ifdef __GLIBC__
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 #endif
 
+char *str_error_r(int errnum, char *buf, size_t buflen);
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
new file mode 100644
index 0000000..23e6c41
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -0,0 +1,15 @@
+#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG
+#define _UAPI__ASM_GENERIC_BITS_PER_LONG
+
+/*
+ * There seems to be no way of detecting this automatically from user
+ * space, so 64 bit architectures should override this in their
+ * bitsperlong.h. In particular, an architecture that supports
+ * both 32 and 64 bit user space must not rely on CONFIG_64BIT
+ * to decide it, but rather check a compiler provided macro.
+ */
+#ifndef __BITS_PER_LONG
+#define __BITS_PER_LONG 32
+#endif
+
+#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
new file mode 100644
index 0000000..406459b
--- /dev/null
+++ b/tools/include/uapi/linux/bpf.h
@@ -0,0 +1,389 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+struct bpf_insn {
+	__u8	code;		/* opcode */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+/* BPF syscall commands, see bpf(2) man-page for details. */
+enum bpf_cmd {
+	BPF_MAP_CREATE,
+	BPF_MAP_LOOKUP_ELEM,
+	BPF_MAP_UPDATE_ELEM,
+	BPF_MAP_DELETE_ELEM,
+	BPF_MAP_GET_NEXT_KEY,
+	BPF_PROG_LOAD,
+	BPF_OBJ_PIN,
+	BPF_OBJ_GET,
+};
+
+enum bpf_map_type {
+	BPF_MAP_TYPE_UNSPEC,
+	BPF_MAP_TYPE_HASH,
+	BPF_MAP_TYPE_ARRAY,
+	BPF_MAP_TYPE_PROG_ARRAY,
+	BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	BPF_MAP_TYPE_PERCPU_HASH,
+	BPF_MAP_TYPE_PERCPU_ARRAY,
+	BPF_MAP_TYPE_STACK_TRACE,
+};
+
+enum bpf_prog_type {
+	BPF_PROG_TYPE_UNSPEC,
+	BPF_PROG_TYPE_SOCKET_FILTER,
+	BPF_PROG_TYPE_KPROBE,
+	BPF_PROG_TYPE_SCHED_CLS,
+	BPF_PROG_TYPE_SCHED_ACT,
+	BPF_PROG_TYPE_TRACEPOINT,
+};
+
+#define BPF_PSEUDO_MAP_FD	1
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY		0 /* create new element or update existing */
+#define BPF_NOEXIST	1 /* create new element if it didn't exist */
+#define BPF_EXIST	2 /* update existing element */
+
+#define BPF_F_NO_PREALLOC	(1U << 0)
+
+union bpf_attr {
+	struct { /* anonymous struct used by BPF_MAP_CREATE command */
+		__u32	map_type;	/* one of enum bpf_map_type */
+		__u32	key_size;	/* size of key in bytes */
+		__u32	value_size;	/* size of value in bytes */
+		__u32	max_entries;	/* max number of entries in a map */
+		__u32	map_flags;	/* prealloc or not */
+	};
+
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+		__u32		map_fd;
+		__aligned_u64	key;
+		union {
+			__aligned_u64 value;
+			__aligned_u64 next_key;
+		};
+		__u64		flags;
+	};
+
+	struct { /* anonymous struct used by BPF_PROG_LOAD command */
+		__u32		prog_type;	/* one of enum bpf_prog_type */
+		__u32		insn_cnt;
+		__aligned_u64	insns;
+		__aligned_u64	license;
+		__u32		log_level;	/* verbosity level of verifier */
+		__u32		log_size;	/* size of user buffer */
+		__aligned_u64	log_buf;	/* user supplied buffer */
+		__u32		kern_version;	/* checked when prog_type=kprobe */
+	};
+
+	struct { /* anonymous struct used by BPF_OBJ_* commands */
+		__aligned_u64	pathname;
+		__u32		bpf_fd;
+	};
+} __attribute__((aligned(8)));
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+	BPF_FUNC_unspec,
+	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
+	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
+	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
+	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
+	BPF_FUNC_ktime_get_ns,    /* u64 bpf_ktime_get_ns(void) */
+	BPF_FUNC_trace_printk,    /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
+	BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
+	BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
+
+	/**
+	 * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
+	 * @skb: pointer to skb
+	 * @offset: offset within packet from skb->mac_header
+	 * @from: pointer where to copy bytes from
+	 * @len: number of bytes to store into packet
+	 * @flags: bit 0 - if true, recompute skb->csum
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_skb_store_bytes,
+
+	/**
+	 * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where IP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l3_csum_replace,
+
+	/**
+	 * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where TCP/UDP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         bit 4 - is pseudo header
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l4_csum_replace,
+
+	/**
+	 * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
+	 * @ctx: context pointer passed to next program
+	 * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+	 * @index: index inside array that selects specific program to run
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_tail_call,
+
+	/**
+	 * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
+	 * @skb: pointer to skb
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_clone_redirect,
+
+	/**
+	 * u64 bpf_get_current_pid_tgid(void)
+	 * Return: current->tgid << 32 | current->pid
+	 */
+	BPF_FUNC_get_current_pid_tgid,
+
+	/**
+	 * u64 bpf_get_current_uid_gid(void)
+	 * Return: current_gid << 32 | current_uid
+	 */
+	BPF_FUNC_get_current_uid_gid,
+
+	/**
+	 * bpf_get_current_comm(char *buf, int size_of_buf)
+	 * stores current->comm into buf
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_get_current_comm,
+
+	/**
+	 * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
+	 * @skb: pointer to skb
+	 * Return: classid if != 0
+	 */
+	BPF_FUNC_get_cgroup_classid,
+	BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
+	BPF_FUNC_skb_vlan_pop,  /* bpf_skb_vlan_pop(skb) */
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
+	 * retrieve or populate tunnel metadata
+	 * @skb: pointer to skb
+	 * @key: pointer to 'struct bpf_tunnel_key'
+	 * @size: size of 'struct bpf_tunnel_key'
+	 * @flags: room for future extensions
+	 * Retrun: 0 on success
+	 */
+	BPF_FUNC_skb_get_tunnel_key,
+	BPF_FUNC_skb_set_tunnel_key,
+	BPF_FUNC_perf_event_read,	/* u64 bpf_perf_event_read(&map, index) */
+	/**
+	 * bpf_redirect(ifindex, flags) - redirect to another netdev
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: TC_ACT_REDIRECT
+	 */
+	BPF_FUNC_redirect,
+
+	/**
+	 * bpf_get_route_realm(skb) - retrieve a dst's tclassid
+	 * @skb: pointer to skb
+	 * Return: realm if != 0
+	 */
+	BPF_FUNC_get_route_realm,
+
+	/**
+	 * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to perf_event_array map
+	 * @index: index of event in the map
+	 * @data: data on stack to be output as raw data
+	 * @size: size of data
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_perf_event_output,
+	BPF_FUNC_skb_load_bytes,
+
+	/**
+	 * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to stack_trace map
+	 * @flags: bits 0-7 - numer of stack frames to skip
+	 *         bit 8 - collect user stack instead of kernel
+	 *         bit 9 - compare stacks by hash only
+	 *         bit 10 - if two different stacks hash into the same stackid
+	 *                  discard old
+	 *         other bits - reserved
+	 * Return: >= 0 stackid on success or negative error
+	 */
+	BPF_FUNC_get_stackid,
+
+	/**
+	 * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
+	 * @from: raw from buffer
+	 * @from_size: length of from buffer
+	 * @to: raw to buffer
+	 * @to_size: length of to buffer
+	 * @seed: optional seed
+	 * Return: csum result
+	 */
+	BPF_FUNC_csum_diff,
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
+	 * retrieve or populate tunnel options metadata
+	 * @skb: pointer to skb
+	 * @opt: pointer to raw tunnel option data
+	 * @size: size of @opt
+	 * Return: 0 on success for set, option size for get
+	 */
+	BPF_FUNC_skb_get_tunnel_opt,
+	BPF_FUNC_skb_set_tunnel_opt,
+	__BPF_FUNC_MAX_ID,
+};
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
+#define BPF_F_INVALIDATE_HASH		(1ULL << 1)
+
+/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
+ * First 4 bits are for passing the header field size.
+ */
+#define BPF_F_HDR_FIELD_MASK		0xfULL
+
+/* BPF_FUNC_l4_csum_replace flags. */
+#define BPF_F_PSEUDO_HDR		(1ULL << 4)
+#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+#define BPF_F_INGRESS			(1ULL << 0)
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+#define BPF_F_TUNINFO_IPV6		(1ULL << 0)
+
+/* BPF_FUNC_get_stackid flags. */
+#define BPF_F_SKIP_FIELD_MASK		0xffULL
+#define BPF_F_USER_STACK		(1ULL << 8)
+#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
+#define BPF_F_REUSE_STACKID		(1ULL << 10)
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
+#define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+
+/* BPF_FUNC_perf_event_output flags. */
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+/* user accessible mirror of in-kernel sk_buff.
+ * new fields can only be added to the end of this structure
+ */
+struct __sk_buff {
+	__u32 len;
+	__u32 pkt_type;
+	__u32 mark;
+	__u32 queue_mapping;
+	__u32 protocol;
+	__u32 vlan_present;
+	__u32 vlan_tci;
+	__u32 vlan_proto;
+	__u32 priority;
+	__u32 ingress_ifindex;
+	__u32 ifindex;
+	__u32 tc_index;
+	__u32 cb[5];
+	__u32 hash;
+	__u32 tc_classid;
+	__u32 data;
+	__u32 data_end;
+};
+
+struct bpf_tunnel_key {
+	__u32 tunnel_id;
+	union {
+		__u32 remote_ipv4;
+		__u32 remote_ipv6[4];
+	};
+	__u8 tunnel_tos;
+	__u8 tunnel_ttl;
+	__u16 tunnel_ext;
+	__u32 tunnel_label;
+};
+
+#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
new file mode 100644
index 0000000..a5c220e
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define		BPF_LD		0x00
+#define		BPF_LDX		0x01
+#define		BPF_ST		0x02
+#define		BPF_STX		0x03
+#define		BPF_ALU		0x04
+#define		BPF_JMP		0x05
+#define		BPF_RET		0x06
+#define		BPF_MISC        0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code)  ((code) & 0x18)
+#define		BPF_W		0x00
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#define BPF_MODE(code)  ((code) & 0xe0)
+#define		BPF_IMM		0x00
+#define		BPF_ABS		0x20
+#define		BPF_IND		0x40
+#define		BPF_MEM		0x60
+#define		BPF_LEN		0x80
+#define		BPF_MSH		0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code)    ((code) & 0xf0)
+#define		BPF_ADD		0x00
+#define		BPF_SUB		0x10
+#define		BPF_MUL		0x20
+#define		BPF_DIV		0x30
+#define		BPF_OR		0x40
+#define		BPF_AND		0x50
+#define		BPF_LSH		0x60
+#define		BPF_RSH		0x70
+#define		BPF_NEG		0x80
+#define		BPF_MOD		0x90
+#define		BPF_XOR		0xa0
+
+#define		BPF_JA		0x00
+#define		BPF_JEQ		0x10
+#define		BPF_JGT		0x20
+#define		BPF_JGE		0x30
+#define		BPF_JSET        0x40
+#define BPF_SRC(code)   ((code) & 0x08)
+#define		BPF_K		0x00
+#define		BPF_X		0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 0000000..b04000a
--- /dev/null
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,30 @@
+#ifndef _UAPI_LINUX_HW_BREAKPOINT_H
+#define _UAPI_LINUX_HW_BREAKPOINT_H
+
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
+};
+
+#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
new file mode 100644
index 0000000..c66a485
--- /dev/null
+++ b/tools/include/uapi/linux/perf_event.h
@@ -0,0 +1,983 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _UAPI_LINUX_PERF_EVENT_H
+#define _UAPI_LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+	PERF_COUNT_SW_BPF_OUTPUT		= 10,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type_shift {
+	PERF_SAMPLE_BRANCH_USER_SHIFT		= 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL_SHIFT		= 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV_SHIFT		= 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY_SHIFT		= 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT	= 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT	= 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL_SHIFT	= 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT	= 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX_SHIFT		= 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX_SHIFT		= 9, /* not in transaction */
+	PERF_SAMPLE_BRANCH_COND_SHIFT		= 10, /* conditional branches */
+
+	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT	= 11, /* call/ret stack */
+	PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT	= 12, /* indirect jumps */
+	PERF_SAMPLE_BRANCH_CALL_SHIFT		= 13, /* direct call */
+
+	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
+	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
+
+	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
+};
+
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+	PERF_SAMPLE_BRANCH_HV		= 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_COND		= 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
+
+	PERF_SAMPLE_BRANCH_CALL_STACK	= 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_JUMP	= 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
+	PERF_SAMPLE_BRANCH_CALL		= 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
+
+	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+	PERF_TXN_ELISION        = (1 << 0), /* From elision */
+	PERF_TXN_TRANSACTION    = (1 << 1), /* From transaction */
+	PERF_TXN_SYNC           = (1 << 2), /* Instruction is related */
+	PERF_TXN_ASYNC          = (1 << 3), /* Instruction not related */
+	PERF_TXN_RETRY          = (1 << 4), /* Retry possible */
+	PERF_TXN_CONFLICT       = (1 << 5), /* Conflict abort */
+	PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+	PERF_TXN_CAPACITY_READ  = (1 << 7), /* Capacity read abort */
+
+	PERF_TXN_MAX	        = (1 << 8), /* non-ABI */
+
+	/* bits 32..63 are reserved for the abort code */
+
+	PERF_TXN_ABORT_MASK  = (0xffffffffULL << 32),
+	PERF_TXN_ABORT_SHIFT = 32,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
+#define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ *
+ * @sample_max_stack: Max number of frame pointers in a callchain,
+ *		      should be < /proc/sys/kernel/perf_event_max_stack
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+				comm_exec      :  1, /* flag comm events that are due to an exec */
+				use_clockid    :  1, /* use @clockid for time fields */
+				context_switch :  1, /* context switch data */
+				write_backward :  1, /* Write ring buffer from end to beginning */
+				__reserved_1   : 36;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	__s32	clockid;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
+
+	/*
+	 * Wakeup watermark for AUX area
+	 */
+	__u32	aux_watermark;
+	__u16	sample_max_stack;
+	__u16	__reserved_2;	/* align to __u64 */
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, index, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     index = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_user_rdpmc && index) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(index - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_user_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & (((u64)1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if index), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (index)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & (((u64)1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 *
+	 * data_{offset,size} indicate the location and size of the perf record
+	 * buffer within the mmapped area.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+	__u64	data_offset;		/* where the buffer starts */
+	__u64	data_size;		/* data buffer size */
+
+	/*
+	 * AUX area is defined by aux_{offset,size} fields that should be set
+	 * by the userspace, so that
+	 *
+	 *   aux_offset >= data_offset + data_size
+	 *
+	 * prior to mmap()ing it. Size of the mmap()ed area should be aux_size.
+	 *
+	 * Ring buffer pointers aux_{head,tail} have the same semantics as
+	 * data_{head,tail} and same ordering rules apply.
+	 */
+	__u64	aux_head;
+	__u64	aux_tail;
+	__u64	aux_offset;
+	__u64	aux_size;
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT	(1 << 12)
+/*
+ * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
+ * different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
+ */
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	u32				prot, flags;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	/*
+	 * Records that new data landed in the AUX buffer part.
+	 *
+	 * struct {
+	 * 	struct perf_event_header	header;
+	 *
+	 * 	u64				aux_offset;
+	 * 	u64				aux_size;
+	 *	u64				flags;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_AUX				= 11,
+
+	/*
+	 * Indicates that instruction trace has started
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 * };
+	 */
+	PERF_RECORD_ITRACE_START		= 12,
+
+	/*
+	 * Records the dropped/lost sample number.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u64				lost;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST_SAMPLES		= 13,
+
+	/*
+	 * Records a context switch in or out (flagged by
+	 * PERF_RECORD_MISC_SWITCH_OUT). See also
+	 * PERF_RECORD_SWITCH_CPU_WIDE.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH			= 14,
+
+	/*
+	 * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+	 * next_prev_tid that are the next (switching out) or previous
+	 * (switching in) pid/tid.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				next_prev_pid;
+	 *	u32				next_prev_tid;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+#define PERF_MAX_CONTEXTS_PER_STACK	  8
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+/**
+ * PERF_RECORD_AUX::flags bits
+ */
+#define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
+#define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
+
+#define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
+#define PERF_FLAG_FD_OUTPUT		(1UL << 1)
+#define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
+
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ *    cycles: cycles from last branch (or 0 if not supported)
+ */
+struct perf_branch_entry {
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		cycles:16,  /* cycle count to last branch */
+		reserved:44;
+};
+
+#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 316f308..0a6fda9 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -10,15 +10,23 @@ endif
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
+LD = $(CROSS_COMPILE)ld
 
 MAKEFLAGS += --no-print-directory
 
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+  CFLAGS += -Werror
+endif
+
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 CFLAGS += -I$(srctree)/tools/lib/api
+CFLAGS += -I$(srctree)/tools/include
 
 RM = rm -f
 
diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
index 0e636c4..b0a035f 100644
--- a/tools/lib/api/fd/array.c
+++ b/tools/lib/api/fd/array.c
@@ -85,7 +85,8 @@ int fdarray__add(struct fdarray *fda, int fd, short revents)
 }
 
 int fdarray__filter(struct fdarray *fda, short revents,
-		    void (*entry_destructor)(struct fdarray *fda, int fd))
+		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
+		    void *arg)
 {
 	int fd, nr = 0;
 
@@ -95,7 +96,7 @@ int fdarray__filter(struct fdarray *fda, short revents,
 	for (fd = 0; fd < fda->nr; ++fd) {
 		if (fda->entries[fd].revents & revents) {
 			if (entry_destructor)
-				entry_destructor(fda, fd);
+				entry_destructor(fda, fd, arg);
 
 			continue;
 		}
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
index 45db018..71287dd 100644
--- a/tools/lib/api/fd/array.h
+++ b/tools/lib/api/fd/array.h
@@ -22,6 +22,7 @@ struct fdarray {
 	struct pollfd *entries;
 	union {
 		int    idx;
+		void   *ptr;
 	} *priv;
 };
 
@@ -34,7 +35,8 @@ void fdarray__delete(struct fdarray *fda);
 int fdarray__add(struct fdarray *fda, int fd, short revents);
 int fdarray__poll(struct fdarray *fda, int timeout);
 int fdarray__filter(struct fdarray *fda, short revents,
-		    void (*entry_destructor)(struct fdarray *fda, int fd));
+		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
+		    void *arg);
 int fdarray__grow(struct fdarray *fda, int extra);
 int fdarray__fprintf(struct fdarray *fda, FILE *fp);
 
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 08556cf..ba7094b 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -283,6 +283,11 @@ int filename__read_int(const char *filename, int *value)
 	return err;
 }
 
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 0 for base, the strtoull detects the
+ * base automatically (see man strtoull).
+ */
 int filename__read_ull(const char *filename, unsigned long long *value)
 {
 	char line[64];
@@ -292,7 +297,7 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 		return -1;
 
 	if (read(fd, line, sizeof(line)) > 0) {
-		*value = strtoull(line, NULL, 10);
+		*value = strtoull(line, NULL, 0);
 		if (*value != ULLONG_MAX)
 			err = 0;
 	}
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index a26bb5e..251b7c3 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -5,6 +5,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <unistd.h>
 #include "fs.h"
@@ -118,7 +119,7 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
 	}
 		break;
 	default:
-		snprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+		snprintf(buf, size, "%s", str_error_r(err, sbuf, sizeof(sbuf)));
 		break;
 	}
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index fc1bc75..62d89d5 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -68,7 +68,7 @@ FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
 FEATURE_DISPLAY = libelf bpf
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
 check_feat := 1
@@ -154,6 +154,12 @@ all: fixdep $(VERSION_FILES) all_cmd
 all_cmd: $(CMD_TARGETS)
 
 $(BPF_IN): force elfdep bpfdep
+	@(test -f ../../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
+	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
+	echo "Warning: tools/include/uapi/linux/bpf.h differs from kernel" >&2 )) || true
+	@(test -f ../../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
+	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
+	echo "Warning: tools/include/uapi/linux/bpf_common.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1f91cc9..4212ed6 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -4,6 +4,19 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index a764655..e8ba540 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -4,6 +4,19 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 #ifndef __BPF_BPF_H
 #define __BPF_BPF_H
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7e543c3..32e6b6b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,19 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #include <stdlib.h>
@@ -71,12 +84,13 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
 	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
 	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
-	[ERRCODE_OFFSET(ENDIAN)]	= "Endian missmatch",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
 	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
 	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
 	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
 	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
 	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
 };
 
 int libbpf_strerror(int err, char *buf, size_t size)
@@ -145,6 +159,7 @@ struct bpf_program {
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt;
+	enum bpf_prog_type type;
 
 	struct {
 		int insn_idx;
@@ -286,6 +301,7 @@ bpf_program__init(void *data, size_t size, char *name, int idx,
 	prog->idx = idx;
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
+	prog->type = BPF_PROG_TYPE_KPROBE;
 
 	return 0;
 errout:
@@ -881,8 +897,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(struct bpf_insn *insns, int insns_cnt,
-	     char *license, u32 kern_version, int *pfd)
+load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+	     int insns_cnt, char *license, u32 kern_version, int *pfd)
 {
 	int ret;
 	char *log_buf;
@@ -894,9 +910,8 @@ load_program(struct bpf_insn *insns, int insns_cnt,
 	if (!log_buf)
 		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
 
-	ret = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
-			       insns_cnt, license, kern_version,
-			       log_buf, BPF_LOG_BUF_SIZE);
+	ret = bpf_load_program(type, insns, insns_cnt, license,
+			       kern_version, log_buf, BPF_LOG_BUF_SIZE);
 
 	if (ret >= 0) {
 		*pfd = ret;
@@ -912,15 +927,27 @@ load_program(struct bpf_insn *insns, int insns_cnt,
 		pr_warning("-- BEGIN DUMP LOG ---\n");
 		pr_warning("\n%s\n", log_buf);
 		pr_warning("-- END LOG --\n");
+	} else if (insns_cnt >= BPF_MAXINSNS) {
+		pr_warning("Program too large (%d insns), at most %d insns\n",
+			   insns_cnt, BPF_MAXINSNS);
+		ret = -LIBBPF_ERRNO__PROG2BIG;
 	} else {
-		if (insns_cnt >= BPF_MAXINSNS) {
-			pr_warning("Program too large (%d insns), at most %d insns\n",
-				   insns_cnt, BPF_MAXINSNS);
-			ret = -LIBBPF_ERRNO__PROG2BIG;
-		} else if (log_buf) {
-			pr_warning("log buffer is empty\n");
-			ret = -LIBBPF_ERRNO__KVER;
+		/* Wrong program type? */
+		if (type != BPF_PROG_TYPE_KPROBE) {
+			int fd;
+
+			fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+					      insns_cnt, license, kern_version,
+					      NULL, 0);
+			if (fd >= 0) {
+				close(fd);
+				ret = -LIBBPF_ERRNO__PROGTYPE;
+				goto out;
+			}
 		}
+
+		if (log_buf)
+			ret = -LIBBPF_ERRNO__KVER;
 	}
 
 out:
@@ -955,7 +982,7 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->insns, prog->insns_cnt,
+		err = load_program(prog->type, prog->insns, prog->insns_cnt,
 				   license, kern_version, &fd);
 		if (!err)
 			prog->instances.fds[0] = fd;
@@ -984,7 +1011,7 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(result.new_insn_ptr,
+		err = load_program(prog->type, result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd);
 
@@ -1186,20 +1213,14 @@ bpf_object__next(struct bpf_object *prev)
 	return next;
 }
 
-const char *
-bpf_object__get_name(struct bpf_object *obj)
+const char *bpf_object__name(struct bpf_object *obj)
 {
-	if (!obj)
-		return ERR_PTR(-EINVAL);
-	return obj->path;
+	return obj ? obj->path : ERR_PTR(-EINVAL);
 }
 
-unsigned int
-bpf_object__get_kversion(struct bpf_object *obj)
+unsigned int bpf_object__kversion(struct bpf_object *obj)
 {
-	if (!obj)
-		return 0;
-	return obj->kern_version;
+	return obj ? obj->kern_version : 0;
 }
 
 struct bpf_program *
@@ -1224,9 +1245,8 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 	return &obj->programs[idx];
 }
 
-int bpf_program__set_private(struct bpf_program *prog,
-			     void *priv,
-			     bpf_program_clear_priv_t clear_priv)
+int bpf_program__set_priv(struct bpf_program *prog, void *priv,
+			  bpf_program_clear_priv_t clear_priv)
 {
 	if (prog->priv && prog->clear_priv)
 		prog->clear_priv(prog, prog->priv);
@@ -1236,10 +1256,9 @@ int bpf_program__set_private(struct bpf_program *prog,
 	return 0;
 }
 
-int bpf_program__get_private(struct bpf_program *prog, void **ppriv)
+void *bpf_program__priv(struct bpf_program *prog)
 {
-	*ppriv = prog->priv;
-	return 0;
+	return prog ? prog->priv : ERR_PTR(-EINVAL);
 }
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
@@ -1311,32 +1330,61 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
 	return fd;
 }
 
-int bpf_map__get_fd(struct bpf_map *map)
+static void bpf_program__set_type(struct bpf_program *prog,
+				  enum bpf_prog_type type)
 {
-	if (!map)
-		return -EINVAL;
-
-	return map->fd;
+	prog->type = type;
 }
 
-int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
+int bpf_program__set_tracepoint(struct bpf_program *prog)
 {
-	if (!map || !pdef)
+	if (!prog)
 		return -EINVAL;
+	bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
+	return 0;
+}
 
-	*pdef = map->def;
+int bpf_program__set_kprobe(struct bpf_program *prog)
+{
+	if (!prog)
+		return -EINVAL;
+	bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
 	return 0;
 }
 
-const char *bpf_map__get_name(struct bpf_map *map)
+static bool bpf_program__is_type(struct bpf_program *prog,
+				 enum bpf_prog_type type)
 {
-	if (!map)
-		return NULL;
-	return map->name;
+	return prog ? (prog->type == type) : false;
+}
+
+bool bpf_program__is_tracepoint(struct bpf_program *prog)
+{
+	return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
+}
+
+bool bpf_program__is_kprobe(struct bpf_program *prog)
+{
+	return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
+}
+
+int bpf_map__fd(struct bpf_map *map)
+{
+	return map ? map->fd : -EINVAL;
 }
 
-int bpf_map__set_private(struct bpf_map *map, void *priv,
-			 bpf_map_clear_priv_t clear_priv)
+const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
+{
+	return map ? &map->def : ERR_PTR(-EINVAL);
+}
+
+const char *bpf_map__name(struct bpf_map *map)
+{
+	return map ? map->name : NULL;
+}
+
+int bpf_map__set_priv(struct bpf_map *map, void *priv,
+		     bpf_map_clear_priv_t clear_priv)
 {
 	if (!map)
 		return -EINVAL;
@@ -1351,14 +1399,9 @@ int bpf_map__set_private(struct bpf_map *map, void *priv,
 	return 0;
 }
 
-int bpf_map__get_private(struct bpf_map *map, void **ppriv)
+void *bpf_map__priv(struct bpf_map *map)
 {
-	if (!map)
-		return -EINVAL;
-
-	if (ppriv)
-		*ppriv = map->priv;
-	return 0;
+	return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
 struct bpf_map *
@@ -1389,7 +1432,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 }
 
 struct bpf_map *
-bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
+bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 {
 	struct bpf_map *pos;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a51594c..dd7a513 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -4,6 +4,19 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 #ifndef __BPF_LIBBPF_H
 #define __BPF_LIBBPF_H
@@ -19,13 +32,14 @@ enum libbpf_errno {
 	LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START,
 	LIBBPF_ERRNO__FORMAT,	/* BPF object format invalid */
 	LIBBPF_ERRNO__KVERSION,	/* Incorrect or no 'version' section */
-	LIBBPF_ERRNO__ENDIAN,	/* Endian missmatch */
+	LIBBPF_ERRNO__ENDIAN,	/* Endian mismatch */
 	LIBBPF_ERRNO__INTERNAL,	/* Internal error in libbpf */
 	LIBBPF_ERRNO__RELOC,	/* Relocation failed */
 	LIBBPF_ERRNO__LOAD,	/* Load program failure for unknown reason */
 	LIBBPF_ERRNO__VERIFY,	/* Kernel verifier blocks program loading */
 	LIBBPF_ERRNO__PROG2BIG,	/* Program too big */
 	LIBBPF_ERRNO__KVER,	/* Incorrect kernel version */
+	LIBBPF_ERRNO__PROGTYPE,	/* Kernel doesn't support this program type */
 	__LIBBPF_ERRNO__END,
 };
 
@@ -55,8 +69,8 @@ void bpf_object__close(struct bpf_object *object);
 /* Load/unload object into/from kernel */
 int bpf_object__load(struct bpf_object *obj);
 int bpf_object__unload(struct bpf_object *obj);
-const char *bpf_object__get_name(struct bpf_object *obj);
-unsigned int bpf_object__get_kversion(struct bpf_object *obj);
+const char *bpf_object__name(struct bpf_object *obj);
+unsigned int bpf_object__kversion(struct bpf_object *obj);
 
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
@@ -78,11 +92,10 @@ struct bpf_program *bpf_program__next(struct bpf_program *prog,
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
-int bpf_program__set_private(struct bpf_program *prog, void *priv,
-			     bpf_program_clear_priv_t clear_priv);
+int bpf_program__set_priv(struct bpf_program *prog, void *priv,
+			  bpf_program_clear_priv_t clear_priv);
 
-int bpf_program__get_private(struct bpf_program *prog,
-			     void **ppriv);
+void *bpf_program__priv(struct bpf_program *prog);
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
@@ -153,6 +166,15 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
 int bpf_program__nth_fd(struct bpf_program *prog, int n);
 
 /*
+ * Adjust type of bpf program. Default is kprobe.
+ */
+int bpf_program__set_tracepoint(struct bpf_program *prog);
+int bpf_program__set_kprobe(struct bpf_program *prog);
+
+bool bpf_program__is_tracepoint(struct bpf_program *prog);
+bool bpf_program__is_kprobe(struct bpf_program *prog);
+
+/*
  * We don't need __attribute__((packed)) now since it is
  * unnecessary for 'bpf_map_def' because they are all aligned.
  * In addition, using it will trigger -Wpacked warning message,
@@ -171,7 +193,7 @@ struct bpf_map_def {
  */
 struct bpf_map;
 struct bpf_map *
-bpf_object__get_map_by_name(struct bpf_object *obj, const char *name);
+bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
 
 struct bpf_map *
 bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
@@ -180,13 +202,13 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
-int bpf_map__get_fd(struct bpf_map *map);
-int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef);
-const char *bpf_map__get_name(struct bpf_map *map);
+int bpf_map__fd(struct bpf_map *map);
+const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
+const char *bpf_map__name(struct bpf_map *map);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
-int bpf_map__set_private(struct bpf_map *map, void *priv,
-			 bpf_map_clear_priv_t clear_priv);
-int bpf_map__get_private(struct bpf_map *map, void **ppriv);
+int bpf_map__set_priv(struct bpf_map *map, void *priv,
+		      bpf_map_clear_priv_t clear_priv);
+void *bpf_map__priv(struct bpf_map *map);
 
 #endif
diff --git a/tools/lib/str_error_r.c b/tools/lib/str_error_r.c
new file mode 100644
index 0000000..503ae07
--- /dev/null
+++ b/tools/lib/str_error_r.c
@@ -0,0 +1,26 @@
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+#include <linux/string.h>
+
+/*
+ * The tools so far have been using the strerror_r() GNU variant, that returns
+ * a string, be it the buffer passed or something else.
+ *
+ * But that, besides being tricky in cases where we expect that the function
+ * using strerror_r() returns the error formatted in a provided buffer (we have
+ * to check if it returned something else and copy that instead), breaks the
+ * build on systems not using glibc, like Alpine Linux, where musl libc is
+ * used.
+ *
+ * So, introduce yet another wrapper, str_error_r(), that has the GNU
+ * interface, but uses the portable XSI variant of strerror_r(), so that users
+ * rest asured that the provided buffer is used and it is what is returned.
+ */
+char *str_error_r(int errnum, char *buf, size_t buflen)
+{
+	int err = strerror_r(errnum, buf, buflen);
+	if (err)
+		snprintf(buf, buflen, "INTERNAL ERROR: strerror_r(%d, %p, %zd)=%d", errnum, buf, buflen, err);
+	return buf;
+}
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index a810370..ce4b7e5 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+  CFLAGS += -Werror
+endif
+
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 
 CFLAGS += -I$(srctree)/tools/include/
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index f4f6c9e..911f839 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -3,6 +3,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <sys/wait.h>
 #include "subcmd-util.h"
@@ -109,7 +110,7 @@ int start_command(struct child_process *cmd)
 
 		if (cmd->dir && chdir(cmd->dir))
 			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-			    cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
+			    cmd->dir, str_error_r(errno, sbuf, sizeof(sbuf)));
 		if (cmd->env) {
 			for (; *cmd->env; cmd->env++) {
 				if (strchr(*cmd->env, '='))
@@ -173,7 +174,7 @@ static int wait_or_whine(pid_t pid)
 			if (errno == EINTR)
 				continue;
 			fprintf(stderr, " Error: waitpid failed (%s)",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
+				str_error_r(errno, sbuf, sizeof(sbuf)));
 			return -ERR_RUN_COMMAND_WAITPID;
 		}
 		if (waiting != pid)
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index a8b6357..664c90c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -23,6 +23,7 @@
  *  Frederic Weisbecker gave his permission to relicense the code to
  *  the Lesser General Public License.
  */
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -31,8 +32,9 @@
 #include <errno.h>
 #include <stdint.h>
 #include <limits.h>
+#include <linux/string.h>
 
-#include <netinet/ip6.h>
+#include <netinet/in.h>
 #include "event-parse.h"
 #include "event-utils.h"
 
@@ -6131,12 +6133,7 @@ int pevent_strerror(struct pevent *pevent __maybe_unused,
 	const char *msg;
 
 	if (errnum >= 0) {
-		msg = strerror_r(errnum, buf, buflen);
-		if (msg != buf) {
-			size_t len = strlen(msg);
-			memcpy(buf, msg, min(buflen - 1, len));
-			*(buf + min(buflen - 1, len)) = '\0';
-		}
+		str_error_r(errnum, buf, buflen);
 		return 0;
 	}
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 88cccea..7c214ce 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -28,11 +28,16 @@
 #include "event-utils.h"
 
 #define COMM "COMM"
+#define CPU "CPU"
 
 static struct format_field comm = {
 	.name = "COMM",
 };
 
+static struct format_field cpu = {
+	.name = "CPU",
+};
+
 struct event_list {
 	struct event_list	*next;
 	struct event_format	*event;
@@ -382,14 +387,17 @@ create_arg_item(struct event_format *event, const char *token,
 		/* Consider this a field */
 		field = pevent_find_any_field(event, token);
 		if (!field) {
-			if (strcmp(token, COMM) != 0) {
+			/* If token is 'COMM' or 'CPU' then it is special */
+			if (strcmp(token, COMM) == 0) {
+				field = &comm;
+			} else if (strcmp(token, CPU) == 0) {
+				field = &cpu;
+			} else {
 				/* not a field, Make it false */
 				arg->type = FILTER_ARG_BOOLEAN;
 				arg->boolean.value = FILTER_FALSE;
 				break;
 			}
-			/* If token is 'COMM' then it is special */
-			field = &comm;
 		}
 		arg->type = FILTER_ARG_FIELD;
 		arg->field.field = field;
@@ -1718,6 +1726,10 @@ get_value(struct event_format *event,
 		return (unsigned long)name;
 	}
 
+	/* Handle our dummy "cpu" field */
+	if (field == &cpu)
+		return record->cpu;
+
 	pevent_read_number_field(field, record->data, &val);
 
 	if (!(field->flags & FIELD_IS_SIGNED))
diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c
new file mode 100644
index 0000000..45f9a06
--- /dev/null
+++ b/tools/lib/vsprintf.c
@@ -0,0 +1,24 @@
+#include <sys/types.h>
+#include <linux/kernel.h>
+#include <stdio.h>
+
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+       int i = vsnprintf(buf, size, fmt, args);
+       ssize_t ssize = size;
+
+       return (i >= ssize) ? (ssize - 1) : i;
+}
+
+int scnprintf(char * buf, size_t size, const char * fmt, ...)
+{
+       ssize_t ssize = size;
+       va_list args;
+       int i;
+
+       va_start(args, fmt);
+       i = vsnprintf(buf, size, fmt, args);
+       va_end(args);
+
+       return (i >= ssize) ? (ssize - 1) : i;
+}
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 0e89258..2457916 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -5,9 +5,14 @@ objtool-y += special.o
 objtool-y += objtool.o
 
 objtool-y += libstring.o
+objtool-y += str_error_r.o
 
 CFLAGS += -I$(srctree)/tools/lib
 
 $(OUTPUT)libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)str_error_r.o: ../lib/str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f094f3c..1f75b0a 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -26,7 +26,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include
+INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi
 CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
@@ -41,8 +41,11 @@ include $(srctree)/tools/build/Makefile.include
 $(OBJTOOL_IN): fixdep FORCE
 	@$(MAKE) $(build)=objtool
 
+# Busybox's diff doesn't have -I, avoid warning in that case
+#
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
+	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
+	test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
 	diff -I'^#include' arch/x86/insn/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
 	diff -I'^#include' arch/x86/insn/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
 	diff arch/x86/insn/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 25d8031..17fa7fc 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -26,6 +26,7 @@
  */
 
 #include <string.h>
+#include <stdlib.h>
 #include <subcmd/parse-options.h>
 
 #include "builtin.h"
@@ -667,7 +668,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 				  struct symbol *func)
 {
 	struct instruction *insn, *prev_jump;
-	struct rela *text_rela, *rodata_rela, *prev_rela;
+	struct rela *text_rela, *rodata_rela, *prev_rela = NULL;
 	int ret;
 
 	prev_jump = NULL;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index e11f6b6..0d7983a 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -30,6 +30,13 @@
 #include "elf.h"
 #include "warn.h"
 
+/*
+ * Fallback for systems without this "read, mmaping if possible" cmd.
+ */
+#ifndef ELF_C_READ_MMAP
+#define ELF_C_READ_MMAP ELF_C_READ
+#endif
+
 struct section *find_section_by_name(struct elf *elf, const char *name)
 {
 	struct section *sec;
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 3d1bb80..3db3db9 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -30,3 +30,4 @@ config.mak.autogen
 *.pyo
 .config-detected
 util/intel-pt-decoder/inat-tables.c
+arch/*/include/generated/
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt
index 8484c3a..24a5999 100644
--- a/tools/perf/Documentation/android.txt
+++ b/tools/perf/Documentation/android.txt
@@ -12,14 +12,14 @@ Set the NDK variable to point to the path where you installed the NDK:
 
 2. Set cross-compiling environment variables for NDK toolchain and sysroot.
 For arm:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi-
-  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm
+  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.9/prebuilt/linux-x86_64/bin/arm-linux-androideabi-
+  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-arm
 For x86:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android-
-  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86
+  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.9/prebuilt/linux-x86_64/bin/i686-linux-android-
+  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-x86
 
-This method is not working for Android NDK versions up to Revision 8b.
-perf uses some bionic enhancements that are not included in these NDK versions.
+This method is only tested for Android NDK versions Revision 11b and later.
+perf uses some bionic enhancements that are not included in prior NDK versions.
 You can use method (b) described below instead.
 
 (b). Use the Android source tree
@@ -49,9 +49,9 @@ II. Compile perf for Android
 ------------------------------------------------
 You need to run make with the NDK toolchain and sysroot defined above:
 For arm:
-  make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+  make WERROR=0 ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
 For x86:
-  make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+  make WERROR=0 ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
 
 III. Install perf
 -----------------------------------------------
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 778f54d..8ffbd27 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -61,6 +61,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+	'always', 'never' or 'auto', allowing configuring color output
+	via the command line, in addition to via "color.ui" .perfconfig.
+	Use '--stdio-color always' to generate color even when redirecting
+	to a pipe or file. Using just '--stdio-color' is equivalent to
+	using 'always'.
+
 --tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
 	present, as when piping to other commands, the stdio interface is
 	used. This interfaces starts by centering on the line with more
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index dd07b55..058064d 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -15,6 +15,9 @@ DESCRIPTION
 This command manages the build-id cache. It can add, remove, update and purge
 files to/from the cache. In the future it should as well set upper limits for
 the space used by the cache, etc.
+This also scans the target binary for SDT (Statically Defined Tracing) and
+record it along with the buildid-cache, which will be used by perf-probe.
+For more details, see linkperf:perf-probe[1].
 
 OPTIONS
 -------
diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index be8fa1a..f0796a4 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -34,6 +34,10 @@ OPTIONS for 'convert'
 --verbose::
         Be more verbose (show counter open errors, etc).
 
+--all::
+	Convert all events, including non-sample events (comm, fork, ...), to output.
+	Default is off, only convert samples.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 1d6092c..7349632 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -56,6 +56,9 @@ OPTIONS
 --all-user::
 	Configure all used events to run in user space.
 
+--ldload::
+	Specify desired latency for loads event.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 3a8a9ba..736da44 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -67,7 +67,10 @@ OPTIONS
 
 -l::
 --list[=[GROUP:]EVENT]::
-	List up current probe events. This can also accept filtering patterns of event names.
+	List up current probe events. This can also accept filtering patterns of
+	event names.
+	When this is used with --cache, perf shows all cached probes instead of
+	the live probes.
 
 -L::
 --line=::
@@ -109,6 +112,12 @@ OPTIONS
 	Dry run. With this option, --add and --del doesn't execute actual
 	adding and removal operations.
 
+--cache::
+	(With --add) Cache the probes. Any events which successfully added
+	are also stored in the cache file.
+	(With --list) Show cached probes.
+	(With --del) Remove cached probes.
+
 --max-probes=NUM::
 	Set the maximum number of probe points for an event. Default is 128.
 
@@ -134,19 +143,30 @@ PROBE SYNTAX
 Probe points are defined by following syntax.
 
     1) Define event based on function name
-     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+     [[GROUP:]EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
 
     2) Define event based on source file with line number
-     [EVENT=]SRC:ALN [ARG ...]
+     [[GROUP:]EVENT=]SRC:ALN [ARG ...]
 
     3) Define event based on source file with lazy pattern
-     [EVENT=]SRC;PTN [ARG ...]
+     [[GROUP:]EVENT=]SRC;PTN [ARG ...]
 
+    4) Pre-defined SDT events or cached event with name
+     %[sdt_PROVIDER:]SDTEVENT
+     or,
+     sdt_PROVIDER:SDTEVENT
 
-'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
+Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
+modules.
 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
 It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
 'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
+'SDTEVENT' and 'PROVIDER' is the pre-defined event name which is defined by user SDT (Statically Defined Tracing) or the pre-cached probes with event name.
+Note that before using the SDT event, the target binary (on which SDT events are defined) must be scanned by linkperf:perf-buildid-cache[1] to make SDT events as cached events.
+
+For details of the SDT, see below.
+https://sourceware.org/gdb/onlinedocs/gdb/Static-Probe-Points.html
 
 PROBE ARGUMENT
 --------------
@@ -226,4 +246,4 @@ Add probes at malloc() function on libc
 
 SEE ALSO
 --------
-linkperf:perf-trace[1], linkperf:perf-record[1]
+linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8dbee83..69966ab 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -360,6 +360,35 @@ particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
 
+--dry-run::
+Parse options then exit. --dry-run can be used to detect errors in cmdline
+options.
+
+'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj
+in config file is set to true.
+
+--tail-synthesize::
+Instead of collecting non-sample events (for example, fork, comm, mmap) at
+the beginning of record, collect them during finalizing an output file.
+The collected non-sample events reflects the status of the system when
+record is finished.
+
+--overwrite::
+Makes all events use an overwritable ring buffer. An overwritable ring
+buffer works like a flight recorder: when it gets full, the kernel will
+overwrite the oldest records, that thus will never make it to the
+perf.data file.
+
+When '--overwrite' and '--switch-output' are used perf records and drops
+events until it receives a signal, meaning that something unusual was
+detected that warrants taking a snapshot of the most current events,
+those fitting in the ring buffer at that moment.
+
+'overwrite' attribute can also be set or canceled for an event using
+config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'.
+
+Implies --tail-synthesize.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9cbddc2..2d17462 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -265,6 +265,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+	'always', 'never' or 'auto', allowing configuring color output
+	via the command line, in addition to via "color.ui" .perfconfig.
+	Use '--stdio-color always' to generate color even when redirecting
+	to a pipe or file. Using just '--stdio-color' is equivalent to
+	using 'always'.
+
 --tui:: Use the TUI interface, that is integrated with annotate and allows
         zooming into DSOs or threads, among other features. Use of --tui
 	requires a tty, if one is not present, as when piping to other
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4fc44c7..1f6c705 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -119,13 +119,13 @@ OPTIONS
 	srcline, period, iregs, brstack, brstacksym, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
-        e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
+        e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
 
-		perf script -f <fields>
+		perf script -F <fields>
 
 	is equivalent to:
 
-		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+		perf script -F trace:<fields> -F sw:<fields> -F hw:<fields>
 
 	i.e., the specified fields apply to all event types if the type string
 	is not given.
@@ -133,9 +133,9 @@ OPTIONS
 	The arguments are processed in the order received. A later usage can
 	reset a prior request. e.g.:
 
-		-f trace: -f comm,tid,time,ip,sym
+		-F trace: -F comm,tid,time,ip,sym
 
-	The first -f suppresses trace events (field list is ""), but then the
+	The first -F suppresses trace events (field list is ""), but then the
 	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
 	warning is given to the user:
 
@@ -143,9 +143,9 @@ OPTIONS
 
 	Alternatively, consider the order:
 
-		-f comm,tid,time,ip,sym -f trace:
+		-F comm,tid,time,ip,sym -F trace:
 
-	The first -f sets the fields for all events and the second -f
+	The first -F sets the fields for all events and the second -F
 	suppresses trace events. The user is given a warning message about
 	the override, and the result of the above is that only S/W and H/W
 	events are displayed with the given fields.
@@ -154,14 +154,14 @@ OPTIONS
 	event type, a message is displayed to the user that the option is
 	ignored for that type. For example:
 
-		$ perf script -f comm,tid,trace
+		$ perf script -F comm,tid,trace
 		'trace' not valid for hardware events. Ignoring.
 		'trace' not valid for software events. Ignoring.
 
 	Alternatively, if the type is given an invalid field is specified it
 	is an error. For example:
 
-        perf script -v -f sw:comm,tid,trace
+        perf script -v -F sw:comm,tid,trace
         'trace' not valid for software events.
 
 	At this point usage is displayed, and perf-script exits.
@@ -170,10 +170,19 @@ OPTIONS
 	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
 	call, return, conditional, system, asynchronous, interrupt,
 	transaction abort, trace begin, trace end, and in transaction,
-	respectively.
+	respectively. Known combinations of flags are printed more nicely e.g.
+	"call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
+	"int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
+	"async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
+	"tr end" for "bE". However the "x" flag will be display separately in those
+	cases e.g. "jcc     (x)" for a condition branch within a transaction.
+
+	The callindent field is synthesized and may have a value when
+	Instruction Trace decoding. For calls and returns, it will display the
+	name of the symbol indented with spaces to reflect the stack depth.
 
 	Finally, a user may not set fields to none for all event types.
-	i.e., -f "" is not allowed.
+	i.e., -F "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
 	/v/v/v/v/ syntax in the following order:
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04f23b4..d96ccd4 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -204,6 +204,38 @@ Aggregate counts per physical processor for system-wide mode measurements.
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
 
+--topdown::
+Print top down level 1 metrics if supported by the CPU. This allows to
+determine bottle necks in the CPU pipeline for CPU bound workloads,
+by breaking the cycles consumed down into frontend bound, backend bound,
+bad speculation and retiring.
+
+Frontend bound means that the CPU cannot fetch and decode instructions fast
+enough. Backend bound means that computation or memory access is the bottle
+neck. Bad Speculation means that the CPU wasted cycles due to branch
+mispredictions and similar issues. Retiring means that the CPU computed without
+an apparently bottleneck. The bottleneck is only the real bottleneck
+if the workload is actually bound by the CPU and not by something else.
+
+For best results it is usually a good idea to use it with interval
+mode like -I 1000, as the bottleneck of workloads can change often.
+
+The top down metrics are collected per core instead of per
+CPU thread. Per core mode is automatically enabled
+and -a (global monitoring) is needed, requiring root rights or
+perf.perf_event_paranoid=-1.
+
+Topdown uses the full Performance Monitoring Unit, and needs
+disabling of the NMI watchdog (as root):
+echo 0 > /proc/sys/kernel/nmi_watchdog
+for best results. Otherwise the bottlenecks may be inconsistent
+on workload with changing phases.
+
+This enables --metric-only, unless overriden with --no-metric-only.
+
+To interpret the results it is usually needed to know on which
+CPUs the workload runs on. If needed the CPUs can be forced using
+taskset.
 
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 31a5c3e..b329c65 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -30,3 +30,7 @@ OPTIONS
 -v::
 --verbose::
 	Be more verbose.
+
+-F::
+--dont-fork::
+	Do not fork child for each test, run all tests within single process.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
new file mode 100644
index 0000000..fdc99fe
--- /dev/null
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -0,0 +1,442 @@
+perf.data format
+
+Uptodate as of v4.7
+
+This document describes the on-disk perf.data format, generated by perf record
+or perf inject and consumed by the other perf tools.
+
+On a high level perf.data contains the events generated by the PMUs, plus metadata.
+
+All fields are in native-endian of the machine that generated the perf.data.
+
+When perf is writing to a pipe it uses a special version of the file
+format that does not rely on seeking to adjust data offsets.  This
+format is not described here. The pipe version can be converted to
+normal perf.data with perf inject.
+
+The file starts with a perf_header:
+
+struct perf_header {
+	char magic[8];		/* PERFILE2 */
+	uint64_t size;		/* size of the header */
+	uint64_t attr_size;	/* size of an attribute in attrs */
+	struct perf_file_section attrs;
+	struct perf_file_section data;
+	struct perf_file_section event_types;
+	uint64_t flags;
+	uint64_t flags1[3];
+};
+
+The magic number identifies the perf file and the version. Current perf versions
+use PERFILE2. Old perf versions generated a version 1 format (PERFFILE). Version 1
+is not described here. The magic number also identifies the endian. When the
+magic value is 64bit byte swapped compared the file is in non-native
+endian.
+
+A perf_file_section contains a pointer to another section of the perf file.
+The header contains three such pointers: for attributes, data and event types.
+
+struct perf_file_section {
+	uint64_t offset;	/* offset from start of file */
+	uint64_t size;		/* size of the section */
+};
+
+Flags section:
+
+The header is followed by different optional headers, described by the bits set
+in flags. Only headers for which the bit is set are included. Each header
+consists of a perf_file_section located after the initial header.
+The respective perf_file_section points to the data of the additional
+header and defines its size.
+
+Some headers consist of strings, which are defined like this:
+
+struct perf_header_string {
+       uint32_t len;
+       char string[len]; /* zero terminated */
+};
+
+Some headers consist of a sequence of strings, which start with a
+
+struct perf_header_string_list {
+     uint32_t nr;
+     struct perf_header_string strings[nr]; /* variable length records */
+};
+
+The bits are the flags bits in a 256 bit bitmap starting with
+flags. These define the valid bits:
+
+	HEADER_RESERVED		= 0,	/* always cleared */
+	HEADER_FIRST_FEATURE	= 1,
+	HEADER_TRACING_DATA	= 1,
+
+Describe me.
+
+	HEADER_BUILD_ID = 2,
+
+The header consists of an sequence of build_id_event. The size of each record
+is defined by header.size (see perf_event.h). Each event defines a ELF build id
+for a executable file name for a pid. An ELF build id is a unique identifier
+assigned by the linker to an executable.
+
+struct build_id_event {
+	struct perf_event_header header;
+	pid_t			 pid;
+	uint8_t			 build_id[24];
+	char			 filename[header.size - offsetof(struct build_id_event, filename)];
+};
+
+	HEADER_HOSTNAME = 3,
+
+A perf_header_string with the hostname where the data was collected
+(uname -n)
+
+	HEADER_OSRELEASE = 4,
+
+A perf_header_string with the os release where the data was collected
+(uname -r)
+
+	HEADER_VERSION = 5,
+
+A perf_header_string with the perf user tool version where the
+data was collected. This is the same as the version of the source tree
+the perf tool was built from.
+
+	HEADER_ARCH = 6,
+
+A perf_header_string with the CPU architecture (uname -m)
+
+	HEADER_NRCPUS = 7,
+
+A structure defining the number of CPUs.
+
+struct nr_cpus {
+       uint32_t nr_cpus_online;
+       uint32_t nr_cpus_available; /* CPUs not yet onlined */
+};
+
+	HEADER_CPUDESC = 8,
+
+A perf_header_string with description of the CPU. On x86 this is the model name
+in /proc/cpuinfo
+
+	HEADER_CPUID = 9,
+
+A perf_header_string with the exact CPU type. On x86 this is
+vendor,family,model,stepping. For example: GenuineIntel,6,69,1
+
+	HEADER_TOTAL_MEM = 10,
+
+An uint64_t with the total memory in bytes.
+
+	HEADER_CMDLINE = 11,
+
+A perf_header_string with the perf command line used to collect the data.
+
+	HEADER_EVENT_DESC = 12,
+
+Another description of the perf_event_attrs, more detailed than header.attrs
+including IDs and names. See perf_event.h or the man page for a description
+of a struct perf_event_attr.
+
+struct {
+       uint32_t nr; /* number of events */
+       uint32_t attr_size; /* size of each perf_event_attr */
+       struct {
+	      struct perf_event_attr attr;  /* size of attr_size */
+	      uint32_t nr_ids;
+	      struct perf_header_string event_string;
+	      uint64_t ids[nr_ids];
+       } events[nr]; /* Variable length records */
+};
+
+	HEADER_CPU_TOPOLOGY = 13,
+
+String lists defining the core and CPU threads topology.
+
+struct {
+       struct perf_header_string_list cores; /* Variable length */
+       struct perf_header_string_list threads; /* Variable length */
+};
+
+Example:
+	sibling cores   : 0-3
+	sibling threads : 0-1
+	sibling threads : 2-3
+
+	HEADER_NUMA_TOPOLOGY = 14,
+
+	A list of NUMA node descriptions
+
+struct {
+       uint32_t nr;
+       struct {
+	      uint32_t nodenr;
+	      uint64_t mem_total;
+	      uint64_t mem_free;
+	      struct perf_header_string cpus;
+       } nodes[nr]; /* Variable length records */
+};
+
+	HEADER_BRANCH_STACK = 15,
+
+Not implemented in perf.
+
+	HEADER_PMU_MAPPINGS = 16,
+
+	A list of PMU structures, defining the different PMUs supported by perf.
+
+struct {
+       uint32_t nr;
+       struct pmu {
+	      uint32_t pmu_type;
+	      struct perf_header_string pmu_name;
+       } [nr]; /* Variable length records */
+};
+
+	HEADER_GROUP_DESC = 17,
+
+	Description of counter groups ({...} in perf syntax)
+
+struct {
+         uint32_t nr;
+         struct {
+		struct perf_header_string string;
+		uint32_t leader_idx;
+		uint32_t nr_members;
+	 } [nr]; /* Variable length records */
+};
+
+	HEADER_AUXTRACE = 18,
+
+Define additional auxtrace areas in the perf.data. auxtrace is used to store
+undecoded hardware tracing information, such as Intel Processor Trace data.
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+	u64			file_offset;
+	u64			sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+	struct list_head	list;
+	size_t			nr;
+	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+	other bits are reserved and should ignored for now
+	HEADER_FEAT_BITS	= 256,
+
+Attributes
+
+This is an array of perf_event_attrs, each attr_size bytes long, which defines
+each event collected. See perf_event.h or the man page for a detailed
+description.
+
+Data
+
+This section is the bulk of the file. It consist of a stream of perf_events
+describing events. This matches the format generated by the kernel.
+See perf_event.h or the manpage for a detailed description.
+
+Some notes on parsing:
+
+Ordering
+
+The events are not necessarily in time stamp order, as they can be
+collected in parallel on different CPUs. If the events should be
+processed in time order they need to be sorted first. It is possible
+to only do a partial sort using the FINISHED_ROUND event header (see
+below). perf record guarantees that there is no reordering over a
+FINISHED_ROUND.
+
+ID vs IDENTIFIER
+
+When the event stream contains multiple events each event is identified
+by an ID. This can be either through the PERF_SAMPLE_ID or the
+PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is
+at a fixed offset from the event header, which allows reliable
+parsing of the header. Relying on ID may be ambigious.
+IDENTIFIER is only supported by newer Linux kernels.
+
+Perf record specific events:
+
+In addition to the kernel generated event types perf record adds its
+own event types (in addition it also synthesizes some kernel events,
+for example MMAP events)
+
+	PERF_RECORD_USER_TYPE_START		= 64,
+	PERF_RECORD_HEADER_ATTR			= 64,
+
+struct attr_event {
+	struct perf_event_header header;
+	struct perf_event_attr attr;
+	uint64_t id[];
+};
+
+	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* depreceated */
+
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+	uint64_t	event_id;
+	char	name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+	struct perf_event_header header;
+	struct perf_trace_event_type event_type;
+};
+
+
+	PERF_RECORD_HEADER_TRACING_DATA		= 66,
+
+Describe me
+
+struct tracing_data_event {
+	struct perf_event_header header;
+	uint32_t size;
+};
+
+	PERF_RECORD_HEADER_BUILD_ID		= 67,
+
+Define a ELF build ID for a referenced executable.
+
+       struct build_id_event;   /* See above */
+
+	PERF_RECORD_FINISHED_ROUND		= 68,
+
+No event reordering over this header. No payload.
+
+	PERF_RECORD_ID_INDEX			= 69,
+
+Map event ids to CPUs and TIDs.
+
+struct id_index_entry {
+	uint64_t id;
+	uint64_t idx;
+	uint64_t cpu;
+	uint64_t tid;
+};
+
+struct id_index_event {
+	struct perf_event_header header;
+	uint64_t nr;
+	struct id_index_entry entries[nr];
+};
+
+	PERF_RECORD_AUXTRACE_INFO		= 70,
+
+Auxtrace type specific information. Describe me
+
+struct auxtrace_info_event {
+	struct perf_event_header header;
+	uint32_t type;
+	uint32_t reserved__; /* For alignment */
+	uint64_t priv[];
+};
+
+	PERF_RECORD_AUXTRACE			= 71,
+
+Defines auxtrace data. Followed by the actual data. The contents of
+the auxtrace data is dependent on the event and the CPU. For example
+for Intel Processor Trace it contains Processor Trace data generated
+by the CPU.
+
+struct auxtrace_event {
+	struct perf_event_header header;
+	uint64_t size;
+	uint64_t offset;
+	uint64_t reference;
+	uint32_t idx;
+	uint32_t tid;
+	uint32_t cpu;
+	uint32_t reserved__; /* For alignment */
+};
+
+struct aux_event {
+	struct perf_event_header header;
+	uint64_t	aux_offset;
+	uint64_t	aux_size;
+	uint64_t	flags;
+};
+
+	PERF_RECORD_AUXTRACE_ERROR		= 72,
+
+Describes an error in hardware tracing
+
+enum auxtrace_error_type {
+	PERF_AUXTRACE_ERROR_ITRACE  = 1,
+	PERF_AUXTRACE_ERROR_MAX
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+	struct perf_event_header header;
+	uint32_t type;
+	uint32_t code;
+	uint32_t cpu;
+	uint32_t pid;
+	uint32_t tid;
+	uint32_t reserved__; /* For alignment */
+	uint64_t ip;
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+Event types
+
+Define the event attributes with their IDs.
+
+An array bound by the perf_file_section size.
+
+	struct {
+		struct perf_event_attr attr;   /* Size defined by header.attr_size */
+		struct perf_file_section ids;
+	}
+
+ids points to a array of uint64_t defining the ids for event attr attr.
+
+References:
+
+include/uapi/linux/perf_event.h
+
+This is the canonical description of the kernel generated perf_events
+and the perf_event_attrs.
+
+perf_events manpage
+
+A manpage describing perf_event and perf_event_attr is here:
+http://web.eece.maine.edu/~vweaver/projects/perf_events/programming.html
+This tends to be slightly behind the kernel include, but has better
+descriptions.  An (typically older) version of the man page may be
+included with the standard Linux man pages, available with "man
+perf_events"
+
+pmu-tools
+
+https://github.com/andikleen/pmu-tools/tree/master/parser
+
+A definition of the perf.data format in python "construct" format is available
+in pmu-tools parser. This allows to read perf.data from python and dump it.
+
+quipper
+
+The quipper C++ parser is available at
+https://chromium.googlesource.com/chromiumos/platform/chromiumos-wide-profiling/
+Unfortunately this parser tends to be many versions behind and may not be able
+to parse data files generated by recent perf.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8c8c6b9..ad2534d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -12,13 +12,23 @@ tools/arch/sparc/include/asm/barrier_32.h
 tools/arch/sparc/include/asm/barrier_64.h
 tools/arch/tile/include/asm/barrier.h
 tools/arch/x86/include/asm/barrier.h
+tools/arch/x86/include/asm/cpufeatures.h
+tools/arch/x86/include/asm/disabled-features.h
+tools/arch/x86/include/asm/required-features.h
+tools/arch/x86/include/uapi/asm/svm.h
+tools/arch/x86/include/uapi/asm/vmx.h
+tools/arch/x86/include/uapi/asm/kvm.h
+tools/arch/x86/include/uapi/asm/kvm_perf.h
+tools/arch/x86/lib/memcpy_64.S
+tools/arch/x86/lib/memset_64.S
+tools/arch/s390/include/uapi/asm/kvm_perf.h
+tools/arch/s390/include/uapi/asm/sie.h
 tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
 tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
-tools/lib/bpf
 tools/lib/api
 tools/lib/bpf
 tools/lib/subcmd
@@ -29,6 +39,9 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
 tools/lib/bitmap.c
+tools/lib/str_error_r.c
+tools/lib/vsprintf.c
+tools/include/asm/alternative-asm.h
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
@@ -52,43 +65,16 @@ tools/include/linux/hash.h
 tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/uapi/linux/bpf.h
+tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/hw_breakpoint.h
+tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
 tools/include/linux/string.h
+tools/include/linux/stringify.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 tools/include/linux/bitmap.h
-include/asm-generic/bitops/arch_hweight.h
-include/asm-generic/bitops/const_hweight.h
-include/asm-generic/bitops/fls64.h
-include/asm-generic/bitops/__fls.h
-include/asm-generic/bitops/fls.h
-include/linux/perf_event.h
-include/linux/list.h
-include/linux/hash.h
-include/linux/stringify.h
-include/linux/swab.h
-arch/*/include/asm/unistd*.h
-arch/*/include/uapi/asm/unistd*.h
-arch/*/include/uapi/asm/perf_regs.h
-arch/*/lib/memcpy*.S
-arch/*/lib/memset*.S
-arch/*/include/asm/*features.h
-include/linux/poison.h
-include/linux/hw_breakpoint.h
-include/uapi/linux/perf_event.h
-include/uapi/linux/bpf.h
-include/uapi/linux/bpf_common.h
-include/uapi/linux/const.h
-include/uapi/linux/swab.h
-include/uapi/linux/hw_breakpoint.h
-arch/x86/include/asm/svm.h
-arch/x86/include/asm/vmx.h
-arch/x86/include/asm/kvm_host.h
-arch/x86/include/uapi/asm/svm.h
-arch/x86/include/uapi/asm/vmx.h
-arch/x86/include/uapi/asm/kvm.h
-arch/x86/include/uapi/asm/kvm_perf.h
-arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/kvm_perf.h
+tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index bde8cba..6641abb 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -81,6 +81,9 @@ include ../scripts/utilities.mak
 #
 # Define NO_LIBBPF if you do not want BPF support
 #
+# Define NO_SDT if you do not want to define SDT event in perf tools,
+# note that it doesn't disable SDT scanning support.
+#
 # Define FEATURES_DUMP to provide features detection dump file
 # and bypass the feature detection
 
@@ -254,7 +257,8 @@ PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
-	$(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
+        CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
@@ -344,6 +348,87 @@ export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(PERF_IN): prepare FORCE
+	@(test -f ../../include/uapi/linux/perf_event.h && ( \
+        (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/linux/hash.h && ( \
+        (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
+        || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
+        (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
+        (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/required-features.h && ( \
+        (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
+        (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/lib/memcpy_64.S && ( \
+        (diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/lib/memset_64.S && ( \
+        (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/__fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/fls64.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index d22e3d0..f98da17 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -1,4 +1,4 @@
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
-libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index e58123a8..02f41db 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,2 +1,2 @@
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
-libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index a87afa9..c116b71 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -1,11 +1,13 @@
 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 #include "../../util/debug.h"
+#endif
 
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
 	switch (regnum) {
 	case UNW_AARCH64_X0:
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index e83c8ce..886dd2a 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,6 +1,7 @@
 #include <stdio.h>
 #include <sys/utsname.h>
 #include "common.h"
+#include "../util/util.h"
 #include "../util/debug.h"
 
 const char *const arm_triplets[] = {
@@ -9,34 +10,44 @@ const char *const arm_triplets[] = {
 	"arm-unknown-linux-",
 	"arm-unknown-linux-gnu-",
 	"arm-unknown-linux-gnueabi-",
+	"arm-linux-gnu-",
+	"arm-linux-gnueabihf-",
+	"arm-none-eabi-",
 	NULL
 };
 
 const char *const arm64_triplets[] = {
 	"aarch64-linux-android-",
+	"aarch64-linux-gnu-",
 	NULL
 };
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
+	"powerpc64-linux-gnu-",
+	"powerpc64le-linux-gnu-",
 	NULL
 };
 
 const char *const s390_triplets[] = {
 	"s390-ibm-linux-",
+	"s390x-linux-gnu-",
 	NULL
 };
 
 const char *const sh_triplets[] = {
 	"sh-unknown-linux-gnu-",
 	"sh64-unknown-linux-gnu-",
+	"sh-linux-gnu-",
+	"sh64-linux-gnu-",
 	NULL
 };
 
 const char *const sparc_triplets[] = {
 	"sparc-unknown-linux-gnu-",
 	"sparc64-unknown-linux-gnu-",
+	"sparc64-linux-gnu-",
 	NULL
 };
 
@@ -49,12 +60,19 @@ const char *const x86_triplets[] = {
 	"i386-pc-linux-gnu-",
 	"i686-linux-android-",
 	"i686-android-linux-",
+	"x86_64-linux-gnu-",
+	"i586-linux-gnu-",
 	NULL
 };
 
 const char *const mips_triplets[] = {
 	"mips-unknown-linux-gnu-",
 	"mipsel-linux-android-",
+	"mips-linux-gnu-",
+	"mips64-linux-gnu-",
+	"mips64el-linux-gnuabi64-",
+	"mips64-linux-gnuabi64-",
+	"mipsel-linux-gnu-",
 	NULL
 };
 
@@ -102,7 +120,7 @@ static int lookup_triplets(const char *const *triplets, const char *name)
  * Return architecture name in a normalized form.
  * The conversion logic comes from the Makefile.
  */
-static const char *normalize_arch(char *arch)
+const char *normalize_arch(char *arch)
 {
 	if (!strcmp(arch, "x86_64"))
 		return "x86";
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index 7529cfb..6b01c73 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -6,5 +6,6 @@
 extern const char *objdump_path;
 
 int perf_env__lookup_objdump(struct perf_env *env);
+const char *normalize_arch(char *arch);
 
 #endif /* ARCH_PERF_COMMON_H */
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index cac6d17..555263e 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,3 +374,5 @@
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
 545	x32	execveat		compat_sys_execveat/ptregs
+534	x32	preadv2			compat_sys_preadv2
+535	x32	pwritev2		compat_sys_pwritev2
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index d4aa567..5c76cc8 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -154,10 +154,6 @@ next_event:
 	err = 0;
 
 out_err:
-	if (evlist) {
-		perf_evlist__disable(evlist);
-		perf_evlist__delete(evlist);
-	}
-
+	perf_evlist__delete(evlist);
 	return err;
 }
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 72193f19..500cf96 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -1,12 +1,16 @@
+#include <errno.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
 #include <linux/types.h>
 #include "perf.h"
 #include "debug.h"
 #include "tests/tests.h"
 #include "cloexec.h"
+#include "util.h"
 #include "arch-tests.h"
 
 static u64 rdpmc(unsigned int counter)
@@ -111,14 +115,14 @@ static int __test__rdpmc(void)
 	if (fd < 0) {
 		pr_err("Error: sys_perf_event_open() syscall returned "
 		       "with %d (%s)\n", fd,
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
 		pr_err("Error: mmap() syscall returned with (%s)\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_close;
 	}
 
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 4659703..f95e6f4 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -3,11 +3,12 @@ libperf-y += tsc.o
 libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += group.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
 
-libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 7a78055..cc1d865 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -37,7 +37,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
 	if (evlist) {
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (intel_pt_pmu &&
 			    evsel->attr.type == intel_pt_pmu->type)
 				found_pt = true;
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
new file mode 100644
index 0000000..37f92aa
--- /dev/null
+++ b/tools/perf/arch/x86/util/group.c
@@ -0,0 +1,27 @@
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/group.h"
+
+/*
+ * Check whether we can use a group for top down.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool arch_topdown_check_group(bool *warn)
+{
+	int n;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+		return false;
+	if (n > 0) {
+		*warn = true;
+		return false;
+	}
+	return true;
+}
+
+void arch_topdown_group_warn(void)
+{
+	fprintf(stderr,
+		"nmi_watchdog enabled with topdown. May give wrong results.\n"
+		"Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 7dc3063..5132775 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -124,7 +124,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	btsr->evlist = evlist;
 	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_bts_pmu->type) {
 			if (intel_bts_evsel) {
 				pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
@@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evsel__disable(evsel);
 	}
@@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evsel__enable(evsel);
 	}
@@ -422,7 +422,7 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(btsr->evlist, evsel) {
+	evlist__for_each_entry(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
 			return perf_evlist__enable_event_idx(btsr->evlist,
 							     evsel, idx);
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a07b960..fb51457 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -131,7 +131,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str,
 	if (!mask)
 		return -EINVAL;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_pt_pmu->type) {
 			*res = intel_pt_masked_bits(mask, evsel->attr.config);
 			return 0;
@@ -511,7 +511,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	ptr->evlist = evlist;
 	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == intel_pt_pmu->type) {
 			if (intel_pt_evsel) {
 				pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n");
@@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evsel__disable(evsel);
 	}
@@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evsel__enable(evsel);
 	}
@@ -1011,7 +1011,7 @@ static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_evsel *evsel;
 
-	evlist__for_each(ptr->evlist, evsel) {
+	evlist__for_each_entry(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
 			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
 							     idx);
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 357f1b1..2e5567c 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -62,6 +62,8 @@ int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
 	struct perf_tsc_conversion tc;
 	int err;
 
+	if (!pc)
+		return 0;
 	err = perf_read_tsc_conversion(pc, &tc);
 	if (err == -EOPNOTSUPP)
 		return 0;
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index db25e93..4f16661 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,12 +1,14 @@
 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 #include "../../util/debug.h"
+#endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
 	int id;
 
@@ -70,7 +72,7 @@ int libunwind__arch_reg_id(int regnum)
 	return id;
 }
 #else
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
 	int id;
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 0999ac5..8024cd5 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -8,18 +8,23 @@
  * many threads and futexes as possible.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <errno.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
-#include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6952db6..936d89d 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -2,18 +2,21 @@
  * Copyright (C) 2015 Davidlohr Bueso.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct worker {
 	int tid;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 7182386..f96e22e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -8,18 +8,21 @@
  * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static u_int32_t futex1 = 0, futex2 = 0;
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 91aaf2a..4a2ecd7 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,18 +7,21 @@
  * it can be used to measure futex_wake() changes.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct thread_data {
 	pthread_t worker;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index f416bd7..87d8f4f 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -8,18 +8,21 @@
  * one or more tasks, and thus the waitqueue is never empty.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 /* all threads will block on the same futex */
 static u_int32_t futex1 = 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 5c3cce0..f700369 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,7 +6,7 @@
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
 
-#include "../../../arch/x86/lib/memcpy_64.S"
+#include "../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
  * NOT executable stack. Otherwise the final linking will assume that
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index de27878..58407aa 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,7 +1,7 @@
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
-#include "../../../arch/x86/lib/memset_64.S"
+#include "../../arch/x86/lib/memset_64.S"
 
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 7500d95..f7f5300 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -4,6 +4,9 @@
  * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
@@ -21,7 +24,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <sys/resource.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 25c8173..9c1034d 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -75,7 +75,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	sample->period = 1;
 	sample->weight = 1;
 
-	he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
+	he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -236,7 +236,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		perf_session__fprintf_dsos(session, stdout);
 
 	total_nr_samples = 0;
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
@@ -339,6 +339,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show event group information together"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+			     stdio__config_color, "always"),
 	OPT_END()
 	};
 	int ret = hists__init();
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d75bded..30e2b2c 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -209,7 +209,7 @@ static int build_id_cache__purge_path(const char *pathname)
 	if (err)
 		goto out;
 
-	strlist__for_each(pos, list) {
+	strlist__for_each_entry(pos, list) {
 		err = build_id_cache__remove_s(pos->s);
 		pr_debug("Removing %s %s: %s\n", pos->s, pathname,
 			 err ? "FAIL" : "Ok");
@@ -343,7 +343,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (add_name_list_str) {
 		list = strlist__new(add_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__add_file(pos->s)) {
 					if (errno == EEXIST) {
 						pr_debug("%s already in the cache\n",
@@ -351,7 +351,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't add %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -361,7 +361,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (remove_name_list_str) {
 		list = strlist__new(remove_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__remove_file(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -369,7 +369,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -379,7 +379,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (purge_name_list_str) {
 		list = strlist__new(purge_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__purge_path(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -387,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -400,7 +400,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	if (update_name_list_str) {
 		list = strlist__new(update_name_list_str, NULL);
 		if (list) {
-			strlist__for_each(pos, list)
+			strlist__for_each_entry(pos, list)
 				if (build_id_cache__update_file(pos->s)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
@@ -408,7 +408,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't update %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -419,8 +419,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
 out:
-	if (session)
-		perf_session__delete(session);
+	perf_session__delete(session);
 
 	return ret;
 }
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index fe1b77f..e4207a2 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -37,23 +37,16 @@ static int show_config(struct perf_config_set *set)
 {
 	struct perf_config_section *section;
 	struct perf_config_item *item;
-	struct list_head *sections;
 
 	if (set == NULL)
 		return -1;
 
-	sections = &set->sections;
-	if (list_empty(sections))
-		return -1;
-
-	list_for_each_entry(section, sections, node) {
-		list_for_each_entry(item, &section->items, node) {
-			char *value = item->value;
+	perf_config_set__for_each_entry(set, section, item) {
+		char *value = item->value;
 
-			if (value)
-				printf("%s.%s=%s\n", section->name,
-				       item->name, value);
-		}
+		if (value)
+			printf("%s.%s=%s\n", section->name,
+			       item->name, value);
 	}
 
 	return 0;
@@ -80,6 +73,10 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (use_user_config)
 		config_exclusive_filename = user_config;
 
+	/*
+	 * At only 'config' sub-command, individually use the config set
+	 * because of reinitializing with options config file location.
+	 */
 	set = perf_config_set__new();
 	if (!set) {
 		ret = -1;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index b97bc15..7ad6e17 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -3,6 +3,7 @@
 #include "perf.h"
 #include "debug.h"
 #include <subcmd/parse-options.h>
+#include "data-convert.h"
 #include "data-convert-bt.h"
 
 typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
@@ -53,14 +54,18 @@ static int cmd_data_convert(int argc, const char **argv,
 			    const char *prefix __maybe_unused)
 {
 	const char *to_ctf     = NULL;
-	bool force = false;
+	struct perf_data_convert_opts opts = {
+		.force = false,
+		.all = false,
+	};
 	const struct option options[] = {
 		OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 		OPT_STRING('i', "input", &input_name, "file", "input file name"),
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
 		OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"),
 #endif
-		OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+		OPT_BOOLEAN('f', "force", &opts.force, "don't complain, do it"),
+		OPT_BOOLEAN(0, "all", &opts.all, "Convert all events"),
 		OPT_END()
 	};
 
@@ -78,7 +83,7 @@ static int cmd_data_convert(int argc, const char **argv,
 
 	if (to_ctf) {
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
-		return bt_convert__perf2ctf(input_name, to_ctf, force);
+		return bt_convert__perf2ctf(input_name, to_ctf, &opts);
 #else
 		pr_err("The libbabeltrace support is not compiled in.\n");
 		return -1;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f7645a4..21ee753 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -310,16 +310,6 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
 	return -1;
 }
 
-static int hists__add_entry(struct hists *hists,
-			    struct addr_location *al,
-			    struct perf_sample *sample)
-{
-	if (__hists__add_entry(hists, al, NULL, NULL, NULL,
-			       sample, true) != NULL)
-		return 0;
-	return -ENOMEM;
-}
-
 static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 				      union perf_event *event,
 				      struct perf_sample *sample,
@@ -336,7 +326,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	if (hists__add_entry(hists, &al, sample)) {
+	if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		goto out_put;
 	}
@@ -373,7 +363,7 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
 	struct perf_evsel *e;
 
-	evlist__for_each(evlist, e) {
+	evlist__for_each_entry(evlist, e) {
 		if (perf_evsel__match2(evsel, e))
 			return e;
 	}
@@ -385,7 +375,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
@@ -666,7 +656,8 @@ static void hists__process(struct hists *hists)
 	hists__precompute(hists);
 	hists__output_resort(hists, NULL);
 
-	hists__fprintf(hists, true, 0, 0, 0, stdout);
+	hists__fprintf(hists, true, 0, 0, 0, stdout,
+		       symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
@@ -690,7 +681,7 @@ static void data_process(void)
 	struct perf_evsel *evsel_base;
 	bool first = true;
 
-	evlist__for_each(evlist_base, evsel_base) {
+	evlist__for_each_entry(evlist_base, evsel_base) {
 		struct hists *hists_base = evsel__hists(evsel_base);
 		struct data__file *d;
 		int i;
@@ -765,9 +756,7 @@ static int __cmd_diff(void)
 
  out_delete:
 	data__for_each_file(i, d) {
-		if (d->session)
-			perf_session__delete(d->session);
-
+		perf_session__delete(d->session);
 		data__free(d);
 	}
 
@@ -1044,7 +1033,7 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 }
 
 static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		       struct perf_evsel *evsel __maybe_unused)
+		       struct hists *hists __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
@@ -1055,7 +1044,7 @@ static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int hpp__width(struct perf_hpp_fmt *fmt,
 		      struct perf_hpp *hpp __maybe_unused,
-		      struct perf_evsel *evsel __maybe_unused)
+		      struct hists *hists __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 8a31f51..e09c428 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -32,7 +32,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	if (session == NULL)
 		return -1;
 
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		perf_evsel__fprintf(pos, details, stdout);
 
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index f9830c9..3bdb2c7 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -4,7 +4,7 @@
  * Builtin help command
  */
 #include "perf.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "builtin.h"
 #include <subcmd/exec-cmd.h>
 #include "common-cmds.h"
@@ -117,7 +117,7 @@ static void exec_woman_emacs(const char *path, const char *page)
 			free(man_page);
 		}
 		warning("failed to exec '%s': %s", path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -150,7 +150,7 @@ static void exec_man_konqueror(const char *path, const char *page)
 			free(man_page);
 		}
 		warning("failed to exec '%s': %s", path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -162,7 +162,7 @@ static void exec_man_man(const char *path, const char *page)
 		path = "man";
 	execlp(path, "man", page, NULL);
 	warning("failed to exec '%s': %s", path,
-		strerror_r(errno, sbuf, sizeof(sbuf)));
+		str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
@@ -175,7 +175,7 @@ static void exec_man_cmd(const char *cmd, const char *page)
 		free(shell_cmd);
 	}
 	warning("failed to exec '%s': %s", cmd,
-		strerror_r(errno, sbuf, sizeof(sbuf)));
+		str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index e5afa8f..73c1c4c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -562,7 +562,7 @@ static void strip_init(struct perf_inject *inject)
 
 	inject->tool.context_switch = perf_event__drop;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evsel->handler = drop_sample;
 }
 
@@ -590,7 +590,7 @@ static bool ok_to_remove(struct perf_evlist *evlist,
 	if (!has_tracking(evsel_to_remove))
 		return true;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->handler != drop_sample) {
 			cnt += 1;
 			if ((evsel->attr.sample_type & COMPAT_MASK) ==
@@ -608,7 +608,7 @@ static void strip_fini(struct perf_inject *inject)
 	struct perf_evsel *evsel, *tmp;
 
 	/* Remove non-synthesized evsels if possible */
-	evlist__for_each_safe(evlist, tmp, evsel) {
+	evlist__for_each_entry_safe(evlist, tmp, evsel) {
 		if (evsel->handler == drop_sample &&
 		    ok_to_remove(evlist, evsel)) {
 			pr_debug("Deleting %s\n", perf_evsel__name(evsel));
@@ -643,7 +643,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
 
 			if (!strcmp(name, "sched:sched_switch")) {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 58adfee..b1d491c 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -4,7 +4,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
@@ -1354,7 +1354,7 @@ static int __cmd_kmem(struct perf_session *session)
 		goto out;
 	}
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
 		    perf_evsel__field(evsel, "pfn")) {
 			use_pfn = true;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 6487c06..5e2127e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -988,7 +988,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	 * Note: exclude_{guest,host} do not apply here.
 	 *       This command processes KVM tracepoints from host only
 	 */
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct perf_event_attr *attr = &pos->attr;
 
 		/* make sure these *are* set */
@@ -1018,13 +1018,13 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		printf("Couldn't create the events: %s\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 
 	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
 		ui__error("Failed to mmap the events: %s\n",
-			  strerror_r(errno, sbuf, sizeof(sbuf)));
+			  str_error_r(errno, sbuf, sizeof(sbuf)));
 		perf_evlist__close(evlist);
 		goto out;
 	}
@@ -1426,11 +1426,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	err = kvm_events_live_report(kvm);
 
 out:
-	if (kvm->session)
-		perf_session__delete(kvm->session);
+	perf_session__delete(kvm->session);
 	kvm->session = NULL;
-	if (kvm->evlist)
-		perf_evlist__delete(kvm->evlist);
+	perf_evlist__delete(kvm->evlist);
 
 	return err;
 }
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 5e22db4..88ee419 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -25,7 +25,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_END()
 	};
 	const char * const list_usage[] = {
-		"perf list [hw|sw|cache|tracepoint|pmu|event_glob]",
+		"perf list [hw|sw|cache|tracepoint|pmu|sdt|event_glob]",
 		NULL
 	};
 
@@ -62,6 +62,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, raw_dump);
+		else if (strcmp(argv[i], "sdt") == 0)
+			print_sdt_events(NULL, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;
 
@@ -76,6 +78,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 
 			s[sep_idx] = '\0';
 			print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
+			print_sdt_events(s, s + sep_idx + 1, raw_dump);
 			free(s);
 		} else {
 			if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -89,6 +92,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump);
 			print_tracepoint_events(NULL, s, raw_dump);
+			print_sdt_events(NULL, s, raw_dump);
 			free(s);
 		}
 	}
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 1dc140c..d608a2c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -67,6 +67,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
 		     parse_record_events),
+	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 9af859b..ee5b421 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,7 +44,7 @@
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
 #define DEFAULT_FUNC_FILTER "!_*"
-#define DEFAULT_LIST_FILTER "*:*"
+#define DEFAULT_LIST_FILTER "*"
 
 /* Session management structure */
 static struct {
@@ -308,7 +308,7 @@ static void pr_err_with_code(const char *msg, int err)
 
 	pr_err("%s", msg);
 	pr_debug(" Reason: %s (Code: %d)",
-		 strerror_r(-err, sbuf, sizeof(sbuf)), err);
+		 str_error_r(-err, sbuf, sizeof(sbuf)), err);
 	pr_err("\n");
 }
 
@@ -363,6 +363,32 @@ out_cleanup:
 	return ret;
 }
 
+static int del_perf_probe_caches(struct strfilter *filter)
+{
+	struct probe_cache *cache;
+	struct strlist *bidlist;
+	struct str_node *nd;
+	int ret;
+
+	bidlist = build_id_cache__list_all(false);
+	if (!bidlist) {
+		ret = -errno;
+		pr_debug("Failed to get buildids: %d\n", ret);
+		return ret ?: -ENOMEM;
+	}
+
+	strlist__for_each_entry(nd, bidlist) {
+		cache = probe_cache__new(nd->s);
+		if (!cache)
+			continue;
+		if (probe_cache__filter_purge(cache, filter) < 0 ||
+		    probe_cache__commit(cache) < 0)
+			pr_warning("Failed to remove entries for %s\n", nd->s);
+		probe_cache__delete(cache);
+	}
+	return 0;
+}
+
 static int perf_del_probe_events(struct strfilter *filter)
 {
 	int ret, ret2, ufd = -1, kfd = -1;
@@ -375,6 +401,9 @@ static int perf_del_probe_events(struct strfilter *filter)
 
 	pr_debug("Delete filter: \'%s\'\n", str);
 
+	if (probe_conf.cache)
+		return del_perf_probe_caches(filter);
+
 	/* Get current event names */
 	ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
 	if (ret < 0)
@@ -389,7 +418,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
 	ret = probe_file__get_events(kfd, filter, klist);
 	if (ret == 0) {
-		strlist__for_each(ent, klist)
+		strlist__for_each_entry(ent, klist)
 			pr_info("Removed event: %s\n", ent->s);
 
 		ret = probe_file__del_strlist(kfd, klist);
@@ -399,7 +428,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
-		strlist__for_each(ent, ulist)
+		strlist__for_each_entry(ent, ulist)
 			pr_info("Removed event: %s\n", ent->s);
 
 		ret2 = probe_file__del_strlist(ufd, ulist);
@@ -512,6 +541,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
+	OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc3fcb5..8f2c16d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -13,6 +13,7 @@
 #include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
+#include "util/config.h"
 
 #include "util/callchain.h"
 #include "util/cgroup.h"
@@ -118,11 +119,10 @@ backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 }
 
 static int
-rb_find_range(struct perf_evlist *evlist,
-	      void *data, int mask, u64 head, u64 old,
-	      u64 *start, u64 *end)
+rb_find_range(void *data, int mask, u64 head, u64 old,
+	      u64 *start, u64 *end, bool backward)
 {
-	if (!evlist->backward) {
+	if (!backward) {
 		*start = old;
 		*end = head;
 		return 0;
@@ -131,9 +131,10 @@ rb_find_range(struct perf_evlist *evlist,
 	return backward_rb_find_range(data, mask, head, start, end);
 }
 
-static int record__mmap_read(struct record *rec, int idx)
+static int
+record__mmap_read(struct record *rec, struct perf_mmap *md,
+		  bool overwrite, bool backward)
 {
-	struct perf_mmap *md = &rec->evlist->mmap[idx];
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
 	u64 end = head, start = old;
@@ -142,8 +143,8 @@ static int record__mmap_read(struct record *rec, int idx)
 	void *buf;
 	int rc = 0;
 
-	if (rb_find_range(rec->evlist, data, md->mask, head,
-			  old, &start, &end))
+	if (rb_find_range(data, md->mask, head,
+			  old, &start, &end, backward))
 		return -1;
 
 	if (start == end)
@@ -156,7 +157,7 @@ static int record__mmap_read(struct record *rec, int idx)
 		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 		md->prev = head;
-		perf_evlist__mmap_consume(rec->evlist, idx);
+		perf_mmap__consume(md, overwrite || backward);
 		return 0;
 	}
 
@@ -181,7 +182,7 @@ static int record__mmap_read(struct record *rec, int idx)
 	}
 
 	md->prev = head;
-	perf_evlist__mmap_consume(rec->evlist, idx);
+	perf_mmap__consume(md, overwrite || backward);
 out:
 	return rc;
 }
@@ -341,6 +342,40 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
 
 #endif
 
+static int record__mmap_evlist(struct record *rec,
+			       struct perf_evlist *evlist)
+{
+	struct record_opts *opts = &rec->opts;
+	char msg[512];
+
+	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+				 opts->auxtrace_mmap_pages,
+				 opts->auxtrace_snapshot_mode) < 0) {
+		if (errno == EPERM) {
+			pr_err("Permission error mapping pages.\n"
+			       "Consider increasing "
+			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
+			       "or try again with a smaller value of -m/--mmap_pages.\n"
+			       "(current value: %u,%u)\n",
+			       opts->mmap_pages, opts->auxtrace_mmap_pages);
+			return -errno;
+		} else {
+			pr_err("failed to mmap with %d (%s)\n", errno,
+				str_error_r(errno, msg, sizeof(msg)));
+			if (errno)
+				return -errno;
+			else
+				return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int record__mmap(struct record *rec)
+{
+	return record__mmap_evlist(rec, rec->evlist);
+}
+
 static int record__open(struct record *rec)
 {
 	char msg[512];
@@ -352,7 +387,7 @@ static int record__open(struct record *rec)
 
 	perf_evlist__config(evlist, opts, &callchain_param);
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
@@ -372,32 +407,14 @@ try_again:
 	if (perf_evlist__apply_filters(evlist, &pos)) {
 		error("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			pos->filter, perf_evsel__name(pos), errno,
-			strerror_r(errno, msg, sizeof(msg)));
+			str_error_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
 	}
 
-	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
-				 opts->auxtrace_mmap_pages,
-				 opts->auxtrace_snapshot_mode) < 0) {
-		if (errno == EPERM) {
-			pr_err("Permission error mapping pages.\n"
-			       "Consider increasing "
-			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
-			       "or try again with a smaller value of -m/--mmap_pages.\n"
-			       "(current value: %u,%u)\n",
-			       opts->mmap_pages, opts->auxtrace_mmap_pages);
-			rc = -errno;
-		} else {
-			pr_err("failed to mmap with %d (%s)\n", errno,
-				strerror_r(errno, msg, sizeof(msg)));
-			if (errno)
-				rc = -errno;
-			else
-				rc = -EINVAL;
-		}
+	rc = record__mmap(rec);
+	if (rc)
 		goto out;
-	}
 
 	session->evlist = evlist;
 	perf_session__set_id_hdr_size(session);
@@ -481,17 +498,30 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
+				    bool backward)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
+	struct perf_mmap *maps;
 
-	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+	if (!evlist)
+		return 0;
 
-		if (rec->evlist->mmap[i].base) {
-			if (record__mmap_read(rec, i) != 0) {
+	maps = backward ? evlist->backward_mmap : evlist->mmap;
+	if (!maps)
+		return 0;
+
+	if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+		return 0;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
+
+		if (maps[i].base) {
+			if (record__mmap_read(rec, &maps[i],
+					      evlist->overwrite, backward) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -511,10 +541,23 @@ static int record__mmap_read_all(struct record *rec)
 	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
+	if (backward)
+		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
 	return rc;
 }
 
+static int record__mmap_read_all(struct record *rec)
+{
+	int err;
+
+	err = record__mmap_read_evlist(rec, rec->evlist, false);
+	if (err)
+		return err;
+
+	return record__mmap_read_evlist(rec, rec->evlist, true);
+}
+
 static void record__init_features(struct record *rec)
 {
 	struct perf_session *session = rec->session;
@@ -561,13 +604,16 @@ record__finish_output(struct record *rec)
 	return;
 }
 
-static int record__synthesize_workload(struct record *rec)
+static int record__synthesize_workload(struct record *rec, bool tail)
 {
 	struct {
 		struct thread_map map;
 		struct thread_map_data map_data;
 	} thread_map;
 
+	if (rec->opts.tail_synthesize != tail)
+		return 0;
+
 	thread_map.map.nr = 1;
 	thread_map.map.map[0].pid = rec->evlist->workload.pid;
 	thread_map.map.map[0].comm = NULL;
@@ -578,7 +624,7 @@ static int record__synthesize_workload(struct record *rec)
 						 rec->opts.proc_map_timeout);
 }
 
-static int record__synthesize(struct record *rec);
+static int record__synthesize(struct record *rec, bool tail);
 
 static int
 record__switch_output(struct record *rec, bool at_exit)
@@ -589,6 +635,10 @@ record__switch_output(struct record *rec, bool at_exit)
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
 
+	record__synthesize(rec, true);
+	if (target__none(&rec->opts.target))
+		record__synthesize_workload(rec, true);
+
 	rec->samples = 0;
 	record__finish_output(rec);
 	err = fetch_current_timestamp(timestamp, sizeof(timestamp));
@@ -611,7 +661,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	/* Output tracking events */
 	if (!at_exit) {
-		record__synthesize(rec);
+		record__synthesize(rec, false);
 
 		/*
 		 * In 'perf record --switch-output' without -a,
@@ -623,7 +673,7 @@ record__switch_output(struct record *rec, bool at_exit)
 		 * perf_event__synthesize_thread_map() for those events.
 		 */
 		if (target__none(&rec->opts.target))
-			record__synthesize_workload(rec);
+			record__synthesize_workload(rec, false);
 	}
 	return fd;
 }
@@ -655,7 +705,29 @@ perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused
 	return 0;
 }
 
-static int record__synthesize(struct record *rec)
+static const struct perf_event_mmap_page *
+perf_evlist__pick_pc(struct perf_evlist *evlist)
+{
+	if (evlist) {
+		if (evlist->mmap && evlist->mmap[0].base)
+			return evlist->mmap[0].base;
+		if (evlist->backward_mmap && evlist->backward_mmap[0].base)
+			return evlist->backward_mmap[0].base;
+	}
+	return NULL;
+}
+
+static const struct perf_event_mmap_page *record__pick_pc(struct record *rec)
+{
+	const struct perf_event_mmap_page *pc;
+
+	pc = perf_evlist__pick_pc(rec->evlist);
+	if (pc)
+		return pc;
+	return NULL;
+}
+
+static int record__synthesize(struct record *rec, bool tail)
 {
 	struct perf_session *session = rec->session;
 	struct machine *machine = &session->machines.host;
@@ -665,6 +737,9 @@ static int record__synthesize(struct record *rec)
 	int fd = perf_data_file__fd(file);
 	int err = 0;
 
+	if (rec->opts.tail_synthesize != tail)
+		return 0;
+
 	if (file->is_pipe) {
 		err = perf_event__synthesize_attrs(tool, session,
 						   process_synthesized_event);
@@ -692,7 +767,7 @@ static int record__synthesize(struct record *rec)
 		}
 	}
 
-	err = perf_event__synth_time_conv(rec->evlist->mmap[0].base, tool,
+	err = perf_event__synth_time_conv(record__pick_pc(rec), tool,
 					  process_synthesized_event, machine);
 	if (err)
 		goto out;
@@ -828,7 +903,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	machine = &session->machines.host;
 
-	err = record__synthesize(rec);
+	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;
 
@@ -888,6 +963,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	for (;;) {
 		unsigned long long hits = rec->samples;
 
+		/*
+		 * rec->evlist->bkw_mmap_state is possible to be
+		 * BKW_MMAP_EMPTY here: when done == true and
+		 * hits != rec->samples in previous round.
+		 *
+		 * perf_evlist__toggle_bkw_mmap ensure we never
+		 * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING.
+		 */
+		if (trigger_is_hit(&switch_output_trigger) || done || draining)
+			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
+
 		if (record__mmap_read_all(rec) < 0) {
 			trigger_error(&auxtrace_snapshot_trigger);
 			trigger_error(&switch_output_trigger);
@@ -907,8 +993,26 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 
 		if (trigger_is_hit(&switch_output_trigger)) {
+			/*
+			 * If switch_output_trigger is hit, the data in
+			 * overwritable ring buffer should have been collected,
+			 * so bkw_mmap_state should be set to BKW_MMAP_EMPTY.
+			 *
+			 * If SIGUSR2 raise after or during record__mmap_read_all(),
+			 * record__mmap_read_all() didn't collect data from
+			 * overwritable ring buffer. Read again.
+			 */
+			if (rec->evlist->bkw_mmap_state == BKW_MMAP_RUNNING)
+				continue;
 			trigger_ready(&switch_output_trigger);
 
+			/*
+			 * Reenable events in overwrite ring buffer after
+			 * record__mmap_read_all(): we should have collected
+			 * data from it.
+			 */
+			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING);
+
 			if (!quiet)
 				fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
 					waking);
@@ -954,7 +1058,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	if (forks && workload_exec_errno) {
 		char msg[STRERR_BUFSIZE];
-		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+		const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
 		pr_err("Workload failed: %s\n", emsg);
 		err = -1;
 		goto out_child;
@@ -963,6 +1067,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (!quiet)
 		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
+	if (target__none(&rec->opts.target))
+		record__synthesize_workload(rec, true);
+
 out_child:
 	if (forks) {
 		int exit_status;
@@ -981,6 +1088,7 @@ out_child:
 	} else
 		status = err;
 
+	record__synthesize(rec, true);
 	/* this will be recalculated during process_buildids() */
 	rec->samples = 0;
 
@@ -1267,6 +1375,8 @@ static struct record record = {
 const char record_callchain_help[] = CALLCHAIN_RECORD_HELP
 	"\n\t\t\t\tDefault: fp";
 
+static bool dry_run;
+
 /*
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
@@ -1303,6 +1413,9 @@ struct option __record_options[] = {
 	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
 			&record.opts.no_inherit_set,
 			"child tasks do not inherit counters"),
+	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
+		    "synthesize non-sample events at the end of output"),
+	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
 		     "number of mmap data pages and AUX area tracing mmap pages",
@@ -1386,6 +1499,8 @@ struct option __record_options[] = {
 		    "append timestamp to output filename"),
 	OPT_BOOLEAN(0, "switch-output", &record.switch_output,
 		    "Switch output when receive SIGUSR2"),
+	OPT_BOOLEAN(0, "dry-run", &dry_run,
+		    "Parse options then exit"),
 	OPT_END()
 };
 
@@ -1455,6 +1570,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (err)
 		return err;
 
+	if (dry_run)
+		return 0;
+
 	err = bpf__setup_stdout(rec->evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
@@ -1508,6 +1626,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 	}
 
+	if (record.opts.overwrite)
+		record.opts.tail_synthesize = true;
+
 	if (rec->evlist->nr_entries == 0 &&
 	    perf_evlist__add_default(rec->evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a87cb33..949e5a1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,7 +8,7 @@
 #include "builtin.h"
 
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 
 #include "util/annotate.h"
 #include "util/color.h"
@@ -361,7 +361,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	struct perf_evsel *pos;
 
 	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 
@@ -370,7 +370,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 			continue;
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
-		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
+		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+			       symbol_conf.use_callchain);
 		fprintf(stdout, "\n\n");
 	}
 
@@ -477,7 +478,7 @@ static int report__collapse_hists(struct report *rep)
 
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
-	evlist__for_each(rep->session->evlist, pos) {
+	evlist__for_each_entry(rep->session->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 
 		if (pos->idx == 0)
@@ -510,7 +511,7 @@ static void report__output_resort(struct report *rep)
 
 	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
-	evlist__for_each(rep->session->evlist, pos)
+	evlist__for_each_entry(rep->session->evlist, pos)
 		perf_evsel__output_resort(pos, &prog);
 
 	ui_progress__finish();
@@ -551,7 +552,7 @@ static int __cmd_report(struct report *rep)
 
 	report__warn_kptr_restrict(rep);
 
-	evlist__for_each(session->evlist, pos)
+	evlist__for_each_entry(session->evlist, pos)
 		rep->nr_entries += evsel__hists(pos)->nr_entries;
 
 	if (use_browser == 0) {
@@ -582,7 +583,7 @@ static int __cmd_report(struct report *rep)
 	 * might be changed during the collapse phase.
 	 */
 	rep->nr_entries = 0;
-	evlist__for_each(session->evlist, pos)
+	evlist__for_each_entry(session->evlist, pos)
 		rep->nr_entries += evsel__hists(pos)->nr_entries;
 
 	if (rep->nr_entries == 0) {
@@ -816,6 +817,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+			     stdio__config_color, "always"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index afa0576..0dfe8df 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -494,7 +494,7 @@ force_again:
 		}
 		pr_err("Error: sys_perf_event_open() syscall returned "
 		       "with %d (%s)\n%s", fd,
-		       strerror_r(errno, sbuf, sizeof(sbuf)), info);
+		       str_error_r(errno, sbuf, sizeof(sbuf)), info);
 		exit(EXIT_FAILURE);
 	}
 	return fd;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e3ce2f3..971ff91 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -21,6 +21,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/thread-stack.h"
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
 #include "asm/bug.h"
@@ -63,6 +64,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
+	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 };
 
 struct output_option {
@@ -89,6 +91,7 @@ struct output_option {
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
+	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -339,7 +342,7 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
  */
 static int perf_session__check_output_opt(struct perf_session *session)
 {
-	int j;
+	unsigned int j;
 	struct perf_evsel *evsel;
 
 	for (j = 0; j < PERF_TYPE_MAX; ++j) {
@@ -369,7 +372,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	if (!no_callchain) {
 		bool use_callchain = false;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
 			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 				use_callchain = true;
 				break;
@@ -388,17 +391,20 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		struct perf_event_attr *attr;
 
 		j = PERF_TYPE_TRACEPOINT;
-		evsel = perf_session__find_first_evtype(session, j);
-		if (evsel == NULL)
-			goto out;
 
-		attr = &evsel->attr;
+		evlist__for_each_entry(session->evlist, evsel) {
+			if (evsel->attr.type != j)
+				continue;
+
+			attr = &evsel->attr;
 
-		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
-			output[j].fields |= PERF_OUTPUT_IP;
-			output[j].fields |= PERF_OUTPUT_SYM;
-			output[j].fields |= PERF_OUTPUT_DSO;
-			set_print_ip_opts(attr);
+			if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+				output[j].fields |= PERF_OUTPUT_IP;
+				output[j].fields |= PERF_OUTPUT_SYM;
+				output[j].fields |= PERF_OUTPUT_DSO;
+				set_print_ip_opts(attr);
+				goto out;
+			}
 		}
 	}
 
@@ -559,6 +565,62 @@ static void print_sample_addr(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_callindent(struct perf_sample *sample,
+				    struct perf_evsel *evsel,
+				    struct thread *thread,
+				    struct addr_location *al)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	size_t depth = thread_stack__depth(thread);
+	struct addr_location addr_al;
+	const char *name = NULL;
+	static int spacing;
+	int len = 0;
+	u64 ip = 0;
+
+	/*
+	 * The 'return' has already been popped off the stack so the depth has
+	 * to be adjusted to match the 'call'.
+	 */
+	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
+		depth += 1;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				ip = sample->addr;
+		} else {
+			ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			ip = sample->ip;
+	}
+
+	if (name)
+		len = printf("%*s%s", (int)depth * 4, "", name);
+	else if (ip)
+		len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+
+	if (len < 0)
+		return;
+
+	/*
+	 * Try to keep the output length from changing frequently so that the
+	 * output lines up more nicely.
+	 */
+	if (len > spacing || (len && len < spacing - 52))
+		spacing = round_up(len + 4, 32);
+
+	if (len < spacing)
+		printf("%*s", spacing - len, "");
+}
+
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
@@ -567,6 +629,9 @@ static void print_sample_bts(struct perf_sample *sample,
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
 
+	if (PRINT_FIELD(CALLINDENT))
+		print_sample_callindent(sample, evsel, thread, al);
+
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
 		unsigned int print_opts = output[attr->type].print_ip_opts;
@@ -603,13 +668,42 @@ static void print_sample_bts(struct perf_sample *sample,
 	printf("\n");
 }
 
+static struct {
+	u32 flags;
+	const char *name;
+} sample_flags[] = {
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"},
+	{PERF_IP_FLAG_BRANCH, "jmp"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |	PERF_IP_FLAG_INTERRUPT, "hw int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"},
+	{0, NULL}
+};
+
 static void print_sample_flags(u32 flags)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
 	const int n = strlen(PERF_IP_FLAG_CHARS);
+	bool in_tx = flags & PERF_IP_FLAG_IN_TX;
+	const char *name = NULL;
 	char str[33];
 	int i, pos = 0;
 
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
+			name = sample_flags[i].name;
+			break;
+		}
+	}
+
 	for (i = 0; i < n; i++, flags >>= 1) {
 		if (flags & 1)
 			str[pos++] = chars[i];
@@ -619,7 +713,11 @@ static void print_sample_flags(u32 flags)
 			str[pos++] = '?';
 	}
 	str[pos] = 0;
-	printf("  %-4s ", str);
+
+	if (name)
+		printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
+	else
+		printf("  %-11s ", str);
 }
 
 struct printer_data {
@@ -717,7 +815,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int max = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		int len = strlen(perf_evsel__name(evsel));
 
 		max = MAX(len, max);
@@ -942,7 +1040,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	if (evsel->attr.type >= PERF_TYPE_MAX)
 		return 0;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->attr.type == evsel->attr.type && pos != evsel)
 			return 0;
 	}
@@ -1668,7 +1766,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 			snprintf(evname, len + 1, "%s", p);
 
 			match = 0;
-			evlist__for_each(session->evlist, pos) {
+			evlist__for_each_entry(session->evlist, pos) {
 				if (!strcmp(perf_evsel__name(pos), evname)) {
 					match = 1;
 					break;
@@ -1870,7 +1968,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
 
-	evlist__for_each(session->evlist, counter) {
+	evlist__for_each_entry(session->evlist, counter) {
 		perf_stat_process_counter(&stat_config, counter);
 		process_stat(counter, round->time);
 	}
@@ -2017,7 +2115,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+		     "callindent", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2256,6 +2355,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	script.session = session;
 	script__setup_sample_type(&script);
 
+	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+		itrace_synth_opts.thread_stack = true;
+
 	session->itrace_synth_opts = &itrace_synth_opts;
 
 	if (cpu_list) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee7ada7..0c16d20 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -59,10 +59,13 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
+#include "util/group.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/group.h"
 #include "asm/bug.h"
 
+#include <api/fs/fs.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
@@ -98,6 +101,15 @@ static const char * transaction_limited_attrs = {
 	"}"
 };
 
+static const char * topdown_attrs[] = {
+	"topdown-total-slots",
+	"topdown-slots-retired",
+	"topdown-recovery-bubbles",
+	"topdown-fetch-bubbles",
+	"topdown-slots-issued",
+	NULL,
+};
+
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
@@ -112,6 +124,7 @@ static volatile pid_t		child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
 static bool			transaction_run;
+static bool			topdown_run			= false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*csv_sep			= NULL;
@@ -124,6 +137,7 @@ static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
+static bool			force_metric_only		= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -276,8 +290,12 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 static int read_counter(struct perf_evsel *counter)
 {
 	int nthreads = thread_map__nr(evsel_list->threads);
-	int ncpus = perf_evsel__nr_cpus(counter);
-	int cpu, thread;
+	int ncpus, cpu, thread;
+
+	if (target__has_cpu(&target))
+		ncpus = perf_evsel__nr_cpus(counter);
+	else
+		ncpus = 1;
 
 	if (!counter->supported)
 		return -ENOENT;
@@ -317,7 +335,7 @@ static void read_counters(bool close_counters)
 {
 	struct perf_evsel *counter;
 
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		if (read_counter(counter))
 			pr_debug("failed to read counter %s\n", counter->name);
 
@@ -403,7 +421,7 @@ static int perf_stat_synthesize_config(bool is_pipe)
 	 * Synthesize other events stuff not carried within
 	 * attr event - unit, scale, name
 	 */
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		if (!counter->supported)
 			continue;
 
@@ -536,7 +554,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
@@ -582,7 +600,7 @@ try_again:
 	if (perf_evlist__apply_filters(evsel_list, &counter)) {
 		error("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			counter->filter, perf_evsel__name(counter), errno,
-			strerror_r(errno, msg, sizeof(msg)));
+			str_error_r(errno, msg, sizeof(msg)));
 		return -1;
 	}
 
@@ -623,7 +641,7 @@ try_again:
 		wait(&status);
 
 		if (workload_exec_errno) {
-			const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
 			pr_err("Workload failed: %s\n", emsg);
 			return -1;
 		}
@@ -1120,7 +1138,7 @@ static void aggr_update_shadow(void)
 
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			val = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 				s2 = aggr_get_id(evsel_list->cpus, cpu);
@@ -1159,7 +1177,7 @@ static void print_aggr(char *prefix)
 
 		id = aggr_map->map[s];
 		first = true;
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1278,7 +1296,7 @@ static void print_no_aggr_metric(char *prefix)
 
 		if (prefix)
 			fputs(prefix, stat_config.output);
-		evlist__for_each(evsel_list, counter) {
+		evlist__for_each_entry(evsel_list, counter) {
 			if (first) {
 				aggr_printout(counter, cpu, 0);
 				first = false;
@@ -1302,7 +1320,15 @@ static int aggr_header_lens[] = {
 	[AGGR_GLOBAL] = 0,
 };
 
-static void print_metric_headers(char *prefix)
+static const char *aggr_header_csv[] = {
+	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_SOCKET] 	= 	"socket,cpus",
+	[AGGR_NONE] 	= 	"cpu,",
+	[AGGR_THREAD] 	= 	"comm-pid,",
+	[AGGR_GLOBAL] 	=	""
+};
+
+static void print_metric_headers(const char *prefix, bool no_indent)
 {
 	struct perf_stat_output_ctx out;
 	struct perf_evsel *counter;
@@ -1313,12 +1339,18 @@ static void print_metric_headers(char *prefix)
 	if (prefix)
 		fprintf(stat_config.output, "%s", prefix);
 
-	if (!csv_output)
+	if (!csv_output && !no_indent)
 		fprintf(stat_config.output, "%*s",
 			aggr_header_lens[stat_config.aggr_mode], "");
+	if (csv_output) {
+		if (stat_config.interval)
+			fputs("time,", stat_config.output);
+		fputs(aggr_header_csv[stat_config.aggr_mode],
+			stat_config.output);
+	}
 
 	/* Print metrics headers only */
-	evlist__for_each(evsel_list, counter) {
+	evlist__for_each_entry(evsel_list, counter) {
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
@@ -1338,28 +1370,40 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output && !metric_only) {
+	if (num_print_interval == 0 && !csv_output) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+			fprintf(output, "#           time socket cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+			fprintf(output, "#           time core         cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_NONE:
-			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+			fprintf(output, "#           time CPU");
+			if (!metric_only)
+				fprintf(output, "                counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_THREAD:
-			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			fprintf(output, "#           time             comm-pid");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_GLOBAL:
 		default:
-			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 		case AGGR_UNSET:
 			break;
 		}
 	}
 
+	if (num_print_interval == 0 && metric_only)
+		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
 }
@@ -1428,8 +1472,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	if (metric_only) {
 		static int num_print_iv;
 
-		if (num_print_iv == 0)
-			print_metric_headers(prefix);
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(prefix, false);
 		if (num_print_iv++ == 25)
 			num_print_iv = 0;
 		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
@@ -1442,11 +1486,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		print_aggr(prefix);
 		break;
 	case AGGR_THREAD:
-		evlist__for_each(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter)
 			print_aggr_thread(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
-		evlist__for_each(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
 		if (metric_only)
 			fputc('\n', stat_config.output);
@@ -1455,7 +1499,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		if (metric_only)
 			print_no_aggr_metric(prefix);
 		else {
-			evlist__for_each(evsel_list, counter)
+			evlist__for_each_entry(evsel_list, counter)
 				print_counter(counter, prefix);
 		}
 		break;
@@ -1520,6 +1564,14 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int enable_metric_only(const struct option *opt __maybe_unused,
+			      const char *s __maybe_unused, int unset)
+{
+	force_metric_only = true;
+	metric_only = !unset;
+	return 0;
+}
+
 static const struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1578,8 +1630,10 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
-	OPT_BOOLEAN(0, "metric-only", &metric_only,
-			"Only print computed metrics. No raw values"),
+	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+			"Only print computed metrics. No raw values", enable_metric_only),
+	OPT_BOOLEAN(0, "topdown", &topdown_run,
+			"measure topdown level 1 statistics"),
 	OPT_END()
 };
 
@@ -1772,12 +1826,62 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 	return 0;
 }
 
+static int topdown_filter_events(const char **attr, char **str, bool use_group)
+{
+	int off = 0;
+	int i;
+	int len = 0;
+	char *s;
+
+	for (i = 0; attr[i]; i++) {
+		if (pmu_have_event("cpu", attr[i])) {
+			len += strlen(attr[i]) + 1;
+			attr[i - off] = attr[i];
+		} else
+			off++;
+	}
+	attr[i - off] = NULL;
+
+	*str = malloc(len + 1 + 2);
+	if (!*str)
+		return -1;
+	s = *str;
+	if (i - off == 0) {
+		*s = 0;
+		return 0;
+	}
+	if (use_group)
+		*s++ = '{';
+	for (i = 0; attr[i]; i++) {
+		strcpy(s, attr[i]);
+		s += strlen(s);
+		*s++ = ',';
+	}
+	if (use_group) {
+		s[-1] = '}';
+		*s = 0;
+	} else
+		s[-1] = 0;
+	return 0;
+}
+
+__weak bool arch_topdown_check_group(bool *warn)
+{
+	*warn = false;
+	return false;
+}
+
+__weak void arch_topdown_group_warn(void)
+{
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
  */
 static int add_default_attributes(void)
 {
+	int err;
 	struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
@@ -1896,7 +2000,6 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
-		int err;
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs, NULL);
@@ -1909,6 +2012,46 @@ static int add_default_attributes(void)
 		return 0;
 	}
 
+	if (topdown_run) {
+		char *str = NULL;
+		bool warn = false;
+
+		if (stat_config.aggr_mode != AGGR_GLOBAL &&
+		    stat_config.aggr_mode != AGGR_CORE) {
+			pr_err("top down event configuration requires --per-core mode\n");
+			return -1;
+		}
+		stat_config.aggr_mode = AGGR_CORE;
+		if (nr_cgroups || !target__has_cpu(&target)) {
+			pr_err("top down event configuration requires system-wide mode (-a)\n");
+			return -1;
+		}
+
+		if (!force_metric_only)
+			metric_only = true;
+		if (topdown_filter_events(topdown_attrs, &str,
+				arch_topdown_check_group(&warn)) < 0) {
+			pr_err("Out of memory\n");
+			return -1;
+		}
+		if (topdown_attrs[0] && str) {
+			if (warn)
+				arch_topdown_group_warn();
+			err = parse_events(evsel_list, str, NULL);
+			if (err) {
+				fprintf(stderr,
+					"Cannot set up top down events %s: %d\n",
+					str, err);
+				free(str);
+				return -1;
+			}
+		} else {
+			fprintf(stderr, "System does not support topdown\n");
+			return -1;
+		}
+		free(str);
+	}
+
 	if (!evsel_list->nr_entries) {
 		if (target__has_cpu(&target))
 			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
@@ -2010,7 +2153,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	const char **argv = session->header.env.cmdline_argv;
 	int argc = session->header.env.nr_cmdline;
 
-	evlist__for_each(evsel_list, counter)
+	evlist__for_each_entry(evsel_list, counter)
 		perf_stat_process_counter(&stat_config, counter);
 
 	if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2a6cc25..bd10868 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -22,7 +22,7 @@
 #include "perf.h"
 
 #include "util/annotate.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/color.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
@@ -295,7 +295,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout);
+		       top->min_percent, stdout, symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
@@ -479,7 +479,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
 				fprintf(stderr, "\nAvailable events:");
 
-				evlist__for_each(top->evlist, top->sym_evsel)
+				evlist__for_each_entry(top->evlist, top->sym_evsel)
 					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
 				prompt_integer(&counter, "Enter details event counter");
@@ -490,7 +490,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 					sleep(1);
 					break;
 				}
-				evlist__for_each(top->evlist, top->sym_evsel)
+				evlist__for_each_entry(top->evlist, top->sym_evsel)
 					if (top->sym_evsel->idx == counter)
 						break;
 			} else
@@ -583,7 +583,7 @@ static void *display_thread_tui(void *arg)
 	 * Zooming in/out UIDs. For now juse use whatever the user passed
 	 * via --uid.
 	 */
-	evlist__for_each(top->evlist, pos) {
+	evlist__for_each_entry(top->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
@@ -888,7 +888,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	perf_evlist__config(evlist, opts, &callchain_param);
 
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {
@@ -907,7 +907,7 @@ try_again:
 
 	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
-			    errno, strerror_r(errno, msg, sizeof(msg)));
+			    errno, str_error_r(errno, msg, sizeof(msg)));
 		goto out_err;
 	}
 
@@ -1028,7 +1028,7 @@ out_delete:
 
 out_err_cpu_topo: {
 	char errbuf[BUFSIZ];
-	const char *err = strerror_r(-ret, errbuf, sizeof(errbuf));
+	const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
 
 	ui__error("Could not read the CPU topology map: %s\n", err);
 	goto out_delete;
@@ -1295,7 +1295,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (perf_evlist__create_maps(top.evlist, target) < 0) {
 		ui__error("Couldn't create thread/CPU maps: %s\n",
-			  errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf)));
+			  errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5c50fe7..b8c6766 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -43,7 +43,6 @@
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
-#include <sys/ptrace.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 
@@ -334,6 +333,10 @@ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
 
 #define SCA_FD syscall_arg__scnprintf_fd
 
+#ifndef AT_FDCWD
+#define AT_FDCWD	-100
+#endif
+
 static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
 					   struct syscall_arg *arg)
 {
@@ -1247,7 +1250,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
 	i = 0;
 
-	strlist__for_each(pos, trace->ev_qualifier) {
+	strlist__for_each_entry(pos, trace->ev_qualifier) {
 		const char *sc = pos->s;
 		int id = syscalltbl__id(trace->sctbl, sc);
 
@@ -1601,7 +1604,7 @@ signed_print:
 		fprintf(trace->output, ") = %ld", ret);
 	} else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
 		char bf[STRERR_BUFSIZE];
-		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
+		const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
 			   *e = audit_errno_to_name(-ret);
 
 		fprintf(trace->output, ") = -1 %s %s", e, emsg);
@@ -2402,7 +2405,7 @@ out_error_apply_filters:
 	fprintf(trace->output,
 		"Failed to set filter \"%s\" on event %s with %d (%s)\n",
 		evsel->filter, perf_evsel__name(evsel), errno,
-		strerror_r(errno, errbuf, sizeof(errbuf)));
+		str_error_r(errno, errbuf, sizeof(errbuf)));
 	goto out_delete_evlist;
 }
 out_error_mem:
@@ -2483,7 +2486,7 @@ static int trace__replay(struct trace *trace)
 		goto out;
 	}
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
 		    (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
 		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
@@ -2550,7 +2553,7 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 	printed += fprintf(fp, "                               (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- -------- --------- --------- --------- ---------     ------\n");
 
-	resort_rb__for_each(nd, syscall_stats) {
+	resort_rb__for_each_entry(nd, syscall_stats) {
 		struct stats *stats = syscall_stats_entry->stats;
 		if (stats) {
 			double min = (double)(stats->min) / NSEC_PER_MSEC;
@@ -2627,7 +2630,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 		return 0;
 	}
 
-	resort_rb__for_each(nd, threads)
+	resort_rb__for_each_entry(nd, threads)
 		printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
 	resort_rb__delete(threads);
@@ -2714,7 +2717,7 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evsel->handler = handler;
 }
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5ad0255..24803c5 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -73,17 +73,25 @@ endif
 #
 #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
 #
+
+libunwind_arch_set_flags = $(eval $(libunwind_arch_set_flags_code))
+define libunwind_arch_set_flags_code
+  FEATURE_CHECK_CFLAGS-libunwind-$(1)  = -I$(LIBUNWIND_DIR)/include
+  FEATURE_CHECK_LDFLAGS-libunwind-$(1) = -L$(LIBUNWIND_DIR)/lib
+endef
+
 ifdef LIBUNWIND_DIR
   LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
   LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64
+  $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch)))
 endif
-LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
 
 # Set per-feature check compilation flags
 FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
@@ -107,7 +115,7 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
-FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -198,11 +206,11 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include
-CFLAGS += -I$(srctree)/include/uapi
-CFLAGS += -I$(srctree)/include
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
 
 # $(obj-perf)      for generated common-cmds.h
 # $(obj-perf)/util for generated bison/flex headers
@@ -249,7 +257,7 @@ else
       LIBC_SUPPORT := 1
     endif
     ifeq ($(LIBC_SUPPORT),1)
-      msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install elfutils-libelf-devel/libelf-dev);
+      msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel);
 
       NO_LIBELF := 1
       NO_DWARF := 1
@@ -301,6 +309,16 @@ ifndef NO_LIBELF
     CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
   endif
 
+  ifeq ($(feature-libelf-gelf_getnote), 1)
+    CFLAGS += -DHAVE_GELF_GETNOTE_SUPPORT
+  else
+    msg := $(warning gelf_getnote() not found on libelf, SDT support disabled);
+  endif
+
+  ifeq ($(feature-libelf-getshdrstrndx), 1)
+    CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT
+  endif
+
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
       msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
@@ -337,6 +355,16 @@ ifndef NO_LIBELF
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
+ifndef NO_SDT
+  ifneq ($(feature-sdt), 1)
+    msg := $(warning No sys/sdt.h found, no SDT events are defined, please install systemtap-sdt-devel or systemtap-sdt-dev);
+    NO_SDT := 1;
+  else
+    CFLAGS += -DHAVE_SDT_EVENT
+    $(call detected,CONFIG_SDT_EVENT)
+  endif
+endif
+
 ifdef PERF_HAVE_JITDUMP
   ifndef NO_DWARF
     $(call detected,CONFIG_JITDUMP)
@@ -351,10 +379,42 @@ ifeq ($(ARCH),powerpc)
 endif
 
 ifndef NO_LIBUNWIND
+  have_libunwind :=
+
+  ifeq ($(feature-libunwind-x86), 1)
+    $(call detected,CONFIG_LIBUNWIND_X86)
+    CFLAGS += -DHAVE_LIBUNWIND_X86_SUPPORT
+    LDFLAGS += -lunwind-x86
+    EXTLIBS_LIBUNWIND += -lunwind-x86
+    have_libunwind = 1
+  endif
+
+  ifeq ($(feature-libunwind-aarch64), 1)
+    $(call detected,CONFIG_LIBUNWIND_AARCH64)
+    CFLAGS += -DHAVE_LIBUNWIND_AARCH64_SUPPORT
+    LDFLAGS += -lunwind-aarch64
+    EXTLIBS_LIBUNWIND += -lunwind-aarch64
+    have_libunwind = 1
+    $(call feature_check,libunwind-debug-frame-aarch64)
+    ifneq ($(feature-libunwind-debug-frame-aarch64), 1)
+      msg := $(warning No debug_frame support found in libunwind-aarch64);
+      CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME_AARCH64
+    endif
+  endif
+
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
+    NO_LOCAL_LIBUNWIND := 1
+  else
+    have_libunwind := 1
+    $(call detected,CONFIG_LOCAL_LIBUNWIND)
+  endif
+
+  ifneq ($(have_libunwind), 1)
     NO_LIBUNWIND := 1
   endif
+else
+  NO_LOCAL_LIBUNWIND := 1
 endif
 
 ifndef NO_LIBBPF
@@ -392,7 +452,7 @@ else
   NO_DWARF_UNWIND := 1
 endif
 
-ifndef NO_LIBUNWIND
+ifndef NO_LOCAL_LIBUNWIND
   ifeq ($(ARCH),$(filter $(ARCH),arm arm64))
     $(call feature_check,libunwind-debug-frame)
     ifneq ($(feature-libunwind-debug-frame), 1)
@@ -403,10 +463,15 @@ ifndef NO_LIBUNWIND
     # non-ARM has no dwarf_find_debug_frame() function:
     CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
   endif
-  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
   EXTLIBS += $(LIBUNWIND_LIBS)
+  LDFLAGS += $(LIBUNWIND_LIBS)
+endif
+
+ifndef NO_LIBUNWIND
+  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
   CFLAGS  += $(LIBUNWIND_CFLAGS)
   LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  EXTLIBS += $(EXTLIBS_LIBUNWIND)
 endif
 
 ifndef NO_LIBAUDIT
@@ -437,7 +502,7 @@ endif
 
 ifndef NO_SLANG
   ifneq ($(feature-libslang), 1)
-    msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+    msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
     NO_SLANG := 1
   else
     # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 3573f31..55daeff 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -59,7 +59,6 @@ static int get_e_machine(struct jitheader *hdr)
 	ssize_t sret;
 	char id[16];
 	int fd, ret = -1;
-	int m = -1;
 	struct {
 		uint16_t e_type;
 		uint16_t e_machine;
@@ -81,11 +80,7 @@ static int get_e_machine(struct jitheader *hdr)
 	if (sret != sizeof(info))
 		goto error;
 
-	m = info.e_machine;
-	if (m < 0)
-		m = 0; /* ELF EM_NONE */
-
-	hdr->elf_mach = m;
+	hdr->elf_mach = info.e_machine;
 	ret = 0;
 error:
 	close(fd);
@@ -491,10 +486,11 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
 		if (sret != 1)
 			goto error;
 	}
-	if (padding_count)
+	if (padding_count) {
 		sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
 		if (sret != 1)
 			goto error;
+	}
 
 	funlockfile(fp);
 	return 0;
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 83a25ce..7ed72a47 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -5,35 +5,18 @@
 #include <sys/types.h>
 #include <sys/syscall.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <asm/barrier.h>
 
 #if defined(__i386__)
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 336
-#endif
-#ifndef __NR_futex
-# define __NR_futex 240
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 224
-#endif
 #endif
 
 #if defined(__x86_64__)
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 298
-#endif
-#ifndef __NR_futex
-# define __NR_futex 202
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 186
-#endif
 #endif
 
 #ifdef __powerpc__
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 15982ce..64c0696 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -10,7 +10,7 @@
 
 #include "util/env.h"
 #include <subcmd/exec-cmd.h>
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/quote.h"
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
@@ -139,8 +139,6 @@ struct option options[] = {
 	OPT_ARGUMENT("html-path", "html-path"),
 	OPT_ARGUMENT("paginate", "paginate"),
 	OPT_ARGUMENT("no-pager", "no-pager"),
-	OPT_ARGUMENT("perf-dir", "perf-dir"),
-	OPT_ARGUMENT("work-tree", "work-tree"),
 	OPT_ARGUMENT("debugfs-dir", "debugfs-dir"),
 	OPT_ARGUMENT("buildid-dir", "buildid-dir"),
 	OPT_ARGUMENT("list-cmds", "list-cmds"),
@@ -200,35 +198,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			use_pager = 0;
 			if (envchanged)
 				*envchanged = 1;
-		} else if (!strcmp(cmd, "--perf-dir")) {
-			if (*argc < 2) {
-				fprintf(stderr, "No directory given for --perf-dir.\n");
-				usage(perf_usage_string);
-			}
-			setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1);
-			if (envchanged)
-				*envchanged = 1;
-			(*argv)++;
-			(*argc)--;
-			handled++;
-		} else if (!prefixcmp(cmd, CMD_PERF_DIR)) {
-			setenv(PERF_DIR_ENVIRONMENT, cmd + strlen(CMD_PERF_DIR), 1);
-			if (envchanged)
-				*envchanged = 1;
-		} else if (!strcmp(cmd, "--work-tree")) {
-			if (*argc < 2) {
-				fprintf(stderr, "No directory given for --work-tree.\n");
-				usage(perf_usage_string);
-			}
-			setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1);
-			if (envchanged)
-				*envchanged = 1;
-			(*argv)++;
-			(*argc)--;
-		} else if (!prefixcmp(cmd, CMD_WORK_TREE)) {
-			setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + strlen(CMD_WORK_TREE), 1);
-			if (envchanged)
-				*envchanged = 1;
 		} else if (!strcmp(cmd, "--debugfs-dir")) {
 			if (*argc < 2) {
 				fprintf(stderr, "No directory given for --debugfs-dir.\n");
@@ -363,11 +332,6 @@ const char perf_version_string[] = PERF_VERSION;
 
 #define RUN_SETUP	(1<<0)
 #define USE_PAGER	(1<<1)
-/*
- * require working tree to be present -- anything uses this needs
- * RUN_SETUP for reading from the configuration file.
- */
-#define NEED_WORK_TREE	(1<<2)
 
 static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
@@ -391,6 +355,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 
 	perf_env__set_cmdline(&perf_env, argc, argv);
 	status = p->fn(argc, argv, prefix);
+	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
 	bpf__clear();
@@ -409,7 +374,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	/* Check for ENOSPC and EIO errors.. */
 	if (fflush(stdout)) {
 		fprintf(stderr, "write failure on standard output: %s",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	if (ferror(stdout)) {
@@ -418,7 +383,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	}
 	if (fclose(stdout)) {
 		fprintf(stderr, "close failed on standard output: %s",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	status = 0;
@@ -532,6 +497,16 @@ void pthread__unblock_sigwinch(void)
 	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		pr_debug("cannot determine cache line size");
+}
+#endif
+
 int main(int argc, const char **argv)
 {
 	const char *cmd;
@@ -544,7 +519,7 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
-	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+	cache_line_size(&cacheline_size);
 
 	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
 		sysctl_perf_event_max_stack = value;
@@ -558,6 +533,7 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
+	perf_config__init();
 	perf_config(perf_default_config, NULL);
 	set_buildid_dir(NULL);
 
@@ -649,7 +625,7 @@ int main(int argc, const char **argv)
 	}
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
-		cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
+		cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
 out:
 	return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cd8f1b1..a7e0f14 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -59,6 +59,8 @@ struct record_opts {
 	bool	     record_switch_events;
 	bool	     all_kernel;
 	bool	     all_user;
+	bool	     tail_synthesize;
+	bool	     overwrite;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
new file mode 100755
index 0000000..eb4dbed
--- /dev/null
+++ b/tools/perf/python/tracepoint.py
@@ -0,0 +1,47 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+
+import perf
+
+class tracepoint(perf.evsel):
+    def __init__(self, sys, name):
+        config = perf.tracepoint(sys, name)
+        perf.evsel.__init__(self,
+                            type   = perf.TYPE_TRACEPOINT,
+                            config = config,
+                            freq = 0, sample_period = 1, wakeup_events = 1,
+                            sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_RAW | perf.SAMPLE_TIME)
+
+def main():
+    tp      = tracepoint("sched", "sched_switch")
+    cpus    = perf.cpu_map()
+    threads = perf.thread_map(-1)
+
+    evlist = perf.evlist(cpus, threads)
+    evlist.add(tp)
+    evlist.open()
+    evlist.mmap()
+
+    while True:
+        evlist.poll(timeout = -1)
+        for cpu in cpus:
+            event = evlist.read_on_cpu(cpu)
+            if not event:
+                continue
+
+            if not isinstance(event, perf.sample_event):
+                continue
+
+            print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
+                   event.sample_time,
+                   event.prev_comm,
+                   event.prev_pid,
+                   event.prev_prio,
+                   event.prev_state,
+                   event.next_comm,
+                   event.next_pid,
+                   event.next_prio)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/scripts/python/bin/stackcollapse-record b/tools/perf/scripts/python/bin/stackcollapse-record
new file mode 100755
index 0000000..9d8f9f0
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-record
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+#
+# stackcollapse.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record "$@"
diff --git a/tools/perf/scripts/python/bin/stackcollapse-report b/tools/perf/scripts/python/bin/stackcollapse-report
new file mode 100755
index 0000000..356b965
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-report
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: produce callgraphs in short form for scripting use
+perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py -- "$@"
diff --git a/tools/perf/scripts/python/stackcollapse.py b/tools/perf/scripts/python/stackcollapse.py
new file mode 100755
index 0000000..5a605f7
--- /dev/null
+++ b/tools/perf/scripts/python/stackcollapse.py
@@ -0,0 +1,125 @@
+# stackcollapse.py - format perf samples with one line per distinct call stack
+#
+# This script's output has two space-separated fields.  The first is a semicolon
+# separated stack including the program name (from the "comm" field) and the
+# function names from the call stack.  The second is a count:
+#
+#  swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2
+#
+# The file is sorted according to the first field.
+#
+# Input may be created and processed using:
+#
+#  perf record -a -g -F 99 sleep 60
+#  perf script report stackcollapse > out.stacks-folded
+#
+# (perf script record stackcollapse works too).
+#
+# Written by Paolo Bonzini <pbonzini@redhat.com>
+# Based on Brendan Gregg's stackcollapse-perf.pl script.
+
+import os
+import sys
+from collections import defaultdict
+from optparse import OptionParser, make_option
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+                '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from EventClass import *
+
+# command line parsing
+
+option_list = [
+    # formatting options for the bottom entry of the stack
+    make_option("--include-tid", dest="include_tid",
+                 action="store_true", default=False,
+                 help="include thread id in stack"),
+    make_option("--include-pid", dest="include_pid",
+                 action="store_true", default=False,
+                 help="include process id in stack"),
+    make_option("--no-comm", dest="include_comm",
+                 action="store_false", default=True,
+                 help="do not separate stacks according to comm"),
+    make_option("--tidy-java", dest="tidy_java",
+                 action="store_true", default=False,
+                 help="beautify Java signatures"),
+    make_option("--kernel", dest="annotate_kernel",
+                 action="store_true", default=False,
+                 help="annotate kernel functions with _[k]")
+]
+
+parser = OptionParser(option_list=option_list)
+(opts, args) = parser.parse_args()
+
+if len(args) != 0:
+    parser.error("unexpected command line argument")
+if opts.include_tid and not opts.include_comm:
+    parser.error("requesting tid but not comm is invalid")
+if opts.include_pid and not opts.include_comm:
+    parser.error("requesting pid but not comm is invalid")
+
+# event handlers
+
+lines = defaultdict(lambda: 0)
+
+def process_event(param_dict):
+    def tidy_function_name(sym, dso):
+        if sym is None:
+            sym = '[unknown]'
+
+        sym = sym.replace(';', ':')
+        if opts.tidy_java:
+            # the original stackcollapse-perf.pl script gives the
+            # example of converting this:
+            #    Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V
+            # to this:
+            #    org/mozilla/javascript/MemberBox:.init
+            sym = sym.replace('<', '')
+            sym = sym.replace('>', '')
+            if sym[0] == 'L' and sym.find('/'):
+                sym = sym[1:]
+            try:
+                sym = sym[:sym.index('(')]
+            except ValueError:
+                pass
+
+        if opts.annotate_kernel and dso == '[kernel.kallsyms]':
+            return sym + '_[k]'
+        else:
+            return sym
+
+    stack = list()
+    if 'callchain' in param_dict:
+        for entry in param_dict['callchain']:
+            entry.setdefault('sym', dict())
+            entry['sym'].setdefault('name', None)
+            entry.setdefault('dso', None)
+            stack.append(tidy_function_name(entry['sym']['name'],
+                                            entry['dso']))
+    else:
+        param_dict.setdefault('symbol', None)
+        param_dict.setdefault('dso', None)
+        stack.append(tidy_function_name(param_dict['symbol'],
+                                        param_dict['dso']))
+
+    if opts.include_comm:
+        comm = param_dict["comm"].replace(' ', '_')
+        sep = "-"
+        if opts.include_pid:
+            comm = comm + sep + str(param_dict['sample']['pid'])
+            sep = "/"
+        if opts.include_tid:
+            comm = comm + sep + str(param_dict['sample']['tid'])
+        stack.append(comm)
+
+    stack_string = ';'.join(reversed(stack))
+    lines[stack_string] = lines[stack_string] + 1
+
+def trace_end():
+    list = lines.keys()
+    list.sort()
+    for stack in list:
+        print "%s %d" % (stack, lines[stack])
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 66a2898..cb20ae1 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -39,6 +39,8 @@ perf-y += stat.o
 perf-y += event_update.o
 perf-y += event-times.o
 perf-y += backward-ring-buffer.o
+perf-y += sdt.o
+perf-y += is_printable_array.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index d9ba991..615780c 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,8 +31,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
 
-		perf_evlist__mmap_read_catchup(evlist, i);
-		while ((event = perf_evlist__mmap_read_backward(evlist, i)) != NULL) {
+		perf_mmap__read_catchup(&evlist->backward_mmap[i]);
+		while ((event = perf_mmap__read_backward(&evlist->backward_mmap[i])) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -60,7 +60,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 	err = perf_evlist__mmap(evlist, mmap_pages, true);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		return TEST_FAIL;
 	}
 
@@ -108,7 +108,11 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 	}
 
 	bzero(&parse_error, sizeof(parse_error));
-	err = parse_events(evlist, "syscalls:sys_enter_prctl", &parse_error);
+	/*
+	 * Set backward bit, ring buffer should be writing from end. Record
+	 * it in aux evlist
+	 */
+	err = parse_events(evlist, "syscalls:sys_enter_prctl/overwrite/", &parse_error);
 	if (err) {
 		pr_debug("Failed to parse tracepoint event, try use root\n");
 		ret = TEST_SKIP;
@@ -117,14 +121,10 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 
 	perf_evlist__config(evlist, &opts, NULL);
 
-	/* Set backward bit, ring buffer should be writing from end */
-	evlist__for_each(evlist, evsel)
-		evsel->attr.write_backward = 1;
-
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 0ec9c2c..e53bc91 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = {
 	.max_entries = 1,
 };
 
-SEC("func=sys_epoll_pwait")
-int bpf_func__sys_epoll_pwait(void *ctx)
+SEC("func=sys_epoll_wait")
+int bpf_func__sys_epoll_wait(void *ctx)
 {
 	int ind =0;
 	int *flag = bpf_map_lookup_elem(&flip_table, &ind);
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f31eed3..fc54064 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -13,13 +13,13 @@
 
 #ifdef HAVE_LIBBPF_SUPPORT
 
-static int epoll_pwait_loop(void)
+static int epoll_wait_loop(void)
 {
 	int i;
 
 	/* Should fail NR_ITERS times */
 	for (i = 0; i < NR_ITERS; i++)
-		epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+		epoll_wait(-(i + 1), NULL, 0, 0);
 	return 0;
 }
 
@@ -61,7 +61,7 @@ static struct {
 		"[basic_bpf_test]",
 		"fix 'perf test LLVM' first",
 		"load bpf object failed",
-		&epoll_pwait_loop,
+		&epoll_wait_loop,
 		(NR_ITERS + 1) / 2,
 	},
 #ifdef HAVE_BPF_PROLOGUE
@@ -143,14 +143,14 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0e95c20..10eb306 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -14,6 +14,8 @@
 #include <subcmd/parse-options.h>
 #include "symbol.h"
 
+static bool dont_fork;
+
 struct test __weak arch_tests[] = {
 	{
 		.func = NULL,
@@ -212,6 +214,18 @@ static struct test generic_tests[] = {
 		.func = test__backward_ring_buffer,
 	},
 	{
+		.desc = "Test cpu map print",
+		.func = test__cpu_map_print,
+	},
+	{
+		.desc = "Test SDT event probing",
+		.func = test__sdt_event,
+	},
+	{
+		.desc = "Test is_printable_array function",
+		.func = test__is_printable_array,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -247,44 +261,51 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char
 
 static int run_test(struct test *test, int subtest)
 {
-	int status, err = -1, child = fork();
+	int status, err = -1, child = dont_fork ? 0 : fork();
 	char sbuf[STRERR_BUFSIZE];
 
 	if (child < 0) {
 		pr_err("failed to fork test: %s\n",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
 	if (!child) {
-		pr_debug("test child forked, pid %d\n", getpid());
-		if (!verbose) {
-			int nullfd = open("/dev/null", O_WRONLY);
-			if (nullfd >= 0) {
-				close(STDERR_FILENO);
-				close(STDOUT_FILENO);
-
-				dup2(nullfd, STDOUT_FILENO);
-				dup2(STDOUT_FILENO, STDERR_FILENO);
-				close(nullfd);
+		if (!dont_fork) {
+			pr_debug("test child forked, pid %d\n", getpid());
+
+			if (!verbose) {
+				int nullfd = open("/dev/null", O_WRONLY);
+
+				if (nullfd >= 0) {
+					close(STDERR_FILENO);
+					close(STDOUT_FILENO);
+
+					dup2(nullfd, STDOUT_FILENO);
+					dup2(STDOUT_FILENO, STDERR_FILENO);
+					close(nullfd);
+				}
+			} else {
+				signal(SIGSEGV, sighandler_dump_stack);
+				signal(SIGFPE, sighandler_dump_stack);
 			}
-		} else {
-			signal(SIGSEGV, sighandler_dump_stack);
-			signal(SIGFPE, sighandler_dump_stack);
 		}
 
 		err = test->func(subtest);
-		exit(err);
+		if (!dont_fork)
+			exit(err);
 	}
 
-	wait(&status);
+	if (!dont_fork) {
+		wait(&status);
 
-	if (WIFEXITED(status)) {
-		err = (signed char)WEXITSTATUS(status);
-		pr_debug("test child finished with %d\n", err);
-	} else if (WIFSIGNALED(status)) {
-		err = -1;
-		pr_debug("test child interrupted\n");
+		if (WIFEXITED(status)) {
+			err = (signed char)WEXITSTATUS(status);
+			pr_debug("test child finished with %d\n", err);
+		} else if (WIFSIGNALED(status)) {
+			err = -1;
+			pr_debug("test child interrupted\n");
+		}
 	}
 
 	return err;
@@ -425,6 +446,8 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('F', "dont-fork", &dont_fork,
+		    "Do not fork for testcase"),
 	OPT_END()
 	};
 	const char * const test_subcommands[] = { "list", NULL };
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 4cb6418..f168a85 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -1,5 +1,12 @@
 #include "tests.h"
+#include <stdio.h>
 #include "cpumap.h"
+#include "event.h"
+#include <string.h>
+#include <linux/bitops.h>
+#include "debug.h"
+
+struct machine;
 
 static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 union perf_event *event,
@@ -86,3 +93,27 @@ int test__cpu_map_synthesize(int subtest __maybe_unused)
 	cpu_map__put(cpus);
 	return 0;
 }
+
+static int cpu_map_print(const char *str)
+{
+	struct cpu_map *map = cpu_map__new(str);
+	char buf[100];
+
+	if (!map)
+		return -1;
+
+	cpu_map__snprint(map, buf, sizeof(buf));
+	return !strcmp(buf, str);
+}
+
+int test__cpu_map_print(int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3,5,7,9,11,13,15,17,19,21-40"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("2-5"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3-6,8-10,24,35-37"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3-6,8-10,24,35-37"));
+	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
+	return 0;
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 8cf0d9e..13725e0 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -251,6 +251,9 @@ int test__dso_data_cache(int subtest __maybe_unused)
 	long nr_end, nr = open_files_cnt();
 	int dso_cnt, limit, i, fd;
 
+	/* Rest the internal dso open counter limit. */
+	reset_fd_limit();
+
 	memset(&machine, 0, sizeof(machine));
 
 	/* set as system limit */
@@ -312,6 +315,9 @@ int test__dso_data_reopen(int subtest __maybe_unused)
 #define dso_1 (dsos[1])
 #define dso_2 (dsos[2])
 
+	/* Rest the internal dso open counter limit. */
+	reset_fd_limit();
+
 	memset(&machine, 0, sizeof(machine));
 
 	/*
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 95fb744..19ef77b 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -37,7 +37,7 @@ static int attach__enable_on_exec(struct perf_evlist *evlist)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		return err;
 	}
 
@@ -200,8 +200,7 @@ static int test_times(int (attach)(struct perf_evlist *),
 		 count.ena, count.run);
 
 out_err:
-	if (evlist)
-		perf_evlist__delete(evlist);
+	perf_evlist__delete(evlist);
 	return !err ? TEST_OK : TEST_FAIL;
 }
 
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 2de4a4f..60926a1 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -80,7 +80,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
 	}
 
 	err = 0;
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
 			--err;
 			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index c809463..a2b5ff9 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -1,4 +1,5 @@
 #include <api/fd/array.h>
+#include <poll.h>
 #include "util/debug.h"
 #include "tests/tests.h"
 
@@ -36,7 +37,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 	}
 
 	fdarray__init_revents(fda, POLLIN);
-	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
 	if (nr_fds != fda->nr_alloc) {
 		pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
 			 nr_fds, fda->nr_alloc);
@@ -44,7 +45,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 	}
 
 	fdarray__init_revents(fda, POLLHUP);
-	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
 	if (nr_fds != 0) {
 		pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
 			 nr_fds, fda->nr_alloc);
@@ -57,7 +58,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 
 	pr_debug("\nfiltering all but fda->entries[2]:");
 	fdarray__fprintf_prefix(fda, "before", stderr);
-	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
 	fdarray__fprintf_prefix(fda, " after", stderr);
 	if (nr_fds != 1) {
 		pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
@@ -78,7 +79,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 
 	pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
 	fdarray__fprintf_prefix(fda, "before", stderr);
-	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
 	fdarray__fprintf_prefix(fda, " after", stderr);
 	if (nr_fds != 2) {
 		pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index a9e3db3..9fd54b7 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -216,6 +216,8 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 
 		/* check callchain entries */
 		root = &he->callchain->node.rb_root;
+
+		TEST_ASSERT_VAL("callchains expected", !RB_EMPTY_ROOT(root));
 		cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
 
 		c = 0;
@@ -666,6 +668,8 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
 	setup_sorting(NULL);
+
+	callchain_param = callchain_param_default;
 	callchain_register_param(&callchain_param);
 
 	err = add_hist_entries(hists, machine);
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index e846f8c..62efb14 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -56,7 +56,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 	 * (perf [perf] main) will be collapsed to an existing entry
 	 * so total 9 entries will be in the tree.
 	 */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
 			struct hist_entry_iter iter = {
 				.evsel = evsel,
@@ -136,7 +136,7 @@ int test__hists_filter(int subtest __maybe_unused)
 	if (err < 0)
 		goto out;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index acf5a13..eddc740 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -72,7 +72,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 * However the second evsel also has a collapsed entry for
 	 * "bash [libc] malloc" so total 9 entries will be in the tree.
 	 */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
 
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
@@ -84,7 +84,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			if (machine__resolve(machine, &al, &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(hists, &al, NULL,
+			he = hists__add_entry(hists, &al, NULL,
 						NULL, NULL, &sample, true);
 			if (he == NULL) {
 				addr_location__put(&al);
@@ -103,7 +103,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			if (machine__resolve(machine, &al, &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(hists, &al, NULL,
+			he = hists__add_entry(hists, &al, NULL,
 						NULL, NULL, &sample, true);
 			if (he == NULL) {
 				addr_location__put(&al);
@@ -301,7 +301,7 @@ int test__hists_link(int subtest __maybe_unused)
 	if (err < 0)
 		goto out;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		hists = evsel__hists(evsel);
 		hists__collapse_resort(hists, NULL);
 
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
new file mode 100644
index 0000000..42e1339
--- /dev/null
+++ b/tools/perf/tests/is_printable_array.c
@@ -0,0 +1,36 @@
+#include <linux/compiler.h>
+#include "tests.h"
+#include "debug.h"
+#include "util.h"
+
+int test__is_printable_array(int subtest __maybe_unused)
+{
+	char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
+	char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
+	struct {
+		char		*buf;
+		unsigned int	 len;
+		int		 ret;
+	} t[] = {
+		{ (char *) "krava",	sizeof("krava"),	1 },
+		{ (char *) "krava",	sizeof("krava") - 1,	0 },
+		{ (char *) "",		sizeof(""),		1 },
+		{ (char *) "",		0,			0 },
+		{ NULL,			0,			0 },
+		{ buf1,			sizeof(buf1),		0 },
+		{ buf2,			sizeof(buf2),		0 },
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(t); i++) {
+		int ret;
+
+		ret = is_printable_array((char *) t[i].buf, t[i].len);
+		if (ret != t[i].ret) {
+			pr_err("failed: test %u\n", i);
+			return TEST_FAIL;
+		}
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index cff564f..b798a4b 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -5,6 +5,7 @@
 #include "llvm.h"
 #include "tests.h"
 #include "debug.h"
+#include "util.h"
 
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index cac15d9..143f4d5 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -81,6 +81,8 @@ make_no_libbionic   := NO_LIBBIONIC=1
 make_no_auxtrace    := NO_AUXTRACE=1
 make_no_libbpf	    := NO_LIBBPF=1
 make_no_libcrypto   := NO_LIBCRYPTO=1
+make_with_babeltrace:= LIBBABELTRACE=1
+make_no_sdt	    := NO_SDT=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -104,7 +106,7 @@ make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
-make_minimal        += NO_LIBCRYPTO=1
+make_minimal        += NO_LIBCRYPTO=1 NO_SDT=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -136,6 +138,7 @@ run += make_no_libaudit
 run += make_no_libbionic
 run += make_no_auxtrace
 run += make_no_libbpf
+run += make_with_babeltrace
 run += make_help
 run += make_doc
 run += make_perf_o
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 359e98f..634bce9 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
@@ -49,7 +52,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
+			 cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}
 
@@ -79,7 +82,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-				 strerror_r(errno, sbuf, sizeof(sbuf)));
+				 str_error_r(errno, sbuf, sizeof(sbuf)));
 			goto out_delete_evlist;
 		}
 
@@ -89,7 +92,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -126,7 +129,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 	}
 
 	err = 0;
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index ad1cb63..c8d9592 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -1,3 +1,6 @@
+/* For the CPU_* macros */
+#include <pthread.h>
+
 #include <api/fs/fs.h>
 #include <linux/err.h>
 #include "evsel.h"
@@ -41,7 +44,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
@@ -62,7 +65,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
 				 cpus->map[cpu],
-				 strerror_r(errno, sbuf, sizeof(sbuf)));
+				 str_error_r(errno, sbuf, sizeof(sbuf)));
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 4344fe4..f52239f 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,6 +6,13 @@
 #include "tests.h"
 #include "debug.h"
 
+#ifndef O_DIRECTORY
+#define O_DIRECTORY    00200000
+#endif
+#ifndef AT_FDCWD
+#define AT_FDCWD       -100
+#endif
+
 int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 {
 	struct record_opts opts = {
@@ -51,14 +58,14 @@ int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 1184f9b..d741412 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -29,7 +29,7 @@ int test__openat_syscall_event(int subtest __maybe_unused)
 	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7865f68..20c2e64 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -32,7 +32,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
@@ -207,7 +207,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong exclude_user",
 				!evsel->attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel",
@@ -1783,8 +1783,8 @@ static int test_pmu_events(void)
 		struct evlist_test e;
 		char name[MAX_NAME];
 
-		if (!strcmp(ent->d_name, ".") ||
-		    !strcmp(ent->d_name, ".."))
+		/* Names containing . are special and cannot be used directly */
+		if (strchr(ent->d_name, '.'))
 			continue;
 
 		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 294c76b..81c6eea 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -44,8 +44,7 @@ static int process_events(union perf_event **events, size_t count)
 	for (i = 0; i < count && !err; i++)
 		err = process_event(&evlist, events[i]);
 
-	if (evlist)
-		perf_evlist__delete(evlist);
+	perf_evlist__delete(evlist);
 
 	return err;
 }
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b836ee6a..8f2e1de 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include <sched.h>
 #include "evlist.h"
 #include "evsel.h"
@@ -104,7 +107,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -115,7 +118,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -126,7 +129,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -138,7 +141,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
new file mode 100644
index 0000000..f59d210
--- /dev/null
+++ b/tools/perf/tests/sdt.c
@@ -0,0 +1,115 @@
+#include <stdio.h>
+#include <sys/epoll.h>
+#include <util/util.h>
+#include <util/evlist.h>
+#include <linux/filter.h>
+#include "tests.h"
+#include "debug.h"
+#include "probe-file.h"
+#include "build-id.h"
+
+/* To test SDT event, we need libelf support to scan elf binary */
+#if defined(HAVE_SDT_EVENT) && defined(HAVE_LIBELF_SUPPORT)
+
+#include <sys/sdt.h>
+
+static int target_function(void)
+{
+	DTRACE_PROBE(perf, test_target);
+	return TEST_OK;
+}
+
+/* Copied from builtin-buildid-cache.c */
+static int build_id_cache__add_file(const char *filename)
+{
+	char sbuild_id[SBUILD_ID_SIZE];
+	u8 build_id[BUILD_ID_SIZE];
+	int err;
+
+	err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+	if (err < 0) {
+		pr_debug("Failed to read build id of %s\n", filename);
+		return err;
+	}
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	err = build_id_cache__add_s(sbuild_id, filename, false, false);
+	if (err < 0)
+		pr_debug("Failed to add build id cache of %s\n", filename);
+	return err;
+}
+
+static char *get_self_path(void)
+{
+	char *buf = calloc(PATH_MAX, sizeof(char));
+
+	if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+		pr_debug("Failed to get correct path of perf\n");
+		free(buf);
+		return NULL;
+	}
+	return buf;
+}
+
+static int search_cached_probe(const char *target,
+			       const char *group, const char *event)
+{
+	struct probe_cache *cache = probe_cache__new(target);
+	int ret = 0;
+
+	if (!cache) {
+		pr_debug("Failed to open probe cache of %s\n", target);
+		return -EINVAL;
+	}
+
+	if (!probe_cache__find_by_name(cache, group, event)) {
+		pr_debug("Failed to find %s:%s in the cache\n", group, event);
+		ret = -ENOENT;
+	}
+	probe_cache__delete(cache);
+
+	return ret;
+}
+
+int test__sdt_event(int subtests __maybe_unused)
+{
+	int ret = TEST_FAIL;
+	char __tempdir[] = "./test-buildid-XXXXXX";
+	char *tempdir = NULL, *myself = get_self_path();
+
+	if (myself == NULL || mkdtemp(__tempdir) == NULL) {
+		pr_debug("Failed to make a tempdir for build-id cache\n");
+		goto error;
+	}
+	/* Note that buildid_dir must be an absolute path */
+	tempdir = realpath(__tempdir, NULL);
+
+	/* At first, scan itself */
+	set_buildid_dir(tempdir);
+	if (build_id_cache__add_file(myself) < 0)
+		goto error_rmdir;
+
+	/* Open a cache and make sure the SDT is stored */
+	if (search_cached_probe(myself, "sdt_perf", "test_target") < 0)
+		goto error_rmdir;
+
+	/* TBD: probing on the SDT event and collect logs */
+
+	/* Call the target and get an event */
+	ret = target_function();
+
+error_rmdir:
+	/* Cleanup temporary buildid dir */
+	rm_rf(tempdir);
+error:
+	free(tempdir);
+	free(myself);
+	return ret;
+}
+#else
+int test__sdt_event(int subtests __maybe_unused)
+{
+	pr_debug("Skip SDT event test because SDT support is not compiled\n");
+	return TEST_SKIP;
+}
+#endif
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 36e8ce1..4c9fd04 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -70,7 +70,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 		err = -errno;
 		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)),
+			 str_error_r(errno, sbuf, sizeof(sbuf)),
 			 knob, (u64)attr.sample_freq);
 		goto out_delete_evlist;
 	}
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	err = perf_evlist__mmap(evlist, 128, true);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 39a689b..7ddbe26 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -432,7 +432,7 @@ int test__switch_tracking(int subtest __maybe_unused)
 	}
 
 	/* Check non-tracking events are not tracking */
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel != tracking_evsel) {
 			if (evsel->attr.mmap || evsel->attr.comm) {
 				pr_debug("Non-tracking event is tracking\n");
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 2dfff7a..01a5ba2 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -91,13 +91,13 @@ int test__task_exit(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("Couldn't open the evlist: %s\n",
-			 strerror_r(-err, sbuf, sizeof(sbuf)));
+			 str_error_r(-err, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c57e72c..9bfc0e0 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -87,6 +87,9 @@ int test__synthesize_stat_round(int subtest);
 int test__event_update(int subtest);
 int test__event_times(int subtest);
 int test__backward_ring_buffer(int subtest);
+int test__cpu_map_print(int subtest);
+int test__sdt_event(int subtest);
+int test__is_printable_array(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index fccde84..cee2a2c 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,13 +1,20 @@
 #include <sys/types.h>
 #include <unistd.h>
+#include <sys/prctl.h>
 #include "tests.h"
 #include "thread_map.h"
 #include "debug.h"
 
+#define NAME	(const char *) "perf"
+#define NAMEUL	(unsigned long) NAME
+
 int test__thread_map(int subtest __maybe_unused)
 {
 	struct thread_map *map;
 
+	TEST_ASSERT_VAL("failed to set process name",
+			!prctl(PR_SET_NAME, NAMEUL, 0, 0, 0));
+
 	/* test map on current pid */
 	map = thread_map__new_by_pid(getpid());
 	TEST_ASSERT_VAL("failed to alloc map", map);
@@ -19,7 +26,7 @@ int test__thread_map(int subtest __maybe_unused)
 			thread_map__pid(map, 0) == getpid());
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(map, 0) &&
-			!strcmp(thread_map__comm(map, 0), "perf"));
+			!strcmp(thread_map__comm(map, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
 			atomic_read(&map->refcnt) == 1);
 	thread_map__put(map);
@@ -51,7 +58,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong nr",   map->nr == 1);
 	TEST_ASSERT_VAL("wrong pid",  map->entries[0].pid == (u64) getpid());
-	TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf"));
+	TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, NAME));
 
 	threads = thread_map__new_event(&event->thread_map);
 	TEST_ASSERT_VAL("failed to alloc map", threads);
@@ -61,7 +68,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 			thread_map__pid(threads, 0) == getpid());
 	TEST_ASSERT_VAL("wrong comm",
 			thread_map__comm(threads, 0) &&
-			!strcmp(thread_map__comm(threads, 0), "perf"));
+			!strcmp(thread_map__comm(threads, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
 			atomic_read(&threads->refcnt) == 1);
 	thread_map__put(threads);
@@ -72,6 +79,9 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
 {
 	struct thread_map *threads;
 
+	TEST_ASSERT_VAL("failed to set process name",
+			!prctl(PR_SET_NAME, NAMEUL, 0, 0, 0));
+
 	/* test map on current pid */
 	threads = thread_map__new_by_pid(getpid());
 	TEST_ASSERT_VAL("failed to alloc map", threads);
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index d64f4a9..b08f21e 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,5 +1,3 @@
-#include <sys/eventfd.h>
-
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE		1
 #endif
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index 021bb48..7461370 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,3 +1,20 @@
+#include <fcntl.h>
+
+#ifndef LOCK_MAND
+#define LOCK_MAND	 32
+#endif
+
+#ifndef LOCK_READ
+#define LOCK_READ	 64
+#endif
+
+#ifndef LOCK_WRITE
+#define LOCK_WRITE	128
+#endif
+
+#ifndef LOCK_RW
+#define LOCK_RW		192
+#endif
 
 static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
 					   struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index e247621..bfd3359 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,5 +1,21 @@
 #include <linux/futex.h>
 
+#ifndef FUTEX_WAIT_BITSET
+#define FUTEX_WAIT_BITSET	  9
+#endif
+#ifndef FUTEX_WAKE_BITSET
+#define FUTEX_WAKE_BITSET	 10
+#endif
+#ifndef FUTEX_WAIT_REQUEUE_PI
+#define FUTEX_WAIT_REQUEUE_PI	 11
+#endif
+#ifndef FUTEX_CMP_REQUEUE_PI
+#define FUTEX_CMP_REQUEUE_PI	 12
+#endif
+#ifndef FUTEX_CLOCK_REALTIME
+#define FUTEX_CLOCK_REALTIME	256
+#endif
+
 static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
 {
 	enum syscall_futex_args {
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 3444a4d..d0a3a8e 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,9 @@
 #include <sys/mman.h>
 
+#ifndef PROT_SEM
+#define PROT_SEM 0x8
+#endif
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {
@@ -16,9 +20,7 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 	P_MMAP_PROT(EXEC);
 	P_MMAP_PROT(READ);
 	P_MMAP_PROT(WRITE);
-#ifdef PROT_SEM
 	P_MMAP_PROT(SEM);
-#endif
 	P_MMAP_PROT(GROWSDOWN);
 	P_MMAP_PROT(GROWSUP);
 #undef P_MMAP_PROT
@@ -31,10 +33,31 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+#ifndef MAP_FIXED
+#define MAP_FIXED		     0x10
+#endif
+
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS		     0x20
+#endif
+
+#ifndef MAP_32BIT
+#define MAP_32BIT		     0x40
+#endif
+
 #ifndef MAP_STACK
-# define MAP_STACK		0x20000
+#define MAP_STACK		  0x20000
 #endif
 
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB		  0x40000
+#endif
+
+#ifndef MAP_UNINITIALIZED
+#define MAP_UNINITIALIZED	0x4000000
+#endif
+
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
@@ -48,26 +71,20 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
-#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
 	P_MMAP_FLAG(FILE);
 	P_MMAP_FLAG(FIXED);
 	P_MMAP_FLAG(GROWSDOWN);
-#ifdef MAP_HUGETLB
 	P_MMAP_FLAG(HUGETLB);
-#endif
 	P_MMAP_FLAG(LOCKED);
 	P_MMAP_FLAG(NONBLOCK);
 	P_MMAP_FLAG(NORESERVE);
 	P_MMAP_FLAG(POPULATE);
 	P_MMAP_FLAG(STACK);
-#ifdef MAP_UNINITIALIZED
 	P_MMAP_FLAG(UNINITIALIZED);
-#endif
 #undef P_MMAP_FLAG
 
 	if (flags)
@@ -78,6 +95,13 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+#ifndef MREMAP_MAYMOVE
+#define MREMAP_MAYMOVE 1
+#endif
+#ifndef MREMAP_FIXED
+#define MREMAP_FIXED 2
+#endif
+
 static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 						  struct syscall_arg *arg)
 {
@@ -90,9 +114,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 	}
 
 	P_MREMAP_FLAG(MAYMOVE);
-#ifdef MREMAP_FIXED
 	P_MREMAP_FLAG(FIXED);
-#endif
 #undef P_MREMAP_FLAG
 
 	if (flags)
@@ -107,6 +129,10 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_HWPOISON		100
 #endif
 
+#ifndef MADV_SOFT_OFFLINE
+#define MADV_SOFT_OFFLINE	101
+#endif
+
 #ifndef MADV_MERGEABLE
 #define MADV_MERGEABLE		 12
 #endif
@@ -115,6 +141,23 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_UNMERGEABLE	 13
 #endif
 
+#ifndef MADV_HUGEPAGE
+#define MADV_HUGEPAGE		 14
+#endif
+
+#ifndef MADV_NOHUGEPAGE
+#define MADV_NOHUGEPAGE		 15
+#endif
+
+#ifndef MADV_DONTDUMP
+#define MADV_DONTDUMP		 16
+#endif
+
+#ifndef MADV_DODUMP
+#define MADV_DODUMP		 17
+#endif
+
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
@@ -131,24 +174,14 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 	P_MADV_BHV(DONTFORK);
 	P_MADV_BHV(DOFORK);
 	P_MADV_BHV(HWPOISON);
-#ifdef MADV_SOFT_OFFLINE
 	P_MADV_BHV(SOFT_OFFLINE);
-#endif
 	P_MADV_BHV(MERGEABLE);
 	P_MADV_BHV(UNMERGEABLE);
-#ifdef MADV_HUGEPAGE
 	P_MADV_BHV(HUGEPAGE);
-#endif
-#ifdef MADV_NOHUGEPAGE
 	P_MADV_BHV(NOHUGEPAGE);
-#endif
-#ifdef MADV_DONTDUMP
 	P_MADV_BHV(DONTDUMP);
-#endif
-#ifdef MADV_DODUMP
 	P_MADV_BHV(DODUMP);
-#endif
-#undef P_MADV_PHV
+#undef P_MADV_BHV
 	default: break;
 	}
 
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index 07fa8a0..1106c89 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -33,7 +33,6 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
 	P_MSG_FLAG(OOB);
 	P_MSG_FLAG(PEEK);
 	P_MSG_FLAG(DONTROUTE);
-	P_MSG_FLAG(TRYHARD);
 	P_MSG_FLAG(CTRUNC);
 	P_MSG_FLAG(PROBE);
 	P_MSG_FLAG(TRUNC);
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 0f3679e..f55a459 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,3 +1,18 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#ifndef O_DIRECT
+#define O_DIRECT	00040000
+#endif
+
+#ifndef O_DIRECTORY
+#define O_DIRECTORY	00200000
+#endif
+
+#ifndef O_NOATIME
+#define O_NOATIME	01000000
+#endif
 
 static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 					       struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index c205bc6..3477529 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -9,6 +9,9 @@
 #ifndef SCHED_DEADLINE
 #define SCHED_DEADLINE 6
 #endif
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
 
 static size_t syscall_arg__scnprintf_sched_policy(char *bf, size_t size,
 						  struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index 213c5a7..356441b 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,5 +1,3 @@
-#include <linux/seccomp.h>
-
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index af68a9d..3eb3edb 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,5 +1,5 @@
 #include "../util.h"
-#include "../cache.h"
+#include "../config.h"
 #include "../../perf.h"
 #include "libslang.h"
 #include "ui.h"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4fc208e..29dc6d2 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -8,6 +8,7 @@
 #include "../../util/sort.h"
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
+#include "../../util/config.h"
 #include <pthread.h>
 
 struct disasm_line_samples {
@@ -222,16 +223,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			} else if (ins__is_call(dl->ins)) {
 				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
 				SLsmg_write_char(' ');
+			} else if (ins__is_ret(dl->ins)) {
+				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+				SLsmg_write_char(' ');
 			} else {
 				ui_browser__write_nstring(browser, " ", 2);
 			}
 		} else {
-			if (strcmp(dl->name, "retq")) {
-				ui_browser__write_nstring(browser, " ", 2);
-			} else {
-				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-				SLsmg_write_char(' ');
-			}
+			ui_browser__write_nstring(browser, " ", 2);
 		}
 
 		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
@@ -842,14 +841,14 @@ show_help:
 				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
 			else if (browser->selection->offset == -1)
 				ui_helpline__puts("Actions are only available for assembly lines.");
-			else if (!browser->selection->ins) {
-				if (strcmp(browser->selection->name, "retq"))
-					goto show_sup_ins;
+			else if (!browser->selection->ins)
+				goto show_sup_ins;
+			else if (ins__is_ret(browser->selection->ins))
 				goto out;
-			} else if (!(annotate_browser__jump(browser) ||
+			else if (!(annotate_browser__jump(browser) ||
 				     annotate_browser__callq(browser, evsel, hbt))) {
 show_sup_ins:
-				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
+				ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
 			}
 			continue;
 		case 't':
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 538bae8..13d4143 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -12,35 +12,17 @@
 #include "../../util/top.h"
 #include "../../arch/common.h"
 
-#include "../browser.h"
+#include "../browsers/hists.h"
 #include "../helpline.h"
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
 #include "annotate.h"
 
-struct hist_browser {
-	struct ui_browser   b;
-	struct hists	    *hists;
-	struct hist_entry   *he_selection;
-	struct map_symbol   *selection;
-	struct hist_browser_timer *hbt;
-	struct pstack	    *pstack;
-	struct perf_env *env;
-	int		     print_seq;
-	bool		     show_dso;
-	bool		     show_headers;
-	float		     min_pcnt;
-	u64		     nr_non_filtered_entries;
-	u64		     nr_hierarchy_entries;
-	u64		     nr_callchain_rows;
-};
-
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists,
-				struct hist_browser_timer *hbt,
-				char *bf, size_t size);
+static int perf_evsel_browser_title(struct hist_browser *browser,
+				    char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -585,7 +567,12 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser, const char *help)
+static int hist_browser__title(struct hist_browser *browser, char *bf, size_t size)
+{
+	return browser->title ? browser->title(browser, bf, size) : 0;
+}
+
+int hist_browser__run(struct hist_browser *browser, const char *help)
 {
 	int key;
 	char title[160];
@@ -595,7 +582,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hists__browser_title(browser->hists, hbt, title, sizeof(title));
+	hist_browser__title(browser, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
@@ -621,8 +608,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists,
-					     hbt, title, sizeof(title));
+			hist_browser__title(browser, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -1470,7 +1456,7 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
 		    column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+		ret = fmt->width(fmt, NULL, browser->hists);
 
 		if (first) {
 			/* for folded sign */
@@ -1531,7 +1517,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret = fmt->header(fmt, &dummy_hpp, hists);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1568,7 +1554,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret = fmt->header(fmt, &dummy_hpp, hists);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1605,7 +1591,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			ret = fmt->header(fmt, &dummy_hpp, hists);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = trim(dummy_hpp.buf);
@@ -1622,21 +1608,38 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	return ret;
 }
 
-static void hist_browser__show_headers(struct hist_browser *browser)
+static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 {
 	char headers[1024];
 
-	if (symbol_conf.report_hierarchy)
-		hists_browser__scnprintf_hierarchy_headers(browser, headers,
-							   sizeof(headers));
-	else
-		hists_browser__scnprintf_headers(browser, headers,
-						 sizeof(headers));
+	hists_browser__scnprintf_hierarchy_headers(browser, headers,
+						   sizeof(headers));
+
+	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+}
+
+static void hists_browser__headers(struct hist_browser *browser)
+{
+	char headers[1024];
+
+	hists_browser__scnprintf_headers(browser, headers,
+					 sizeof(headers));
+
 	ui_browser__gotorc(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }
 
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+	if (symbol_conf.report_hierarchy)
+		hists_browser__hierarchy_headers(browser);
+	else
+		hists_browser__headers(browser);
+}
+
 static void ui_browser__hists_init_top(struct ui_browser *browser)
 {
 	if (browser->top == NULL) {
@@ -2026,7 +2029,7 @@ static int hist_browser__dump(struct hist_browser *browser)
 	fp = fopen(filename, "w");
 	if (fp == NULL) {
 		char bf[64];
-		const char *err = strerror_r(errno, bf, sizeof(bf));
+		const char *err = str_error_r(errno, bf, sizeof(bf));
 		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
 		return -1;
 	}
@@ -2039,27 +2042,50 @@ static int hist_browser__dump(struct hist_browser *browser)
 	return 0;
 }
 
-static struct hist_browser *hist_browser__new(struct hists *hists,
-					      struct hist_browser_timer *hbt,
-					      struct perf_env *env)
+void hist_browser__init(struct hist_browser *browser,
+			struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+
+	browser->hists			= hists;
+	browser->b.refresh		= hist_browser__refresh;
+	browser->b.refresh_dimensions	= hist_browser__refresh_dimensions;
+	browser->b.seek			= ui_browser__hists_seek;
+	browser->b.use_navkeypressed	= true;
+	browser->show_headers		= symbol_conf.show_hist_headers;
+
+	hists__for_each_format(hists, fmt) {
+		perf_hpp__reset_width(fmt, hists);
+		++browser->b.columns;
+	}
+}
+
+struct hist_browser *hist_browser__new(struct hists *hists)
 {
 	struct hist_browser *browser = zalloc(sizeof(*browser));
 
+	if (browser)
+		hist_browser__init(browser, hists);
+
+	return browser;
+}
+
+static struct hist_browser *
+perf_evsel_browser__new(struct perf_evsel *evsel,
+			struct hist_browser_timer *hbt,
+			struct perf_env *env)
+{
+	struct hist_browser *browser = hist_browser__new(evsel__hists(evsel));
+
 	if (browser) {
-		browser->hists = hists;
-		browser->b.refresh = hist_browser__refresh;
-		browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
-		browser->b.seek = ui_browser__hists_seek;
-		browser->b.use_navkeypressed = true;
-		browser->show_headers = symbol_conf.show_hist_headers;
-		browser->hbt = hbt;
-		browser->env = env;
+		browser->hbt   = hbt;
+		browser->env   = env;
+		browser->title = perf_evsel_browser_title;
 	}
-
 	return browser;
 }
 
-static void hist_browser__delete(struct hist_browser *browser)
+void hist_browser__delete(struct hist_browser *browser)
 {
 	free(browser);
 }
@@ -2080,10 +2106,11 @@ static inline bool is_report_browser(void *timer)
 	return timer == NULL;
 }
 
-static int hists__browser_title(struct hists *hists,
-				struct hist_browser_timer *hbt,
+static int perf_evsel_browser_title(struct hist_browser *browser,
 				char *bf, size_t size)
 {
+	struct hist_browser_timer *hbt = browser->hbt;
+	struct hists *hists = browser->hists;
 	char unit;
 	int printed;
 	const struct dso *dso = hists->dso_filter;
@@ -2640,7 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    struct perf_env *env)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = hist_browser__new(hists, hbt, env);
+	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
 	struct branch_info *bi;
 #define MAX_OPTIONS  16
 	char *options[MAX_OPTIONS];
@@ -2649,7 +2676,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	int key = -1;
 	char buf[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
-	struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON					\
 	"h/?/F1        Show this window\n"				\
@@ -2708,18 +2734,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	memset(options, 0, sizeof(options));
 	memset(actions, 0, sizeof(actions));
 
-	hists__for_each_format(browser->hists, fmt) {
-		perf_hpp__reset_width(fmt, hists);
-		/*
-		 * This is done just once, and activates the horizontal scrolling
-		 * code in the ui_browser code, it would be better to have a the
-		 * counter in the perf_hpp code, but I couldn't find doing it here
-		 * works, FIXME by setting this in hist_browser__new, for now, be
-		 * clever 8-)
-		 */
-		++browser->b.columns;
-	}
-
 	if (symbol_conf.col_width_list_str)
 		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
 
@@ -3185,7 +3199,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
 	ui_helpline__push("Press ESC to exit");
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		const char *ev_name = perf_evsel__name(pos);
 		size_t line_len = strlen(ev_name) + 7;
 
@@ -3216,7 +3230,7 @@ single_entry:
 		struct perf_evsel *pos;
 
 		nr_entries = 0;
-		evlist__for_each(evlist, pos) {
+		evlist__for_each_entry(evlist, pos) {
 			if (perf_evsel__is_group_leader(pos))
 				nr_entries++;
 		}
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
new file mode 100644
index 0000000..39bd0f2
--- /dev/null
+++ b/tools/perf/ui/browsers/hists.h
@@ -0,0 +1,32 @@
+#ifndef _PERF_UI_BROWSER_HISTS_H_
+#define _PERF_UI_BROWSER_HISTS_H_ 1
+
+#include "ui/browser.h"
+
+struct hist_browser {
+	struct ui_browser   b;
+	struct hists	    *hists;
+	struct hist_entry   *he_selection;
+	struct map_symbol   *selection;
+	struct hist_browser_timer *hbt;
+	struct pstack	    *pstack;
+	struct perf_env	    *env;
+	int		     print_seq;
+	bool		     show_dso;
+	bool		     show_headers;
+	float		     min_pcnt;
+	u64		     nr_non_filtered_entries;
+	u64		     nr_hierarchy_entries;
+	u64		     nr_callchain_rows;
+
+	/* Get title string. */
+	int                  (*title)(struct hist_browser *browser,
+			     char *bf, size_t size);
+};
+
+struct hist_browser *hist_browser__new(struct hists *hists);
+void hist_browser__delete(struct hist_browser *browser);
+int hist_browser__run(struct hist_browser *browser, const char *help);
+void hist_browser__init(struct hist_browser *browser,
+			struct hists *hists);
+#endif /* _PERF_UI_BROWSER_HISTS_H_ */
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 932adfa..c5f3677 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				strcat(buf, "+");
 			first_col = false;
 
-			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			fmt->header(fmt, &hpp, hists);
 			strcat(buf, ltrim(rtrim(hpp.buf)));
 		}
 	}
@@ -627,7 +627,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
 	gtk_container_add(GTK_CONTAINER(window), vbox);
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 52e7fc4..00b9192 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,4 +1,5 @@
 #include "../util.h"
+#include "../../util/util.h"
 #include "../../util/debug.h"
 #include "gtk.h"
 
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 700fb3c..5b74a7e 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -5,6 +5,7 @@
 #include "../debug.h"
 #include "helpline.h"
 #include "ui.h"
+#include "../util.h"
 
 char ui_helpline__current[512];
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index af07ffb..4274969 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -215,9 +215,10 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 
 static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 			 struct perf_hpp *hpp __maybe_unused,
-			 struct perf_evsel *evsel)
+			 struct hists *hists)
 {
 	int len = fmt->user_len ?: fmt->len;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 
 	if (symbol_conf.event_group)
 		len = max(len, evsel->nr_members * fmt->len);
@@ -229,9 +230,9 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct perf_evsel *evsel)
+			  struct hists *hists)
 {
-	int len = hpp__width_fn(fmt, hpp, evsel);
+	int len = hpp__width_fn(fmt, hpp, hists);
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
@@ -632,7 +633,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 		else
 			ret += 2;
 
-		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret += fmt->width(fmt, &dummy_hpp, hists);
 	}
 
 	if (verbose && hists__has(hists, sym)) /* Addr + origin */
@@ -657,7 +658,7 @@ unsigned int hists__overhead_width(struct hists *hists)
 		else
 			ret += 2;
 
-		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		ret += fmt->width(fmt, &dummy_hpp, hists);
 	}
 
 	return ret;
@@ -765,7 +766,7 @@ int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
 	if (!symbol_conf.report_hierarchy)
 		return 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		hists = evsel__hists(evsel);
 
 		perf_hpp_list__for_each_sort_list(list, fmt) {
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ba51fa8..1f6b099 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -60,6 +60,13 @@ static inline int setup_gtk_browser(void) { return -1; }
 static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {}
 #endif
 
+int stdio__config_color(const struct option *opt __maybe_unused,
+			const char *mode, int unset __maybe_unused)
+{
+	perf_use_color_default = perf_config_colorbool("color.ui", mode, -1);
+	return 0;
+}
+
 void setup_browser(bool fallback_to_pager)
 {
 	if (use_browser < 2 && (!isatty(1) || dump_trace))
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 560eb47..f04a631 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -492,14 +492,15 @@ out:
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
-			       struct hists *hists,
-			       char *bf, size_t bfsz, FILE *fp)
+			       char *bf, size_t bfsz, FILE *fp,
+			       bool use_callchain)
 {
 	int ret;
 	struct perf_hpp hpp = {
 		.buf		= bf,
 		.size		= size,
 	};
+	struct hists *hists = he->hists;
 	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
@@ -512,7 +513,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (symbol_conf.use_callchain)
+	if (use_callchain)
 		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
@@ -548,7 +549,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				    struct perf_hpp_list_node, list);
 
 	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists_to_evsel(hists));
+		fmt->header(fmt, hpp, hists);
 		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
@@ -568,7 +569,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				header_width += fprintf(fp, "+");
 			first_col = false;
 
-			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			fmt->header(fmt, hpp, hists);
 
 			header_width += fprintf(fp, "%s", trim(hpp->buf));
 		}
@@ -589,7 +590,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 			fprintf(fp, "%s", sep ?: "..");
 		first_col = false;
 
-		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		width = fmt->width(fmt, hpp, hists);
 		fprintf(fp, "%.*s", width, dots);
 	}
 
@@ -606,7 +607,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				width++;  /* for '+' sign between column header */
 			first_col = false;
 
-			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+			width += fmt->width(fmt, hpp, hists);
 		}
 
 		if (width > header_width)
@@ -622,47 +623,31 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	return 2;
 }
 
-size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-		      int max_cols, float min_pcnt, FILE *fp)
+static int
+hists__fprintf_hierarchy_headers(struct hists *hists,
+				 struct perf_hpp *hpp,
+				 FILE *fp)
 {
-	struct perf_hpp_fmt *fmt;
 	struct perf_hpp_list_node *fmt_node;
-	struct rb_node *nd;
-	size_t ret = 0;
-	unsigned int width;
-	const char *sep = symbol_conf.field_sep;
-	int nr_rows = 0;
-	char bf[96];
-	struct perf_hpp dummy_hpp = {
-		.buf	= bf,
-		.size	= sizeof(bf),
-	};
-	bool first = true;
-	size_t linesz;
-	char *line = NULL;
-	unsigned indent;
-
-	init_rem_hits();
-
-	hists__for_each_format(hists, fmt)
-		perf_hpp__reset_width(fmt, hists);
-
-	if (symbol_conf.col_width_list_str)
-		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+	struct perf_hpp_fmt *fmt;
 
-	if (!show_header)
-		goto print_entries;
+	list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+			perf_hpp__reset_width(fmt, hists);
+	}
 
-	fprintf(fp, "# ");
+	return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
+}
 
-	if (symbol_conf.report_hierarchy) {
-		list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
-			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
-				perf_hpp__reset_width(fmt, hists);
-		}
-		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
-		goto print_entries;
-	}
+static int
+hists__fprintf_standard_headers(struct hists *hists,
+				struct perf_hpp *hpp,
+				FILE *fp)
+{
+	struct perf_hpp_fmt *fmt;
+	unsigned int width;
+	const char *sep = symbol_conf.field_sep;
+	bool first = true;
 
 	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
@@ -673,16 +658,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
-		fprintf(fp, "%s", bf);
+		fmt->header(fmt, hpp, hists);
+		fprintf(fp, "%s", hpp->buf);
 	}
 
 	fprintf(fp, "\n");
-	if (max_rows && ++nr_rows >= max_rows)
-		goto out;
 
 	if (sep)
-		goto print_entries;
+		return 1;
 
 	first = true;
 
@@ -699,20 +682,60 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		width = fmt->width(fmt, hpp, hists);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
 
 	fprintf(fp, "\n");
-	if (max_rows && ++nr_rows >= max_rows)
-		goto out;
-
 	fprintf(fp, "#\n");
-	if (max_rows && ++nr_rows >= max_rows)
+	return 3;
+}
+
+static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+{
+	char bf[96];
+	struct perf_hpp dummy_hpp = {
+		.buf	= bf,
+		.size	= sizeof(bf),
+	};
+
+	fprintf(fp, "# ");
+
+	if (symbol_conf.report_hierarchy)
+		return hists__fprintf_hierarchy_headers(hists, &dummy_hpp, fp);
+	else
+		return hists__fprintf_standard_headers(hists, &dummy_hpp, fp);
+
+}
+
+size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
+		      int max_cols, float min_pcnt, FILE *fp,
+		      bool use_callchain)
+{
+	struct perf_hpp_fmt *fmt;
+	struct rb_node *nd;
+	size_t ret = 0;
+	const char *sep = symbol_conf.field_sep;
+	int nr_rows = 0;
+	size_t linesz;
+	char *line = NULL;
+	unsigned indent;
+
+	init_rem_hits();
+
+	hists__for_each_format(hists, fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
+	if (show_header)
+		nr_rows += hists__fprintf_headers(hists, fp);
+
+	if (max_rows && nr_rows >= max_rows)
 		goto out;
 
-print_entries:
 	linesz = hists__sort_list_width(hists) + 3 + 1;
 	linesz += perf_hpp__color_overhead();
 	line = malloc(linesz);
@@ -734,7 +757,7 @@ print_entries:
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 7dfeba0..4ea2ba8 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
@@ -6,6 +7,7 @@
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
+#include "../../util/util.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index ab88383..4b6fb6c 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -26,4 +26,8 @@ static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
 
 void ui__refresh_dimensions(bool force);
 
+struct option;
+
+int stdio__config_color(const struct option *opt, const char *mode, int unset);
+
 #endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8c6c8a0..2fa7d8b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -70,6 +70,7 @@ libperf-y += stat.o
 libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
+libperf-y += str_error_r.o
 libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
@@ -84,6 +85,7 @@ libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
+libperf-y += vsprintf.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -99,7 +101,10 @@ libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
 
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LIBUNWIND_X86)      += libunwind/x86_32.o
+libperf-$(CONFIG_LIBUNWIND_AARCH64)  += libunwind/arm64.o
 
 libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
 
@@ -108,6 +113,7 @@ libperf-y += scripting-engines/
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 libperf-y += demangle-java.o
+libperf-y += demangle-rust.o
 
 ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
@@ -170,6 +176,14 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index c0b43ee..6455471 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -1,4 +1,6 @@
 #include "cache.h"
+#include "util.h"
+#include "config.h"
 
 static const char *alias_key;
 static char *alias_val;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7e5a1e8..e9825fe 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,6 +354,15 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
+static struct ins_ops ret_ops = {
+	.scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_ret(const struct ins *ins)
+{
+	return ins->ops == &ret_ops;
+}
+
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
@@ -444,6 +453,7 @@ static struct ins instructions[] = {
 	{ .name = "xadd",  .ops  = &mov_ops, },
 	{ .name = "xbeginl", .ops  = &jump_ops, },
 	{ .name = "xbeginq", .ops  = &jump_ops, },
+	{ .name = "retq",  .ops  = &ret_ops, },
 };
 
 static int ins__key_cmp(const void *name, const void *insp)
@@ -1512,13 +1522,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	const char *d_filename;
 	const char *evsel_name = perf_evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
 	struct disasm_line *pos, *queue = NULL;
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0;
 	int more = 0;
 	u64 len;
 	int width = 8;
-	int namelen, evsel_name_len, graph_dotted_len;
+	int graph_dotted_len;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1530,17 +1541,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 		d_filename = basename(filename);
 
 	len = symbol__size(sym);
-	namelen = strlen(d_filename);
-	evsel_name_len = strlen(evsel_name);
 
 	if (perf_evsel__is_group_event(evsel))
 		width *= evsel->nr_members;
 
-	printf(" %-*.*s|	Source code & Disassembly of %s for %s\n",
-	       width, width, "Percent", d_filename, evsel_name);
+	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
+	       width, width, "Percent", d_filename, evsel_name, h->sum);
 
-	graph_dotted_len = width + namelen + evsel_name_len;
-	printf("-%-*.*s-----------------------------------------\n",
+	printf("%-*.*s----\n",
 	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
 	if (verbose)
@@ -1676,11 +1684,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	return 0;
 }
 
-int hist_entry__annotate(struct hist_entry *he, size_t privsize)
-{
-	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
-}
-
 bool ui__has_annotation(void)
 {
 	return use_browser == 1 && perf_hpp_list.sym;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 9241f8c..a23084f 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -48,6 +48,7 @@ struct ins {
 
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 
 struct annotation;
@@ -156,8 +157,6 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
 
-int hist_entry__annotate(struct hist_entry *he, size_t privsize);
-
 int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 767989e..ac5f0d7 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -63,6 +63,7 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
@@ -82,6 +83,7 @@ struct itrace_synth_opts {
 	bool			calls;
 	bool			returns;
 	bool			callchain;
+	bool			thread_stack;
 	bool			last_branch;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 493307d..1f12e4e 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -37,6 +37,9 @@ DEFINE_PRINT_FN(info, 1)
 DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
+	bool is_tp;
+	char *sys_name;
+	char *evt_name;
 	struct perf_probe_event pev;
 	bool need_prologue;
 	struct bpf_insn *insns_buf;
@@ -118,6 +121,8 @@ clear_prog_priv(struct bpf_program *prog __maybe_unused,
 	cleanup_perf_probe_events(&priv->pev, 1);
 	zfree(&priv->insns_buf);
 	zfree(&priv->type_mapping);
+	zfree(&priv->sys_name);
+	zfree(&priv->evt_name);
 	free(priv);
 }
 
@@ -269,7 +274,8 @@ nextline:
 }
 
 static int
-parse_prog_config(const char *config_str, struct perf_probe_event *pev)
+parse_prog_config(const char *config_str, const char **p_main_str,
+		  bool *is_tp, struct perf_probe_event *pev)
 {
 	int err;
 	const char *main_str = parse_prog_config_kvpair(config_str, pev);
@@ -277,6 +283,22 @@ parse_prog_config(const char *config_str, struct perf_probe_event *pev)
 	if (IS_ERR(main_str))
 		return PTR_ERR(main_str);
 
+	*p_main_str = main_str;
+	if (!strchr(main_str, '=')) {
+		/* Is a tracepoint event? */
+		const char *s = strchr(main_str, ':');
+
+		if (!s) {
+			pr_debug("bpf: '%s' is not a valid tracepoint\n",
+				 config_str);
+			return -BPF_LOADER_ERRNO__CONFIG;
+		}
+
+		*is_tp = true;
+		return 0;
+	}
+
+	*is_tp = false;
 	err = parse_perf_probe_command(main_str, pev);
 	if (err < 0) {
 		pr_debug("bpf: '%s' is not a valid config string\n",
@@ -292,7 +314,8 @@ config_bpf_program(struct bpf_program *prog)
 {
 	struct perf_probe_event *pev = NULL;
 	struct bpf_prog_priv *priv = NULL;
-	const char *config_str;
+	const char *config_str, *main_str;
+	bool is_tp = false;
 	int err;
 
 	/* Initialize per-program probing setting */
@@ -313,10 +336,19 @@ config_bpf_program(struct bpf_program *prog)
 	pev = &priv->pev;
 
 	pr_debug("bpf: config program '%s'\n", config_str);
-	err = parse_prog_config(config_str, pev);
+	err = parse_prog_config(config_str, &main_str, &is_tp, pev);
 	if (err)
 		goto errout;
 
+	if (is_tp) {
+		char *s = strchr(main_str, ':');
+
+		priv->is_tp = true;
+		priv->sys_name = strndup(main_str, s - main_str);
+		priv->evt_name = strdup(s + 1);
+		goto set_priv;
+	}
+
 	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
 		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
 			 config_str, PERF_BPF_PROBE_GROUP);
@@ -339,7 +371,8 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
-	err = bpf_program__set_private(prog, priv, clear_prog_priv);
+set_priv:
+	err = bpf_program__set_priv(prog, priv, clear_prog_priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;
@@ -380,15 +413,14 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
 		     struct bpf_insn *orig_insns, int orig_insns_cnt,
 		     struct bpf_prog_prep_result *res)
 {
+	struct bpf_prog_priv *priv = bpf_program__priv(prog);
 	struct probe_trace_event *tev;
 	struct perf_probe_event *pev;
-	struct bpf_prog_priv *priv;
 	struct bpf_insn *buf;
 	size_t prologue_cnt = 0;
 	int i, err;
 
-	err = bpf_program__get_private(prog, (void **)&priv);
-	if (err || !priv)
+	if (IS_ERR(priv) || !priv || priv->is_tp)
 		goto errout;
 
 	pev = &priv->pev;
@@ -535,17 +567,21 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping,
 
 static int hook_load_preprocessor(struct bpf_program *prog)
 {
+	struct bpf_prog_priv *priv = bpf_program__priv(prog);
 	struct perf_probe_event *pev;
-	struct bpf_prog_priv *priv;
 	bool need_prologue = false;
 	int err, i;
 
-	err = bpf_program__get_private(prog, (void **)&priv);
-	if (err || !priv) {
+	if (IS_ERR(priv) || !priv) {
 		pr_debug("Internal error when hook preprocessor\n");
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
 
+	if (priv->is_tp) {
+		priv->need_prologue = false;
+		return 0;
+	}
+
 	pev = &priv->pev;
 	for (i = 0; i < pev->ntevs; i++) {
 		struct probe_trace_event *tev = &pev->tevs[i];
@@ -607,9 +643,18 @@ int bpf__probe(struct bpf_object *obj)
 		if (err)
 			goto out;
 
-		err = bpf_program__get_private(prog, (void **)&priv);
-		if (err || !priv)
+		priv = bpf_program__priv(prog);
+		if (IS_ERR(priv) || !priv) {
+			err = PTR_ERR(priv);
 			goto out;
+		}
+
+		if (priv->is_tp) {
+			bpf_program__set_tracepoint(prog);
+			continue;
+		}
+
+		bpf_program__set_kprobe(prog);
 		pev = &priv->pev;
 
 		err = convert_perf_probe_events(pev, 1);
@@ -645,13 +690,12 @@ int bpf__unprobe(struct bpf_object *obj)
 {
 	int err, ret = 0;
 	struct bpf_program *prog;
-	struct bpf_prog_priv *priv;
 
 	bpf_object__for_each_program(prog, obj) {
+		struct bpf_prog_priv *priv = bpf_program__priv(prog);
 		int i;
 
-		err = bpf_program__get_private(prog, (void **)&priv);
-		if (err || !priv)
+		if (IS_ERR(priv) || !priv || priv->is_tp)
 			continue;
 
 		for (i = 0; i < priv->pev.ntevs; i++) {
@@ -694,26 +738,34 @@ int bpf__load(struct bpf_object *obj)
 	return 0;
 }
 
-int bpf__foreach_tev(struct bpf_object *obj,
-		     bpf_prog_iter_callback_t func,
-		     void *arg)
+int bpf__foreach_event(struct bpf_object *obj,
+		       bpf_prog_iter_callback_t func,
+		       void *arg)
 {
 	struct bpf_program *prog;
 	int err;
 
 	bpf_object__for_each_program(prog, obj) {
+		struct bpf_prog_priv *priv = bpf_program__priv(prog);
 		struct probe_trace_event *tev;
 		struct perf_probe_event *pev;
-		struct bpf_prog_priv *priv;
 		int i, fd;
 
-		err = bpf_program__get_private(prog,
-				(void **)&priv);
-		if (err || !priv) {
+		if (IS_ERR(priv) || !priv) {
 			pr_debug("bpf: failed to get private field\n");
 			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
 
+		if (priv->is_tp) {
+			fd = bpf_program__fd(prog);
+			err = (*func)(priv->sys_name, priv->evt_name, fd, arg);
+			if (err) {
+				pr_debug("bpf: tracepoint call back failed, stop iterate\n");
+				return err;
+			}
+			continue;
+		}
+
 		pev = &priv->pev;
 		for (i = 0; i < pev->ntevs; i++) {
 			tev = &pev->tevs[i];
@@ -731,7 +783,7 @@ int bpf__foreach_tev(struct bpf_object *obj,
 				return fd;
 			}
 
-			err = (*func)(tev, fd, arg);
+			err = (*func)(tev->group, tev->event, fd, arg);
 			if (err) {
 				pr_debug("bpf: call back failed, stop iterate\n");
 				return err;
@@ -897,15 +949,12 @@ bpf_map_priv__clone(struct bpf_map_priv *priv)
 static int
 bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 {
-	struct bpf_map_priv *priv;
-	const char *map_name;
-	int err;
+	const char *map_name = bpf_map__name(map);
+	struct bpf_map_priv *priv = bpf_map__priv(map);
 
-	map_name = bpf_map__get_name(map);
-	err = bpf_map__get_private(map, (void **)&priv);
-	if (err) {
+	if (IS_ERR(priv)) {
 		pr_debug("Failed to get private from map %s\n", map_name);
-		return err;
+		return PTR_ERR(priv);
 	}
 
 	if (!priv) {
@@ -916,7 +965,7 @@ bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 		}
 		INIT_LIST_HEAD(&priv->ops_list);
 
-		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+		if (bpf_map__set_priv(map, priv, bpf_map_priv__clear)) {
 			free(priv);
 			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
@@ -948,30 +997,26 @@ static int
 __bpf_map__config_value(struct bpf_map *map,
 			struct parse_events_term *term)
 {
-	struct bpf_map_def def;
 	struct bpf_map_op *op;
-	const char *map_name;
-	int err;
+	const char *map_name = bpf_map__name(map);
+	const struct bpf_map_def *def = bpf_map__def(map);
 
-	map_name = bpf_map__get_name(map);
-
-	err = bpf_map__get_def(map, &def);
-	if (err) {
+	if (IS_ERR(def)) {
 		pr_debug("Unable to get map definition from '%s'\n",
 			 map_name);
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
 
-	if (def.type != BPF_MAP_TYPE_ARRAY) {
+	if (def->type != BPF_MAP_TYPE_ARRAY) {
 		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
 			 map_name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
 	}
-	if (def.key_size < sizeof(unsigned int)) {
+	if (def->key_size < sizeof(unsigned int)) {
 		pr_debug("Map %s has incorrect key size\n", map_name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
 	}
-	switch (def.value_size) {
+	switch (def->value_size) {
 	case 1:
 	case 2:
 	case 4:
@@ -1014,12 +1059,10 @@ __bpf_map__config_event(struct bpf_map *map,
 			struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
-	struct bpf_map_def def;
+	const struct bpf_map_def *def;
 	struct bpf_map_op *op;
-	const char *map_name;
-	int err;
+	const char *map_name = bpf_map__name(map);
 
-	map_name = bpf_map__get_name(map);
 	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
 	if (!evsel) {
 		pr_debug("Event (for '%s') '%s' doesn't exist\n",
@@ -1027,18 +1070,18 @@ __bpf_map__config_event(struct bpf_map *map,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
 	}
 
-	err = bpf_map__get_def(map, &def);
-	if (err) {
+	def = bpf_map__def(map);
+	if (IS_ERR(def)) {
 		pr_debug("Unable to get map definition from '%s'\n",
 			 map_name);
-		return err;
+		return PTR_ERR(def);
 	}
 
 	/*
 	 * No need to check key_size and value_size:
 	 * kernel has already checked them.
 	 */
-	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+	if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
 		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
 			 map_name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
@@ -1087,9 +1130,8 @@ config_map_indices_range_check(struct parse_events_term *term,
 			       const char *map_name)
 {
 	struct parse_events_array *array = &term->array;
-	struct bpf_map_def def;
+	const struct bpf_map_def *def;
 	unsigned int i;
-	int err;
 
 	if (!array->nr_ranges)
 		return 0;
@@ -1099,8 +1141,8 @@ config_map_indices_range_check(struct parse_events_term *term,
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
 
-	err = bpf_map__get_def(map, &def);
-	if (err) {
+	def = bpf_map__def(map);
+	if (IS_ERR(def)) {
 		pr_debug("ERROR: Unable to get map definition from '%s'\n",
 			 map_name);
 		return -BPF_LOADER_ERRNO__INTERNAL;
@@ -1111,7 +1153,7 @@ config_map_indices_range_check(struct parse_events_term *term,
 		size_t length = array->ranges[i].length;
 		unsigned int idx = start + length - 1;
 
-		if (idx >= def.max_entries) {
+		if (idx >= def->max_entries) {
 			pr_debug("ERROR: index %d too large\n", idx);
 			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
 		}
@@ -1147,7 +1189,7 @@ bpf__obj_config_map(struct bpf_object *obj,
 		goto out;
 	}
 
-	map = bpf_object__get_map_by_name(obj, map_name);
+	map = bpf_object__find_map_by_name(obj, map_name);
 	if (!map) {
 		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
 		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
@@ -1204,14 +1246,14 @@ out:
 }
 
 typedef int (*map_config_func_t)(const char *name, int map_fd,
-				 struct bpf_map_def *pdef,
+				 const struct bpf_map_def *pdef,
 				 struct bpf_map_op *op,
 				 void *pkey, void *arg);
 
 static int
 foreach_key_array_all(map_config_func_t func,
 		      void *arg, const char *name,
-		      int map_fd, struct bpf_map_def *pdef,
+		      int map_fd, const struct bpf_map_def *pdef,
 		      struct bpf_map_op *op)
 {
 	unsigned int i;
@@ -1231,7 +1273,7 @@ foreach_key_array_all(map_config_func_t func,
 static int
 foreach_key_array_ranges(map_config_func_t func, void *arg,
 			 const char *name, int map_fd,
-			 struct bpf_map_def *pdef,
+			 const struct bpf_map_def *pdef,
 			 struct bpf_map_op *op)
 {
 	unsigned int i, j;
@@ -1261,15 +1303,12 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 			   void *arg)
 {
 	int err, map_fd;
-	const char *name;
 	struct bpf_map_op *op;
-	struct bpf_map_def def;
-	struct bpf_map_priv *priv;
+	const struct bpf_map_def *def;
+	const char *name = bpf_map__name(map);
+	struct bpf_map_priv *priv = bpf_map__priv(map);
 
-	name = bpf_map__get_name(map);
-
-	err = bpf_map__get_private(map, (void **)&priv);
-	if (err) {
+	if (IS_ERR(priv)) {
 		pr_debug("ERROR: failed to get private from map %s\n", name);
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
@@ -1278,29 +1317,29 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 		return 0;
 	}
 
-	err = bpf_map__get_def(map, &def);
-	if (err) {
+	def = bpf_map__def(map);
+	if (IS_ERR(def)) {
 		pr_debug("ERROR: failed to get definition from map %s\n", name);
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
-	map_fd = bpf_map__get_fd(map);
+	map_fd = bpf_map__fd(map);
 	if (map_fd < 0) {
 		pr_debug("ERROR: failed to get fd from map %s\n", name);
 		return map_fd;
 	}
 
 	list_for_each_entry(op, &priv->ops_list, list) {
-		switch (def.type) {
+		switch (def->type) {
 		case BPF_MAP_TYPE_ARRAY:
 		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 			switch (op->key_type) {
 			case BPF_MAP_KEY_ALL:
 				err = foreach_key_array_all(func, arg, name,
-							    map_fd, &def, op);
+							    map_fd, def, op);
 				break;
 			case BPF_MAP_KEY_RANGES:
 				err = foreach_key_array_ranges(func, arg, name,
-							       map_fd, &def,
+							       map_fd, def,
 							       op);
 				break;
 			default:
@@ -1410,7 +1449,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
 
 static int
 apply_obj_config_map_for_key(const char *name, int map_fd,
-			     struct bpf_map_def *pdef __maybe_unused,
+			     const struct bpf_map_def *pdef,
 			     struct bpf_map_op *op,
 			     void *pkey, void *arg __maybe_unused)
 {
@@ -1475,9 +1514,9 @@ int bpf__apply_obj_config(void)
 
 #define bpf__for_each_stdout_map(pos, obj, objtmp)	\
 	bpf__for_each_map(pos, obj, objtmp) 		\
-		if (bpf_map__get_name(pos) && 		\
+		if (bpf_map__name(pos) && 		\
 			(strcmp("__bpf_stdout__", 	\
-				bpf_map__get_name(pos)) == 0))
+				bpf_map__name(pos)) == 0))
 
 int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 {
@@ -1489,10 +1528,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 	bool need_init = false;
 
 	bpf__for_each_stdout_map(map, obj, tmp) {
-		struct bpf_map_priv *priv;
+		struct bpf_map_priv *priv = bpf_map__priv(map);
 
-		err = bpf_map__get_private(map, (void **)&priv);
-		if (err)
+		if (IS_ERR(priv))
 			return -BPF_LOADER_ERRNO__INTERNAL;
 
 		/*
@@ -1520,10 +1558,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 	}
 
 	bpf__for_each_stdout_map(map, obj, tmp) {
-		struct bpf_map_priv *priv;
+		struct bpf_map_priv *priv = bpf_map__priv(map);
 
-		err = bpf_map__get_private(map, (void **)&priv);
-		if (err)
+		if (IS_ERR(priv))
 			return -BPF_LOADER_ERRNO__INTERNAL;
 		if (priv)
 			continue;
@@ -1533,7 +1570,7 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 			if (!priv)
 				return -ENOMEM;
 
-			err = bpf_map__set_private(map, priv, bpf_map_priv__clear);
+			err = bpf_map__set_priv(map, priv, bpf_map_priv__clear);
 			if (err) {
 				bpf_map_priv__clear(map, priv);
 				return err;
@@ -1607,7 +1644,7 @@ bpf_loader_strerror(int err, char *buf, size_t size)
 		snprintf(buf, size, "Unknown bpf loader error %d", err);
 	else
 		snprintf(buf, size, "%s",
-			 strerror_r(err, sbuf, sizeof(sbuf)));
+			 str_error_r(err, sbuf, sizeof(sbuf)));
 
 	buf[size - 1] = '\0';
 	return -1;
@@ -1677,7 +1714,7 @@ int bpf__strerror_load(struct bpf_object *obj,
 {
 	bpf__strerror_head(err, buf, size);
 	case LIBBPF_ERRNO__KVER: {
-		unsigned int obj_kver = bpf_object__get_kversion(obj);
+		unsigned int obj_kver = bpf_object__kversion(obj);
 		unsigned int real_kver;
 
 		if (fetch_kernel_version(&real_kver, NULL, 0)) {
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 941e172..f2b737b 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -46,7 +46,7 @@ struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
-typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
+typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event,
 					int fd, void *arg);
 
 #ifdef HAVE_LIBBPF_SUPPORT
@@ -67,8 +67,8 @@ int bpf__strerror_probe(struct bpf_object *obj, int err,
 int bpf__load(struct bpf_object *obj);
 int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
-int bpf__foreach_tev(struct bpf_object *obj,
-		     bpf_prog_iter_callback_t func, void *arg);
+int bpf__foreach_event(struct bpf_object *obj,
+		       bpf_prog_iter_callback_t func, void *arg);
 
 int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
 		    struct perf_evlist *evlist, int *error_pos);
@@ -107,9 +107,9 @@ static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0
 static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; }
 
 static inline int
-bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
-		 bpf_prog_iter_callback_t func __maybe_unused,
-		 void *arg __maybe_unused)
+bpf__foreach_event(struct bpf_object *obj __maybe_unused,
+		   bpf_prog_iter_callback_t func __maybe_unused,
+		   void *arg __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 67e5966..5651f3c 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -17,6 +17,7 @@
 #include "tool.h"
 #include "header.h"
 #include "vdso.h"
+#include "probe-file.h"
 
 
 static bool no_buildid_cache;
@@ -144,7 +145,28 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
 	return ret;
 }
 
-static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
+char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
+				    size_t size)
+{
+	bool retry_old = true;
+
+	snprintf(bf, size, "%s/%s/%s/kallsyms",
+		 buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+retry:
+	if (!access(bf, F_OK))
+		return bf;
+	if (retry_old) {
+		/* Try old style kallsyms cache */
+		snprintf(bf, size, "%s/%s/%s",
+			 buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+		retry_old = false;
+		goto retry;
+	}
+
+	return NULL;
+}
+
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size)
 {
 	char *tmp = bf;
 	int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
@@ -154,23 +176,107 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
 	return bf;
 }
 
+char *build_id_cache__origname(const char *sbuild_id)
+{
+	char *linkname;
+	char buf[PATH_MAX];
+	char *ret = NULL, *p;
+	size_t offs = 5;	/* == strlen("../..") */
+
+	linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+	if (!linkname)
+		return NULL;
+
+	if (readlink(linkname, buf, PATH_MAX) < 0)
+		goto out;
+	/* The link should be "../..<origpath>/<sbuild_id>" */
+	p = strrchr(buf, '/');	/* Cut off the "/<sbuild_id>" */
+	if (p && (p > buf + offs)) {
+		*p = '\0';
+		if (buf[offs + 1] == '[')
+			offs++;	/*
+				 * This is a DSO name, like [kernel.kallsyms].
+				 * Skip the first '/', since this is not the
+				 * cache of a regular file.
+				 */
+		ret = strdup(buf + offs);	/* Skip "../..[/]" */
+	}
+out:
+	free(linkname);
+	return ret;
+}
+
+/* Check if the given build_id cache is valid on current running system */
+static bool build_id_cache__valid_id(char *sbuild_id)
+{
+	char real_sbuild_id[SBUILD_ID_SIZE] = "";
+	char *pathname;
+	int ret = 0;
+	bool result = false;
+
+	pathname = build_id_cache__origname(sbuild_id);
+	if (!pathname)
+		return false;
+
+	if (!strcmp(pathname, DSO__NAME_KALLSYMS))
+		ret = sysfs__sprintf_build_id("/", real_sbuild_id);
+	else if (pathname[0] == '/')
+		ret = filename__sprintf_build_id(pathname, real_sbuild_id);
+	else
+		ret = -EINVAL;	/* Should we support other special DSO cache? */
+	if (ret >= 0)
+		result = (strcmp(sbuild_id, real_sbuild_id) == 0);
+	free(pathname);
+
+	return result;
+}
+
+static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
+{
+	return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
+}
+
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
-	char build_id_hex[SBUILD_ID_SIZE];
+	bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
+	bool is_vdso = dso__is_vdso((struct dso *)dso);
+	char sbuild_id[SBUILD_ID_SIZE];
+	char *linkname;
+	bool alloc = (bf == NULL);
+	int ret;
 
 	if (!dso->has_build_id)
 		return NULL;
 
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
-	return build_id__filename(build_id_hex, bf, size);
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+	linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+	if (!linkname)
+		return NULL;
+
+	/* Check if old style build_id cache */
+	if (is_regular_file(linkname))
+		ret = asnprintf(&bf, size, "%s", linkname);
+	else
+		ret = asnprintf(&bf, size, "%s/%s", linkname,
+			 build_id_cache__basename(is_kallsyms, is_vdso));
+	if (ret < 0 || (!alloc && size < (unsigned int)ret))
+		bf = NULL;
+	free(linkname);
+
+	return bf;
 }
 
 bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
 {
-	char *id_name, *ch;
+	char *id_name = NULL, *ch;
 	struct stat sb;
+	char sbuild_id[SBUILD_ID_SIZE];
 
-	id_name = dso__build_id_filename(dso, bf, size);
+	if (!dso->has_build_id)
+		goto err;
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+	id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
 	if (!id_name)
 		goto err;
 	if (access(id_name, F_OK))
@@ -194,18 +300,14 @@ bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
 	if (ch - 3 < bf)
 		goto err;
 
+	free(id_name);
 	return strncmp(".ko", ch - 3, 3) == 0;
 err:
-	/*
-	 * If dso__build_id_filename work, get id_name again,
-	 * because id_name points to bf and is broken.
-	 */
-	if (id_name)
-		id_name = dso__build_id_filename(dso, bf, size);
 	pr_err("Invalid build id: %s\n", id_name ? :
 					 dso->long_name ? :
 					 dso->short_name ? :
 					 "[unknown]");
+	free(id_name);
 	return false;
 }
 
@@ -340,8 +442,132 @@ void disable_buildid_cache(void)
 	no_buildid_cache = true;
 }
 
-static char *build_id_cache__dirname_from_path(const char *name,
-					       bool is_kallsyms, bool is_vdso)
+static bool lsdir_bid_head_filter(const char *name __maybe_unused,
+				  struct dirent *d __maybe_unused)
+{
+	return (strlen(d->d_name) == 2) &&
+		isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]);
+}
+
+static bool lsdir_bid_tail_filter(const char *name __maybe_unused,
+				  struct dirent *d __maybe_unused)
+{
+	int i = 0;
+	while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3)
+		i++;
+	return (i == SBUILD_ID_SIZE - 3) && (d->d_name[i] == '\0');
+}
+
+struct strlist *build_id_cache__list_all(bool validonly)
+{
+	struct strlist *toplist, *linklist = NULL, *bidlist;
+	struct str_node *nd, *nd2;
+	char *topdir, *linkdir = NULL;
+	char sbuild_id[SBUILD_ID_SIZE];
+
+	/* for filename__ functions */
+	if (validonly)
+		symbol__init(NULL);
+
+	/* Open the top-level directory */
+	if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0)
+		return NULL;
+
+	bidlist = strlist__new(NULL, NULL);
+	if (!bidlist)
+		goto out;
+
+	toplist = lsdir(topdir, lsdir_bid_head_filter);
+	if (!toplist) {
+		pr_debug("Error in lsdir(%s): %d\n", topdir, errno);
+		/* If there is no buildid cache, return an empty list */
+		if (errno == ENOENT)
+			goto out;
+		goto err_out;
+	}
+
+	strlist__for_each_entry(nd, toplist) {
+		if (asprintf(&linkdir, "%s/%s", topdir, nd->s) < 0)
+			goto err_out;
+		/* Open the lower-level directory */
+		linklist = lsdir(linkdir, lsdir_bid_tail_filter);
+		if (!linklist) {
+			pr_debug("Error in lsdir(%s): %d\n", linkdir, errno);
+			goto err_out;
+		}
+		strlist__for_each_entry(nd2, linklist) {
+			if (snprintf(sbuild_id, SBUILD_ID_SIZE, "%s%s",
+				     nd->s, nd2->s) != SBUILD_ID_SIZE - 1)
+				goto err_out;
+			if (validonly && !build_id_cache__valid_id(sbuild_id))
+				continue;
+			if (strlist__add(bidlist, sbuild_id) < 0)
+				goto err_out;
+		}
+		strlist__delete(linklist);
+		zfree(&linkdir);
+	}
+
+out_free:
+	strlist__delete(toplist);
+out:
+	free(topdir);
+
+	return bidlist;
+
+err_out:
+	strlist__delete(linklist);
+	zfree(&linkdir);
+	strlist__delete(bidlist);
+	bidlist = NULL;
+	goto out_free;
+}
+
+static bool str_is_build_id(const char *maybe_sbuild_id, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (!isxdigit(maybe_sbuild_id[i]))
+			return false;
+	}
+	return true;
+}
+
+/* Return the valid complete build-id */
+char *build_id_cache__complement(const char *incomplete_sbuild_id)
+{
+	struct strlist *bidlist;
+	struct str_node *nd, *cand = NULL;
+	char *sbuild_id = NULL;
+	size_t len = strlen(incomplete_sbuild_id);
+
+	if (len >= SBUILD_ID_SIZE ||
+	    !str_is_build_id(incomplete_sbuild_id, len))
+		return NULL;
+
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist)
+		return NULL;
+
+	strlist__for_each_entry(nd, bidlist) {
+		if (strncmp(nd->s, incomplete_sbuild_id, len) != 0)
+			continue;
+		if (cand) {	/* Error: There are more than 2 candidates. */
+			cand = NULL;
+			break;
+		}
+		cand = nd;
+	}
+	if (cand)
+		sbuild_id = strdup(cand->s);
+	strlist__delete(bidlist);
+
+	return sbuild_id;
+}
+
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+			       bool is_kallsyms, bool is_vdso)
 {
 	char *realname = (char *)name, *filename;
 	bool slash = is_kallsyms || is_vdso;
@@ -352,8 +578,9 @@ static char *build_id_cache__dirname_from_path(const char *name,
 			return NULL;
 	}
 
-	if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "",
-		     is_vdso ? DSO__NAME_VDSO : realname) < 0)
+	if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "",
+		     is_vdso ? DSO__NAME_VDSO : realname,
+		     sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
 		filename = NULL;
 
 	if (!slash)
@@ -368,7 +595,7 @@ int build_id_cache__list_build_ids(const char *pathname,
 	char *dir_name;
 	int ret = 0;
 
-	dir_name = build_id_cache__dirname_from_path(pathname, false, false);
+	dir_name = build_id_cache__cachedir(NULL, pathname, false, false);
 	if (!dir_name)
 		return -ENOMEM;
 
@@ -380,12 +607,36 @@ int build_id_cache__list_build_ids(const char *pathname,
 	return ret;
 }
 
+#if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT)
+static int build_id_cache__add_sdt_cache(const char *sbuild_id,
+					  const char *realname)
+{
+	struct probe_cache *cache;
+	int ret;
+
+	cache = probe_cache__new(sbuild_id);
+	if (!cache)
+		return -1;
+
+	ret = probe_cache__scan_sdt(cache, realname);
+	if (ret >= 0) {
+		pr_debug("Found %d SDTs in %s\n", ret, realname);
+		if (probe_cache__commit(cache) < 0)
+			ret = -1;
+	}
+	probe_cache__delete(cache);
+	return ret;
+}
+#else
+#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0)
+#endif
+
 int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			  bool is_kallsyms, bool is_vdso)
 {
 	const size_t size = PATH_MAX;
 	char *realname = NULL, *filename = NULL, *dir_name = NULL,
-	     *linkname = zalloc(size), *targetname, *tmp;
+	     *linkname = zalloc(size), *tmp;
 	int err = -1;
 
 	if (!is_kallsyms) {
@@ -394,14 +645,22 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			goto out_free;
 	}
 
-	dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso);
+	dir_name = build_id_cache__cachedir(sbuild_id, name,
+					    is_kallsyms, is_vdso);
 	if (!dir_name)
 		goto out_free;
 
+	/* Remove old style build-id cache */
+	if (is_regular_file(dir_name))
+		if (unlink(dir_name))
+			goto out_free;
+
 	if (mkdir_p(dir_name, 0755))
 		goto out_free;
 
-	if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
+	/* Save the allocated buildid dirname */
+	if (asprintf(&filename, "%s/%s", dir_name,
+		     build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
 		filename = NULL;
 		goto out_free;
 	}
@@ -415,7 +674,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			goto out_free;
 	}
 
-	if (!build_id__filename(sbuild_id, linkname, size))
+	if (!build_id_cache__linkname(sbuild_id, linkname, size))
 		goto out_free;
 	tmp = strrchr(linkname, '/');
 	*tmp = '\0';
@@ -424,11 +683,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 		goto out_free;
 
 	*tmp = '/';
-	targetname = filename + strlen(buildid_dir) - 5;
-	memcpy(targetname, "../..", 5);
+	tmp = dir_name + strlen(buildid_dir) - 5;
+	memcpy(tmp, "../..", 5);
 
-	if (symlink(targetname, linkname) == 0)
+	if (symlink(tmp, linkname) == 0)
 		err = 0;
+
+	/* Update SDT cache : error is just warned */
+	if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+		pr_debug("Failed to update/scan SDT cache for %s\n", realname);
+
 out_free:
 	if (!is_kallsyms)
 		free(realname);
@@ -452,7 +716,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 bool build_id_cache__cached(const char *sbuild_id)
 {
 	bool ret = false;
-	char *filename = build_id__filename(sbuild_id, NULL, 0);
+	char *filename = build_id_cache__linkname(sbuild_id, NULL, 0);
 
 	if (filename && !access(filename, F_OK))
 		ret = true;
@@ -471,7 +735,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
 	if (filename == NULL || linkname == NULL)
 		goto out_free;
 
-	if (!build_id__filename(sbuild_id, linkname, size))
+	if (!build_id_cache__linkname(sbuild_id, linkname, size))
 		goto out_free;
 
 	if (access(linkname, F_OK))
@@ -489,7 +753,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
 	tmp = strrchr(linkname, '/') + 1;
 	snprintf(tmp, size - (tmp - linkname), "%s", filename);
 
-	if (unlink(linkname))
+	if (rm_rf(linkname))
 		goto out_free;
 
 	err = 0;
@@ -501,7 +765,7 @@ out_free:
 
 static int dso__cache_build_id(struct dso *dso, struct machine *machine)
 {
-	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
 	char nm[PATH_MAX];
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 64af3e2..d279906 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -14,6 +14,8 @@ struct dso;
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
+char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
+				    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
@@ -28,6 +30,12 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
 int perf_session__write_buildid_table(struct perf_session *session, int fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
+char *build_id_cache__origname(const char *sbuild_id);
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+			       bool is_kallsyms, bool is_vdso);
+struct strlist *build_id_cache__list_all(bool validonly);
+char *build_id_cache__complement(const char *incomplete_sbuild_id);
 int build_id_cache__list_build_ids(const char *pathname,
 				   struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 0d814bb..512c0c8 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,40 +1,20 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
-#include <stdbool.h>
-#include "util.h"
 #include "strbuf.h"
 #include <subcmd/pager.h>
-#include "../perf.h"
 #include "../ui/ui.h"
 
 #include <linux/string.h>
 
 #define CMD_EXEC_PATH "--exec-path"
-#define CMD_PERF_DIR "--perf-dir="
-#define CMD_WORK_TREE "--work-tree="
 #define CMD_DEBUGFS_DIR "--debugfs-dir="
 
-#define PERF_DIR_ENVIRONMENT "PERF_DIR"
-#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE"
 #define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH"
-#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
-extern const char *config_exclusive_filename;
-
-typedef int (*config_fn_t)(const char *, const char *, void *);
-int perf_default_config(const char *, const char *, void *);
-int perf_config(config_fn_t fn, void *);
-int perf_config_int(const char *, const char *);
-u64 perf_config_u64(const char *, const char *);
-int perf_config_bool(const char *, const char *);
-int config_error_nonbool(const char *);
-const char *perf_config_dirname(const char *, const char *);
-const char *perf_etc_perfconfig(void);
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -45,9 +25,6 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-char *strip_path_suffix(const char *path, const char *suffix);
-
 char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 65e2a4f..13e7554 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -94,6 +94,7 @@ struct callchain_param {
 	enum perf_call_graph_mode record_mode;
 	u32			dump_size;
 	enum chain_mode 	mode;
+	u16			max_stack;
 	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
@@ -105,6 +106,7 @@ struct callchain_param {
 };
 
 extern struct callchain_param callchain_param;
+extern struct callchain_param callchain_param_default;
 
 struct callchain_list {
 	u64			ip;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 90aa1b4..8fdee24 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 		cgrp = counter->cgrp;
 		if (!cgrp)
 			continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	 * if add cgroup N, then need to find event N
 	 */
 	n = 0;
-	evlist__for_each(evlist, counter) {
+	evlist__for_each_entry(evlist, counter) {
 		if (n == nr_cgroups)
 			goto found;
 		n++;
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 2babdda..f0dcd0e 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -4,18 +4,24 @@
 #include "cloexec.h"
 #include "asm/bug.h"
 #include "debug.h"
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6)
 int __weak sched_getcpu(void)
 {
+#ifdef __NR_getcpu
+	unsigned cpu;
+	int err = syscall(__NR_getcpu, &cpu, NULL, NULL);
+	if (!err)
+		return cpu;
+#else
 	errno = ENOSYS;
+#endif
 	return -1;
 }
-#endif
-#endif
 
 static int perf_flag_probe(void)
 {
@@ -58,7 +64,7 @@ static int perf_flag_probe(void)
 
 	WARN_ONCE(err != EINVAL && err != EBUSY,
 		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-		  err, strerror_r(err, sbuf, sizeof(sbuf)));
+		  err, str_error_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
 	while (1) {
@@ -76,7 +82,7 @@ static int perf_flag_probe(void)
 
 	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-		      err, strerror_r(err, sbuf, sizeof(sbuf))))
+		      err, str_error_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 43e84aa..dbbf89b 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,7 +1,11 @@
 #include <linux/kernel.h>
 #include "cache.h"
+#include "config.h"
+#include <stdlib.h>
+#include <stdio.h>
 #include "color.h"
 #include <math.h>
+#include <unistd.h>
 
 int perf_use_color_default = -1;
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index dad7d82..18dae74 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,6 +26,7 @@ static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
+static struct perf_config_set *config_set;
 
 const char *config_exclusive_filename;
 
@@ -275,7 +276,8 @@ static int perf_parse_file(config_fn_t fn, void *data)
 			break;
 		}
 	}
-	die("bad config file line %d in %s", config_linenr, config_file_name);
+	pr_err("bad config file line %d in %s\n", config_linenr, config_file_name);
+	return -1;
 }
 
 static int parse_unit_factor(const char *end, unsigned long *val)
@@ -371,7 +373,7 @@ 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)
+static const char *perf_config_dirname(const char *name, const char *value)
 {
 	if (!name)
 		return NULL;
@@ -477,54 +479,6 @@ static int perf_config_global(void)
 	return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0);
 }
 
-int perf_config(config_fn_t fn, void *data)
-{
-	int ret = 0, found = 0;
-	const char *home = NULL;
-
-	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
-	if (config_exclusive_filename)
-		return perf_config_from_file(fn, config_exclusive_filename, data);
-	if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
-		ret += perf_config_from_file(fn, perf_etc_perfconfig(),
-					    data);
-		found += 1;
-	}
-
-	home = getenv("HOME");
-	if (perf_config_global() && home) {
-		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		struct stat st;
-
-		if (user_config == NULL) {
-			warning("Not enough memory to process %s/.perfconfig, "
-				"ignoring it.", home);
-			goto out;
-		}
-
-		if (stat(user_config, &st) < 0)
-			goto out_free;
-
-		if (st.st_uid && (st.st_uid != geteuid())) {
-			warning("File %s not owned by current user or root, "
-				"ignoring it.", user_config);
-			goto out_free;
-		}
-
-		if (!st.st_size)
-			goto out_free;
-
-		ret += perf_config_from_file(fn, user_config, data);
-		found += 1;
-out_free:
-		free(user_config);
-	}
-out:
-	if (found == 0)
-		return -1;
-	return ret;
-}
-
 static struct perf_config_section *find_section(struct list_head *sections,
 						const char *section_name)
 {
@@ -609,8 +563,12 @@ static int collect_config(const char *var, const char *value,
 	struct perf_config_section *section = NULL;
 	struct perf_config_item *item = NULL;
 	struct perf_config_set *set = perf_config_set;
-	struct list_head *sections = &set->sections;
+	struct list_head *sections;
+
+	if (set == NULL)
+		return -1;
 
+	sections = &set->sections;
 	key = ptr = strdup(var);
 	if (!key) {
 		pr_debug("%s: strdup failed\n", __func__);
@@ -641,22 +599,115 @@ static int collect_config(const char *var, const char *value,
 
 out_free:
 	free(key);
-	perf_config_set__delete(set);
 	return -1;
 }
 
+static int perf_config_set__init(struct perf_config_set *set)
+{
+	int ret = -1;
+	const char *home = NULL;
+
+	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
+	if (config_exclusive_filename)
+		return perf_config_from_file(collect_config, config_exclusive_filename, set);
+	if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
+		if (perf_config_from_file(collect_config, perf_etc_perfconfig(), set) < 0)
+			goto out;
+	}
+
+	home = getenv("HOME");
+	if (perf_config_global() && home) {
+		char *user_config = strdup(mkpath("%s/.perfconfig", home));
+		struct stat st;
+
+		if (user_config == NULL) {
+			warning("Not enough memory to process %s/.perfconfig, "
+				"ignoring it.", home);
+			goto out;
+		}
+
+		if (stat(user_config, &st) < 0)
+			goto out_free;
+
+		if (st.st_uid && (st.st_uid != geteuid())) {
+			warning("File %s not owned by current user or root, "
+				"ignoring it.", user_config);
+			goto out_free;
+		}
+
+		if (!st.st_size)
+			goto out_free;
+
+		ret = perf_config_from_file(collect_config, user_config, set);
+
+out_free:
+		free(user_config);
+	}
+out:
+	return ret;
+}
+
 struct perf_config_set *perf_config_set__new(void)
 {
 	struct perf_config_set *set = zalloc(sizeof(*set));
 
 	if (set) {
 		INIT_LIST_HEAD(&set->sections);
-		perf_config(collect_config, set);
+		if (perf_config_set__init(set) < 0) {
+			perf_config_set__delete(set);
+			set = NULL;
+		}
 	}
 
 	return set;
 }
 
+int perf_config(config_fn_t fn, void *data)
+{
+	int ret = 0;
+	char key[BUFSIZ];
+	struct perf_config_section *section;
+	struct perf_config_item *item;
+
+	if (config_set == NULL)
+		return -1;
+
+	perf_config_set__for_each_entry(config_set, section, item) {
+		char *value = item->value;
+
+		if (value) {
+			scnprintf(key, sizeof(key), "%s.%s",
+				  section->name, item->name);
+			ret = fn(key, value, data);
+			if (ret < 0) {
+				pr_err("Error: wrong config key-value pair %s=%s\n",
+				       key, value);
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
+void perf_config__init(void)
+{
+	if (config_set == NULL)
+		config_set = perf_config_set__new();
+}
+
+void perf_config__exit(void)
+{
+	perf_config_set__delete(config_set);
+	config_set = NULL;
+}
+
+void perf_config__refresh(void)
+{
+	perf_config__exit();
+	perf_config__init();
+}
+
 static void perf_config_item__delete(struct perf_config_item *item)
 {
 	zfree(&item->name);
@@ -693,6 +744,9 @@ static void perf_config_set__purge(struct perf_config_set *set)
 
 void perf_config_set__delete(struct perf_config_set *set)
 {
+	if (set == NULL)
+		return;
+
 	perf_config_set__purge(set);
 	free(set);
 }
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index 22ec626..6f813d4 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -20,7 +20,47 @@ struct perf_config_set {
 	struct list_head sections;
 };
 
+extern const char *config_exclusive_filename;
+
+typedef int (*config_fn_t)(const char *, const char *, void *);
+int perf_default_config(const char *, const char *, void *);
+int perf_config(config_fn_t fn, void *);
+int perf_config_int(const char *, const char *);
+u64 perf_config_u64(const char *, const char *);
+int perf_config_bool(const char *, const char *);
+int config_error_nonbool(const char *);
+const char *perf_etc_perfconfig(void);
+
 struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
+void perf_config__init(void);
+void perf_config__exit(void);
+void perf_config__refresh(void);
+
+/**
+ * perf_config_sections__for_each - iterate thru all the sections
+ * @list: list_head instance to iterate
+ * @section: struct perf_config_section iterator
+ */
+#define perf_config_sections__for_each_entry(list, section)	\
+        list_for_each_entry(section, list, node)
+
+/**
+ * perf_config_items__for_each - iterate thru all the items
+ * @list: list_head instance to iterate
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_items__for_each_entry(list, item)	\
+        list_for_each_entry(item, list, node)
+
+/**
+ * perf_config_set__for_each - iterate thru all the config section-item pairs
+ * @set: evlist instance to iterate
+ * @section: struct perf_config_section iterator
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_set__for_each_entry(set, section, item)			\
+	perf_config_sections__for_each_entry(&set->sections, section)		\
+	perf_config_items__for_each_entry(&section->items, item)
 
 #endif /* __PERF_CONFIG_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 02d8016..2c0b522 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -236,13 +236,12 @@ struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
 
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
 {
-	int i;
-	size_t printed = fprintf(fp, "%d cpu%s: ",
-				 map->nr, map->nr > 1 ? "s" : "");
-	for (i = 0; i < map->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]);
+#define BUFSIZE 1024
+	char buf[BUFSIZE];
 
-	return printed + fprintf(fp, "\n");
+	cpu_map__snprint(map, buf, sizeof(buf));
+	return fprintf(fp, "%s\n", buf);
+#undef BUFSIZE
 }
 
 struct cpu_map *cpu_map__dummy_new(void)
@@ -590,12 +589,65 @@ int cpu__setup_cpunode_map(void)
 
 bool cpu_map__has(struct cpu_map *cpus, int cpu)
 {
+	return cpu_map__idx(cpus, cpu) != -1;
+}
+
+int cpu_map__idx(struct cpu_map *cpus, int cpu)
+{
 	int i;
 
 	for (i = 0; i < cpus->nr; ++i) {
 		if (cpus->map[i] == cpu)
-			return true;
+			return i;
+	}
+
+	return -1;
+}
+
+int cpu_map__cpu(struct cpu_map *cpus, int idx)
+{
+	return cpus->map[idx];
+}
+
+size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
+{
+	int i, cpu, start = -1;
+	bool first = true;
+	size_t ret = 0;
+
+#define COMMA first ? "" : ","
+
+	for (i = 0; i < map->nr + 1; i++) {
+		bool last = i == map->nr;
+
+		cpu = last ? INT_MAX : map->map[i];
+
+		if (start == -1) {
+			start = i;
+			if (last) {
+				ret += snprintf(buf + ret, size - ret,
+						"%s%d", COMMA,
+						map->map[i]);
+			}
+		} else if (((i - start) != (cpu - map->map[start])) || last) {
+			int end = i - 1;
+
+			if (start == end) {
+				ret += snprintf(buf + ret, size - ret,
+						"%s%d", COMMA,
+						map->map[start]);
+			} else {
+				ret += snprintf(buf + ret, size - ret,
+						"%s%d-%d", COMMA,
+						map->map[start], map->map[end]);
+			}
+			first = false;
+			start = i;
+		}
 	}
 
-	return false;
+#undef COMMA
+
+	pr_debug("cpumask list: %s\n", buf);
+	return ret;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 1a0a350..06bd689 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -19,6 +19,7 @@ struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
+size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
 int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
@@ -67,5 +68,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
 		       void *data);
 
+int cpu_map__cpu(struct cpu_map *cpus, int idx);
 bool cpu_map__has(struct cpu_map *cpus, int cpu);
+int cpu_map__idx(struct cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 9f53020..4f979bb 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -26,6 +26,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "machine.h"
+#include "config.h"
 
 #define pr_N(n, fmt, ...) \
 	eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
@@ -68,6 +69,9 @@ struct ctf_writer {
 		};
 		struct bt_ctf_field_type *array[6];
 	} data;
+	struct bt_ctf_event_class	*comm_class;
+	struct bt_ctf_event_class	*exit_class;
+	struct bt_ctf_event_class	*fork_class;
 };
 
 struct convert {
@@ -76,6 +80,7 @@ struct convert {
 
 	u64			events_size;
 	u64			events_count;
+	u64			non_sample_count;
 
 	/* Ordered events configured queue size. */
 	u64			queue_size;
@@ -140,6 +145,36 @@ FUNC_VALUE_SET(s64)
 FUNC_VALUE_SET(u64)
 __FUNC_VALUE_SET(u64_hex, u64)
 
+static int string_set_value(struct bt_ctf_field *field, const char *string);
+static __maybe_unused int
+value_set_string(struct ctf_writer *cw, struct bt_ctf_event *event,
+		 const char *name, const char *string)
+{
+	struct bt_ctf_field_type *type = cw->data.string;
+	struct bt_ctf_field *field;
+	int ret = 0;
+
+	field = bt_ctf_field_create(type);
+	if (!field) {
+		pr_err("failed to create a field %s\n", name);
+		return -1;
+	}
+
+	ret = string_set_value(field, string);
+	if (ret) {
+		pr_err("failed to set value %s\n", name);
+		goto err_put_field;
+	}
+
+	ret = bt_ctf_event_set_payload(event, name, field);
+	if (ret)
+		pr_err("failed to set payload %s\n", name);
+
+err_put_field:
+	bt_ctf_field_put(field);
+	return ret;
+}
+
 static struct bt_ctf_field_type*
 get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
 {
@@ -731,6 +766,72 @@ static int process_sample_event(struct perf_tool *tool,
 	return cs ? 0 : -1;
 }
 
+#define __NON_SAMPLE_SET_FIELD(_name, _type, _field) 	\
+do {							\
+	ret = value_set_##_type(cw, event, #_field, _event->_name._field);\
+	if (ret)					\
+		return -1;				\
+} while(0)
+
+#define __FUNC_PROCESS_NON_SAMPLE(_name, body) 	\
+static int process_##_name##_event(struct perf_tool *tool,	\
+				   union perf_event *_event,	\
+				   struct perf_sample *sample,	\
+				   struct machine *machine)	\
+{								\
+	struct convert *c = container_of(tool, struct convert, tool);\
+	struct ctf_writer *cw = &c->writer;			\
+	struct bt_ctf_event_class *event_class = cw->_name##_class;\
+	struct bt_ctf_event *event;				\
+	struct ctf_stream *cs;					\
+	int ret;						\
+								\
+	c->non_sample_count++;					\
+	c->events_size += _event->header.size;			\
+	event = bt_ctf_event_create(event_class);		\
+	if (!event) {						\
+		pr_err("Failed to create an CTF event\n");	\
+		return -1;					\
+	}							\
+								\
+	bt_ctf_clock_set_time(cw->clock, sample->time);		\
+	body							\
+	cs = ctf_stream(cw, 0);					\
+	if (cs) {						\
+		if (is_flush_needed(cs))			\
+			ctf_stream__flush(cs);			\
+								\
+		cs->count++;					\
+		bt_ctf_stream_append_event(cs->stream, event);	\
+	}							\
+	bt_ctf_event_put(event);				\
+								\
+	return perf_event__process_##_name(tool, _event, sample, machine);\
+}
+
+__FUNC_PROCESS_NON_SAMPLE(comm,
+	__NON_SAMPLE_SET_FIELD(comm, u32, pid);
+	__NON_SAMPLE_SET_FIELD(comm, u32, tid);
+	__NON_SAMPLE_SET_FIELD(comm, string, comm);
+)
+__FUNC_PROCESS_NON_SAMPLE(fork,
+	__NON_SAMPLE_SET_FIELD(fork, u32, pid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, ppid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, tid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, ptid);
+	__NON_SAMPLE_SET_FIELD(fork, u64, time);
+)
+
+__FUNC_PROCESS_NON_SAMPLE(exit,
+	__NON_SAMPLE_SET_FIELD(fork, u32, pid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, ppid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, tid);
+	__NON_SAMPLE_SET_FIELD(fork, u32, ptid);
+	__NON_SAMPLE_SET_FIELD(fork, u64, time);
+)
+#undef __NON_SAMPLE_SET_FIELD
+#undef __FUNC_PROCESS_NON_SAMPLE
+
 /* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
 static char *change_name(char *name, char *orig_name, int dup)
 {
@@ -997,7 +1098,7 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	struct perf_evsel *evsel;
 	int ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		ret = add_event(cw, evsel);
 		if (ret)
 			return ret;
@@ -1005,12 +1106,86 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+#define __NON_SAMPLE_ADD_FIELD(t, n)						\
+	do {							\
+		pr2("  field '%s'\n", #n);			\
+		if (bt_ctf_event_class_add_field(event_class, cw->data.t, #n)) {\
+			pr_err("Failed to add field '%s';\n", #n);\
+			return -1;				\
+		}						\
+	} while(0)
+
+#define __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(_name, body) 		\
+static int add_##_name##_event(struct ctf_writer *cw)		\
+{								\
+	struct bt_ctf_event_class *event_class;			\
+	int ret;						\
+								\
+	pr("Adding "#_name" event\n");				\
+	event_class = bt_ctf_event_class_create("perf_" #_name);\
+	if (!event_class)					\
+		return -1;					\
+	body							\
+								\
+	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);\
+	if (ret) {						\
+		pr("Failed to add event class '"#_name"' into stream.\n");\
+		return ret;					\
+	}							\
+								\
+	cw->_name##_class = event_class;			\
+	bt_ctf_event_class_put(event_class);			\
+	return 0;						\
+}
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(comm,
+	__NON_SAMPLE_ADD_FIELD(u32, pid);
+	__NON_SAMPLE_ADD_FIELD(u32, tid);
+	__NON_SAMPLE_ADD_FIELD(string, comm);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(fork,
+	__NON_SAMPLE_ADD_FIELD(u32, pid);
+	__NON_SAMPLE_ADD_FIELD(u32, ppid);
+	__NON_SAMPLE_ADD_FIELD(u32, tid);
+	__NON_SAMPLE_ADD_FIELD(u32, ptid);
+	__NON_SAMPLE_ADD_FIELD(u64, time);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit,
+	__NON_SAMPLE_ADD_FIELD(u32, pid);
+	__NON_SAMPLE_ADD_FIELD(u32, ppid);
+	__NON_SAMPLE_ADD_FIELD(u32, tid);
+	__NON_SAMPLE_ADD_FIELD(u32, ptid);
+	__NON_SAMPLE_ADD_FIELD(u64, time);
+)
+
+#undef __NON_SAMPLE_ADD_FIELD
+#undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS
+
+static int setup_non_sample_events(struct ctf_writer *cw,
+				   struct perf_session *session __maybe_unused)
+{
+	int ret;
+
+	ret = add_comm_event(cw);
+	if (ret)
+		return ret;
+	ret = add_exit_event(cw);
+	if (ret)
+		return ret;
+	ret = add_fork_event(cw);
+	if (ret)
+		return ret;
+	return 0;
+}
+
 static void cleanup_events(struct perf_session *session)
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		struct evsel_priv *priv;
 
 		priv = evsel->priv;
@@ -1273,13 +1448,14 @@ static int convert__config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
-int bt_convert__perf2ctf(const char *input, const char *path, bool force)
+int bt_convert__perf2ctf(const char *input, const char *path,
+			 struct perf_data_convert_opts *opts)
 {
 	struct perf_session *session;
 	struct perf_data_file file = {
 		.path = input,
 		.mode = PERF_DATA_MODE_READ,
-		.force = force,
+		.force = opts->force,
 	};
 	struct convert c = {
 		.tool = {
@@ -1299,6 +1475,12 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	struct ctf_writer *cw = &c.writer;
 	int err = -1;
 
+	if (opts->all) {
+		c.tool.comm = process_comm_event;
+		c.tool.exit = process_exit_event;
+		c.tool.fork = process_fork_event;
+	}
+
 	perf_config(convert__config, &c);
 
 	/* CTF writer */
@@ -1323,6 +1505,9 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (setup_events(cw, session))
 		goto free_session;
 
+	if (opts->all && setup_non_sample_events(cw, session))
+		goto free_session;
+
 	if (setup_streams(cw, session))
 		goto free_session;
 
@@ -1337,10 +1522,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		file.path, path);
 
 	fprintf(stderr,
-		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n",
+		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
+	if (!c.non_sample_count)
+		fprintf(stderr, ") ]\n");
+	else
+		fprintf(stderr, ", %" PRIu64 " non-samples) ]\n", c.non_sample_count);
+
 	cleanup_events(session);
 	perf_session__delete(session);
 	ctf_writer__cleanup(cw);
diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h
index 4c20434..9a3b587 100644
--- a/tools/perf/util/data-convert-bt.h
+++ b/tools/perf/util/data-convert-bt.h
@@ -1,8 +1,10 @@
 #ifndef __DATA_CONVERT_BT_H
 #define __DATA_CONVERT_BT_H
+#include "data-convert.h"
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
 
-int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, bool force);
+int bt_convert__perf2ctf(const char *input_name, const char *to_ctf,
+			 struct perf_data_convert_opts *opts);
 
 #endif /* HAVE_LIBBABELTRACE_SUPPORT */
 #endif /* __DATA_CONVERT_BT_H */
diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h
new file mode 100644
index 0000000..5314962
--- /dev/null
+++ b/tools/perf/util/data-convert.h
@@ -0,0 +1,9 @@
+#ifndef __DATA_CONVERT_H
+#define __DATA_CONVERT_H
+
+struct perf_data_convert_opts {
+	bool force;
+	bool all;
+};
+
+#endif /* __DATA_CONVERT_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index be835161..60bfc9c 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -57,7 +57,7 @@ static int open_file_read(struct perf_data_file *file)
 		int err = errno;
 
 		pr_err("failed to open %s: %s", file->path,
-			strerror_r(err, sbuf, sizeof(sbuf)));
+			str_error_r(err, sbuf, sizeof(sbuf)));
 		if (err == ENOENT && !strcmp(file->path, "perf.data"))
 			pr_err("  (try 'perf record' first)");
 		pr_err("\n");
@@ -99,7 +99,7 @@ static int open_file_write(struct perf_data_file *file)
 
 	if (fd < 0)
 		pr_err("failed to open %s : %s\n", file->path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 
 	return fd;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index c9a6dc1..b0c2b5c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -233,17 +233,6 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 	return 0;
 }
 
-static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
-{
-	if (thread->pid_ == thread->tid)
-		return thread__get(thread);
-
-	if (thread->pid_ == -1)
-		return NULL;
-
-	return machine__find_thread(machine, thread->pid_, thread->pid_);
-}
-
 static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 			  u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
 {
@@ -382,7 +371,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 	if (err)
 		return err;
 
-	main_thread = get_main_thread(al->machine, thread);
+	main_thread = thread__main_thread(al->machine, thread);
 	if (main_thread)
 		comm = machine__thread_exec_comm(al->machine, main_thread);
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 14bafda..d242adc 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -38,7 +38,7 @@ extern int debug_data_convert;
 #define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 
-#define STRERR_BUFSIZE	128	/* For the buffer size of strerror_r */
+#define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
new file mode 100644
index 0000000..f9dafa8
--- /dev/null
+++ b/tools/perf/util/demangle-rust.c
@@ -0,0 +1,269 @@
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+
+#include "demangle-rust.h"
+
+/*
+ * Mangled Rust symbols look like this:
+ *
+ *     _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a
+ *
+ * The original symbol is:
+ *
+ *     <std::sys::fd::FileDesc as core::ops::Drop>::drop
+ *
+ * The last component of the path is a 64-bit hash in lowercase hex, prefixed
+ * with "h". Rust does not have a global namespace between crates, an illusion
+ * which Rust maintains by using the hash to distinguish things that would
+ * otherwise have the same symbol.
+ *
+ * Any path component not starting with a XID_Start character is prefixed with
+ * "_".
+ *
+ * The following escape sequences are used:
+ *
+ *     ","  =>  $C$
+ *     "@"  =>  $SP$
+ *     "*"  =>  $BP$
+ *     "&"  =>  $RF$
+ *     "<"  =>  $LT$
+ *     ">"  =>  $GT$
+ *     "("  =>  $LP$
+ *     ")"  =>  $RP$
+ *     " "  =>  $u20$
+ *     "'"  =>  $u27$
+ *     "["  =>  $u5b$
+ *     "]"  =>  $u5d$
+ *     "~"  =>  $u7e$
+ *
+ * A double ".." means "::" and a single "." means "-".
+ *
+ * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$
+ */
+
+static const char *hash_prefix = "::h";
+static const size_t hash_prefix_len = 3;
+static const size_t hash_len = 16;
+
+static bool is_prefixed_hash(const char *start);
+static bool looks_like_rust(const char *sym, size_t len);
+static bool unescape(const char **in, char **out, const char *seq, char value);
+
+/*
+ * INPUT:
+ *     sym: symbol that has been through BFD-demangling
+ *
+ * This function looks for the following indicators:
+ *
+ *  1. The hash must consist of "h" followed by 16 lowercase hex digits.
+ *
+ *  2. As a sanity check, the hash must use between 5 and 15 of the 16 possible
+ *     hex digits. This is true of 99.9998% of hashes so once in your life you
+ *     may see a false negative. The point is to notice path components that
+ *     could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In
+ *     this case a false positive (non-Rust symbol has an important path
+ *     component removed because it looks like a Rust hash) is worse than a
+ *     false negative (the rare Rust symbol is not demangled) so this sets the
+ *     balance in favor of false negatives.
+ *
+ *  3. There must be no characters other than a-zA-Z0-9 and _.:$
+ *
+ *  4. There must be no unrecognized $-sign sequences.
+ *
+ *  5. There must be no sequence of three or more dots in a row ("...").
+ */
+bool
+rust_is_mangled(const char *sym)
+{
+	size_t len, len_without_hash;
+
+	if (!sym)
+		return false;
+
+	len = strlen(sym);
+	if (len <= hash_prefix_len + hash_len)
+		/* Not long enough to contain "::h" + hash + something else */
+		return false;
+
+	len_without_hash = len - (hash_prefix_len + hash_len);
+	if (!is_prefixed_hash(sym + len_without_hash))
+		return false;
+
+	return looks_like_rust(sym, len_without_hash);
+}
+
+/*
+ * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex
+ * digits must comprise between 5 and 15 (inclusive) distinct digits.
+ */
+static bool is_prefixed_hash(const char *str)
+{
+	const char *end;
+	bool seen[16];
+	size_t i;
+	int count;
+
+	if (strncmp(str, hash_prefix, hash_prefix_len))
+		return false;
+	str += hash_prefix_len;
+
+	memset(seen, false, sizeof(seen));
+	for (end = str + hash_len; str < end; str++)
+		if (*str >= '0' && *str <= '9')
+			seen[*str - '0'] = true;
+		else if (*str >= 'a' && *str <= 'f')
+			seen[*str - 'a' + 10] = true;
+		else
+			return false;
+
+	/* Count how many distinct digits seen */
+	count = 0;
+	for (i = 0; i < 16; i++)
+		if (seen[i])
+			count++;
+
+	return count >= 5 && count <= 15;
+}
+
+static bool looks_like_rust(const char *str, size_t len)
+{
+	const char *end = str + len;
+
+	while (str < end)
+		switch (*str) {
+		case '$':
+			if (!strncmp(str, "$C$", 3))
+				str += 3;
+			else if (!strncmp(str, "$SP$", 4)
+					|| !strncmp(str, "$BP$", 4)
+					|| !strncmp(str, "$RF$", 4)
+					|| !strncmp(str, "$LT$", 4)
+					|| !strncmp(str, "$GT$", 4)
+					|| !strncmp(str, "$LP$", 4)
+					|| !strncmp(str, "$RP$", 4))
+				str += 4;
+			else if (!strncmp(str, "$u20$", 5)
+					|| !strncmp(str, "$u27$", 5)
+					|| !strncmp(str, "$u5b$", 5)
+					|| !strncmp(str, "$u5d$", 5)
+					|| !strncmp(str, "$u7e$", 5))
+				str += 5;
+			else
+				return false;
+			break;
+		case '.':
+			/* Do not allow three or more consecutive dots */
+			if (!strncmp(str, "...", 3))
+				return false;
+			/* Fall through */
+		case 'a' ... 'z':
+		case 'A' ... 'Z':
+		case '0' ... '9':
+		case '_':
+		case ':':
+			str++;
+			break;
+		default:
+			return false;
+		}
+
+	return true;
+}
+
+/*
+ * INPUT:
+ *     sym: symbol for which rust_is_mangled(sym) returns true
+ *
+ * The input is demangled in-place because the mangled name is always longer
+ * than the demangled one.
+ */
+void
+rust_demangle_sym(char *sym)
+{
+	const char *in;
+	char *out;
+	const char *end;
+
+	if (!sym)
+		return;
+
+	in = sym;
+	out = sym;
+	end = sym + strlen(sym) - (hash_prefix_len + hash_len);
+
+	while (in < end)
+		switch (*in) {
+		case '$':
+			if (!(unescape(&in, &out, "$C$", ',')
+					|| unescape(&in, &out, "$SP$", '@')
+					|| unescape(&in, &out, "$BP$", '*')
+					|| unescape(&in, &out, "$RF$", '&')
+					|| unescape(&in, &out, "$LT$", '<')
+					|| unescape(&in, &out, "$GT$", '>')
+					|| unescape(&in, &out, "$LP$", '(')
+					|| unescape(&in, &out, "$RP$", ')')
+					|| unescape(&in, &out, "$u20$", ' ')
+					|| unescape(&in, &out, "$u27$", '\'')
+					|| unescape(&in, &out, "$u5b$", '[')
+					|| unescape(&in, &out, "$u5d$", ']')
+					|| unescape(&in, &out, "$u7e$", '~'))) {
+				pr_err("demangle-rust: unexpected escape sequence");
+				goto done;
+			}
+			break;
+		case '_':
+			/*
+			 * If this is the start of a path component and the next
+			 * character is an escape sequence, ignore the
+			 * underscore. The mangler inserts an underscore to make
+			 * sure the path component begins with a XID_Start
+			 * character.
+			 */
+			if ((in == sym || in[-1] == ':') && in[1] == '$')
+				in++;
+			else
+				*out++ = *in++;
+			break;
+		case '.':
+			if (in[1] == '.') {
+				/* ".." becomes "::" */
+				*out++ = ':';
+				*out++ = ':';
+				in += 2;
+			} else {
+				/* "." becomes "-" */
+				*out++ = '-';
+				in++;
+			}
+			break;
+		case 'a' ... 'z':
+		case 'A' ... 'Z':
+		case '0' ... '9':
+		case ':':
+			*out++ = *in++;
+			break;
+		default:
+			pr_err("demangle-rust: unexpected character '%c' in symbol\n",
+				*in);
+			goto done;
+		}
+
+done:
+	*out = '\0';
+}
+
+static bool unescape(const char **in, char **out, const char *seq, char value)
+{
+	size_t len = strlen(seq);
+
+	if (strncmp(*in, seq, len))
+		return false;
+
+	**out = value;
+
+	*in += len;
+	*out += 1;
+
+	return true;
+}
diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h
new file mode 100644
index 0000000..7b41ead
--- /dev/null
+++ b/tools/perf/util/demangle-rust.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_DEMANGLE_RUST
+#define __PERF_DEMANGLE_RUST 1
+
+bool rust_is_mangled(const char *str);
+void rust_demangle_sym(char *str);
+
+#endif /* __PERF_DEMANGLE_RUST */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 5d286f5..774f6ec 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -335,7 +335,7 @@ static int do_open(char *name)
 			return fd;
 
 		pr_debug("dso open failed: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		if (!dso__data_open_cnt || errno != EMFILE)
 			break;
 
@@ -442,17 +442,27 @@ static rlim_t get_fd_limit(void)
 	return limit;
 }
 
-static bool may_cache_fd(void)
+static rlim_t fd_limit;
+
+/*
+ * Used only by tests/dso-data.c to reset the environment
+ * for tests. I dont expect we should change this during
+ * standard runtime.
+ */
+void reset_fd_limit(void)
 {
-	static rlim_t limit;
+	fd_limit = 0;
+}
 
-	if (!limit)
-		limit = get_fd_limit();
+static bool may_cache_fd(void)
+{
+	if (!fd_limit)
+		fd_limit = get_fd_limit();
 
-	if (limit == RLIM_INFINITY)
+	if (fd_limit == RLIM_INFINITY)
 		return true;
 
-	return limit > (rlim_t) dso__data_open_cnt;
+	return fd_limit > (rlim_t) dso__data_open_cnt;
 }
 
 /*
@@ -776,7 +786,7 @@ static int data_file_size(struct dso *dso, struct machine *machine)
 	if (fstat(dso->data.fd, &st) < 0) {
 		ret = -errno;
 		pr_err("dso cache fstat failed: %s\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		dso->data.status = DSO_DATA_STATUS_ERROR;
 		goto out;
 	}
@@ -1356,7 +1366,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
 	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
-		const char *err = strerror_r(errnum, buf, buflen);
+		const char *err = str_error_r(errnum, buf, buflen);
 
 		if (err != buf)
 			scnprintf(buf, buflen, "%s", err);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 0953280..ecc4bbd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -4,6 +4,7 @@
 #include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
+#include <sys/types.h>
 #include <stdbool.h>
 #include <pthread.h>
 #include <linux/types.h>
@@ -349,10 +350,17 @@ static inline bool dso__is_kcore(struct dso *dso)
 	       dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
+static inline bool dso__is_kallsyms(struct dso *dso)
+{
+	return dso->kernel && dso->long_name[0] != '/';
+}
+
 void dso__free_a2l(struct dso *dso);
 
 enum dso_type dso__type(struct dso *dso, struct machine *machine);
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen);
 
+void reset_fd_limit(void);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 49a11d9..bb964e8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -18,10 +18,13 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->cmdline_argv);
 	zfree(&env->sibling_cores);
 	zfree(&env->sibling_threads);
-	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
 
+	for (i = 0; i < env->nr_numa_nodes; i++)
+		cpu_map__put(env->numa_nodes[i].map);
+	zfree(&env->numa_nodes);
+
 	for (i = 0; i < env->caches_cnt; i++)
 		cpu_cache_level__free(&env->caches[i]);
 	zfree(&env->caches);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 56cffb6..b164dfd 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -2,6 +2,7 @@
 #define __PERF_ENV_H
 
 #include <linux/types.h>
+#include "cpumap.h"
 
 struct cpu_topology_map {
 	int	socket_id;
@@ -18,6 +19,13 @@ struct cpu_cache_level {
 	char	*map;
 };
 
+struct numa_node {
+	u32		 node;
+	u64		 mem_total;
+	u64		 mem_free;
+	struct cpu_map	*map;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -40,11 +48,11 @@ struct perf_env {
 	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_threads;
-	char			*numa_nodes;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
+	struct numa_node	*numa_nodes;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9b141f1..e20438b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1092,7 +1092,7 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
 	struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
 	size_t ret;
 
-	ret = fprintf(fp, " nr: ");
+	ret = fprintf(fp, ": ");
 
 	if (cpus)
 		ret += cpu_map__fprintf(cpus, fp);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8d363d5..b32464b 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,6 +8,7 @@
 #include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
+#include <asm/perf_regs.h>
 
 struct mmap_event {
 	struct perf_event_header header;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e82ba90..2a40b8e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -15,6 +15,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
+#include "asm/bug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -27,8 +28,8 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+static void perf_mmap__munmap(struct perf_mmap *map);
+static void perf_mmap__put(struct perf_mmap *map);
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
@@ -44,7 +45,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__set_maps(evlist, cpus, threads);
 	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
-	evlist->backward = false;
+	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -100,7 +101,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		perf_evsel__calc_id_pos(evsel);
 
 	perf_evlist__set_id_pos(evlist);
@@ -110,7 +111,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos, *n;
 
-	evlist__for_each_safe(evlist, n, pos) {
+	evlist__for_each_entry_safe(evlist, n, pos) {
 		list_del_init(&pos->node);
 		pos->evlist = NULL;
 		perf_evsel__delete(pos);
@@ -122,11 +123,15 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 	fdarray__exit(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+	if (evlist == NULL)
+		return;
+
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
 	cpu_map__put(evlist->cpus);
@@ -161,7 +166,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evlist__propagate_maps(evlist, evsel);
 }
 
@@ -190,7 +195,7 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel, *temp;
 
-	__evlist__for_each_safe(list, temp, evsel) {
+	__evlist__for_each_entry_safe(list, temp, evsel) {
 		list_del_init(&evsel->node);
 		perf_evlist__add(evlist, evsel);
 	}
@@ -205,7 +210,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
 	leader->nr_members = evsel->idx - leader->idx + 1;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		evsel->leader = leader;
 	}
 }
@@ -296,7 +301,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 	return 0;
 
 out_delete_partial_list:
-	__evlist__for_each_safe(&head, n, evsel)
+	__evlist__for_each_entry_safe(&head, n, evsel)
 		perf_evsel__delete(evsel);
 	return -1;
 }
@@ -317,7 +322,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
 		    (int)evsel->attr.config == id)
 			return evsel;
@@ -332,7 +337,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
 		    (strcmp(evsel->name, name) == 0))
 			return evsel;
@@ -367,7 +372,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
@@ -380,7 +385,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__enable(pos);
@@ -448,7 +453,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	int nfds = 0;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->system_wide)
 			nfds += nr_cpus;
 		else
@@ -462,15 +467,16 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	return 0;
 }
 
-static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+				     struct perf_mmap *map, short revent)
 {
-	int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
 	/*
 	 * Save the idx so that when we filter out fds POLLHUP'ed we can
 	 * close the associated evlist->mmap[] entry.
 	 */
 	if (pos >= 0) {
-		evlist->pollfd.priv[pos].idx = idx;
+		evlist->pollfd.priv[pos].ptr = map;
 
 		fcntl(fd, F_SETFL, O_NONBLOCK);
 	}
@@ -480,20 +486,22 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
 {
-	return __perf_evlist__add_pollfd(evlist, fd, -1);
+	return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN);
 }
 
-static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
+					 void *arg __maybe_unused)
 {
-	struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+	struct perf_mmap *map = fda->priv[fd].ptr;
 
-	perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+	if (map)
+		perf_mmap__put(map);
 }
 
 int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
 {
 	return fdarray__filter(&evlist->pollfd, revents_and_mask,
-			       perf_evlist__munmap_filtered);
+			       perf_evlist__munmap_filtered, NULL);
 }
 
 int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
@@ -647,8 +655,8 @@ static int perf_evlist__event2id(struct perf_evlist *evlist,
 	return 0;
 }
 
-static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
-						   union perf_event *event)
+struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+					    union perf_event *event)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist);
 	struct hlist_head *head;
@@ -684,8 +692,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
 	int i;
 
+	if (!evlist->backward_mmap)
+		return 0;
+
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->mmap[i].fd;
+		int fd = evlist->backward_mmap[i].fd;
 		int err;
 
 		if (fd < 0)
@@ -697,12 +708,12 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 	return 0;
 }
 
-int perf_evlist__pause(struct perf_evlist *evlist)
+static int perf_evlist__pause(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, true);
 }
 
-int perf_evlist__resume(struct perf_evlist *evlist)
+static int perf_evlist__resume(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, false);
 }
@@ -777,9 +788,8 @@ broken_event:
 	return event;
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head;
 	u64 old = md->prev;
 
@@ -791,13 +801,12 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 	head = perf_mmap__read_head(md);
 
-	return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+	return perf_mmap__read(md, check_messup, old, head, &md->prev);
 }
 
 union perf_event *
-perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
+perf_mmap__read_backward(struct perf_mmap *md)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head, end;
 	u64 start = md->prev;
 
@@ -832,9 +841,38 @@ perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 	return perf_mmap__read(md, false, start, end, &md->prev);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
+{
+	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * Check messup is required for forward overwritable ring buffer:
+	 * memory pointed by md->prev can be overwritten in this case.
+	 * No need for read-write ring buffer: kernel stop outputting when
+	 * it hit md->prev (perf_mmap__consume()).
+	 */
+	return perf_mmap__read_forward(md, evlist->overwrite);
+}
+
+union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * No need to check messup for backward ring buffer:
+	 * We can always read arbitrary long data from a backward
+	 * ring buffer unless we forget to pause it before reading.
+	 */
+	return perf_mmap__read_backward(md);
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+	return perf_evlist__mmap_read_forward(evlist, idx);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *md)
+{
 	u64 head;
 
 	if (!atomic_read(&md->refcnt))
@@ -844,36 +882,44 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 	md->prev = head;
 }
 
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__read_catchup(&evlist->mmap[idx]);
+}
+
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
 	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
-static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+static void perf_mmap__get(struct perf_mmap *map)
 {
-	atomic_inc(&evlist->mmap[idx].refcnt);
+	atomic_inc(&map->refcnt);
 }
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+static void perf_mmap__put(struct perf_mmap *md)
 {
-	BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
+	BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
 
-	if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
-		__perf_evlist__munmap(evlist, idx);
+	if (atomic_dec_and_test(&md->refcnt))
+		perf_mmap__munmap(md);
 }
 
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-
-	if (!evlist->overwrite) {
+	if (!overwrite) {
 		u64 old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
 
 	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-		perf_evlist__mmap_put(evlist, idx);
+		perf_mmap__put(md);
+}
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
 int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
@@ -904,41 +950,52 @@ void __weak auxtrace_mmap_params__set_idx(
 {
 }
 
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+static void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (evlist->mmap[idx].base != NULL) {
-		munmap(evlist->mmap[idx].base, evlist->mmap_len);
-		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].fd = -1;
-		atomic_set(&evlist->mmap[idx].refcnt, 0);
+	if (map->base != NULL) {
+		munmap(map->base, perf_mmap__mmap_len(map));
+		map->base = NULL;
+		map->fd = -1;
+		atomic_set(&map->refcnt, 0);
 	}
-	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
+	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-void perf_evlist__munmap(struct perf_evlist *evlist)
+static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;
 
-	if (evlist->mmap == NULL)
-		return;
+	if (evlist->mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->mmap[i]);
 
-	for (i = 0; i < evlist->nr_mmaps; i++)
-		__perf_evlist__munmap(evlist, i);
+	if (evlist->backward_mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->backward_mmap[i]);
+}
 
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+	perf_evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 }
 
-static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	int i;
+	struct perf_mmap *map;
 
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
-	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	if (!map)
+		return NULL;
+
 	for (i = 0; i < evlist->nr_mmaps; i++)
-		evlist->mmap[i].fd = -1;
-	return evlist->mmap != NULL ? 0 : -ENOMEM;
+		map[i].fd = -1;
+	return map;
 }
 
 struct mmap_params {
@@ -947,8 +1004,8 @@ struct mmap_params {
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
-			       struct mmap_params *mp, int fd)
+static int perf_mmap__mmap(struct perf_mmap *map,
+			   struct mmap_params *mp, int fd)
 {
 	/*
 	 * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -963,35 +1020,61 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	atomic_set(&evlist->mmap[idx].refcnt, 2);
-	evlist->mmap[idx].prev = 0;
-	evlist->mmap[idx].mask = mp->mask;
-	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
-				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
+	atomic_set(&map->refcnt, 2);
+	map->prev = 0;
+	map->mask = mp->mask;
+	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+			 MAP_SHARED, fd, 0);
+	if (map->base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
 			  errno);
-		evlist->mmap[idx].base = NULL;
+		map->base = NULL;
 		return -1;
 	}
-	evlist->mmap[idx].fd = fd;
+	map->fd = fd;
 
-	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
-				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+				&mp->auxtrace_mp, map->base, fd))
 		return -1;
 
 	return 0;
 }
 
+static bool
+perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	if (evsel->attr.write_backward)
+		return false;
+	return true;
+}
+
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu,
-				       int thread, int *output)
+				       int thread, int *_output, int *_output_backward)
 {
 	struct perf_evsel *evsel;
+	int revent;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
+		struct perf_mmap *maps = evlist->mmap;
+		int *output = _output;
 		int fd;
 
+		if (evsel->attr.write_backward) {
+			output = _output_backward;
+			maps = evlist->backward_mmap;
+
+			if (!maps) {
+				maps = perf_evlist__alloc_mmap(evlist);
+				if (!maps)
+					return -1;
+				evlist->backward_mmap = maps;
+				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
+					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+			}
+		}
+
 		if (evsel->system_wide && thread)
 			continue;
 
@@ -999,15 +1082,18 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
 		if (*output == -1) {
 			*output = fd;
-			if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
+
+			if (perf_mmap__mmap(&maps[idx], mp, *output)  < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
 
-			perf_evlist__mmap_get(evlist, idx);
+			perf_mmap__get(&maps[idx]);
 		}
 
+		revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0;
+
 		/*
 		 * The system_wide flag causes a selected event to be opened
 		 * always without a pid.  Consequently it will never get a
@@ -1016,8 +1102,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		 * Therefore don't add it for polling.
 		 */
 		if (!evsel->system_wide &&
-		    __perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
-			perf_evlist__mmap_put(evlist, idx);
+		    __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) {
+			perf_mmap__put(&maps[idx]);
 			return -1;
 		}
 
@@ -1043,13 +1129,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output))
+							thread, &output, &output_backward))
 				goto out_unmap;
 		}
 	}
@@ -1057,8 +1144,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		__perf_evlist__munmap(evlist, cpu);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1071,20 +1157,20 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output))
+						&output, &output_backward))
 			goto out_unmap;
 	}
 
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++)
-		__perf_evlist__munmap(evlist, thread);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1217,7 +1303,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
 	};
 
-	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+	if (!evlist->mmap)
+		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+	if (!evlist->mmap)
 		return -ENOMEM;
 
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
@@ -1231,7 +1319,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -1307,7 +1395,7 @@ void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__set_sample_bit(evsel, bit);
 }
 
@@ -1316,7 +1404,7 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__reset_sample_bit(evsel, bit);
 }
 
@@ -1327,7 +1415,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 	const int ncpus = cpu_map__nr(evlist->cpus),
 		  nthreads = thread_map__nr(evlist->threads);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->filter == NULL)
 			continue;
 
@@ -1350,7 +1438,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -1404,7 +1492,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 	if (evlist->id_pos < 0 || evlist->is_pos < 0)
 		return false;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->id_pos != evlist->id_pos ||
 		    pos->is_pos != evlist->is_pos)
 			return false;
@@ -1420,7 +1508,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 	if (evlist->combined_sample_type)
 		return evlist->combined_sample_type;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		evlist->combined_sample_type |= evsel->attr.sample_type;
 
 	return evlist->combined_sample_type;
@@ -1437,7 +1525,7 @@ u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	u64 branch_type = 0;
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		branch_type |= evsel->attr.branch_sample_type;
 	return branch_type;
 }
@@ -1448,7 +1536,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
 	u64 read_format = first->attr.read_format;
 	u64 sample_type = first->attr.sample_type;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (read_format != pos->attr.read_format)
 			return false;
 	}
@@ -1505,7 +1593,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-	evlist__for_each_continue(evlist, pos) {
+	evlist__for_each_entry_continue(evlist, pos) {
 		if (first->attr.sample_id_all != pos->attr.sample_id_all)
 			return false;
 	}
@@ -1532,7 +1620,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	int nthreads = thread_map__nr(evlist->threads);
 	int n;
 
-	evlist__for_each_reverse(evlist, evsel) {
+	evlist__for_each_entry_reverse(evlist, evsel) {
 		n = evsel->cpus ? evsel->cpus->nr : ncpus;
 		perf_evsel__close(evsel, n, nthreads);
 	}
@@ -1586,7 +1674,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	perf_evlist__update_id_pos(evlist);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
 		if (err < 0)
 			goto out_err;
@@ -1747,7 +1835,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	struct perf_evsel *evsel;
 	size_t printed = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
 				   perf_evsel__name(evsel));
 	}
@@ -1759,7 +1847,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
-	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 
 	switch (err) {
 	case EACCES:
@@ -1811,7 +1899,7 @@ out_default:
 
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
 {
-	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 	int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
 
 	switch (err) {
@@ -1849,7 +1937,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 	if (move_evsel == perf_evlist__first(evlist))
 		return;
 
-	evlist__for_each_safe(evlist, n, evsel) {
+	evlist__for_each_entry_safe(evlist, n, evsel) {
 		if (evsel->leader == move_evsel->leader)
 			list_move_tail(&evsel->node, &move);
 	}
@@ -1865,7 +1953,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 	if (tracking_evsel->tracking)
 		return;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel != tracking_evsel)
 			evsel->tracking = false;
 	}
@@ -1879,7 +1967,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (!evsel->name)
 			continue;
 		if (strcmp(str, evsel->name) == 0)
@@ -1888,3 +1976,61 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 
 	return NULL;
 }
+
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
+				  enum bkw_mmap_state state)
+{
+	enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
+	enum action {
+		NONE,
+		PAUSE,
+		RESUME,
+	} action = NONE;
+
+	if (!evlist->backward_mmap)
+		return;
+
+	switch (old_state) {
+	case BKW_MMAP_NOTREADY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;;
+		break;
+	}
+	case BKW_MMAP_RUNNING: {
+		if (state != BKW_MMAP_DATA_PENDING)
+			goto state_err;
+		action = PAUSE;
+		break;
+	}
+	case BKW_MMAP_DATA_PENDING: {
+		if (state != BKW_MMAP_EMPTY)
+			goto state_err;
+		break;
+	}
+	case BKW_MMAP_EMPTY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;
+		action = RESUME;
+		break;
+	}
+	default:
+		WARN_ONCE(1, "Shouldn't get there\n");
+	}
+
+	evlist->bkw_mmap_state = state;
+
+	switch (action) {
+	case PAUSE:
+		perf_evlist__pause(evlist);
+		break;
+	case RESUME:
+		perf_evlist__resume(evlist);
+		break;
+	case NONE:
+	default:
+		break;
+	}
+
+state_err:
+	return;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index d740fb8..4fd034f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -35,6 +35,40 @@ struct perf_mmap {
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
+static inline size_t
+perf_mmap__mmap_len(struct perf_mmap *map)
+{
+	return map->mask + 1 + page_size;
+}
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+	BKW_MMAP_NOTREADY,
+	BKW_MMAP_RUNNING,
+	BKW_MMAP_DATA_PENDING,
+	BKW_MMAP_EMPTY,
+};
+
 struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -44,17 +78,18 @@ struct perf_evlist {
 	bool		 overwrite;
 	bool		 enabled;
 	bool		 has_user_cpus;
-	bool		 backward;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
 	u64		 combined_sample_type;
+	enum bkw_mmap_state bkw_mmap_state;
 	struct {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
+	struct perf_mmap *backward_mmap;
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
@@ -129,16 +164,24 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
 
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+void perf_mmap__read_catchup(struct perf_mmap *md);
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
+						 int idx);
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
 						  int idx);
 void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
-int perf_evlist__pause(struct perf_evlist *evlist);
-int perf_evlist__resume(struct perf_evlist *evlist);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
@@ -249,70 +292,70 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 			   struct perf_evsel *move_evsel);
 
 /**
- * __evlist__for_each - iterate thru all the evsels
+ * __evlist__for_each_entry - iterate thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each(list, evsel) \
+#define __evlist__for_each_entry(list, evsel) \
         list_for_each_entry(evsel, list, node)
 
 /**
- * evlist__for_each - iterate thru all the evsels
+ * evlist__for_each_entry - iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each(evlist, evsel) \
-	__evlist__for_each(&(evlist)->entries, evsel)
+#define evlist__for_each_entry(evlist, evsel) \
+	__evlist__for_each_entry(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_continue - continue iteration thru all the evsels
+ * __evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_continue(list, evsel) \
+#define __evlist__for_each_entry_continue(list, evsel) \
         list_for_each_entry_continue(evsel, list, node)
 
 /**
- * evlist__for_each_continue - continue iteration thru all the evsels
+ * evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_continue(evlist, evsel) \
-	__evlist__for_each_continue(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_continue(evlist, evsel) \
+	__evlist__for_each_entry_continue(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_reverse(list, evsel) \
+#define __evlist__for_each_entry_reverse(list, evsel) \
         list_for_each_entry_reverse(evsel, list, node)
 
 /**
- * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_reverse(evlist, evsel) \
-	__evlist__for_each_reverse(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_reverse(evlist, evsel) \
+	__evlist__for_each_entry_reverse(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_safe - safely iterate thru all the evsels
+ * __evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @list: list_head instance to iterate
  * @tmp: struct evsel temp iterator
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_safe(list, tmp, evsel) \
+#define __evlist__for_each_entry_safe(list, tmp, evsel) \
         list_for_each_entry_safe(evsel, tmp, list, node)
 
 /**
- * evlist__for_each_safe - safely iterate thru all the evsels
+ * evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  * @tmp: struct evsel temp iterator
  */
-#define evlist__for_each_safe(evlist, tmp, evsel) \
-	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
+	__evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel)
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
@@ -321,4 +364,7 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
 
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
+
+struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+					    union perf_event *event);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5d7037e..8c54df6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -200,6 +200,24 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel,
 	evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+	return evsel->name &&
+	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
@@ -572,6 +590,8 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
+	attr->sample_max_stack = param->max_stack;
+
 	if (param->record_mode == CALLCHAIN_LBR) {
 		if (!opts->branch_stack) {
 			if (attr->exclude_user) {
@@ -635,7 +655,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	struct perf_event_attr *attr = &evsel->attr;
 	struct callchain_param param;
 	u32 dump_size = 0;
-	char *callgraph_buf = NULL;
+	int max_stack = 0;
+	const char *callgraph_buf = NULL;
 
 	/* callgraph default */
 	param.record_mode = callchain_param.record_mode;
@@ -662,6 +683,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_STACK_USER:
 			dump_size = term->val.stack_user;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
+			max_stack = term->val.max_stack;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
@@ -671,13 +695,21 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			 */
 			attr->inherit = term->val.inherit ? 1 : 0;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
+			attr->write_backward = term->val.overwrite ? 1 : 0;
+			break;
 		default:
 			break;
 		}
 	}
 
 	/* User explicitly set per-event callgraph, clear the old setting and reset. */
-	if ((callgraph_buf != NULL) || (dump_size > 0)) {
+	if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
+		if (max_stack) {
+			param.max_stack = max_stack;
+			if (callgraph_buf == NULL)
+				callgraph_buf = "fp";
+		}
 
 		/* parse callgraph parameters */
 		if (callgraph_buf != NULL) {
@@ -747,6 +779,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
+	attr->write_backward = opts->overwrite ? 1 : 0;
 
 	perf_evsel__set_sample_bit(evsel, IP);
 	perf_evsel__set_sample_bit(evsel, TID);
@@ -1329,6 +1362,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(clockid, p_signed);
 	PRINT_ATTRf(sample_regs_intr, p_hex);
 	PRINT_ATTRf(aux_watermark, p_unsigned);
+	PRINT_ATTRf(sample_max_stack, p_unsigned);
 
 	return ret;
 }
@@ -1347,6 +1381,9 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (perf_missing_features.write_backward && evsel->attr.write_backward)
+		return -EINVAL;
+
 	if (evsel->system_wide)
 		nthreads = 1;
 	else
@@ -1377,8 +1414,6 @@ fallback_missing_features:
 	if (perf_missing_features.lbr_flags)
 		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
-	if (perf_missing_features.write_backward)
-		evsel->attr.write_backward = false;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1441,12 +1476,6 @@ retry_open:
 				err = -EINVAL;
 				goto out_close;
 			}
-
-			if (evsel->overwrite &&
-			    perf_missing_features.write_backward) {
-				err = -EINVAL;
-				goto out_close;
-			}
 		}
 	}
 
@@ -1484,7 +1513,10 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
+	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
+		perf_missing_features.write_backward = true;
+		goto out_close;
+	} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
 		perf_missing_features.clockid_wrong = true;
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
@@ -1509,12 +1541,7 @@ try_fallback:
 			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
 		perf_missing_features.lbr_flags = true;
 		goto fallback_missing_features;
-	} else if (!perf_missing_features.write_backward &&
-			evsel->attr.write_backward) {
-		perf_missing_features.write_backward = true;
-		goto fallback_missing_features;
 	}
-
 out_close:
 	do {
 		while (--thread >= 0) {
@@ -2239,17 +2266,11 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 	return sample->raw_data + offset;
 }
 
-u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
-		       const char *name)
+u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+			 bool needs_swap)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
-	void *ptr;
 	u64 value;
-
-	if (!field)
-		return 0;
-
-	ptr = sample->raw_data + field->offset;
+	void *ptr = sample->raw_data + field->offset;
 
 	switch (field->size) {
 	case 1:
@@ -2267,7 +2288,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		return 0;
 	}
 
-	if (!evsel->needs_swap)
+	if (!needs_swap)
 		return value;
 
 	switch (field->size) {
@@ -2284,6 +2305,17 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 	return 0;
 }
 
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+		       const char *name)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+
+	if (!field)
+		return 0;
+
+	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
+}
+
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
@@ -2372,6 +2404,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	 "No such device - did you specify an out-of-range profile CPU?");
 		break;
 	case EOPNOTSUPP:
+		if (evsel->attr.sample_period != 0)
+			return scnprintf(msg, size, "%s",
+	"PMU Hardware doesn't support sampling/overflow-interrupts.");
 		if (evsel->attr.precise_ip)
 			return scnprintf(msg, size, "%s",
 	"\'precise\' request may not be supported. Try removing 'p' modifier.");
@@ -2389,6 +2424,8 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"We found oprofile daemon running, please stop it and try again.");
 		break;
 	case EINVAL:
+		if (evsel->attr.write_backward && perf_missing_features.write_backward)
+			return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
 		if (perf_missing_features.clockid)
 			return scnprintf(msg, size, "clockid feature not supported.");
 		if (perf_missing_features.clockid_wrong)
@@ -2402,6 +2439,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg may provide additional information.\n"
 	"No CONFIG_PERF_EVENTS=y kernel support configured?",
-			 err, strerror_r(err, sbuf, sizeof(sbuf)),
+			 err, str_error_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
+
+char *perf_evsel__env_arch(struct perf_evsel *evsel)
+{
+	if (evsel && evsel->evlist && evsel->evlist->env)
+		return evsel->evlist->env->arch;
+	return NULL;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c1f1015..8a4a6c9 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -44,6 +44,8 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
+	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -56,7 +58,9 @@ struct perf_evsel_config_term {
 		bool	time;
 		char	*callgraph;
 		u64	stack_user;
+		int	max_stack;
 		bool	inherit;
+		bool	overwrite;
 	} val;
 };
 
@@ -112,7 +116,6 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
-	bool			overwrite;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
@@ -259,6 +262,8 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 
 struct format_field;
 
+u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+
 struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
@@ -351,23 +356,7 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
 	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
 }
 
-/**
- * perf_evsel__is_function_event - Return whether given evsel is a function
- * trace event
- *
- * @evsel - evsel selector to be tested
- *
- * Return %true if event is function trace event
- */
-static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
-{
-#define FUNCTION_EVENT "ftrace:function"
-
-	return evsel->name &&
-	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
-
-#undef FUNCTION_EVENT
-}
+bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
@@ -431,4 +420,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv);
 
+char *perf_evsel__env_arch(struct perf_evsel *evsel);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h
new file mode 100644
index 0000000..116debe
--- /dev/null
+++ b/tools/perf/util/group.h
@@ -0,0 +1,7 @@
+#ifndef GROUP_H
+#define GROUP_H 1
+
+bool arch_topdown_check_group(bool *warn);
+void arch_topdown_group_warn(void);
+
+#endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 08852dd..8f0db40 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -336,7 +336,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		ret = do_write(fd, &evsel->attr, sz);
 		if (ret < 0)
 			return ret;
@@ -801,7 +801,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			const char *name = evsel->group_name ?: "{anon_group}";
@@ -1306,42 +1306,19 @@ static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
 static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
 				FILE *fp)
 {
-	u32 nr, c, i;
-	char *str, *tmp;
-	uint64_t mem_total, mem_free;
-
-	/* nr nodes */
-	nr = ph->env.nr_numa_nodes;
-	str = ph->env.numa_nodes;
-
-	for (i = 0; i < nr; i++) {
-		/* node number */
-		c = strtoul(str, &tmp, 0);
-		if (*tmp != ':')
-			goto error;
-
-		str = tmp + 1;
-		mem_total = strtoull(str, &tmp, 0);
-		if (*tmp != ':')
-			goto error;
+	int i;
+	struct numa_node *n;
 
-		str = tmp + 1;
-		mem_free = strtoull(str, &tmp, 0);
-		if (*tmp != ':')
-			goto error;
+	for (i = 0; i < ph->env.nr_numa_nodes; i++) {
+		n = &ph->env.numa_nodes[i];
 
 		fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
 			    " free = %"PRIu64" kB\n",
-			c, mem_total, mem_free);
+			n->node, n->mem_total, n->mem_free);
 
-		str = tmp + 1;
-		fprintf(fp, "# node%u cpu list : %s\n", c, str);
-
-		str += strlen(str) + 1;
+		fprintf(fp, "# node%u cpu list : ", n->node);
+		cpu_map__fprintf(n->map, fp);
 	}
-	return;
-error:
-	fprintf(fp, "# numa topology : not available\n");
 }
 
 static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
@@ -1425,7 +1402,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
 	session = container_of(ph, struct perf_session, header);
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1703,7 +1680,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->idx == idx)
 			return evsel;
 	}
@@ -1906,11 +1883,10 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 				 struct perf_header *ph, int fd,
 				 void *data __maybe_unused)
 {
+	struct numa_node *nodes, *n;
 	ssize_t ret;
-	u32 nr, node, i;
+	u32 nr, i;
 	char *str;
-	uint64_t mem_total, mem_free;
-	struct strbuf sb;
 
 	/* nr nodes */
 	ret = readn(fd, &nr, sizeof(nr));
@@ -1921,47 +1897,47 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 		nr = bswap_32(nr);
 
 	ph->env.nr_numa_nodes = nr;
-	if (strbuf_init(&sb, 256) < 0)
-		return -1;
+	nodes = zalloc(sizeof(*nodes) * nr);
+	if (!nodes)
+		return -ENOMEM;
 
 	for (i = 0; i < nr; i++) {
+		n = &nodes[i];
+
 		/* node number */
-		ret = readn(fd, &node, sizeof(node));
-		if (ret != sizeof(node))
+		ret = readn(fd, &n->node, sizeof(u32));
+		if (ret != sizeof(n->node))
 			goto error;
 
-		ret = readn(fd, &mem_total, sizeof(u64));
+		ret = readn(fd, &n->mem_total, sizeof(u64));
 		if (ret != sizeof(u64))
 			goto error;
 
-		ret = readn(fd, &mem_free, sizeof(u64));
+		ret = readn(fd, &n->mem_free, sizeof(u64));
 		if (ret != sizeof(u64))
 			goto error;
 
 		if (ph->needs_swap) {
-			node = bswap_32(node);
-			mem_total = bswap_64(mem_total);
-			mem_free = bswap_64(mem_free);
+			n->node      = bswap_32(n->node);
+			n->mem_total = bswap_64(n->mem_total);
+			n->mem_free  = bswap_64(n->mem_free);
 		}
 
-		if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
-				node, mem_total, mem_free) < 0)
-			goto error;
-
 		str = do_read_string(fd, ph);
 		if (!str)
 			goto error;
 
-		/* include a NULL character at the end */
-		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+		n->map = cpu_map__new(str);
+		if (!n->map)
 			goto error;
+
 		free(str);
 	}
-	ph->env.numa_nodes = strbuf_detach(&sb, NULL);
+	ph->env.numa_nodes = nodes;
 	return 0;
 
 error:
-	strbuf_release(&sb);
+	free(nodes);
 	return -1;
 }
 
@@ -2075,7 +2051,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 	session->evlist->nr_groups = nr_groups;
 
 	i = nr = 0;
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->idx == (int) desc[i].leader_idx) {
 			evsel->leader = evsel;
 			/* {anon_group} is a dummy name */
@@ -2383,7 +2359,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	lseek(fd, sizeof(f_header), SEEK_SET);
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		evsel->id_offset = lseek(fd, 0, SEEK_CUR);
 		err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
 		if (err < 0) {
@@ -2394,7 +2370,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	attr_offset = lseek(fd, 0, SEEK_CUR);
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		f_attr = (struct perf_file_attr){
 			.attr = evsel->attr,
 			.ids  = {
@@ -2828,7 +2804,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
 		    perf_evsel__prepare_tracepoint_event(pos, pevent))
 			return -1;
@@ -3127,7 +3103,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index d62ccae..2821f8d 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -1,4 +1,6 @@
 #include "cache.h"
+#include "config.h"
+#include <stdio.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d1f19e0..a18d142 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -79,7 +79,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
-		hists__set_col_len(hists, HISTC_THREAD, len + 6);
+		hists__set_col_len(hists, HISTC_THREAD, len + 8);
 
 	if (h->ms.map) {
 		len = dso__name_len(h->ms.map->dso);
@@ -352,86 +352,114 @@ void hists__delete_entries(struct hists *hists)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template,
-					  bool sample_self)
+static int hist_entry__init(struct hist_entry *he,
+			    struct hist_entry *template,
+			    bool sample_self)
 {
-	size_t callchain_size = 0;
-	struct hist_entry *he;
+	*he = *template;
 
-	if (symbol_conf.use_callchain)
-		callchain_size = sizeof(struct callchain_root);
+	if (symbol_conf.cumulate_callchain) {
+		he->stat_acc = malloc(sizeof(he->stat));
+		if (he->stat_acc == NULL)
+			return -ENOMEM;
+		memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+		if (!sample_self)
+			memset(&he->stat, 0, sizeof(he->stat));
+	}
 
-	he = zalloc(sizeof(*he) + callchain_size);
+	map__get(he->ms.map);
 
-	if (he != NULL) {
-		*he = *template;
+	if (he->branch_info) {
+		/*
+		 * This branch info is (a part of) allocated from
+		 * sample__resolve_bstack() and will be freed after
+		 * adding new entries.  So we need to save a copy.
+		 */
+		he->branch_info = malloc(sizeof(*he->branch_info));
+		if (he->branch_info == NULL) {
+			map__zput(he->ms.map);
+			free(he->stat_acc);
+			return -ENOMEM;
+		}
+
+		memcpy(he->branch_info, template->branch_info,
+		       sizeof(*he->branch_info));
+
+		map__get(he->branch_info->from.map);
+		map__get(he->branch_info->to.map);
+	}
 
-		if (symbol_conf.cumulate_callchain) {
-			he->stat_acc = malloc(sizeof(he->stat));
-			if (he->stat_acc == NULL) {
-				free(he);
-				return NULL;
+	if (he->mem_info) {
+		map__get(he->mem_info->iaddr.map);
+		map__get(he->mem_info->daddr.map);
+	}
+
+	if (symbol_conf.use_callchain)
+		callchain_init(he->callchain);
+
+	if (he->raw_data) {
+		he->raw_data = memdup(he->raw_data, he->raw_size);
+
+		if (he->raw_data == NULL) {
+			map__put(he->ms.map);
+			if (he->branch_info) {
+				map__put(he->branch_info->from.map);
+				map__put(he->branch_info->to.map);
+				free(he->branch_info);
+			}
+			if (he->mem_info) {
+				map__put(he->mem_info->iaddr.map);
+				map__put(he->mem_info->daddr.map);
 			}
-			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
-			if (!sample_self)
-				memset(&he->stat, 0, sizeof(he->stat));
+			free(he->stat_acc);
+			return -ENOMEM;
 		}
+	}
+	INIT_LIST_HEAD(&he->pairs.node);
+	thread__get(he->thread);
 
-		map__get(he->ms.map);
+	if (!symbol_conf.report_hierarchy)
+		he->leaf = true;
 
-		if (he->branch_info) {
-			/*
-			 * This branch info is (a part of) allocated from
-			 * sample__resolve_bstack() and will be freed after
-			 * adding new entries.  So we need to save a copy.
-			 */
-			he->branch_info = malloc(sizeof(*he->branch_info));
-			if (he->branch_info == NULL) {
-				map__zput(he->ms.map);
-				free(he->stat_acc);
-				free(he);
-				return NULL;
-			}
+	return 0;
+}
 
-			memcpy(he->branch_info, template->branch_info,
-			       sizeof(*he->branch_info));
+static void *hist_entry__zalloc(size_t size)
+{
+	return zalloc(size + sizeof(struct hist_entry));
+}
 
-			map__get(he->branch_info->from.map);
-			map__get(he->branch_info->to.map);
-		}
+static void hist_entry__free(void *ptr)
+{
+	free(ptr);
+}
 
-		if (he->mem_info) {
-			map__get(he->mem_info->iaddr.map);
-			map__get(he->mem_info->daddr.map);
-		}
+static struct hist_entry_ops default_ops = {
+	.new	= hist_entry__zalloc,
+	.free	= hist_entry__free,
+};
 
-		if (symbol_conf.use_callchain)
-			callchain_init(he->callchain);
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
+{
+	struct hist_entry_ops *ops = template->ops;
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+	int err = 0;
 
-		if (he->raw_data) {
-			he->raw_data = memdup(he->raw_data, he->raw_size);
+	if (!ops)
+		ops = template->ops = &default_ops;
 
-			if (he->raw_data == NULL) {
-				map__put(he->ms.map);
-				if (he->branch_info) {
-					map__put(he->branch_info->from.map);
-					map__put(he->branch_info->to.map);
-					free(he->branch_info);
-				}
-				if (he->mem_info) {
-					map__put(he->mem_info->iaddr.map);
-					map__put(he->mem_info->daddr.map);
-				}
-				free(he->stat_acc);
-				free(he);
-				return NULL;
-			}
-		}
-		INIT_LIST_HEAD(&he->pairs.node);
-		thread__get(he->thread);
+	if (symbol_conf.use_callchain)
+		callchain_size = sizeof(struct callchain_root);
 
-		if (!symbol_conf.report_hierarchy)
-			he->leaf = true;
+	he = ops->new(callchain_size);
+	if (he) {
+		err = hist_entry__init(he, template, sample_self);
+		if (err) {
+			ops->free(he);
+			he = NULL;
+		}
 	}
 
 	return he;
@@ -531,13 +559,15 @@ out:
 	return he;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
-				      struct addr_location *al,
-				      struct symbol *sym_parent,
-				      struct branch_info *bi,
-				      struct mem_info *mi,
-				      struct perf_sample *sample,
-				      bool sample_self)
+static struct hist_entry*
+__hists__add_entry(struct hists *hists,
+		   struct addr_location *al,
+		   struct symbol *sym_parent,
+		   struct branch_info *bi,
+		   struct mem_info *mi,
+		   struct perf_sample *sample,
+		   bool sample_self,
+		   struct hist_entry_ops *ops)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -564,11 +594,37 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = sample->transaction,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
+		.ops = ops,
 	};
 
 	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
+struct hist_entry *hists__add_entry(struct hists *hists,
+				    struct addr_location *al,
+				    struct symbol *sym_parent,
+				    struct branch_info *bi,
+				    struct mem_info *mi,
+				    struct perf_sample *sample,
+				    bool sample_self)
+{
+	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+				  sample, sample_self, NULL);
+}
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+					struct hist_entry_ops *ops,
+					struct addr_location *al,
+					struct symbol *sym_parent,
+					struct branch_info *bi,
+					struct mem_info *mi,
+					struct perf_sample *sample,
+					bool sample_self)
+{
+	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+				  sample, sample_self, ops);
+}
+
 static int
 iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
 		    struct addr_location *al __maybe_unused)
@@ -622,8 +678,8 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	 */
 	sample->period = cost;
 
-	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-				sample, true);
+	he = hists__add_entry(hists, al, iter->parent, NULL, mi,
+			      sample, true);
 	if (!he)
 		return -ENOMEM;
 
@@ -727,8 +783,8 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	sample->period = 1;
 	sample->weight = bi->flags.cycles ? bi->flags.cycles : 1;
 
-	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-				sample, true);
+	he = hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
+			      sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -764,8 +820,8 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
-	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample, true);
+	he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+			      sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -825,8 +881,8 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	struct hist_entry *he;
 	int err = 0;
 
-	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
-				sample, true);
+	he = hists__add_entry(hists, al, iter->parent, NULL, NULL,
+			      sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -900,8 +956,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 		}
 	}
 
-	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample, false);
+	he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+			      sample, false);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -1043,6 +1099,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__delete(struct hist_entry *he)
 {
+	struct hist_entry_ops *ops = he->ops;
+
 	thread__zput(he->thread);
 	map__zput(he->ms.map);
 
@@ -1067,7 +1125,7 @@ void hist_entry__delete(struct hist_entry *he)
 	free_callchain(he->callchain);
 	free(he->trace_output);
 	free(he->raw_data);
-	free(he);
+	ops->free(he);
 }
 
 /*
@@ -1081,7 +1139,7 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed)
 {
 	if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
-		const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+		const int width = fmt->width(fmt, hpp, he->hists);
 		if (printed < width) {
 			advance_hpp(hpp, printed);
 			printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
@@ -2199,7 +2257,7 @@ size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
 	struct perf_evsel *pos;
 	size_t ret = 0;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
 		ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7b54ccf..49aa4fa 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,6 +10,7 @@
 #include "ui/progress.h"
 
 struct hist_entry;
+struct hist_entry_ops;
 struct addr_location;
 struct symbol;
 
@@ -120,13 +121,23 @@ extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
 extern const struct hist_iter_ops hist_iter_cumulative;
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
-				      struct addr_location *al,
-				      struct symbol *parent,
-				      struct branch_info *bi,
-				      struct mem_info *mi,
-				      struct perf_sample *sample,
-				      bool sample_self);
+struct hist_entry *hists__add_entry(struct hists *hists,
+				    struct addr_location *al,
+				    struct symbol *parent,
+				    struct branch_info *bi,
+				    struct mem_info *mi,
+				    struct perf_sample *sample,
+				    bool sample_self);
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+					struct hist_entry_ops *ops,
+					struct addr_location *al,
+					struct symbol *sym_parent,
+					struct branch_info *bi,
+					struct mem_info *mi,
+					struct perf_sample *sample,
+					bool sample_self);
+
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 
@@ -159,7 +170,8 @@ void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-		      int max_cols, float min_pcnt, FILE *fp);
+		      int max_cols, float min_pcnt, FILE *fp,
+		      bool use_callchain);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
@@ -214,9 +226,9 @@ struct perf_hpp {
 struct perf_hpp_fmt {
 	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		      struct perf_evsel *evsel);
+		      struct hists *hists);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		     struct perf_evsel *evsel);
+		     struct hists *hists);
 	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hist_entry *he);
 	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h
deleted file mode 100644
index 2a9bdc0..0000000
--- a/tools/perf/util/include/asm/byteorder.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <asm/types.h>
-#include "../../../../include/uapi/linux/swab.h"
diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h
deleted file mode 100644
index 8b13789..0000000
--- a/tools/perf/util/include/asm/unistd_32.h
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h
deleted file mode 100644
index 8b13789..0000000
--- a/tools/perf/util/include/asm/unistd_64.h
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
deleted file mode 100644
index c10a35e..0000000
--- a/tools/perf/util/include/linux/const.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/uapi/linux/const.h"
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 9df9960..749e6f2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -422,7 +422,8 @@ static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
 }
 
 static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
-				    struct auxtrace_buffer *buffer)
+				    struct auxtrace_buffer *buffer,
+				    struct thread *thread)
 {
 	struct branch *branch;
 	size_t sz, bsz = sizeof(struct branch);
@@ -444,6 +445,12 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 		if (!branch->from && !branch->to)
 			continue;
 		intel_bts_get_branch_type(btsq, branch);
+		if (btsq->bts->synth_opts.thread_stack)
+			thread_stack__event(thread, btsq->sample_flags,
+					    le64_to_cpu(branch->from),
+					    le64_to_cpu(branch->to),
+					    btsq->intel_pt_insn.length,
+					    buffer->buffer_nr + 1);
 		if (filter && !(filter & btsq->sample_flags))
 			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
@@ -507,12 +514,13 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 		goto out_put;
 	}
 
-	if (!btsq->bts->synth_opts.callchain && thread &&
+	if (!btsq->bts->synth_opts.callchain &&
+	    !btsq->bts->synth_opts.thread_stack && thread &&
 	    (!old_buffer || btsq->bts->sampling_mode ||
 	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
 		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
 
-	err = intel_bts_process_buffer(btsq, buffer);
+	err = intel_bts_process_buffer(btsq, buffer, thread);
 
 	auxtrace_buffer__drop_data(buffer);
 
@@ -777,7 +785,7 @@ static int intel_bts_synth_events(struct intel_bts *bts,
 	u64 id;
 	int err;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == bts->pmu_type && evsel->ids) {
 			found = true;
 			break;
@@ -905,10 +913,14 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (dump_trace)
 		return 0;
 
-	if (session->itrace_synth_opts && session->itrace_synth_opts->set)
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
-	else
+	} else {
 		itrace_synth_opts__set_default(&bts->synth_opts);
+		if (session->itrace_synth_opts)
+			bts->synth_opts.thread_stack =
+				session->itrace_synth_opts->thread_stack;
+	}
 
 	if (bts->synth_opts.calls)
 		bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 0611d61..9b742ea 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -7,8 +7,11 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
+# Busybox's diff doesn't have -I, avoid warning in the case
+
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
+	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
+	test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
 	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
 	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
 	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 1371969..551ff6f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -39,6 +39,7 @@
 #include "auxtrace.h"
 #include "tsc.h"
 #include "intel-pt.h"
+#include "config.h"
 
 #include "intel-pt-decoder/intel-pt-log.h"
 #include "intel-pt-decoder/intel-pt-decoder.h"
@@ -556,7 +557,7 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
 		    !evsel->attr.exclude_kernel)
 			return false;
@@ -572,7 +573,7 @@ static bool intel_pt_return_compression(struct intel_pt *pt)
 	if (!pt->noretcomp_bit)
 		return true;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
 		    (config & pt->noretcomp_bit))
 			return false;
@@ -592,7 +593,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 	for (shift = 0, config = pt->mtc_freq_bits; !(config & 1); shift++)
 		config >>= 1;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config))
 			return (config & pt->mtc_freq_bits) >> shift;
 	}
@@ -608,7 +609,7 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt)
 	if (!pt->tsc_bit || !pt->cap_user_time_zero)
 		return true;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
 			return true;
 		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
@@ -625,7 +626,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
 		    !evsel->attr.exclude_kernel)
 			return true;
@@ -642,7 +643,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt)
 	if (!pt->tsc_bit)
 		return false;
 
-	evlist__for_each(pt->session->evlist, evsel) {
+	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
 			if (config & pt->tsc_bit)
 				have_tsc = true;
@@ -1233,7 +1234,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->synth_opts.callchain)
+	if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
 		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
@@ -1850,7 +1851,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 	u64 id;
 	int err;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == pt->pmu_type && evsel->ids) {
 			found = true;
 			break;
@@ -1930,7 +1931,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		pt->sample_transactions = true;
 		pt->transactions_id = id;
 		id += 1;
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (evsel->id && evsel->id[0] == pt->transactions_id) {
 				if (evsel->name)
 					zfree(&evsel->name);
@@ -1968,7 +1969,7 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each_reverse(evlist, evsel) {
+	evlist__for_each_entry_reverse(evlist, evsel) {
 		const char *name = perf_evsel__name(evsel);
 
 		if (!strcmp(name, "sched:sched_switch"))
@@ -1982,7 +1983,7 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.context_switch)
 			return true;
 	}
@@ -2136,6 +2137,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
 		}
+		if (session->itrace_synth_opts)
+			pt->synth_opts.thread_stack =
+				session->itrace_synth_opts->thread_stack;
 	}
 
 	if (pt->synth_opts.log)
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index aa6877d..020b9ca 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -57,21 +57,21 @@ static inline struct int_node *intlist__next(struct int_node *in)
 }
 
 /**
- * intlist_for_each      - iterate over a intlist
+ * intlist__for_each_entry      - iterate over a intlist
  * @pos:	the &struct int_node to use as a loop cursor.
  * @ilist:	the &struct intlist for loop.
  */
-#define intlist__for_each(pos, ilist)	\
+#define intlist__for_each_entry(pos, ilist)	\
 	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
 
 /**
- * intlist_for_each_safe - iterate over a intlist safe against removal of
+ * intlist__for_each_entry_safe - iterate over a intlist safe against removal of
  *                         int_node
  * @pos:	the &struct int_node to use as a loop cursor.
  * @n:		another &struct int_node to use as temporary storage.
  * @ilist:	the &struct intlist for loop.
  */
-#define intlist__for_each_safe(pos, n, ilist)	\
+#define intlist__for_each_entry_safe(pos, n, ilist)	\
 	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
 	     pos = n, n = intlist__next(n))
 #endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 86afe96..9f3305f 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -108,7 +108,7 @@ jit_validate_events(struct perf_session *session)
 	/*
 	 * check that all events use CLOCK_MONOTONIC
 	 */
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
 			return -1;
 	}
diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c
index e521d15..f616e4f 100644
--- a/tools/perf/util/levenshtein.c
+++ b/tools/perf/util/levenshtein.c
@@ -1,5 +1,7 @@
-#include "cache.h"
 #include "levenshtein.h"
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
 
 /*
  * This function implements the Damerau-Levenshtein algorithm to
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
new file mode 100644
index 0000000..6559bc5
--- /dev/null
+++ b/tools/perf/util/libunwind/arm64.c
@@ -0,0 +1,40 @@
+/*
+ * This file setups defines to compile arch specific binary from the
+ * generic one.
+ *
+ * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch
+ * name and the defination of this function is included directly from
+ * 'arch/arm64/util/unwind-libunwind.c', to make sure that this function
+ * is defined no matter what arch the host is.
+ *
+ * Finally, the arch specific unwind methods are exported which will
+ * be assigned to each arm64 thread.
+ */
+
+#define REMOTE_UNWIND_LIBUNWIND
+
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
+
+#include "unwind.h"
+#include "debug.h"
+#include "libunwind-aarch64.h"
+#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
+#include "../../arch/arm64/util/unwind-libunwind.c"
+
+/* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind,
+ * assign NO_LIBUNWIND_DEBUG_FRAME_AARCH64 to it for compiling arm64
+ * unwind methods.
+ */
+#undef NO_LIBUNWIND_DEBUG_FRAME
+#ifdef NO_LIBUNWIND_DEBUG_FRAME_AARCH64
+#define NO_LIBUNWIND_DEBUG_FRAME
+#endif
+#include "util/unwind-libunwind-local.c"
+
+struct unwind_libunwind_ops *
+arm64_unwind_libunwind_ops = &_unwind_libunwind_ops;
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
new file mode 100644
index 0000000..957ffff
--- /dev/null
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -0,0 +1,43 @@
+/*
+ * This file setups defines to compile arch specific binary from the
+ * generic one.
+ *
+ * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch
+ * name and the defination of this function is included directly from
+ * 'arch/x86/util/unwind-libunwind.c', to make sure that this function
+ * is defined no matter what arch the host is.
+ *
+ * Finally, the arch specific unwind methods are exported which will
+ * be assigned to each x86 thread.
+ */
+
+#define REMOTE_UNWIND_LIBUNWIND
+
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
+
+#include "unwind.h"
+#include "debug.h"
+#include "libunwind-x86.h"
+#include <../../../../arch/x86/include/uapi/asm/perf_regs.h>
+
+/* HAVE_ARCH_X86_64_SUPPORT is used in'arch/x86/util/unwind-libunwind.c'
+ * for x86_32, we undef it to compile code for x86_32 only.
+ */
+#undef HAVE_ARCH_X86_64_SUPPORT
+#include "../../arch/x86/util/unwind-libunwind.c"
+
+/* Explicitly define NO_LIBUNWIND_DEBUG_FRAME, because non-ARM has no
+ * dwarf_find_debug_frame() function.
+ */
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+#define NO_LIBUNWIND_DEBUG_FRAME
+#endif
+#include "util/unwind-libunwind-local.c"
+
+struct unwind_libunwind_ops *
+x86_32_unwind_libunwind_ops = &_unwind_libunwind_ops;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 33071d6..bf7216b 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -3,11 +3,14 @@
  * Copyright (C) 2015, Huawei Inc.
  */
 
+#include <errno.h>
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
+#include "config.h"
+#include "util.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
@@ -42,6 +45,8 @@ int perf_llvm_config(const char *var, const char *value)
 		llvm_param.kbuild_dir = strdup(value);
 	else if (!strcmp(var, "kbuild-opts"))
 		llvm_param.kbuild_opts = strdup(value);
+	else if (!strcmp(var, "dump-obj"))
+		llvm_param.dump_obj = !!perf_config_bool(var, value);
 	else
 		return -1;
 	llvm_param.user_set_param = true;
@@ -103,7 +108,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 	file = popen(cmd, "r");
 	if (!file) {
 		pr_err("ERROR: unable to popen cmd: %s\n",
-		       strerror_r(errno, serr, sizeof(serr)));
+		       str_error_r(errno, serr, sizeof(serr)));
 		return -EINVAL;
 	}
 
@@ -137,7 +142,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 
 	if (ferror(file)) {
 		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       strerror_r(errno, serr, sizeof(serr)));
+		       str_error_r(errno, serr, sizeof(serr)));
 		err = -EIO;
 		goto errout;
 	}
@@ -326,6 +331,42 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 	pr_debug("include option is set to %s\n", *kbuild_include_opts);
 }
 
+static void
+dump_obj(const char *path, void *obj_buf, size_t size)
+{
+	char *obj_path = strdup(path);
+	FILE *fp;
+	char *p;
+
+	if (!obj_path) {
+		pr_warning("WARNING: No enough memory, skip object dumping\n");
+		return;
+	}
+
+	p = strrchr(obj_path, '.');
+	if (!p || (strcmp(p, ".c") != 0)) {
+		pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n",
+			   obj_path);
+		goto out;
+	}
+
+	p[1] = 'o';
+	fp = fopen(obj_path, "wb");
+	if (!fp) {
+		pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n",
+			   obj_path, strerror(errno));
+		goto out;
+	}
+
+	pr_info("LLVM: dumping %s\n", obj_path);
+	if (fwrite(obj_buf, size, 1, fp) != 1)
+		pr_warning("WARNING: failed to write to file '%s': %s, skip object dumping\n",
+			   obj_path, strerror(errno));
+	fclose(fp);
+out:
+	free(obj_path);
+}
+
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		      size_t *p_obj_buf_sz)
 {
@@ -343,7 +384,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (path[0] != '-' && realpath(path, abspath) == NULL) {
 		err = errno;
 		pr_err("ERROR: problems with path %s: %s\n",
-		       path, strerror_r(err, serr, sizeof(serr)));
+		       path, str_error_r(err, serr, sizeof(serr)));
 		return -err;
 	}
 
@@ -371,7 +412,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (nr_cpus_avail <= 0) {
 		pr_err(
 "WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr)));
+"        \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr)));
 		nr_cpus_avail = 128;
 	}
 	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
@@ -411,6 +452,10 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 
 	free(kbuild_dir);
 	free(kbuild_include_opts);
+
+	if (llvm_param.dump_obj)
+		dump_obj(path, obj_buf, obj_buf_sz);
+
 	if (!p_obj_buf)
 		free(obj_buf);
 	else
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index 23b9a74..9f501ce 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -30,6 +30,11 @@ struct llvm_param {
 	 */
 	const char *kbuild_opts;
 	/*
+	 * Default is false. If set to true, write compiling result
+	 * to object file.
+	 */
+	bool dump_obj;
+	/*
 	 * Default is false. If one of the above fields is set by user
 	 * explicitly then user_set_llvm is set to true. This is used
 	 * for perf test. If user doesn't set anything in .perfconfig
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b177218..bc2cdbd 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -138,8 +138,10 @@ void machine__exit(struct machine *machine)
 
 void machine__delete(struct machine *machine)
 {
-	machine__exit(machine);
-	free(machine);
+	if (machine) {
+		machine__exit(machine);
+		free(machine);
+	}
 }
 
 void machines__init(struct machines *machines)
@@ -1353,11 +1355,16 @@ int machine__process_mmap2_event(struct machine *machine,
 	if (map == NULL)
 		goto out_problem_map;
 
-	thread__insert_map(thread, map);
+	ret = thread__insert_map(thread, map);
+	if (ret)
+		goto out_problem_insert;
+
 	thread__put(thread);
 	map__put(map);
 	return 0;
 
+out_problem_insert:
+	map__put(map);
 out_problem_map:
 	thread__put(thread);
 out_problem:
@@ -1403,11 +1410,16 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	if (map == NULL)
 		goto out_problem_map;
 
-	thread__insert_map(thread, map);
+	ret = thread__insert_map(thread, map);
+	if (ret)
+		goto out_problem_insert;
+
 	thread__put(thread);
 	map__put(map);
 	return 0;
 
+out_problem_insert:
+	map__put(map);
 out_problem_map:
 	thread__put(thread);
 out_problem:
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b19bcd3..728129a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -15,6 +15,7 @@
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
 
@@ -311,6 +312,9 @@ int map__load(struct map *map, symbol_filter_t filter)
 			pr_warning("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
+		} else if (filter) {
+			pr_warning("no symbols passed the given filter.\n");
+			return -2;	/* Empty but maybe by the filter */
 		} else {
 			pr_warning("no symbols found in %s, maybe install "
 				   "a debug package?\n", name);
@@ -744,9 +748,10 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
 		      struct map_groups *parent, enum map_type type)
 {
+	struct map_groups *mg = thread->mg;
 	int err = -ENOMEM;
 	struct map *map;
 	struct maps *maps = &parent->maps[type];
@@ -757,6 +762,11 @@ int map_groups__clone(struct map_groups *mg,
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			goto out_unlock;
+
+		err = unwind__prepare_access(thread, new, NULL);
+		if (err)
+			goto out_unlock;
+
 		map_groups__insert(mg, new);
 		map__put(new);
 	}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7309d64..d83396c 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -194,7 +194,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
                                          struct map **mapp, symbol_filter_t filter);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
 		      struct map_groups *parent, enum map_type type);
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 75465f8..bbc368e 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -10,18 +10,33 @@
 #include "debug.h"
 #include "symbol.h"
 
+unsigned int perf_mem_events__loads_ldlat = 30;
+
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
 	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
 };
 #undef E
 
 #undef E
 
+static char mem_loads_name[100];
+static bool mem_loads_name__init;
+
 char *perf_mem_events__name(int i)
 {
+	if (i == PERF_MEM_EVENTS__LOAD) {
+		if (!mem_loads_name__init) {
+			mem_loads_name__init = true;
+			scnprintf(mem_loads_name, sizeof(mem_loads_name),
+				  perf_mem_events[i].name,
+				  perf_mem_events__loads_ldlat);
+		}
+		return mem_loads_name;
+	}
+
 	return (char *)perf_mem_events[i].name;
 }
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 5d6d930..7f69bf9 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -18,6 +18,7 @@ enum {
 };
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c6fd047..6c913c3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -20,6 +20,7 @@
 #include "pmu.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "probe-file.h"
 #include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
@@ -436,7 +437,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
-			     char *sys, char *name)
+			     const char *sys, const char *name)
 {
 	char help[BUFSIZ];
 
@@ -466,7 +467,7 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 }
 
 static int add_tracepoint(struct list_head *list, int *idx,
-			  char *sys_name, char *evt_name,
+			  const char *sys_name, const char *evt_name,
 			  struct parse_events_error *err,
 			  struct list_head *head_config)
 {
@@ -491,7 +492,7 @@ static int add_tracepoint(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
-				      char *sys_name, char *evt_name,
+				      const char *sys_name, const char *evt_name,
 				      struct parse_events_error *err,
 				      struct list_head *head_config)
 {
@@ -533,7 +534,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_event(struct list_head *list, int *idx,
-				char *sys_name, char *evt_name,
+				const char *sys_name, const char *evt_name,
 				struct parse_events_error *err,
 				struct list_head *head_config)
 {
@@ -545,7 +546,7 @@ static int add_tracepoint_event(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
-				    char *sys_name, char *evt_name,
+				    const char *sys_name, const char *evt_name,
 				    struct parse_events_error *err,
 				    struct list_head *head_config)
 {
@@ -584,7 +585,7 @@ struct __add_bpf_event_param {
 	struct list_head *head_config;
 };
 
-static int add_bpf_event(struct probe_trace_event *tev, int fd,
+static int add_bpf_event(const char *group, const char *event, int fd,
 			 void *_param)
 {
 	LIST_HEAD(new_evsels);
@@ -595,27 +596,27 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 	int err;
 
 	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
-		 tev->group, tev->event, fd);
+		 group, event, fd);
 
-	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-					  tev->event, evlist->error,
+	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group,
+					  event, evlist->error,
 					  param->head_config);
 	if (err) {
 		struct perf_evsel *evsel, *tmp;
 
 		pr_debug("Failed to add BPF event %s:%s\n",
-			 tev->group, tev->event);
+			 group, event);
 		list_for_each_entry_safe(evsel, tmp, &new_evsels, node) {
 			list_del(&evsel->node);
 			perf_evsel__delete(evsel);
 		}
 		return err;
 	}
-	pr_debug("adding %s:%s\n", tev->group, tev->event);
+	pr_debug("adding %s:%s\n", group, event);
 
 	list_for_each_entry(pos, &new_evsels, node) {
 		pr_debug("adding %s:%s to %p\n",
-			 tev->group, tev->event, pos);
+			 group, event, pos);
 		pos->bpf_fd = fd;
 	}
 	list_splice(&new_evsels, list);
@@ -661,7 +662,7 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 		goto errout;
 	}
 
-	err = bpf__foreach_tev(obj, add_bpf_event, &param);
+	err = bpf__foreach_event(obj, add_bpf_event, &param);
 	if (err) {
 		snprintf(errbuf, sizeof(errbuf),
 			 "Attach events in BPF object failed");
@@ -900,6 +901,9 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
+	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 };
 
 static bool config_term_shrinked;
@@ -992,9 +996,18 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+		CHECK_TYPE_VAL(NUM);
+		break;
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 		CHECK_TYPE_VAL(STR);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1040,6 +1053,9 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1109,6 +1125,15 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 			ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1);
+			break;
 		default:
 			break;
 		}
@@ -1118,7 +1143,7 @@ do {								\
 }
 
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
-				char *sys, char *event,
+				const char *sys, const char *event,
 				struct parse_events_error *err,
 				struct list_head *head_config)
 {
@@ -1388,7 +1413,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 	if (!add && get_event_modifier(&mod, str, NULL))
 		return -EINVAL;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		if (add && get_event_modifier(&mod, str, evsel))
 			return -EINVAL;
 
@@ -1414,7 +1439,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
 	struct perf_evsel *evsel;
 
-	__evlist__for_each(list, evsel) {
+	__evlist__for_each_entry(list, evsel) {
 		if (!evsel->name)
 			evsel->name = strdup(name);
 	}
@@ -1976,6 +2001,85 @@ static bool is_event_supported(u8 type, unsigned config)
 	return ret;
 }
 
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+		      bool name_only)
+{
+	struct probe_cache *pcache;
+	struct probe_cache_entry *ent;
+	struct strlist *bidlist, *sdtlist;
+	struct strlist_config cfg = {.dont_dupstr = true};
+	struct str_node *nd, *nd2;
+	char *buf, *path, *ptr = NULL;
+	bool show_detail = false;
+	int ret;
+
+	sdtlist = strlist__new(NULL, &cfg);
+	if (!sdtlist) {
+		pr_debug("Failed to allocate new strlist for SDT\n");
+		return;
+	}
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: %d\n", errno);
+		return;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		pcache = probe_cache__new(nd->s);
+		if (!pcache)
+			continue;
+		list_for_each_entry(ent, &pcache->entries, node) {
+			if (!ent->sdt)
+				continue;
+			if (subsys_glob &&
+			    !strglobmatch(ent->pev.group, subsys_glob))
+				continue;
+			if (event_glob &&
+			    !strglobmatch(ent->pev.event, event_glob))
+				continue;
+			ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
+					ent->pev.event, nd->s);
+			if (ret > 0)
+				strlist__add(sdtlist, buf);
+		}
+		probe_cache__delete(pcache);
+	}
+	strlist__delete(bidlist);
+
+	strlist__for_each_entry(nd, sdtlist) {
+		buf = strchr(nd->s, '@');
+		if (buf)
+			*(buf++) = '\0';
+		if (name_only) {
+			printf("%s ", nd->s);
+			continue;
+		}
+		nd2 = strlist__next(nd);
+		if (nd2) {
+			ptr = strchr(nd2->s, '@');
+			if (ptr)
+				*ptr = '\0';
+			if (strcmp(nd->s, nd2->s) == 0)
+				show_detail = true;
+		}
+		if (show_detail) {
+			path = build_id_cache__origname(buf);
+			ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
+			if (ret > 0) {
+				printf("  %-50s [%s]\n", buf, "SDT event");
+				free(buf);
+			}
+		} else
+			printf("  %-50s [%s]\n", nd->s, "SDT event");
+		if (nd2) {
+			if (strcmp(nd->s, nd2->s) != 0)
+				show_detail = false;
+			if (ptr)
+				*ptr = '@';
+		}
+	}
+	strlist__delete(sdtlist);
+}
+
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
 	unsigned int type, op, i, evt_i = 0, evt_num = 0;
@@ -2158,6 +2262,8 @@ void print_events(const char *event_glob, bool name_only)
 	}
 
 	print_tracepoint_events(NULL, NULL, name_only);
+
+	print_sdt_events(NULL, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
@@ -2322,9 +2428,9 @@ static void config_terms_list(char *buf, size_t buf_sz)
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	/* "branch_type" is the longest name */
+	/* "no-overwrite" is the longest name */
 	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
-			  (sizeof("branch_type") - 1)];
+			  (sizeof("no-overwrite") - 1)];
 
 	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d740c3c..d1edbf8 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -68,6 +68,9 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
+	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
@@ -133,7 +136,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
-				char *sys, char *event,
+				const char *sys, const char *event,
 				struct parse_events_error *error,
 				struct list_head *head_config);
 int parse_events_load_bpf(struct parse_events_evlist *data,
@@ -182,6 +185,8 @@ void print_symbol_events(const char *event_glob, unsigned type,
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+		      bool name_only);
 int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 1477fbc..7a25194 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -199,8 +199,11 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
+max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
+overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
+no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
@@ -259,6 +262,7 @@ cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+topdown-[a-z-]+					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 3bf6bf8..7c7630b 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,17 +11,13 @@
  * which is what it's designed for.
  */
 #include "cache.h"
+#include "util.h"
+#include <limits.h>
 
 static char bad_path[] = "/bad-path/";
 /*
- * Two hacks:
+ * One hack:
  */
-
-static const char *get_perf_dir(void)
-{
-	return ".";
-}
-
 static char *get_pathname(void)
 {
 	static char pathname_array[4][PATH_MAX];
@@ -54,60 +50,3 @@ char *mkpath(const char *fmt, ...)
 		return bad_path;
 	return cleanup_path(pathname);
 }
-
-char *perf_path(const char *fmt, ...)
-{
-	const char *perf_dir = get_perf_dir();
-	char *pathname = get_pathname();
-	va_list args;
-	unsigned len;
-
-	len = strlen(perf_dir);
-	if (len > PATH_MAX-100)
-		return bad_path;
-	memcpy(pathname, perf_dir, len);
-	if (len && perf_dir[len-1] != '/')
-		pathname[len++] = '/';
-	va_start(args, fmt);
-	len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args);
-	va_end(args);
-	if (len >= PATH_MAX)
-		return bad_path;
-	return cleanup_path(pathname);
-}
-
-/* strip arbitrary amount of directory separators at end of path */
-static inline int chomp_trailing_dir_sep(const char *path, int len)
-{
-	while (len && is_dir_sep(path[len - 1]))
-		len--;
-	return len;
-}
-
-/*
- * If path ends with suffix (complete path components), returns the
- * part before suffix (sans trailing directory separators).
- * Otherwise returns NULL.
- */
-char *strip_path_suffix(const char *path, const char *suffix)
-{
-	int path_len = strlen(path), suffix_len = strlen(suffix);
-
-	while (suffix_len) {
-		if (!path_len)
-			return NULL;
-
-		if (is_dir_sep(path[path_len - 1])) {
-			if (!is_dir_sep(suffix[suffix_len - 1]))
-				return NULL;
-			path_len = chomp_trailing_dir_sep(path, path_len);
-			suffix_len = chomp_trailing_dir_sep(suffix, suffix_len);
-		}
-		else if (path[--path_len] != suffix[--suffix_len])
-			return NULL;
-	}
-
-	if (path_len && !is_dir_sep(path[path_len - 1]))
-		return NULL;
-	return strndup(path, chomp_trailing_dir_sep(path, path_len));
-}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 74401a2..953dc1a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -67,7 +67,6 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
 	return ret;
 }
 
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
@@ -103,10 +102,8 @@ out:
 
 void exit_probe_symbol_maps(void)
 {
-	if (host_machine) {
-		machine__delete(host_machine);
-		host_machine = NULL;
-	}
+	machine__delete(host_machine);
+	host_machine = NULL;
 	symbol__exit();
 }
 
@@ -471,7 +468,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
 		err = kernel_get_module_dso(module, &dso);
 		if (err < 0) {
 			if (!dso || dso->load_errno == 0) {
-				if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+				if (!str_error_r(-err, reason, STRERR_BUFSIZE))
 					strcpy(reason, "(unknown)");
 			} else
 				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
@@ -809,7 +806,7 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 error:
 	if (ferror(fp)) {
 		pr_warning("File read error: %s\n",
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 	return 0;
@@ -889,7 +886,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
 		pr_warning("Failed to open %s: %s\n", lr->path,
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 	/* Skip to starting line number */
@@ -899,7 +896,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
 			goto end;
 	}
 
-	intlist__for_each(ln, lr->line_list) {
+	intlist__for_each_entry(ln, lr->line_list) {
 		for (; ln->i > l; l++) {
 			ret = show_one_line(fp, l - lr->offset);
 			if (ret < 0)
@@ -983,7 +980,7 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		zfree(&vl->point.symbol);
 		nvars = 0;
 		if (vl->vars) {
-			strlist__for_each(node, vl->vars) {
+			strlist__for_each_entry(node, vl->vars) {
 				var = strchr(node->s, '\t') + 1;
 				if (strfilter__compare(_filter, var)) {
 					fprintf(stdout, "\t\t%s\n", node->s);
@@ -1200,6 +1197,34 @@ err:
 	return err;
 }
 
+static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
+{
+	char *ptr;
+
+	ptr = strchr(*arg, ':');
+	if (ptr) {
+		*ptr = '\0';
+		if (!pev->sdt && !is_c_func_name(*arg))
+			goto ng_name;
+		pev->group = strdup(*arg);
+		if (!pev->group)
+			return -ENOMEM;
+		*arg = ptr + 1;
+	} else
+		pev->group = NULL;
+	if (!pev->sdt && !is_c_func_name(*arg)) {
+ng_name:
+		semantic_error("%s is bad for event name -it must "
+			       "follow C symbol-naming rule.\n", *arg);
+		return -EINVAL;
+	}
+	pev->event = strdup(*arg);
+	if (pev->event == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
 /* Parse probepoint definition. */
 static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
@@ -1207,33 +1232,64 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	char *ptr, *tmp;
 	char c, nc = 0;
 	bool file_spec = false;
+	int ret;
+
 	/*
 	 * <Syntax>
-	 * perf probe [EVENT=]SRC[:LN|;PTN]
-	 * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
-	 *
-	 * TODO:Group name support
+	 * perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
+	 * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
+	 * perf probe %[GRP:]SDT_EVENT
 	 */
 	if (!arg)
 		return -EINVAL;
 
+	/*
+	 * If the probe point starts with '%',
+	 * or starts with "sdt_" and has a ':' but no '=',
+	 * then it should be a SDT/cached probe point.
+	 */
+	if (arg[0] == '%' ||
+	    (!strncmp(arg, "sdt_", 4) &&
+	     !!strchr(arg, ':') && !strchr(arg, '='))) {
+		pev->sdt = true;
+		if (arg[0] == '%')
+			arg++;
+	}
+
 	ptr = strpbrk(arg, ";=@+%");
+	if (pev->sdt) {
+		if (ptr) {
+			if (*ptr != '@') {
+				semantic_error("%s must be an SDT name.\n",
+					       arg);
+				return -EINVAL;
+			}
+			/* This must be a target file name or build id */
+			tmp = build_id_cache__complement(ptr + 1);
+			if (tmp) {
+				pev->target = build_id_cache__origname(tmp);
+				free(tmp);
+			} else
+				pev->target = strdup(ptr + 1);
+			if (!pev->target)
+				return -ENOMEM;
+			*ptr = '\0';
+		}
+		ret = parse_perf_probe_event_name(&arg, pev);
+		if (ret == 0) {
+			if (asprintf(&pev->point.function, "%%%s", pev->event) < 0)
+				ret = -errno;
+		}
+		return ret;
+	}
+
 	if (ptr && *ptr == '=') {	/* Event name */
 		*ptr = '\0';
 		tmp = ptr + 1;
-		if (strchr(arg, ':')) {
-			semantic_error("Group name is not supported yet.\n");
-			return -ENOTSUP;
-		}
-		if (!is_c_func_name(arg)) {
-			semantic_error("%s is bad for event name -it must "
-				       "follow C symbol-naming rule.\n", arg);
-			return -EINVAL;
-		}
-		pev->event = strdup(arg);
-		if (pev->event == NULL)
-			return -ENOMEM;
-		pev->group = NULL;
+		ret = parse_perf_probe_event_name(&arg, pev);
+		if (ret < 0)
+			return ret;
+
 		arg = tmp;
 	}
 
@@ -1545,7 +1601,9 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
 		return true;
 
 	for (i = 0; i < pev->nargs; i++)
-		if (is_c_varname(pev->args[i].var))
+		if (is_c_varname(pev->args[i].var) ||
+		    !strcmp(pev->args[i].var, "$params") ||
+		    !strcmp(pev->args[i].var, "$vars"))
 			return true;
 
 	return false;
@@ -1603,6 +1661,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 	p = strchr(argv[1], ':');
 	if (p) {
 		tp->module = strndup(argv[1], p - argv[1]);
+		if (!tp->module) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		tev->uprobes = (tp->module[0] == '/');
 		p++;
 	} else
 		p = argv[1];
@@ -1712,7 +1775,7 @@ out:
 }
 
 /* Compose only probe point (not argument) */
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
 	struct strbuf buf;
 	char *tmp, *ret = NULL;
@@ -1751,30 +1814,36 @@ out:
 	return ret;
 }
 
-#if 0
 char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 {
-	char *buf;
-	int i, len, ret;
+	struct strbuf buf;
+	char *tmp, *ret = NULL;
+	int i;
 
-	buf = synthesize_perf_probe_point(&pev->point);
-	if (!buf)
+	if (strbuf_init(&buf, 64))
 		return NULL;
+	if (pev->event)
+		if (strbuf_addf(&buf, "%s:%s=", pev->group ?: PERFPROBE_GROUP,
+				pev->event) < 0)
+			goto out;
+
+	tmp = synthesize_perf_probe_point(&pev->point);
+	if (!tmp || strbuf_addstr(&buf, tmp) < 0)
+		goto out;
+	free(tmp);
 
-	len = strlen(buf);
 	for (i = 0; i < pev->nargs; i++) {
-		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pev->args[i].name);
-		if (ret <= 0) {
-			free(buf);
-			return NULL;
-		}
-		len += ret;
+		tmp = synthesize_perf_probe_arg(pev->args + i);
+		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0)
+			goto out;
+		free(tmp);
 	}
 
-	return buf;
+	ret = strbuf_detach(&buf, NULL);
+out:
+	strbuf_release(&buf);
+	return ret;
 }
-#endif
 
 static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
 					    struct strbuf *buf, int depth)
@@ -2026,6 +2095,79 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 	memset(pev, 0, sizeof(*pev));
 }
 
+#define strdup_or_goto(str, label)	\
+({ char *__p = NULL; if (str && !(__p = strdup(str))) goto label; __p; })
+
+static int perf_probe_point__copy(struct perf_probe_point *dst,
+				  struct perf_probe_point *src)
+{
+	dst->file = strdup_or_goto(src->file, out_err);
+	dst->function = strdup_or_goto(src->function, out_err);
+	dst->lazy_line = strdup_or_goto(src->lazy_line, out_err);
+	dst->line = src->line;
+	dst->retprobe = src->retprobe;
+	dst->offset = src->offset;
+	return 0;
+
+out_err:
+	clear_perf_probe_point(dst);
+	return -ENOMEM;
+}
+
+static int perf_probe_arg__copy(struct perf_probe_arg *dst,
+				struct perf_probe_arg *src)
+{
+	struct perf_probe_arg_field *field, **ppfield;
+
+	dst->name = strdup_or_goto(src->name, out_err);
+	dst->var = strdup_or_goto(src->var, out_err);
+	dst->type = strdup_or_goto(src->type, out_err);
+
+	field = src->field;
+	ppfield = &(dst->field);
+	while (field) {
+		*ppfield = zalloc(sizeof(*field));
+		if (!*ppfield)
+			goto out_err;
+		(*ppfield)->name = strdup_or_goto(field->name, out_err);
+		(*ppfield)->index = field->index;
+		(*ppfield)->ref = field->ref;
+		field = field->next;
+		ppfield = &((*ppfield)->next);
+	}
+	return 0;
+out_err:
+	return -ENOMEM;
+}
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+			   struct perf_probe_event *src)
+{
+	int i;
+
+	dst->event = strdup_or_goto(src->event, out_err);
+	dst->group = strdup_or_goto(src->group, out_err);
+	dst->target = strdup_or_goto(src->target, out_err);
+	dst->uprobes = src->uprobes;
+
+	if (perf_probe_point__copy(&dst->point, &src->point) < 0)
+		goto out_err;
+
+	dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs);
+	if (!dst->args)
+		goto out_err;
+	dst->nargs = src->nargs;
+
+	for (i = 0; i < src->nargs; i++)
+		if (perf_probe_arg__copy(&dst->args[i], &src->args[i]) < 0)
+			goto out_err;
+	return 0;
+
+out_err:
+	clear_perf_probe_event(dst);
+	return -ENOMEM;
+}
+
 void clear_probe_trace_event(struct probe_trace_event *tev)
 {
 	struct probe_trace_arg_ref *ref, *next;
@@ -2253,7 +2395,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe,
 	if (!rawlist)
 		return -ENOMEM;
 
-	strlist__for_each(ent, rawlist) {
+	strlist__for_each_entry(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
 			if (!filter_probe_trace_event(&tev, filter))
@@ -2286,6 +2428,9 @@ int show_perf_probe_events(struct strfilter *filter)
 
 	setup_pager();
 
+	if (probe_conf.cache)
+		return probe_cache__show_all_caches(filter);
+
 	ret = init_probe_symbol_maps(false);
 	if (ret < 0)
 		return ret;
@@ -2394,17 +2539,24 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 	char buf[64];
 	int ret;
 
-	if (pev->event)
+	/* If probe_event or trace_event already have the name, reuse it */
+	if (pev->event && !pev->sdt)
 		event = pev->event;
-	else
+	else if (tev->event)
+		event = tev->event;
+	else {
+		/* Or generate new one from probe point */
 		if (pev->point.function &&
 			(strncmp(pev->point.function, "0x", 2) != 0) &&
 			!strisglob(pev->point.function))
 			event = pev->point.function;
 		else
 			event = tev->point.realname;
-	if (pev->group)
+	}
+	if (pev->group && !pev->sdt)
 		group = pev->group;
+	else if (tev->group)
+		group = tev->group;
 	else
 		group = PERFPROBE_GROUP;
 
@@ -2426,40 +2578,60 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 	return 0;
 }
 
-static int __add_probe_trace_events(struct perf_probe_event *pev,
-				     struct probe_trace_event *tevs,
-				     int ntevs, bool allow_suffix)
+static int __open_probe_file_and_namelist(bool uprobe,
+					  struct strlist **namelist)
 {
-	int i, fd, ret;
-	struct probe_trace_event *tev = NULL;
-	struct strlist *namelist;
+	int fd;
 
-	fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
+	fd = probe_file__open(PF_FL_RW | (uprobe ? PF_FL_UPROBE : 0));
 	if (fd < 0)
 		return fd;
 
 	/* Get current event names */
-	namelist = probe_file__get_namelist(fd);
-	if (!namelist) {
+	*namelist = probe_file__get_namelist(fd);
+	if (!(*namelist)) {
 		pr_debug("Failed to get current event list.\n");
-		ret = -ENOMEM;
-		goto close_out;
+		close(fd);
+		return -ENOMEM;
 	}
+	return fd;
+}
+
+static int __add_probe_trace_events(struct perf_probe_event *pev,
+				     struct probe_trace_event *tevs,
+				     int ntevs, bool allow_suffix)
+{
+	int i, fd[2] = {-1, -1}, up, ret;
+	struct probe_trace_event *tev = NULL;
+	struct probe_cache *cache = NULL;
+	struct strlist *namelist[2] = {NULL, NULL};
+
+	up = pev->uprobes ? 1 : 0;
+	fd[up] = __open_probe_file_and_namelist(up, &namelist[up]);
+	if (fd[up] < 0)
+		return fd[up];
 
 	ret = 0;
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
+		up = tev->uprobes ? 1 : 0;
+		if (fd[up] == -1) {	/* Open the kprobe/uprobe_events */
+			fd[up] = __open_probe_file_and_namelist(up,
+								&namelist[up]);
+			if (fd[up] < 0)
+				goto close_out;
+		}
 		/* Skip if the symbol is out of .text or blacklisted */
-		if (!tev->point.symbol)
+		if (!tev->point.symbol && !pev->uprobes)
 			continue;
 
 		/* Set new name for tev (and update namelist) */
-		ret = probe_trace_event__set_name(tev, pev, namelist,
+		ret = probe_trace_event__set_name(tev, pev, namelist[up],
 						  allow_suffix);
 		if (ret < 0)
 			break;
 
-		ret = probe_file__add_event(fd, tev);
+		ret = probe_file__add_event(fd[up], tev);
 		if (ret < 0)
 			break;
 
@@ -2473,10 +2645,21 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 	if (ret == -EINVAL && pev->uprobes)
 		warn_uprobe_event_compat(tev);
+	if (ret == 0 && probe_conf.cache) {
+		cache = probe_cache__new(pev->target);
+		if (!cache ||
+		    probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 ||
+		    probe_cache__commit(cache) < 0)
+			pr_warning("Failed to add event to probe cache\n");
+		probe_cache__delete(cache);
+	}
 
-	strlist__delete(namelist);
 close_out:
-	close(fd);
+	for (up = 0; up < 2; up++) {
+		strlist__delete(namelist[up]);
+		if (fd[up] >= 0)
+			close(fd[up]);
+	}
 	return ret;
 }
 
@@ -2501,9 +2684,6 @@ static int find_probe_functions(struct map *map, char *name,
 	return found;
 }
 
-#define strdup_or_goto(str, label)	\
-	({ char *__p = strdup(str); if (!__p) goto label; __p; })
-
 void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
 				struct probe_trace_event *tev __maybe_unused,
 				struct map *map __maybe_unused,
@@ -2758,12 +2938,205 @@ errout:
 
 bool __weak arch__prefers_symtab(void) { return false; }
 
+/* Concatinate two arrays */
+static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
+{
+	void *ret;
+
+	ret = malloc(sz_a + sz_b);
+	if (ret) {
+		memcpy(ret, a, sz_a);
+		memcpy(ret + sz_a, b, sz_b);
+	}
+	return ret;
+}
+
+static int
+concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
+			  struct probe_trace_event **tevs2, int ntevs2)
+{
+	struct probe_trace_event *new_tevs;
+	int ret = 0;
+
+	if (ntevs == 0) {
+		*tevs = *tevs2;
+		*ntevs = ntevs2;
+		*tevs2 = NULL;
+		return 0;
+	}
+
+	if (*ntevs + ntevs2 > probe_conf.max_probes)
+		ret = -E2BIG;
+	else {
+		/* Concatinate the array of probe_trace_event */
+		new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
+				  *tevs2, ntevs2 * sizeof(**tevs2));
+		if (!new_tevs)
+			ret = -ENOMEM;
+		else {
+			free(*tevs);
+			*tevs = new_tevs;
+			*ntevs += ntevs2;
+		}
+	}
+	if (ret < 0)
+		clear_probe_trace_events(*tevs2, ntevs2);
+	zfree(tevs2);
+
+	return ret;
+}
+
+/*
+ * Try to find probe_trace_event from given probe caches. Return the number
+ * of cached events found, if an error occurs return the error.
+ */
+static int find_cached_events(struct perf_probe_event *pev,
+			      struct probe_trace_event **tevs,
+			      const char *target)
+{
+	struct probe_cache *cache;
+	struct probe_cache_entry *entry;
+	struct probe_trace_event *tmp_tevs = NULL;
+	int ntevs = 0;
+	int ret = 0;
+
+	cache = probe_cache__new(target);
+	/* Return 0 ("not found") if the target has no probe cache. */
+	if (!cache)
+		return 0;
+
+	for_each_probe_cache_entry(entry, cache) {
+		/* Skip the cache entry which has no name */
+		if (!entry->pev.event || !entry->pev.group)
+			continue;
+		if ((!pev->group || strglobmatch(entry->pev.group, pev->group)) &&
+		    strglobmatch(entry->pev.event, pev->event)) {
+			ret = probe_cache_entry__get_event(entry, &tmp_tevs);
+			if (ret > 0)
+				ret = concat_probe_trace_events(tevs, &ntevs,
+								&tmp_tevs, ret);
+			if (ret < 0)
+				break;
+		}
+	}
+	probe_cache__delete(cache);
+	if (ret < 0) {
+		clear_probe_trace_events(*tevs, ntevs);
+		zfree(tevs);
+	} else {
+		ret = ntevs;
+		if (ntevs > 0 && target && target[0] == '/')
+			pev->uprobes = true;
+	}
+
+	return ret;
+}
+
+/* Try to find probe_trace_event from all probe caches */
+static int find_cached_events_all(struct perf_probe_event *pev,
+				   struct probe_trace_event **tevs)
+{
+	struct probe_trace_event *tmp_tevs = NULL;
+	struct strlist *bidlist;
+	struct str_node *nd;
+	char *pathname;
+	int ntevs = 0;
+	int ret;
+
+	/* Get the buildid list of all valid caches */
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		ret = -errno;
+		pr_debug("Failed to get buildids: %d\n", ret);
+		return ret;
+	}
+
+	ret = 0;
+	strlist__for_each_entry(nd, bidlist) {
+		pathname = build_id_cache__origname(nd->s);
+		ret = find_cached_events(pev, &tmp_tevs, pathname);
+		/* In the case of cnt == 0, we just skip it */
+		if (ret > 0)
+			ret = concat_probe_trace_events(tevs, &ntevs,
+							&tmp_tevs, ret);
+		free(pathname);
+		if (ret < 0)
+			break;
+	}
+	strlist__delete(bidlist);
+
+	if (ret < 0) {
+		clear_probe_trace_events(*tevs, ntevs);
+		zfree(tevs);
+	} else
+		ret = ntevs;
+
+	return ret;
+}
+
+static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
+					      struct probe_trace_event **tevs)
+{
+	struct probe_cache *cache;
+	struct probe_cache_entry *entry;
+	struct probe_trace_event *tev;
+	struct str_node *node;
+	int ret, i;
+
+	if (pev->sdt) {
+		/* For SDT/cached events, we use special search functions */
+		if (!pev->target)
+			return find_cached_events_all(pev, tevs);
+		else
+			return find_cached_events(pev, tevs, pev->target);
+	}
+	cache = probe_cache__new(pev->target);
+	if (!cache)
+		return 0;
+
+	entry = probe_cache__find(cache, pev);
+	if (!entry) {
+		/* SDT must be in the cache */
+		ret = pev->sdt ? -ENOENT : 0;
+		goto out;
+	}
+
+	ret = strlist__nr_entries(entry->tevlist);
+	if (ret > probe_conf.max_probes) {
+		pr_debug("Too many entries matched in the cache of %s\n",
+			 pev->target ? : "kernel");
+		ret = -E2BIG;
+		goto out;
+	}
+
+	*tevs = zalloc(ret * sizeof(*tev));
+	if (!*tevs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	i = 0;
+	strlist__for_each_entry(node, entry->tevlist) {
+		tev = &(*tevs)[i++];
+		ret = parse_probe_trace_command(node->s, tev);
+		if (ret < 0)
+			goto out;
+		/* Set the uprobes attribute as same as original */
+		tev->uprobes = pev->uprobes;
+	}
+	ret = i;
+
+out:
+	probe_cache__delete(cache);
+	return ret;
+}
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 					 struct probe_trace_event **tevs)
 {
 	int ret;
 
-	if (!pev->group) {
+	if (!pev->group && !pev->sdt) {
 		/* Set group name if not given */
 		if (!pev->uprobes) {
 			pev->group = strdup(PERFPROBE_GROUP);
@@ -2780,6 +3153,11 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 	if (ret > 0)
 		return ret;
 
+	/* At first, we need to lookup cache entry */
+	ret = find_probe_trace_events_from_cache(pev, tevs);
+	if (ret > 0 || pev->sdt)	/* SDT can be found only in the cache */
+		return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
+
 	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
 		ret = find_probe_trace_events_from_map(pev, tevs);
 		if (ret > 0)
@@ -2934,8 +3312,16 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 
 	/* Load symbols with given filter */
 	available_func_filter = _filter;
-	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+	ret = map__load(map, filter_available_functions);
+	if (ret) {
+		if (ret == -2) {
+			char *str = strfilter__string(_filter);
+			pr_err("Failed to find symbols matched to \"%s\"\n",
+			       str);
+			free(str);
+		} else
+			pr_err("Failed to load symbols in %s\n",
+			       (target) ? : "kernel");
 		goto end;
 	}
 	if (!dso__sorted_by_name(map->dso, map->type))
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5a27eb4..e18ea9f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_conf {
 	bool	show_location_range;
 	bool	force_add;
 	bool	no_inlines;
+	bool	cache;
 	int	max_probes;
 };
 extern struct probe_conf probe_conf;
@@ -84,6 +85,7 @@ struct perf_probe_event {
 	char			*group;	/* Group name */
 	struct perf_probe_point	point;	/* Probe point */
 	int			nargs;	/* Number of arguments */
+	bool			sdt;	/* SDT/cached event flag */
 	bool			uprobes;	/* Uprobe event flag */
 	char			*target;	/* Target binary */
 	struct perf_probe_arg	*args;	/* Arguments */
@@ -121,6 +123,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
+char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+			   struct perf_probe_event *src);
 
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3fe6214..9aed9c3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  *
  */
+#include <sys/uio.h>
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
@@ -49,7 +50,7 @@ static void print_open_warning(int err, bool uprobe)
 	else
 		pr_warning("Failed to open %cprobe_events: %s\n",
 			   uprobe ? 'u' : 'k',
-			   strerror_r(-err, sbuf, sizeof(sbuf)));
+			   str_error_r(-err, sbuf, sizeof(sbuf)));
 }
 
 static void print_both_open_warning(int kerr, int uerr)
@@ -63,9 +64,9 @@ static void print_both_open_warning(int kerr, int uerr)
 	else {
 		char sbuf[STRERR_BUFSIZE];
 		pr_warning("Failed to open kprobe events: %s.\n",
-			   strerror_r(-kerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-kerr, sbuf, sizeof(sbuf)));
 		pr_warning("Failed to open uprobe events: %s.\n",
-			   strerror_r(-uerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-uerr, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -177,7 +178,7 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
 	if (!rawlist)
 		return NULL;
 	sl = strlist__new(NULL, NULL);
-	strlist__for_each(ent, rawlist) {
+	strlist__for_each_entry(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret < 0)
 			break;
@@ -223,7 +224,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev)
 		if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
 			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
-				   strerror_r(errno, sbuf, sizeof(sbuf)));
+				   str_error_r(errno, sbuf, sizeof(sbuf)));
 		}
 	}
 	free(buf);
@@ -261,7 +262,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
-		   strerror_r(-ret, buf, sizeof(buf)));
+		   str_error_r(-ret, buf, sizeof(buf)));
 	return ret;
 }
 
@@ -280,7 +281,7 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 	if (!namelist)
 		return -ENOENT;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
@@ -298,7 +299,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist)
 	int ret = 0;
 	struct str_node *ent;
 
-	strlist__for_each(ent, namelist) {
+	strlist__for_each_entry(ent, namelist) {
 		ret = __del_trace_probe_event(fd, ent);
 		if (ret < 0)
 			break;
@@ -324,3 +325,533 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 
 	return ret;
 }
+
+/* Caller must ensure to remove this entry from list */
+static void probe_cache_entry__delete(struct probe_cache_entry *entry)
+{
+	if (entry) {
+		BUG_ON(!list_empty(&entry->node));
+
+		strlist__delete(entry->tevlist);
+		clear_perf_probe_event(&entry->pev);
+		zfree(&entry->spev);
+		free(entry);
+	}
+}
+
+static struct probe_cache_entry *
+probe_cache_entry__new(struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = zalloc(sizeof(*entry));
+
+	if (entry) {
+		INIT_LIST_HEAD(&entry->node);
+		entry->tevlist = strlist__new(NULL, NULL);
+		if (!entry->tevlist)
+			zfree(&entry);
+		else if (pev) {
+			entry->spev = synthesize_perf_probe_command(pev);
+			if (!entry->spev ||
+			    perf_probe_event__copy(&entry->pev, pev) < 0) {
+				probe_cache_entry__delete(entry);
+				return NULL;
+			}
+		}
+	}
+
+	return entry;
+}
+
+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+				 struct probe_trace_event **tevs)
+{
+	struct probe_trace_event *tev;
+	struct str_node *node;
+	int ret, i;
+
+	ret = strlist__nr_entries(entry->tevlist);
+	if (ret > probe_conf.max_probes)
+		return -E2BIG;
+
+	*tevs = zalloc(ret * sizeof(*tev));
+	if (!*tevs)
+		return -ENOMEM;
+
+	i = 0;
+	strlist__for_each_entry(node, entry->tevlist) {
+		tev = &(*tevs)[i++];
+		ret = parse_probe_trace_command(node->s, tev);
+		if (ret < 0)
+			break;
+	}
+	return i;
+}
+
+/* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */
+static int probe_cache__open(struct probe_cache *pcache, const char *target)
+{
+	char cpath[PATH_MAX];
+	char sbuildid[SBUILD_ID_SIZE];
+	char *dir_name = NULL;
+	bool is_kallsyms = false;
+	int ret, fd;
+
+	if (target && build_id_cache__cached(target)) {
+		/* This is a cached buildid */
+		strncpy(sbuildid, target, SBUILD_ID_SIZE);
+		dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
+		goto found;
+	}
+
+	if (!target || !strcmp(target, DSO__NAME_KALLSYMS)) {
+		target = DSO__NAME_KALLSYMS;
+		is_kallsyms = true;
+		ret = sysfs__sprintf_build_id("/", sbuildid);
+	} else
+		ret = filename__sprintf_build_id(target, sbuildid);
+
+	if (ret < 0) {
+		pr_debug("Failed to get build-id from %s.\n", target);
+		return ret;
+	}
+
+	/* If we have no buildid cache, make it */
+	if (!build_id_cache__cached(sbuildid)) {
+		ret = build_id_cache__add_s(sbuildid, target,
+					    is_kallsyms, NULL);
+		if (ret < 0) {
+			pr_debug("Failed to add build-id cache: %s\n", target);
+			return ret;
+		}
+	}
+
+	dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+					    false);
+found:
+	if (!dir_name) {
+		pr_debug("Failed to get cache from %s\n", target);
+		return -ENOMEM;
+	}
+
+	snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
+	fd = open(cpath, O_CREAT | O_RDWR, 0644);
+	if (fd < 0)
+		pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
+	free(dir_name);
+	pcache->fd = fd;
+
+	return fd;
+}
+
+static int probe_cache__load(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry = NULL;
+	char buf[MAX_CMDLEN], *p;
+	int ret = 0;
+	FILE *fp;
+
+	fp = fdopen(dup(pcache->fd), "r");
+	if (!fp)
+		return -EINVAL;
+
+	while (!feof(fp)) {
+		if (!fgets(buf, MAX_CMDLEN, fp))
+			break;
+		p = strchr(buf, '\n');
+		if (p)
+			*p = '\0';
+		/* #perf_probe_event or %sdt_event */
+		if (buf[0] == '#' || buf[0] == '%') {
+			entry = probe_cache_entry__new(NULL);
+			if (!entry) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			if (buf[0] == '%')
+				entry->sdt = true;
+			entry->spev = strdup(buf + 1);
+			if (entry->spev)
+				ret = parse_perf_probe_command(buf + 1,
+								&entry->pev);
+			else
+				ret = -ENOMEM;
+			if (ret < 0) {
+				probe_cache_entry__delete(entry);
+				goto out;
+			}
+			list_add_tail(&entry->node, &pcache->entries);
+		} else {	/* trace_probe_event */
+			if (!entry) {
+				ret = -EINVAL;
+				goto out;
+			}
+			strlist__add(entry->tevlist, buf);
+		}
+	}
+out:
+	fclose(fp);
+	return ret;
+}
+
+static struct probe_cache *probe_cache__alloc(void)
+{
+	struct probe_cache *pcache = zalloc(sizeof(*pcache));
+
+	if (pcache) {
+		INIT_LIST_HEAD(&pcache->entries);
+		pcache->fd = -EINVAL;
+	}
+	return pcache;
+}
+
+void probe_cache__purge(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry, *n;
+
+	list_for_each_entry_safe(entry, n, &pcache->entries, node) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+}
+
+void probe_cache__delete(struct probe_cache *pcache)
+{
+	if (!pcache)
+		return;
+
+	probe_cache__purge(pcache);
+	if (pcache->fd > 0)
+		close(pcache->fd);
+	free(pcache);
+}
+
+struct probe_cache *probe_cache__new(const char *target)
+{
+	struct probe_cache *pcache = probe_cache__alloc();
+	int ret;
+
+	if (!pcache)
+		return NULL;
+
+	ret = probe_cache__open(pcache, target);
+	if (ret < 0) {
+		pr_debug("Cache open error: %d\n", ret);
+		goto out_err;
+	}
+
+	ret = probe_cache__load(pcache);
+	if (ret < 0) {
+		pr_debug("Cache read error: %d\n", ret);
+		goto out_err;
+	}
+
+	return pcache;
+
+out_err:
+	probe_cache__delete(pcache);
+	return NULL;
+}
+
+static bool streql(const char *a, const char *b)
+{
+	if (a == b)
+		return true;
+
+	if (!a || !b)
+		return false;
+
+	return !strcmp(a, b);
+}
+
+struct probe_cache_entry *
+probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *cmd = synthesize_perf_probe_command(pev);
+
+	if (!cmd)
+		return NULL;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		if (pev->sdt) {
+			if (entry->pev.event &&
+			    streql(entry->pev.event, pev->event) &&
+			    (!pev->group ||
+			     streql(entry->pev.group, pev->group)))
+				goto found;
+
+			continue;
+		}
+		/* Hit if same event name or same command-string */
+		if ((pev->event &&
+		     (streql(entry->pev.group, pev->group) &&
+		      streql(entry->pev.event, pev->event))) ||
+		    (!strcmp(entry->spev, cmd)))
+			goto found;
+	}
+	entry = NULL;
+
+found:
+	free(cmd);
+	return entry;
+}
+
+struct probe_cache_entry *
+probe_cache__find_by_name(struct probe_cache *pcache,
+			  const char *group, const char *event)
+{
+	struct probe_cache_entry *entry = NULL;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		/* Hit if same event name or same command-string */
+		if (streql(entry->pev.group, group) &&
+		    streql(entry->pev.event, event))
+			goto found;
+	}
+	entry = NULL;
+
+found:
+	return entry;
+}
+
+int probe_cache__add_entry(struct probe_cache *pcache,
+			   struct perf_probe_event *pev,
+			   struct probe_trace_event *tevs, int ntevs)
+{
+	struct probe_cache_entry *entry = NULL;
+	char *command;
+	int i, ret = 0;
+
+	if (!pcache || !pev || !tevs || ntevs <= 0) {
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Remove old cache entry */
+	entry = probe_cache__find(pcache, pev);
+	if (entry) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+
+	ret = -ENOMEM;
+	entry = probe_cache_entry__new(pev);
+	if (!entry)
+		goto out_err;
+
+	for (i = 0; i < ntevs; i++) {
+		if (!tevs[i].point.symbol)
+			continue;
+
+		command = synthesize_probe_trace_command(&tevs[i]);
+		if (!command)
+			goto out_err;
+		strlist__add(entry->tevlist, command);
+		free(command);
+	}
+	list_add_tail(&entry->node, &pcache->entries);
+	pr_debug("Added probe cache: %d\n", ntevs);
+	return 0;
+
+out_err:
+	pr_debug("Failed to add probe caches\n");
+	probe_cache_entry__delete(entry);
+	return ret;
+}
+
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
+static unsigned long long sdt_note__get_addr(struct sdt_note *note)
+{
+	return note->bit32 ? (unsigned long long)note->addr.a32[0]
+		 : (unsigned long long)note->addr.a64[0];
+}
+
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
+{
+	struct probe_cache_entry *entry = NULL;
+	struct list_head sdtlist;
+	struct sdt_note *note;
+	char *buf;
+	char sdtgrp[64];
+	int ret;
+
+	INIT_LIST_HEAD(&sdtlist);
+	ret = get_sdt_note_list(&sdtlist, pathname);
+	if (ret < 0) {
+		pr_debug("Failed to get sdt note: %d\n", ret);
+		return ret;
+	}
+	list_for_each_entry(note, &sdtlist, note_list) {
+		ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider);
+		if (ret < 0)
+			break;
+		/* Try to find same-name entry */
+		entry = probe_cache__find_by_name(pcache, sdtgrp, note->name);
+		if (!entry) {
+			entry = probe_cache_entry__new(NULL);
+			if (!entry) {
+				ret = -ENOMEM;
+				break;
+			}
+			entry->sdt = true;
+			ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp,
+					note->name, note->name);
+			if (ret < 0)
+				break;
+			entry->pev.event = strdup(note->name);
+			entry->pev.group = strdup(sdtgrp);
+			list_add_tail(&entry->node, &pcache->entries);
+		}
+		ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
+				sdtgrp, note->name, pathname,
+				sdt_note__get_addr(note));
+		if (ret < 0)
+			break;
+		strlist__add(entry->tevlist, buf);
+		free(buf);
+		entry = NULL;
+	}
+	if (entry) {
+		list_del_init(&entry->node);
+		probe_cache_entry__delete(entry);
+	}
+	cleanup_sdt_note_list(&sdtlist);
+	return ret;
+}
+#endif
+
+static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
+{
+	struct str_node *snode;
+	struct stat st;
+	struct iovec iov[3];
+	const char *prefix = entry->sdt ? "%" : "#";
+	int ret;
+	/* Save stat for rollback */
+	ret = fstat(fd, &st);
+	if (ret < 0)
+		return ret;
+
+	pr_debug("Writing cache: %s%s\n", prefix, entry->spev);
+	iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1;
+	iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
+	iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
+	ret = writev(fd, iov, 3);
+	if (ret < (int)iov[1].iov_len + 2)
+		goto rollback;
+
+	strlist__for_each_entry(snode, entry->tevlist) {
+		iov[0].iov_base = (void *)snode->s;
+		iov[0].iov_len = strlen(snode->s);
+		iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;
+		ret = writev(fd, iov, 2);
+		if (ret < (int)iov[0].iov_len + 1)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	/* Rollback to avoid cache file corruption */
+	if (ret > 0)
+		ret = -1;
+	if (ftruncate(fd, st.st_size) < 0)
+		ret = -2;
+
+	return ret;
+}
+
+int probe_cache__commit(struct probe_cache *pcache)
+{
+	struct probe_cache_entry *entry;
+	int ret = 0;
+
+	/* TBD: if we do not update existing entries, skip it */
+	ret = lseek(pcache->fd, 0, SEEK_SET);
+	if (ret < 0)
+		goto out;
+
+	ret = ftruncate(pcache->fd, 0);
+	if (ret < 0)
+		goto out;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		ret = probe_cache_entry__write(entry, pcache->fd);
+		pr_debug("Cache committed: %d\n", ret);
+		if (ret < 0)
+			break;
+	}
+out:
+	return ret;
+}
+
+static bool probe_cache_entry__compare(struct probe_cache_entry *entry,
+				       struct strfilter *filter)
+{
+	char buf[128], *ptr = entry->spev;
+
+	if (entry->pev.event) {
+		snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
+		ptr = buf;
+	}
+	return strfilter__compare(filter, ptr);
+}
+
+int probe_cache__filter_purge(struct probe_cache *pcache,
+			      struct strfilter *filter)
+{
+	struct probe_cache_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &pcache->entries, node) {
+		if (probe_cache_entry__compare(entry, filter)) {
+			pr_info("Removed cached event: %s\n", entry->spev);
+			list_del_init(&entry->node);
+			probe_cache_entry__delete(entry);
+		}
+	}
+	return 0;
+}
+
+static int probe_cache__show_entries(struct probe_cache *pcache,
+				     struct strfilter *filter)
+{
+	struct probe_cache_entry *entry;
+
+	for_each_probe_cache_entry(entry, pcache) {
+		if (probe_cache_entry__compare(entry, filter))
+			printf("%s\n", entry->spev);
+	}
+	return 0;
+}
+
+/* Show all cached probes */
+int probe_cache__show_all_caches(struct strfilter *filter)
+{
+	struct probe_cache *pcache;
+	struct strlist *bidlist;
+	struct str_node *nd;
+	char *buf = strfilter__string(filter);
+
+	pr_debug("list cache with filter: %s\n", buf);
+	free(buf);
+
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: %d\n", errno);
+		return -EINVAL;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		pcache = probe_cache__new(nd->s);
+		if (!pcache)
+			continue;
+		if (!list_empty(&pcache->entries)) {
+			buf = build_id_cache__origname(nd->s);
+			printf("%s (%s):\n", buf, nd->s);
+			free(buf);
+			probe_cache__show_entries(pcache, filter);
+		}
+		probe_cache__delete(pcache);
+	}
+	strlist__delete(bidlist);
+
+	return 0;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 18ac9cf..9577b5c 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -5,9 +5,27 @@
 #include "strfilter.h"
 #include "probe-event.h"
 
+/* Cache of probe definitions */
+struct probe_cache_entry {
+	struct list_head	node;
+	bool			sdt;
+	struct perf_probe_event pev;
+	char			*spev;
+	struct strlist		*tevlist;
+};
+
+struct probe_cache {
+	int	fd;
+	struct list_head entries;
+};
+
 #define PF_FL_UPROBE	1
 #define PF_FL_RW	2
+#define for_each_probe_cache_entry(entry, pcache) \
+	list_for_each_entry(entry, &pcache->entries, node)
 
+/* probe-file.c depends on libelf */
+#ifdef HAVE_LIBELF_SUPPORT
 int probe_file__open(int flag);
 int probe_file__open_both(int *kfd, int *ufd, int flag);
 struct strlist *probe_file__get_namelist(int fd);
@@ -18,5 +36,29 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 				  struct strlist *plist);
 int probe_file__del_strlist(int fd, struct strlist *namelist);
 
+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+				 struct probe_trace_event **tevs);
 
+struct probe_cache *probe_cache__new(const char *target);
+int probe_cache__add_entry(struct probe_cache *pcache,
+			   struct perf_probe_event *pev,
+			   struct probe_trace_event *tevs, int ntevs);
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname);
+int probe_cache__commit(struct probe_cache *pcache);
+void probe_cache__purge(struct probe_cache *pcache);
+void probe_cache__delete(struct probe_cache *pcache);
+int probe_cache__filter_purge(struct probe_cache *pcache,
+			      struct strfilter *filter);
+struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
+					    struct perf_probe_event *pev);
+struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
+					const char *group, const char *event);
+int probe_cache__show_all_caches(struct strfilter *filter);
+#else	/* ! HAVE_LIBELF_SUPPORT */
+static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
+{
+	return NULL;
+}
+#define probe_cache__delete(pcache) do {} while (0)
+#endif
 #endif
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1259839..f2d9ff0 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -381,7 +381,7 @@ formatted:
 		if (ret >= 16)
 			ret = -E2BIG;
 		pr_warning("Failed to convert variable type: %s\n",
-			   strerror_r(-ret, sbuf, sizeof(sbuf)));
+			   str_error_r(-ret, sbuf, sizeof(sbuf)));
 		return ret;
 	}
 	tvar->type = strdup(buf);
@@ -809,7 +809,7 @@ static int find_lazy_match_lines(struct intlist *list,
 	fp = fopen(fname, "r");
 	if (!fp) {
 		pr_warning("Failed to open %s: %s\n", fname,
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 36c6862..5065ec9 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -13,6 +13,8 @@ util/cpumap.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
+../lib/str_error_r.c
+../lib/vsprintf.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 98f127a..a5fbc01 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -2,6 +2,7 @@
 #include <structmember.h>
 #include <inttypes.h>
 #include <poll.h>
+#include <linux/err.h>
 #include "evlist.h"
 #include "evsel.h"
 #include "event.h"
@@ -47,6 +48,7 @@ PyMODINIT_FUNC initperf(void);
 
 struct pyrf_event {
 	PyObject_HEAD
+	struct perf_evsel *evsel;
 	struct perf_sample sample;
 	union perf_event   event;
 };
@@ -288,6 +290,85 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
 	return ret;
 }
 
+static bool is_tracepoint(struct pyrf_event *pevent)
+{
+	return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT;
+}
+
+static PyObject*
+tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+{
+	struct pevent *pevent = field->event->pevent;
+	void *data = pe->sample.raw_data;
+	PyObject *ret = NULL;
+	unsigned long long val;
+	unsigned int offset, len;
+
+	if (field->flags & FIELD_IS_ARRAY) {
+		offset = field->offset;
+		len    = field->size;
+		if (field->flags & FIELD_IS_DYNAMIC) {
+			val     = pevent_read_number(pevent, data + offset, len);
+			offset  = val;
+			len     = offset >> 16;
+			offset &= 0xffff;
+		}
+		if (field->flags & FIELD_IS_STRING &&
+		    is_printable_array(data + offset, len)) {
+			ret = PyString_FromString((char *)data + offset);
+		} else {
+			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+			field->flags &= ~FIELD_IS_STRING;
+		}
+	} else {
+		val = pevent_read_number(pevent, data + field->offset,
+					 field->size);
+		if (field->flags & FIELD_IS_POINTER)
+			ret = PyLong_FromUnsignedLong((unsigned long) val);
+		else if (field->flags & FIELD_IS_SIGNED)
+			ret = PyLong_FromLong((long) val);
+		else
+			ret = PyLong_FromUnsignedLong((unsigned long) val);
+	}
+
+	return ret;
+}
+
+static PyObject*
+get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
+{
+	const char *str = PyString_AsString(PyObject_Str(attr_name));
+	struct perf_evsel *evsel = pevent->evsel;
+	struct format_field *field;
+
+	if (!evsel->tp_format) {
+		struct event_format *tp_format;
+
+		tp_format = trace_event__tp_format_id(evsel->attr.config);
+		if (!tp_format)
+			return NULL;
+
+		evsel->tp_format = tp_format;
+	}
+
+	field = pevent_find_any_field(evsel->tp_format, str);
+	if (!field)
+		return NULL;
+
+	return tracepoint_field(pevent, field);
+}
+
+static PyObject*
+pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
+{
+	PyObject *obj = NULL;
+
+	if (is_tracepoint(pevent))
+		obj = get_tracepoint_field(pevent, attr_name);
+
+	return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name);
+}
+
 static PyTypeObject pyrf_sample_event__type = {
 	PyVarObject_HEAD_INIT(NULL, 0)
 	.tp_name	= "perf.sample_event",
@@ -296,6 +377,7 @@ static PyTypeObject pyrf_sample_event__type = {
 	.tp_doc		= pyrf_sample_event__doc,
 	.tp_members	= pyrf_sample_event__members,
 	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
+	.tp_getattro	= (getattrofunc) pyrf_sample_event__getattro,
 };
 
 static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object.");
@@ -653,6 +735,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 	attr.precise_ip	    = precise_ip;
 	attr.mmap_data	    = mmap_data;
 	attr.sample_id_all  = sample_id_all;
+	attr.size	    = sizeof(attr);
 
 	perf_evsel__init(&pevsel->evsel, &attr, idx);
 	return 0;
@@ -863,13 +946,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
-
-		perf_evlist__mmap_consume(evlist, cpu);
+		struct perf_evsel *evsel;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
+		evsel = perf_evlist__event2evsel(evlist, event);
+		if (!evsel)
+			return Py_None;
+
+		pevent->evsel = evsel;
+
+		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
+
+		/* Consume the even only after we parsed it out. */
+		perf_evlist__mmap_consume(evlist, cpu);
+
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
@@ -957,7 +1049,7 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
 	if (i >= pevlist->evlist.nr_entries)
 		return NULL;
 
-	evlist__for_each(&pevlist->evlist, pos) {
+	evlist__for_each_entry(&pevlist->evlist, pos) {
 		if (i-- == 0)
 			break;
 	}
@@ -1073,7 +1165,32 @@ static struct {
 	{ .name = NULL, },
 };
 
+static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
+				  PyObject *args, PyObject *kwargs)
+{
+	struct event_format *tp_format;
+	static char *kwlist[] = { "sys", "name", NULL };
+	char *sys  = NULL;
+	char *name = NULL;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss", kwlist,
+					 &sys, &name))
+		return NULL;
+
+	tp_format = trace_event__tp_format(sys, name);
+	if (IS_ERR(tp_format))
+		return PyInt_FromLong(-1);
+
+	return PyInt_FromLong(tp_format->id);
+}
+
 static PyMethodDef perf__methods[] = {
+	{
+		.ml_name  = "tracepoint",
+		.ml_meth  = (PyCFunction) pyrf__tracepoint,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("Get tracepoint config.")
+	},
 	{ .ml_name = NULL, }
 };
 
@@ -1100,6 +1217,33 @@ PyMODINIT_FUNC initperf(void)
 	Py_INCREF(&pyrf_evsel__type);
 	PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
 
+	Py_INCREF(&pyrf_mmap_event__type);
+	PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type);
+
+	Py_INCREF(&pyrf_lost_event__type);
+	PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type);
+
+	Py_INCREF(&pyrf_comm_event__type);
+	PyModule_AddObject(module, "comm_event", (PyObject *)&pyrf_comm_event__type);
+
+	Py_INCREF(&pyrf_task_event__type);
+	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+	Py_INCREF(&pyrf_throttle_event__type);
+	PyModule_AddObject(module, "throttle_event", (PyObject *)&pyrf_throttle_event__type);
+
+	Py_INCREF(&pyrf_task_event__type);
+	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+	Py_INCREF(&pyrf_read_event__type);
+	PyModule_AddObject(module, "read_event", (PyObject *)&pyrf_read_event__type);
+
+	Py_INCREF(&pyrf_sample_event__type);
+	PyModule_AddObject(module, "sample_event", (PyObject *)&pyrf_sample_event__type);
+
+	Py_INCREF(&pyrf_context_switch_event__type);
+	PyModule_AddObject(module, "switch_event", (PyObject *)&pyrf_context_switch_event__type);
+
 	Py_INCREF(&pyrf_thread_map__type);
 	PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
 
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index c6d4ee2..639d1da 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -1,5 +1,7 @@
-#include "cache.h"
+#include <stdlib.h>
+#include "strbuf.h"
 #include "quote.h"
+#include "util.h"
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index e1ec191..055ca45 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -2,7 +2,6 @@
 #define __PERF_QUOTE_H
 
 #include <stddef.h>
-#include <stdio.h>
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
@@ -24,6 +23,8 @@
  * sq_quote() in a real application.
  */
 
+struct strbuf;
+
 int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index abc76e3..808cc45 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -35,7 +35,7 @@ DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname,
 
 	struct rb_node *nd;
 
-	resort_rb__for_each(nd, threads) {
+	resort_rb__for_each_entry(nd, threads) {
 		struct thread *t = threads_entry;
 		printf("%s: %d\n", t->shortname, t->tid);
 	}
@@ -123,7 +123,7 @@ static void __name##_sorted__init_entry(struct rb_node *nd,			\
 struct __name##_sorted_entry *__name##_entry;					\
 struct __name##_sorted *__name = __name##_sorted__new
 
-#define resort_rb__for_each(__nd, __name)					\
+#define resort_rb__for_each_entry(__nd, __name)					\
 	for (__nd = rb_first(&__name->entries);					\
 	     __name##_entry = rb_entry(__nd, struct __name##_sorted_entry,	\
 				       rb_node), __nd;				\
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 481792c..98bf584 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -148,7 +148,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 
 	use_comm_exec = perf_can_comm_exec();
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__config(evsel, opts, callchain);
 		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
@@ -161,18 +161,18 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 		 * match the id.
 		 */
 		use_sample_identifier = perf_can_sample_identifier();
-		evlist__for_each(evlist, evsel)
+		evlist__for_each_entry(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
-		evlist__for_each(evlist, evsel) {
+		evlist__for_each_entry(evlist, evsel) {
 			if (evsel->attr.sample_type == first->attr.sample_type)
 				continue;
 			use_sample_identifier = perf_can_sample_identifier();
 			break;
 		}
-		evlist__for_each(evlist, evsel)
+		evlist__for_each_entry(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ff13470..e0203b9 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -273,7 +273,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 		struct format_field *field, void *data)
 {
 	bool is_array = field->flags & FIELD_IS_ARRAY;
-	PyObject *obj, *list = NULL;
+	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
 
@@ -386,13 +386,12 @@ exit:
 	return pylist;
 }
 
-
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
 {
 	struct event_format *event = evsel->tp_format;
-	PyObject *handler, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
@@ -457,14 +456,26 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
-			int offset;
+		unsigned int offset, len;
+		unsigned long long val;
+
+		if (field->flags & FIELD_IS_ARRAY) {
+			offset = field->offset;
+			len    = field->size;
 			if (field->flags & FIELD_IS_DYNAMIC) {
-				offset = *(int *)(data + field->offset);
+				val     = pevent_read_number(scripting_context->pevent,
+							     data + offset, len);
+				offset  = val;
+				len     = offset >> 16;
 				offset &= 0xffff;
-			} else
-				offset = field->offset;
-			obj = PyString_FromString((char *)data + offset);
+			}
+			if (field->flags & FIELD_IS_STRING &&
+			    is_printable_array(data + offset, len)) {
+				obj = PyString_FromString((char *) data + offset);
+			} else {
+				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+				field->flags &= ~FIELD_IS_STRING;
+			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
 		}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5214974..5d61242 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -83,7 +83,7 @@ static bool perf_session__has_comm_exec(struct perf_session *session)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.comm_exec)
 			return true;
 	}
@@ -178,6 +178,8 @@ static void perf_session__delete_threads(struct perf_session *session)
 
 void perf_session__delete(struct perf_session *session)
 {
+	if (session == NULL)
+		return;
 	auxtrace__free(session);
 	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
@@ -593,6 +595,7 @@ do { 						\
 	if (bswap_safe(f, 0))			\
 		attr->f = bswap_##sz(attr->f);	\
 } while(0)
+#define bswap_field_16(f) bswap_field(f, 16)
 #define bswap_field_32(f) bswap_field(f, 32)
 #define bswap_field_64(f) bswap_field(f, 64)
 
@@ -608,6 +611,7 @@ do { 						\
 	bswap_field_64(sample_regs_user);
 	bswap_field_32(sample_stack_user);
 	bswap_field_32(aux_watermark);
+	bswap_field_16(sample_max_stack);
 
 	/*
 	 * After read_format are bitfields. Check read_format because
@@ -1495,10 +1499,27 @@ int perf_session__register_idle_thread(struct perf_session *session)
 	return err;
 }
 
+static void
+perf_session__warn_order(const struct perf_session *session)
+{
+	const struct ordered_events *oe = &session->ordered_events;
+	struct perf_evsel *evsel;
+	bool should_warn = true;
+
+	evlist__for_each_entry(session->evlist, evsel) {
+		if (evsel->attr.write_backward)
+			should_warn = false;
+	}
+
+	if (!should_warn)
+		return;
+	if (oe->nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+}
+
 static void perf_session__warn_about_errors(const struct perf_session *session)
 {
 	const struct events_stats *stats = &session->evlist->stats;
-	const struct ordered_events *oe = &session->ordered_events;
 
 	if (session->tool->lost == perf_event__process_lost &&
 	    stats->nr_events[PERF_RECORD_LOST] != 0) {
@@ -1555,8 +1576,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_unprocessable_samples);
 	}
 
-	if (oe->nr_unordered_events != 0)
-		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+	perf_session__warn_order(session);
 
 	events_stats__auxtrace_error_warn(stats);
 
@@ -1868,7 +1888,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(session->evlist, evsel) {
+	evlist__for_each_entry(session->evlist, evsel) {
 		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 	}
@@ -1950,7 +1970,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
 	struct perf_evsel *pos;
 
-	evlist__for_each(session->evlist, pos) {
+	evlist__for_each_entry(session->evlist, pos) {
 		if (pos->attr.type == type)
 			return pos;
 	}
@@ -2105,7 +2125,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
 	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
 		 sizeof(struct id_index_entry);
 
-	evlist__for_each(evlist, evsel)
+	evlist__for_each_entry(evlist, evsel)
 		nr += evsel->ids;
 
 	n = nr > max_nr ? max_nr : nr;
@@ -2118,7 +2138,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
 	ev->id_index.header.size = sz;
 	ev->id_index.nr = n;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		u32 j;
 
 		for (j = 0; j < evsel->ids; j++) {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c4e9bd7..947d21f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -79,8 +79,8 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 {
 	const char *comm = thread__comm_str(he->thread);
 
-	width = max(7U, width) - 6;
-	return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+	width = max(7U, width) - 8;
+	return repsep_snprintf(bf, size, "%7d:%-*.*s", he->thread->tid,
 			       width, width, comm ?: "");
 }
 
@@ -95,7 +95,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void
 }
 
 struct sort_entry sort_thread = {
-	.se_header	= "  Pid:Command",
+	.se_header	= "    Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
 	.se_filter	= hist_entry__thread_filter,
@@ -1218,7 +1218,7 @@ struct sort_entry sort_mem_daddr_dso = {
 	.se_header	= "Data Object",
 	.se_cmp		= sort__dso_daddr_cmp,
 	.se_snprintf	= hist_entry__dso_daddr_snprintf,
-	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+	.se_width_idx	= HISTC_MEM_DADDR_DSO,
 };
 
 struct sort_entry sort_mem_locked = {
@@ -1488,7 +1488,7 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct perf_evsel *evsel)
+			      struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1496,14 +1496,14 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+		len = hists__col_len(hists, hse->se->se_width_idx);
 
 	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 			     struct perf_hpp *hpp __maybe_unused,
-			     struct perf_evsel *evsel)
+			     struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1511,7 +1511,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+		len = hists__col_len(hists, hse->se->se_width_idx);
 
 	return len;
 }
@@ -1793,7 +1793,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 }
 
 static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct perf_evsel *evsel __maybe_unused)
+			      struct hists *hists __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
@@ -1808,7 +1808,7 @@ static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int __sort__hde_width(struct perf_hpp_fmt *fmt,
 			     struct perf_hpp *hpp __maybe_unused,
-			     struct perf_evsel *evsel __maybe_unused)
+			     struct hists *hists __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
@@ -2069,7 +2069,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 	}
 
 	full_name = !!strchr(event_name, ':');
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		/* case 2 */
 		if (full_name && !strcmp(pos->name, event_name))
 			return pos;
@@ -2125,7 +2125,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
 	int ret;
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -2143,7 +2143,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 	struct perf_evsel *evsel;
 	struct format_field *field;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
@@ -2381,6 +2381,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
+		if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+			return -EINVAL;
+
 		if (sd->entry == &sort_mem_daddr_sym)
 			list->sym = 1;
 
@@ -2424,7 +2427,10 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 		if (*tok) {
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
-				error("Invalid --sort key: `%s'", tok);
+				if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+					error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
+				else
+					error("Invalid --sort key: `%s'", tok);
 				break;
 			} else if (ret == -ESRCH) {
 				error("Unknown --sort key: `%s'", tok);
@@ -2456,7 +2462,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist)
 	if (evlist == NULL)
 		goto out_no_evlist;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			use_trace = false;
 			break;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ebb59ca..7ca37ea 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -67,6 +67,11 @@ struct hist_entry_diff {
 	};
 };
 
+struct hist_entry_ops {
+	void	*(*new)(size_t size);
+	void	(*free)(void *ptr);
+};
+
 /**
  * struct hist_entry - histogram entry
  *
@@ -125,6 +130,7 @@ struct hist_entry {
 	void			*trace_output;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
+	struct hist_entry_ops	*ops;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index aa9efe0..8a2bbd2 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -36,6 +36,11 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
 static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
@@ -82,6 +87,11 @@ void perf_stat__reset_shadow_stats(void)
 		sizeof(runtime_transaction_stats));
 	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
 	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+	memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots));
+	memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired));
+	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
+	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
+	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
 }
 
 /*
@@ -105,6 +115,16 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
 		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
+		update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
+		update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
+		update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
+		update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
+		update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
@@ -302,6 +322,107 @@ static void print_ll_cache_misses(int cpu,
 	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
+/*
+ * High level "TopDown" CPU core pipe line bottleneck break down.
+ *
+ * Basic concept following
+ * Yasin, A Top Down Method for Performance analysis and Counter architecture
+ * ISPASS14
+ *
+ * The CPU pipeline is divided into 4 areas that can be bottlenecks:
+ *
+ * Frontend -> Backend -> Retiring
+ * BadSpeculation in addition means out of order execution that is thrown away
+ * (for example branch mispredictions)
+ * Frontend is instruction decoding.
+ * Backend is execution, like computation and accessing data in memory
+ * Retiring is good execution that is not directly bottlenecked
+ *
+ * The formulas are computed in slots.
+ * A slot is an entry in the pipeline each for the pipeline width
+ * (for example a 4-wide pipeline has 4 slots for each cycle)
+ *
+ * Formulas:
+ * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) /
+ *			TotalSlots
+ * Retiring = SlotsRetired / TotalSlots
+ * FrontendBound = FetchBubbles / TotalSlots
+ * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound
+ *
+ * The kernel provides the mapping to the low level CPU events and any scaling
+ * needed for the CPU pipeline width, for example:
+ *
+ * TotalSlots = Cycles * 4
+ *
+ * The scaling factor is communicated in the sysfs unit.
+ *
+ * In some cases the CPU may not be able to measure all the formulas due to
+ * missing events. In this case multiple formulas are combined, as possible.
+ *
+ * Full TopDown supports more levels to sub-divide each area: for example
+ * BackendBound into computing bound and memory bound. For now we only
+ * support Level 1 TopDown.
+ */
+
+static double sanitize_val(double x)
+{
+	if (x < 0 && x >= -0.02)
+		return 0.0;
+	return x;
+}
+
+static double td_total_slots(int ctx, int cpu)
+{
+	return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+}
+
+static double td_bad_spec(int ctx, int cpu)
+{
+	double bad_spec = 0;
+	double total_slots;
+	double total;
+
+	total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) -
+		avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) +
+		avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]);
+	total_slots = td_total_slots(ctx, cpu);
+	if (total_slots)
+		bad_spec = total / total_slots;
+	return sanitize_val(bad_spec);
+}
+
+static double td_retiring(int ctx, int cpu)
+{
+	double retiring = 0;
+	double total_slots = td_total_slots(ctx, cpu);
+	double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]);
+
+	if (total_slots)
+		retiring = ret_slots / total_slots;
+	return retiring;
+}
+
+static double td_fe_bound(int ctx, int cpu)
+{
+	double fe_bound = 0;
+	double total_slots = td_total_slots(ctx, cpu);
+	double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]);
+
+	if (total_slots)
+		fe_bound = fetch_bub / total_slots;
+	return fe_bound;
+}
+
+static double td_be_bound(int ctx, int cpu)
+{
+	double sum = (td_fe_bound(ctx, cpu) +
+		      td_bad_spec(ctx, cpu) +
+		      td_retiring(ctx, cpu));
+	if (sum == 0)
+		return 0;
+	return sanitize_val(1.0 - sum);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out)
@@ -309,6 +430,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
+	const char *color = NULL;
 	int ctx = evsel_context(evsel);
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
@@ -452,6 +574,46 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				     avg / ratio);
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
+		double fe_bound = td_fe_bound(ctx, cpu);
+
+		if (fe_bound > 0.2)
+			color = PERF_COLOR_RED;
+		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+				fe_bound * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
+		double retiring = td_retiring(ctx, cpu);
+
+		if (retiring > 0.7)
+			color = PERF_COLOR_GREEN;
+		print_metric(ctxp, color, "%8.1f%%", "retiring",
+				retiring * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
+		double bad_spec = td_bad_spec(ctx, cpu);
+
+		if (bad_spec > 0.1)
+			color = PERF_COLOR_RED;
+		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+				bad_spec * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
+		double be_bound = td_be_bound(ctx, cpu);
+		const char *name = "backend bound";
+		static int have_recovery_bubbles = -1;
+
+		/* In case the CPU does not support topdown-recovery-bubbles */
+		if (have_recovery_bubbles < 0)
+			have_recovery_bubbles = pmu_have_event("cpu",
+					"topdown-recovery-bubbles");
+		if (!have_recovery_bubbles)
+			name = "backend bound/bad spec";
+
+		if (be_bound > 0.2)
+			color = PERF_COLOR_RED;
+		if (td_total_slots(ctx, cpu) > 0)
+			print_metric(ctxp, color, "%8.1f%%", name,
+					be_bound * 100.);
+		else
+			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ffa1d06..39345c2d 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -79,6 +79,11 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 	ID(TRANSACTION_START,	cpu/tx-start/),
 	ID(ELISION_START,	cpu/el-start/),
 	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
+	ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
+	ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
+	ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
+	ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
+	ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
 };
 #undef ID
 
@@ -157,7 +162,7 @@ int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__alloc_stats(evsel, alloc_raw))
 			goto out_free;
 	}
@@ -173,7 +178,7 @@ void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__free_stat_priv(evsel);
 		perf_evsel__free_counts(evsel);
 		perf_evsel__free_prev_raw_counts(evsel);
@@ -184,7 +189,7 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__reset_stat_priv(evsel);
 		perf_evsel__reset_counts(evsel);
 	}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 0150e78..c29bb94 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -17,6 +17,11 @@ enum perf_stat_evsel_id {
 	PERF_STAT_EVSEL_ID__TRANSACTION_START,
 	PERF_STAT_EVSEL_ID__ELISION_START,
 	PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+	PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS,
+	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED,
+	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
+	PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
+	PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
 	PERF_STAT_EVSEL_ID__MAX,
 };
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index f95f682..81759390 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,5 +1,5 @@
 #include "debug.h"
-#include "cache.h"
+#include "util.h"
 #include <linux/kernel.h>
 
 int prefixcmp(const char *str, const char *prefix)
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 54b4092..b268a66 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -40,6 +40,9 @@
 
 #include <assert.h>
 #include <stdarg.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
 
 extern char strbuf_slopbuf[];
 struct strbuf {
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index ca99002..19207e5 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -73,7 +73,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @pos:	the &struct str_node to use as a loop cursor.
  * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, slist)	\
+#define strlist__for_each_entry(pos, slist)	\
 	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
@@ -83,7 +83,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @n:		another &struct str_node to use as temporary storage.
  * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, slist)	\
+#define strlist__for_each_entry_safe(pos, n, slist)	\
 	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 #endif /* __PERF_STRLIST_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 87a297d..a34321e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -7,6 +7,7 @@
 
 #include "symbol.h"
 #include "demangle-java.h"
+#include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -16,6 +17,7 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
@@ -54,6 +56,14 @@ static int elf_getphdrnum(Elf *elf, size_t *dst)
 }
 #endif
 
+#ifndef HAVE_ELF_GETSHDRSTRNDX_SUPPORT
+static int elf_getshdrstrndx(Elf *elf __maybe_unused, size_t *dst __maybe_unused)
+{
+	pr_err("%s: update your libelf to > 0.140, this one lacks elf_getshdrstrndx().\n", __func__);
+	return -1;
+}
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
@@ -1072,6 +1082,13 @@ new_symbol:
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
 			if (demangled == NULL)
 				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+			else if (rust_is_mangled(demangled))
+				/*
+				 * Input to Rust demangling is the BFD-demangled
+				 * name which it Rust-demangles in place.
+				 */
+				rust_demangle_sym(demangled);
+
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
@@ -1781,6 +1798,260 @@ void kcore_extract__delete(struct kcore_extract *kce)
 	unlink(kce->extract_filename);
 }
 
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
+/**
+ * populate_sdt_note : Parse raw data and identify SDT note
+ * @elf: elf of the opened file
+ * @data: raw data of a section with description offset applied
+ * @len: note description size
+ * @type: type of the note
+ * @sdt_notes: List to add the SDT note
+ *
+ * Responsible for parsing the @data in section .note.stapsdt in @elf and
+ * if its an SDT note, it appends to @sdt_notes list.
+ */
+static int populate_sdt_note(Elf **elf, const char *data, size_t len,
+			     struct list_head *sdt_notes)
+{
+	const char *provider, *name;
+	struct sdt_note *tmp = NULL;
+	GElf_Ehdr ehdr;
+	GElf_Addr base_off = 0;
+	GElf_Shdr shdr;
+	int ret = -EINVAL;
+
+	union {
+		Elf64_Addr a64[NR_ADDR];
+		Elf32_Addr a32[NR_ADDR];
+	} buf;
+
+	Elf_Data dst = {
+		.d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT,
+		.d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT),
+		.d_off = 0, .d_align = 0
+	};
+	Elf_Data src = {
+		.d_buf = (void *) data, .d_type = ELF_T_ADDR,
+		.d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0,
+		.d_align = 0
+	};
+
+	tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note));
+	if (!tmp) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	INIT_LIST_HEAD(&tmp->note_list);
+
+	if (len < dst.d_size + 3)
+		goto out_free_note;
+
+	/* Translation from file representation to memory representation */
+	if (gelf_xlatetom(*elf, &dst, &src,
+			  elf_getident(*elf, NULL)[EI_DATA]) == NULL) {
+		pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1));
+		goto out_free_note;
+	}
+
+	/* Populate the fields of sdt_note */
+	provider = data + dst.d_size;
+
+	name = (const char *)memchr(provider, '\0', data + len - provider);
+	if (name++ == NULL)
+		goto out_free_note;
+
+	tmp->provider = strdup(provider);
+	if (!tmp->provider) {
+		ret = -ENOMEM;
+		goto out_free_note;
+	}
+	tmp->name = strdup(name);
+	if (!tmp->name) {
+		ret = -ENOMEM;
+		goto out_free_prov;
+	}
+
+	if (gelf_getclass(*elf) == ELFCLASS32) {
+		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
+		tmp->bit32 = true;
+	} else {
+		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr));
+		tmp->bit32 = false;
+	}
+
+	if (!gelf_getehdr(*elf, &ehdr)) {
+		pr_debug("%s : cannot get elf header.\n", __func__);
+		ret = -EBADF;
+		goto out_free_name;
+	}
+
+	/* Adjust the prelink effect :
+	 * Find out the .stapsdt.base section.
+	 * This scn will help us to handle prelinking (if present).
+	 * Compare the retrieved file offset of the base section with the
+	 * base address in the description of the SDT note. If its different,
+	 * then accordingly, adjust the note location.
+	 */
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
+		base_off = shdr.sh_offset;
+		if (base_off) {
+			if (tmp->bit32)
+				tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
+					tmp->addr.a32[1];
+			else
+				tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
+					tmp->addr.a64[1];
+		}
+	}
+
+	list_add_tail(&tmp->note_list, sdt_notes);
+	return 0;
+
+out_free_name:
+	free(tmp->name);
+out_free_prov:
+	free(tmp->provider);
+out_free_note:
+	free(tmp);
+out_err:
+	return ret;
+}
+
+/**
+ * construct_sdt_notes_list : constructs a list of SDT notes
+ * @elf : elf to look into
+ * @sdt_notes : empty list_head
+ *
+ * Scans the sections in 'elf' for the section
+ * .note.stapsdt. It, then calls populate_sdt_note to find
+ * out the SDT events and populates the 'sdt_notes'.
+ */
+static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes)
+{
+	GElf_Ehdr ehdr;
+	Elf_Scn *scn = NULL;
+	Elf_Data *data;
+	GElf_Shdr shdr;
+	size_t shstrndx, next;
+	GElf_Nhdr nhdr;
+	size_t name_off, desc_off, offset;
+	int ret = 0;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		ret = -EBADF;
+		goto out_ret;
+	}
+	if (elf_getshdrstrndx(elf, &shstrndx) != 0) {
+		ret = -EBADF;
+		goto out_ret;
+	}
+
+	/* Look for the required section */
+	scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL);
+	if (!scn) {
+		ret = -ENOENT;
+		goto out_ret;
+	}
+
+	if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) {
+		ret = -ENOENT;
+		goto out_ret;
+	}
+
+	data = elf_getdata(scn, NULL);
+
+	/* Get the SDT notes */
+	for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off,
+					      &desc_off)) > 0; offset = next) {
+		if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) &&
+		    !memcmp(data->d_buf + name_off, SDT_NOTE_NAME,
+			    sizeof(SDT_NOTE_NAME))) {
+			/* Check the type of the note */
+			if (nhdr.n_type != SDT_NOTE_TYPE)
+				goto out_ret;
+
+			ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off),
+						nhdr.n_descsz, sdt_notes);
+			if (ret < 0)
+				goto out_ret;
+		}
+	}
+	if (list_empty(sdt_notes))
+		ret = -ENOENT;
+
+out_ret:
+	return ret;
+}
+
+/**
+ * get_sdt_note_list : Wrapper to construct a list of sdt notes
+ * @head : empty list_head
+ * @target : file to find SDT notes from
+ *
+ * This opens the file, initializes
+ * the ELF and then calls construct_sdt_notes_list.
+ */
+int get_sdt_note_list(struct list_head *head, const char *target)
+{
+	Elf *elf;
+	int fd, ret;
+
+	fd = open(target, O_RDONLY);
+	if (fd < 0)
+		return -EBADF;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		ret = -EBADF;
+		goto out_close;
+	}
+	ret = construct_sdt_notes_list(elf, head);
+	elf_end(elf);
+out_close:
+	close(fd);
+	return ret;
+}
+
+/**
+ * cleanup_sdt_note_list : free the sdt notes' list
+ * @sdt_notes: sdt notes' list
+ *
+ * Free up the SDT notes in @sdt_notes.
+ * Returns the number of SDT notes free'd.
+ */
+int cleanup_sdt_note_list(struct list_head *sdt_notes)
+{
+	struct sdt_note *tmp, *pos;
+	int nr_free = 0;
+
+	list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
+		list_del(&pos->note_list);
+		free(pos->name);
+		free(pos->provider);
+		free(pos);
+		nr_free++;
+	}
+	return nr_free;
+}
+
+/**
+ * sdt_notes__get_count: Counts the number of sdt events
+ * @start: list_head to sdt_notes list
+ *
+ * Returns the number of SDT notes in a list
+ */
+int sdt_notes__get_count(struct list_head *start)
+{
+	struct sdt_note *sdt_ptr;
+	int count = 0;
+
+	list_for_each_entry(sdt_ptr, start, note_list)
+		count++;
+	return count;
+}
+#endif
+
 void symbol__elf_init(void)
 {
 	elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 54c4ff2..37e8d20 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1430,7 +1430,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (is_regular_file(name) &&
+	if (is_regular_file(dso->long_name) &&
 	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
@@ -1626,7 +1626,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 	if (!dirs)
 		return -1;
 
-	strlist__for_each(nd, dirs) {
+	strlist__for_each_entry(nd, dirs) {
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
 			  "%s/%s/kallsyms", dir, nd->s);
 		if (!validate_kcore_addresses(kallsyms_filename, map)) {
@@ -1641,6 +1641,20 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 	return ret;
 }
 
+/*
+ * Use open(O_RDONLY) to check readability directly instead of access(R_OK)
+ * since access(R_OK) only checks with real UID/GID but open() use effective
+ * UID/GID and actual capabilities (e.g. /proc/kcore requires CAP_SYS_RAWIO).
+ */
+static bool filename__readable(const char *file)
+{
+	int fd = open(file, O_RDONLY);
+	if (fd < 0)
+		return false;
+	close(fd);
+	return true;
+}
+
 static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 {
 	u8 host_build_id[BUILD_ID_SIZE];
@@ -1660,58 +1674,43 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 				 sizeof(host_build_id)) == 0)
 		is_host = dso__build_id_equal(dso, host_build_id);
 
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-
-	scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
-		  DSO__NAME_KCORE, sbuild_id);
-
-	/* Use /proc/kallsyms if possible */
+	/* Try a fast path for /proc/kallsyms if possible */
 	if (is_host) {
-		DIR *d;
-		int fd;
-
-		/* If no cached kcore go with /proc/kallsyms */
-		d = opendir(path);
-		if (!d)
-			goto proc_kallsyms;
-		closedir(d);
-
 		/*
-		 * Do not check the build-id cache, until we know we cannot use
-		 * /proc/kcore.
+		 * Do not check the build-id cache, unless we know we cannot use
+		 * /proc/kcore or module maps don't match to /proc/kallsyms.
+		 * To check readability of /proc/kcore, do not use access(R_OK)
+		 * since /proc/kcore requires CAP_SYS_RAWIO to read and access
+		 * can't check it.
 		 */
-		fd = open("/proc/kcore", O_RDONLY);
-		if (fd != -1) {
-			close(fd);
-			/* If module maps match go with /proc/kallsyms */
-			if (!validate_kcore_addresses("/proc/kallsyms", map))
-				goto proc_kallsyms;
-		}
-
-		/* Find kallsyms in build-id cache with kcore */
-		if (!find_matching_kcore(map, path, sizeof(path)))
-			return strdup(path);
-
-		goto proc_kallsyms;
+		if (filename__readable("/proc/kcore") &&
+		    !validate_kcore_addresses("/proc/kallsyms", map))
+			goto proc_kallsyms;
 	}
 
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
 	/* Find kallsyms in build-id cache with kcore */
+	scnprintf(path, sizeof(path), "%s/%s/%s",
+		  buildid_dir, DSO__NAME_KCORE, sbuild_id);
+
 	if (!find_matching_kcore(map, path, sizeof(path)))
 		return strdup(path);
 
-	scnprintf(path, sizeof(path), "%s/%s/%s",
-		  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+	/* Use current /proc/kallsyms if possible */
+	if (is_host) {
+proc_kallsyms:
+		return strdup("/proc/kallsyms");
+	}
 
-	if (access(path, F_OK)) {
+	/* Finally, find a cache of kallsyms */
+	if (!build_id_cache__kallsyms_path(sbuild_id, path, sizeof(path))) {
 		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
 		       sbuild_id);
 		return NULL;
 	}
 
 	return strdup(path);
-
-proc_kallsyms:
-	return strdup("/proc/kallsyms");
 }
 
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b10d558..699f7cb 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -342,4 +342,26 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 
 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 
+/* structure containing an SDT note's info */
+struct sdt_note {
+	char *name;			/* name of the note*/
+	char *provider;			/* provider name */
+	bool bit32;			/* whether the location is 32 bits? */
+	union {				/* location, base and semaphore addrs */
+		Elf64_Addr a64[3];
+		Elf32_Addr a32[3];
+	} addr;
+	struct list_head note_list;	/* SDT notes' list */
+};
+
+int get_sdt_note_list(struct list_head *head, const char *target);
+int cleanup_sdt_note_list(struct list_head *sdt_notes);
+int sdt_notes__get_count(struct list_head *start);
+
+#define SDT_BASE_SCN ".stapsdt.base"
+#define SDT_NOTE_SCN  ".note.stapsdt"
+#define SDT_NOTE_TYPE 3
+#define SDT_NOTE_NAME "stapsdt"
+#define NR_ADDR 3
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index a53603b..8cdcf46 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -7,6 +7,7 @@
  */
 
 #include "target.h"
+#include "util.h"
 #include "debug.h"
 
 #include <pwd.h>
@@ -121,7 +122,7 @@ int target__strerror(struct target *target, int errnum,
 	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
-		const char *err = strerror_r(errnum, buf, buflen);
+		const char *err = str_error_r(errnum, buf, buflen);
 
 		if (err != buf)
 			scnprintf(buf, buflen, "%s", err);
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 825086a..d330152 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -616,3 +616,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	return err;
 }
+
+size_t thread_stack__depth(struct thread *thread)
+{
+	if (!thread->ts)
+		return 0;
+	return thread->ts->cnt;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index ad44c79..b7e41c4 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -87,6 +87,7 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread);
 
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, void *data),
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 45fcb71..8b10a55 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -43,9 +43,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
-		if (unwind__prepare_access(thread) < 0)
-			goto err_thread;
-
 		comm_str = malloc(32);
 		if (!comm_str)
 			goto err_thread;
@@ -201,10 +198,51 @@ size_t thread__fprintf(struct thread *thread, FILE *fp)
 	       map_groups__fprintf(thread->mg, fp);
 }
 
-void thread__insert_map(struct thread *thread, struct map *map)
+int thread__insert_map(struct thread *thread, struct map *map)
 {
+	int ret;
+
+	ret = unwind__prepare_access(thread, map, NULL);
+	if (ret)
+		return ret;
+
 	map_groups__fixup_overlappings(thread->mg, map, stderr);
 	map_groups__insert(thread->mg, map);
+
+	return 0;
+}
+
+static int __thread__prepare_access(struct thread *thread)
+{
+	bool initialized = false;
+	int i, err = 0;
+
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		struct maps *maps = &thread->mg->maps[i];
+		struct map *map;
+
+		pthread_rwlock_rdlock(&maps->lock);
+
+		for (map = maps__first(maps); map; map = map__next(map)) {
+			err = unwind__prepare_access(thread, map, &initialized);
+			if (err || initialized)
+				break;
+		}
+
+		pthread_rwlock_unlock(&maps->lock);
+	}
+
+	return err;
+}
+
+static int thread__prepare_access(struct thread *thread)
+{
+	int err = 0;
+
+	if (symbol_conf.use_callchain)
+		err = __thread__prepare_access(thread);
+
+	return err;
 }
 
 static int thread__clone_map_groups(struct thread *thread,
@@ -214,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
-		return 0;
+		return thread__prepare_access(thread);
 
 	if (thread->mg == parent->mg) {
 		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
@@ -224,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+		if (map_groups__clone(thread, parent->mg, i) < 0)
 			return -ENOMEM;
 
 	return 0;
@@ -265,3 +303,14 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 			break;
 	}
 }
+
+struct thread *thread__main_thread(struct machine *machine, struct thread *thread)
+{
+	if (thread->pid_ == thread->tid)
+		return thread__get(thread);
+
+	if (thread->pid_ == -1)
+		return NULL;
+
+	return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 45fba13..99263cb 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -9,11 +9,9 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
-#ifdef HAVE_LIBUNWIND_SUPPORT
-#include <libunwind.h>
-#endif
 
 struct thread_stack;
+struct unwind_libunwind_ops;
 
 struct thread {
 	union {
@@ -36,7 +34,8 @@ struct thread {
 	void			*priv;
 	struct thread_stack	*ts;
 #ifdef HAVE_LIBUNWIND_SUPPORT
-	unw_addr_space_t	addr_space;
+	void				*addr_space;
+	struct unwind_libunwind_ops	*unwind_libunwind_ops;
 #endif
 };
 
@@ -77,10 +76,12 @@ int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
-void thread__insert_map(struct thread *thread, struct map *map);
+int thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
+struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
+
 void thread__find_addr_map(struct thread *thread,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5654fe1..40585f5 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -202,7 +202,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 	if (!slist)
 		return NULL;
 
-	strlist__for_each(pos, slist) {
+	strlist__for_each_entry(pos, slist) {
 		pid = strtol(pos->s, &end_ptr, 10);
 
 		if (pid == INT_MIN || pid == INT_MAX ||
@@ -278,7 +278,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	if (!slist)
 		return NULL;
 
-	strlist__for_each(pos, slist) {
+	strlist__for_each_entry(pos, slist) {
 		tid = strtol(pos->s, &end_ptr, 10);
 
 		if (tid == INT_MIN || tid == INT_MAX ||
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 8ae051e..c330780 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -105,3 +105,11 @@ trace_event__tp_format(const char *sys, const char *name)
 
 	return tp_format(sys, name);
 }
+
+struct event_format *trace_event__tp_format_id(int id)
+{
+	if (!tevent_initialized && trace_event__init2())
+		return ERR_PTR(-ENOMEM);
+
+	return pevent_find_event(tevent.pevent, id);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index bce5b1d..b0af9c8 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -23,6 +23,8 @@ int trace_event__register_resolver(struct machine *machine,
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
+struct event_format *trace_event__tp_format_id(int id);
+
 int bigendian(void);
 
 void event_format__fprintf(struct event_format *event,
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
new file mode 100644
index 0000000..97c0f8f
--- /dev/null
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -0,0 +1,699 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ *	Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#ifndef REMOTE_UNWIND_LIBUNWIND
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#endif
+#include "callchain.h"
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "symbol.h"
+#include "util.h"
+#include "debug.h"
+#include "asm/bug.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+				    unw_word_t ip,
+				    unw_dyn_info_t *di,
+				    unw_proc_info_t *pi,
+				    int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+extern int
+UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
+				 unw_word_t ip,
+				 unw_word_t segbase,
+				 const char *obj_name, unw_word_t start,
+				 unw_word_t end);
+
+#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
+
+#define DW_EH_PE_FORMAT_MASK	0x0f	/* format of the encoded value */
+#define DW_EH_PE_APPL_MASK	0x70	/* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit		0xff
+#define DW_EH_PE_ptr		0x00	/* pointer-sized unsigned value */
+#define DW_EH_PE_udata4		0x03	/* unsigned 32-bit value */
+#define DW_EH_PE_udata8		0x04	/* unsigned 64-bit value */
+#define DW_EH_PE_sdata4		0x0b	/* signed 32-bit value */
+#define DW_EH_PE_sdata8		0x0c	/* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr		0x00	/* absolute value */
+#define DW_EH_PE_pcrel		0x10	/* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel	0x40	/* start-of-procedure-relative */
+#define DW_EH_PE_aligned	0x50	/* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect      0x80
+ * #define DW_EH_PE_uleb128       0x01
+ * #define DW_EH_PE_udata2        0x02
+ * #define DW_EH_PE_sleb128       0x09
+ * #define DW_EH_PE_sdata2        0x0a
+ * #define DW_EH_PE_textrel       0x20
+ * #define DW_EH_PE_datarel       0x30
+ */
+
+struct unwind_info {
+	struct perf_sample	*sample;
+	struct machine		*machine;
+	struct thread		*thread;
+};
+
+#define dw_read(ptr, type, end) ({	\
+	type *__p = (type *) ptr;	\
+	type  __v;			\
+	if ((__p + 1) > (type *) end)	\
+		return -EINVAL;		\
+	__v = *__p++;			\
+	ptr = (typeof(ptr)) __p;	\
+	__v;				\
+	})
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+				   u8 encoding)
+{
+	u8 *cur = *p;
+	*val = 0;
+
+	switch (encoding) {
+	case DW_EH_PE_omit:
+		*val = 0;
+		goto out;
+	case DW_EH_PE_ptr:
+		*val = dw_read(cur, unsigned long, end);
+		goto out;
+	default:
+		break;
+	}
+
+	switch (encoding & DW_EH_PE_APPL_MASK) {
+	case DW_EH_PE_absptr:
+		break;
+	case DW_EH_PE_pcrel:
+		*val = (unsigned long) cur;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if ((encoding & 0x07) == 0x00)
+		encoding |= DW_EH_PE_udata4;
+
+	switch (encoding & DW_EH_PE_FORMAT_MASK) {
+	case DW_EH_PE_sdata4:
+		*val += dw_read(cur, s32, end);
+		break;
+	case DW_EH_PE_udata4:
+		*val += dw_read(cur, u32, end);
+		break;
+	case DW_EH_PE_sdata8:
+		*val += dw_read(cur, s64, end);
+		break;
+	case DW_EH_PE_udata8:
+		*val += dw_read(cur, u64, end);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+ out:
+	*p = cur;
+	return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({			\
+	u64 __v;						\
+	if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {	\
+		return -EINVAL;                                 \
+	}                                                       \
+	__v;                                                    \
+	})
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	u64 offset = 0;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return 0;
+
+	do {
+		if (gelf_getehdr(elf, &ehdr) == NULL)
+			break;
+
+		if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
+			break;
+
+		offset = shdr.sh_offset;
+	} while (0);
+
+	elf_end(elf);
+	return offset;
+}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	int retval = 0;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return 0;
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	retval = (ehdr.e_type == ET_EXEC);
+
+out:
+	elf_end(elf);
+	pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+	return retval;
+}
+#endif
+
+struct table_entry {
+	u32 start_ip_offset;
+	u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+	unsigned char version;
+	unsigned char eh_frame_ptr_enc;
+	unsigned char fde_count_enc;
+	unsigned char table_enc;
+
+	/*
+	 * The rest of the header is variable-length and consists of the
+	 * following members:
+	 *
+	 *	encoded_t eh_frame_ptr;
+	 *	encoded_t fde_count;
+	 */
+
+	/* A single encoded pointer should not be more than 8 bytes. */
+	u64 enc[2];
+
+	/*
+	 * struct {
+	 *    encoded_t start_ip;
+	 *    encoded_t fde_addr;
+	 * } binary_search_table[fde_count];
+	 */
+	char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+			       u64 offset, u64 *table_data, u64 *segbase,
+			       u64 *fde_count)
+{
+	struct eh_frame_hdr hdr;
+	u8 *enc = (u8 *) &hdr.enc;
+	u8 *end = (u8 *) &hdr.data;
+	ssize_t r;
+
+	r = dso__data_read_offset(dso, machine, offset,
+				  (u8 *) &hdr, sizeof(hdr));
+	if (r != sizeof(hdr))
+		return -EINVAL;
+
+	/* We dont need eh_frame_ptr, just skip it. */
+	dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+	*fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+	*segbase    = offset;
+	*table_data = (enc - (u8 *) &hdr) + offset;
+	return 0;
+}
+
+static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
+				     u64 *table_data, u64 *segbase,
+				     u64 *fde_count)
+{
+	int ret = -EINVAL, fd;
+	u64 offset = dso->data.eh_frame_hdr_offset;
+
+	if (offset == 0) {
+		fd = dso__data_get_fd(dso, machine);
+		if (fd < 0)
+			return -EINVAL;
+
+		/* Check the .eh_frame section for unwinding info */
+		offset = elf_section_offset(fd, ".eh_frame_hdr");
+		dso->data.eh_frame_hdr_offset = offset;
+		dso__data_put_fd(dso);
+	}
+
+	if (offset)
+		ret = unwind_spec_ehframe(dso, machine, offset,
+					  table_data, segbase,
+					  fde_count);
+
+	return ret;
+}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int read_unwind_spec_debug_frame(struct dso *dso,
+					struct machine *machine, u64 *offset)
+{
+	int fd;
+	u64 ofs = dso->data.debug_frame_offset;
+
+	if (ofs == 0) {
+		fd = dso__data_get_fd(dso, machine);
+		if (fd < 0)
+			return -EINVAL;
+
+		/* Check the .debug_frame section for unwinding info */
+		ofs = elf_section_offset(fd, ".debug_frame");
+		dso->data.debug_frame_offset = ofs;
+		dso__data_put_fd(dso);
+	}
+
+	*offset = ofs;
+	if (*offset)
+		return 0;
+
+	return -EINVAL;
+}
+#endif
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, ip, &al);
+	if (!al.map) {
+		/*
+		 * We've seen cases (softice) where DWARF unwinder went
+		 * through non executable mmaps, which we need to lookup
+		 * in MAP__VARIABLE tree.
+		 */
+		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+				      MAP__VARIABLE, ip, &al);
+	}
+	return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+	       int need_unwind_info, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct map *map;
+	unw_dyn_info_t di;
+	u64 table_data, segbase, fde_count;
+	int ret = -EINVAL;
+
+	map = find_map(ip, ui);
+	if (!map || !map->dso)
+		return -EINVAL;
+
+	pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+	/* Check the .eh_frame section for unwinding info */
+	if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
+				       &table_data, &segbase, &fde_count)) {
+		memset(&di, 0, sizeof(di));
+		di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
+		di.start_ip = map->start;
+		di.end_ip   = map->end;
+		di.u.rti.segbase    = map->start + segbase;
+		di.u.rti.table_data = map->start + table_data;
+		di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
+				      / sizeof(unw_word_t);
+		ret = dwarf_search_unwind_table(as, ip, &di, pi,
+						need_unwind_info, arg);
+	}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+	/* Check the .debug_frame section for unwinding info */
+	if (ret < 0 &&
+	    !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+		int fd = dso__data_get_fd(map->dso, ui->machine);
+		int is_exec = elf_is_exec(fd, map->dso->name);
+		unw_word_t base = is_exec ? 0 : map->start;
+		const char *symfile;
+
+		if (fd >= 0)
+			dso__data_put_fd(map->dso);
+
+		symfile = map->dso->symsrc_filename ?: map->dso->name;
+
+		memset(&di, 0, sizeof(di));
+		if (dwarf_find_debug_frame(0, &di, ip, base, symfile,
+					   map->start, map->end))
+			return dwarf_search_unwind_table(as, ip, &di, pi,
+							 need_unwind_info, arg);
+	}
+#endif
+
+	return ret;
+}
+
+static int access_fpreg(unw_addr_space_t __maybe_unused as,
+			unw_regnum_t __maybe_unused num,
+			unw_fpreg_t __maybe_unused *val,
+			int __maybe_unused __write,
+			void __maybe_unused *arg)
+{
+	pr_err("unwind: access_fpreg unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
+				  unw_word_t __maybe_unused *dil_addr,
+				  void __maybe_unused *arg)
+{
+	return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __maybe_unused as,
+		  unw_cursor_t __maybe_unused *cu,
+		  void __maybe_unused *arg)
+{
+	pr_err("unwind: resume unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __maybe_unused as,
+	      unw_word_t __maybe_unused addr,
+		char __maybe_unused *bufp, size_t __maybe_unused buf_len,
+		unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
+{
+	pr_err("unwind: get_proc_name unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+			  unw_word_t *data)
+{
+	struct map *map;
+	ssize_t size;
+
+	map = find_map(addr, ui);
+	if (!map) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		return -1;
+	}
+
+	if (!map->dso)
+		return -1;
+
+	size = dso__data_read_addr(map->dso, map, ui->machine,
+				   addr, (u8 *) data, sizeof(*data));
+
+	return !(size == sizeof(*data));
+}
+
+static int access_mem(unw_addr_space_t __maybe_unused as,
+		      unw_word_t addr, unw_word_t *valp,
+		      int __write, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	/* Don't support write, probably not needed. */
+	if (__write || !stack || !ui->sample->user_regs.regs) {
+		*valp = 0;
+		return 0;
+	}
+
+	ret = perf_reg_value(&start, &ui->sample->user_regs,
+			     LIBUNWIND__ARCH_REG_SP);
+	if (ret)
+		return ret;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(unw_word_t) < addr)
+		return -EINVAL;
+
+	if (addr < start || addr + sizeof(unw_word_t) >= end) {
+		ret = access_dso_mem(ui, addr, valp);
+		if (ret) {
+			pr_debug("unwind: access_mem %p not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				 (void *) (uintptr_t) addr, start, end);
+			*valp = 0;
+			return ret;
+		}
+		return 0;
+	}
+
+	offset = addr - start;
+	*valp  = *(unw_word_t *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+		 (void *) (uintptr_t) addr, (unsigned long)*valp, offset);
+	return 0;
+}
+
+static int access_reg(unw_addr_space_t __maybe_unused as,
+		      unw_regnum_t regnum, unw_word_t *valp,
+		      int __write, void *arg)
+{
+	struct unwind_info *ui = arg;
+	int id, ret;
+	u64 val;
+
+	/* Don't support write, I suspect we don't need it. */
+	if (__write) {
+		pr_err("unwind: access_reg w %d\n", regnum);
+		return 0;
+	}
+
+	if (!ui->sample->user_regs.regs) {
+		*valp = 0;
+		return 0;
+	}
+
+	id = LIBUNWIND__ARCH_REG_ID(regnum);
+	if (id < 0)
+		return -EINVAL;
+
+	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
+	if (ret) {
+		pr_err("unwind: can't read reg %d\n", regnum);
+		return ret;
+	}
+
+	*valp = (unw_word_t) val;
+	pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+	return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __maybe_unused as,
+			    unw_proc_info_t *pi __maybe_unused,
+			    void *arg __maybe_unused)
+{
+	pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread,
+		 unwind_entry_cb_t cb, void *arg)
+{
+	struct unwind_entry e;
+	struct addr_location al;
+
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
+				   MAP__FUNCTION, ip, &al);
+
+	e.ip = ip;
+	e.map = al.map;
+	e.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+	return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+	switch (err) {
+	case UNW_EINVAL:
+		pr_err("unwind: Only supports local.\n");
+		break;
+	case UNW_EUNSPEC:
+		pr_err("unwind: Unspecified error.\n");
+		break;
+	case UNW_EBADREG:
+		pr_err("unwind: Register unavailable.\n");
+		break;
+	default:
+		break;
+	}
+}
+
+static unw_accessors_t accessors = {
+	.find_proc_info		= find_proc_info,
+	.put_unwind_info	= put_unwind_info,
+	.get_dyn_info_list_addr	= get_dyn_info_list_addr,
+	.access_mem		= access_mem,
+	.access_reg		= access_reg,
+	.access_fpreg		= access_fpreg,
+	.resume			= resume,
+	.get_proc_name		= get_proc_name,
+};
+
+static int _unwind__prepare_access(struct thread *thread)
+{
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return 0;
+
+	thread->addr_space = unw_create_addr_space(&accessors, 0);
+	if (!thread->addr_space) {
+		pr_err("unwind: Can't create unwind address space.\n");
+		return -ENOMEM;
+	}
+
+	unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
+	return 0;
+}
+
+static void _unwind__flush_access(struct thread *thread)
+{
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	unw_flush_cache(thread->addr_space, 0, 0);
+}
+
+static void _unwind__finish_access(struct thread *thread)
+{
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	unw_destroy_addr_space(thread->addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+		       void *arg, int max_stack)
+{
+	u64 val;
+	unw_word_t ips[max_stack];
+	unw_addr_space_t addr_space;
+	unw_cursor_t c;
+	int ret, i = 0;
+
+	ret = perf_reg_value(&val, &ui->sample->user_regs,
+			     LIBUNWIND__ARCH_REG_IP);
+	if (ret)
+		return ret;
+
+	ips[i++] = (unw_word_t) val;
+
+	/*
+	 * If we need more than one entry, do the DWARF
+	 * unwind itself.
+	 */
+	if (max_stack - 1 > 0) {
+		WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
+		addr_space = ui->thread->addr_space;
+
+		if (addr_space == NULL)
+			return -1;
+
+		ret = unw_init_remote(&c, addr_space, ui);
+		if (ret)
+			display_error(ret);
+
+		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+			++i;
+		}
+
+		max_stack = i;
+	}
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < max_stack && !ret; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = max_stack - i - 1;
+		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
+	}
+
+	return ret;
+}
+
+static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct thread *thread,
+			struct perf_sample *data, int max_stack)
+{
+	struct unwind_info ui = {
+		.sample       = data,
+		.thread       = thread,
+		.machine      = thread->mg->machine,
+	};
+
+	if (!data->user_regs.regs)
+		return -EINVAL;
+
+	if (max_stack <= 0)
+		return -EINVAL;
+
+	return get_entries(&ui, cb, arg, max_stack);
+}
+
+static struct unwind_libunwind_ops
+_unwind_libunwind_ops = {
+	.prepare_access = _unwind__prepare_access,
+	.flush_access   = _unwind__flush_access,
+	.finish_access  = _unwind__finish_access,
+	.get_entries    = _unwind__get_entries,
+};
+
+#ifndef REMOTE_UNWIND_LIBUNWIND
+struct unwind_libunwind_ops *
+local_unwind_libunwind_ops = &_unwind_libunwind_ops;
+#endif
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 63687d3..6d542a4 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,682 +1,83 @@
-/*
- * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
- *
- * Lots of this code have been borrowed or heavily inspired from parts of
- * the libunwind 0.99 code which are (amongst other contributors I may have
- * forgotten):
- *
- * Copyright (C) 2002-2007 Hewlett-Packard Co
- *	Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
- *
- * And the bugs have been added by:
- *
- * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
- * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
- *
- */
-
-#include <elf.h>
-#include <gelf.h>
-#include <fcntl.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <linux/list.h>
-#include <libunwind.h>
-#include <libunwind-ptrace.h>
-#include "callchain.h"
+#include "unwind.h"
 #include "thread.h"
 #include "session.h"
-#include "perf_regs.h"
-#include "unwind.h"
-#include "symbol.h"
-#include "util.h"
 #include "debug.h"
-#include "asm/bug.h"
-
-extern int
-UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
-				    unw_word_t ip,
-				    unw_dyn_info_t *di,
-				    unw_proc_info_t *pi,
-				    int need_unwind_info, void *arg);
-
-#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
-
-extern int
-UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
-				 unw_word_t ip,
-				 unw_word_t segbase,
-				 const char *obj_name, unw_word_t start,
-				 unw_word_t end);
-
-#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
-
-#define DW_EH_PE_FORMAT_MASK	0x0f	/* format of the encoded value */
-#define DW_EH_PE_APPL_MASK	0x70	/* how the value is to be applied */
-
-/* Pointer-encoding formats: */
-#define DW_EH_PE_omit		0xff
-#define DW_EH_PE_ptr		0x00	/* pointer-sized unsigned value */
-#define DW_EH_PE_udata4		0x03	/* unsigned 32-bit value */
-#define DW_EH_PE_udata8		0x04	/* unsigned 64-bit value */
-#define DW_EH_PE_sdata4		0x0b	/* signed 32-bit value */
-#define DW_EH_PE_sdata8		0x0c	/* signed 64-bit value */
-
-/* Pointer-encoding application: */
-#define DW_EH_PE_absptr		0x00	/* absolute value */
-#define DW_EH_PE_pcrel		0x10	/* rel. to addr. of encoded value */
-
-/*
- * The following are not documented by LSB v1.3, yet they are used by
- * GCC, presumably they aren't documented by LSB since they aren't
- * used on Linux:
- */
-#define DW_EH_PE_funcrel	0x40	/* start-of-procedure-relative */
-#define DW_EH_PE_aligned	0x50	/* aligned pointer */
+#include "arch/common.h"
 
-/* Flags intentionaly not handled, since they're not needed:
- * #define DW_EH_PE_indirect      0x80
- * #define DW_EH_PE_uleb128       0x01
- * #define DW_EH_PE_udata2        0x02
- * #define DW_EH_PE_sleb128       0x09
- * #define DW_EH_PE_sdata2        0x0a
- * #define DW_EH_PE_textrel       0x20
- * #define DW_EH_PE_datarel       0x30
- */
+struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
+struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
+struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops;
 
-struct unwind_info {
-	struct perf_sample	*sample;
-	struct machine		*machine;
-	struct thread		*thread;
-};
-
-#define dw_read(ptr, type, end) ({	\
-	type *__p = (type *) ptr;	\
-	type  __v;			\
-	if ((__p + 1) > (type *) end)	\
-		return -EINVAL;		\
-	__v = *__p++;			\
-	ptr = (typeof(ptr)) __p;	\
-	__v;				\
-	})
-
-static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
-				   u8 encoding)
+static void unwind__register_ops(struct thread *thread,
+			  struct unwind_libunwind_ops *ops)
 {
-	u8 *cur = *p;
-	*val = 0;
-
-	switch (encoding) {
-	case DW_EH_PE_omit:
-		*val = 0;
-		goto out;
-	case DW_EH_PE_ptr:
-		*val = dw_read(cur, unsigned long, end);
-		goto out;
-	default:
-		break;
-	}
-
-	switch (encoding & DW_EH_PE_APPL_MASK) {
-	case DW_EH_PE_absptr:
-		break;
-	case DW_EH_PE_pcrel:
-		*val = (unsigned long) cur;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if ((encoding & 0x07) == 0x00)
-		encoding |= DW_EH_PE_udata4;
-
-	switch (encoding & DW_EH_PE_FORMAT_MASK) {
-	case DW_EH_PE_sdata4:
-		*val += dw_read(cur, s32, end);
-		break;
-	case DW_EH_PE_udata4:
-		*val += dw_read(cur, u32, end);
-		break;
-	case DW_EH_PE_sdata8:
-		*val += dw_read(cur, s64, end);
-		break;
-	case DW_EH_PE_udata8:
-		*val += dw_read(cur, u64, end);
-		break;
-	default:
-		return -EINVAL;
-	}
-
- out:
-	*p = cur;
-	return 0;
-}
-
-#define dw_read_encoded_value(ptr, end, enc) ({			\
-	u64 __v;						\
-	if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {	\
-		return -EINVAL;                                 \
-	}                                                       \
-	__v;                                                    \
-	})
-
-static u64 elf_section_offset(int fd, const char *name)
-{
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-	u64 offset = 0;
-
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL)
-		return 0;
-
-	do {
-		if (gelf_getehdr(elf, &ehdr) == NULL)
-			break;
-
-		if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
-			break;
-
-		offset = shdr.sh_offset;
-	} while (0);
-
-	elf_end(elf);
-	return offset;
+	thread->unwind_libunwind_ops = ops;
 }
 
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-static int elf_is_exec(int fd, const char *name)
+int unwind__prepare_access(struct thread *thread, struct map *map,
+			   bool *initialized)
 {
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	int retval = 0;
+	const char *arch;
+	enum dso_type dso_type;
+	struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops;
+	int err;
 
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL)
+	if (thread->addr_space) {
+		pr_debug("unwind: thread map already set, dso=%s\n",
+			 map->dso->name);
+		if (initialized)
+			*initialized = true;
 		return 0;
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		goto out;
-
-	retval = (ehdr.e_type == ET_EXEC);
-
-out:
-	elf_end(elf);
-	pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
-	return retval;
-}
-#endif
-
-struct table_entry {
-	u32 start_ip_offset;
-	u32 fde_offset;
-};
-
-struct eh_frame_hdr {
-	unsigned char version;
-	unsigned char eh_frame_ptr_enc;
-	unsigned char fde_count_enc;
-	unsigned char table_enc;
-
-	/*
-	 * The rest of the header is variable-length and consists of the
-	 * following members:
-	 *
-	 *	encoded_t eh_frame_ptr;
-	 *	encoded_t fde_count;
-	 */
-
-	/* A single encoded pointer should not be more than 8 bytes. */
-	u64 enc[2];
-
-	/*
-	 * struct {
-	 *    encoded_t start_ip;
-	 *    encoded_t fde_addr;
-	 * } binary_search_table[fde_count];
-	 */
-	char data[0];
-} __packed;
-
-static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
-			       u64 offset, u64 *table_data, u64 *segbase,
-			       u64 *fde_count)
-{
-	struct eh_frame_hdr hdr;
-	u8 *enc = (u8 *) &hdr.enc;
-	u8 *end = (u8 *) &hdr.data;
-	ssize_t r;
-
-	r = dso__data_read_offset(dso, machine, offset,
-				  (u8 *) &hdr, sizeof(hdr));
-	if (r != sizeof(hdr))
-		return -EINVAL;
-
-	/* We dont need eh_frame_ptr, just skip it. */
-	dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
-
-	*fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
-	*segbase    = offset;
-	*table_data = (enc - (u8 *) &hdr) + offset;
-	return 0;
-}
-
-static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
-				     u64 *table_data, u64 *segbase,
-				     u64 *fde_count)
-{
-	int ret = -EINVAL, fd;
-	u64 offset = dso->data.eh_frame_hdr_offset;
-
-	if (offset == 0) {
-		fd = dso__data_get_fd(dso, machine);
-		if (fd < 0)
-			return -EINVAL;
-
-		/* Check the .eh_frame section for unwinding info */
-		offset = elf_section_offset(fd, ".eh_frame_hdr");
-		dso->data.eh_frame_hdr_offset = offset;
-		dso__data_put_fd(dso);
 	}
 
-	if (offset)
-		ret = unwind_spec_ehframe(dso, machine, offset,
-					  table_data, segbase,
-					  fde_count);
+	/* env->arch is NULL for live-mode (i.e. perf top) */
+	if (!thread->mg->machine->env || !thread->mg->machine->env->arch)
+		goto out_register;
 
-	return ret;
-}
-
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-static int read_unwind_spec_debug_frame(struct dso *dso,
-					struct machine *machine, u64 *offset)
-{
-	int fd;
-	u64 ofs = dso->data.debug_frame_offset;
-
-	if (ofs == 0) {
-		fd = dso__data_get_fd(dso, machine);
-		if (fd < 0)
-			return -EINVAL;
-
-		/* Check the .debug_frame section for unwinding info */
-		ofs = elf_section_offset(fd, ".debug_frame");
-		dso->data.debug_frame_offset = ofs;
-		dso__data_put_fd(dso);
-	}
-
-	*offset = ofs;
-	if (*offset)
+	dso_type = dso__type(map->dso, thread->mg->machine);
+	if (dso_type == DSO__TYPE_UNKNOWN)
 		return 0;
 
-	return -EINVAL;
-}
-#endif
-
-static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
-{
-	struct addr_location al;
-
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, ip, &al);
-	if (!al.map) {
-		/*
-		 * We've seen cases (softice) where DWARF unwinder went
-		 * through non executable mmaps, which we need to lookup
-		 * in MAP__VARIABLE tree.
-		 */
-		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-				      MAP__VARIABLE, ip, &al);
-	}
-	return al.map;
-}
-
-static int
-find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
-	       int need_unwind_info, void *arg)
-{
-	struct unwind_info *ui = arg;
-	struct map *map;
-	unw_dyn_info_t di;
-	u64 table_data, segbase, fde_count;
-	int ret = -EINVAL;
-
-	map = find_map(ip, ui);
-	if (!map || !map->dso)
-		return -EINVAL;
-
-	pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
-
-	/* Check the .eh_frame section for unwinding info */
-	if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
-				       &table_data, &segbase, &fde_count)) {
-		memset(&di, 0, sizeof(di));
-		di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
-		di.start_ip = map->start;
-		di.end_ip   = map->end;
-		di.u.rti.segbase    = map->start + segbase;
-		di.u.rti.table_data = map->start + table_data;
-		di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
-				      / sizeof(unw_word_t);
-		ret = dwarf_search_unwind_table(as, ip, &di, pi,
-						need_unwind_info, arg);
-	}
-
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-	/* Check the .debug_frame section for unwinding info */
-	if (ret < 0 &&
-	    !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-		int fd = dso__data_get_fd(map->dso, ui->machine);
-		int is_exec = elf_is_exec(fd, map->dso->name);
-		unw_word_t base = is_exec ? 0 : map->start;
-		const char *symfile;
-
-		if (fd >= 0)
-			dso__data_put_fd(map->dso);
-
-		symfile = map->dso->symsrc_filename ?: map->dso->name;
-
-		memset(&di, 0, sizeof(di));
-		if (dwarf_find_debug_frame(0, &di, ip, base, symfile,
-					   map->start, map->end))
-			return dwarf_search_unwind_table(as, ip, &di, pi,
-							 need_unwind_info, arg);
-	}
-#endif
-
-	return ret;
-}
-
-static int access_fpreg(unw_addr_space_t __maybe_unused as,
-			unw_regnum_t __maybe_unused num,
-			unw_fpreg_t __maybe_unused *val,
-			int __maybe_unused __write,
-			void __maybe_unused *arg)
-{
-	pr_err("unwind: access_fpreg unsupported\n");
-	return -UNW_EINVAL;
-}
-
-static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
-				  unw_word_t __maybe_unused *dil_addr,
-				  void __maybe_unused *arg)
-{
-	return -UNW_ENOINFO;
-}
-
-static int resume(unw_addr_space_t __maybe_unused as,
-		  unw_cursor_t __maybe_unused *cu,
-		  void __maybe_unused *arg)
-{
-	pr_err("unwind: resume unsupported\n");
-	return -UNW_EINVAL;
-}
+	arch = normalize_arch(thread->mg->machine->env->arch);
 
-static int
-get_proc_name(unw_addr_space_t __maybe_unused as,
-	      unw_word_t __maybe_unused addr,
-		char __maybe_unused *bufp, size_t __maybe_unused buf_len,
-		unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
-{
-	pr_err("unwind: get_proc_name unsupported\n");
-	return -UNW_EINVAL;
-}
-
-static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
-			  unw_word_t *data)
-{
-	struct map *map;
-	ssize_t size;
-
-	map = find_map(addr, ui);
-	if (!map) {
-		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
-		return -1;
+	if (!strcmp(arch, "x86")) {
+		if (dso_type != DSO__TYPE_64BIT)
+			ops = x86_32_unwind_libunwind_ops;
+	} else if (!strcmp(arch, "arm64") || !strcmp(arch, "arm")) {
+		if (dso_type == DSO__TYPE_64BIT)
+			ops = arm64_unwind_libunwind_ops;
 	}
 
-	if (!map->dso)
+	if (!ops) {
+		pr_err("unwind: target platform=%s is not supported\n", arch);
 		return -1;
-
-	size = dso__data_read_addr(map->dso, map, ui->machine,
-				   addr, (u8 *) data, sizeof(*data));
-
-	return !(size == sizeof(*data));
-}
-
-static int access_mem(unw_addr_space_t __maybe_unused as,
-		      unw_word_t addr, unw_word_t *valp,
-		      int __write, void *arg)
-{
-	struct unwind_info *ui = arg;
-	struct stack_dump *stack = &ui->sample->user_stack;
-	u64 start, end;
-	int offset;
-	int ret;
-
-	/* Don't support write, probably not needed. */
-	if (__write || !stack || !ui->sample->user_regs.regs) {
-		*valp = 0;
-		return 0;
-	}
-
-	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
-	if (ret)
-		return ret;
-
-	end = start + stack->size;
-
-	/* Check overflow. */
-	if (addr + sizeof(unw_word_t) < addr)
-		return -EINVAL;
-
-	if (addr < start || addr + sizeof(unw_word_t) >= end) {
-		ret = access_dso_mem(ui, addr, valp);
-		if (ret) {
-			pr_debug("unwind: access_mem %p not inside range"
-				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
-				 (void *) (uintptr_t) addr, start, end);
-			*valp = 0;
-			return ret;
-		}
-		return 0;
-	}
-
-	offset = addr - start;
-	*valp  = *(unw_word_t *)&stack->data[offset];
-	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
-		 (void *) (uintptr_t) addr, (unsigned long)*valp, offset);
-	return 0;
-}
-
-static int access_reg(unw_addr_space_t __maybe_unused as,
-		      unw_regnum_t regnum, unw_word_t *valp,
-		      int __write, void *arg)
-{
-	struct unwind_info *ui = arg;
-	int id, ret;
-	u64 val;
-
-	/* Don't support write, I suspect we don't need it. */
-	if (__write) {
-		pr_err("unwind: access_reg w %d\n", regnum);
-		return 0;
-	}
-
-	if (!ui->sample->user_regs.regs) {
-		*valp = 0;
-		return 0;
-	}
-
-	id = libunwind__arch_reg_id(regnum);
-	if (id < 0)
-		return -EINVAL;
-
-	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
-	if (ret) {
-		pr_err("unwind: can't read reg %d\n", regnum);
-		return ret;
-	}
-
-	*valp = (unw_word_t) val;
-	pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
-	return 0;
-}
-
-static void put_unwind_info(unw_addr_space_t __maybe_unused as,
-			    unw_proc_info_t *pi __maybe_unused,
-			    void *arg __maybe_unused)
-{
-	pr_debug("unwind: put_unwind_info called\n");
-}
-
-static int entry(u64 ip, struct thread *thread,
-		 unwind_entry_cb_t cb, void *arg)
-{
-	struct unwind_entry e;
-	struct addr_location al;
-
-	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-				   MAP__FUNCTION, ip, &al);
-
-	e.ip = ip;
-	e.map = al.map;
-	e.sym = al.sym;
-
-	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
-		 al.sym ? al.sym->name : "''",
-		 ip,
-		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-	return cb(&e, arg);
-}
-
-static void display_error(int err)
-{
-	switch (err) {
-	case UNW_EINVAL:
-		pr_err("unwind: Only supports local.\n");
-		break;
-	case UNW_EUNSPEC:
-		pr_err("unwind: Unspecified error.\n");
-		break;
-	case UNW_EBADREG:
-		pr_err("unwind: Register unavailable.\n");
-		break;
-	default:
-		break;
-	}
-}
-
-static unw_accessors_t accessors = {
-	.find_proc_info		= find_proc_info,
-	.put_unwind_info	= put_unwind_info,
-	.get_dyn_info_list_addr	= get_dyn_info_list_addr,
-	.access_mem		= access_mem,
-	.access_reg		= access_reg,
-	.access_fpreg		= access_fpreg,
-	.resume			= resume,
-	.get_proc_name		= get_proc_name,
-};
-
-int unwind__prepare_access(struct thread *thread)
-{
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
-		return 0;
-
-	thread->addr_space = unw_create_addr_space(&accessors, 0);
-	if (!thread->addr_space) {
-		pr_err("unwind: Can't create unwind address space.\n");
-		return -ENOMEM;
 	}
+out_register:
+	unwind__register_ops(thread, ops);
 
-	unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
-	return 0;
+	err = thread->unwind_libunwind_ops->prepare_access(thread);
+	if (initialized)
+		*initialized = err ? false : true;
+	return err;
 }
 
 void unwind__flush_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
-		return;
-
-	unw_flush_cache(thread->addr_space, 0, 0);
+	if (thread->unwind_libunwind_ops)
+		thread->unwind_libunwind_ops->flush_access(thread);
 }
 
 void unwind__finish_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
-		return;
-
-	unw_destroy_addr_space(thread->addr_space);
-}
-
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-		       void *arg, int max_stack)
-{
-	u64 val;
-	unw_word_t ips[max_stack];
-	unw_addr_space_t addr_space;
-	unw_cursor_t c;
-	int ret, i = 0;
-
-	ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
-	if (ret)
-		return ret;
-
-	ips[i++] = (unw_word_t) val;
-
-	/*
-	 * If we need more than one entry, do the DWARF
-	 * unwind itself.
-	 */
-	if (max_stack - 1 > 0) {
-		WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
-		addr_space = ui->thread->addr_space;
-
-		if (addr_space == NULL)
-			return -1;
-
-		ret = unw_init_remote(&c, addr_space, ui);
-		if (ret)
-			display_error(ret);
-
-		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
-			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
-			++i;
-		}
-
-		max_stack = i;
-	}
-
-	/*
-	 * Display what we got based on the order setup.
-	 */
-	for (i = 0; i < max_stack && !ret; i++) {
-		int j = i;
-
-		if (callchain_param.order == ORDER_CALLER)
-			j = max_stack - i - 1;
-		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
-	}
-
-	return ret;
+	if (thread->unwind_libunwind_ops)
+		thread->unwind_libunwind_ops->finish_access(thread);
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct thread *thread,
-			struct perf_sample *data, int max_stack)
+			 struct thread *thread,
+			 struct perf_sample *data, int max_stack)
 {
-	struct unwind_info ui = {
-		.sample       = data,
-		.thread       = thread,
-		.machine      = thread->mg->machine,
-	};
-
-	if (!data->user_regs.regs)
-		return -EINVAL;
-
-	if (max_stack <= 0)
-		return -EINVAL;
-
-	return get_entries(&ui, cb, arg, max_stack);
+	if (thread->unwind_libunwind_ops)
+		return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+	return 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 12790cf..61fb1e9 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -14,18 +14,42 @@ struct unwind_entry {
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
+struct unwind_libunwind_ops {
+	int (*prepare_access)(struct thread *thread);
+	void (*flush_access)(struct thread *thread);
+	void (*finish_access)(struct thread *thread);
+	int (*get_entries)(unwind_entry_cb_t cb, void *arg,
+			   struct thread *thread,
+			   struct perf_sample *data, int max_stack);
+};
+
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack);
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
-int libunwind__arch_reg_id(int regnum);
-int unwind__prepare_access(struct thread *thread);
+#ifndef LIBUNWIND__ARCH_REG_ID
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
+#endif
+
+#ifndef LIBUNWIND__ARCH_REG_SP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP
+#endif
+
+#ifndef LIBUNWIND__ARCH_REG_IP
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP
+#endif
+
+int LIBUNWIND__ARCH_REG_ID(int regnum);
+int unwind__prepare_access(struct thread *thread, struct map *map,
+			   bool *initialized);
 void unwind__flush_access(struct thread *thread);
 void unwind__finish_access(struct thread *thread);
 #else
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+					 struct map *map __maybe_unused,
+					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
@@ -44,7 +68,9 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 	return 0;
 }
 
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+					 struct map *map __maybe_unused,
+					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 23504ad..cee559d 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -19,12 +19,19 @@
 #include "callchain.h"
 #include "strlist.h"
 
-struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
-	.min_percent = 0.5,
-	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION,
-	.value	= CCVAL_PERCENT,
+#define CALLCHAIN_PARAM_DEFAULT			\
+	.mode		= CHAIN_GRAPH_ABS,	\
+	.min_percent	= 0.5,			\
+	.order		= ORDER_CALLEE,		\
+	.key		= CCKEY_FUNCTION,	\
+	.value		= CCVAL_PERCENT,	\
+
+struct callchain_param callchain_param = {
+	CALLCHAIN_PARAM_DEFAULT
+};
+
+struct callchain_param callchain_param_default = {
+	CALLCHAIN_PARAM_DEFAULT
 };
 
 /*
@@ -97,20 +104,17 @@ int rm_rf(char *path)
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
 
-		ret = stat(namebuf, &statbuf);
+		/* We have to check symbolic link itself */
+		ret = lstat(namebuf, &statbuf);
 		if (ret < 0) {
 			pr_debug("stat failed: %s\n", namebuf);
 			break;
 		}
 
-		if (S_ISREG(statbuf.st_mode))
-			ret = unlink(namebuf);
-		else if (S_ISDIR(statbuf.st_mode))
+		if (S_ISDIR(statbuf.st_mode))
 			ret = rm_rf(namebuf);
-		else {
-			pr_debug("unknown file: %s\n", namebuf);
-			ret = -1;
-		}
+		else
+			ret = unlink(namebuf);
 	}
 	closedir(dir);
 
@@ -742,3 +746,19 @@ void print_binary(unsigned char *data, size_t len,
 	}
 	printer(BINARY_PRINT_DATA_END, -1, extra);
 }
+
+int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	if (!p || !len || p[len - 1] != 0)
+		return 0;
+
+	len--;
+
+	for (i = 0; i < len; i++) {
+		if (!isprint(p[i]) && !isspace(p[i]))
+			return 0;
+	}
+	return 1;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1e8c316..e5f5547 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -72,7 +72,6 @@
 #include <sys/ioctl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
-#include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/tracing_path.h>
@@ -360,4 +359,10 @@ typedef void (*print_binary_t)(enum binary_printer_ops,
 void print_binary(unsigned char *data, size_t len,
 		  size_t bytes_per_line, print_binary_t printer,
 		  void *extra);
+
+#if !defined(__GLIBC__) && !defined(__ANDROID__)
+extern int sched_getcpu(void);
+#endif
+
+int is_printable_array(char *p, unsigned int len);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 44d440d..7bdcad4 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -134,8 +134,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
-#if BITS_PER_LONG == 64
-
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
@@ -156,6 +154,8 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
 	return dso_type;
 }
 
+#if BITS_PER_LONG == 64
+
 static int vdso__do_copy_compat(FILE *f, int fd)
 {
 	char buf[4096];
@@ -283,8 +283,38 @@ static int __machine__findnew_vdso_compat(struct machine *machine,
 
 #endif
 
+static struct dso *machine__find_vdso(struct machine *machine,
+				      struct thread *thread)
+{
+	struct dso *dso = NULL;
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+		if (!dso) {
+			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
+					   true);
+			if (dso && dso_type != dso__type(dso, machine))
+				dso = NULL;
+		}
+		break;
+	case DSO__TYPE_X32BIT:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+		break;
+	case DSO__TYPE_64BIT:
+	case DSO__TYPE_UNKNOWN:
+	default:
+		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		break;
+	}
+
+	return dso;
+}
+
 struct dso *machine__findnew_vdso(struct machine *machine,
-				  struct thread *thread __maybe_unused)
+				  struct thread *thread)
 {
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
@@ -297,6 +327,10 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	if (!vdso_info)
 		goto out_unlock;
 
+	dso = machine__find_vdso(machine, thread);
+	if (dso)
+		goto out_unlock;
+
 #if BITS_PER_LONG == 64
 	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
 		goto out_unlock;