diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e9054fd1d0d0..4c74a2f4ddfc 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -856,6 +856,11 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
+	disable_counter_freezing [HW]
+			Disable Intel PMU counter freezing feature.
+			The feature only exists starting from
+			Arch Perfmon v4 (Skylake and newer).
+
 	disable_ddw	[PPC/PSERIES]
 			Disable Dynamic DMA Window support. Use this if
 			to workaround buggy firmware.
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index f662d3c530e5..52b10945ff75 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -520,18 +520,24 @@ the pseudo-locked region:
 2) Cache hit and miss measurements using model specific precision counters if
    available. Depending on the levels of cache on the system the pseudo_lock_l2
    and pseudo_lock_l3 tracepoints are available.
-   WARNING: triggering this  measurement uses from two (for just L2
-   measurements) to four (for L2 and L3 measurements) precision counters on
-   the system, if any other measurements are in progress the counters and
-   their corresponding event registers will be clobbered.
 
 When a pseudo-locked region is created a new debugfs directory is created for
 it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single
 write-only file, pseudo_lock_measure, is present in this directory. The
-measurement on the pseudo-locked region depends on the number, 1 or 2,
-written to this debugfs file. Since the measurements are recorded with the
-tracing infrastructure the relevant tracepoints need to be enabled before the
-measurement is triggered.
+measurement of the pseudo-locked region depends on the number written to this
+debugfs file:
+1 -  writing "1" to the pseudo_lock_measure file will trigger the latency
+     measurement captured in the pseudo_lock_mem_latency tracepoint. See
+     example below.
+2 -  writing "2" to the pseudo_lock_measure file will trigger the L2 cache
+     residency (cache hits and misses) measurement captured in the
+     pseudo_lock_l2 tracepoint. See example below.
+3 -  writing "3" to the pseudo_lock_measure file will trigger the L3 cache
+     residency (cache hits and misses) measurement captured in the
+     pseudo_lock_l3 tracepoint.
+
+All measurements are recorded with the tracing infrastructure. This requires
+the relevant tracepoints to be enabled before the measurement is triggered.
 
 Example of latency debugging interface:
 In this example a pseudo-locked region named "newlock" was created. Here is
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index dfb2f7c0d019..de32741d041a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1033,6 +1033,27 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 	}
 }
 
+/**
+ * x86_perf_rdpmc_index - Return PMC counter used for event
+ * @event: the perf_event to which the PMC counter was assigned
+ *
+ * The counter assigned to this performance event may change if interrupts
+ * are enabled. This counter should thus never be used while interrupts are
+ * enabled. Before this function is used to obtain the assigned counter the
+ * event should be checked for validity using, for example,
+ * perf_event_read_local(), within the same interrupt disabled section in
+ * which this counter is planned to be used.
+ *
+ * Return: The index of the performance monitoring counter assigned to
+ * @perf_event.
+ */
+int x86_perf_rdpmc_index(struct perf_event *event)
+{
+	lockdep_assert_irqs_disabled();
+
+	return event->hw.event_base_rdpmc;
+}
+
 static inline int match_prev_assignment(struct hw_perf_event *hwc,
 					struct cpu_hw_events *cpuc,
 					int i)
@@ -1584,7 +1605,7 @@ static void __init pmu_check_apic(void)
 
 }
 
-static struct attribute_group x86_pmu_format_group = {
+static struct attribute_group x86_pmu_format_group __ro_after_init = {
 	.name = "format",
 	.attrs = NULL,
 };
@@ -1631,9 +1652,9 @@ __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
 	struct attribute **new;
 	int j, i;
 
-	for (j = 0; a[j]; j++)
+	for (j = 0; a && a[j]; j++)
 		;
-	for (i = 0; b[i]; i++)
+	for (i = 0; b && b[i]; i++)
 		j++;
 	j++;
 
@@ -1642,9 +1663,9 @@ __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
 		return NULL;
 
 	j = 0;
-	for (i = 0; a[i]; i++)
+	for (i = 0; a && a[i]; i++)
 		new[j++] = a[i];
-	for (i = 0; b[i]; i++)
+	for (i = 0; b && b[i]; i++)
 		new[j++] = b[i];
 	new[j] = NULL;
 
@@ -1715,7 +1736,7 @@ static struct attribute *events_attr[] = {
 	NULL,
 };
 
-static struct attribute_group x86_pmu_events_group = {
+static struct attribute_group x86_pmu_events_group __ro_after_init = {
 	.name = "events",
 	.attrs = events_attr,
 };
@@ -2230,7 +2251,7 @@ static struct attribute *x86_pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group x86_pmu_attr_group = {
+static struct attribute_group x86_pmu_attr_group __ro_after_init = {
 	.attrs = x86_pmu_attrs,
 };
 
@@ -2248,7 +2269,7 @@ static struct attribute *x86_pmu_caps_attrs[] = {
 	NULL
 };
 
-static struct attribute_group x86_pmu_caps_group = {
+static struct attribute_group x86_pmu_caps_group __ro_after_init = {
 	.name = "caps",
 	.attrs = x86_pmu_caps_attrs,
 };
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 035c37481f57..0fb8659b20d8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -242,7 +242,7 @@ 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");
 
-static struct attribute *nhm_events_attrs[] = {
+static struct attribute *nhm_mem_events_attrs[] = {
 	EVENT_PTR(mem_ld_nhm),
 	NULL,
 };
@@ -278,8 +278,6 @@ 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),
@@ -290,6 +288,12 @@ static struct attribute *snb_events_attrs[] = {
 	NULL,
 };
 
+static struct attribute *snb_mem_events_attrs[] = {
+	EVENT_PTR(mem_ld_snb),
+	EVENT_PTR(mem_st_snb),
+	NULL,
+};
+
 static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -1995,6 +1999,18 @@ static void intel_pmu_nhm_enable_all(int added)
 	intel_pmu_enable_all(added);
 }
 
+static void enable_counter_freeze(void)
+{
+	update_debugctlmsr(get_debugctlmsr() |
+			DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
+static void disable_counter_freeze(void)
+{
+	update_debugctlmsr(get_debugctlmsr() &
+			~DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
 static inline u64 intel_pmu_get_status(void)
 {
 	u64 status;
@@ -2200,59 +2216,15 @@ static void intel_pmu_reset(void)
 	local_irq_restore(flags);
 }
 
-/*
- * This handler is triggered by the local APIC, so the APIC IRQ handling
- * rules apply:
- */
-static int intel_pmu_handle_irq(struct pt_regs *regs)
+static int handle_pmi_common(struct pt_regs *regs, u64 status)
 {
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
-	int bit, loops;
-	u64 status;
-	int handled;
-	int pmu_enabled;
-
-	cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	/*
-	 * Save the PMU state.
-	 * It needs to be restored when leaving the handler.
-	 */
-	pmu_enabled = cpuc->enabled;
-	/*
-	 * No known reason to not always do late ACK,
-	 * but just in case do it opt-in.
-	 */
-	if (!x86_pmu.late_ack)
-		apic_write(APIC_LVTPC, APIC_DM_NMI);
-	intel_bts_disable_local();
-	cpuc->enabled = 0;
-	__intel_pmu_disable_all();
-	handled = intel_pmu_drain_bts_buffer();
-	handled += intel_bts_interrupt();
-	status = intel_pmu_get_status();
-	if (!status)
-		goto done;
-
-	loops = 0;
-again:
-	intel_pmu_lbr_read();
-	intel_pmu_ack_status(status);
-	if (++loops > 100) {
-		static bool warned = false;
-		if (!warned) {
-			WARN(1, "perfevents: irq loop stuck!\n");
-			perf_event_print_debug();
-			warned = true;
-		}
-		intel_pmu_reset();
-		goto done;
-	}
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int bit;
+	int handled = 0;
 
 	inc_irq_stat(apic_perf_irqs);
 
-
 	/*
 	 * Ignore a range of extra bits in status that do not indicate
 	 * overflow by themselves.
@@ -2261,7 +2233,7 @@ again:
 		    GLOBAL_STATUS_ASIF |
 		    GLOBAL_STATUS_LBRS_FROZEN);
 	if (!status)
-		goto done;
+		return 0;
 	/*
 	 * In case multiple PEBS events are sampled at the same time,
 	 * it is possible to have GLOBAL_STATUS bit 62 set indicating
@@ -2331,6 +2303,146 @@ again:
 			x86_pmu_stop(event, 0);
 	}
 
+	return handled;
+}
+
+static bool disable_counter_freezing;
+static int __init intel_perf_counter_freezing_setup(char *s)
+{
+	disable_counter_freezing = true;
+	pr_info("Intel PMU Counter freezing feature disabled\n");
+	return 1;
+}
+__setup("disable_counter_freezing", intel_perf_counter_freezing_setup);
+
+/*
+ * Simplified handler for Arch Perfmon v4:
+ * - We rely on counter freezing/unfreezing to enable/disable the PMU.
+ * This is done automatically on PMU ack.
+ * - Ack the PMU only after the APIC.
+ */
+
+static int intel_pmu_handle_irq_v4(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int handled = 0;
+	bool bts = false;
+	u64 status;
+	int pmu_enabled = cpuc->enabled;
+	int loops = 0;
+
+	/* PMU has been disabled because of counter freezing */
+	cpuc->enabled = 0;
+	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+		bts = true;
+		intel_bts_disable_local();
+		handled = intel_pmu_drain_bts_buffer();
+		handled += intel_bts_interrupt();
+	}
+	status = intel_pmu_get_status();
+	if (!status)
+		goto done;
+again:
+	intel_pmu_lbr_read();
+	if (++loops > 100) {
+		static bool warned;
+
+		if (!warned) {
+			WARN(1, "perfevents: irq loop stuck!\n");
+			perf_event_print_debug();
+			warned = true;
+		}
+		intel_pmu_reset();
+		goto done;
+	}
+
+
+	handled += handle_pmi_common(regs, status);
+done:
+	/* Ack the PMI in the APIC */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+	/*
+	 * The counters start counting immediately while ack the status.
+	 * Make it as close as possible to IRET. This avoids bogus
+	 * freezing on Skylake CPUs.
+	 */
+	if (status) {
+		intel_pmu_ack_status(status);
+	} else {
+		/*
+		 * CPU may issues two PMIs very close to each other.
+		 * When the PMI handler services the first one, the
+		 * GLOBAL_STATUS is already updated to reflect both.
+		 * When it IRETs, the second PMI is immediately
+		 * handled and it sees clear status. At the meantime,
+		 * there may be a third PMI, because the freezing bit
+		 * isn't set since the ack in first PMI handlers.
+		 * Double check if there is more work to be done.
+		 */
+		status = intel_pmu_get_status();
+		if (status)
+			goto again;
+	}
+
+	if (bts)
+		intel_bts_enable_local();
+	cpuc->enabled = pmu_enabled;
+	return handled;
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc;
+	int loops;
+	u64 status;
+	int handled;
+	int pmu_enabled;
+
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * Save the PMU state.
+	 * It needs to be restored when leaving the handler.
+	 */
+	pmu_enabled = cpuc->enabled;
+	/*
+	 * No known reason to not always do late ACK,
+	 * but just in case do it opt-in.
+	 */
+	if (!x86_pmu.late_ack)
+		apic_write(APIC_LVTPC, APIC_DM_NMI);
+	intel_bts_disable_local();
+	cpuc->enabled = 0;
+	__intel_pmu_disable_all();
+	handled = intel_pmu_drain_bts_buffer();
+	handled += intel_bts_interrupt();
+	status = intel_pmu_get_status();
+	if (!status)
+		goto done;
+
+	loops = 0;
+again:
+	intel_pmu_lbr_read();
+	intel_pmu_ack_status(status);
+	if (++loops > 100) {
+		static bool warned;
+
+		if (!warned) {
+			WARN(1, "perfevents: irq loop stuck!\n");
+			perf_event_print_debug();
+			warned = true;
+		}
+		intel_pmu_reset();
+		goto done;
+	}
+
+	handled += handle_pmi_common(regs, status);
+
 	/*
 	 * Repeat if there is more work to be done:
 	 */
@@ -3350,6 +3462,9 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (x86_pmu.version > 1)
 		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 
+	if (x86_pmu.counter_freezing)
+		enable_counter_freeze();
+
 	if (!cpuc->shared_regs)
 		return;
 
@@ -3421,6 +3536,9 @@ static void intel_pmu_cpu_dying(int cpu)
 	free_excl_cntrs(cpu);
 
 	fini_debug_store_on_cpu(cpu);
+
+	if (x86_pmu.counter_freezing)
+		disable_counter_freeze();
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3725,6 +3843,40 @@ static __init void intel_nehalem_quirk(void)
 	}
 }
 
+static bool intel_glp_counter_freezing_broken(int cpu)
+{
+	u32 rev = UINT_MAX; /* default to broken for unknown stepping */
+
+	switch (cpu_data(cpu).x86_stepping) {
+	case 1:
+		rev = 0x28;
+		break;
+	case 8:
+		rev = 0x6;
+		break;
+	}
+
+	return (cpu_data(cpu).microcode < rev);
+}
+
+static __init void intel_glp_counter_freezing_quirk(void)
+{
+	/* Check if it's already disabled */
+	if (disable_counter_freezing)
+		return;
+
+	/*
+	 * If the system starts with the wrong ucode, leave the
+	 * counter-freezing feature permanently disabled.
+	 */
+	if (intel_glp_counter_freezing_broken(raw_smp_processor_id())) {
+		pr_info("PMU counter freezing disabled due to CPU errata,"
+			"please upgrade microcode\n");
+		x86_pmu.counter_freezing = false;
+		x86_pmu.handle_irq = intel_pmu_handle_irq;
+	}
+}
+
 /*
  * enable software workaround for errata:
  * SNB: BJ122
@@ -3764,8 +3916,6 @@ EVENT_ATTR_STR(cycles-t,	cycles_t,	"event=0x3c,in_tx=1");
 EVENT_ATTR_STR(cycles-ct,	cycles_ct,	"event=0x3c,in_tx=1,in_tx_cp=1");
 
 static struct attribute *hsw_events_attrs[] = {
-	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),
@@ -3776,6 +3926,12 @@ static struct attribute *hsw_events_attrs[] = {
 	NULL
 };
 
+static struct attribute *hsw_mem_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	NULL,
+};
+
 static struct attribute *hsw_tsx_events_attrs[] = {
 	EVENT_PTR(tx_start),
 	EVENT_PTR(tx_commit),
@@ -3792,13 +3948,6 @@ static struct attribute *hsw_tsx_events_attrs[] = {
 	NULL
 };
 
-static __init struct attribute **get_hsw_events_attrs(void)
-{
-	return boot_cpu_has(X86_FEATURE_RTM) ?
-		merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
-		hsw_events_attrs;
-}
-
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -3875,9 +4024,32 @@ static struct attribute *intel_pmu_attrs[] = {
 	NULL,
 };
 
+static __init struct attribute **
+get_events_attrs(struct attribute **base,
+		 struct attribute **mem,
+		 struct attribute **tsx)
+{
+	struct attribute **attrs = base;
+	struct attribute **old;
+
+	if (mem && x86_pmu.pebs)
+		attrs = merge_attr(attrs, mem);
+
+	if (tsx && boot_cpu_has(X86_FEATURE_RTM)) {
+		old = attrs;
+		attrs = merge_attr(attrs, tsx);
+		if (old != base)
+			kfree(old);
+	}
+
+	return attrs;
+}
+
 __init int intel_pmu_init(void)
 {
 	struct attribute **extra_attr = NULL;
+	struct attribute **mem_attr = NULL;
+	struct attribute **tsx_attr = NULL;
 	struct attribute **to_free = NULL;
 	union cpuid10_edx edx;
 	union cpuid10_eax eax;
@@ -3935,6 +4107,9 @@ __init int intel_pmu_init(void)
 			max((int)edx.split.num_counters_fixed, assume);
 	}
 
+	if (version >= 4)
+		x86_pmu.counter_freezing = !disable_counter_freezing;
+
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
 
@@ -3986,7 +4161,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
-		x86_pmu.cpu_events = nhm_events_attrs;
+		mem_attr = nhm_mem_events_attrs;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4004,11 +4179,11 @@ __init int intel_pmu_init(void)
 		name = "nehalem";
 		break;
 
-	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:
+	case INTEL_FAM6_ATOM_BONNELL:
+	case INTEL_FAM6_ATOM_BONNELL_MID:
+	case INTEL_FAM6_ATOM_SALTWELL:
+	case INTEL_FAM6_ATOM_SALTWELL_MID:
+	case INTEL_FAM6_ATOM_SALTWELL_TABLET:
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -4021,9 +4196,11 @@ __init int intel_pmu_init(void)
 		name = "bonnell";
 		break;
 
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
+	case INTEL_FAM6_ATOM_SILVERMONT_MID:
 	case INTEL_FAM6_ATOM_AIRMONT:
+	case INTEL_FAM6_ATOM_AIRMONT_MID:
 		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,
@@ -4042,7 +4219,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		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,
@@ -4068,7 +4245,8 @@ __init int intel_pmu_init(void)
 		name = "goldmont";
 		break;
 
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+		x86_add_quirk(intel_glp_counter_freezing_quirk);
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4112,7 +4290,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.extra_regs = intel_westmere_extra_regs;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 
-		x86_pmu.cpu_events = nhm_events_attrs;
+		mem_attr = nhm_mem_events_attrs;
 
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4152,6 +4330,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 
 		x86_pmu.cpu_events = snb_events_attrs;
+		mem_attr = snb_mem_events_attrs;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4192,6 +4371,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 
 		x86_pmu.cpu_events = snb_events_attrs;
+		mem_attr = snb_mem_events_attrs;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4226,10 +4406,12 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = get_hsw_events_attrs();
+		x86_pmu.cpu_events = hsw_events_attrs;
 		x86_pmu.lbr_double_abort = true;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
+		mem_attr = hsw_mem_events_attrs;
+		tsx_attr = hsw_tsx_events_attrs;
 		pr_cont("Haswell events, ");
 		name = "haswell";
 		break;
@@ -4265,10 +4447,12 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = get_hsw_events_attrs();
+		x86_pmu.cpu_events = hsw_events_attrs;
 		x86_pmu.limit_period = bdw_limit_period;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
+		mem_attr = hsw_mem_events_attrs;
+		tsx_attr = hsw_tsx_events_attrs;
 		pr_cont("Broadwell events, ");
 		name = "broadwell";
 		break;
@@ -4324,7 +4508,9 @@ __init int intel_pmu_init(void)
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
 		to_free = extra_attr;
-		x86_pmu.cpu_events = get_hsw_events_attrs();
+		x86_pmu.cpu_events = hsw_events_attrs;
+		mem_attr = hsw_mem_events_attrs;
+		tsx_attr = hsw_tsx_events_attrs;
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
 		pr_cont("Skylake events, ");
@@ -4357,6 +4543,9 @@ __init int intel_pmu_init(void)
 		WARN_ON(!x86_pmu.format_attrs);
 	}
 
+	x86_pmu.cpu_events = get_events_attrs(x86_pmu.cpu_events,
+					      mem_attr, tsx_attr);
+
 	if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
 		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
@@ -4431,6 +4620,13 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	/*
+	 * For arch perfmon 4 use counter freezing to avoid
+	 * several MSR accesses in the PMI.
+	 */
+	if (x86_pmu.counter_freezing)
+		x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
+
 	kfree(to_free);
 	return 0;
 }
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f8084f18d58..d2e780705c5a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -559,8 +559,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT,     slm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE,   snb_cstates),
@@ -581,9 +581,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 8d016ce5b80d..3a0aa83cbd07 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -95,7 +95,7 @@ static ssize_t pt_cap_show(struct device *cdev,
 	return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap));
 }
 
-static struct attribute_group pt_cap_group = {
+static struct attribute_group pt_cap_group __ro_after_init = {
 	.name	= "caps",
 };
 
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 32f3e9423e99..91039ffed633 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -777,9 +777,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE,  skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b4771a6ddbc1..1b9f85abf9bc 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -69,14 +69,14 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_BROADWELL_GT3E:
 	case INTEL_FAM6_BROADWELL_X:
 
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
 	case INTEL_FAM6_ATOM_AIRMONT:
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 156286335351..adae087cecdd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -560,9 +560,11 @@ struct x86_pmu {
 	struct event_constraint *event_constraints;
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
-	bool		late_ack;
 	u64		(*limit_period)(struct perf_event *event, u64 l);
 
+	/* PMI handler bits */
+	unsigned int	late_ack		:1,
+			counter_freezing	:1;
 	/*
 	 * sysfs attrs
 	 */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 7ed08a7c3398..0dd6b0f4000e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,9 +8,6 @@
  * The "_X" parts are generally the EP and EX Xeons, or the
  * "Extreme" ones, like Broadwell-E.
  *
- * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "SILVERMONT2".
- *
  * While adding a new CPUID for a new microarchitecture, add a new
  * group to keep logically sorted out in chronological order. Within
  * that group keep the CPUID for the variants sorted by model number.
@@ -57,19 +54,23 @@
 
 /* "Small Core" Processors (Atom) */
 
-#define INTEL_FAM6_ATOM_PINEVIEW	0x1C
-#define INTEL_FAM6_ATOM_LINCROFT	0x26
-#define INTEL_FAM6_ATOM_PENWELL		0x27
-#define INTEL_FAM6_ATOM_CLOVERVIEW	0x35
-#define INTEL_FAM6_ATOM_CEDARVIEW	0x36
-#define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
-#define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
-#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
-#define INTEL_FAM6_ATOM_GOLDMONT	0x5C
-#define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
-#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
+#define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
+#define INTEL_FAM6_ATOM_BONNELL_MID	0x26 /* Silverthorne, Lincroft */
+
+#define INTEL_FAM6_ATOM_SALTWELL	0x36 /* Cedarview */
+#define INTEL_FAM6_ATOM_SALTWELL_MID	0x27 /* Penwell */
+#define INTEL_FAM6_ATOM_SALTWELL_TABLET	0x35 /* Cloverview */
+
+#define INTEL_FAM6_ATOM_SILVERMONT	0x37 /* Bay Trail, Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT_X	0x4D /* Avaton, Rangely */
+#define INTEL_FAM6_ATOM_SILVERMONT_MID	0x4A /* Merriefield */
+
+#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* Cherry Trail, Braswell */
+#define INTEL_FAM6_ATOM_AIRMONT_MID	0x5A /* Moorefield */
+
+#define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
+#define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
+#define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4731f0cf97c5..80f4a4f38c79 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -164,6 +164,7 @@
 #define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 78241b736f2a..8bdf74902293 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -278,6 +278,7 @@ struct perf_guest_switch_msr {
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
+extern int x86_perf_rdpmc_index(struct perf_event *event);
 #else
 static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5e58a74bfd3a..25f49af1b13c 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -238,24 +238,52 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs,
 		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
 }
 
+/**
+ * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns the address of the @n th entry of the
+ * kernel stack which is specified by @regs. If the @n th entry is NOT in
+ * the kernel stack, this returns NULL.
+ */
+static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return addr;
+	else
+		return NULL;
+}
+
+/* To avoid include hell, we can't include uaccess.h */
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+
 /**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
  * @regs:	pt_regs which contains kernel stack pointer.
  * @n:		stack entry number.
  *
  * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack
  * this returns 0.
  */
 static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 						      unsigned int n)
 {
-	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
-	addr += n;
-	if (regs_within_kernel_stack(regs, (unsigned long)addr))
-		return *addr;
-	else
-		return 0;
+	unsigned long *addr;
+	unsigned long val;
+	long ret;
+
+	addr = regs_get_kernel_stack_nth_addr(regs, n);
+	if (addr) {
+		ret = probe_kernel_read(&val, addr, sizeof(val));
+		if (!ret)
+			return val;
+	}
+	return 0;
 }
 
 #define arch_has_single_step()	(1)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 44c4ef3d989b..10e5ccfa9278 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -949,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 }
 
 static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PENWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PINEVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
 	{ X86_VENDOR_CENTAUR,	5 },
 	{ X86_VENDOR_INTEL,	5 },
 	{ X86_VENDOR_NSC,	5 },
@@ -968,10 +968,10 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 
 /* Only list CPUs which speculate but are non susceptible to SSB */
 static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
@@ -984,14 +984,14 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 
 static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
 	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
 	{}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index abb71ac70443..44272b7107ad 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -485,9 +485,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 	size_t tsize;
 
 	if (is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid),
-					   sizeof(unsigned long),
-					   GFP_KERNEL);
+		d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
@@ -496,7 +494,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 		tsize = sizeof(*d->mbm_total);
 		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
-			kfree(d->rmid_busy_llc);
+			bitmap_free(d->rmid_busy_llc);
 			return -ENOMEM;
 		}
 	}
@@ -504,7 +502,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 		tsize = sizeof(*d->mbm_local);
 		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
-			kfree(d->rmid_busy_llc);
+			bitmap_free(d->rmid_busy_llc);
 			kfree(d->mbm_total);
 			return -ENOMEM;
 		}
@@ -610,9 +608,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 			cancel_delayed_work(&d->cqm_limbo);
 		}
 
+		/*
+		 * rdt_domain "d" is going to be freed below, so clear
+		 * its pointer from pseudo_lock_region struct.
+		 */
+		if (d->plr)
+			d->plr->d = NULL;
+
 		kfree(d->ctrl_val);
 		kfree(d->mbps_val);
-		kfree(d->rmid_busy_llc);
+		bitmap_free(d->rmid_busy_llc);
 		kfree(d->mbm_total);
 		kfree(d->mbm_local);
 		kfree(d);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 0f53049719cd..27937458c231 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -404,8 +404,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			for_each_alloc_enabled_rdt_resource(r)
 				seq_printf(s, "%s:uninitialized\n", r->name);
 		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
-				   rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+			if (!rdtgrp->plr->d) {
+				rdt_last_cmd_clear();
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				seq_printf(s, "%s:%d=%x\n",
+					   rdtgrp->plr->r->name,
+					   rdtgrp->plr->d->id,
+					   rdtgrp->plr->cbm);
+			}
 		} else {
 			closid = rdtgrp->closid;
 			for_each_alloc_enabled_rdt_resource(r) {
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index f8c260d522ca..815b4e92522c 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
 #include <linux/mman.h>
+#include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -26,6 +27,7 @@
 #include <asm/intel_rdt_sched.h>
 #include <asm/perf_event.h>
 
+#include "../../events/perf_event.h" /* For X86_CONFIG() */
 #include "intel_rdt.h"
 
 #define CREATE_TRACE_POINTS
@@ -91,7 +93,7 @@ static u64 get_prefetch_disable_bits(void)
 		 */
 		return 0xF;
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		/*
 		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
 		 * as:
@@ -106,16 +108,6 @@ static u64 get_prefetch_disable_bits(void)
 	return 0;
 }
 
-/*
- * Helper to write 64bit value to MSR without tracing. Used when
- * use of the cache should be restricted and use of registers used
- * for local variables avoided.
- */
-static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
-{
-	__wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
-}
-
 /**
  * pseudo_lock_minor_get - Obtain available minor number
  * @minor: Pointer to where new minor number will be stored
@@ -888,31 +880,14 @@ static int measure_cycles_lat_fn(void *_plr)
 	struct pseudo_lock_region *plr = _plr;
 	unsigned long i;
 	u64 start, end;
-#ifdef CONFIG_KASAN
-	/*
-	 * The registers used for local register variables are also used
-	 * when KASAN is active. When KASAN is active we use a regular
-	 * variable to ensure we always use a valid pointer to access memory.
-	 * The cost is that accessing this pointer, which could be in
-	 * cache, will be included in the measurement of memory read latency.
-	 */
 	void *mem_r;
-#else
-#ifdef CONFIG_X86_64
-	register void *mem_r asm("rbx");
-#else
-	register void *mem_r asm("ebx");
-#endif /* CONFIG_X86_64 */
-#endif /* CONFIG_KASAN */
 
 	local_irq_disable();
 	/*
-	 * The wrmsr call may be reordered with the assignment below it.
-	 * Call wrmsr as directly as possible to avoid tracing clobbering
-	 * local register variable used for memory pointer.
+	 * Disable hardware prefetchers.
 	 */
-	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
-	mem_r = plr->kmem;
+	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	mem_r = READ_ONCE(plr->kmem);
 	/*
 	 * Dummy execute of the time measurement to load the needed
 	 * instructions into the L1 instruction cache.
@@ -934,157 +909,240 @@ static int measure_cycles_lat_fn(void *_plr)
 	return 0;
 }
 
-static int measure_cycles_perf_fn(void *_plr)
+/*
+ * Create a perf_event_attr for the hit and miss perf events that will
+ * be used during the performance measurement. A perf_event maintains
+ * a pointer to its perf_event_attr so a unique attribute structure is
+ * created for each perf_event.
+ *
+ * The actual configuration of the event is set right before use in order
+ * to use the X86_CONFIG macro.
+ */
+static struct perf_event_attr perf_miss_attr = {
+	.type		= PERF_TYPE_RAW,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 0,
+	.exclude_user	= 1,
+};
+
+static struct perf_event_attr perf_hit_attr = {
+	.type		= PERF_TYPE_RAW,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 0,
+	.exclude_user	= 1,
+};
+
+struct residency_counts {
+	u64 miss_before, hits_before;
+	u64 miss_after,  hits_after;
+};
+
+static int measure_residency_fn(struct perf_event_attr *miss_attr,
+				struct perf_event_attr *hit_attr,
+				struct pseudo_lock_region *plr,
+				struct residency_counts *counts)
 {
-	unsigned long long l3_hits = 0, l3_miss = 0;
-	u64 l3_hit_bits = 0, l3_miss_bits = 0;
-	struct pseudo_lock_region *plr = _plr;
-	unsigned long long l2_hits, l2_miss;
-	u64 l2_hit_bits, l2_miss_bits;
-	unsigned long i;
-#ifdef CONFIG_KASAN
-	/*
-	 * The registers used for local register variables are also used
-	 * when KASAN is active. When KASAN is active we use regular variables
-	 * at the cost of including cache access latency to these variables
-	 * in the measurements.
-	 */
+	u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0;
+	struct perf_event *miss_event, *hit_event;
+	int hit_pmcnum, miss_pmcnum;
 	unsigned int line_size;
 	unsigned int size;
+	unsigned long i;
 	void *mem_r;
-#else
-	register unsigned int line_size asm("esi");
-	register unsigned int size asm("edi");
-#ifdef CONFIG_X86_64
-	register void *mem_r asm("rbx");
-#else
-	register void *mem_r asm("ebx");
-#endif /* CONFIG_X86_64 */
-#endif /* CONFIG_KASAN */
+	u64 tmp;
 
-	/*
-	 * Non-architectural event for the Goldmont Microarchitecture
-	 * from Intel x86 Architecture Software Developer Manual (SDM):
-	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
-	 * Umask values:
-	 *     L1_HIT   01H
-	 *     L2_HIT   02H
-	 *     L1_MISS  08H
-	 *     L2_MISS  10H
-	 *
-	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
-	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
-	 * this platform we use the following events instead:
-	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
-	 *       REFERENCES FFH
-	 *       MISS       3FH
-	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
-	 *       REFERENCE 4FH
-	 *       MISS      41H
-	 */
-
-	/*
-	 * Start by setting flags for IA32_PERFEVTSELx:
-	 *     OS  (Operating system mode)  0x2
-	 *     INT (APIC interrupt enable)  0x10
-	 *     EN  (Enable counter)         0x40
-	 *
-	 * Then add the Umask value and event number to select performance
-	 * event.
-	 */
-
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
-		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
-		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
-		break;
-	case INTEL_FAM6_BROADWELL_X:
-		/* On BDW the l2_hit_bits count references, not hits */
-		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
-		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
-		/* On BDW the l3_hit_bits count references, not hits */
-		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
-		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
-		break;
-	default:
+	miss_event = perf_event_create_kernel_counter(miss_attr, plr->cpu,
+						      NULL, NULL, NULL);
+	if (IS_ERR(miss_event))
 		goto out;
-	}
+
+	hit_event = perf_event_create_kernel_counter(hit_attr, plr->cpu,
+						     NULL, NULL, NULL);
+	if (IS_ERR(hit_event))
+		goto out_miss;
 
 	local_irq_disable();
 	/*
-	 * Call wrmsr direcly to avoid the local register variables from
-	 * being overwritten due to reordering of their assignment with
-	 * the wrmsr calls.
+	 * Check any possible error state of events used by performing
+	 * one local read.
 	 */
-	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
-	/* Disable events and reset counters */
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
-	if (l3_hit_bits > 0) {
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+	if (perf_event_read_local(miss_event, &tmp, NULL, NULL)) {
+		local_irq_enable();
+		goto out_hit;
 	}
-	/* Set and enable the L2 counters */
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
-	if (l3_hit_bits > 0) {
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
-				      l3_hit_bits);
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
-				      l3_miss_bits);
+	if (perf_event_read_local(hit_event, &tmp, NULL, NULL)) {
+		local_irq_enable();
+		goto out_hit;
 	}
-	mem_r = plr->kmem;
-	size = plr->size;
-	line_size = plr->line_size;
+
+	/*
+	 * Disable hardware prefetchers.
+	 */
+	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+
+	/* Initialize rest of local variables */
+	/*
+	 * Performance event has been validated right before this with
+	 * interrupts disabled - it is thus safe to read the counter index.
+	 */
+	miss_pmcnum = x86_perf_rdpmc_index(miss_event);
+	hit_pmcnum = x86_perf_rdpmc_index(hit_event);
+	line_size = READ_ONCE(plr->line_size);
+	mem_r = READ_ONCE(plr->kmem);
+	size = READ_ONCE(plr->size);
+
+	/*
+	 * Read counter variables twice - first to load the instructions
+	 * used in L1 cache, second to capture accurate value that does not
+	 * include cache misses incurred because of instruction loads.
+	 */
+	rdpmcl(hit_pmcnum, hits_before);
+	rdpmcl(miss_pmcnum, miss_before);
+	/*
+	 * From SDM: Performing back-to-back fast reads are not guaranteed
+	 * to be monotonic.
+	 * Use LFENCE to ensure all previous instructions are retired
+	 * before proceeding.
+	 */
+	rmb();
+	rdpmcl(hit_pmcnum, hits_before);
+	rdpmcl(miss_pmcnum, miss_before);
+	/*
+	 * Use LFENCE to ensure all previous instructions are retired
+	 * before proceeding.
+	 */
+	rmb();
 	for (i = 0; i < size; i += line_size) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
 		asm volatile("mov (%0,%1,1), %%eax\n\t"
 			     :
 			     : "r" (mem_r), "r" (i)
 			     : "%eax", "memory");
 	}
 	/*
-	 * Call wrmsr directly (no tracing) to not influence
-	 * the cache access counters as they are disabled.
+	 * Use LFENCE to ensure all previous instructions are retired
+	 * before proceeding.
 	 */
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
-			      l2_hit_bits & ~(0x40ULL << 16));
-	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
-			      l2_miss_bits & ~(0x40ULL << 16));
-	if (l3_hit_bits > 0) {
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
-				      l3_hit_bits & ~(0x40ULL << 16));
-		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
-				      l3_miss_bits & ~(0x40ULL << 16));
-	}
-	l2_hits = native_read_pmc(0);
-	l2_miss = native_read_pmc(1);
-	if (l3_hit_bits > 0) {
-		l3_hits = native_read_pmc(2);
-		l3_miss = native_read_pmc(3);
-	}
+	rmb();
+	rdpmcl(hit_pmcnum, hits_after);
+	rdpmcl(miss_pmcnum, miss_after);
+	/*
+	 * Use LFENCE to ensure all previous instructions are retired
+	 * before proceeding.
+	 */
+	rmb();
+	/* Re-enable hardware prefetchers */
 	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
 	local_irq_enable();
+out_hit:
+	perf_event_release_kernel(hit_event);
+out_miss:
+	perf_event_release_kernel(miss_event);
+out:
 	/*
-	 * On BDW we count references and misses, need to adjust. Sometimes
-	 * the "hits" counter is a bit more than the references, for
-	 * example, x references but x + 1 hits. To not report invalid
-	 * hit values in this case we treat that as misses eaqual to
-	 * references.
+	 * All counts will be zero on failure.
 	 */
-	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
-		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
-	trace_pseudo_lock_l2(l2_hits, l2_miss);
-	if (l3_hit_bits > 0) {
-		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
-			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
-		trace_pseudo_lock_l3(l3_hits, l3_miss);
+	counts->miss_before = miss_before;
+	counts->hits_before = hits_before;
+	counts->miss_after  = miss_after;
+	counts->hits_after  = hits_after;
+	return 0;
+}
+
+static int measure_l2_residency(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	struct residency_counts counts = {0};
+
+	/*
+	 * Non-architectural event for the Goldmont Microarchitecture
+	 * from Intel x86 Architecture Software Developer Manual (SDM):
+	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
+	 * Umask values:
+	 *     L2_HIT   02H
+	 *     L2_MISS  10H
+	 */
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+		perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
+						   .umask = 0x10);
+		perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
+						  .umask = 0x2);
+		break;
+	default:
+		goto out;
 	}
 
+	measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts);
+	/*
+	 * If a failure prevented the measurements from succeeding
+	 * tracepoints will still be written and all counts will be zero.
+	 */
+	trace_pseudo_lock_l2(counts.hits_after - counts.hits_before,
+			     counts.miss_after - counts.miss_before);
+out:
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+static int measure_l3_residency(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	struct residency_counts counts = {0};
+
+	/*
+	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
+	 * this platform the following events are used instead:
+	 * LONGEST_LAT_CACHE 2EH (Documented in SDM)
+	 *       REFERENCE 4FH
+	 *       MISS      41H
+	 */
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_BROADWELL_X:
+		/* On BDW the hit event counts references, not hits */
+		perf_hit_attr.config = X86_CONFIG(.event = 0x2e,
+						  .umask = 0x4f);
+		perf_miss_attr.config = X86_CONFIG(.event = 0x2e,
+						   .umask = 0x41);
+		break;
+	default:
+		goto out;
+	}
+
+	measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts);
+	/*
+	 * If a failure prevented the measurements from succeeding
+	 * tracepoints will still be written and all counts will be zero.
+	 */
+
+	counts.miss_after -= counts.miss_before;
+	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) {
+		/*
+		 * On BDW references and misses are counted, need to adjust.
+		 * Sometimes the "hits" counter is a bit more than the
+		 * references, for example, x references but x + 1 hits.
+		 * To not report invalid hit values in this case we treat
+		 * that as misses equal to references.
+		 */
+		/* First compute the number of cache references measured */
+		counts.hits_after -= counts.hits_before;
+		/* Next convert references to cache hits */
+		counts.hits_after -= min(counts.miss_after, counts.hits_after);
+	} else {
+		counts.hits_after -= counts.hits_before;
+	}
+
+	trace_pseudo_lock_l3(counts.hits_after, counts.miss_after);
 out:
 	plr->thread_done = 1;
 	wake_up_interruptible(&plr->lock_thread_wq);
@@ -1116,6 +1174,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 		goto out;
 	}
 
+	if (!plr->d) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	plr->thread_done = 0;
 	cpu = cpumask_first(&plr->d->cpu_mask);
 	if (!cpu_online(cpu)) {
@@ -1123,13 +1186,20 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 		goto out;
 	}
 
+	plr->cpu = cpu;
+
 	if (sel == 1)
 		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
 						cpu_to_node(cpu),
 						"pseudo_lock_measure/%u",
 						cpu);
 	else if (sel == 2)
-		thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+		thread = kthread_create_on_node(measure_l2_residency, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else if (sel == 3)
+		thread = kthread_create_on_node(measure_l3_residency, plr,
 						cpu_to_node(cpu),
 						"pseudo_lock_measure/%u",
 						cpu);
@@ -1173,7 +1243,7 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
 	buf[buf_size] = '\0';
 	ret = kstrtoint(buf, 10, &sel);
 	if (ret == 0) {
-		if (sel != 1)
+		if (sel != 1 && sel != 2 && sel != 3)
 			return -EINVAL;
 		ret = debugfs_file_get(file->f_path.dentry);
 		if (ret)
@@ -1429,6 +1499,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	plr = rdtgrp->plr;
 
+	if (!plr->d) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
 	/*
 	 * Task is required to run with affinity to the cpus associated
 	 * with the pseudo-locked region. If this is not the case the task
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index b140c68bc14b..f27b8115ffa2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
 	struct rdtgroup *rdtgrp;
+	struct cpumask *mask;
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
 	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-				   cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
-		else
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			if (!rdtgrp->plr->d) {
+				rdt_last_cmd_clear();
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				mask = &rdtgrp->plr->d->cpu_mask;
+				seq_printf(s, is_cpu_list(of) ?
+					   "%*pbl\n" : "%*pb\n",
+					   cpumask_pr_args(mask));
+			}
+		} else {
 			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
 				   cpumask_pr_args(&rdtgrp->cpu_mask));
+		}
 	} else {
 		ret = -ENOENT;
 	}
@@ -961,7 +971,78 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
 }
 
 /**
- * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * rdt_cdp_peer_get - Retrieve CDP peer if it exists
+ * @r: RDT resource to which RDT domain @d belongs
+ * @d: Cache instance for which a CDP peer is requested
+ * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer)
+ *         Used to return the result.
+ * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer)
+ *         Used to return the result.
+ *
+ * RDT resources are managed independently and by extension the RDT domains
+ * (RDT resource instances) are managed independently also. The Code and
+ * Data Prioritization (CDP) RDT resources, while managed independently,
+ * could refer to the same underlying hardware. For example,
+ * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache.
+ *
+ * When provided with an RDT resource @r and an instance of that RDT
+ * resource @d rdt_cdp_peer_get() will return if there is a peer RDT
+ * resource and the exact instance that shares the same hardware.
+ *
+ * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists.
+ *         If a CDP peer was found, @r_cdp will point to the peer RDT resource
+ *         and @d_cdp will point to the peer RDT domain.
+ */
+static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
+			    struct rdt_resource **r_cdp,
+			    struct rdt_domain **d_cdp)
+{
+	struct rdt_resource *_r_cdp = NULL;
+	struct rdt_domain *_d_cdp = NULL;
+	int ret = 0;
+
+	switch (r->rid) {
+	case RDT_RESOURCE_L3DATA:
+		_r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+		break;
+	case RDT_RESOURCE_L3CODE:
+		_r_cdp =  &rdt_resources_all[RDT_RESOURCE_L3DATA];
+		break;
+	case RDT_RESOURCE_L2DATA:
+		_r_cdp =  &rdt_resources_all[RDT_RESOURCE_L2CODE];
+		break;
+	case RDT_RESOURCE_L2CODE:
+		_r_cdp =  &rdt_resources_all[RDT_RESOURCE_L2DATA];
+		break;
+	default:
+		ret = -ENOENT;
+		goto out;
+	}
+
+	/*
+	 * When a new CPU comes online and CDP is enabled then the new
+	 * RDT domains (if any) associated with both CDP RDT resources
+	 * are added in the same CPU online routine while the
+	 * rdtgroup_mutex is held. It should thus not happen for one
+	 * RDT domain to exist and be associated with its RDT CDP
+	 * resource but there is no RDT domain associated with the
+	 * peer RDT CDP resource. Hence the WARN.
+	 */
+	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
+	if (WARN_ON(!_d_cdp)) {
+		_r_cdp = NULL;
+		ret = -EINVAL;
+	}
+
+out:
+	*r_cdp = _r_cdp;
+	*d_cdp = _d_cdp;
+
+	return ret;
+}
+
+/**
+ * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
  * @r: Resource to which domain instance @d belongs.
  * @d: The domain instance for which @closid is being tested.
  * @cbm: Capacity bitmask being tested.
@@ -980,8 +1061,8 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
  *
  * Return: false if CBM does not overlap, true if it does.
  */
-bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-			   unsigned long cbm, int closid, bool exclusive)
+static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+				    unsigned long cbm, int closid, bool exclusive)
 {
 	enum rdtgrp_mode mode;
 	unsigned long ctrl_b;
@@ -1016,6 +1097,41 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
 	return false;
 }
 
+/**
+ * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Resources that can be allocated using a CBM can use the CBM to control
+ * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
+ * for overlap. Overlap test is not limited to the specific resource for
+ * which the CBM is intended though - when dealing with CDP resources that
+ * share the underlying hardware the overlap check should be performed on
+ * the CDP resource sharing the hardware also.
+ *
+ * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
+ * overlap test.
+ *
+ * Return: true if CBM overlap detected, false if there is no overlap
+ */
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   unsigned long cbm, int closid, bool exclusive)
+{
+	struct rdt_resource *r_cdp;
+	struct rdt_domain *d_cdp;
+
+	if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive))
+		return true;
+
+	if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0)
+		return false;
+
+	return  __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive);
+}
+
 /**
  * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
  *
@@ -1176,6 +1292,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 	unsigned int size;
+	int ret = 0;
 	bool sep;
 	u32 ctrl;
 
@@ -1186,11 +1303,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	}
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
-		size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
-					    rdtgrp->plr->d,
-					    rdtgrp->plr->cbm);
-		seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		if (!rdtgrp->plr->d) {
+			rdt_last_cmd_clear();
+			rdt_last_cmd_puts("Cache domain offline\n");
+			ret = -ENODEV;
+		} else {
+			seq_printf(s, "%*s:", max_name_width,
+				   rdtgrp->plr->r->name);
+			size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+						    rdtgrp->plr->d,
+						    rdtgrp->plr->cbm);
+			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		}
 		goto out;
 	}
 
@@ -1220,7 +1344,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 out:
 	rdtgroup_kn_unlock(of->kn);
 
-	return 0;
+	return ret;
 }
 
 /* rdtgroup information files for one cache resource. */
@@ -2354,14 +2478,16 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
  */
 static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 {
+	struct rdt_resource *r_cdp = NULL;
+	struct rdt_domain *d_cdp = NULL;
 	u32 used_b = 0, unused_b = 0;
 	u32 closid = rdtgrp->closid;
 	struct rdt_resource *r;
 	unsigned long tmp_cbm;
 	enum rdtgrp_mode mode;
 	struct rdt_domain *d;
+	u32 peer_ctl, *ctrl;
 	int i, ret;
-	u32 *ctrl;
 
 	for_each_alloc_enabled_rdt_resource(r) {
 		/*
@@ -2371,6 +2497,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 		if (r->rid == RDT_RESOURCE_MBA)
 			continue;
 		list_for_each_entry(d, &r->domains, list) {
+			rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
 			d->have_new_ctrl = false;
 			d->new_ctrl = r->cache.shareable_bits;
 			used_b = r->cache.shareable_bits;
@@ -2380,9 +2507,19 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 					mode = rdtgroup_mode_by_closid(i);
 					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
 						break;
-					used_b |= *ctrl;
+					/*
+					 * If CDP is active include peer
+					 * domain's usage to ensure there
+					 * is no overlap with an exclusive
+					 * group.
+					 */
+					if (d_cdp)
+						peer_ctl = d_cdp->ctrl_val[i];
+					else
+						peer_ctl = 0;
+					used_b |= *ctrl | peer_ctl;
 					if (mode == RDT_MODE_SHAREABLE)
-						d->new_ctrl |= *ctrl;
+						d->new_ctrl |= *ctrl | peer_ctl;
 				}
 			}
 			if (d->plr && d->plr->cbm > 0)
@@ -2805,6 +2942,13 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
 {
 	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
 		seq_puts(seq, ",cdp");
+
+	if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
+		seq_puts(seq, ",cdpl2");
+
+	if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA]))
+		seq_puts(seq, ",mba_MBps");
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index eaf02f2e7300..40b16b270656 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -179,7 +179,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 		opt_pre_handler(&op->kp, regs);
 		__this_cpu_write(current_kprobe, NULL);
 	}
-	preempt_enable_no_resched();
+	preempt_enable();
 }
 NOKPROBE_SYMBOL(optimized_callback);
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6d5dc5dabfd7..03b7529333a6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -636,7 +636,7 @@ unsigned long native_calibrate_tsc(void)
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_ATOM_DENVERTON:
+		case INTEL_FAM6_ATOM_GOLDMONT_X:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
 		case INTEL_FAM6_ATOM_GOLDMONT:
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 27ef714d886c..3d0e9aeea7c8 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -59,12 +59,12 @@ static const struct freq_desc freq_desc_ann = {
 };
 
 static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_PENWELL,		freq_desc_pnw),
-	INTEL_CPU_FAM6(ATOM_CLOVERVIEW,		freq_desc_clv),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_SALTWELL_MID,	freq_desc_pnw),
+	INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET,	freq_desc_clv),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT,		freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	freq_desc_tng),
 	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
-	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		freq_desc_tng),
-	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		freq_desc_ann),
+	INTEL_CPU_FAM6(ATOM_AIRMONT_MID,	freq_desc_ann),
 	{}
 };
 
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index 034813d4ab1e..6cb6076223ba 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -115,7 +115,7 @@ static struct dentry *punit_dbg_file;
 
 static int punit_dbgfs_register(struct punit_device *punit_device)
 {
-	static struct dentry *dev_state;
+	struct dentry *dev_state;
 
 	punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
 	if (!punit_dbg_file)
@@ -143,8 +143,8 @@ static void punit_dbgfs_unregister(void)
 	  (kernel_ulong_t)&drv_data }
 
 static const struct x86_cpu_id intel_punit_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD,  punit_device_tng),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,  punit_device_tng),
 	ICPU(INTEL_FAM6_ATOM_AIRMONT,	  punit_device_cht),
 	{}
 };
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index 5a0483e7bf66..31dce781364c 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -68,7 +68,7 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
 
 static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data),
 	{}
 };
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 10adb8cb3a3f..b9bda06d344d 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -314,7 +314,7 @@ static const struct lpss_device_desc bsw_spi_dev_desc = {
 #define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
 
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1),	/* Valleyview, Bay Trail */
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT),	/* Valleyview, Bay Trail */
 	ICPU(INTEL_FAM6_ATOM_AIRMONT),	/* Braswell, Cherry Trail */
 	{}
 };
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 06c31ec3cc70..9a8e286dd86f 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -54,7 +54,7 @@ static const struct always_present_id always_present_ids[] = {
 	 * Bay / Cherry Trail PWM directly poked by GPU driver in win10,
 	 * but Linux uses a separate PWM driver, harmless if not used.
 	 */
-	ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}),
+	ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT), {}),
 	ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
 	/*
 	 * The INT0002 device is necessary to clear wakeup interrupt sources
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2a99e2fd9412..49c0abf2d48f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1816,7 +1816,7 @@ static const struct pstate_funcs knl_funcs = {
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_SANDYBRIDGE, 		core_funcs),
 	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	silvermont_funcs),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT,	silvermont_funcs),
 	ICPU(INTEL_FAM6_IVYBRIDGE,		core_funcs),
 	ICPU(INTEL_FAM6_HASWELL_CORE,		core_funcs),
 	ICPU(INTEL_FAM6_BROADWELL_CORE,		core_funcs),
@@ -1833,7 +1833,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_funcs),
 	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_funcs),
 	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,       core_funcs),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS,     core_funcs),
 	ICPU(INTEL_FAM6_SKYLAKE_X,		core_funcs),
 	{}
 };
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index df28b65358d2..903a4f1fadcc 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1541,7 +1541,7 @@ static struct dunit_ops dnv_ops = {
 
 static const struct x86_cpu_id pnd2_cpuids[] = {
 	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops },
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X, 0, (kernel_ulong_t)&dnv_ops },
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 791b8a366e6e..8b5d85c91e9d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1073,14 +1073,14 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	INTEL_CPU_FAM6(WESTMERE,		idle_cpu_nehalem),
 	INTEL_CPU_FAM6(WESTMERE_EP,		idle_cpu_nehalem),
 	INTEL_CPU_FAM6(NEHALEM_EX,		idle_cpu_nehalem),
-	INTEL_CPU_FAM6(ATOM_PINEVIEW,		idle_cpu_atom),
-	INTEL_CPU_FAM6(ATOM_LINCROFT,		idle_cpu_lincroft),
+	INTEL_CPU_FAM6(ATOM_BONNELL,		idle_cpu_atom),
+	INTEL_CPU_FAM6(ATOM_BONNELL_MID,	idle_cpu_lincroft),
 	INTEL_CPU_FAM6(WESTMERE_EX,		idle_cpu_nehalem),
 	INTEL_CPU_FAM6(SANDYBRIDGE,		idle_cpu_snb),
 	INTEL_CPU_FAM6(SANDYBRIDGE_X,		idle_cpu_snb),
-	INTEL_CPU_FAM6(ATOM_CEDARVIEW,		idle_cpu_atom),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	idle_cpu_byt),
-	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		idle_cpu_tangier),
+	INTEL_CPU_FAM6(ATOM_SALTWELL,		idle_cpu_atom),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT,		idle_cpu_byt),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	idle_cpu_tangier),
 	INTEL_CPU_FAM6(ATOM_AIRMONT,		idle_cpu_cht),
 	INTEL_CPU_FAM6(IVYBRIDGE,		idle_cpu_ivb),
 	INTEL_CPU_FAM6(IVYBRIDGE_X,		idle_cpu_ivt),
@@ -1088,7 +1088,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	INTEL_CPU_FAM6(HASWELL_X,		idle_cpu_hsw),
 	INTEL_CPU_FAM6(HASWELL_ULT,		idle_cpu_hsw),
 	INTEL_CPU_FAM6(HASWELL_GT3E,		idle_cpu_hsw),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT2,	idle_cpu_avn),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT_X,	idle_cpu_avn),
 	INTEL_CPU_FAM6(BROADWELL_CORE,		idle_cpu_bdw),
 	INTEL_CPU_FAM6(BROADWELL_GT3E,		idle_cpu_bdw),
 	INTEL_CPU_FAM6(BROADWELL_X,		idle_cpu_bdw),
@@ -1101,8 +1101,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	INTEL_CPU_FAM6(XEON_PHI_KNL,		idle_cpu_knl),
 	INTEL_CPU_FAM6(XEON_PHI_KNM,		idle_cpu_knl),
 	INTEL_CPU_FAM6(ATOM_GOLDMONT,		idle_cpu_bxt),
-	INTEL_CPU_FAM6(ATOM_GEMINI_LAKE,	idle_cpu_bxt),
-	INTEL_CPU_FAM6(ATOM_DENVERTON,		idle_cpu_dnv),
+	INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS,	idle_cpu_bxt),
+	INTEL_CPU_FAM6(ATOM_GOLDMONT_X,		idle_cpu_dnv),
 	{}
 };
 
@@ -1319,7 +1319,7 @@ static void intel_idle_state_table_update(void)
 		ivt_idle_state_table_update();
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		bxt_idle_state_table_update();
 		break;
 	case INTEL_FAM6_SKYLAKE_DESKTOP:
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 82c9b9326e9e..057e24f4a620 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -247,7 +247,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 static bool sdhci_acpi_byt(void)
 {
 	static const struct x86_cpu_id byt[] = {
-		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
 		{}
 	};
 
diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c
index 314e135014dc..30fbe2ea6eab 100644
--- a/drivers/pci/pci-mid.c
+++ b/drivers/pci/pci-mid.c
@@ -62,8 +62,8 @@ static const struct pci_platform_pm_ops mid_pci_platform_pm = {
  * arch/x86/platform/intel-mid/pwr.c.
  */
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_PENWELL),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD),
+	ICPU(INTEL_FAM6_ATOM_SALTWELL_MID),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c
index a473dc51b18d..e89ad4964dc1 100644
--- a/drivers/platform/x86/intel_int0002_vgpio.c
+++ b/drivers/platform/x86/intel_int0002_vgpio.c
@@ -60,7 +60,7 @@ static const struct x86_cpu_id int0002_cpu_ids[] = {
 /*
  * Limit ourselves to Cherry Trail for now, until testing shows we
  * need to handle the INT0002 device on Baytrail too.
- *	ICPU(INTEL_FAM6_ATOM_SILVERMONT1),	 * Valleyview, Bay Trail *
+ *	ICPU(INTEL_FAM6_ATOM_SILVERMONT),	 * Valleyview, Bay Trail *
  */
 	ICPU(INTEL_FAM6_ATOM_AIRMONT),		/* Braswell, Cherry Trail */
 	{}
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index d79fbf924b13..5ad44204a9c3 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -125,8 +125,8 @@ static const struct mid_pb_ddata mrfld_ddata = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
 
 static const struct x86_cpu_id mid_pb_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_PENWELL,		mfld_ddata),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD,	mrfld_ddata),
+	ICPU(INTEL_FAM6_ATOM_SALTWELL_MID,		mfld_ddata),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,	mrfld_ddata),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c
index ffd0474b0531..cee08f236292 100644
--- a/drivers/platform/x86/intel_telemetry_debugfs.c
+++ b/drivers/platform/x86/intel_telemetry_debugfs.c
@@ -320,7 +320,7 @@ static struct telemetry_debugfs_conf telem_apl_debugfs_conf = {
 
 static const struct x86_cpu_id telemetry_debugfs_cpu_ids[] = {
 	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_debugfs_conf),
-	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, telem_apl_debugfs_conf),
+	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_apl_debugfs_conf),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c
index 2f889d6c270e..fcc6bee51a42 100644
--- a/drivers/platform/x86/intel_telemetry_pltdrv.c
+++ b/drivers/platform/x86/intel_telemetry_pltdrv.c
@@ -192,7 +192,7 @@ static struct telemetry_plt_config telem_glk_config = {
 
 static const struct x86_cpu_id telemetry_cpu_ids[] = {
 	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_config),
-	TELEM_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, telem_glk_config),
+	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_glk_config),
 	{}
 };
 
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index bb92874b1175..6cdb2c14eee4 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -1157,13 +1157,13 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	INTEL_CPU_FAM6(KABYLAKE_DESKTOP,	rapl_defaults_core),
 	INTEL_CPU_FAM6(CANNONLAKE_MOBILE,	rapl_defaults_core),
 
-	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	rapl_defaults_byt),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT,		rapl_defaults_byt),
 	INTEL_CPU_FAM6(ATOM_AIRMONT,		rapl_defaults_cht),
-	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		rapl_defaults_tng),
-	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		rapl_defaults_ann),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	rapl_defaults_tng),
+	INTEL_CPU_FAM6(ATOM_AIRMONT_MID,	rapl_defaults_ann),
 	INTEL_CPU_FAM6(ATOM_GOLDMONT,		rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_GEMINI_LAKE,	rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_DENVERTON,		rapl_defaults_core),
+	INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS,	rapl_defaults_core),
+	INTEL_CPU_FAM6(ATOM_GOLDMONT_X,		rapl_defaults_core),
 
 	INTEL_CPU_FAM6(XEON_PHI_KNL,		rapl_defaults_hsw_server),
 	INTEL_CPU_FAM6(XEON_PHI_KNM,		rapl_defaults_hsw_server),
diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c
index 1e47511a6bd5..d748527d7a38 100644
--- a/drivers/thermal/intel_soc_dts_thermal.c
+++ b/drivers/thermal/intel_soc_dts_thermal.c
@@ -45,7 +45,7 @@ static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
 }
 
 static const struct x86_cpu_id soc_thermal_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1, 0,
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0,
 		BYT_SOC_DTS_APIC_IRQ},
 	{}
 };
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d3cf407e374..4a9937076331 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,10 +459,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
+		 *
+		 * Note: the OVERWRITE records by themselves are not considered
+		 * useful, as they don't communicate any *new* information,
+		 * aside from the short-lived offset, that becomes history at
+		 * the next event sched-in and therefore isn't useful.
+		 * The userspace that needs to copy out AUX data in overwrite
+		 * mode should know to use user_page::aux_head for the actual
+		 * offset. So, from now on we don't output AUX records that
+		 * have *only* OVERWRITE flag set.
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
+			perf_event_aux_event(handle->event, aux_head, size,
+			                     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab257be4d924..90e98e233647 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -546,8 +546,14 @@ static void do_free_cleaned_kprobes(void)
 	struct optimized_kprobe *op, *tmp;
 
 	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
-		BUG_ON(!kprobe_unused(&op->kp));
 		list_del_init(&op->list);
+		if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) {
+			/*
+			 * This must not happen, but if there is a kprobe
+			 * still in use, keep it on kprobes hash list.
+			 */
+			continue;
+		}
 		free_aggr_kprobe(&op->kp);
 	}
 }
@@ -700,11 +706,11 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 }
 
 /* Cancel unoptimizing for reusing */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
+	int ret;
 
-	BUG_ON(!kprobe_unused(ap));
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
 	 * there is still a relative jump) and disabled.
@@ -714,8 +720,12 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	BUG_ON(!kprobe_optready(ap));
+	ret = kprobe_optready(ap);
+	if (ret)
+		return ret;
+
 	optimize_kprobe(ap);
+	return 0;
 }
 
 /* Remove optimized instructions */
@@ -940,11 +950,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt)
 #define kprobe_disarmed(p)			kprobe_disabled(p)
 #define wait_for_kprobe_optimizer()		do {} while (0)
 
-/* There should be no unused kprobes can be reused without optimization */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
 {
+	/*
+	 * If the optimized kprobe is NOT supported, the aggr kprobe is
+	 * released at the same time that the last aggregated kprobe is
+	 * unregistered.
+	 * Thus there should be no chance to reuse unused kprobe.
+	 */
 	printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
-	BUG_ON(kprobe_unused(ap));
+	return -EINVAL;
 }
 
 static void free_aggr_kprobe(struct kprobe *p)
@@ -1259,8 +1274,6 @@ NOKPROBE_SYMBOL(cleanup_rp_inst);
 /* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
-	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
-
 	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
@@ -1318,9 +1331,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 			goto out;
 		}
 		init_aggr_kprobe(ap, orig_p);
-	} else if (kprobe_unused(ap))
+	} else if (kprobe_unused(ap)) {
 		/* This probe is going to die. Rescue it */
-		reuse_unused_kprobe(ap);
+		ret = reuse_unused_kprobe(ap);
+		if (ret)
+			goto out;
+	}
 
 	if (kprobe_gone(ap)) {
 		/*
@@ -1704,7 +1720,6 @@ noclean:
 	return 0;
 
 disarmed:
-	BUG_ON(!kprobe_disarmed(ap));
 	hlist_del_rcu(&ap->hlist);
 	return 0;
 }
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index f8a68bdb3885..6af02bf879ac 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -787,7 +787,7 @@ static struct snd_soc_card byt_rt5651_card = {
 };
 
 static const struct x86_cpu_id baytrail_cpu_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, /* Valleyview */
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, /* Valleyview */
 	{}
 };
 
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index acc704bd3998..0b0ef3abc966 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -3,8 +3,6 @@
 #define _TOOLS_LINUX_BITOPS_H_
 
 #include <asm/types.h>
-#include <linux/compiler.h>
-
 #ifndef __WORDSIZE
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
 #endif
@@ -12,10 +10,9 @@
 #ifndef BITS_PER_LONG
 # define BITS_PER_LONG __WORDSIZE
 #endif
+#include <linux/bits.h>
+#include <linux/compiler.h>
 
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/tools/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h
index 7a8b61ad44cb..094649667bae 100644
--- a/tools/include/linux/err.h
+++ b/tools/include/linux/err.h
@@ -52,4 +52,11 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 	return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
 }
 
+static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	else
+		return 0;
+}
 #endif /* _LINUX_ERR_H */
diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c
index 9997a8805a82..e3d47b59b14d 100644
--- a/tools/lib/subcmd/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -23,6 +23,13 @@ void pager_init(const char *pager_env)
 	subcmd_config.pager_env = pager_env;
 }
 
+static const char *forced_pager;
+
+void force_pager(const char *pager)
+{
+	forced_pager = pager;
+}
+
 static void pager_preexec(void)
 {
 	/*
@@ -66,7 +73,9 @@ void setup_pager(void)
 	const char *pager = getenv(subcmd_config.pager_env);
 	struct winsize sz;
 
-	if (!isatty(1))
+	if (forced_pager)
+		pager = forced_pager;
+	if (!isatty(1) && !forced_pager)
 		return;
 	if (ioctl(1, TIOCGWINSZ, &sz) == 0)
 		pager_columns = sz.ws_col;
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
index f1a53cf29880..a818964693ab 100644
--- a/tools/lib/subcmd/pager.h
+++ b/tools/lib/subcmd/pager.h
@@ -7,5 +7,6 @@ extern void pager_init(const char *pager_env);
 extern void setup_pager(void);
 extern int pager_in_use(void);
 extern int pager_get_columns(void);
+extern void force_pager(const char *);
 
 #endif /* __SUBCMD_PAGER_H */
diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build
index c681d0575d16..ba54bfce0b0b 100644
--- a/tools/lib/traceevent/Build
+++ b/tools/lib/traceevent/Build
@@ -4,6 +4,8 @@ libtraceevent-y += trace-seq.o
 libtraceevent-y += parse-filter.o
 libtraceevent-y += parse-utils.o
 libtraceevent-y += kbuffer-parse.o
+libtraceevent-y += tep_strerror.o
+libtraceevent-y += event-parse-api.o
 
 plugin_jbd2-y         += plugin_jbd2.o
 plugin_hrtimer-y      += plugin_hrtimer.o
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
new file mode 100644
index 000000000000..61f7149085ee
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#include "event-parse.h"
+#include "event-parse-local.h"
+#include "event-utils.h"
+
+/**
+ * tep_get_first_event - returns the first event in the events array
+ * @tep: a handle to the tep_handle
+ *
+ * This returns pointer to the first element of the events array
+ * If @tep is NULL, NULL is returned.
+ */
+struct tep_event_format *tep_get_first_event(struct tep_handle *tep)
+{
+	if (tep && tep->events)
+		return tep->events[0];
+
+	return NULL;
+}
+
+/**
+ * tep_get_events_count - get the number of defined events
+ * @tep: a handle to the tep_handle
+ *
+ * This returns number of elements in event array
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_events_count(struct tep_handle *tep)
+{
+	if(tep)
+		return tep->nr_events;
+	return 0;
+}
+
+/**
+ * tep_set_flag - set event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag, or combination of flags to be set
+ * can be any combination from enum tep_flag
+ *
+ * This sets a flag or mbination of flags  from enum tep_flag
+  */
+void tep_set_flag(struct tep_handle *tep, int flag)
+{
+	if(tep)
+		tep->flags |= flag;
+}
+
+unsigned short __tep_data2host2(struct tep_handle *pevent, unsigned short data)
+{
+	unsigned short swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 8) |
+		((data & (0xffULL << 8)) >> 8);
+
+	return swap;
+}
+
+unsigned int __tep_data2host4(struct tep_handle *pevent, unsigned int data)
+{
+	unsigned int swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 24) |
+		((data & (0xffULL << 8)) << 8) |
+		((data & (0xffULL << 16)) >> 8) |
+		((data & (0xffULL << 24)) >> 24);
+
+	return swap;
+}
+
+unsigned long long
+__tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+{
+	unsigned long long swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 56) |
+		((data & (0xffULL << 8)) << 40) |
+		((data & (0xffULL << 16)) << 24) |
+		((data & (0xffULL << 24)) << 8) |
+		((data & (0xffULL << 32)) >> 8) |
+		((data & (0xffULL << 40)) >> 24) |
+		((data & (0xffULL << 48)) >> 40) |
+		((data & (0xffULL << 56)) >> 56);
+
+	return swap;
+}
+
+/**
+ * tep_get_header_page_size - get size of the header page
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns size of the header page
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->header_page_size_size;
+	return 0;
+}
+
+/**
+ * tep_get_cpus - get the number of CPUs
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the number of CPUs
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_cpus(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->cpus;
+	return 0;
+}
+
+/**
+ * tep_set_cpus - set the number of CPUs
+ * @pevent: a handle to the tep_handle
+ *
+ * This sets the number of CPUs
+ */
+void tep_set_cpus(struct tep_handle *pevent, int cpus)
+{
+	if(pevent)
+		pevent->cpus = cpus;
+}
+
+/**
+ * tep_get_long_size - get the size of a long integer on the current machine
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the size of a long integer on the current machine
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_long_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->long_size;
+	return 0;
+}
+
+/**
+ * tep_set_long_size - set the size of a long integer on the current machine
+ * @pevent: a handle to the tep_handle
+ * @size: size, in bytes, of a long integer
+ *
+ * This sets the size of a long integer on the current machine
+ */
+void tep_set_long_size(struct tep_handle *pevent, int long_size)
+{
+	if(pevent)
+		pevent->long_size = long_size;
+}
+
+/**
+ * tep_get_page_size - get the size of a memory page on the current machine
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the size of a memory page on the current machine
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_page_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->page_size;
+	return 0;
+}
+
+/**
+ * tep_set_page_size - set the size of a memory page on the current machine
+ * @pevent: a handle to the tep_handle
+ * @_page_size: size of a memory page, in bytes
+ *
+ * This sets the size of a memory page on the current machine
+ */
+void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+{
+	if(pevent)
+		pevent->page_size = _page_size;
+}
+
+/**
+ * tep_is_file_bigendian - get if the file is in big endian order
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns if the file is in big endian order
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_file_bigendian(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->file_bigendian;
+	return 0;
+}
+
+/**
+ * tep_set_file_bigendian - set if the file is in big endian order
+ * @pevent: a handle to the tep_handle
+ * @endian: non zero, if the file is in big endian order
+ *
+ * This sets if the file is in big endian order
+ */
+void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+{
+	if(pevent)
+		pevent->file_bigendian = endian;
+}
+
+/**
+ * tep_is_host_bigendian - get if the order of the current host is big endian
+ * @pevent: a handle to the tep_handle
+ *
+ * This gets if the order of the current host is big endian
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_host_bigendian(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->host_bigendian;
+	return 0;
+}
+
+/**
+ * tep_set_host_bigendian - set the order of the local host
+ * @pevent: a handle to the tep_handle
+ * @endian: non zero, if the local host has big endian order
+ *
+ * This sets the order of the local host
+ */
+void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+{
+	if(pevent)
+		pevent->host_bigendian = endian;
+}
+
+/**
+ * tep_is_latency_format - get if the latency output format is configured
+ * @pevent: a handle to the tep_handle
+ *
+ * This gets if the latency output format is configured
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_latency_format(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->latency_format;
+	return 0;
+}
+
+/**
+ * tep_set_latency_format - set the latency output format
+ * @pevent: a handle to the tep_handle
+ * @lat: non zero for latency output format
+ *
+ * This sets the latency output format
+  */
+void tep_set_latency_format(struct tep_handle *pevent, int lat)
+{
+	if(pevent)
+		pevent->latency_format = lat;
+}
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
new file mode 100644
index 000000000000..b9bddde577f8
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _PARSE_EVENTS_INT_H
+#define _PARSE_EVENTS_INT_H
+
+struct cmdline;
+struct cmdline_list;
+struct func_map;
+struct func_list;
+struct event_handler;
+struct func_resolver;
+
+struct tep_handle {
+	int ref_count;
+
+	int header_page_ts_offset;
+	int header_page_ts_size;
+	int header_page_size_offset;
+	int header_page_size_size;
+	int header_page_data_offset;
+	int header_page_data_size;
+	int header_page_overwrite;
+
+	enum tep_endian file_bigendian;
+	enum tep_endian host_bigendian;
+
+	int latency_format;
+
+	int old_format;
+
+	int cpus;
+	int long_size;
+	int page_size;
+
+	struct cmdline *cmdlines;
+	struct cmdline_list *cmdlist;
+	int cmdline_count;
+
+	struct func_map *func_map;
+	struct func_resolver *func_resolver;
+	struct func_list *funclist;
+	unsigned int func_count;
+
+	struct printk_map *printk_map;
+	struct printk_list *printklist;
+	unsigned int printk_count;
+
+
+	struct tep_event_format **events;
+	int nr_events;
+	struct tep_event_format **sort_events;
+	enum tep_event_sort_type last_type;
+
+	int type_offset;
+	int type_size;
+
+	int pid_offset;
+	int pid_size;
+
+	int pc_offset;
+	int pc_size;
+
+	int flags_offset;
+	int flags_size;
+
+	int ld_offset;
+	int ld_size;
+
+	int print_raw;
+
+	int test_filters;
+
+	int flags;
+
+	struct tep_format_field *bprint_ip_field;
+	struct tep_format_field *bprint_fmt_field;
+	struct tep_format_field *bprint_buf_field;
+
+	struct event_handler *handlers;
+	struct tep_function_handler *func_handlers;
+
+	/* cache */
+	struct tep_event_format *last_event;
+
+	char *trace_clock;
+};
+
+#endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index ce1e20227c64..3692f29fee46 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -18,12 +18,14 @@
 #include <errno.h>
 #include <stdint.h>
 #include <limits.h>
-#include <linux/string.h>
 #include <linux/time64.h>
 
 #include <netinet/in.h>
 #include "event-parse.h"
+
+#include "event-parse-local.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static const char *input_buf;
 static unsigned long long input_buf_ptr;
@@ -94,7 +96,7 @@ struct tep_function_handler {
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct event_format *event, struct print_arg *arg);
+		     struct tep_event_format *event, struct tep_print_arg *arg);
 
 static void free_func_handle(struct tep_function_handler *func);
 
@@ -117,9 +119,9 @@ void breakpoint(void)
 	x++;
 }
 
-struct print_arg *alloc_arg(void)
+struct tep_print_arg *alloc_arg(void)
 {
-	return calloc(1, sizeof(struct print_arg));
+	return calloc(1, sizeof(struct tep_print_arg));
 }
 
 struct cmdline {
@@ -737,16 +739,16 @@ void tep_print_printk(struct tep_handle *pevent)
 	}
 }
 
-static struct event_format *alloc_event(void)
+static struct tep_event_format *alloc_event(void)
 {
-	return calloc(1, sizeof(struct event_format));
+	return calloc(1, sizeof(struct tep_event_format));
 }
 
-static int add_event(struct tep_handle *pevent, struct event_format *event)
+static int add_event(struct tep_handle *pevent, struct tep_event_format *event)
 {
 	int i;
-	struct event_format **events = realloc(pevent->events, sizeof(event) *
-					       (pevent->nr_events + 1));
+	struct tep_event_format **events = realloc(pevent->events, sizeof(event) *
+						  (pevent->nr_events + 1));
 	if (!events)
 		return -1;
 
@@ -769,20 +771,20 @@ static int add_event(struct tep_handle *pevent, struct event_format *event)
 	return 0;
 }
 
-static int event_item_type(enum event_type type)
+static int event_item_type(enum tep_event_type type)
 {
 	switch (type) {
-	case EVENT_ITEM ... EVENT_SQUOTE:
+	case TEP_EVENT_ITEM ... TEP_EVENT_SQUOTE:
 		return 1;
-	case EVENT_ERROR ... EVENT_DELIM:
+	case TEP_EVENT_ERROR ... TEP_EVENT_DELIM:
 	default:
 		return 0;
 	}
 }
 
-static void free_flag_sym(struct print_flag_sym *fsym)
+static void free_flag_sym(struct tep_print_flag_sym *fsym)
 {
-	struct print_flag_sym *next;
+	struct tep_print_flag_sym *next;
 
 	while (fsym) {
 		next = fsym->next;
@@ -793,60 +795,60 @@ static void free_flag_sym(struct print_flag_sym *fsym)
 	}
 }
 
-static void free_arg(struct print_arg *arg)
+static void free_arg(struct tep_print_arg *arg)
 {
-	struct print_arg *farg;
+	struct tep_print_arg *farg;
 
 	if (!arg)
 		return;
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		free(arg->atom.atom);
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(arg->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		free_arg(arg->flags.field);
 		free(arg->flags.delim);
 		free_flag_sym(arg->flags.flags);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		free_arg(arg->symbol.field);
 		free_flag_sym(arg->symbol.symbols);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		free_arg(arg->hex.field);
 		free_arg(arg->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		free_arg(arg->int_array.field);
 		free_arg(arg->int_array.count);
 		free_arg(arg->int_array.el_size);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		free(arg->typecast.type);
 		free_arg(arg->typecast.item);
 		break;
-	case PRINT_STRING:
-	case PRINT_BSTRING:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
 		free(arg->string.string);
 		break;
-	case PRINT_BITMASK:
+	case TEP_PRINT_BITMASK:
 		free(arg->bitmask.bitmask);
 		break;
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
 		free(arg->dynarray.index);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		free(arg->op.op);
 		free_arg(arg->op.left);
 		free_arg(arg->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 		while (arg->func.args) {
 			farg = arg->func.args;
 			arg->func.args = farg->next;
@@ -854,7 +856,7 @@ static void free_arg(struct print_arg *arg)
 		}
 		break;
 
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 	default:
 		break;
 	}
@@ -862,24 +864,24 @@ static void free_arg(struct print_arg *arg)
 	free(arg);
 }
 
-static enum event_type get_type(int ch)
+static enum tep_event_type get_type(int ch)
 {
 	if (ch == '\n')
-		return EVENT_NEWLINE;
+		return TEP_EVENT_NEWLINE;
 	if (isspace(ch))
-		return EVENT_SPACE;
+		return TEP_EVENT_SPACE;
 	if (isalnum(ch) || ch == '_')
-		return EVENT_ITEM;
+		return TEP_EVENT_ITEM;
 	if (ch == '\'')
-		return EVENT_SQUOTE;
+		return TEP_EVENT_SQUOTE;
 	if (ch == '"')
-		return EVENT_DQUOTE;
+		return TEP_EVENT_DQUOTE;
 	if (!isprint(ch))
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 	if (ch == '(' || ch == ')' || ch == ',')
-		return EVENT_DELIM;
+		return TEP_EVENT_DELIM;
 
-	return EVENT_OP;
+	return TEP_EVENT_OP;
 }
 
 static int __read_char(void)
@@ -927,38 +929,38 @@ static int extend_token(char **tok, char *buf, int size)
 	return 0;
 }
 
-static enum event_type force_token(const char *str, char **tok);
+static enum tep_event_type force_token(const char *str, char **tok);
 
-static enum event_type __read_token(char **tok)
+static enum tep_event_type __read_token(char **tok)
 {
 	char buf[BUFSIZ];
 	int ch, last_ch, quote_ch, next_ch;
 	int i = 0;
 	int tok_size = 0;
-	enum event_type type;
+	enum tep_event_type type;
 
 	*tok = NULL;
 
 
 	ch = __read_char();
 	if (ch < 0)
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 
 	type = get_type(ch);
-	if (type == EVENT_NONE)
+	if (type == TEP_EVENT_NONE)
 		return type;
 
 	buf[i++] = ch;
 
 	switch (type) {
-	case EVENT_NEWLINE:
-	case EVENT_DELIM:
+	case TEP_EVENT_NEWLINE:
+	case TEP_EVENT_DELIM:
 		if (asprintf(tok, "%c", ch) < 0)
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 
 		return type;
 
-	case EVENT_OP:
+	case TEP_EVENT_OP:
 		switch (ch) {
 		case '-':
 			next_ch = __peek_char();
@@ -1001,8 +1003,8 @@ static enum event_type __read_token(char **tok)
 			buf[i++] = __read_char();
 		goto out;
 
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
+	case TEP_EVENT_DQUOTE:
+	case TEP_EVENT_SQUOTE:
 		/* don't keep quotes */
 		i--;
 		quote_ch = ch;
@@ -1014,7 +1016,7 @@ static enum event_type __read_token(char **tok)
 				tok_size += BUFSIZ;
 
 				if (extend_token(tok, buf, tok_size) < 0)
-					return EVENT_NONE;
+					return TEP_EVENT_NONE;
 				i = 0;
 			}
 			last_ch = ch;
@@ -1031,7 +1033,7 @@ static enum event_type __read_token(char **tok)
 		 * For strings (double quotes) check the next token.
 		 * If it is another string, concatinate the two.
 		 */
-		if (type == EVENT_DQUOTE) {
+		if (type == TEP_EVENT_DQUOTE) {
 			unsigned long long save_input_buf_ptr = input_buf_ptr;
 
 			do {
@@ -1044,8 +1046,8 @@ static enum event_type __read_token(char **tok)
 
 		goto out;
 
-	case EVENT_ERROR ... EVENT_SPACE:
-	case EVENT_ITEM:
+	case TEP_EVENT_ERROR ... TEP_EVENT_SPACE:
+	case TEP_EVENT_ITEM:
 	default:
 		break;
 	}
@@ -1056,7 +1058,7 @@ static enum event_type __read_token(char **tok)
 			tok_size += BUFSIZ;
 
 			if (extend_token(tok, buf, tok_size) < 0)
-				return EVENT_NONE;
+				return TEP_EVENT_NONE;
 			i = 0;
 		}
 		ch = __read_char();
@@ -1066,9 +1068,9 @@ static enum event_type __read_token(char **tok)
  out:
 	buf[i] = 0;
 	if (extend_token(tok, buf, tok_size + i + 1) < 0)
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 
-	if (type == EVENT_ITEM) {
+	if (type == TEP_EVENT_ITEM) {
 		/*
 		 * Older versions of the kernel has a bug that
 		 * creates invalid symbols and will break the mac80211
@@ -1095,12 +1097,12 @@ static enum event_type __read_token(char **tok)
 	return type;
 }
 
-static enum event_type force_token(const char *str, char **tok)
+static enum tep_event_type force_token(const char *str, char **tok)
 {
 	const char *save_input_buf;
 	unsigned long long save_input_buf_ptr;
 	unsigned long long save_input_buf_siz;
-	enum event_type type;
+	enum tep_event_type type;
 	
 	/* save off the current input pointers */
 	save_input_buf = input_buf;
@@ -1125,13 +1127,13 @@ static void free_token(char *tok)
 		free(tok);
 }
 
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	for (;;) {
 		type = __read_token(tok);
-		if (type != EVENT_SPACE)
+		if (type != TEP_EVENT_SPACE)
 			return type;
 
 		free_token(*tok);
@@ -1139,7 +1141,7 @@ static enum event_type read_token(char **tok)
 
 	/* not reached */
 	*tok = NULL;
-	return EVENT_NONE;
+	return TEP_EVENT_NONE;
 }
 
 /**
@@ -1151,7 +1153,7 @@ static enum event_type read_token(char **tok)
  *
  * Returns the token type.
  */
-enum event_type tep_read_token(char **tok)
+enum tep_event_type tep_read_token(char **tok)
 {
 	return read_token(tok);
 }
@@ -1166,13 +1168,13 @@ void tep_free_token(char *token)
 }
 
 /* no newline */
-static enum event_type read_token_item(char **tok)
+static enum tep_event_type read_token_item(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	for (;;) {
 		type = __read_token(tok);
-		if (type != EVENT_SPACE && type != EVENT_NEWLINE)
+		if (type != TEP_EVENT_SPACE && type != TEP_EVENT_NEWLINE)
 			return type;
 		free_token(*tok);
 		*tok = NULL;
@@ -1180,10 +1182,10 @@ static enum event_type read_token_item(char **tok)
 
 	/* not reached */
 	*tok = NULL;
-	return EVENT_NONE;
+	return TEP_EVENT_NONE;
 }
 
-static int test_type(enum event_type type, enum event_type expect)
+static int test_type(enum tep_event_type type, enum tep_event_type expect)
 {
 	if (type != expect) {
 		do_warning("Error: expected type %d but read %d",
@@ -1193,8 +1195,8 @@ static int test_type(enum event_type type, enum event_type expect)
 	return 0;
 }
 
-static int test_type_token(enum event_type type, const char *token,
-		    enum event_type expect, const char *expect_tok)
+static int test_type_token(enum tep_event_type type, const char *token,
+		    enum tep_event_type expect, const char *expect_tok)
 {
 	if (type != expect) {
 		do_warning("Error: expected type %d but read %d",
@@ -1210,9 +1212,9 @@ static int test_type_token(enum event_type type, const char *token,
 	return 0;
 }
 
-static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
+static int __read_expect_type(enum tep_event_type expect, char **tok, int newline_ok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	if (newline_ok)
 		type = read_token(tok);
@@ -1221,15 +1223,15 @@ static int __read_expect_type(enum event_type expect, char **tok, int newline_ok
 	return test_type(type, expect);
 }
 
-static int read_expect_type(enum event_type expect, char **tok)
+static int read_expect_type(enum tep_event_type expect, char **tok)
 {
 	return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, const char *str,
+static int __read_expected(enum tep_event_type expect, const char *str,
 			   int newline_ok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int ret;
 
@@ -1245,12 +1247,12 @@ static int __read_expected(enum event_type expect, const char *str,
 	return ret;
 }
 
-static int read_expected(enum event_type expect, const char *str)
+static int read_expected(enum tep_event_type expect, const char *str)
 {
 	return __read_expected(expect, str, 1);
 }
 
-static int read_expected_item(enum event_type expect, const char *str)
+static int read_expected_item(enum tep_event_type expect, const char *str)
 {
 	return __read_expected(expect, str, 0);
 }
@@ -1259,13 +1261,13 @@ static char *event_read_name(void)
 {
 	char *token;
 
-	if (read_expected(EVENT_ITEM, "name") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "name") < 0)
 		return NULL;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return NULL;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 
 	return token;
@@ -1280,13 +1282,13 @@ static int event_read_id(void)
 	char *token;
 	int id;
 
-	if (read_expected_item(EVENT_ITEM, "ID") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "ID") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 
 	id = strtoul(token, NULL, 0);
@@ -1298,9 +1300,9 @@ static int event_read_id(void)
 	return -1;
 }
 
-static int field_is_string(struct format_field *field)
+static int field_is_string(struct tep_format_field *field)
 {
-	if ((field->flags & FIELD_IS_ARRAY) &&
+	if ((field->flags & TEP_FIELD_IS_ARRAY) &&
 	    (strstr(field->type, "char") || strstr(field->type, "u8") ||
 	     strstr(field->type, "s8")))
 		return 1;
@@ -1308,7 +1310,7 @@ static int field_is_string(struct format_field *field)
 	return 0;
 }
 
-static int field_is_dynamic(struct format_field *field)
+static int field_is_dynamic(struct tep_format_field *field)
 {
 	if (strncmp(field->type, "__data_loc", 10) == 0)
 		return 1;
@@ -1316,7 +1318,7 @@ static int field_is_dynamic(struct format_field *field)
 	return 0;
 }
 
-static int field_is_long(struct format_field *field)
+static int field_is_long(struct tep_format_field *field)
 {
 	/* includes long long */
 	if (strstr(field->type, "long"))
@@ -1327,7 +1329,7 @@ static int field_is_long(struct format_field *field)
 
 static unsigned int type_size(const char *name)
 {
-	/* This covers all FIELD_IS_STRING types. */
+	/* This covers all TEP_FIELD_IS_STRING types. */
 	static struct {
 		const char *type;
 		unsigned int size;
@@ -1353,10 +1355,10 @@ static unsigned int type_size(const char *name)
 	return 0;
 }
 
-static int event_read_fields(struct event_format *event, struct format_field **fields)
+static int event_read_fields(struct tep_event_format *event, struct tep_format_field **fields)
 {
-	struct format_field *field = NULL;
-	enum event_type type;
+	struct tep_format_field *field = NULL;
+	enum tep_event_type type;
 	char *token;
 	char *last_token;
 	int count = 0;
@@ -1365,14 +1367,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		unsigned int size_dynamic = 0;
 
 		type = read_token(&token);
-		if (type == EVENT_NEWLINE) {
+		if (type == TEP_EVENT_NEWLINE) {
 			free_token(token);
 			return count;
 		}
 
 		count++;
 
-		if (test_type_token(type, token, EVENT_ITEM, "field"))
+		if (test_type_token(type, token, TEP_EVENT_ITEM, "field"))
 			goto fail;
 		free_token(token);
 
@@ -1381,17 +1383,17 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		 * The ftrace fields may still use the "special" name.
 		 * Just ignore it.
 		 */
-		if (event->flags & EVENT_FL_ISFTRACE &&
-		    type == EVENT_ITEM && strcmp(token, "special") == 0) {
+		if (event->flags & TEP_EVENT_FL_ISFTRACE &&
+		    type == TEP_EVENT_ITEM && strcmp(token, "special") == 0) {
 			free_token(token);
 			type = read_token(&token);
 		}
 
-		if (test_type_token(type, token, EVENT_OP, ":") < 0)
+		if (test_type_token(type, token, TEP_EVENT_OP, ":") < 0)
 			goto fail;
 
 		free_token(token);
-		if (read_expect_type(EVENT_ITEM, &token) < 0)
+		if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 			goto fail;
 
 		last_token = token;
@@ -1405,17 +1407,17 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		/* read the rest of the type */
 		for (;;) {
 			type = read_token(&token);
-			if (type == EVENT_ITEM ||
-			    (type == EVENT_OP && strcmp(token, "*") == 0) ||
+			if (type == TEP_EVENT_ITEM ||
+			    (type == TEP_EVENT_OP && strcmp(token, "*") == 0) ||
 			    /*
 			     * Some of the ftrace fields are broken and have
 			     * an illegal "." in them.
 			     */
-			    (event->flags & EVENT_FL_ISFTRACE &&
-			     type == EVENT_OP && strcmp(token, ".") == 0)) {
+			    (event->flags & TEP_EVENT_FL_ISFTRACE &&
+			     type == TEP_EVENT_OP && strcmp(token, ".") == 0)) {
 
 				if (strcmp(token, "*") == 0)
-					field->flags |= FIELD_IS_POINTER;
+					field->flags |= TEP_FIELD_IS_POINTER;
 
 				if (field->type) {
 					char *new_type;
@@ -1445,27 +1447,27 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		}
 		field->name = field->alias = last_token;
 
-		if (test_type(type, EVENT_OP))
+		if (test_type(type, TEP_EVENT_OP))
 			goto fail;
 
 		if (strcmp(token, "[") == 0) {
-			enum event_type last_type = type;
+			enum tep_event_type last_type = type;
 			char *brackets = token;
 			char *new_brackets;
 			int len;
 
-			field->flags |= FIELD_IS_ARRAY;
+			field->flags |= TEP_FIELD_IS_ARRAY;
 
 			type = read_token(&token);
 
-			if (type == EVENT_ITEM)
+			if (type == TEP_EVENT_ITEM)
 				field->arraylen = strtoul(token, NULL, 0);
 			else
 				field->arraylen = 0;
 
 		        while (strcmp(token, "]") != 0) {
-				if (last_type == EVENT_ITEM &&
-				    type == EVENT_ITEM)
+				if (last_type == TEP_EVENT_ITEM &&
+				    type == TEP_EVENT_ITEM)
 					len = 2;
 				else
 					len = 1;
@@ -1486,7 +1488,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				field->arraylen = strtoul(token, NULL, 0);
 				free_token(token);
 				type = read_token(&token);
-				if (type == EVENT_NONE) {
+				if (type == TEP_EVENT_NONE) {
 					do_warning_event(event, "failed to find token");
 					goto fail;
 				}
@@ -1509,7 +1511,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 			 * If the next token is not an OP, then it is of
 			 * the format: type [] item;
 			 */
-			if (type == EVENT_ITEM) {
+			if (type == TEP_EVENT_ITEM) {
 				char *new_type;
 				new_type = realloc(field->type,
 						   strlen(field->type) +
@@ -1543,79 +1545,79 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		}
 
 		if (field_is_string(field))
-			field->flags |= FIELD_IS_STRING;
+			field->flags |= TEP_FIELD_IS_STRING;
 		if (field_is_dynamic(field))
-			field->flags |= FIELD_IS_DYNAMIC;
+			field->flags |= TEP_FIELD_IS_DYNAMIC;
 		if (field_is_long(field))
-			field->flags |= FIELD_IS_LONG;
+			field->flags |= TEP_FIELD_IS_LONG;
 
-		if (test_type_token(type, token,  EVENT_OP, ";"))
+		if (test_type_token(type, token,  TEP_EVENT_OP, ";"))
 			goto fail;
 		free_token(token);
 
-		if (read_expected(EVENT_ITEM, "offset") < 0)
+		if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			goto fail_expect;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 		field->offset = strtoul(token, NULL, 0);
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_ITEM, "size") < 0)
+		if (read_expected(TEP_EVENT_ITEM, "size") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			goto fail_expect;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 		field->size = strtoul(token, NULL, 0);
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			goto fail_expect;
 
 		type = read_token(&token);
-		if (type != EVENT_NEWLINE) {
+		if (type != TEP_EVENT_NEWLINE) {
 			/* newer versions of the kernel have a "signed" type */
-			if (test_type_token(type, token, EVENT_ITEM, "signed"))
+			if (test_type_token(type, token, TEP_EVENT_ITEM, "signed"))
 				goto fail;
 
 			free_token(token);
 
-			if (read_expected(EVENT_OP, ":") < 0)
+			if (read_expected(TEP_EVENT_OP, ":") < 0)
 				goto fail_expect;
 
-			if (read_expect_type(EVENT_ITEM, &token))
+			if (read_expect_type(TEP_EVENT_ITEM, &token))
 				goto fail;
 
 			if (strtoul(token, NULL, 0))
-				field->flags |= FIELD_IS_SIGNED;
+				field->flags |= TEP_FIELD_IS_SIGNED;
 
 			free_token(token);
-			if (read_expected(EVENT_OP, ";") < 0)
+			if (read_expected(TEP_EVENT_OP, ";") < 0)
 				goto fail_expect;
 
-			if (read_expect_type(EVENT_NEWLINE, &token))
+			if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 				goto fail;
 		}
 
 		free_token(token);
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			if (field->arraylen)
 				field->elementsize = field->size / field->arraylen;
-			else if (field->flags & FIELD_IS_DYNAMIC)
+			else if (field->flags & TEP_FIELD_IS_DYNAMIC)
 				field->elementsize = size_dynamic;
-			else if (field->flags & FIELD_IS_STRING)
+			else if (field->flags & TEP_FIELD_IS_STRING)
 				field->elementsize = 1;
-			else if (field->flags & FIELD_IS_LONG)
+			else if (field->flags & TEP_FIELD_IS_LONG)
 				field->elementsize = event->pevent ?
 						     event->pevent->long_size :
 						     sizeof(long);
@@ -1640,18 +1642,18 @@ fail_expect:
 	return -1;
 }
 
-static int event_read_format(struct event_format *event)
+static int event_read_format(struct tep_event_format *event)
 {
 	char *token;
 	int ret;
 
-	if (read_expected_item(EVENT_ITEM, "format") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "format") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_NEWLINE, &token))
+	if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 		goto fail;
 	free_token(token);
 
@@ -1672,14 +1674,14 @@ static int event_read_format(struct event_format *event)
 	return -1;
 }
 
-static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
-		  char **tok, enum event_type type);
+static enum tep_event_type
+process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
+		  char **tok, enum tep_event_type type);
 
-static enum event_type
-process_arg(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_arg(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
 	type = read_token(&token);
@@ -1688,32 +1690,32 @@ process_arg(struct event_format *event, struct print_arg *arg, char **tok)
 	return process_arg_token(event, arg, tok, type);
 }
 
-static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok);
+static enum tep_event_type
+process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok);
 
 /*
  * For __print_symbolic() and __print_flags, we need to completely
  * evaluate the first argument, which defines what to print next.
  */
-static enum event_type
-process_field_arg(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_field_arg(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	type = process_arg(event, arg, tok);
 
-	while (type == EVENT_OP) {
+	while (type == TEP_EVENT_OP) {
 		type = process_op(event, arg, tok);
 	}
 
 	return type;
 }
 
-static enum event_type
-process_cond(struct event_format *event, struct print_arg *top, char **tok)
+static enum tep_event_type
+process_cond(struct tep_event_format *event, struct tep_print_arg *top, char **tok)
 {
-	struct print_arg *arg, *left, *right;
-	enum event_type type;
+	struct tep_print_arg *arg, *left, *right;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	arg = alloc_arg();
@@ -1728,7 +1730,7 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok)
 		goto out_free;
 	}
 
-	arg->type = PRINT_OP;
+	arg->type = TEP_PRINT_OP;
 	arg->op.left = left;
 	arg->op.right = right;
 
@@ -1736,16 +1738,16 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok)
 	type = process_arg(event, left, &token);
 
  again:
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
 	/* Handle other operations in the arguments */
-	if (type == EVENT_OP && strcmp(token, ":") != 0) {
+	if (type == TEP_EVENT_OP && strcmp(token, ":") != 0) {
 		type = process_op(event, left, &token);
 		goto again;
 	}
 
-	if (test_type_token(type, token, EVENT_OP, ":"))
+	if (test_type_token(type, token, TEP_EVENT_OP, ":"))
 		goto out_free;
 
 	arg->op.op = token;
@@ -1762,14 +1764,14 @@ out_free:
 	top->op.right = NULL;
 	free_token(token);
 	free_arg(arg);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_array(struct event_format *event, struct print_arg *top, char **tok)
+static enum tep_event_type
+process_array(struct tep_event_format *event, struct tep_print_arg *top, char **tok)
 {
-	struct print_arg *arg;
-	enum event_type type;
+	struct tep_print_arg *arg;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	arg = alloc_arg();
@@ -1777,12 +1779,12 @@ process_array(struct event_format *event, struct print_arg *top, char **tok)
 		do_warning_event(event, "%s: not enough memory!", __func__);
 		/* '*tok' is set to top->op.op.  No need to free. */
 		*tok = NULL;
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 
 	*tok = NULL;
 	type = process_arg(event, arg, &token);
-	if (test_type_token(type, token, EVENT_OP, "]"))
+	if (test_type_token(type, token, TEP_EVENT_OP, "]"))
 		goto out_free;
 
 	top->op.right = arg;
@@ -1796,7 +1798,7 @@ process_array(struct event_format *event, struct print_arg *top, char **tok)
 out_free:
 	free_token(token);
 	free_arg(arg);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 static int get_op_prio(char *op)
@@ -1854,11 +1856,11 @@ static int get_op_prio(char *op)
 	}
 }
 
-static int set_op_prio(struct print_arg *arg)
+static int set_op_prio(struct tep_print_arg *arg)
 {
 
 	/* single ops are the greatest */
-	if (!arg->op.left || arg->op.left->type == PRINT_NULL)
+	if (!arg->op.left || arg->op.left->type == TEP_PRINT_NULL)
 		arg->op.prio = 0;
 	else
 		arg->op.prio = get_op_prio(arg->op.op);
@@ -1867,17 +1869,17 @@ static int set_op_prio(struct print_arg *arg)
 }
 
 /* Note, *tok does not get freed, but will most likely be saved */
-static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *left, *right = NULL;
-	enum event_type type;
+	struct tep_print_arg *left, *right = NULL;
+	enum tep_event_type type;
 	char *token;
 
 	/* the op is passed in via tok */
 	token = *tok;
 
-	if (arg->type == PRINT_OP && !arg->op.left) {
+	if (arg->type == TEP_PRINT_OP && !arg->op.left) {
 		/* handle single op */
 		if (token[1]) {
 			do_warning_event(event, "bad op token %s", token);
@@ -1900,7 +1902,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		if (!left)
 			goto out_warn_free;
 
-		left->type = PRINT_NULL;
+		left->type = TEP_PRINT_NULL;
 		arg->op.left = left;
 
 		right = alloc_arg();
@@ -1922,7 +1924,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		/* copy the top arg to the left */
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 		arg->op.prio = 0;
@@ -1956,13 +1958,13 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		/* copy the top arg to the left */
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 		arg->op.right = NULL;
 
 		if (set_op_prio(arg) == -1) {
-			event->flags |= EVENT_FL_FAILED;
+			event->flags |= TEP_EVENT_FL_FAILED;
 			/* arg->op.op (= token) will be freed at out_free */
 			arg->op.op = NULL;
 			goto out_free;
@@ -1973,10 +1975,10 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 		/* could just be a type pointer */
 		if ((strcmp(arg->op.op, "*") == 0) &&
-		    type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
+		    type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
 			char *new_atom;
 
-			if (left->type != PRINT_ATOM) {
+			if (left->type != TEP_PRINT_ATOM) {
 				do_warning_event(event, "bad pointer type");
 				goto out_free;
 			}
@@ -1999,16 +2001,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 			goto out_warn_free;
 
 		type = process_arg_token(event, right, tok, type);
-		if (type == EVENT_ERROR) {
+		if (type == TEP_EVENT_ERROR) {
 			free_arg(right);
 			/* token was freed in process_arg_token() via *tok */
 			token = NULL;
 			goto out_free;
 		}
 
-		if (right->type == PRINT_OP &&
+		if (right->type == TEP_PRINT_OP &&
 		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
-			struct print_arg tmp;
+			struct tep_print_arg tmp;
 
 			/* rotate ops according to the priority */
 			arg->op.right = right->op.left;
@@ -2030,7 +2032,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 
@@ -2041,12 +2043,12 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 	} else {
 		do_warning_event(event, "unknown op '%s'", token);
-		event->flags |= EVENT_FL_FAILED;
+		event->flags |= TEP_EVENT_FL_FAILED;
 		/* the arg is now the left side */
 		goto out_free;
 	}
 
-	if (type == EVENT_OP && strcmp(*tok, ":") != 0) {
+	if (type == TEP_EVENT_OP && strcmp(*tok, ":") != 0) {
 		int prio;
 
 		/* higher prios need to be closer to the root */
@@ -2065,34 +2067,34 @@ out_warn_free:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
+static enum tep_event_type
+process_entry(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
 	      char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *field;
 	char *token;
 
-	if (read_expected(EVENT_OP, "->") < 0)
+	if (read_expected(TEP_EVENT_OP, "->") < 0)
 		goto out_err;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 	field = token;
 
-	arg->type = PRINT_FIELD;
+	arg->type = TEP_PRINT_FIELD;
 	arg->field.name = field;
 
 	if (is_flag_field) {
 		arg->field.field = tep_find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_FLAG;
+		arg->field.field->flags |= TEP_FIELD_IS_FLAG;
 		is_flag_field = 0;
 	} else if (is_symbolic_field) {
 		arg->field.field = tep_find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_SYMBOLIC;
+		arg->field.field->flags |= TEP_FIELD_IS_SYMBOLIC;
 		is_symbolic_field = 0;
 	}
 
@@ -2105,14 +2107,14 @@ process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static int alloc_and_process_delim(struct event_format *event, char *next_token,
-				   struct print_arg **print_arg)
+static int alloc_and_process_delim(struct tep_event_format *event, char *next_token,
+				   struct tep_print_arg **print_arg)
 {
-	struct print_arg *field;
-	enum event_type type;
+	struct tep_print_arg *field;
+	enum tep_event_type type;
 	char *token;
 	int ret = 0;
 
@@ -2125,7 +2127,7 @@ static int alloc_and_process_delim(struct event_format *event, char *next_token,
 
 	type = process_arg(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, next_token)) {
+	if (test_type_token(type, token, TEP_EVENT_DELIM, next_token)) {
 		errno = EINVAL;
 		ret = -1;
 		free_arg(field);
@@ -2140,7 +2142,7 @@ out_free_token:
 	return ret;
 }
 
-static char *arg_eval (struct print_arg *arg);
+static char *arg_eval (struct tep_print_arg *arg);
 
 static unsigned long long
 eval_type_str(unsigned long long val, const char *type, int pointer)
@@ -2237,9 +2239,9 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
  * Try to figure out the type.
  */
 static unsigned long long
-eval_type(unsigned long long val, struct print_arg *arg, int pointer)
+eval_type(unsigned long long val, struct tep_print_arg *arg, int pointer)
 {
-	if (arg->type != PRINT_TYPE) {
+	if (arg->type != TEP_PRINT_TYPE) {
 		do_warning("expected type argument");
 		return 0;
 	}
@@ -2247,22 +2249,22 @@ eval_type(unsigned long long val, struct print_arg *arg, int pointer)
 	return eval_type_str(val, arg->typecast.type, pointer);
 }
 
-static int arg_num_eval(struct print_arg *arg, long long *val)
+static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 {
 	long long left, right;
 	int ret = 1;
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		*val = strtoll(arg->atom.atom, NULL, 0);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		ret = arg_num_eval(arg->typecast.item, val);
 		if (!ret)
 			break;
 		*val = eval_type(*val, arg, 0);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		switch (arg->op.op[0]) {
 		case '|':
 			ret = arg_num_eval(arg->op.left, &left);
@@ -2365,7 +2367,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 			break;
 		case '-':
 			/* check for negative */
-			if (arg->op.left->type == PRINT_NULL)
+			if (arg->op.left->type == TEP_PRINT_NULL)
 				left = 0;
 			else
 				ret = arg_num_eval(arg->op.left, &left);
@@ -2377,7 +2379,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 			*val = left - right;
 			break;
 		case '+':
-			if (arg->op.left->type == PRINT_NULL)
+			if (arg->op.left->type == TEP_PRINT_NULL)
 				left = 0;
 			else
 				ret = arg_num_eval(arg->op.left, &left);
@@ -2400,11 +2402,11 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 		}
 		break;
 
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_NULL:
+	case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		ret = 0;
@@ -2413,27 +2415,27 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 	return ret;
 }
 
-static char *arg_eval (struct print_arg *arg)
+static char *arg_eval (struct tep_print_arg *arg)
 {
 	long long val;
 	static char buf[20];
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		return arg->atom.atom;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		return arg_eval(arg->typecast.item);
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (!arg_num_eval(arg, &val))
 			break;
 		sprintf(buf, "%lld", val);
 		return buf;
 
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_NULL:
+	case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		break;
@@ -2442,19 +2444,19 @@ static char *arg_eval (struct print_arg *arg)
 	return NULL;
 }
 
-static enum event_type
-process_fields(struct event_format *event, struct print_flag_sym **list, char **tok)
+static enum tep_event_type
+process_fields(struct tep_event_format *event, struct tep_print_flag_sym **list, char **tok)
 {
-	enum event_type type;
-	struct print_arg *arg = NULL;
-	struct print_flag_sym *field;
+	enum tep_event_type type;
+	struct tep_print_arg *arg = NULL;
+	struct tep_print_flag_sym *field;
 	char *token = *tok;
 	char *value;
 
 	do {
 		free_token(token);
 		type = read_token_item(&token);
-		if (test_type_token(type, token, EVENT_OP, "{"))
+		if (test_type_token(type, token, TEP_EVENT_OP, "{"))
 			break;
 
 		arg = alloc_arg();
@@ -2464,13 +2466,13 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 		free_token(token);
 		type = process_arg(event, arg, &token);
 
-		if (type == EVENT_OP)
+		if (type == TEP_EVENT_OP)
 			type = process_op(event, arg, &token);
 
-		if (type == EVENT_ERROR)
+		if (type == TEP_EVENT_ERROR)
 			goto out_free;
 
-		if (test_type_token(type, token, EVENT_DELIM, ","))
+		if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 			goto out_free;
 
 		field = calloc(1, sizeof(*field));
@@ -2491,7 +2493,7 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
-		if (test_type_token(type, token, EVENT_OP, "}"))
+		if (test_type_token(type, token, TEP_EVENT_OP, "}"))
 			goto out_free_field;
 
 		value = arg_eval(arg);
@@ -2508,7 +2510,7 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 
 		free_token(token);
 		type = read_token_item(&token);
-	} while (type == EVENT_DELIM && strcmp(token, ",") == 0);
+	} while (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0);
 
 	*tok = token;
 	return type;
@@ -2520,18 +2522,18 @@ out_free:
 	free_token(token);
 	*tok = NULL;
 
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_flags(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_flags(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *field;
-	enum event_type type;
+	struct tep_print_arg *field;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_FLAGS;
+	arg->type = TEP_PRINT_FLAGS;
 
 	field = alloc_arg();
 	if (!field) {
@@ -2542,10 +2544,10 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 	type = process_field_arg(event, field, &token);
 
 	/* Handle operations in the first argument */
-	while (type == EVENT_OP)
+	while (type == TEP_EVENT_OP)
 		type = process_op(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free_field;
 	free_token(token);
 
@@ -2557,11 +2559,11 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 		type = read_token_item(&token);
 	}
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free;
 
 	type = process_fields(event, &arg->flags.flags, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2573,18 +2575,18 @@ out_free_field:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_symbols(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *field;
-	enum event_type type;
+	struct tep_print_arg *field;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_SYMBOL;
+	arg->type = TEP_PRINT_SYMBOL;
 
 	field = alloc_arg();
 	if (!field) {
@@ -2594,13 +2596,13 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 
 	type = process_field_arg(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free_field;
 
 	arg->symbol.field = field;
 
 	type = process_fields(event, &arg->symbol.symbols, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2612,12 +2614,12 @@ out_free_field:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_hex_common(struct event_format *event, struct print_arg *arg,
-		   char **tok, enum print_arg_type type)
+static enum tep_event_type
+process_hex_common(struct tep_event_format *event, struct tep_print_arg *arg,
+		   char **tok, enum tep_print_arg_type type)
 {
 	memset(arg, 0, sizeof(*arg));
 	arg->type = type;
@@ -2635,27 +2637,27 @@ free_field:
 	arg->hex.field = NULL;
 out:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_hex(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	return process_hex_common(event, arg, tok, PRINT_HEX);
+	return process_hex_common(event, arg, tok, TEP_PRINT_HEX);
 }
 
-static enum event_type
-process_hex_str(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_hex_str(struct tep_event_format *event, struct tep_print_arg *arg,
 		char **tok)
 {
-	return process_hex_common(event, arg, tok, PRINT_HEX_STR);
+	return process_hex_common(event, arg, tok, TEP_PRINT_HEX_STR);
 }
 
-static enum event_type
-process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_int_array(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_INT_ARRAY;
+	arg->type = TEP_PRINT_INT_ARRAY;
 
 	if (alloc_and_process_delim(event, ",", &arg->int_array.field))
 		goto out;
@@ -2676,18 +2678,18 @@ free_field:
 	arg->int_array.field = NULL;
 out:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_dynamic_array(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct format_field *field;
-	enum event_type type;
+	struct tep_format_field *field;
+	enum tep_event_type type;
 	char *token;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_DYNAMIC_ARRAY;
+	arg->type = TEP_PRINT_DYNAMIC_ARRAY;
 
 	/*
 	 * The item within the parenthesis is another field that holds
@@ -2695,7 +2697,7 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 	 */
 	type = read_token(&token);
 	*tok = token;
-	if (type != EVENT_ITEM)
+	if (type != TEP_EVENT_ITEM)
 		goto out_free;
 
 	/* Find the field */
@@ -2707,13 +2709,13 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 	arg->dynarray.field = field;
 	arg->dynarray.index = 0;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_free;
 
 	free_token(token);
 	type = read_token_item(&token);
 	*tok = token;
-	if (type != EVENT_OP || strcmp(token, "[") != 0)
+	if (type != TEP_EVENT_OP || strcmp(token, "[") != 0)
 		return type;
 
 	free_token(token);
@@ -2721,14 +2723,14 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 	if (!arg) {
 		do_warning_event(event, "%s: not enough memory!", __func__);
 		*tok = NULL;
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 
 	type = process_arg(event, arg, &token);
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free_arg;
 
-	if (!test_type_token(type, token, EVENT_OP, "]"))
+	if (!test_type_token(type, token, TEP_EVENT_OP, "]"))
 		goto out_free_arg;
 
 	free_token(token);
@@ -2740,21 +2742,21 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
  out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_dynamic_array_len(struct tep_event_format *event, struct tep_print_arg *arg,
 			  char **tok)
 {
-	struct format_field *field;
-	enum event_type type;
+	struct tep_format_field *field;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_DYNAMIC_ARRAY_LEN;
+	arg->type = TEP_PRINT_DYNAMIC_ARRAY_LEN;
 
 	/* Find the field */
 	field = tep_find_field(event, token);
@@ -2764,7 +2766,7 @@ process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
 	arg->dynarray.field = field;
 	arg->dynarray.index = 0;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2776,28 +2778,28 @@ process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_paren(struct event_format *event, struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_paren(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *item_arg;
-	enum event_type type;
+	struct tep_print_arg *item_arg;
+	enum tep_event_type type;
 	char *token;
 
 	type = process_arg(event, arg, &token);
 
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
-	if (type == EVENT_OP)
+	if (type == TEP_EVENT_OP)
 		type = process_op(event, arg, &token);
 
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2808,13 +2810,13 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 	 * this was a typecast.
 	 */
 	if (event_item_type(type) ||
-	    (type == EVENT_DELIM && strcmp(token, "(") == 0)) {
+	    (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0)) {
 
 		/* make this a typecast and contine */
 
 		/* prevous must be an atom */
-		if (arg->type != PRINT_ATOM) {
-			do_warning_event(event, "previous needed to be PRINT_ATOM");
+		if (arg->type != TEP_PRINT_ATOM) {
+			do_warning_event(event, "previous needed to be TEP_PRINT_ATOM");
 			goto out_free;
 		}
 
@@ -2825,7 +2827,7 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 			goto out_free;
 		}
 
-		arg->type = PRINT_TYPE;
+		arg->type = TEP_PRINT_TYPE;
 		arg->typecast.type = arg->atom.atom;
 		arg->typecast.item = item_arg;
 		type = process_arg_token(event, item_arg, &token, type);
@@ -2838,25 +2840,25 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
  out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 
-static enum event_type
-process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
+static enum tep_event_type
+process_str(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
 	    char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_STRING;
+	arg->type = TEP_PRINT_STRING;
 	arg->string.string = token;
 	arg->string.offset = -1;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2868,24 +2870,24 @@ process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
-	    char **tok)
+static enum tep_event_type
+process_bitmask(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
+		char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_BITMASK;
+	arg->type = TEP_PRINT_BITMASK;
 	arg->bitmask.bitmask = token;
 	arg->bitmask.offset = -1;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2897,7 +2899,7 @@ process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 static struct tep_function_handler *
@@ -2932,17 +2934,17 @@ static void remove_func_handler(struct tep_handle *pevent, char *func_name)
 	}
 }
 
-static enum event_type
-process_func_handler(struct event_format *event, struct tep_function_handler *func,
-		     struct print_arg *arg, char **tok)
+static enum tep_event_type
+process_func_handler(struct tep_event_format *event, struct tep_function_handler *func,
+		     struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg **next_arg;
-	struct print_arg *farg;
-	enum event_type type;
+	struct tep_print_arg **next_arg;
+	struct tep_print_arg *farg;
+	enum tep_event_type type;
 	char *token;
 	int i;
 
-	arg->type = PRINT_FUNC;
+	arg->type = TEP_PRINT_FUNC;
 	arg->func.func = func;
 
 	*tok = NULL;
@@ -2953,12 +2955,12 @@ process_func_handler(struct event_format *event, struct tep_function_handler *fu
 		if (!farg) {
 			do_warning_event(event, "%s: not enough memory!",
 					 __func__);
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 		}
 
 		type = process_arg(event, farg, &token);
 		if (i < (func->nr_args - 1)) {
-			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+			if (type != TEP_EVENT_DELIM || strcmp(token, ",") != 0) {
 				do_warning_event(event,
 					"Error: function '%s()' expects %d arguments but event %s only uses %d",
 					func->name, func->nr_args,
@@ -2966,7 +2968,7 @@ process_func_handler(struct event_format *event, struct tep_function_handler *fu
 				goto err;
 			}
 		} else {
-			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+			if (type != TEP_EVENT_DELIM || strcmp(token, ")") != 0) {
 				do_warning_event(event,
 					"Error: function '%s()' only expects %d arguments but event %s has more",
 					func->name, func->nr_args, event->name);
@@ -2987,11 +2989,11 @@ process_func_handler(struct event_format *event, struct tep_function_handler *fu
 err:
 	free_arg(farg);
 	free_token(token);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_function(struct event_format *event, struct print_arg *arg,
+static enum tep_event_type
+process_function(struct tep_event_format *event, struct tep_print_arg *arg,
 		 char *token, char **tok)
 {
 	struct tep_function_handler *func;
@@ -3043,12 +3045,12 @@ process_function(struct event_format *event, struct print_arg *arg,
 
 	do_warning_event(event, "function %s not defined", token);
 	free_token(token);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
-		  char **tok, enum event_type type)
+static enum tep_event_type
+process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
+		  char **tok, enum tep_event_type type)
 {
 	char *token;
 	char *atom;
@@ -3056,7 +3058,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 	token = *tok;
 
 	switch (type) {
-	case EVENT_ITEM:
+	case TEP_EVENT_ITEM:
 		if (strcmp(token, "REC") == 0) {
 			free_token(token);
 			type = process_entry(event, arg, &token);
@@ -3070,7 +3072,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 		 * If the next token is a parenthesis, then this
 		 * is a function.
 		 */
-		if (type == EVENT_DELIM && strcmp(token, "(") == 0) {
+		if (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0) {
 			free_token(token);
 			token = NULL;
 			/* this will free atom. */
@@ -3078,7 +3080,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 			break;
 		}
 		/* atoms can be more than one token long */
-		while (type == EVENT_ITEM) {
+		while (type == TEP_EVENT_ITEM) {
 			char *new_atom;
 			new_atom = realloc(atom,
 					   strlen(atom) + strlen(token) + 2);
@@ -3086,7 +3088,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 				free(atom);
 				*tok = NULL;
 				free_token(token);
-				return EVENT_ERROR;
+				return TEP_EVENT_ERROR;
 			}
 			atom = new_atom;
 			strcat(atom, " ");
@@ -3095,55 +3097,55 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 			type = read_token_item(&token);
 		}
 
-		arg->type = PRINT_ATOM;
+		arg->type = TEP_PRINT_ATOM;
 		arg->atom.atom = atom;
 		break;
 
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
-		arg->type = PRINT_ATOM;
+	case TEP_EVENT_DQUOTE:
+	case TEP_EVENT_SQUOTE:
+		arg->type = TEP_PRINT_ATOM;
 		arg->atom.atom = token;
 		type = read_token_item(&token);
 		break;
-	case EVENT_DELIM:
+	case TEP_EVENT_DELIM:
 		if (strcmp(token, "(") == 0) {
 			free_token(token);
 			type = process_paren(event, arg, &token);
 			break;
 		}
-	case EVENT_OP:
+	case TEP_EVENT_OP:
 		/* handle single ops */
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = NULL;
 		type = process_op(event, arg, &token);
 
 		/* On error, the op is freed */
-		if (type == EVENT_ERROR)
+		if (type == TEP_EVENT_ERROR)
 			arg->op.op = NULL;
 
 		/* return error type if errored */
 		break;
 
-	case EVENT_ERROR ... EVENT_NEWLINE:
+	case TEP_EVENT_ERROR ... TEP_EVENT_NEWLINE:
 	default:
 		do_warning_event(event, "unexpected type %d", type);
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 	*tok = token;
 
 	return type;
 }
 
-static int event_read_print_args(struct event_format *event, struct print_arg **list)
+static int event_read_print_args(struct tep_event_format *event, struct tep_print_arg **list)
 {
-	enum event_type type = EVENT_ERROR;
-	struct print_arg *arg;
+	enum tep_event_type type = TEP_EVENT_ERROR;
+	struct tep_print_arg *arg;
 	char *token;
 	int args = 0;
 
 	do {
-		if (type == EVENT_NEWLINE) {
+		if (type == TEP_EVENT_NEWLINE) {
 			type = read_token_item(&token);
 			continue;
 		}
@@ -3157,7 +3159,7 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 
 		type = process_arg(event, arg, &token);
 
-		if (type == EVENT_ERROR) {
+		if (type == TEP_EVENT_ERROR) {
 			free_token(token);
 			free_arg(arg);
 			return -1;
@@ -3166,10 +3168,10 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 		*list = arg;
 		args++;
 
-		if (type == EVENT_OP) {
+		if (type == TEP_EVENT_OP) {
 			type = process_op(event, arg, &token);
 			free_token(token);
-			if (type == EVENT_ERROR) {
+			if (type == TEP_EVENT_ERROR) {
 				*list = NULL;
 				free_arg(arg);
 				return -1;
@@ -3178,37 +3180,37 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 			continue;
 		}
 
-		if (type == EVENT_DELIM && strcmp(token, ",") == 0) {
+		if (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0) {
 			free_token(token);
 			*list = arg;
 			list = &arg->next;
 			continue;
 		}
 		break;
-	} while (type != EVENT_NONE);
+	} while (type != TEP_EVENT_NONE);
 
-	if (type != EVENT_NONE && type != EVENT_ERROR)
+	if (type != TEP_EVENT_NONE && type != TEP_EVENT_ERROR)
 		free_token(token);
 
 	return args;
 }
 
-static int event_read_print(struct event_format *event)
+static int event_read_print(struct tep_event_format *event)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int ret;
 
-	if (read_expected_item(EVENT_ITEM, "print") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "print") < 0)
 		return -1;
 
-	if (read_expected(EVENT_ITEM, "fmt") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "fmt") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_DQUOTE, &token) < 0)
+	if (read_expect_type(TEP_EVENT_DQUOTE, &token) < 0)
 		goto fail;
 
  concat:
@@ -3218,11 +3220,11 @@ static int event_read_print(struct event_format *event)
 	/* ok to have no arg */
 	type = read_token_item(&token);
 
-	if (type == EVENT_NONE)
+	if (type == TEP_EVENT_NONE)
 		return 0;
 
 	/* Handle concatenation of print lines */
-	if (type == EVENT_DQUOTE) {
+	if (type == TEP_EVENT_DQUOTE) {
 		char *cat;
 
 		if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0)
@@ -3234,7 +3236,7 @@ static int event_read_print(struct event_format *event)
 		goto concat;
 	}
 			     
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto fail;
 
 	free_token(token);
@@ -3258,10 +3260,10 @@ static int event_read_print(struct event_format *event)
  * Returns a common field from the event by the given @name.
  * This only searchs the common fields and not all field.
  */
-struct format_field *
-tep_find_common_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_common_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	for (format = event->format.common_fields;
 	     format; format = format->next) {
@@ -3280,10 +3282,10 @@ tep_find_common_field(struct event_format *event, const char *name)
  * Returns a non-common field by the given @name.
  * This does not search common fields.
  */
-struct format_field *
-tep_find_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	for (format = event->format.fields;
 	     format; format = format->next) {
@@ -3303,10 +3305,10 @@ tep_find_field(struct event_format *event, const char *name)
  * This searchs the common field names first, then
  * the non-common ones if a common one was not found.
  */
-struct format_field *
-tep_find_any_field(struct event_format *event, const char *name)
+struct tep_format_field *
+tep_find_any_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	format = tep_find_common_field(event, name);
 	if (format)
@@ -3330,11 +3332,11 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
 	case 1:
 		return *(unsigned char *)ptr;
 	case 2:
-		return data2host2(pevent, ptr);
+		return tep_data2host2(pevent, ptr);
 	case 4:
-		return data2host4(pevent, ptr);
+		return tep_data2host4(pevent, ptr);
 	case 8:
-		return data2host8(pevent, ptr);
+		return tep_data2host8(pevent, ptr);
 	default:
 		/* BUG! */
 		return 0;
@@ -3352,7 +3354,7 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
  *
  * Returns 0 on success, -1 otherwise.
  */
-int tep_read_number_field(struct format_field *field, const void *data,
+int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value)
 {
 	if (!field)
@@ -3373,8 +3375,8 @@ int tep_read_number_field(struct format_field *field, const void *data,
 static int get_common_info(struct tep_handle *pevent,
 			   const char *type, int *offset, int *size)
 {
-	struct event_format *event;
-	struct format_field *field;
+	struct tep_event_format *event;
+	struct tep_format_field *field;
 
 	/*
 	 * All events should have the same common elements.
@@ -3460,11 +3462,11 @@ static int events_id_cmp(const void *a, const void *b);
  *
  * Returns an event that has a given @id.
  */
-struct event_format *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id)
 {
-	struct event_format **eventptr;
-	struct event_format key;
-	struct event_format *pkey = &key;
+	struct tep_event_format **eventptr;
+	struct tep_event_format key;
+	struct tep_event_format *pkey = &key;
 
 	/* Check cache first */
 	if (pevent->last_event && pevent->last_event->id == id)
@@ -3492,11 +3494,11 @@ struct event_format *tep_find_event(struct tep_handle *pevent, int id)
  * This returns an event with a given @name and under the system
  * @sys. If @sys is NULL the first event with @name is returned.
  */
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_name(struct tep_handle *pevent,
 		       const char *sys, const char *name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	int i;
 
 	if (pevent->last_event &&
@@ -3521,23 +3523,23 @@ tep_find_event_by_name(struct tep_handle *pevent,
 }
 
 static unsigned long long
-eval_num_arg(void *data, int size, struct event_format *event, struct print_arg *arg)
+eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long val = 0;
 	unsigned long long left, right;
-	struct print_arg *typearg = NULL;
-	struct print_arg *larg;
+	struct tep_print_arg *typearg = NULL;
+	struct tep_print_arg *larg;
 	unsigned long offset;
 	unsigned int field_size;
 
 	switch (arg->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		/* ?? */
 		return 0;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		return strtoull(arg->atom.atom, NULL, 0);
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		if (!arg->field.field) {
 			arg->field.field = tep_find_any_field(event, arg->field.name);
 			if (!arg->field.field)
@@ -3548,27 +3550,27 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		val = tep_read_number(pevent, data + arg->field.field->offset,
 				      arg->field.field->size);
 		break;
-	case PRINT_FLAGS:
-	case PRINT_SYMBOL:
-	case PRINT_INT_ARRAY:
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_FLAGS:
+	case TEP_PRINT_SYMBOL:
+	case TEP_PRINT_INT_ARRAY:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		val = eval_num_arg(data, size, event, arg->typecast.item);
 		return eval_type(val, arg, 0);
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 		return 0;
-	case PRINT_FUNC: {
+	case TEP_PRINT_FUNC: {
 		struct trace_seq s;
 		trace_seq_init(&s);
 		val = process_defined_func(&s, data, size, event, arg);
 		trace_seq_destroy(&s);
 		return val;
 	}
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(arg->op.op, "[") == 0) {
 			/*
 			 * Arrays are special, since we don't want
@@ -3578,7 +3580,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 
 			/* handle typecasts */
 			larg = arg->op.left;
-			while (larg->type == PRINT_TYPE) {
+			while (larg->type == TEP_PRINT_TYPE) {
 				if (!typearg)
 					typearg = larg;
 				larg = larg->typecast.item;
@@ -3588,7 +3590,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 			field_size = pevent->long_size;
 
 			switch (larg->type) {
-			case PRINT_DYNAMIC_ARRAY:
+			case TEP_PRINT_DYNAMIC_ARRAY:
 				offset = tep_read_number(pevent,
 						   data + larg->dynarray.field->offset,
 						   larg->dynarray.field->size);
@@ -3602,7 +3604,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 				offset &= 0xffff;
 				offset += right;
 				break;
-			case PRINT_FIELD:
+			case TEP_PRINT_FIELD:
 				if (!larg->field.field) {
 					larg->field.field =
 						tep_find_any_field(event, larg->field.name);
@@ -3718,7 +3720,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 			goto out_warning_op;
 		}
 		break;
-	case PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
 		offset = tep_read_number(pevent,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
@@ -3729,7 +3731,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		 */
 		val = (unsigned long long)(offset >> 16);
 		break;
-	case PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY:
 		/* Without [], we pass the address to the dynamic data */
 		offset = tep_read_number(pevent,
 					 data + arg->dynarray.field->offset,
@@ -3861,12 +3863,12 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
 }
 
 static void print_str_arg(struct trace_seq *s, void *data, int size,
-			  struct event_format *event, const char *format,
-			  int len_arg, struct print_arg *arg)
+			  struct tep_event_format *event, const char *format,
+			  int len_arg, struct tep_print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct print_flag_sym *flag;
-	struct format_field *field;
+	struct tep_print_flag_sym *flag;
+	struct tep_format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
 	unsigned long long addr;
@@ -3876,13 +3878,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	int i, len;
 
 	switch (arg->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		/* ?? */
 		return;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		print_str_to_seq(s, format, len_arg, arg->atom.atom);
 		return;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		field = arg->field.field;
 		if (!field) {
 			field = tep_find_any_field(event, arg->field.name);
@@ -3900,7 +3902,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 * and the size is the same as long_size, assume that it
 		 * is a pointer.
 		 */
-		if (!(field->flags & FIELD_IS_ARRAY) &&
+		if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
 
 			/* Handle heterogeneous recording and processing
@@ -3939,7 +3941,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		print_str_to_seq(s, format, len_arg, str);
 		free(str);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		val = eval_num_arg(data, size, event, arg->flags.field);
 		print = 0;
 		for (flag = arg->flags.flags; flag; flag = flag->next) {
@@ -3962,7 +3964,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			trace_seq_printf(s, "0x%llx", val);
 		}
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		val = eval_num_arg(data, size, event, arg->symbol.field);
 		for (flag = arg->symbol.symbols; flag; flag = flag->next) {
 			fval = eval_flag(flag->value);
@@ -3974,9 +3976,9 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		if (!flag)
 			trace_seq_printf(s, "0x%llx", val);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
-		if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
+		if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
 			offset = tep_read_number(pevent,
 				data + arg->hex.field->dynarray.field->offset,
@@ -3995,19 +3997,19 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		len = eval_num_arg(data, size, event, arg->hex.size);
 		for (i = 0; i < len; i++) {
-			if (i && arg->type == PRINT_HEX)
+			if (i && arg->type == TEP_PRINT_HEX)
 				trace_seq_putc(s, ' ');
 			trace_seq_printf(s, "%02x", hex[i]);
 		}
 		break;
 
-	case PRINT_INT_ARRAY: {
+	case TEP_PRINT_INT_ARRAY: {
 		void *num;
 		int el_size;
 
-		if (arg->int_array.field->type == PRINT_DYNAMIC_ARRAY) {
+		if (arg->int_array.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
-			struct format_field *field =
+			struct tep_format_field *field =
 				arg->int_array.field->dynarray.field;
 			offset = tep_read_number(pevent,
 						 data + field->offset,
@@ -4049,43 +4051,43 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		break;
 	}
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		break;
-	case PRINT_STRING: {
+	case TEP_PRINT_STRING: {
 		int str_offset;
 
 		if (arg->string.offset == -1) {
-			struct format_field *f;
+			struct tep_format_field *f;
 
 			f = tep_find_any_field(event, arg->string.string);
 			arg->string.offset = f->offset;
 		}
-		str_offset = data2host4(pevent, data + arg->string.offset);
+		str_offset = tep_data2host4(pevent, data + arg->string.offset);
 		str_offset &= 0xffff;
 		print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
 		break;
 	}
-	case PRINT_BSTRING:
+	case TEP_PRINT_BSTRING:
 		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
-	case PRINT_BITMASK: {
+	case TEP_PRINT_BITMASK: {
 		int bitmask_offset;
 		int bitmask_size;
 
 		if (arg->bitmask.offset == -1) {
-			struct format_field *f;
+			struct tep_format_field *f;
 
 			f = tep_find_any_field(event, arg->bitmask.bitmask);
 			arg->bitmask.offset = f->offset;
 		}
-		bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+		bitmask_offset = tep_data2host4(pevent, data + arg->bitmask.offset);
 		bitmask_size = bitmask_offset >> 16;
 		bitmask_offset &= 0xffff;
 		print_bitmask_to_seq(pevent, s, format, len_arg,
 				     data + bitmask_offset, bitmask_size);
 		break;
 	}
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		/*
 		 * The only op for string should be ? :
 		 */
@@ -4099,7 +4101,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			print_str_arg(s, data, size, event,
 				      format, len_arg, arg->op.right->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 		process_defined_func(s, data, size, event, arg);
 		break;
 	default:
@@ -4116,13 +4118,13 @@ out_warning_field:
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct event_format *event, struct print_arg *arg)
+		     struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	struct tep_function_handler *func_handle = arg->func.func;
 	struct func_params *param;
 	unsigned long long *args;
 	unsigned long long ret;
-	struct print_arg *farg;
+	struct tep_print_arg *farg;
 	struct trace_seq str;
 	struct save_str {
 		struct save_str *next;
@@ -4199,9 +4201,9 @@ out_free:
 	return ret;
 }
 
-static void free_args(struct print_arg *args)
+static void free_args(struct tep_print_arg *args)
 {
-	struct print_arg *next;
+	struct tep_print_arg *next;
 
 	while (args) {
 		next = args->next;
@@ -4211,11 +4213,11 @@ static void free_args(struct print_arg *args)
 	}
 }
 
-static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event_format *event)
+static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct format_field *field, *ip_field;
-	struct print_arg *args, *arg, **next;
+	struct tep_format_field *field, *ip_field;
+	struct tep_print_arg *args, *arg, **next;
 	unsigned long long ip, val;
 	char *ptr;
 	void *bptr;
@@ -4254,7 +4256,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	arg->next = NULL;
 	next = &arg->next;
 
-	arg->type = PRINT_ATOM;
+	arg->type = TEP_PRINT_ATOM;
 		
 	if (asprintf(&arg->atom.atom, "%lld", ip) < 0)
 		goto out_free;
@@ -4342,7 +4344,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 					goto out_free;
 				}
 				arg->next = NULL;
-				arg->type = PRINT_ATOM;
+				arg->type = TEP_PRINT_ATOM;
 				if (asprintf(&arg->atom.atom, "%lld", val) < 0) {
 					free(arg);
 					goto out_free;
@@ -4366,7 +4368,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 					goto out_free;
 				}
 				arg->next = NULL;
-				arg->type = PRINT_BSTRING;
+				arg->type = TEP_PRINT_BSTRING;
 				arg->string.string = strdup(bptr);
 				if (!arg->string.string)
 					goto out_free;
@@ -4388,11 +4390,11 @@ out_free:
 
 static char *
 get_bprint_format(void *data, int size __maybe_unused,
-		  struct event_format *event)
+		  struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long addr;
-	struct format_field *field;
+	struct tep_format_field *field;
 	struct printk_map *printk;
 	char *format;
 
@@ -4423,17 +4425,17 @@ get_bprint_format(void *data, int size __maybe_unused,
 }
 
 static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
-			  struct event_format *event, struct print_arg *arg)
+			  struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	unsigned char *buf;
 	const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d",
 				 arg->type);
 		return;
@@ -4576,17 +4578,17 @@ static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf)
  * %pISpc print an IP address based on sockaddr; p adds port.
  */
 static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
-			  struct print_arg *arg)
+			  void *data, int size, struct tep_event_format *event,
+			  struct tep_print_arg *arg)
 {
 	unsigned char *buf;
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return 0;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return 0;
 	}
@@ -4613,8 +4615,8 @@ static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
-			  struct print_arg *arg)
+			  void *data, int size, struct tep_event_format *event,
+			  struct tep_print_arg *arg)
 {
 	char have_c = 0;
 	unsigned char *buf;
@@ -4627,12 +4629,12 @@ static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 		rc++;
 	}
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return rc;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return rc;
 	}
@@ -4663,8 +4665,8 @@ static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
-			  struct print_arg *arg)
+			  void *data, int size, struct tep_event_format *event,
+			  struct tep_print_arg *arg)
 {
 	char have_c = 0, have_p = 0;
 	unsigned char *buf;
@@ -4685,12 +4687,12 @@ static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 		}
 	}
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return rc;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return rc;
 	}
@@ -4745,8 +4747,8 @@ static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ip_arg(struct trace_seq *s, const char *ptr,
-			void *data, int size, struct event_format *event,
-			struct print_arg *arg)
+			void *data, int size, struct tep_event_format *event,
+			struct tep_print_arg *arg)
 {
 	char i = *ptr;  /* 'i' or 'I' */
 	char ver;
@@ -4787,22 +4789,22 @@ static int is_printable_array(char *p, unsigned int len)
 }
 
 void tep_print_field(struct trace_seq *s, void *data,
-		     struct format_field *field)
+		     struct tep_format_field *field)
 {
 	unsigned long long val;
 	unsigned int offset, len, i;
 	struct tep_handle *pevent = field->event->pevent;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val = tep_read_number(pevent, data + offset, len);
 			offset = val;
 			len = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			trace_seq_printf(s, "%s", (char *)data + offset);
 		} else {
@@ -4814,21 +4816,21 @@ void tep_print_field(struct trace_seq *s, void *data,
 						 *((unsigned char *)data + offset + i));
 			}
 			trace_seq_putc(s, ']');
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER) {
+		if (field->flags & TEP_FIELD_IS_POINTER) {
 			trace_seq_printf(s, "0x%llx", val);
-		} else if (field->flags & FIELD_IS_SIGNED) {
+		} else if (field->flags & TEP_FIELD_IS_SIGNED) {
 			switch (field->size) {
 			case 4:
 				/*
 				 * If field is long then print it in hex.
 				 * A long usually stores pointers.
 				 */
-				if (field->flags & FIELD_IS_LONG)
+				if (field->flags & TEP_FIELD_IS_LONG)
 					trace_seq_printf(s, "0x%x", (int)val);
 				else
 					trace_seq_printf(s, "%d", (int)val);
@@ -4843,7 +4845,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 				trace_seq_printf(s, "%lld", val);
 			}
 		} else {
-			if (field->flags & FIELD_IS_LONG)
+			if (field->flags & TEP_FIELD_IS_LONG)
 				trace_seq_printf(s, "0x%llx", val);
 			else
 				trace_seq_printf(s, "%llu", val);
@@ -4852,9 +4854,9 @@ void tep_print_field(struct trace_seq *s, void *data,
 }
 
 void tep_print_fields(struct trace_seq *s, void *data,
-		      int size __maybe_unused, struct event_format *event)
+		      int size __maybe_unused, struct tep_event_format *event)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = event->format.fields;
 	while (field) {
@@ -4864,12 +4866,12 @@ void tep_print_fields(struct trace_seq *s, void *data,
 	}
 }
 
-static void pretty_print(struct trace_seq *s, void *data, int size, struct event_format *event)
+static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct print_fmt *print_fmt = &event->print_fmt;
-	struct print_arg *arg = print_fmt->args;
-	struct print_arg *args = NULL;
+	struct tep_print_fmt *print_fmt = &event->print_fmt;
+	struct tep_print_arg *arg = print_fmt->args;
+	struct tep_print_arg *args = NULL;
 	const char *ptr = print_fmt->format;
 	unsigned long long val;
 	struct func_map *func;
@@ -4883,13 +4885,13 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 	int len;
 	int ls;
 
-	if (event->flags & EVENT_FL_FAILED) {
+	if (event->flags & TEP_EVENT_FL_FAILED) {
 		trace_seq_printf(s, "[FAILED TO PARSE]");
 		tep_print_fields(s, data, size, event);
 		return;
 	}
 
-	if (event->flags & EVENT_FL_ISBPRINT) {
+	if (event->flags & TEP_EVENT_FL_ISBPRINT) {
 		bprint_fmt = get_bprint_format(data, size, event);
 		args = make_bprint_args(bprint_fmt, data, size, event);
 		arg = args;
@@ -4944,7 +4946,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				/* The argument is the length. */
 				if (!arg) {
 					do_warning_event(event, "no argument match");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 				len_arg = eval_num_arg(data, size, event, arg);
@@ -4966,7 +4968,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				if (isalnum(ptr[1]))
 					ptr++;
 
-				if (arg->type == PRINT_BSTRING) {
+				if (arg->type == TEP_PRINT_BSTRING) {
 					trace_seq_puts(s, arg->string.string);
 					break;
 				}
@@ -4997,7 +4999,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 			case 'u':
 				if (!arg) {
 					do_warning_event(event, "no argument match");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 
@@ -5007,7 +5009,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				/* should never happen */
 				if (len > 31) {
 					do_warning_event(event, "bad format!");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					len = 31;
 				}
 
@@ -5073,13 +5075,13 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 					break;
 				default:
 					do_warning_event(event, "bad count (%d)", ls);
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 				}
 				break;
 			case 's':
 				if (!arg) {
 					do_warning_event(event, "no matching argument");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 
@@ -5089,7 +5091,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				/* should never happen */
 				if (len > 31) {
 					do_warning_event(event, "bad format!");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					len = 31;
 				}
 
@@ -5114,7 +5116,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 			trace_seq_putc(s, *ptr);
 	}
 
-	if (event->flags & EVENT_FL_FAILED) {
+	if (event->flags & TEP_EVENT_FL_FAILED) {
 out_failed:
 		trace_seq_printf(s, "[FAILED TO PARSE]");
 	}
@@ -5227,7 +5229,7 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
  *
  * This returns the event form a given @type;
  */
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type)
+struct tep_event_format *tep_data_event_from_type(struct tep_handle *pevent, int type)
 {
 	return tep_find_event(pevent, type);
 }
@@ -5385,16 +5387,16 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
  * This parses the raw @data using the given @event information and
  * writes the print format into the trace_seq.
  */
-void tep_event_info(struct trace_seq *s, struct event_format *event,
+void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 		    struct tep_record *record)
 {
 	int print_pretty = 1;
 
-	if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
+	if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
 		tep_print_fields(s, record->data, record->size, event);
 	else {
 
-		if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
+		if (event->handler && !(event->flags & TEP_EVENT_FL_NOHANDLE))
 			print_pretty = event->handler(s, record, event,
 						      event->context);
 
@@ -5426,7 +5428,7 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
  * Returns the associated event for a given record, or NULL if non is
  * is found.
  */
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
 {
 	int type;
@@ -5451,7 +5453,7 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
  * Writes the tasks comm, pid and CPU to @s.
  */
 void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record)
 {
 	void *data = record->data;
@@ -5479,7 +5481,7 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
  * Writes the timestamp of the record into @s.
  */
 void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record,
 			  bool use_trace_clock)
 {
@@ -5529,7 +5531,7 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
  * Writes the parsing of the record's data to @s.
  */
 void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record)
 {
 	static const char *spaces = "                    "; /* 20 spaces */
@@ -5548,7 +5550,7 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
 void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 
 	event = tep_find_event_by_record(pevent, record);
 	if (!event) {
@@ -5570,8 +5572,8 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 
 static int events_id_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 
 	if ((*ea)->id < (*eb)->id)
 		return -1;
@@ -5584,8 +5586,8 @@ static int events_id_cmp(const void *a, const void *b)
 
 static int events_name_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 	int res;
 
 	res = strcmp((*ea)->name, (*eb)->name);
@@ -5601,8 +5603,8 @@ static int events_name_cmp(const void *a, const void *b)
 
 static int events_system_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 	int res;
 
 	res = strcmp((*ea)->system, (*eb)->system);
@@ -5616,9 +5618,9 @@ static int events_system_cmp(const void *a, const void *b)
 	return events_id_cmp(a, b);
 }
 
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type sort_type)
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
 {
-	struct event_format **events;
+	struct tep_event_format **events;
 	int (*sort)(const void *a, const void *b);
 
 	events = pevent->sort_events;
@@ -5637,20 +5639,20 @@ struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort
 		pevent->sort_events = events;
 
 		/* the internal events are sorted by id */
-		if (sort_type == EVENT_SORT_ID) {
+		if (sort_type == TEP_EVENT_SORT_ID) {
 			pevent->last_type = sort_type;
 			return events;
 		}
 	}
 
 	switch (sort_type) {
-	case EVENT_SORT_ID:
+	case TEP_EVENT_SORT_ID:
 		sort = events_id_cmp;
 		break;
-	case EVENT_SORT_NAME:
+	case TEP_EVENT_SORT_NAME:
 		sort = events_name_cmp;
 		break;
-	case EVENT_SORT_SYSTEM:
+	case TEP_EVENT_SORT_SYSTEM:
 		sort = events_system_cmp;
 		break;
 	default:
@@ -5663,12 +5665,12 @@ struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort
 	return events;
 }
 
-static struct format_field **
+static struct tep_format_field **
 get_event_fields(const char *type, const char *name,
-		 int count, struct format_field *list)
+		 int count, struct tep_format_field *list)
 {
-	struct format_field **fields;
-	struct format_field *field;
+	struct tep_format_field **fields;
+	struct tep_format_field *field;
 	int i = 0;
 
 	fields = malloc(sizeof(*fields) * (count + 1));
@@ -5701,7 +5703,7 @@ get_event_fields(const char *type, const char *name,
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_common_fields(struct event_format *event)
+struct tep_format_field **tep_event_common_fields(struct tep_event_format *event)
 {
 	return get_event_fields("common", event->name,
 				event->format.nr_common,
@@ -5715,14 +5717,14 @@ struct format_field **tep_event_common_fields(struct event_format *event)
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_fields(struct event_format *event)
+struct tep_format_field **tep_event_fields(struct tep_event_format *event)
 {
 	return get_event_fields("event", event->name,
 				event->format.nr_fields,
 				event->format.fields);
 }
 
-static void print_fields(struct trace_seq *s, struct print_flag_sym *field)
+static void print_fields(struct trace_seq *s, struct tep_print_flag_sym *field)
 {
 	trace_seq_printf(s, "{ %s, %s }", field->value, field->str);
 	if (field->next) {
@@ -5732,22 +5734,22 @@ static void print_fields(struct trace_seq *s, struct print_flag_sym *field)
 }
 
 /* for debugging */
-static void print_args(struct print_arg *args)
+static void print_args(struct tep_print_arg *args)
 {
 	int print_paren = 1;
 	struct trace_seq s;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		printf("null");
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		printf("%s", args->atom.atom);
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		printf("REC->%s", args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		printf("__print_flags(");
 		print_args(args->flags.field);
 		printf(", %s, ", args->flags.delim);
@@ -5757,7 +5759,7 @@ static void print_args(struct print_arg *args)
 		trace_seq_destroy(&s);
 		printf(")");
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		printf("__print_symbolic(");
 		print_args(args->symbol.field);
 		printf(", ");
@@ -5767,21 +5769,21 @@ static void print_args(struct print_arg *args)
 		trace_seq_destroy(&s);
 		printf(")");
 		break;
-	case PRINT_HEX:
+	case TEP_PRINT_HEX:
 		printf("__print_hex(");
 		print_args(args->hex.field);
 		printf(", ");
 		print_args(args->hex.size);
 		printf(")");
 		break;
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX_STR:
 		printf("__print_hex_str(");
 		print_args(args->hex.field);
 		printf(", ");
 		print_args(args->hex.size);
 		printf(")");
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		printf("__print_array(");
 		print_args(args->int_array.field);
 		printf(", ");
@@ -5790,18 +5792,18 @@ static void print_args(struct print_arg *args)
 		print_args(args->int_array.el_size);
 		printf(")");
 		break;
-	case PRINT_STRING:
-	case PRINT_BSTRING:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
 		break;
-	case PRINT_BITMASK:
+	case TEP_PRINT_BITMASK:
 		printf("__get_bitmask(%s)", args->bitmask.bitmask);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		printf("(%s)", args->typecast.type);
 		print_args(args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			print_paren = 0;
 		if (print_paren)
@@ -5833,13 +5835,13 @@ static void parse_header_field(const char *field,
 	save_input_buf_ptr = input_buf_ptr;
 	save_input_buf_siz = input_buf_siz;
 
-	if (read_expected(EVENT_ITEM, "field") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "field") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
 
 	/* type */
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	free_token(token);
 
@@ -5847,42 +5849,42 @@ static void parse_header_field(const char *field,
 	 * If this is not a mandatory field, then test it first.
 	 */
 	if (mandatory) {
-		if (read_expected(EVENT_ITEM, field) < 0)
+		if (read_expected(TEP_EVENT_ITEM, field) < 0)
 			return;
 	} else {
-		if (read_expect_type(EVENT_ITEM, &token) < 0)
+		if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 			goto fail;
 		if (strcmp(token, field) != 0)
 			goto discard;
 		free_token(token);
 	}
 
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
-	if (read_expected(EVENT_ITEM, "offset") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	*offset = atoi(token);
 	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
-	if (read_expected(EVENT_ITEM, "size") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "size") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	*size = atoi(token);
 	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
 	type = read_token(&token);
-	if (type != EVENT_NEWLINE) {
+	if (type != TEP_EVENT_NEWLINE) {
 		/* newer versions of the kernel have a "signed" type */
-		if (type != EVENT_ITEM)
+		if (type != TEP_EVENT_ITEM)
 			goto fail;
 
 		if (strcmp(token, "signed") != 0)
@@ -5890,17 +5892,17 @@ static void parse_header_field(const char *field,
 
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			return;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 
 		free_token(token);
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			return;
 
-		if (read_expect_type(EVENT_NEWLINE, &token))
+		if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 			goto fail;
 	}
  fail:
@@ -5957,7 +5959,7 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 	return 0;
 }
 
-static int event_matches(struct event_format *event,
+static int event_matches(struct tep_event_format *event,
 			 int id, const char *sys_name,
 			 const char *event_name)
 {
@@ -5980,7 +5982,7 @@ static void free_handler(struct event_handler *handle)
 	free(handle);
 }
 
-static int find_event_handle(struct tep_handle *pevent, struct event_format *event)
+static int find_event_handle(struct tep_handle *pevent, struct tep_event_format *event)
 {
 	struct event_handler *handle, **next;
 
@@ -6021,11 +6023,11 @@ static int find_event_handle(struct tep_handle *pevent, struct event_format *eve
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno __tep_parse_format(struct event_format **eventp,
+enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 				  struct tep_handle *pevent, const char *buf,
 				  unsigned long size, const char *sys)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	int ret;
 
 	init_input_buf(buf, size);
@@ -6042,10 +6044,10 @@ enum tep_errno __tep_parse_format(struct event_format **eventp,
 	}
 
 	if (strcmp(sys, "ftrace") == 0) {
-		event->flags |= EVENT_FL_ISFTRACE;
+		event->flags |= TEP_EVENT_FL_ISFTRACE;
 
 		if (strcmp(event->name, "bprint") == 0)
-			event->flags |= EVENT_FL_ISBPRINT;
+			event->flags |= TEP_EVENT_FL_ISBPRINT;
 	}
 		
 	event->id = event_read_id();
@@ -6088,22 +6090,22 @@ enum tep_errno __tep_parse_format(struct event_format **eventp,
 		goto event_parse_failed;
 	}
 
-	if (!ret && (event->flags & EVENT_FL_ISFTRACE)) {
-		struct format_field *field;
-		struct print_arg *arg, **list;
+	if (!ret && (event->flags & TEP_EVENT_FL_ISFTRACE)) {
+		struct tep_format_field *field;
+		struct tep_print_arg *arg, **list;
 
 		/* old ftrace had no args */
 		list = &event->print_fmt.args;
 		for (field = event->format.fields; field; field = field->next) {
 			arg = alloc_arg();
 			if (!arg) {
-				event->flags |= EVENT_FL_FAILED;
+				event->flags |= TEP_EVENT_FL_FAILED;
 				return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
 			}
-			arg->type = PRINT_FIELD;
+			arg->type = TEP_PRINT_FIELD;
 			arg->field.name = strdup(field->name);
 			if (!arg->field.name) {
-				event->flags |= EVENT_FL_FAILED;
+				event->flags |= TEP_EVENT_FL_FAILED;
 				free_arg(arg);
 				return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
 			}
@@ -6117,7 +6119,7 @@ enum tep_errno __tep_parse_format(struct event_format **eventp,
 	return 0;
 
  event_parse_failed:
-	event->flags |= EVENT_FL_FAILED;
+	event->flags |= TEP_EVENT_FL_FAILED;
 	return ret;
 
  event_alloc_failed:
@@ -6130,12 +6132,12 @@ enum tep_errno __tep_parse_format(struct event_format **eventp,
 
 static enum tep_errno
 __parse_event(struct tep_handle *pevent,
-	      struct event_format **eventp,
+	      struct tep_event_format **eventp,
 	      const char *buf, unsigned long size,
 	      const char *sys)
 {
 	int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
-	struct event_format *event = *eventp;
+	struct tep_event_format *event = *eventp;
 
 	if (event == NULL)
 		return ret;
@@ -6172,7 +6174,7 @@ event_add_failed:
  * /sys/kernel/debug/tracing/events/.../.../format
  */
 enum tep_errno tep_parse_format(struct tep_handle *pevent,
-				struct event_format **eventp,
+				struct tep_event_format **eventp,
 				const char *buf,
 				unsigned long size, const char *sys)
 {
@@ -6196,40 +6198,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
 enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
 			       unsigned long size, const char *sys)
 {
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	return __parse_event(pevent, &event, buf, size, sys);
 }
 
-#undef _PE
-#define _PE(code, str) str
-static const char * const tep_error_str[] = {
-	TEP_ERRORS
-};
-#undef _PE
-
-int tep_strerror(struct tep_handle *pevent __maybe_unused,
-		 enum tep_errno errnum, char *buf, size_t buflen)
-{
-	int idx;
-	const char *msg;
-
-	if (errnum >= 0) {
-		str_error_r(errnum, buf, buflen);
-		return 0;
-	}
-
-	if (errnum <= __TEP_ERRNO__START ||
-	    errnum >= __TEP_ERRNO__END)
-		return -1;
-
-	idx = errnum - __TEP_ERRNO__START - 1;
-	msg = tep_error_str[idx];
-	snprintf(buf, buflen, "%s", msg);
-
-	return 0;
-}
-
-int get_field_val(struct trace_seq *s, struct format_field *field,
+int get_field_val(struct trace_seq *s, struct tep_format_field *field,
 		  const char *name, struct tep_record *record,
 		  unsigned long long *val, int err)
 {
@@ -6262,11 +6235,11 @@ int get_field_val(struct trace_seq *s, struct format_field *field,
  *
  * On failure, it returns NULL.
  */
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
 			int *len, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	void *data = record->data;
 	unsigned offset;
 	int dummy;
@@ -6287,7 +6260,7 @@ void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
 		len = &dummy;
 
 	offset = field->offset;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = tep_read_number(event->pevent,
 					    data + offset, field->size);
 		*len = offset >> 16;
@@ -6309,11 +6282,11 @@ void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event_format *event,
 		      const char *name, struct tep_record *record,
 		      unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6334,11 +6307,11 @@ int tep_get_field_val(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event_format *event,
 			     const char *name, struct tep_record *record,
 			     unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6359,11 +6332,11 @@ int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event_format *event,
 			  const char *name, struct tep_record *record,
 			  unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6385,10 +6358,10 @@ int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
  * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
  */
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
-			struct event_format *event, const char *name,
+			struct tep_event_format *event, const char *name,
 			struct tep_record *record, int err)
 {
-	struct format_field *field = tep_find_field(event, name);
+	struct tep_format_field *field = tep_find_field(event, name);
 	unsigned long long val;
 
 	if (!field)
@@ -6417,10 +6390,10 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
  * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
  */
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
-			 struct event_format *event, const char *name,
+			 struct tep_event_format *event, const char *name,
 			 struct tep_record *record, int err)
 {
-	struct format_field *field = tep_find_field(event, name);
+	struct tep_format_field *field = tep_find_field(event, name);
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long val;
 	struct func_map *func;
@@ -6577,11 +6550,11 @@ int tep_unregister_print_function(struct tep_handle *pevent,
 	return -1;
 }
 
-static struct event_format *search_event(struct tep_handle *pevent, int id,
+static struct tep_event_format *search_event(struct tep_handle *pevent, int id,
 					 const char *sys_name,
 					 const char *event_name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 
 	if (id >= 0) {
 		/* search by id */
@@ -6621,7 +6594,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct event_handler *handle;
 
 	event = search_event(pevent, id, sys_name, event_name);
@@ -6705,7 +6678,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct event_handler *handle;
 	struct event_handler **next;
 
@@ -6757,7 +6730,7 @@ void tep_ref(struct tep_handle *pevent)
 	pevent->ref_count++;
 }
 
-void tep_free_format_field(struct format_field *field)
+void tep_free_format_field(struct tep_format_field *field)
 {
 	free(field->type);
 	if (field->alias != field->name)
@@ -6766,9 +6739,9 @@ void tep_free_format_field(struct format_field *field)
 	free(field);
 }
 
-static void free_format_fields(struct format_field *field)
+static void free_format_fields(struct tep_format_field *field)
 {
-	struct format_field *next;
+	struct tep_format_field *next;
 
 	while (field) {
 		next = field->next;
@@ -6777,13 +6750,13 @@ static void free_format_fields(struct format_field *field)
 	}
 }
 
-static void free_formats(struct format *format)
+static void free_formats(struct tep_format *format)
 {
 	free_format_fields(format->common_fields);
 	free_format_fields(format->fields);
 }
 
-void tep_free_format(struct event_format *event)
+void tep_free_format(struct tep_event_format *event)
 {
 	free(event->name);
 	free(event->system);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 44b7c2d41f9f..16bf4c890b6f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -26,17 +26,12 @@
 #include <regex.h>
 #include <string.h>
 
+#include "trace-seq.h"
+
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
 #endif
 
-/* ----------------------- trace_seq ----------------------- */
-
-
-#ifndef TRACE_SEQ_BUF_SIZE
-#define TRACE_SEQ_BUF_SIZE 4096
-#endif
-
 #ifndef DEBUG_RECORD
 #define DEBUG_RECORD 0
 #endif
@@ -59,51 +54,14 @@ struct tep_record {
 #endif
 };
 
-enum trace_seq_fail {
-	TRACE_SEQ__GOOD,
-	TRACE_SEQ__BUFFER_POISONED,
-	TRACE_SEQ__MEM_ALLOC_FAILED,
-};
-
-/*
- * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
- */
-
-struct trace_seq {
-	char			*buffer;
-	unsigned int		buffer_size;
-	unsigned int		len;
-	unsigned int		readpos;
-	enum trace_seq_fail	state;
-};
-
-void trace_seq_init(struct trace_seq *s);
-void trace_seq_reset(struct trace_seq *s);
-void trace_seq_destroy(struct trace_seq *s);
-
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
-	__attribute__ ((format (printf, 2, 0)));
-
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-
-extern void trace_seq_terminate(struct trace_seq *s);
-
-extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
-extern int trace_seq_do_printf(struct trace_seq *s);
-
-
-/* ----------------------- pevent ----------------------- */
+/* ----------------------- tep ----------------------- */
 
 struct tep_handle;
-struct event_format;
+struct tep_event_format;
 
 typedef int (*tep_event_handler_func)(struct trace_seq *s,
 				      struct tep_record *record,
-				      struct event_format *event,
+				      struct tep_event_format *event,
 				      void *context);
 
 typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
@@ -172,20 +130,20 @@ struct tep_plugin_option {
 #define TEP_PLUGIN_OPTIONS_NAME MAKE_STR(TEP_PLUGIN_OPTIONS)
 #define TEP_PLUGIN_ALIAS_NAME MAKE_STR(TEP_PLUGIN_ALIAS)
 
-enum format_flags {
-	FIELD_IS_ARRAY		= 1,
-	FIELD_IS_POINTER	= 2,
-	FIELD_IS_SIGNED		= 4,
-	FIELD_IS_STRING		= 8,
-	FIELD_IS_DYNAMIC	= 16,
-	FIELD_IS_LONG		= 32,
-	FIELD_IS_FLAG		= 64,
-	FIELD_IS_SYMBOLIC	= 128,
+enum tep_format_flags {
+	TEP_FIELD_IS_ARRAY	= 1,
+	TEP_FIELD_IS_POINTER	= 2,
+	TEP_FIELD_IS_SIGNED	= 4,
+	TEP_FIELD_IS_STRING	= 8,
+	TEP_FIELD_IS_DYNAMIC	= 16,
+	TEP_FIELD_IS_LONG	= 32,
+	TEP_FIELD_IS_FLAG	= 64,
+	TEP_FIELD_IS_SYMBOLIC	= 128,
 };
 
-struct format_field {
-	struct format_field	*next;
-	struct event_format	*event;
+struct tep_format_field {
+	struct tep_format_field	*next;
+	struct tep_event_format	*event;
 	char			*type;
 	char			*name;
 	char			*alias;
@@ -196,169 +154,169 @@ struct format_field {
 	unsigned long		flags;
 };
 
-struct format {
+struct tep_format {
 	int			nr_common;
 	int			nr_fields;
-	struct format_field	*common_fields;
-	struct format_field	*fields;
+	struct tep_format_field	*common_fields;
+	struct tep_format_field	*fields;
 };
 
-struct print_arg_atom {
+struct tep_print_arg_atom {
 	char			*atom;
 };
 
-struct print_arg_string {
+struct tep_print_arg_string {
 	char			*string;
 	int			offset;
 };
 
-struct print_arg_bitmask {
+struct tep_print_arg_bitmask {
 	char			*bitmask;
 	int			offset;
 };
 
-struct print_arg_field {
+struct tep_print_arg_field {
 	char			*name;
-	struct format_field	*field;
+	struct tep_format_field	*field;
 };
 
-struct print_flag_sym {
-	struct print_flag_sym	*next;
-	char			*value;
-	char			*str;
+struct tep_print_flag_sym {
+	struct tep_print_flag_sym	*next;
+	char				*value;
+	char				*str;
 };
 
-struct print_arg_typecast {
+struct tep_print_arg_typecast {
 	char 			*type;
-	struct print_arg	*item;
+	struct tep_print_arg	*item;
 };
 
-struct print_arg_flags {
-	struct print_arg	*field;
-	char			*delim;
-	struct print_flag_sym	*flags;
+struct tep_print_arg_flags {
+	struct tep_print_arg		*field;
+	char				*delim;
+	struct tep_print_flag_sym	*flags;
 };
 
-struct print_arg_symbol {
-	struct print_arg	*field;
-	struct print_flag_sym	*symbols;
+struct tep_print_arg_symbol {
+	struct tep_print_arg		*field;
+	struct tep_print_flag_sym	*symbols;
 };
 
-struct print_arg_hex {
-	struct print_arg	*field;
-	struct print_arg	*size;
+struct tep_print_arg_hex {
+	struct tep_print_arg	*field;
+	struct tep_print_arg	*size;
 };
 
-struct print_arg_int_array {
-	struct print_arg	*field;
-	struct print_arg	*count;
-	struct print_arg	*el_size;
+struct tep_print_arg_int_array {
+	struct tep_print_arg	*field;
+	struct tep_print_arg	*count;
+	struct tep_print_arg	*el_size;
 };
 
-struct print_arg_dynarray {
-	struct format_field	*field;
-	struct print_arg	*index;
+struct tep_print_arg_dynarray {
+	struct tep_format_field	*field;
+	struct tep_print_arg	*index;
 };
 
-struct print_arg;
+struct tep_print_arg;
 
-struct print_arg_op {
+struct tep_print_arg_op {
 	char			*op;
 	int			prio;
-	struct print_arg	*left;
-	struct print_arg	*right;
+	struct tep_print_arg	*left;
+	struct tep_print_arg	*right;
 };
 
 struct tep_function_handler;
 
-struct print_arg_func {
+struct tep_print_arg_func {
 	struct tep_function_handler	*func;
-	struct print_arg		*args;
+	struct tep_print_arg		*args;
 };
 
-enum print_arg_type {
-	PRINT_NULL,
-	PRINT_ATOM,
-	PRINT_FIELD,
-	PRINT_FLAGS,
-	PRINT_SYMBOL,
-	PRINT_HEX,
-	PRINT_INT_ARRAY,
-	PRINT_TYPE,
-	PRINT_STRING,
-	PRINT_BSTRING,
-	PRINT_DYNAMIC_ARRAY,
-	PRINT_OP,
-	PRINT_FUNC,
-	PRINT_BITMASK,
-	PRINT_DYNAMIC_ARRAY_LEN,
-	PRINT_HEX_STR,
+enum tep_print_arg_type {
+	TEP_PRINT_NULL,
+	TEP_PRINT_ATOM,
+	TEP_PRINT_FIELD,
+	TEP_PRINT_FLAGS,
+	TEP_PRINT_SYMBOL,
+	TEP_PRINT_HEX,
+	TEP_PRINT_INT_ARRAY,
+	TEP_PRINT_TYPE,
+	TEP_PRINT_STRING,
+	TEP_PRINT_BSTRING,
+	TEP_PRINT_DYNAMIC_ARRAY,
+	TEP_PRINT_OP,
+	TEP_PRINT_FUNC,
+	TEP_PRINT_BITMASK,
+	TEP_PRINT_DYNAMIC_ARRAY_LEN,
+	TEP_PRINT_HEX_STR,
 };
 
-struct print_arg {
-	struct print_arg		*next;
-	enum print_arg_type		type;
+struct tep_print_arg {
+	struct tep_print_arg		*next;
+	enum tep_print_arg_type		type;
 	union {
-		struct print_arg_atom		atom;
-		struct print_arg_field		field;
-		struct print_arg_typecast	typecast;
-		struct print_arg_flags		flags;
-		struct print_arg_symbol		symbol;
-		struct print_arg_hex		hex;
-		struct print_arg_int_array	int_array;
-		struct print_arg_func		func;
-		struct print_arg_string		string;
-		struct print_arg_bitmask	bitmask;
-		struct print_arg_op		op;
-		struct print_arg_dynarray	dynarray;
+		struct tep_print_arg_atom	atom;
+		struct tep_print_arg_field	field;
+		struct tep_print_arg_typecast	typecast;
+		struct tep_print_arg_flags	flags;
+		struct tep_print_arg_symbol	symbol;
+		struct tep_print_arg_hex	hex;
+		struct tep_print_arg_int_array	int_array;
+		struct tep_print_arg_func	func;
+		struct tep_print_arg_string	string;
+		struct tep_print_arg_bitmask	bitmask;
+		struct tep_print_arg_op		op;
+		struct tep_print_arg_dynarray	dynarray;
 	};
 };
 
-struct print_fmt {
+struct tep_print_fmt {
 	char			*format;
-	struct print_arg	*args;
+	struct tep_print_arg	*args;
 };
 
-struct event_format {
+struct tep_event_format {
 	struct tep_handle	*pevent;
 	char			*name;
 	int			id;
 	int			flags;
-	struct format		format;
-	struct print_fmt	print_fmt;
+	struct tep_format	format;
+	struct tep_print_fmt	print_fmt;
 	char			*system;
 	tep_event_handler_func	handler;
 	void			*context;
 };
 
 enum {
-	EVENT_FL_ISFTRACE	= 0x01,
-	EVENT_FL_ISPRINT	= 0x02,
-	EVENT_FL_ISBPRINT	= 0x04,
-	EVENT_FL_ISFUNCENT	= 0x10,
-	EVENT_FL_ISFUNCRET	= 0x20,
-	EVENT_FL_NOHANDLE	= 0x40,
-	EVENT_FL_PRINTRAW	= 0x80,
+	TEP_EVENT_FL_ISFTRACE	= 0x01,
+	TEP_EVENT_FL_ISPRINT	= 0x02,
+	TEP_EVENT_FL_ISBPRINT	= 0x04,
+	TEP_EVENT_FL_ISFUNCENT	= 0x10,
+	TEP_EVENT_FL_ISFUNCRET	= 0x20,
+	TEP_EVENT_FL_NOHANDLE	= 0x40,
+	TEP_EVENT_FL_PRINTRAW	= 0x80,
 
-	EVENT_FL_FAILED		= 0x80000000
+	TEP_EVENT_FL_FAILED	= 0x80000000
 };
 
-enum event_sort_type {
-	EVENT_SORT_ID,
-	EVENT_SORT_NAME,
-	EVENT_SORT_SYSTEM,
+enum tep_event_sort_type {
+	TEP_EVENT_SORT_ID,
+	TEP_EVENT_SORT_NAME,
+	TEP_EVENT_SORT_SYSTEM,
 };
 
-enum event_type {
-	EVENT_ERROR,
-	EVENT_NONE,
-	EVENT_SPACE,
-	EVENT_NEWLINE,
-	EVENT_OP,
-	EVENT_DELIM,
-	EVENT_ITEM,
-	EVENT_DQUOTE,
-	EVENT_SQUOTE,
+enum tep_event_type {
+	TEP_EVENT_ERROR,
+	TEP_EVENT_NONE,
+	TEP_EVENT_SPACE,
+	TEP_EVENT_NEWLINE,
+	TEP_EVENT_OP,
+	TEP_EVENT_DELIM,
+	TEP_EVENT_ITEM,
+	TEP_EVENT_DQUOTE,
+	TEP_EVENT_SQUOTE,
 };
 
 typedef unsigned long long (*tep_func_handler)(struct trace_seq *s,
@@ -431,12 +389,12 @@ enum tep_errno {
 };
 #undef _PE
 
-struct plugin_list;
+struct tep_plugin_list;
 
 #define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
 
-struct plugin_list *tep_load_plugins(struct tep_handle *pevent);
-void tep_unload_plugins(struct plugin_list *plugin_list,
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+void tep_unload_plugins(struct tep_plugin_list *plugin_list,
 			struct tep_handle *pevent);
 char **tep_plugin_list_options(void);
 void tep_plugin_free_options_list(char **list);
@@ -445,156 +403,25 @@ int tep_plugin_add_options(const char *name,
 void tep_plugin_remove_options(struct tep_plugin_option *options);
 void tep_print_plugins(struct trace_seq *s,
 			const char *prefix, const char *suffix,
-			const struct plugin_list *list);
-
-struct cmdline;
-struct cmdline_list;
-struct func_map;
-struct func_list;
-struct event_handler;
-struct func_resolver;
+			const struct tep_plugin_list *list);
 
+/* tep_handle */
 typedef char *(tep_func_resolver_t)(void *priv,
 				    unsigned long long *addrp, char **modp);
+void tep_set_flag(struct tep_handle *tep, int flag);
+unsigned short __tep_data2host2(struct tep_handle *pevent, unsigned short data);
+unsigned int __tep_data2host4(struct tep_handle *pevent, unsigned int data);
+unsigned long long
+__tep_data2host8(struct tep_handle *pevent, unsigned long long data);
 
-struct tep_handle {
-	int ref_count;
-
-	int header_page_ts_offset;
-	int header_page_ts_size;
-	int header_page_size_offset;
-	int header_page_size_size;
-	int header_page_data_offset;
-	int header_page_data_size;
-	int header_page_overwrite;
-
-	int file_bigendian;
-	int host_bigendian;
-
-	int latency_format;
-
-	int old_format;
-
-	int cpus;
-	int long_size;
-	int page_size;
-
-	struct cmdline *cmdlines;
-	struct cmdline_list *cmdlist;
-	int cmdline_count;
-
-	struct func_map *func_map;
-	struct func_resolver *func_resolver;
-	struct func_list *funclist;
-	unsigned int func_count;
-
-	struct printk_map *printk_map;
-	struct printk_list *printklist;
-	unsigned int printk_count;
-
-
-	struct event_format **events;
-	int nr_events;
-	struct event_format **sort_events;
-	enum event_sort_type last_type;
-
-	int type_offset;
-	int type_size;
-
-	int pid_offset;
-	int pid_size;
-
- 	int pc_offset;
-	int pc_size;
-
-	int flags_offset;
-	int flags_size;
-
-	int ld_offset;
-	int ld_size;
-
-	int print_raw;
-
-	int test_filters;
-
-	int flags;
-
-	struct format_field *bprint_ip_field;
-	struct format_field *bprint_fmt_field;
-	struct format_field *bprint_buf_field;
-
-	struct event_handler *handlers;
-	struct tep_function_handler *func_handlers;
-
-	/* cache */
-	struct event_format *last_event;
-
-	char *trace_clock;
-};
-
-static inline void tep_set_flag(struct tep_handle *pevent, int flag)
-{
-	pevent->flags |= flag;
-}
-
-static inline unsigned short
-__data2host2(struct tep_handle *pevent, unsigned short data)
-{
-	unsigned short swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 8) |
-		((data & (0xffULL << 8)) >> 8);
-
-	return swap;
-}
-
-static inline unsigned int
-__data2host4(struct tep_handle *pevent, unsigned int data)
-{
-	unsigned int swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 24) |
-		((data & (0xffULL << 8)) << 8) |
-		((data & (0xffULL << 16)) >> 8) |
-		((data & (0xffULL << 24)) >> 24);
-
-	return swap;
-}
-
-static inline unsigned long long
-__data2host8(struct tep_handle *pevent, unsigned long long data)
-{
-	unsigned long long swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 56) |
-		((data & (0xffULL << 8)) << 40) |
-		((data & (0xffULL << 16)) << 24) |
-		((data & (0xffULL << 24)) << 8) |
-		((data & (0xffULL << 32)) >> 8) |
-		((data & (0xffULL << 40)) >> 24) |
-		((data & (0xffULL << 48)) >> 40) |
-		((data & (0xffULL << 56)) >> 56);
-
-	return swap;
-}
-
-#define data2host2(pevent, ptr)		__data2host2(pevent, *(unsigned short *)(ptr))
-#define data2host4(pevent, ptr)		__data2host4(pevent, *(unsigned int *)(ptr))
-#define data2host8(pevent, ptr)					\
+#define tep_data2host2(pevent, ptr)	__tep_data2host2(pevent, *(unsigned short *)(ptr))
+#define tep_data2host4(pevent, ptr)	__tep_data2host4(pevent, *(unsigned int *)(ptr))
+#define tep_data2host8(pevent, ptr)	\
 ({								\
 	unsigned long long __val;				\
 								\
 	memcpy(&__val, (ptr), sizeof(unsigned long long));	\
-	__data2host8(pevent, __val);				\
+	__tep_data2host8(pevent, __val);				\
 })
 
 static inline int tep_host_bigendian(void)
@@ -627,14 +454,14 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 int tep_pid_is_registered(struct tep_handle *pevent, int pid);
 
 void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record);
 void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record,
 			  bool use_trace_clock);
 void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record);
 void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock);
@@ -645,32 +472,32 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
 			       unsigned long size, const char *sys);
 enum tep_errno tep_parse_format(struct tep_handle *pevent,
-				struct event_format **eventp,
+				struct tep_event_format **eventp,
 				const char *buf,
 				unsigned long size, const char *sys);
-void tep_free_format(struct event_format *event);
-void tep_free_format_field(struct format_field *field);
+void tep_free_format(struct tep_event_format *event);
+void tep_free_format_field(struct tep_format_field *field);
 
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
 			int *len, int err);
 
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event_format *event,
 		      const char *name, struct tep_record *record,
 		      unsigned long long *val, int err);
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event_format *event,
 			     const char *name, struct tep_record *record,
 			     unsigned long long *val, int err);
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event_format *event,
 			  const char *name, struct tep_record *record,
 			  unsigned long long *val, int err);
 
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
-			   struct event_format *event, const char *name,
-			   struct tep_record *record, int err);
+			struct tep_event_format *event, const char *name,
+			struct tep_record *record, int err);
 
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
-			 struct event_format *event, const char *name,
+			 struct tep_event_format *event, const char *name,
 			 struct tep_record *record, int err);
 
 int tep_register_event_handler(struct tep_handle *pevent, int id,
@@ -686,29 +513,30 @@ int tep_register_print_function(struct tep_handle *pevent,
 int tep_unregister_print_function(struct tep_handle *pevent,
 				  tep_func_handler func, char *name);
 
-struct format_field *tep_find_common_field(struct event_format *event, const char *name);
-struct format_field *tep_find_field(struct event_format *event, const char *name);
-struct format_field *tep_find_any_field(struct event_format *event, const char *name);
+struct tep_format_field *tep_find_common_field(struct tep_event_format *event, const char *name);
+struct tep_format_field *tep_find_field(struct tep_event_format *event, const char *name);
+struct tep_format_field *tep_find_any_field(struct tep_event_format *event, const char *name);
 
 const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
 unsigned long long
 tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
 unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
-int tep_read_number_field(struct format_field *field, const void *data,
+int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value);
 
-struct event_format *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event_format *tep_get_first_event(struct tep_handle *tep);
+int tep_get_events_count(struct tep_handle *tep);
+struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id);
 
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
-
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 
 void tep_data_lat_fmt(struct tep_handle *pevent,
 		      struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type);
+struct tep_event_format *tep_data_event_from_type(struct tep_handle *pevent, int type);
 int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
@@ -719,77 +547,35 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co
 int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
-		     struct format_field *field);
+		     struct tep_format_field *field);
 void tep_print_fields(struct trace_seq *s, void *data,
-		      int size __maybe_unused, struct event_format *event);
-void tep_event_info(struct trace_seq *s, struct event_format *event,
+		      int size __maybe_unused, struct tep_event_format *event);
+void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 		       struct tep_record *record);
 int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
 		    char *buf, size_t buflen);
 
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
-struct format_field **tep_event_common_fields(struct event_format *event);
-struct format_field **tep_event_fields(struct event_format *event);
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
+struct tep_format_field **tep_event_common_fields(struct tep_event_format *event);
+struct tep_format_field **tep_event_fields(struct tep_event_format *event);
 
-static inline int tep_get_cpus(struct tep_handle *pevent)
-{
-	return pevent->cpus;
-}
-
-static inline void tep_set_cpus(struct tep_handle *pevent, int cpus)
-{
-	pevent->cpus = cpus;
-}
-
-static inline int tep_get_long_size(struct tep_handle *pevent)
-{
-	return pevent->long_size;
-}
-
-static inline void tep_set_long_size(struct tep_handle *pevent, int long_size)
-{
-	pevent->long_size = long_size;
-}
-
-static inline int tep_get_page_size(struct tep_handle *pevent)
-{
-	return pevent->page_size;
-}
-
-static inline void tep_set_page_size(struct tep_handle *pevent, int _page_size)
-{
-	pevent->page_size = _page_size;
-}
-
-static inline int tep_is_file_bigendian(struct tep_handle *pevent)
-{
-	return pevent->file_bigendian;
-}
-
-static inline void tep_set_file_bigendian(struct tep_handle *pevent, int endian)
-{
-	pevent->file_bigendian = endian;
-}
-
-static inline int tep_is_host_bigendian(struct tep_handle *pevent)
-{
-	return pevent->host_bigendian;
-}
-
-static inline void tep_set_host_bigendian(struct tep_handle *pevent, int endian)
-{
-	pevent->host_bigendian = endian;
-}
-
-static inline int tep_is_latency_format(struct tep_handle *pevent)
-{
-	return pevent->latency_format;
-}
-
-static inline void tep_set_latency_format(struct tep_handle *pevent, int lat)
-{
-	pevent->latency_format = lat;
-}
+enum tep_endian {
+        TEP_LITTLE_ENDIAN = 0,
+        TEP_BIG_ENDIAN
+};
+int tep_get_cpus(struct tep_handle *pevent);
+void tep_set_cpus(struct tep_handle *pevent, int cpus);
+int tep_get_long_size(struct tep_handle *pevent);
+void tep_set_long_size(struct tep_handle *pevent, int long_size);
+int tep_get_page_size(struct tep_handle *pevent);
+void tep_set_page_size(struct tep_handle *pevent, int _page_size);
+int tep_is_file_bigendian(struct tep_handle *pevent);
+void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
+int tep_is_host_bigendian(struct tep_handle *pevent);
+void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
+int tep_is_latency_format(struct tep_handle *pevent);
+void tep_set_latency_format(struct tep_handle *pevent, int lat);
+int tep_get_header_page_size(struct tep_handle *pevent);
 
 struct tep_handle *tep_alloc(void);
 void tep_free(struct tep_handle *pevent);
@@ -798,7 +584,7 @@ void tep_unref(struct tep_handle *pevent);
 
 /* access to the internal parser */
 void tep_buffer_init(const char *buf, unsigned long long size);
-enum event_type tep_read_token(char **tok);
+enum tep_event_type tep_read_token(char **tok);
 void tep_free_token(char *token);
 int tep_peek_char(void);
 const char *tep_get_input_buf(void);
@@ -810,136 +596,136 @@ void tep_print_printk(struct tep_handle *pevent);
 
 /* ----------------------- filtering ----------------------- */
 
-enum filter_boolean_type {
-	FILTER_FALSE,
-	FILTER_TRUE,
+enum tep_filter_boolean_type {
+	TEP_FILTER_FALSE,
+	TEP_FILTER_TRUE,
 };
 
-enum filter_op_type {
-	FILTER_OP_AND = 1,
-	FILTER_OP_OR,
-	FILTER_OP_NOT,
+enum tep_filter_op_type {
+	TEP_FILTER_OP_AND = 1,
+	TEP_FILTER_OP_OR,
+	TEP_FILTER_OP_NOT,
 };
 
-enum filter_cmp_type {
-	FILTER_CMP_NONE,
-	FILTER_CMP_EQ,
-	FILTER_CMP_NE,
-	FILTER_CMP_GT,
-	FILTER_CMP_LT,
-	FILTER_CMP_GE,
-	FILTER_CMP_LE,
-	FILTER_CMP_MATCH,
-	FILTER_CMP_NOT_MATCH,
-	FILTER_CMP_REGEX,
-	FILTER_CMP_NOT_REGEX,
+enum tep_filter_cmp_type {
+	TEP_FILTER_CMP_NONE,
+	TEP_FILTER_CMP_EQ,
+	TEP_FILTER_CMP_NE,
+	TEP_FILTER_CMP_GT,
+	TEP_FILTER_CMP_LT,
+	TEP_FILTER_CMP_GE,
+	TEP_FILTER_CMP_LE,
+	TEP_FILTER_CMP_MATCH,
+	TEP_FILTER_CMP_NOT_MATCH,
+	TEP_FILTER_CMP_REGEX,
+	TEP_FILTER_CMP_NOT_REGEX,
 };
 
-enum filter_exp_type {
-	FILTER_EXP_NONE,
-	FILTER_EXP_ADD,
-	FILTER_EXP_SUB,
-	FILTER_EXP_MUL,
-	FILTER_EXP_DIV,
-	FILTER_EXP_MOD,
-	FILTER_EXP_RSHIFT,
-	FILTER_EXP_LSHIFT,
-	FILTER_EXP_AND,
-	FILTER_EXP_OR,
-	FILTER_EXP_XOR,
-	FILTER_EXP_NOT,
+enum tep_filter_exp_type {
+	TEP_FILTER_EXP_NONE,
+	TEP_FILTER_EXP_ADD,
+	TEP_FILTER_EXP_SUB,
+	TEP_FILTER_EXP_MUL,
+	TEP_FILTER_EXP_DIV,
+	TEP_FILTER_EXP_MOD,
+	TEP_FILTER_EXP_RSHIFT,
+	TEP_FILTER_EXP_LSHIFT,
+	TEP_FILTER_EXP_AND,
+	TEP_FILTER_EXP_OR,
+	TEP_FILTER_EXP_XOR,
+	TEP_FILTER_EXP_NOT,
 };
 
-enum filter_arg_type {
-	FILTER_ARG_NONE,
-	FILTER_ARG_BOOLEAN,
-	FILTER_ARG_VALUE,
-	FILTER_ARG_FIELD,
-	FILTER_ARG_EXP,
-	FILTER_ARG_OP,
-	FILTER_ARG_NUM,
-	FILTER_ARG_STR,
+enum tep_filter_arg_type {
+	TEP_FILTER_ARG_NONE,
+	TEP_FILTER_ARG_BOOLEAN,
+	TEP_FILTER_ARG_VALUE,
+	TEP_FILTER_ARG_FIELD,
+	TEP_FILTER_ARG_EXP,
+	TEP_FILTER_ARG_OP,
+	TEP_FILTER_ARG_NUM,
+	TEP_FILTER_ARG_STR,
 };
 
-enum filter_value_type {
-	FILTER_NUMBER,
-	FILTER_STRING,
-	FILTER_CHAR
+enum tep_filter_value_type {
+	TEP_FILTER_NUMBER,
+	TEP_FILTER_STRING,
+	TEP_FILTER_CHAR
 };
 
-struct fliter_arg;
+struct tep_filter_arg;
 
-struct filter_arg_boolean {
-	enum filter_boolean_type	value;
+struct tep_filter_arg_boolean {
+	enum tep_filter_boolean_type	value;
 };
 
-struct filter_arg_field {
-	struct format_field	*field;
+struct tep_filter_arg_field {
+	struct tep_format_field		*field;
 };
 
-struct filter_arg_value {
-	enum filter_value_type	type;
+struct tep_filter_arg_value {
+	enum tep_filter_value_type	type;
 	union {
 		char			*str;
 		unsigned long long	val;
 	};
 };
 
-struct filter_arg_op {
-	enum filter_op_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+struct tep_filter_arg_op {
+	enum tep_filter_op_type		type;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_exp {
-	enum filter_exp_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+struct tep_filter_arg_exp {
+	enum tep_filter_exp_type	type;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_num {
-	enum filter_cmp_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+struct tep_filter_arg_num {
+	enum tep_filter_cmp_type	type;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_str {
-	enum filter_cmp_type	type;
-	struct format_field	*field;
-	char			*val;
-	char			*buffer;
-	regex_t			reg;
+struct tep_filter_arg_str {
+	enum tep_filter_cmp_type	type;
+	struct tep_format_field		*field;
+	char				*val;
+	char				*buffer;
+	regex_t				reg;
 };
 
-struct filter_arg {
-	enum filter_arg_type	type;
+struct tep_filter_arg {
+	enum tep_filter_arg_type		type;
 	union {
-		struct filter_arg_boolean	boolean;
-		struct filter_arg_field		field;
-		struct filter_arg_value		value;
-		struct filter_arg_op		op;
-		struct filter_arg_exp		exp;
-		struct filter_arg_num		num;
-		struct filter_arg_str		str;
+		struct tep_filter_arg_boolean	boolean;
+		struct tep_filter_arg_field	field;
+		struct tep_filter_arg_value	value;
+		struct tep_filter_arg_op	op;
+		struct tep_filter_arg_exp	exp;
+		struct tep_filter_arg_num	num;
+		struct tep_filter_arg_str	str;
 	};
 };
 
-struct filter_type {
+struct tep_filter_type {
 	int			event_id;
-	struct event_format	*event;
-	struct filter_arg	*filter;
+	struct tep_event_format	*event;
+	struct tep_filter_arg	*filter;
 };
 
 #define TEP_FILTER_ERROR_BUFSZ  1024
 
-struct event_filter {
+struct tep_event_filter {
 	struct tep_handle	*pevent;
 	int			filters;
-	struct filter_type	*event_filters;
+	struct tep_filter_type	*event_filters;
 	char			error_buffer[TEP_FILTER_ERROR_BUFSZ];
 };
 
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
 
 /* for backward compatibility */
 #define FILTER_NONE		TEP_ERRNO__NO_FILTER
@@ -947,45 +733,45 @@ struct event_filter *tep_filter_alloc(struct tep_handle *pevent);
 #define FILTER_MISS		TEP_ERRNO__FILTER_MISS
 #define FILTER_MATCH		TEP_ERRNO__FILTER_MATCH
 
-enum filter_trivial_type {
-	FILTER_TRIVIAL_FALSE,
-	FILTER_TRIVIAL_TRUE,
-	FILTER_TRIVIAL_BOTH,
+enum tep_filter_trivial_type {
+	TEP_FILTER_TRIVIAL_FALSE,
+	TEP_FILTER_TRIVIAL_TRUE,
+	TEP_FILTER_TRIVIAL_BOTH,
 };
 
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str);
 
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record);
 
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 			char *buf, size_t buflen);
 
-int tep_event_filtered(struct event_filter *filter,
+int tep_event_filtered(struct tep_event_filter *filter,
 		       int event_id);
 
-void tep_filter_reset(struct event_filter *filter);
+void tep_filter_reset(struct tep_event_filter *filter);
 
-int tep_filter_clear_trivial(struct event_filter *filter,
-			     enum filter_trivial_type type);
+int tep_filter_clear_trivial(struct tep_event_filter *filter,
+			     enum tep_filter_trivial_type type);
 
-void tep_filter_free(struct event_filter *filter);
+void tep_filter_free(struct tep_event_filter *filter);
 
-char *tep_filter_make_string(struct event_filter *filter, int event_id);
+char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
 
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id);
 
-int tep_filter_event_has_trivial(struct event_filter *filter,
+int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
-				 enum filter_trivial_type type);
+				 enum tep_filter_trivial_type type);
 
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source);
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
 
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
-			enum filter_trivial_type type);
+int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
+			enum tep_filter_trivial_type type);
 
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2);
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
 
 #endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index f17e25097e1e..e74f16c88398 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -14,7 +14,9 @@
 #include <unistd.h>
 #include <dirent.h>
 #include "event-parse.h"
+#include "event-parse-local.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 
@@ -30,8 +32,8 @@ static struct trace_plugin_options {
 	char				*value;
 } *trace_plugin_options;
 
-struct plugin_list {
-	struct plugin_list	*next;
+struct tep_plugin_list {
+	struct tep_plugin_list	*next;
 	char			*name;
 	void			*handle;
 };
@@ -258,7 +260,7 @@ void tep_plugin_remove_options(struct tep_plugin_option *options)
  */
 void tep_print_plugins(struct trace_seq *s,
 		       const char *prefix, const char *suffix,
-		       const struct plugin_list *list)
+		       const struct tep_plugin_list *list)
 {
 	while (list) {
 		trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
@@ -270,9 +272,9 @@ static void
 load_plugin(struct tep_handle *pevent, const char *path,
 	    const char *file, void *data)
 {
-	struct plugin_list **plugin_list = data;
+	struct tep_plugin_list **plugin_list = data;
 	tep_plugin_load_func func;
-	struct plugin_list *list;
+	struct tep_plugin_list *list;
 	const char *alias;
 	char *plugin;
 	void *handle;
@@ -416,20 +418,20 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	free(path);
 }
 
-struct plugin_list*
+struct tep_plugin_list*
 tep_load_plugins(struct tep_handle *pevent)
 {
-	struct plugin_list *list = NULL;
+	struct tep_plugin_list *list = NULL;
 
 	load_plugins(pevent, ".so", load_plugin, &list);
 	return list;
 }
 
 void
-tep_unload_plugins(struct plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
 {
 	tep_plugin_unload_func func;
-	struct plugin_list *list;
+	struct tep_plugin_list *list;
 
 	while (plugin_list) {
 		list = plugin_list;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index e76154c02ee7..ed87cb56713d 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -11,22 +11,23 @@
 #include <sys/types.h>
 
 #include "event-parse.h"
+#include "event-parse-local.h"
 #include "event-utils.h"
 
 #define COMM "COMM"
 #define CPU "CPU"
 
-static struct format_field comm = {
+static struct tep_format_field comm = {
 	.name = "COMM",
 };
 
-static struct format_field cpu = {
+static struct tep_format_field cpu = {
 	.name = "CPU",
 };
 
 struct event_list {
 	struct event_list	*next;
-	struct event_format	*event;
+	struct tep_event_format	*event;
 };
 
 static void show_error(char *error_buf, const char *fmt, ...)
@@ -61,15 +62,15 @@ static void free_token(char *token)
 	tep_free_token(token);
 }
 
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	do {
 		free_token(token);
 		type = tep_read_token(&token);
-	} while (type == EVENT_NEWLINE || type == EVENT_SPACE);
+	} while (type == TEP_EVENT_NEWLINE || type == TEP_EVENT_SPACE);
 
 	/* If token is = or ! check to see if the next char is ~ */
 	if (token &&
@@ -79,7 +80,7 @@ static enum event_type read_token(char **tok)
 		*tok = malloc(3);
 		if (*tok == NULL) {
 			free_token(token);
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 		}
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
@@ -94,8 +95,8 @@ static enum event_type read_token(char **tok)
 
 static int filter_cmp(const void *a, const void *b)
 {
-	const struct filter_type *ea = a;
-	const struct filter_type *eb = b;
+	const struct tep_filter_type *ea = a;
+	const struct tep_filter_type *eb = b;
 
 	if (ea->event_id < eb->event_id)
 		return -1;
@@ -106,11 +107,11 @@ static int filter_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static struct filter_type *
-find_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+find_filter_type(struct tep_event_filter *filter, int id)
 {
-	struct filter_type *filter_type;
-	struct filter_type key;
+	struct tep_filter_type *filter_type;
+	struct tep_filter_type key;
 
 	key.event_id = id;
 
@@ -122,10 +123,10 @@ find_filter_type(struct event_filter *filter, int id)
 	return filter_type;
 }
 
-static struct filter_type *
-add_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+add_filter_type(struct tep_event_filter *filter, int id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int i;
 
 	filter_type = find_filter_type(filter, id);
@@ -165,9 +166,9 @@ add_filter_type(struct event_filter *filter, int id)
  * tep_filter_alloc - create a new event filter
  * @pevent: The pevent that this filter is associated with
  */
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
 {
-	struct event_filter *filter;
+	struct tep_event_filter *filter;
 
 	filter = malloc(sizeof(*filter));
 	if (filter == NULL)
@@ -180,44 +181,44 @@ struct event_filter *tep_filter_alloc(struct tep_handle *pevent)
 	return filter;
 }
 
-static struct filter_arg *allocate_arg(void)
+static struct tep_filter_arg *allocate_arg(void)
 {
-	return calloc(1, sizeof(struct filter_arg));
+	return calloc(1, sizeof(struct tep_filter_arg));
 }
 
-static void free_arg(struct filter_arg *arg)
+static void free_arg(struct tep_filter_arg *arg)
 {
 	if (!arg)
 		return;
 
 	switch (arg->type) {
-	case FILTER_ARG_NONE:
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_NONE:
+	case TEP_FILTER_ARG_BOOLEAN:
 		break;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		free_arg(arg->num.left);
 		free_arg(arg->num.right);
 		break;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		free_arg(arg->exp.left);
 		free_arg(arg->exp.right);
 		break;
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		free(arg->str.val);
 		regfree(&arg->str.reg);
 		free(arg->str.buffer);
 		break;
 
-	case FILTER_ARG_VALUE:
-		if (arg->value.type == FILTER_STRING ||
-		    arg->value.type == FILTER_CHAR)
+	case TEP_FILTER_ARG_VALUE:
+		if (arg->value.type == TEP_FILTER_STRING ||
+		    arg->value.type == TEP_FILTER_CHAR)
 			free(arg->value.str);
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		free_arg(arg->op.left);
 		free_arg(arg->op.right);
 	default:
@@ -228,7 +229,7 @@ static void free_arg(struct filter_arg *arg)
 }
 
 static int add_event(struct event_list **events,
-		      struct event_format *event)
+		     struct tep_event_format *event)
 {
 	struct event_list *list;
 
@@ -242,7 +243,7 @@ static int add_event(struct event_list **events,
 	return 0;
 }
 
-static int event_match(struct event_format *event,
+static int event_match(struct tep_event_format *event,
 		       regex_t *sreg, regex_t *ereg)
 {
 	if (sreg) {
@@ -258,7 +259,7 @@ static enum tep_errno
 find_event(struct tep_handle *pevent, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	regex_t ereg;
 	regex_t sreg;
 	int match = 0;
@@ -333,11 +334,11 @@ static void free_events(struct event_list *events)
 }
 
 static enum tep_errno
-create_arg_item(struct event_format *event, const char *token,
-		enum event_type type, struct filter_arg **parg, char *error_str)
+create_arg_item(struct tep_event_format *event, const char *token,
+		enum tep_event_type type, struct tep_filter_arg **parg, char *error_str)
 {
-	struct format_field *field;
-	struct filter_arg *arg;
+	struct tep_format_field *field;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (arg == NULL) {
@@ -347,11 +348,11 @@ create_arg_item(struct event_format *event, const char *token,
 
 	switch (type) {
 
-	case EVENT_SQUOTE:
-	case EVENT_DQUOTE:
-		arg->type = FILTER_ARG_VALUE;
+	case TEP_EVENT_SQUOTE:
+	case TEP_EVENT_DQUOTE:
+		arg->type = TEP_FILTER_ARG_VALUE;
 		arg->value.type =
-			type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
+			type == TEP_EVENT_DQUOTE ? TEP_FILTER_STRING : TEP_FILTER_CHAR;
 		arg->value.str = strdup(token);
 		if (!arg->value.str) {
 			free_arg(arg);
@@ -359,11 +360,11 @@ create_arg_item(struct event_format *event, const char *token,
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 		}
 		break;
-	case EVENT_ITEM:
+	case TEP_EVENT_ITEM:
 		/* if it is a number, then convert it */
 		if (isdigit(token[0])) {
-			arg->type = FILTER_ARG_VALUE;
-			arg->value.type = FILTER_NUMBER;
+			arg->type = TEP_FILTER_ARG_VALUE;
+			arg->value.type = TEP_FILTER_NUMBER;
 			arg->value.val = strtoull(token, NULL, 0);
 			break;
 		}
@@ -377,12 +378,12 @@ create_arg_item(struct event_format *event, const char *token,
 				field = &cpu;
 			} else {
 				/* not a field, Make it false */
-				arg->type = FILTER_ARG_BOOLEAN;
-				arg->boolean.value = FILTER_FALSE;
+				arg->type = TEP_FILTER_ARG_BOOLEAN;
+				arg->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 		}
-		arg->type = FILTER_ARG_FIELD;
+		arg->type = TEP_FILTER_ARG_FIELD;
 		arg->field.field = field;
 		break;
 	default:
@@ -394,82 +395,82 @@ create_arg_item(struct event_format *event, const char *token,
 	return 0;
 }
 
-static struct filter_arg *
-create_arg_op(enum filter_op_type btype)
+static struct tep_filter_arg *
+create_arg_op(enum tep_filter_op_type btype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
 		return NULL;
 
-	arg->type = FILTER_ARG_OP;
+	arg->type = TEP_FILTER_ARG_OP;
 	arg->op.type = btype;
 
 	return arg;
 }
 
-static struct filter_arg *
-create_arg_exp(enum filter_exp_type etype)
+static struct tep_filter_arg *
+create_arg_exp(enum tep_filter_exp_type etype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
 		return NULL;
 
-	arg->type = FILTER_ARG_EXP;
+	arg->type = TEP_FILTER_ARG_EXP;
 	arg->exp.type = etype;
 
 	return arg;
 }
 
-static struct filter_arg *
-create_arg_cmp(enum filter_cmp_type ctype)
+static struct tep_filter_arg *
+create_arg_cmp(enum tep_filter_cmp_type ctype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
 		return NULL;
 
 	/* Use NUM and change if necessary */
-	arg->type = FILTER_ARG_NUM;
+	arg->type = TEP_FILTER_ARG_NUM;
 	arg->num.type = ctype;
 
 	return arg;
 }
 
 static enum tep_errno
-add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
+add_right(struct tep_filter_arg *op, struct tep_filter_arg *arg, char *error_str)
 {
-	struct filter_arg *left;
+	struct tep_filter_arg *left;
 	char *str;
 	int op_type;
 	int ret;
 
 	switch (op->type) {
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		if (op->exp.right)
 			goto out_fail;
 		op->exp.right = arg;
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		if (op->op.right)
 			goto out_fail;
 		op->op.right = arg;
 		break;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		if (op->op.right)
 			goto out_fail;
 		/*
 		 * The arg must be num, str, or field
 		 */
 		switch (arg->type) {
-		case FILTER_ARG_VALUE:
-		case FILTER_ARG_FIELD:
+		case TEP_FILTER_ARG_VALUE:
+		case TEP_FILTER_ARG_FIELD:
 			break;
 		default:
 			show_error(error_str, "Illegal rvalue");
@@ -481,20 +482,20 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 		 * convert this to a string or regex.
 		 */
 		switch (arg->value.type) {
-		case FILTER_CHAR:
+		case TEP_FILTER_CHAR:
 			/*
 			 * A char should be converted to number if
 			 * the string is 1 byte, and the compare
 			 * is not a REGEX.
 			 */
 			if (strlen(arg->value.str) == 1 &&
-			    op->num.type != FILTER_CMP_REGEX &&
-			    op->num.type != FILTER_CMP_NOT_REGEX) {
-				arg->value.type = FILTER_NUMBER;
+			    op->num.type != TEP_FILTER_CMP_REGEX &&
+			    op->num.type != TEP_FILTER_CMP_NOT_REGEX) {
+				arg->value.type = TEP_FILTER_NUMBER;
 				goto do_int;
 			}
 			/* fall through */
-		case FILTER_STRING:
+		case TEP_FILTER_STRING:
 
 			/* convert op to a string arg */
 			op_type = op->num.type;
@@ -508,16 +509,16 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 			 * If left arg was a field not found then
 			 * NULL the entire op.
 			 */
-			if (left->type == FILTER_ARG_BOOLEAN) {
+			if (left->type == TEP_FILTER_ARG_BOOLEAN) {
 				free_arg(left);
 				free_arg(arg);
-				op->type = FILTER_ARG_BOOLEAN;
-				op->boolean.value = FILTER_FALSE;
+				op->type = TEP_FILTER_ARG_BOOLEAN;
+				op->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 
 			/* Left arg must be a field */
-			if (left->type != FILTER_ARG_FIELD) {
+			if (left->type != TEP_FILTER_ARG_FIELD) {
 				show_error(error_str,
 					   "Illegal lvalue for string comparison");
 				return TEP_ERRNO__ILLEGAL_LVALUE;
@@ -525,15 +526,15 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 
 			/* Make sure this is a valid string compare */
 			switch (op_type) {
-			case FILTER_CMP_EQ:
-				op_type = FILTER_CMP_MATCH;
+			case TEP_FILTER_CMP_EQ:
+				op_type = TEP_FILTER_CMP_MATCH;
 				break;
-			case FILTER_CMP_NE:
-				op_type = FILTER_CMP_NOT_MATCH;
+			case TEP_FILTER_CMP_NE:
+				op_type = TEP_FILTER_CMP_NOT_MATCH;
 				break;
 
-			case FILTER_CMP_REGEX:
-			case FILTER_CMP_NOT_REGEX:
+			case TEP_FILTER_CMP_REGEX:
+			case TEP_FILTER_CMP_NOT_REGEX:
 				ret = regcomp(&op->str.reg, str, REG_ICASE|REG_NOSUB);
 				if (ret) {
 					show_error(error_str,
@@ -548,7 +549,7 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 				return TEP_ERRNO__ILLEGAL_STRING_CMP;
 			}
 
-			op->type = FILTER_ARG_STR;
+			op->type = TEP_FILTER_ARG_STR;
 			op->str.type = op_type;
 			op->str.field = left->field.field;
 			op->str.val = strdup(str);
@@ -573,12 +574,12 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 
 			break;
 
-		case FILTER_NUMBER:
+		case TEP_FILTER_NUMBER:
 
  do_int:
 			switch (op->num.type) {
-			case FILTER_CMP_REGEX:
-			case FILTER_CMP_NOT_REGEX:
+			case TEP_FILTER_CMP_REGEX:
+			case TEP_FILTER_CMP_NOT_REGEX:
 				show_error(error_str,
 					   "Op not allowed with integers");
 				return TEP_ERRNO__ILLEGAL_INTEGER_CMP;
@@ -605,35 +606,35 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 	return TEP_ERRNO__SYNTAX_ERROR;
 }
 
-static struct filter_arg *
-rotate_op_right(struct filter_arg *a, struct filter_arg *b)
+static struct tep_filter_arg *
+rotate_op_right(struct tep_filter_arg *a, struct tep_filter_arg *b)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = a->op.right;
 	a->op.right = b;
 	return arg;
 }
 
-static enum tep_errno add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum tep_errno add_left(struct tep_filter_arg *op, struct tep_filter_arg *arg)
 {
 	switch (op->type) {
-	case FILTER_ARG_EXP:
-		if (arg->type == FILTER_ARG_OP)
+	case TEP_FILTER_ARG_EXP:
+		if (arg->type == TEP_FILTER_ARG_OP)
 			arg = rotate_op_right(arg, op);
 		op->exp.left = arg;
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		op->op.left = arg;
 		break;
-	case FILTER_ARG_NUM:
-		if (arg->type == FILTER_ARG_OP)
+	case TEP_FILTER_ARG_NUM:
+		if (arg->type == TEP_FILTER_ARG_OP)
 			arg = rotate_op_right(arg, op);
 
 		/* left arg of compares must be a field */
-		if (arg->type != FILTER_ARG_FIELD &&
-		    arg->type != FILTER_ARG_BOOLEAN)
+		if (arg->type != TEP_FILTER_ARG_FIELD &&
+		    arg->type != TEP_FILTER_ARG_BOOLEAN)
 			return TEP_ERRNO__INVALID_ARG_TYPE;
 		op->num.left = arg;
 		break;
@@ -652,91 +653,91 @@ enum op_type {
 };
 
 static enum op_type process_op(const char *token,
-			       enum filter_op_type *btype,
-			       enum filter_cmp_type *ctype,
-			       enum filter_exp_type *etype)
+			       enum tep_filter_op_type *btype,
+			       enum tep_filter_cmp_type *ctype,
+			       enum tep_filter_exp_type *etype)
 {
-	*btype = FILTER_OP_NOT;
-	*etype = FILTER_EXP_NONE;
-	*ctype = FILTER_CMP_NONE;
+	*btype = TEP_FILTER_OP_NOT;
+	*etype = TEP_FILTER_EXP_NONE;
+	*ctype = TEP_FILTER_CMP_NONE;
 
 	if (strcmp(token, "&&") == 0)
-		*btype = FILTER_OP_AND;
+		*btype = TEP_FILTER_OP_AND;
 	else if (strcmp(token, "||") == 0)
-		*btype = FILTER_OP_OR;
+		*btype = TEP_FILTER_OP_OR;
 	else if (strcmp(token, "!") == 0)
 		return OP_NOT;
 
-	if (*btype != FILTER_OP_NOT)
+	if (*btype != TEP_FILTER_OP_NOT)
 		return OP_BOOL;
 
 	/* Check for value expressions */
 	if (strcmp(token, "+") == 0) {
-		*etype = FILTER_EXP_ADD;
+		*etype = TEP_FILTER_EXP_ADD;
 	} else if (strcmp(token, "-") == 0) {
-		*etype = FILTER_EXP_SUB;
+		*etype = TEP_FILTER_EXP_SUB;
 	} else if (strcmp(token, "*") == 0) {
-		*etype = FILTER_EXP_MUL;
+		*etype = TEP_FILTER_EXP_MUL;
 	} else if (strcmp(token, "/") == 0) {
-		*etype = FILTER_EXP_DIV;
+		*etype = TEP_FILTER_EXP_DIV;
 	} else if (strcmp(token, "%") == 0) {
-		*etype = FILTER_EXP_MOD;
+		*etype = TEP_FILTER_EXP_MOD;
 	} else if (strcmp(token, ">>") == 0) {
-		*etype = FILTER_EXP_RSHIFT;
+		*etype = TEP_FILTER_EXP_RSHIFT;
 	} else if (strcmp(token, "<<") == 0) {
-		*etype = FILTER_EXP_LSHIFT;
+		*etype = TEP_FILTER_EXP_LSHIFT;
 	} else if (strcmp(token, "&") == 0) {
-		*etype = FILTER_EXP_AND;
+		*etype = TEP_FILTER_EXP_AND;
 	} else if (strcmp(token, "|") == 0) {
-		*etype = FILTER_EXP_OR;
+		*etype = TEP_FILTER_EXP_OR;
 	} else if (strcmp(token, "^") == 0) {
-		*etype = FILTER_EXP_XOR;
+		*etype = TEP_FILTER_EXP_XOR;
 	} else if (strcmp(token, "~") == 0)
-		*etype = FILTER_EXP_NOT;
+		*etype = TEP_FILTER_EXP_NOT;
 
-	if (*etype != FILTER_EXP_NONE)
+	if (*etype != TEP_FILTER_EXP_NONE)
 		return OP_EXP;
 
 	/* Check for compares */
 	if (strcmp(token, "==") == 0)
-		*ctype = FILTER_CMP_EQ;
+		*ctype = TEP_FILTER_CMP_EQ;
 	else if (strcmp(token, "!=") == 0)
-		*ctype = FILTER_CMP_NE;
+		*ctype = TEP_FILTER_CMP_NE;
 	else if (strcmp(token, "<") == 0)
-		*ctype = FILTER_CMP_LT;
+		*ctype = TEP_FILTER_CMP_LT;
 	else if (strcmp(token, ">") == 0)
-		*ctype = FILTER_CMP_GT;
+		*ctype = TEP_FILTER_CMP_GT;
 	else if (strcmp(token, "<=") == 0)
-		*ctype = FILTER_CMP_LE;
+		*ctype = TEP_FILTER_CMP_LE;
 	else if (strcmp(token, ">=") == 0)
-		*ctype = FILTER_CMP_GE;
+		*ctype = TEP_FILTER_CMP_GE;
 	else if (strcmp(token, "=~") == 0)
-		*ctype = FILTER_CMP_REGEX;
+		*ctype = TEP_FILTER_CMP_REGEX;
 	else if (strcmp(token, "!~") == 0)
-		*ctype = FILTER_CMP_NOT_REGEX;
+		*ctype = TEP_FILTER_CMP_NOT_REGEX;
 	else
 		return OP_NONE;
 
 	return OP_CMP;
 }
 
-static int check_op_done(struct filter_arg *arg)
+static int check_op_done(struct tep_filter_arg *arg)
 {
 	switch (arg->type) {
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return arg->exp.right != NULL;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return arg->op.right != NULL;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return arg->num.right != NULL;
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		/* A string conversion is always done */
 		return 1;
 
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		/* field not found, is ok */
 		return 1;
 
@@ -752,14 +753,14 @@ enum filter_vals {
 };
 
 static enum tep_errno
-reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		struct filter_arg *arg, char *error_str)
+reparent_op_arg(struct tep_filter_arg *parent, struct tep_filter_arg *old_child,
+		struct tep_filter_arg *arg, char *error_str)
 {
-	struct filter_arg *other_child;
-	struct filter_arg **ptr;
+	struct tep_filter_arg *other_child;
+	struct tep_filter_arg **ptr;
 
-	if (parent->type != FILTER_ARG_OP &&
-	    arg->type != FILTER_ARG_OP) {
+	if (parent->type != TEP_FILTER_ARG_OP &&
+	    arg->type != TEP_FILTER_ARG_OP) {
 		show_error(error_str, "can not reparent other than OP");
 		return TEP_ERRNO__REPARENT_NOT_OP;
 	}
@@ -804,7 +805,7 @@ reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 }
 
 /* Returns either filter_vals (success) or tep_errno (failfure) */
-static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+static int test_arg(struct tep_filter_arg *parent, struct tep_filter_arg *arg,
 		    char *error_str)
 {
 	int lval, rval;
@@ -812,16 +813,16 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 	switch (arg->type) {
 
 		/* bad case */
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		return FILTER_VAL_FALSE + arg->boolean.value;
 
 		/* good cases: */
-	case FILTER_ARG_STR:
-	case FILTER_ARG_VALUE:
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_STR:
+	case TEP_FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_FIELD:
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		lval = test_arg(arg, arg->exp.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
@@ -830,7 +831,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			return rval;
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		lval = test_arg(arg, arg->num.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
@@ -839,14 +840,14 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			return rval;
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_OP:
-		if (arg->op.type != FILTER_OP_NOT) {
+	case TEP_FILTER_ARG_OP:
+		if (arg->op.type != TEP_FILTER_OP_NOT) {
 			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
 			case FILTER_VAL_NORM:
 				break;
 			case FILTER_VAL_TRUE:
-				if (arg->op.type == FILTER_OP_OR)
+				if (arg->op.type == TEP_FILTER_OP_OR)
 					return FILTER_VAL_TRUE;
 				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
@@ -856,7 +857,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 						       error_str);
 
 			case FILTER_VAL_FALSE:
-				if (arg->op.type == FILTER_OP_AND)
+				if (arg->op.type == TEP_FILTER_OP_AND)
 					return FILTER_VAL_FALSE;
 				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
@@ -877,18 +878,18 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			break;
 
 		case FILTER_VAL_TRUE:
-			if (arg->op.type == FILTER_OP_OR)
+			if (arg->op.type == TEP_FILTER_OP_OR)
 				return FILTER_VAL_TRUE;
-			if (arg->op.type == FILTER_OP_NOT)
+			if (arg->op.type == TEP_FILTER_OP_NOT)
 				return FILTER_VAL_FALSE;
 
 			return reparent_op_arg(parent, arg, arg->op.left,
 					       error_str);
 
 		case FILTER_VAL_FALSE:
-			if (arg->op.type == FILTER_OP_AND)
+			if (arg->op.type == TEP_FILTER_OP_AND)
 				return FILTER_VAL_FALSE;
-			if (arg->op.type == FILTER_OP_NOT)
+			if (arg->op.type == TEP_FILTER_OP_NOT)
 				return FILTER_VAL_TRUE;
 
 			return reparent_op_arg(parent, arg, arg->op.left,
@@ -904,8 +905,8 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 }
 
 /* Remove any unknown event fields */
-static int collapse_tree(struct filter_arg *arg,
-			 struct filter_arg **arg_collapsed, char *error_str)
+static int collapse_tree(struct tep_filter_arg *arg,
+			 struct tep_filter_arg **arg_collapsed, char *error_str)
 {
 	int ret;
 
@@ -919,7 +920,7 @@ static int collapse_tree(struct filter_arg *arg,
 		free_arg(arg);
 		arg = allocate_arg();
 		if (arg) {
-			arg->type = FILTER_ARG_BOOLEAN;
+			arg->type = TEP_FILTER_ARG_BOOLEAN;
 			arg->boolean.value = ret == FILTER_VAL_TRUE;
 		} else {
 			show_error(error_str, "Failed to allocate filter arg");
@@ -939,19 +940,19 @@ static int collapse_tree(struct filter_arg *arg,
 }
 
 static enum tep_errno
-process_filter(struct event_format *event, struct filter_arg **parg,
+process_filter(struct tep_event_format *event, struct tep_filter_arg **parg,
 	       char *error_str, int not)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
-	struct filter_arg *current_op = NULL;
-	struct filter_arg *current_exp = NULL;
-	struct filter_arg *left_item = NULL;
-	struct filter_arg *arg = NULL;
+	struct tep_filter_arg *current_op = NULL;
+	struct tep_filter_arg *current_exp = NULL;
+	struct tep_filter_arg *left_item = NULL;
+	struct tep_filter_arg *arg = NULL;
 	enum op_type op_type;
-	enum filter_op_type btype;
-	enum filter_exp_type etype;
-	enum filter_cmp_type ctype;
+	enum tep_filter_op_type btype;
+	enum tep_filter_exp_type etype;
+	enum tep_filter_cmp_type ctype;
 	enum tep_errno ret;
 
 	*parg = NULL;
@@ -960,9 +961,9 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		free(token);
 		type = read_token(&token);
 		switch (type) {
-		case EVENT_SQUOTE:
-		case EVENT_DQUOTE:
-		case EVENT_ITEM:
+		case TEP_EVENT_SQUOTE:
+		case TEP_EVENT_DQUOTE:
+		case TEP_EVENT_ITEM:
 			ret = create_arg_item(event, token, type, &arg, error_str);
 			if (ret < 0)
 				goto fail;
@@ -987,7 +988,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			arg = NULL;
 			break;
 
-		case EVENT_DELIM:
+		case TEP_EVENT_DELIM:
 			if (*token == ',') {
 				show_error(error_str, "Illegal token ','");
 				ret = TEP_ERRNO__ILLEGAL_TOKEN;
@@ -1054,7 +1055,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			}
 			break;
 
-		case EVENT_OP:
+		case TEP_EVENT_OP:
 			op_type = process_op(token, &btype, &ctype, &etype);
 
 			/* All expect a left arg except for NOT */
@@ -1139,14 +1140,14 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			if (ret < 0)
 				goto fail_syntax;
 			break;
-		case EVENT_NONE:
+		case TEP_EVENT_NONE:
 			break;
-		case EVENT_ERROR:
+		case TEP_EVENT_ERROR:
 			goto fail_alloc;
 		default:
 			goto fail_syntax;
 		}
-	} while (type != EVENT_NONE);
+	} while (type != TEP_EVENT_NONE);
 
 	if (!current_op && !current_exp)
 		goto fail_syntax;
@@ -1179,8 +1180,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 }
 
 static enum tep_errno
-process_event(struct event_format *event, const char *filter_str,
-	      struct filter_arg **parg, char *error_str)
+process_event(struct tep_event_format *event, const char *filter_str,
+	      struct tep_filter_arg **parg, char *error_str)
 {
 	int ret;
 
@@ -1196,19 +1197,19 @@ process_event(struct event_format *event, const char *filter_str,
 		if (*parg == NULL)
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
-		(*parg)->type = FILTER_ARG_BOOLEAN;
-		(*parg)->boolean.value = FILTER_FALSE;
+		(*parg)->type = TEP_FILTER_ARG_BOOLEAN;
+		(*parg)->boolean.value = TEP_FILTER_FALSE;
 	}
 
 	return 0;
 }
 
 static enum tep_errno
-filter_event(struct event_filter *filter, struct event_format *event,
+filter_event(struct tep_event_filter *filter, struct tep_event_format *event,
 	     const char *filter_str, char *error_str)
 {
-	struct filter_type *filter_type;
-	struct filter_arg *arg;
+	struct tep_filter_type *filter_type;
+	struct tep_filter_arg *arg;
 	enum tep_errno ret;
 
 	if (filter_str) {
@@ -1222,8 +1223,8 @@ filter_event(struct event_filter *filter, struct event_format *event,
 		if (arg == NULL)
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
-		arg->type = FILTER_ARG_BOOLEAN;
-		arg->boolean.value = FILTER_TRUE;
+		arg->type = TEP_FILTER_ARG_BOOLEAN;
+		arg->boolean.value = TEP_FILTER_TRUE;
 	}
 
 	filter_type = add_filter_type(filter, event->id);
@@ -1237,7 +1238,7 @@ filter_event(struct event_filter *filter, struct event_format *event,
 	return 0;
 }
 
-static void filter_init_error_buf(struct event_filter *filter)
+static void filter_init_error_buf(struct tep_event_filter *filter)
 {
 	/* clear buffer to reset show error */
 	tep_buffer_init("", 0);
@@ -1253,7 +1254,7 @@ static void filter_init_error_buf(struct event_filter *filter)
  * negative error code.  Use tep_filter_strerror() to see
  * actual error message in case of error.
  */
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str)
 {
 	struct tep_handle *pevent = filter->pevent;
@@ -1351,7 +1352,7 @@ enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
 	return rtn;
 }
 
-static void free_filter_type(struct filter_type *filter_type)
+static void free_filter_type(struct tep_filter_type *filter_type)
 {
 	free_arg(filter_type->filter);
 }
@@ -1365,7 +1366,7 @@ static void free_filter_type(struct filter_type *filter_type)
  *
  * Returns 0 if message was filled successfully, -1 if error
  */
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 			char *buf, size_t buflen)
 {
 	if (err <= __TEP_ERRNO__START || err >= __TEP_ERRNO__END)
@@ -1393,10 +1394,10 @@ int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
  * Returns 1: if an event was removed
  *   0: if the event was not found
  */
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	unsigned long len;
 
 	if (!filter->filters)
@@ -1428,7 +1429,7 @@ int tep_filter_remove_event(struct event_filter *filter,
  *
  * Removes all filters from a filter and resets it.
  */
-void tep_filter_reset(struct event_filter *filter)
+void tep_filter_reset(struct tep_event_filter *filter)
 {
 	int i;
 
@@ -1440,7 +1441,7 @@ void tep_filter_reset(struct event_filter *filter)
 	filter->event_filters = NULL;
 }
 
-void tep_filter_free(struct event_filter *filter)
+void tep_filter_free(struct tep_event_filter *filter)
 {
 	tep_unref(filter->pevent);
 
@@ -1449,14 +1450,14 @@ void tep_filter_free(struct event_filter *filter)
 	free(filter);
 }
 
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg);
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg);
 
-static int copy_filter_type(struct event_filter *filter,
-			     struct event_filter *source,
-			     struct filter_type *filter_type)
+static int copy_filter_type(struct tep_event_filter *filter,
+			    struct tep_event_filter *source,
+			    struct tep_filter_type *filter_type)
 {
-	struct filter_arg *arg;
-	struct event_format *event;
+	struct tep_filter_arg *arg;
+	struct tep_event_format *event;
 	const char *sys;
 	const char *name;
 	char *str;
@@ -1478,7 +1479,7 @@ static int copy_filter_type(struct event_filter *filter,
 		if (arg == NULL)
 			return -1;
 
-		arg->type = FILTER_ARG_BOOLEAN;
+		arg->type = TEP_FILTER_ARG_BOOLEAN;
 		if (strcmp(str, "TRUE") == 0)
 			arg->boolean.value = 1;
 		else
@@ -1507,7 +1508,7 @@ static int copy_filter_type(struct event_filter *filter,
  *
  * Returns 0 on success and -1 if not all filters were copied
  */
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source)
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source)
 {
 	int ret = 0;
 	int i;
@@ -1533,14 +1534,14 @@ int tep_filter_copy(struct event_filter *dest, struct event_filter *source)
  * Returns 0 on success and -1 if there was a problem updating, but
  *   events may have still been updated on error.
  */
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
-		       enum filter_trivial_type type)
+int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
+		       enum tep_filter_trivial_type type)
 {
 	struct tep_handle *src_pevent;
 	struct tep_handle *dest_pevent;
-	struct event_format *event;
-	struct filter_type *filter_type;
-	struct filter_arg *arg;
+	struct tep_event_format *event;
+	struct tep_filter_type *filter_type;
+	struct tep_filter_arg *arg;
 	char *str;
 	int i;
 
@@ -1554,10 +1555,10 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
 	for (i = 0; i < dest->filters; i++) {
 		filter_type = &dest->event_filters[i];
 		arg = filter_type->filter;
-		if (arg->type != FILTER_ARG_BOOLEAN)
+		if (arg->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
-		if ((arg->boolean.value && type == FILTER_TRIVIAL_FALSE) ||
-		    (!arg->boolean.value && type == FILTER_TRIVIAL_TRUE))
+		if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
+		    (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
 			continue;
 
 		event = filter_type->event;
@@ -1592,10 +1593,10 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
  *
  * Returns 0 on success and -1 if there was a problem.
  */
-int tep_filter_clear_trivial(struct event_filter *filter,
-			     enum filter_trivial_type type)
+int tep_filter_clear_trivial(struct tep_event_filter *filter,
+			     enum tep_filter_trivial_type type)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int count = 0;
 	int *ids = NULL;
 	int i;
@@ -1611,14 +1612,14 @@ int tep_filter_clear_trivial(struct event_filter *filter,
 		int *new_ids;
 
 		filter_type = &filter->event_filters[i];
-		if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
+		if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
 		switch (type) {
-		case FILTER_TRIVIAL_FALSE:
+		case TEP_FILTER_TRIVIAL_FALSE:
 			if (filter_type->filter->boolean.value)
 				continue;
 			break;
-		case FILTER_TRIVIAL_TRUE:
+		case TEP_FILTER_TRIVIAL_TRUE:
 			if (!filter_type->filter->boolean.value)
 				continue;
 		default:
@@ -1654,11 +1655,11 @@ int tep_filter_clear_trivial(struct event_filter *filter,
  * Returns 1 if the event contains a matching trivial type
  *  otherwise 0.
  */
-int tep_filter_event_has_trivial(struct event_filter *filter,
+int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
-				 enum filter_trivial_type type)
+				 enum tep_filter_trivial_type type)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return 0;
@@ -1668,25 +1669,25 @@ int tep_filter_event_has_trivial(struct event_filter *filter,
 	if (!filter_type)
 		return 0;
 
-	if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
+	if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
 		return 0;
 
 	switch (type) {
-	case FILTER_TRIVIAL_FALSE:
+	case TEP_FILTER_TRIVIAL_FALSE:
 		return !filter_type->filter->boolean.value;
 
-	case FILTER_TRIVIAL_TRUE:
+	case TEP_FILTER_TRIVIAL_TRUE:
 		return filter_type->filter->boolean.value;
 	default:
 		return 1;
 	}
 }
 
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err);
 
 static const char *
-get_comm(struct event_format *event, struct tep_record *record)
+get_comm(struct tep_event_format *event, struct tep_record *record)
 {
 	const char *comm;
 	int pid;
@@ -1697,8 +1698,8 @@ get_comm(struct event_format *event, struct tep_record *record)
 }
 
 static unsigned long long
-get_value(struct event_format *event,
-	  struct format_field *field, struct tep_record *record)
+get_value(struct tep_event_format *event,
+	  struct tep_format_field *field, struct tep_record *record)
 {
 	unsigned long long val;
 
@@ -1716,7 +1717,7 @@ get_value(struct event_format *event,
 
 	tep_read_number_field(field, record->data, &val);
 
-	if (!(field->flags & FIELD_IS_SIGNED))
+	if (!(field->flags & TEP_FIELD_IS_SIGNED))
 		return val;
 
 	switch (field->size) {
@@ -1733,11 +1734,11 @@ get_value(struct event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err);
 
 static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg,
+get_exp_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1753,37 +1754,37 @@ get_exp_value(struct event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->exp.type) {
-	case FILTER_EXP_ADD:
+	case TEP_FILTER_EXP_ADD:
 		return lval + rval;
 
-	case FILTER_EXP_SUB:
+	case TEP_FILTER_EXP_SUB:
 		return lval - rval;
 
-	case FILTER_EXP_MUL:
+	case TEP_FILTER_EXP_MUL:
 		return lval * rval;
 
-	case FILTER_EXP_DIV:
+	case TEP_FILTER_EXP_DIV:
 		return lval / rval;
 
-	case FILTER_EXP_MOD:
+	case TEP_FILTER_EXP_MOD:
 		return lval % rval;
 
-	case FILTER_EXP_RSHIFT:
+	case TEP_FILTER_EXP_RSHIFT:
 		return lval >> rval;
 
-	case FILTER_EXP_LSHIFT:
+	case TEP_FILTER_EXP_LSHIFT:
 		return lval << rval;
 
-	case FILTER_EXP_AND:
+	case TEP_FILTER_EXP_AND:
 		return lval & rval;
 
-	case FILTER_EXP_OR:
+	case TEP_FILTER_EXP_OR:
 		return lval | rval;
 
-	case FILTER_EXP_XOR:
+	case TEP_FILTER_EXP_XOR:
 		return lval ^ rval;
 
-	case FILTER_EXP_NOT:
+	case TEP_FILTER_EXP_NOT:
 	default:
 		if (!*err)
 			*err = TEP_ERRNO__INVALID_EXP_TYPE;
@@ -1792,21 +1793,21 @@ get_exp_value(struct event_format *event, struct filter_arg *arg,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->type) {
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_FIELD:
 		return get_value(event, arg->field.field, record);
 
-	case FILTER_ARG_VALUE:
-		if (arg->value.type != FILTER_NUMBER) {
+	case TEP_FILTER_ARG_VALUE:
+		if (arg->value.type != TEP_FILTER_NUMBER) {
 			if (!*err)
 				*err = TEP_ERRNO__NOT_A_NUMBER;
 		}
 		return arg->value.val;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return get_exp_value(event, arg, record, err);
 
 	default:
@@ -1816,7 +1817,7 @@ get_arg_value(struct event_format *event, struct filter_arg *arg,
 	return 0;
 }
 
-static int test_num(struct event_format *event, struct filter_arg *arg,
+static int test_num(struct tep_event_format *event, struct tep_filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1832,22 +1833,22 @@ static int test_num(struct event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->num.type) {
-	case FILTER_CMP_EQ:
+	case TEP_FILTER_CMP_EQ:
 		return lval == rval;
 
-	case FILTER_CMP_NE:
+	case TEP_FILTER_CMP_NE:
 		return lval != rval;
 
-	case FILTER_CMP_GT:
+	case TEP_FILTER_CMP_GT:
 		return lval > rval;
 
-	case FILTER_CMP_LT:
+	case TEP_FILTER_CMP_LT:
 		return lval < rval;
 
-	case FILTER_CMP_GE:
+	case TEP_FILTER_CMP_GE:
 		return lval >= rval;
 
-	case FILTER_CMP_LE:
+	case TEP_FILTER_CMP_LE:
 		return lval <= rval;
 
 	default:
@@ -1857,9 +1858,9 @@ static int test_num(struct event_format *event, struct filter_arg *arg,
 	}
 }
 
-static const char *get_field_str(struct filter_arg *arg, struct tep_record *record)
+static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct tep_handle *pevent;
 	unsigned long long addr;
 	const char *val = NULL;
@@ -1867,11 +1868,11 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 	char hex[64];
 
 	/* If the field is not a string convert it */
-	if (arg->str.field->flags & FIELD_IS_STRING) {
+	if (arg->str.field->flags & TEP_FIELD_IS_STRING) {
 		val = record->data + arg->str.field->offset;
 		size = arg->str.field->size;
 
-		if (arg->str.field->flags & FIELD_IS_DYNAMIC) {
+		if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) {
 			addr = *(unsigned int *)val;
 			val = record->data + (addr & 0xffff);
 			size = addr >> 16;
@@ -1893,7 +1894,7 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 		pevent = event->pevent;
 		addr = get_value(event, arg->str.field, record);
 
-		if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG))
+		if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
 			/* convert to a kernel symbol */
 			val = tep_find_function(pevent, addr);
 
@@ -1907,7 +1908,7 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 	return val;
 }
 
-static int test_str(struct event_format *event, struct filter_arg *arg,
+static int test_str(struct tep_event_format *event, struct tep_filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	const char *val;
@@ -1918,17 +1919,17 @@ static int test_str(struct event_format *event, struct filter_arg *arg,
 		val = get_field_str(arg, record);
 
 	switch (arg->str.type) {
-	case FILTER_CMP_MATCH:
+	case TEP_FILTER_CMP_MATCH:
 		return strcmp(val, arg->str.val) == 0;
 
-	case FILTER_CMP_NOT_MATCH:
+	case TEP_FILTER_CMP_NOT_MATCH:
 		return strcmp(val, arg->str.val) != 0;
 
-	case FILTER_CMP_REGEX:
+	case TEP_FILTER_CMP_REGEX:
 		/* Returns zero on match */
 		return !regexec(&arg->str.reg, val, 0, NULL, 0);
 
-	case FILTER_CMP_NOT_REGEX:
+	case TEP_FILTER_CMP_NOT_REGEX:
 		return regexec(&arg->str.reg, val, 0, NULL, 0);
 
 	default:
@@ -1938,19 +1939,19 @@ static int test_str(struct event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_op(struct event_format *event, struct filter_arg *arg,
+static int test_op(struct tep_event_format *event, struct tep_filter_arg *arg,
 		   struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->op.type) {
-	case FILTER_OP_AND:
+	case TEP_FILTER_OP_AND:
 		return test_filter(event, arg->op.left, record, err) &&
 			test_filter(event, arg->op.right, record, err);
 
-	case FILTER_OP_OR:
+	case TEP_FILTER_OP_OR:
 		return test_filter(event, arg->op.left, record, err) ||
 			test_filter(event, arg->op.right, record, err);
 
-	case FILTER_OP_NOT:
+	case TEP_FILTER_OP_NOT:
 		return !test_filter(event, arg->op.right, record, err);
 
 	default:
@@ -1960,7 +1961,7 @@ static int test_op(struct event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err)
 {
 	if (*err) {
@@ -1971,22 +1972,22 @@ static int test_filter(struct event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->type) {
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		/* easy case */
 		return arg->boolean.value;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return test_op(event, arg, record, err);
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return test_num(event, arg, record, err);
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		return test_str(event, arg, record, err);
 
-	case FILTER_ARG_EXP:
-	case FILTER_ARG_VALUE:
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_FIELD:
 		/*
 		 * Expressions, fields and values evaluate
 		 * to true if they return non zero
@@ -2008,9 +2009,9 @@ static int test_filter(struct event_format *event, struct filter_arg *arg,
  * Returns 1 if filter found for @event_id
  *   otherwise 0;
  */
-int tep_event_filtered(struct event_filter *filter, int event_id)
+int tep_event_filtered(struct tep_event_filter *filter, int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return 0;
@@ -2032,11 +2033,11 @@ int tep_event_filtered(struct event_filter *filter, int event_id)
  * NO_FILTER - if no filters exist
  * otherwise - error occurred during test
  */
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record)
 {
 	struct tep_handle *pevent = filter->pevent;
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int event_id;
 	int ret;
 	enum tep_errno err = 0;
@@ -2059,7 +2060,7 @@ enum tep_errno tep_filter_match(struct event_filter *filter,
 	return ret ? TEP_ERRNO__FILTER_MATCH : TEP_ERRNO__FILTER_MISS;
 }
 
-static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *left = NULL;
@@ -2070,10 +2071,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	int val;
 
 	switch (arg->op.type) {
-	case FILTER_OP_AND:
+	case TEP_FILTER_OP_AND:
 		op = "&&";
 		/* fall through */
-	case FILTER_OP_OR:
+	case TEP_FILTER_OP_OR:
 		if (!op)
 			op = "||";
 
@@ -2094,8 +2095,8 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			right_val = 0;
 
 		if (left_val >= 0) {
-			if ((arg->op.type == FILTER_OP_AND && !left_val) ||
-			    (arg->op.type == FILTER_OP_OR && left_val)) {
+			if ((arg->op.type == TEP_FILTER_OP_AND && !left_val) ||
+			    (arg->op.type == TEP_FILTER_OP_OR && left_val)) {
 				/* Just return left value */
 				str = left;
 				left = NULL;
@@ -2105,10 +2106,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 				/* just evaluate this. */
 				val = 0;
 				switch (arg->op.type) {
-				case FILTER_OP_AND:
+				case TEP_FILTER_OP_AND:
 					val = left_val && right_val;
 					break;
-				case FILTER_OP_OR:
+				case TEP_FILTER_OP_OR:
 					val = left_val || right_val;
 					break;
 				default:
@@ -2119,8 +2120,8 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			}
 		}
 		if (right_val >= 0) {
-			if ((arg->op.type == FILTER_OP_AND && !right_val) ||
-			    (arg->op.type == FILTER_OP_OR && right_val)) {
+			if ((arg->op.type == TEP_FILTER_OP_AND && !right_val) ||
+			    (arg->op.type == TEP_FILTER_OP_OR && right_val)) {
 				/* Just return right value */
 				str = right;
 				right = NULL;
@@ -2135,7 +2136,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 		asprintf(&str, "(%s) %s (%s)", left, op, right);
 		break;
 
-	case FILTER_OP_NOT:
+	case TEP_FILTER_OP_NOT:
 		op = "!";
 		right = arg_to_str(filter, arg->op.right);
 		if (!right)
@@ -2163,7 +2164,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *val_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
@@ -2172,12 +2173,12 @@ static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *field_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *field_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	return strdup(arg->field.field->name);
 }
 
-static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *exp_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2190,34 +2191,34 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 		goto out;
 
 	switch (arg->exp.type) {
-	case FILTER_EXP_ADD:
+	case TEP_FILTER_EXP_ADD:
 		op = "+";
 		break;
-	case FILTER_EXP_SUB:
+	case TEP_FILTER_EXP_SUB:
 		op = "-";
 		break;
-	case FILTER_EXP_MUL:
+	case TEP_FILTER_EXP_MUL:
 		op = "*";
 		break;
-	case FILTER_EXP_DIV:
+	case TEP_FILTER_EXP_DIV:
 		op = "/";
 		break;
-	case FILTER_EXP_MOD:
+	case TEP_FILTER_EXP_MOD:
 		op = "%";
 		break;
-	case FILTER_EXP_RSHIFT:
+	case TEP_FILTER_EXP_RSHIFT:
 		op = ">>";
 		break;
-	case FILTER_EXP_LSHIFT:
+	case TEP_FILTER_EXP_LSHIFT:
 		op = "<<";
 		break;
-	case FILTER_EXP_AND:
+	case TEP_FILTER_EXP_AND:
 		op = "&";
 		break;
-	case FILTER_EXP_OR:
+	case TEP_FILTER_EXP_OR:
 		op = "|";
 		break;
-	case FILTER_EXP_XOR:
+	case TEP_FILTER_EXP_XOR:
 		op = "^";
 		break;
 	default:
@@ -2233,7 +2234,7 @@ out:
 	return str;
 }
 
-static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *num_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2246,26 +2247,26 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		goto out;
 
 	switch (arg->num.type) {
-	case FILTER_CMP_EQ:
+	case TEP_FILTER_CMP_EQ:
 		op = "==";
 		/* fall through */
-	case FILTER_CMP_NE:
+	case TEP_FILTER_CMP_NE:
 		if (!op)
 			op = "!=";
 		/* fall through */
-	case FILTER_CMP_GT:
+	case TEP_FILTER_CMP_GT:
 		if (!op)
 			op = ">";
 		/* fall through */
-	case FILTER_CMP_LT:
+	case TEP_FILTER_CMP_LT:
 		if (!op)
 			op = "<";
 		/* fall through */
-	case FILTER_CMP_GE:
+	case TEP_FILTER_CMP_GE:
 		if (!op)
 			op = ">=";
 		/* fall through */
-	case FILTER_CMP_LE:
+	case TEP_FILTER_CMP_LE:
 		if (!op)
 			op = "<=";
 
@@ -2283,24 +2284,24 @@ out:
 	return str;
 }
 
-static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *str_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
 
 	switch (arg->str.type) {
-	case FILTER_CMP_MATCH:
+	case TEP_FILTER_CMP_MATCH:
 		op = "==";
 		/* fall through */
-	case FILTER_CMP_NOT_MATCH:
+	case TEP_FILTER_CMP_NOT_MATCH:
 		if (!op)
 			op = "!=";
 		/* fall through */
-	case FILTER_CMP_REGEX:
+	case TEP_FILTER_CMP_REGEX:
 		if (!op)
 			op = "=~";
 		/* fall through */
-	case FILTER_CMP_NOT_REGEX:
+	case TEP_FILTER_CMP_NOT_REGEX:
 		if (!op)
 			op = "!~";
 
@@ -2315,31 +2316,31 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
 	switch (arg->type) {
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
 		return str;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return op_to_str(filter, arg);
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return num_to_str(filter, arg);
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		return str_to_str(filter, arg);
 
-	case FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_VALUE:
 		return val_to_str(filter, arg);
 
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_FIELD:
 		return field_to_str(filter, arg);
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return exp_to_str(filter, arg);
 
 	default:
@@ -2359,9 +2360,9 @@ static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
  *  NULL is returned if no filter is found or allocation failed.
  */
 char *
-tep_filter_make_string(struct event_filter *filter, int event_id)
+tep_filter_make_string(struct tep_event_filter *filter, int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return NULL;
@@ -2383,10 +2384,10 @@ tep_filter_make_string(struct event_filter *filter, int event_id)
  *  1 if the two filters hold the same content.
  *  0 if they do not.
  */
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2)
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2)
 {
-	struct filter_type *filter_type1;
-	struct filter_type *filter_type2;
+	struct tep_filter_type *filter_type1;
+	struct tep_filter_type *filter_type2;
 	char *str1, *str2;
 	int result;
 	int i;
@@ -2409,8 +2410,8 @@ int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter
 		if (filter_type1->filter->type != filter_type2->filter->type)
 			break;
 		switch (filter_type1->filter->type) {
-		case FILTER_TRIVIAL_FALSE:
-		case FILTER_TRIVIAL_TRUE:
+		case TEP_FILTER_TRIVIAL_FALSE:
+		case TEP_FILTER_TRIVIAL_TRUE:
 			/* trivial types just need the type compared */
 			continue;
 		default:
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 424747475d37..528acc75d81a 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -23,6 +23,7 @@
 
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static struct func_stack {
 	int size;
@@ -123,7 +124,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
 }
 
 static int function_handler(struct trace_seq *s, struct tep_record *record,
-			    struct event_format *event, void *context)
+			    struct tep_event_format *event, void *context)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long function;
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index b43bfec565d8..9aa05b4ca811 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -23,10 +23,11 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int timer_expire_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	trace_seq_printf(s, "hrtimer=");
 
@@ -46,7 +47,7 @@ static int timer_expire_handler(struct trace_seq *s,
 
 static int timer_start_handler(struct trace_seq *s,
 			       struct tep_record *record,
-			       struct event_format *event, void *context)
+			       struct tep_event_format *event, void *context)
 {
 	trace_seq_printf(s, "hrtimer=");
 
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 45a9acd19640..a5e34135dd6a 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define MINORBITS	20
 #define MINORMASK	((1U << MINORBITS) - 1)
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 73966b05abce..1beb4eaddfdf 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -22,11 +22,12 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int call_site_handler(struct trace_seq *s, struct tep_record *record,
-			     struct event_format *event, void *context)
+			     struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val, addr;
 	void *data = record->data;
 	const char *func;
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 1d0d15906225..d13c22846fa9 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -23,6 +23,7 @@
 #include <stdint.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #ifdef HAVE_UDIS86
 
@@ -248,7 +249,7 @@ static const char *find_exit_reason(unsigned isa, int val)
 }
 
 static int print_exit_reason(struct trace_seq *s, struct tep_record *record,
-			     struct event_format *event, const char *field)
+			     struct tep_event_format *event, const char *field)
 {
 	unsigned long long isa;
 	unsigned long long val;
@@ -269,7 +270,7 @@ static int print_exit_reason(struct trace_seq *s, struct tep_record *record,
 }
 
 static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record,
-			    struct event_format *event, void *context)
+			    struct tep_event_format *event, void *context)
 {
 	unsigned long long info1 = 0, info2 = 0;
 
@@ -292,7 +293,7 @@ static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record,
 
 static int kvm_emulate_insn_handler(struct trace_seq *s,
 				    struct tep_record *record,
-				    struct event_format *event, void *context)
+				    struct tep_event_format *event, void *context)
 {
 	unsigned long long rip, csbase, len, flags, failed;
 	int llen;
@@ -331,7 +332,7 @@ static int kvm_emulate_insn_handler(struct trace_seq *s,
 
 
 static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_record *record,
-					    struct event_format *event, void *context)
+					    struct tep_event_format *event, void *context)
 {
 	if (print_exit_reason(s, record, event, "exit_code") < 0)
 		return -1;
@@ -345,7 +346,7 @@ static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_reco
 }
 
 static int kvm_nested_vmexit_handler(struct trace_seq *s, struct tep_record *record,
-				     struct event_format *event, void *context)
+				     struct tep_event_format *event, void *context)
 {
 	tep_print_num_field(s, "rip %llx ", event, "rip", record, 1);
 
@@ -371,7 +372,7 @@ union kvm_mmu_page_role {
 };
 
 static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
-			      struct event_format *event, void *context)
+			      struct tep_event_format *event, void *context)
 {
 	unsigned long long val;
 	static const char *access_str[] = {
@@ -418,7 +419,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 
 static int kvm_mmu_get_page_handler(struct trace_seq *s,
 				    struct tep_record *record,
-				    struct event_format *event, void *context)
+				    struct tep_event_format *event, void *context)
 {
 	unsigned long long val;
 
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index de50a5316203..da3855e7b86f 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -22,13 +22,14 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define INDENT 65
 
-static void print_string(struct trace_seq *s, struct event_format *event,
+static void print_string(struct trace_seq *s, struct tep_event_format *event,
 			 const char *name, const void *data)
 {
-	struct format_field *f = tep_find_field(event, name);
+	struct tep_format_field *f = tep_find_field(event, name);
 	int offset;
 	int length;
 
@@ -59,7 +60,7 @@ static void print_string(struct trace_seq *s, struct event_format *event,
 
 static int drv_bss_info_changed(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	void *data = record->data;
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index eecb4bd95c11..77882272672f 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static void write_state(struct trace_seq *s, int val)
 {
@@ -44,7 +45,7 @@ static void write_state(struct trace_seq *s, int val)
 		trace_seq_putc(s, 'R');
 }
 
-static void write_and_save_comm(struct format_field *field,
+static void write_and_save_comm(struct tep_format_field *field,
 				struct tep_record *record,
 				struct trace_seq *s, int pid)
 {
@@ -66,9 +67,9 @@ static void write_and_save_comm(struct format_field *field,
 
 static int sched_wakeup_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	if (tep_get_field_val(s, event, "pid", record, &val, 1))
@@ -95,9 +96,9 @@ static int sched_wakeup_handler(struct trace_seq *s,
 
 static int sched_switch_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	if (tep_get_field_val(s, event, "prev_pid", record, &val, 1))
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 5ec346f6b842..4eba25cc1431 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -3,6 +3,7 @@
 #include <string.h>
 #include <inttypes.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 typedef unsigned long sector_t;
 typedef uint64_t u64;
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index b2acbd6e9c86..bc0496e4c296 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -3,6 +3,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define __HYPERVISOR_set_trap_table			0
 #define __HYPERVISOR_mmu_update				1
diff --git a/tools/lib/traceevent/tep_strerror.c b/tools/lib/traceevent/tep_strerror.c
new file mode 100644
index 000000000000..4ac26445b2f6
--- /dev/null
+++ b/tools/lib/traceevent/tep_strerror.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: LGPL-2.1
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+
+#include "event-parse.h"
+
+#undef _PE
+#define _PE(code, str) str
+static const char * const tep_error_str[] = {
+	TEP_ERRORS
+};
+#undef _PE
+
+/*
+ * 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.
+ */
+int tep_strerror(struct tep_handle *tep __maybe_unused,
+		 enum tep_errno errnum, char *buf, size_t buflen)
+{
+	const char *msg;
+	int idx;
+
+	if (!buflen)
+		return 0;
+
+	if (errnum >= 0) {
+		int err = strerror_r(errnum, buf, buflen);
+		buf[buflen - 1] = 0;
+		return err;
+	}
+
+	if (errnum <= __TEP_ERRNO__START ||
+	    errnum >= __TEP_ERRNO__END)
+		return -1;
+
+	idx = errnum - __TEP_ERRNO__START - 1;
+	msg = tep_error_str[idx];
+	snprintf(buf, buflen, "%s", msg);
+
+	return 0;
+}
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index e3bac4543d3b..8ff1d55954d1 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -3,6 +3,8 @@
  * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
  *
  */
+#include "trace-seq.h"
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/lib/traceevent/trace-seq.h b/tools/lib/traceevent/trace-seq.h
new file mode 100644
index 000000000000..d68ec69f8d1a
--- /dev/null
+++ b/tools/lib/traceevent/trace-seq.h
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _TRACE_SEQ_H
+#define _TRACE_SEQ_H
+
+#include <stdarg.h>
+#include <stdio.h>
+
+/* ----------------------- trace_seq ----------------------- */
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+enum trace_seq_fail {
+	TRACE_SEQ__GOOD,
+	TRACE_SEQ__BUFFER_POISONED,
+	TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+	char			*buffer;
+	unsigned int		buffer_size;
+	unsigned int		len;
+	unsigned int		readpos;
+	enum trace_seq_fail	state;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+#endif /* _TRACE_SEQ_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0be411695379..2f3bf025e305 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -779,7 +779,9 @@ endif
 ifndef NO_LIBBPF
 	$(call QUIET_INSTALL, bpf-headers) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
-		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
 	$(call QUIET_INSTALL, bpf-examples) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
 		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 6688977e4ac7..76c6345a57d5 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -8,6 +8,63 @@ struct arm64_annotate {
 		jump_insn;
 };
 
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+			    struct ins_operands *ops,
+			    struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	*s = ' ';
+	ops->target.name = strdup(s);
+	*s = '<';
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops arm64_mov_ops = {
+	.parse	   = arm64_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
 {
 	struct arm64_annotate *arm = arch->priv;
@@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
 	else if (!strcmp(name, "ret"))
 		ops = &ret_ops;
 	else
-		return NULL;
+		ops = &arm64_mov_ops;
 
 	arch__associate_ins_ops(arch, name, ops);
 	return ops;
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index cee4e2f7c057..de0dd66dbb48 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -100,8 +100,6 @@ out_free_source:
 	return -1;
 }
 
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops);
 
 static struct ins_ops s390_mov_ops = {
 	.parse	   = s390_mov__parse,
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 830481b8db26..93d679eaf1f4 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,12 +283,11 @@ out_put:
 	return ret;
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a3b346359ba0..eda41673c4f3 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -86,12 +86,10 @@ static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
-static int perf_event__repipe_op2_synth(struct perf_tool *tool,
-					union perf_event *event,
-					struct perf_session *session
-					__maybe_unused)
+static int perf_event__repipe_op2_synth(struct perf_session *session,
+					union perf_event *event)
 {
-	return perf_event__repipe_synth(tool, event);
+	return perf_event__repipe_synth(session->tool, event);
 }
 
 static int perf_event__repipe_attr(struct perf_tool *tool,
@@ -133,10 +131,10 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
 	return 0;
 }
 
-static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static s64 perf_event__repipe_auxtrace(struct perf_session *session,
+				       union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
 	int ret;
@@ -174,9 +172,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 #else
 
 static s64
-perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
-			    union perf_event *event __maybe_unused,
-			    struct perf_session *session __maybe_unused)
+perf_event__repipe_auxtrace(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused)
 {
 	pr_err("AUX area tracing not supported\n");
 	return -EINVAL;
@@ -362,26 +359,24 @@ static int perf_event__repipe_exit(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(struct perf_tool *tool,
-					   union perf_event *event,
-					   struct perf_session *session)
+static int perf_event__repipe_tracing_data(struct perf_session *session,
+					   union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_tracing_data(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_tracing_data(session, event);
 
 	return err;
 }
 
-static int perf_event__repipe_id_index(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static int perf_event__repipe_id_index(struct perf_session *session,
+				       union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_id_index(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_id_index(session, event);
 
 	return err;
 }
@@ -803,7 +798,8 @@ int cmd_inject(int argc, const char **argv)
 			   "kallsyms pathname"),
 		OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
 		OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
-				    NULL, "opts", "Instruction Tracing options",
+				    NULL, "opts", "Instruction Tracing options\n"
+				    ITRACE_HELP,
 				    itrace_parse_synth_opts),
 		OPT_BOOLEAN(0, "strip", &inject.strip,
 			    "strip non-synthesized events (use with --itrace)"),
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 22ebeb92ac51..0980dfe3396b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -106,9 +106,12 @@ static bool switch_output_time(struct record *rec)
 	       trigger_is_ready(&switch_output_trigger);
 }
 
-static int record__write(struct record *rec, void *bf, size_t size)
+static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused,
+			 void *bf, size_t size)
 {
-	if (perf_data__write(rec->session->data, bf, size) < 0) {
+	struct perf_data_file *file = &rec->session->data->file;
+
+	if (perf_data_file__write(file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
@@ -127,15 +130,15 @@ static int process_synthesized_event(struct perf_tool *tool,
 				     struct machine *machine __maybe_unused)
 {
 	struct record *rec = container_of(tool, struct record, tool);
-	return record__write(rec, event, event->header.size);
+	return record__write(rec, NULL, event, event->header.size);
 }
 
-static int record__pushfn(void *to, void *bf, size_t size)
+static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size)
 {
 	struct record *rec = to;
 
 	rec->samples++;
-	return record__write(rec, bf, size);
+	return record__write(rec, map, bf, size);
 }
 
 static volatile int done;
@@ -170,6 +173,7 @@ static void record__sig_exit(void)
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 static int record__process_auxtrace(struct perf_tool *tool,
+				    struct perf_mmap *map,
 				    union perf_event *event, void *data1,
 				    size_t len1, void *data2, size_t len2)
 {
@@ -197,21 +201,21 @@ static int record__process_auxtrace(struct perf_tool *tool,
 	if (padding)
 		padding = 8 - padding;
 
-	record__write(rec, event, event->header.size);
-	record__write(rec, data1, len1);
+	record__write(rec, map, event, event->header.size);
+	record__write(rec, map, data1, len1);
 	if (len2)
-		record__write(rec, data2, len2);
-	record__write(rec, &pad, padding);
+		record__write(rec, map, data2, len2);
+	record__write(rec, map, &pad, padding);
 
 	return 0;
 }
 
 static int record__auxtrace_mmap_read(struct record *rec,
-				      struct auxtrace_mmap *mm)
+				      struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read(map, rec->itr, &rec->tool,
 				  record__process_auxtrace);
 	if (ret < 0)
 		return ret;
@@ -223,11 +227,11 @@ static int record__auxtrace_mmap_read(struct record *rec,
 }
 
 static int record__auxtrace_mmap_read_snapshot(struct record *rec,
-					       struct auxtrace_mmap *mm)
+					       struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read_snapshot(map, rec->itr, &rec->tool,
 					   record__process_auxtrace,
 					   rec->opts.auxtrace_snapshot_size);
 	if (ret < 0)
@@ -245,13 +249,12 @@ static int record__auxtrace_read_snapshot_all(struct record *rec)
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm =
-				&rec->evlist->mmap[i].auxtrace_mmap;
+		struct perf_mmap *map = &rec->evlist->mmap[i];
 
-		if (!mm->base)
+		if (!map->auxtrace_mmap.base)
 			continue;
 
-		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+		if (record__auxtrace_mmap_read_snapshot(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
@@ -295,7 +298,7 @@ static int record__auxtrace_init(struct record *rec)
 
 static inline
 int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
-			       struct auxtrace_mmap *mm __maybe_unused)
+			       struct perf_mmap *map __maybe_unused)
 {
 	return 0;
 }
@@ -529,17 +532,17 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
+		struct perf_mmap *map = &maps[i];
 
-		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
+		if (map->base) {
+			if (perf_mmap__push(map, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
 		}
 
-		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
-		    record__auxtrace_mmap_read(rec, mm) != 0) {
+		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
+		    record__auxtrace_mmap_read(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
@@ -550,7 +553,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	 * at least one event.
 	 */
 	if (bytes_written != rec->bytes_written)
-		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
+		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
 
 	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
@@ -758,7 +761,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		 * We need to synthesize events first, because some
 		 * features works on top of them (on report side).
 		 */
-		err = perf_event__synthesize_attrs(tool, session,
+		err = perf_event__synthesize_attrs(tool, rec->evlist,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b2188e623e22..257c9c18cb7e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -201,14 +201,13 @@ static void setup_forced_leader(struct report *report,
 		perf_evlist__force_leader(evlist);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session __maybe_unused)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
-	struct report *rep = container_of(tool, struct report, tool);
+	struct report *rep = container_of(session->tool, struct report, tool);
 
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 
 	if (event->feat.feat_id != HEADER_LAST_FEATURE) {
 		pr_err("failed: wrong feature ID: %" PRIu64 "\n",
@@ -1106,7 +1105,7 @@ int cmd_report(int argc, const char **argv)
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ba481d73f910..4da5e32b9e03 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_WEIGHT))
 		return -EINVAL;
 
-	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+	if (PRINT_FIELD(SYM) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
 		pr_err("Display of symbols requested but neither sample IP nor "
-			   "sample address\nis selected. Hence, no addresses to convert "
+			   "sample address\navailable. Hence, no addresses to convert "
 		       "to symbols.\n");
 		return -EINVAL;
 	}
@@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
-		pr_err("Display of DSO requested but no address to convert.  Select\n"
-		       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
+	if (PRINT_FIELD(DSO) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+		pr_err("Display of DSO requested but no address to convert.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
+	int dlen = 0;
 	u64 ip = 0;
 
 	/*
@@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 			ip = sample->ip;
 	}
 
+	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
+		dlen += fprintf(fp, "(");
+		dlen += map__fprintf_dsoname(al->map, fp);
+		dlen += fprintf(fp, ")\t");
+	}
+
 	if (name)
 		len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
 	else if (ip)
@@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (len < spacing)
 		len += fprintf(fp, "%*s", spacing - len, "");
 
-	return len;
+	return len + dlen;
 }
 
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
@@ -1255,6 +1262,18 @@ static struct {
 	{0, NULL}
 };
 
+static const char *sample_flags_to_name(u32 flags)
+{
+	int i;
+
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == flags)
+			return sample_flags[i].name;
+	}
+
+	return NULL;
+}
+
 static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
@@ -1264,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	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;
-		}
+	name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX);
+	if (name)
+		return fprintf(fp, "  %-15s%4s ", name, in_tx ? "(x)" : "");
+
+	if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN));
+		if (name)
+			return fprintf(fp, "  tr strt %-7s%4s ", name, in_tx ? "(x)" : "");
+	}
+
+	if (flags & PERF_IP_FLAG_TRACE_END) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END));
+		if (name)
+			return fprintf(fp, "  tr end  %-7s%4s ", name, in_tx ? "(x)" : "");
 	}
 
 	for (i = 0; i < n; i++, flags >>= 1) {
@@ -1281,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	}
 	str[pos] = 0;
 
-	if (name)
-		return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
-
-	return fprintf(fp, "  %-11s ", str);
+	return fprintf(fp, "  %-19s ", str);
 }
 
 struct printer_data {
@@ -1544,7 +1569,8 @@ struct metric_ctx {
 	FILE 			*fp;
 };
 
-static void script_print_metric(void *ctx, const char *color,
+static void script_print_metric(struct perf_stat_config *config __maybe_unused,
+				void *ctx, const char *color,
 			        const char *fmt,
 			        const char *unit, double val)
 {
@@ -1562,7 +1588,8 @@ static void script_print_metric(void *ctx, const char *color,
 	fprintf(mctx->fp, " %s\n", unit);
 }
 
-static void script_new_line(void *ctx)
+static void script_new_line(struct perf_stat_config *config __maybe_unused,
+			    void *ctx)
 {
 	struct metric_ctx *mctx = ctx;
 
@@ -1608,7 +1635,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	evsel_script(evsel)->val = val;
 	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
 		for_each_group_member (ev2, evsel->leader) {
-			perf_stat__print_shadow_stats(ev2,
+			perf_stat__print_shadow_stats(&stat_config, ev2,
 						      evsel_script(ev2)->val,
 						      sample->cpu,
 						      &ctx,
@@ -2489,6 +2516,8 @@ parse:
 						output[j].fields &= ~all_output_options[i].field;
 					else
 						output[j].fields |= all_output_options[i].field;
+					output[j].user_set = true;
+					output[j].wildcard_set = true;
 				}
 			}
 		} else {
@@ -2499,7 +2528,8 @@ parse:
 				rc = -EINVAL;
 				goto out;
 			}
-			output[type].fields |= all_output_options[i].field;
+			output[type].user_set = true;
+			output[type].wildcard_set = true;
 		}
 	}
 
@@ -2963,9 +2993,8 @@ static void script__setup_sample_type(struct perf_script *script)
 	}
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -2979,9 +3008,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session __maybe_unused)
+static int process_stat_config_event(struct perf_session *session __maybe_unused,
+				     union perf_event *event)
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 	return 0;
@@ -3007,10 +3035,10 @@ static int set_maps(struct perf_script *script)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->threads) {
@@ -3026,10 +3054,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->cpus) {
@@ -3044,21 +3072,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
 #ifdef HAVE_AUXTRACE_SUPPORT
-static int perf_script__process_auxtrace_info(struct perf_tool *tool,
-					      union perf_event *event,
-					      struct perf_session *session)
+static int perf_script__process_auxtrace_info(struct perf_session *session,
+					      union perf_event *event)
 {
-	int ret = perf_event__process_auxtrace_info(tool, event, session);
+	struct perf_tool *tool = session->tool;
+
+	int ret = perf_event__process_auxtrace_info(session, event);
 
 	if (ret == 0) {
 		struct perf_script *script = container_of(tool, struct perf_script, tool);
@@ -3193,7 +3221,7 @@ int cmd_script(int argc, const char **argv)
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d097b5b47eb8..b86aba1c8028 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -88,8 +88,6 @@
 #include "sane_ctype.h"
 
 #define DEFAULT_SEPARATOR	" "
-#define CNTR_NOT_SUPPORTED	"<not supported>"
-#define CNTR_NOT_COUNTED	"<not counted>"
 #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
@@ -137,54 +135,30 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
-static struct rblist		 metric_events;
-
 static struct target target = {
 	.uid	= UINT_MAX,
 };
 
-typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
-
 #define METRIC_ONLY_LEN 20
 
-static int			run_count			=  1;
-static bool			no_inherit			= false;
 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			smi_cost			= false;
 static bool			smi_reset			= false;
-static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
-static const char		*csv_sep			= NULL;
-static bool			csv_output			= false;
 static bool			group				= false;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
-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 bool			no_merge			= false;
-static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
-static struct cpu_map		*aggr_map;
-static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
-static bool			interval_clear;
 static const char		*output_name;
 static int			output_fd;
-static int			print_free_counters_hint;
-static int			print_mixed_hw_group_error;
-static u64			*walltime_run;
-static bool			ru_display			= false;
-static struct rusage		ru_data;
-static unsigned int		metric_only_len			= METRIC_ONLY_LEN;
 
 struct perf_stat {
 	bool			 record;
@@ -204,15 +178,15 @@ static struct perf_stat		perf_stat;
 static volatile int done = 0;
 
 static struct perf_stat_config stat_config = {
-	.aggr_mode	= AGGR_GLOBAL,
-	.scale		= true,
+	.aggr_mode		= AGGR_GLOBAL,
+	.scale			= true,
+	.unit_width		= 4, /* strlen("unit") */
+	.run_count		= 1,
+	.metric_only_len	= METRIC_ONLY_LEN,
+	.walltime_nsecs_stats	= &walltime_nsecs_stats,
+	.big_num		= true,
 };
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -236,66 +210,6 @@ static void perf_stat__reset_stats(void)
 		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
-static int create_perf_stat_counter(struct perf_evsel *evsel)
-{
-	struct perf_event_attr *attr = &evsel->attr;
-	struct perf_evsel *leader = evsel->leader;
-
-	if (stat_config.scale) {
-		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-				    PERF_FORMAT_TOTAL_TIME_RUNNING;
-	}
-
-	/*
-	 * The event is part of non trivial group, let's enable
-	 * the group read (for leader) and ID retrieval for all
-	 * members.
-	 */
-	if (leader->nr_members > 1)
-		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
-
-	attr->inherit = !no_inherit;
-
-	/*
-	 * Some events get initialized with sample_(period/type) set,
-	 * like tracepoints. Clear it up for counting.
-	 */
-	attr->sample_period = 0;
-
-	/*
-	 * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
-	 * while avoiding that older tools show confusing messages.
-	 *
-	 * However for pipe sessions we need to keep it zero,
-	 * because script's perf_evsel__check_attr is triggered
-	 * by attr->sample_type != 0, and we can't run it on
-	 * stat sessions.
-	 */
-	if (!(STAT_RECORD && perf_stat.data.is_pipe))
-		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
-
-	/*
-	 * Disabling all counters initially, they will be enabled
-	 * either manually by us or by kernel via enable_on_exec
-	 * set later.
-	 */
-	if (perf_evsel__is_group_leader(evsel)) {
-		attr->disabled = 1;
-
-		/*
-		 * In case of initial_delay we enable tracee
-		 * events manually.
-		 */
-		if (target__none(&target) && !initial_delay)
-			attr->enable_on_exec = 1;
-	}
-
-	if (target__has_cpu(&target) && !target__has_per_thread(&target))
-		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
-
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -428,15 +342,15 @@ static void process_interval(void)
 
 static void enable_counters(void)
 {
-	if (initial_delay)
-		usleep(initial_delay * USEC_PER_MSEC);
+	if (stat_config.initial_delay)
+		usleep(stat_config.initial_delay * USEC_PER_MSEC);
 
 	/*
 	 * We need to enable counters only if:
 	 * - we don't have tracee (attaching to task or cpu)
 	 * - we have initial delay configured
 	 */
-	if (!target__none(&target) || initial_delay)
+	if (!target__none(&target) || stat_config.initial_delay)
 		perf_evlist__enable(evsel_list);
 }
 
@@ -464,80 +378,6 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(bool is_pipe)
-{
-	int err;
-
-	if (is_pipe) {
-		err = perf_event__synthesize_attrs(NULL, perf_stat.session,
-						   process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			return err;
-		}
-	}
-
-	err = perf_event__synthesize_extra_attr(NULL,
-						evsel_list,
-						process_synthesized_event,
-						is_pipe);
-
-	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
-						process_synthesized_event,
-						NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
-					     process_synthesized_event, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_stat_config(NULL, &stat_config,
-						 process_synthesized_event, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize config.\n");
-		return err;
-	}
-
-	return 0;
-}
-
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
-static int __store_counter_ids(struct perf_evsel *counter)
-{
-	int cpu, thread;
-
-	for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(counter->fd);
-		     thread++) {
-			int fd = FD(counter, cpu, thread);
-
-			if (perf_evlist__id_add_fd(evsel_list, counter,
-						   cpu, thread, fd) < 0)
-				return -1;
-		}
-	}
-
-	return 0;
-}
-
-static int store_counter_ids(struct perf_evsel *counter)
-{
-	struct cpu_map *cpus = counter->cpus;
-	struct thread_map *threads = counter->threads;
-
-	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
-		return -ENOMEM;
-
-	return __store_counter_ids(counter);
-}
-
 static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 {
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
@@ -609,7 +449,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
-		if (create_perf_stat_counter(counter) < 0) {
+		if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
 
 			/* Weak group failed. Reset the group. */
 			if ((errno == EINVAL || errno == EBADF) &&
@@ -664,11 +504,11 @@ try_again:
 		counter->supported = true;
 
 		l = strlen(counter->unit);
-		if (l > unit_width)
-			unit_width = l;
+		if (l > stat_config.unit_width)
+			stat_config.unit_width = l;
 
 		if (perf_evsel__should_store_id(counter) &&
-		    store_counter_ids(counter))
+		    perf_evsel__store_ids(counter, evsel_list))
 			return -1;
 	}
 
@@ -699,7 +539,8 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(is_pipe);
+		err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+						  process_synthesized_event, is_pipe);
 		if (err < 0)
 			return err;
 	}
@@ -724,7 +565,7 @@ try_again:
 					break;
 			}
 		}
-		wait4(child_pid, &status, 0, &ru_data);
+		wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -752,8 +593,8 @@ try_again:
 
 	t1 = rdclock();
 
-	if (walltime_run_table)
-		walltime_run[run_idx] = t1 - t0;
+	if (stat_config.walltime_run_table)
+		stat_config.walltime_run[run_idx] = t1 - t0;
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
@@ -795,1105 +636,14 @@ static int run_perf_stat(int argc, const char **argv, int run_idx)
 	return ret;
 }
 
-static void print_running(u64 run, u64 ena)
-{
-	if (csv_output) {
-		fprintf(stat_config.output, "%s%" PRIu64 "%s%.2f",
-					csv_sep,
-					run,
-					csv_sep,
-					ena ? 100.0 * run / ena : 100.0);
-	} else if (run != ena) {
-		fprintf(stat_config.output, "  (%.2f%%)", 100.0 * run / ena);
-	}
-}
-
-static void print_noise_pct(double total, double avg)
-{
-	double pct = rel_stddev_stats(total, avg);
-
-	if (csv_output)
-		fprintf(stat_config.output, "%s%.2f%%", csv_sep, pct);
-	else if (pct)
-		fprintf(stat_config.output, "  ( +-%6.2f%% )", pct);
-}
-
-static void print_noise(struct perf_evsel *evsel, double avg)
-{
-	struct perf_stat_evsel *ps;
-
-	if (run_count == 1)
-		return;
-
-	ps = evsel->stats;
-	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
-}
-
-static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
-{
-	switch (stat_config.aggr_mode) {
-	case AGGR_CORE:
-		fprintf(stat_config.output, "S%d-C%*d%s%*d%s",
-			cpu_map__id_to_socket(id),
-			csv_output ? 0 : -8,
-			cpu_map__id_to_cpu(id),
-			csv_sep,
-			csv_output ? 0 : 4,
-			nr,
-			csv_sep);
-		break;
-	case AGGR_SOCKET:
-		fprintf(stat_config.output, "S%*d%s%*d%s",
-			csv_output ? 0 : -5,
-			id,
-			csv_sep,
-			csv_output ? 0 : 4,
-			nr,
-			csv_sep);
-			break;
-	case AGGR_NONE:
-		fprintf(stat_config.output, "CPU%*d%s",
-			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[id], csv_sep);
-		break;
-	case AGGR_THREAD:
-		fprintf(stat_config.output, "%*s-%*d%s",
-			csv_output ? 0 : 16,
-			thread_map__comm(evsel->threads, id),
-			csv_output ? 0 : -8,
-			thread_map__pid(evsel->threads, id),
-			csv_sep);
-		break;
-	case AGGR_GLOBAL:
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-}
-
-struct outstate {
-	FILE *fh;
-	bool newline;
-	const char *prefix;
-	int  nfields;
-	int  id, nr;
-	struct perf_evsel *evsel;
-};
-
-#define METRIC_LEN  35
-
-static void new_line_std(void *ctx)
-{
-	struct outstate *os = ctx;
-
-	os->newline = true;
-}
-
-static void do_new_line_std(struct outstate *os)
-{
-	fputc('\n', os->fh);
-	fputs(os->prefix, os->fh);
-	aggr_printout(os->evsel, os->id, os->nr);
-	if (stat_config.aggr_mode == AGGR_NONE)
-		fprintf(os->fh, "        ");
-	fprintf(os->fh, "                                                 ");
-}
-
-static void print_metric_std(void *ctx, const char *color, const char *fmt,
-			     const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	int n;
-	bool newline = os->newline;
-
-	os->newline = false;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%-*s", METRIC_LEN, "");
-		return;
-	}
-
-	if (newline)
-		do_new_line_std(os);
-
-	n = fprintf(out, " # ");
-	if (color)
-		n += color_fprintf(out, color, fmt, val);
-	else
-		n += fprintf(out, fmt, val);
-	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
-}
-
-static void new_line_csv(void *ctx)
-{
-	struct outstate *os = ctx;
-	int i;
-
-	fputc('\n', os->fh);
-	if (os->prefix)
-		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
-	aggr_printout(os->evsel, os->id, os->nr);
-	for (i = 0; i < os->nfields; i++)
-		fputs(csv_sep, os->fh);
-}
-
-static void print_metric_csv(void *ctx,
-			     const char *color __maybe_unused,
-			     const char *fmt, const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%s%s", csv_sep, csv_sep);
-		return;
-	}
-	snprintf(buf, sizeof(buf), fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	while (isspace(*unit))
-		unit++;
-	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
-}
-
-/* Filter out some columns that don't work well in metrics only mode */
-
-static bool valid_only_metric(const char *unit)
-{
-	if (!unit)
-		return false;
-	if (strstr(unit, "/sec") ||
-	    strstr(unit, "hz") ||
-	    strstr(unit, "Hz") ||
-	    strstr(unit, "CPUs utilized"))
-		return false;
-	return true;
-}
-
-static const char *fixunit(char *buf, struct perf_evsel *evsel,
-			   const char *unit)
-{
-	if (!strncmp(unit, "of all", 6)) {
-		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
-			 unit);
-		return buf;
-	}
-	return unit;
-}
-
-static void print_metric_only(void *ctx, const char *color, const char *fmt,
-			      const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[1024], str[1024];
-	unsigned mlen = metric_only_len;
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(buf, os->evsel, unit);
-	if (mlen < strlen(unit))
-		mlen = strlen(unit) + 1;
-
-	if (color)
-		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
-
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
-	fprintf(out, "%*s ", mlen, str);
-}
-
-static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
-				  const char *fmt,
-				  const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof buf, fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	fprintf(out, "%s%s", vals, csv_sep);
-}
-
-static void new_line_metric(void *ctx __maybe_unused)
-{
-}
-
-static void print_metric_header(void *ctx, const char *color __maybe_unused,
-				const char *fmt __maybe_unused,
-				const char *unit, double val __maybe_unused)
-{
-	struct outstate *os = ctx;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	if (csv_output)
-		fprintf(os->fh, "%s%s", unit, csv_sep);
-	else
-		fprintf(os->fh, "%*s ", metric_only_len, unit);
-}
-
-static int first_shadow_cpu(struct perf_evsel *evsel, int id)
-{
-	int i;
-
-	if (!aggr_get_id)
-		return 0;
-
-	if (stat_config.aggr_mode == AGGR_NONE)
-		return id;
-
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		return 0;
-
-	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
-		int cpu2 = perf_evsel__cpus(evsel)->map[i];
-
-		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
-			return cpu2;
-	}
-	return 0;
-}
-
-static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double sc =  evsel->scale;
-	const char *fmt;
-
-	if (csv_output) {
-		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
-	} else {
-		if (big_num)
-			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
-		else
-			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
-	}
-
-	aggr_printout(evsel, id, nr);
-
-	fprintf(output, fmt, avg, csv_sep);
-
-	if (evsel->unit)
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			evsel->unit, csv_sep);
-
-	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
-static bool is_mixed_hw_group(struct perf_evsel *counter)
-{
-	struct perf_evlist *evlist = counter->evlist;
-	u32 pmu_type = counter->attr.type;
-	struct perf_evsel *pos;
-
-	if (counter->nr_members < 2)
-		return false;
-
-	evlist__for_each_entry(evlist, pos) {
-		/* software events can be part of any hardware group */
-		if (pos->attr.type == PERF_TYPE_SOFTWARE)
-			continue;
-		if (pmu_type == PERF_TYPE_SOFTWARE) {
-			pmu_type = pos->attr.type;
-			continue;
-		}
-		if (pmu_type != pos->attr.type)
-			return true;
-	}
-
-	return false;
-}
-
-static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-		     char *prefix, u64 run, u64 ena, double noise,
-		     struct runtime_stat *st)
-{
-	struct perf_stat_output_ctx out;
-	struct outstate os = {
-		.fh = stat_config.output,
-		.prefix = prefix ? prefix : "",
-		.id = id,
-		.nr = nr,
-		.evsel = counter,
-	};
-	print_metric_t pm = print_metric_std;
-	void (*nl)(void *);
-
-	if (metric_only) {
-		nl = new_line_metric;
-		if (csv_output)
-			pm = print_metric_only_csv;
-		else
-			pm = print_metric_only;
-	} else
-		nl = new_line_std;
-
-	if (csv_output && !metric_only) {
-		static int aggr_fields[] = {
-			[AGGR_GLOBAL] = 0,
-			[AGGR_THREAD] = 1,
-			[AGGR_NONE] = 1,
-			[AGGR_SOCKET] = 2,
-			[AGGR_CORE] = 2,
-		};
-
-		pm = print_metric_csv;
-		nl = new_line_csv;
-		os.nfields = 3;
-		os.nfields += aggr_fields[stat_config.aggr_mode];
-		if (counter->cgrp)
-			os.nfields++;
-	}
-	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
-		if (metric_only) {
-			pm(&os, NULL, "", "", 0);
-			return;
-		}
-		aggr_printout(counter, id, nr);
-
-		fprintf(stat_config.output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-
-		if (counter->supported) {
-			print_free_counters_hint = 1;
-			if (is_mixed_hw_group(counter))
-				print_mixed_hw_group_error = 1;
-		}
-
-		fprintf(stat_config.output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-
-		fprintf(stat_config.output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(stat_config.output, "%s%s",
-				csv_sep, counter->cgrp->name);
-
-		if (!csv_output)
-			pm(&os, NULL, NULL, "", 0);
-		print_noise(counter, noise);
-		print_running(run, ena);
-		if (csv_output)
-			pm(&os, NULL, NULL, "", 0);
-		return;
-	}
-
-	if (!metric_only)
-		abs_printout(id, nr, counter, uval);
-
-	out.print_metric = pm;
-	out.new_line = nl;
-	out.ctx = &os;
-	out.force_header = false;
-
-	if (csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
-	}
-
-	perf_stat__print_shadow_stats(counter, uval,
-				first_shadow_cpu(counter, id),
-				&out, &metric_events, st);
-	if (!csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
-	}
-}
-
-static void aggr_update_shadow(void)
-{
-	int cpu, s2, id, s;
-	u64 val;
-	struct perf_evsel *counter;
-
-	for (s = 0; s < aggr_map->nr; s++) {
-		id = aggr_map->map[s];
-		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);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-			}
-			perf_stat__update_shadow_stats(counter, val,
-					first_shadow_cpu(counter, id),
-					&rt_stat);
-		}
-	}
-}
-
-static void uniquify_event_name(struct perf_evsel *counter)
-{
-	char *new_name;
-	char *config;
-
-	if (counter->uniquified_name ||
-	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
-					   strlen(counter->pmu_name)))
-		return;
-
-	config = strchr(counter->name, '/');
-	if (config) {
-		if (asprintf(&new_name,
-			     "%s%s", counter->pmu_name, config) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	} else {
-		if (asprintf(&new_name,
-			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	}
-
-	counter->uniquified_name = true;
-}
-
-static void collect_all_aliases(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	struct perf_evsel *alias;
-
-	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
-	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
-		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
-		    alias->scale != counter->scale ||
-		    alias->cgrp != counter->cgrp ||
-		    strcmp(alias->unit, counter->unit) ||
-		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
-			break;
-		alias->merged_stat = true;
-		cb(alias, data, false);
-	}
-}
-
-static bool collect_data(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	if (counter->merged_stat)
-		return false;
-	cb(counter, data, true);
-	if (no_merge)
-		uniquify_event_name(counter);
-	else if (counter->auto_merge_stats)
-		collect_all_aliases(counter, cb, data);
-	return true;
-}
-
-struct aggr_data {
-	u64 ena, run, val;
-	int id;
-	int nr;
-	int cpu;
-};
-
-static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
-{
-	struct aggr_data *ad = data;
-	int cpu, s2;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct perf_counts_values *counts;
-
-		s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
-		if (s2 != ad->id)
-			continue;
-		if (first)
-			ad->nr++;
-		counts = perf_counts(counter->counts, cpu, 0);
-		/*
-		 * When any result is bad, make them all to give
-		 * consistent output in interval mode.
-		 */
-		if (counts->ena == 0 || counts->run == 0 ||
-		    counter->counts->scaled == -1) {
-			ad->ena = 0;
-			ad->run = 0;
-			break;
-		}
-		ad->val += counts->val;
-		ad->ena += counts->ena;
-		ad->run += counts->run;
-	}
-}
-
-static void print_aggr(char *prefix)
-{
-	FILE *output = stat_config.output;
-	struct perf_evsel *counter;
-	int s, id, nr;
-	double uval;
-	u64 ena, run, val;
-	bool first;
-
-	if (!(aggr_map || aggr_get_id))
-		return;
-
-	aggr_update_shadow();
-
-	/*
-	 * With metric_only everything is on a single line.
-	 * Without each counter has its own line.
-	 */
-	for (s = 0; s < aggr_map->nr; s++) {
-		struct aggr_data ad;
-		if (prefix && metric_only)
-			fprintf(output, "%s", prefix);
-
-		ad.id = id = aggr_map->map[s];
-		first = true;
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-
-			ad.val = ad.ena = ad.run = 0;
-			ad.nr = 0;
-			if (!collect_data(counter, aggr_cb, &ad))
-				continue;
-			nr = ad.nr;
-			ena = ad.ena;
-			run = ad.run;
-			val = ad.val;
-			if (first && metric_only) {
-				first = false;
-				aggr_printout(counter, id, nr);
-			}
-			if (prefix && !metric_only)
-				fprintf(output, "%s", prefix);
-
-			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
-			if (!metric_only)
-				fputc('\n', output);
-		}
-		if (metric_only)
-			fputc('\n', output);
-	}
-}
-
-static int cmp_val(const void *a, const void *b)
-{
-	return ((struct perf_aggr_thread_value *)b)->val -
-		((struct perf_aggr_thread_value *)a)->val;
-}
-
-static struct perf_aggr_thread_value *sort_aggr_thread(
-					struct perf_evsel *counter,
-					int nthreads, int ncpus,
-					int *ret)
-{
-	int cpu, thread, i = 0;
-	double uval;
-	struct perf_aggr_thread_value *buf;
-
-	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
-	if (!buf)
-		return NULL;
-
-	for (thread = 0; thread < nthreads; thread++) {
-		u64 ena = 0, run = 0, val = 0;
-
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			val += perf_counts(counter->counts, cpu, thread)->val;
-			ena += perf_counts(counter->counts, cpu, thread)->ena;
-			run += perf_counts(counter->counts, cpu, thread)->run;
-		}
-
-		uval = val * counter->scale;
-
-		/*
-		 * Skip value 0 when enabling --per-thread globally,
-		 * otherwise too many 0 output.
-		 */
-		if (uval == 0.0 && target__has_per_thread(&target))
-			continue;
-
-		buf[i].counter = counter;
-		buf[i].id = thread;
-		buf[i].uval = uval;
-		buf[i].val = val;
-		buf[i].run = run;
-		buf[i].ena = ena;
-		i++;
-	}
-
-	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
-
-	if (ret)
-		*ret = i;
-
-	return buf;
-}
-
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	int nthreads = thread_map__nr(counter->threads);
-	int ncpus = cpu_map__nr(counter->cpus);
-	int thread, sorted_threads, id;
-	struct perf_aggr_thread_value *buf;
-
-	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
-	if (!buf) {
-		perror("cannot sort aggr thread");
-		return;
-	}
-
-	for (thread = 0; thread < sorted_threads; thread++) {
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		id = buf[thread].id;
-		if (stat_config.stats)
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &stat_config.stats[id]);
-		else
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &rt_stat);
-		fputc('\n', output);
-	}
-
-	free(buf);
-}
-
-struct caggr_data {
-	double avg, avg_enabled, avg_running;
-};
-
-static void counter_aggr_cb(struct perf_evsel *counter, void *data,
-			    bool first __maybe_unused)
-{
-	struct caggr_data *cd = data;
-	struct perf_stat_evsel *ps = counter->stats;
-
-	cd->avg += avg_stats(&ps->res_stats[0]);
-	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
-	cd->avg_running += avg_stats(&ps->res_stats[2]);
-}
-
-/*
- * Print out the results of a single counter:
- * aggregated counts in system-wide mode
- */
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	double uval;
-	struct caggr_data cd = { .avg = 0.0 };
-
-	if (!collect_data(counter, counter_aggr_cb, &cd))
-		return;
-
-	if (prefix && !metric_only)
-		fprintf(output, "%s", prefix);
-
-	uval = cd.avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
-		 cd.avg, &rt_stat);
-	if (!metric_only)
-		fprintf(output, "\n");
-}
-
-static void counter_cb(struct perf_evsel *counter, void *data,
-		       bool first __maybe_unused)
-{
-	struct aggr_data *ad = data;
-
-	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
-	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
-	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
-}
-
-/*
- * Print out the results of a single counter:
- * does not use aggregated count in system-wide
- */
-static void print_counter(struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = stat_config.output;
-	u64 ena, run, val;
-	double uval;
-	int cpu;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct aggr_data ad = { .cpu = cpu };
-
-		if (!collect_data(counter, counter_cb, &ad))
-			return;
-		val = ad.val;
-		ena = ad.ena;
-		run = ad.run;
-
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
-			 &rt_stat);
-
-		fputc('\n', output);
-	}
-}
-
-static void print_no_aggr_metric(char *prefix)
-{
-	int cpu;
-	int nrcpus = 0;
-	struct perf_evsel *counter;
-	u64 ena, run, val;
-	double uval;
-
-	nrcpus = evsel_list->cpus->nr;
-	for (cpu = 0; cpu < nrcpus; cpu++) {
-		bool first = true;
-
-		if (prefix)
-			fputs(prefix, stat_config.output);
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			if (first) {
-				aggr_printout(counter, cpu, 0);
-				first = false;
-			}
-			val = perf_counts(counter->counts, cpu, 0)->val;
-			ena = perf_counts(counter->counts, cpu, 0)->ena;
-			run = perf_counts(counter->counts, cpu, 0)->run;
-
-			uval = val * counter->scale;
-			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
-		}
-		fputc('\n', stat_config.output);
-	}
-}
-
-static int aggr_header_lens[] = {
-	[AGGR_CORE] = 18,
-	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 6,
-	[AGGR_THREAD] = 24,
-	[AGGR_GLOBAL] = 0,
-};
-
-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;
-	struct outstate os = {
-		.fh = stat_config.output
-	};
-
-	if (prefix)
-		fprintf(stat_config.output, "%s", prefix);
-
-	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_entry(evsel_list, counter) {
-		if (is_duration_time(counter))
-			continue;
-		os.evsel = counter;
-		out.ctx = &os;
-		out.print_metric = print_metric_header;
-		out.new_line = new_line_metric;
-		out.force_header = true;
-		os.evsel = counter;
-		perf_stat__print_shadow_stats(counter, 0,
-					      0,
-					      &out,
-					      &metric_events,
-					      &rt_stat);
-	}
-	fputc('\n', stat_config.output);
-}
-
-static void print_interval(char *prefix, struct timespec *ts)
-{
-	FILE *output = stat_config.output;
-	static int num_print_interval;
-
-	if (interval_clear)
-		puts(CONSOLE_CLEAR);
-
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
-
-	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
-		switch (stat_config.aggr_mode) {
-		case AGGR_SOCKET:
-			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");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			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");
-			if (!metric_only)
-				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-		case AGGR_UNSET:
-			break;
-		}
-	}
-
-	if ((num_print_interval == 0 || interval_clear) && metric_only)
-		print_metric_headers(" ", true);
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
-}
-
-static void print_header(int argc, const char **argv)
-{
-	FILE *output = stat_config.output;
-	int i;
-
-	fflush(stdout);
-
-	if (!csv_output) {
-		fprintf(output, "\n");
-		fprintf(output, " Performance counter stats for ");
-		if (target.system_wide)
-			fprintf(output, "\'system wide");
-		else if (target.cpu_list)
-			fprintf(output, "\'CPU(s) %s", target.cpu_list);
-		else if (!target__has_task(&target)) {
-			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
-			for (i = 1; argv && (i < argc); i++)
-				fprintf(output, " %s", argv[i]);
-		} else if (target.pid)
-			fprintf(output, "process id \'%s", target.pid);
-		else
-			fprintf(output, "thread id \'%s", target.tid);
-
-		fprintf(output, "\'");
-		if (run_count > 1)
-			fprintf(output, " (%d runs)", run_count);
-		fprintf(output, ":\n\n");
-	}
-}
-
-static int get_precision(double num)
-{
-	if (num > 1)
-		return 0;
-
-	return lround(ceil(-log10(num)));
-}
-
-static void print_table(FILE *output, int precision, double avg)
-{
-	char tmp[64];
-	int idx, indent = 0;
-
-	scnprintf(tmp, 64, " %17.*f", precision, avg);
-	while (tmp[indent] == ' ')
-		indent++;
-
-	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
-
-	for (idx = 0; idx < run_count; idx++) {
-		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
-		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
-
-		fprintf(output, " %17.*f (%+.*f) ",
-			precision, run, precision, run - avg);
-
-		for (h = 0; h < n; h++)
-			fprintf(output, "#");
-
-		fprintf(output, "\n");
-	}
-
-	fprintf(output, "\n%*s# Final result:\n", indent, "");
-}
-
-static double timeval2double(struct timeval *t)
-{
-	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
-}
-
-static void print_footer(void)
-{
-	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
-	FILE *output = stat_config.output;
-	int n;
-
-	if (!null_run)
-		fprintf(output, "\n");
-
-	if (run_count == 1) {
-		fprintf(output, " %17.9f seconds time elapsed", avg);
-
-		if (ru_display) {
-			double ru_utime = timeval2double(&ru_data.ru_utime);
-			double ru_stime = timeval2double(&ru_data.ru_stime);
-
-			fprintf(output, "\n\n");
-			fprintf(output, " %17.9f seconds user\n", ru_utime);
-			fprintf(output, " %17.9f seconds sys\n", ru_stime);
-		}
-	} else {
-		double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
-		/*
-		 * Display at most 2 more significant
-		 * digits than the stddev inaccuracy.
-		 */
-		int precision = get_precision(sd) + 2;
-
-		if (walltime_run_table)
-			print_table(output, precision, avg);
-
-		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
-			precision, avg, precision, sd);
-
-		print_noise_pct(sd, avg);
-	}
-	fprintf(output, "\n\n");
-
-	if (print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
-		fprintf(output,
-"Some events weren't counted. Try disabling the NMI watchdog:\n"
-"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
-"	perf stat ...\n"
-"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
-
-	if (print_mixed_hw_group_error)
-		fprintf(output,
-			"The events in group usually have to be from "
-			"the same PMU. Try reorganizing the group.\n");
-}
-
 static void print_counters(struct timespec *ts, int argc, const char **argv)
 {
-	int interval = stat_config.interval;
-	struct perf_evsel *counter;
-	char buf[64], *prefix = NULL;
-
 	/* Do not print anything if we record to the pipe. */
 	if (STAT_RECORD && perf_stat.data.is_pipe)
 		return;
 
-	if (interval)
-		print_interval(prefix = buf, ts);
-	else
-		print_header(argc, argv);
-
-	if (metric_only) {
-		static int num_print_iv;
-
-		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)
-			fprintf(stat_config.output, "%s", prefix);
-	}
-
-	switch (stat_config.aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(prefix);
-		break;
-	case AGGR_THREAD:
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_aggr_thread(counter, prefix);
-		}
-		break;
-	case AGGR_GLOBAL:
-		evlist__for_each_entry(evsel_list, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_counter_aggr(counter, prefix);
-		}
-		if (metric_only)
-			fputc('\n', stat_config.output);
-		break;
-	case AGGR_NONE:
-		if (metric_only)
-			print_no_aggr_metric(prefix);
-		else {
-			evlist__for_each_entry(evsel_list, counter) {
-				if (is_duration_time(counter))
-					continue;
-				print_counter(counter, prefix);
-			}
-		}
-		break;
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-
-	if (!interval && !csv_output)
-		print_footer();
-
-	fflush(stat_config.output);
+	perf_evlist__print_counters(evsel_list, &stat_config, &target,
+				    ts, argc, argv);
 }
 
 static volatile int signr = -1;
@@ -1950,7 +700,7 @@ 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;
+	stat_config.metric_only = !unset;
 	return 0;
 }
 
@@ -1958,7 +708,7 @@ static int parse_metric_groups(const struct option *opt,
 			       const char *str,
 			       int unset __maybe_unused)
 {
-	return metricgroup__parse_groups(opt, str, &metric_events);
+	return metricgroup__parse_groups(opt, str, &stat_config.metric_events);
 }
 
 static const struct option stat_options[] = {
@@ -1969,7 +719,7 @@ static const struct option stat_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+	OPT_BOOLEAN('i', "no-inherit", &stat_config.no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_STRING('p', "pid", &target.pid, "pid",
 		   "stat events on existing process id"),
@@ -1982,11 +732,11 @@ static const struct option stat_options[] = {
 	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
+	OPT_INTEGER('r', "repeat", &stat_config.run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN(0, "table", &walltime_run_table,
+	OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table,
 		    "display details about each run (only with -r option)"),
-	OPT_BOOLEAN('n', "null", &null_run,
+	OPT_BOOLEAN('n', "null", &stat_config.null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
 		    "detailed run - start a lot of events"),
@@ -1999,8 +749,8 @@ static const struct option stat_options[] = {
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
+	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
 		     "monitor event in cgroup name only", parse_cgroups),
@@ -2017,7 +767,7 @@ static const struct option stat_options[] = {
 		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
-	OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+	OPT_BOOLEAN(0, "interval-clear", &stat_config.interval_clear,
 		    "clear screen in between new interval"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
 		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
@@ -2027,9 +777,9 @@ static const struct option stat_options[] = {
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
 		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
+	OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
 		     "ms to wait before starting measurement after program start"),
-	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure topdown level 1 statistics"),
@@ -2041,12 +791,14 @@ static const struct option stat_options[] = {
 	OPT_END()
 };
 
-static int perf_stat__get_socket(struct cpu_map *map, int cpu)
+static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
+				 struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
 }
 
-static int perf_stat__get_core(struct cpu_map *map, int cpu)
+static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
+			       struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_core(map, cpu, NULL);
 }
@@ -2063,9 +815,8 @@ static int cpu_map__get_max(struct cpu_map *map)
 	return max;
 }
 
-static struct cpu_map *cpus_aggr_map;
-
-static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+static int perf_stat__get_aggr(struct perf_stat_config *config,
+			       aggr_get_id_t get_id, struct cpu_map *map, int idx)
 {
 	int cpu;
 
@@ -2074,20 +825,22 @@ static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int id
 
 	cpu = map->map[idx];
 
-	if (cpus_aggr_map->map[cpu] == -1)
-		cpus_aggr_map->map[cpu] = get_id(map, idx);
+	if (config->cpus_aggr_map->map[cpu] == -1)
+		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
 
-	return cpus_aggr_map->map[cpu];
+	return config->cpus_aggr_map->map[cpu];
 }
 
-static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_cached(struct perf_stat_config *config,
+					struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
 }
 
-static int perf_stat__get_core_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_core_cached(struct perf_stat_config *config,
+				      struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_core, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
 }
 
 static int perf_stat_init_aggr_mode(void)
@@ -2096,18 +849,18 @@ static int perf_stat_init_aggr_mode(void)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_socket_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_cached;
+		stat_config.aggr_get_id = perf_stat__get_socket_cached;
 		break;
 	case AGGR_CORE:
-		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_cached;
+		stat_config.aggr_get_id = perf_stat__get_core_cached;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -2123,16 +876,16 @@ static int perf_stat_init_aggr_mode(void)
 	 * the aggregation translate cpumap.
 	 */
 	nr = cpu_map__get_max(evsel_list->cpus);
-	cpus_aggr_map = cpu_map__empty_new(nr + 1);
-	return cpus_aggr_map ? 0 : -ENOMEM;
+	stat_config.cpus_aggr_map = cpu_map__empty_new(nr + 1);
+	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
 
 static void perf_stat__exit_aggr_mode(void)
 {
-	cpu_map__put(aggr_map);
-	cpu_map__put(cpus_aggr_map);
-	aggr_map = NULL;
-	cpus_aggr_map = NULL;
+	cpu_map__put(stat_config.aggr_map);
+	cpu_map__put(stat_config.cpus_aggr_map);
+	stat_config.aggr_map = NULL;
+	stat_config.cpus_aggr_map = NULL;
 }
 
 static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
@@ -2190,12 +943,14 @@ static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
 	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
 }
 
-static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
+				      struct cpu_map *map, int idx)
 {
 	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
 }
 
-static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
+				    struct cpu_map *map, int idx)
 {
 	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
 }
@@ -2206,18 +961,18 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_socket_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_file;
+		stat_config.aggr_get_id = perf_stat__get_socket_file;
 		break;
 	case AGGR_CORE:
-		if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_file;
+		stat_config.aggr_get_id = perf_stat__get_core_file;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -2401,7 +1156,7 @@ static int add_default_attributes(void)
 	struct parse_events_error errinfo;
 
 	/* Set attrs if no event is selected and !null_run: */
-	if (null_run)
+	if (stat_config.null_run)
 		return 0;
 
 	if (transaction_run) {
@@ -2414,7 +1169,7 @@ static int add_default_attributes(void)
 			struct option opt = { .value = &evsel_list };
 
 			return metricgroup__parse_groups(&opt, "transaction",
-							 &metric_events);
+							 &stat_config.metric_events);
 		}
 
 		if (pmu_have_event("cpu", "cycles-ct") &&
@@ -2452,7 +1207,7 @@ static int add_default_attributes(void)
 		if (pmu_have_event("msr", "aperf") &&
 		    pmu_have_event("msr", "smi")) {
 			if (!force_metric_only)
-				metric_only = true;
+				stat_config.metric_only = true;
 			err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
 		} else {
 			fprintf(stderr, "To measure SMI cost, it needs "
@@ -2483,7 +1238,7 @@ static int add_default_attributes(void)
 		}
 
 		if (!force_metric_only)
-			metric_only = true;
+			stat_config.metric_only = true;
 		if (topdown_filter_events(topdown_attrs, &str,
 				arch_topdown_check_group(&warn)) < 0) {
 			pr_err("Out of memory\n");
@@ -2580,7 +1335,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (output_name)
 		data->file.path = output_name;
 
-	if (run_count != 1 || forever) {
+	if (stat_config.run_count != 1 || forever) {
 		pr_err("Cannot use -r option with perf stat record.\n");
 		return -1;
 	}
@@ -2599,9 +1354,8 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *stat_round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -2626,10 +1380,10 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool,
-			      union perf_event *event,
-			      struct perf_session *session __maybe_unused)
+int process_stat_config_event(struct perf_session *session,
+			      union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
@@ -2669,10 +1423,10 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	if (st->threads) {
@@ -2688,10 +1442,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 	struct cpu_map *cpus;
 
@@ -2853,12 +1607,12 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__collect_metric_expr(evsel_list);
 	perf_stat__init_shadow_stats();
 
-	if (csv_sep) {
-		csv_output = true;
-		if (!strcmp(csv_sep, "\\t"))
-			csv_sep = "\t";
+	if (stat_config.csv_sep) {
+		stat_config.csv_output = true;
+		if (!strcmp(stat_config.csv_sep, "\\t"))
+			stat_config.csv_sep = "\t";
 	} else
-		csv_sep = DEFAULT_SEPARATOR;
+		stat_config.csv_sep = DEFAULT_SEPARATOR;
 
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = __cmd_record(argc, argv);
@@ -2883,17 +1637,17 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+	if (stat_config.metric_only && stat_config.aggr_mode == AGGR_THREAD) {
 		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
 		goto out;
 	}
 
-	if (metric_only && run_count > 1) {
+	if (stat_config.metric_only && stat_config.run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
 	}
 
-	if (walltime_run_table && run_count <= 1) {
+	if (stat_config.walltime_run_table && stat_config.run_count <= 1) {
 		fprintf(stderr, "--table is only supported with -r\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		parse_options_usage(NULL, stat_options, "table", 0);
@@ -2931,7 +1685,7 @@ int cmd_stat(int argc, const char **argv)
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
-	if (csv_output) {
+	if (stat_config.csv_output) {
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
@@ -2939,9 +1693,9 @@ int cmd_stat(int argc, const char **argv)
 			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
-			big_num = false;
+			stat_config.big_num = false;
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
-		big_num = false;
+		stat_config.big_num = false;
 
 	setup_system_wide(argc);
 
@@ -2949,21 +1703,21 @@ int cmd_stat(int argc, const char **argv)
 	 * Display user/system times only for single
 	 * run and when there's specified tracee.
 	 */
-	if ((run_count == 1) && target__none(&target))
-		ru_display = true;
+	if ((stat_config.run_count == 1) && target__none(&target))
+		stat_config.ru_display = true;
 
-	if (run_count < 0) {
+	if (stat_config.run_count < 0) {
 		pr_err("Run count must be a positive number\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
-	} else if (run_count == 0) {
+	} else if (stat_config.run_count == 0) {
 		forever = true;
-		run_count = 1;
+		stat_config.run_count = 1;
 	}
 
-	if (walltime_run_table) {
-		walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
-		if (!walltime_run) {
+	if (stat_config.walltime_run_table) {
+		stat_config.walltime_run = zalloc(stat_config.run_count * sizeof(stat_config.walltime_run[0]));
+		if (!stat_config.walltime_run) {
 			pr_err("failed to setup -r option");
 			goto out;
 		}
@@ -3065,6 +1819,17 @@ int cmd_stat(int argc, const char **argv)
 	if (perf_stat_init_aggr_mode())
 		goto out;
 
+	/*
+	 * Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+	 * while avoiding that older tools show confusing messages.
+	 *
+	 * However for pipe sessions we need to keep it zero,
+	 * because script's perf_evsel__check_attr is triggered
+	 * by attr->sample_type != 0, and we can't run it on
+	 * stat sessions.
+	 */
+	stat_config.identifier = !(STAT_RECORD && perf_stat.data.is_pipe);
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
@@ -3079,8 +1844,8 @@ int cmd_stat(int argc, const char **argv)
 	signal(SIGABRT, skip_signal);
 
 	status = 0;
-	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-		if (run_count != 1 && verbose > 0)
+	for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
+		if (stat_config.run_count != 1 && verbose > 0)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
@@ -3132,7 +1897,7 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
-	free(walltime_run);
+	free(stat_config.walltime_run);
 
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 22ab8e67c760..90289f31dd87 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -181,7 +181,7 @@ static int __tp_field__init_uint(struct tp_field *field, int size, int offset, b
 	return 0;
 }
 
-static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap)
+static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap)
 {
 	return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
 }
@@ -198,7 +198,7 @@ static int __tp_field__init_ptr(struct tp_field *field, int offset)
 	return 0;
 }
 
-static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field)
 {
 	return __tp_field__init_ptr(field, format_field->offset);
 }
@@ -214,7 +214,7 @@ static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
 					  struct tp_field *field,
 					  const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -230,7 +230,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
 					 struct tp_field *field,
 					 const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -288,6 +288,13 @@ static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
 	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
 }
 
+static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv;
+
+	return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
+}
+
 static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
 {
 	evsel->priv = malloc(sizeof(struct syscall_tp));
@@ -498,16 +505,6 @@ static const char *clockid[] = {
 };
 static DEFINE_STRARRAY(clockid);
 
-static const char *socket_families[] = {
-	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
-	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
-	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
-	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
-	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
-	"ALG", "NFC", "VSOCK",
-};
-static DEFINE_STRARRAY(socket_families);
-
 static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
 						 struct syscall_arg *arg)
 {
@@ -631,6 +628,8 @@ static struct syscall_fmt {
 } syscall_fmts[] = {
 	{ .name	    = "access",
 	  .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
+	{ .name	    = "bind",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
 	{ .name	    = "bpf",
 	  .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
 	{ .name	    = "brk",	    .hexret = true,
@@ -645,6 +644,8 @@ static struct syscall_fmt {
 		   [4] = { .name = "tls",	    .scnprintf = SCA_HEX, }, }, },
 	{ .name	    = "close",
 	  .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+	{ .name	    = "connect",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
 	{ .name	    = "epoll_ctl",
 	  .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
 	{ .name	    = "eventfd2",
@@ -801,7 +802,8 @@ static struct syscall_fmt {
 	{ .name	    = "sendmsg",
 	  .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
 	{ .name	    = "sendto",
-	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
+		   [4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
 	  .arg = { [0] = STRARRAY(which, itimers), }, },
@@ -830,6 +832,7 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+	{ .name     = "umount2", .alias = "umount", },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@@ -856,13 +859,15 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	int		    nr_args;
+	int		    args_size;
 	bool		    is_exit;
 	bool		    is_open;
-	struct format_field *args;
+	struct tep_format_field *args;
 	const char	    *name;
 	struct syscall_fmt  *fmt;
 	struct syscall_arg_fmt *arg_fmt;
@@ -1095,11 +1100,21 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf,
 	ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
 }
 
+static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct augmented_arg *augmented_arg = arg->augmented.args;
+
+	return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
+}
+
 static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
 					      struct syscall_arg *arg)
 {
 	unsigned long ptr = arg->val;
 
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_string(arg, bf, size);
+
 	if (!arg->trace->vfs_getname)
 		return scnprintf(bf, size, "%#x", ptr);
 
@@ -1142,11 +1157,9 @@ static void sig_handler(int sig)
 	interrupted = sig == SIGINT;
 }
 
-static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
 {
-	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
-	printed += fprintf_duration(duration, duration_calculated, fp);
+	size_t printed = 0;
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
@@ -1157,6 +1170,14 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	return printed;
 }
 
+static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
+					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+{
+	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
+	printed += fprintf_duration(duration, duration_calculated, fp);
+	return printed + trace__fprintf_comm_tid(trace, thread, fp);
+}
+
 static int trace__process_event(struct trace *trace, struct machine *machine,
 				union perf_event *event, struct perf_sample *sample)
 {
@@ -1258,10 +1279,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	struct format_field *field;
+	struct tep_format_field *field, *last_field = NULL;
 	int idx = 0, len;
 
 	for (field = sc->args; field; field = field->next, ++idx) {
+		last_field = field;
+
 		if (sc->fmt && sc->fmt->arg[idx].scnprintf)
 			continue;
 
@@ -1270,7 +1293,7 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 			  strcmp(field->name, "path") == 0 ||
 			  strcmp(field->name, "pathname") == 0))
 			sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
-		else if (field->flags & FIELD_IS_POINTER)
+		else if (field->flags & TEP_FIELD_IS_POINTER)
 			sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
 		else if (strcmp(field->type, "pid_t") == 0)
 			sc->arg_fmt[idx].scnprintf = SCA_PID;
@@ -1292,6 +1315,9 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 		}
 	}
 
+	if (last_field)
+		sc->args_size = last_field->offset + last_field->size;
+
 	return 0;
 }
 
@@ -1472,14 +1498,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 }
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
-				      unsigned char *args, struct trace *trace,
-				      struct thread *thread)
+				      unsigned char *args, void *augmented_args, int augmented_args_size,
+				      struct trace *trace, struct thread *thread)
 {
 	size_t printed = 0;
 	unsigned long val;
 	u8 bit = 1;
 	struct syscall_arg arg = {
 		.args	= args,
+		.augmented = {
+			.size = augmented_args_size,
+			.args = augmented_args,
+		},
 		.idx	= 0,
 		.mask	= 0,
 		.trace  = trace,
@@ -1495,7 +1525,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 	ttrace->ret_scnprintf = NULL;
 
 	if (sc->args != NULL) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		for (field = sc->args; field;
 		     field = field->next, ++arg.idx, bit <<= 1) {
@@ -1654,6 +1684,17 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+{
+	void *augmented_args = NULL;
+
+	*augmented_args_size = sample->raw_size - sc->args_size;
+	if (*augmented_args_size > 0)
+		augmented_args = sample->raw_data + sc->args_size;
+
+	return augmented_args;
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
@@ -1663,6 +1704,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	size_t printed = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+	int augmented_args_size = 0;
+	void *augmented_args = NULL;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1686,13 +1729,24 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
 		trace__printf_interrupted_entry(trace);
-
+	/*
+	 * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
+	 * arguments, even if the syscall being handled, say "openat", uses only 4 arguments
+	 * this breaks syscall__augmented_args() check for augmented args, as we calculate
+	 * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
+	 * so when handling, say the openat syscall, we end up getting 6 args for the
+	 * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
+	 * thinking that the extra 2 u64 args are the augmented filename, so just check
+	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
+	 */
+	if (evsel != trace->syscalls.events.sys_enter)
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
 
 	printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
-					   args, trace, thread);
+					   args, augmented_args, augmented_args_size, trace, thread);
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
@@ -1723,7 +1777,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	char msg[1024];
-	void *args;
+	void *args, *augmented_args = NULL;
+	int augmented_args_size;
 
 	if (sc == NULL)
 		return -1;
@@ -1738,7 +1793,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
 out_put:
@@ -2022,6 +2078,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
+	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	int callchain_ret = 0;
 
 	if (sample->callchain) {
@@ -2039,13 +2096,31 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->trace_syscalls)
 		fprintf(trace->output, "(         ): ");
 
+	if (thread)
+		trace__fprintf_comm_tid(trace, thread, trace->output);
+
+	if (evsel == trace->syscalls.events.augmented) {
+		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+		struct syscall *sc = trace__syscall_info(trace, evsel, id);
+
+		if (sc) {
+			fprintf(trace->output, "%s(", sc->name);
+			trace__fprintf_sys_enter(trace, evsel, sample);
+			fputc(')', trace->output);
+			goto newline;
+		}
+
+		/*
+		 * XXX: Not having the associated syscall info or not finding/adding
+		 * 	the thread should never happen, but if it does...
+		 * 	fall thru and print it as a bpf_output event.
+		 */
+	}
+
 	fprintf(trace->output, "%s:", evsel->name);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		if (evsel == trace->syscalls.events.augmented)
-			trace__fprintf_sys_enter(trace, evsel, sample);
-		else
-			bpf_output__fprintf(trace, sample);
+		bpf_output__fprintf(trace, sample);
 	} else if (evsel->tp_format) {
 		if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
 		    trace__fprintf_sys_enter(trace, evsel, sample)) {
@@ -2055,12 +2130,14 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
+newline:
 	fprintf(trace->output, "\n");
 
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+	thread__put(thread);
 out:
 	return 0;
 }
@@ -3276,12 +3353,8 @@ int cmd_trace(int argc, const char **argv)
 		goto out;
 	}
 
-	if (evsel) {
-		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
-		    perf_evsel__init_augmented_syscall_tp_args(evsel))
-			goto out;
+	if (evsel)
 		trace.syscalls.events.augmented = evsel;
-	}
 
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
@@ -3326,6 +3399,34 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
+	/*
+	 * If we are augmenting syscalls, then combine what we put in the
+	 * __augmented_syscalls__ BPF map with what is in the
+	 * syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
+	 * combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
+	 *
+	 * We'll switch to look at two BPF maps, one for sys_enter and the
+	 * other for sys_exit when we start augmenting the sys_exit paths with
+	 * buffers that are being copied from kernel to userspace, think 'read'
+	 * syscall.
+	 */
+	if (trace.syscalls.events.augmented) {
+		evsel = trace.syscalls.events.augmented;
+
+		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+		    perf_evsel__init_augmented_syscall_tp_args(evsel))
+			goto out;
+		evsel->handler = trace__sys_enter;
+
+		evlist__for_each_entry(trace.evlist, evsel) {
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+				perf_evsel__init_augmented_syscall_tp(evsel);
+				perf_evsel__init_augmented_syscall_tp_ret(evsel);
+				evsel->handler = trace__sys_exit;
+			}
+		}
+	}
+
 	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
 		return trace__record(&trace, argc-1, &argv[1]);
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 466540ee8ea7..c72cc73a6b09 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -14,6 +14,7 @@ include/uapi/linux/sched.h
 include/uapi/linux/stat.h
 include/uapi/linux/vhost.h
 include/uapi/sound/asound.h
+include/linux/bits.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 2d0caf20ff3a..bc6c585f74fc 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -30,3 +30,4 @@ perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
 perf-trace			mainporcelain audit
+perf-version			mainporcelain common
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 69a31386d8cd..2ae44813ef2d 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Augment the openat syscall with the contents of the filename pointer argument.
+ * Augment syscalls with the contents of the pointer arguments.
  *
  * Test it with:
  *
@@ -10,15 +10,14 @@
  * the last one should be the one for '/etc/passwd'.
  *
  * This matches what is marshalled into the raw_syscall:sys_enter payload
- * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
- * which will be done as that feature is implemented in the next csets, for now
- * it will appear in a dump done by the default tracepoint handler in 'perf trace',
- * that uses bpf_output__fprintf() to just dump those contents, as done with
- * the bpf-output event associated with the __bpf_output__ map declared in
- * tools/perf/include/bpf/stdio.h.
+ * expected by the 'perf trace' beautifiers, and can be used by them, that will
+ * check if perf_sample->raw_data is more than what is expected for each
+ * syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
+ * contents of pointer arguments.
  */
 
 #include <stdio.h>
+#include <linux/socket.h>
 
 struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
@@ -27,6 +26,44 @@ struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .max_entries = __NR_CPUS__,
 };
 
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define augmented_filename_syscall(syscall)							\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	unsigned int len = sizeof(augmented_args);						\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {		\
+		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\
+		len &= sizeof(augmented_args.filename.value) - 1;				\
+	}											\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, len);						\
+	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
+}
+
 struct syscall_enter_openat_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
@@ -36,20 +73,101 @@ struct syscall_enter_openat_args {
 	long		   mode;
 };
 
-struct augmented_enter_openat_args {
-	struct syscall_enter_openat_args args;
-	char				 filename[64];
+augmented_filename_syscall(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
 };
 
-int syscall_enter(openat)(struct syscall_enter_openat_args *args)
-{
-	struct augmented_enter_openat_args augmented_args;
+augmented_filename_syscall(open);
 
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-	probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
-			  &augmented_args, sizeof(augmented_args));
-	return 1;
+struct syscall_enter_inotify_add_watch_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	char		   *filename_ptr;
+	long		   mask;
+};
+
+augmented_filename_syscall(inotify_add_watch);
+
+struct statbuf;
+
+struct syscall_enter_newstat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	struct stat	   *statbuf;
+};
+
+augmented_filename_syscall(newstat);
+
+#ifndef _K_SS_MAXSIZE
+#define _K_SS_MAXSIZE 128
+#endif
+
+#define augmented_sockaddr_syscall(syscall)						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct sockaddr_storage			addr;						\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args;				 	\
+	unsigned long addrlen = sizeof(augmented_args.addr);					\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */		\
+/*	if (addrlen > augmented_args.args.addrlen)				     */		\
+/*		addrlen = augmented_args.args.addrlen;				     */		\
+/*										     */		\
+	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 				\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);	\
+	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
 }
 
+struct sockaddr;
+
+struct syscall_enter_bind_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+augmented_sockaddr_syscall(bind);
+
+struct syscall_enter_connect_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+augmented_sockaddr_syscall(connect);
+
+struct syscall_enter_sendto_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	void		   *buff;
+	long		   len;
+	unsigned long	   flags;
+	struct sockaddr	   *addr_ptr;
+	long		   addr_len;
+};
+
+augmented_sockaddr_syscall(sendto);
+
 license(GPL);
diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c
new file mode 100644
index 000000000000..b59e8812ee8c
--- /dev/null
+++ b/tools/perf/examples/bpf/etcsnoop.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the filename syscalls with the contents of the filename pointer argument
+ * filtering only those that do not start with /etc/.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#include <stdio.h>
+
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+struct augmented_filename {
+	int	size;
+	int	reserved;
+	char	value[64];
+};
+
+#define augmented_filename_syscall_enter(syscall) 						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	char etc[6] = "/etc/";									\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0)			\
+		return 0;									\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
+			   augmented_args.filename.size));					\
+	return 0;										\
+}
+
+struct syscall_enter_openat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(open);
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index 47897d65e799..52b6d87fe822 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -26,6 +26,9 @@ struct bpf_map {
 #define syscall_enter(name) \
 	SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
 
+#define syscall_exit(name) \
+	SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
+
 #define license(name) \
 char _license[] SEC("license") = #name; \
 int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/include/bpf/linux/socket.h b/tools/perf/include/bpf/linux/socket.h
new file mode 100644
index 000000000000..7f844568dab8
--- /dev/null
+++ b/tools/perf/include/bpf/linux/socket.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SOCKET_H
+#define _UAPI_LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE	128	/* Implementation specific max size */
+#define _K_SS_ALIGNSIZE	(__alignof__ (struct sockaddr *))
+				/* Implementation specific desired alignment */
+
+typedef unsigned short __kernel_sa_family_t;
+
+struct __kernel_sockaddr_storage {
+	__kernel_sa_family_t	ss_family;		/* address family */
+	/* Following field(s) are implementation specific */
+	char		__data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+				/* space to achieve desired size, */
+				/* _SS_MAXSIZE value minus size of ss_family */
+} __attribute__ ((aligned(_K_SS_ALIGNSIZE)));	/* force desired alignment */
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+#endif /* _UAPI_LINUX_SOCKET_H */
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
new file mode 100644
index 000000000000..abc98b018446
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
@@ -0,0 +1,23 @@
+[
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC",
+    },
+    {
+        "PublicDescription": "Mispredicted or not predicted branch speculatively executed",
+        "EventCode": "0x10",
+        "EventName": "BR_MIS_PRED",
+        "BriefDescription": "Branch mispredicted"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed",
+        "EventCode": "0x12",
+        "EventName": "BR_PRED",
+        "BriefDescription": "Predictable branch"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
new file mode 100644
index 000000000000..687b2629e1d1
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
@@ -0,0 +1,26 @@
+[
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NOT_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NORMAL",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_PERIPH",
+    },
+    {
+        "PublicDescription": "Bus access",
+        "EventCode": "0x19",
+        "EventName": "BUS_ACCESS",
+        "BriefDescription": "Bus access"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
new file mode 100644
index 000000000000..df9201434cb6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
@@ -0,0 +1,191 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache refill",
+        "EventCode": "0x01",
+        "EventName": "L1I_CACHE_REFILL",
+        "BriefDescription": "L1I cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB refill",
+        "EventCode": "0x02",
+        "EventName": "L1I_TLB_REFILL",
+        "BriefDescription": "L1I TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache refill",
+        "EventCode": "0x03",
+        "EventName": "L1D_CACHE_REFILL",
+        "BriefDescription": "L1D cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache access",
+        "EventCode": "0x04",
+        "EventName": "L1D_CACHE_ACCESS",
+        "BriefDescription": "L1D cache access"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB refill",
+        "EventCode": "0x05",
+        "EventName": "L1D_TLB_REFILL",
+        "BriefDescription": "L1D TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache access",
+        "EventCode": "0x14",
+        "EventName": "L1I_CACHE_ACCESS",
+        "BriefDescription": "L1I cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data cache access",
+        "EventCode": "0x16",
+        "EventName": "L2D_CACHE_ACCESS",
+        "BriefDescription": "L2D cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data refill",
+        "EventCode": "0x17",
+        "EventName": "L2D_CACHE_REFILL",
+        "BriefDescription": "L2D cache refill"
+    },
+    {
+        "PublicDescription": "Level 2 data cache, Write-Back",
+        "EventCode": "0x18",
+        "EventName": "L2D_CACHE_WB",
+        "BriefDescription": "L2D cache Write-Back"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB",
+        "EventCode": "0x25",
+        "EventName": "L1D_TLB_ACCESS",
+        "BriefDescription": "L1D TLB access"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB",
+        "EventCode": "0x26",
+        "EventName": "L1I_TLB_ACCESS",
+        "BriefDescription": "L1I TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count",
+        "EventCode": "0x34",
+        "EventName": "L2D_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count",
+        "EventCode": "0x35",
+        "EventName": "L2I_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Branch target buffer misprediction",
+        "EventCode": "0x102",
+        "EventName": "BTB_MIS_PRED",
+        "BriefDescription": "BTB misprediction"
+    },
+    {
+        "PublicDescription": "ITB miss",
+        "EventCode": "0x103",
+        "EventName": "ITB_MISS",
+        "BriefDescription": "ITB miss"
+    },
+    {
+        "PublicDescription": "DTB miss",
+        "EventCode": "0x104",
+        "EventName": "DTB_MISS",
+        "BriefDescription": "DTB miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache late miss",
+        "EventCode": "0x105",
+        "EventName": "L1D_CACHE_LATE_MISS",
+        "BriefDescription": "L1D cache late miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache prefetch request",
+        "EventCode": "0x106",
+        "EventName": "L1D_CACHE_PREFETCH",
+        "BriefDescription": "L1D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 2 data cache prefetch request",
+        "EventCode": "0x107",
+        "EventName": "L2D_CACHE_PREFETCH",
+        "BriefDescription": "L2D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 1 stage 2 TLB refill",
+        "EventCode": "0x111",
+        "EventName": "L1_STAGE2_TLB_REFILL",
+        "BriefDescription": "L1 stage 2 TLB refill"
+    },
+    {
+        "PublicDescription": "Page walk cache level-0 stage-1 hit",
+        "EventCode": "0x112",
+        "EventName": "PAGE_WALK_L0_STAGE1_HIT",
+        "BriefDescription": "Page walk, L0 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-1 hit",
+        "EventCode": "0x113",
+        "EventName": "PAGE_WALK_L1_STAGE1_HIT",
+        "BriefDescription": "Page walk, L1 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-1 hit",
+        "EventCode": "0x114",
+        "EventName": "PAGE_WALK_L2_STAGE1_HIT",
+        "BriefDescription": "Page walk, L2 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-2 hit",
+        "EventCode": "0x115",
+        "EventName": "PAGE_WALK_L1_STAGE2_HIT",
+        "BriefDescription": "Page walk, L1 stage-2 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-2 hit",
+        "EventCode": "0x116",
+        "EventName": "PAGE_WALK_L2_STAGE2_HIT",
+        "BriefDescription": "Page walk, L2 stage-2 hit"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
new file mode 100644
index 000000000000..38cd1f1a70dc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
@@ -0,0 +1,20 @@
+[
+    {
+        "PublicDescription": "The number of core clock cycles",
+        "EventCode": "0x11",
+        "EventName": "CPU_CYCLES",
+        "BriefDescription": "Clock cycles"
+    },
+    {
+        "PublicDescription": "FSU clocking gated off cycle",
+        "EventCode": "0x101",
+        "EventName": "FSU_CLOCK_OFF_CYCLES",
+        "BriefDescription": "FSU clocking gated off cycle"
+    },
+    {
+        "PublicDescription": "Wait state cycle",
+        "EventCode": "0x110",
+        "EventName": "Wait_CYCLES",
+        "BriefDescription": "Wait state cycle"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
deleted file mode 100644
index bc03c06c3918..000000000000
--- a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
+++ /dev/null
@@ -1,32 +0,0 @@
-[
-    {
-        "ArchStdEvent": "L1D_CACHE_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_WR",
-    },
-    {
-        "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
-        "ArchStdEvent": "BUS_ACCESS_WR",
-   }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
new file mode 100644
index 000000000000..3720dc28a15f
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    },
+    {
+        "PublicDescription": "Exception taken",
+        "EventCode": "0x09",
+        "EventName": "EXC_TAKEN",
+        "BriefDescription": "Exception taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition check pass, exception return",
+        "EventCode": "0x0a",
+        "EventName": "EXC_RETURN",
+        "BriefDescription": "Exception return"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
new file mode 100644
index 000000000000..82cf753e6472
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
@@ -0,0 +1,89 @@
+[
+    {
+        "ArchStdEvent": "LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "DP_SPEC",
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC",
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC",
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC",
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC",
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC",
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, software increment",
+        "EventCode": "0x00",
+        "EventName": "SW_INCR",
+        "BriefDescription": "Software increment"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed",
+        "EventCode": "0x08",
+        "EventName": "INST_RETIRED",
+        "BriefDescription": "Instruction retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR",
+        "EventCode": "0x0b",
+        "EventName": "CID_WRITE_RETIRED",
+        "BriefDescription": "Write to CONTEXTIDR"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed",
+        "EventCode": "0x1b",
+        "EventName": "INST_SPEC",
+        "BriefDescription": "Speculatively executed"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed (condition check pass), write to TTBR",
+        "EventCode": "0x1c",
+        "EventName": "TTBR_WRITE_RETIRED",
+        "BriefDescription": "Instruction executed, TTBR write"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches",
+        "EventCode": "0x21",
+        "EventName": "BR_RETIRED",
+        "BriefDescription": "Branch retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush",
+        "EventCode": "0x22",
+        "EventName": "BR_MISPRED_RETIRED",
+        "BriefDescription": "Mispredicted branch retired"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed, NOP",
+        "EventCode": "0x100",
+        "EventName": "NOP_SPEC",
+        "BriefDescription": "Speculatively executed, NOP"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
new file mode 100644
index 000000000000..2aecc5c2347d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "LDREX_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC",
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
new file mode 100644
index 000000000000..08508697b318
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
@@ -0,0 +1,29 @@
+[
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "PublicDescription": "Data memory access",
+        "EventCode": "0x13",
+        "EventName": "MEM_ACCESS",
+        "BriefDescription": "Memory access"
+    },
+    {
+        "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs",
+        "EventCode": "0x1a",
+        "EventName": "MEM_ERROR",
+        "BriefDescription": "Memory error"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
new file mode 100644
index 000000000000..e2087de586bf
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
@@ -0,0 +1,50 @@
+[
+    {
+        "PublicDescription": "Decode starved for instruction cycle",
+        "EventCode": "0x108",
+        "EventName": "DECODE_STALL",
+        "BriefDescription": "Decode starved"
+    },
+    {
+        "PublicDescription": "Op dispatch stalled cycle",
+        "EventCode": "0x109",
+        "EventName": "DISPATCH_STALL",
+        "BriefDescription": "Dispatch stalled"
+    },
+    {
+        "PublicDescription": "IXA Op non-issue",
+        "EventCode": "0x10a",
+        "EventName": "IXA_STALL",
+        "BriefDescription": "IXA stalled"
+    },
+    {
+        "PublicDescription": "IXB Op non-issue",
+        "EventCode": "0x10b",
+        "EventName": "IXB_STALL",
+        "BriefDescription": "IXB stalled"
+    },
+    {
+        "PublicDescription": "BX Op non-issue",
+        "EventCode": "0x10c",
+        "EventName": "BX_STALL",
+        "BriefDescription": "BX stalled"
+    },
+    {
+        "PublicDescription": "LX Op non-issue",
+        "EventCode": "0x10d",
+        "EventName": "LX_STALL",
+        "BriefDescription": "LX stalled"
+    },
+    {
+        "PublicDescription": "SX Op non-issue",
+        "EventCode": "0x10e",
+        "EventName": "SX_STALL",
+        "BriefDescription": "SX stalled"
+    },
+    {
+        "PublicDescription": "FX Op non-issue",
+        "EventCode": "0x10f",
+        "EventName": "FX_STALL",
+        "BriefDescription": "FX stalled"
+    },
+]
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6c108fa79ae3..0b2b8305c965 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -21,6 +21,7 @@ perf-y += python-use.o
 perf-y += bp_signal.o
 perf-y += bp_signal_overflow.o
 perf-y += bp_account.o
+perf-y += wp.o
 perf-y += task-exit.o
 perf-y += sw-clock.o
 perf-y += mmap-thread-lookup.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d7a5e1b9aa6f..12c09e0ece71 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -120,6 +120,16 @@ static struct test generic_tests[] = {
 		.func = test__bp_accounting,
 		.is_supported = test__bp_signal_is_supported,
 	},
+	{
+		.desc = "Watchpoint",
+		.func = test__wp,
+		.is_supported = test__wp_is_supported,
+		.subtest = {
+			.skip_if_fail	= false,
+			.get_nr		= test__wp_subtest_get_nr,
+			.get_desc	= test__wp_subtest_get_desc,
+		},
+	},
 	{
 		.desc = "Number of exit events of a simple workload",
 		.func = test__task_exit,
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 699561fa512c..5f8501c68da4 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -8,7 +8,7 @@
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int is_signed;
 	int ret = 0;
 
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 3013ac8f83d0..cab7b0aea6ea 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -48,7 +48,7 @@ trace_libc_inet_pton_backtrace() {
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
-		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a9760e790563..b82f55fcc294 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -59,6 +59,9 @@ int test__python_use(struct test *test, int subtest);
 int test__bp_signal(struct test *test, int subtest);
 int test__bp_signal_overflow(struct test *test, int subtest);
 int test__bp_accounting(struct test *test, int subtest);
+int test__wp(struct test *test, int subtest);
+const char *test__wp_subtest_get_desc(int subtest);
+int test__wp_subtest_get_nr(void);
 int test__task_exit(struct test *test, int subtest);
 int test__mem(struct test *test, int subtest);
 int test__sw_clock_freq(struct test *test, int subtest);
@@ -106,6 +109,7 @@ int test__unit_number__scnprint(struct test *test, int subtest);
 int test__mem2node(struct test *t, int subtest);
 
 bool test__bp_signal_is_supported(void);
+bool test__wp_is_supported(void);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
new file mode 100644
index 000000000000..f89e6806557b
--- /dev/null
+++ b/tools/perf/tests/wp.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <linux/hw_breakpoint.h>
+#include "tests.h"
+#include "debug.h"
+#include "cloexec.h"
+
+#define WP_TEST_ASSERT_VAL(fd, text, val)       \
+do {                                            \
+	long long count;                        \
+	wp_read(fd, &count, sizeof(long long)); \
+	TEST_ASSERT_VAL(text, count == val);    \
+} while (0)
+
+volatile u64 data1;
+volatile u8 data2[3];
+
+static int wp_read(int fd, long long *count, int size)
+{
+	int ret = read(fd, count, size);
+
+	if (ret != size) {
+		pr_debug("failed to read: %d\n", ret);
+		return -1;
+	}
+	return 0;
+}
+
+static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
+				 void *wp_addr, unsigned long wp_len)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type           = PERF_TYPE_BREAKPOINT;
+	attr->size           = sizeof(struct perf_event_attr);
+	attr->config         = 0;
+	attr->bp_type        = wp_type;
+	attr->bp_addr        = (unsigned long)wp_addr;
+	attr->bp_len         = wp_len;
+	attr->sample_period  = 1;
+	attr->sample_type    = PERF_SAMPLE_IP;
+	attr->exclude_kernel = 1;
+	attr->exclude_hv     = 1;
+}
+
+static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
+{
+	int fd;
+	struct perf_event_attr attr;
+
+	get__perf_event_attr(&attr, wp_type, wp_addr, wp_len);
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0)
+		pr_debug("failed opening event %x\n", attr.bp_type);
+
+	return fd;
+}
+
+static int wp_ro_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_wo_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 0);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_rw_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R | HW_BREAKPOINT_W, (void *)&data1,
+		     sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_modify_test(void)
+{
+	int fd, ret;
+	unsigned long tmp = rand();
+	struct perf_event_attr new_attr;
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	data1 = tmp;
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Modify watchpoint with disabled = 1 */
+	get__perf_event_attr(&new_attr, HW_BREAKPOINT_W, (void *)&data2[0],
+			     sizeof(u8) * 2);
+	new_attr.disabled = 1;
+	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);
+	if (ret < 0) {
+		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Enable the event */
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0) {
+		pr_debug("Failed to enable event\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	data2[2] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static bool wp_ro_supported(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	return false;
+#else
+	return true;
+#endif
+}
+
+static void wp_ro_skip_msg(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	pr_debug("Hardware does not support read only watchpoints.\n");
+#endif
+}
+
+static struct {
+	const char *desc;
+	int (*target_func)(void);
+	bool (*is_supported)(void);
+	void (*skip_msg)(void);
+} wp_testcase_table[] = {
+	{
+		.desc = "Read Only Watchpoint",
+		.target_func = &wp_ro_test,
+		.is_supported = &wp_ro_supported,
+		.skip_msg = &wp_ro_skip_msg,
+	},
+	{
+		.desc = "Write Only Watchpoint",
+		.target_func = &wp_wo_test,
+	},
+	{
+		.desc = "Read / Write Watchpoint",
+		.target_func = &wp_rw_test,
+	},
+	{
+		.desc = "Modify Watchpoint",
+		.target_func = &wp_modify_test,
+	},
+};
+
+int test__wp_subtest_get_nr(void)
+{
+	return (int)ARRAY_SIZE(wp_testcase_table);
+}
+
+const char *test__wp_subtest_get_desc(int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return NULL;
+	return wp_testcase_table[i].desc;
+}
+
+int test__wp(struct test *test __maybe_unused, int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return TEST_FAIL;
+
+	if (wp_testcase_table[i].is_supported &&
+	    !wp_testcase_table[i].is_supported()) {
+		wp_testcase_table[i].skip_msg();
+		return TEST_SKIP;
+	}
+
+	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
+}
+
+/* The s390 so far does not have support for
+ * instruction breakpoint using the perf_event_open() system call.
+ */
+bool test__wp_is_supported(void)
+{
+#if defined(__s390x__)
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index f528ba35e140..c3b0afd67760 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,5 +7,6 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += sockaddr.o
 libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 9615af5d412b..2570152d3909 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -30,9 +30,36 @@ struct thread;
 
 size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
 
+extern struct strarray strarray__socket_families;
+
+/**
+ * augmented_arg: extra payload for syscall pointer arguments
+ 
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
+ * then its the arguments contents, so that we can show more than just a
+ * pointer. This will be done initially with eBPF, the start of that is at the
+ * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
+ * will eventually be done automagically caching the running kernel tracefs
+ * events data into an eBPF C script, that then gets compiled and its .o file
+ * cached for subsequent use. For char pointers like the ones for 'open' like
+ * syscalls its easy, for the rest we should use DWARF or better, BTF, much
+ * more compact.
+ *
+ * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
+ * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
+ * @value: u64 aligned, for structs, pathnames
+ */
+struct augmented_arg {
+	int  size;
+	int  int_arg;
+	u64  value[];
+};
+
 /**
  * @val: value of syscall argument being formatted
  * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
+ * @augmented_args_size: augmented_args total payload size
  * @thread: tid state (maps, pid, tid, etc)
  * @trace: 'perf trace' internals: all threads, etc
  * @parm: private area, may be an strarray, for instance
@@ -43,6 +70,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
 struct syscall_arg {
 	unsigned long val;
 	unsigned char *args;
+	struct {
+		struct augmented_arg *args;
+		int		     size;
+	} augmented;
 	struct thread *thread;
 	struct trace  *trace;
 	void	      *parm;
@@ -106,6 +137,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr
+
 size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
new file mode 100644
index 000000000000..71a79f72d9d9
--- /dev/null
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "trace/beauty/beauty.h"
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <arpa/inet.h>
+
+static const char *socket_families[] = {
+	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+	"ALG", "NFC", "VSOCK",
+};
+DEFINE_STRARRAY(socket_families);
+
+static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sa;
+	char tmp[16];
+	return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port),
+			 inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
+}
+
+static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
+	u32 flowinfo = ntohl(sin6->sin6_flowinfo);
+	char tmp[512];
+	size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
+				   inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
+	if (flowinfo != 0)
+		printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
+	if (sin6->sin6_scope_id != 0)
+		printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
+
+	return printed;
+}
+
+static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_un *sun = (struct sockaddr_un *)sa;
+	return scnprintf(bf, size, ", path: %s", sun->sun_path);
+}
+
+static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = {
+	[AF_LOCAL] = af_local__scnprintf,
+	[AF_INET]  = af_inet__scnprintf,
+	[AF_INET6] = af_inet6__scnprintf,
+};
+
+static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct sockaddr *sa = (struct sockaddr *)arg->augmented.args;
+	char family[32];
+	size_t printed;
+
+	strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family);
+	printed = scnprintf(bf, size, "{ .family: %s", family);
+
+	if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family])
+		printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed);
+
+	return printed + scnprintf(bf + printed, size - printed, " }");
+}
+
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg)
+{
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
+
+	return scnprintf(bf, size, "%#x", arg->val);
+}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7efe15b9618d..ecd9f9ceda77 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -73,6 +73,7 @@ libperf-y += vdso.o
 libperf-y += counts.o
 libperf-y += stat.o
 libperf-y += stat-shadow.o
+libperf-y += stat-display.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db1511359c5e..c4617bcfd521 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -906,9 +906,8 @@ out_free:
 	return err;
 }
 
-int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event,
-				      struct perf_session *session)
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 
@@ -932,9 +931,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	}
 }
 
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event)
 {
 	s64 err;
 
@@ -950,7 +948,7 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
 		return -EINVAL;
 
-	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	err = session->auxtrace->process_auxtrace_event(session, event, session->tool);
 	if (err < 0)
 		return err;
 
@@ -1185,9 +1183,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
 	}
 }
 
-int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session)
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event)
 {
 	if (auxtrace__dont_decode(session))
 		return 0;
@@ -1196,11 +1193,12 @@ int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+static int __auxtrace_mmap__read(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 bool snapshot, size_t snapshot_size)
 {
+	struct auxtrace_mmap *mm = &map->auxtrace_mmap;
 	u64 head, old = mm->prev, offset, ref;
 	unsigned char *data = mm->base;
 	size_t size, head_off, old_off, len1, len2, padding;
@@ -1287,7 +1285,7 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	ev.auxtrace.tid = mm->tid;
 	ev.auxtrace.cpu = mm->cpu;
 
-	if (fn(tool, &ev, data1, len1, data2, len2))
+	if (fn(tool, map, &ev, data1, len1, data2, len2))
 		return -1;
 
 	mm->prev = head;
@@ -1306,18 +1304,18 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	return 1;
 }
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+	return __auxtrace_mmap__read(map, itr, tool, fn, false, 0);
 }
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+	return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size);
 }
 
 /**
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 71fc3bd74299..d88f6e9eb461 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include <asm/bitsperlong.h>
 
 #include "../perf.h"
 #include "event.h"
@@ -33,6 +34,7 @@ union perf_event;
 struct perf_session;
 struct perf_evlist;
 struct perf_tool;
+struct perf_mmap;
 struct option;
 struct record_opts;
 struct auxtrace_info_event;
@@ -434,13 +436,14 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   bool per_cpu);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  struct perf_mmap *map,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn);
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
@@ -517,15 +520,12 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
 					 struct perf_session *session,
 					 perf_event__handler_t process);
-int perf_event__process_auxtrace_info(struct perf_tool *tool,
-				      union perf_event *event,
-				      struct perf_session *session);
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
-int perf_event__process_auxtrace_error(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session);
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event);
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event);
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
@@ -577,6 +577,23 @@ static inline void auxtrace__free(struct perf_session *session)
 	return session->auxtrace->free(session);
 }
 
+#define ITRACE_HELP \
+"				i:	    		synthesize instructions events\n"		\
+"				b:	    		synthesize branches events\n"		\
+"				c:	    		synthesize branches events (calls only)\n"	\
+"				r:	    		synthesize branches events (returns only)\n" \
+"				x:	    		synthesize transactions events\n"		\
+"				w:	    		synthesize ptwrite events\n"		\
+"				p:	    		synthesize power events\n"			\
+"				e:	    		synthesize error events\n"			\
+"				d:	    		create a debug log\n"			\
+"				g[len]:     		synthesize a call chain (use with i or x)\n" \
+"				l[len]:     		synthesize last branch entries (use with i or x)\n" \
+"				sNUMBER:    		skip initial number of events\n"		\
+"				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
+"				concatenate multiple options. Default is ibxwpe or cewp\n"
+
+
 #else
 
 static inline struct auxtrace_record *
@@ -717,6 +734,8 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct perf_evlist *evlist, int idx,
 				   bool per_cpu);
 
+#define ITRACE_HELP ""
+
 #endif
 
 #endif
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 47aac41349a2..f9ae1a993806 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1615,7 +1615,7 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
+	return PTR_ERR_OR_ZERO(evsel);
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index abd38abf1d91..2a36fab76994 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -182,20 +182,20 @@ err_put_field:
 }
 
 static struct bt_ctf_field_type*
-get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
+get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field)
 {
 	unsigned long flags = field->flags;
 
-	if (flags & FIELD_IS_STRING)
+	if (flags & TEP_FIELD_IS_STRING)
 		return cw->data.string;
 
-	if (!(flags & FIELD_IS_SIGNED)) {
+	if (!(flags & TEP_FIELD_IS_SIGNED)) {
 		/* unsigned long are mostly pointers */
-		if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER)
+		if (flags & TEP_FIELD_IS_LONG || flags & TEP_FIELD_IS_POINTER)
 			return cw->data.u64_hex;
 	}
 
-	if (flags & FIELD_IS_SIGNED) {
+	if (flags & TEP_FIELD_IS_SIGNED) {
 		if (field->size == 8)
 			return cw->data.s64;
 		else
@@ -287,7 +287,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
 				      struct perf_sample *sample,
-				      struct format_field *fmtf)
+				      struct tep_format_field *fmtf)
 {
 	struct bt_ctf_field_type *type;
 	struct bt_ctf_field *array_field;
@@ -304,10 +304,10 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
-	if (flags & FIELD_IS_STRING)
-		flags &= ~FIELD_IS_ARRAY;
+	if (flags & TEP_FIELD_IS_STRING)
+		flags &= ~TEP_FIELD_IS_ARRAY;
 
-	if (flags & FIELD_IS_DYNAMIC) {
+	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
 		tmp_val = tep_read_number(fmtf->event->pevent,
@@ -317,7 +317,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		offset &= 0xffff;
 	}
 
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 
 		type = bt_ctf_event_class_get_field_by_name(
 				event_class, name);
@@ -338,7 +338,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
 			field = bt_ctf_field_create(type);
@@ -348,7 +348,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			return -1;
 		}
 
-		if (flags & FIELD_IS_STRING)
+		if (flags & TEP_FIELD_IS_STRING)
 			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
@@ -357,7 +357,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 					fmtf->event->pevent,
 					data + offset + i * len, len);
 
-			if (!(flags & FIELD_IS_SIGNED))
+			if (!(flags & TEP_FIELD_IS_SIGNED))
 				ret = bt_ctf_field_unsigned_integer_set_value(
 						field, value_int);
 			else
@@ -369,7 +369,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
 		}
-		if (!(flags & FIELD_IS_ARRAY)) {
+		if (!(flags & TEP_FIELD_IS_ARRAY)) {
 			ret = bt_ctf_event_set_payload(event, name, field);
 			if (ret) {
 				pr_err("failed to set payload %s\n", name);
@@ -378,7 +378,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 		bt_ctf_field_put(field);
 	}
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 		ret = bt_ctf_event_set_payload(event, name, array_field);
 		if (ret) {
 			pr_err("Failed add payload array %s\n", name);
@@ -396,10 +396,10 @@ err_put_field:
 static int add_tracepoint_fields_values(struct ctf_writer *cw,
 					struct bt_ctf_event_class *event_class,
 					struct bt_ctf_event *event,
-					struct format_field *fields,
+					struct tep_format_field *fields,
 					struct perf_sample *sample)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -417,8 +417,8 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 				 struct perf_evsel *evsel,
 				 struct perf_sample *sample)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_values(cw, event_class, event,
@@ -970,7 +970,7 @@ out:
 
 static int event_class_add_field(struct bt_ctf_event_class *event_class,
 		struct bt_ctf_field_type *type,
-		struct format_field *field)
+		struct tep_format_field *field)
 {
 	struct bt_ctf_field_type *t = NULL;
 	char *name;
@@ -1009,10 +1009,10 @@ static int event_class_add_field(struct bt_ctf_event_class *event_class,
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
-				       struct format_field *fields,
+				       struct tep_format_field *fields,
 				       struct bt_ctf_event_class *event_class)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -1030,15 +1030,15 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		 * type and don't care that it is an array. What we don't
 		 * support is an array of strings.
 		 */
-		if (flags & FIELD_IS_STRING)
-			flags &= ~FIELD_IS_ARRAY;
+		if (flags & TEP_FIELD_IS_STRING)
+			flags &= ~TEP_FIELD_IS_ARRAY;
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
 		ret = event_class_add_field(event_class, type, field);
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
@@ -1055,8 +1055,8 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 				struct perf_evsel *evsel,
 				struct bt_ctf_event_class *class)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_types(cw, common_fields, class);
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file.path = input,
+		.file      = { .path = input, .fd = -1 },
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 7123746edcf4..69fbb0a72d0c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -463,6 +463,28 @@ int db_export__branch_types(struct db_export *dbe)
 		if (err)
 			break;
 	}
+
+	/* Add trace begin / end variants */
+	for (i = 0; branch_types[i].name ; i++) {
+		const char *name = branch_types[i].name;
+		u32 type = branch_types[i].branch_type;
+		char buf[64];
+
+		if (type == PERF_IP_FLAG_BRANCH ||
+		    (type & (PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END)))
+			continue;
+
+		snprintf(buf, sizeof(buf), "trace begin / %s", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_BEGIN, buf);
+		if (err)
+			break;
+
+		snprintf(buf, sizeof(buf), "%s / trace end", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_END, buf);
+		if (err)
+			break;
+	}
+
 	return err;
 }
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e596ae358c4d..29d7b97f66fb 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2685,7 +2685,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	return 0;
 }
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
@@ -2693,7 +2693,7 @@ struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *nam
 void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int offset;
 
 	if (!field)
@@ -2701,7 +2701,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 
 	offset = field->offset;
 
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = *(int *)(sample->raw_data + field->offset);
 		offset &= 0xffff;
 	}
@@ -2709,7 +2709,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 	return sample->raw_data + offset;
 }
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
 			 bool needs_swap)
 {
 	u64 value;
@@ -2751,7 +2751,7 @@ u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 
 	if (!field)
 		return 0;
@@ -2943,3 +2943,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 		return evsel->evlist->env;
 	return NULL;
 }
+
+static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd);
+		     thread++) {
+			int fd = FD(evsel, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evlist, evsel,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	struct cpu_map *cpus = evsel->cpus;
+	struct thread_map *threads = evsel->threads;
+
+	if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return store_evsel_ids(evsel, evlist);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c960614d3..4107c39f4a54 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,7 +102,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	struct event_format	*tp_format;
+	struct tep_event_format	*tp_format;
 	off_t			id_offset;
 	struct perf_stat_evsel  *stats;
 	void			*priv;
@@ -211,7 +211,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
 
 struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
-struct event_format *event_format__new(const char *sys, const char *name);
+struct tep_event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
@@ -296,11 +296,11 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 	return perf_evsel__rawptr(evsel, sample, name);
 }
 
-struct format_field;
+struct tep_format_field;
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
@@ -481,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 06dfb027879d..0d0a4c6f368b 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -73,7 +73,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 	}
 
 	if (details->trace_fields) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3cadc252dd89..1ec1d9bc2d63 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3206,7 +3206,7 @@ static int read_attr(int fd, struct perf_header *ph,
 static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 						struct tep_handle *pevent)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	char bf[128];
 
 	/* already prepared */
@@ -3448,10 +3448,10 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 	return ret;
 }
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session __maybe_unused)
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct feat_fd ff = { .fd = 0 };
 	struct feature_event *fe = (struct feature_event *)event;
 	int type = fe->header.type;
@@ -3637,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 }
 
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				   struct perf_session *session,
-				   perf_event__handler_t process)
+				 struct perf_evlist *evlist,
+				 perf_event__handler_t process)
 {
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each_entry(session->evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
@@ -3856,9 +3856,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
 	int fd = perf_data__fd(session->data);
@@ -3924,9 +3923,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event)
 {
 	__event_process_build_id(&event->build_id,
 				 event->build_id.filename,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6d7fe44aadc0..e17903caa71d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -116,15 +116,14 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool,
 				      perf_event__handler_t process,
 				      bool is_pipe);
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session);
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event);
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct perf_session *session,
+				 struct perf_evlist *evlist,
 				 perf_event__handler_t process);
 int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
 					     struct perf_evsel *evsel,
@@ -148,17 +147,15 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_session *session);
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
 				    struct dso *pos, u16 misc,
 				    perf_event__handler_t process,
 				    struct machine *machine);
-int perf_event__process_build_id(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event);
 bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index d404bed7003a..58f6a9ceb590 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1165,7 +1165,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 		decoder->pge = false;
 		decoder->continuous_period = false;
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_TRACE_END;
 		return 0;
 	}
 	if (err == INTEL_PT_RETURN)
@@ -1179,9 +1179,13 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->continuous_period = false;
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0)
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
+				decoder->state.to_ip = decoder->last_ip;
 				decoder->ip = decoder->last_ip;
+			}
+			decoder->state.type |= INTEL_PT_TRACE_END;
 		} else {
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
@@ -1208,7 +1212,8 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->ip = to_ip;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
+			decoder->state.to_ip = to_ip;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 		}
 		intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
@@ -1640,14 +1645,15 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_TIP_PGD:
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0) {
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
 				intel_pt_set_ip(decoder);
-				intel_pt_log("Omitting PGD ip " x64_fmt "\n",
-					     decoder->ip);
+				decoder->state.to_ip = decoder->ip;
 			}
 			decoder->pge = false;
 			decoder->continuous_period = false;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 
 		case INTEL_PT_TIP_PGE:
@@ -1661,6 +1667,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 				intel_pt_set_ip(decoder);
 				decoder->state.to_ip = decoder->ip;
 			}
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 
 		case INTEL_PT_TIP:
@@ -1739,6 +1746,7 @@ next:
 			intel_pt_set_ip(decoder);
 			decoder->state.from_ip = 0;
 			decoder->state.to_ip = decoder->ip;
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 		}
 
@@ -2077,9 +2085,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
 			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
-			if (decoder->ip)
-				return 0;
-			break;
+			if (!decoder->ip)
+				break;
+			if (decoder->packet.type == INTEL_PT_TIP_PGE)
+				decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			if (decoder->packet.type == INTEL_PT_TIP_PGD)
+				decoder->state.type |= INTEL_PT_TRACE_END;
+			return 0;
 
 		case INTEL_PT_FUP:
 			if (intel_pt_have_ip(decoder))
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 51c18d67f4ca..ed088d4726ba 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -37,6 +37,8 @@ enum intel_pt_sample_type {
 	INTEL_PT_EX_STOP	= 1 << 6,
 	INTEL_PT_PWR_EXIT	= 1 << 7,
 	INTEL_PT_CBR_CHG	= 1 << 8,
+	INTEL_PT_TRACE_BEGIN	= 1 << 9,
+	INTEL_PT_TRACE_END	= 1 << 10,
 };
 
 enum intel_pt_period_type {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index aec68908d604..48c1d415c6b0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -908,6 +908,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->insn_len = ptq->state->insn_len;
 		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
 	}
+
+	if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+	if (ptq->state->type & INTEL_PT_TRACE_END)
+		ptq->flags |= PERF_IP_FLAG_TRACE_END;
 }
 
 static int intel_pt_setup_queue(struct intel_pt *pt,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 19262f98cd4e..5b0b60f00275 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -19,7 +19,7 @@
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6a6929f208b4..354e54550d2b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -320,12 +320,11 @@ int map__load(struct map *map)
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
 					  sbuild_id);
-			pr_warning("%s with build id %s not found",
-				   name, sbuild_id);
+			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
-			pr_warning("Failed to open %s", name);
+			pr_debug("Failed to open %s", name);
 
-		pr_warning(", continuing without symbols\n");
+		pr_debug(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
 #ifdef HAVE_LIBELF_SUPPORT
@@ -334,12 +333,11 @@ int map__load(struct map *map)
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated (is prelink enabled?). "
+			pr_debug("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
-			pr_warning("no symbols found in %s, maybe install "
-				   "a debug package?\n", name);
+			pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
 		}
 #endif
 		return -1;
@@ -712,8 +710,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 		if (verbose >= 2) {
 
 			if (use_browser) {
-				pr_warning("overlapping maps in %s "
-					   "(disable tui for more info)\n",
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
 					   map->dso->name);
 			} else {
 				fputs("overlapping maps:\n", fp);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 215f69f41672..cdb95b3a1213 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -281,7 +281,7 @@ int perf_mmap__read_init(struct perf_mmap *map)
 }
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size))
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	unsigned char *data = md->base + page_size;
@@ -300,7 +300,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		size = md->mask + 1 - (md->start & md->mask);
 		md->start += size;
 
-		if (push(to, buf, size) < 0) {
+		if (push(md, to, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -310,7 +310,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	size = md->end - md->start;
 	md->start += size;
 
-	if (push(to, buf, size) < 0) {
+	if (push(md, to, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47c7956..e603314dc792 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -93,7 +93,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size));
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bad9e0296e9a..1904e7f6ec84 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -80,14 +80,20 @@ static union perf_event *dup_event(struct ordered_events *oe,
 	return oe->copy_on_queue ? __dup_event(oe, event) : event;
 }
 
-static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+static void __free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (event && oe->copy_on_queue) {
+	if (event) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
 }
 
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue)
+		__free_dup_event(oe, event);
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
 static struct ordered_event *alloc_event(struct ordered_events *oe,
 					 union perf_event *event)
@@ -95,21 +101,49 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
 	union perf_event *new_event;
+	size_t size;
 
 	new_event = dup_event(oe, event);
 	if (!new_event)
 		return NULL;
 
+	/*
+	 * We maintain the following scheme of buffers for ordered
+	 * event allocation:
+	 *
+	 *   to_free list -> buffer1 (64K)
+	 *                   buffer2 (64K)
+	 *                   ...
+	 *
+	 * Each buffer keeps an array of ordered events objects:
+	 *    buffer -> event[0]
+	 *              event[1]
+	 *              ...
+	 *
+	 * Each allocated ordered event is linked to one of
+	 * following lists:
+	 *   - time ordered list 'events'
+	 *   - list of currently removed events 'cache'
+	 *
+	 * Allocation of the ordered event uses the following order
+	 * to get the memory:
+	 *   - use recently removed object from 'cache' list
+	 *   - use available object in current allocation buffer
+	 *   - allocate new buffer if the current buffer is full
+	 *
+	 * Removal of ordered event object moves it from events to
+	 * the cache list.
+	 */
+	size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new);
+
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
 		list_del(&new->list);
 	} else if (oe->buffer) {
-		new = oe->buffer + oe->buffer_idx;
+		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
-	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
-
+	} else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) {
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
 			free_dup_event(oe, new_event);
@@ -122,11 +156,11 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 		oe->cur_alloc_size += size;
 		list_add(&oe->buffer->list, &oe->to_free);
 
-		/* First entry is abused to maintain the to_free list. */
-		oe->buffer_idx = 2;
-		new = oe->buffer + 1;
+		oe->buffer_idx = 1;
+		new = &oe->buffer->event[0];
 	} else {
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+		return NULL;
 	}
 
 	new->event = new_event;
@@ -300,15 +334,38 @@ void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t d
 	oe->deliver	   = deliver;
 }
 
+static void
+ordered_events_buffer__free(struct ordered_events_buffer *buffer,
+			    unsigned int max, struct ordered_events *oe)
+{
+	if (oe->copy_on_queue) {
+		unsigned int i;
+
+		for (i = 0; i < max; i++)
+			__free_dup_event(oe, buffer->event[i].event);
+	}
+
+	free(buffer);
+}
+
 void ordered_events__free(struct ordered_events *oe)
 {
-	while (!list_empty(&oe->to_free)) {
-		struct ordered_event *event;
+	struct ordered_events_buffer *buffer, *tmp;
 
-		event = list_entry(oe->to_free.next, struct ordered_event, list);
-		list_del(&event->list);
-		free_dup_event(oe, event->event);
-		free(event);
+	if (list_empty(&oe->to_free))
+		return;
+
+	/*
+	 * Current buffer might not have all the events allocated
+	 * yet, we need to free only allocated ones ...
+	 */
+	list_del(&oe->buffer->list);
+	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+
+	/* ... and continue with the rest */
+	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
+		list_del(&buffer->list);
+		ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
 	}
 }
 
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 8c7a2948593e..1338d5c345dc 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -25,23 +25,28 @@ struct ordered_events;
 typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
 					 struct ordered_event *event);
 
+struct ordered_events_buffer {
+	struct list_head	list;
+	struct ordered_event	event[0];
+};
+
 struct ordered_events {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	u64			max_alloc_size;
-	u64			cur_alloc_size;
-	struct list_head	events;
-	struct list_head	cache;
-	struct list_head	to_free;
-	struct ordered_event	*buffer;
-	struct ordered_event	*last;
-	ordered_events__deliver_t deliver;
-	int			buffer_idx;
-	unsigned int		nr_events;
-	enum oe_flush		last_flush_type;
-	u32			nr_unordered_events;
-	bool                    copy_on_queue;
+	u64				 last_flush;
+	u64				 next_flush;
+	u64				 max_timestamp;
+	u64				 max_alloc_size;
+	u64				 cur_alloc_size;
+	struct list_head		 events;
+	struct list_head		 cache;
+	struct list_head		 to_free;
+	struct ordered_events_buffer	*buffer;
+	struct ordered_event		*last;
+	ordered_events__deliver_t	 deliver;
+	int				 buffer_idx;
+	unsigned int			 nr_events;
+	enum oe_flush			 last_flush_type;
+	u32				 nr_unordered_events;
+	bool				 copy_on_queue;
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ce501ba14b08..50150dfc0cdf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -340,7 +340,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 }
 
 static PyObject*
-tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
 	struct tep_handle *pevent = field->event->pevent;
 	void *data = pe->sample.raw_data;
@@ -348,28 +348,28 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 	unsigned long long val;
 	unsigned int offset, len;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len    = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val     = tep_read_number(pevent, data + offset, len);
 			offset  = val;
 			len     = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			ret = _PyUnicode_FromString((char *)data + offset);
 		} else {
 			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER)
+		if (field->flags & TEP_FIELD_IS_POINTER)
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
-		else if (field->flags & FIELD_IS_SIGNED)
+		else if (field->flags & TEP_FIELD_IS_SIGNED)
 			ret = PyLong_FromLong((long) val);
 		else
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
@@ -383,10 +383,10 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 {
 	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
 	struct perf_evsel *evsel = pevent->evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!evsel->tp_format) {
-		struct event_format *tp_format;
+		struct tep_event_format *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->attr.config);
 		if (!tp_format)
@@ -1240,7 +1240,7 @@ static struct {
 static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	static char *kwlist[] = { "sys", "name", NULL };
 	char *sys  = NULL;
 	char *name = NULL;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d2c78ffd9fee..a2eeebbfb25f 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -147,6 +147,9 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 
+#include <sys/stat.h>
+#include <sys/types.h>
+
 #include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
@@ -159,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "config.h"
 
 struct s390_cpumsf {
 	struct auxtrace		auxtrace;
@@ -170,6 +174,8 @@ struct s390_cpumsf {
 	u32			pmu_type;
 	u16			machine_type;
 	bool			data_queued;
+	bool			use_logfile;
+	char			*logdir;
 };
 
 struct s390_cpumsf_queue {
@@ -177,6 +183,7 @@ struct s390_cpumsf_queue {
 	unsigned int		queue_nr;
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
+	FILE			*logfile;
 };
 
 /* Display s390 CPU measurement facility basic-sampling data entry */
@@ -595,6 +602,12 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			buffer->use_size = buffer->size;
 			buffer->use_data = buffer->data;
 		}
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	} else
 		buffer = sfq->buffer;
 
@@ -606,6 +619,13 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			return -ENOMEM;
 		buffer->use_size = buffer->size;
 		buffer->use_data = buffer->data;
+
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	}
 	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
 		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@@ -640,6 +660,23 @@ s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
 	sfq->sf = sf;
 	sfq->queue_nr = queue_nr;
 	sfq->cpu = -1;
+	if (sf->use_logfile) {
+		char *name;
+		int rc;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.smp.%02x",
+				 sf->logdir, queue_nr)
+			: asprintf(&name, "aux.smp.%02x", queue_nr);
+		if (rc > 0)
+			sfq->logfile = fopen(name, "w");
+		if (sfq->logfile == NULL) {
+			pr_err("Failed to open auxiliary log file %s,"
+			       "continue...\n", name);
+			sf->use_logfile = false;
+		}
+		free(name);
+	}
 	return sfq;
 }
 
@@ -850,8 +887,16 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 	struct auxtrace_queues *queues = &sf->queues;
 	unsigned int i;
 
-	for (i = 0; i < queues->nr_queues; i++)
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+						queues->queue_array[i].priv;
+
+		if (sfq != NULL && sfq->logfile) {
+			fclose(sfq->logfile);
+			sfq->logfile = NULL;
+		}
 		zfree(&queues->queue_array[i].priv);
+	}
 	auxtrace_queues__free(queues);
 }
 
@@ -864,6 +909,7 @@ static void s390_cpumsf_free(struct perf_session *session)
 	auxtrace_heap__free(&sf->heap);
 	s390_cpumsf_free_queues(session);
 	session->auxtrace = NULL;
+	free(sf->logdir);
 	free(sf);
 }
 
@@ -877,17 +923,55 @@ static int s390_cpumsf_get_type(const char *cpuid)
 
 /* Check itrace options set on perf report command.
  * Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
  * Return false otherwise.
  */
 static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 {
+	bool ison = false;
+
 	if (!itops || !itops->set)
 		return true;
-	pr_err("No --itrace options supported\n");
+	ison = itops->inject || itops->instructions || itops->branches ||
+		itops->transactions || itops->ptwrites ||
+		itops->pwr_events || itops->errors ||
+		itops->dont_decode || itops->calls || itops->returns ||
+		itops->callchain || itops->thread_stack ||
+		itops->last_branch;
+	if (!ison)
+		return true;
+	pr_err("Unsupported --itrace options specified\n");
 	return false;
 }
 
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+	struct s390_cpumsf *sf = cb;
+	struct stat stbuf;
+	int rc;
+
+	if (strcmp(var, "auxtrace.dumpdir"))
+		return 0;
+	sf->logdir = strdup(value);
+	if (sf->logdir == NULL) {
+		pr_err("Failed to find auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		return 1;
+	}
+	rc = stat(sf->logdir, &stbuf);
+	if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+		pr_err("Missing auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		free(sf->logdir);
+		sf->logdir = NULL;
+	}
+	return 1;
+}
+
 int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 				      struct perf_session *session)
 {
@@ -906,6 +990,9 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 		err = -EINVAL;
 		goto err_free;
 	}
+	sf->use_logfile = session->itrace_synth_opts->log;
+	if (sf->use_logfile)
+		perf_config(s390_cpumsf__config, sf);
 
 	err = auxtrace_queues__init(&sf->queues);
 	if (err)
@@ -940,6 +1027,7 @@ err_free_queues:
 	auxtrace_queues__free(&sf->queues);
 	session->auxtrace = NULL;
 err_free:
+	free(sf->logdir);
 	free(sf);
 	return err;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 45484f0f7292..89cb887648f9 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -99,7 +99,7 @@ static void define_symbolic_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_symbolic_values(struct print_flag_sym *field,
+static void define_symbolic_values(struct tep_print_flag_sym *field,
 				   const char *ev_name,
 				   const char *field_name)
 {
@@ -157,7 +157,7 @@ static void define_flag_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_flag_values(struct print_flag_sym *field,
+static void define_flag_values(struct tep_print_flag_sym *field,
 			       const char *ev_name,
 			       const char *field_name)
 {
@@ -189,62 +189,62 @@ static void define_flag_field(const char *ev_name,
 	LEAVE;
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		define_flag_value(ev_name, cur_field_name, "0",
 				  args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
 		define_flag_field(ev_name, cur_field_name, args->flags.delim);
 		define_flag_values(args->flags.flags, ev_name, cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
 		define_symbolic_field(ev_name, cur_field_name);
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_STRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BITMASK:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 	default:
 		pr_err("Unsupported print arg type\n");
 		/* we should warn... */
@@ -338,8 +338,8 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct addr_location *al)
 {
 	struct thread *thread = al->thread;
-	struct event_format *event = evsel->tp_format;
-	struct format_field *field;
+	struct tep_event_format *event = evsel->tp_format;
+	struct tep_format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
@@ -388,9 +388,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	/* common fields other than pid can be accessed via xsub fns */
 
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
+		if (field->flags & TEP_FIELD_IS_STRING) {
 			int offset;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				offset = *(int *)(data + field->offset);
 				offset &= 0xffff;
 			} else
@@ -399,7 +399,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 		} else { /* FIELD_IS_NUMERIC */
 			val = read_size(event, data + field->offset,
 					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
+			if (field->flags & TEP_FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
 				XPUSHs(sv_2mortal(newSVuv(val)));
@@ -537,8 +537,8 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -646,11 +646,11 @@ sub print_backtrace\n\
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -668,7 +668,7 @@ sub print_backtrace\n\
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t       ");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
@@ -678,7 +678,7 @@ sub print_backtrace\n\
 					event->name);
 				fprintf(ofp, "\"%s\", $%s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index dfc6093f118c..69aa93d4ee99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -193,7 +193,7 @@ static void try_call_object(const char *handler_name, PyObject *args)
 		call_object(handler, args, handler_name);
 }
 
-static void define_value(enum print_arg_type field_type,
+static void define_value(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *field_value,
@@ -204,7 +204,7 @@ static void define_value(enum print_arg_type field_type,
 	unsigned long long value;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_value";
 
 	t = PyTuple_New(4);
@@ -223,8 +223,8 @@ static void define_value(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_values(enum print_arg_type field_type,
-			  struct print_flag_sym *field,
+static void define_values(enum tep_print_arg_type field_type,
+			  struct tep_print_flag_sym *field,
 			  const char *ev_name,
 			  const char *field_name)
 {
@@ -235,7 +235,7 @@ static void define_values(enum print_arg_type field_type,
 		define_values(field_type, field->next, ev_name, field_name);
 }
 
-static void define_field(enum print_arg_type field_type,
+static void define_field(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *delim)
@@ -244,10 +244,10 @@ static void define_field(enum print_arg_type field_type,
 	PyObject *t;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_field";
 
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		t = PyTuple_New(3);
 	else
 		t = PyTuple_New(2);
@@ -256,7 +256,7 @@ static void define_field(enum print_arg_type field_type,
 
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
 
 	try_call_object(handler_name, t);
@@ -264,54 +264,54 @@ static void define_field(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
-		define_value(PRINT_FLAGS, ev_name, cur_field_name, "0",
+	case TEP_PRINT_ATOM:
+		define_value(TEP_PRINT_FLAGS, ev_name, cur_field_name, "0",
 			     args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
-		define_field(PRINT_FLAGS, ev_name, cur_field_name,
+		define_field(TEP_PRINT_FLAGS, ev_name, cur_field_name,
 			     args->flags.delim);
-		define_values(PRINT_FLAGS, args->flags.flags, ev_name,
+		define_values(TEP_PRINT_FLAGS, args->flags.flags, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
-		define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL);
-		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
+		define_field(TEP_PRINT_SYMBOL, ev_name, cur_field_name, NULL);
+		define_values(TEP_PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_STRING:
+	case TEP_PRINT_STRING:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
@@ -319,11 +319,11 @@ static void define_event_symbols(struct event_format *event,
 		break;
 	default:
 		/* gcc warns for these? */
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_FUNC:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_FUNC:
+	case TEP_PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -332,10 +332,10 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static PyObject *get_field_numeric_entry(struct event_format *event,
-		struct format_field *field, void *data)
+static PyObject *get_field_numeric_entry(struct tep_event_format *event,
+		struct tep_format_field *field, void *data)
 {
-	bool is_array = field->flags & FIELD_IS_ARRAY;
+	bool is_array = field->flags & TEP_FIELD_IS_ARRAY;
 	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
@@ -353,7 +353,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 
 		val = read_size(event, data + field->offset + i * item_size,
 				item_size);
-		if (field->flags & FIELD_IS_SIGNED) {
+		if (field->flags & TEP_FIELD_IS_SIGNED) {
 			if ((long long)val >= LONG_MIN &&
 					(long long)val <= LONG_MAX)
 				obj = _PyLong_FromLong(val);
@@ -790,11 +790,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
 {
-	struct event_format *event = evsel->tp_format;
+	struct tep_event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL, *all_entries_dict = NULL;
 	static char handler_name[256];
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long s, ns;
 	unsigned n = 0;
 	int pid;
@@ -867,22 +867,22 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		unsigned int offset, len;
 		unsigned long long val;
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			offset = field->offset;
 			len    = field->size;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				val     = tep_read_number(scripting_context->pevent,
 							  data + offset, len);
 				offset  = val;
 				len     = offset >> 16;
 				offset &= 0xffff;
 			}
-			if (field->flags & FIELD_IS_STRING &&
+			if (field->flags & TEP_FIELD_IS_STRING &&
 			    is_printable_array(data + offset, len)) {
 				obj = _PyUnicode_FromString((char *) data + offset);
 			} else {
 				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-				field->flags &= ~FIELD_IS_STRING;
+				field->flags &= ~TEP_FIELD_IS_STRING;
 			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
@@ -1590,8 +1590,8 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -1686,12 +1686,12 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_ARRAY ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_ARRAY ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -1709,7 +1709,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t\t");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
@@ -1719,7 +1719,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 					event->name);
 				fprintf(ofp, "\"%s\", %s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8b9369303561..7d2c8ce6cfad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -199,12 +199,10 @@ void perf_session__delete(struct perf_session *session)
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+static int process_event_synth_tracing_data_stub(struct perf_session *session
 						 __maybe_unused,
 						 union perf_event *event
-						 __maybe_unused,
-						 struct perf_session *session
-						__maybe_unused)
+						 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -277,10 +275,8 @@ static int skipn(int fd, off_t n)
 	return 0;
 }
 
-static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused,
+				       union perf_event *event)
 {
 	dump_printf(": unhandled!\n");
 	if (perf_data__is_pipe(session->data))
@@ -288,9 +284,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -298,9 +293,8 @@ static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
 
 
 static
-int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_thread_map(event, stdout);
@@ -310,9 +304,8 @@ int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
-			       union perf_event *event __maybe_unused,
-			       struct perf_session *session __maybe_unused)
+int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
+			       union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_cpu_map(event, stdout);
@@ -322,9 +315,8 @@ int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *session __maybe_unused)
+int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_config(event, stdout);
@@ -333,10 +325,8 @@ int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_stub(struct perf_tool *tool __maybe_unused,
-			     union perf_event *event __maybe_unused,
-			     struct perf_session *perf_session
-			     __maybe_unused)
+static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
+			     union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat(event, stdout);
@@ -345,10 +335,8 @@ static int process_stat_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *perf_session
-				   __maybe_unused)
+static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
+				   union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_round(event, stdout);
@@ -1374,37 +1362,37 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(tool, event, session);
+		return tool->tracing_data(session, event);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(tool, event, session);
+		return tool->build_id(session, event);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(tool, event, session);
+		return tool->id_index(session, event);
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(tool, event, session);
+		return tool->auxtrace_info(session, event);
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(tool, event, session);
+		return tool->auxtrace(session, event);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(tool, event, session);
+		return tool->auxtrace_error(session, event);
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(tool, event, session);
+		return tool->thread_map(session, event);
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(tool, event, session);
+		return tool->cpu_map(session, event);
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(tool, event, session);
+		return tool->stat_config(session, event);
 	case PERF_RECORD_STAT:
-		return tool->stat(tool, event, session);
+		return tool->stat(session, event);
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(tool, event, session);
+		return tool->stat_round(session, event);
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(tool, event, session);
+		return tool->time_conv(session, event);
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(tool, event, session);
+		return tool->feature(session, event);
 	default:
 		return -EINVAL;
 	}
@@ -2133,9 +2121,8 @@ out:
 	return err;
 }
 
-int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event)
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct id_index_event *ie = &event->id_index;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da40b4b380ca..d96eccd7d27f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -120,9 +120,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
-int perf_event__process_id_index(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event);
 
 int perf_event__synthesize_id_index(struct perf_tool *tool,
 				    perf_event__handler_t process,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1942f6dd24f6..63f758c655d5 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -5,16 +5,18 @@ from subprocess import Popen, PIPE
 from re import sub
 
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ]
+    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
 cc = getenv("CC")
 if cc == "clang":
-    from _sysconfigdata import build_time_vars
-    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-mcet"):
-        build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-fcf-protection"):
-        build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"])
+    from distutils.sysconfig import get_config_vars
+    vars = get_config_vars()
+    for var in ('CFLAGS', 'OPT'):
+        vars[var] = sub("-specs=[^ ]+", "", vars[var])
+        if not clang_has_option("-mcet"):
+            vars[var] = sub("-mcet", "", vars[var])
+        if not clang_has_option("-fcf-protection"):
+            vars[var] = sub("-fcf-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b284276ec963..f96c005b3c41 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1884,7 +1884,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
 struct hpp_dynamic_entry {
 	struct perf_hpp_fmt hpp;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned dynamic_len;
 	bool raw_trace;
 };
@@ -1899,7 +1899,7 @@ static int hde_width(struct hpp_dynamic_entry *hde)
 		if (namelen > len)
 			len = namelen;
 
-		if (!(hde->field->flags & FIELD_IS_STRING)) {
+		if (!(hde->field->flags & TEP_FIELD_IS_STRING)) {
 			/* length for print hex numbers */
 			fieldlen = hde->field->size * 2 + 2;
 		}
@@ -1915,7 +1915,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 			       struct hist_entry *he)
 {
 	char *str, *pos;
-	struct format_field *field = hde->field;
+	struct tep_format_field *field = hde->field;
 	size_t namelen;
 	bool last = false;
 
@@ -2000,7 +2000,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
 	char *str, *pos;
-	struct format_field *field;
+	struct tep_format_field *field;
 	size_t namelen;
 	bool last = false;
 	int ret;
@@ -2060,7 +2060,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 			       struct hist_entry *a, struct hist_entry *b)
 {
 	struct hpp_dynamic_entry *hde;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned offset, size;
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
@@ -2071,7 +2071,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	}
 
 	field = hde->field;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
 
 		tep_read_number_field(field, a->raw_data, &dyn);
@@ -2117,7 +2117,7 @@ static void hde_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field,
 		      int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2252,7 +2252,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 }
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
-				    struct format_field *field,
+				    struct tep_format_field *field,
 				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2270,7 +2270,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
@@ -2305,7 +2305,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
@@ -2327,7 +2327,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	bool raw_trace = symbol_conf.raw_trace;
 	int ret = 0;
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
new file mode 100644
index 000000000000..e7b4c44ebb62
--- /dev/null
+++ b/tools/perf/util/stat-display.c
@@ -0,0 +1,1166 @@
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include "sane_ctype.h"
+#include "cgroup.h"
+#include <math.h>
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
+{
+	if (config->csv_output) {
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+					config->csv_sep,
+					run,
+					config->csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+	else if (pct)
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+			struct perf_evsel *evsel, double avg)
+{
+	struct perf_stat_evsel *ps;
+
+	if (config->run_count == 1)
+		return;
+
+	ps = evsel->stats;
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void aggr_printout(struct perf_stat_config *config,
+			  struct perf_evsel *evsel, int id, int nr)
+{
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+		fprintf(config->output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(config->output, "S%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(config->output, "CPU%*d%s",
+			config->csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
+		break;
+	case AGGR_THREAD:
+		fprintf(config->output, "%*s-%*d%s",
+			config->csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			config->csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			config->csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+}
+
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(config, os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
+}
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(struct perf_stat_config *config,
+			      void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[1024], str[1024];
+	unsigned mlen = config->metric_only_len;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
+}
+
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+				void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
+	else
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct perf_evsel *evsel, int id)
+{
+	struct perf_evlist *evlist = evsel->evlist;
+	int i;
+
+	if (!config->aggr_get_id)
+		return 0;
+
+	if (config->aggr_mode == AGGR_NONE)
+		return id;
+
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct perf_evsel *evsel, double avg)
+{
+	FILE *output = config->output;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (config->csv_output) {
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (config->big_num)
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(config, evsel, id, nr);
+
+	fprintf(output, fmt, avg, config->csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			evsel->unit, config->csv_sep);
+
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
+}
+
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->attr.type;
+	struct perf_evsel *pos;
+
+	if (counter->nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->attr.type;
+			continue;
+		}
+		if (pmu_type != pos->attr.type)
+			return true;
+	}
+
+	return false;
+}
+
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
+{
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = config->output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	new_line_t nl;
+
+	if (config->metric_only) {
+		nl = new_line_metric;
+		if (config->csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (config->csv_output && !config->metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[config->aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (config->metric_only) {
+			pm(config, &os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(config, counter, id, nr);
+
+		fprintf(config->output, "%*s%s",
+			config->csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			config->csv_sep);
+
+		if (counter->supported) {
+			config->print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				config->print_mixed_hw_group_error = 1;
+		}
+
+		fprintf(config->output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			counter->unit, config->csv_sep);
+
+		fprintf(config->output, "%*s",
+			config->csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(config->output, "%s%s",
+				config->csv_sep, counter->cgrp->name);
+
+		if (!config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+		if (config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (!config->metric_only)
+		abs_printout(config, id, nr, counter, uval);
+
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+	out.force_header = false;
+
+	if (config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+
+	perf_stat__print_shadow_stats(config, counter, uval,
+				first_shadow_cpu(config, counter, id),
+				&out, &config->metric_events, st);
+	if (!config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct perf_evlist *evlist)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
+		evlist__for_each_entry(evlist, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			perf_stat__update_shadow_stats(counter, val,
+					first_shadow_cpu(config, counter, id),
+					&rt_stat);
+		}
+	}
+}
+
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+
+	counter->uniquified_name = true;
+}
+
+static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evlist->entries), node);
+	list_for_each_entry_continue (alias, &evlist->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
+			break;
+		alias->merged_stat = true;
+		cb(config, alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(config, counter, data, true);
+	if (config->no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
+		collect_all_aliases(config, counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+		    struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
+static void print_aggr(struct perf_stat_config *config,
+		       struct perf_evlist *evlist,
+		       char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	struct perf_evsel *counter;
+	int s, id, nr;
+	double uval;
+	u64 ena, run, val;
+	bool first;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	aggr_update_shadow(config, evlist);
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		struct aggr_data ad;
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		ad.id = id = config->aggr_map->map[s];
+		first = true;
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(config, counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(config, counter, id, nr);
+			}
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
+
+			uval = val * counter->scale;
+			printout(config, id, nr, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
+			if (!metric_only)
+				fputc('\n', output);
+		}
+		if (metric_only)
+			fputc('\n', output);
+	}
+}
+
+static int cmp_val(const void *a, const void *b)
+{
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret,
+					struct target *_target)
+{
+	int cpu, thread, i = 0;
+	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(_target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
+			      struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		id = buf[thread].id;
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &config->stats[id]);
+		else
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
+		fputc('\n', output);
+	}
+
+	free(buf);
+}
+
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->stats;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
+/*
+ * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
+ */
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct perf_evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	double uval;
+	struct caggr_data cd = { .avg = 0.0 };
+
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
+		return;
+
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = cd.avg * counter->scale;
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
+	if (!metric_only)
+		fprintf(output, "\n");
+}
+
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_stat_config *config,
+			  struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(config, counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
+
+		fputc('\n', output);
+	}
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evlist->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, config->output);
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			if (first) {
+				aggr_printout(config, counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
+		}
+		fputc('\n', config->output);
+	}
+}
+
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+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(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 const char *prefix, bool no_indent)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = config->output
+	};
+
+	if (prefix)
+		fprintf(config->output, "%s", prefix);
+
+	if (!config->csv_output && !no_indent)
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
+	if (config->csv_output) {
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
+	}
+
+	/* Print metrics headers only */
+	evlist__for_each_entry(evlist, counter) {
+		if (is_duration_time(counter))
+			continue;
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		out.force_header = true;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(config, counter, 0,
+					      0,
+					      &out,
+					      &config->metric_events,
+					      &rt_stat);
+	}
+	fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+			   struct perf_evlist *evlist,
+			   char *prefix, struct timespec *ts)
+{
+	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
+	FILE *output = config->output;
+	static int num_print_interval;
+
+	if (config->interval_clear)
+		puts(CONSOLE_CLEAR);
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+		switch (config->aggr_mode) {
+		case AGGR_SOCKET:
+			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");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			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");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+		case AGGR_UNSET:
+			break;
+		}
+	}
+
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
+		print_metric_headers(config, evlist, " ", true);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
+			 int argc, const char **argv)
+{
+	FILE *output = config->output;
+	int i;
+
+	fflush(stdout);
+
+	if (!config->csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (_target->system_wide)
+			fprintf(output, "\'system wide");
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
+		else
+			fprintf(output, "thread id \'%s", _target->tid);
+
+		fprintf(output, "\'");
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
+		fprintf(output, ":\n\n");
+	}
+}
+
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < config->run_count; idx++) {
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
+static double timeval2double(struct timeval *t)
+{
+	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
+}
+
+static void print_footer(struct perf_stat_config *config)
+{
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+	FILE *output = config->output;
+	int n;
+
+	if (!config->null_run)
+		fprintf(output, "\n");
+
+	if (config->run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
+
+			fprintf(output, "\n\n");
+			fprintf(output, " %17.9f seconds user\n", ru_utime);
+			fprintf(output, " %17.9f seconds sys\n", ru_stime);
+		}
+	} else {
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (config->walltime_run_table)
+			print_table(config, output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(config, sd, avg);
+	}
+	fprintf(output, "\n\n");
+
+	if (config->print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (config->print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
+}
+
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv)
+{
+	bool metric_only = config->metric_only;
+	int interval = config->interval;
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(config, evlist, prefix = buf, ts);
+	else
+		print_header(config, _target, argc, argv);
+
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(config, evlist, prefix, false);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
+	}
+
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(config, evlist, prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_aggr_thread(config, _target, counter, prefix);
+		}
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_counter_aggr(config, counter, prefix);
+		}
+		if (metric_only)
+			fputc('\n', config->output);
+		break;
+	case AGGR_NONE:
+		if (metric_only)
+			print_no_aggr_metric(config, evlist, prefix);
+		else {
+			evlist__for_each_entry(evlist, counter) {
+				if (is_duration_time(counter))
+					continue;
+				print_counter(config, counter, prefix);
+			}
+		}
+		break;
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	if (!interval && !config->csv_output)
+		print_footer(config);
+
+	fflush(config->output);
+}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5f2512..8ad32763cfff 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st,
 	return v->stats.n;
 }
 
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+					  int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st)
@@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu,
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
 	if (ratio)
-		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
 				  ratio);
 	else
-		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+					 int cpu,
 					 struct perf_evsel *evsel, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st)
@@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(int cpu,
+static void print_branch_misses(struct perf_stat_config *config,
+				int cpu,
 				struct perf_evsel *evsel,
 				double avg,
 				struct perf_stat_output_ctx *out,
@@ -469,10 +472,11 @@ static void print_branch_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+				  int cpu,
 				  struct perf_evsel *evsel,
 				  double avg,
 				  struct perf_stat_output_ctx *out,
@@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
 /*
@@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 	return sanitize_val(1.0 - sum);
 }
 
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+			   int cpu, struct perf_evsel *evsel,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 
 	if (cost > 10)
 		color = PERF_COLOR_RED;
-	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
-	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
-static void generic_metric(const char *metric_expr,
+static void generic_metric(struct perf_stat_config *config,
+			   const char *metric_expr,
 			   struct perf_evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
@@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr,
 		const char *p = metric_expr;
 
 		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(ctxp, NULL, "%8.1f",
+			print_metric(config, ctxp, NULL, "%8.1f",
 				metric_name ?
 				metric_name :
 				out->force_header ?  name : "",
 				ratio);
 		else
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 	} else
-		print_metric(ctxp, NULL, NULL, "", 0);
+		print_metric(config, ctxp, NULL, NULL, "", 0);
 }
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"insn per cycle", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
 		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 						    ctx, cpu));
 
 		if (total && avg) {
-			out->new_line(ctxp);
+			out->new_line(config, ctxp);
 			ratio = total / avg;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(cpu, evsel, avg, out, st);
+			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all branches", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
@@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(cpu, evsel, avg, out, st);
+			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(cpu, evsel, avg, out, st);
+			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(cpu, evsel, avg, out, st);
+			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(cpu, evsel, avg, out, st);
+			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
@@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = avg * 100 / total;
 
 		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.3f %%",
+			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "Ghz", 0);
+			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total)
-			print_metric(ctxp, NULL,
+			print_metric(config, ctxp, NULL,
 					"%7.2f%%", "transactional cycles",
 					100.0 * (avg / total));
 		else
-			print_metric(ctxp, NULL, NULL, "transactional cycles",
+			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
 		else
-			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
 					 ctx, cpu);
@@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.0f",
+			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@@ -912,33 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (avg)
 			ratio = total / avg;
 
-		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
 		else
-			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
 		double fe_bound = td_fe_bound(ctx, cpu, st);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, 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, st);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, 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, st);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, 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, st);
@@ -955,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		if (td_total_slots(ctx, cpu, st) > 0)
-			print_metric(ctxp, color, "%8.1f%%", name,
+			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
-			print_metric(ctxp, NULL, NULL, name, 0);
+			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
 				evsel->metric_name, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
@@ -975,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			unit = 'K';
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(cpu, evsel, out, st);
+		print_smi_cost(config, cpu, evsel, out, st);
 	} else {
 		num = 0;
 	}
@@ -987,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		list_for_each_entry (mexp, &me->head, nd) {
 			if (num++ > 0)
-				out->new_line(ctxp);
-			generic_metric(mexp->metric_expr, mexp->metric_events,
+				out->new_line(config, ctxp);
+			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
 					avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0b0fad..4d40515307b8 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -374,9 +374,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	return 0;
 }
 
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event,
-				   struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event)
 {
 	struct perf_counts_values count;
 	struct stat_event *st = &event->stat;
@@ -435,3 +434,98 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 
 	return ret;
 }
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_evsel *leader = evsel->leader;
+
+	if (config->scale) {
+		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+				    PERF_FORMAT_TOTAL_TIME_RUNNING;
+	}
+
+	/*
+	 * The event is part of non trivial group, let's enable
+	 * the group read (for leader) and ID retrieval for all
+	 * members.
+	 */
+	if (leader->nr_members > 1)
+		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+	attr->inherit = !config->no_inherit;
+
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+
+	if (config->identifier)
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(target) && !config->initial_delay)
+			attr->enable_on_exec = 1;
+	}
+
+	if (target__has_cpu(target) && !target__has_per_thread(target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
+	return perf_evsel__open_per_thread(evsel, evsel->threads);
+}
+
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs)
+{
+	int err;
+
+	if (attrs) {
+		err = perf_event__synthesize_attrs(tool, evlist, process);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	err = perf_event__synthesize_extra_attr(tool, evlist, process,
+						attrs);
+
+	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
+						 process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
+					     process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb986f7fc..2f9c9159a364 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -4,8 +4,14 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
 #include "xyarray.h"
 #include "rblist.h"
+#include "perf.h"
+#include "event.h"
 
 struct stats {
 	double n, mean, M2;
@@ -84,15 +90,42 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+			     struct cpu_map *m, int cpu);
+
 struct perf_stat_config {
-	enum aggr_mode	aggr_mode;
-	bool		scale;
-	FILE		*output;
-	unsigned int	interval;
-	unsigned int	timeout;
-	int		times;
-	struct runtime_stat *stats;
-	int		stats_num;
+	enum aggr_mode		 aggr_mode;
+	bool			 scale;
+	bool			 no_inherit;
+	bool			 identifier;
+	bool			 csv_output;
+	bool			 interval_clear;
+	bool			 metric_only;
+	bool			 null_run;
+	bool			 ru_display;
+	bool			 big_num;
+	bool			 no_merge;
+	bool			 walltime_run_table;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 initial_delay;
+	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
+	int			 times;
+	int			 run_count;
+	int			 print_free_counters_hint;
+	int			 print_mixed_hw_group_error;
+	struct runtime_stat	*stats;
+	int			 stats_num;
+	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
+	struct cpu_map		*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct cpu_map		*cpus_aggr_map;
+	u64			*walltime_run;
+	struct rblist		 metric_events;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -130,9 +163,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
@@ -148,7 +182,8 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -164,11 +199,25 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 struct perf_tool;
 union perf_event;
 struct perf_session;
-int perf_event__process_stat_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct perf_session *session);
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event);
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target);
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs);
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv);
 #endif
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 3d1cf5bf7f18..9005fbe0780e 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -98,19 +98,25 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 
 	va_copy(ap_saved, ap);
 	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
-	if (len < 0)
+	if (len < 0) {
+		va_end(ap_saved);
 		return len;
+	}
 	if (len > strbuf_avail(sb)) {
 		ret = strbuf_grow(sb, len);
-		if (ret)
+		if (ret) {
+			va_end(ap_saved);
 			return ret;
+		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
 		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
+			va_end(ap_saved);
 			return -EINVAL;
 		}
 	}
+	va_end(ap_saved);
 	return strbuf_setlen(sb, sb->len + len);
 }
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index dd17d6a38d3a..c091635bf7dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -36,6 +36,7 @@
  * @branch_count: the branch count when the entry was created
  * @cp: call path
  * @no_call: a 'call' was not seen
+ * @trace_end: a 'call' but trace ended
  */
 struct thread_stack_entry {
 	u64 ret_addr;
@@ -44,6 +45,7 @@ struct thread_stack_entry {
 	u64 branch_count;
 	struct call_path *cp;
 	bool no_call;
+	bool trace_end;
 };
 
 /**
@@ -112,7 +114,8 @@ static struct thread_stack *thread_stack__new(struct thread *thread,
 	return ts;
 }
 
-static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr,
+			      bool trace_end)
 {
 	int err = 0;
 
@@ -124,6 +127,7 @@ static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
 		}
 	}
 
+	ts->stack[ts->cnt].trace_end = trace_end;
 	ts->stack[ts->cnt++].ret_addr = ret_addr;
 
 	return err;
@@ -150,6 +154,18 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static void thread_stack__pop_trace_end(struct thread_stack *ts)
+{
+	size_t i;
+
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].trace_end)
+			ts->cnt = i;
+		else
+			return;
+	}
+}
+
 static bool thread_stack__in_kernel(struct thread_stack *ts)
 {
 	if (!ts->cnt)
@@ -254,10 +270,19 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		ret_addr = from_ip + insn_len;
 		if (ret_addr == to_ip)
 			return 0; /* Zero-length calls are excluded */
-		return thread_stack__push(thread->ts, ret_addr);
-	} else if (flags & PERF_IP_FLAG_RETURN) {
-		if (!from_ip)
-			return 0;
+		return thread_stack__push(thread->ts, ret_addr,
+					  flags & PERF_IP_FLAG_TRACE_END);
+	} else if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		/*
+		 * If the caller did not change the trace number (which would
+		 * have flushed the stack) then try to make sense of the stack.
+		 * Possibly, tracing began after returning to the current
+		 * address, so try to pop that. Also, do not expect a call made
+		 * when the trace ended, to return, so pop that.
+		 */
+		thread_stack__pop(thread->ts, to_ip);
+		thread_stack__pop_trace_end(thread->ts);
+	} else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) {
 		thread_stack__pop(thread->ts, to_ip);
 	}
 
@@ -332,7 +357,7 @@ void call_return_processor__free(struct call_return_processor *crp)
 
 static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 				 u64 timestamp, u64 ref, struct call_path *cp,
-				 bool no_call)
+				 bool no_call, bool trace_end)
 {
 	struct thread_stack_entry *tse;
 	int err;
@@ -350,6 +375,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->branch_count = ts->branch_count;
 	tse->cp = cp;
 	tse->no_call = no_call;
+	tse->trace_end = trace_end;
 
 	return 0;
 }
@@ -423,7 +449,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
 		return -ENOMEM;
 
 	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
-				     true);
+				     true, false);
 }
 
 static int thread_stack__no_call_return(struct thread *thread,
@@ -455,7 +481,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 			if (!cp)
 				return -ENOMEM;
 			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true);
+						     cp, true, false);
 		}
 	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
@@ -480,7 +506,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 		return -ENOMEM;
 
 	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true);
+				    true, false);
 	if (err)
 		return err;
 
@@ -500,7 +526,7 @@ static int thread_stack__trace_begin(struct thread *thread,
 
 	/* Pop trace end */
 	tse = &ts->stack[ts->cnt - 1];
-	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+	if (tse->trace_end) {
 		err = thread_stack__call_return(thread, ts, --ts->cnt,
 						timestamp, ref, false);
 		if (err)
@@ -529,7 +555,7 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 	ret_addr = sample->ip + sample->insn_len;
 
 	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
-				     false);
+				     false, true);
 }
 
 int thread_stack__process(struct thread *thread, struct comm *comm,
@@ -579,6 +605,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	ts->last_time = sample->time;
 
 	if (sample->flags & PERF_IP_FLAG_CALL) {
+		bool trace_end = sample->flags & PERF_IP_FLAG_TRACE_END;
 		struct call_path_root *cpr = ts->crp->cpr;
 		struct call_path *cp;
 		u64 ret_addr;
@@ -596,7 +623,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		if (!cp)
 			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
-					    cp, false);
+					    cp, false, trace_end);
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 183c91453522..56e4ca54020a 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -26,15 +26,12 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist);
 
-typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
+typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
+typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
-typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
-
 enum show_feature_header {
 	SHOW_FEAT_NO_HEADER = 0,
 	SHOW_FEAT_HEADER,
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7b0ca7cbb7de..8ad8e755127b 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -531,12 +531,14 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
 			 "/tmp/perf-XXXXXX");
 		if (!mkstemp(tdata->temp_file)) {
 			pr_debug("Can't make temp file");
+			free(tdata);
 			return NULL;
 		}
 
 		temp_fd = open(tdata->temp_file, O_RDWR);
 		if (temp_fd < 0) {
 			pr_debug("Can't read '%s'", tdata->temp_file);
+			free(tdata);
 			return NULL;
 		}
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e76214f8d596..32e558a65af3 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -33,14 +33,15 @@ static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
 	struct tep_handle *pevent = context->pevent;
-	struct event_format *event;
-	struct format_field *field;
+	struct tep_event_format *event;
+	struct tep_format_field *field;
 
 	if (!*size) {
-		if (!pevent->events)
+
+		event = tep_get_first_event(pevent);
+		if (!event)
 			return 0;
 
-		event = pevent->events[0];
 		field = tep_find_common_field(event, type);
 		if (!field)
 			return 0;
@@ -94,9 +95,9 @@ int common_pc(struct scripting_context *context)
 }
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data)
+raw_field_value(struct tep_event_format *event, const char *name, void *data)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	field = tep_find_any_field(event, name);
@@ -108,12 +109,12 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	return val;
 }
 
-unsigned long long read_size(struct event_format *event, void *ptr, int size)
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size)
 {
 	return tep_read_number(event->pevent, ptr, size);
 }
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
 	struct tep_record record;
@@ -130,7 +131,7 @@ void event_format__fprintf(struct event_format *event,
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size)
 {
 	return event_format__fprintf(event, cpu, data, size, stdout);
@@ -158,6 +159,7 @@ void parse_ftrace_printk(struct tep_handle *pevent,
 		printk = strdup(fmt+1);
 		line = strtok_r(NULL, "\n", &next);
 		tep_register_print_string(pevent, printk, addr);
+		free(printk);
 	}
 }
 
@@ -188,29 +190,33 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event)
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event)
 {
 	static int idx;
+	int events_count;
+	struct tep_event_format *all_events;
 
-	if (!pevent || !pevent->events)
+	all_events = tep_get_first_event(pevent);
+	events_count = tep_get_events_count(pevent);
+	if (!pevent || !all_events || events_count < 1)
 		return NULL;
 
 	if (!event) {
 		idx = 0;
-		return pevent->events[0];
+		return all_events;
 	}
 
-	if (idx < pevent->nr_events && event == pevent->events[idx]) {
+	if (idx < events_count && event == (all_events + idx)) {
 		idx++;
-		if (idx == pevent->nr_events)
+		if (idx == events_count)
 			return NULL;
-		return pevent->events[idx];
+		return (all_events + idx);
 	}
 
-	for (idx = 1; idx < pevent->nr_events; idx++) {
-		if (event == pevent->events[idx - 1])
-			return pevent->events[idx];
+	for (idx = 1; idx < events_count; idx++) {
+		if (event == (all_events + (idx - 1)))
+			return (all_events + idx);
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3dfc1db6b25b..76f12c705ef9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -102,7 +102,7 @@ static unsigned int read4(struct tep_handle *pevent)
 
 	if (do_read(&data, 4) < 0)
 		return 0;
-	return __data2host4(pevent, data);
+	return __tep_data2host4(pevent, data);
 }
 
 static unsigned long long read8(struct tep_handle *pevent)
@@ -111,7 +111,7 @@ static unsigned long long read8(struct tep_handle *pevent)
 
 	if (do_read(&data, 8) < 0)
 		return 0;
-	return __data2host8(pevent, data);
+	return __tep_data2host8(pevent, data);
 }
 
 static char *read_string(void)
@@ -241,7 +241,7 @@ static int read_header_files(struct tep_handle *pevent)
 		 * The commit field in the page is of type long,
 		 * use that instead, since it represents the kernel.
 		 */
-		tep_set_long_size(pevent, pevent->header_page_size_size);
+		tep_set_long_size(pevent, tep_get_header_page_size(pevent));
 	}
 	free(header_page);
 
@@ -297,10 +297,8 @@ static int read_event_file(struct tep_handle *pevent, char *sys,
 	}
 
 	ret = do_read(buf, size);
-	if (ret < 0) {
-		free(buf);
+	if (ret < 0)
 		goto out;
-	}
 
 	ret = parse_event_file(pevent, buf, size, sys);
 	if (ret < 0)
@@ -349,9 +347,12 @@ static int read_event_files(struct tep_handle *pevent)
 		for (x=0; x < count; x++) {
 			size = read8(pevent);
 			ret = read_event_file(pevent, sys, size);
-			if (ret)
+			if (ret) {
+				free(sys);
 				return ret;
+			}
 		}
+		free(sys);
 	}
 	return 0;
 }
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 58bb72f266f3..95664b2f771e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -72,12 +72,12 @@ void trace_event__cleanup(struct trace_event *t)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static struct event_format*
+static struct tep_event_format*
 tp_format(const char *sys, const char *name)
 {
 	char *tp_dir = get_events_file(sys);
 	struct tep_handle *pevent = tevent.pevent;
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
@@ -102,7 +102,7 @@ tp_format(const char *sys, const char *name)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
@@ -111,7 +111,7 @@ 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)
+struct tep_event_format *trace_event__tp_format_id(int id)
 {
 	if (!tevent_initialized && trace_event__init2())
 		return ERR_PTR(-ENOMEM);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 40204ec3a7a2..f024d73bfc40 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 #define _PERF_UTIL_TRACE_EVENT_H
 
 #include <traceevent/event-parse.h>
+#include <traceevent/trace-seq.h>
 #include "parse-events.h"
 
 struct machine;
@@ -10,28 +11,28 @@ struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
-struct plugin_list;
+struct tep_plugin_list;
 
 struct trace_event {
 	struct tep_handle	*pevent;
-	struct plugin_list	*plugin_list;
+	struct tep_plugin_list	*plugin_list;
 };
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
 int trace_event__register_resolver(struct machine *machine,
 				   tep_func_resolver_t *func);
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
-struct event_format *trace_event__tp_format_id(int id);
+struct tep_event_format *trace_event__tp_format_id(int id);
 
 int bigendian(void);
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size);
 
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
@@ -39,7 +40,7 @@ int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data);
+raw_field_value(struct tep_event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
@@ -47,9 +48,9 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event);
-unsigned long long read_size(struct event_format *event, void *ptr, int size);
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event);
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eac5b858a371..093352e93d50 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -221,7 +221,7 @@ out:
 	return err;
 }
 
-static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dc58254a2b69..14508ee7707a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,6 +6,7 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -35,6 +36,7 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 980bd9d20646..328f62e6ea02 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2082,7 +2082,7 @@ int has_turbo_ratio_group_limits(int family, int model)
 	switch (model) {
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		return 1;
 	}
 	return 0;
@@ -3149,9 +3149,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = skx_pkg_cstate_limits;
 		has_misc_feature_control = 1;
 		break;
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
 		no_MSR_MISC_PWR_MGMT = 1;
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		pkg_cstate_limits = slv_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
@@ -3163,8 +3163,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		pkg_cstate_limits = bxt_pkg_cstate_limits;
 		break;
 	default:
@@ -3193,9 +3193,9 @@ int has_slv_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_MERRIFIELD:
-	case INTEL_FAM6_ATOM_MOOREFIELD:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_MID:
+	case INTEL_FAM6_ATOM_AIRMONT_MID:
 		return 1;
 	}
 	return 0;
@@ -3207,7 +3207,7 @@ int is_dnv(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		return 1;
 	}
 	return 0;
@@ -3724,8 +3724,8 @@ double get_tdp(unsigned int model)
 			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
 		return 30.0;
 	default:
 		return 135.0;
@@ -3791,7 +3791,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		}
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
 		if (rapl_joules)
 			BIC_PRESENT(BIC_Pkg_J);
@@ -3850,8 +3850,8 @@ void rapl_probe(unsigned int family, unsigned int model)
 			BIC_PRESENT(BIC_RAMWatt);
 		}
 		break;
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		do_rapl = RAPL_PKG | RAPL_CORES;
 		if (rapl_joules) {
 			BIC_PRESENT(BIC_Pkg_J);
@@ -3861,7 +3861,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 			BIC_PRESENT(BIC_CorWatt);
 		}
 		break;
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
 		BIC_PRESENT(BIC_PKG__);
 		BIC_PRESENT(BIC_RAM__);
@@ -3884,7 +3884,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == INTEL_FAM6_ATOM_SILVERMONT1)
+	if (model == INTEL_FAM6_ATOM_SILVERMONT)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
@@ -4141,8 +4141,8 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		return 1;
 	}
 	return 0;
@@ -4174,7 +4174,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		return 1;
 	}
 	return 0;
@@ -4209,8 +4209,8 @@ int is_slm(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		return 1;
 	}
 	return 0;
@@ -4581,11 +4581,11 @@ void process_cpuid()
 				case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 					crystal_hz = 24000000;	/* 24.0 MHz */
 					break;
-				case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+				case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
 				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-				case INTEL_FAM6_ATOM_GEMINI_LAKE:
+				case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default: