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

Pull perf updates from Ingo Molnar:
 "The main kernel side changes were:

   - uprobes enhancements (Masami Hiramatsu)

   - Uncore group events enhancements (David Carrillo-Cisneros)

   - x86 Intel: Add support for Skylake server uncore PMUs (Kan Liang)

   - x86 Intel: LBR cleanups and enhancements, for better branch
     annotation tracking (Peter Zijlstra)

   - x86 Intel: Add support for PTWRITE and power event tracing
     (Alexander Shishkin)

   - ... various fixes, cleanups and smaller enhancements.

  Lots of tooling changes - a couple of highlights:

   - Support event group view with hierarchy mode in 'perf top' and
     'perf report' (Namhyung Kim)

     e.g.:

     $ perf record -e '{cycles,instructions}' make
     $ perf report --hierarchy --stdio
     ...
     #   Overhead  Command / Shared Object / Symbol
     # ......................  ..................................
     ...
     25.74%  27.18%sh
     19.96%  24.14%libc-2.24.so
      9.55%  14.64%[.] __strcmp_sse2
      1.54%   0.00%[.] __tfind
      1.07%   1.13%[.] _int_malloc
      0.95%   0.00%[.] __strchr_sse2
      0.89%   1.39%[.] __tsearch
      0.76%   0.00%[.] strlen

   - Add branch stack / basic block info to 'perf annotate --stdio',
     where for each branch, we add an asm comment after the instruction
     with information on how often it was taken and predicted. See
     example with color output at:

       http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

     (Peter Zijlstra)

   - Add support for using symbols in address filters with Intel PT and
     ARM CoreSight (hardware assisted tracing facilities) (Adrian
     Hunter, Mathieu Poirier)

   - Add support for interacting with Coresight PMU ETMs/PTMs, that are
     IP blocks to perform hardware assisted tracing on a ARM CPU core
     (Mathieu Poirier)

   - Support generating cross arch probes, i.e. if you specify a vmlinux
     file for different arch than the one in the host machine,

        $ perf probe --definition function_name args

     will generate the probe definition string needed to append to the
     target machine /sys/kernel/debug/tracing/kprobes_events file, using
     scripting (Masami Hiramatsu).

   - Allow configuring the default 'perf report -s' sort order in
     ~/.perfconfig, for instance, "sym,dso" may be more fitting for
     kernel developers. (Arnaldo Carvalho de Melo)

   - ... plus lots of other changes, refactorings, features and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (149 commits)
  perf tests: Add dwarf unwind test for powerpc
  perf probe: Match linkage name with mangled name
  perf probe: Fix to cut off incompatible chars from group name
  perf probe: Skip if the function address is 0
  perf probe: Ignore the error of finding inline instance
  perf intel-pt: Fix decoding when there are address filters
  perf intel-pt: Enable decoder to handle TIP.PGD with missing IP
  perf intel-pt: Read address filter from AUXTRACE_INFO event
  perf intel-pt: Record address filter in AUXTRACE_INFO event
  perf intel-pt: Add a helper function for processing AUXTRACE_INFO
  perf intel-pt: Fix missing error codes processing auxtrace_info
  perf intel-pt: Add support for recording the max non-turbo ratio
  perf intel-pt: Fix snapshot overlap detection decoder errors
  perf probe: Increase debug level of SDT debug messages
  perf record: Add support for using symbols in address filters
  perf symbols: Add dso__last_symbol()
  perf record: Fix error paths
  perf record: Rename label 'out_symbol_exit'
  perf script: Fix vanished idle symbols
  perf evsel: Add support for address filters
  ...

179 files changed, 6053 insertions, 988 deletions

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index ea52ec1f8484..e4991fb1eedc 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -44,8 +44,8 @@ Synopsis of kprobe_events
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
-		  (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield
-		  are supported.
+		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
+		  (x8/x16/x32/x64), "string" and bitfield are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.
@@ -54,7 +54,10 @@ Types
 -----
 Several types are supported for fetch-args. Kprobe tracer will access memory
 by given type. Prefix 's' and 'u' means those types are signed and unsigned
-respectively. Traced arguments are shown in decimal (signed) or hex (unsigned).
+respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
+in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
+or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
+x86-64 uses x64).
 String type is a special type, which fetches a "null-terminated" string from
 kernel space. This means it will fail and store NULL if the string container
 has been paged out.
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index 72d1cd4f7bf3..94b6b4581763 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -40,8 +40,8 @@ Synopsis of uprobe_tracer
    +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
    NAME=FETCHARG     : Set NAME as the argument name of FETCHARG.
    FETCHARG:TYPE     : Set TYPE as the type of FETCHARG. Currently, basic types
-		       (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield
-		       are supported.
+		       (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
+		       (x8/x16/x32/x64), "string" and bitfield are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.
@@ -50,7 +50,10 @@ Types
 -----
 Several types are supported for fetch-args. Uprobe tracer will access memory
 by given type. Prefix 's' and 'u' means those types are signed and unsigned
-respectively. Traced arguments are shown in decimal (signed) or hex (unsigned).
+respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
+in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
+or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
+x86-64 uses x64).
 String type is a special type, which fetches a "null-terminated" string from
 user space.
 Bitfield is another special type, which takes 3 parameters, bit-width, bit-
diff --git a/MAINTAINERS b/MAINTAINERS
index 413b0da2620d..9a7a9c6cd64c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1125,6 +1125,11 @@ F:	drivers/hwtracing/coresight/*
 F:	Documentation/trace/coresight.txt
 F:	Documentation/devicetree/bindings/arm/coresight.txt
 F:	Documentation/ABI/testing/sysfs-bus-coresight-devices-*
+F:	tools/perf/arch/arm/util/pmu.c
+F:	tools/perf/arch/arm/util/auxtrace.c
+F:	tools/perf/arch/arm/util/cs-etm.c
+F:	tools/perf/arch/arm/util/cs-etm.h
+F:	tools/perf/util/cs-etm.h
 
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d0efb5cb1b00..18a1acf86c90 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1201,6 +1201,9 @@ static int x86_pmu_add(struct perf_event *event, int flags)
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be performed
 	 * at commit time (->commit_txn) as a whole.
+	 *
+	 * If commit fails, we'll call ->del() on all events
+	 * for which ->add() was called.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
 		goto done_collect;
@@ -1223,6 +1226,14 @@ done_collect:
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
+	if (x86_pmu.add) {
+		/*
+		 * This is before x86_pmu_enable() will call x86_pmu_start(),
+		 * so we enable LBRs before an event needs them etc..
+		 */
+		x86_pmu.add(event);
+	}
+
 	ret = 0;
 out:
 	return ret;
@@ -1346,7 +1357,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
 
 	/*
-	 * If we're called during a txn, we don't need to do anything.
+	 * If we're called during a txn, we only need to undo x86_pmu.add.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
 	 *
@@ -1354,7 +1365,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	 * an event added during that same TXN.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
-		return;
+		goto do_del;
 
 	/*
 	 * Not a TXN, therefore cleanup properly.
@@ -1384,6 +1395,15 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
+
+do_del:
+	if (x86_pmu.del) {
+		/*
+		 * This is after x86_pmu_stop(); so we disable LBRs after any
+		 * event can need them etc..
+		 */
+		x86_pmu.del(event);
+	}
 }
 
 int x86_pmu_handle_irq(struct pt_regs *regs)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 4c9a79b9cd69..a3a9eb84b5cf 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1906,13 +1906,6 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	/*
-	 * must disable before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -1924,6 +1917,14 @@ static void intel_pmu_disable_event(struct perf_event *event)
 		intel_pmu_pebs_disable(event);
 }
 
+static void intel_pmu_del_event(struct perf_event *event)
+{
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_del(event);
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_del(event);
+}
+
 static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
@@ -1967,12 +1968,6 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
-	/*
-	 * must enabled before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1993,6 +1988,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
+static void intel_pmu_add_event(struct perf_event *event)
+{
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_add(event);
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_add(event);
+}
+
 /*
  * Save and restart an expired event. Called by NMI contexts,
  * so it has to be careful about preempting normal event ops:
@@ -3291,6 +3294,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.enable_all		= intel_pmu_enable_all,
 	.enable			= intel_pmu_enable_event,
 	.disable		= intel_pmu_disable_event,
+	.add			= intel_pmu_add_event,
+	.del			= intel_pmu_del_event,
 	.hw_config		= intel_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9b983a474253..0319311dbdbb 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -806,9 +806,65 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
-static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+/*
+ * We need the sched_task callback even for per-cpu events when we use
+ * the large interrupt threshold, such that we can provide PID and TID
+ * to PEBS samples.
+ */
+static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
+{
+	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
+}
+
+static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+{
+	struct debug_store *ds = cpuc->ds;
+	u64 threshold;
+
+	if (cpuc->n_pebs == cpuc->n_large_pebs) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+	}
+
+	ds->pebs_interrupt_threshold = threshold;
+}
+
+static void
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+{
+	/*
+	 * Make sure we get updated with the first PEBS
+	 * event. It will trigger also during removal, but
+	 * that does not hurt:
+	 */
+	bool update = cpuc->n_pebs == 1;
+
+	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
+		if (!needed_cb)
+			perf_sched_cb_inc(pmu);
+		else
+			perf_sched_cb_dec(pmu);
+
+		update = true;
+	}
+
+	if (update)
+		pebs_update_threshold(cpuc);
+}
+
+void intel_pmu_pebs_add(struct perf_event *event)
 {
-	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
+
+	cpuc->n_pebs++;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs++;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -816,12 +872,9 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
-	bool first_pebs;
-	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
-	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
@@ -830,46 +883,34 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		cpuc->pebs_enabled |= 1ULL << 63;
 
 	/*
-	 * When the event is constrained enough we can use a larger
-	 * threshold and run the event with less frequent PMI.
+	 * Use auto-reload if possible to save a MSR write in the PMI.
+	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
-		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
-
-		if (first_pebs)
-			perf_sched_cb_inc(event->ctx->pmu);
-	} else {
-		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
-
-		/*
-		 * If not all events can use larger buffer,
-		 * roll back to threshold = 1
-		 */
-		if (!first_pebs &&
-		    (ds->pebs_interrupt_threshold > threshold))
-			perf_sched_cb_dec(event->ctx->pmu);
-	}
-
-	/* Use auto-reload if possible to save a MSR write in the PMI */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	}
+}
+
+void intel_pmu_pebs_del(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
-	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
-		ds->pebs_interrupt_threshold = threshold;
+	cpuc->n_pebs--;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs--;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct debug_store *ds = cpuc->ds;
-	bool large_pebs = ds->pebs_interrupt_threshold >
-		ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 
-	if (large_pebs)
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
 		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -879,9 +920,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
-	if (large_pebs && !pebs_is_enabled(cpuc))
-		perf_sched_cb_dec(event->ctx->pmu);
-
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 707d358e0dff..fc6cf21c535e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -380,7 +380,6 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
 	/*
@@ -390,31 +389,21 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 	 */
 	task_ctx = ctx ? ctx->task_ctx_data : NULL;
 	if (task_ctx) {
-		if (sched_in) {
+		if (sched_in)
 			__intel_pmu_lbr_restore(task_ctx);
-			cpuc->lbr_context = ctx;
-		} else {
+		else
 			__intel_pmu_lbr_save(task_ctx);
-		}
 		return;
 	}
 
 	/*
-	 * When sampling the branck stack in system-wide, it may be
-	 * necessary to flush the stack on context switch. This happens
-	 * when the branch stack does not tag its entries with the pid
-	 * of the current task. Otherwise it becomes impossible to
-	 * associate a branch entry with a task. This ambiguity is more
-	 * likely to appear when the branch stack supports priv level
-	 * filtering and the user sets it to monitor only at the user
-	 * level (which could be a useful measurement in system-wide
-	 * mode). In that case, the risk is high of having a branch
-	 * stack with branch from multiple tasks.
- 	 */
-	if (sched_in) {
+	 * Since a context switch can flip the address space and LBR entries
+	 * are not tagged with an identifier, we need to wipe the LBR, even for
+	 * per-cpu events. You simply cannot resolve the branches from the old
+	 * address space.
+	 */
+	if (sched_in)
 		intel_pmu_lbr_reset();
-		cpuc->lbr_context = ctx;
-	}
 }
 
 static inline bool branch_user_callstack(unsigned br_sel)
@@ -422,7 +411,7 @@ static inline bool branch_user_callstack(unsigned br_sel)
 	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
 }
 
-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
@@ -430,27 +419,38 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	/*
-	 * Reset the LBR stack if we changed task context to
-	 * avoid data leaks.
-	 */
-	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
-		intel_pmu_lbr_reset();
-		cpuc->lbr_context = event->ctx;
-	}
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
-					event->ctx->task_ctx_data) {
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
 		task_ctx = event->ctx->task_ctx_data;
 		task_ctx->lbr_callstack_users++;
 	}
 
-	cpuc->lbr_users++;
+	/*
+	 * Request pmu::sched_task() callback, which will fire inside the
+	 * regular perf event scheduling, so that call will:
+	 *
+	 *  - restore or wipe; when LBR-callstack,
+	 *  - wipe; otherwise,
+	 *
+	 * when this is from __perf_event_task_sched_in().
+	 *
+	 * However, if this is from perf_install_in_context(), no such callback
+	 * will follow and we'll need to reset the LBR here if this is the
+	 * first LBR event.
+	 *
+	 * The problem is, we cannot tell these cases apart... but we can
+	 * exclude the biggest chunk of cases by looking at
+	 * event->total_time_running. An event that has accrued runtime cannot
+	 * be 'new'. Conversely, a new event can get installed through the
+	 * context switch path for the first time.
+	 */
 	perf_sched_cb_inc(event->ctx->pmu);
+	if (!cpuc->lbr_users++ && !event->total_time_running)
+		intel_pmu_lbr_reset();
 }
 
-void intel_pmu_lbr_disable(struct perf_event *event)
+void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
@@ -467,12 +467,6 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 	perf_sched_cb_dec(event->ctx->pmu);
-
-	if (cpuc->enabled && !cpuc->lbr_users) {
-		__intel_pmu_lbr_disable();
-		/* avoid stale pointer */
-		cpuc->lbr_context = NULL;
-	}
 }
 
 void intel_pmu_lbr_enable_all(bool pmi)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 861a7d9cb60f..c5047b8f777b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -69,6 +69,8 @@ static struct pt_cap_desc {
 	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
 	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
 	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
+	PT_CAP(ptwrite,			0, CR_EBX, BIT(4)),
+	PT_CAP(power_event_trace,	0, CR_EBX, BIT(5)),
 	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
 	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
 	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
@@ -259,10 +261,16 @@ fail:
 #define RTIT_CTL_MTC	(RTIT_CTL_MTC_EN	| \
 			 RTIT_CTL_MTC_RANGE)
 
+#define RTIT_CTL_PTW	(RTIT_CTL_PTW_EN	| \
+			 RTIT_CTL_FUP_ON_PTW)
+
 #define PT_CONFIG_MASK (RTIT_CTL_TSC_EN		| \
 			RTIT_CTL_DISRETC	| \
 			RTIT_CTL_CYC_PSB	| \
-			RTIT_CTL_MTC)
+			RTIT_CTL_MTC		| \
+			RTIT_CTL_PWR_EVT_EN	| \
+			RTIT_CTL_FUP_ON_PTW	| \
+			RTIT_CTL_PTW_EN)
 
 static bool pt_event_valid(struct perf_event *event)
 {
@@ -311,6 +319,20 @@ static bool pt_event_valid(struct perf_event *event)
 			return false;
 	}
 
+	if (config & RTIT_CTL_PWR_EVT_EN &&
+	    !pt_cap_get(PT_CAP_power_event_trace))
+		return false;
+
+	if (config & RTIT_CTL_PTW) {
+		if (!pt_cap_get(PT_CAP_ptwrite))
+			return false;
+
+		/* FUPonPTW without PTW doesn't make sense */
+		if ((config & RTIT_CTL_FUP_ON_PTW) &&
+		    !(config & RTIT_CTL_PTW_EN))
+			return false;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index efffa4a09f68..53473c21b554 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -26,11 +26,14 @@
 #define RTIT_CTL_CYCLEACC		BIT(1)
 #define RTIT_CTL_OS			BIT(2)
 #define RTIT_CTL_USR			BIT(3)
+#define RTIT_CTL_PWR_EVT_EN		BIT(4)
+#define RTIT_CTL_FUP_ON_PTW		BIT(5)
 #define RTIT_CTL_CR3EN			BIT(7)
 #define RTIT_CTL_TOPA			BIT(8)
 #define RTIT_CTL_MTC_EN			BIT(9)
 #define RTIT_CTL_TSC_EN			BIT(10)
 #define RTIT_CTL_DISRETC		BIT(11)
+#define RTIT_CTL_PTW_EN			BIT(12)
 #define RTIT_CTL_BRANCH_EN		BIT(13)
 #define RTIT_CTL_MTC_RANGE_OFFSET	14
 #define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
@@ -91,6 +94,8 @@ enum pt_capabilities {
 	PT_CAP_psb_cyc,
 	PT_CAP_ip_filtering,
 	PT_CAP_mtc,
+	PT_CAP_ptwrite,
+	PT_CAP_power_event_trace,
 	PT_CAP_topa_output,
 	PT_CAP_topa_multiple_entries,
 	PT_CAP_single_range_output,
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 28865938aadf..b0f0e835a770 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -357,6 +357,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
+	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
 	/*
 	 * check event is known (determines counter)
 	 */
@@ -765,6 +767,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE,  skl_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,	 hsx_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 463dc7a5a6c3..d9844cc74486 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -664,6 +664,8 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	event->cpu = box->cpu;
 	event->pmu_private = box;
 
+	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -683,7 +685,8 @@ static int uncore_pmu_event_init(struct perf_event *event)
 		/* fixed counters have event field hardcoded to zero */
 		hwc->config = 0ULL;
 	} else {
-		hwc->config = event->attr.config & pmu->type->event_mask;
+		hwc->config = event->attr.config &
+			      (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
 		if (pmu->type->ops->hw_config) {
 			ret = pmu->type->ops->hw_config(box, event);
 			if (ret)
@@ -1321,6 +1324,11 @@ static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
 	.pci_init = skl_uncore_pci_init,
 };
 
+static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
+	.cpu_init = skx_uncore_cpu_init,
+	.pci_init = skx_uncore_pci_init,
+};
+
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
@@ -1343,6 +1351,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 78b9c23e2d8d..ad986c1e29bc 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -44,6 +44,7 @@ struct intel_uncore_type {
 	unsigned perf_ctr;
 	unsigned event_ctl;
 	unsigned event_mask;
+	unsigned event_mask_ext;
 	unsigned fixed_ctr;
 	unsigned fixed_ctl;
 	unsigned box_ctl;
@@ -120,6 +121,7 @@ struct intel_uncore_box {
 };
 
 #define UNCORE_BOX_FLAG_INITIATED	0
+#define UNCORE_BOX_FLAG_CTL_OFFS8	1 /* event config registers are 8-byte apart */
 
 struct uncore_event_desc {
 	struct kobj_attribute attr;
@@ -172,6 +174,9 @@ static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box)
 static inline
 unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx)
 {
+	if (test_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags))
+		return idx * 8 + box->pmu->type->event_ctl;
+
 	return idx * 4 + box->pmu->type->event_ctl;
 }
 
@@ -377,6 +382,8 @@ int bdx_uncore_pci_init(void);
 void bdx_uncore_cpu_init(void);
 int knl_uncore_pci_init(void);
 void knl_uncore_cpu_init(void);
+int skx_uncore_pci_init(void);
+void skx_uncore_cpu_init(void);
 
 /* perf_event_intel_uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 9d35ec0cb8fc..5f845eef9a4d 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -388,6 +388,8 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 	event->cpu = box->cpu;
 	event->pmu_private = box;
 
+	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 8aee83bcf71f..272427700d48 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,10 @@
 /* SandyBridge-EP/IvyTown uncore support */
 #include "uncore.h"
 
+/* SNB-EP pci bus to socket mapping */
+#define SNBEP_CPUNODEID			0x40
+#define SNBEP_GIDNIDMAP			0x54
+
 /* SNB-EP Box level control */
 #define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
 #define SNBEP_PMON_BOX_CTL_RST_CTRS	(1 << 1)
@@ -264,15 +268,72 @@
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
 
+/* SKX pci bus to socket mapping */
+#define SKX_CPUNODEID			0xc0
+#define SKX_GIDNIDMAP			0xd4
+
+/* SKX CHA */
+#define SKX_CHA_MSR_PMON_BOX_FILTER_TID		(0x1ffULL << 0)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 9)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_STATE	(0x3ffULL << 17)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_REM		(0x1ULL << 32)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_LOC		(0x1ULL << 33)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC	(0x1ULL << 35)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NM		(0x1ULL << 36)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM	(0x1ULL << 37)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC0	(0x3ffULL << 41)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_OPC1	(0x3ffULL << 51)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
+#define SKX_CHA_MSR_PMON_BOX_FILTER_ISOC	(0x1ULL << 63)
+
+/* SKX IIO */
+#define SKX_IIO0_MSR_PMON_CTL0		0xa48
+#define SKX_IIO0_MSR_PMON_CTR0		0xa41
+#define SKX_IIO0_MSR_PMON_BOX_CTL	0xa40
+#define SKX_IIO_MSR_OFFSET		0x20
+
+#define SKX_PMON_CTL_TRESH_MASK		(0xff << 24)
+#define SKX_PMON_CTL_TRESH_MASK_EXT	(0xf)
+#define SKX_PMON_CTL_CH_MASK		(0xff << 4)
+#define SKX_PMON_CTL_FC_MASK		(0x7 << 12)
+#define SKX_IIO_PMON_RAW_EVENT_MASK	(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_INVERT | \
+					 SKX_PMON_CTL_TRESH_MASK)
+#define SKX_IIO_PMON_RAW_EVENT_MASK_EXT	(SKX_PMON_CTL_TRESH_MASK_EXT | \
+					 SKX_PMON_CTL_CH_MASK | \
+					 SKX_PMON_CTL_FC_MASK)
+
+/* SKX IRP */
+#define SKX_IRP0_MSR_PMON_CTL0		0xa5b
+#define SKX_IRP0_MSR_PMON_CTR0		0xa59
+#define SKX_IRP0_MSR_PMON_BOX_CTL	0xa58
+#define SKX_IRP_MSR_OFFSET		0x20
+
+/* SKX UPI */
+#define SKX_UPI_PCI_PMON_CTL0		0x350
+#define SKX_UPI_PCI_PMON_CTR0		0x318
+#define SKX_UPI_PCI_PMON_BOX_CTL	0x378
+#define SKX_PMON_CTL_UMASK_EXT		0xff
+
+/* SKX M2M */
+#define SKX_M2M_PCI_PMON_CTL0		0x228
+#define SKX_M2M_PCI_PMON_CTR0		0x200
+#define SKX_M2M_PCI_PMON_BOX_CTL	0x258
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
 DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
 DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39");
 DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
 DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh9, thresh, "config:24-35");
 DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
 DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29");
 DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
@@ -280,6 +341,8 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
 DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
+DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
+DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
@@ -288,18 +351,26 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state5, filter_state, "config1:17-26");
+DEFINE_UNCORE_FORMAT_ATTR(filter_rem, filter_rem, "config1:32");
+DEFINE_UNCORE_FORMAT_ATTR(filter_loc, filter_loc, "config1:33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nm, filter_nm, "config1:36");
+DEFINE_UNCORE_FORMAT_ATTR(filter_not_nm, filter_not_nm, "config1:37");
 DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33");
 DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc_0, filter_opc0, "config1:41-50");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc_1, filter_opc1, "config1:51-60");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
 DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
 DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
@@ -1153,7 +1224,7 @@ static struct pci_driver snbep_uncore_pci_driver = {
 /*
  * build pci bus to socket mapping
  */
-static int snbep_pci2phy_map_init(int devid)
+static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool reverse)
 {
 	struct pci_dev *ubox_dev = NULL;
 	int i, bus, nodeid, segment;
@@ -1168,12 +1239,12 @@ static int snbep_pci2phy_map_init(int devid)
 			break;
 		bus = ubox_dev->bus->number;
 		/* get the Node ID of the local register */
-		err = pci_read_config_dword(ubox_dev, 0x40, &config);
+		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
 		if (err)
 			break;
 		nodeid = config;
 		/* get the Node ID mapping */
-		err = pci_read_config_dword(ubox_dev, 0x54, &config);
+		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
 		if (err)
 			break;
 
@@ -1207,11 +1278,20 @@ static int snbep_pci2phy_map_init(int devid)
 		raw_spin_lock(&pci2phy_map_lock);
 		list_for_each_entry(map, &pci2phy_map_head, list) {
 			i = -1;
-			for (bus = 255; bus >= 0; bus--) {
-				if (map->pbus_to_physid[bus] >= 0)
-					i = map->pbus_to_physid[bus];
-				else
-					map->pbus_to_physid[bus] = i;
+			if (reverse) {
+				for (bus = 255; bus >= 0; bus--) {
+					if (map->pbus_to_physid[bus] >= 0)
+						i = map->pbus_to_physid[bus];
+					else
+						map->pbus_to_physid[bus] = i;
+				}
+			} else {
+				for (bus = 0; bus <= 255; bus++) {
+					if (map->pbus_to_physid[bus] >= 0)
+						i = map->pbus_to_physid[bus];
+					else
+						map->pbus_to_physid[bus] = i;
+				}
 			}
 		}
 		raw_spin_unlock(&pci2phy_map_lock);
@@ -1224,7 +1304,7 @@ static int snbep_pci2phy_map_init(int devid)
 
 int snbep_uncore_pci_init(void)
 {
-	int ret = snbep_pci2phy_map_init(0x3ce0);
+	int ret = snbep_pci2phy_map_init(0x3ce0, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
 	if (ret)
 		return ret;
 	uncore_pci_uncores = snbep_pci_uncores;
@@ -1788,7 +1868,7 @@ static struct pci_driver ivbep_uncore_pci_driver = {
 
 int ivbep_uncore_pci_init(void)
 {
-	int ret = snbep_pci2phy_map_init(0x0e1e);
+	int ret = snbep_pci2phy_map_init(0x0e1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
 	if (ret)
 		return ret;
 	uncore_pci_uncores = ivbep_pci_uncores;
@@ -2897,7 +2977,7 @@ static struct pci_driver hswep_uncore_pci_driver = {
 
 int hswep_uncore_pci_init(void)
 {
-	int ret = snbep_pci2phy_map_init(0x2f1e);
+	int ret = snbep_pci2phy_map_init(0x2f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
 	if (ret)
 		return ret;
 	uncore_pci_uncores = hswep_pci_uncores;
@@ -3186,7 +3266,7 @@ static struct pci_driver bdx_uncore_pci_driver = {
 
 int bdx_uncore_pci_init(void)
 {
-	int ret = snbep_pci2phy_map_init(0x6f1e);
+	int ret = snbep_pci2phy_map_init(0x6f1e, SNBEP_CPUNODEID, SNBEP_GIDNIDMAP, true);
 
 	if (ret)
 		return ret;
@@ -3196,3 +3276,525 @@ int bdx_uncore_pci_init(void)
 }
 
 /* end of BDX uncore support */
+
+/* SKX uncore support */
+
+static struct intel_uncore_type skx_uncore_ubox = {
+	.name			= "ubox",
+	.num_counters		= 2,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_U_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_U_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops			= &ivbep_uncore_msr_ops,
+	.format_group		= &ivbep_uncore_ubox_format_group,
+};
+
+static struct attribute *skx_uncore_cha_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid4.attr,
+	&format_attr_filter_link4.attr,
+	&format_attr_filter_state5.attr,
+	&format_attr_filter_rem.attr,
+	&format_attr_filter_loc.attr,
+	&format_attr_filter_nm.attr,
+	&format_attr_filter_all_op.attr,
+	&format_attr_filter_not_nm.attr,
+	&format_attr_filter_opc_0.attr,
+	&format_attr_filter_opc_1.attr,
+	&format_attr_filter_nc.attr,
+	&format_attr_filter_c6.attr,
+	&format_attr_filter_isoc.attr,
+	NULL,
+};
+
+static struct attribute_group skx_uncore_chabox_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_cha_formats_attr,
+};
+
+static struct event_constraint skx_uncore_chabox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg skx_uncore_cha_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4),
+};
+
+static u64 skx_cha_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK;
+	if (fields & 0x4)
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE;
+	return mask;
+}
+
+static struct event_constraint *
+skx_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, skx_cha_filter_mask);
+}
+
+static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = skx_uncore_cha_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+			    HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & skx_cha_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops skx_uncore_chabox_ops = {
+	/* There is no frz_en for chabox ctl */
+	.init_box		= ivbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= hswep_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= skx_cha_hw_config,
+	.get_constraint		= skx_cha_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type skx_uncore_chabox = {
+	.name			= "cha",
+	.num_counters		= 4,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
+	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= skx_uncore_chabox_constraints,
+	.ops			= &skx_uncore_chabox_ops,
+	.format_group		= &skx_uncore_chabox_format_group,
+};
+
+static struct attribute *skx_uncore_iio_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh9.attr,
+	&format_attr_ch_mask.attr,
+	&format_attr_fc_mask.attr,
+	NULL,
+};
+
+static struct attribute_group skx_uncore_iio_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_iio_formats_attr,
+};
+
+static struct event_constraint skx_uncore_iio_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x83, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x88, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x95, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xd4, 0xc),
+	EVENT_CONSTRAINT_END
+};
+
+static void skx_iio_enable_event(struct intel_uncore_box *box,
+				 struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops skx_uncore_iio_ops = {
+	.init_box		= ivbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= skx_iio_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_iio = {
+	.name			= "iio",
+	.num_counters		= 4,
+	.num_boxes		= 5,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= SKX_IIO0_MSR_PMON_CTL0,
+	.perf_ctr		= SKX_IIO0_MSR_PMON_CTR0,
+	.event_mask		= SKX_IIO_PMON_RAW_EVENT_MASK,
+	.event_mask_ext		= SKX_IIO_PMON_RAW_EVENT_MASK_EXT,
+	.box_ctl		= SKX_IIO0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SKX_IIO_MSR_OFFSET,
+	.constraints		= skx_uncore_iio_constraints,
+	.ops			= &skx_uncore_iio_ops,
+	.format_group		= &skx_uncore_iio_format_group,
+};
+
+static struct attribute *skx_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group skx_uncore_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_formats_attr,
+};
+
+static struct intel_uncore_type skx_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 2,
+	.num_boxes		= 5,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= SKX_IRP0_MSR_PMON_CTL0,
+	.perf_ctr		= SKX_IRP0_MSR_PMON_CTR0,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SKX_IRP0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SKX_IRP_MSR_OFFSET,
+	.ops			= &skx_uncore_iio_ops,
+	.format_group		= &skx_uncore_format_group,
+};
+
+static struct intel_uncore_ops skx_uncore_pcu_ops = {
+	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= hswep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type skx_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &skx_uncore_pcu_ops,
+	.format_group		= &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *skx_msr_uncores[] = {
+	&skx_uncore_ubox,
+	&skx_uncore_chabox,
+	&skx_uncore_iio,
+	&skx_uncore_irp,
+	&skx_uncore_pcu,
+	NULL,
+};
+
+static int skx_count_chabox(void)
+{
+	struct pci_dev *chabox_dev = NULL;
+	int bus, count = 0;
+
+	while (1) {
+		chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
+		if (!chabox_dev)
+			break;
+		if (count == 0)
+			bus = chabox_dev->bus->number;
+		if (bus != chabox_dev->bus->number)
+			break;
+		count++;
+	}
+
+	pci_dev_put(chabox_dev);
+	return count;
+}
+
+void skx_uncore_cpu_init(void)
+{
+	skx_uncore_chabox.num_boxes = skx_count_chabox();
+	uncore_msr_uncores = skx_msr_uncores;
+}
+
+static struct intel_uncore_type skx_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 6,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= hswep_uncore_imc_events,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &ivbep_uncore_pci_ops,
+	.format_group	= &skx_uncore_format_group,
+};
+
+static struct attribute *skx_upi_uncore_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask_ext.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group skx_upi_uncore_format_group = {
+	.name = "format",
+	.attrs = skx_upi_uncore_formats_attr,
+};
+
+static void skx_upi_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+	pci_write_config_dword(pdev, SKX_UPI_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops skx_upi_uncore_pci_ops = {
+	.init_box	= skx_upi_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_uncore_pci_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_upi = {
+	.name		= "upi",
+	.num_counters   = 4,
+	.num_boxes	= 3,
+	.perf_ctr_bits	= 48,
+	.perf_ctr	= SKX_UPI_PCI_PMON_CTR0,
+	.event_ctl	= SKX_UPI_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.event_mask_ext = SKX_PMON_CTL_UMASK_EXT,
+	.box_ctl	= SKX_UPI_PCI_PMON_BOX_CTL,
+	.ops		= &skx_upi_uncore_pci_ops,
+	.format_group	= &skx_upi_uncore_format_group,
+};
+
+static void skx_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+	pci_write_config_dword(pdev, SKX_M2M_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops skx_m2m_uncore_pci_ops = {
+	.init_box	= skx_m2m_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_uncore_pci_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+};
+
+static struct intel_uncore_type skx_uncore_m2m = {
+	.name		= "m2m",
+	.num_counters   = 4,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	.perf_ctr	= SKX_M2M_PCI_PMON_CTR0,
+	.event_ctl	= SKX_M2M_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SKX_M2M_PCI_PMON_BOX_CTL,
+	.ops		= &skx_m2m_uncore_pci_ops,
+	.format_group	= &skx_uncore_format_group,
+};
+
+static struct event_constraint skx_uncore_m2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type skx_uncore_m2pcie = {
+	.name		= "m2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 48,
+	.constraints	= skx_uncore_m2pcie_constraints,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &ivbep_uncore_pci_ops,
+	.format_group	= &skx_uncore_format_group,
+};
+
+static struct event_constraint skx_uncore_m3upi_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x1d, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x1e, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x40, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x4e, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x4f, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x50, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x51, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x52, 0x7),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type skx_uncore_m3upi = {
+	.name		= "m3upi",
+	.num_counters   = 3,
+	.num_boxes	= 3,
+	.perf_ctr_bits	= 48,
+	.constraints	= skx_uncore_m3upi_constraints,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &ivbep_uncore_pci_ops,
+	.format_group	= &skx_uncore_format_group,
+};
+
+enum {
+	SKX_PCI_UNCORE_IMC,
+	SKX_PCI_UNCORE_M2M,
+	SKX_PCI_UNCORE_UPI,
+	SKX_PCI_UNCORE_M2PCIE,
+	SKX_PCI_UNCORE_M3UPI,
+};
+
+static struct intel_uncore_type *skx_pci_uncores[] = {
+	[SKX_PCI_UNCORE_IMC]	= &skx_uncore_imc,
+	[SKX_PCI_UNCORE_M2M]	= &skx_uncore_m2m,
+	[SKX_PCI_UNCORE_UPI]	= &skx_uncore_upi,
+	[SKX_PCI_UNCORE_M2PCIE]	= &skx_uncore_m2pcie,
+	[SKX_PCI_UNCORE_M3UPI]	= &skx_uncore_m3upi,
+	NULL,
+};
+
+static const struct pci_device_id skx_uncore_pci_ids[] = {
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 2, SKX_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 6, SKX_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC0 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(11, 2, SKX_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2042),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 2, SKX_PCI_UNCORE_IMC, 3),
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2046),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 6, SKX_PCI_UNCORE_IMC, 4),
+	},
+	{ /* MC1 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204a),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(13, 2, SKX_PCI_UNCORE_IMC, 5),
+	},
+	{ /* M2M0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 0, SKX_PCI_UNCORE_M2M, 0),
+	},
+	{ /* M2M1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2066),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 0, SKX_PCI_UNCORE_M2M, 1),
+	},
+	{ /* UPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(14, 0, SKX_PCI_UNCORE_UPI, 0),
+	},
+	{ /* UPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, SKX_PCI_UNCORE_UPI, 1),
+	},
+	{ /* UPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2058),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(16, 0, SKX_PCI_UNCORE_UPI, 2),
+	},
+	{ /* M2PCIe 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 1, SKX_PCI_UNCORE_M2PCIE, 0),
+	},
+	{ /* M2PCIe 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(22, 1, SKX_PCI_UNCORE_M2PCIE, 1),
+	},
+	{ /* M2PCIe 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(23, 1, SKX_PCI_UNCORE_M2PCIE, 2),
+	},
+	{ /* M2PCIe 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2088),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
+	},
+	{ /* M3UPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+	},
+	{ /* M3UPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+	},
+	{ /* M3UPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+	},
+	{ /* end: all zeroes */ }
+};
+
+
+static struct pci_driver skx_uncore_pci_driver = {
+	.name		= "skx_uncore",
+	.id_table	= skx_uncore_pci_ids,
+};
+
+int skx_uncore_pci_init(void)
+{
+	/* need to double check pci address */
+	int ret = snbep_pci2phy_map_init(0x2014, SKX_CPUNODEID, SKX_GIDNIDMAP, false);
+
+	if (ret)
+		return ret;
+
+	uncore_pci_uncores = skx_pci_uncores;
+	uncore_pci_driver = &skx_uncore_pci_driver;
+	return 0;
+}
+
+/* end of SKX uncore support */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8c4a47706296..5874d8de1f8d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -194,12 +194,13 @@ struct cpu_hw_events {
 	 */
 	struct debug_store	*ds;
 	u64			pebs_enabled;
+	int			n_pebs;
+	int			n_large_pebs;
 
 	/*
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
-	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -508,6 +509,8 @@ struct x86_pmu {
 	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	void		(*add)(struct perf_event *);
+	void		(*del)(struct perf_event *);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
@@ -888,6 +891,10 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
+void intel_pmu_pebs_add(struct perf_event *event);
+
+void intel_pmu_pebs_del(struct perf_event *event);
+
 void intel_pmu_pebs_enable(struct perf_event *event);
 
 void intel_pmu_pebs_disable(struct perf_event *event);
@@ -906,9 +913,9 @@ u64 lbr_from_signext_quirk_wr(u64 val);
 
 void intel_pmu_lbr_reset(void);
 
-void intel_pmu_lbr_enable(struct perf_event *event);
+void intel_pmu_lbr_add(struct perf_event *event);
 
-void intel_pmu_lbr_disable(struct perf_event *event);
+void intel_pmu_lbr_del(struct perf_event *event);
 
 void intel_pmu_lbr_enable_all(bool pmi);
 
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 598bc999f4c2..3b77588a9360 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -339,6 +339,24 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen,
 	return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
 }
 
+/*
+ * bitmap_from_u64 - Check and swap words within u64.
+ *  @mask: source bitmap
+ *  @dst:  destination bitmap
+ *
+ * In 32-bit Big Endian kernel, when using (u32 *)(&val)[*]
+ * to read u64 mask, we will get the wrong word.
+ * That is "(u32 *)(&val)[0]" gets the upper 32 bits,
+ * but we expect the lower 32-bits of u64.
+ */
+static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+{
+	dst[0] = mask & ULONG_MAX;
+
+	if (sizeof(mask) > sizeof(unsigned long))
+		dst[1] = mask >> 32;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2b6b43cc0dd5..5c5362584aba 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -510,9 +510,15 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
 					struct perf_sample_data *,
 					struct pt_regs *regs);
 
-enum perf_group_flag {
-	PERF_GROUP_SOFTWARE		= 0x1,
-};
+/*
+ * Event capabilities. For event_caps and groups caps.
+ *
+ * PERF_EV_CAP_SOFTWARE: Is a software event.
+ * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
+ * from any CPU in the package where it is active.
+ */
+#define PERF_EV_CAP_SOFTWARE		BIT(0)
+#define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
@@ -568,7 +574,12 @@ struct perf_event {
 	struct hlist_node		hlist_entry;
 	struct list_head		active_entry;
 	int				nr_siblings;
-	int				group_flags;
+
+	/* Not serialized. Only written during event initialization. */
+	int				event_caps;
+	/* The cumulative AND of all event_caps for events in this group. */
+	int				group_caps;
+
 	struct perf_event		*group_leader;
 	struct pmu			*pmu;
 	void				*pmu_private;
@@ -774,6 +785,9 @@ struct perf_cpu_context {
 #ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
 #endif
+
+	struct list_head		sched_cb_entry;
+	int				sched_cb_usage;
 };
 
 struct perf_output_handle {
@@ -985,7 +999,7 @@ static inline bool is_sampling_event(struct perf_event *event)
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	return event->pmu->task_ctx_nr == perf_sw_context;
+	return event->event_caps & PERF_EV_CAP_SOFTWARE;
 }
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc9bb2225291..7c0d263f6bc5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1475,8 +1475,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (event->group_leader == event) {
 		struct list_head *list;
 
-		if (is_software_event(event))
-			event->group_flags |= PERF_GROUP_SOFTWARE;
+		event->group_caps = event->event_caps;
 
 		list = ctx_group_list(event, ctx);
 		list_add_tail(&event->group_entry, list);
@@ -1630,9 +1629,7 @@ static void perf_group_attach(struct perf_event *event)
 
 	WARN_ON_ONCE(group_leader->ctx != event->ctx);
 
-	if (group_leader->group_flags & PERF_GROUP_SOFTWARE &&
-			!is_software_event(event))
-		group_leader->group_flags &= ~PERF_GROUP_SOFTWARE;
+	group_leader->group_caps &= event->event_caps;
 
 	list_add_tail(&event->group_entry, &group_leader->sibling_list);
 	group_leader->nr_siblings++;
@@ -1723,7 +1720,7 @@ static void perf_group_detach(struct perf_event *event)
 		sibling->group_leader = sibling;
 
 		/* Inherit group flags from the previous leader */
-		sibling->group_flags = event->group_flags;
+		sibling->group_caps = event->group_caps;
 
 		WARN_ON_ONCE(sibling->ctx != event->ctx);
 	}
@@ -1832,6 +1829,8 @@ group_sched_out(struct perf_event *group_event,
 	struct perf_event *event;
 	int state = group_event->state;
 
+	perf_pmu_disable(ctx->pmu);
+
 	event_sched_out(group_event, cpuctx, ctx);
 
 	/*
@@ -1840,6 +1839,8 @@ group_sched_out(struct perf_event *group_event,
 	list_for_each_entry(event, &group_event->sibling_list, group_entry)
 		event_sched_out(event, cpuctx, ctx);
 
+	perf_pmu_enable(ctx->pmu);
+
 	if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive)
 		cpuctx->exclusive = 0;
 }
@@ -2145,7 +2146,7 @@ static int group_can_go_on(struct perf_event *event,
 	/*
 	 * Groups consisting entirely of software events can always go on.
 	 */
-	if (event->group_flags & PERF_GROUP_SOFTWARE)
+	if (event->group_caps & PERF_EV_CAP_SOFTWARE)
 		return 1;
 	/*
 	 * If an exclusive group is already on, no other hardware
@@ -2491,7 +2492,7 @@ static int __perf_event_stop(void *info)
 	 * while restarting.
 	 */
 	if (sd->restart)
-		event->pmu->start(event, PERF_EF_START);
+		event->pmu->start(event, 0);
 
 	return 0;
 }
@@ -2837,19 +2838,36 @@ unlock:
 	}
 }
 
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
 void perf_sched_cb_dec(struct pmu *pmu)
 {
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
 	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
+
 void perf_sched_cb_inc(struct pmu *pmu)
 {
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
 	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
  * This function provides the context switch callback to the lower code
  * layer. It is invoked ONLY when the context switch callback is enabled.
+ *
+ * This callback is relevant even to per-cpu events; for example multi event
+ * PEBS requires this to provide PID/TID information. This requires we flush
+ * all queued PEBS records before we context switch to a new task.
  */
 static void perf_pmu_sched_task(struct task_struct *prev,
 				struct task_struct *next,
@@ -2857,34 +2875,24 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 {
 	struct perf_cpu_context *cpuctx;
 	struct pmu *pmu;
-	unsigned long flags;
 
 	if (prev == next)
 		return;
 
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		if (pmu->sched_task) {
-			cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
 
-			perf_pmu_disable(pmu);
+		if (WARN_ON_ONCE(!pmu->sched_task))
+			continue;
 
-			pmu->sched_task(cpuctx->task_ctx, sched_in);
+		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+		perf_pmu_disable(pmu);
 
-			perf_pmu_enable(pmu);
+		pmu->sched_task(cpuctx->task_ctx, sched_in);
 
-			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-		}
+		perf_pmu_enable(pmu);
+		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 	}
-
-	rcu_read_unlock();
-
-	local_irq_restore(flags);
 }
 
 static void perf_event_switch(struct task_struct *task,
@@ -3416,6 +3424,22 @@ struct perf_read_data {
 	int ret;
 };
 
+static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+{
+	int event_cpu = event->oncpu;
+	u16 local_pkg, event_pkg;
+
+	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
+		event_pkg =  topology_physical_package_id(event_cpu);
+		local_pkg =  topology_physical_package_id(local_cpu);
+
+		if (event_pkg == local_pkg)
+			return local_cpu;
+	}
+
+	return event_cpu;
+}
+
 /*
  * Cross CPU call to read the hardware event
  */
@@ -3537,7 +3561,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0;
+	int ret = 0, cpu_to_read, local_cpu;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3549,6 +3573,11 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
+
+		local_cpu = get_cpu();
+		cpu_to_read = find_cpu_to_read(event, local_cpu);
+		put_cpu();
+
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
@@ -3559,7 +3588,7 @@ static int perf_event_read(struct perf_event *event, bool group)
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
@@ -5350,9 +5379,10 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 			struct pt_regs *regs, u64 mask)
 {
 	int bit;
+	DECLARE_BITMAP(_mask, 64);
 
-	for_each_set_bit(bit, (const unsigned long *) &mask,
-			 sizeof(mask) * BITS_PER_BYTE) {
+	bitmap_from_u64(_mask, mask);
+	for_each_set_bit(bit, _mask, sizeof(mask) * BITS_PER_BYTE) {
 		u64 val;
 
 		val = perf_reg_value(regs, bit);
@@ -9505,6 +9535,9 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_alloc;
 	}
 
+	if (pmu->task_ctx_nr == perf_sw_context)
+		event->event_caps |= PERF_EV_CAP_SOFTWARE;
+
 	if (group_leader &&
 	    (is_software_event(event) != is_software_event(group_leader))) {
 		if (is_software_event(event)) {
@@ -9518,7 +9551,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			 */
 			pmu = group_leader->pmu;
 		} else if (is_software_event(group_leader) &&
-			   (group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			   (group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
 			/*
 			 * In case the group is a pure software group, and we
 			 * try to add a hardware event, move the whole group to
@@ -10453,6 +10486,8 @@ static void __init perf_event_init_all_cpus(void)
 
 		INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
 		raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
+
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 8c50276b60d1..d4129bb05e5d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -150,7 +150,7 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
  * Returns 0 on success, -EFAULT on failure.
  */
 static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
-				struct page *page, struct page *kpage)
+				struct page *old_page, struct page *new_page)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
@@ -161,49 +161,49 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	const unsigned long mmun_end   = addr + PAGE_SIZE;
 	struct mem_cgroup *memcg;
 
-	err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg,
+	err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, &memcg,
 			false);
 	if (err)
 		return err;
 
 	/* For try_to_free_swap() and munlock_vma_page() below */
-	lock_page(page);
+	lock_page(old_page);
 
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
-	ptep = page_check_address(page, mm, addr, &ptl, 0);
+	ptep = page_check_address(old_page, mm, addr, &ptl, 0);
 	if (!ptep) {
-		mem_cgroup_cancel_charge(kpage, memcg, false);
+		mem_cgroup_cancel_charge(new_page, memcg, false);
 		goto unlock;
 	}
 
-	get_page(kpage);
-	page_add_new_anon_rmap(kpage, vma, addr, false);
-	mem_cgroup_commit_charge(kpage, memcg, false, false);
-	lru_cache_add_active_or_unevictable(kpage, vma);
+	get_page(new_page);
+	page_add_new_anon_rmap(new_page, vma, addr, false);
+	mem_cgroup_commit_charge(new_page, memcg, false, false);
+	lru_cache_add_active_or_unevictable(new_page, vma);
 
-	if (!PageAnon(page)) {
-		dec_mm_counter(mm, mm_counter_file(page));
+	if (!PageAnon(old_page)) {
+		dec_mm_counter(mm, mm_counter_file(old_page));
 		inc_mm_counter(mm, MM_ANONPAGES);
 	}
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
 	ptep_clear_flush_notify(vma, addr, ptep);
-	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
+	set_pte_at_notify(mm, addr, ptep, mk_pte(new_page, vma->vm_page_prot));
 
-	page_remove_rmap(page, false);
-	if (!page_mapped(page))
-		try_to_free_swap(page);
+	page_remove_rmap(old_page, false);
+	if (!page_mapped(old_page))
+		try_to_free_swap(old_page);
 	pte_unmap_unlock(ptep, ptl);
 
 	if (vma->vm_flags & VM_LOCKED)
-		munlock_vma_page(page);
-	put_page(page);
+		munlock_vma_page(old_page);
+	put_page(old_page);
 
 	err = 0;
  unlock:
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-	unlock_page(page);
+	unlock_page(old_page);
 	return err;
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7bc56762ca35..37824d98ae71 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4123,6 +4123,30 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
+#ifdef CONFIG_KPROBE_EVENT
+	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
+	"\t\t\t  Write into this file to define/undefine new trace events.\n"
+#endif
+#ifdef CONFIG_UPROBE_EVENT
+	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
+	"\t\t\t  Write into this file to define/undefine new trace events.\n"
+#endif
+#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+	"\t  accepts: event-definitions (one definition per line)\n"
+	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
+	"\t           -:[<group>/]<event>\n"
+#ifdef CONFIG_KPROBE_EVENT
+	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+#endif
+#ifdef CONFIG_UPROBE_EVENT
+	"\t    place: <path>:<offset>\n"
+#endif
+	"\t     args: <name>=fetcharg[:type]\n"
+	"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
+	"\t           $stack<index>, $stack, $retval, $comm\n"
+	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string,\n"
+	"\t           b<bit-width>@<bit-offset>/<container-size>\n"
+#endif
 	"  events/\t\t- Directory containing all trace event subsystems:\n"
 	"      enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
 	"  events/<system>/\t- Directory containing all trace events for <system>:\n"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9aedb0b06683..eb6c9f1d3a93 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -253,6 +253,10 @@ static const struct fetch_type kprobes_fetch_type_table[] = {
 	ASSIGN_FETCH_TYPE(s16, u16, 1),
 	ASSIGN_FETCH_TYPE(s32, u32, 1),
 	ASSIGN_FETCH_TYPE(s64, u64, 1),
+	ASSIGN_FETCH_TYPE_ALIAS(x8,  u8,  u8,  0),
+	ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
+	ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
+	ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),
 
 	ASSIGN_FETCH_TYPE_END
 };
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 74e80a582c28..8c0553d9afd3 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -36,24 +36,28 @@ const char *reserved_field_names[] = {
 };
 
 /* Printing  in basic type function template */
-#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt)				\
-int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name,	\
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(tname, type, fmt)			\
+int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, const char *name,	\
 				void *data, void *ent)			\
 {									\
 	trace_seq_printf(s, " %s=" fmt, name, *(type *)data);		\
 	return !trace_seq_has_overflowed(s);				\
 }									\
-const char PRINT_TYPE_FMT_NAME(type)[] = fmt;				\
-NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(type));
-
-DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x")
-DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x")
-DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "0x%x")
-DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "0x%Lx")
-DEFINE_BASIC_PRINT_TYPE_FUNC(s8,  "%d")
-DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d")
-DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d")
-DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld")
+const char PRINT_TYPE_FMT_NAME(tname)[] = fmt;				\
+NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(tname));
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8,  u8,  "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, u16, "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, u32, "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, u64, "%Lu")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8,  s8,  "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, s16, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, s32, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, s64, "%Ld")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x8,  u8,  "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x16, u16, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x32, u32, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x64, u64, "0x%Lx")
 
 /* Print type function for string type */
 int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name,
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 45400ca5ded1..0c0ae54d44c6 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -149,6 +149,11 @@ DECLARE_BASIC_PRINT_TYPE_FUNC(s8);
 DECLARE_BASIC_PRINT_TYPE_FUNC(s16);
 DECLARE_BASIC_PRINT_TYPE_FUNC(s32);
 DECLARE_BASIC_PRINT_TYPE_FUNC(s64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x64);
+
 DECLARE_BASIC_PRINT_TYPE_FUNC(string);
 
 #define FETCH_FUNC_NAME(method, type)	fetch_##method##_##type
@@ -203,7 +208,7 @@ DEFINE_FETCH_##method(u32)		\
 DEFINE_FETCH_##method(u64)
 
 /* Default (unsigned long) fetch type */
-#define __DEFAULT_FETCH_TYPE(t) u##t
+#define __DEFAULT_FETCH_TYPE(t) x##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
 #define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
 #define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
@@ -234,6 +239,10 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define ASSIGN_FETCH_TYPE(ptype, ftype, sign)			\
 	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
 
+/* If ptype is an alias of atype, use this macro (show atype in format) */
+#define ASSIGN_FETCH_TYPE_ALIAS(ptype, atype, ftype, sign)		\
+	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #atype)
+
 #define ASSIGN_FETCH_TYPE_END {}
 
 #define FETCH_TYPE_STRING	0
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c53485441c88..7a687320f867 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -211,6 +211,10 @@ static const struct fetch_type uprobes_fetch_type_table[] = {
 	ASSIGN_FETCH_TYPE(s16, u16, 1),
 	ASSIGN_FETCH_TYPE(s32, u32, 1),
 	ASSIGN_FETCH_TYPE(s64, u64, 1),
+	ASSIGN_FETCH_TYPE_ALIAS(x8,  u8,  u8,  0),
+	ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0),
+	ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0),
+	ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0),
 
 	ASSIGN_FETCH_TYPE_END
 };
diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..e38b64c82b97
--- /dev/null
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -0,0 +1,47 @@
+#ifndef TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H
+#define MADV_DODUMP	17
+#define MADV_DOFORK	11
+#define MADV_DONTDUMP   16
+#define MADV_DONTFORK	10
+#define MADV_DONTNEED	6
+#define MADV_FREE	8
+#define MADV_HUGEPAGE	14
+#define MADV_MERGEABLE   12
+#define MADV_NOHUGEPAGE	15
+#define MADV_NORMAL	0
+#define MADV_RANDOM	1
+#define MADV_REMOVE	9
+#define MADV_SEQUENTIAL	2
+#define MADV_UNMERGEABLE 13
+#define MADV_WILLNEED	3
+#define MAP_ANONYMOUS	0x10
+#define MAP_DENYWRITE	0x02000
+#define MAP_EXECUTABLE	0x04000
+#define MAP_FILE	0
+#define MAP_FIXED	0x100
+#define MAP_GROWSDOWN	0x01000
+#define MAP_HUGETLB	0x100000
+#define MAP_LOCKED	0x08000
+#define MAP_NONBLOCK	0x40000
+#define MAP_NORESERVE	0x10000
+#define MAP_POPULATE	0x20000
+#define MAP_PRIVATE	0x02
+#define MAP_SHARED	0x01
+#define MAP_STACK	0x80000
+#define PROT_EXEC	0x4
+#define PROT_GROWSDOWN	0x01000000
+#define PROT_GROWSUP	0x02000000
+#define PROT_NONE	0x0
+#define PROT_READ	0x1
+#define PROT_SEM	0x8
+#define PROT_WRITE	0x2
+/* MADV_HWPOISON is undefined on alpha, fix it for perf */
+#define MADV_HWPOISON	100
+/* MADV_SOFT_OFFLINE is undefined on alpha, fix it for perf */
+#define MADV_SOFT_OFFLINE 101
+/* MAP_32BIT is undefined on alpha, fix it for perf */
+#define MAP_32BIT	0
+/* MAP_UNINITIALIZED is undefined on alpha, fix it for perf */
+#define MAP_UNINITIALIZED	0
+#endif
diff --git a/tools/arch/arc/include/uapi/asm/mman.h b/tools/arch/arc/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..aa3acd2aa9af
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on arc, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/arm/include/uapi/asm/mman.h b/tools/arch/arm/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..478f699f56fd
--- /dev/null
+++ b/tools/arch/arm/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on arm, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/arm64/include/uapi/asm/mman.h b/tools/arch/arm64/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..70fd3113710a
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on arm64, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/frv/include/uapi/asm/mman.h b/tools/arch/frv/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..5be78ac12464
--- /dev/null
+++ b/tools/arch/frv/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on frv, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/h8300/include/uapi/asm/mman.h b/tools/arch/h8300/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..9d9ac54d3c5a
--- /dev/null
+++ b/tools/arch/h8300/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on h8300, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/hexagon/include/uapi/asm/mman.h b/tools/arch/hexagon/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..102f3fae6085
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on hexagon, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/ia64/include/uapi/asm/mman.h b/tools/arch/ia64/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..1d6e5ac6442d
--- /dev/null
+++ b/tools/arch/ia64/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on ia64, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/m32r/include/uapi/asm/mman.h b/tools/arch/m32r/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..1c29635bb73b
--- /dev/null
+++ b/tools/arch/m32r/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on m32r, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/microblaze/include/uapi/asm/mman.h b/tools/arch/microblaze/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..005cd50b50e1
--- /dev/null
+++ b/tools/arch/microblaze/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on microblaze, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..c02052965d50
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -0,0 +1,46 @@
+#ifndef TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H
+#define MADV_DODUMP	17
+#define MADV_DOFORK	11
+#define MADV_DONTDUMP	16
+#define MADV_DONTFORK	10
+#define MADV_DONTNEED	4
+#define MADV_FREE	8
+#define MADV_HUGEPAGE	14
+#define MADV_HWPOISON	 100
+#define MADV_MERGEABLE	 12
+#define MADV_NOHUGEPAGE 15
+#define MADV_NORMAL	0
+#define MADV_RANDOM	1
+#define MADV_REMOVE	9
+#define MADV_SEQUENTIAL 2
+#define MADV_UNMERGEABLE 13
+#define MADV_WILLNEED	3
+#define MAP_ANONYMOUS	0x0800
+#define MAP_DENYWRITE	0x2000
+#define MAP_EXECUTABLE	0x4000
+#define MAP_FILE	0
+#define MAP_FIXED	0x010
+#define MAP_GROWSDOWN	0x1000
+#define MAP_HUGETLB	0x80000
+#define MAP_LOCKED	0x8000
+#define MAP_NONBLOCK	0x20000
+#define MAP_NORESERVE	0x0400
+#define MAP_POPULATE	0x10000
+#define MAP_PRIVATE	0x002
+#define MAP_SHARED	0x001
+#define MAP_STACK	0x40000
+#define PROT_EXEC	0x04
+#define PROT_GROWSDOWN	0x01000000
+#define PROT_GROWSUP	0x02000000
+#define PROT_NONE	0x00
+#define PROT_READ	0x01
+#define PROT_SEM	0x10
+#define PROT_WRITE	0x02
+/* MADV_SOFT_OFFLINE is undefined on mips, fix it for perf */
+#define MADV_SOFT_OFFLINE 101
+/* MAP_32BIT is undefined on mips, fix it for perf */
+#define MAP_32BIT	0
+/* MAP_UNINITIALIZED is undefined on mips, fix it for perf */
+#define MAP_UNINITIALIZED	0
+#endif
diff --git a/tools/arch/mn10300/include/uapi/asm/mman.h b/tools/arch/mn10300/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..c1ea36d83acc
--- /dev/null
+++ b/tools/arch/mn10300/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on mn10300, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..03d8d5b7ae7f
--- /dev/null
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -0,0 +1,47 @@
+#ifndef TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H
+#define MADV_DODUMP	70
+#define MADV_DOFORK	11
+#define MADV_DONTDUMP   69
+#define MADV_DONTFORK	10
+#define MADV_DONTNEED   4
+#define MADV_FREE	8
+#define MADV_HUGEPAGE	67
+#define MADV_MERGEABLE   65
+#define MADV_NOHUGEPAGE	68
+#define MADV_NORMAL     0
+#define MADV_RANDOM     1
+#define MADV_REMOVE	9
+#define MADV_SEQUENTIAL 2
+#define MADV_UNMERGEABLE 66
+#define MADV_WILLNEED   3
+#define MAP_ANONYMOUS	0x10
+#define MAP_DENYWRITE	0x0800
+#define MAP_EXECUTABLE	0x1000
+#define MAP_FILE	0
+#define MAP_FIXED	0x04
+#define MAP_GROWSDOWN	0x8000
+#define MAP_HUGETLB	0x80000
+#define MAP_LOCKED	0x2000
+#define MAP_NONBLOCK	0x20000
+#define MAP_NORESERVE	0x4000
+#define MAP_POPULATE	0x10000
+#define MAP_PRIVATE	0x02
+#define MAP_SHARED	0x01
+#define MAP_STACK	0x40000
+#define PROT_EXEC	0x4
+#define PROT_GROWSDOWN	0x01000000
+#define PROT_GROWSUP	0x02000000
+#define PROT_NONE	0x0
+#define PROT_READ	0x1
+#define PROT_SEM	0x8
+#define PROT_WRITE	0x2
+/* MADV_HWPOISON is undefined on parisc, fix it for perf */
+#define MADV_HWPOISON	100
+/* MADV_SOFT_OFFLINE is undefined on parisc, fix it for perf */
+#define MADV_SOFT_OFFLINE 101
+/* MAP_32BIT is undefined on parisc, fix it for perf */
+#define MAP_32BIT	0
+/* MAP_UNINITIALIZED is undefined on parisc, fix it for perf */
+#define MAP_UNINITIALIZED	0
+#endif
diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..761db43172fe
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/mman.h
@@ -0,0 +1,15 @@
+#ifndef TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H
+#define MAP_DENYWRITE	0x0800
+#define MAP_EXECUTABLE	0x1000
+#define MAP_GROWSDOWN	0x0100
+#define MAP_HUGETLB	0x40000
+#define MAP_LOCKED	0x80
+#define MAP_NONBLOCK	0x10000
+#define MAP_NORESERVE   0x40
+#define MAP_POPULATE	0x8000
+#define MAP_STACK	0x20000
+#include <uapi/asm-generic/mman-common.h>
+/* MAP_32BIT is undefined on powerpc, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/s390/include/uapi/asm/mman.h b/tools/arch/s390/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..b03dea9e1f56
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on s390, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/score/include/uapi/asm/mman.h b/tools/arch/score/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..2f8fb89944fd
--- /dev/null
+++ b/tools/arch/score/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on score, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/sh/include/uapi/asm/mman.h b/tools/arch/sh/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..26504f6f060e
--- /dev/null
+++ b/tools/arch/sh/include/uapi/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H
+#include <uapi/asm-generic/mman.h>
+/* MAP_32BIT is undefined on sh, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..8640525de991
--- /dev/null
+++ b/tools/arch/sparc/include/uapi/asm/mman.h
@@ -0,0 +1,15 @@
+#ifndef TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H
+#define MAP_DENYWRITE	0x0800
+#define MAP_EXECUTABLE	0x1000
+#define MAP_GROWSDOWN	0x0200
+#define MAP_HUGETLB	0x40000
+#define MAP_LOCKED      0x100
+#define MAP_NONBLOCK	0x10000
+#define MAP_NORESERVE   0x40
+#define MAP_POPULATE	0x8000
+#define MAP_STACK	0x20000
+#include <uapi/asm-generic/mman-common.h>
+/* MAP_32BIT is undefined on sparc, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/tile/include/uapi/asm/mman.h b/tools/arch/tile/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..7116c4b928b3
--- /dev/null
+++ b/tools/arch/tile/include/uapi/asm/mman.h
@@ -0,0 +1,15 @@
+#ifndef TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H
+#define MAP_DENYWRITE	0x0800
+#define MAP_EXECUTABLE	0x1000
+#define MAP_GROWSDOWN	0x0100
+#define MAP_HUGETLB	0x4000
+#define MAP_LOCKED	0x0200
+#define MAP_NONBLOCK	0x0080
+#define MAP_NORESERVE	0x0400
+#define MAP_POPULATE	0x0040
+#define MAP_STACK	MAP_GROWSDOWN
+#include <uapi/asm-generic/mman-common.h>
+/* MAP_32BIT is undefined on tile, fix it for perf */
+#define MAP_32BIT	0
+#endif
diff --git a/tools/arch/x86/include/uapi/asm/mman.h b/tools/arch/x86/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..b73c1af8b1dd
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/mman.h
@@ -0,0 +1,5 @@
+#ifndef TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H
+#define MAP_32BIT	0x40
+#include <uapi/asm-generic/mman.h>
+#endif
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..4453195c450c
--- /dev/null
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -0,0 +1,47 @@
+#ifndef TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H
+#define TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H
+#define MADV_DODUMP	17
+#define MADV_DOFORK	11
+#define MADV_DONTDUMP   16
+#define MADV_DONTFORK	10
+#define MADV_DONTNEED	4
+#define MADV_FREE	8
+#define MADV_HUGEPAGE	14
+#define MADV_MERGEABLE   12
+#define MADV_NOHUGEPAGE	15
+#define MADV_NORMAL	0
+#define MADV_RANDOM	1
+#define MADV_REMOVE	9
+#define MADV_SEQUENTIAL	2
+#define MADV_UNMERGEABLE 13
+#define MADV_WILLNEED	3
+#define MAP_ANONYMOUS	0x0800
+#define MAP_DENYWRITE	0x2000
+#define MAP_EXECUTABLE	0x4000
+#define MAP_FILE	0
+#define MAP_FIXED	0x010
+#define MAP_GROWSDOWN	0x1000
+#define MAP_HUGETLB	0x80000
+#define MAP_LOCKED	0x8000
+#define MAP_NONBLOCK	0x20000
+#define MAP_NORESERVE	0x0400
+#define MAP_POPULATE	0x10000
+#define MAP_PRIVATE	0x002
+#define MAP_SHARED	0x001
+#define MAP_STACK	0x40000
+#define PROT_EXEC	0x4
+#define PROT_GROWSDOWN	0x01000000
+#define PROT_GROWSUP	0x02000000
+#define PROT_NONE	0x0
+#define PROT_READ	0x1
+#define PROT_SEM	0x10
+#define PROT_WRITE	0x2
+/* MADV_HWPOISON is undefined on xtensa, fix it for perf */
+#define MADV_HWPOISON	100
+/* MADV_SOFT_OFFLINE is undefined on xtensa, fix it for perf */
+#define MADV_SOFT_OFFLINE 101
+/* MAP_32BIT is undefined on xtensa, fix it for perf */
+#define MAP_32BIT	0
+/* MAP_UNINITIALIZED is undefined on xtensa, fix it for perf */
+#define MAP_UNINITIALIZED	0
+#endif
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
new file mode 100644
index 000000000000..7d410260661b
--- /dev/null
+++ b/tools/include/linux/coresight-pmu.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _LINUX_CORESIGHT_PMU_H
+#define _LINUX_CORESIGHT_PMU_H
+
+#define CORESIGHT_ETM_PMU_NAME "cs_etm"
+#define CORESIGHT_ETM_PMU_SEED  0x10
+
+/* ETMv3.5/PTM's ETMCR config bit */
+#define ETM_OPT_CYCACC  12
+#define ETM_OPT_TS      28
+
+static inline int coresight_get_trace_id(int cpu)
+{
+	/*
+	 * A trace ID of value 0 is invalid, so let's start at some
+	 * random value that fits in 7 bits and go from there.  Since
+	 * the common convention is to have data trace IDs be I(N) + 1,
+	 * set instruction trace IDs as a function of the CPU number.
+	 */
+	return (CORESIGHT_ETM_PMU_SEED + (cpu * 2));
+}
+
+#endif
diff --git a/tools/include/linux/time64.h b/tools/include/linux/time64.h
new file mode 100644
index 000000000000..df9265483d65
--- /dev/null
+++ b/tools/include/linux/time64.h
@@ -0,0 +1,12 @@
+#ifndef _TOOLS_LINUX_TIME64_H
+#define _TOOLS_LINUX_TIME64_H
+
+#define MSEC_PER_SEC	1000L
+#define USEC_PER_MSEC	1000L
+#define NSEC_PER_USEC	1000L
+#define NSEC_PER_MSEC	1000000L
+#define USEC_PER_SEC	1000000L
+#define NSEC_PER_SEC	1000000000L
+#define FSEC_PER_SEC	1000000000000000LL
+
+#endif /* _LINUX_TIME64_H */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
new file mode 100644
index 000000000000..58274382a616
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -0,0 +1,75 @@
+#ifndef __ASM_GENERIC_MMAN_COMMON_H
+#define __ASM_GENERIC_MMAN_COMMON_H
+
+/*
+ Author: Michael S. Tsirkin <mst@mellanox.co.il>, Mellanox Technologies Ltd.
+ Based on: asm-xxx/mman.h
+*/
+
+#define PROT_READ	0x1		/* page can be read */
+#define PROT_WRITE	0x2		/* page can be written */
+#define PROT_EXEC	0x4		/* page can be executed */
+#define PROT_SEM	0x8		/* page may be used for atomic ops */
+#define PROT_NONE	0x0		/* page can not be accessed */
+#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
+
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_TYPE	0x0f		/* Mask for type of mapping */
+#define MAP_FIXED	0x10		/* Interpret addr exactly */
+#define MAP_ANONYMOUS	0x20		/* don't use a file */
+#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
+# define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be uninitialized */
+#else
+# define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
+#endif
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
+#define MS_ASYNC	1		/* sync memory asynchronously */
+#define MS_INVALIDATE	2		/* invalidate the caches */
+#define MS_SYNC		4		/* synchronous memory sync */
+
+#define MADV_NORMAL	0		/* no further special treatment */
+#define MADV_RANDOM	1		/* expect random page references */
+#define MADV_SEQUENTIAL	2		/* expect sequential page references */
+#define MADV_WILLNEED	3		/* will need these pages */
+#define MADV_DONTNEED	4		/* don't need these pages */
+
+/* common parameters: try to keep these consistent across architectures */
+#define MADV_FREE	8		/* free pages only if memory pressure */
+#define MADV_REMOVE	9		/* remove these pages & resources */
+#define MADV_DONTFORK	10		/* don't inherit across fork */
+#define MADV_DOFORK	11		/* do inherit across fork */
+#define MADV_HWPOISON	100		/* poison a page for testing */
+#define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
+
+#define MADV_MERGEABLE   12		/* KSM may merge identical pages */
+#define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
+
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+#define MADV_NOHUGEPAGE	15		/* Not worth backing with hugepages */
+
+#define MADV_DONTDUMP   16		/* Explicity exclude from the core dump,
+					   overrides the coredump filter bits */
+#define MADV_DODUMP	17		/* Clear the MADV_DONTDUMP flag */
+
+/* compatibility flags */
+#define MAP_FILE	0
+
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
+#endif /* __ASM_GENERIC_MMAN_COMMON_H */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
new file mode 100644
index 000000000000..10fa7857777f
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -0,0 +1,22 @@
+#ifndef __ASM_GENERIC_MMAN_H
+#define __ASM_GENERIC_MMAN_H
+
+#include <uapi/asm-generic/mman-common.h>
+
+#define MAP_GROWSDOWN	0x0100		/* stack-like segment */
+#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
+#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
+#define MAP_LOCKED	0x2000		/* pages are locked */
+#define MAP_NORESERVE	0x4000		/* don't check for reservations */
+#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
+#define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
+
+/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
+
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+#endif /* __ASM_GENERIC_MMAN_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
new file mode 100644
index 000000000000..81d8edf11789
--- /dev/null
+++ b/tools/include/uapi/linux/mman.h
@@ -0,0 +1,13 @@
+#ifndef _UAPI_LINUX_MMAN_H
+#define _UAPI_LINUX_MMAN_H
+
+#include <uapi/asm/mman.h>
+
+#define MREMAP_MAYMOVE	1
+#define MREMAP_FIXED	2
+
+#define OVERCOMMIT_GUESS		0
+#define OVERCOMMIT_ALWAYS		1
+#define OVERCOMMIT_NEVER		2
+
+#endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index ba7094b945ff..f99f49e4a31e 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -34,6 +34,10 @@
 #define TRACEFS_MAGIC          0x74726163
 #endif
 
+#ifndef HUGETLBFS_MAGIC
+#define HUGETLBFS_MAGIC        0x958458f6
+#endif
+
 static const char * const sysfs__fs_known_mountpoints[] = {
 	"/sys",
 	0,
@@ -67,6 +71,10 @@ static const char * const tracefs__known_mountpoints[] = {
 	0,
 };
 
+static const char * const hugetlbfs__known_mountpoints[] = {
+	0,
+};
+
 struct fs {
 	const char		*name;
 	const char * const	*mounts;
@@ -80,6 +88,7 @@ enum {
 	FS__PROCFS  = 1,
 	FS__DEBUGFS = 2,
 	FS__TRACEFS = 3,
+	FS__HUGETLBFS = 4,
 };
 
 #ifndef TRACEFS_MAGIC
@@ -107,6 +116,11 @@ static struct fs fs__entries[] = {
 		.mounts	= tracefs__known_mountpoints,
 		.magic	= TRACEFS_MAGIC,
 	},
+	[FS__HUGETLBFS] = {
+		.name	= "hugetlbfs",
+		.mounts = hugetlbfs__known_mountpoints,
+		.magic	= HUGETLBFS_MAGIC,
+	},
 };
 
 static bool fs__read_mounts(struct fs *fs)
@@ -265,6 +279,7 @@ FS(sysfs,   FS__SYSFS);
 FS(procfs,  FS__PROCFS);
 FS(debugfs, FS__DEBUGFS);
 FS(tracefs, FS__TRACEFS);
+FS(hugetlbfs, FS__HUGETLBFS);
 
 int filename__read_int(const char *filename, int *value)
 {
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 16c9c2ed7c5b..a63269f5d20c 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -21,6 +21,7 @@ FS(sysfs)
 FS(procfs)
 FS(debugfs)
 FS(tracefs)
+FS(hugetlbfs)
 
 #undef FS
 
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 15949e2a7805..cb081ac59fd1 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -110,6 +110,14 @@ Given a $HOME/.perfconfig like this:
 		order = caller
 		sort-key = function
 
+	[report]
+		# Defaults
+		sort-order = comm,dso,symbol
+		percent-limit = 0
+		queue-size = 0
+		children = true
+		group = true
+
 Variables
 ~~~~~~~~~
 
@@ -382,6 +390,10 @@ call-graph.*::
 		histogram entry. Default is 0 which means no limitation.
 
 report.*::
+	report.sort_order::
+		Allows changing the default sort order from "comm,dso,symbol" to
+		some other default, for instance "sym,dso" may be more fitting for
+		kernel developers.
 	report.percent-limit::
 		This one is mostly the same as call-graph.threshold but works for
 		histogram entries. Entries having an overhead lower than this
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index b303bcdd8ed1..e6c9902c6d82 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -21,6 +21,8 @@ or
 'perf probe' [options] --vars='PROBEPOINT'
 or
 'perf probe' [options] --funcs
+or
+'perf probe' [options] --definition='PROBE' [...]
 
 DESCRIPTION
 -----------
@@ -34,6 +36,8 @@ OPTIONS
 -k::
 --vmlinux=PATH::
 	Specify vmlinux path which has debuginfo (Dwarf binary).
+	Only when using this with --definition, you can give an offline
+	vmlinux file.
 
 -m::
 --module=MODNAME|PATH::
@@ -96,6 +100,11 @@ OPTIONS
 	can also list functions in a user space executable / shared library.
 	This also can accept a FILTER rule argument.
 
+-D::
+--definition=::
+	Show trace-event definition converted from given probe-event instead
+	of write it into tracing/[k,u]probe_events.
+
 --filter=FILTER::
 	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
 	pattern, see FILTER PATTERN for detail.
@@ -176,13 +185,12 @@ Each probe argument follows below syntax.
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
-'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
-
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo (*). Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal integers (x/x8/x16/x32/x64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
 
 TYPES
 -----
-Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe.
+Basic types (u8/u16/u32/u64/s8/s16/s32/s64) and hexadecimal integers (x8/x16/x32/x64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively, and 'x' means that is shown in hexadecimal format. Traced arguments are shown in decimal (sNN/uNN) or hex (xNN). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe. Moreover, you can use 'x' to explicitly specify to be shown in hexadecimal (the size is also auto-detected).
 String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is;
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 379a2bed07c0..92335193dc33 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -35,15 +35,15 @@ OPTIONS
 
 	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
 	  'param1', 'param2', etc are defined as formats for the PMU in
-	  /sys/bus/event_sources/devices/<pmu>/format/*.
+	  /sys/bus/event_source/devices/<pmu>/format/*.
 
 	- a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
 
           where M, N, K are numbers (in decimal, hex, octal format). Acceptable
           values for each of 'config', 'config1' and 'config2' are defined by
-          corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/*
+          corresponding entries in /sys/bus/event_source/devices/<pmu>/format/*
           param1 and param2 are defined as formats for the PMU in:
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
 	  There are also some params which are not defined in .../<pmu>/format/*.
 	  These params can be used to overload default config values per event.
@@ -60,6 +60,18 @@ OPTIONS
 	  Note: If user explicitly sets options which conflict with the params,
 	  the value set by the params will be overridden.
 
+	  Also not defined in .../<pmu>/format/* are PMU driver specific
+	  configuration parameters.  Any configuration parameter preceded by
+	  the letter '@' is not interpreted in user space and sent down directly
+	  to the PMU driver.  For example:
+
+	  perf record -e some_event/@cfg1,@cfg2=config/ ...
+
+	  will see 'cfg1' and 'cfg2=config' pushed to the PMU driver associated
+	  with the event for further processing.  There is no restriction on
+	  what the configuration parameters are, as long as their semantic is
+	  understood and supported by the PMU driver.
+
         - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
           where addr is the address in memory you want to break in.
           Access is the memory access type (read, write, execute) it can
@@ -77,9 +89,62 @@ OPTIONS
 
 --filter=<filter>::
         Event filter. This option should follow a event selector (-e) which
-	selects tracepoint event(s). Multiple '--filter' options are combined
+	selects either tracepoint event(s) or a hardware trace PMU
+	(e.g. Intel PT or CoreSight).
+
+	- tracepoint filters
+
+	In the case of tracepoints, multiple '--filter' options are combined
 	using '&&'.
 
+	- address filters
+
+	A hardware trace PMU advertises its ability to accept a number of
+	address filters	by specifying a non-zero value in
+	/sys/bus/event_source/devices/<pmu>/nr_addr_filters.
+
+	Address filters have the format:
+
+	filter|start|stop|tracestop <start> [/ <size>] [@<file name>]
+
+	Where:
+	- 'filter': defines a region that will be traced.
+	- 'start': defines an address at which tracing will begin.
+	- 'stop': defines an address at which tracing will stop.
+	- 'tracestop': defines a region in which tracing will stop.
+
+	<file name> is the name of the object file, <start> is the offset to the
+	code to trace in that file, and <size> is the size of the region to
+	trace. 'start' and 'stop' filters need not specify a <size>.
+
+	If no object file is specified then the kernel is assumed, in which case
+	the start address must be a current kernel memory address.
+
+	<start> can also be specified by providing the name of a symbol. If the
+	symbol name is not unique, it can be disambiguated by inserting #n where
+	'n' selects the n'th symbol in address order. Alternately #0, #g or #G
+	select only a global symbol. <size> can also be specified by providing
+	the name of a symbol, in which case the size is calculated to the end
+	of that symbol. For 'filter' and 'tracestop' filters, if <size> is
+	omitted and <start> is a symbol, then the size is calculated to the end
+	of that symbol.
+
+	If <size> is omitted and <start> is '*', then the start and size will
+	be calculated from the first and last symbols, i.e. to trace the whole
+	file.
+
+	If symbol names (or '*') are provided, they must be surrounded by white
+	space.
+
+	The filter passed to the kernel is not necessarily the same as entered.
+	To see the filter that is passed, use the -v option.
+
+	The kernel may not be able to configure a trace region if it is not
+	within a single mapping.  MMAP events (or /proc/<pid>/maps) can be
+	examined to determine if that is a possibility.
+
+	Multiple filters can be separated with space or comma.
+
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
 	a event selector (-e) which selects tracepoint event(s). It adds a
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index fdc99fe6bbc3..b664b18d3991 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -437,6 +437,10 @@ in pmu-tools parser. This allows to read perf.data from python and dump it.
 quipper
 
 The quipper C++ parser is available at
-https://chromium.googlesource.com/chromiumos/platform/chromiumos-wide-profiling/
+https://chromium.googlesource.com/chromiumos/platform2
+
+It is under the chromiumos-wide-profiling/ subdirectory. This library can
+convert a perf data file to a protobuf and vice versa.
+
 Unfortunately this parser tends to be many versions behind and may not be able
 to parse data files generated by recent perf.
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
index 1d8d5bc4cd2d..2b477c1d1efe 100644
--- a/tools/perf/Documentation/perfconfig.example
+++ b/tools/perf/Documentation/perfconfig.example
@@ -27,3 +27,12 @@
 	use_offset = true
 	jump_arrows = true
 	show_nr_jumps = false
+
+[report]
+
+	# Defaults
+	sort-order = comm,dso,symbol
+	percent-limit = 0
+	queue-size = 0
+	children = true
+	group = true
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index ad2534df4ba6..0bda2cca2b3a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -60,14 +60,18 @@ tools/include/asm-generic/bitops.h
 tools/include/linux/atomic.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
+tools/include/linux/coresight-pmu.h
 tools/include/linux/filter.h
 tools/include/linux/hash.h
 tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/uapi/asm-generic/mman-common.h
+tools/include/uapi/asm-generic/mman.h
 tools/include/uapi/linux/bpf.h
 tools/include/uapi/linux/bpf_common.h
 tools/include/uapi/linux/hw_breakpoint.h
+tools/include/uapi/linux/mman.h
 tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
@@ -77,4 +81,6 @@ tools/include/linux/stringify.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 tools/include/linux/bitmap.h
+tools/include/linux/time64.h
+tools/arch/*/include/uapi/asm/mman.h
 tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 24803c58049a..72edf83d76b7 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -746,10 +746,13 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  ifeq ($(feature-get_cpuid), 0)
-    msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
-    NO_AUXTRACE := 1
-  else
+  ifeq ($(ARCH),x86)
+    ifeq ($(feature-get_cpuid), 0)
+      msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+      NO_AUXTRACE := 1
+    endif
+  endif
+  ifndef NO_AUXTRACE
     $(call detected,CONFIG_AUXTRACE)
     CFLAGS += -DHAVE_AUXTRACE_SUPPORT
   endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2d9087501633..d710db16b963 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -165,7 +165,7 @@ SUBCMD_DIR	= $(srctree)/tools/lib/subcmd/
 # non-config cases
 config := 1
 
-NON_CONFIG_TARGETS := clean TAGS tags cscope help
+NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -429,6 +429,18 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../include/asm-generic/bitops/fls64.h && ( \
         (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
         || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/linux/coresight-pmu.h && ( \
+	(diff -B ../include/linux/coresight-pmu.h ../../include/linux/coresight-pmu.h >/dev/null) \
+	|| echo "Warning: tools/include/linux/coresight-pmu.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/uapi/asm-generic/mman-common.h && ( \
+	(diff -B ../include/uapi/asm-generic/mman-common.h ../../include/uapi/asm-generic/mman-common.h >/dev/null) \
+	|| echo "Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/uapi/asm-generic/mman.h && ( \
+	(diff -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>$$" ../include/uapi/asm-generic/mman.h ../../include/uapi/asm-generic/mman.h >/dev/null) \
+	|| echo "Warning: tools/include/uapi/asm-generic/mman.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/uapi/linux/mman.h && ( \
+	(diff -B -I "^#include <\(uapi/\)*asm/mman.h>$$" ../include/uapi/linux/mman.h ../../include/uapi/linux/mman.h >/dev/null) \
+	|| echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/arch/arm/include/dwarf-regs-table.h b/tools/perf/arch/arm/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..f298d034c37b
--- /dev/null
+++ b/tools/perf/arch/arm/include/dwarf-regs-table.h
@@ -0,0 +1,9 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const arm_regstr_tbl[] = {
+	"%r0", "%r1", "%r2", "%r3", "%r4",
+	"%r5", "%r6", "%r7", "%r8", "%r9", "%r10",
+	"%fp", "%ip", "%sp", "%lr", "%pc",
+};
+#endif
diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index f98da17357c0..e64c5f216448 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -2,3 +2,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs-etm.o
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
new file mode 100644
index 000000000000..8edf2cb71564
--- /dev/null
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <stdbool.h>
+#include <linux/coresight-pmu.h>
+
+#include "../../util/auxtrace.h"
+#include "../../util/evlist.h"
+#include "../../util/pmu.h"
+#include "cs-etm.h"
+
+struct auxtrace_record
+*auxtrace_record__init(struct perf_evlist *evlist, int *err)
+{
+	struct perf_pmu	*cs_etm_pmu;
+	struct perf_evsel *evsel;
+	bool found_etm = false;
+
+	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
+
+	if (evlist) {
+		evlist__for_each_entry(evlist, evsel) {
+			if (cs_etm_pmu &&
+			    evsel->attr.type == cs_etm_pmu->type)
+				found_etm = true;
+		}
+	}
+
+	if (found_etm)
+		return cs_etm_record_init(err);
+
+	/*
+	 * Clear 'err' even if we haven't found a cs_etm event - that way perf
+	 * record can still be used even if tracers aren't present.  The NULL
+	 * return value will take care of telling the infrastructure HW tracing
+	 * isn't available.
+	 */
+	*err = 0;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
new file mode 100644
index 000000000000..47d584da5819
--- /dev/null
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -0,0 +1,617 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <api/fs/fs.h>
+#include <linux/bitops.h>
+#include <linux/coresight-pmu.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+
+#include "cs-etm.h"
+#include "../../perf.h"
+#include "../../util/auxtrace.h"
+#include "../../util/cpumap.h"
+#include "../../util/evlist.h"
+#include "../../util/evsel.h"
+#include "../../util/pmu.h"
+#include "../../util/thread_map.h"
+#include "../../util/cs-etm.h"
+
+#include <stdlib.h>
+
+#define ENABLE_SINK_MAX	128
+#define CS_BUS_DEVICE_PATH "/bus/coresight/devices/"
+
+struct cs_etm_recording {
+	struct auxtrace_record	itr;
+	struct perf_pmu		*cs_etm_pmu;
+	struct perf_evlist	*evlist;
+	bool			snapshot_mode;
+	size_t			snapshot_size;
+};
+
+static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
+
+static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
+					 struct record_opts *opts,
+					 const char *str)
+{
+	struct cs_etm_recording *ptr =
+				container_of(itr, struct cs_etm_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+	ptr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static int cs_etm_recording_options(struct auxtrace_record *itr,
+				    struct perf_evlist *evlist,
+				    struct record_opts *opts)
+{
+	struct cs_etm_recording *ptr =
+				container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	struct perf_evsel *evsel, *cs_etm_evsel = NULL;
+	const struct cpu_map *cpus = evlist->cpus;
+	bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0);
+
+	ptr->evlist = evlist;
+	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == cs_etm_pmu->type) {
+			if (cs_etm_evsel) {
+				pr_err("There may be only one %s event\n",
+				       CORESIGHT_ETM_PMU_NAME);
+				return -EINVAL;
+			}
+			evsel->attr.freq = 0;
+			evsel->attr.sample_period = 1;
+			cs_etm_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	/* no need to continue if at least one event of interest was found */
+	if (!cs_etm_evsel)
+		return 0;
+
+	if (opts->use_clockid) {
+		pr_err("Cannot use clockid (-k option) with %s\n",
+		       CORESIGHT_ETM_PMU_NAME);
+		return -EINVAL;
+	}
+
+	/* we are in snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		/*
+		 * No size were given to '-S' or '-m,', so go with
+		 * the default
+		 */
+		if (!opts->auxtrace_snapshot_size &&
+		    !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages =
+							KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+						opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+
+		/*
+		 * '-m,xyz' was specified but no snapshot size, so make the
+		 * snapshot size as big as the auxtrace mmap area.
+		 */
+		if (!opts->auxtrace_snapshot_size) {
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		}
+
+		/*
+		 * -Sxyz was specified but no auxtrace mmap area, so make the
+		 * auxtrace mmap area big enough to fit the requested snapshot
+		 * size.
+		 */
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+
+		/* Snapshost size can't be bigger than the auxtrace area */
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+
+		/* Something went wrong somewhere - this shouldn't happen */
+		if (!opts->auxtrace_snapshot_size ||
+		    !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+	}
+
+	/* We are in full trace mode but '-m,xyz' wasn't specified */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+
+	}
+
+	/* Validate auxtrace_mmap_pages provided by user */
+	if (opts->auxtrace_mmap_pages) {
+		unsigned int max_page = (KiB(128) / page_size);
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+
+		if (!privileged &&
+		    opts->auxtrace_mmap_pages > max_page) {
+			opts->auxtrace_mmap_pages = max_page;
+			pr_err("auxtrace too big, truncating to %d\n",
+			       max_page);
+		}
+
+		if (!is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for %s: must be a power of 2\n",
+			       CORESIGHT_ETM_PMU_NAME);
+			return -EINVAL;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode)
+		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
+			  opts->auxtrace_snapshot_size);
+
+	if (cs_etm_evsel) {
+		/*
+		 * To obtain the auxtrace buffer file descriptor, the auxtrace
+		 * event must come first.
+		 */
+		perf_evlist__to_front(evlist, cs_etm_evsel);
+		/*
+		 * In the case of per-cpu mmaps, we need the CPU on the
+		 * AUX event.
+		 */
+		if (!cpu_map__empty(cpus))
+			perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct perf_evsel *tracking_evsel;
+		int err;
+
+		err = parse_events(evlist, "dummy:u", NULL);
+		if (err)
+			return err;
+
+		tracking_evsel = perf_evlist__last(evlist);
+		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+		tracking_evsel->attr.freq = 0;
+		tracking_evsel->attr.sample_period = 1;
+
+		/* In per-cpu case, always need the time of mmap events etc */
+		if (!cpu_map__empty(cpus))
+			perf_evsel__set_sample_bit(tracking_evsel, TIME);
+	}
+
+	return 0;
+}
+
+static u64 cs_etm_get_config(struct auxtrace_record *itr)
+{
+	u64 config = 0;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	struct perf_evlist *evlist = ptr->evlist;
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == cs_etm_pmu->type) {
+			/*
+			 * Variable perf_event_attr::config is assigned to
+			 * ETMv3/PTM.  The bit fields have been made to match
+			 * the ETMv3.5 ETRMCR register specification.  See the
+			 * PMU_FORMAT_ATTR() declarations in
+			 * drivers/hwtracing/coresight/coresight-perf.c for
+			 * details.
+			 */
+			config = evsel->attr.config;
+			break;
+		}
+	}
+
+	return config;
+}
+
+static size_t
+cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	int i;
+	int etmv3 = 0, etmv4 = 0;
+	const struct cpu_map *cpus = evlist->cpus;
+
+	/* cpu map is not empty, we have specific CPUs to work with */
+	if (!cpu_map__empty(cpus)) {
+		for (i = 0; i < cpu_map__nr(cpus); i++) {
+			if (cs_etm_is_etmv4(itr, cpus->map[i]))
+				etmv4++;
+			else
+				etmv3++;
+		}
+	} else {
+		/* get configuration for all CPUs in the system */
+		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (cs_etm_is_etmv4(itr, i))
+				etmv4++;
+			else
+				etmv3++;
+		}
+	}
+
+	return (CS_ETM_HEADER_SIZE +
+	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
+	       (etmv3 * CS_ETMV3_PRIV_SIZE));
+}
+
+static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
+	[CS_ETM_ETMCCER]	= "mgmt/etmccer",
+	[CS_ETM_ETMIDR]		= "mgmt/etmidr",
+};
+
+static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
+	[CS_ETMV4_TRCIDR0]		= "trcidr/trcidr0",
+	[CS_ETMV4_TRCIDR1]		= "trcidr/trcidr1",
+	[CS_ETMV4_TRCIDR2]		= "trcidr/trcidr2",
+	[CS_ETMV4_TRCIDR8]		= "trcidr/trcidr8",
+	[CS_ETMV4_TRCAUTHSTATUS]	= "mgmt/trcauthstatus",
+};
+
+static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu)
+{
+	bool ret = false;
+	char path[PATH_MAX];
+	int scan;
+	unsigned int val;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	/* Take any of the RO files for ETMv4 and see if it present */
+	snprintf(path, PATH_MAX, "cpu%d/%s",
+		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+	scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+	/* The file was read successfully, we have a winner */
+	if (scan == 1)
+		ret = true;
+
+	return ret;
+}
+
+static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path)
+{
+	char pmu_path[PATH_MAX];
+	int scan;
+	unsigned int val = 0;
+
+	/* Get RO metadata from sysfs */
+	snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path);
+
+	scan = perf_pmu__scan_file(pmu, pmu_path, "%x", &val);
+	if (scan != 1)
+		pr_err("%s: error reading: %s\n", __func__, pmu_path);
+
+	return val;
+}
+
+static void cs_etm_get_metadata(int cpu, u32 *offset,
+				struct auxtrace_record *itr,
+				struct auxtrace_info_event *info)
+{
+	u32 increment;
+	u64 magic;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	/* first see what kind of tracer this cpu is affined to */
+	if (cs_etm_is_etmv4(itr, cpu)) {
+		magic = __perf_cs_etmv4_magic;
+		/* Get trace configuration register */
+		info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
+						cs_etm_get_config(itr);
+		/* Get traceID from the framework */
+		info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
+						coresight_get_trace_id(cpu);
+		/* Get read-only information from sysFS */
+		info->priv[*offset + CS_ETMV4_TRCIDR0] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+		info->priv[*offset + CS_ETMV4_TRCIDR1] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR1]);
+		info->priv[*offset + CS_ETMV4_TRCIDR2] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
+		info->priv[*offset + CS_ETMV4_TRCIDR8] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR8]);
+		info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro
+				      [CS_ETMV4_TRCAUTHSTATUS]);
+
+		/* How much space was used */
+		increment = CS_ETMV4_PRIV_MAX;
+	} else {
+		magic = __perf_cs_etmv3_magic;
+		/* Get configuration register */
+		info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
+		/* Get traceID from the framework */
+		info->priv[*offset + CS_ETM_ETMTRACEIDR] =
+						coresight_get_trace_id(cpu);
+		/* Get read-only information from sysFS */
+		info->priv[*offset + CS_ETM_ETMCCER] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv3_ro[CS_ETM_ETMCCER]);
+		info->priv[*offset + CS_ETM_ETMIDR] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv3_ro[CS_ETM_ETMIDR]);
+
+		/* How much space was used */
+		increment = CS_ETM_PRIV_MAX;
+	}
+
+	/* Build generic header portion */
+	info->priv[*offset + CS_ETM_MAGIC] = magic;
+	info->priv[*offset + CS_ETM_CPU] = cpu;
+	/* Where the next CPU entry should start from */
+	*offset += increment;
+}
+
+static int cs_etm_info_fill(struct auxtrace_record *itr,
+			    struct perf_session *session,
+			    struct auxtrace_info_event *info,
+			    size_t priv_size)
+{
+	int i;
+	u32 offset;
+	u64 nr_cpu, type;
+	const struct cpu_map *cpus = session->evlist->cpus;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	if (priv_size != cs_etm_info_priv_size(itr, session->evlist))
+		return -EINVAL;
+
+	if (!session->evlist->nr_mmaps)
+		return -EINVAL;
+
+	/* If the cpu_map is empty all CPUs are involved */
+	nr_cpu = cpu_map__empty(cpus) ? cpu__max_cpu() : cpu_map__nr(cpus);
+	/* Get PMU type as dynamically assigned by the core */
+	type = cs_etm_pmu->type;
+
+	/* First fill out the session header */
+	info->type = PERF_AUXTRACE_CS_ETM;
+	info->priv[CS_HEADER_VERSION_0] = 0;
+	info->priv[CS_PMU_TYPE_CPUS] = type << 32;
+	info->priv[CS_PMU_TYPE_CPUS] |= nr_cpu;
+	info->priv[CS_ETM_SNAPSHOT] = ptr->snapshot_mode;
+
+	offset = CS_ETM_SNAPSHOT + 1;
+
+	/* cpu map is not empty, we have specific CPUs to work with */
+	if (!cpu_map__empty(cpus)) {
+		for (i = 0; i < cpu_map__nr(cpus) && offset < priv_size; i++)
+			cs_etm_get_metadata(cpus->map[i], &offset, itr, info);
+	} else {
+		/* get configuration for all CPUs in the system */
+		for (i = 0; i < cpu__max_cpu(); i++)
+			cs_etm_get_metadata(i, &offset, itr, info);
+	}
+
+	return 0;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+				int idx, struct auxtrace_mmap *mm,
+				unsigned char *data __maybe_unused,
+				u64 *head, u64 *old)
+{
+	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
+
+	*old = *head;
+	*head += mm->len;
+
+	return 0;
+}
+
+static int cs_etm_snapshot_start(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->cs_etm_pmu->type)
+			return perf_evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int cs_etm_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->cs_etm_pmu->type)
+			return perf_evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return (((u64) rand() <<  0) & 0x00000000FFFFFFFFull) |
+		(((u64) rand() << 32) & 0xFFFFFFFF00000000ull);
+}
+
+static void cs_etm_recording_free(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	free(ptr);
+}
+
+static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->cs_etm_pmu->type)
+			return perf_evlist__enable_event_idx(ptr->evlist,
+							     evsel, idx);
+	}
+
+	return -EINVAL;
+}
+
+struct auxtrace_record *cs_etm_record_init(int *err)
+{
+	struct perf_pmu *cs_etm_pmu;
+	struct cs_etm_recording *ptr;
+
+	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
+
+	if (!cs_etm_pmu) {
+		*err = -EINVAL;
+		goto out;
+	}
+
+	ptr = zalloc(sizeof(struct cs_etm_recording));
+	if (!ptr) {
+		*err = -ENOMEM;
+		goto out;
+	}
+
+	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
+	ptr->itr.recording_options	= cs_etm_recording_options;
+	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
+	ptr->itr.info_fill		= cs_etm_info_fill;
+	ptr->itr.find_snapshot		= cs_etm_find_snapshot;
+	ptr->itr.snapshot_start		= cs_etm_snapshot_start;
+	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
+	ptr->itr.reference		= cs_etm_reference;
+	ptr->itr.free			= cs_etm_recording_free;
+	ptr->itr.read_finish		= cs_etm_read_finish;
+
+	*err = 0;
+	return &ptr->itr;
+out:
+	return NULL;
+}
+
+static FILE *cs_device__open_file(const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s" CS_BUS_DEVICE_PATH "%s", sysfs, name);
+
+	printf("path: %s\n", path);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	return fopen(path, "w");
+
+}
+
+static __attribute__((format(printf, 2, 3)))
+int cs_device__print_file(const char *name, const char *fmt, ...)
+{
+	va_list args;
+	FILE *file;
+	int ret = -EINVAL;
+
+	va_start(args, fmt);
+	file = cs_device__open_file(name);
+	if (file) {
+		ret = vfprintf(file, fmt, args);
+		fclose(file);
+	}
+	va_end(args);
+	return ret;
+}
+
+int cs_etm_set_drv_config(struct perf_evsel_config_term *term)
+{
+	int ret;
+	char enable_sink[ENABLE_SINK_MAX];
+
+	snprintf(enable_sink, ENABLE_SINK_MAX, "%s/%s",
+		 term->val.drv_cfg, "enable_sink");
+
+	ret = cs_device__print_file(enable_sink, "%d", 1);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h
new file mode 100644
index 000000000000..5256741be549
--- /dev/null
+++ b/tools/perf/arch/arm/util/cs-etm.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef INCLUDE__PERF_CS_ETM_H__
+#define INCLUDE__PERF_CS_ETM_H__
+
+#include "../../util/evsel.h"
+
+struct auxtrace_record *cs_etm_record_init(int *err);
+int cs_etm_set_drv_config(struct perf_evsel_config_term *term);
+
+#endif
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
new file mode 100644
index 000000000000..98d67399a0d6
--- /dev/null
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -0,0 +1,36 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <string.h>
+#include <linux/coresight-pmu.h>
+#include <linux/perf_event.h>
+
+#include "cs-etm.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr
+*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+	if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
+		/* add ETM default config here */
+		pmu->selectable = true;
+		pmu->set_drv_config = cs_etm_set_drv_config;
+	}
+#endif
+	return NULL;
+}
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..26759363f921
--- /dev/null
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -0,0 +1,13 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const aarch64_regstr_tbl[] = {
+	"%r0", "%r1", "%r2", "%r3", "%r4",
+	"%r5", "%r6", "%r7", "%r8", "%r9",
+	"%r10", "%r11", "%r12", "%r13", "%r14",
+	"%r15", "%r16", "%r17", "%r18", "%r19",
+	"%r20", "%r21", "%r22", "%r23", "%r24",
+	"%r25", "%r26", "%r27", "%r28", "%r29",
+	"%lr", "%sp",
+};
+#endif
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 02f41dba4f4f..cef6fb38d17e 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,2 +1,6 @@
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+
+libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
+			      ../../arm/util/auxtrace.o \
+			      ../../arm/util/cs-etm.o
diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build
index 54afe4a467e7..db52fa22d3a1 100644
--- a/tools/perf/arch/powerpc/Build
+++ b/tools/perf/arch/powerpc/Build
@@ -1 +1,2 @@
 libperf-y += util/
+libperf-y += tests/
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
new file mode 100644
index 000000000000..84d8dedef2ed
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -0,0 +1,13 @@
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/powerpc/include/dwarf-regs-table.h b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..db4730f5585c
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
@@ -0,0 +1,27 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+/*
+ * Reference:
+ * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html
+ * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf
+ */
+#define REG_DWARFNUM_NAME(reg, idx)	[idx] = "%" #reg
+
+static const char * const powerpc_regstr_tbl[] = {
+	"%gpr0", "%gpr1", "%gpr2", "%gpr3", "%gpr4",
+	"%gpr5", "%gpr6", "%gpr7", "%gpr8", "%gpr9",
+	"%gpr10", "%gpr11", "%gpr12", "%gpr13", "%gpr14",
+	"%gpr15", "%gpr16", "%gpr17", "%gpr18", "%gpr19",
+	"%gpr20", "%gpr21", "%gpr22", "%gpr23", "%gpr24",
+	"%gpr25", "%gpr26", "%gpr27", "%gpr28", "%gpr29",
+	"%gpr30", "%gpr31",
+	REG_DWARFNUM_NAME(msr,   66),
+	REG_DWARFNUM_NAME(ctr,   109),
+	REG_DWARFNUM_NAME(link,  108),
+	REG_DWARFNUM_NAME(xer,   101),
+	REG_DWARFNUM_NAME(dar,   119),
+	REG_DWARFNUM_NAME(dsisr, 118),
+};
+
+#endif
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 75de0e92e71e..c12f4e804f66 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -5,6 +5,8 @@
 #include <linux/types.h>
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #define PERF_REGS_MASK  ((1ULL << PERF_REG_POWERPC_MAX) - 1)
 #define PERF_REGS_MAX   PERF_REG_POWERPC_MAX
 #ifdef __powerpc64__
diff --git a/tools/perf/arch/powerpc/tests/Build b/tools/perf/arch/powerpc/tests/Build
new file mode 100644
index 000000000000..d827ef384b33
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/Build
@@ -0,0 +1,4 @@
+libperf-$(CONFIG_DWARF_UNWIND) += regs_load.o
+libperf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c
new file mode 100644
index 000000000000..e24f46241f40
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/arch-tests.c
@@ -0,0 +1,15 @@
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..0bac3137ccbd
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -0,0 +1,62 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/powerpc/tests/regs_load.S b/tools/perf/arch/powerpc/tests/regs_load.S
new file mode 100644
index 000000000000..d76c9a32f327
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/regs_load.S
@@ -0,0 +1,94 @@
+#include <linux/linkage.h>
+
+/* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */
+#define R0	 0
+#define R1	 1 * 8
+#define R2	 2 * 8
+#define R3	 3 * 8
+#define R4	 4 * 8
+#define R5	 5 * 8
+#define R6	 6 * 8
+#define R7	 7 * 8
+#define R8	 8 * 8
+#define R9	 9 * 8
+#define R10	10 * 8
+#define R11	11 * 8
+#define R12	12 * 8
+#define R13	13 * 8
+#define R14	14 * 8
+#define R15	15 * 8
+#define R16	16 * 8
+#define R17	17 * 8
+#define R18	18 * 8
+#define R19	19 * 8
+#define R20	20 * 8
+#define R21	21 * 8
+#define R22	22 * 8
+#define R23	23 * 8
+#define R24	24 * 8
+#define R25	25 * 8
+#define R26	26 * 8
+#define R27	27 * 8
+#define R28	28 * 8
+#define R29	29 * 8
+#define R30	30 * 8
+#define R31	31 * 8
+#define NIP	32 * 8
+#define CTR	35 * 8
+#define LINK	36 * 8
+#define XER	37 * 8
+
+.globl perf_regs_load
+perf_regs_load:
+	std 0, R0(3)
+	std 1, R1(3)
+	std 2, R2(3)
+	std 3, R3(3)
+	std 4, R4(3)
+	std 5, R5(3)
+	std 6, R6(3)
+	std 7, R7(3)
+	std 8, R8(3)
+	std 9, R9(3)
+	std 10, R10(3)
+	std 11, R11(3)
+	std 12, R12(3)
+	std 13, R13(3)
+	std 14, R14(3)
+	std 15, R15(3)
+	std 16, R16(3)
+	std 17, R17(3)
+	std 18, R18(3)
+	std 19, R19(3)
+	std 20, R20(3)
+	std 21, R21(3)
+	std 22, R22(3)
+	std 23, R23(3)
+	std 24, R24(3)
+	std 25, R25(3)
+	std 26, R26(3)
+	std 27, R27(3)
+	std 28, R28(3)
+	std 29, R29(3)
+	std 30, R30(3)
+	std 31, R31(3)
+
+	/* store NIP */
+	mflr 4
+	std 4, NIP(3)
+
+	/* Store LR */
+	std 4, LINK(3)
+
+	/* Store XER */
+	mfxer 4
+	std 4, XER(3)
+
+	/* Store CTR */
+	mfctr 4
+	std 4, CTR(3)
+
+	/* Restore original value of r4 */
+	ld 4, R4(3)
+
+	blr
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 35745a733100..ed9d5d15d5b6 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -108,7 +108,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 	int i = 0;
 
 	map = get_target_map(pev->target, pev->uprobes);
-	if (!map || map__load(map, NULL) < 0)
+	if (!map || map__load(map) < 0)
 		return;
 
 	for (i = 0; i < ntevs; i++) {
diff --git a/tools/perf/arch/s390/include/dwarf-regs-table.h b/tools/perf/arch/s390/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..9da74a933bd6
--- /dev/null
+++ b/tools/perf/arch/s390/include/dwarf-regs-table.h
@@ -0,0 +1,8 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const s390_regstr_tbl[] = {
+	"%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
+	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+};
+#endif
diff --git a/tools/perf/arch/sh/include/dwarf-regs-table.h b/tools/perf/arch/sh/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..3a2deaf3dab4
--- /dev/null
+++ b/tools/perf/arch/sh/include/dwarf-regs-table.h
@@ -0,0 +1,25 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+const char * const sh_regstr_tbl[] = {
+	"r0",
+	"r1",
+	"r2",
+	"r3",
+	"r4",
+	"r5",
+	"r6",
+	"r7",
+	"r8",
+	"r9",
+	"r10",
+	"r11",
+	"r12",
+	"r13",
+	"r14",
+	"r15",
+	"pc",
+	"pr",
+};
+
+#endif
diff --git a/tools/perf/arch/sparc/include/dwarf-regs-table.h b/tools/perf/arch/sparc/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..12c07619002c
--- /dev/null
+++ b/tools/perf/arch/sparc/include/dwarf-regs-table.h
@@ -0,0 +1,18 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const sparc_regstr_tbl[] = {
+	"%g0", "%g1", "%g2", "%g3", "%g4", "%g5", "%g6", "%g7",
+	"%o0", "%o1", "%o2", "%o3", "%o4", "%o5", "%sp", "%o7",
+	"%l0", "%l1", "%l2", "%l3", "%l4", "%l5", "%l6", "%l7",
+	"%i0", "%i1", "%i2", "%i3", "%i4", "%i5", "%fp", "%i7",
+	"%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
+	"%f8", "%f9", "%f10", "%f11", "%f12", "%f13", "%f14", "%f15",
+	"%f16", "%f17", "%f18", "%f19", "%f20", "%f21", "%f22", "%f23",
+	"%f24", "%f25", "%f26", "%f27", "%f28", "%f29", "%f30", "%f31",
+	"%f32", "%f33", "%f34", "%f35", "%f36", "%f37", "%f38", "%f39",
+	"%f40", "%f41", "%f42", "%f43", "%f44", "%f45", "%f46", "%f47",
+	"%f48", "%f49", "%f50", "%f51", "%f52", "%f53", "%f54", "%f55",
+	"%f56", "%f57", "%f58", "%f59", "%f60", "%f61", "%f62", "%f63",
+};
+#endif
diff --git a/tools/perf/arch/x86/include/dwarf-regs-table.h b/tools/perf/arch/x86/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..9b5e5cbb4209
--- /dev/null
+++ b/tools/perf/arch/x86/include/dwarf-regs-table.h
@@ -0,0 +1,14 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const x86_32_regstr_tbl[] = {
+	"%ax", "%cx", "%dx", "%bx", "$stack",/* Stack address instead of %sp */
+	"%bp", "%si", "%di",
+};
+
+static const char * const x86_64_regstr_tbl[] = {
+	"%ax", "%dx", "%cx", "%bx", "%si", "%di",
+	"%bp", "%sp", "%r8", "%r9", "%r10", "%r11",
+	"%r12", "%r13", "%r14", "%r15",
+};
+#endif
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a2412e9d883b..90fa2286edcf 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -62,6 +62,7 @@ struct intel_pt_recording {
 	size_t				snapshot_ref_buf_size;
 	int				snapshot_ref_cnt;
 	struct intel_pt_snapshot_ref	*snapshot_refs;
+	size_t				priv_size;
 };
 
 static int intel_pt_parse_terms_with_default(struct list_head *formats,
@@ -273,11 +274,37 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
 	return attr;
 }
 
+static const char *intel_pt_find_filter(struct perf_evlist *evlist,
+					struct perf_pmu *intel_pt_pmu)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == intel_pt_pmu->type)
+			return evsel->filter;
+	}
+
+	return NULL;
+}
+
+static size_t intel_pt_filter_bytes(const char *filter)
+{
+	size_t len = filter ? strlen(filter) : 0;
+
+	return len ? roundup(len + 1, 8) : 0;
+}
+
 static size_t
-intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
-			struct perf_evlist *evlist __maybe_unused)
+intel_pt_info_priv_size(struct auxtrace_record *itr, struct perf_evlist *evlist)
 {
-	return INTEL_PT_AUXTRACE_PRIV_SIZE;
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	const char *filter = intel_pt_find_filter(evlist, ptr->intel_pt_pmu);
+
+	ptr->priv_size = (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64)) +
+			 intel_pt_filter_bytes(filter);
+
+	return ptr->priv_size;
 }
 
 static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d)
@@ -302,9 +329,13 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	bool cap_user_time_zero = false, per_cpu_mmaps;
 	u64 tsc_bit, mtc_bit, mtc_freq_bits, cyc_bit, noretcomp_bit;
 	u32 tsc_ctc_ratio_n, tsc_ctc_ratio_d;
+	unsigned long max_non_turbo_ratio;
+	size_t filter_str_len;
+	const char *filter;
+	u64 *info;
 	int err;
 
-	if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE)
+	if (priv_size != ptr->priv_size)
 		return -EINVAL;
 
 	intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
@@ -317,6 +348,13 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 
 	intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);
 
+	if (perf_pmu__scan_file(intel_pt_pmu, "max_nonturbo_ratio",
+				"%lu", &max_non_turbo_ratio) != 1)
+		max_non_turbo_ratio = 0;
+
+	filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu);
+	filter_str_len = filter ? strlen(filter) : 0;
+
 	if (!session->evlist->nr_mmaps)
 		return -EINVAL;
 
@@ -351,6 +389,17 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	auxtrace_info->priv[INTEL_PT_TSC_CTC_N] = tsc_ctc_ratio_n;
 	auxtrace_info->priv[INTEL_PT_TSC_CTC_D] = tsc_ctc_ratio_d;
 	auxtrace_info->priv[INTEL_PT_CYC_BIT] = cyc_bit;
+	auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO] = max_non_turbo_ratio;
+	auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] = filter_str_len;
+
+	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
+
+	if (filter_str_len) {
+		size_t len = intel_pt_filter_bytes(filter);
+
+		strncpy((char *)info, filter, len);
+		info += len >> 3;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/arch/xtensa/include/dwarf-regs-table.h b/tools/perf/arch/xtensa/include/dwarf-regs-table.h
new file mode 100644
index 000000000000..aa0444a33fe6
--- /dev/null
+++ b/tools/perf/arch/xtensa/include/dwarf-regs-table.h
@@ -0,0 +1,8 @@
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const xtensa_regstr_tbl[] = {
+	"a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
+	"a8", "a9", "a10", "a11", "a12", "a13", "a14", "a15",
+};
+#endif
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index f96e22ed9f87..2b9705a8734c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -16,6 +16,7 @@
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/time64.h>
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
@@ -62,7 +63,7 @@ static void print_summary(void)
 	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
 	       requeued_avg,
 	       nthreads,
-	       requeuetime_avg/1e3,
+	       requeuetime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
 }
 
@@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		if (!silent) {
 			printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
-			       j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
+			       j + 1, nrequeued, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 4a2ecd7438ca..2c8fa67ad537 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -15,6 +15,7 @@
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/time64.h>
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
@@ -156,7 +157,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
 
 	printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
 	       "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
-	       nblocked_threads, waketime_avg/1e3,
+	       nblocked_threads, waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
 
@@ -172,7 +173,7 @@ static void print_summary(void)
 	printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
 	       wakeup_avg,
 	       nblocked_threads,
-	       waketime_avg/1e3,
+	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 87d8f4f292d9..e246b1b8388a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -16,6 +16,7 @@
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/time64.h>
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
@@ -81,7 +82,7 @@ static void print_summary(void)
 	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
 	       wakeup_avg,
 	       nthreads,
-	       waketime_avg/1e3,
+	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
 }
 
@@ -182,7 +183,7 @@ int bench_futex_wake(int argc, const char **argv,
 
 		if (!silent) {
 			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
-			       j + 1, nwoken, nthreads, runtime.tv_usec/1e3);
+			       j + 1, nwoken, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
 		}
 
 		for (i = 0; i < nthreads; i++) {
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 2b54d0f2672a..c684910e5a48 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -21,6 +21,7 @@
 #include <string.h>
 #include <sys/time.h>
 #include <errno.h>
+#include <linux/time64.h>
 
 #define K 1024
 
@@ -89,7 +90,7 @@ static u64 get_cycles(void)
 
 static double timeval2double(struct timeval *ts)
 {
-	return (double)ts->tv_sec + (double)ts->tv_usec / (double)1000000;
+	return (double)ts->tv_sec + (double)ts->tv_usec / (double)USEC_PER_SEC;
 }
 
 #define print_bps(x) do {						\
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index f7f530081aa9..8efe904e486b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -30,6 +30,7 @@
 #include <sys/wait.h>
 #include <sys/prctl.h>
 #include <sys/types.h>
+#include <linux/time64.h>
 
 #include <numa.h>
 #include <numaif.h>
@@ -1004,7 +1005,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	if (strong && process_groups == g->p.nr_proc) {
 		if (!*convergence) {
 			*convergence = runtime_ns_max;
-			tprintf(" (%6.1fs converged)\n", *convergence/1e9);
+			tprintf(" (%6.1fs converged)\n", *convergence / NSEC_PER_SEC);
 			if (g->p.measure_convergence) {
 				g->all_converged = true;
 				g->stop_work = true;
@@ -1012,7 +1013,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 		}
 	} else {
 		if (*convergence) {
-			tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9);
+			tprintf(" (%6.1fs de-converged)", runtime_ns_max / NSEC_PER_SEC);
 			*convergence = 0;
 		}
 		tprintf("\n");
@@ -1022,7 +1023,7 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 static void show_summary(double runtime_ns_max, int l, double *convergence)
 {
 	tprintf("\r #  %5.1f%%  [%.1f mins]",
-		(double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0);
+		(double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max / NSEC_PER_SEC / 60.0);
 
 	calc_convergence(runtime_ns_max, convergence);
 
@@ -1179,8 +1180,8 @@ static void *worker_thread(void *__tdata)
 
 		if (details >= 3) {
 			timersub(&stop, &start, &diff);
-			runtime_ns_max = diff.tv_sec * 1000000000;
-			runtime_ns_max += diff.tv_usec * 1000;
+			runtime_ns_max = diff.tv_sec * NSEC_PER_SEC;
+			runtime_ns_max += diff.tv_usec * NSEC_PER_USEC;
 
 			if (details >= 0) {
 				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
@@ -1192,23 +1193,23 @@ static void *worker_thread(void *__tdata)
 			continue;
 
 		timersub(&stop, &start0, &diff);
-		runtime_ns_max = diff.tv_sec * 1000000000ULL;
-		runtime_ns_max += diff.tv_usec * 1000ULL;
+		runtime_ns_max = diff.tv_sec * NSEC_PER_SEC;
+		runtime_ns_max += diff.tv_usec * NSEC_PER_USEC;
 
 		show_summary(runtime_ns_max, l, &convergence);
 	}
 
 	gettimeofday(&stop, NULL);
 	timersub(&stop, &start0, &diff);
-	td->runtime_ns = diff.tv_sec * 1000000000ULL;
-	td->runtime_ns += diff.tv_usec * 1000ULL;
-	td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9;
+	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
+	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
+	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
 
 	getrusage(RUSAGE_THREAD, &rusage);
-	td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL;
-	td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL;
-	td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL;
-	td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL;
+	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
+	td->system_time_ns += rusage.ru_stime.tv_usec * NSEC_PER_USEC;
+	td->user_time_ns = rusage.ru_utime.tv_sec * NSEC_PER_SEC;
+	td->user_time_ns += rusage.ru_utime.tv_usec * NSEC_PER_USEC;
 
 	free_data(thread_data, g->p.bytes_thread);
 
@@ -1469,7 +1470,7 @@ static int __bench_numa(const char *name)
 	}
 	/* Wait for all the threads to start up: */
 	while (g->nr_tasks_started != g->p.nr_tasks)
-		usleep(1000);
+		usleep(USEC_PER_MSEC);
 
 	BUG_ON(g->nr_tasks_started != g->p.nr_tasks);
 
@@ -1488,9 +1489,9 @@ static int __bench_numa(const char *name)
 
 		timersub(&stop, &start, &diff);
 
-		startup_sec = diff.tv_sec * 1000000000.0;
-		startup_sec += diff.tv_usec * 1000.0;
-		startup_sec /= 1e9;
+		startup_sec = diff.tv_sec * NSEC_PER_SEC;
+		startup_sec += diff.tv_usec * NSEC_PER_USEC;
+		startup_sec /= NSEC_PER_SEC;
 
 		tprintf(" threads initialized in %.6f seconds.\n", startup_sec);
 		tprintf(" #\n");
@@ -1529,14 +1530,14 @@ static int __bench_numa(const char *name)
 	tprintf("\n ###\n");
 	tprintf("\n");
 
-	runtime_sec_max = diff.tv_sec * 1000000000.0;
-	runtime_sec_max += diff.tv_usec * 1000.0;
-	runtime_sec_max /= 1e9;
+	runtime_sec_max = diff.tv_sec * NSEC_PER_SEC;
+	runtime_sec_max += diff.tv_usec * NSEC_PER_USEC;
+	runtime_sec_max /= NSEC_PER_SEC;
 
-	runtime_sec_min = runtime_ns_min/1e9;
+	runtime_sec_min = runtime_ns_min / NSEC_PER_SEC;
 
 	bytes = g->bytes_done;
-	runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9;
+	runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / NSEC_PER_SEC;
 
 	if (g->p.measure_convergence) {
 		print_res(name, runtime_sec_max,
@@ -1562,7 +1563,7 @@ static int __bench_numa(const char *name)
 	print_res(name, bytes / 1e9,
 		"GB,", "data-total",		"GB data processed, total");
 
-	print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks),
+	print_res(name, runtime_sec_max * NSEC_PER_SEC / (bytes / g->p.nr_tasks),
 		"nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime");
 
 	print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max,
@@ -1581,9 +1582,9 @@ static int __bench_numa(const char *name)
 				snprintf(tname, 32, "process%d:thread%d", p, t);
 				print_res(tname, td->speed_gbs,
 					"GB/sec",	"thread-speed", "GB/sec/thread speed");
-				print_res(tname, td->system_time_ns / 1e9,
+				print_res(tname, td->system_time_ns / NSEC_PER_SEC,
 					"secs",	"thread-system-time", "system CPU time/thread");
-				print_res(tname, td->user_time_ns / 1e9,
+				print_res(tname, td->user_time_ns / NSEC_PER_SEC,
 					"secs",	"thread-user-time", "user CPU time/thread");
 			}
 		}
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index bfaf9503de8e..6a111e775210 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -29,6 +29,7 @@
 #include <poll.h>
 #include <limits.h>
 #include <err.h>
+#include <linux/time64.h>
 
 #define DATASIZE 100
 
@@ -312,11 +313,11 @@ int bench_sched_messaging(int argc, const char **argv,
 		       thread_mode ? "threads" : "processes");
 		printf(" %14s: %lu.%03lu [sec]\n", "Total time",
 		       diff.tv_sec,
-		       (unsigned long) (diff.tv_usec/1000));
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n", diff.tv_sec,
-		       (unsigned long) (diff.tv_usec/1000));
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 	default:
 		/* reaching here is something disaster */
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 1dc2d13cc272..2243f0150d76 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -25,6 +25,7 @@
 #include <sys/time.h>
 #include <sys/types.h>
 #include <sys/syscall.h>
+#include <linux/time64.h>
 
 #include <pthread.h>
 
@@ -153,24 +154,24 @@ int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unu
 		printf("# Executed %d pipe operations between two %s\n\n",
 			loops, threaded ? "threads" : "processes");
 
-		result_usec = diff.tv_sec * 1000000;
+		result_usec = diff.tv_sec * USEC_PER_SEC;
 		result_usec += diff.tv_usec;
 
 		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
 		       diff.tv_sec,
-		       (unsigned long) (diff.tv_usec/1000));
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 
 		printf(" %14lf usecs/op\n",
 		       (double)result_usec / (double)loops);
 		printf(" %14d ops/sec\n",
 		       (int)((double)loops /
-			     ((double)result_usec / (double)1000000)));
+			     ((double)result_usec / (double)USEC_PER_SEC)));
 		break;
 
 	case BENCH_FORMAT_SIMPLE:
 		printf("%lu.%03lu\n",
 		       diff.tv_sec,
-		       (unsigned long) (diff.tv_usec / 1000));
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
 		break;
 
 	default:
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 9c1034d81b4f..ebb628332a6e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -30,6 +30,7 @@
 #include "util/tool.h"
 #include "util/data.h"
 #include "arch/common.h"
+#include "util/block-range.h"
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
@@ -46,6 +47,103 @@ struct perf_annotate {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+/*
+ * Given one basic block:
+ *
+ *	from	to		branch_i
+ *	* ----> *
+ *		|
+ *		| block
+ *		v
+ *		* ----> *
+ *		from	to	branch_i+1
+ *
+ * where the horizontal are the branches and the vertical is the executed
+ * block of instructions.
+ *
+ * We count, for each 'instruction', the number of blocks that covered it as
+ * well as count the ratio each branch is taken.
+ *
+ * We can do this without knowing the actual instruction stream by keeping
+ * track of the address ranges. We break down ranges such that there is no
+ * overlap and iterate from the start until the end.
+ *
+ * @acme: once we parse the objdump output _before_ processing the samples,
+ * we can easily fold the branch.cycles IPC bits in.
+ */
+static void process_basic_block(struct addr_map_symbol *start,
+				struct addr_map_symbol *end,
+				struct branch_flags *flags)
+{
+	struct symbol *sym = start->sym;
+	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
+	struct block_range_iter iter;
+	struct block_range *entry;
+
+	/*
+	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
+	 */
+	if (!start->addr || start->addr > end->addr)
+		return;
+
+	iter = block_range__create(start->addr, end->addr);
+	if (!block_range_iter__valid(&iter))
+		return;
+
+	/*
+	 * First block in range is a branch target.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_target);
+	entry->entry++;
+
+	do {
+		entry = block_range_iter(&iter);
+
+		entry->coverage++;
+		entry->sym = sym;
+
+		if (notes)
+			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+
+	} while (block_range_iter__next(&iter));
+
+	/*
+	 * Last block in rage is a branch.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_branch);
+	entry->taken++;
+	if (flags->predicted)
+		entry->pred++;
+}
+
+static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
+				 struct perf_sample *sample)
+{
+	struct addr_map_symbol *prev = NULL;
+	struct branch_info *bi;
+	int i;
+
+	if (!bs || !bs->nr)
+		return;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return;
+
+	for (i = bs->nr - 1; i >= 0; i--) {
+		/*
+		 * XXX filter against symbol
+		 */
+		if (prev)
+			process_basic_block(prev, &bi[i].from, &bi[i].flags);
+		prev = &bi[i].to;
+	}
+
+	free(bi);
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
@@ -72,6 +170,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	/*
+	 * XXX filtered samples can still have branch entires pointing into our
+	 * symbol and are missed.
+	 */
+	process_branch_stack(sample->branch_stack, al, sample);
+
 	sample->period = 1;
 	sample->weight = 1;
 
@@ -204,8 +308,6 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	struct perf_evsel *pos;
 	u64 total_nr_samples;
 
-	machines__set_symbol_filter(&session->machines, symbol__annotate_init);
-
 	if (ann->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
 					       ann->cpu_bitmap);
@@ -367,7 +469,10 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (annotate.session == NULL)
 		return -1;
 
-	symbol_conf.priv_size = sizeof(struct annotation);
+	ret = symbol__annotation_init();
+	if (ret < 0)
+		goto out_delete;
+
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 21ee753211ad..9ff0db4e2d0c 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1033,7 +1033,9 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 }
 
 static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		       struct hists *hists __maybe_unused)
+		       struct hists *hists __maybe_unused,
+		       int line __maybe_unused,
+		       int *span __maybe_unused)
 {
 	struct diff_hpp_fmt *dfmt =
 		container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 73c1c4cc3600..b9bc7e39833a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -429,7 +429,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
 			al.map->dso->hit = 1;
-			if (map__load(al.map, NULL) >= 0) {
+			if (map__load(al.map) >= 0) {
 				dso__inject_build_id(al.map->dso, tool, machine);
 				/*
 				 * If this fails, too bad, let the other side
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fdde1bd3e306..d426dcb18ce9 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -330,7 +330,7 @@ static int build_alloc_func_list(void)
 	}
 
 	kernel_map = machine__kernel_map(machine);
-	if (map__load(kernel_map, NULL) < 0) {
+	if (map__load(kernel_map) < 0) {
 		pr_err("cannot load kernel map\n");
 		return -ENOENT;
 	}
@@ -979,7 +979,7 @@ static void __print_slab_result(struct rb_root *root,
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = machine__find_kernel_function(machine, addr, &map, NULL);
+				sym = machine__find_kernel_function(machine, addr, &map);
 		} else
 			addr = data->ptr;
 
@@ -1043,8 +1043,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite,
-						    &map, NULL);
+		sym = machine__find_kernel_function(machine, data->callsite, &map);
 		if (sym && sym->name)
 			caller = sym->name;
 		else
@@ -1086,8 +1085,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite,
-						    &map, NULL);
+		sym = machine__find_kernel_function(machine, data->callsite, &map);
 		if (sym && sym->name)
 			caller = sym->name;
 		else
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 5e2127e04f83..08fa88f62a24 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -24,6 +24,7 @@
 #include <sys/timerfd.h>
 #endif
 
+#include <linux/time64.h>
 #include <termios.h>
 #include <semaphore.h>
 #include <pthread.h>
@@ -362,7 +363,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 		if (!skip_event(decode)) {
 			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
 				 sample->time, sample->pid, vcpu_record->vcpu_id,
-				 decode, time_diff/1000);
+				 decode, time_diff / NSEC_PER_USEC);
 		}
 	}
 
@@ -608,15 +609,15 @@ static void print_result(struct perf_kvm_stat *kvm)
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
-		pr_info("%9.2fus ", (double)min / 1e3);
-		pr_info("%9.2fus ", (double)max / 1e3);
-		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
+		pr_info("%9.2fus ", (double)min / NSEC_PER_USEC);
+		pr_info("%9.2fus ", (double)max / NSEC_PER_USEC);
+		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount / NSEC_PER_USEC,
 			kvm_event_rel_stddev(vcpu, event));
 		pr_info("\n");
 	}
 
 	pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
-		kvm->total_count, kvm->total_time / 1e3);
+		kvm->total_count, kvm->total_time / (double)NSEC_PER_USEC);
 
 	if (kvm->lost_events)
 		pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index ee5b42173ba3..f87996b0cb29 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -326,6 +326,11 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs)
 	if (ret < 0)
 		goto out_cleanup;
 
+	if (params.command == 'D') {	/* it shows definition */
+		ret = show_probe_trace_events(pevs, npevs);
+		goto out_cleanup;
+	}
+
 	ret = apply_perf_probe_events(pevs, npevs);
 	if (ret < 0)
 		goto out_cleanup;
@@ -454,6 +459,14 @@ out:
 	return ret;
 }
 
+#ifdef HAVE_DWARF_SUPPORT
+#define PROBEDEF_STR	\
+	"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT [[NAME=]ARG ...]"
+#else
+#define PROBEDEF_STR	"[EVENT=]FUNC[+OFF|%return] [[NAME=]ARG ...]"
+#endif
+
+
 static int
 __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -479,13 +492,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			     opt_set_filter_with_command, DEFAULT_LIST_FILTER),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
 		     opt_set_filter_with_command),
-	OPT_CALLBACK('a', "add", NULL,
-#ifdef HAVE_DWARF_SUPPORT
-		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
-		" [[NAME=]ARG ...]",
-#else
-		"[EVENT=]FUNC[+OFF|%return] [[NAME=]ARG ...]",
-#endif
+	OPT_CALLBACK('a', "add", NULL, PROBEDEF_STR,
 		"probe point definition, where\n"
 		"\t\tGROUP:\tGroup name (optional)\n"
 		"\t\tEVENT:\tEvent name\n"
@@ -503,6 +510,9 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
 #endif
 		opt_add_probe_event),
+	OPT_CALLBACK('D', "definition", NULL, PROBEDEF_STR,
+		"Show trace event definition of given traceevent for k/uprobe_events.",
+		opt_add_probe_event),
 	OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
 		    " with existing name"),
 	OPT_CALLBACK('L', "line", NULL,
@@ -548,6 +558,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'D', "definition", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE);
 #ifdef HAVE_DWARF_SUPPORT
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
@@ -600,6 +611,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	 */
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
+	/*
+	 * Except for --list, --del and --add, other command doesn't depend
+	 * nor change running kernel. So if user gives offline vmlinux,
+	 * ignore its buildid.
+	 */
+	if (!strchr("lda", params.command) && symbol_conf.vmlinux_name)
+		symbol_conf.ignore_vmlinux_buildid = true;
+
 	switch (params.command) {
 	case 'l':
 		if (params.uprobes) {
@@ -643,7 +662,9 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			return ret;
 		}
 		break;
+	case 'D':
 	case 'a':
+
 		/* Ensure the last given target is used */
 		if (params.target && !params.target_used) {
 			pr_err("  Error: -x/-m must follow the probe definitions.\n");
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6355902fbfc8..67d2a9003294 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -22,6 +22,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/drv_configs.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"
@@ -42,7 +43,7 @@
 #include <sched.h>
 #include <sys/mman.h>
 #include <asm/bug.h>
-
+#include <linux/time64.h>
 
 struct record {
 	struct perf_tool	tool;
@@ -96,7 +97,7 @@ backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 	*start = head;
 	while (true) {
 		if (evt_head - head >= (unsigned int)size) {
-			pr_debug("Finshed reading backward ring buffer: rewind\n");
+			pr_debug("Finished reading backward ring buffer: rewind\n");
 			if (evt_head - head > (unsigned int)size)
 				evt_head -= pheader->size;
 			*end = evt_head;
@@ -106,7 +107,7 @@ backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
 
 		if (pheader->size == 0) {
-			pr_debug("Finshed reading backward ring buffer: get start\n");
+			pr_debug("Finished reading backward ring buffer: get start\n");
 			*end = evt_head;
 			return 0;
 		}
@@ -383,6 +384,7 @@ static int record__open(struct record *rec)
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
 	struct record_opts *opts = &rec->opts;
+	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
 	perf_evlist__config(evlist, opts, &callchain_param);
@@ -412,6 +414,14 @@ try_again:
 		goto out;
 	}
 
+	if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) {
+		error("failed to set config \"%s\" on event %s with %d (%s)\n",
+		      err_term->val.drv_cfg, perf_evsel__name(pos), errno,
+		      str_error_r(errno, msg, sizeof(msg)));
+		rc = -1;
+		goto out;
+	}
+
 	rc = record__mmap(rec);
 	if (rc)
 		goto out;
@@ -954,7 +964,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	if (opts->initial_delay) {
-		usleep(opts->initial_delay * 1000);
+		usleep(opts->initial_delay * USEC_PER_MSEC);
 		perf_evlist__enable(rec->evlist);
 	}
 
@@ -1563,29 +1573,39 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
 					      rec->opts.auxtrace_snapshot_opts);
 	if (err)
-		return err;
+		goto out;
+
+	/*
+	 * Allow aliases to facilitate the lookup of symbols for address
+	 * filters. Refer to auxtrace_parse_filters().
+	 */
+	symbol_conf.allow_aliases = true;
+
+	symbol__init(NULL);
+
+	err = auxtrace_parse_filters(rec->evlist);
+	if (err)
+		goto out;
 
 	if (dry_run)
-		return 0;
+		goto out;
 
 	err = bpf__setup_stdout(rec->evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
 		pr_err("ERROR: Setup BPF stdout failed: %s\n",
 			 errbuf);
-		return err;
+		goto out;
 	}
 
 	err = -ENOMEM;
 
-	symbol__init(NULL);
-
 	if (symbol_conf.kptr_restrict)
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
@@ -1633,7 +1653,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (rec->evlist->nr_entries == 0 &&
 	    perf_evlist__add_default(rec->evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
@@ -1653,7 +1673,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		ui__error("%s", errbuf);
 
 		err = -saved_errno;
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	err = -ENOMEM;
@@ -1662,7 +1682,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
 	if (err)
-		goto out_symbol_exit;
+		goto out;
 
 	/*
 	 * We take all buildids when the file contains
@@ -1674,11 +1694,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	err = __cmd_record(&record, argc, argv);
-out_symbol_exit:
+out:
 	perf_evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 949e5a15c960..6e88460cd13d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -89,6 +89,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->queue_size = perf_config_u64(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "report.sort_order")) {
+		default_sort_order = strdup(value);
+		return 0;
+	}
 
 	return 0;
 }
@@ -931,7 +935,6 @@ repeat:
 
 	if (symbol_conf.report_hierarchy) {
 		/* disable incompatible options */
-		symbol_conf.event_group = false;
 		symbol_conf.cumulate_callchain = false;
 
 		if (field_order) {
@@ -980,9 +983,9 @@ repeat:
 	 * implementation.
 	 */
 	if (ui__has_annotation()) {
-		symbol_conf.priv_size = sizeof(struct annotation);
-		machines__set_symbol_filter(&session->machines,
-					    symbol__annotate_init);
+		ret = symbol__annotation_init();
+		if (ret < 0)
+			goto error;
 		/*
  		 * For searching by name on the "Browse map details".
  		 * providing it only in verbose mode not to bloat too
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0dfe8df2ab9b..f5503ca22e1c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -26,6 +26,7 @@
 #include <pthread.h>
 #include <math.h>
 #include <api/fs/fs.h>
+#include <linux/time64.h>
 
 #define PR_SET_NAME		15               /* Set process name */
 #define MAX_CPUS		4096
@@ -199,7 +200,7 @@ static u64 get_nsecs(void)
 
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 
-	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
+	return ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec;
 }
 
 static void burn_nsecs(struct perf_sched *sched, u64 nsecs)
@@ -223,7 +224,7 @@ static void sleep_nsecs(u64 nsecs)
 
 static void calibrate_run_measurement_overhead(struct perf_sched *sched)
 {
-	u64 T0, T1, delta, min_delta = 1000000000ULL;
+	u64 T0, T1, delta, min_delta = NSEC_PER_SEC;
 	int i;
 
 	for (i = 0; i < 10; i++) {
@@ -240,7 +241,7 @@ static void calibrate_run_measurement_overhead(struct perf_sched *sched)
 
 static void calibrate_sleep_measurement_overhead(struct perf_sched *sched)
 {
-	u64 T0, T1, delta, min_delta = 1000000000ULL;
+	u64 T0, T1, delta, min_delta = NSEC_PER_SEC;
 	int i;
 
 	for (i = 0; i < 10; i++) {
@@ -452,8 +453,8 @@ static u64 get_cpu_usage_nsec_parent(void)
 	err = getrusage(RUSAGE_SELF, &ru);
 	BUG_ON(err);
 
-	sum =  ru.ru_utime.tv_sec*1e9 + ru.ru_utime.tv_usec*1e3;
-	sum += ru.ru_stime.tv_sec*1e9 + ru.ru_stime.tv_usec*1e3;
+	sum =  ru.ru_utime.tv_sec * NSEC_PER_SEC + ru.ru_utime.tv_usec * NSEC_PER_USEC;
+	sum += ru.ru_stime.tv_sec * NSEC_PER_SEC + ru.ru_stime.tv_usec * NSEC_PER_USEC;
 
 	return sum;
 }
@@ -667,12 +668,12 @@ static void run_one_test(struct perf_sched *sched)
 		sched->run_avg = delta;
 	sched->run_avg = (sched->run_avg * (sched->replay_repeat - 1) + delta) / sched->replay_repeat;
 
-	printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0);
+	printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / NSEC_PER_MSEC);
 
-	printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6);
+	printf("ravg: %0.2f, ", (double)sched->run_avg / NSEC_PER_MSEC);
 
 	printf("cpu: %0.2f / %0.2f",
-		(double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6);
+		(double)sched->cpu_usage / NSEC_PER_MSEC, (double)sched->runavg_cpu_usage / NSEC_PER_MSEC);
 
 #if 0
 	/*
@@ -680,8 +681,8 @@ static void run_one_test(struct perf_sched *sched)
 	 * accurate than the sched->sum_exec_runtime based statistics:
 	 */
 	printf(" [%0.2f / %0.2f]",
-		(double)sched->parent_cpu_usage/1e6,
-		(double)sched->runavg_parent_cpu_usage/1e6);
+		(double)sched->parent_cpu_usage / NSEC_PER_MSEC,
+		(double)sched->runavg_parent_cpu_usage / NSEC_PER_MSEC);
 #endif
 
 	printf("\n");
@@ -696,13 +697,13 @@ static void test_calibrations(struct perf_sched *sched)
 	u64 T0, T1;
 
 	T0 = get_nsecs();
-	burn_nsecs(sched, 1e6);
+	burn_nsecs(sched, NSEC_PER_MSEC);
 	T1 = get_nsecs();
 
 	printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
 
 	T0 = get_nsecs();
-	sleep_nsecs(1e6);
+	sleep_nsecs(NSEC_PER_MSEC);
 	T1 = get_nsecs();
 
 	printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
@@ -1213,10 +1214,10 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	avg = work_list->total_lat / work_list->nb_atoms;
 
 	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n",
-	      (double)work_list->total_runtime / 1e6,
-		 work_list->nb_atoms, (double)avg / 1e6,
-		 (double)work_list->max_lat / 1e6,
-		 (double)work_list->max_lat_at / 1e9);
+	      (double)work_list->total_runtime / NSEC_PER_MSEC,
+		 work_list->nb_atoms, (double)avg / NSEC_PER_MSEC,
+		 (double)work_list->max_lat / NSEC_PER_MSEC,
+		 (double)work_list->max_lat_at / NSEC_PER_SEC);
 }
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
@@ -1491,7 +1492,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
 		goto out;
 
-	color_fprintf(stdout, color, "  %12.6f secs ", (double)timestamp/1e9);
+	color_fprintf(stdout, color, "  %12.6f secs ", (double)timestamp / NSEC_PER_SEC);
 	if (new_shortname) {
 		const char *pid_color = color;
 
@@ -1753,7 +1754,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 
 	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
-		(double)sched->all_runtime / 1e6, sched->all_count);
+		(double)sched->all_runtime / NSEC_PER_MSEC, sched->all_count);
 
 	printf(" ---------------------------------------------------\n");
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c859e59dfe3e..7228d141a789 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -24,6 +24,7 @@
 #include "util/thread-stack.h"
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
+#include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 
@@ -464,9 +465,9 @@ static void print_sample_start(struct perf_sample *sample,
 
 	if (PRINT_FIELD(TIME)) {
 		nsecs = sample->time;
-		secs = nsecs / NSECS_PER_SEC;
-		nsecs -= secs * NSECS_PER_SEC;
-		usecs = nsecs / NSECS_PER_USEC;
+		secs = nsecs / NSEC_PER_SEC;
+		nsecs -= secs * NSEC_PER_SEC;
+		usecs = nsecs / NSEC_PER_USEC;
 		if (nanosecs)
 			printf("%5lu.%09llu: ", secs, nsecs);
 		else
@@ -521,11 +522,11 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
 		if (alf.map)
-			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
+			alf.sym = map__find_symbol(alf.map, alf.addr);
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		if (alt.map)
-			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
+			alt.sym = map__find_symbol(alt.map, alt.addr);
 
 		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
 		putchar('/');
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3c7452b39f57..688dea7cb08f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -52,6 +52,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/drv_configs.h"
 #include "util/color.h"
 #include "util/stat.h"
 #include "util/header.h"
@@ -65,6 +66,7 @@
 #include "util/group.h"
 #include "asm/bug.h"
 
+#include <linux/time64.h>
 #include <api/fs/fs.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
@@ -172,7 +174,7 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 {
 	r->tv_sec = a->tv_sec - b->tv_sec;
 	if (a->tv_nsec < b->tv_nsec) {
-		r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
+		r->tv_nsec = a->tv_nsec + NSEC_PER_SEC - b->tv_nsec;
 		r->tv_sec--;
 	} else {
 		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
@@ -354,7 +356,7 @@ static void process_interval(void)
 	diff_timespec(&rs, &ts, &ref_time);
 
 	if (STAT_RECORD) {
-		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL))
+		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
 			pr_err("failed to write stat round event\n");
 	}
 
@@ -364,7 +366,7 @@ static void process_interval(void)
 static void enable_counters(void)
 {
 	if (initial_delay)
-		usleep(initial_delay * 1000);
+		usleep(initial_delay * USEC_PER_MSEC);
 
 	/*
 	 * We need to enable counters only if:
@@ -539,10 +541,11 @@ static int __run_perf_stat(int argc, const char **argv)
 	int status = 0;
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
+	struct perf_evsel_config_term *err_term;
 
 	if (interval) {
-		ts.tv_sec  = interval / 1000;
-		ts.tv_nsec = (interval % 1000) * 1000000;
+		ts.tv_sec  = interval / USEC_PER_MSEC;
+		ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
 	} else {
 		ts.tv_sec  = 1;
 		ts.tv_nsec = 0;
@@ -610,6 +613,13 @@ try_again:
 		return -1;
 	}
 
+	if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) {
+		error("failed to set config \"%s\" on event %s with %d (%s)\n",
+		      err_term->val.drv_cfg, perf_evsel__name(counter), errno,
+		      str_error_r(errno, msg, sizeof(msg)));
+		return -1;
+	}
+
 	if (STAT_RECORD) {
 		int err, fd = perf_data_file__fd(&perf_stat.file);
 
@@ -971,7 +981,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
-	double msecs = avg / 1e6;
+	double msecs = avg / NSEC_PER_MSEC;
 	const char *fmt_v, *fmt_n;
 	char name[25];
 
@@ -1460,7 +1470,7 @@ static void print_footer(void)
 	if (!null_run)
 		fprintf(output, "\n");
 	fprintf(output, " %17.9f seconds time elapsed",
-			avg_stats(&walltime_nsecs_stats)/1e9);
+			avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC);
 	if (run_count > 1) {
 		fprintf(output, "                                        ");
 		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
@@ -2175,8 +2185,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 		update_stats(&walltime_nsecs_stats, stat_round->time);
 
 	if (stat_config.interval && stat_round->time) {
-		tsh.tv_sec  = stat_round->time / NSECS_PER_SEC;
-		tsh.tv_nsec = stat_round->time % NSECS_PER_SEC;
+		tsh.tv_sec  = stat_round->time / NSEC_PER_SEC;
+		tsh.tv_nsec = stat_round->time % NSEC_PER_SEC;
 		ts = &tsh;
 	}
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 733a55422d03..e7eaa298d34a 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -24,6 +24,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include <linux/rbtree.h>
+#include <linux/time64.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
 #include "util/strlist.h"
@@ -1288,9 +1289,9 @@ static void draw_process_bars(struct timechart *tchart)
 			if (c->comm) {
 				char comm[256];
 				if (c->total_time > 5000000000) /* 5 seconds */
-					sprintf(comm, "%s:%i (%2.2fs)", c->comm, p->pid, c->total_time / 1000000000.0);
+					sprintf(comm, "%s:%i (%2.2fs)", c->comm, p->pid, c->total_time / (double)NSEC_PER_SEC);
 				else
-					sprintf(comm, "%s:%i (%3.1fms)", c->comm, p->pid, c->total_time / 1000000.0);
+					sprintf(comm, "%s:%i (%3.1fms)", c->comm, p->pid, c->total_time / (double)NSEC_PER_MSEC);
 
 				svg_text(Y, c->start_time, comm);
 			}
@@ -1637,7 +1638,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 	write_svg_file(tchart, output_name);
 
 	pr_info("Written %2.1f seconds of trace to %s.\n",
-		(tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
+		(tchart->last_time - tchart->first_time) / (double)NSEC_PER_SEC, output_name);
 out_delete:
 	perf_session__delete(session);
 	return ret;
@@ -1901,10 +1902,10 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
 	if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) {
 		switch (unit) {
 		case 'm':
-			*value *= 1000000;
+			*value *= NSEC_PER_MSEC;
 			break;
 		case 'u':
-			*value *= 1000;
+			*value *= NSEC_PER_USEC;
 			break;
 		case 'n':
 			break;
@@ -1928,7 +1929,7 @@ int cmd_timechart(int argc, const char **argv,
 			.ordered_events	 = true,
 		},
 		.proc_num = 15,
-		.min_time = 1000000,
+		.min_time = NSEC_PER_MSEC,
 		.merge_dist = 1000,
 	};
 	const char *output_name = "output.svg";
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 418ed94756d3..fe3af9535e85 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -24,6 +24,7 @@
 #include "util/annotate.h"
 #include "util/config.h"
 #include "util/color.h"
+#include "util/drv_configs.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/machine.h"
@@ -68,6 +69,7 @@
 #include <sys/mman.h>
 
 #include <linux/stringify.h>
+#include <linux/time64.h>
 #include <linux/types.h>
 
 static volatile int done;
@@ -624,7 +626,7 @@ static void *display_thread(void *arg)
 	display_setup_sig();
 	pthread__unblock_sigwinch();
 repeat:
-	delay_msecs = top->delay_secs * 1000;
+	delay_msecs = top->delay_secs * MSEC_PER_SEC;
 	set_term_quiet_input(&save);
 	/* trash return*/
 	getc(stdin);
@@ -656,34 +658,6 @@ repeat:
 	return NULL;
 }
 
-static int symbol_filter(struct map *map, struct symbol *sym)
-{
-	const char *name = sym->name;
-
-	if (!__map__is_kernel(map))
-		return 0;
-	/*
-	 * ppc64 uses function descriptors and appends a '.' to the
-	 * start of every instruction address. Remove it.
-	 */
-	if (name[0] == '.')
-		name++;
-
-	if (!strcmp(name, "_text") ||
-	    !strcmp(name, "_etext") ||
-	    !strcmp(name, "_sinittext") ||
-	    !strncmp("init_module", name, 11) ||
-	    !strncmp("cleanup_module", name, 14) ||
-	    strstr(name, "_text_start") ||
-	    strstr(name, "_text_end"))
-		return 1;
-
-	if (symbol__is_idle(sym))
-		sym->ignore = true;
-
-	return 0;
-}
-
 static int hist_iter__top_callback(struct hist_entry_iter *iter,
 				   struct addr_location *al, bool single,
 				   void *arg)
@@ -782,7 +756,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		}
 	}
 
-	if (al.sym == NULL || !al.sym->ignore) {
+	if (al.sym == NULL || !al.sym->idle) {
 		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
 			.evsel		= evsel,
@@ -940,6 +914,10 @@ static int callchain_param__setup_sample_type(struct callchain_param *callchain)
 
 static int __cmd_top(struct perf_top *top)
 {
+	char msg[512];
+	struct perf_evsel *pos;
+	struct perf_evsel_config_term *err_term;
+	struct perf_evlist *evlist = top->evlist;
 	struct record_opts *opts = &top->record_opts;
 	pthread_t thread;
 	int ret;
@@ -948,8 +926,6 @@ static int __cmd_top(struct perf_top *top)
 	if (top->session == NULL)
 		return -1;
 
-	machines__set_symbol_filter(&top->session->machines, symbol_filter);
-
 	if (!objdump_path) {
 		ret = perf_env__lookup_objdump(&top->session->header.env);
 		if (ret)
@@ -976,6 +952,14 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
+	ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term);
+	if (ret) {
+		error("failed to set config \"%s\" on event %s with %d (%s)\n",
+			err_term->val.drv_cfg, perf_evsel__name(pos), errno,
+			str_error_r(errno, msg, sizeof(msg)));
+		goto out_delete;
+	}
+
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
 
@@ -1323,7 +1307,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
 		callchain_param.order = ORDER_CALLER;
 
-	symbol_conf.priv_size = sizeof(struct annotation);
+	status = symbol__annotation_init();
+	if (status < 0)
+		goto out_delete_evlist;
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b8c6766301db..c298bd3e1d90 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -45,6 +45,7 @@
 #include <linux/audit.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
+#include <linux/time64.h>
 
 #ifndef O_CLOEXEC
 # define O_CLOEXEC		02000000
@@ -741,6 +742,8 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "sched_getattr",	      .errmsg = true, },
+	{ .name	    = "sched_setattr",	      .errmsg = true, },
 	{ .name	    = "sched_setscheduler",   .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
 	{ .name	    = "seccomp", .errmsg = true,
@@ -2140,6 +2143,7 @@ out_delete_sys_enter:
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
 	int err = -1;
+	struct perf_evsel *sys_exit;
 	char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier,
 						trace->ev_qualifier_ids.nr,
 						trace->ev_qualifier_ids.entries);
@@ -2147,8 +2151,11 @@ static int trace__set_ev_qualifier_filter(struct trace *trace)
 	if (filter == NULL)
 		goto out_enomem;
 
-	if (!perf_evsel__append_filter(trace->syscalls.events.sys_enter, "&&", filter))
-		err = perf_evsel__append_filter(trace->syscalls.events.sys_exit, "&&", filter);
+	if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
+					  filter)) {
+		sys_exit = trace->syscalls.events.sys_exit;
+		err = perf_evsel__append_tp_filter(sys_exit, filter);
+	}
 
 	free(filter);
 out:
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 7ed72a475c57..e4b717e9eb6c 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -20,7 +20,6 @@
 #endif
 
 #ifdef __powerpc__
-#include "../../arch/powerpc/include/uapi/asm/unistd.h"
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cb0f1356ff81..9a0236a4cf95 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -14,13 +14,6 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 #define HAVE_ATTR_TEST
 #include "perf-sys.h"
 
-#ifndef NSEC_PER_SEC
-# define NSEC_PER_SEC			1000000000ULL
-#endif
-#ifndef NSEC_PER_USEC
-# define NSEC_PER_USEC			1000ULL
-#endif
-
 static inline unsigned long long rdclock(void)
 {
 	struct timespec ts;
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index dc51bc570e51..8a4ce492f7b2 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -71,7 +71,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 615780cbfe1d..e6d1816e431a 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -97,7 +97,7 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 
 	evlist = perf_evlist__new();
 	if (!evlist) {
-		pr_debug("No ehough memory to create evlist\n");
+		pr_debug("No enough memory to create evlist\n");
 		return TEST_FAIL;
 	}
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index fc54064b9186..2673e86ed50f 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -125,7 +125,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	/* Instead of perf_evlist__new_default, don't add default events */
 	evlist = perf_evlist__new();
 	if (!evlist) {
-		pr_debug("No ehough memory to create evlist\n");
+		pr_debug("No enough memory to create evlist\n");
 		return TEST_FAIL;
 	}
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 2af156a8d4e5..ff5bc6363a79 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -263,7 +263,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	 * Converting addresses for use by objdump requires more information.
 	 * map__load() does that.  See map__rip_2objdump() for details.
 	 */
-	if (map__load(al.map, NULL))
+	if (map__load(al.map))
 		return -1;
 
 	/* objdump struggles with kcore - try each map only once */
@@ -511,7 +511,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	/* Load kernel map */
 	map = machine__kernel_map(machine);
-	ret = map__load(map, NULL);
+	ret = map__load(map);
 	if (ret < 0) {
 		pr_debug("map__load failed\n");
 		goto out_err;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 8f6eb853aaf7..1046491de4b2 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,7 +11,7 @@
 #include "thread.h"
 #include "callchain.h"
 
-#if defined (__x86_64__) || defined (__i386__)
+#if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__)
 #include "arch-tests.h"
 #endif
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index e63abab7d5a1..a5082331f246 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -8,14 +8,6 @@
 #include "debug.h"
 #include "machine.h"
 
-static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
-					   struct symbol *sym)
-{
-	bool *visited = symbol__priv(sym);
-	*visited = true;
-	return 0;
-}
-
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
 int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
@@ -28,6 +20,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	enum map_type type = MAP__FUNCTION;
 	struct maps *maps = &vmlinux.kmaps.maps[type];
 	u64 mem_start, mem_end;
+	bool header_printed;
 
 	/*
 	 * Step 1:
@@ -61,7 +54,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true, NULL) <= 0) {
+	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true) <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -99,8 +92,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
 	 * to fixup the symbols.
 	 */
-	if (machine__load_vmlinux_path(&vmlinux, type,
-				       vmlinux_matches_kallsyms_filter) <= 0) {
+	if (machine__load_vmlinux_path(&vmlinux, type) <= 0) {
 		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
 		err = TEST_SKIP;
 		goto out;
@@ -126,7 +118,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
 
 		first_pair = machine__find_kernel_symbol(&kallsyms, type,
-							 mem_start, NULL, NULL);
+							 mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -143,7 +135,7 @@ next_pair:
 				 */
 				s64 skew = mem_end - UM(pair->end);
 				if (llabs(skew) >= page_size)
-					pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+					pr_debug("WARN: %#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
 						 mem_start, sym->name, mem_end,
 						 UM(pair->end));
 
@@ -154,22 +146,23 @@ next_pair:
 				 * kallsyms.
 				 */
 				continue;
-
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;
 
-					pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+					pr_debug("WARN: %#" PRIx64 ": diff name v: %s k: %s\n",
 						 mem_start, sym->name, pair->name);
 				} else {
-					pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+					pr_debug("WARN: %#" PRIx64 ": diff name v: %s k: %s\n",
 						 mem_start, sym->name, first_pair->name);
 				}
+
+				continue;
 			}
 		} else
-			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
+			pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n",
 				 mem_start, sym->name);
 
 		err = -1;
@@ -178,7 +171,7 @@ next_pair:
 	if (!verbose)
 		goto out;
 
-	pr_info("Maps only in vmlinux:\n");
+	header_printed = false;
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *
@@ -192,13 +185,18 @@ next_pair:
 						(map->dso->kernel ?
 							map->dso->short_name :
 							map->dso->name));
-		if (pair)
+		if (pair) {
 			pair->priv = 1;
-		else
+		} else {
+			if (!header_printed) {
+				pr_info("WARN: Maps only in vmlinux:\n");
+				header_printed = true;
+			}
 			map__fprintf(map, stderr);
+		}
 	}
 
-	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
+	header_printed = false;
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *pair;
@@ -211,24 +209,33 @@ next_pair:
 			continue;
 
 		if (pair->start == mem_start) {
-			pair->priv = 1;
-			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
+			if (!header_printed) {
+				pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n");
+				header_printed = true;
+			}
+
+			pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
 				map->start, map->end, map->pgoff, map->dso->name);
 			if (mem_end != pair->end)
-				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
+				pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);
 			pr_info(" %s\n", pair->dso->name);
 			pair->priv = 1;
 		}
 	}
 
-	pr_info("Maps only in kallsyms:\n");
+	header_printed = false;
 
 	maps = &kallsyms.kmaps.maps[type];
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
-		if (!map->priv)
+		if (!map->priv) {
+			if (!header_printed) {
+				pr_info("WARN: Maps only in kallsyms:\n");
+				header_printed = true;
+			}
 			map__fprintf(map, stderr);
+		}
 	}
 out:
 	machine__exit(&kallsyms);
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index d0a3a8e402e7..fd710ab33684 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,8 +1,4 @@
-#include <sys/mman.h>
-
-#ifndef PROT_SEM
-#define PROT_SEM 0x8
-#endif
+#include <uapi/linux/mman.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
@@ -33,31 +29,6 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
-#ifndef MAP_FIXED
-#define MAP_FIXED		     0x10
-#endif
-
-#ifndef MAP_ANONYMOUS
-#define MAP_ANONYMOUS		     0x20
-#endif
-
-#ifndef MAP_32BIT
-#define MAP_32BIT		     0x40
-#endif
-
-#ifndef MAP_STACK
-#define MAP_STACK		  0x20000
-#endif
-
-#ifndef MAP_HUGETLB
-#define MAP_HUGETLB		  0x40000
-#endif
-
-#ifndef MAP_UNINITIALIZED
-#define MAP_UNINITIALIZED	0x4000000
-#endif
-
-
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
@@ -95,13 +66,6 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
-#ifndef MREMAP_MAYMOVE
-#define MREMAP_MAYMOVE 1
-#endif
-#ifndef MREMAP_FIXED
-#define MREMAP_FIXED 2
-#endif
-
 static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 						  struct syscall_arg *arg)
 {
@@ -125,39 +89,6 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 #define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
 
-#ifndef MADV_HWPOISON
-#define MADV_HWPOISON		100
-#endif
-
-#ifndef MADV_SOFT_OFFLINE
-#define MADV_SOFT_OFFLINE	101
-#endif
-
-#ifndef MADV_MERGEABLE
-#define MADV_MERGEABLE		 12
-#endif
-
-#ifndef MADV_UNMERGEABLE
-#define MADV_UNMERGEABLE	 13
-#endif
-
-#ifndef MADV_HUGEPAGE
-#define MADV_HUGEPAGE		 14
-#endif
-
-#ifndef MADV_NOHUGEPAGE
-#define MADV_NOHUGEPAGE		 15
-#endif
-
-#ifndef MADV_DONTDUMP
-#define MADV_DONTDUMP		 16
-#endif
-
-#ifndef MADV_DODUMP
-#define MADV_DODUMP		 17
-#endif
-
-
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
@@ -170,6 +101,7 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 	P_MADV_BHV(SEQUENTIAL);
 	P_MADV_BHV(WILLNEED);
 	P_MADV_BHV(DONTNEED);
+	P_MADV_BHV(FREE);
 	P_MADV_BHV(REMOVE);
 	P_MADV_BHV(DONTFORK);
 	P_MADV_BHV(DOFORK);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 2e2d10022355..4c18271c71c9 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -495,7 +495,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	if (!ins__is_call(dl->ins))
 		return false;
 
-	if (map_groups__find_ams(&target, NULL) ||
+	if (map_groups__find_ams(&target) ||
 	    map__rip_2objdump(target.map, target.map->map_ip(target.map,
 							     target.addr)) !=
 	    dl->ops.target.addr) {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 13d414384739..fb8e42c7507a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -69,8 +69,11 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 static void hist_browser__update_rows(struct hist_browser *hb)
 {
 	struct ui_browser *browser = &hb->b;
-	u16 header_offset = hb->show_headers ? 1 : 0, index_row;
+	struct hists *hists = hb->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
+	u16 header_offset, index_row;
 
+	header_offset = hb->show_headers ? hpp_list->nr_header_lines : 0;
 	browser->rows = browser->height - header_offset;
 	/*
 	 * Verify if we were at the last line and that line isn't
@@ -99,8 +102,11 @@ static void hist_browser__refresh_dimensions(struct ui_browser *browser)
 
 static void hist_browser__gotorc(struct hist_browser *browser, int row, int column)
 {
-	u16 header_offset = browser->show_headers ? 1 : 0;
+	struct hists *hists = browser->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
+	u16 header_offset;
 
+	header_offset = browser->show_headers ? hpp_list->nr_header_lines : 0;
 	ui_browser__gotorc(&browser->b, row + header_offset, column);
 }
 
@@ -1074,7 +1080,7 @@ struct hpp_arg {
 	bool current_entry;
 };
 
-static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
+int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
 	int ret, len;
@@ -1091,7 +1097,6 @@ static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	ui_browser__printf(arg->b, "%s", hpp->buf);
 
-	advance_hpp(hpp, ret);
 	return ret;
 }
 
@@ -1496,7 +1501,9 @@ static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 	return hpp->size <= 0;
 }
 
-static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf, size_t size)
+static int
+hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf,
+				 size_t size, int line)
 {
 	struct hists *hists = browser->hists;
 	struct perf_hpp dummy_hpp = {
@@ -1506,6 +1513,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	struct perf_hpp_fmt *fmt;
 	size_t ret = 0;
 	int column = 0;
+	int span = 0;
 
 	if (symbol_conf.use_callchain) {
 		ret = scnprintf(buf, size, "  ");
@@ -1517,10 +1525,13 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists);
+		ret = fmt->header(fmt, &dummy_hpp, hists, line, &span);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
+		if (span)
+			continue;
+
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1554,7 +1565,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists);
+		ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1591,7 +1602,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists);
+			ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = trim(dummy_hpp.buf);
@@ -1622,14 +1633,21 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 
 static void hists_browser__headers(struct hist_browser *browser)
 {
-	char headers[1024];
+	struct hists *hists = browser->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 
-	hists_browser__scnprintf_headers(browser, headers,
-					 sizeof(headers));
+	int line;
 
-	ui_browser__gotorc(&browser->b, 0, 0);
-	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
-	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+	for (line = 0; line < hpp_list->nr_header_lines; line++) {
+		char headers[1024];
+
+		hists_browser__scnprintf_headers(browser, headers,
+						 sizeof(headers), line);
+
+		ui_browser__gotorc(&browser->b, line, 0);
+		ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+		ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+	}
 }
 
 static void hist_browser__show_headers(struct hist_browser *browser)
@@ -1656,10 +1674,13 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	u16 header_offset = 0;
 	struct rb_node *nd;
 	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+	struct hists *hists = hb->hists;
 
 	if (hb->show_headers) {
+		struct perf_hpp_list *hpp_list = hists->hpp_list;
+
 		hist_browser__show_headers(hb);
-		header_offset = 1;
+		header_offset = hpp_list->nr_header_lines;
 	}
 
 	ui_browser__hists_init_top(browser);
@@ -2054,10 +2075,10 @@ void hist_browser__init(struct hist_browser *browser,
 	browser->b.use_navkeypressed	= true;
 	browser->show_headers		= symbol_conf.show_hist_headers;
 
-	hists__for_each_format(hists, fmt) {
-		perf_hpp__reset_width(fmt, hists);
+	hists__for_each_format(hists, fmt)
 		++browser->b.columns;
-	}
+
+	hists__reset_column_width(hists);
 }
 
 struct hist_browser *hist_browser__new(struct hists *hists)
@@ -2418,8 +2439,6 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 		browser->hists->dso_filter = NULL;
 		ui_helpline__pop();
 	} else {
-		if (map == NULL)
-			return 0;
 		ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s DSO\"",
 				   __map__is_kernel(map) ? "the Kernel" : map->dso->short_name);
 		browser->hists->dso_filter = map->dso;
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 80912778bb6d..98a34664bb7e 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -52,9 +52,9 @@ static int map_browser__search(struct map_browser *browser)
 
 	if (target[0] == '0' && tolower(target[1]) == 'x') {
 		u64 addr = strtoull(target, NULL, 16);
-		sym = map__find_symbol(browser->map, addr, NULL);
+		sym = map__find_symbol(browser->map, addr);
 	} else
-		sym = map__find_symbol_by_name(browser->map, target, NULL);
+		sym = map__find_symbol_by_name(browser->map, target);
 
 	if (sym != NULL) {
 		u32 *idx = symbol__browser_index(sym);
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index c5f3677f6679..a4f02de7c1b5 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				strcat(buf, "+");
 			first_col = false;
 
-			fmt->header(fmt, &hpp, hists);
+			fmt->header(fmt, &hpp, hists, 0, NULL);
 			strcat(buf, ltrim(rtrim(hpp.buf)));
 		}
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4274969ddc89..37388397b5bc 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -230,13 +230,14 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct hists *hists)
+			  struct hists *hists, int line __maybe_unused,
+			  int *span __maybe_unused)
 {
 	int len = hpp__width_fn(fmt, hpp, hists);
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
-static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	va_list args;
 	ssize_t ssize = hpp->size;
@@ -441,6 +442,7 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 struct perf_hpp_list perf_hpp_list = {
 	.fields	= LIST_HEAD_INIT(perf_hpp_list.fields),
 	.sorts	= LIST_HEAD_INIT(perf_hpp_list.sorts),
+	.nr_header_lines = 1,
 };
 
 #undef HPP__COLOR_PRINT_FNS
@@ -697,6 +699,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 	}
 }
 
+void hists__reset_column_width(struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *node;
+
+	hists__for_each_format(hists, fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	/* hierarchy entries have their own hpp list */
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format(&node->hpp, fmt)
+			perf_hpp__reset_width(fmt, hists);
+	}
+}
+
 void perf_hpp__set_user_width(const char *width_list_str)
 {
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index f04a63112079..89d8441f9890 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -373,7 +373,8 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+			   struct perf_hpp_list *hpp_list)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
@@ -384,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	hists__for_each_format(he->hists, fmt) {
+	perf_hpp_list__for_each_format(hpp_list, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
@@ -410,6 +411,11 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 	return hpp->buf - start;
 }
 
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+{
+	return __hist_entry__snprintf(he, hpp, he->hists->hpp_list);
+}
+
 static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 					 struct perf_hpp *hpp,
 					 struct hists *hists,
@@ -528,8 +534,8 @@ static int print_hierarchy_indent(const char *sep, int indent,
 	return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
 }
 
-static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
-				  const char *sep, FILE *fp)
+static int hists__fprintf_hierarchy_headers(struct hists *hists,
+					    struct perf_hpp *hpp, FILE *fp)
 {
 	bool first_node, first_col;
 	int indent;
@@ -538,6 +544,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	unsigned header_width = 0;
 	struct perf_hpp_fmt *fmt;
 	struct perf_hpp_list_node *fmt_node;
+	const char *sep = symbol_conf.field_sep;
 
 	indent = hists->nr_hpp_node;
 
@@ -549,7 +556,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				    struct perf_hpp_list_node, list);
 
 	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists);
+		fmt->header(fmt, hpp, hists, 0, NULL);
 		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
@@ -569,7 +576,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				header_width += fprintf(fp, "+");
 			first_col = false;
 
-			fmt->header(fmt, hpp, hists);
+			fmt->header(fmt, hpp, hists, 0, NULL);
 
 			header_width += fprintf(fp, "%s", trim(hpp->buf));
 		}
@@ -623,20 +630,28 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	return 2;
 }
 
-static int
-hists__fprintf_hierarchy_headers(struct hists *hists,
-				 struct perf_hpp *hpp,
-				 FILE *fp)
+static void fprintf_line(struct hists *hists, struct perf_hpp *hpp,
+			 int line, FILE *fp)
 {
-	struct perf_hpp_list_node *fmt_node;
 	struct perf_hpp_fmt *fmt;
+	const char *sep = symbol_conf.field_sep;
+	bool first = true;
+	int span = 0;
 
-	list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
-		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
-			perf_hpp__reset_width(fmt, hists);
-	}
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__should_skip(fmt, hists))
+			continue;
+
+		if (!first && !span)
+			fprintf(fp, "%s", sep ?: "  ");
+		else
+			first = false;
+
+		fmt->header(fmt, hpp, hists, line, &span);
 
-	return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
+		if (!span)
+			fprintf(fp, "%s", hpp->buf);
+	}
 }
 
 static int
@@ -644,28 +659,23 @@ hists__fprintf_standard_headers(struct hists *hists,
 				struct perf_hpp *hpp,
 				FILE *fp)
 {
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 	struct perf_hpp_fmt *fmt;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
 	bool first = true;
-
-	hists__for_each_format(hists, fmt) {
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
-
-		if (!first)
-			fprintf(fp, "%s", sep ?: "  ");
-		else
-			first = false;
-
-		fmt->header(fmt, hpp, hists);
-		fprintf(fp, "%s", hpp->buf);
+	int line;
+
+	for (line = 0; line < hpp_list->nr_header_lines; line++) {
+		/* first # is displayed one level up */
+		if (line)
+			fprintf(fp, "# ");
+		fprintf_line(hists, hpp, line, fp);
+		fprintf(fp, "\n");
 	}
 
-	fprintf(fp, "\n");
-
 	if (sep)
-		return 1;
+		return hpp_list->nr_header_lines;
 
 	first = true;
 
@@ -689,12 +699,12 @@ hists__fprintf_standard_headers(struct hists *hists,
 
 	fprintf(fp, "\n");
 	fprintf(fp, "#\n");
-	return 3;
+	return hpp_list->nr_header_lines + 2;
 }
 
-static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+int hists__fprintf_headers(struct hists *hists, FILE *fp)
 {
-	char bf[96];
+	char bf[1024];
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),
@@ -713,7 +723,6 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
 		      bool use_callchain)
 {
-	struct perf_hpp_fmt *fmt;
 	struct rb_node *nd;
 	size_t ret = 0;
 	const char *sep = symbol_conf.field_sep;
@@ -724,8 +733,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	init_rem_hits();
 
-	hists__for_each_format(hists, fmt)
-		perf_hpp__reset_width(fmt, hists);
+	hists__reset_column_width(hists);
 
 	if (symbol_conf.col_width_list_str)
 		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 91c5f6e1af59..eb60e613d795 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,5 +1,6 @@
 libperf-y += alias.o
 libperf-y += annotate.o
+libperf-y += block-range.o
 libperf-y += build-id.o
 libperf-y += config.o
 libperf-y += ctype.o
@@ -85,6 +86,7 @@ libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
 libperf-y += vsprintf.o
+libperf-y += drv_configs.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -98,6 +100,7 @@ endif
 
 libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
+libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4024d309bb00..aeb5a441bd74 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,6 +17,7 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include "block-range.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
@@ -53,7 +54,7 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
 	return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
-static int call__parse(struct ins_operands *ops)
+static int call__parse(struct ins_operands *ops, struct map *map)
 {
 	char *endptr, *tok, *name;
 
@@ -81,16 +82,16 @@ static int call__parse(struct ins_operands *ops)
 	return ops->target.name == NULL ? -1 : 0;
 
 indirect_call:
-	tok = strchr(endptr, '(');
-	if (tok != NULL) {
-		ops->target.addr = 0;
+	tok = strchr(endptr, '*');
+	if (tok == NULL) {
+		struct symbol *sym = map__find_symbol(map, map->map_ip(map, ops->target.addr));
+		if (sym != NULL)
+			ops->target.name = strdup(sym->name);
+		else
+			ops->target.addr = 0;
 		return 0;
 	}
 
-	tok = strchr(endptr, '*');
-	if (tok == NULL)
-		return -1;
-
 	ops->target.addr = strtoull(tok + 1, NULL, 16);
 	return 0;
 }
@@ -117,7 +118,7 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops;
 }
 
-static int jump__parse(struct ins_operands *ops)
+static int jump__parse(struct ins_operands *ops, struct map *map __maybe_unused)
 {
 	const char *s = strchr(ops->raw, '+');
 
@@ -172,7 +173,7 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 	return 0;
 }
 
-static int lock__parse(struct ins_operands *ops)
+static int lock__parse(struct ins_operands *ops, struct map *map)
 {
 	char *name;
 
@@ -193,7 +194,7 @@ static int lock__parse(struct ins_operands *ops)
 		return 0;
 
 	if (ops->locked.ins->ops->parse &&
-	    ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+	    ops->locked.ins->ops->parse(ops->locked.ops, map) < 0)
 		goto out_free_ops;
 
 	return 0;
@@ -236,7 +237,7 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
-static int mov__parse(struct ins_operands *ops)
+static int mov__parse(struct ins_operands *ops, struct map *map __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
 
@@ -303,7 +304,7 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
-static int dec__parse(struct ins_operands *ops)
+static int dec__parse(struct ins_operands *ops, struct map *map __maybe_unused)
 {
 	char *target, *comment, *s, prev;
 
@@ -491,13 +492,6 @@ static struct ins *ins__find(const char *name)
 	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
-int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	pthread_mutex_init(&notes->lock, NULL);
-	return 0;
-}
-
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -715,7 +709,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
 }
 
-static void disasm_line__init_ins(struct disasm_line *dl)
+static void disasm_line__init_ins(struct disasm_line *dl, struct map *map)
 {
 	dl->ins = ins__find(dl->name);
 
@@ -725,7 +719,7 @@ static void disasm_line__init_ins(struct disasm_line *dl)
 	if (!dl->ins->ops)
 		return;
 
-	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops, map) < 0)
 		dl->ins = NULL;
 }
 
@@ -767,7 +761,8 @@ out_free_name:
 }
 
 static struct disasm_line *disasm_line__new(s64 offset, char *line,
-					size_t privsize, int line_nr)
+					    size_t privsize, int line_nr,
+					    struct map *map)
 {
 	struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
 
@@ -782,7 +777,7 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line,
 			if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0)
 				goto out_free_line;
 
-			disasm_line__init_ins(dl);
+			disasm_line__init_ins(dl, map);
 		}
 	}
 
@@ -866,6 +861,89 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 	return percent;
 }
 
+static const char *annotate__address_color(struct block_range *br)
+{
+	double cov = block_range__coverage(br);
+
+	if (cov >= 0) {
+		/* mark red for >75% coverage */
+		if (cov > 0.75)
+			return PERF_COLOR_RED;
+
+		/* mark dull for <1% coverage */
+		if (cov < 0.01)
+			return PERF_COLOR_NORMAL;
+	}
+
+	return PERF_COLOR_MAGENTA;
+}
+
+static const char *annotate__asm_color(struct block_range *br)
+{
+	double cov = block_range__coverage(br);
+
+	if (cov >= 0) {
+		/* mark dull for <1% coverage */
+		if (cov < 0.01)
+			return PERF_COLOR_NORMAL;
+	}
+
+	return PERF_COLOR_BLUE;
+}
+
+static void annotate__branch_printf(struct block_range *br, u64 addr)
+{
+	bool emit_comment = true;
+
+	if (!br)
+		return;
+
+#if 1
+	if (br->is_target && br->start == addr) {
+		struct block_range *branch = br;
+		double p;
+
+		/*
+		 * Find matching branch to our target.
+		 */
+		while (!branch->is_branch)
+			branch = block_range__next(branch);
+
+		p = 100 *(double)br->entry / branch->coverage;
+
+		if (p > 0.1) {
+			if (emit_comment) {
+				emit_comment = false;
+				printf("\t#");
+			}
+
+			/*
+			 * The percentage of coverage joined at this target in relation
+			 * to the next branch.
+			 */
+			printf(" +%.2f%%", p);
+		}
+	}
+#endif
+	if (br->is_branch && br->end == addr) {
+		double p = 100*(double)br->taken / br->coverage;
+
+		if (p > 0.1) {
+			if (emit_comment) {
+				emit_comment = false;
+				printf("\t#");
+			}
+
+			/*
+			 * The percentage of coverage leaving at this branch, and
+			 * its prediction ratio.
+			 */
+			printf(" -%.2f%% (p:%.2f%%)", p, 100*(double)br->pred  / br->taken);
+		}
+	}
+}
+
+
 static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
 		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
 		      int max_lines, struct disasm_line *queue)
@@ -885,6 +963,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		s64 offset = dl->offset;
 		const u64 addr = start + offset;
 		struct disasm_line *next;
+		struct block_range *br;
 
 		next = disasm__get_next_ip_line(&notes->src->source, dl);
 
@@ -954,8 +1033,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		}
 
 		printf(" :	");
-		color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
-		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+		br = block_range__find(addr);
+		color_fprintf(stdout, annotate__address_color(br), "  %" PRIx64 ":", addr);
+		color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line);
+		annotate__branch_printf(br, addr);
+		printf("\n");
 
 		if (ppercents != &percent)
 			free(ppercents);
@@ -1066,7 +1149,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			parsed_line = tmp2 + 1;
 	}
 
-	dl = disasm_line__new(offset, parsed_line, privsize, *line_nr);
+	dl = disasm_line__new(offset, parsed_line, privsize, *line_nr, map);
 	free(line);
 	(*line_nr)++;
 
@@ -1084,7 +1167,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			.addr = dl->ops.target.addr,
 		};
 
-		if (!map_groups__find_ams(&target, NULL) &&
+		if (!map_groups__find_ams(&target) &&
 		    target.sym->start == target.al_addr)
 			dl->ops.target.name = strdup(target.sym->name);
 	}
@@ -1162,53 +1245,60 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 	return 0;
 }
 
-int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
+static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
 {
-	struct dso *dso = map->dso;
-	char *filename = dso__build_id_filename(dso, NULL, 0);
-	bool free_filename = true;
-	char command[PATH_MAX * 2];
-	FILE *file;
-	int err = 0;
-	char symfs_filename[PATH_MAX];
-	struct kcore_extract kce;
-	bool delete_extract = false;
-	int stdout_fd[2];
-	int lineno = 0;
-	int nline;
-	pid_t pid;
+	char linkname[PATH_MAX];
+	char *build_id_filename;
 
-	if (filename)
-		symbol__join_symfs(symfs_filename, filename);
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(dso))
+		return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
 
-	if (filename == NULL) {
+	build_id_filename = dso__build_id_filename(dso, NULL, 0);
+	if (build_id_filename) {
+		__symbol__join_symfs(filename, filename_size, build_id_filename);
+		free(build_id_filename);
+	} else {
 		if (dso->has_build_id)
 			return ENOMEM;
 		goto fallback;
-	} else if (dso__is_kcore(dso) ||
-		   readlink(symfs_filename, command, sizeof(command)) < 0 ||
-		   strstr(command, DSO__NAME_KALLSYMS) ||
-		   access(symfs_filename, R_OK)) {
-		free(filename);
+	}
+
+	if (dso__is_kcore(dso) ||
+	    readlink(filename, linkname, sizeof(linkname)) < 0 ||
+	    strstr(linkname, DSO__NAME_KALLSYMS) ||
+	    access(filename, R_OK)) {
 fallback:
 		/*
 		 * If we don't have build-ids or the build-id file isn't in the
 		 * cache, or is just a kallsyms file, well, lets hope that this
 		 * DSO is the same as when 'perf record' ran.
 		 */
-		filename = (char *)dso->long_name;
-		symbol__join_symfs(symfs_filename, filename);
-		free_filename = false;
+		__symbol__join_symfs(filename, filename_size, dso->long_name);
 	}
 
-	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
-	    !dso__is_kcore(dso)) {
-		err = SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
-		goto out_free_filename;
-	}
+	return 0;
+}
+
+int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
+{
+	struct dso *dso = map->dso;
+	char command[PATH_MAX * 2];
+	FILE *file;
+	char symfs_filename[PATH_MAX];
+	struct kcore_extract kce;
+	bool delete_extract = false;
+	int stdout_fd[2];
+	int lineno = 0;
+	int nline;
+	pid_t pid;
+	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
+
+	if (err)
+		return err;
 
 	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
-		 filename, sym->name, map->unmap_ip(map, sym->start),
+		 symfs_filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
 
 	pr_debug("annotating [%p] %30s : [%p] %30s\n",
@@ -1223,11 +1313,6 @@ fallback:
 			delete_extract = true;
 			strlcpy(symfs_filename, kce.extract_filename,
 				sizeof(symfs_filename));
-			if (free_filename) {
-				free(filename);
-				free_filename = false;
-			}
-			filename = symfs_filename;
 		}
 	} else if (dso__needs_decompress(dso)) {
 		char tmp[PATH_MAX];
@@ -1236,14 +1321,14 @@ fallback:
 		bool ret;
 
 		if (kmod_path__parse_ext(&m, symfs_filename))
-			goto out_free_filename;
+			goto out;
 
 		snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
 
 		fd = mkstemp(tmp);
 		if (fd < 0) {
 			free(m.ext);
-			goto out_free_filename;
+			goto out;
 		}
 
 		ret = decompress_to_file(m.ext, symfs_filename, fd);
@@ -1255,7 +1340,7 @@ fallback:
 		close(fd);
 
 		if (!ret)
-			goto out_free_filename;
+			goto out;
 
 		strcpy(symfs_filename, tmp);
 	}
@@ -1271,7 +1356,7 @@ fallback:
 		 map__rip_2objdump(map, sym->end),
 		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
 		 symbol_conf.annotate_src ? "-S" : "",
-		 symfs_filename, filename);
+		 symfs_filename, symfs_filename);
 
 	pr_debug("Executing: %s\n", command);
 
@@ -1333,11 +1418,10 @@ out_remove_tmp:
 
 	if (dso__needs_decompress(dso))
 		unlink(symfs_filename);
-out_free_filename:
+
 	if (delete_extract)
 		kcore_extract__delete(&kce);
-	if (free_filename)
-		free(filename);
+out:
 	return err;
 
 out_close_stdout:
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f67ccb027561..5bbcec173b82 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -36,7 +36,7 @@ struct ins_operands {
 
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct ins_operands *ops);
+	int (*parse)(struct ins_operands *ops, struct map *map);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
 			 struct ins_operands *ops);
 };
@@ -130,6 +130,7 @@ struct annotated_source {
 
 struct annotation {
 	pthread_mutex_t		lock;
+	u64			max_coverage;
 	struct annotated_source *src;
 };
 
@@ -177,7 +178,6 @@ enum symbol_disassemble_errno {
 int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
 				 int errnum, char *buf, size_t buflen);
 
-int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c9169011e55e..c5a6e0b12452 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -16,6 +16,10 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <stdbool.h>
+#include <ctype.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
 
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -35,9 +39,14 @@
 #include "../perf.h"
 #include "util.h"
 #include "evlist.h"
+#include "dso.h"
+#include "map.h"
+#include "pmu.h"
+#include "evsel.h"
 #include "cpumap.h"
 #include "thread_map.h"
 #include "asm/bug.h"
+#include "symbol/kallsyms.h"
 #include "auxtrace.h"
 
 #include <linux/hash.h>
@@ -892,6 +901,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 		return intel_pt_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_INTEL_BTS:
 		return intel_bts_process_auxtrace_info(event, session);
+	case PERF_AUXTRACE_CS_ETM:
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;
@@ -1398,3 +1408,731 @@ void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
 
 	return NULL;
 }
+
+static void addr_filter__free_str(struct addr_filter *filt)
+{
+	free(filt->str);
+	filt->action   = NULL;
+	filt->sym_from = NULL;
+	filt->sym_to   = NULL;
+	filt->filename = NULL;
+	filt->str      = NULL;
+}
+
+static struct addr_filter *addr_filter__new(void)
+{
+	struct addr_filter *filt = zalloc(sizeof(*filt));
+
+	if (filt)
+		INIT_LIST_HEAD(&filt->list);
+
+	return filt;
+}
+
+static void addr_filter__free(struct addr_filter *filt)
+{
+	if (filt)
+		addr_filter__free_str(filt);
+	free(filt);
+}
+
+static void addr_filters__add(struct addr_filters *filts,
+			      struct addr_filter *filt)
+{
+	list_add_tail(&filt->list, &filts->head);
+	filts->cnt += 1;
+}
+
+static void addr_filters__del(struct addr_filters *filts,
+			      struct addr_filter *filt)
+{
+	list_del_init(&filt->list);
+	filts->cnt -= 1;
+}
+
+void addr_filters__init(struct addr_filters *filts)
+{
+	INIT_LIST_HEAD(&filts->head);
+	filts->cnt = 0;
+}
+
+void addr_filters__exit(struct addr_filters *filts)
+{
+	struct addr_filter *filt, *n;
+
+	list_for_each_entry_safe(filt, n, &filts->head, list) {
+		addr_filters__del(filts, filt);
+		addr_filter__free(filt);
+	}
+}
+
+static int parse_num_or_str(char **inp, u64 *num, const char **str,
+			    const char *str_delim)
+{
+	*inp += strspn(*inp, " ");
+
+	if (isdigit(**inp)) {
+		char *endptr;
+
+		if (!num)
+			return -EINVAL;
+		errno = 0;
+		*num = strtoull(*inp, &endptr, 0);
+		if (errno)
+			return -errno;
+		if (endptr == *inp)
+			return -EINVAL;
+		*inp = endptr;
+	} else {
+		size_t n;
+
+		if (!str)
+			return -EINVAL;
+		*inp += strspn(*inp, " ");
+		*str = *inp;
+		n = strcspn(*inp, str_delim);
+		if (!n)
+			return -EINVAL;
+		*inp += n;
+		if (**inp) {
+			**inp = '\0';
+			*inp += 1;
+		}
+	}
+	return 0;
+}
+
+static int parse_action(struct addr_filter *filt)
+{
+	if (!strcmp(filt->action, "filter")) {
+		filt->start = true;
+		filt->range = true;
+	} else if (!strcmp(filt->action, "start")) {
+		filt->start = true;
+	} else if (!strcmp(filt->action, "stop")) {
+		filt->start = false;
+	} else if (!strcmp(filt->action, "tracestop")) {
+		filt->start = false;
+		filt->range = true;
+		filt->action += 5; /* Change 'tracestop' to 'stop' */
+	} else {
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int parse_sym_idx(char **inp, int *idx)
+{
+	*idx = -1;
+
+	*inp += strspn(*inp, " ");
+
+	if (**inp != '#')
+		return 0;
+
+	*inp += 1;
+
+	if (**inp == 'g' || **inp == 'G') {
+		*inp += 1;
+		*idx = 0;
+	} else {
+		unsigned long num;
+		char *endptr;
+
+		errno = 0;
+		num = strtoul(*inp, &endptr, 0);
+		if (errno)
+			return -errno;
+		if (endptr == *inp || num > INT_MAX)
+			return -EINVAL;
+		*inp = endptr;
+		*idx = num;
+	}
+
+	return 0;
+}
+
+static int parse_addr_size(char **inp, u64 *num, const char **str, int *idx)
+{
+	int err = parse_num_or_str(inp, num, str, " ");
+
+	if (!err && *str)
+		err = parse_sym_idx(inp, idx);
+
+	return err;
+}
+
+static int parse_one_filter(struct addr_filter *filt, const char **filter_inp)
+{
+	char *fstr;
+	int err;
+
+	filt->str = fstr = strdup(*filter_inp);
+	if (!fstr)
+		return -ENOMEM;
+
+	err = parse_num_or_str(&fstr, NULL, &filt->action, " ");
+	if (err)
+		goto out_err;
+
+	err = parse_action(filt);
+	if (err)
+		goto out_err;
+
+	err = parse_addr_size(&fstr, &filt->addr, &filt->sym_from,
+			      &filt->sym_from_idx);
+	if (err)
+		goto out_err;
+
+	fstr += strspn(fstr, " ");
+
+	if (*fstr == '/') {
+		fstr += 1;
+		err = parse_addr_size(&fstr, &filt->size, &filt->sym_to,
+				      &filt->sym_to_idx);
+		if (err)
+			goto out_err;
+		filt->range = true;
+	}
+
+	fstr += strspn(fstr, " ");
+
+	if (*fstr == '@') {
+		fstr += 1;
+		err = parse_num_or_str(&fstr, NULL, &filt->filename, " ,");
+		if (err)
+			goto out_err;
+	}
+
+	fstr += strspn(fstr, " ,");
+
+	*filter_inp += fstr - filt->str;
+
+	return 0;
+
+out_err:
+	addr_filter__free_str(filt);
+
+	return err;
+}
+
+int addr_filters__parse_bare_filter(struct addr_filters *filts,
+				    const char *filter)
+{
+	struct addr_filter *filt;
+	const char *fstr = filter;
+	int err;
+
+	while (*fstr) {
+		filt = addr_filter__new();
+		err = parse_one_filter(filt, &fstr);
+		if (err) {
+			addr_filter__free(filt);
+			addr_filters__exit(filts);
+			return err;
+		}
+		addr_filters__add(filts, filt);
+	}
+
+	return 0;
+}
+
+struct sym_args {
+	const char	*name;
+	u64		start;
+	u64		size;
+	int		idx;
+	int		cnt;
+	bool		started;
+	bool		global;
+	bool		selected;
+	bool		duplicate;
+	bool		near;
+};
+
+static bool kern_sym_match(struct sym_args *args, const char *name, char type)
+{
+	/* A function with the same name, and global or the n'th found or any */
+	return symbol_type__is_a(type, MAP__FUNCTION) &&
+	       !strcmp(name, args->name) &&
+	       ((args->global && isupper(type)) ||
+		(args->selected && ++(args->cnt) == args->idx) ||
+		(!args->global && !args->selected));
+}
+
+static int find_kern_sym_cb(void *arg, const char *name, char type, u64 start)
+{
+	struct sym_args *args = arg;
+
+	if (args->started) {
+		if (!args->size)
+			args->size = start - args->start;
+		if (args->selected) {
+			if (args->size)
+				return 1;
+		} else if (kern_sym_match(args, name, type)) {
+			args->duplicate = true;
+			return 1;
+		}
+	} else if (kern_sym_match(args, name, type)) {
+		args->started = true;
+		args->start = start;
+	}
+
+	return 0;
+}
+
+static int print_kern_sym_cb(void *arg, const char *name, char type, u64 start)
+{
+	struct sym_args *args = arg;
+
+	if (kern_sym_match(args, name, type)) {
+		pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n",
+		       ++args->cnt, start, type, name);
+		args->near = true;
+	} else if (args->near) {
+		args->near = false;
+		pr_err("\t\twhich is near\t\t%s\n", name);
+	}
+
+	return 0;
+}
+
+static int sym_not_found_error(const char *sym_name, int idx)
+{
+	if (idx > 0) {
+		pr_err("N'th occurrence (N=%d) of symbol '%s' not found.\n",
+		       idx, sym_name);
+	} else if (!idx) {
+		pr_err("Global symbol '%s' not found.\n", sym_name);
+	} else {
+		pr_err("Symbol '%s' not found.\n", sym_name);
+	}
+	pr_err("Note that symbols must be functions.\n");
+
+	return -EINVAL;
+}
+
+static int find_kern_sym(const char *sym_name, u64 *start, u64 *size, int idx)
+{
+	struct sym_args args = {
+		.name = sym_name,
+		.idx = idx,
+		.global = !idx,
+		.selected = idx > 0,
+	};
+	int err;
+
+	*start = 0;
+	*size = 0;
+
+	err = kallsyms__parse("/proc/kallsyms", &args, find_kern_sym_cb);
+	if (err < 0) {
+		pr_err("Failed to parse /proc/kallsyms\n");
+		return err;
+	}
+
+	if (args.duplicate) {
+		pr_err("Multiple kernel symbols with name '%s'\n", sym_name);
+		args.cnt = 0;
+		kallsyms__parse("/proc/kallsyms", &args, print_kern_sym_cb);
+		pr_err("Disambiguate symbol name by inserting #n after the name e.g. %s #2\n",
+		       sym_name);
+		pr_err("Or select a global symbol by inserting #0 or #g or #G\n");
+		return -EINVAL;
+	}
+
+	if (!args.started) {
+		pr_err("Kernel symbol lookup: ");
+		return sym_not_found_error(sym_name, idx);
+	}
+
+	*start = args.start;
+	*size = args.size;
+
+	return 0;
+}
+
+static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
+			       char type, u64 start)
+{
+	struct sym_args *args = arg;
+
+	if (!symbol_type__is_a(type, MAP__FUNCTION))
+		return 0;
+
+	if (!args->started) {
+		args->started = true;
+		args->start = start;
+	}
+	/* Don't know exactly where the kernel ends, so we add a page */
+	args->size = round_up(start, page_size) + page_size - args->start;
+
+	return 0;
+}
+
+static int addr_filter__entire_kernel(struct addr_filter *filt)
+{
+	struct sym_args args = { .started = false };
+	int err;
+
+	err = kallsyms__parse("/proc/kallsyms", &args, find_entire_kern_cb);
+	if (err < 0 || !args.started) {
+		pr_err("Failed to parse /proc/kallsyms\n");
+		return err;
+	}
+
+	filt->addr = args.start;
+	filt->size = args.size;
+
+	return 0;
+}
+
+static int check_end_after_start(struct addr_filter *filt, u64 start, u64 size)
+{
+	if (start + size >= filt->addr)
+		return 0;
+
+	if (filt->sym_from) {
+		pr_err("Symbol '%s' (0x%"PRIx64") comes before '%s' (0x%"PRIx64")\n",
+		       filt->sym_to, start, filt->sym_from, filt->addr);
+	} else {
+		pr_err("Symbol '%s' (0x%"PRIx64") comes before address 0x%"PRIx64")\n",
+		       filt->sym_to, start, filt->addr);
+	}
+
+	return -EINVAL;
+}
+
+static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
+{
+	bool no_size = false;
+	u64 start, size;
+	int err;
+
+	if (symbol_conf.kptr_restrict) {
+		pr_err("Kernel addresses are restricted. Unable to resolve kernel symbols.\n");
+		return -EINVAL;
+	}
+
+	if (filt->sym_from && !strcmp(filt->sym_from, "*"))
+		return addr_filter__entire_kernel(filt);
+
+	if (filt->sym_from) {
+		err = find_kern_sym(filt->sym_from, &start, &size,
+				    filt->sym_from_idx);
+		if (err)
+			return err;
+		filt->addr = start;
+		if (filt->range && !filt->size && !filt->sym_to) {
+			filt->size = size;
+			no_size = !!size;
+		}
+	}
+
+	if (filt->sym_to) {
+		err = find_kern_sym(filt->sym_to, &start, &size,
+				    filt->sym_to_idx);
+		if (err)
+			return err;
+
+		err = check_end_after_start(filt, start, size);
+		if (err)
+			return err;
+		filt->size = start + size - filt->addr;
+		no_size = !!size;
+	}
+
+	/* The very last symbol in kallsyms does not imply a particular size */
+	if (no_size) {
+		pr_err("Cannot determine size of symbol '%s'\n",
+		       filt->sym_to ? filt->sym_to : filt->sym_from);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct dso *load_dso(const char *name)
+{
+	struct map *map;
+	struct dso *dso;
+
+	map = dso__new_map(name);
+	if (!map)
+		return NULL;
+
+	map__load(map);
+
+	dso = dso__get(map->dso);
+
+	map__put(map);
+
+	return dso;
+}
+
+static bool dso_sym_match(struct symbol *sym, const char *name, int *cnt,
+			  int idx)
+{
+	/* Same name, and global or the n'th found or any */
+	return !arch__compare_symbol_names(name, sym->name) &&
+	       ((!idx && sym->binding == STB_GLOBAL) ||
+		(idx > 0 && ++*cnt == idx) ||
+		idx < 0);
+}
+
+static void print_duplicate_syms(struct dso *dso, const char *sym_name)
+{
+	struct symbol *sym;
+	bool near = false;
+	int cnt = 0;
+
+	pr_err("Multiple symbols with name '%s'\n", sym_name);
+
+	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	while (sym) {
+		if (dso_sym_match(sym, sym_name, &cnt, -1)) {
+			pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n",
+			       ++cnt, sym->start,
+			       sym->binding == STB_GLOBAL ? 'g' :
+			       sym->binding == STB_LOCAL  ? 'l' : 'w',
+			       sym->name);
+			near = true;
+		} else if (near) {
+			near = false;
+			pr_err("\t\twhich is near\t\t%s\n", sym->name);
+		}
+		sym = dso__next_symbol(sym);
+	}
+
+	pr_err("Disambiguate symbol name by inserting #n after the name e.g. %s #2\n",
+	       sym_name);
+	pr_err("Or select a global symbol by inserting #0 or #g or #G\n");
+}
+
+static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
+			u64 *size, int idx)
+{
+	struct symbol *sym;
+	int cnt = 0;
+
+	*start = 0;
+	*size = 0;
+
+	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	while (sym) {
+		if (*start) {
+			if (!*size)
+				*size = sym->start - *start;
+			if (idx > 0) {
+				if (*size)
+					return 1;
+			} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
+				print_duplicate_syms(dso, sym_name);
+				return -EINVAL;
+			}
+		} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
+			*start = sym->start;
+			*size = sym->end - sym->start;
+		}
+		sym = dso__next_symbol(sym);
+	}
+
+	if (!*start)
+		return sym_not_found_error(sym_name, idx);
+
+	return 0;
+}
+
+static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
+{
+	struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION);
+	struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION);
+
+	if (!first_sym || !last_sym) {
+		pr_err("Failed to determine filter for %s\nNo symbols found.\n",
+		       filt->filename);
+		return -EINVAL;
+	}
+
+	filt->addr = first_sym->start;
+	filt->size = last_sym->end - first_sym->start;
+
+	return 0;
+}
+
+static int addr_filter__resolve_syms(struct addr_filter *filt)
+{
+	u64 start, size;
+	struct dso *dso;
+	int err = 0;
+
+	if (!filt->sym_from && !filt->sym_to)
+		return 0;
+
+	if (!filt->filename)
+		return addr_filter__resolve_kernel_syms(filt);
+
+	dso = load_dso(filt->filename);
+	if (!dso) {
+		pr_err("Failed to load symbols from: %s\n", filt->filename);
+		return -EINVAL;
+	}
+
+	if (filt->sym_from && !strcmp(filt->sym_from, "*")) {
+		err = addr_filter__entire_dso(filt, dso);
+		goto put_dso;
+	}
+
+	if (filt->sym_from) {
+		err = find_dso_sym(dso, filt->sym_from, &start, &size,
+				   filt->sym_from_idx);
+		if (err)
+			goto put_dso;
+		filt->addr = start;
+		if (filt->range && !filt->size && !filt->sym_to)
+			filt->size = size;
+	}
+
+	if (filt->sym_to) {
+		err = find_dso_sym(dso, filt->sym_to, &start, &size,
+				   filt->sym_to_idx);
+		if (err)
+			goto put_dso;
+
+		err = check_end_after_start(filt, start, size);
+		if (err)
+			return err;
+
+		filt->size = start + size - filt->addr;
+	}
+
+put_dso:
+	dso__put(dso);
+
+	return err;
+}
+
+static char *addr_filter__to_str(struct addr_filter *filt)
+{
+	char filename_buf[PATH_MAX];
+	const char *at = "";
+	const char *fn = "";
+	char *filter;
+	int err;
+
+	if (filt->filename) {
+		at = "@";
+		fn = realpath(filt->filename, filename_buf);
+		if (!fn)
+			return NULL;
+	}
+
+	if (filt->range) {
+		err = asprintf(&filter, "%s 0x%"PRIx64"/0x%"PRIx64"%s%s",
+			       filt->action, filt->addr, filt->size, at, fn);
+	} else {
+		err = asprintf(&filter, "%s 0x%"PRIx64"%s%s",
+			       filt->action, filt->addr, at, fn);
+	}
+
+	return err < 0 ? NULL : filter;
+}
+
+static int parse_addr_filter(struct perf_evsel *evsel, const char *filter,
+			     int max_nr)
+{
+	struct addr_filters filts;
+	struct addr_filter *filt;
+	int err;
+
+	addr_filters__init(&filts);
+
+	err = addr_filters__parse_bare_filter(&filts, filter);
+	if (err)
+		goto out_exit;
+
+	if (filts.cnt > max_nr) {
+		pr_err("Error: number of address filters (%d) exceeds maximum (%d)\n",
+		       filts.cnt, max_nr);
+		err = -EINVAL;
+		goto out_exit;
+	}
+
+	list_for_each_entry(filt, &filts.head, list) {
+		char *new_filter;
+
+		err = addr_filter__resolve_syms(filt);
+		if (err)
+			goto out_exit;
+
+		new_filter = addr_filter__to_str(filt);
+		if (!new_filter) {
+			err = -ENOMEM;
+			goto out_exit;
+		}
+
+		if (perf_evsel__append_addr_filter(evsel, new_filter)) {
+			err = -ENOMEM;
+			goto out_exit;
+		}
+	}
+
+out_exit:
+	addr_filters__exit(&filts);
+
+	if (err) {
+		pr_err("Failed to parse address filter: '%s'\n", filter);
+		pr_err("Filter format is: filter|start|stop|tracestop <start symbol or address> [/ <end symbol or size>] [@<file name>]\n");
+		pr_err("Where multiple filters are separated by space or comma.\n");
+	}
+
+	return err;
+}
+
+static struct perf_pmu *perf_evsel__find_pmu(struct perf_evsel *evsel)
+{
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		if (pmu->type == evsel->attr.type)
+			break;
+	}
+
+	return pmu;
+}
+
+static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel)
+{
+	struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
+	int nr_addr_filters = 0;
+
+	if (!pmu)
+		return 0;
+
+	perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters);
+
+	return nr_addr_filters;
+}
+
+int auxtrace_parse_filters(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	char *filter;
+	int err, max_nr;
+
+	evlist__for_each_entry(evlist, evsel) {
+		filter = evsel->filter;
+		max_nr = perf_evsel__nr_addr_filter(evsel);
+		if (!filter || !max_nr)
+			continue;
+		evsel->filter = NULL;
+		err = parse_addr_filter(evsel, filter, max_nr);
+		free(filter);
+		if (err)
+			return err;
+		pr_debug("Address filter: %s\n", evsel->filter);
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index ac5f0d7167e6..26fb1ee5746a 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -41,6 +41,7 @@ enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
 	PERF_AUXTRACE_INTEL_PT,
 	PERF_AUXTRACE_INTEL_BTS,
+	PERF_AUXTRACE_CS_ETM,
 };
 
 enum itrace_period_type {
@@ -317,6 +318,48 @@ struct auxtrace_record {
 	unsigned int alignment;
 };
 
+/**
+ * struct addr_filter - address filter.
+ * @list: list node
+ * @range: true if it is a range filter
+ * @start: true if action is 'filter' or 'start'
+ * @action: 'filter', 'start' or 'stop' ('tracestop' is accepted but converted
+ *          to 'stop')
+ * @sym_from: symbol name for the filter address
+ * @sym_to: symbol name that determines the filter size
+ * @sym_from_idx: selects n'th from symbols with the same name (0 means global
+ *                and less than 0 means symbol must be unique)
+ * @sym_to_idx: same as @sym_from_idx but for @sym_to
+ * @addr: filter address
+ * @size: filter region size (for range filters)
+ * @filename: DSO file name or NULL for the kernel
+ * @str: allocated string that contains the other string members
+ */
+struct addr_filter {
+	struct list_head	list;
+	bool			range;
+	bool			start;
+	const char		*action;
+	const char		*sym_from;
+	const char		*sym_to;
+	int			sym_from_idx;
+	int			sym_to_idx;
+	u64			addr;
+	u64			size;
+	const char		*filename;
+	char			*str;
+};
+
+/**
+ * struct addr_filters - list of address filters.
+ * @head: list of address filters
+ * @cnt: number of address filters
+ */
+struct addr_filters {
+	struct list_head	head;
+	int			cnt;
+};
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 /*
@@ -481,6 +524,12 @@ void perf_session__auxtrace_error_inc(struct perf_session *session,
 				      union perf_event *event);
 void events_stats__auxtrace_error_warn(const struct events_stats *stats);
 
+void addr_filters__init(struct addr_filters *filts);
+void addr_filters__exit(struct addr_filters *filts);
+int addr_filters__parse_bare_filter(struct addr_filters *filts,
+				    const char *filter);
+int auxtrace_parse_filters(struct perf_evlist *evlist);
+
 static inline int auxtrace__process_event(struct perf_session *session,
 					  union perf_event *event,
 					  struct perf_sample *sample,
@@ -639,6 +688,12 @@ void auxtrace_index__free(struct list_head *head __maybe_unused)
 {
 }
 
+static inline
+int auxtrace_parse_filters(struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
 			void *userpg, int fd);
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
new file mode 100644
index 000000000000..7b3e1d75d803
--- /dev/null
+++ b/tools/perf/util/block-range.c
@@ -0,0 +1,328 @@
+#include "block-range.h"
+#include "annotate.h"
+
+struct {
+	struct rb_root root;
+	u64 blocks;
+} block_ranges;
+
+static void block_range__debug(void)
+{
+	/*
+	 * XXX still paranoid for now; see if we can make this depend on
+	 * DEBUG=1 builds.
+	 */
+#if 1
+	struct rb_node *rb;
+	u64 old = 0; /* NULL isn't executable */
+
+	for (rb = rb_first(&block_ranges.root); rb; rb = rb_next(rb)) {
+		struct block_range *entry = rb_entry(rb, struct block_range, node);
+
+		assert(old < entry->start);
+		assert(entry->start <= entry->end); /* single instruction block; jump to a jump */
+
+		old = entry->end;
+	}
+#endif
+}
+
+struct block_range *block_range__find(u64 addr)
+{
+	struct rb_node **p = &block_ranges.root.rb_node;
+	struct rb_node *parent = NULL;
+	struct block_range *entry;
+
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct block_range, node);
+
+		if (addr < entry->start)
+			p = &parent->rb_left;
+		else if (addr > entry->end)
+			p = &parent->rb_right;
+		else
+			return entry;
+	}
+
+	return NULL;
+}
+
+static inline void rb_link_left_of_node(struct rb_node *left, struct rb_node *node)
+{
+	struct rb_node **p = &node->rb_left;
+	while (*p) {
+		node = *p;
+		p = &node->rb_right;
+	}
+	rb_link_node(left, node, p);
+}
+
+static inline void rb_link_right_of_node(struct rb_node *right, struct rb_node *node)
+{
+	struct rb_node **p = &node->rb_right;
+	while (*p) {
+		node = *p;
+		p = &node->rb_left;
+	}
+	rb_link_node(right, node, p);
+}
+
+/**
+ * block_range__create
+ * @start: branch target starting this basic block
+ * @end:   branch ending this basic block
+ *
+ * Create all the required block ranges to precisely span the given range.
+ */
+struct block_range_iter block_range__create(u64 start, u64 end)
+{
+	struct rb_node **p = &block_ranges.root.rb_node;
+	struct rb_node *n, *parent = NULL;
+	struct block_range *next, *entry = NULL;
+	struct block_range_iter iter = { NULL, NULL };
+
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct block_range, node);
+
+		if (start < entry->start)
+			p = &parent->rb_left;
+		else if (start > entry->end)
+			p = &parent->rb_right;
+		else
+			break;
+	}
+
+	/*
+	 * Didn't find anything.. there's a hole at @start, however @end might
+	 * be inside/behind the next range.
+	 */
+	if (!*p) {
+		if (!entry) /* tree empty */
+			goto do_whole;
+
+		/*
+		 * If the last node is before, advance one to find the next.
+		 */
+		n = parent;
+		if (entry->end < start) {
+			n = rb_next(n);
+			if (!n)
+				goto do_whole;
+		}
+		next = rb_entry(n, struct block_range, node);
+
+		if (next->start <= end) { /* add head: [start...][n->start...] */
+			struct block_range *head = malloc(sizeof(struct block_range));
+			if (!head)
+				return iter;
+
+			*head = (struct block_range){
+				.start		= start,
+				.end		= next->start - 1,
+				.is_target	= 1,
+				.is_branch	= 0,
+			};
+
+			rb_link_left_of_node(&head->node, &next->node);
+			rb_insert_color(&head->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.start = head;
+			goto do_tail;
+		}
+
+do_whole:
+		/*
+		 * The whole [start..end] range is non-overlapping.
+		 */
+		entry = malloc(sizeof(struct block_range));
+		if (!entry)
+			return iter;
+
+		*entry = (struct block_range){
+			.start		= start,
+			.end		= end,
+			.is_target	= 1,
+			.is_branch	= 1,
+		};
+
+		rb_link_node(&entry->node, parent, p);
+		rb_insert_color(&entry->node, &block_ranges.root);
+		block_range__debug();
+
+		iter.start = entry;
+		iter.end   = entry;
+		goto done;
+	}
+
+	/*
+	 * We found a range that overlapped with ours, split if needed.
+	 */
+	if (entry->start < start) { /* split: [e->start...][start...] */
+		struct block_range *head = malloc(sizeof(struct block_range));
+		if (!head)
+			return iter;
+
+		*head = (struct block_range){
+			.start		= entry->start,
+			.end		= start - 1,
+			.is_target	= entry->is_target,
+			.is_branch	= 0,
+
+			.coverage	= entry->coverage,
+			.entry		= entry->entry,
+		};
+
+		entry->start		= start;
+		entry->is_target	= 1;
+		entry->entry		= 0;
+
+		rb_link_left_of_node(&head->node, &entry->node);
+		rb_insert_color(&head->node, &block_ranges.root);
+		block_range__debug();
+
+	} else if (entry->start == start)
+		entry->is_target = 1;
+
+	iter.start = entry;
+
+do_tail:
+	/*
+	 * At this point we've got: @iter.start = [@start...] but @end can still be
+	 * inside or beyond it.
+	 */
+	entry = iter.start;
+	for (;;) {
+		/*
+		 * If @end is inside @entry, split.
+		 */
+		if (end < entry->end) { /* split: [...end][...e->end] */
+			struct block_range *tail = malloc(sizeof(struct block_range));
+			if (!tail)
+				return iter;
+
+			*tail = (struct block_range){
+				.start		= end + 1,
+				.end		= entry->end,
+				.is_target	= 0,
+				.is_branch	= entry->is_branch,
+
+				.coverage	= entry->coverage,
+				.taken		= entry->taken,
+				.pred		= entry->pred,
+			};
+
+			entry->end		= end;
+			entry->is_branch	= 1;
+			entry->taken		= 0;
+			entry->pred		= 0;
+
+			rb_link_right_of_node(&tail->node, &entry->node);
+			rb_insert_color(&tail->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.end = entry;
+			goto done;
+		}
+
+		/*
+		 * If @end matches @entry, done
+		 */
+		if (end == entry->end) {
+			entry->is_branch = 1;
+			iter.end = entry;
+			goto done;
+		}
+
+		next = block_range__next(entry);
+		if (!next)
+			goto add_tail;
+
+		/*
+		 * If @end is in beyond @entry but not inside @next, add tail.
+		 */
+		if (end < next->start) { /* add tail: [...e->end][...end] */
+			struct block_range *tail;
+add_tail:
+			tail = malloc(sizeof(struct block_range));
+			if (!tail)
+				return iter;
+
+			*tail = (struct block_range){
+				.start		= entry->end + 1,
+				.end		= end,
+				.is_target	= 0,
+				.is_branch	= 1,
+			};
+
+			rb_link_right_of_node(&tail->node, &entry->node);
+			rb_insert_color(&tail->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.end = tail;
+			goto done;
+		}
+
+		/*
+		 * If there is a hole between @entry and @next, fill it.
+		 */
+		if (entry->end + 1 != next->start) {
+			struct block_range *hole = malloc(sizeof(struct block_range));
+			if (!hole)
+				return iter;
+
+			*hole = (struct block_range){
+				.start		= entry->end + 1,
+				.end		= next->start - 1,
+				.is_target	= 0,
+				.is_branch	= 0,
+			};
+
+			rb_link_left_of_node(&hole->node, &next->node);
+			rb_insert_color(&hole->node, &block_ranges.root);
+			block_range__debug();
+		}
+
+		entry = next;
+	}
+
+done:
+	assert(iter.start->start == start && iter.start->is_target);
+	assert(iter.end->end == end && iter.end->is_branch);
+
+	block_ranges.blocks++;
+
+	return iter;
+}
+
+
+/*
+ * Compute coverage as:
+ *
+ *    br->coverage / br->sym->max_coverage
+ *
+ * This ensures each symbol has a 100% spot, to reflect that each symbol has a
+ * most covered section.
+ *
+ * Returns [0-1] for coverage and -1 if we had no data what so ever or the
+ * symbol does not exist.
+ */
+double block_range__coverage(struct block_range *br)
+{
+	struct symbol *sym;
+
+	if (!br) {
+		if (block_ranges.blocks)
+			return 0;
+
+		return -1;
+	}
+
+	sym = br->sym;
+	if (!sym)
+		return -1;
+
+	return (double)br->coverage / symbol__annotation(sym)->max_coverage;
+}
diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h
new file mode 100644
index 000000000000..a8c841381131
--- /dev/null
+++ b/tools/perf/util/block-range.h
@@ -0,0 +1,71 @@
+#ifndef __PERF_BLOCK_RANGE_H
+#define __PERF_BLOCK_RANGE_H
+
+#include "symbol.h"
+
+/*
+ * struct block_range - non-overlapping parts of basic blocks
+ * @node:	treenode
+ * @start:	inclusive start of range
+ * @end:	inclusive end of range
+ * @is_target:	@start is a jump target
+ * @is_branch:	@end is a branch instruction
+ * @coverage:	number of blocks that cover this range
+ * @taken:	number of times the branch is taken (requires @is_branch)
+ * @pred:	number of times the taken branch was predicted
+ */
+struct block_range {
+	struct rb_node node;
+
+	struct symbol *sym;
+
+	u64 start;
+	u64 end;
+
+	int is_target, is_branch;
+
+	u64 coverage;
+	u64 entry;
+	u64 taken;
+	u64 pred;
+};
+
+static inline struct block_range *block_range__next(struct block_range *br)
+{
+	struct rb_node *n = rb_next(&br->node);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct block_range, node);
+}
+
+struct block_range_iter {
+	struct block_range *start;
+	struct block_range *end;
+};
+
+static inline struct block_range *block_range_iter(struct block_range_iter *iter)
+{
+	return iter->start;
+}
+
+static inline bool block_range_iter__next(struct block_range_iter *iter)
+{
+	if (iter->start == iter->end)
+		return false;
+
+	iter->start = block_range__next(iter->start);
+	return true;
+}
+
+static inline bool block_range_iter__valid(struct block_range_iter *iter)
+{
+	if (!iter->start || !iter->end)
+		return false;
+	return true;
+}
+
+extern struct block_range *block_range__find(u64 addr);
+extern struct block_range_iter block_range__create(u64 start, u64 end);
+extern double block_range__coverage(struct block_range *br);
+
+#endif /* __PERF_BLOCK_RANGE_H */
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 1f12e4e40006..2b2c9b82f5ab 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -531,7 +531,7 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping,
 
 	ptevs = malloc(array_sz);
 	if (!ptevs) {
-		pr_debug("No ehough memory: alloc ptevs failed\n");
+		pr_debug("No enough memory: alloc ptevs failed\n");
 		return -ENOMEM;
 	}
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 5651f3c12f93..e528c40739cc 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -620,7 +620,7 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id,
 
 	ret = probe_cache__scan_sdt(cache, realname);
 	if (ret >= 0) {
-		pr_debug("Found %d SDTs in %s\n", ret, realname);
+		pr_debug4("Found %d SDTs in %s\n", ret, realname);
 		if (probe_cache__commit(cache) < 0)
 			ret = -1;
 	}
@@ -691,7 +691,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 
 	/* Update SDT cache : error is just warned */
 	if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
-		pr_debug("Failed to update/scan SDT cache for %s\n", realname);
+		pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
 	if (!is_kallsyms)
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
new file mode 100644
index 000000000000..3cc6bc3263fe
--- /dev/null
+++ b/tools/perf/util/cs-etm.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
+#define INCLUDE__UTIL_PERF_CS_ETM_H__
+
+/* Versionning header in case things need tro change in the future.  That way
+ * decoding of old snapshot is still possible.
+ */
+enum {
+	/* Starting with 0x0 */
+	CS_HEADER_VERSION_0,
+	/* PMU->type (32 bit), total # of CPUs (32 bit) */
+	CS_PMU_TYPE_CPUS,
+	CS_ETM_SNAPSHOT,
+	CS_HEADER_VERSION_0_MAX,
+};
+
+/* Beginning of header common to both ETMv3 and V4 */
+enum {
+	CS_ETM_MAGIC,
+	CS_ETM_CPU,
+};
+
+/* ETMv3/PTM metadata */
+enum {
+	/* Dynamic, configurable parameters */
+	CS_ETM_ETMCR = CS_ETM_CPU + 1,
+	CS_ETM_ETMTRACEIDR,
+	/* RO, taken from sysFS */
+	CS_ETM_ETMCCER,
+	CS_ETM_ETMIDR,
+	CS_ETM_PRIV_MAX,
+};
+
+/* ETMv4 metadata */
+enum {
+	/* Dynamic, configurable parameters */
+	CS_ETMV4_TRCCONFIGR = CS_ETM_CPU + 1,
+	CS_ETMV4_TRCTRACEIDR,
+	/* RO, taken from sysFS */
+	CS_ETMV4_TRCIDR0,
+	CS_ETMV4_TRCIDR1,
+	CS_ETMV4_TRCIDR2,
+	CS_ETMV4_TRCIDR8,
+	CS_ETMV4_TRCAUTHSTATUS,
+	CS_ETMV4_PRIV_MAX,
+};
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+
+#define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64))
+
+static const u64 __perf_cs_etmv3_magic   = 0x3030303030303030ULL;
+static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
+#define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64))
+#define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64))
+
+#endif
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 4f979bb27b6c..7123f4de32cc 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -437,7 +437,7 @@ add_bpf_output_values(struct bt_ctf_event_class *event_class,
 	int ret;
 
 	if (nr_elements * sizeof(u32) != raw_size)
-		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %zu bytes\n",
 			   raw_size, nr_elements * sizeof(u32) - raw_size);
 
 	len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 8c4212abd19b..c1838b643108 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -6,6 +6,7 @@
 #include <stdarg.h>
 #include <stdio.h>
 #include <api/debug.h>
+#include <linux/time64.h>
 
 #include "cache.h"
 #include "color.h"
@@ -14,9 +15,6 @@
 #include "util.h"
 #include "target.h"
 
-#define NSECS_PER_SEC  1000000000ULL
-#define NSECS_PER_USEC 1000ULL
-
 int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
@@ -54,9 +52,9 @@ static int veprintf_time(u64 t, const char *fmt, va_list args)
 	int ret = 0;
 	u64 secs, usecs, nsecs = t;
 
-	secs   = nsecs / NSECS_PER_SEC;
-	nsecs -= secs  * NSECS_PER_SEC;
-	usecs  = nsecs / NSECS_PER_USEC;
+	secs   = nsecs / NSEC_PER_SEC;
+	nsecs -= secs  * NSEC_PER_SEC;
+	usecs  = nsecs / NSEC_PER_USEC;
 
 	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
 		      secs, usecs);
diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c
new file mode 100644
index 000000000000..1647f285c629
--- /dev/null
+++ b/tools/perf/util/drv_configs.c
@@ -0,0 +1,77 @@
+/*
+ * drv_configs.h: Interface to apply PMU specific configuration
+ * Copyright (c) 2016-2018, Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "drv_configs.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "pmu.h"
+
+static int
+perf_evsel__apply_drv_configs(struct perf_evsel *evsel,
+			      struct perf_evsel_config_term **err_term)
+{
+	bool found = false;
+	int err = 0;
+	struct perf_evsel_config_term *term;
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		if (pmu->type == evsel->attr.type) {
+			found = true;
+			break;
+		}
+
+	list_for_each_entry(term, &evsel->config_terms, list) {
+		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
+			continue;
+
+		/*
+		 * We have a configuration term, report an error if we
+		 * can't find the PMU or if the PMU driver doesn't support
+		 * cmd line driver configuration.
+		 */
+		if (!found || !pmu->set_drv_config) {
+			err = -EINVAL;
+			*err_term = term;
+			break;
+		}
+
+		err = pmu->set_drv_config(term);
+		if (err) {
+			*err_term = term;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
+				   struct perf_evsel **err_evsel,
+				   struct perf_evsel_config_term **err_term)
+{
+	struct perf_evsel *evsel;
+	int err = 0;
+
+	evlist__for_each_entry(evlist, evsel) {
+		err = perf_evsel__apply_drv_configs(evsel, err_term);
+		if (err) {
+			*err_evsel = evsel;
+			break;
+		}
+	}
+
+	return err;
+}
diff --git a/tools/perf/util/drv_configs.h b/tools/perf/util/drv_configs.h
new file mode 100644
index 000000000000..32bc9babc2e0
--- /dev/null
+++ b/tools/perf/util/drv_configs.h
@@ -0,0 +1,26 @@
+/*
+ * drv_configs.h: Interface to apply PMU specific configuration
+ * Copyright (c) 2016-2018, Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_DRV_CONFIGS_H
+#define __PERF_DRV_CONFIGS_H
+
+#include "drv_configs.h"
+#include "evlist.h"
+#include "evsel.h"
+
+int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
+				   struct perf_evsel **err_evsel,
+				   struct perf_evsel_config_term **term);
+#endif
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 774f6ec884d5..d2c6cdd9d42b 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -363,6 +363,9 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
+	if (!is_regular_file(name))
+		return -EINVAL;
+
 	fd = do_open(name);
 	free(name);
 	return fd;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index a347b19c961a..41e068e94349 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -130,6 +130,22 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 }
 
 /**
+ * die_get_linkage_name - Get the linkage name of the object
+ * @dw_die: A DIE of the object
+ *
+ * Get the linkage name attiribute of given @dw_die.
+ * For C++ binary, the linkage name will be the mangled symbol.
+ */
+const char *die_get_linkage_name(Dwarf_Die *dw_die)
+{
+	Dwarf_Attribute attr;
+
+	if (dwarf_attr_integrate(dw_die, DW_AT_linkage_name, &attr) == NULL)
+		return NULL;
+	return dwarf_formstring(&attr);
+}
+
+/**
  * die_compare_name - Compare diename and tname
  * @dw_die: a DIE
  * @tname: a string of target name
@@ -145,18 +161,26 @@ bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 }
 
 /**
- * die_match_name - Match diename and glob
+ * die_match_name - Match diename/linkage name and glob
  * @dw_die: a DIE
  * @glob: a string of target glob pattern
  *
  * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ * This also match linkage name.
  */
 bool die_match_name(Dwarf_Die *dw_die, const char *glob)
 {
 	const char *name;
 
 	name = dwarf_diename(dw_die);
-	return name ? strglobmatch(name, glob) : false;
+	if (name && strglobmatch(name, glob))
+		return true;
+	/* fall back to check linkage name */
+	name = die_get_linkage_name(dw_die);
+	if (name && strglobmatch(name, glob))
+		return true;
+
+	return false;
 }
 
 /**
@@ -1085,3 +1109,182 @@ int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
 	return -ENOTSUP;
 }
 #endif
+
+/*
+ * die_has_loclist - Check if DW_AT_location of @vr_die is a location list
+ * @vr_die: a variable DIE
+ */
+static bool die_has_loclist(Dwarf_Die *vr_die)
+{
+	Dwarf_Attribute loc;
+	int tag = dwarf_tag(vr_die);
+
+	if (tag != DW_TAG_formal_parameter &&
+	    tag != DW_TAG_variable)
+		return false;
+
+	return (dwarf_attr_integrate(vr_die, DW_AT_location, &loc) &&
+		dwarf_whatform(&loc) == DW_FORM_sec_offset);
+}
+
+/*
+ * die_is_optimized_target - Check if target program is compiled with
+ * optimization
+ * @cu_die: a CU DIE
+ *
+ * For any object in given CU whose DW_AT_location is a location list,
+ * target program is compiled with optimization. This is applicable to
+ * clang as well.
+ */
+bool die_is_optimized_target(Dwarf_Die *cu_die)
+{
+	Dwarf_Die tmp_die;
+
+	if (die_has_loclist(cu_die))
+		return true;
+
+	if (!dwarf_child(cu_die, &tmp_die) &&
+	    die_is_optimized_target(&tmp_die))
+		return true;
+
+	if (!dwarf_siblingof(cu_die, &tmp_die) &&
+	    die_is_optimized_target(&tmp_die))
+		return true;
+
+	return false;
+}
+
+/*
+ * die_search_idx - Search index of given line address
+ * @lines: Line records of single CU
+ * @nr_lines: Number of @lines
+ * @addr: address we are looking for
+ * @idx: index to be set by this function (return value)
+ *
+ * Search for @addr by looping over every lines of CU. If address
+ * matches, set index of that line in @idx. Note that single source
+ * line can have multiple line records. i.e. single source line can
+ * have multiple index.
+ */
+static bool die_search_idx(Dwarf_Lines *lines, unsigned long nr_lines,
+			   Dwarf_Addr addr, unsigned long *idx)
+{
+	unsigned long i;
+	Dwarf_Addr tmp;
+
+	for (i = 0; i < nr_lines; i++) {
+		if (dwarf_lineaddr(dwarf_onesrcline(lines, i), &tmp))
+			return false;
+
+		if (tmp == addr) {
+			*idx = i;
+			return true;
+		}
+	}
+	return false;
+}
+
+/*
+ * die_get_postprologue_addr - Search next address after function prologue
+ * @entrypc_idx: entrypc index
+ * @lines: Line records of single CU
+ * @nr_lines: Number of @lines
+ * @hignpc: high PC address of function
+ * @postprologue_addr: Next address after function prologue (return value)
+ *
+ * Look for prologue-end marker. If there is no explicit marker, return
+ * address of next line record or next source line.
+ */
+static bool die_get_postprologue_addr(unsigned long entrypc_idx,
+				      Dwarf_Lines *lines,
+				      unsigned long nr_lines,
+				      Dwarf_Addr highpc,
+				      Dwarf_Addr *postprologue_addr)
+{
+	unsigned long i;
+	int entrypc_lno, lno;
+	Dwarf_Line *line;
+	Dwarf_Addr addr;
+	bool p_end;
+
+	/* entrypc_lno is actual source line number */
+	line = dwarf_onesrcline(lines, entrypc_idx);
+	if (dwarf_lineno(line, &entrypc_lno))
+		return false;
+
+	for (i = entrypc_idx; i < nr_lines; i++) {
+		line = dwarf_onesrcline(lines, i);
+
+		if (dwarf_lineaddr(line, &addr) ||
+		    dwarf_lineno(line, &lno)    ||
+		    dwarf_lineprologueend(line, &p_end))
+			return false;
+
+		/* highpc is exclusive. [entrypc,highpc) */
+		if (addr >= highpc)
+			break;
+
+		/* clang supports prologue-end marker */
+		if (p_end)
+			break;
+
+		/* Actual next line in source */
+		if (lno != entrypc_lno)
+			break;
+
+		/*
+		 * Single source line can have multiple line records.
+		 * For Example,
+		 *     void foo() { printf("hello\n"); }
+		 * contains two line records. One points to declaration and
+		 * other points to printf() line. Variable 'lno' won't get
+		 * incremented in this case but 'i' will.
+		 */
+		if (i != entrypc_idx)
+			break;
+	}
+
+	dwarf_lineaddr(line, postprologue_addr);
+	if (*postprologue_addr >= highpc)
+		dwarf_lineaddr(dwarf_onesrcline(lines, i - 1),
+			       postprologue_addr);
+
+	return true;
+}
+
+/*
+ * die_skip_prologue - Use next address after prologue as probe location
+ * @sp_die: a subprogram DIE
+ * @cu_die: a CU DIE
+ * @entrypc: entrypc of the function
+ *
+ * Function prologue prepares stack and registers before executing function
+ * logic. When target program is compiled without optimization, function
+ * parameter information is only valid after prologue. When we probe entrypc
+ * of the function, and try to record function parameter, it contains
+ * garbage value.
+ */
+void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
+		       Dwarf_Addr *entrypc)
+{
+	size_t nr_lines = 0;
+	unsigned long entrypc_idx = 0;
+	Dwarf_Lines *lines = NULL;
+	Dwarf_Addr postprologue_addr;
+	Dwarf_Addr highpc;
+
+	if (dwarf_highpc(sp_die, &highpc))
+		return;
+
+	if (dwarf_getsrclines(cu_die, &lines, &nr_lines))
+		return;
+
+	if (!die_search_idx(lines, nr_lines, *entrypc, &entrypc_idx))
+		return;
+
+	if (!die_get_postprologue_addr(entrypc_idx, lines, nr_lines,
+				       highpc, &postprologue_addr))
+		return;
+
+	*entrypc = postprologue_addr;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index dc0ce1adb075..8ac53bf1ec4e 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -38,6 +38,9 @@ int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
 int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 			 int (*callback)(Dwarf_Die *, void *), void *data);
 
+/* Get DW_AT_linkage_name (should be NULL for C binary) */
+const char *die_get_linkage_name(Dwarf_Die *dw_die);
+
 /* Ensure that this DIE is a subprogram and definition (not declaration) */
 bool die_is_func_def(Dwarf_Die *dw_die);
 
@@ -125,4 +128,12 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 /* Get the name and type of given variable DIE, stored as "type\tname" */
 int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
 int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
+
+/* Check if target program is compiled with optimization */
+bool die_is_optimized_target(Dwarf_Die *cu_die);
+
+/* Use next address after prologue as probe location */
+void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
+		       Dwarf_Addr *entrypc);
+
 #endif
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
new file mode 100644
index 000000000000..62bc4a86a970
--- /dev/null
+++ b/tools/perf/util/dwarf-regs.c
@@ -0,0 +1,59 @@
+/*
+ * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
+ *
+ * Written by: Masami Hiramatsu <mhiramat@kernel.org>
+ */
+
+#include <util.h>
+#include <debug.h>
+#include <dwarf-regs.h>
+#include <elf.h>
+
+#ifndef EM_AARCH64
+#define EM_AARCH64	183  /* ARM 64 bit */
+#endif
+
+/* Define const char * {arch}_register_tbl[] */
+#define DEFINE_DWARF_REGSTR_TABLE
+#include "../arch/x86/include/dwarf-regs-table.h"
+#include "../arch/arm/include/dwarf-regs-table.h"
+#include "../arch/arm64/include/dwarf-regs-table.h"
+#include "../arch/sh/include/dwarf-regs-table.h"
+#include "../arch/powerpc/include/dwarf-regs-table.h"
+#include "../arch/s390/include/dwarf-regs-table.h"
+#include "../arch/sparc/include/dwarf-regs-table.h"
+#include "../arch/xtensa/include/dwarf-regs-table.h"
+
+#define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL)
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
+{
+	switch (machine) {
+	case EM_NONE:	/* Generic arch - use host arch */
+		return get_arch_regstr(n);
+	case EM_386:
+		return __get_dwarf_regstr(x86_32_regstr_tbl, n);
+	case EM_X86_64:
+		return __get_dwarf_regstr(x86_64_regstr_tbl, n);
+	case EM_ARM:
+		return __get_dwarf_regstr(arm_regstr_tbl, n);
+	case EM_AARCH64:
+		return __get_dwarf_regstr(aarch64_regstr_tbl, n);
+	case EM_SH:
+		return __get_dwarf_regstr(sh_regstr_tbl, n);
+	case EM_S390:
+		return __get_dwarf_regstr(s390_regstr_tbl, n);
+	case EM_PPC:
+	case EM_PPC64:
+		return __get_dwarf_regstr(powerpc_regstr_tbl, n);
+	case EM_SPARC:
+	case EM_SPARCV9:
+		return __get_dwarf_regstr(sparc_regstr_tbl, n);
+	case EM_XTENSA:
+		return __get_dwarf_regstr(xtensa_regstr_tbl, n);
+	default:
+		pr_err("ELF MACHINE %x is not supported.\n", machine);
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index e20438b784be..8ab0d7da956b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,5 +1,6 @@
 #include <linux/types.h>
-#include <sys/mman.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <api/fs/fs.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -248,6 +249,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	bool truncation = false;
 	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
+	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
+	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
 
 	if (machine__is_default_guest(machine))
 		return 0;
@@ -343,6 +346,12 @@ out:
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
 
+		if (hugetlbfs_mnt_len &&
+		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
+			strcpy(execname, anonstr);
+			event->mmap2.flags |= MAP_HUGETLB;
+		}
+
 		size = strlen(execname) + 1;
 		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
@@ -1286,7 +1295,7 @@ try_again:
 		 * must be done prior to using kernel maps.
 		 */
 		if (load_map)
-			map__load(al->map, machine->symbol_filter);
+			map__load(al->map);
 		al->addr = al->map->map_ip(al->map, al->addr);
 	}
 }
@@ -1297,8 +1306,7 @@ void thread__find_addr_location(struct thread *thread,
 {
 	thread__find_addr_map(thread, cpumode, type, addr, al);
 	if (al->map != NULL)
-		al->sym = map__find_symbol(al->map, al->addr,
-					   thread->mg->machine->symbol_filter);
+		al->sym = map__find_symbol(al->map, al->addr);
 	else
 		al->sym = NULL;
 }
@@ -1359,8 +1367,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 			al->filtered |= (1 << HIST_FILTER__DSO);
 		}
 
-		al->sym = map__find_symbol(al->map, al->addr,
-					   machine->symbol_filter);
+		al->sym = map__find_symbol(al->map, al->addr);
 	}
 
 	if (symbol_conf.sym_list &&
@@ -1416,5 +1423,5 @@ void thread__resolve(struct thread *thread, struct addr_location *al,
 	al->sym = NULL;
 
 	if (al->map)
-		al->sym = map__find_symbol(al->map, al->addr, NULL);
+		al->sym = map__find_symbol(al->map, al->addr);
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 097b3ed77fdd..ea34c5a32c11 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1032,16 +1032,18 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-				       struct mmap_params *mp, int cpu,
+				       struct mmap_params *mp, int cpu_idx,
 				       int thread, int *_output, int *_output_backward)
 {
 	struct perf_evsel *evsel;
 	int revent;
+	int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
 
 	evlist__for_each_entry(evlist, evsel) {
 		struct perf_mmap *maps = evlist->mmap;
 		int *output = _output;
 		int fd;
+		int cpu;
 
 		if (evsel->attr.write_backward) {
 			output = _output_backward;
@@ -1060,6 +1062,10 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		if (evsel->system_wide && thread)
 			continue;
 
+		cpu = cpu_map__idx(evsel->cpus, evlist_cpu);
+		if (cpu == -1)
+			continue;
+
 		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21fd573106ed..380e84c3af3d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1045,15 +1045,15 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter)
 	return -1;
 }
 
-int perf_evsel__append_filter(struct perf_evsel *evsel,
-			      const char *op, const char *filter)
+static int perf_evsel__append_filter(struct perf_evsel *evsel,
+				     const char *fmt, const char *filter)
 {
 	char *new_filter;
 
 	if (evsel->filter == NULL)
 		return perf_evsel__set_filter(evsel, filter);
 
-	if (asprintf(&new_filter,"(%s) %s (%s)", evsel->filter, op, filter) > 0) {
+	if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) {
 		free(evsel->filter);
 		evsel->filter = new_filter;
 		return 0;
@@ -1062,6 +1062,16 @@ int perf_evsel__append_filter(struct perf_evsel *evsel,
 	return -1;
 }
 
+int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter)
+{
+	return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
+}
+
+int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
+{
+	return perf_evsel__append_filter(evsel, "%s,%s", filter);
+}
+
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
 	int nthreads = thread_map__nr(evsel->threads);
@@ -1728,7 +1738,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = evsel->attr.sample_period;
-	data->weight = 0;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -1935,7 +1944,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		}
 	}
 
-	data->weight = 0;
 	if (type & PERF_SAMPLE_WEIGHT) {
 		OVERFLOW_CHECK_u64(array);
 		data->weight = *array;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4d44129e050b..b1503b0ecdff 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
+	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -57,6 +58,7 @@ struct perf_evsel_config_term {
 		u64	freq;
 		bool	time;
 		char	*callgraph;
+		char	*drv_cfg;
 		u64	stack_user;
 		int	max_stack;
 		bool	inherit;
@@ -233,8 +235,9 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel,
 			       bool use_sample_identifier);
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter);
-int perf_evsel__append_filter(struct perf_evsel *evsel,
-			      const char *op, const char *filter);
+int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter);
+int perf_evsel__append_addr_filter(struct perf_evsel *evsel,
+				   const char *filter);
 int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			     const char *filter);
 int perf_evsel__enable(struct perf_evsel *evsel);
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 3674e77ad640..662a0a6182e7 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -122,9 +122,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (!node)
 				break;
 
-			if (node->sym && node->sym->ignore)
-				goto next;
-
 			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
 
 			if (print_ip)
@@ -158,7 +155,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
-next:
+
 			callchain_cursor_advance(cursor);
 		}
 	}
@@ -181,7 +178,7 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
 	if (cursor != NULL) {
 		printed += sample__fprintf_callchain(sample, left_alignment,
 						     print_opts, cursor, fp);
-	} else if (!(al->sym && al->sym->ignore)) {
+	} else {
 		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
 
 		if (print_ip)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8f0db4007282..85dd0db0a127 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -828,8 +828,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
-int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused,
-				     size_t sz __maybe_unused)
+int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
 {
 	return -1;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index de15dbcdcecf..b02992efb513 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -177,8 +177,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
 
-	if (h->srcline)
-		hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline));
+	if (h->srcline) {
+		len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
+		hists__new_col_len(hists, HISTC_SRCLINE, len);
+	}
 
 	if (h->srcfile)
 		hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile));
@@ -417,6 +419,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 	INIT_LIST_HEAD(&he->pairs.node);
 	thread__get(he->thread);
+	he->hroot_in  = RB_ROOT;
+	he->hroot_out = RB_ROOT;
 
 	if (!symbol_conf.report_hierarchy)
 		he->leaf = true;
@@ -2149,6 +2153,50 @@ out:
 	return he;
 }
 
+static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists,
+						    struct rb_root *root,
+						    struct hist_entry *pair)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct hist_entry *he;
+	struct perf_hpp_fmt *fmt;
+
+	p = &root->rb_node;
+	while (*p != NULL) {
+		int64_t cmp = 0;
+
+		parent = *p;
+		he = rb_entry(parent, struct hist_entry, rb_node_in);
+
+		perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, he, pair);
+			if (cmp)
+				break;
+		}
+		if (!cmp)
+			goto out;
+
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	he = hist_entry__new(pair, true);
+	if (he) {
+		rb_link_node(&he->rb_node_in, parent, p);
+		rb_insert_color(&he->rb_node_in, root);
+
+		he->dummy = true;
+		he->hists = hists;
+		memset(&he->stat, 0, sizeof(he->stat));
+		hists__inc_stats(hists, he);
+	}
+out:
+	return he;
+}
+
 static struct hist_entry *hists__find_entry(struct hists *hists,
 					    struct hist_entry *he)
 {
@@ -2174,6 +2222,51 @@ static struct hist_entry *hists__find_entry(struct hists *hists,
 	return NULL;
 }
 
+static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root,
+						      struct hist_entry *he)
+{
+	struct rb_node *n = root->rb_node;
+
+	while (n) {
+		struct hist_entry *iter;
+		struct perf_hpp_fmt *fmt;
+		int64_t cmp = 0;
+
+		iter = rb_entry(n, struct hist_entry, rb_node_in);
+		perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, iter, he);
+			if (cmp)
+				break;
+		}
+
+		if (cmp < 0)
+			n = n->rb_left;
+		else if (cmp > 0)
+			n = n->rb_right;
+		else
+			return iter;
+	}
+
+	return NULL;
+}
+
+static void hists__match_hierarchy(struct rb_root *leader_root,
+				   struct rb_root *other_root)
+{
+	struct rb_node *nd;
+	struct hist_entry *pos, *pair;
+
+	for (nd = rb_first(leader_root); nd; nd = rb_next(nd)) {
+		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
+		pair = hists__find_hierarchy_entry(other_root, pos);
+
+		if (pair) {
+			hist_entry__add_pair(pair, pos);
+			hists__match_hierarchy(&pos->hroot_in, &pair->hroot_in);
+		}
+	}
+}
+
 /*
  * Look for pairs to link to the leader buckets (hist_entries):
  */
@@ -2183,6 +2276,12 @@ void hists__match(struct hists *leader, struct hists *other)
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
+	if (symbol_conf.report_hierarchy) {
+		/* hierarchy report always collapses entries */
+		return hists__match_hierarchy(&leader->entries_collapsed,
+					      &other->entries_collapsed);
+	}
+
 	if (hists__has(leader, need_collapse))
 		root = &leader->entries_collapsed;
 	else
@@ -2197,6 +2296,50 @@ void hists__match(struct hists *leader, struct hists *other)
 	}
 }
 
+static int hists__link_hierarchy(struct hists *leader_hists,
+				 struct hist_entry *parent,
+				 struct rb_root *leader_root,
+				 struct rb_root *other_root)
+{
+	struct rb_node *nd;
+	struct hist_entry *pos, *leader;
+
+	for (nd = rb_first(other_root); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(pos)) {
+			bool found = false;
+
+			list_for_each_entry(leader, &pos->pairs.head, pairs.node) {
+				if (leader->hists == leader_hists) {
+					found = true;
+					break;
+				}
+			}
+			if (!found)
+				return -1;
+		} else {
+			leader = add_dummy_hierarchy_entry(leader_hists,
+							   leader_root, pos);
+			if (leader == NULL)
+				return -1;
+
+			/* do not point parent in the pos */
+			leader->parent_he = parent;
+
+			hist_entry__add_pair(pos, leader);
+		}
+
+		if (!pos->leaf) {
+			if (hists__link_hierarchy(leader_hists, leader,
+						  &leader->hroot_in,
+						  &pos->hroot_in) < 0)
+				return -1;
+		}
+	}
+	return 0;
+}
+
 /*
  * Look for entries in the other hists that are not present in the leader, if
  * we find them, just add a dummy entry on the leader hists, with period=0,
@@ -2208,6 +2351,13 @@ int hists__link(struct hists *leader, struct hists *other)
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
+	if (symbol_conf.report_hierarchy) {
+		/* hierarchy report always collapses entries */
+		return hists__link_hierarchy(leader, NULL,
+					     &leader->entries_collapsed,
+					     &other->entries_collapsed);
+	}
+
 	if (hists__has(other, need_collapse))
 		root = &other->entries_collapsed;
 	else
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 0a1edf1ab450..9928fed8bc59 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -230,7 +230,7 @@ struct perf_hpp {
 struct perf_hpp_fmt {
 	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		      struct hists *hists);
+		      struct hists *hists, int line, int *span);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		     struct hists *hists);
 	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -259,6 +259,7 @@ struct perf_hpp_list {
 	struct list_head fields;
 	struct list_head sorts;
 
+	int nr_header_lines;
 	int need_collapse;
 	int parent;
 	int sym;
@@ -367,6 +368,7 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 void perf_hpp__set_user_width(const char *width_list_str);
+void hists__reset_column_width(struct hists *hists);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
@@ -483,5 +485,10 @@ static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
 #define HIERARCHY_INDENT  3
 
 bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...);
+int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...);
+int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+			   struct perf_hpp_list *hpp_list);
+int hists__fprintf_headers(struct hists *hists, FILE *fp);
 
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 07c644ed64c4..43bfd8da7919 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -3,6 +3,12 @@
 
 #ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
+/*
+ * get_dwarf_regstr - Returns ftrace register string from DWARF regnum
+ * n: DWARF register number
+ * machine: ELF machine signature (EM_*)
+ */
+const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
 #endif
 
 #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 749e6f2e37ca..f545ec1e758a 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -346,7 +346,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
 		goto out_put;
 
 	/* Load maps to ensure dso->is_64_bit has been updated */
-	map__load(al.map, machine->symbol_filter);
+	map__load(al.map);
 
 	x86_64 = al.map->dso->is_64_bit;
 
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 8ff6c6a61291..7591a0c37473 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -80,6 +80,7 @@ struct intel_pt_decoder {
 	int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
 			 uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
 			 uint64_t max_insn_cnt, void *data);
+	bool (*pgd_ip)(uint64_t ip, void *data);
 	void *data;
 	struct intel_pt_state state;
 	const unsigned char *buf;
@@ -186,6 +187,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 
 	decoder->get_trace          = params->get_trace;
 	decoder->walk_insn          = params->walk_insn;
+	decoder->pgd_ip             = params->pgd_ip;
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 
@@ -1008,6 +1010,19 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 	int err;
 
 	err = intel_pt_walk_insn(decoder, &intel_pt_insn, 0);
+	if (err == INTEL_PT_RETURN &&
+	    decoder->pgd_ip &&
+	    decoder->pkt_state == INTEL_PT_STATE_TIP_PGD &&
+	    (decoder->state.type & INTEL_PT_BRANCH) &&
+	    decoder->pgd_ip(decoder->state.to_ip, decoder->data)) {
+		/* Unconditional branch leaving filter region */
+		decoder->no_progress = 0;
+		decoder->pge = false;
+		decoder->continuous_period = false;
+		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+		decoder->state.to_ip = 0;
+		return 0;
+	}
 	if (err == INTEL_PT_RETURN)
 		return 0;
 	if (err)
@@ -1036,6 +1051,21 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 	}
 
 	if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
+		uint64_t to_ip = decoder->ip + intel_pt_insn.length +
+				 intel_pt_insn.rel;
+
+		if (decoder->pgd_ip &&
+		    decoder->pkt_state == INTEL_PT_STATE_TIP_PGD &&
+		    decoder->pgd_ip(to_ip, decoder->data)) {
+			/* Conditional branch leaving filter region */
+			decoder->pge = false;
+			decoder->continuous_period = false;
+			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+			decoder->ip = to_ip;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			return 0;
+		}
 		intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
 				decoder->ip);
 		decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
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 02c38fec1c37..89399985fa4d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -83,6 +83,7 @@ struct intel_pt_params {
 	int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
 			 uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
 			 uint64_t max_insn_cnt, void *data);
+	bool (*pgd_ip)(uint64_t ip, void *data);
 	void *data;
 	bool return_compression;
 	uint64_t period;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 551ff6f640be..dc041d4368c8 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -103,6 +103,9 @@ struct intel_pt {
 	unsigned max_non_turbo_ratio;
 
 	unsigned long num_events;
+
+	char *filter;
+	struct addr_filters filts;
 };
 
 enum switch_state {
@@ -241,7 +244,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 
 	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-
+next:
 	buffer = auxtrace_buffer__next(queue, buffer);
 	if (!buffer) {
 		if (old_buffer)
@@ -264,9 +267,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
 		return -ENOMEM;
 
-	if (old_buffer)
-		auxtrace_buffer__drop_data(old_buffer);
-
 	if (buffer->use_data) {
 		b->len = buffer->use_size;
 		b->buf = buffer->use_data;
@@ -276,6 +276,16 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 	b->ref_timestamp = buffer->reference;
 
+	/*
+	 * If in snapshot mode and the buffer has no usable data, get next
+	 * buffer and again check overlap against old_buffer.
+	 */
+	if (ptq->pt->snapshot_mode && !b->len)
+		goto next;
+
+	if (old_buffer)
+		auxtrace_buffer__drop_data(old_buffer);
+
 	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
 						      !buffer->consecutive)) {
 		b->consecutive = false;
@@ -477,7 +487,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 		start_ip = *ip;
 
 		/* Load maps to ensure dso->is_64_bit has been updated */
-		map__load(al.map, machine->symbol_filter);
+		map__load(al.map);
 
 		x86_64 = al.map->dso->is_64_bit;
 
@@ -541,6 +551,76 @@ out_no_cache:
 	return 0;
 }
 
+static bool intel_pt_match_pgd_ip(struct intel_pt *pt, uint64_t ip,
+				  uint64_t offset, const char *filename)
+{
+	struct addr_filter *filt;
+	bool have_filter   = false;
+	bool hit_tracestop = false;
+	bool hit_filter    = false;
+
+	list_for_each_entry(filt, &pt->filts.head, list) {
+		if (filt->start)
+			have_filter = true;
+
+		if ((filename && !filt->filename) ||
+		    (!filename && filt->filename) ||
+		    (filename && strcmp(filename, filt->filename)))
+			continue;
+
+		if (!(offset >= filt->addr && offset < filt->addr + filt->size))
+			continue;
+
+		intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s hit filter: %s offset %#"PRIx64" size %#"PRIx64"\n",
+			     ip, offset, filename ? filename : "[kernel]",
+			     filt->start ? "filter" : "stop",
+			     filt->addr, filt->size);
+
+		if (filt->start)
+			hit_filter = true;
+		else
+			hit_tracestop = true;
+	}
+
+	if (!hit_tracestop && !hit_filter)
+		intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s is not in a filter region\n",
+			     ip, offset, filename ? filename : "[kernel]");
+
+	return hit_tracestop || (have_filter && !hit_filter);
+}
+
+static int __intel_pt_pgd_ip(uint64_t ip, void *data)
+{
+	struct intel_pt_queue *ptq = data;
+	struct thread *thread;
+	struct addr_location al;
+	u8 cpumode;
+	u64 offset;
+
+	if (ip >= ptq->pt->kernel_start)
+		return intel_pt_match_pgd_ip(ptq->pt, ip, ip, NULL);
+
+	cpumode = PERF_RECORD_MISC_USER;
+
+	thread = ptq->thread;
+	if (!thread)
+		return -EINVAL;
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
+	if (!al.map || !al.map->dso)
+		return -EINVAL;
+
+	offset = al.map->map_ip(al.map, ip);
+
+	return intel_pt_match_pgd_ip(ptq->pt, ip, offset,
+				     al.map->dso->long_name);
+}
+
+static bool intel_pt_pgd_ip(uint64_t ip, void *data)
+{
+	return __intel_pt_pgd_ip(ip, data) > 0;
+}
+
 static bool intel_pt_get_config(struct intel_pt *pt,
 				struct perf_event_attr *attr, u64 *config)
 {
@@ -717,6 +797,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n;
 	params.tsc_ctc_ratio_d = pt->tsc_ctc_ratio_d;
 
+	if (pt->filts.cnt > 0)
+		params.pgd_ip = intel_pt_pgd_ip;
+
 	if (pt->synth_opts.instructions) {
 		if (pt->synth_opts.period) {
 			switch (pt->synth_opts.period_type) {
@@ -1294,7 +1377,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	if (!map)
 		return 0;
 
-	if (map__load(map, machine->symbol_filter))
+	if (map__load(map))
 		return 0;
 
 	start = dso__first_symbol(map->dso, MAP__FUNCTION);
@@ -1767,6 +1850,8 @@ static void intel_pt_free(struct perf_session *session)
 	intel_pt_free_events(session);
 	session->auxtrace = NULL;
 	thread__put(pt->unknown_thread);
+	addr_filters__exit(&pt->filts);
+	zfree(&pt->filter);
 	free(pt);
 }
 
@@ -2016,6 +2101,8 @@ static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_TSC_CTC_N]		= "  TSC:CTC numerator   %"PRIu64"\n",
 	[INTEL_PT_TSC_CTC_D]		= "  TSC:CTC denominator %"PRIu64"\n",
 	[INTEL_PT_CYC_BIT]		= "  CYC bit             %#"PRIx64"\n",
+	[INTEL_PT_MAX_NONTURBO_RATIO]	= "  Max non-turbo ratio %"PRIu64"\n",
+	[INTEL_PT_FILTER_STR_LEN]	= "  Filter string len.  %"PRIu64"\n",
 };
 
 static void intel_pt_print_info(u64 *arr, int start, int finish)
@@ -2029,12 +2116,28 @@ static void intel_pt_print_info(u64 *arr, int start, int finish)
 		fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
 }
 
+static void intel_pt_print_info_str(const char *name, const char *str)
+{
+	if (!dump_trace)
+		return;
+
+	fprintf(stdout, "  %-20s%s\n", name, str ? str : "");
+}
+
+static bool intel_pt_has(struct auxtrace_info_event *auxtrace_info, int pos)
+{
+	return auxtrace_info->header.size >=
+		sizeof(struct auxtrace_info_event) + (sizeof(u64) * (pos + 1));
+}
+
 int intel_pt_process_auxtrace_info(union perf_event *event,
 				   struct perf_session *session)
 {
 	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
 	size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
 	struct intel_pt *pt;
+	void *info_end;
+	u64 *info;
 	int err;
 
 	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
@@ -2045,6 +2148,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (!pt)
 		return -ENOMEM;
 
+	addr_filters__init(&pt->filts);
+
 	perf_config(intel_pt_perf_config, pt);
 
 	err = auxtrace_queues__init(&pt->queues);
@@ -2069,8 +2174,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_PMU_TYPE,
 			    INTEL_PT_PER_CPU_MMAPS);
 
-	if (auxtrace_info->header.size >= sizeof(struct auxtrace_info_event) +
-					(sizeof(u64) * INTEL_PT_CYC_BIT)) {
+	if (intel_pt_has(auxtrace_info, INTEL_PT_CYC_BIT)) {
 		pt->mtc_bit = auxtrace_info->priv[INTEL_PT_MTC_BIT];
 		pt->mtc_freq_bits = auxtrace_info->priv[INTEL_PT_MTC_FREQ_BITS];
 		pt->tsc_ctc_ratio_n = auxtrace_info->priv[INTEL_PT_TSC_CTC_N];
@@ -2080,6 +2184,54 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 				    INTEL_PT_CYC_BIT);
 	}
 
+	if (intel_pt_has(auxtrace_info, INTEL_PT_MAX_NONTURBO_RATIO)) {
+		pt->max_non_turbo_ratio =
+			auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO];
+		intel_pt_print_info(&auxtrace_info->priv[0],
+				    INTEL_PT_MAX_NONTURBO_RATIO,
+				    INTEL_PT_MAX_NONTURBO_RATIO);
+	}
+
+	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
+	info_end = (void *)info + auxtrace_info->header.size;
+
+	if (intel_pt_has(auxtrace_info, INTEL_PT_FILTER_STR_LEN)) {
+		size_t len;
+
+		len = auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN];
+		intel_pt_print_info(&auxtrace_info->priv[0],
+				    INTEL_PT_FILTER_STR_LEN,
+				    INTEL_PT_FILTER_STR_LEN);
+		if (len) {
+			const char *filter = (const char *)info;
+
+			len = roundup(len + 1, 8);
+			info += len >> 3;
+			if ((void *)info > info_end) {
+				pr_err("%s: bad filter string length\n", __func__);
+				err = -EINVAL;
+				goto err_free_queues;
+			}
+			pt->filter = memdup(filter, len);
+			if (!pt->filter) {
+				err = -ENOMEM;
+				goto err_free_queues;
+			}
+			if (session->header.needs_swap)
+				mem_bswap_64(pt->filter, len);
+			if (pt->filter[len - 1]) {
+				pr_err("%s: filter string not null terminated\n", __func__);
+				err = -EINVAL;
+				goto err_free_queues;
+			}
+			err = addr_filters__parse_bare_filter(&pt->filts,
+							      filter);
+			if (err)
+				goto err_free_queues;
+		}
+		intel_pt_print_info_str("Filter string", pt->filter);
+	}
+
 	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
 	pt->have_tsc = intel_pt_have_tsc(pt);
 	pt->sampling_mode = false;
@@ -2121,11 +2273,13 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		pt->switch_evsel = intel_pt_find_sched_switch(session->evlist);
 		if (!pt->switch_evsel) {
 			pr_err("%s: missing sched_switch event\n", __func__);
+			err = -EINVAL;
 			goto err_delete_thread;
 		}
 	} else if (pt->have_sched_switch == 2 &&
 		   !intel_pt_find_switch(session->evlist)) {
 		pr_err("%s: missing context_switch attribute flag\n", __func__);
+		err = -EINVAL;
 		goto err_delete_thread;
 	}
 
@@ -2149,7 +2303,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (pt->tc.time_mult) {
 		u64 tsc_freq = intel_pt_ns_to_ticks(pt, 1000000000);
 
-		pt->max_non_turbo_ratio = (tsc_freq + 50000000) / 100000000;
+		if (!pt->max_non_turbo_ratio)
+			pt->max_non_turbo_ratio =
+					(tsc_freq + 50000000) / 100000000;
 		intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq);
 		intel_pt_log("Maximum non-turbo ratio %u\n",
 			     pt->max_non_turbo_ratio);
@@ -2193,6 +2349,8 @@ err_free_queues:
 	auxtrace_queues__free(&pt->queues);
 	session->auxtrace = NULL;
 err_free:
+	addr_filters__exit(&pt->filts);
+	zfree(&pt->filter);
 	free(pt);
 	return err;
 }
diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h
index 0065949df693..e13b14e5a37b 100644
--- a/tools/perf/util/intel-pt.h
+++ b/tools/perf/util/intel-pt.h
@@ -34,11 +34,11 @@ enum {
 	INTEL_PT_TSC_CTC_N,
 	INTEL_PT_TSC_CTC_D,
 	INTEL_PT_CYC_BIT,
+	INTEL_PT_MAX_NONTURBO_RATIO,
+	INTEL_PT_FILTER_STR_LEN,
 	INTEL_PT_AUXTRACE_PRIV_MAX,
 };
 
-#define INTEL_PT_AUXTRACE_PRIV_SIZE (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64))
-
 struct auxtrace_record;
 struct perf_tool;
 union perf_event;
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 95a1acb61245..9ddea5cecd94 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -29,6 +29,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 	lzma_action action = LZMA_RUN;
 	lzma_stream strm   = LZMA_STREAM_INIT;
 	lzma_ret ret;
+	int err = -1;
 
 	u8 buf_in[BUFSIZE];
 	u8 buf_out[BUFSIZE];
@@ -45,7 +46,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 	if (ret != LZMA_OK) {
 		pr_err("lzma: lzma_stream_decoder failed %s (%d)\n",
 			lzma_strerror(ret), ret);
-		return -1;
+		goto err_fclose;
 	}
 
 	strm.next_in   = NULL;
@@ -60,7 +61,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (ferror(infile)) {
 				pr_err("lzma: read error: %s\n", strerror(errno));
-				return -1;
+				goto err_fclose;
 			}
 
 			if (feof(infile))
@@ -74,7 +75,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 			if (writen(output_fd, buf_out, write_size) != write_size) {
 				pr_err("lzma: write error: %s\n", strerror(errno));
-				return -1;
+				goto err_fclose;
 			}
 
 			strm.next_out  = buf_out;
@@ -83,13 +84,15 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 		if (ret != LZMA_OK) {
 			if (ret == LZMA_STREAM_END)
-				return 0;
+				break;
 
 			pr_err("lzma: failed %s\n", lzma_strerror(ret));
-			return -1;
+			goto err_fclose;
 		}
 	}
 
+	err = 0;
+err_fclose:
 	fclose(infile);
-	return 0;
+	return err;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index cb6388dbdd98..18e4519abef2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -41,7 +41,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->pid = pid;
 
-	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
 	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
@@ -148,7 +147,6 @@ void machines__init(struct machines *machines)
 {
 	machine__init(&machines->host, "", HOST_KERNEL_ID);
 	machines->guests = RB_ROOT;
-	machines->symbol_filter = NULL;
 }
 
 void machines__exit(struct machines *machines)
@@ -172,8 +170,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 		return NULL;
 	}
 
-	machine->symbol_filter = machines->symbol_filter;
-
 	while (*p != NULL) {
 		parent = *p;
 		pos = rb_entry(parent, struct machine, rb_node);
@@ -189,21 +185,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 	return machine;
 }
 
-void machines__set_symbol_filter(struct machines *machines,
-				 symbol_filter_t symbol_filter)
-{
-	struct rb_node *nd;
-
-	machines->symbol_filter = symbol_filter;
-	machines->host.symbol_filter = symbol_filter;
-
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
-		struct machine *machine = rb_entry(nd, struct machine, rb_node);
-
-		machine->symbol_filter = symbol_filter;
-	}
-}
-
 void machines__set_comm_exec(struct machines *machines, bool comm_exec)
 {
 	struct rb_node *nd;
@@ -916,10 +897,10 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 }
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore, symbol_filter_t filter)
+			     enum map_type type, bool no_kcore)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter);
+	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore);
 
 	if (ret > 0) {
 		dso__set_loaded(map->dso, type);
@@ -935,16 +916,15 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename,
 }
 
 int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
+			   enum map_type type)
 {
-	return __machine__load_kallsyms(machine, filename, type, false, filter);
+	return __machine__load_kallsyms(machine, filename, type, false);
 }
 
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter)
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+	int ret = dso__load_vmlinux_path(map->dso, map);
 
 	if (ret > 0)
 		dso__set_loaded(map->dso, type);
@@ -1313,7 +1293,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			/*
 			 * preload dso of guest kernel and modules
 			 */
-			dso__load(kernel, machine__kernel_map(machine), NULL);
+			dso__load(kernel, machine__kernel_map(machine));
 		}
 	}
 	return 0;
@@ -2115,7 +2095,7 @@ int machine__get_kernel_start(struct machine *machine)
 	 */
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
-		err = map__load(map, machine->symbol_filter);
+		err = map__load(map);
 		if (map->start)
 			machine->kernel_start = map->start;
 	}
@@ -2131,7 +2111,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 {
 	struct machine *machine = vmachine;
 	struct map *map;
-	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map,  NULL);
+	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map);
 
 	if (sym == NULL)
 		return NULL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 20739f746bc4..354de6e56109 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -41,7 +41,6 @@ struct machine {
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	u64		  kernel_start;
-	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
 	union { /* Tool specific area */
 		void	  *priv;
@@ -110,7 +109,6 @@ typedef void (*machine__process_t)(struct machine *machine, void *data);
 struct machines {
 	struct machine host;
 	struct rb_root guests;
-	symbol_filter_t symbol_filter;
 };
 
 void machines__init(struct machines *machines);
@@ -128,8 +126,6 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid);
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
-void machines__set_symbol_filter(struct machines *machines,
-				 symbol_filter_t symbol_filter);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
@@ -178,40 +174,33 @@ size_t machine__fprintf(struct machine *machine, FILE *fp);
 static inline
 struct symbol *machine__find_kernel_symbol(struct machine *machine,
 					   enum map_type type, u64 addr,
-					   struct map **mapp,
-					   symbol_filter_t filter)
+					   struct map **mapp)
 {
-	return map_groups__find_symbol(&machine->kmaps, type, addr,
-				       mapp, filter);
+	return map_groups__find_symbol(&machine->kmaps, type, addr, mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 						   enum map_type type, const char *name,
-						   struct map **mapp,
-						   symbol_filter_t filter)
+						   struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
-					       mapp, filter);
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
-					     struct map **mapp,
-					     symbol_filter_t filter)
+					     struct map **mapp)
 {
 	return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
-					   mapp, filter);
+					   mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 						     const char *name,
-						     struct map **mapp,
-						     symbol_filter_t filter)
+						     struct map **mapp)
 {
-	return map_groups__find_function_by_name(&machine->kmaps, name, mapp,
-						 filter);
+	return map_groups__find_function_by_name(&machine->kmaps, name, mapp);
 }
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
@@ -219,11 +208,10 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 int arch__fix_module_text_start(u64 *start, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore, symbol_filter_t filter);
+			     enum map_type type, bool no_kcore);
 int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter);
+			   enum map_type type);
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
 
 size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 728129ac653a..c662fef95d14 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -6,6 +6,7 @@
 #include <string.h>
 #include <stdio.h>
 #include <unistd.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include "map.h"
 #include "thread.h"
 #include "strlist.h"
@@ -24,9 +25,10 @@ const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__VARIABLE] = "Variables",
 };
 
-static inline int is_anon_memory(const char *filename)
+static inline int is_anon_memory(const char *filename, u32 flags)
 {
-	return !strcmp(filename, "//anon") ||
+	return flags & MAP_HUGETLB ||
+	       !strcmp(filename, "//anon") ||
 	       !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
 	       !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
 }
@@ -155,7 +157,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		int anon, no_dso, vdso, android;
 
 		android = is_android_lib(filename);
-		anon = is_anon_memory(filename);
+		anon = is_anon_memory(filename, flags);
 		vdso = is_vdso_map(filename);
 		no_dso = is_no_dso_memory(filename);
 
@@ -279,7 +281,7 @@ void map__fixup_end(struct map *map)
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *map, symbol_filter_t filter)
+int map__load(struct map *map)
 {
 	const char *name = map->dso->long_name;
 	int nr;
@@ -287,7 +289,7 @@ int map__load(struct map *map, symbol_filter_t filter)
 	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(map->dso, map, filter);
+	nr = dso__load(map->dso, map);
 	if (nr < 0) {
 		if (map->dso->has_build_id) {
 			char sbuild_id[SBUILD_ID_SIZE];
@@ -312,9 +314,6 @@ int map__load(struct map *map, symbol_filter_t filter)
 			pr_warning("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
-		} else if (filter) {
-			pr_warning("no symbols passed the given filter.\n");
-			return -2;	/* Empty but maybe by the filter */
 		} else {
 			pr_warning("no symbols found in %s, maybe install "
 				   "a debug package?\n", name);
@@ -331,19 +330,17 @@ int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
 	return strcmp(namea, nameb);
 }
 
-struct symbol *map__find_symbol(struct map *map, u64 addr,
-				symbol_filter_t filter)
+struct symbol *map__find_symbol(struct map *map, u64 addr)
 {
-	if (map__load(map, filter) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
-					symbol_filter_t filter)
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 {
-	if (map__load(map, filter) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	if (!dso__sorted_by_name(map->dso, map->type))
@@ -556,23 +553,22 @@ void map_groups__put(struct map_groups *mg)
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
-				       struct map **mapp,
-				       symbol_filter_t filter)
+				       struct map **mapp)
 {
 	struct map *map = map_groups__find(mg, type, addr);
 
 	/* Ensure map is loaded before using map->map_ip */
-	if (map != NULL && map__load(map, filter) >= 0) {
+	if (map != NULL && map__load(map) >= 0) {
 		if (mapp != NULL)
 			*mapp = map;
-		return map__find_symbol(map, map->map_ip(map, addr), filter);
+		return map__find_symbol(map, map->map_ip(map, addr));
 	}
 
 	return NULL;
 }
 
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-					 struct map **mapp, symbol_filter_t filter)
+					 struct map **mapp)
 {
 	struct symbol *sym;
 	struct rb_node *nd;
@@ -582,7 +578,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 
-		sym = map__find_symbol_by_name(pos, name, filter);
+		sym = map__find_symbol_by_name(pos, name);
 
 		if (sym == NULL)
 			continue;
@@ -600,15 +596,14 @@ out:
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
-					       struct map **mapp,
-					       symbol_filter_t filter)
+					       struct map **mapp)
 {
-	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp, filter);
+	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp);
 
 	return sym;
 }
 
-int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
+int map_groups__find_ams(struct addr_map_symbol *ams)
 {
 	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
@@ -620,7 +615,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	}
 
 	ams->al_addr = ams->map->map_ip(ams->map, ams->addr);
-	ams->sym = map__find_symbol(ams->map, ams->al_addr, filter);
+	ams->sym = map__find_symbol(ams->map, ams->al_addr);
 
 	return ams->sym ? 0 : -1;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index d83396ceecba..abdacf800c98 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -127,17 +127,14 @@ struct thread;
  * @map: the 'struct map *' in which symbols itereated
  * @sym_name: the symbol name
  * @pos: the 'struct symbol *' to use as a loop cursor
- * @filter: to use when loading the DSO
  */
-#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
-	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
+#define __map__for_each_symbol_by_name(map, sym_name, pos)	\
+	for (pos = map__find_symbol_by_name(map, sym_name);	\
 	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
-	__map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
-
-typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
+	__map__for_each_symbol_by_name(map, sym_name, (pos))
 
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
@@ -173,11 +170,9 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
-int map__load(struct map *map, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *map,
-				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
-					symbol_filter_t filter);
+int map__load(struct map *map);
+struct symbol *map__find_symbol(struct map *map, u64 addr);
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
 void map__fixup_start(struct map *map);
 void map__fixup_end(struct map *map);
 
@@ -191,7 +186,7 @@ struct map *maps__find(struct maps *maps, u64 addr);
 struct map *maps__first(struct maps *maps);
 struct map *map__next(struct map *map);
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-                                         struct map **mapp, symbol_filter_t filter);
+                                         struct map **mapp);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct thread *thread,
@@ -231,25 +226,22 @@ static inline struct map *map_groups__next(struct map *map)
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
-				       struct map **mapp,
-				       symbol_filter_t filter);
+				       struct map **mapp);
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
-					       struct map **mapp,
-					       symbol_filter_t filter);
+					       struct map **mapp);
 
 struct addr_map_symbol;
 
-int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
+int map_groups__find_ams(struct addr_map_symbol *ams);
 
 static inline
 struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
-						 const char *name, struct map **mapp,
-						 symbol_filter_t filter)
+						 const char *name, struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
+	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp);
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6c913c3914fb..33546c3ac1fe 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -904,6 +904,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
+	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
 };
 
 static bool config_term_shrinked;
@@ -1034,7 +1035,8 @@ static int config_term_pmu(struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct parse_events_error *err)
 {
-	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER)
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER ||
+	    term->type_term == PARSE_EVENTS__TERM_TYPE_DRV_CFG)
 		/*
 		 * Always succeed for sysfs terms, as we dont know
 		 * at this point what type they need to have.
@@ -1134,6 +1136,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+			ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str);
+			break;
 		default:
 			break;
 		}
@@ -1755,20 +1760,49 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist,
 static int set_filter(struct perf_evsel *evsel, const void *arg)
 {
 	const char *str = arg;
+	bool found = false;
+	int nr_addr_filters = 0;
+	struct perf_pmu *pmu = NULL;
 
-	if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) {
-		fprintf(stderr,
-			"--filter option should follow a -e tracepoint option\n");
-		return -1;
+	if (evsel == NULL)
+		goto err;
+
+	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+		if (perf_evsel__append_tp_filter(evsel, str) < 0) {
+			fprintf(stderr,
+				"not enough memory to hold filter string\n");
+			return -1;
+		}
+
+		return 0;
 	}
 
-	if (perf_evsel__append_filter(evsel, "&&", str) < 0) {
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		if (pmu->type == evsel->attr.type) {
+			found = true;
+			break;
+		}
+
+	if (found)
+		perf_pmu__scan_file(pmu, "nr_addr_filters",
+				    "%d", &nr_addr_filters);
+
+	if (!nr_addr_filters)
+		goto err;
+
+	if (perf_evsel__append_addr_filter(evsel, str) < 0) {
 		fprintf(stderr,
 			"not enough memory to hold filter string\n");
 		return -1;
 	}
 
 	return 0;
+
+err:
+	fprintf(stderr,
+		"--filter option should follow a -e tracepoint or HW tracer option\n");
+
+	return -1;
 }
 
 int parse_filter(const struct option *opt, const char *str,
@@ -1793,7 +1827,7 @@ static int add_exclude_perf_filter(struct perf_evsel *evsel,
 
 	snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid());
 
-	if (perf_evsel__append_filter(evsel, "&&", new_filter) < 0) {
+	if (perf_evsel__append_tp_filter(evsel, new_filter) < 0) {
 		fprintf(stderr,
 			"not enough memory to hold filter string\n");
 		return -1;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d1edbf8cc66a..8d09a976fca8 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
+	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 7a2519435da0..9f43fda2570f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -53,6 +53,26 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+/*
+ * This function is called when the parser gets two kind of input:
+ *
+ * 	@cfg1 or @cfg2=config
+ *
+ * The leading '@' is stripped off before 'cfg1' and 'cfg2=config' are given to
+ * bison.  In the latter case it is necessary to keep the string intact so that
+ * the PMU kernel driver can determine what configurable is associated to
+ * 'config'.
+ */
+static int drv_str(yyscan_t scanner, int token)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	/* Strip off the '@' */
+	yylval->str = strdup(text + 1);
+	return token;
+}
+
 #define REWIND(__alloc)				\
 do {								\
 	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
@@ -124,6 +144,7 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
+drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -209,6 +230,7 @@ no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
 \[all\]			{ return PE_ARRAY_ALL; }
 "["			{ BEGIN(array); return '['; }
+@{drv_cfg_term}		{ return drv_str(yyscanner, PE_DRV_CFG_TERM); }
 }
 
 <mem>{
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 5be4a5f216d6..879115f93edc 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -49,6 +49,7 @@ static void inc_group_count(struct list_head *list,
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %token PE_ARRAY_ALL PE_ARRAY_RANGE
+%token PE_DRV_CFG_TERM
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -63,6 +64,7 @@ static void inc_group_count(struct list_head *list,
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%type <str> PE_DRV_CFG_TERM
 %type <num> value_sym
 %type <head> event_config
 %type <head> opt_event_config
@@ -599,6 +601,15 @@ PE_NAME array '=' PE_VALUE
 	term->array = $2;
 	$$ = term;
 }
+|
+PE_DRV_CFG_TERM
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG,
+					$1, $1, &@1, NULL));
+	$$ = term;
+}
 
 array:
 '[' array_terms ']'
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ddb0261b2577..2babcdf62839 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -445,14 +445,23 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
+	const char *templates[] = {
+		 "%s/bus/event_source/devices/%s/cpumask",
+		 "%s/bus/event_source/devices/%s/cpus",
+		 NULL
+	};
+	const char **template;
 
 	if (!sysfs)
 		return NULL;
 
-	snprintf(path, PATH_MAX,
-		 "%s/bus/event_source/devices/%s/cpumask", sysfs, name);
+	for (template = templates; *template; template++) {
+		snprintf(path, PATH_MAX, *template, sysfs, name);
+		if (stat(path, &st) == 0)
+			break;
+	}
 
-	if (stat(path, &st) < 0)
+	if (!*template)
 		return NULL;
 
 	file = fopen(path, "r");
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 5d7e84466bee..743422ad900b 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -4,6 +4,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
+#include "evsel.h"
 #include "parse-events.h"
 
 enum {
@@ -25,6 +26,7 @@ struct perf_pmu {
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
 	struct list_head list;    /* ELEM */
+	int (*set_drv_config)	(struct perf_evsel_config_term *term);
 };
 
 struct perf_pmu_info {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28733962cd80..fcfbef07b92d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -110,13 +110,12 @@ void exit_probe_symbol_maps(void)
 static struct symbol *__find_kernel_function_by_name(const char *name,
 						     struct map **mapp)
 {
-	return machine__find_kernel_function_by_name(host_machine, name, mapp,
-						     NULL);
+	return machine__find_kernel_function_by_name(host_machine, name, mapp);
 }
 
 static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
 {
-	return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+	return machine__find_kernel_function(host_machine, addr, mapp);
 }
 
 static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
@@ -125,7 +124,7 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 	struct kmap *kmap;
 	struct map *map = machine__kernel_map(host_machine);
 
-	if (map__load(map, NULL) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	kmap = map__kmap(map);
@@ -214,9 +213,13 @@ static int convert_exec_to_group(const char *exec, char **result)
 		goto out;
 	}
 
-	ptr2 = strpbrk(ptr1, "-._");
-	if (ptr2)
-		*ptr2 = '\0';
+	for (ptr2 = ptr1; ptr2 != '\0'; ptr2++) {
+		if (!isalnum(*ptr2) && *ptr2 != '_') {
+			*ptr2 = '\0';
+			break;
+		}
+	}
+
 	ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
 	if (ret < 0)
 		goto out;
@@ -351,9 +354,9 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 	vmlinux_name = symbol_conf.vmlinux_name;
 	dso->load_errno = 0;
 	if (vmlinux_name)
-		ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+		ret = dso__load_vmlinux(dso, map, vmlinux_name, false);
 	else
-		ret = dso__load_vmlinux_path(dso, map, NULL);
+		ret = dso__load_vmlinux_path(dso, map);
 found:
 	*pdso = dso;
 	return ret;
@@ -674,6 +677,10 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 	char *tmp;
 	int i, skipped = 0;
 
+	/* Skip post process if the target is an offline kernel */
+	if (symbol_conf.ignore_vmlinux_buildid)
+		return 0;
+
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (!reloc_sym) {
 		pr_warning("Relocated base symbol is not found!\n");
@@ -1614,19 +1621,27 @@ out:
 	return ret;
 }
 
+/* Returns true if *any* ARG is either C variable, $params or $vars. */
+bool perf_probe_with_var(struct perf_probe_event *pev)
+{
+	int i = 0;
+
+	for (i = 0; i < pev->nargs; i++)
+		if (is_c_varname(pev->args[i].var)              ||
+		    !strcmp(pev->args[i].var, PROBE_ARG_PARAMS) ||
+		    !strcmp(pev->args[i].var, PROBE_ARG_VARS))
+			return true;
+	return false;
+}
+
 /* Return true if this perf_probe_event requires debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
 {
-	int i;
-
 	if (pev->point.file || pev->point.line || pev->point.lazy_line)
 		return true;
 
-	for (i = 0; i < pev->nargs; i++)
-		if (is_c_varname(pev->args[i].var) ||
-		    !strcmp(pev->args[i].var, "$params") ||
-		    !strcmp(pev->args[i].var, "$vars"))
-			return true;
+	if (perf_probe_with_var(pev))
+		return true;
 
 	return false;
 }
@@ -1987,7 +2002,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		map = dso__new_map(tp->module);
 		if (!map)
 			goto out;
-		sym = map__find_symbol(map, addr, NULL);
+		sym = map__find_symbol(map, addr);
 	} else {
 		if (tp->symbol && !addr) {
 			if (kernel_get_symbol_address_by_name(tp->symbol,
@@ -2692,7 +2707,7 @@ static int find_probe_functions(struct map *map, char *name,
 	struct symbol *sym;
 	struct rb_node *tmp;
 
-	if (map__load(map, NULL) < 0)
+	if (map__load(map) < 0)
 		return 0;
 
 	map__for_each_symbol(map, sym, tmp) {
@@ -3207,6 +3222,52 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 	return 0;
 }
 
+static int show_probe_trace_event(struct probe_trace_event *tev)
+{
+	char *buf = synthesize_probe_trace_command(tev);
+
+	if (!buf) {
+		pr_debug("Failed to synthesize probe trace event.\n");
+		return -EINVAL;
+	}
+
+	/* Showing definition always go stdout */
+	printf("%s\n", buf);
+	free(buf);
+
+	return 0;
+}
+
+int show_probe_trace_events(struct perf_probe_event *pevs, int npevs)
+{
+	struct strlist *namelist = strlist__new(NULL, NULL);
+	struct probe_trace_event *tev;
+	struct perf_probe_event *pev;
+	int i, j, ret = 0;
+
+	if (!namelist)
+		return -ENOMEM;
+
+	for (j = 0; j < npevs && !ret; j++) {
+		pev = &pevs[j];
+		for (i = 0; i < pev->ntevs && !ret; i++) {
+			tev = &pev->tevs[i];
+			/* Skip if the symbol is out of .text or blacklisted */
+			if (!tev->point.symbol && !pev->uprobes)
+				continue;
+
+			/* Set new name for tev (and update namelist) */
+			ret = probe_trace_event__set_name(tev, pev,
+							  namelist, true);
+			if (!ret)
+				ret = show_probe_trace_event(tev);
+		}
+	}
+	strlist__delete(namelist);
+
+	return ret;
+}
+
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
 	int i, ret = 0;
@@ -3289,24 +3350,10 @@ out:
 	return ret;
 }
 
-/* TODO: don't use a global variable for filter ... */
-static struct strfilter *available_func_filter;
-
-/*
- * If a symbol corresponds to a function with global binding and
- * matches filter return 0. For all others return 1.
- */
-static int filter_available_functions(struct map *map __maybe_unused,
-				      struct symbol *sym)
-{
-	if (strfilter__compare(available_func_filter, sym->name))
-		return 0;
-	return 1;
-}
-
 int show_available_funcs(const char *target, struct strfilter *_filter,
 					bool user)
 {
+        struct rb_node *nd;
 	struct map *map;
 	int ret;
 
@@ -3324,9 +3371,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 		return -EINVAL;
 	}
 
-	/* Load symbols with given filter */
-	available_func_filter = _filter;
-	ret = map__load(map, filter_available_functions);
+	ret = map__load(map);
 	if (ret) {
 		if (ret == -2) {
 			char *str = strfilter__string(_filter);
@@ -3343,7 +3388,14 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 
 	/* Show all (filtered) symbols */
 	setup_pager();
-	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+
+        for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) {
+		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+
+		if (strfilter__compare(_filter, pos->sym.name))
+			printf("%s\n", pos->sym.name);
+        }
+
 end:
 	if (user) {
 		map__put(map);
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index f4f45db77c1c..8091d15113f7 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,6 +128,8 @@ char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 int perf_probe_event__copy(struct perf_probe_event *dst,
 			   struct perf_probe_event *src);
 
+bool perf_probe_with_var(struct perf_probe_event *pev);
+
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
 
@@ -147,6 +149,7 @@ int line_range__init(struct line_range *lr);
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int show_probe_trace_events(struct perf_probe_event *pevs, int npevs);
 void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 int del_perf_probe_events(struct strfilter *filter);
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 9c3b9ed5b3c3..436b64731f65 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -73,11 +73,10 @@ static void print_both_open_warning(int kerr, int uerr)
 static int open_probe_events(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
-	const char *tracing_dir = "";
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/%s%s",
-			 tracing_path, tracing_dir, trace_file);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s",
+			 tracing_path, trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
@@ -700,7 +699,7 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 	INIT_LIST_HEAD(&sdtlist);
 	ret = get_sdt_note_list(&sdtlist, pathname);
 	if (ret < 0) {
-		pr_debug("Failed to get sdt note: %d\n", ret);
+		pr_debug4("Failed to get sdt note: %d\n", ret);
 		return ret;
 	}
 	list_for_each_entry(note, &sdtlist, note_list) {
@@ -877,3 +876,60 @@ int probe_cache__show_all_caches(struct strfilter *filter)
 
 	return 0;
 }
+
+static struct {
+	const char *pattern;
+	bool	avail;
+	bool	checked;
+} probe_type_table[] = {
+#define DEFINE_TYPE(idx, pat, def_avail)	\
+	[idx] = {.pattern = pat, .avail = (def_avail)}
+	DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true),
+	DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true),
+	DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false),
+	DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true),
+	DEFINE_TYPE(PROBE_TYPE_BITFIELD,
+		    "* b<bit-width>@<bit-offset>/<container-size>", true),
+};
+
+bool probe_type_is_available(enum probe_type type)
+{
+	FILE *fp;
+	char *buf = NULL;
+	size_t len = 0;
+	bool target_line = false;
+	bool ret = probe_type_table[type].avail;
+
+	if (type >= PROBE_TYPE_END)
+		return false;
+	/* We don't have to check the type which supported by default */
+	if (ret || probe_type_table[type].checked)
+		return ret;
+
+	if (asprintf(&buf, "%s/README", tracing_path) < 0)
+		return ret;
+
+	fp = fopen(buf, "r");
+	if (!fp)
+		goto end;
+
+	zfree(&buf);
+	while (getline(&buf, &len, fp) > 0 && !ret) {
+		if (!target_line) {
+			target_line = !!strstr(buf, " type: ");
+			if (!target_line)
+				continue;
+		} else if (strstr(buf, "\t          ") != buf)
+			break;
+		ret = strglobmatch(buf, probe_type_table[type].pattern);
+	}
+	/* Cache the result */
+	probe_type_table[type].checked = true;
+	probe_type_table[type].avail = ret;
+
+	fclose(fp);
+end:
+	free(buf);
+
+	return ret;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 9577b5c0b487..eba44c3e9dca 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -19,6 +19,15 @@ struct probe_cache {
 	struct list_head entries;
 };
 
+enum probe_type {
+	PROBE_TYPE_U = 0,
+	PROBE_TYPE_S,
+	PROBE_TYPE_X,
+	PROBE_TYPE_STRING,
+	PROBE_TYPE_BITFIELD,
+	PROBE_TYPE_END,
+};
+
 #define PF_FL_UPROBE	1
 #define PF_FL_RW	2
 #define for_each_probe_cache_entry(entry, pcache) \
@@ -54,6 +63,7 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
 struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
 					const char *group, const char *event);
 int probe_cache__show_all_caches(struct strfilter *filter);
+bool probe_type_is_available(enum probe_type type);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 5c290c682afe..df4debe564da 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -39,6 +39,7 @@
 #include "util.h"
 #include "symbol.h"
 #include "probe-finder.h"
+#include "probe-file.h"
 
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
@@ -170,6 +171,7 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
  */
 static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 				     Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
+				     unsigned int machine,
 				     struct probe_trace_arg *tvar)
 {
 	Dwarf_Attribute attr;
@@ -265,7 +267,7 @@ static_var:
 	if (!tvar)
 		return ret2;
 
-	regs = get_arch_regstr(regn);
+	regs = get_dwarf_regstr(regn, machine);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
@@ -297,13 +299,13 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	char sbuf[STRERR_BUFSIZE];
 	int bsize, boffs, total;
 	int ret;
-	char sign;
+	char prefix;
 
 	/* TODO: check all types */
-	if (cast && strcmp(cast, "string") != 0 &&
+	if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "x") != 0 &&
 	    strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
 		/* Non string type is OK */
-		/* and respect signedness cast */
+		/* and respect signedness/hexadecimal cast */
 		tvar->type = strdup(cast);
 		return (tvar->type == NULL) ? -ENOMEM : 0;
 	}
@@ -365,11 +367,15 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	}
 
 	if (cast && (strcmp(cast, "u") == 0))
-		sign = 'u';
+		prefix = 'u';
 	else if (cast && (strcmp(cast, "s") == 0))
-		sign = 's';
+		prefix = 's';
+	else if (cast && (strcmp(cast, "x") == 0) &&
+		 probe_type_is_available(PROBE_TYPE_X))
+		prefix = 'x';
 	else
-		sign = die_is_signed_type(&type) ? 's' : 'u';
+		prefix = die_is_signed_type(&type) ? 's' :
+			 probe_type_is_available(PROBE_TYPE_X) ? 'x' : 'u';
 
 	ret = dwarf_bytesize(&type);
 	if (ret <= 0)
@@ -383,7 +389,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 			dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
 		ret = MAX_BASIC_TYPE_BITS;
 	}
-	ret = snprintf(buf, 16, "%c%d", sign, ret);
+	ret = snprintf(buf, 16, "%c%d", prefix, ret);
 
 formatted:
 	if (ret < 0 || ret >= 16) {
@@ -538,7 +544,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 		 dwarf_diename(vr_die));
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
-					&pf->sp_die, pf->tvar);
+					&pf->sp_die, pf->machine, pf->tvar);
 	if (ret == -ENOENT || ret == -EINVAL) {
 		pr_err("Failed to find the location of the '%s' variable at this address.\n"
 		       " Perhaps it has been optimized out.\n"
@@ -901,6 +907,38 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 	return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
 }
 
+static void skip_prologue(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+	struct perf_probe_point *pp = &pf->pev->point;
+
+	/* Not uprobe? */
+	if (!pf->pev->uprobes)
+		return;
+
+	/* Compiled with optimization? */
+	if (die_is_optimized_target(&pf->cu_die))
+		return;
+
+	/* Don't know entrypc? */
+	if (!pf->addr)
+		return;
+
+	/* Only FUNC and FUNC@SRC are eligible. */
+	if (!pp->function || pp->line || pp->retprobe || pp->lazy_line ||
+	    pp->offset || pp->abs_address)
+		return;
+
+	/* Not interested in func parameter? */
+	if (!perf_probe_with_var(pf->pev))
+		return;
+
+	pr_info("Target program is compiled without optimization. Skipping prologue.\n"
+		"Probe on address 0x%" PRIx64 " to force probing at the function entry.\n\n",
+		pf->addr);
+
+	die_skip_prologue(sp_die, &pf->cu_die, &pf->addr);
+}
+
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
 	struct probe_finder *pf = data;
@@ -917,6 +955,11 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 				   dwarf_diename(in_die));
 			return -ENOENT;
 		}
+		if (addr == 0) {
+			pr_debug("%s has no valid entry address. skipped.\n",
+				 dwarf_diename(in_die));
+			return -ENOENT;
+		}
 		pf->addr = addr;
 		pf->addr += pp->offset;
 		pr_debug("found inline addr: 0x%jx\n",
@@ -950,7 +993,8 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
-	pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
+	pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die),
+		 (unsigned long)dwarf_dieoffset(sp_die));
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -959,10 +1003,16 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	} else if (die_is_func_instance(sp_die)) {
 		/* Instances always have the entry address */
 		dwarf_entrypc(sp_die, &pf->addr);
+		/* But in some case the entry address is 0 */
+		if (pf->addr == 0) {
+			pr_debug("%s has no entry PC. Skipped\n",
+				 dwarf_diename(sp_die));
+			param->retval = 0;
 		/* Real function */
-		if (pp->lazy_line)
+		} else if (pp->lazy_line)
 			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
+			skip_prologue(sp_die, pf);
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
 			param->retval = call_probe_finder(sp_die, pf);
@@ -972,7 +1022,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 		param->retval = die_walk_instances(sp_die,
 					probe_point_inline_cb, (void *)pf);
 		/* This could be a non-existed inline definition */
-		if (param->retval == -ENOENT && strisglob(pp->function))
+		if (param->retval == -ENOENT)
 			param->retval = 0;
 	}
 
@@ -1101,11 +1151,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 				  struct probe_finder *pf)
 {
 	int ret = 0;
-
-#if _ELFUTILS_PREREQ(0, 142)
 	Elf *elf;
 	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
 
 	if (pf->cfi_eh || pf->cfi_dbg)
 		return debuginfo__find_probe_location(dbg, pf);
@@ -1118,11 +1165,18 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	if (gelf_getehdr(elf, &ehdr) == NULL)
 		return -EINVAL;
 
-	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-	    shdr.sh_type == SHT_PROGBITS)
-		pf->cfi_eh = dwarf_getcfi_elf(elf);
+	pf->machine = ehdr.e_machine;
+
+#if _ELFUTILS_PREREQ(0, 142)
+	do {
+		GElf_Shdr shdr;
+
+		if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+		    shdr.sh_type == SHT_PROGBITS)
+			pf->cfi_eh = dwarf_getcfi_elf(elf);
 
-	pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+	} while (0);
 #endif
 
 	ret = debuginfo__find_probe_location(dbg, pf);
@@ -1150,7 +1204,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
-					      NULL) == 0) {
+					      pf->machine, NULL) == 0) {
 			vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
 			if (vf->args[vf->nargs].var == NULL) {
 				vf->ret = -ENOMEM;
@@ -1313,7 +1367,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 	    tag == DW_TAG_variable) {
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
-						NULL);
+						af->pf.machine, NULL);
 		if (ret == 0 || ret == -ERANGE) {
 			int ret2;
 			bool externs = !af->child;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 51137fccb9c8..f1d8558f498e 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -80,6 +80,7 @@ struct probe_finder {
 	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
+	unsigned int		machine;	/* Target machine arch */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
 	struct probe_trace_arg	*tvar;		/* Current result variable */
 };
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5d1eb1ccd96c..e55a132f69b7 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -25,6 +25,7 @@
 #include <ctype.h>
 #include <errno.h>
 #include <linux/bitmap.h>
+#include <linux/time64.h>
 
 #include "../util.h"
 #include <EXTERN.h>
@@ -359,8 +360,8 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (!test_and_set_bit(event->id, events_defined))
 		define_event_symbols(event, handler, event->print_fmt.args);
 
-	s = nsecs / NSECS_PER_SEC;
-	ns = nsecs - s * NSECS_PER_SEC;
+	s = nsecs / NSEC_PER_SEC;
+	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
 	scripting_context->pevent = evsel->tp_format->pevent;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e0203b979474..089438da1f7f 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -27,6 +27,7 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <linux/bitmap.h>
+#include <linux/time64.h>
 
 #include "../../perf.h"
 #include "../debug.h"
@@ -426,8 +427,8 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		if (!dict)
 			Py_FatalError("couldn't create Python dict");
 	}
-	s = nsecs / NSECS_PER_SEC;
-	ns = nsecs - s * NSECS_PER_SEC;
+	s = nsecs / NSEC_PER_SEC;
+	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
 	scripting_context->pevent = evsel->tp_format->pevent;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 3d3cb8392c86..452e15a10dd2 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -11,7 +11,7 @@
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
-const char	default_sort_order[] = "comm,dso,symbol";
+const char	*default_sort_order = "comm,dso,symbol";
 const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
 const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 const char	default_top_sort_order[] = "dso,symbol";
@@ -867,7 +867,7 @@ struct sort_entry sort_cycles = {
 };
 
 /* --sort daddr_sym */
-static int64_t
+int64_t
 sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	uint64_t l = 0, r = 0;
@@ -896,7 +896,7 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
 					 width);
 }
 
-static int64_t
+int64_t
 sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	uint64_t l = 0, r = 0;
@@ -1062,7 +1062,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static int64_t
+int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 l, r;
@@ -1492,7 +1492,8 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct hists *hists)
+			      struct hists *hists, int line __maybe_unused,
+			      int *span __maybe_unused)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
@@ -1797,7 +1798,9 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 }
 
 static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct hists *hists __maybe_unused)
+			      struct hists *hists __maybe_unused,
+			      int line __maybe_unused,
+			      int *span __maybe_unused)
 {
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
@@ -2305,9 +2308,9 @@ int hpp_dimension__add_output(unsigned col)
 	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
-			       struct perf_evlist *evlist,
-			       int level)
+int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			struct perf_evlist *evlist,
+			int level)
 {
 	unsigned int i;
 
@@ -2682,7 +2685,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-static int output_field_add(struct perf_hpp_list *list, char *tok)
+int output_field_add(struct perf_hpp_list *list, char *tok)
 {
 	unsigned int i;
 
@@ -2745,7 +2748,7 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
 	return ret;
 }
 
-static void reset_dimensions(void)
+void reset_dimensions(void)
 {
 	unsigned int i;
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7ca37ea17395..099c97557d33 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -28,7 +28,7 @@ extern const char *sort_order;
 extern const char *field_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
-extern const char default_sort_order[];
+extern const char *default_sort_order;
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern enum sort_mode sort__mode;
@@ -40,6 +40,7 @@ extern struct sort_entry sort_dso_from;
 extern struct sort_entry sort_dso_to;
 extern struct sort_entry sort_sym_from;
 extern struct sort_entry sort_sym_to;
+extern struct sort_entry sort_srcline;
 extern enum sort_type sort__first_dimension;
 extern const char default_mem_sort_order[];
 
@@ -268,4 +269,15 @@ int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, i
 bool is_strict_order(const char *order);
 
 int hpp_dimension__add_output(unsigned col);
+void reset_dimensions(void);
+int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			struct perf_evlist *evlist,
+			int level);
+int output_field_add(struct perf_hpp_list *list, char *tok);
+int64_t
+sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index eec6c1149f44..1cbada2dc6be 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -18,6 +18,7 @@
 #include <unistd.h>
 #include <string.h>
 #include <linux/bitmap.h>
+#include <linux/time64.h>
 
 #include "perf.h"
 #include "svghelper.h"
@@ -274,14 +275,14 @@ static char *time_to_string(u64 duration)
 
 	text[0] = 0;
 
-	if (duration < 1000) /* less than 1 usec */
+	if (duration < NSEC_PER_USEC) /* less than 1 usec */
 		return text;
 
-	if (duration < 1000 * 1000) { /* less than 1 msec */
-		sprintf(text, "%.1f us", duration / 1000.0);
+	if (duration < NSEC_PER_MSEC) { /* less than 1 msec */
+		sprintf(text, "%.1f us", duration / (double)NSEC_PER_USEC);
 		return text;
 	}
-	sprintf(text, "%.1f ms", duration / 1000.0 / 1000);
+	sprintf(text, "%.1f ms", duration / (double)NSEC_PER_MSEC);
 
 	return text;
 }
@@ -297,7 +298,7 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 
 	style = "waiting";
 
-	if (end-start > 10 * 1000000) /* 10 msec */
+	if (end-start > 10 * NSEC_PER_MSEC) /* 10 msec */
 		style = "WAITING";
 
 	text = time_to_string(end-start);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a811c13a74d6..99400b0e8f2a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -206,6 +206,37 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static bool want_demangle(bool is_kernel_sym)
+{
+	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
+static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
+{
+	int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
+	char *demangled = NULL;
+
+	/*
+	 * We need to figure out if the object was created from C++ sources
+	 * DWARF DW_compile_unit has this, but we don't always have access
+	 * to it...
+	 */
+	if (!want_demangle(dso->kernel || kmodule))
+	    return demangled;
+
+	demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+	if (demangled == NULL)
+		demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+	else if (rust_is_mangled(demangled))
+		/*
+		    * Input to Rust demangling is the BFD-demangled
+		    * name which it Rust-demangles in place.
+		    */
+		rust_demangle_sym(demangled);
+
+	return demangled;
+}
+
 #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
 	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
 	     idx < nr_entries; \
@@ -223,8 +254,7 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map,
-				symbol_filter_t filter)
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map)
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
@@ -301,45 +331,53 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 
 		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
 					   nr_rel_entries) {
+			const char *elf_name = NULL;
+			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
 			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
+
+			elf_name = elf_sym__name(&sym, symstrs);
+			demangled = demangle_sym(dso, 0, elf_name);
+			if (demangled != NULL)
+				elf_name = demangled;
 			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
+				 "%s@plt", elf_name);
+			free(demangled);
 
 			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
 					STB_GLOBAL, sympltname);
 			if (!f)
 				goto out_elf_end;
 
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
-				symbols__insert(&dso->symbols[map->type], f);
-				++nr;
-			}
+			symbols__insert(&dso->symbols[map->type], f);
+			++nr;
 		}
 	} else if (shdr_rel_plt.sh_type == SHT_REL) {
 		GElf_Rel pos_mem, *pos;
 		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
 					  nr_rel_entries) {
+			const char *elf_name = NULL;
+			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
 			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
+
+			elf_name = elf_sym__name(&sym, symstrs);
+			demangled = demangle_sym(dso, 0, elf_name);
+			if (demangled != NULL)
+				elf_name = demangled;
 			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
+				 "%s@plt", elf_name);
+			free(demangled);
 
 			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
 					STB_GLOBAL, sympltname);
 			if (!f)
 				goto out_elf_end;
 
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
-				symbols__insert(&dso->symbols[map->type], f);
-				++nr;
-			}
+			symbols__insert(&dso->symbols[map->type], f);
+			++nr;
 		}
 	}
 
@@ -685,7 +723,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	}
 
 	/* Always reject images with a mismatched build-id: */
-	if (dso->has_build_id) {
+	if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) {
 		u8 build_id[BUILD_ID_SIZE];
 
 		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) {
@@ -775,17 +813,11 @@ static u64 ref_reloc(struct kmap *kmap)
 	return 0;
 }
 
-static bool want_demangle(bool is_kernel_sym)
-{
-	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
-}
-
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
-int dso__load_sym(struct dso *dso, struct map *map,
-		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
-		  symbol_filter_t filter, int kmodule)
+int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
+		  struct symsrc *runtime_ss, int kmodule)
 {
 	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
 	struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL;
@@ -1070,29 +1102,10 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
 new_symbol:
-		/*
-		 * We need to figure out if the object was created from C++ sources
-		 * DWARF DW_compile_unit has this, but we don't always have access
-		 * to it...
-		 */
-		if (want_demangle(dso->kernel || kmodule)) {
-			int demangle_flags = DMGL_NO_OPTS;
-			if (verbose)
-				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
-
-			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
-			if (demangled == NULL)
-				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
-			else if (rust_is_mangled(demangled))
-				/*
-				 * Input to Rust demangling is the BFD-demangled
-				 * name which it Rust-demangles in place.
-				 */
-				rust_demangle_sym(demangled);
+		demangled = demangle_sym(dso, kmodule, elf_name);
+		if (demangled != NULL)
+			elf_name = demangled;
 
-			if (demangled != NULL)
-				elf_name = demangled;
-		}
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
 		free(demangled);
@@ -1101,21 +1114,16 @@ new_symbol:
 
 		arch__sym_update(f, &sym);
 
-		if (filter && filter(curr_map, f))
-			symbol__delete(f);
-		else {
-			symbols__insert(&curr_dso->symbols[curr_map->type], f);
-			nr++;
-		}
+		__symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel);
+		nr++;
 	}
 
 	/*
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		if (!symbol_conf.allow_aliases)
-			symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 48906333a858..11cdde980545 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -287,8 +287,7 @@ void symsrc__destroy(struct symsrc *ss)
 
 int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
 				struct symsrc *ss __maybe_unused,
-				struct map *map __maybe_unused,
-				symbol_filter_t filter __maybe_unused)
+				struct map *map __maybe_unused)
 {
 	return 0;
 }
@@ -334,7 +333,6 @@ enum dso_type dso__type_fd(int fd)
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  struct symsrc *ss,
 		  struct symsrc *runtime_ss __maybe_unused,
-		  symbol_filter_t filter __maybe_unused,
 		  int kmodule __maybe_unused)
 {
 	unsigned char build_id[BUILD_ID_SIZE];
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 37e8d20ae03e..aecff69a510d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <inttypes.h>
+#include "annotate.h"
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
@@ -23,10 +24,10 @@
 #include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
-static int dso__load_kernel_sym(struct dso *dso, struct map *map,
-				symbol_filter_t filter);
-static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
-			symbol_filter_t filter);
+static int dso__load_kernel_sym(struct dso *dso, struct map *map);
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map);
+static bool symbol__is_idle(const char *name);
+
 int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
@@ -152,6 +153,9 @@ void symbols__fixup_duplicate(struct rb_root *symbols)
 	struct rb_node *nd;
 	struct symbol *curr, *next;
 
+	if (symbol_conf.allow_aliases)
+		return;
+
 	nd = rb_first(symbols);
 
 	while (nd) {
@@ -235,8 +239,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 	if (sym == NULL)
 		return NULL;
 
-	if (symbol_conf.priv_size)
+	if (symbol_conf.priv_size) {
+		if (symbol_conf.init_annotation) {
+			struct annotation *notes = (void *)sym;
+			pthread_mutex_init(&notes->lock, NULL);
+		}
 		sym = ((void *)sym) + symbol_conf.priv_size;
+	}
 
 	sym->start   = start;
 	sym->end     = len ? start + len : start;
@@ -268,13 +277,24 @@ void symbols__delete(struct rb_root *symbols)
 	}
 }
 
-void symbols__insert(struct rb_root *symbols, struct symbol *sym)
+void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
 {
 	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
 
+	if (kernel) {
+		const char *name = sym->name;
+		/*
+		 * ppc64 uses function descriptors and appends a '.' to the
+		 * start of every instruction address. Remove it.
+		 */
+		if (name[0] == '.')
+			name++;
+		sym->idle = symbol__is_idle(name);
+	}
+
 	while (*p != NULL) {
 		parent = *p;
 		s = rb_entry(parent, struct symbol, rb_node);
@@ -287,6 +307,11 @@ void symbols__insert(struct rb_root *symbols, struct symbol *sym)
 	rb_insert_color(&sym->rb_node, symbols);
 }
 
+void symbols__insert(struct rb_root *symbols, struct symbol *sym)
+{
+	__symbols__insert(symbols, sym, false);
+}
+
 static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 {
 	struct rb_node *n;
@@ -320,6 +345,16 @@ static struct symbol *symbols__first(struct rb_root *symbols)
 	return NULL;
 }
 
+static struct symbol *symbols__last(struct rb_root *symbols)
+{
+	struct rb_node *n = rb_last(symbols);
+
+	if (n)
+		return rb_entry(n, struct symbol, rb_node);
+
+	return NULL;
+}
+
 static struct symbol *symbols__next(struct symbol *sym)
 {
 	struct rb_node *n = rb_next(&sym->rb_node);
@@ -415,7 +450,7 @@ void dso__reset_find_symbol_cache(struct dso *dso)
 
 void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
 {
-	symbols__insert(&dso->symbols[type], sym);
+	__symbols__insert(&dso->symbols[type], sym, dso->kernel);
 
 	/* update the symbol cache if necessary */
 	if (dso->last_find_result[type].addr >= sym->start &&
@@ -441,6 +476,11 @@ struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 	return symbols__first(&dso->symbols[type]);
 }
 
+struct symbol *dso__last_symbol(struct dso *dso, enum map_type type)
+{
+	return symbols__last(&dso->symbols[type]);
+}
+
 struct symbol *dso__next_symbol(struct symbol *sym)
 {
 	return symbols__next(sym);
@@ -537,7 +577,7 @@ struct process_kallsyms_args {
  * These are symbols in the kernel image, so make sure that
  * sym is from a kernel DSO.
  */
-bool symbol__is_idle(struct symbol *sym)
+static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
 		"cpu_idle",
@@ -554,14 +594,10 @@ bool symbol__is_idle(struct symbol *sym)
 		"pseries_dedicated_idle_sleep",
 		NULL
 	};
-
 	int i;
 
-	if (!sym)
-		return false;
-
 	for (i = 0; idle_symbols[i]; i++) {
-		if (!strcmp(idle_symbols[i], sym->name))
+		if (!strcmp(idle_symbols[i], name))
 			return true;
 	}
 
@@ -590,7 +626,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	 * We will pass the symbols to the filter later, in
 	 * map__split_kallsyms, when we have split the maps per module
 	 */
-	symbols__insert(root, sym);
+	__symbols__insert(root, sym, !strchr(name, '['));
 
 	return 0;
 }
@@ -607,8 +643,7 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
 	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
-static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
-					 symbol_filter_t filter)
+static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
 {
 	struct map_groups *kmaps = map__kmaps(map);
 	struct map *curr_map;
@@ -637,7 +672,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
-		if (!curr_map || (filter && filter(curr_map, pos))) {
+		if (!curr_map) {
 			symbol__delete(pos);
 			continue;
 		}
@@ -660,8 +695,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
-			       symbol_filter_t filter)
+static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 {
 	struct map_groups *kmaps = map__kmaps(map);
 	struct machine *machine;
@@ -738,7 +772,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 
 			if (count == 0) {
 				curr_map = map;
-				goto filter_symbol;
+				goto add_symbol;
 			}
 
 			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
@@ -770,18 +804,18 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 			pos->start -= delta;
 			pos->end -= delta;
 		}
-filter_symbol:
-		if (filter && filter(curr_map, pos)) {
-discard_symbol:		rb_erase(&pos->rb_node, root);
-			symbol__delete(pos);
-		} else {
-			if (curr_map != map) {
-				rb_erase(&pos->rb_node, root);
-				symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
-				++moved;
-			} else
-				++count;
-		}
+add_symbol:
+		if (curr_map != map) {
+			rb_erase(&pos->rb_node, root);
+			symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+			++moved;
+		} else
+			++count;
+
+		continue;
+discard_symbol:
+		rb_erase(&pos->rb_node, root);
+		symbol__delete(pos);
 	}
 
 	if (curr_map != map &&
@@ -1221,7 +1255,7 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
 }
 
 int __dso__load_kallsyms(struct dso *dso, const char *filename,
-			 struct map *map, bool no_kcore, symbol_filter_t filter)
+			 struct map *map, bool no_kcore)
 {
 	u64 delta = 0;
 
@@ -1234,8 +1268,8 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(map, filename, &delta))
 		return -1;
 
-	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
@@ -1243,19 +1277,18 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	if (!no_kcore && !dso__load_kcore(dso, map, filename))
-		return dso__split_kallsyms_for_kcore(dso, map, filter);
+		return dso__split_kallsyms_for_kcore(dso, map);
 	else
-		return dso__split_kallsyms(dso, map, delta, filter);
+		return dso__split_kallsyms(dso, map, delta);
 }
 
 int dso__load_kallsyms(struct dso *dso, const char *filename,
-		       struct map *map, symbol_filter_t filter)
+		       struct map *map)
 {
-	return __dso__load_kallsyms(dso, filename, map, false, filter);
+	return __dso__load_kallsyms(dso, filename, map, false);
 }
 
-static int dso__load_perf_map(struct dso *dso, struct map *map,
-			      symbol_filter_t filter)
+static int dso__load_perf_map(struct dso *dso, struct map *map)
 {
 	char *line = NULL;
 	size_t n;
@@ -1297,12 +1330,8 @@ static int dso__load_perf_map(struct dso *dso, struct map *map,
 		if (sym == NULL)
 			goto out_delete_line;
 
-		if (filter && filter(map, sym))
-			symbol__delete(sym);
-		else {
-			symbols__insert(&dso->symbols[map->type], sym);
-			nr_syms++;
-		}
+		symbols__insert(&dso->symbols[map->type], sym);
+		nr_syms++;
 	}
 
 	free(line);
@@ -1358,7 +1387,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	}
 }
 
-int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
+int dso__load(struct dso *dso, struct map *map)
 {
 	char *name;
 	int ret = -1;
@@ -1381,9 +1410,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 	if (dso->kernel) {
 		if (dso->kernel == DSO_TYPE_KERNEL)
-			ret = dso__load_kernel_sym(dso, map, filter);
+			ret = dso__load_kernel_sym(dso, map);
 		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-			ret = dso__load_guest_kernel_sym(dso, map, filter);
+			ret = dso__load_guest_kernel_sym(dso, map);
 
 		goto out;
 	}
@@ -1407,7 +1436,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 			goto out;
 		}
 
-		ret = dso__load_perf_map(dso, map, filter);
+		ret = dso__load_perf_map(dso, map);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
 		goto out;
@@ -1498,14 +1527,14 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 			kmod = true;
 
 	if (syms_ss)
-		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
+		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
 	else
 		ret = -1;
 
 	if (ret > 0) {
 		int nr_plt;
 
-		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter);
+		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map);
 		if (nr_plt > 0)
 			ret += nr_plt;
 	}
@@ -1544,8 +1573,7 @@ out_unlock:
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, bool vmlinux_allocated,
-		      symbol_filter_t filter)
+		      const char *vmlinux, bool vmlinux_allocated)
 {
 	int err = -1;
 	struct symsrc ss;
@@ -1565,7 +1593,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
 		return -1;
 
-	err = dso__load_sym(dso, map, &ss, &ss, filter, 0);
+	err = dso__load_sym(dso, map, &ss, &ss, 0);
 	symsrc__destroy(&ss);
 
 	if (err > 0) {
@@ -1581,8 +1609,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	return err;
 }
 
-int dso__load_vmlinux_path(struct dso *dso, struct map *map,
-			   symbol_filter_t filter)
+int dso__load_vmlinux_path(struct dso *dso, struct map *map)
 {
 	int i, err = 0;
 	char *filename = NULL;
@@ -1591,7 +1618,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 		 vmlinux_path__nr_entries + 1);
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false);
 		if (err > 0)
 			goto out;
 	}
@@ -1599,7 +1626,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 	if (!symbol_conf.ignore_vmlinux_buildid)
 		filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
-		err = dso__load_vmlinux(dso, map, filename, true, filter);
+		err = dso__load_vmlinux(dso, map, filename, true);
 		if (err > 0)
 			goto out;
 		free(filename);
@@ -1713,8 +1740,7 @@ proc_kallsyms:
 	return strdup(path);
 }
 
-static int dso__load_kernel_sym(struct dso *dso, struct map *map,
-				symbol_filter_t filter)
+static int dso__load_kernel_sym(struct dso *dso, struct map *map)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
@@ -1740,12 +1766,11 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 	}
 
 	if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
-		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name,
-					 false, filter);
+		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false);
 	}
 
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
-		err = dso__load_vmlinux_path(dso, map, filter);
+		err = dso__load_vmlinux_path(dso, map);
 		if (err > 0)
 			return err;
 	}
@@ -1761,7 +1786,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 	kallsyms_filename = kallsyms_allocated_filename;
 
 do_kallsyms:
-	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	free(kallsyms_allocated_filename);
@@ -1776,8 +1801,7 @@ do_kallsyms:
 	return err;
 }
 
-static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
-				      symbol_filter_t filter)
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
@@ -1799,7 +1823,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
 			err = dso__load_vmlinux(dso, map,
 						symbol_conf.default_guest_vmlinux_name,
-						false, filter);
+						false);
 			return err;
 		}
 
@@ -1811,7 +1835,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		kallsyms_filename = path;
 	}
 
-	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
@@ -1948,6 +1972,23 @@ static bool symbol__read_kptr_restrict(void)
 	return value;
 }
 
+int symbol__annotation_init(void)
+{
+	if (symbol_conf.initialized) {
+		pr_err("Annotation needs to be init before symbol__init()\n");
+		return -1;
+	}
+
+	if (symbol_conf.init_annotation) {
+		pr_warning("Annotation being initialized multiple times\n");
+		return 0;
+	}
+
+	symbol_conf.priv_size += sizeof(struct annotation);
+	symbol_conf.init_annotation = true;
+	return 0;
+}
+
 int symbol__init(struct perf_env *env)
 {
 	const char *symfs;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 699f7cbcfe72..d964844eb314 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -57,7 +57,7 @@ struct symbol {
 	u64		end;
 	u16		namelen;
 	u8		binding;
-	bool		ignore;
+	u8		idle:1;
 	u8		arch_sym;
 	char		name[0];
 };
@@ -88,6 +88,7 @@ struct symbol_conf {
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			init_annotation,
 			force,
 			ignore_vmlinux,
 			ignore_vmlinux_buildid,
@@ -240,16 +241,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 bool symsrc__has_symtab(struct symsrc *ss);
 bool symsrc__possibly_runtime(struct symsrc *ss);
 
-int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load(struct dso *dso, struct map *map);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, bool vmlinux_allocated,
-		      symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *dso, struct map *map,
-			   symbol_filter_t filter);
+		      const char *vmlinux, bool vmlinux_allocated);
+int dso__load_vmlinux_path(struct dso *dso, struct map *map);
 int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
-			 bool no_kcore, symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
-		       symbol_filter_t filter);
+			 bool no_kcore);
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
 void dso__insert_symbol(struct dso *dso, enum map_type type,
 			struct symbol *sym);
@@ -261,6 +259,7 @@ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 struct symbol *symbol__next_by_name(struct symbol *sym);
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__last_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);
 
 enum dso_type dso__type_fd(int fd);
@@ -277,6 +276,8 @@ struct perf_env;
 int symbol__init(struct perf_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
+int symbol__annotation_init(void);
+
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,
@@ -291,16 +292,15 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
-bool symbol__is_idle(struct symbol *sym);
 int symbol__config_symfs(const struct option *opt __maybe_unused,
 			 const char *dir, int unset __maybe_unused);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
-		  struct symsrc *runtime_ss, symbol_filter_t filter,
-		  int kmodule);
+		  struct symsrc *runtime_ss, int kmodule);
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
-				struct map *map, symbol_filter_t filter);
+				struct map *map);
 
+void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
 void symbols__fixup_end(struct rb_root *symbols);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index cee559d8c9e8..85c56800f17a 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -15,6 +15,7 @@
 #include <byteswap.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
+#include <linux/time64.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index e5f55477491d..43899e0d6fa1 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -179,10 +179,6 @@ static inline void *zalloc(size_t size)
 #undef tolower
 #undef toupper
 
-#ifndef NSEC_PER_MSEC
-#define NSEC_PER_MSEC	1000000L
-#endif
-
 int parse_nsec_time(const char *str, u64 *ptime);
 
 extern unsigned char sane_ctype[256];