Merge tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "New features:

  perf ftrace:

   - Add -n/--use-nsec option to the 'latency' subcommand.

     Default: usecs:

     $ sudo perf ftrace latency -T dput -a sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |    2098375 | #############################  |
          1 - 2    us |         61 |                                |
          2 - 4    us |         33 |                                |
          4 - 8    us |         13 |                                |
          8 - 16   us |        124 |                                |
         16 - 32   us |        123 |                                |
         32 - 64   us |          1 |                                |
         64 - 128  us |          0 |                                |
        128 - 256  us |          1 |                                |
        256 - 512  us |          0 |                                |

     Better granularity with nsec:

     $ sudo perf ftrace latency -T dput -a -n sleep 1
     #   DURATION     |      COUNT | GRAPH                          |
          0 - 1    us |          0 |                                |
          1 - 2    ns |          0 |                                |
          2 - 4    ns |          0 |                                |
          4 - 8    ns |          0 |                                |
          8 - 16   ns |          0 |                                |
         16 - 32   ns |          0 |                                |
         32 - 64   ns |          0 |                                |
         64 - 128  ns |    1163434 | ##############                 |
        128 - 256  ns |     914102 | #############                  |
        256 - 512  ns |        884 |                                |
        512 - 1024 ns |        613 |                                |
          1 - 2    us |         31 |                                |
          2 - 4    us |         17 |                                |
          4 - 8    us |          7 |                                |
          8 - 16   us |        123 |                                |
         16 - 32   us |         83 |                                |

  perf lock:

   - Add -c/--combine-locks option to merge lock instances in the same
     class into a single entry.

     # perf lock report -c
                    Name acquired contended avg wait(ns) total wait(ns) max wait(ns) min wait(ns)

           rcu_read_lock   251225         0            0              0            0            0
      hrtimer_bases.lock    39450         0            0              0            0            0
     &sb->s_type->i_l...    10301         1          662            662          662          662
        ptlock_ptr(page)    10173         2          701           1402          760          642
     &(ei->i_block_re...     8732         0            0              0            0            0
            &xa->xa_lock     8088         0            0              0            0            0
             &base->lock     6705         0            0              0            0            0
             &p->pi_lock     5549         0            0              0            0            0
     &dentry->d_lockr...     5010         4         1274           5097         1844          789
               &ep->lock     3958         0            0              0            0            0

      - Add -F/--field option to customize the list of fields to output:

     $ perf lock report -F contended,wait_max -k avg_wait
                     Name contended max wait(ns) avg wait(ns)

           slock-AF_INET6         1        23543        23543
        &lruvec->lru_lock         5        18317        11254
           slock-AF_INET6         1        10379        10379
               rcu_node_1         1         2104         2104
      &dentry->d_lockr...         1         1844         1844
      &dentry->d_lockr...         1         1672         1672
         &newf->file_lock        15         2279         1025
      &dentry->d_lockr...         1          792          792

   - Add --synth=no option for record, as there is no need to symbolize,
     lock names comes from the tracepoints.

  perf record:

   - Threaded recording, opt-in, via the new --threads command line
     option.

   - Improve AMD IBS (Instruction-Based Sampling) error handling
     messages.

  perf script:

   - Add 'brstackinsnlen' field (use it with -F) for branch stacks.

   - Output branch sample type in 'perf script'.

  perf report:

   - Add "addr_from" and "addr_to" sort dimensions.

   - Print branch stack entry type in 'perf report --dump-raw-trace'

   - Fix symbolization for chrooted workloads.

  Hardware tracing:

  Intel PT:

   - Add CFE (Control Flow Event) and EVD (Event Data) packets support.

   - Add MODE.Exec IFLAG bit support.

     Explanation about these features from the "Intel® 64 and IA-32
     architectures software developer’s manual combined volumes: 1, 2A,
     2B, 2C, 2D, 3A, 3B, 3C, 3D, and 4" PDF at:

        https://cdrdv2.intel.com/v1/dl/getContent/671200

     At page 3951:
      "32.2.4

       Event Trace is a capability that exposes details about the
       asynchronous events, when they are generated, and when their
       corresponding software event handler completes execution. These
       include:

        o Interrupts, including NMI and SMI, including the interrupt
          vector when defined.

        o Faults, exceptions including the fault vector.

           - Page faults additionally include the page fault address,
             when in context.

        o Event handler returns, including IRET and RSM.

        o VM exits and VM entries.¹

           - VM exits include the values written to the “exit reason”
             and “exit qualification” VMCS fields. INIT and SIPI events.

        o TSX aborts, including the abort status returned for the RTM
          instructions.

        o Shutdown.

       Additionally, it provides indication of the status of the
       Interrupt Flag (IF), to indicate when interrupts are masked"

  ARM CoreSight:

   - Use advertised caps/min_interval as default sample_period on ARM
     spe.

   - Update deduction of TRCCONFIGR register for branch broadcast on
     ARM's CoreSight ETM.

  Vendor Events (JSON):

  Intel:

   - Update events and metrics for: Alderlake, Broadwell, Broadwell DE,
     BroadwellX, CascadelakeX, Elkhartlake, Bonnell, Goldmont,
     GoldmontPlus, Westmere EP-DP, Haswell, HaswellX, Icelake, IcelakeX,
     Ivybridge, Ivytown, Jaketown, Knights Landing, Nehalem EP,
     Sandybridge, Silvermont, Skylake, Skylake Server, SkylakeX,
     Tigerlake, TremontX, Westmere EP-SP, and Westmere EX.

  ARM:

   - Add support for HiSilicon CPA PMU aliasing.

  perf stat:

   - Fix forked applications enablement of counters.

   - The 'slots' should only be printed on a different order than the
     one specified on the command line when 'topdown' events are
     present, fix it.

  Miscellaneous:

   - Sync msr-index, cpufeatures header files with the kernel sources.

   - Stop using some deprecated libbpf APIs in 'perf trace'.

   - Fix some spelling mistakes.

   - Refactor the maps pointers usage to pave the way for using refcount
     debugging.

   - Only offer the --tui option on perf top, report and annotate when
     perf was built with libslang.

   - Don't mention --to-ctf in 'perf data --help' when not linking with
     the required library, libbabeltrace.

   - Use ARRAY_SIZE() instead of ad hoc equivalent, spotted by
     array_size.cocci.

   - Enhance the matching of sub-commands abbreviations:
	'perf c2c rec' -> 'perf c2c record'
	'perf c2c recport -> error

   - Set build-id using build-id header on new mmap records.

   - Fix generation of 'perf --version' string.

  perf test:

   - Add test for the arm_spe event.

   - Add test to check unwinding using fame-pointer (fp) mode on arm64.

   - Make metric testing more robust in 'perf test'.

   - Add error message for unsupported branch stack cases.

  libperf:

   - Add API for allocating new thread map array.

   - Fix typo in perf_evlist__open() failure error messages in libperf
     tests.

  perf c2c:

   - Replace bitmap_weight() with bitmap_empty() where appropriate"

* tag 'perf-tools-for-v5.18-2022-03-26' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (143 commits)
  perf evsel: Improve AMD IBS (Instruction-Based Sampling) error handling messages
  perf python: Add perf_env stubs that will be needed in evsel__open_strerror()
  perf tools: Enhance the matching of sub-commands abbreviations
  libperf tests: Fix typo in perf_evlist__open() failure error messages
  tools arm64: Import cputype.h
  perf lock: Add -F/--field option to control output
  perf lock: Extend struct lock_key to have print function
  perf lock: Add --synth=no option for record
  tools headers cpufeatures: Sync with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  perf stat: Fix forked applications enablement of counters
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf evsel: Make evsel__env() always return a valid env
  perf build-id: Fix spelling mistake "Cant" -> "Can't"
  perf header: Fix spelling mistake "could't" -> "couldn't"
  perf script: Add 'brstackinsnlen' for branch stacks
  perf parse-events: Move slots only with topdown
  perf ftrace latency: Update documentation
  perf ftrace latency: Add -n/--use-nsec option
  perf tools: Fix version kernel tag
  ...

57 files changed, 1789 insertions, 615 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2a403cefcaf2..9a7209a99e16 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -56,6 +56,7 @@ perf-y += debug.o
 perf-y += fncache.o
 perf-y += machine.o
 perf-y += map.o
+perf-y += maps.o
 perf-y += pstack.o
 perf-y += session.o
 perf-y += sample-raw.o
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 59241ff342be..0ee5af529238 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -11,23 +11,18 @@ LF='
 '
 
 #
-# First check if there is a .git to get the version from git describe
-# otherwise try to get the version from the kernel Makefile
+# Always try first to get the version from the kernel Makefile
 #
 CID=
 TAG=
 if test -d ../../.git -o -f ../../.git
 then
-	TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
+	TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
 	CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
-elif test -f ../../PERF-VERSION-FILE
-then
+else
 	TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
 fi
-if test -z "$TAG"
-then
-	TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
-fi
+
 VN="$TAG$CID"
 if test -n "$CID"
 then
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8190a124b99d..e4c641b240df 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -33,6 +33,7 @@
 #include "string2.h"
 #include "util/event.h"
 #include "arch/common.h"
+#include "namespaces.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
@@ -1696,6 +1697,15 @@ fallback:
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		__symbol__join_symfs(filename, filename_size, dso->long_name);
+
+		if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
+			char *new_name = filename_with_chroot(dso->nsinfo->pid,
+							      filename);
+			if (new_name) {
+				strlcpy(filename, new_name, filename_size);
+				free(new_name);
+			}
+		}
 	}
 
 	free(build_id_path);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 825336304a37..9e48652662d4 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1333,6 +1333,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
 	synth_opts->other_events = true;
+	synth_opts->intr_events = true;
 	synth_opts->errors = true;
 	synth_opts->flc = true;
 	synth_opts->llc = true;
@@ -1479,6 +1480,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		case 'o':
 			synth_opts->other_events = true;
 			break;
+		case 'I':
+			synth_opts->intr_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			if (get_flags(&p, &synth_opts->error_plus_flags,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 19910b9011f3..dc38b6f57232 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -76,6 +76,7 @@ enum itrace_period_type {
  * @pwr_events: whether to synthesize power events
  * @other_events: whether to synthesize other events recorded due to the use of
  *                aux_output
+ * @intr_events: whether to synthesize interrupt events
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -120,6 +121,7 @@ struct itrace_synth_opts {
 	bool			ptwrites;
 	bool			pwr_events;
 	bool			other_events;
+	bool			intr_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;
@@ -636,6 +638,8 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 "				p:	    		synthesize power events\n"			\
 "				o:			synthesize other events recorded due to the use\n" \
 "							of aux-output (refer to perf record)\n"	\
+"				I:			synthesize interrupt or similar (asynchronous) events\n" \
+"							(e.g. Intel PT Event Trace)\n" \
 "				e[flags]:		synthesize error events\n" \
 "							each flag must be preceded by + or -\n" \
 "							error flags are: o (overflow)\n" \
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index a517eaa51eb3..94624733af7e 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -33,6 +33,19 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
        return err ? ERR_PTR(err) : btf;
 }
 
+int __weak bpf_prog_load(enum bpf_prog_type prog_type,
+			 const char *prog_name __maybe_unused,
+			 const char *license,
+			 const struct bpf_insn *insns, size_t insn_cnt,
+			 const struct bpf_prog_load_opts *opts)
+{
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+	return bpf_load_program(prog_type, insns, insn_cnt, license,
+				opts->kern_version, opts->log_buf, opts->log_size);
+#pragma GCC diagnostic pop
+}
+
 struct bpf_program * __weak
 bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
 {
@@ -92,7 +105,7 @@ static int machine__process_bpf_event_load(struct machine *machine,
 	for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) {
 		u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
 		u64 addr = addrs[i];
-		struct map *map = maps__find(&machine->kmaps, addr);
+		struct map *map = maps__find(machine__kernel_maps(machine), addr);
 
 		if (map) {
 			map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index ec6d9e7b446d..b72cef1ae959 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -26,6 +26,8 @@
 #include "util.h"
 #include "llvm-utils.h"
 #include "c++/clang-c.h"
+#include "hashmap.h"
+#include "asm/bug.h"
 
 #include <internal/xyarray.h>
 
@@ -49,8 +51,54 @@ struct bpf_prog_priv {
 	int *type_mapping;
 };
 
+struct bpf_perf_object {
+	struct list_head list;
+	struct bpf_object *obj;
+};
+
+static LIST_HEAD(bpf_objects_list);
+static struct hashmap *bpf_program_hash;
+static struct hashmap *bpf_map_hash;
+
+static struct bpf_perf_object *
+bpf_perf_object__next(struct bpf_perf_object *prev)
+{
+	struct bpf_perf_object *next;
+
+	if (!prev)
+		next = list_first_entry(&bpf_objects_list,
+					struct bpf_perf_object,
+					list);
+	else
+		next = list_next_entry(prev, list);
+
+	/* Empty list is noticed here so don't need checking on entry. */
+	if (&next->list == &bpf_objects_list)
+		return NULL;
+
+	return next;
+}
+
+#define bpf_perf_object__for_each(perf_obj, tmp)	\
+	for ((perf_obj) = bpf_perf_object__next(NULL),	\
+	     (tmp) = bpf_perf_object__next(perf_obj);	\
+	     (perf_obj) != NULL;			\
+	     (perf_obj) = (tmp), (tmp) = bpf_perf_object__next(tmp))
+
 static bool libbpf_initialized;
 
+static int bpf_perf_object__add(struct bpf_object *obj)
+{
+	struct bpf_perf_object *perf_obj = zalloc(sizeof(*perf_obj));
+
+	if (perf_obj) {
+		INIT_LIST_HEAD(&perf_obj->list);
+		perf_obj->obj = obj;
+		list_add_tail(&perf_obj->list, &bpf_objects_list);
+	}
+	return perf_obj ? 0 : -ENOMEM;
+}
+
 struct bpf_object *
 bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
 {
@@ -68,9 +116,21 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (bpf_perf_object__add(obj)) {
+		bpf_object__close(obj);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	return obj;
 }
 
+static void bpf_perf_object__close(struct bpf_perf_object *perf_obj)
+{
+	list_del(&perf_obj->list);
+	bpf_object__close(perf_obj->obj);
+	free(perf_obj);
+}
+
 struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 {
 	LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename);
@@ -102,29 +162,25 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 			llvm__dump_obj(filename, obj_buf, obj_buf_sz);
 
 		free(obj_buf);
-	} else
+	} else {
 		obj = bpf_object__open(filename);
+	}
 
 	if (IS_ERR_OR_NULL(obj)) {
 		pr_debug("bpf: failed to load %s\n", filename);
 		return obj;
 	}
 
-	return obj;
-}
-
-void bpf__clear(void)
-{
-	struct bpf_object *obj, *tmp;
-
-	bpf_object__for_each_safe(obj, tmp) {
-		bpf__unprobe(obj);
+	if (bpf_perf_object__add(obj)) {
 		bpf_object__close(obj);
+		return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
 	}
+
+	return obj;
 }
 
 static void
-clear_prog_priv(struct bpf_program *prog __maybe_unused,
+clear_prog_priv(const struct bpf_program *prog __maybe_unused,
 		void *_priv)
 {
 	struct bpf_prog_priv *priv = _priv;
@@ -137,6 +193,83 @@ clear_prog_priv(struct bpf_program *prog __maybe_unused,
 	free(priv);
 }
 
+static void bpf_program_hash_free(void)
+{
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (IS_ERR_OR_NULL(bpf_program_hash))
+		return;
+
+	hashmap__for_each_entry(bpf_program_hash, cur, bkt)
+		clear_prog_priv(cur->key, cur->value);
+
+	hashmap__free(bpf_program_hash);
+	bpf_program_hash = NULL;
+}
+
+static void bpf_map_hash_free(void);
+
+void bpf__clear(void)
+{
+	struct bpf_perf_object *perf_obj, *tmp;
+
+	bpf_perf_object__for_each(perf_obj, tmp) {
+		bpf__unprobe(perf_obj->obj);
+		bpf_perf_object__close(perf_obj);
+	}
+
+	bpf_program_hash_free();
+	bpf_map_hash_free();
+}
+
+static size_t ptr_hash(const void *__key, void *ctx __maybe_unused)
+{
+	return (size_t) __key;
+}
+
+static bool ptr_equal(const void *key1, const void *key2,
+			  void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
+static void *program_priv(const struct bpf_program *prog)
+{
+	void *priv;
+
+	if (IS_ERR_OR_NULL(bpf_program_hash))
+		return NULL;
+	if (!hashmap__find(bpf_program_hash, prog, &priv))
+		return NULL;
+	return priv;
+}
+
+static int program_set_priv(struct bpf_program *prog, void *priv)
+{
+	void *old_priv;
+
+	/*
+	 * Should not happen, we warn about it in the
+	 * caller function - config_bpf_program
+	 */
+	if (IS_ERR(bpf_program_hash))
+		return PTR_ERR(bpf_program_hash);
+
+	if (!bpf_program_hash) {
+		bpf_program_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
+		if (IS_ERR(bpf_program_hash))
+			return PTR_ERR(bpf_program_hash);
+	}
+
+	old_priv = program_priv(prog);
+	if (old_priv) {
+		clear_prog_priv(prog, old_priv);
+		return hashmap__set(bpf_program_hash, prog, priv, NULL, NULL);
+	}
+	return hashmap__add(bpf_program_hash, prog, priv);
+}
+
 static int
 prog_config__exec(const char *value, struct perf_probe_event *pev)
 {
@@ -378,7 +511,7 @@ config_bpf_program(struct bpf_program *prog)
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
 set_priv:
-	err = bpf_program__set_priv(prog, priv, clear_prog_priv);
+	err = program_set_priv(prog, priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;
@@ -419,7 +552,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
 		     struct bpf_insn *orig_insns, int orig_insns_cnt,
 		     struct bpf_prog_prep_result *res)
 {
-	struct bpf_prog_priv *priv = bpf_program__priv(prog);
+	struct bpf_prog_priv *priv = program_priv(prog);
 	struct probe_trace_event *tev;
 	struct perf_probe_event *pev;
 	struct bpf_insn *buf;
@@ -570,7 +703,7 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping,
 
 static int hook_load_preprocessor(struct bpf_program *prog)
 {
-	struct bpf_prog_priv *priv = bpf_program__priv(prog);
+	struct bpf_prog_priv *priv = program_priv(prog);
 	struct perf_probe_event *pev;
 	bool need_prologue = false;
 	int err, i;
@@ -646,7 +779,7 @@ int bpf__probe(struct bpf_object *obj)
 		if (err)
 			goto out;
 
-		priv = bpf_program__priv(prog);
+		priv = program_priv(prog);
 		if (IS_ERR_OR_NULL(priv)) {
 			if (!priv)
 				err = -BPF_LOADER_ERRNO__INTERNAL;
@@ -698,7 +831,7 @@ int bpf__unprobe(struct bpf_object *obj)
 	struct bpf_program *prog;
 
 	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = bpf_program__priv(prog);
+		struct bpf_prog_priv *priv = program_priv(prog);
 		int i;
 
 		if (IS_ERR_OR_NULL(priv) || priv->is_tp)
@@ -754,7 +887,7 @@ int bpf__foreach_event(struct bpf_object *obj,
 	int err;
 
 	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = bpf_program__priv(prog);
+		struct bpf_prog_priv *priv = program_priv(prog);
 		struct probe_trace_event *tev;
 		struct perf_probe_event *pev;
 		int i, fd;
@@ -850,7 +983,7 @@ bpf_map_priv__purge(struct bpf_map_priv *priv)
 }
 
 static void
-bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+bpf_map_priv__clear(const struct bpf_map *map __maybe_unused,
 		    void *_priv)
 {
 	struct bpf_map_priv *priv = _priv;
@@ -859,6 +992,53 @@ bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
 	free(priv);
 }
 
+static void *map_priv(const struct bpf_map *map)
+{
+	void *priv;
+
+	if (IS_ERR_OR_NULL(bpf_map_hash))
+		return NULL;
+	if (!hashmap__find(bpf_map_hash, map, &priv))
+		return NULL;
+	return priv;
+}
+
+static void bpf_map_hash_free(void)
+{
+	struct hashmap_entry *cur;
+	size_t bkt;
+
+	if (IS_ERR_OR_NULL(bpf_map_hash))
+		return;
+
+	hashmap__for_each_entry(bpf_map_hash, cur, bkt)
+		bpf_map_priv__clear(cur->key, cur->value);
+
+	hashmap__free(bpf_map_hash);
+	bpf_map_hash = NULL;
+}
+
+static int map_set_priv(struct bpf_map *map, void *priv)
+{
+	void *old_priv;
+
+	if (WARN_ON_ONCE(IS_ERR(bpf_map_hash)))
+		return PTR_ERR(bpf_program_hash);
+
+	if (!bpf_map_hash) {
+		bpf_map_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
+		if (IS_ERR(bpf_map_hash))
+			return PTR_ERR(bpf_map_hash);
+	}
+
+	old_priv = map_priv(map);
+	if (old_priv) {
+		bpf_map_priv__clear(map, old_priv);
+		return hashmap__set(bpf_map_hash, map, priv, NULL, NULL);
+	}
+	return hashmap__add(bpf_map_hash, map, priv);
+}
+
 static int
 bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
 {
@@ -958,7 +1138,7 @@ static int
 bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 {
 	const char *map_name = bpf_map__name(map);
-	struct bpf_map_priv *priv = bpf_map__priv(map);
+	struct bpf_map_priv *priv = map_priv(map);
 
 	if (IS_ERR(priv)) {
 		pr_debug("Failed to get private from map %s\n", map_name);
@@ -973,7 +1153,7 @@ bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 		}
 		INIT_LIST_HEAD(&priv->ops_list);
 
-		if (bpf_map__set_priv(map, priv, bpf_map_priv__clear)) {
+		if (map_set_priv(map, priv)) {
 			free(priv);
 			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
@@ -1305,7 +1485,7 @@ bpf_map_config_foreach_key(struct bpf_map *map,
 	int err, map_fd, type;
 	struct bpf_map_op *op;
 	const char *name = bpf_map__name(map);
-	struct bpf_map_priv *priv = bpf_map__priv(map);
+	struct bpf_map_priv *priv = map_priv(map);
 
 	if (IS_ERR(priv)) {
 		pr_debug("ERROR: failed to get private from map %s\n", name);
@@ -1494,11 +1674,11 @@ apply_obj_config_object(struct bpf_object *obj)
 
 int bpf__apply_obj_config(void)
 {
-	struct bpf_object *obj, *tmp;
+	struct bpf_perf_object *perf_obj, *tmp;
 	int err;
 
-	bpf_object__for_each_safe(obj, tmp) {
-		err = apply_obj_config_object(obj);
+	bpf_perf_object__for_each(perf_obj, tmp) {
+		err = apply_obj_config_object(perf_obj->obj);
 		if (err)
 			return err;
 	}
@@ -1506,27 +1686,25 @@ int bpf__apply_obj_config(void)
 	return 0;
 }
 
-#define bpf__for_each_map(pos, obj, objtmp)	\
-	bpf_object__for_each_safe(obj, objtmp)	\
-		bpf_object__for_each_map(pos, obj)
+#define bpf__perf_for_each_map(map, pobj, tmp)			\
+	bpf_perf_object__for_each(pobj, tmp)			\
+		bpf_object__for_each_map(map, pobj->obj)
 
-#define bpf__for_each_map_named(pos, obj, objtmp, name)	\
-	bpf__for_each_map(pos, obj, objtmp) 		\
-		if (bpf_map__name(pos) && 		\
-			(strcmp(name, 			\
-				bpf_map__name(pos)) == 0))
+#define bpf__perf_for_each_map_named(map, pobj, pobjtmp, name)	\
+	bpf__perf_for_each_map(map, pobj, pobjtmp)		\
+		if (bpf_map__name(map) && (strcmp(name, bpf_map__name(map)) == 0))
 
 struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
-	struct bpf_object *obj, *tmp;
+	struct bpf_perf_object *perf_obj, *tmp;
 	struct evsel *evsel = NULL;
 	struct bpf_map *map;
 	int err;
 	bool need_init = false;
 
-	bpf__for_each_map_named(map, obj, tmp, name) {
-		struct bpf_map_priv *priv = bpf_map__priv(map);
+	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
+		struct bpf_map_priv *priv = map_priv(map);
 
 		if (IS_ERR(priv))
 			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
@@ -1561,8 +1739,8 @@ struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
 		evsel = evlist__last(evlist);
 	}
 
-	bpf__for_each_map_named(map, obj, tmp, name) {
-		struct bpf_map_priv *priv = bpf_map__priv(map);
+	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
+		struct bpf_map_priv *priv = map_priv(map);
 
 		if (IS_ERR(priv))
 			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
@@ -1574,7 +1752,7 @@ struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
 			if (!priv)
 				return ERR_PTR(-ENOMEM);
 
-			err = bpf_map__set_priv(map, priv, bpf_map_priv__clear);
+			err = map_set_priv(map, priv);
 			if (err) {
 				bpf_map_priv__clear(map, priv);
 				return ERR_PTR(err);
diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c
index d756cc66eef3..4f4d3aaff37c 100644
--- a/tools/perf/util/bpf_ftrace.c
+++ b/tools/perf/util/bpf_ftrace.c
@@ -81,6 +81,8 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
 		}
 	}
 
+	skel->bss->use_nsec = ftrace->use_nsec;
+
 	skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin,
 							    false, func->name);
 	if (IS_ERR(skel->links.func_begin)) {
diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
index ea94187fe443..9d01e3af7479 100644
--- a/tools/perf/util/bpf_skel/func_latency.bpf.c
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -39,6 +39,7 @@ struct {
 int enabled = 0;
 int has_cpu = 0;
 int has_task = 0;
+int use_nsec = 0;
 
 SEC("kprobe/func")
 int BPF_PROG(func_begin)
@@ -80,6 +81,7 @@ int BPF_PROG(func_end)
 {
 	__u64 tid;
 	__u64 *start;
+	__u64 cmp_base = use_nsec ? 1 : 1000;
 
 	if (!enabled)
 		return 0;
@@ -97,9 +99,9 @@ int BPF_PROG(func_end)
 		if (delta < 0)
 			return 0;
 
-		// calculate index using delta in usec
+		// calculate index using delta
 		for (key = 0; key < (NUM_BUCKET - 1); key++) {
-			if (delta < ((1000UL) << key))
+			if (delta < (cmp_base << key))
 				break;
 		}
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e32e8f2ff3bd..82f3d46bea70 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -706,7 +706,7 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam
 		if (is_kallsyms) {
 			if (copyfile("/proc/kallsyms", filename))
 				goto out_free;
-		} else if (nsi && nsi->need_setns) {
+		} else if (nsi && nsinfo__need_setns(nsi)) {
 			if (copyfile_ns(name, filename, nsi))
 				goto out_free;
 		} else if (link(realname, filename) && errno != EEXIST &&
@@ -730,7 +730,7 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam
 				goto out_free;
 			}
 			if (access(filename, F_OK)) {
-				if (nsi && nsi->need_setns) {
+				if (nsi && nsinfo__need_setns(nsi)) {
 					if (copyfile_ns(debugfile, filename,
 							nsi))
 						goto out_free;
@@ -762,7 +762,7 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam
 
 		len = readlink(linkname, path, sizeof(path) - 1);
 		if (len <= 0) {
-			pr_err("Cant read link: %s\n", linkname);
+			pr_err("Can't read link: %s\n", linkname);
 			goto out_free;
 		}
 		path[len] = '\0';
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 131207b91d15..5c27a4b2e7a7 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1119,7 +1119,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 			goto out;
 	}
 
-	if (al->maps == &al->maps->machine->kmaps) {
+	if (al->maps == machine__kernel_maps(al->maps->machine)) {
 		if (machine__is_host(al->maps->machine)) {
 			al->cpumode = PERF_RECORD_MISC_KERNEL;
 			al->level = 'k';
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 15a4547d608e..a5ace2bbc28d 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -48,12 +48,16 @@ int perf_data__create_dir(struct perf_data *data, int nr)
 		struct perf_data_file *file = &files[i];
 
 		ret = asprintf(&file->path, "%s/data.%d", data->path, i);
-		if (ret < 0)
+		if (ret < 0) {
+			ret = -ENOMEM;
 			goto out_err;
+		}
 
 		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
-		if (ret < 0)
+		if (ret < 0) {
+			ret = -errno;
 			goto out_err;
+		}
 
 		file->fd = ret;
 	}
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 9cc8a1772b4b..5ac13958d1bd 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -508,8 +508,19 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 					    root_dir, name, PATH_MAX))
 		goto out;
 
-	if (!is_regular_file(name))
-		goto out;
+	if (!is_regular_file(name)) {
+		char *new_name;
+
+		if (errno != ENOENT || dso->nsinfo == NULL)
+			goto out;
+
+		new_name = filename_with_chroot(dso->nsinfo->pid, name);
+		if (!new_name)
+			goto out;
+
+		free(name);
+		name = new_name;
+	}
 
 	if (dso__needs_decompress(dso)) {
 		char newpath[KMOD_DECOMP_LEN];
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 011da3924fc1..3a9fd4d389b5 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -167,6 +167,7 @@ struct dso {
 	enum dso_load_errno	load_errno;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
+	u8		 header_build_id:1;
 	u8		 has_srcline:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 183a81d5b2f9..b97366f77bbf 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -2,12 +2,15 @@
 #include "debug.h"
 #include "dsos.h"
 #include "dso.h"
+#include "util.h"
 #include "vdso.h"
 #include "namespaces.h"
+#include <errno.h>
 #include <libgen.h>
 #include <stdlib.h>
 #include <string.h>
 #include <symbol.h> // filename__read_build_id
+#include <unistd.h>
 
 static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
 {
@@ -76,6 +79,16 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 		if (filename__read_build_id(pos->long_name, &pos->bid) > 0) {
 			have_build_id	  = true;
 			pos->has_build_id = true;
+		} else if (errno == ENOENT && pos->nsinfo) {
+			char *new_name = filename_with_chroot(pos->nsinfo->pid,
+							      pos->long_name);
+
+			if (new_name && filename__read_build_id(new_name,
+								&pos->bid) > 0) {
+				have_build_id = true;
+				pos->has_build_id = true;
+			}
+			free(new_name);
 		}
 		nsinfo__mountns_exit(&nsc);
 	}
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fe24801f8e9f..6439c888ae38 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -484,7 +484,7 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma
 	if (machine) {
 		struct addr_location al;
 
-		al.map = maps__find(&machine->kmaps, tp->addr);
+		al.map = maps__find(machine__kernel_maps(machine), tp->addr);
 		if (al.map && map__load(al.map) >= 0) {
 			al.addr = al.map->map_ip(al.map, tp->addr);
 			al.sym = map__find_symbol(al.map, al.addr);
@@ -587,13 +587,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
-		al->maps = maps = &machine->kmaps;
+		al->maps = maps = machine__kernel_maps(machine);
 		load_map = true;
 	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
 		al->level = 'g';
-		al->maps = maps = &machine->kmaps;
+		al->maps = maps = machine__kernel_maps(machine);
 		load_map = true;
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
 		al->level = 'u';
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c59331eea1d9..cdd72e05fd28 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -101,9 +101,11 @@ enum {
 	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
 	PERF_IP_FLAG_VMENTRY		= 1ULL << 11,
 	PERF_IP_FLAG_VMEXIT		= 1ULL << 12,
+	PERF_IP_FLAG_INTR_DISABLE	= 1ULL << 13,
+	PERF_IP_FLAG_INTR_TOGGLE	= 1ULL << 14,
 };
 
-#define PERF_IP_FLAG_CHARS "bcrosyiABExgh"
+#define PERF_IP_FLAG_CHARS "bcrosyiABExghDt"
 
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
@@ -182,6 +184,8 @@ enum perf_synth_id {
 	PERF_SYNTH_INTEL_PWRX,
 	PERF_SYNTH_INTEL_CBR,
 	PERF_SYNTH_INTEL_PSB,
+	PERF_SYNTH_INTEL_EVT,
+	PERF_SYNTH_INTEL_IFLAG_CHG,
 };
 
 /*
@@ -280,6 +284,45 @@ struct perf_synth_intel_psb {
 	u64 offset;
 };
 
+struct perf_synth_intel_evd {
+	union {
+		struct {
+			u8	evd_type;
+			u8	reserved[7];
+		};
+		u64	et;
+	};
+	u64	payload;
+};
+
+/* Intel PT Event Trace */
+struct perf_synth_intel_evt {
+	u32 padding;
+	union {
+		struct {
+			u32	type		:  5,
+				reserved	:  2,
+				ip		:  1,
+				vector		:  8,
+				evd_cnt		: 16;
+		};
+		u32	cfe;
+	};
+	struct perf_synth_intel_evd evd[0];
+};
+
+struct perf_synth_intel_iflag_chg {
+	u32 padding;
+	union {
+		struct {
+			u32	iflag		:  1,
+				via_branch	:  1;
+		};
+		u32	flags;
+	};
+	u64	branch_ip; /* If via_branch */
+};
+
 /*
  * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get
  * 8-byte alignment.
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 41a66a48cbdf..9bb79e049957 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -2145,6 +2145,22 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd)
 	return err;
 }
 
+int evlist__ctlfd_update(struct evlist *evlist, struct pollfd *update)
+{
+	int ctlfd_pos = evlist->ctl_fd.pos;
+	struct pollfd *entries = evlist->core.pollfd.entries;
+
+	if (!evlist__ctlfd_initialized(evlist))
+		return 0;
+
+	if (entries[ctlfd_pos].fd != update->fd ||
+	    entries[ctlfd_pos].events != update->events)
+		return -1;
+
+	entries[ctlfd_pos].revents = update->revents;
+	return 0;
+}
+
 struct evsel *evlist__find_evsel(struct evlist *evlist, int idx)
 {
 	struct evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 64cba56fbc74..a21daaa5fc1b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -410,6 +410,7 @@ void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close);
 int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack);
 int evlist__finalize_ctlfd(struct evlist *evlist);
 bool evlist__ctlfd_initialized(struct evlist *evlist);
+int evlist__ctlfd_update(struct evlist *evlist, struct pollfd *update);
 int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd);
 int evlist__ctlfd_ack(struct evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 22d3267ce294..2a1729e7aee4 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2847,9 +2847,23 @@ static bool find_process(const char *name)
 	return ret ? false : true;
 }
 
+static bool is_amd(const char *arch, const char *cpuid)
+{
+	return arch && !strcmp("x86", arch) && cpuid && strstarts(cpuid, "AuthenticAMD");
+}
+
+static bool is_amd_ibs(struct evsel *evsel)
+{
+	return evsel->core.attr.precise_ip
+	    || (evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3));
+}
+
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size)
 {
+	struct perf_env *env = evsel__env(evsel);
+	const char *arch = perf_env__arch(env);
+	const char *cpuid = perf_env__cpuid(env);
 	char sbuf[STRERR_BUFSIZE];
 	int printed = 0, enforced = 0;
 
@@ -2909,6 +2923,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 	 "No such device - did you specify an out-of-range profile CPU?");
 		break;
 	case EOPNOTSUPP:
+		if (evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK)
+			return scnprintf(msg, size,
+	"%s: PMU Hardware or event type doesn't support branch stack sampling.",
+					 evsel__name(evsel));
 		if (evsel->core.attr.aux_output)
 			return scnprintf(msg, size,
 	"%s: PMU Hardware doesn't support 'aux_output' feature",
@@ -2949,6 +2967,17 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size,
 	"Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
 					evsel__name(evsel));
+		if (is_amd(arch, cpuid)) {
+			if (is_amd_ibs(evsel)) {
+				if (evsel->core.attr.exclude_kernel)
+					return scnprintf(msg, size,
+	"AMD IBS can't exclude kernel events.  Try running at a higher privilege level.");
+				if (!evsel->core.system_wide)
+					return scnprintf(msg, size,
+	"AMD IBS may only be available in system-wide/per-cpu mode.  Try using -a, or -C and workload affinity");
+			}
+		}
+
 		break;
 	case ENODATA:
 		return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. "
@@ -2965,7 +2994,7 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 
 struct perf_env *evsel__env(struct evsel *evsel)
 {
-	if (evsel && evsel->evlist)
+	if (evsel && evsel->evlist && evsel->evlist->env)
 		return evsel->evlist->env;
 	return &perf_env;
 }
diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h
index 887f68a185f7..a34cd15733b8 100644
--- a/tools/perf/util/ftrace.h
+++ b/tools/perf/util/ftrace.h
@@ -17,6 +17,7 @@ struct perf_ftrace {
 	struct list_head	nograph_funcs;
 	unsigned long		percpu_buffer_size;
 	bool			inherit;
+	bool			use_nsec;
 	int			graph_depth;
 	int			func_stack_trace;
 	int			func_irq_info;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6da12e522edc..d546ff724dbe 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1335,7 +1335,7 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
 
 	dir = opendir(path);
 	if (!dir) {
-		pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+		pr_debug2("%s: couldn't read %s, does this arch have topology information?\n",
 			  __func__, path);
 		return -1;
 	}
@@ -2200,6 +2200,7 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
 
 		build_id__init(&bid, bev->data, size);
 		dso__set_build_id(dso, &bid);
+		dso->header_build_id = 1;
 
 		if (dso_space != DSO_SPACE__USER) {
 			struct kmod_path m = { .name = NULL, };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0a8033b09e28..1c085ab56534 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -124,6 +124,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__new_col_len(hists, HISTC_ADDR_FROM, symlen);
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
 		}
 
@@ -138,6 +139,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__new_col_len(hists, HISTC_ADDR_TO, symlen);
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
 		}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 2a15e22fb89c..7ed4648d2fc2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -77,6 +77,8 @@ enum hist_column {
 	HISTC_GLOBAL_INS_LAT,
 	HISTC_LOCAL_P_STAGE_CYC,
 	HISTC_GLOBAL_P_STAGE_CYC,
+	HISTC_ADDR_FROM,
+	HISTC_ADDR_TO,
 	HISTC_NR_COLS, /* Last entry */
 };
 
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 0e013c2d9eb4..e1d8f7504cbe 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -144,6 +144,8 @@ struct intel_pt_decoder {
 	bool vm_tm_corr_continuous;
 	bool nr;
 	bool next_nr;
+	bool iflag;
+	bool next_iflag;
 	enum intel_pt_param_flags flags;
 	uint64_t pos;
 	uint64_t last_ip;
@@ -213,6 +215,9 @@ struct intel_pt_decoder {
 	bool set_fup_pwre;
 	bool set_fup_exstop;
 	bool set_fup_bep;
+	bool set_fup_cfe_ip;
+	bool set_fup_cfe;
+	bool set_fup_mode_exec;
 	bool sample_cyc;
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
@@ -223,6 +228,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp_insn_cnt;
 	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
+	struct intel_pt_pkt fup_cfe_pkt;
 	int max_loops;
 	int no_progress;
 	int stuck_ip_prd;
@@ -231,6 +237,8 @@ struct intel_pt_decoder {
 	const unsigned char *next_buf;
 	size_t next_len;
 	unsigned char temp_buf[INTEL_PT_PKT_MAX_SZ];
+	int evd_cnt;
+	struct intel_pt_evd evd[INTEL_PT_MAX_EVDS];
 };
 
 static uint64_t intel_pt_lower_power_of_2(uint64_t x)
@@ -820,6 +828,9 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 	case INTEL_PT_BIP:
 	case INTEL_PT_BEP:
 	case INTEL_PT_BEP_IP:
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+	case INTEL_PT_EVD:
 		return 0;
 
 	case INTEL_PT_MTC:
@@ -1094,6 +1105,52 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder)
 	decoder->state.type |= INTEL_PT_INSTRUCTION;
 }
 
+/*
+ * Sample FUP instruction at the same time as reporting the FUP event, so the
+ * instruction sample gets the same flags as the FUP event.
+ */
+static void intel_pt_sample_fup_insn(struct intel_pt_decoder *decoder)
+{
+	struct intel_pt_insn intel_pt_insn;
+	uint64_t max_insn_cnt, insn_cnt = 0;
+	int err;
+
+	decoder->state.insn_op = INTEL_PT_OP_OTHER;
+	decoder->state.insn_len = 0;
+
+	if (!decoder->branch_enable || !decoder->pge || decoder->hop ||
+	    decoder->ip != decoder->last_ip)
+		return;
+
+	if (!decoder->mtc_insn)
+		decoder->mtc_insn = true;
+
+	max_insn_cnt = intel_pt_next_sample(decoder);
+	if (max_insn_cnt != 1)
+		return;
+
+	err = decoder->walk_insn(&intel_pt_insn, &insn_cnt, &decoder->ip,
+				 0, max_insn_cnt, decoder->data);
+	/* Ignore error, it will be reported next walk anyway */
+	if (err)
+		return;
+
+	if (intel_pt_insn.branch != INTEL_PT_BR_NO_BRANCH) {
+		intel_pt_log_at("ERROR: Unexpected branch at FUP instruction", decoder->ip);
+		return;
+	}
+
+	decoder->tot_insn_cnt += insn_cnt;
+	decoder->timestamp_insn_cnt += insn_cnt;
+	decoder->sample_insn_cnt += insn_cnt;
+	decoder->period_insn_cnt += insn_cnt;
+
+	intel_pt_sample_insn(decoder);
+
+	decoder->state.type |= INTEL_PT_INSTRUCTION;
+	decoder->ip += intel_pt_insn.length;
+}
+
 static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 			      struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 {
@@ -1203,13 +1260,85 @@ out_no_progress:
 	return err;
 }
 
-static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
+static void intel_pt_mode_exec_status(struct intel_pt_decoder *decoder)
+{
+	bool iflag = decoder->packet.count & INTEL_PT_IFLAG;
+
+	decoder->exec_mode = decoder->packet.payload;
+	decoder->iflag = iflag;
+	decoder->next_iflag = iflag;
+	decoder->state.from_iflag = iflag;
+	decoder->state.to_iflag = iflag;
+}
+
+static void intel_pt_mode_exec(struct intel_pt_decoder *decoder)
+{
+	bool iflag = decoder->packet.count & INTEL_PT_IFLAG;
+
+	decoder->exec_mode = decoder->packet.payload;
+	decoder->next_iflag = iflag;
+}
+
+static void intel_pt_sample_iflag(struct intel_pt_decoder *decoder)
+{
+	decoder->state.type |= INTEL_PT_IFLAG_CHG;
+	decoder->state.from_iflag = decoder->iflag;
+	decoder->state.to_iflag = decoder->next_iflag;
+	decoder->iflag = decoder->next_iflag;
+}
+
+static void intel_pt_sample_iflag_chg(struct intel_pt_decoder *decoder)
+{
+	if (decoder->iflag != decoder->next_iflag)
+		intel_pt_sample_iflag(decoder);
+}
+
+static void intel_pt_clear_fup_event(struct intel_pt_decoder *decoder)
+{
+	decoder->set_fup_tx_flags = false;
+	decoder->set_fup_ptw = false;
+	decoder->set_fup_mwait = false;
+	decoder->set_fup_pwre = false;
+	decoder->set_fup_exstop = false;
+	decoder->set_fup_bep = false;
+	decoder->set_fup_cfe_ip = false;
+	decoder->set_fup_cfe = false;
+	decoder->evd_cnt = 0;
+	decoder->set_fup_mode_exec = false;
+	decoder->iflag = decoder->next_iflag;
+}
+
+static bool intel_pt_fup_event(struct intel_pt_decoder *decoder, bool no_tip)
 {
 	enum intel_pt_sample_type type = decoder->state.type;
+	bool sample_fup_insn = false;
 	bool ret = false;
 
 	decoder->state.type &= ~INTEL_PT_BRANCH;
 
+	if (decoder->set_fup_cfe_ip || decoder->set_fup_cfe) {
+		bool ip = decoder->set_fup_cfe_ip;
+
+		decoder->set_fup_cfe_ip = false;
+		decoder->set_fup_cfe = false;
+		decoder->state.type |= INTEL_PT_EVT;
+		if (!ip && decoder->pge)
+			decoder->state.type |= INTEL_PT_BRANCH;
+		decoder->state.cfe_type = decoder->fup_cfe_pkt.count;
+		decoder->state.cfe_vector = decoder->fup_cfe_pkt.payload;
+		decoder->state.evd_cnt = decoder->evd_cnt;
+		decoder->state.evd = decoder->evd;
+		decoder->evd_cnt = 0;
+		if (ip || decoder->pge)
+			decoder->state.flags |= INTEL_PT_FUP_IP;
+		ret = true;
+	}
+	if (decoder->set_fup_mode_exec) {
+		decoder->set_fup_mode_exec = false;
+		intel_pt_sample_iflag(decoder);
+		sample_fup_insn = no_tip;
+		ret = true;
+	}
 	if (decoder->set_fup_tx_flags) {
 		decoder->set_fup_tx_flags = false;
 		decoder->tx_flags = decoder->fup_tx_flags;
@@ -1266,6 +1395,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 	if (ret) {
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
+		if (sample_fup_insn)
+			intel_pt_sample_fup_insn(decoder);
 	} else {
 		decoder->state.type = type;
 	}
@@ -1298,7 +1429,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 			bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP;
 
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-			if (intel_pt_fup_event(decoder) && no_tip)
+			if (intel_pt_fup_event(decoder, no_tip) && no_tip)
 				return 0;
 			return -EAGAIN;
 		}
@@ -1350,6 +1481,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 		return err;
 
 	intel_pt_update_nr(decoder);
+	intel_pt_sample_iflag_chg(decoder);
 
 	if (intel_pt_insn.branch == INTEL_PT_BR_INDIRECT) {
 		if (decoder->pkt_state == INTEL_PT_STATE_TIP_PGD) {
@@ -1464,6 +1596,7 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
 			decoder->state.to_ip = decoder->last_ip;
 			decoder->ip = decoder->last_ip;
 			intel_pt_update_nr(decoder);
+			intel_pt_sample_iflag_chg(decoder);
 			return 0;
 		}
 
@@ -1527,6 +1660,19 @@ static int intel_pt_mode_tsx(struct intel_pt_decoder *decoder, bool *no_tip)
 	return 0;
 }
 
+static int intel_pt_evd(struct intel_pt_decoder *decoder)
+{
+	if (decoder->evd_cnt >= INTEL_PT_MAX_EVDS) {
+		intel_pt_log_at("ERROR: Too many EVD packets", decoder->pos);
+		return -ENOSYS;
+	}
+	decoder->evd[decoder->evd_cnt++] = (struct intel_pt_evd){
+		.type = decoder->packet.count,
+		.payload = decoder->packet.payload,
+	};
+	return 0;
+}
+
 static uint64_t intel_pt_8b_tsc(uint64_t timestamp, uint64_t ref_timestamp)
 {
 	timestamp |= (ref_timestamp & (0xffULL << 56));
@@ -1620,12 +1766,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	decoder->state.from_ip = decoder->ip;
 	decoder->ip = 0;
 	decoder->pge = false;
-	decoder->set_fup_tx_flags = false;
-	decoder->set_fup_ptw = false;
-	decoder->set_fup_mwait = false;
-	decoder->set_fup_pwre = false;
-	decoder->set_fup_exstop = false;
-	decoder->set_fup_bep = false;
+	intel_pt_clear_fup_event(decoder);
 	decoder->overflow = true;
 	return -EOVERFLOW;
 }
@@ -1873,6 +2014,9 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 		case INTEL_PT_BIP:
 		case INTEL_PT_BEP:
 		case INTEL_PT_BEP_IP:
+		case INTEL_PT_CFE:
+		case INTEL_PT_CFE_IP:
+		case INTEL_PT_EVD:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
 			err = -EAGAIN;
@@ -1895,7 +2039,7 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_MODE_EXEC:
-			decoder->exec_mode = decoder->packet.payload;
+			intel_pt_mode_exec_status(decoder);
 			break;
 
 		case INTEL_PT_PIP:
@@ -1975,6 +2119,9 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_BIP:
 		case INTEL_PT_BEP:
 		case INTEL_PT_BEP_IP:
+		case INTEL_PT_CFE:
+		case INTEL_PT_CFE_IP:
+		case INTEL_PT_EVD:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
 			decoder->pkt_step = 0;
@@ -2026,6 +2173,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 				decoder->state.to_ip = decoder->ip;
 			}
 			intel_pt_update_nr(decoder);
+			intel_pt_sample_iflag_chg(decoder);
 			return 0;
 
 		case INTEL_PT_PIP:
@@ -2043,7 +2191,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_MODE_EXEC:
-			decoder->exec_mode = decoder->packet.payload;
+			intel_pt_mode_exec(decoder);
 			break;
 
 		case INTEL_PT_VMCS:
@@ -2134,6 +2282,9 @@ static int intel_pt_vm_psb_lookahead_cb(struct intel_pt_pkt_info *pkt_info)
 	case INTEL_PT_TIP:
 	case INTEL_PT_PSB:
 	case INTEL_PT_TRACESTOP:
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+	case INTEL_PT_EVD:
 	default:
 		return 1;
 	}
@@ -2653,6 +2804,9 @@ static int intel_pt_vm_time_correlation(struct intel_pt_decoder *decoder)
 			decoder->blk_type = 0;
 			break;
 
+		case INTEL_PT_CFE:
+		case INTEL_PT_CFE_IP:
+		case INTEL_PT_EVD:
 		case INTEL_PT_MODE_EXEC:
 		case INTEL_PT_MODE_TSX:
 		case INTEL_PT_MNT:
@@ -2719,6 +2873,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
 		intel_pt_update_nr(decoder);
+		intel_pt_sample_iflag_chg(decoder);
 		return HOP_RETURN;
 
 	case INTEL_PT_FUP:
@@ -2733,10 +2888,10 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 			decoder->state.type = INTEL_PT_INSTRUCTION;
 			decoder->state.from_ip = decoder->ip;
 			decoder->state.to_ip = 0;
-			intel_pt_fup_event(decoder);
+			intel_pt_fup_event(decoder, *no_tip);
 			return HOP_RETURN;
 		}
-		intel_pt_fup_event(decoder);
+		intel_pt_fup_event(decoder, *no_tip);
 		decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH;
 		*err = intel_pt_walk_fup_tip(decoder);
 		if (!*err && decoder->state.to_ip)
@@ -2789,6 +2944,9 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 	case INTEL_PT_BIP:
 	case INTEL_PT_BEP:
 	case INTEL_PT_BEP_IP:
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+	case INTEL_PT_EVD:
 	default:
 		return HOP_PROCESS;
 	}
@@ -2857,6 +3015,9 @@ static int intel_pt_psb_lookahead_cb(struct intel_pt_pkt_info *pkt_info)
 	case INTEL_PT_BIP:
 	case INTEL_PT_BEP:
 	case INTEL_PT_BEP_IP:
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+	case INTEL_PT_EVD:
 		if (data->after_psbend) {
 			data->after_psbend -= 1;
 			if (!data->after_psbend)
@@ -2994,6 +3155,7 @@ next:
 						decoder->pos);
 				break;
 			}
+			intel_pt_sample_iflag_chg(decoder);
 			intel_pt_set_ip(decoder);
 			decoder->state.from_ip = 0;
 			decoder->state.to_ip = decoder->ip;
@@ -3026,7 +3188,7 @@ next:
 			intel_pt_set_last_ip(decoder);
 			if (!decoder->branch_enable || !decoder->pge) {
 				decoder->ip = decoder->last_ip;
-				if (intel_pt_fup_event(decoder))
+				if (intel_pt_fup_event(decoder, no_tip))
 					return 0;
 				no_tip = false;
 				break;
@@ -3108,8 +3270,15 @@ next:
 			break;
 
 		case INTEL_PT_MODE_EXEC:
-			decoder->exec_mode = decoder->packet.payload;
-			break;
+			intel_pt_mode_exec(decoder);
+			err = intel_pt_get_next_packet(decoder);
+			if (err)
+				return err;
+			if (decoder->packet.type == INTEL_PT_FUP) {
+				decoder->set_fup_mode_exec = true;
+				no_tip = true;
+			}
+			goto next;
 
 		case INTEL_PT_MODE_TSX:
 			/* MODE_TSX need not be followed by FUP */
@@ -3223,6 +3392,35 @@ next:
 			}
 			goto next;
 
+		case INTEL_PT_CFE:
+			decoder->fup_cfe_pkt = decoder->packet;
+			decoder->set_fup_cfe = true;
+			if (!decoder->pge) {
+				intel_pt_fup_event(decoder, true);
+				return 0;
+			}
+			break;
+
+		case INTEL_PT_CFE_IP:
+			decoder->fup_cfe_pkt = decoder->packet;
+			err = intel_pt_get_next_packet(decoder);
+			if (err)
+				return err;
+			if (decoder->packet.type == INTEL_PT_FUP) {
+				decoder->set_fup_cfe_ip = true;
+				no_tip = true;
+			} else {
+				intel_pt_log_at("ERROR: Missing FUP after CFE",
+						decoder->pos);
+			}
+			goto next;
+
+		case INTEL_PT_EVD:
+			err = intel_pt_evd(decoder);
+			if (err)
+				return err;
+			break;
+
 		default:
 			return intel_pt_bug(decoder);
 		}
@@ -3265,6 +3463,9 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 		case INTEL_PT_BIP:
 		case INTEL_PT_BEP:
 		case INTEL_PT_BEP_IP:
+		case INTEL_PT_CFE:
+		case INTEL_PT_CFE_IP:
+		case INTEL_PT_EVD:
 			intel_pt_log("ERROR: Unexpected packet\n");
 			err = -ENOENT;
 			goto out;
@@ -3307,7 +3508,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_MODE_EXEC:
-			decoder->exec_mode = decoder->packet.payload;
+			intel_pt_mode_exec_status(decoder);
 			break;
 
 		case INTEL_PT_MODE_TSX:
@@ -3426,7 +3627,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_MODE_EXEC:
-			decoder->exec_mode = decoder->packet.payload;
+			intel_pt_mode_exec_status(decoder);
 			break;
 
 		case INTEL_PT_MODE_TSX:
@@ -3476,6 +3677,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_BIP:
 		case INTEL_PT_BEP:
 		case INTEL_PT_BEP_IP:
+		case INTEL_PT_CFE:
+		case INTEL_PT_CFE_IP:
+		case INTEL_PT_EVD:
 		default:
 			break;
 		}
@@ -3486,12 +3690,7 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 {
 	int err;
 
-	decoder->set_fup_tx_flags = false;
-	decoder->set_fup_ptw = false;
-	decoder->set_fup_mwait = false;
-	decoder->set_fup_pwre = false;
-	decoder->set_fup_exstop = false;
-	decoder->set_fup_bep = false;
+	intel_pt_clear_fup_event(decoder);
 	decoder->overflow = false;
 
 	if (!decoder->branch_enable) {
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 8fd68f7a0963..efb2cb3ae0ca 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -17,6 +17,7 @@
 
 #define INTEL_PT_IN_TX		(1 << 0)
 #define INTEL_PT_ABORT_TX	(1 << 1)
+#define INTEL_PT_IFLAG		(1 << 2)
 #define INTEL_PT_ASYNC		(1 << 2)
 #define INTEL_PT_FUP_IP		(1 << 3)
 #define INTEL_PT_SAMPLE_IPC	(1 << 4)
@@ -35,6 +36,8 @@ enum intel_pt_sample_type {
 	INTEL_PT_TRACE_END	= 1 << 10,
 	INTEL_PT_BLK_ITEMS	= 1 << 11,
 	INTEL_PT_PSB_EVT	= 1 << 12,
+	INTEL_PT_EVT		= 1 << 13,
+	INTEL_PT_IFLAG_CHG	= 1 << 14,
 };
 
 enum intel_pt_period_type {
@@ -209,10 +212,24 @@ struct intel_pt_vmcs_info {
 	bool error_printed;
 };
 
+/*
+ * Maximum number of event trace data in one go, assuming at most 1 per type
+ * and 6-bits of type in the EVD packet.
+ */
+#define INTEL_PT_MAX_EVDS 64
+
+/* Event trace data from EVD packet */
+struct intel_pt_evd {
+	int type;
+	uint64_t payload;
+};
+
 struct intel_pt_state {
 	enum intel_pt_sample_type type;
 	bool from_nr;
 	bool to_nr;
+	bool from_iflag;
+	bool to_iflag;
 	int err;
 	uint64_t from_ip;
 	uint64_t to_ip;
@@ -234,6 +251,10 @@ struct intel_pt_state {
 	int insn_len;
 	char insn[INTEL_PT_INSN_BUF_SZ];
 	struct intel_pt_blk_items items;
+	int cfe_type;
+	int cfe_vector;
+	int evd_cnt;
+	struct intel_pt_evd *evd;
 };
 
 struct intel_pt_insn;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4bd154848cad..18f97f43e01a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -64,6 +64,9 @@ static const char * const packet_name[] = {
 	[INTEL_PT_BIP]		= "BIP",
 	[INTEL_PT_BEP]		= "BEP",
 	[INTEL_PT_BEP_IP]	= "BEP",
+	[INTEL_PT_CFE]		= "CFE",
+	[INTEL_PT_CFE_IP]	= "CFE",
+	[INTEL_PT_EVD]		= "EVD",
 };
 
 const char *intel_pt_pkt_name(enum intel_pt_pkt_type type)
@@ -197,8 +200,7 @@ static int intel_pt_get_mnt(const unsigned char *buf, size_t len,
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_MNT;
 	memcpy_le64(&packet->payload, buf + 3, 8);
-	return 11
-;
+	return 11;
 }
 
 static int intel_pt_get_3byte(const unsigned char *buf, size_t len,
@@ -329,6 +331,29 @@ static int intel_pt_get_bep_ip(size_t len, struct intel_pt_pkt *packet)
 	return 2;
 }
 
+static int intel_pt_get_cfe(const unsigned char *buf, size_t len,
+			    struct intel_pt_pkt *packet)
+{
+	if (len < 4)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = buf[2] & 0x80 ? INTEL_PT_CFE_IP : INTEL_PT_CFE;
+	packet->count = buf[2] & 0x1f;
+	packet->payload = buf[3];
+	return 4;
+}
+
+static int intel_pt_get_evd(const unsigned char *buf, size_t len,
+			    struct intel_pt_pkt *packet)
+{
+	if (len < 11)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_EVD;
+	packet->count = buf[2] & 0x3f;
+	packet->payload = buf[3];
+	memcpy_le64(&packet->payload, buf + 3, 8);
+	return 11;
+}
+
 static int intel_pt_get_ext(const unsigned char *buf, size_t len,
 			    struct intel_pt_pkt *packet)
 {
@@ -375,6 +400,10 @@ static int intel_pt_get_ext(const unsigned char *buf, size_t len,
 		return intel_pt_get_bep(len, packet);
 	case 0xb3: /* BEP with IP */
 		return intel_pt_get_bep_ip(len, packet);
+	case 0x13: /* CFE */
+		return intel_pt_get_cfe(buf, len, packet);
+	case 0x53: /* EVD */
+		return intel_pt_get_evd(buf, len, packet);
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
@@ -475,6 +504,7 @@ static int intel_pt_get_mode(const unsigned char *buf, size_t len,
 	switch (buf[1] >> 5) {
 	case 0:
 		packet->type = INTEL_PT_MODE_EXEC;
+		packet->count = buf[1];
 		switch (buf[1] & 3) {
 		case 0:
 			packet->payload = 16;
@@ -624,6 +654,9 @@ void intel_pt_upd_pkt_ctx(const struct intel_pt_pkt *packet,
 	case INTEL_PT_MWAIT:
 	case INTEL_PT_BEP:
 	case INTEL_PT_BEP_IP:
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+	case INTEL_PT_EVD:
 		*ctx = INTEL_PT_NO_CTX;
 		break;
 	case INTEL_PT_BBP:
@@ -709,7 +742,8 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
 		return snprintf(buf, buf_len, "%s CTC 0x%x FC 0x%x", name,
 				(unsigned)payload, packet->count);
 	case INTEL_PT_MODE_EXEC:
-		return snprintf(buf, buf_len, "%s %lld", name, payload);
+		return snprintf(buf, buf_len, "%s IF:%d %lld",
+				name, !!(packet->count & 4), payload);
 	case INTEL_PT_MODE_TSX:
 		return snprintf(buf, buf_len, "%s TXAbort:%u InTX:%u",
 				name, (unsigned)(payload >> 1) & 1,
@@ -751,6 +785,13 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
 	case INTEL_PT_BIP:
 		return snprintf(buf, buf_len, "%s ID 0x%02x Value 0x%llx",
 				name, packet->count, payload);
+	case INTEL_PT_CFE:
+	case INTEL_PT_CFE_IP:
+		return snprintf(buf, buf_len, "%s IP:%d Type 0x%02x Vector 0x%llx",
+				name, packet->type == INTEL_PT_CFE_IP, packet->count, payload);
+	case INTEL_PT_EVD:
+		return snprintf(buf, buf_len, "%s Type 0x%02x Payload 0x%llx",
+				name, packet->count, payload);
 	default:
 		break;
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
index 996090cb84f6..496ba4be875c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
@@ -56,6 +56,9 @@ enum intel_pt_pkt_type {
 	INTEL_PT_BIP,
 	INTEL_PT_BEP,
 	INTEL_PT_BEP_IP,
+	INTEL_PT_CFE,
+	INTEL_PT_CFE_IP,
+	INTEL_PT_EVD,
 };
 
 struct intel_pt_pkt {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index e8613cbda331..ec43d364d0de 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -46,6 +46,12 @@
 
 #define MAX_TIMESTAMP (~0ULL)
 
+#define INTEL_PT_CFG_PASS_THRU	BIT_ULL(0)
+#define INTEL_PT_CFG_PWR_EVT_EN	BIT_ULL(4)
+#define INTEL_PT_CFG_BRANCH_EN	BIT_ULL(13)
+#define INTEL_PT_CFG_EVT_EN	BIT_ULL(31)
+#define INTEL_PT_CFG_TNT_DIS	BIT_ULL(55)
+
 struct range {
 	u64 start;
 	u64 end;
@@ -71,6 +77,7 @@ struct intel_pt {
 	bool mispred_all;
 	bool use_thread_stack;
 	bool callstack;
+	bool cap_event_trace;
 	unsigned int br_stack_sz;
 	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
@@ -115,6 +122,12 @@ struct intel_pt {
 	bool sample_pebs;
 	struct evsel *pebs_evsel;
 
+	u64 evt_sample_type;
+	u64 evt_id;
+
+	u64 iflag_chg_sample_type;
+	u64 iflag_chg_id;
+
 	u64 tsc_bit;
 	u64 mtc_bit;
 	u64 mtc_freq_bits;
@@ -953,12 +966,26 @@ static bool intel_pt_branch_enable(struct intel_pt *pt)
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
 		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
-		    (config & 1) && !(config & 0x2000))
+		    (config & INTEL_PT_CFG_PASS_THRU) &&
+		    !(config & INTEL_PT_CFG_BRANCH_EN))
 			return false;
 	}
 	return true;
 }
 
+static bool intel_pt_disabled_tnt(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+	u64 config;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
+		    config & INTEL_PT_CFG_TNT_DIS)
+			return true;
+	}
+	return false;
+}
+
 static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 {
 	struct evsel *evsel;
@@ -1214,6 +1241,10 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	params.first_timestamp = pt->first_timestamp;
 	params.max_loops = pt->max_loops;
 
+	/* Cannot walk code without TNT, so force 'quick' mode */
+	if (params.branch_enable && intel_pt_disabled_tnt(pt) && !params.quick)
+		params.quick = 1;
+
 	if (pt->filts.cnt > 0)
 		params.pgd_ip = intel_pt_pgd_ip;
 
@@ -1316,6 +1347,8 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 
 static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 {
+	struct intel_pt *pt = ptq->pt;
+
 	ptq->insn_len = 0;
 	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
 		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
@@ -1346,6 +1379,17 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
 	if (ptq->state->type & INTEL_PT_TRACE_END)
 		ptq->flags |= PERF_IP_FLAG_TRACE_END;
+
+	if (pt->cap_event_trace) {
+		if (ptq->state->type & INTEL_PT_IFLAG_CHG) {
+			if (!ptq->state->from_iflag)
+				ptq->flags |= PERF_IP_FLAG_INTR_DISABLE;
+			if (ptq->state->from_iflag != ptq->state->to_iflag)
+				ptq->flags |= PERF_IP_FLAG_INTR_TOGGLE;
+		} else if (!ptq->state->to_iflag) {
+			ptq->flags |= PERF_IP_FLAG_INTR_DISABLE;
+		}
+	}
 }
 
 static void intel_pt_setup_time_range(struct intel_pt *pt,
@@ -2160,6 +2204,78 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 	return err;
 }
 
+static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq)
+{
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+	struct {
+		struct perf_synth_intel_evt cfe;
+		struct perf_synth_intel_evd evd[INTEL_PT_MAX_EVDS];
+	} raw;
+	int i;
+
+	if (intel_pt_skip_event(pt))
+		return 0;
+
+	intel_pt_prep_p_sample(pt, ptq, event, &sample);
+
+	sample.id        = ptq->pt->evt_id;
+	sample.stream_id = ptq->pt->evt_id;
+
+	raw.cfe.type     = ptq->state->cfe_type;
+	raw.cfe.reserved = 0;
+	raw.cfe.ip       = !!(ptq->state->flags & INTEL_PT_FUP_IP);
+	raw.cfe.vector   = ptq->state->cfe_vector;
+	raw.cfe.evd_cnt  = ptq->state->evd_cnt;
+
+	for (i = 0; i < ptq->state->evd_cnt; i++) {
+		raw.evd[i].et       = 0;
+		raw.evd[i].evd_type = ptq->state->evd[i].type;
+		raw.evd[i].payload  = ptq->state->evd[i].payload;
+	}
+
+	sample.raw_size = perf_synth__raw_size(raw) +
+			  ptq->state->evd_cnt * sizeof(struct perf_synth_intel_evd);
+	sample.raw_data = perf_synth__raw_data(&raw);
+
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->evt_sample_type);
+}
+
+static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq)
+{
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+	struct perf_synth_intel_iflag_chg raw;
+
+	if (intel_pt_skip_event(pt))
+		return 0;
+
+	intel_pt_prep_p_sample(pt, ptq, event, &sample);
+
+	sample.id = ptq->pt->iflag_chg_id;
+	sample.stream_id = ptq->pt->iflag_chg_id;
+
+	raw.flags = 0;
+	raw.iflag = ptq->state->to_iflag;
+
+	if (ptq->state->type & INTEL_PT_BRANCH) {
+		raw.via_branch = 1;
+		raw.branch_ip = ptq->state->to_ip;
+	} else {
+		sample.addr = 0;
+	}
+	sample.flags = ptq->flags;
+
+	sample.raw_size = perf_synth__raw_size(raw);
+	sample.raw_data = perf_synth__raw_data(&raw);
+
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->iflag_chg_sample_type);
+}
+
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
@@ -2266,6 +2382,19 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
+	if (pt->synth_opts.intr_events) {
+		if (state->type & INTEL_PT_EVT) {
+			err = intel_pt_synth_events_sample(ptq);
+			if (err)
+				return err;
+		}
+		if (state->type & INTEL_PT_IFLAG_CHG) {
+			err = intel_pt_synth_iflag_chg_sample(ptq);
+			if (err)
+				return err;
+		}
+	}
+
 	if (pt->sample_pwr_events) {
 		if (state->type & INTEL_PT_PSB_EVT) {
 			err = intel_pt_synth_psb_sample(ptq);
@@ -3429,7 +3558,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		id += 1;
 	}
 
-	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) {
+	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & INTEL_PT_CFG_PWR_EVT_EN)) {
 		attr.config = PERF_SYNTH_INTEL_MWAIT;
 		err = intel_pt_synth_event(session, "mwait", &attr, id);
 		if (err)
@@ -3463,6 +3592,28 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		id += 1;
 	}
 
+	if (pt->synth_opts.intr_events && (evsel->core.attr.config & INTEL_PT_CFG_EVT_EN)) {
+		attr.config = PERF_SYNTH_INTEL_EVT;
+		err = intel_pt_synth_event(session, "evt", &attr, id);
+		if (err)
+			return err;
+		pt->evt_sample_type = attr.sample_type;
+		pt->evt_id = id;
+		intel_pt_set_event_name(evlist, id, "evt");
+		id += 1;
+	}
+
+	if (pt->synth_opts.intr_events && pt->cap_event_trace) {
+		attr.config = PERF_SYNTH_INTEL_IFLAG_CHG;
+		err = intel_pt_synth_event(session, "iflag", &attr, id);
+		if (err)
+			return err;
+		pt->iflag_chg_sample_type = attr.sample_type;
+		pt->iflag_chg_id = id;
+		intel_pt_set_event_name(evlist, id, "iflag");
+		id += 1;
+	}
+
 	return 0;
 }
 
@@ -3790,7 +3941,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	}
 
 	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
-	info_end = (void *)info + auxtrace_info->header.size;
+	info_end = (void *)auxtrace_info + auxtrace_info->header.size;
 
 	if (intel_pt_has(auxtrace_info, INTEL_PT_FILTER_STR_LEN)) {
 		size_t len;
@@ -3829,6 +3980,13 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		intel_pt_print_info_str("Filter string", pt->filter);
 	}
 
+	if ((void *)info < info_end) {
+		pt->cap_event_trace = *info++;
+		if (dump_trace)
+			fprintf(stdout, "  Cap Event Trace     %d\n",
+				pt->cap_event_trace);
+	}
+
 	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
 	if (pt->timeless_decoding && !pt->tc.time_mult)
 		pt->tc.time_mult = 1;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 917a9c707371..a23255773c60 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -382,15 +382,15 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 
 static pid_t jr_entry_pid(struct jit_buf_desc *jd, union jr_entry *jr)
 {
-	if (jd->nsi && jd->nsi->in_pidns)
-		return jd->nsi->tgid;
+	if (jd->nsi && nsinfo__in_pidns(jd->nsi))
+		return nsinfo__tgid(jd->nsi);
 	return jr->load.pid;
 }
 
 static pid_t jr_entry_tid(struct jit_buf_desc *jd, union jr_entry *jr)
 {
-	if (jd->nsi && jd->nsi->in_pidns)
-		return jd->nsi->pid;
+	if (jd->nsi && nsinfo__in_pidns(jd->nsi))
+		return nsinfo__pid(jd->nsi);
 	return jr->load.tid;
 }
 
@@ -779,7 +779,7 @@ jit_detect(char *mmap_name, pid_t pid, struct nsinfo *nsi)
 	 * pid does not match mmap pid
 	 * pid==0 in system-wide mode (synthesized)
 	 */
-	if (pid && pid2 != nsi->nstgid)
+	if (pid && pid2 != nsinfo__nstgid(nsi))
 		return -1;
 	/*
 	 * validate suffix
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 394550003693..b80048546451 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -89,7 +89,10 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	int err = -ENOMEM;
 
 	memset(machine, 0, sizeof(*machine));
-	maps__init(&machine->kmaps, machine);
+	machine->kmaps = maps__new(machine);
+	if (machine->kmaps == NULL)
+		return -ENOMEM;
+
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
@@ -108,7 +111,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
-		return -ENOMEM;
+		goto out;
 
 	if (machine__set_mmap_name(machine))
 		goto out;
@@ -131,6 +134,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 out:
 	if (err) {
+		zfree(&machine->kmaps);
 		zfree(&machine->root_dir);
 		zfree(&machine->mmap_name);
 	}
@@ -220,7 +224,7 @@ void machine__exit(struct machine *machine)
 		return;
 
 	machine__destroy_kernel_maps(machine);
-	maps__exit(&machine->kmaps);
+	maps__delete(machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
@@ -778,7 +782,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 					     struct perf_sample *sample __maybe_unused)
 {
 	struct symbol *sym;
-	struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
+	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 
 	if (!map) {
 		struct dso *dso = dso__new(event->ksymbol.name);
@@ -801,7 +805,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
-		maps__insert(&machine->kmaps, map);
+		maps__insert(machine__kernel_maps(machine), map);
 		map__put(map);
 		dso__set_loaded(dso);
 
@@ -827,12 +831,12 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 	struct symbol *sym;
 	struct map *map;
 
-	map = maps__find(&machine->kmaps, event->ksymbol.addr);
+	map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
 	if (!map)
 		return 0;
 
 	if (map != machine->vmlinux_map)
-		maps__remove(&machine->kmaps, map);
+		maps__remove(machine__kernel_maps(machine), map);
 	else {
 		sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
 		if (sym)
@@ -858,7 +862,7 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
 int machine__process_text_poke(struct machine *machine, union perf_event *event,
 			       struct perf_sample *sample __maybe_unused)
 {
-	struct map *map = maps__find(&machine->kmaps, event->text_poke.addr);
+	struct map *map = maps__find(machine__kernel_maps(machine), event->text_poke.addr);
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (dump_trace)
@@ -914,7 +918,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start
 	if (map == NULL)
 		goto out;
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 
 	/* Put the map here because maps__insert already got it */
 	map__put(map);
@@ -1100,7 +1104,7 @@ int machine__create_extra_kernel_map(struct machine *machine,
 
 	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 
 	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
 		  kmap->name, map->start, map->end);
@@ -1145,7 +1149,7 @@ static u64 find_entry_trampoline(struct dso *dso)
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel)
 {
-	struct maps *kmaps = &machine->kmaps;
+	struct maps *kmaps = machine__kernel_maps(machine);
 	int nr_cpus_avail, cpu;
 	bool found = false;
 	struct map *map;
@@ -1215,7 +1219,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		return -1;
 
 	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
-	maps__insert(&machine->kmaps, machine->vmlinux_map);
+	maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
 	return 0;
 }
 
@@ -1228,7 +1232,7 @@ void machine__destroy_kernel_maps(struct machine *machine)
 		return;
 
 	kmap = map__kmap(map);
-	maps__remove(&machine->kmaps, map);
+	maps__remove(machine__kernel_maps(machine), map);
 	if (kmap && kmap->ref_reloc_sym) {
 		zfree((char **)&kmap->ref_reloc_sym->name);
 		zfree(&kmap->ref_reloc_sym);
@@ -1323,7 +1327,7 @@ int machine__load_kallsyms(struct machine *machine, const char *filename)
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		maps__fixup_end(&machine->kmaps);
+		maps__fixup_end(machine__kernel_maps(machine));
 	}
 
 	return ret;
@@ -1471,7 +1475,7 @@ static int machine__set_modules_path(struct machine *machine)
 		 machine->root_dir, version);
 	free(version);
 
-	return maps__set_modules_path_dir(&machine->kmaps, modules_path, 0);
+	return maps__set_modules_path_dir(machine__kernel_maps(machine), modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
 				u64 *size __maybe_unused,
@@ -1544,11 +1548,11 @@ static void machine__update_kernel_mmap(struct machine *machine,
 	struct map *map = machine__kernel_map(machine);
 
 	map__get(map);
-	maps__remove(&machine->kmaps, map);
+	maps__remove(machine__kernel_maps(machine), map);
 
 	machine__set_kernel_mmap(machine, start, end);
 
-	maps__insert(&machine->kmaps, map);
+	maps__insert(machine__kernel_maps(machine), map);
 	map__put(map);
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index c5a45dc8df4c..0023165422aa 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -51,7 +51,7 @@ struct machine {
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
 	struct dsos	  dsos;
-	struct maps	  kmaps;
+	struct maps	  *kmaps;
 	struct map	  *vmlinux_map;
 	u64		  kernel_start;
 	pid_t		  *current_tid;
@@ -83,7 +83,7 @@ struct map *machine__kernel_map(struct machine *machine)
 static inline
 struct maps *machine__kernel_maps(struct machine *machine)
 {
-	return &machine->kmaps;
+	return machine->kmaps;
 }
 
 int machine__get_kernel_start(struct machine *machine);
@@ -223,7 +223,7 @@ static inline
 struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr,
 					   struct map **mapp)
 {
-	return maps__find_symbol(&machine->kmaps, addr, mapp);
+	return maps__find_symbol(machine->kmaps, addr, mapp);
 }
 
 static inline
@@ -231,7 +231,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 						   const char *name,
 						   struct map **mapp)
 {
-	return maps__find_symbol_by_name(&machine->kmaps, name, mapp);
+	return maps__find_symbol_by_name(machine->kmaps, name, mapp);
 }
 
 int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8af693d9678c..e0aa4a254583 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,31 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "symbol.h"
-#include <assert.h>
-#include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <stdio.h>
-#include <unistd.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include "debug.h"
 #include "dso.h"
 #include "map.h"
-#include "map_symbol.h"
+#include "namespaces.h"
+#include "srcline.h"
+#include "symbol.h"
 #include "thread.h"
 #include "vdso.h"
-#include "build-id.h"
-#include "debug.h"
-#include "machine.h"
-#include <linux/string.h>
-#include <linux/zalloc.h>
-#include "srcline.h"
-#include "namespaces.h"
-#include "unwind.h"
-#include "srccode.h"
-#include "ui/ui.h"
-
-static void __maps__insert(struct maps *maps, struct map *map);
 
 static inline int is_android_lib(const char *filename)
 {
@@ -138,7 +127,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 
 	if (map != NULL) {
 		char newfilename[PATH_MAX];
-		struct dso *dso;
+		struct dso *dso, *header_bid_dso;
 		int anon, no_dso, vdso, android;
 
 		android = is_android_lib(filename);
@@ -151,7 +140,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 
 		if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) {
 			snprintf(newfilename, sizeof(newfilename),
-				 "/tmp/perf-%d.map", nsi->pid);
+				 "/tmp/perf-%d.map", nsinfo__pid(nsi));
 			filename = newfilename;
 		}
 
@@ -168,7 +157,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			nnsi = nsinfo__copy(nsi);
 			if (nnsi) {
 				nsinfo__put(nsi);
-				nnsi->need_setns = false;
+				nsinfo__clear_need_setns(nnsi);
 				nsi = nnsi;
 			}
 			pgoff = 0;
@@ -194,9 +183,23 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		}
 		dso->nsinfo = nsi;
 
-		if (build_id__is_defined(bid))
+		if (build_id__is_defined(bid)) {
 			dso__set_build_id(dso, bid);
-
+		} else {
+			/*
+			 * If the mmap event had no build ID, search for an existing dso from the
+			 * build ID header by name. Otherwise only the dso loaded at the time of
+			 * reading the header will have the build ID set and all future mmaps will
+			 * have it missing.
+			 */
+			down_read(&machine->dsos.lock);
+			header_bid_dso = __dsos__find(&machine->dsos, filename, false);
+			up_read(&machine->dsos.lock);
+			if (header_bid_dso && header_bid_dso->header_build_id) {
+				dso__set_build_id(dso, &header_bid_dso->bid);
+				dso->header_build_id = 1;
+			}
+		}
 		dso__put(dso);
 	}
 	return map;
@@ -524,403 +527,13 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
-void maps__init(struct maps *maps, struct machine *machine)
-{
-	maps->entries = RB_ROOT;
-	init_rwsem(&maps->lock);
-	maps->machine = machine;
-	maps->last_search_by_name = NULL;
-	maps->nr_maps = 0;
-	maps->maps_by_name = NULL;
-	refcount_set(&maps->refcnt, 1);
-}
-
-static void __maps__free_maps_by_name(struct maps *maps)
-{
-	/*
-	 * Free everything to try to do it from the rbtree in the next search
-	 */
-	zfree(&maps->maps_by_name);
-	maps->nr_maps_allocated = 0;
-}
-
-void maps__insert(struct maps *maps, struct map *map)
-{
-	down_write(&maps->lock);
-	__maps__insert(maps, map);
-	++maps->nr_maps;
-
-	if (map->dso && map->dso->kernel) {
-		struct kmap *kmap = map__kmap(map);
-
-		if (kmap)
-			kmap->kmaps = maps;
-		else
-			pr_err("Internal error: kernel dso with non kernel map\n");
-	}
-
-
-	/*
-	 * If we already performed some search by name, then we need to add the just
-	 * inserted map and resort.
-	 */
-	if (maps->maps_by_name) {
-		if (maps->nr_maps > maps->nr_maps_allocated) {
-			int nr_allocate = maps->nr_maps * 2;
-			struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map));
-
-			if (maps_by_name == NULL) {
-				__maps__free_maps_by_name(maps);
-				up_write(&maps->lock);
-				return;
-			}
-
-			maps->maps_by_name = maps_by_name;
-			maps->nr_maps_allocated = nr_allocate;
-		}
-		maps->maps_by_name[maps->nr_maps - 1] = map;
-		__maps__sort_by_name(maps);
-	}
-	up_write(&maps->lock);
-}
-
-static void __maps__remove(struct maps *maps, struct map *map)
-{
-	rb_erase_init(&map->rb_node, &maps->entries);
-	map__put(map);
-}
-
-void maps__remove(struct maps *maps, struct map *map)
-{
-	down_write(&maps->lock);
-	if (maps->last_search_by_name == map)
-		maps->last_search_by_name = NULL;
-
-	__maps__remove(maps, map);
-	--maps->nr_maps;
-	if (maps->maps_by_name)
-		__maps__free_maps_by_name(maps);
-	up_write(&maps->lock);
-}
-
-static void __maps__purge(struct maps *maps)
-{
-	struct map *pos, *next;
-
-	maps__for_each_entry_safe(maps, pos, next) {
-		rb_erase_init(&pos->rb_node,  &maps->entries);
-		map__put(pos);
-	}
-}
-
-void maps__exit(struct maps *maps)
-{
-	down_write(&maps->lock);
-	__maps__purge(maps);
-	up_write(&maps->lock);
-}
-
-bool maps__empty(struct maps *maps)
-{
-	return !maps__first(maps);
-}
-
-struct maps *maps__new(struct machine *machine)
-{
-	struct maps *maps = zalloc(sizeof(*maps));
-
-	if (maps != NULL)
-		maps__init(maps, machine);
-
-	return maps;
-}
-
-void maps__delete(struct maps *maps)
-{
-	maps__exit(maps);
-	unwind__finish_access(maps);
-	free(maps);
-}
-
-void maps__put(struct maps *maps)
-{
-	if (maps && refcount_dec_and_test(&maps->refcnt))
-		maps__delete(maps);
-}
-
-struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
-{
-	struct map *map = maps__find(maps, addr);
-
-	/* Ensure map is loaded before using map->map_ip */
-	if (map != NULL && map__load(map) >= 0) {
-		if (mapp != NULL)
-			*mapp = map;
-		return map__find_symbol(map, map->map_ip(map, addr));
-	}
-
-	return NULL;
-}
-
-static bool map__contains_symbol(struct map *map, struct symbol *sym)
+bool map__contains_symbol(const struct map *map, const struct symbol *sym)
 {
 	u64 ip = map->unmap_ip(map, sym->start);
 
 	return ip >= map->start && ip < map->end;
 }
 
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
-{
-	struct symbol *sym;
-	struct map *pos;
-
-	down_read(&maps->lock);
-
-	maps__for_each_entry(maps, pos) {
-		sym = map__find_symbol_by_name(pos, name);
-
-		if (sym == NULL)
-			continue;
-		if (!map__contains_symbol(pos, sym)) {
-			sym = NULL;
-			continue;
-		}
-		if (mapp != NULL)
-			*mapp = pos;
-		goto out;
-	}
-
-	sym = NULL;
-out:
-	up_read(&maps->lock);
-	return sym;
-}
-
-int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
-{
-	if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) {
-		if (maps == NULL)
-			return -1;
-		ams->ms.map = maps__find(maps, ams->addr);
-		if (ams->ms.map == NULL)
-			return -1;
-	}
-
-	ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr);
-	ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr);
-
-	return ams->ms.sym ? 0 : -1;
-}
-
-size_t maps__fprintf(struct maps *maps, FILE *fp)
-{
-	size_t printed = 0;
-	struct map *pos;
-
-	down_read(&maps->lock);
-
-	maps__for_each_entry(maps, pos) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-
-	up_read(&maps->lock);
-
-	return printed;
-}
-
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
-{
-	struct rb_root *root;
-	struct rb_node *next, *first;
-	int err = 0;
-
-	down_write(&maps->lock);
-
-	root = &maps->entries;
-
-	/*
-	 * Find first map where end > map->start.
-	 * Same as find_vma() in kernel.
-	 */
-	next = root->rb_node;
-	first = NULL;
-	while (next) {
-		struct map *pos = rb_entry(next, struct map, rb_node);
-
-		if (pos->end > map->start) {
-			first = next;
-			if (pos->start <= map->start)
-				break;
-			next = next->rb_left;
-		} else
-			next = next->rb_right;
-	}
-
-	next = first;
-	while (next) {
-		struct map *pos = rb_entry(next, struct map, rb_node);
-		next = rb_next(&pos->rb_node);
-
-		/*
-		 * Stop if current map starts after map->end.
-		 * Maps are ordered by start: next will not overlap for sure.
-		 */
-		if (pos->start >= map->end)
-			break;
-
-		if (verbose >= 2) {
-
-			if (use_browser) {
-				pr_debug("overlapping maps in %s (disable tui for more info)\n",
-					   map->dso->name);
-			} else {
-				fputs("overlapping maps:\n", fp);
-				map__fprintf(map, fp);
-				map__fprintf(pos, fp);
-			}
-		}
-
-		rb_erase_init(&pos->rb_node, root);
-		/*
-		 * Now check if we need to create new maps for areas not
-		 * overlapped by the new map:
-		 */
-		if (map->start > pos->start) {
-			struct map *before = map__clone(pos);
-
-			if (before == NULL) {
-				err = -ENOMEM;
-				goto put_map;
-			}
-
-			before->end = map->start;
-			__maps__insert(maps, before);
-			if (verbose >= 2 && !use_browser)
-				map__fprintf(before, fp);
-			map__put(before);
-		}
-
-		if (map->end < pos->end) {
-			struct map *after = map__clone(pos);
-
-			if (after == NULL) {
-				err = -ENOMEM;
-				goto put_map;
-			}
-
-			after->start = map->end;
-			after->pgoff += map->end - pos->start;
-			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
-			__maps__insert(maps, after);
-			if (verbose >= 2 && !use_browser)
-				map__fprintf(after, fp);
-			map__put(after);
-		}
-put_map:
-		map__put(pos);
-
-		if (err)
-			goto out;
-	}
-
-	err = 0;
-out:
-	up_write(&maps->lock);
-	return err;
-}
-
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-int maps__clone(struct thread *thread, struct maps *parent)
-{
-	struct maps *maps = thread->maps;
-	int err;
-	struct map *map;
-
-	down_read(&parent->lock);
-
-	maps__for_each_entry(parent, map) {
-		struct map *new = map__clone(map);
-
-		if (new == NULL) {
-			err = -ENOMEM;
-			goto out_unlock;
-		}
-
-		err = unwind__prepare_access(maps, new, NULL);
-		if (err)
-			goto out_unlock;
-
-		maps__insert(maps, new);
-		map__put(new);
-	}
-
-	err = 0;
-out_unlock:
-	up_read(&parent->lock);
-	return err;
-}
-
-static void __maps__insert(struct maps *maps, struct map *map)
-{
-	struct rb_node **p = &maps->entries.rb_node;
-	struct rb_node *parent = NULL;
-	const u64 ip = map->start;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, &maps->entries);
-	map__get(map);
-}
-
-struct map *maps__find(struct maps *maps, u64 ip)
-{
-	struct rb_node *p;
-	struct map *m;
-
-	down_read(&maps->lock);
-
-	p = maps->entries.rb_node;
-	while (p != NULL) {
-		m = rb_entry(p, struct map, rb_node);
-		if (ip < m->start)
-			p = p->rb_left;
-		else if (ip >= m->end)
-			p = p->rb_right;
-		else
-			goto out;
-	}
-
-	m = NULL;
-out:
-	up_read(&maps->lock);
-	return m;
-}
-
-struct map *maps__first(struct maps *maps)
-{
-	struct rb_node *first = rb_first(&maps->entries);
-
-	if (first)
-		return rb_entry(first, struct map, rb_node);
-	return NULL;
-}
-
 static struct map *__map__next(struct map *map)
 {
 	struct rb_node *next = rb_next(&map->rb_node);
@@ -961,3 +574,18 @@ struct maps *map__kmaps(struct map *map)
 	}
 	return kmap->kmaps;
 }
+
+u64 map__map_ip(const struct map *map, u64 ip)
+{
+	return ip - map->start + map->pgoff;
+}
+
+u64 map__unmap_ip(const struct map *map, u64 ip)
+{
+	return ip + map->start - map->pgoff;
+}
+
+u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip)
+{
+	return ip;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index d32f5b28c1fb..3dcfe06db6b3 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -29,9 +29,9 @@ struct map {
 	u64			reloc;
 
 	/* ip -> dso rip */
-	u64			(*map_ip)(struct map *, u64);
+	u64			(*map_ip)(const struct map *, u64);
 	/* dso rip -> ip */
-	u64			(*unmap_ip)(struct map *, u64);
+	u64			(*unmap_ip)(const struct map *, u64);
 
 	struct dso		*dso;
 	refcount_t		refcnt;
@@ -44,20 +44,12 @@ struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct maps *map__kmaps(struct map *map);
 
-static inline u64 map__map_ip(struct map *map, u64 ip)
-{
-	return ip - map->start + map->pgoff;
-}
-
-static inline u64 map__unmap_ip(struct map *map, u64 ip)
-{
-	return ip + map->start - map->pgoff;
-}
-
-static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
-{
-	return ip;
-}
+/* ip -> dso rip */
+u64 map__map_ip(const struct map *map, u64 ip);
+/* dso rip -> ip */
+u64 map__unmap_ip(const struct map *map, u64 ip);
+/* Returns ip */
+u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip);
 
 static inline size_t map__size(const struct map *map)
 {
@@ -160,6 +152,8 @@ static inline bool __map__is_kmodule(const struct map *map)
 
 bool map__has_symbols(const struct map *map);
 
+bool map__contains_symbol(const struct map *map, const struct symbol *sym);
+
 #define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
 
 static inline bool is_entry_trampoline(const char *name)
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
new file mode 100644
index 000000000000..37bd5b40000d
--- /dev/null
+++ b/tools/perf/util/maps.c
@@ -0,0 +1,403 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/zalloc.h>
+#include "debug.h"
+#include "dso.h"
+#include "map.h"
+#include "maps.h"
+#include "thread.h"
+#include "ui/ui.h"
+#include "unwind.h"
+
+static void __maps__insert(struct maps *maps, struct map *map);
+
+static void maps__init(struct maps *maps, struct machine *machine)
+{
+	maps->entries = RB_ROOT;
+	init_rwsem(&maps->lock);
+	maps->machine = machine;
+	maps->last_search_by_name = NULL;
+	maps->nr_maps = 0;
+	maps->maps_by_name = NULL;
+	refcount_set(&maps->refcnt, 1);
+}
+
+static void __maps__free_maps_by_name(struct maps *maps)
+{
+	/*
+	 * Free everything to try to do it from the rbtree in the next search
+	 */
+	zfree(&maps->maps_by_name);
+	maps->nr_maps_allocated = 0;
+}
+
+void maps__insert(struct maps *maps, struct map *map)
+{
+	down_write(&maps->lock);
+	__maps__insert(maps, map);
+	++maps->nr_maps;
+
+	if (map->dso && map->dso->kernel) {
+		struct kmap *kmap = map__kmap(map);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+
+
+	/*
+	 * If we already performed some search by name, then we need to add the just
+	 * inserted map and resort.
+	 */
+	if (maps->maps_by_name) {
+		if (maps->nr_maps > maps->nr_maps_allocated) {
+			int nr_allocate = maps->nr_maps * 2;
+			struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map));
+
+			if (maps_by_name == NULL) {
+				__maps__free_maps_by_name(maps);
+				up_write(&maps->lock);
+				return;
+			}
+
+			maps->maps_by_name = maps_by_name;
+			maps->nr_maps_allocated = nr_allocate;
+		}
+		maps->maps_by_name[maps->nr_maps - 1] = map;
+		__maps__sort_by_name(maps);
+	}
+	up_write(&maps->lock);
+}
+
+static void __maps__remove(struct maps *maps, struct map *map)
+{
+	rb_erase_init(&map->rb_node, &maps->entries);
+	map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	down_write(&maps->lock);
+	if (maps->last_search_by_name == map)
+		maps->last_search_by_name = NULL;
+
+	__maps__remove(maps, map);
+	--maps->nr_maps;
+	if (maps->maps_by_name)
+		__maps__free_maps_by_name(maps);
+	up_write(&maps->lock);
+}
+
+static void __maps__purge(struct maps *maps)
+{
+	struct map *pos, *next;
+
+	maps__for_each_entry_safe(maps, pos, next) {
+		rb_erase_init(&pos->rb_node,  &maps->entries);
+		map__put(pos);
+	}
+}
+
+static void maps__exit(struct maps *maps)
+{
+	down_write(&maps->lock);
+	__maps__purge(maps);
+	up_write(&maps->lock);
+}
+
+bool maps__empty(struct maps *maps)
+{
+	return !maps__first(maps);
+}
+
+struct maps *maps__new(struct machine *machine)
+{
+	struct maps *maps = zalloc(sizeof(*maps));
+
+	if (maps != NULL)
+		maps__init(maps, machine);
+
+	return maps;
+}
+
+void maps__delete(struct maps *maps)
+{
+	maps__exit(maps);
+	unwind__finish_access(maps);
+	free(maps);
+}
+
+void maps__put(struct maps *maps)
+{
+	if (maps && refcount_dec_and_test(&maps->refcnt))
+		maps__delete(maps);
+}
+
+struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
+{
+	struct map *map = maps__find(maps, addr);
+
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map) >= 0) {
+		if (mapp != NULL)
+			*mapp = map;
+		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)
+{
+	struct symbol *sym;
+	struct map *pos;
+
+	down_read(&maps->lock);
+
+	maps__for_each_entry(maps, pos) {
+		sym = map__find_symbol_by_name(pos, name);
+
+		if (sym == NULL)
+			continue;
+		if (!map__contains_symbol(pos, sym)) {
+			sym = NULL;
+			continue;
+		}
+		if (mapp != NULL)
+			*mapp = pos;
+		goto out;
+	}
+
+	sym = NULL;
+out:
+	up_read(&maps->lock);
+	return sym;
+}
+
+int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
+{
+	if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) {
+		if (maps == NULL)
+			return -1;
+		ams->ms.map = maps__find(maps, ams->addr);
+		if (ams->ms.map == NULL)
+			return -1;
+	}
+
+	ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr);
+	ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr);
+
+	return ams->ms.sym ? 0 : -1;
+}
+
+size_t maps__fprintf(struct maps *maps, FILE *fp)
+{
+	size_t printed = 0;
+	struct map *pos;
+
+	down_read(&maps->lock);
+
+	maps__for_each_entry(maps, pos) {
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 2) {
+			printed += dso__fprintf(pos->dso, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+
+	up_read(&maps->lock);
+
+	return printed;
+}
+
+int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+{
+	struct rb_root *root;
+	struct rb_node *next, *first;
+	int err = 0;
+
+	down_write(&maps->lock);
+
+	root = &maps->entries;
+
+	/*
+	 * Find first map where end > map->start.
+	 * Same as find_vma() in kernel.
+	 */
+	next = root->rb_node;
+	first = NULL;
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+
+		if (pos->end > map->start) {
+			first = next;
+			if (pos->start <= map->start)
+				break;
+			next = next->rb_left;
+		} else
+			next = next->rb_right;
+	}
+
+	next = first;
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		/*
+		 * Stop if current map starts after map->end.
+		 * Maps are ordered by start: next will not overlap for sure.
+		 */
+		if (pos->start >= map->end)
+			break;
+
+		if (verbose >= 2) {
+
+			if (use_browser) {
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
+					   map->dso->name);
+			} else {
+				fputs("overlapping maps:\n", fp);
+				map__fprintf(map, fp);
+				map__fprintf(pos, fp);
+			}
+		}
+
+		rb_erase_init(&pos->rb_node, root);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL) {
+				err = -ENOMEM;
+				goto put_map;
+			}
+
+			before->end = map->start;
+			__maps__insert(maps, before);
+			if (verbose >= 2 && !use_browser)
+				map__fprintf(before, fp);
+			map__put(before);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL) {
+				err = -ENOMEM;
+				goto put_map;
+			}
+
+			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
+			__maps__insert(maps, after);
+			if (verbose >= 2 && !use_browser)
+				map__fprintf(after, fp);
+			map__put(after);
+		}
+put_map:
+		map__put(pos);
+
+		if (err)
+			goto out;
+	}
+
+	err = 0;
+out:
+	up_write(&maps->lock);
+	return err;
+}
+
+/*
+ * XXX This should not really _copy_ te maps, but refcount them.
+ */
+int maps__clone(struct thread *thread, struct maps *parent)
+{
+	struct maps *maps = thread->maps;
+	int err;
+	struct map *map;
+
+	down_read(&parent->lock);
+
+	maps__for_each_entry(parent, map) {
+		struct map *new = map__clone(map);
+
+		if (new == NULL) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+
+		err = unwind__prepare_access(maps, new, NULL);
+		if (err)
+			goto out_unlock;
+
+		maps__insert(maps, new);
+		map__put(new);
+	}
+
+	err = 0;
+out_unlock:
+	up_read(&parent->lock);
+	return err;
+}
+
+static void __maps__insert(struct maps *maps, struct map *map)
+{
+	struct rb_node **p = &maps->entries.rb_node;
+	struct rb_node *parent = NULL;
+	const u64 ip = map->start;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color(&map->rb_node, &maps->entries);
+	map__get(map);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+	struct rb_node *p;
+	struct map *m;
+
+	down_read(&maps->lock);
+
+	p = maps->entries.rb_node;
+	while (p != NULL) {
+		m = rb_entry(p, struct map, rb_node);
+		if (ip < m->start)
+			p = p->rb_left;
+		else if (ip >= m->end)
+			p = p->rb_right;
+		else
+			goto out;
+	}
+
+	m = NULL;
+out:
+	up_read(&maps->lock);
+	return m;
+}
+
+struct map *maps__first(struct maps *maps)
+{
+	struct rb_node *first = rb_first(&maps->entries);
+
+	if (first)
+		return rb_entry(first, struct map, rb_node);
+	return NULL;
+}
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 3dd000ddf925..7e729ff42749 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -60,8 +60,6 @@ static inline struct maps *maps__get(struct maps *maps)
 }
 
 void maps__put(struct maps *maps);
-void maps__init(struct maps *maps, struct machine *machine);
-void maps__exit(struct maps *maps);
 int maps__clone(struct thread *thread, struct maps *parent);
 size_t maps__fprintf(struct maps *maps, FILE *fp);
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 0e8ff8d1e206..50502b4a7ca4 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -230,6 +230,10 @@ void mmap__munmap(struct mmap *map)
 {
 	bitmap_free(map->affinity_mask.bits);
 
+#ifndef PYTHON_PERF
+	zstd_fini(&map->zstd_data);
+#endif
+
 	perf_mmap__aio_munmap(map);
 	if (map->data != NULL) {
 		munmap(map->data, mmap__mmap_len(map));
@@ -292,6 +296,12 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 	map->core.flush = mp->flush;
 
 	map->comp_level = mp->comp_level;
+#ifndef PYTHON_PERF
+	if (zstd_init(&map->zstd_data, map->comp_level)) {
+		pr_debug2("failed to init mmap compressor, error %d\n", errno);
+		return -1;
+	}
+#endif
 
 	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 83f6bd4d4082..cd8b0777473b 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -15,6 +15,7 @@
 #endif
 #include "auxtrace.h"
 #include "event.h"
+#include "util/compress.h"
 
 struct aiocb;
 
@@ -45,6 +46,8 @@ struct mmap {
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
 	int		comp_level;
+	struct perf_data_file *file;
+	struct zstd_data      zstd_data;
 };
 
 struct mmap_params {
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 48aa3217300b..dd536220cdb9 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -76,7 +76,7 @@ static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path)
 		if (strstr(statln, "Tgid:") != NULL) {
 			nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
 						     NULL, 10);
-			nsi->nstgid = nsi->tgid;
+			nsi->nstgid = nsinfo__tgid(nsi);
 		}
 
 		if (strstr(statln, "NStgid:") != NULL) {
@@ -108,7 +108,7 @@ int nsinfo__init(struct nsinfo *nsi)
 	if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
 		return rv;
 
-	if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1)
+	if (asprintf(&newns, "/proc/%d/ns/mnt", nsinfo__pid(nsi)) == -1)
 		return rv;
 
 	if (stat(oldns, &old_stat) < 0)
@@ -129,7 +129,7 @@ int nsinfo__init(struct nsinfo *nsi)
 	/* If we're dealing with a process that is in a different PID namespace,
 	 * attempt to work out the innermost tgid for the process.
 	 */
-	if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
+	if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsinfo__pid(nsi)) >= PATH_MAX)
 		goto out;
 
 	rv = nsinfo__get_nspid(nsi, spath);
@@ -166,7 +166,7 @@ struct nsinfo *nsinfo__new(pid_t pid)
 	return nsi;
 }
 
-struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
+struct nsinfo *nsinfo__copy(const struct nsinfo *nsi)
 {
 	struct nsinfo *nnsi;
 
@@ -175,11 +175,11 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
 
 	nnsi = calloc(1, sizeof(*nnsi));
 	if (nnsi != NULL) {
-		nnsi->pid = nsi->pid;
-		nnsi->tgid = nsi->tgid;
-		nnsi->nstgid = nsi->nstgid;
-		nnsi->need_setns = nsi->need_setns;
-		nnsi->in_pidns = nsi->in_pidns;
+		nnsi->pid = nsinfo__pid(nsi);
+		nnsi->tgid = nsinfo__tgid(nsi);
+		nnsi->nstgid = nsinfo__nstgid(nsi);
+		nnsi->need_setns = nsinfo__need_setns(nsi);
+		nnsi->in_pidns = nsinfo__in_pidns(nsi);
 		if (nsi->mntns_path) {
 			nnsi->mntns_path = strdup(nsi->mntns_path);
 			if (!nnsi->mntns_path) {
@@ -193,7 +193,7 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
 	return nnsi;
 }
 
-void nsinfo__delete(struct nsinfo *nsi)
+static void nsinfo__delete(struct nsinfo *nsi)
 {
 	zfree(&nsi->mntns_path);
 	free(nsi);
@@ -212,6 +212,36 @@ void nsinfo__put(struct nsinfo *nsi)
 		nsinfo__delete(nsi);
 }
 
+bool nsinfo__need_setns(const struct nsinfo *nsi)
+{
+        return nsi->need_setns;
+}
+
+void nsinfo__clear_need_setns(struct nsinfo *nsi)
+{
+        nsi->need_setns = false;
+}
+
+pid_t nsinfo__tgid(const struct nsinfo  *nsi)
+{
+        return nsi->tgid;
+}
+
+pid_t nsinfo__nstgid(const struct nsinfo  *nsi)
+{
+        return nsi->nstgid;
+}
+
+pid_t nsinfo__pid(const struct nsinfo  *nsi)
+{
+        return nsi->pid;
+}
+
+pid_t nsinfo__in_pidns(const struct nsinfo  *nsi)
+{
+        return nsi->in_pidns;
+}
+
 void nsinfo__mountns_enter(struct nsinfo *nsi,
 				  struct nscookie *nc)
 {
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 9ceea9643507..567829262c42 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -47,12 +47,18 @@ struct nscookie {
 
 int nsinfo__init(struct nsinfo *nsi);
 struct nsinfo *nsinfo__new(pid_t pid);
-struct nsinfo *nsinfo__copy(struct nsinfo *nsi);
-void nsinfo__delete(struct nsinfo *nsi);
+struct nsinfo *nsinfo__copy(const struct nsinfo *nsi);
 
 struct nsinfo *nsinfo__get(struct nsinfo *nsi);
 void nsinfo__put(struct nsinfo *nsi);
 
+bool nsinfo__need_setns(const struct nsinfo *nsi);
+void nsinfo__clear_need_setns(struct nsinfo *nsi);
+pid_t nsinfo__tgid(const struct nsinfo  *nsi);
+pid_t nsinfo__nstgid(const struct nsinfo  *nsi);
+pid_t nsinfo__pid(const struct nsinfo  *nsi);
+pid_t nsinfo__in_pidns(const struct nsinfo  *nsi);
+
 void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc);
 void nsinfo__mountns_exit(struct nscookie *nc);
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 48c8f609441b..b887dfeea673 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -192,7 +192,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 }
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-			  u64 timestamp, u64 file_offset)
+			  u64 timestamp, u64 file_offset, const char *file_path)
 {
 	struct ordered_event *oevent;
 
@@ -217,6 +217,7 @@ int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
 		return -ENOMEM;
 
 	oevent->file_offset = file_offset;
+	oevent->file_path = file_path;
 	return 0;
 }
 
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 75345946c4b9..0b05c3c0aeaa 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -9,6 +9,7 @@ struct perf_sample;
 struct ordered_event {
 	u64			timestamp;
 	u64			file_offset;
+	const char		*file_path;
 	union perf_event	*event;
 	struct list_head	list;
 };
@@ -53,7 +54,7 @@ struct ordered_events {
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-			  u64 timestamp, u64 file_offset);
+			  u64 timestamp, u64 file_offset, const char *file_path);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
 int ordered_events__flush_time(struct ordered_events *oe, u64 timestamp);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 8dfbba15aeb8..9a1c7e63e663 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1998,7 +1998,8 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
 {
 	struct perf_cpu_map *pmu_cpus = pmu->cpus;
 	struct perf_cpu_map *matched_cpus, *unmatched_cpus;
-	int matched_nr = 0, unmatched_nr = 0;
+	struct perf_cpu cpu;
+	int i, matched_nr = 0, unmatched_nr = 0;
 
 	matched_cpus = perf_cpu_map__default_new();
 	if (!matched_cpus)
@@ -2010,14 +2011,11 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
 		return -1;
 	}
 
-	for (int i = 0; i < cpus->nr; i++) {
-		int cpu;
-
-		cpu = perf_cpu_map__idx(pmu_cpus, cpus->map[i]);
-		if (cpu == -1)
-			unmatched_cpus->map[unmatched_nr++] = cpus->map[i];
+	perf_cpu_map__for_each_cpu(cpu, i, cpus) {
+		if (!perf_cpu_map__has(pmu_cpus, cpu))
+			unmatched_cpus->map[unmatched_nr++] = cpu;
 		else
-			matched_cpus->map[matched_nr++] = cpus->map[i];
+			matched_cpus->map[matched_nr++] = cpu;
 	}
 
 	unmatched_cpus->nr = unmatched_nr;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a834918a0a0d..062b5cbe67af 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -332,7 +332,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 		char module_name[128];
 
 		snprintf(module_name, sizeof(module_name), "[%s]", module);
-		map = maps__find_by_name(&host_machine->kmaps, module_name);
+		map = maps__find_by_name(machine__kernel_maps(host_machine), module_name);
 		if (map) {
 			dso = map->dso;
 			goto found;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 52d8995cfd73..5be5fa2391de 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -58,10 +58,21 @@ int parse_callchain_record(const char *arg __maybe_unused,
 }
 
 /*
- * Add this one here not to drag util/env.c
+ * Add these not to drag util/env.c
  */
 struct perf_env perf_env;
 
+const char *perf_env__cpuid(struct perf_env *env __maybe_unused)
+{
+	return NULL;
+}
+
+// This one is a bit easier, wouldn't drag too much, but leave it as a stub we need it here
+const char *perf_env__arch(struct perf_env *env __maybe_unused)
+{
+	return NULL;
+}
+
 /*
  * Add this one here not to drag util/stat-shadow.c
  */
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index ef6c2715fdd9..be9a957501f4 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -78,6 +78,8 @@ struct record_opts {
 	int	      ctl_fd_ack;
 	bool	      ctl_fd_close;
 	int	      synth;
+	int	      threads_spec;
+	const char    *threads_user_spec;
 };
 
 extern const char * const *record_usage;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e752e1f4a5f0..413f2d19c13f 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1216,7 +1216,7 @@ static void python_export_sample_table(struct db_export *dbe,
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(24);
+	t = tuple_new(25);
 
 	tuple_set_d64(t, 0, es->db_id);
 	tuple_set_d64(t, 1, es->evsel->db_id);
@@ -1242,6 +1242,7 @@ static void python_export_sample_table(struct db_export *dbe,
 	tuple_set_d64(t, 21, es->call_path_id);
 	tuple_set_d64(t, 22, es->sample->insn_cnt);
 	tuple_set_d64(t, 23, es->sample->cyc_cnt);
+	tuple_set_s32(t, 24, es->sample->flags);
 
 	call_object(tables->sample_handler, t, "sample_table");
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 498b05708db5..3b8dfe603e50 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -39,7 +39,8 @@
 
 #ifdef HAVE_ZSTD_SUPPORT
 static int perf_session__process_compressed_event(struct perf_session *session,
-						  union perf_event *event, u64 file_offset)
+						  union perf_event *event, u64 file_offset,
+						  const char *file_path)
 {
 	void *src;
 	size_t decomp_size, src_size;
@@ -61,6 +62,7 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 	}
 
 	decomp->file_pos = file_offset;
+	decomp->file_path = file_path;
 	decomp->mmap_len = mmap_len;
 	decomp->head = 0;
 
@@ -100,7 +102,8 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
-				       u64 file_offset);
+				       u64 file_offset,
+				       const char *file_path);
 
 static int perf_session__open(struct perf_session *session, int repipe_fd)
 {
@@ -182,7 +185,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 						    ordered_events);
 
 	return perf_session__deliver_event(session, event->event,
-					   session->tool, event->file_offset);
+					   session->tool, event->file_offset,
+					   event->file_path);
 }
 
 struct perf_session *__perf_session__new(struct perf_data *data,
@@ -471,7 +475,8 @@ static int process_event_time_conv_stub(struct perf_session *perf_session __mayb
 
 static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused,
 						       union perf_event *event __maybe_unused,
-						       u64 file_offset __maybe_unused)
+						       u64 file_offset __maybe_unused,
+						       const char *file_path __maybe_unused)
 {
        dump_printf(": unhandled!\n");
        return 0;
@@ -1072,9 +1077,9 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 }
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      u64 timestamp, u64 file_offset)
+			      u64 timestamp, u64 file_offset, const char *file_path)
 {
-	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset);
+	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset, file_path);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -1154,14 +1159,15 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
-			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s\n",
 				i, e->from, e->to,
 				(unsigned short)e->flags.cycles,
 				e->flags.mispred ? "M" : " ",
 				e->flags.predicted ? "P" : " ",
 				e->flags.abort ? "A" : " ",
 				e->flags.in_tx ? "T" : " ",
-				(unsigned)e->flags.reserved);
+				(unsigned)e->flags.reserved,
+				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
 			printf("..... %2"PRIu64": %016" PRIx64 "\n",
 				i, i > 0 ? e->from : e->to);
@@ -1277,13 +1283,14 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
-		       u64 file_offset, struct perf_sample *sample)
+		       u64 file_offset, struct perf_sample *sample,
+		       const char *file_path)
 {
 	if (!dump_trace)
 		return;
 
-	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
-	       file_offset, event->header.size, event->header.type);
+	printf("\n%#" PRIx64 "@%s [%#x]: event: %d\n",
+	       file_offset, file_path, event->header.size, event->header.type);
 
 	trace_event(event);
 	if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw)
@@ -1486,12 +1493,13 @@ static int machines__deliver_event(struct machines *machines,
 				   struct evlist *evlist,
 				   union perf_event *event,
 				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset)
+				   struct perf_tool *tool, u64 file_offset,
+				   const char *file_path)
 {
 	struct evsel *evsel;
 	struct machine *machine;
 
-	dump_event(evlist, event, file_offset, sample);
+	dump_event(evlist, event, file_offset, sample, file_path);
 
 	evsel = evlist__id2evsel(evlist, sample->id);
 
@@ -1573,7 +1581,8 @@ static int machines__deliver_event(struct machines *machines,
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
-				       u64 file_offset)
+				       u64 file_offset,
+				       const char *file_path)
 {
 	struct perf_sample sample;
 	int ret = evlist__parse_sample(session->evlist, event, &sample);
@@ -1590,7 +1599,7 @@ static int perf_session__deliver_event(struct perf_session *session,
 		return 0;
 
 	ret = machines__deliver_event(&session->machines, session->evlist,
-				      event, &sample, tool, file_offset);
+				      event, &sample, tool, file_offset, file_path);
 
 	if (dump_trace && sample.aux_sample.size)
 		auxtrace__dump_auxtrace_sample(session, &sample);
@@ -1600,7 +1609,8 @@ static int perf_session__deliver_event(struct perf_session *session,
 
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
-					    u64 file_offset)
+					    u64 file_offset,
+					    const char *file_path)
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
@@ -1610,7 +1620,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 
 	if (event->header.type != PERF_RECORD_COMPRESSED ||
 	    tool->compressed == perf_session__process_compressed_event_stub)
-		dump_event(session->evlist, event, file_offset, &sample);
+		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -1669,9 +1679,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_FEATURE:
 		return tool->feature(session, event);
 	case PERF_RECORD_COMPRESSED:
-		err = tool->compressed(session, event, file_offset);
+		err = tool->compressed(session, event, file_offset, file_path);
 		if (err)
-			dump_event(session->evlist, event, file_offset, &sample);
+			dump_event(session->evlist, event, file_offset, &sample, file_path);
 		return err;
 	default:
 		return -EINVAL;
@@ -1688,9 +1698,9 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, 0);
+		return perf_session__process_user_event(session, event, 0, NULL);
 
-	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0);
+	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0, NULL);
 }
 
 static void event_swap(union perf_event *event, bool sample_id_all)
@@ -1787,7 +1797,8 @@ int perf_session__peek_events(struct perf_session *session, u64 offset,
 }
 
 static s64 perf_session__process_event(struct perf_session *session,
-				       union perf_event *event, u64 file_offset)
+				       union perf_event *event, u64 file_offset,
+				       const char *file_path)
 {
 	struct evlist *evlist = session->evlist;
 	struct perf_tool *tool = session->tool;
@@ -1802,7 +1813,7 @@ static s64 perf_session__process_event(struct perf_session *session,
 	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, file_offset);
+		return perf_session__process_user_event(session, event, file_offset, file_path);
 
 	if (tool->ordered_events) {
 		u64 timestamp = -1ULL;
@@ -1811,12 +1822,12 @@ static s64 perf_session__process_event(struct perf_session *session,
 		if (ret && ret != -1)
 			return ret;
 
-		ret = perf_session__queue_event(session, event, timestamp, file_offset);
+		ret = perf_session__queue_event(session, event, timestamp, file_offset, file_path);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session__deliver_event(session, event, tool, file_offset);
+	return perf_session__deliver_event(session, event, tool, file_offset, file_path);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -2043,7 +2054,7 @@ more:
 		}
 	}
 
-	if ((skip = perf_session__process_event(session, event, head)) < 0) {
+	if ((skip = perf_session__process_event(session, event, head, "pipe")) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       head, event->header.size, event->header.type);
 		err = -EINVAL;
@@ -2140,7 +2151,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session)
 		size = event->header.size;
 
 		if (size < sizeof(struct perf_event_header) ||
-		    (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) {
+		    (skip = perf_session__process_event(session, event, decomp->file_pos,
+							decomp->file_path)) < 0) {
 			pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 				decomp->file_pos + decomp->head, event->header.size, event->header.type);
 			return -EINVAL;
@@ -2171,10 +2183,12 @@ struct reader;
 
 typedef s64 (*reader_cb_t)(struct perf_session *session,
 			   union perf_event *event,
-			   u64 file_offset);
+			   u64 file_offset,
+			   const char *file_path);
 
 struct reader {
 	int		 fd;
+	const char	 *path;
 	u64		 data_size;
 	u64		 data_offset;
 	reader_cb_t	 process;
@@ -2186,6 +2200,8 @@ struct reader {
 	u64		 file_pos;
 	u64		 file_offset;
 	u64		 head;
+	u64		 size;
+	bool		 done;
 	struct zstd_data   zstd_data;
 	struct decomp_data decomp_data;
 };
@@ -2292,7 +2308,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	skip = -EINVAL;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = rd->process(session, event, rd->file_pos)) < 0) {
+	    (skip = rd->process(session, event, rd->file_pos, rd->path)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       rd->file_offset + rd->head, event->header.size,
 		       event->header.type, strerror(-skip));
@@ -2303,6 +2319,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	if (skip)
 		size += skip;
 
+	rd->size += size;
 	rd->head += size;
 	rd->file_pos += size;
 
@@ -2359,15 +2376,17 @@ out:
 
 static s64 process_simple(struct perf_session *session,
 			  union perf_event *event,
-			  u64 file_offset)
+			  u64 file_offset,
+			  const char *file_path)
 {
-	return perf_session__process_event(session, event, file_offset);
+	return perf_session__process_event(session, event, file_offset, file_path);
 }
 
 static int __perf_session__process_events(struct perf_session *session)
 {
 	struct reader rd = {
 		.fd		= perf_data__fd(session->data),
+		.path		= session->data->file.path,
 		.data_size	= session->header.data_size,
 		.data_offset	= session->header.data_offset,
 		.process	= process_simple,
@@ -2411,6 +2430,135 @@ out_err:
 	return err;
 }
 
+/*
+ * Processing 2 MB of data from each reader in sequence,
+ * because that's the way the ordered events sorting works
+ * most efficiently.
+ */
+#define READER_MAX_SIZE (2 * 1024 * 1024)
+
+/*
+ * This function reads, merge and process directory data.
+ * It assumens the version 1 of directory data, where each
+ * data file holds per-cpu data, already sorted by kernel.
+ */
+static int __perf_session__process_dir_events(struct perf_session *session)
+{
+	struct perf_data *data = session->data;
+	struct perf_tool *tool = session->tool;
+	int i, ret, readers, nr_readers;
+	struct ui_progress prog;
+	u64 total_size = perf_data__size(session->data);
+	struct reader *rd;
+
+	perf_tool__fill_defaults(tool);
+
+	ui_progress__init_size(&prog, total_size, "Sorting events...");
+
+	nr_readers = 1;
+	for (i = 0; i < data->dir.nr; i++) {
+		if (data->dir.files[i].size)
+			nr_readers++;
+	}
+
+	rd = zalloc(nr_readers * sizeof(struct reader));
+	if (!rd)
+		return -ENOMEM;
+
+	rd[0] = (struct reader) {
+		.fd		 = perf_data__fd(session->data),
+		.path		 = session->data->file.path,
+		.data_size	 = session->header.data_size,
+		.data_offset	 = session->header.data_offset,
+		.process	 = process_simple,
+		.in_place_update = session->data->in_place_update,
+	};
+	ret = reader__init(&rd[0], NULL);
+	if (ret)
+		goto out_err;
+	ret = reader__mmap(&rd[0], session);
+	if (ret)
+		goto out_err;
+	readers = 1;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		if (!data->dir.files[i].size)
+			continue;
+		rd[readers] = (struct reader) {
+			.fd		 = data->dir.files[i].fd,
+			.path		 = data->dir.files[i].path,
+			.data_size	 = data->dir.files[i].size,
+			.data_offset	 = 0,
+			.process	 = process_simple,
+			.in_place_update = session->data->in_place_update,
+		};
+		ret = reader__init(&rd[readers], NULL);
+		if (ret)
+			goto out_err;
+		ret = reader__mmap(&rd[readers], session);
+		if (ret)
+			goto out_err;
+		readers++;
+	}
+
+	i = 0;
+	while (readers) {
+		if (session_done())
+			break;
+
+		if (rd[i].done) {
+			i = (i + 1) % nr_readers;
+			continue;
+		}
+		if (reader__eof(&rd[i])) {
+			rd[i].done = true;
+			readers--;
+			continue;
+		}
+
+		session->active_decomp = &rd[i].decomp_data;
+		ret = reader__read_event(&rd[i], session, &prog);
+		if (ret < 0) {
+			goto out_err;
+		} else if (ret == READER_NODATA) {
+			ret = reader__mmap(&rd[i], session);
+			if (ret)
+				goto out_err;
+		}
+
+		if (rd[i].size >= READER_MAX_SIZE) {
+			rd[i].size = 0;
+			i = (i + 1) % nr_readers;
+		}
+	}
+
+	ret = ordered_events__flush(&session->ordered_events, OE_FLUSH__FINAL);
+	if (ret)
+		goto out_err;
+
+	ret = perf_session__flush_thread_stacks(session);
+out_err:
+	ui_progress__finish();
+
+	if (!tool->no_warn)
+		perf_session__warn_about_errors(session);
+
+	/*
+	 * We may switching perf.data output, make ordered_events
+	 * reusable.
+	 */
+	ordered_events__reinit(&session->ordered_events);
+
+	session->one_mmap = false;
+
+	session->active_decomp = &session->decomp_data;
+	for (i = 0; i < nr_readers; i++)
+		reader__release_decomp(&rd[i]);
+	zfree(&rd);
+
+	return ret;
+}
+
 int perf_session__process_events(struct perf_session *session)
 {
 	if (perf_session__register_idle_thread(session) < 0)
@@ -2419,6 +2567,9 @@ int perf_session__process_events(struct perf_session *session)
 	if (perf_data__is_pipe(session->data))
 		return __perf_session__process_pipe_events(session);
 
+	if (perf_data__is_dir(session->data))
+		return __perf_session__process_dir_events(session);
+
 	return __perf_session__process_events(session);
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 46c854292ad6..34500a3da735 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -52,6 +52,7 @@ struct perf_session {
 struct decomp {
 	struct decomp *next;
 	u64 file_pos;
+	const char *file_path;
 	size_t mmap_len;
 	u64 head;
 	size_t size;
@@ -87,7 +88,7 @@ int perf_session__peek_events(struct perf_session *session, u64 offset,
 int perf_session__process_events(struct perf_session *session);
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      u64 timestamp, u64 file_offset);
+			      u64 timestamp, u64 file_offset, const char *file_path);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2da081ef532b..6d5588e80935 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -990,6 +990,128 @@ struct sort_entry sort_sym_to = {
 	.se_width_idx	= HISTC_SYMBOL_TO,
 };
 
+static int _hist_entry__addr_snprintf(struct map_symbol *ms,
+				     u64 ip, char level, char *bf, size_t size,
+				     unsigned int width)
+{
+	struct symbol *sym = ms->sym;
+	struct map *map = ms->map;
+	size_t ret = 0, offs;
+
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
+	if (sym && map) {
+		if (sym->type == STT_OBJECT) {
+			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
+			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
+					ip - map->unmap_ip(map, sym->start));
+		} else {
+			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
+					       width - ret,
+					       sym->name);
+			offs = ip - sym->start;
+			if (offs)
+				ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", offs);
+		}
+	} else {
+		size_t len = BITS_PER_LONG / 4;
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
+				       len, ip);
+	}
+
+	return ret;
+}
+
+static int hist_entry__addr_from_snprintf(struct hist_entry *he, char *bf,
+					 size_t size, unsigned int width)
+{
+	if (he->branch_info) {
+		struct addr_map_symbol *from = &he->branch_info->from;
+
+		return _hist_entry__addr_snprintf(&from->ms, from->al_addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
+}
+
+static int hist_entry__addr_to_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	if (he->branch_info) {
+		struct addr_map_symbol *to = &he->branch_info->to;
+
+		return _hist_entry__addr_snprintf(&to->ms, to->al_addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
+}
+
+static int64_t
+sort__addr_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *from_l;
+	struct addr_map_symbol *from_r;
+	int64_t ret;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	from_l = &left->branch_info->from;
+	from_r = &right->branch_info->from;
+
+	/*
+	 * comparing symbol address alone is not enough since it's a
+	 * relative address within a dso.
+	 */
+	ret = _sort__dso_cmp(from_l->ms.map, from_r->ms.map);
+	if (ret != 0)
+		return ret;
+
+	return _sort__addr_cmp(from_l->addr, from_r->addr);
+}
+
+static int64_t
+sort__addr_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *to_l;
+	struct addr_map_symbol *to_r;
+	int64_t ret;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	to_l = &left->branch_info->to;
+	to_r = &right->branch_info->to;
+
+	/*
+	 * comparing symbol address alone is not enough since it's a
+	 * relative address within a dso.
+	 */
+	ret = _sort__dso_cmp(to_l->ms.map, to_r->ms.map);
+	if (ret != 0)
+		return ret;
+
+	return _sort__addr_cmp(to_l->addr, to_r->addr);
+}
+
+struct sort_entry sort_addr_from = {
+	.se_header	= "Source Address",
+	.se_cmp		= sort__addr_from_cmp,
+	.se_snprintf	= hist_entry__addr_from_snprintf,
+	.se_filter	= hist_entry__sym_from_filter, /* shared with sym_from */
+	.se_width_idx	= HISTC_ADDR_FROM,
+};
+
+struct sort_entry sort_addr_to = {
+	.se_header	= "Target Address",
+	.se_cmp		= sort__addr_to_cmp,
+	.se_snprintf	= hist_entry__addr_to_snprintf,
+	.se_filter	= hist_entry__sym_to_filter, /* shared with sym_to */
+	.se_width_idx	= HISTC_ADDR_TO,
+};
+
+
 static int64_t
 sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1893,6 +2015,8 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 	DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
 	DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
 	DIM(SORT_SYM_IPC, "ipc_lbr", sort_sym_ipc),
+	DIM(SORT_ADDR_FROM, "addr_from", sort_addr_from),
+	DIM(SORT_ADDR_TO, "addr_to", sort_addr_to),
 };
 
 #undef DIM
@@ -3126,6 +3250,10 @@ static bool get_elide(int idx, FILE *output)
 		return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
 	case HISTC_DSO_TO:
 		return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+	case HISTC_ADDR_FROM:
+		return __get_elide(symbol_conf.sym_from_list, "addr_from", output);
+	case HISTC_ADDR_TO:
+		return __get_elide(symbol_conf.sym_to_list, "addr_to", output);
 	default:
 		break;
 	}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f994261888e1..2ddc00d1c464 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -251,6 +251,8 @@ enum sort_type {
 	SORT_SRCLINE_FROM,
 	SORT_SRCLINE_TO,
 	SORT_SYM_IPC,
+	SORT_ADDR_FROM,
+	SORT_ADDR_TO,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dfde9eada224..dea0fc495185 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1735,8 +1735,8 @@ static int dso__find_perf_map(char *filebuf, size_t bufsz,
 
 	nsi = *nsip;
 
-	if (nsi->need_setns) {
-		snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsi->nstgid);
+	if (nsinfo__need_setns(nsi)) {
+		snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsinfo__nstgid(nsi));
 		nsinfo__mountns_enter(nsi, &nsc);
 		rc = access(filebuf, R_OK);
 		nsinfo__mountns_exit(&nsc);
@@ -1748,8 +1748,8 @@ static int dso__find_perf_map(char *filebuf, size_t bufsz,
 	if (nnsi) {
 		nsinfo__put(nsi);
 
-		nnsi->need_setns = false;
-		snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nnsi->tgid);
+		nsinfo__clear_need_setns(nnsi);
+		snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsinfo__tgid(nnsi));
 		*nsip = nnsi;
 		rc = 0;
 	}
@@ -1864,6 +1864,16 @@ int dso__load(struct dso *dso, struct map *map)
 			nsinfo__mountns_exit(&nsc);
 
 		is_reg = is_regular_file(name);
+		if (!is_reg && errno == ENOENT && dso->nsinfo) {
+			char *new_name = filename_with_chroot(dso->nsinfo->pid,
+							      name);
+			if (new_name) {
+				is_reg = is_regular_file(new_name);
+				strlcpy(name, new_name, PATH_MAX);
+				free(new_name);
+			}
+		}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 		if (is_reg)
 			bfdrc = dso__load_bfd_symbols(dso, name);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index ef873f2cc38f..f2352dba1875 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -28,7 +28,8 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 
 typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
 typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
-typedef int (*event_op4)(struct perf_session *session, union perf_event *event, u64 data);
+typedef int (*event_op4)(struct perf_session *session, union perf_event *event, u64 data,
+			 const char *str);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index ff8391208ecd..1c2c0a838430 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -33,7 +33,10 @@ struct perf_top {
 	int		   print_entries, count_filter, delay_secs;
 	int		   max_stack;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
-	bool		   use_tui, use_stdio;
+#ifdef HAVE_SLANG_SUPPORT
+	bool		   use_tui;
+#endif
+	bool		   use_stdio;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
 	bool		   stitch_lbr;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 9634f0ae57be..c9c83a40647c 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -206,7 +206,7 @@ unsigned long long eval_flag(const char *flag)
 	if (isdigit(flag[0]))
 		return strtoull(flag, NULL, 0);
 
-	for (i = 0; i < (int)(sizeof(flags)/sizeof(flags[0])); i++)
+	for (i = 0; i < (int)(ARRAY_SIZE(flags)); i++)
 		if (strcmp(flags[i].name, flag) == 0)
 			return flags[i].value;
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index fb4f6616b5fa..f8571a66d063 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -431,3 +431,34 @@ void perf_debuginfod_setup(struct perf_debuginfod *di)
 
 	pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
 }
+
+/*
+ * Return a new filename prepended with task's root directory if it's in
+ * a chroot.  Callers should free the returned string.
+ */
+char *filename_with_chroot(int pid, const char *filename)
+{
+	char buf[PATH_MAX];
+	char proc_root[32];
+	char *new_name = NULL;
+	int ret;
+
+	scnprintf(proc_root, sizeof(proc_root), "/proc/%d/root", pid);
+	ret = readlink(proc_root, buf, sizeof(buf) - 1);
+	if (ret <= 0)
+		return NULL;
+
+	/* readlink(2) does not append a null byte to buf */
+	buf[ret] = '\0';
+
+	if (!strcmp(buf, "/"))
+		return NULL;
+
+	if (strstr(buf, "(deleted)"))
+		return NULL;
+
+	if (asprintf(&new_name, "%s/%s", buf, filename) < 0)
+		return NULL;
+
+	return new_name;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7b625cbd2dd8..0f78f1e7782d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -77,4 +77,6 @@ struct perf_debuginfod {
 	bool		 set;
 };
 void perf_debuginfod_setup(struct perf_debuginfod *di);
+
+char *filename_with_chroot(int pid, const char *filename);
 #endif /* GIT_COMPAT_UTIL_H */