Merge tag 'perf-core-for-mingo-5.1-20190206' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

Hardware tracing:

  Adrian Hunter:

  - Handle calls optimized into jumps to a different symbol
    in the thread stack routines used to process hardware traces (Adrian Hunter)

Intel PT:

  Adrian Hunter:

  - Fix overlap calculation for padding.

  - Fix CYC timestamp calculation after OVF.

  - Packet splitting can only happen in 32-bit.

  - Add timestamp to auxtrace errors.

ARM CoreSight:

  Leo Yan:

  - Add last instruction information in packet

  - Set sample flags for instruction range, exception and
    return packets and for a trace discontinuity.

  - Add exception number in exception packet

  - Change tuple from traceID-CPU# to traceID-metadata

  - Add traceID in packet

  Mathieu Poirier:

  - Add "sinks" group to PMU directory

  - Use event attributes to send sink information to kernel

  - Remove set_drv_config() API, no longer used.

perf annotate:

  Jiri Olsa:

  - Delay symbol annotation to the resort phase, speeding up 'perf report'
    startup.

perf record:

  Alexey Budankov:

  - Allow binding userspace buffers to NUMA nodes.

Symbols:

  Adrian Hunter:

  - Fix calculating of symbol sizes when splitting kallsyms into
    maps for kcore processing.

Vendor events:

  William Cohen:

  - Intel: Fix Load_Miss_Real_Latency on CLX

Misc:

  Arnaldo Carvalho de Melo:

  - Streamline headers, removing includes when all that is needed are
    just forward declarations, fixup the fallout for cases where headers
    should have been explicitely included but were instead obtained
    indirectly, by sheer luck.

  - Add fallback versions for CPU_{OR,EQUAL}(), so that code using it
    continue to build on older systems where those were not yet introduced
    or in systems using some other libc than the GNU one where those
    helpers aren't present.

Documentation:

  Changbin Du:

  - Add documentation for BPF event selection.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

118 files changed, 1398 insertions, 472 deletions

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index bfabeb1889cc0..1266194afb026 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1600,7 +1600,7 @@ static void aux_sdb_init(unsigned long sdb)
 
 /*
  * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
- * @cpu:	On which to allocate, -1 means current
+ * @event:	Event the buffer is setup for, event->cpu == -1 means current
  * @pages:	Array of pointers to buffer pages passed from perf core
  * @nr_pages:	Total pages
  * @snapshot:	Flag for snapshot mode
@@ -1612,8 +1612,8 @@ static void aux_sdb_init(unsigned long sdb)
  *
  * Return the private AUX buffer structure if success or NULL if fails.
  */
-static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
-			      bool snapshot)
+static void *aux_buffer_setup(struct perf_event *event, void **pages,
+			      int nr_pages, bool snapshot)
 {
 	struct sf_buffer *sfb;
 	struct aux_buffer *aux;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index a01ef1b0f8833..7cdd7b13bbda6 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -77,10 +77,12 @@ static size_t buf_size(struct page *page)
 }
 
 static void *
-bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite)
+bts_buffer_setup_aux(struct perf_event *event, void **pages,
+		     int nr_pages, bool overwrite)
 {
 	struct bts_buffer *buf;
 	struct page *page;
+	int cpu = event->cpu;
 	int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
 	unsigned long offset;
 	size_t size = nr_pages << PAGE_SHIFT;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 9494ca68fd9df..c0e86ff21f816 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1114,10 +1114,11 @@ static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages,
  * Return:	Our private PT buffer structure.
  */
 static void *
-pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot)
+pt_buffer_setup_aux(struct perf_event *event, void **pages,
+		    int nr_pages, bool snapshot)
 {
 	struct pt_buffer *buf;
-	int node, ret;
+	int node, ret, cpu = event->cpu;
 
 	if (!nr_pages)
 		return NULL;
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index abe8249b893bb..8c88bf0a1e5f0 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -14,6 +14,7 @@
 #include <linux/perf_event.h>
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
+#include <linux/stringhash.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
@@ -30,11 +31,14 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src);
 PMU_FORMAT_ATTR(cycacc,		"config:" __stringify(ETM_OPT_CYCACC));
 PMU_FORMAT_ATTR(timestamp,	"config:" __stringify(ETM_OPT_TS));
 PMU_FORMAT_ATTR(retstack,	"config:" __stringify(ETM_OPT_RETSTK));
+/* Sink ID - same for all ETMs */
+PMU_FORMAT_ATTR(sinkid,		"config2:0-31");
 
 static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_cycacc.attr,
 	&format_attr_timestamp.attr,
 	&format_attr_retstack.attr,
+	&format_attr_sinkid.attr,
 	NULL,
 };
 
@@ -43,8 +47,18 @@ static const struct attribute_group etm_pmu_format_group = {
 	.attrs  = etm_config_formats_attr,
 };
 
+static struct attribute *etm_config_sinks_attr[] = {
+	NULL,
+};
+
+static const struct attribute_group etm_pmu_sinks_group = {
+	.name   = "sinks",
+	.attrs  = etm_config_sinks_attr,
+};
+
 static const struct attribute_group *etm_pmu_attr_groups[] = {
 	&etm_pmu_format_group,
+	&etm_pmu_sinks_group,
 	NULL,
 };
 
@@ -177,31 +191,28 @@ static void etm_free_aux(void *data)
 	schedule_work(&event_data->work);
 }
 
-static void *etm_setup_aux(int event_cpu, void **pages,
+static void *etm_setup_aux(struct perf_event *event, void **pages,
 			   int nr_pages, bool overwrite)
 {
-	int cpu;
+	u32 id;
+	int cpu = event->cpu;
 	cpumask_t *mask;
 	struct coresight_device *sink;
 	struct etm_event_data *event_data = NULL;
 
-	event_data = alloc_event_data(event_cpu);
+	event_data = alloc_event_data(cpu);
 	if (!event_data)
 		return NULL;
 	INIT_WORK(&event_data->work, free_event_data);
 
-	/*
-	 * In theory nothing prevent tracers in a trace session from being
-	 * associated with different sinks, nor having a sink per tracer.  But
-	 * until we have HW with this kind of topology we need to assume tracers
-	 * in a trace session are using the same sink.  Therefore go through
-	 * the coresight bus and pick the first enabled sink.
-	 *
-	 * When operated from sysFS users are responsible to enable the sink
-	 * while from perf, the perf tools will do it based on the choice made
-	 * on the cmd line.  As such the "enable_sink" flag in sysFS is reset.
-	 */
-	sink = coresight_get_enabled_sink(true);
+	/* First get the selected sink from user space. */
+	if (event->attr.config2) {
+		id = (u32)event->attr.config2;
+		sink = coresight_get_sink_by_id(id);
+	} else {
+		sink = coresight_get_enabled_sink(true);
+	}
+
 	if (!sink || !sink_ops(sink)->alloc_buffer)
 		goto err;
 
@@ -479,6 +490,77 @@ int etm_perf_symlink(struct coresight_device *csdev, bool link)
 	return 0;
 }
 
+static ssize_t etm_perf_sink_name_show(struct device *dev,
+				       struct device_attribute *dattr,
+				       char *buf)
+{
+	struct dev_ext_attribute *ea;
+
+	ea = container_of(dattr, struct dev_ext_attribute, attr);
+	return scnprintf(buf, PAGE_SIZE, "0x%lx\n", (unsigned long)(ea->var));
+}
+
+int etm_perf_add_symlink_sink(struct coresight_device *csdev)
+{
+	int ret;
+	unsigned long hash;
+	const char *name;
+	struct device *pmu_dev = etm_pmu.dev;
+	struct device *pdev = csdev->dev.parent;
+	struct dev_ext_attribute *ea;
+
+	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
+	    csdev->type != CORESIGHT_DEV_TYPE_LINKSINK)
+		return -EINVAL;
+
+	if (csdev->ea != NULL)
+		return -EINVAL;
+
+	if (!etm_perf_up)
+		return -EPROBE_DEFER;
+
+	ea = devm_kzalloc(pdev, sizeof(*ea), GFP_KERNEL);
+	if (!ea)
+		return -ENOMEM;
+
+	name = dev_name(pdev);
+	/* See function coresight_get_sink_by_id() to know where this is used */
+	hash = hashlen_hash(hashlen_string(NULL, name));
+
+	ea->attr.attr.name = devm_kstrdup(pdev, name, GFP_KERNEL);
+	if (!ea->attr.attr.name)
+		return -ENOMEM;
+
+	ea->attr.attr.mode = 0444;
+	ea->attr.show = etm_perf_sink_name_show;
+	ea->var = (unsigned long *)hash;
+
+	ret = sysfs_add_file_to_group(&pmu_dev->kobj,
+				      &ea->attr.attr, "sinks");
+
+	if (!ret)
+		csdev->ea = ea;
+
+	return ret;
+}
+
+void etm_perf_del_symlink_sink(struct coresight_device *csdev)
+{
+	struct device *pmu_dev = etm_pmu.dev;
+	struct dev_ext_attribute *ea = csdev->ea;
+
+	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
+	    csdev->type != CORESIGHT_DEV_TYPE_LINKSINK)
+		return;
+
+	if (!ea)
+		return;
+
+	sysfs_remove_file_from_group(&pmu_dev->kobj,
+				     &ea->attr.attr, "sinks");
+	csdev->ea = NULL;
+}
+
 static int __init etm_perf_init(void)
 {
 	int ret;
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
index da7d9336a15c5..015213abe00a7 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.h
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -59,6 +59,8 @@ struct etm_event_data {
 
 #ifdef CONFIG_CORESIGHT
 int etm_perf_symlink(struct coresight_device *csdev, bool link);
+int etm_perf_add_symlink_sink(struct coresight_device *csdev);
+void etm_perf_del_symlink_sink(struct coresight_device *csdev);
 static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 {
 	struct etm_event_data *data = perf_get_aux(handle);
@@ -70,7 +72,9 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 #else
 static inline int etm_perf_symlink(struct coresight_device *csdev, bool link)
 { return -EINVAL; }
-
+int etm_perf_add_symlink_sink(struct coresight_device *csdev)
+{ return -EINVAL; }
+void etm_perf_del_symlink_sink(struct coresight_device *csdev) {}
 static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 {
 	return NULL;
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 579f34943bf1a..b936c6d7e13f3 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -147,6 +147,7 @@ void coresight_disable_path(struct list_head *path);
 int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data);
 struct coresight_device *coresight_get_sink(struct list_head *path);
 struct coresight_device *coresight_get_enabled_sink(bool reset);
+struct coresight_device *coresight_get_sink_by_id(u32 id);
 struct list_head *coresight_build_path(struct coresight_device *csdev,
 				       struct coresight_device *sink);
 void coresight_release_path(struct list_head *path);
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 2b0df1a0a8df4..29cef898afba0 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/stringhash.h>
 #include <linux/mutex.h>
 #include <linux/clk.h>
 #include <linux/coresight.h>
@@ -18,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
 
+#include "coresight-etm-perf.h"
 #include "coresight-priv.h"
 
 static DEFINE_MUTEX(coresight_mutex);
@@ -540,6 +542,47 @@ struct coresight_device *coresight_get_enabled_sink(bool deactivate)
 	return dev ? to_coresight_device(dev) : NULL;
 }
 
+static int coresight_sink_by_id(struct device *dev, void *data)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+	unsigned long hash;
+
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	     csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+
+		if (!csdev->ea)
+			return 0;
+		/*
+		 * See function etm_perf_add_symlink_sink() to know where
+		 * this comes from.
+		 */
+		hash = (unsigned long)csdev->ea->var;
+
+		if ((u32)hash == *(u32 *)data)
+			return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * coresight_get_sink_by_id - returns the sink that matches the id
+ * @id: Id of the sink to match
+ *
+ * The name of a sink is unique, whether it is found on the AMBA bus or
+ * otherwise.  As such the hash of that name can easily be used to identify
+ * a sink.
+ */
+struct coresight_device *coresight_get_sink_by_id(u32 id)
+{
+	struct device *dev = NULL;
+
+	dev = bus_find_device(&coresight_bustype, NULL, &id,
+			      coresight_sink_by_id);
+
+	return dev ? to_coresight_device(dev) : NULL;
+}
+
 /*
  * coresight_grab_device - Power up this device and any of the helper
  * devices connected to it for trace operation. Since the helper devices
@@ -1167,6 +1210,22 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 		goto err_out;
 	}
 
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		ret = etm_perf_add_symlink_sink(csdev);
+
+		if (ret) {
+			device_unregister(&csdev->dev);
+			/*
+			 * As with the above, all resources are free'd
+			 * explicitly via coresight_device_release() triggered
+			 * from put_device(), which is in turn called from
+			 * function device_unregister().
+			 */
+			goto err_out;
+		}
+	}
+
 	mutex_lock(&coresight_mutex);
 
 	coresight_fixup_device_conns(csdev);
@@ -1185,6 +1244,7 @@ EXPORT_SYMBOL_GPL(coresight_register);
 
 void coresight_unregister(struct coresight_device *csdev)
 {
+	etm_perf_del_symlink_sink(csdev);
 	/* Remove references of that device in the topology */
 	coresight_remove_conns(csdev);
 	device_unregister(&csdev->dev);
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 8e46a9dad2fa2..7cb766dafe851 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -824,10 +824,10 @@ static void arm_spe_pmu_read(struct perf_event *event)
 {
 }
 
-static void *arm_spe_pmu_setup_aux(int cpu, void **pages, int nr_pages,
-				   bool snapshot)
+static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages,
+				   int nr_pages, bool snapshot)
 {
-	int i;
+	int i, cpu = event->cpu;
 	struct page **pglist;
 	struct arm_spe_pmu_buf *buf;
 
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 46c67a7648778..7b87965f7a65c 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -154,8 +154,9 @@ struct coresight_connection {
  * @orphan:	true if the component has connections that haven't been linked.
  * @enable:	'true' if component is currently part of an active path.
  * @activated:	'true' only if a _sink_ has been activated.  A sink can be
-		activated but not yet enabled.  Enabling for a _sink_
-		happens when a source has been selected for that it.
+ *		activated but not yet enabled.  Enabling for a _sink_
+ *		appens when a source has been selected for that it.
+ * @ea:		Device attribute for sink representation under PMU directory.
  */
 struct coresight_device {
 	struct coresight_connection *conns;
@@ -168,7 +169,9 @@ struct coresight_device {
 	atomic_t *refcnt;
 	bool orphan;
 	bool enable;	/* true only if configured as part of a path */
+	/* sink specific fields */
 	bool activated;	/* true only if a sink is part of a path */
+	struct dev_ext_attribute *ea;
 };
 
 #define to_coresight_device(d) container_of(d, struct coresight_device, dev)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6cb5d483ab34d..d9c3610e0e255 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -410,7 +410,7 @@ struct pmu {
 	/*
 	 * Set up pmu-private data structures for an AUX area
 	 */
-	void *(*setup_aux)		(int cpu, void **pages,
+	void *(*setup_aux)		(struct perf_event *event, void **pages,
 					 int nr_pages, bool overwrite);
 					/* optional */
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 805f0423ee0b2..70ae2422cbaf2 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -657,7 +657,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 			goto out;
 	}
 
-	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
+	rb->aux_priv = event->pmu->setup_aux(event, rb->aux_pages, nr_pages,
 					     overwrite);
 	if (!rb->aux_priv)
 		goto out;
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 4ac7775fbc114..86f3dcc15f837 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -120,6 +120,10 @@ Given a $HOME/.perfconfig like this:
 		children = true
 		group = true
 
+	[llvm]
+		dump-obj = true
+		clang-opt = -g
+
 You can hide source code of annotate feature setting the config to false with
 
 	% perf config annotate.hide_src_code=true
@@ -553,6 +557,33 @@ trace.*::
 	trace.show_zeros::
 		Do not suppress syscall arguments that are equal to zero.
 
+llvm.*::
+	llvm.clang-path::
+		Path to clang. If omit, search it from $PATH.
+
+	llvm.clang-bpf-cmd-template::
+		Cmdline template. Below lines show its default value. Environment
+		variable is used to pass options.
+		"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \
+		-Wno-unused-value -Wno-pointer-sign -working-directory \
+		$WORKING_DIR  -c $CLANG_SOURCE -target bpf -O2 -o -"
+
+	llvm.clang-opt::
+		Options passed to clang.
+
+	llvm.kbuild-dir::
+		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
+		If set to "" deliberately, skip kernel header auto-detector.
+
+	llvm.kbuild-opts::
+		Options passed to 'make' when detecting kernel header options.
+
+	llvm.dump-obj::
+		Enable perf dump BPF object files compiled by LLVM.
+
+	llvm.opts::
+		Options passed to llc.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d232b13ea7137..02b4aa2621e72 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -88,6 +88,20 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
+        - a BPF source file (ending in .c) or a precompiled object file (ending
+          in .o) selects one or more BPF events.
+          The BPF program can attach to various perf events based on the ELF section
+          names.
+
+          When processing a '.c' file, perf searches an installed LLVM to compile it
+          into an object file first. Optional clang options can be passed via the
+          '--clang-opt' command line option, e.g.:
+
+            perf record --clang-opt "-DLINUX_VERSION_CODE=0x50000" \
+                        -e tests/bpf-script-example.c
+
+          Note: '--clang-opt' must be placed before '--event/-e'.
+
 	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
 	  Each event is separated by commas and the group should be quoted to
 	  prevent the shell interpretation.  You also need to use --group on
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 9a0242e74cfc3..2c35e532bc9af 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2f595cd73da66..911426721170b 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -5,6 +5,7 @@
  */
 
 #include <api/fs/fs.h>
+#include <linux/bits.h>
 #include <linux/bitops.h>
 #include <linux/compiler.h>
 #include <linux/coresight-pmu.h>
@@ -22,12 +23,10 @@
 #include "../../util/thread_map.h"
 #include "../../util/cs-etm.h"
 
+#include <errno.h>
 #include <stdlib.h>
 #include <sys/stat.h>
 
-#define ENABLE_SINK_MAX	128
-#define CS_BUS_DEVICE_PATH "/bus/coresight/devices/"
-
 struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
@@ -60,10 +59,48 @@ static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
 	return 0;
 }
 
+static int cs_etm_set_sink_attr(struct perf_pmu *pmu,
+				struct perf_evsel *evsel)
+{
+	char msg[BUFSIZ], path[PATH_MAX], *sink;
+	struct perf_evsel_config_term *term;
+	int ret = -EINVAL;
+	u32 hash;
+
+	if (evsel->attr.config2 & GENMASK(31, 0))
+		return 0;
+
+	list_for_each_entry(term, &evsel->config_terms, list) {
+		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
+			continue;
+
+		sink = term->val.drv_cfg;
+		snprintf(path, PATH_MAX, "sinks/%s", sink);
+
+		ret = perf_pmu__scan_file(pmu, path, "%x", &hash);
+		if (ret != 1) {
+			pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n",
+			       sink, perf_evsel__name(evsel), errno,
+			       str_error_r(errno, msg, sizeof(msg)));
+			return ret;
+		}
+
+		evsel->attr.config2 |= hash;
+		return 0;
+	}
+
+	/*
+	 * No sink was provided on the command line - for _now_ treat
+	 * this as an error.
+	 */
+	return ret;
+}
+
 static int cs_etm_recording_options(struct auxtrace_record *itr,
 				    struct perf_evlist *evlist,
 				    struct record_opts *opts)
 {
+	int ret;
 	struct cs_etm_recording *ptr =
 				container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
@@ -92,6 +129,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	if (!cs_etm_evsel)
 		return 0;
 
+	ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel);
+	if (ret)
+		return ret;
+
 	if (opts->use_clockid) {
 		pr_err("Cannot use clockid (-k option) with %s\n",
 		       CORESIGHT_ETM_PMU_NAME);
@@ -598,54 +639,3 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 out:
 	return NULL;
 }
-
-static FILE *cs_device__open_file(const char *name)
-{
-	struct stat st;
-	char path[PATH_MAX];
-	const char *sysfs;
-
-	sysfs = sysfs__mountpoint();
-	if (!sysfs)
-		return NULL;
-
-	snprintf(path, PATH_MAX,
-		 "%s" CS_BUS_DEVICE_PATH "%s", sysfs, name);
-
-	if (stat(path, &st) < 0)
-		return NULL;
-
-	return fopen(path, "w");
-
-}
-
-static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...)
-{
-	va_list args;
-	FILE *file;
-	int ret = -EINVAL;
-
-	va_start(args, fmt);
-	file = cs_device__open_file(name);
-	if (file) {
-		ret = vfprintf(file, fmt, args);
-		fclose(file);
-	}
-	va_end(args);
-	return ret;
-}
-
-int cs_etm_set_drv_config(struct perf_evsel_config_term *term)
-{
-	int ret;
-	char enable_sink[ENABLE_SINK_MAX];
-
-	snprintf(enable_sink, ENABLE_SINK_MAX, "%s/%s",
-		 term->val.drv_cfg, "enable_sink");
-
-	ret = cs_device__print_file(enable_sink, "%d", 1);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h
index 1a12e64f51279..a3354bda4fe8e 100644
--- a/tools/perf/arch/arm/util/cs-etm.h
+++ b/tools/perf/arch/arm/util/cs-etm.h
@@ -7,9 +7,6 @@
 #ifndef INCLUDE__PERF_CS_ETM_H__
 #define INCLUDE__PERF_CS_ETM_H__
 
-#include "../../util/evsel.h"
-
 struct auxtrace_record *cs_etm_record_init(int *err);
-int cs_etm_set_drv_config(struct perf_evsel_config_term *term);
 
 #endif
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index e047571e60800..bbc297a7e2e35 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -7,8 +7,8 @@
 #include <string.h>
 #include <linux/coresight-pmu.h>
 #include <linux/perf_event.h>
+#include <linux/string.h>
 
-#include "cs-etm.h"
 #include "arm-spe.h"
 #include "../../util/pmu.h"
 
@@ -19,7 +19,6 @@ struct perf_event_attr
 	if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
 		/* add ETM default config here */
 		pmu->selectable = true;
-		pmu->set_drv_config = cs_etm_set_drv_config;
 #if defined(__aarch64__)
 	} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
 		return arm_spe_pmu_default_config(pmu);
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
index 5522ce384723a..a6a407fa1b8b9 100644
--- a/tools/perf/arch/arm64/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 5f39efef0856d..5c178e4a19959 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index 596ad6aedaace..f9db341c47b60 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -3,6 +3,8 @@
 #include "util/kvm-stat.h"
 #include "util/parse-events.h"
 #include "util/debug.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
 
 #include "book3s_hv_exits.h"
 #include "book3s_hcalls.h"
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 7c6eeb4633fe1..2918bb16c892f 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -16,6 +16,9 @@
 #include "util/thread.h"
 #include "util/callchain.h"
 #include "util/debug.h"
+#include "util/dso.h"
+#include "util/map.h"
+#include "util/symbol.h"
 
 /*
  * When saving the callchain on Power, the kernel conservatively saves
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index aaabab5e28300..7e3961a4b292c 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -11,6 +11,7 @@
 
 #include <errno.h>
 #include "../../util/kvm-stat.h"
+#include "../../util/evsel.h"
 #include <asm/sie.h>
 
 define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 7879df34569a0..6ad0a1cedb13c 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 081353d7b095c..865a9762f22ef 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include "../../util/kvm-stat.h"
+#include "../../util/evsel.h"
 #include <asm/svm.h>
 #include <asm/vmx.h>
 #include <asm/kvm.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 20db635347e51..7f3c3fea67b48 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -27,6 +27,7 @@
 #include "util/thread.h"
 #include "util/sort.h"
 #include "util/hist.h"
+#include "util/map.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/data.h"
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 72ec0ae7d8ada..efaaab23c6fd7 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -33,6 +33,7 @@
 #include "ui/browsers/hists.h"
 #include "thread.h"
 #include "mem2node.h"
+#include "symbol.h"
 
 struct c2c_hists {
 	struct hists		hists;
@@ -1969,7 +1970,7 @@ static void calc_width(struct c2c_hist_entry *c2c_he)
 	set_nodestr(c2c_he);
 }
 
-static int filter_cb(struct hist_entry *he)
+static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
 {
 	struct c2c_hist_entry *c2c_he;
 
@@ -1986,7 +1987,7 @@ static int filter_cb(struct hist_entry *he)
 	return 0;
 }
 
-static int resort_cl_cb(struct hist_entry *he)
+static int resort_cl_cb(struct hist_entry *he, void *arg __maybe_unused)
 {
 	struct c2c_hist_entry *c2c_he;
 	struct c2c_hists *c2c_hists;
@@ -2073,7 +2074,7 @@ static int setup_nodes(struct perf_session *session)
 
 #define HAS_HITMS(__h) ((__h)->stats.lcl_hitm || (__h)->stats.rmt_hitm)
 
-static int resort_hitm_cb(struct hist_entry *he)
+static int resort_hitm_cb(struct hist_entry *he, void *arg __maybe_unused)
 {
 	struct c2c_hist_entry *c2c_he;
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
@@ -2095,7 +2096,7 @@ static int hists__iterate_cb(struct hists *hists, hists__resort_cb_t cb)
 		struct hist_entry *he;
 
 		he = rb_entry(next, struct hist_entry, rb_node);
-		ret = cb(he);
+		ret = cb(he, NULL);
 		if (ret)
 			break;
 		next = rb_next(&he->rb_node);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index eda41673c4f3c..9bb1f35d5cb7f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -12,6 +12,7 @@
 #include "util/color.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/map.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/debug.h"
@@ -19,6 +20,7 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 #include "util/jit.h"
+#include "util/symbol.h"
 #include "util/thread.h"
 
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index 90d1a2305b728..bc7a2bc7aed7d 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -13,6 +13,7 @@
 #include <subcmd/parse-options.h>
 #include "debug.h"
 #include "machine.h"
+#include "map.h"
 #include "symbol.h"
 
 static int __cmd_kallsyms(int argc, const char **argv)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 088705c167bfa..b80ec0883537a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -6,6 +6,7 @@
 #include "util/evsel.h"
 #include "util/util.h"
 #include "util/config.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 57393e94d1561..ba7e8d87dec33 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -13,6 +13,7 @@
 #include "util/data.h"
 #include "util/mem-events.h"
 #include "util/debug.h"
+#include "util/map.h"
 #include "util/symbol.h"
 
 #define MEM_OPERATION_LOAD	0x1
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 88ea11d57c6f1..3fdfbaebd95ee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -23,7 +23,6 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
-#include "util/drv_configs.h"
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/symbol.h"
@@ -39,6 +38,7 @@
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
+#include "util/cpu-set-sched.h"
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
@@ -82,12 +82,17 @@ struct record {
 	bool			timestamp_boundary;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
+	cpu_set_t		affinity_mask;
 };
 
 static volatile int auxtrace_record__snapshot_started;
 static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
 static DEFINE_TRIGGER(switch_output_trigger);
 
+static const char *affinity_tags[PERF_AFFINITY_MAX] = {
+	"SYS", "NODE", "CPU"
+};
+
 static bool switch_output_signal(struct record *rec)
 {
 	return rec->switch_output.signal &&
@@ -532,9 +537,13 @@ static int record__mmap_evlist(struct record *rec,
 	struct record_opts *opts = &rec->opts;
 	char msg[512];
 
+	if (opts->affinity != PERF_AFFINITY_SYS)
+		cpu__setup_cpunode_map();
+
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
-				 opts->auxtrace_snapshot_mode, opts->nr_cblocks) < 0) {
+				 opts->auxtrace_snapshot_mode,
+				 opts->nr_cblocks, opts->affinity) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -567,7 +576,6 @@ static int record__open(struct record *rec)
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
 	struct record_opts *opts = &rec->opts;
-	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
 	/*
@@ -620,14 +628,6 @@ try_again:
 		goto out;
 	}
 
-	if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) {
-		pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
-		      err_term->val.drv_cfg, perf_evsel__name(pos), errno,
-		      str_error_r(errno, msg, sizeof(msg)));
-		rc = -1;
-		goto out;
-	}
-
 	rc = record__mmap(rec);
 	if (rc)
 		goto out;
@@ -723,6 +723,16 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
+static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+{
+	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
+	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
+		CPU_ZERO(&rec->affinity_mask);
+		CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
+		sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+	}
+}
+
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
 				    bool overwrite)
 {
@@ -750,6 +760,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
+			record__adjust_affinity(rec, map);
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
 					rc = -1;
@@ -1987,6 +1998,9 @@ int cmd_record(int argc, const char **argv)
 # undef REASON
 #endif
 
+	CPU_ZERO(&rec->affinity_mask);
+	rec->opts.affinity = PERF_AFFINITY_SYS;
+
 	rec->evlist = perf_evlist__new();
 	if (rec->evlist == NULL)
 		return -ENOMEM;
@@ -2150,6 +2164,8 @@ int cmd_record(int argc, const char **argv)
 	if (verbose > 0)
 		pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
 
+	pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+
 	err = __cmd_record(&record, argc, argv);
 out:
 	perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c9ceaf88759ca..2e8c74d6430cf 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -16,6 +16,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/err.h>
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/callchain.h"
 #include "util/values.h"
@@ -615,6 +616,21 @@ static int report__collapse_hists(struct report *rep)
 	return ret;
 }
 
+static int hists__resort_cb(struct hist_entry *he, void *arg)
+{
+	struct report *rep = arg;
+	struct symbol *sym = he->ms.sym;
+
+	if (rep->symbol_ipc && sym && !sym->annotate2) {
+		struct perf_evsel *evsel = hists_to_evsel(he->hists);
+
+		symbol__annotate2(sym, he->ms.map, evsel,
+				  &annotation__default_options, NULL);
+	}
+
+	return 0;
+}
+
 static void report__output_resort(struct report *rep)
 {
 	struct ui_progress prog;
@@ -622,8 +638,10 @@ static void report__output_resort(struct report *rep)
 
 	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
-	evlist__for_each_entry(rep->session->evlist, pos)
-		perf_evsel__output_resort(pos, &prog);
+	evlist__for_each_entry(rep->session->evlist, pos) {
+		perf_evsel__output_resort_cb(pos, &prog,
+					     hists__resort_cb, rep);
+	}
 
 	ui_progress__finish();
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ac221f137ed2a..8d5fe092525c6 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -10,6 +10,7 @@
 #include "util/perf_regs.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e587808591e82..bb24f9c17f9a6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -52,7 +52,6 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
-#include "util/drv_configs.h"
 #include "util/color.h"
 #include "util/stat.h"
 #include "util/header.h"
@@ -417,7 +416,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int status = 0;
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
-	struct perf_evsel_config_term *err_term;
 
 	if (interval) {
 		ts.tv_sec  = interval / USEC_PER_MSEC;
@@ -514,13 +512,6 @@ try_again:
 		return -1;
 	}
 
-	if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) {
-		pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
-		      err_term->val.drv_cfg, perf_evsel__name(counter), errno,
-		      str_error_r(errno, msg, sizeof(msg)));
-		return -1;
-	}
-
 	if (STAT_RECORD) {
 		int err, fd = perf_data__fd(&perf_stat.data);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 57b1d7495d02f..231a90daa9581 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -25,11 +25,11 @@
 #include "util/bpf-event.h"
 #include "util/config.h"
 #include "util/color.h"
-#include "util/drv_configs.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/event.h"
 #include "util/machine.h"
+#include "util/map.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -1185,10 +1185,6 @@ static void init_process_thread(struct perf_top *top)
 
 static int __cmd_top(struct perf_top *top)
 {
-	char msg[512];
-	struct perf_evsel *pos;
-	struct perf_evsel_config_term *err_term;
-	struct perf_evlist *evlist = top->evlist;
 	struct record_opts *opts = &top->record_opts;
 	pthread_t thread, thread_process;
 	int ret;
@@ -1239,14 +1235,6 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
-	ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term);
-	if (ret) {
-		pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
-			err_term->val.drv_cfg, perf_evsel__name(pos), errno,
-			str_error_r(errno, msg, sizeof(msg)));
-		goto out_delete;
-	}
-
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 3518d352dd6c4..b4e420c418316 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -29,6 +29,8 @@
 #include "util/evlist.h"
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
+#include "util/map.h"
+#include "util/symbol.h"
 #include "util/path.h"
 #include "util/session.h"
 #include "util/thread.h"
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 5941fb6eccfcd..b120e547ddc7b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -84,6 +84,14 @@ struct record_opts {
 	clockid_t    clockid;
 	u64          clockid_res_ns;
 	int	     nr_cblocks;
+	int	     affinity;
+};
+
+enum perf_affinity {
+	PERF_AFFINITY_SYS = 0,
+	PERF_AFFINITY_NODE,
+	PERF_AFFINITY_CPU,
+	PERF_AFFINITY_MAX
 };
 
 struct option;
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 36c903faed0bf..71e9737f4614d 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -73,7 +73,7 @@
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 0564dd7377f22..30130213da7ea 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -478,7 +478,7 @@ if perf_db_export_calls:
 			'branch_count,'
 			'call_id,'
 			'return_id,'
-			'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,'
+			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 245caf2643ed1..ed237f2ed03f7 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -320,7 +320,7 @@ if perf_db_export_calls:
 			'branch_count,'
 			'call_id,'
 			'return_id,'
-			'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,'
+			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index dbf2c69944d25..4ebd2681e7607 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -15,6 +15,8 @@
 #include "thread_map.h"
 #include "cpumap.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "event.h"
 #include "thread.h"
 
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 7c8d2e422401e..077c306c1cae6 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -10,6 +10,7 @@
 #include "../util/unwind.h"
 #include "perf_regs.h"
 #include "map.h"
+#include "symbol.h"
 #include "thread.h"
 #include "callchain.h"
 
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index 6b0649c8b33e6..469958cd7fe0f 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -2,6 +2,7 @@
 #include <inttypes.h>
 #include "perf.h"
 #include "util/debug.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
 #include "util/evsel.h"
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 4ca417d1a06bb..7a2eed6c783ec 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -2,6 +2,7 @@
 #include "perf.h"
 #include "util/debug.h"
 #include "util/event.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
 #include "util/evsel.h"
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 1c5bedab3c2c1..975844807fe2b 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/debug.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
 #include "util/evsel.h"
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 6c4bc68a77ee5..0a510c524a5de 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -2,6 +2,7 @@
 #include "perf.h"
 #include "util/debug.h"
 #include "util/event.h"
+#include "util/map.h"
 #include "util/symbol.h"
 #include "util/sort.h"
 #include "util/evsel.h"
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 5ede9b561d32b..ba87e6e8d18c5 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -11,6 +11,7 @@
 #include "tests.h"
 #include "machine.h"
 #include "thread_map.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include "util.h"
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 7bedf8608fdde..14a78898d79e6 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -4,7 +4,9 @@
 #include "util.h"
 #include "tests.h"
 #include <errno.h>
+#include <stdio.h>
 #include <linux/kernel.h>
+#include <linux/limits.h>
 
 /* Simulated format definitions. */
 static struct test_format {
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 0e2d00d69e6e2..236ce0d6c8262 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <inttypes.h>
+#include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 
+#include "branch.h"
 #include "util.h"
 #include "event.h"
 #include "evsel.h"
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index 5059452d27ddf..8bfaa630389c2 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -3,6 +3,7 @@
 #include <stdio.h>
 #include <sys/epoll.h>
 #include <util/evlist.h>
+#include <util/symbol.h>
 #include <linux/filter.h>
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 82e16bf844660..35bdfd8b1e719 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -7,6 +7,7 @@
 #include "../../util/annotate.h"
 #include "../../util/hist.h"
 #include "../../util/sort.h"
+#include "../../util/map.h"
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 85790a4d18424..aef800d97ea18 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -8,9 +8,12 @@
 #include <linux/rbtree.h>
 #include <sys/ttydefaults.h>
 
+#include "../../util/callchain.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/hist.h"
+#include "../../util/map.h"
+#include "../../util/symbol.h"
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/util.h"
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index f22a7d142adad..df49c9ba17857 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -4,6 +4,8 @@
 #include "util/debug.h"
 #include "util/annotate.h"
 #include "util/evsel.h"
+#include "util/map.h"
+#include "util/symbol.h"
 #include "ui/helpline.h"
 #include <inttypes.h>
 #include <signal.h>
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 74414ccd8c84b..0c08890f006ae 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../evlist.h"
 #include "../cache.h"
+#include "../callchain.h"
 #include "../evsel.h"
 #include "../sort.h"
 #include "../hist.h"
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index fe3dfaa64a916..412d6f1626e3b 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -3,6 +3,7 @@
 #include <math.h>
 #include <linux/compiler.h>
 
+#include "../util/callchain.h"
 #include "../util/hist.h"
 #include "../util/util.h"
 #include "../util/sort.h"
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 2a9fa4dcbc2ad..a60f2993d390b 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -2,8 +2,12 @@
 #include <stdio.h>
 #include <linux/string.h>
 
+#include "../../util/callchain.h"
 #include "../../util/util.h"
 #include "../../util/hist.h"
+#include "../../util/map.h"
+#include "../../util/map_groups.h"
+#include "../../util/symbol.h"
 #include "../../util/sort.h"
 #include "../../util/evsel.h"
 #include "../../util/srcline.h"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index b69d6294c88c3..a36e6e5a6f4fa 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -107,7 +107,6 @@ libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
 libperf-y += vsprintf.o
-libperf-y += drv_configs.o
 libperf-y += units.o
 libperf-y += time-utils.o
 libperf-y += expr-bison.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3d79add5f7aea..2468b8aa0b6bd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,6 +17,7 @@
 #include "color.h"
 #include "config.h"
 #include "cache.h"
+#include "map.h"
 #include "symbol.h"
 #include "units.h"
 #include "debug.h"
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index f69961c4a4f34..267e54df511be 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -27,6 +27,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/string.h>
+#include <linux/time64.h>
 
 #include <sys/param.h>
 #include <stdlib.h>
@@ -41,6 +42,7 @@
 #include "pmu.h"
 #include "evsel.h"
 #include "cpumap.h"
+#include "symbol.h"
 #include "thread_map.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
@@ -857,7 +859,7 @@ void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
 
 void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
-			  const char *msg)
+			  const char *msg, u64 timestamp)
 {
 	size_t size;
 
@@ -869,7 +871,9 @@ void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
 	auxtrace_error->cpu = cpu;
 	auxtrace_error->pid = pid;
 	auxtrace_error->tid = tid;
+	auxtrace_error->fmt = 1;
 	auxtrace_error->ip = ip;
+	auxtrace_error->time = timestamp;
 	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
 
 	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
@@ -1159,12 +1163,27 @@ static const char *auxtrace_error_name(int type)
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 {
 	struct auxtrace_error_event *e = &event->auxtrace_error;
+	unsigned long long nsecs = e->time;
+	const char *msg = e->msg;
 	int ret;
 
 	ret = fprintf(fp, " %s error type %u",
 		      auxtrace_error_name(e->type), e->type);
+
+	if (e->fmt && nsecs) {
+		unsigned long secs = nsecs / NSEC_PER_SEC;
+
+		nsecs -= secs * NSEC_PER_SEC;
+		ret += fprintf(fp, " time %lu.%09llu", secs, nsecs);
+	} else {
+		ret += fprintf(fp, " time 0");
+	}
+
+	if (!e->fmt)
+		msg = (const char *)&e->time;
+
 	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
-		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+		       e->cpu, e->pid, e->tid, e->ip, e->code, msg);
 	return ret;
 }
 
@@ -1278,9 +1297,9 @@ static int __auxtrace_mmap__read(struct perf_mmap *map,
 	}
 
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
-	padding = size & 7;
+	padding = size & (PERF_AUXTRACE_RECORD_ALIGNMENT - 1);
 	if (padding)
-		padding = 8 - padding;
+		padding = PERF_AUXTRACE_RECORD_ALIGNMENT - padding;
 
 	memset(&ev, 0, sizeof(ev));
 	ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 8e50f96d4b23d..c69bcd9a3091c 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -40,6 +40,9 @@ struct record_opts;
 struct auxtrace_info_event;
 struct events_stats;
 
+/* Auxtrace records must have the same alignment as perf event records */
+#define PERF_AUXTRACE_RECORD_ALIGNMENT 8
+
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
 	PERF_AUXTRACE_INTEL_PT,
@@ -516,7 +519,7 @@ void auxtrace_index__free(struct list_head *head);
 
 void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
-			  const char *msg);
+			  const char *msg, u64 timestamp);
 
 int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 2f3eb6d293eeb..6e68698aa0ad8 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include "perf.h"
 #include "debug.h"
+#include "evlist.h"
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-event.h"
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 62d245a90e1d9..3f46856e3330f 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,11 +8,7 @@
 
 #include <linux/compiler.h>
 #include <linux/err.h>
-#include <string.h>
 #include <bpf/libbpf.h>
-#include "probe-event.h"
-#include "evlist.h"
-#include "debug.h"
 
 enum bpf_loader_errno {
 	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
@@ -44,6 +40,7 @@ enum bpf_loader_errno {
 };
 
 struct perf_evsel;
+struct perf_evlist;
 struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
@@ -87,6 +84,8 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size);
 #else
 #include <errno.h>
+#include <string.h>
+#include "debug.h"
 
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 2ff802068f065..bff0d17920ed7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -16,6 +16,7 @@
 #include "build-id.h"
 #include "event.h"
 #include "namespaces.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index dc2212e121849..abb608b092698 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -23,8 +23,10 @@
 #include "util.h"
 #include "sort.h"
 #include "machine.h"
+#include "map.h"
 #include "callchain.h"
 #include "branch.h"
+#include "symbol.h"
 
 #define CALLCHAIN_PARAM_DEFAULT			\
 	.mode		= CHAIN_GRAPH_ABS,	\
@@ -1577,3 +1579,18 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
 	return rc;
 }
+
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+	struct callchain_cursor_node *node;
+
+	cursor->nr = 0;
+	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8afe1622edf31..80e056a3d8821 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,10 +5,11 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
-#include "map.h"
-#include "symbol.h"
+#include "map_symbol.h"
 #include "branch.h"
 
+struct map;
+
 #define HELP_PAD "\t\t\t\t"
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
@@ -187,20 +188,7 @@ int callchain_append(struct callchain_root *root,
 int callchain_merge(struct callchain_cursor *cursor,
 		    struct callchain_root *dst, struct callchain_root *src);
 
-/*
- * Initialize a cursor before adding entries inside, but keep
- * the previously allocated entries as a cache.
- */
-static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
-{
-	struct callchain_cursor_node *node;
-
-	cursor->nr = 0;
-	cursor->last = &cursor->first;
-
-	for (node = cursor->first; node != NULL; node = node->next)
-		map__zput(node->map);
-}
+void callchain_cursor_reset(struct callchain_cursor *cursor);
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
 			    struct map *map, struct symbol *sym,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 1ea8f898f1a1c..fa092511c52b6 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -13,6 +13,7 @@
 #include <sys/param.h>
 #include "util.h"
 #include "cache.h"
+#include "callchain.h"
 #include <subcmd/exec-cmd.h>
 #include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
diff --git a/tools/perf/util/cpu-set-sched.h b/tools/perf/util/cpu-set-sched.h
new file mode 100644
index 0000000000000..8cf4e40d322a9
--- /dev/null
+++ b/tools/perf/util/cpu-set-sched.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: LGPL-2.1
+// Definitions taken from glibc for use with older systems, same licensing.
+#ifndef _CPU_SET_SCHED_PERF_H
+#define _CPU_SET_SCHED_PERF_H
+
+#include <features.h>
+#include <sched.h>
+
+#ifndef CPU_EQUAL
+#ifndef __CPU_EQUAL_S
+#if __GNUC_PREREQ (2, 91)
+# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \
+  (__builtin_memcmp (cpusetp1, cpusetp2, setsize) == 0)
+#else
+# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \
+  (__extension__							      \
+   ({ const __cpu_mask *__arr1 = (cpusetp1)->__bits;			      \
+      const __cpu_mask *__arr2 = (cpusetp2)->__bits;			      \
+      size_t __imax = (setsize) / sizeof (__cpu_mask);			      \
+      size_t __i;							      \
+      for (__i = 0; __i < __imax; ++__i)				      \
+	if (__arr1[__i] != __arr2[__i])					      \
+	  break;							      \
+      __i == __imax; }))
+#endif
+#endif // __CPU_EQUAL_S
+
+#define CPU_EQUAL(cpusetp1, cpusetp2) \
+  __CPU_EQUAL_S (sizeof (cpu_set_t), cpusetp1, cpusetp2)
+#endif // CPU_EQUAL
+
+#ifndef CPU_OR
+#ifndef __CPU_OP_S
+#define __CPU_OP_S(setsize, destset, srcset1, srcset2, op) \
+  (__extension__							      \
+   ({ cpu_set_t *__dest = (destset);					      \
+      const __cpu_mask *__arr1 = (srcset1)->__bits;			      \
+      const __cpu_mask *__arr2 = (srcset2)->__bits;			      \
+      size_t __imax = (setsize) / sizeof (__cpu_mask);			      \
+      size_t __i;							      \
+      for (__i = 0; __i < __imax; ++__i)				      \
+	((__cpu_mask *) __dest->__bits)[__i] = __arr1[__i] op __arr2[__i];    \
+      __dest; }))
+#endif // __CPU_OP_S
+
+#define CPU_OR(destset, srcset1, srcset2) \
+  __CPU_OP_S (sizeof (cpu_set_t), destset, srcset1, srcset2, |)
+#endif // CPU_OR
+
+#endif // _CPU_SET_SCHED_PERF_H
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 383674f448fcd..0bbc3feb08945 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -730,3 +730,13 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	buf[size - 1] = '\0';
 	return ptr - buf;
 }
+
+const struct cpu_map *cpu_map__online(void) /* thread unsafe */
+{
+	static const struct cpu_map *online = NULL;
+
+	if (!online)
+		online = cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+
+	return online;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index ed8999d1a6402..f00ce624b9f79 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -29,6 +29,7 @@ int cpu_map__get_core_id(int cpu);
 int cpu_map__get_core(struct cpu_map *map, int idx, void *data);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
+const struct cpu_map *cpu_map__online(void); /* thread unsafe */
 
 struct cpu_map *cpu_map__get(struct cpu_map *map);
 void cpu_map__put(struct cpu_map *map);
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 8c155575c6c50..ba4c623cd8de0 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -290,6 +290,12 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 		decoder->packet_buffer[i].instr_count = 0;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].last_instr_size = 0;
+		decoder->packet_buffer[i].last_instr_type = 0;
+		decoder->packet_buffer[i].last_instr_subtype = 0;
+		decoder->packet_buffer[i].last_instr_cond = 0;
+		decoder->packet_buffer[i].flags = 0;
+		decoder->packet_buffer[i].exception_number = UINT32_MAX;
+		decoder->packet_buffer[i].trace_chan_id = UINT8_MAX;
 		decoder->packet_buffer[i].cpu = INT_MIN;
 	}
 }
@@ -300,14 +306,12 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 			      enum cs_etm_sample_type sample_type)
 {
 	u32 et = 0;
-	struct int_node *inode = NULL;
+	int cpu;
 
 	if (decoder->packet_count >= MAX_BUFFER - 1)
 		return OCSD_RESP_FATAL_SYS_ERR;
 
-	/* Search the RB tree for the cpu associated with this traceID */
-	inode = intlist__find(traceid_list, trace_chan_id);
-	if (!inode)
+	if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
 		return OCSD_RESP_FATAL_SYS_ERR;
 
 	et = decoder->tail;
@@ -317,12 +321,18 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 
 	decoder->packet_buffer[et].sample_type = sample_type;
 	decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
-	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
+	decoder->packet_buffer[et].cpu = cpu;
 	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
 	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 	decoder->packet_buffer[et].instr_count = 0;
 	decoder->packet_buffer[et].last_instr_taken_branch = false;
 	decoder->packet_buffer[et].last_instr_size = 0;
+	decoder->packet_buffer[et].last_instr_type = 0;
+	decoder->packet_buffer[et].last_instr_subtype = 0;
+	decoder->packet_buffer[et].last_instr_cond = 0;
+	decoder->packet_buffer[et].flags = 0;
+	decoder->packet_buffer[et].exception_number = UINT32_MAX;
+	decoder->packet_buffer[et].trace_chan_id = trace_chan_id;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -366,6 +376,9 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 	packet->start_addr = elem->st_addr;
 	packet->end_addr = elem->en_addr;
 	packet->instr_count = elem->num_instr_range;
+	packet->last_instr_type = elem->last_i_type;
+	packet->last_instr_subtype = elem->last_i_subtype;
+	packet->last_instr_cond = elem->last_instr_cond;
 
 	switch (elem->last_i_type) {
 	case OCSD_INSTR_BR:
@@ -395,10 +408,20 @@ cs_etm_decoder__buffer_discontinuity(struct cs_etm_decoder *decoder,
 
 static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder,
+				 const ocsd_generic_trace_elem *elem,
 				 const uint8_t trace_chan_id)
-{
-	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
-					     CS_ETM_EXCEPTION);
+{	int ret = 0;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_EXCEPTION);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+	packet->exception_number = elem->exception_number;
+
+	return ret;
 }
 
 static ocsd_datapath_resp_t
@@ -432,7 +455,7 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
-		resp = cs_etm_decoder__buffer_exception(decoder,
+		resp = cs_etm_decoder__buffer_exception(decoder, elem,
 							trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index a6407d41598fc..7e6a8850be4a4 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -43,8 +43,14 @@ struct cs_etm_packet {
 	u64 start_addr;
 	u64 end_addr;
 	u32 instr_count;
+	u32 last_instr_type;
+	u32 last_instr_subtype;
+	u32 flags;
+	u32 exception_number;
+	u8 last_instr_cond;
 	u8 last_instr_taken_branch;
 	u8 last_instr_size;
+	u8 trace_chan_id;
 	int cpu;
 };
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 27a374ddf6615..8b3f882d6e2f0 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -12,6 +12,7 @@
 #include <linux/log2.h>
 #include <linux/types.h>
 
+#include <opencsd/ocsd_if_types.h>
 #include <stdlib.h>
 
 #include "auxtrace.h"
@@ -96,6 +97,34 @@ static u32 cs_etm__get_v7_protocol_version(u32 etmidr)
 	return CS_ETM_PROTO_ETMV3;
 }
 
+static int cs_etm__get_magic(u8 trace_chan_id, u64 *magic)
+{
+	struct int_node *inode;
+	u64 *metadata;
+
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return -EINVAL;
+
+	metadata = inode->priv;
+	*magic = metadata[CS_ETM_MAGIC];
+	return 0;
+}
+
+int cs_etm__get_cpu(u8 trace_chan_id, int *cpu)
+{
+	struct int_node *inode;
+	u64 *metadata;
+
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return -EINVAL;
+
+	metadata = inode->priv;
+	*cpu = (int)metadata[CS_ETM_CPU];
+	return 0;
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -251,7 +280,7 @@ static void cs_etm__free(struct perf_session *session)
 	cs_etm__free_events(session);
 	session->auxtrace = NULL;
 
-	/* First remove all traceID/CPU# nodes for the RB tree */
+	/* First remove all traceID/metadata nodes for the RB tree */
 	intlist__for_each_entry_safe(inode, tmp, traceid_list)
 		intlist__remove(traceid_list, inode);
 	/* Then the RB tree itself */
@@ -719,7 +748,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.stream_id = etmq->etm->instructions_id;
 	sample.period = period;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.insn_len = 1;
 	sample.cpumode = event->sample.header.misc;
 
@@ -778,7 +807,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
 	/*
@@ -1107,6 +1136,344 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq)
 	return 0;
 }
 
+static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq,
+				 struct cs_etm_packet *packet,
+				 u64 end_addr)
+{
+	u16 instr16;
+	u32 instr32;
+	u64 addr;
+
+	switch (packet->isa) {
+	case CS_ETM_ISA_T32:
+		/*
+		 * The SVC of T32 is defined in ARM DDI 0487D.a, F5.1.247:
+		 *
+		 *  b'15         b'8
+		 * +-----------------+--------+
+		 * | 1 1 0 1 1 1 1 1 |  imm8  |
+		 * +-----------------+--------+
+		 *
+		 * According to the specifiction, it only defines SVC for T32
+		 * with 16 bits instruction and has no definition for 32bits;
+		 * so below only read 2 bytes as instruction size for T32.
+		 */
+		addr = end_addr - 2;
+		cs_etm__mem_access(etmq, addr, sizeof(instr16), (u8 *)&instr16);
+		if ((instr16 & 0xFF00) == 0xDF00)
+			return true;
+
+		break;
+	case CS_ETM_ISA_A32:
+		/*
+		 * The SVC of A32 is defined in ARM DDI 0487D.a, F5.1.247:
+		 *
+		 *  b'31 b'28 b'27 b'24
+		 * +---------+---------+-------------------------+
+		 * |  !1111  | 1 1 1 1 |        imm24            |
+		 * +---------+---------+-------------------------+
+		 */
+		addr = end_addr - 4;
+		cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32);
+		if ((instr32 & 0x0F000000) == 0x0F000000 &&
+		    (instr32 & 0xF0000000) != 0xF0000000)
+			return true;
+
+		break;
+	case CS_ETM_ISA_A64:
+		/*
+		 * The SVC of A64 is defined in ARM DDI 0487D.a, C6.2.294:
+		 *
+		 *  b'31               b'21           b'4     b'0
+		 * +-----------------------+---------+-----------+
+		 * | 1 1 0 1 0 1 0 0 0 0 0 |  imm16  | 0 0 0 0 1 |
+		 * +-----------------------+---------+-----------+
+		 */
+		addr = end_addr - 4;
+		cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32);
+		if ((instr32 & 0xFFE0001F) == 0xd4000001)
+			return true;
+
+		break;
+	case CS_ETM_ISA_UNKNOWN:
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->prev_packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_SVC)
+			return true;
+
+	/*
+	 * ETMv4 exception type CS_ETMV4_EXC_CALL covers SVC, SMC and
+	 * HVC cases; need to check if it's SVC instruction based on
+	 * packet address.
+	 */
+	if (magic == __perf_cs_etmv4_magic) {
+		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
+		    cs_etm__is_svc_instr(etmq, prev_packet,
+					 prev_packet->end_addr))
+			return true;
+	}
+
+	return false;
+}
+
+static bool cs_etm__is_async_exception(struct cs_etm_queue *etmq, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_DEBUG_HALT ||
+		    packet->exception_number == CS_ETMV3_EXC_ASYNC_DATA_ABORT ||
+		    packet->exception_number == CS_ETMV3_EXC_PE_RESET ||
+		    packet->exception_number == CS_ETMV3_EXC_IRQ ||
+		    packet->exception_number == CS_ETMV3_EXC_FIQ)
+			return true;
+
+	if (magic == __perf_cs_etmv4_magic)
+		if (packet->exception_number == CS_ETMV4_EXC_RESET ||
+		    packet->exception_number == CS_ETMV4_EXC_DEBUG_HALT ||
+		    packet->exception_number == CS_ETMV4_EXC_SYSTEM_ERROR ||
+		    packet->exception_number == CS_ETMV4_EXC_INST_DEBUG ||
+		    packet->exception_number == CS_ETMV4_EXC_DATA_DEBUG ||
+		    packet->exception_number == CS_ETMV4_EXC_IRQ ||
+		    packet->exception_number == CS_ETMV4_EXC_FIQ)
+			return true;
+
+	return false;
+}
+
+static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->prev_packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_SMC ||
+		    packet->exception_number == CS_ETMV3_EXC_HYP ||
+		    packet->exception_number == CS_ETMV3_EXC_JAZELLE_THUMBEE ||
+		    packet->exception_number == CS_ETMV3_EXC_UNDEFINED_INSTR ||
+		    packet->exception_number == CS_ETMV3_EXC_PREFETCH_ABORT ||
+		    packet->exception_number == CS_ETMV3_EXC_DATA_FAULT ||
+		    packet->exception_number == CS_ETMV3_EXC_GENERIC)
+			return true;
+
+	if (magic == __perf_cs_etmv4_magic) {
+		if (packet->exception_number == CS_ETMV4_EXC_TRAP ||
+		    packet->exception_number == CS_ETMV4_EXC_ALIGNMENT ||
+		    packet->exception_number == CS_ETMV4_EXC_INST_FAULT ||
+		    packet->exception_number == CS_ETMV4_EXC_DATA_FAULT)
+			return true;
+
+		/*
+		 * For CS_ETMV4_EXC_CALL, except SVC other instructions
+		 * (SMC, HVC) are taken as sync exceptions.
+		 */
+		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
+		    !cs_etm__is_svc_instr(etmq, prev_packet,
+					  prev_packet->end_addr))
+			return true;
+
+		/*
+		 * ETMv4 has 5 bits for exception number; if the numbers
+		 * are in the range ( CS_ETMV4_EXC_FIQ, CS_ETMV4_EXC_END ]
+		 * they are implementation defined exceptions.
+		 *
+		 * For this case, simply take it as sync exception.
+		 */
+		if (packet->exception_number > CS_ETMV4_EXC_FIQ &&
+		    packet->exception_number <= CS_ETMV4_EXC_END)
+			return true;
+	}
+
+	return false;
+}
+
+static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->prev_packet;
+	u64 magic;
+	int ret;
+
+	switch (packet->sample_type) {
+	case CS_ETM_RANGE:
+		/*
+		 * Immediate branch instruction without neither link nor
+		 * return flag, it's normal branch instruction within
+		 * the function.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_NONE) {
+			packet->flags = PERF_IP_FLAG_BRANCH;
+
+			if (packet->last_instr_cond)
+				packet->flags |= PERF_IP_FLAG_CONDITIONAL;
+		}
+
+		/*
+		 * Immediate branch instruction with link (e.g. BL), this is
+		 * branch instruction for function call.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/*
+		 * Indirect branch instruction with link (e.g. BLR), this is
+		 * branch instruction for function call.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/*
+		 * Indirect branch instruction with subtype of
+		 * OCSD_S_INSTR_V7_IMPLIED_RET, this is explicit hint for
+		 * function return for A32/T32.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_V7_IMPLIED_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Indirect branch instruction without link (e.g. BR), usually
+		 * this is used for function return, especially for functions
+		 * within dynamic link lib.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_NONE)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/* Return instruction for function return. */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_V8_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Decoder might insert a discontinuity in the middle of
+		 * instruction packets, fixup prev_packet with flag
+		 * PERF_IP_FLAG_TRACE_BEGIN to indicate restarting trace.
+		 */
+		if (prev_packet->sample_type == CS_ETM_DISCONTINUITY)
+			prev_packet->flags |= PERF_IP_FLAG_BRANCH |
+					      PERF_IP_FLAG_TRACE_BEGIN;
+
+		/*
+		 * If the previous packet is an exception return packet
+		 * and the return address just follows SVC instuction,
+		 * it needs to calibrate the previous packet sample flags
+		 * as PERF_IP_FLAG_SYSCALLRET.
+		 */
+		if (prev_packet->flags == (PERF_IP_FLAG_BRANCH |
+					   PERF_IP_FLAG_RETURN |
+					   PERF_IP_FLAG_INTERRUPT) &&
+		    cs_etm__is_svc_instr(etmq, packet, packet->start_addr))
+			prev_packet->flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_RETURN |
+					     PERF_IP_FLAG_SYSCALLRET;
+		break;
+	case CS_ETM_DISCONTINUITY:
+		/*
+		 * The trace is discontinuous, if the previous packet is
+		 * instruction packet, set flag PERF_IP_FLAG_TRACE_END
+		 * for previous packet.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags |= PERF_IP_FLAG_BRANCH |
+					      PERF_IP_FLAG_TRACE_END;
+		break;
+	case CS_ETM_EXCEPTION:
+		ret = cs_etm__get_magic(packet->trace_chan_id, &magic);
+		if (ret)
+			return ret;
+
+		/* The exception is for system call. */
+		if (cs_etm__is_syscall(etmq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_SYSCALLRET;
+		/*
+		 * The exceptions are triggered by external signals from bus,
+		 * interrupt controller, debug module, PE reset or halt.
+		 */
+		else if (cs_etm__is_async_exception(etmq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_ASYNC |
+					PERF_IP_FLAG_INTERRUPT;
+		/*
+		 * Otherwise, exception is caused by trap, instruction &
+		 * data fault, or alignment errors.
+		 */
+		else if (cs_etm__is_sync_exception(etmq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_INTERRUPT;
+
+		/*
+		 * When the exception packet is inserted, since exception
+		 * packet is not used standalone for generating samples
+		 * and it's affiliation to the previous instruction range
+		 * packet; so set previous range packet flags to tell perf
+		 * it is an exception taken branch.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags = packet->flags;
+		break;
+	case CS_ETM_EXCEPTION_RET:
+		/*
+		 * When the exception return packet is inserted, since
+		 * exception return packet is not used standalone for
+		 * generating samples and it's affiliation to the previous
+		 * instruction range packet; so set previous range packet
+		 * flags to tell perf it is an exception return branch.
+		 *
+		 * The exception return can be for either system call or
+		 * other exception types; unfortunately the packet doesn't
+		 * contain exception type related info so we cannot decide
+		 * the exception type purely based on exception return packet.
+		 * If we record the exception number from exception packet and
+		 * reuse it for excpetion return packet, this is not reliable
+		 * due the trace can be discontinuity or the interrupt can
+		 * be nested, thus the recorded exception number cannot be
+		 * used for exception return packet for these two cases.
+		 *
+		 * For exception return packet, we only need to distinguish the
+		 * packet is for system call or for other types.  Thus the
+		 * decision can be deferred when receive the next packet which
+		 * contains the return address, based on the return address we
+		 * can read out the previous instruction and check if it's a
+		 * system call instruction and then calibrate the sample flag
+		 * as needed.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_RETURN |
+					     PERF_IP_FLAG_INTERRUPT;
+		break;
+	case CS_ETM_EMPTY:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
@@ -1158,6 +1525,17 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					break;
 
+				/*
+				 * Since packet addresses are swapped in packet
+				 * handling within below switch() statements,
+				 * thus setting sample flags must be called
+				 * prior to switch() statement to use address
+				 * information before packets swapping.
+				 */
+				err = cs_etm__set_sample_flags(etmq);
+				if (err < 0)
+					break;
+
 				switch (etmq->packet->sample_type) {
 				case CS_ETM_RANGE:
 					/*
@@ -1414,9 +1792,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 				    0xffffffff);
 
 	/*
-	 * Create an RB tree for traceID-CPU# tuple. Since the conversion has
-	 * to be made for each packet that gets decoded, optimizing access in
-	 * anything other than a sequential array is worth doing.
+	 * Create an RB tree for traceID-metadata tuple.  Since the conversion
+	 * has to be made for each packet that gets decoded, optimizing access
+	 * in anything other than a sequential array is worth doing.
 	 */
 	traceid_list = intlist__new(NULL);
 	if (!traceid_list) {
@@ -1482,8 +1860,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 			err = -EINVAL;
 			goto err_free_metadata;
 		}
-		/* All good, associate the traceID with the CPU# */
-		inode->priv = &metadata[j][CS_ETM_CPU];
+		/* All good, associate the traceID with the metadata pointer */
+		inode->priv = metadata[j];
 	}
 
 	/*
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 37f8d48179cae..d76126e0e3d02 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -53,7 +53,51 @@ enum {
 	CS_ETMV4_PRIV_MAX,
 };
 
-/* RB tree for quick conversion between traceID and CPUs */
+/*
+ * ETMv3 exception encoding number:
+ * See Embedded Trace Macrocell spcification (ARM IHI 0014Q)
+ * table 7-12 Encoding of Exception[3:0] for non-ARMv7-M processors.
+ */
+enum {
+	CS_ETMV3_EXC_NONE = 0,
+	CS_ETMV3_EXC_DEBUG_HALT = 1,
+	CS_ETMV3_EXC_SMC = 2,
+	CS_ETMV3_EXC_HYP = 3,
+	CS_ETMV3_EXC_ASYNC_DATA_ABORT = 4,
+	CS_ETMV3_EXC_JAZELLE_THUMBEE = 5,
+	CS_ETMV3_EXC_PE_RESET = 8,
+	CS_ETMV3_EXC_UNDEFINED_INSTR = 9,
+	CS_ETMV3_EXC_SVC = 10,
+	CS_ETMV3_EXC_PREFETCH_ABORT = 11,
+	CS_ETMV3_EXC_DATA_FAULT = 12,
+	CS_ETMV3_EXC_GENERIC = 13,
+	CS_ETMV3_EXC_IRQ = 14,
+	CS_ETMV3_EXC_FIQ = 15,
+};
+
+/*
+ * ETMv4 exception encoding number:
+ * See ARM Embedded Trace Macrocell Architecture Specification (ARM IHI 0064D)
+ * table 6-12 Possible values for the TYPE field in an Exception instruction
+ * trace packet, for ARMv7-A/R and ARMv8-A/R PEs.
+ */
+enum {
+	CS_ETMV4_EXC_RESET = 0,
+	CS_ETMV4_EXC_DEBUG_HALT = 1,
+	CS_ETMV4_EXC_CALL = 2,
+	CS_ETMV4_EXC_TRAP = 3,
+	CS_ETMV4_EXC_SYSTEM_ERROR = 4,
+	CS_ETMV4_EXC_INST_DEBUG = 6,
+	CS_ETMV4_EXC_DATA_DEBUG = 7,
+	CS_ETMV4_EXC_ALIGNMENT = 10,
+	CS_ETMV4_EXC_INST_FAULT = 11,
+	CS_ETMV4_EXC_DATA_FAULT = 12,
+	CS_ETMV4_EXC_IRQ = 14,
+	CS_ETMV4_EXC_FIQ = 15,
+	CS_ETMV4_EXC_END = 31,
+};
+
+/* RB tree for quick conversion between traceID and metadata pointers */
 struct intlist *traceid_list;
 
 #define KiB(x) ((x) * 1024)
@@ -69,6 +113,7 @@ static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
 #ifdef HAVE_CSTRACE_SUPPORT
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
+int cs_etm__get_cpu(u8 trace_chan_id, int *cpu);
 #else
 static inline int
 cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
@@ -76,6 +121,12 @@ cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
 {
 	return -1;
 }
+
+static inline int cs_etm__get_cpu(u8 trace_chan_id __maybe_unused,
+				  int *cpu __maybe_unused)
+{
+	return -1;
+}
 #endif
 
 #endif
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 69fbb0a72d0cb..de9b4769d06c9 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -20,6 +20,7 @@
 #include "thread.h"
 #include "comm.h"
 #include "symbol.h"
+#include "map.h"
 #include "event.h"
 #include "util.h"
 #include "thread-stack.h"
diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c
deleted file mode 100644
index eec754243f4d3..0000000000000
--- a/tools/perf/util/drv_configs.c
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * drv_configs.h: Interface to apply PMU specific configuration
- * Copyright (c) 2016-2018, Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- */
-
-#include "drv_configs.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "pmu.h"
-#include <errno.h>
-
-static int
-perf_evsel__apply_drv_configs(struct perf_evsel *evsel,
-			      struct perf_evsel_config_term **err_term)
-{
-	bool found = false;
-	int err = 0;
-	struct perf_evsel_config_term *term;
-	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
-		if (pmu->type == evsel->attr.type) {
-			found = true;
-			break;
-		}
-
-	list_for_each_entry(term, &evsel->config_terms, list) {
-		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
-			continue;
-
-		/*
-		 * We have a configuration term, report an error if we
-		 * can't find the PMU or if the PMU driver doesn't support
-		 * cmd line driver configuration.
-		 */
-		if (!found || !pmu->set_drv_config) {
-			err = -EINVAL;
-			*err_term = term;
-			break;
-		}
-
-		err = pmu->set_drv_config(term);
-		if (err) {
-			*err_term = term;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
-				   struct perf_evsel **err_evsel,
-				   struct perf_evsel_config_term **err_term)
-{
-	struct perf_evsel *evsel;
-	int err = 0;
-
-	evlist__for_each_entry(evlist, evsel) {
-		err = perf_evsel__apply_drv_configs(evsel, err_term);
-		if (err) {
-			*err_evsel = evsel;
-			break;
-		}
-	}
-
-	return err;
-}
diff --git a/tools/perf/util/drv_configs.h b/tools/perf/util/drv_configs.h
deleted file mode 100644
index 32bc9babc2e01..0000000000000
--- a/tools/perf/util/drv_configs.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * drv_configs.h: Interface to apply PMU specific configuration
- * Copyright (c) 2016-2018, Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- */
-
-#ifndef __PERF_DRV_CONFIGS_H
-#define __PERF_DRV_CONFIGS_H
-
-#include "drv_configs.h"
-#include "evlist.h"
-#include "evsel.h"
-
-int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
-				   struct perf_evsel **err_evsel,
-				   struct perf_evsel_config_term **term);
-#endif
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index a8a54115b115b..ba58ba603b69c 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -12,6 +12,7 @@
 #include "compress.h"
 #include "namespaces.h"
 #include "path.h"
+#include "map.h"
 #include "symbol.h"
 #include "srcline.h"
 #include "dso.h"
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1b5091a3d14f8..ba7be74fad6ea 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -21,6 +21,8 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "sane_ctype.h"
+#include "map.h"
+#include "symbol.h"
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index feba1aa819b4f..36ae7e92dab1d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -532,8 +532,9 @@ struct auxtrace_error_event {
 	u32 cpu;
 	u32 pid;
 	u32 tid;
-	u32 reserved__; /* For alignment */
+	u32 fmt;
 	u64 ip;
+	u64 time;
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8c902276d4b4c..08cedb643ea6e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1022,7 +1022,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1032,7 +1032,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks };
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1064,7 +1064,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 00ab43c6dd157..744906dd48873 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -165,7 +165,7 @@ unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks);
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 29c5eb68c44b2..cc578e02e08fb 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,7 +8,7 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include "xyarray.h"
-#include "symbol.h"
+#include "symbol_conf.h"
 #include "cpumap.h"
 #include "counts.h"
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 9e7a8e044a0a9..669f961316f05 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "callchain.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -11,6 +12,7 @@
 #include "evsel.h"
 #include "annotate.h"
 #include "srcline.h"
+#include "symbol.h"
 #include "thread.h"
 #include "ui/progress.h"
 #include <errno.h>
@@ -1719,7 +1721,8 @@ static void __hists__insert_output_entry(struct rb_root_cached *entries,
 }
 
 static void output_resort(struct hists *hists, struct ui_progress *prog,
-			  bool use_callchain, hists__resort_cb_t cb)
+			  bool use_callchain, hists__resort_cb_t cb,
+			  void *cb_arg)
 {
 	struct rb_root_cached *root;
 	struct rb_node *next;
@@ -1758,7 +1761,7 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
-		if (cb && cb(n))
+		if (cb && cb(n, cb_arg))
 			continue;
 
 		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain);
@@ -1772,7 +1775,8 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	}
 }
 
-void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg)
 {
 	bool use_callchain;
 
@@ -1783,18 +1787,23 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
 
 	use_callchain |= symbol_conf.show_branchflag_count;
 
-	output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
+	output_resort(evsel__hists(evsel), prog, use_callchain, cb, cb_arg);
+}
+
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+{
+	return perf_evsel__output_resort_cb(evsel, prog, NULL, NULL);
 }
 
 void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
-	output_resort(hists, prog, symbol_conf.use_callchain, NULL);
+	output_resort(hists, prog, symbol_conf.use_callchain, NULL, NULL);
 }
 
 void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
 			     hists__resort_cb_t cb)
 {
-	output_resort(hists, prog, symbol_conf.use_callchain, cb);
+	output_resort(hists, prog, symbol_conf.use_callchain, cb, NULL);
 }
 
 static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 08267af7439c8..4af27fbab24f5 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -2,9 +2,9 @@
 #ifndef __PERF_HIST_H
 #define __PERF_HIST_H
 
+#include <linux/rbtree.h>
 #include <linux/types.h>
 #include <pthread.h>
-#include "callchain.h"
 #include "evsel.h"
 #include "header.h"
 #include "color.h"
@@ -13,6 +13,9 @@
 struct hist_entry;
 struct hist_entry_ops;
 struct addr_location;
+struct map_symbol;
+struct mem_info;
+struct branch_info;
 struct symbol;
 
 enum hist_filter {
@@ -160,8 +163,10 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
-typedef int (*hists__resort_cb_t)(struct hist_entry *he);
+typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg);
 
+void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg);
 void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index ee6ca65f81f47..0c0180c67574d 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -27,6 +27,8 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "session.h"
 #include "util.h"
 #include "thread.h"
@@ -142,7 +144,7 @@ static int intel_bts_lost(struct intel_bts *bts, struct perf_sample *sample)
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
 			     INTEL_BTS_ERR_LOST, sample->cpu, sample->pid,
-			     sample->tid, 0, "Lost trace data");
+			     sample->tid, 0, "Lost trace data", sample->time);
 
 	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
 	if (err)
@@ -372,7 +374,7 @@ static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
 			     INTEL_BTS_ERR_NOINSN, cpu, pid, tid, ip,
-			     "Failed to get instruction");
+			     "Failed to get instruction", 0);
 
 	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
 	if (err)
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 4503f3ca45ab4..6e03db142091b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -26,6 +26,7 @@
 
 #include "../cache.h"
 #include "../util.h"
+#include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
 #include "intel-pt-pkt-decoder.h"
@@ -867,7 +868,7 @@ static int intel_pt_get_next_packet(struct intel_pt_decoder *decoder)
 
 		ret = intel_pt_get_packet(decoder->buf, decoder->len,
 					  &decoder->packet);
-		if (ret == INTEL_PT_NEED_MORE_BYTES &&
+		if (ret == INTEL_PT_NEED_MORE_BYTES && BITS_PER_LONG == 32 &&
 		    decoder->len < INTEL_PT_PKT_MAX_SZ && !decoder->next_buf) {
 			ret = intel_pt_get_split_packet(decoder);
 			if (ret < 0)
@@ -1394,7 +1395,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 {
 	intel_pt_log("ERROR: Buffer overflow\n");
 	intel_pt_clear_tx_flags(decoder);
-	decoder->cbr = 0;
 	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
@@ -2575,6 +2575,34 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 	}
 }
 
+#define MAX_PADDING (PERF_AUXTRACE_RECORD_ALIGNMENT - 1)
+
+/**
+ * adj_for_padding - adjust overlap to account for padding.
+ * @buf_b: second buffer
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ *
+ * @buf_a might have up to 7 bytes of padding appended. Adjust the overlap
+ * accordingly.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts
+ */
+static unsigned char *adj_for_padding(unsigned char *buf_b,
+				      unsigned char *buf_a, size_t len_a)
+{
+	unsigned char *p = buf_b - MAX_PADDING;
+	unsigned char *q = buf_a + len_a - MAX_PADDING;
+	int i;
+
+	for (i = MAX_PADDING; i; i--, p++, q++) {
+		if (*p != *q)
+			break;
+	}
+
+	return p;
+}
+
 /**
  * intel_pt_find_overlap_tsc - determine start of non-overlapped trace data
  *                             using TSC.
@@ -2625,8 +2653,11 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 
 			/* Same TSC, so buffers are consecutive */
 			if (!cmp && rem_b >= rem_a) {
+				unsigned char *start;
+
 				*consecutive = true;
-				return buf_b + len_b - (rem_b - rem_a);
+				start = buf_b + len_b - (rem_b - rem_a);
+				return adj_for_padding(start, buf_a, len_a);
 			}
 			if (cmp < 0)
 				return buf_b; /* tsc_a < tsc_b => no overlap */
@@ -2689,7 +2720,7 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		found = memmem(buf_a, len_a, buf_b, len_a);
 		if (found) {
 			*consecutive = true;
-			return buf_b + len_a;
+			return adj_for_padding(buf_b + len_a, buf_a, len_a);
 		}
 
 		/* Try again at next PSB in buffer 'a' */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 2e72373ec6df6..3b497bab43241 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1411,7 +1411,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
-				pid_t pid, pid_t tid, u64 ip)
+				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
 	union perf_event event;
 	char msg[MAX_AUXTRACE_ERROR_MSG];
@@ -1420,7 +1420,7 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 	intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
-			     code, cpu, pid, tid, ip, msg);
+			     code, cpu, pid, tid, ip, msg, timestamp);
 
 	err = perf_session__deliver_synth_event(pt->session, &event, NULL);
 	if (err)
@@ -1430,6 +1430,18 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 	return err;
 }
 
+static int intel_ptq_synth_error(struct intel_pt_queue *ptq,
+				 const struct intel_pt_state *state)
+{
+	struct intel_pt *pt = ptq->pt;
+	u64 tm = ptq->timestamp;
+
+	tm = pt->timeless_decoding ? 0 : tsc_to_perf_time(tm, &pt->tc);
+
+	return intel_pt_synth_error(pt, state->err, ptq->cpu, ptq->pid,
+				    ptq->tid, state->from_ip, tm);
+}
+
 static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
 {
 	struct auxtrace_queue *queue;
@@ -1676,10 +1688,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {
-				err = intel_pt_synth_error(pt, state->err,
-							   ptq->cpu, ptq->pid,
-							   ptq->tid,
-							   state->from_ip);
+				err = intel_ptq_synth_error(ptq, state);
 				if (err)
 					return err;
 			}
@@ -1804,7 +1813,7 @@ static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid,
 static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
 {
 	return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
-				    sample->pid, sample->tid, 0);
+				    sample->pid, sample->tid, 0, sample->time);
 }
 
 static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 7b1f065675217..1403dec189b4e 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -3,12 +3,13 @@
 #define __PERF_KVM_STAT_H
 
 #include "../perf.h"
-#include "evsel.h"
-#include "evlist.h"
-#include "session.h"
 #include "tool.h"
 #include "stat.h"
 
+struct perf_evsel;
+struct perf_evlist;
+struct perf_session;
+
 struct event_key {
 	#define INVALID_KEY     (~0ULL)
 	u64 key;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 66f019fdc5102..61959aba7e270 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -10,6 +10,7 @@
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "symbol.h"
 #include "sort.h"
 #include "strlist.h"
 #include "thread.h"
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e2f3df45410ac..f70ab98a7bde5 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,7 +4,7 @@
 
 #include <sys/types.h>
 #include <linux/rbtree.h>
-#include "map.h"
+#include "map_groups.h"
 #include "dso.h"
 #include "event.h"
 #include "rwsem.h"
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index cf407cc9d9152..fbeb0c6efaa6e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -557,6 +557,12 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 	refcount_set(&mg->refcnt, 1);
 }
 
+void map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	maps__insert(&mg->maps, map);
+	map->groups = mg;
+}
+
 static void __maps__purge(struct maps *maps)
 {
 	struct rb_root *root = &maps->entries;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 09282aa45c80b..0e20749f2c55d 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,12 +6,10 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include <pthread.h>
 #include <stdio.h>
 #include <string.h>
 #include <stdbool.h>
 #include <linux/types.h>
-#include "rwsem.h"
 
 struct dso;
 struct ip_callchain;
@@ -48,38 +46,7 @@ struct map {
 	refcount_t		refcnt;
 };
 
-#define KMAP_NAME_LEN 256
-
-struct kmap {
-	struct ref_reloc_sym	*ref_reloc_sym;
-	struct map_groups	*kmaps;
-	char			name[KMAP_NAME_LEN];
-};
-
-struct maps {
-	struct rb_root	 entries;
-	struct rb_root	 names;
-	struct rw_semaphore lock;
-};
-
-struct map_groups {
-	struct maps	 maps;
-	struct machine	 *machine;
-	refcount_t	 refcnt;
-};
-
-struct map_groups *map_groups__new(struct machine *machine);
-void map_groups__delete(struct map_groups *mg);
-bool map_groups__empty(struct map_groups *mg);
-
-static inline struct map_groups *map_groups__get(struct map_groups *mg)
-{
-	if (mg)
-		refcount_inc(&mg->refcnt);
-	return mg;
-}
-
-void map_groups__put(struct map_groups *mg);
+struct kmap;
 
 struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
@@ -174,18 +141,7 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
-struct srccode_state {
-	char *srcfile;
-	unsigned line;
-};
-
-static inline void srccode_state_init(struct srccode_state *state)
-{
-	state->srcfile = NULL;
-	state->line = 0;
-}
-
-void srccode_state_free(struct srccode_state *state);
+struct srccode_state;
 
 int map__fprintf_srccode(struct map *map, u64 addr,
 			 FILE *fp, struct srccode_state *state);
@@ -198,61 +154,9 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-void maps__insert(struct maps *maps, struct map *map);
-void maps__remove(struct maps *maps, struct map *map);
-struct map *maps__find(struct maps *maps, u64 addr);
-struct map *maps__first(struct maps *maps);
-struct map *map__next(struct map *map);
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-                                         struct map **mapp);
-void map_groups__init(struct map_groups *mg, struct machine *machine);
-void map_groups__exit(struct map_groups *mg);
-int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent);
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
-
 int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 				    u64 addr);
 
-static inline void map_groups__insert(struct map_groups *mg, struct map *map)
-{
-	maps__insert(&mg->maps, map);
-	map->groups = mg;
-}
-
-static inline void map_groups__remove(struct map_groups *mg, struct map *map)
-{
-	maps__remove(&mg->maps, map);
-}
-
-static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
-{
-	return maps__find(&mg->maps, addr);
-}
-
-struct map *map_groups__first(struct map_groups *mg);
-
-static inline struct map *map_groups__next(struct map *map)
-{
-	return map__next(map);
-}
-
-struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       u64 addr, struct map **mapp);
-
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       const char *name,
-					       struct map **mapp);
-
-struct addr_map_symbol;
-
-int map_groups__find_ams(struct addr_map_symbol *ams);
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   FILE *fp);
-
-struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
-
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
 
diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h
new file mode 100644
index 0000000000000..4dcda33e0fdf7
--- /dev/null
+++ b/tools/perf/util/map_groups.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_MAP_GROUPS_H
+#define __PERF_MAP_GROUPS_H
+
+#include <linux/refcount.h>
+#include <linux/rbtree.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include "rwsem.h"
+
+struct ref_reloc_sym;
+struct machine;
+struct map;
+struct thread;
+
+struct maps {
+	struct rb_root      entries;
+	struct rb_root	    names;
+	struct rw_semaphore lock;
+};
+
+void maps__insert(struct maps *maps, struct map *map);
+void maps__remove(struct maps *maps, struct map *map);
+struct map *maps__find(struct maps *maps, u64 addr);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp);
+
+struct map_groups {
+	struct maps	 maps;
+	struct machine	 *machine;
+	refcount_t	 refcnt;
+};
+
+#define KMAP_NAME_LEN 256
+
+struct kmap {
+	struct ref_reloc_sym *ref_reloc_sym;
+	struct map_groups    *kmaps;
+	char		     name[KMAP_NAME_LEN];
+};
+
+struct map_groups *map_groups__new(struct machine *machine);
+void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
+
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
+{
+	if (mg)
+		refcount_inc(&mg->refcnt);
+	return mg;
+}
+
+void map_groups__put(struct map_groups *mg);
+void map_groups__init(struct map_groups *mg, struct machine *machine);
+void map_groups__exit(struct map_groups *mg);
+int map_groups__clone(struct thread *thread, struct map_groups *parent);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
+
+void map_groups__insert(struct map_groups *mg, struct map *map);
+
+static inline void map_groups__remove(struct map_groups *mg, struct map *map)
+{
+	maps__remove(&mg->maps, map);
+}
+
+static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
+{
+	return maps__find(&mg->maps, addr);
+}
+
+struct map *map_groups__first(struct map_groups *mg);
+
+static inline struct map *map_groups__next(struct map *map)
+{
+	return map__next(map);
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp);
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp);
+
+struct addr_map_symbol;
+
+int map_groups__find_ams(struct addr_map_symbol *ams);
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp);
+
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
+
+#endif // __PERF_MAP_GROUPS_H
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
new file mode 100644
index 0000000000000..5a1aed9f6bb44
--- /dev/null
+++ b/tools/perf/util/map_symbol.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_MAP_SYMBOL
+#define __PERF_MAP_SYMBOL 1
+
+#include <linux/types.h>
+
+struct map;
+struct symbol;
+
+struct map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+};
+
+struct addr_map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+	u64	      al_addr;
+	u64	      phys_addr;
+};
+#endif // __PERF_MAP_SYMBOL
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 8fc39311a30dc..cdc7740fc1819 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,6 +10,9 @@
 #include <sys/mman.h>
 #include <inttypes.h>
 #include <asm/bug.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
 #include "debug.h"
 #include "event.h"
 #include "mmap.h"
@@ -154,9 +157,72 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
 }
 
 #ifdef HAVE_AIO_SUPPORT
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
+{
+	map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+				  MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+	if (map->aio.data[idx] == MAP_FAILED) {
+		map->aio.data[idx] = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int idx)
+{
+	if (map->aio.data[idx]) {
+		munmap(map->aio.data[idx], perf_mmap__mmap_len(map));
+		map->aio.data[idx] = NULL;
+	}
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affinity)
+{
+	void *data;
+	size_t mmap_len;
+	unsigned long node_mask;
+
+	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+		data = map->aio.data[idx];
+		mmap_len = perf_mmap__mmap_len(map);
+		node_mask = 1UL << cpu__get_node(cpu);
+		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
+				data, data + mmap_len, cpu__get_node(cpu));
+			return -1;
+		}
+	}
+
+	return 0;
+}
+#else
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
+{
+	map->aio.data[idx] = malloc(perf_mmap__mmap_len(map));
+	if (map->aio.data[idx] == NULL)
+		return -1;
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int idx)
+{
+	zfree(&(map->aio.data[idx]));
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int idx __maybe_unused,
+		int cpu __maybe_unused, int affinity __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
 {
-	int delta_max, i, prio;
+	int delta_max, i, prio, ret;
 
 	map->aio.nr_cblocks = mp->nr_cblocks;
 	if (map->aio.nr_cblocks) {
@@ -177,11 +243,14 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
 		}
 		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
 		for (i = 0; i < map->aio.nr_cblocks; ++i) {
-			map->aio.data[i] = malloc(perf_mmap__mmap_len(map));
-			if (!map->aio.data[i]) {
+			ret = perf_mmap__aio_alloc(map, i);
+			if (ret == -1) {
 				pr_debug2("failed to allocate data buffer area, error %m");
 				return -1;
 			}
+			ret = perf_mmap__aio_bind(map, i, map->cpu, mp->affinity);
+			if (ret == -1)
+				return -1;
 			/*
 			 * Use cblock.aio_fildes value different from -1
 			 * to denote started aio write operation on the
@@ -210,7 +279,7 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
 	int i;
 
 	for (i = 0; i < map->aio.nr_cblocks; ++i)
-		zfree(&map->aio.data[i]);
+		perf_mmap__aio_free(map, i);
 	if (map->aio.data)
 		zfree(&map->aio.data);
 	zfree(&map->aio.cblocks);
@@ -314,6 +383,32 @@ void perf_mmap__munmap(struct perf_mmap *map)
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
+static void build_node_mask(int node, cpu_set_t *mask)
+{
+	int c, cpu, nr_cpus;
+	const struct cpu_map *cpu_map = NULL;
+
+	cpu_map = cpu_map__online();
+	if (!cpu_map)
+		return;
+
+	nr_cpus = cpu_map__nr(cpu_map);
+	for (c = 0; c < nr_cpus; c++) {
+		cpu = cpu_map->map[c]; /* map c index to online cpu index */
+		if (cpu__get_node(cpu) == node)
+			CPU_SET(cpu, mask);
+	}
+}
+
+static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp)
+{
+	CPU_ZERO(&map->affinity_mask);
+	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
+		build_node_mask(cpu__get_node(map->cpu), &map->affinity_mask);
+	else if (mp->affinity == PERF_AFFINITY_CPU)
+		CPU_SET(map->cpu, &map->affinity_mask);
+}
+
 int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
 	/*
@@ -343,6 +438,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
 	map->fd = fd;
 	map->cpu = cpu;
 
+	perf_mmap__setup_affinity_mask(map, mp);
+
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
 		return -1;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index aeb6942fdb00c..e566c19b242b6 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -38,6 +38,7 @@ struct perf_mmap {
 		int		 nr_cblocks;
 	} aio;
 #endif
+	cpu_set_t	affinity_mask;
 };
 
 /*
@@ -69,7 +70,7 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-	int			    prot, mask, nr_cblocks;
+	int			    prot, mask, nr_cblocks, affinity;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 11a2347406320..51d437f55d18c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -29,8 +29,6 @@ struct perf_pmu_format {
 	struct list_head list;
 };
 
-#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
-
 int perf_pmu_parse(struct list_head *list, char *name);
 extern FILE *perf_pmu_in;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 76fecec7b3f91..47253c3daf55b 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -6,9 +6,10 @@
 #include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
-#include "evsel.h"
 #include "parse-events.h"
 
+struct perf_evsel_config_term;
+
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
 	PERF_PMU_FORMAT_VALUE_CONFIG1,
@@ -16,6 +17,7 @@ enum {
 };
 
 #define PERF_PMU_FORMAT_BITS 64
+#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
 
 struct perf_event_attr;
 
@@ -29,7 +31,6 @@ struct perf_pmu {
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
 	struct list_head list;    /* ELEM */
-	int (*set_drv_config)	(struct perf_evsel_config_term *term);
 };
 
 struct perf_pmu_info {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 4008f0cc36e56..0030f9b9bf7e2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -41,6 +41,8 @@
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
 #include "thread.h"
 #include <api/fs/fs.h>
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 835249c77f568..d9525d220db17 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -819,7 +819,7 @@ static int s390_cpumsf_process_queues(struct s390_cpumsf *sf, u64 timestamp)
 }
 
 static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
-				   pid_t pid, pid_t tid, u64 ip)
+				   pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 	union perf_event event;
@@ -827,7 +827,7 @@ static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
 
 	strncpy(msg, "Lost Auxiliary Trace Buffer", sizeof(msg) - 1);
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
-			     code, cpu, pid, tid, ip, msg);
+			     code, cpu, pid, tid, ip, msg, timestamp);
 
 	err = perf_session__deliver_synth_event(sf->session, &event, NULL);
 	if (err)
@@ -839,7 +839,8 @@ static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
 static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample)
 {
 	return s390_cpumsf_synth_error(sf, 1, sample->cpu,
-				       sample->pid, sample->tid, 0);
+				       sample->pid, sample->tid, 0,
+				       sample->time);
 }
 
 static int
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b93f36b887b5f..5f06378a482b8 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -37,6 +37,8 @@
 #include "../../perf.h"
 #include "../callchain.h"
 #include "../machine.h"
+#include "../map.h"
+#include "../symbol.h"
 #include "../thread.h"
 #include "../event.h"
 #include "../trace-event.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7059d1be2d098..0e17db41b49bc 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -44,6 +44,8 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../call-path.h"
+#include "map.h"
+#include "symbol.h"
 #include "thread_map.h"
 #include "cpumap.h"
 #include "print_binary.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 24fd62528a338..18fb9c8cbf9c1 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -13,6 +13,8 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "memswap.h"
+#include "map.h"
+#include "symbol.h"
 #include "session.h"
 #include "tool.h"
 #include "sort.h"
@@ -701,7 +703,10 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
 	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
 	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
 	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.fmt  = bswap_32(event->auxtrace_error.fmt);
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+	if (event->auxtrace_error.fmt)
+		event->auxtrace_error.time = bswap_64(event->auxtrace_error.time);
 }
 
 static void perf_event__thread_map_swap(union perf_event *event,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index d3ffc18424b5c..5b5a167b43ce5 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -53,9 +53,14 @@ ext_sources = [f.strip() for f in open('util/python-ext-sources')
 # use full paths with source files
 ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
 
+extra_libraries = []
+if '-DHAVE_LIBNUMA_SUPPORT' in cflags:
+    extra_libraries = [ 'numa' ]
+
 perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
+		  libraries = extra_libraries,
 		  extra_compile_args = cflags,
 		  extra_objects = [libtraceevent, libapikfs],
                  )
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 6c1a83768eb0a..2b6c1ccb878cc 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include "evsel.h"
@@ -428,8 +429,6 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 {
 
 	struct symbol *sym = he->ms.sym;
-	struct map *map = he->ms.map;
-	struct perf_evsel *evsel = hists_to_evsel(he->hists);
 	struct annotation *notes;
 	double ipc = 0.0, coverage = 0.0;
 	char tmp[64];
@@ -437,11 +436,6 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 	if (!sym)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 
-	if (!sym->annotate2 && symbol__annotate2(sym, map, evsel,
-		&annotation__default_options, NULL) < 0) {
-		return 0;
-	}
-
 	notes = symbol__annotation(sym);
 
 	if (notes->hit_cycles)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index dd63128764924..2fbee0b1011c6 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -9,7 +9,8 @@
 #include <linux/list.h>
 #include "cache.h"
 #include <linux/rbtree.h>
-#include "symbol.h"
+#include "map_symbol.h"
+#include "symbol_conf.h"
 #include "string.h"
 #include "callchain.h"
 #include "values.h"
diff --git a/tools/perf/util/srccode.h b/tools/perf/util/srccode.h
index e500a746d5f11..1b5ed769779cc 100644
--- a/tools/perf/util/srccode.h
+++ b/tools/perf/util/srccode.h
@@ -1,6 +1,19 @@
 #ifndef SRCCODE_H
 #define SRCCODE_H 1
 
+struct srccode_state {
+	char	 *srcfile;
+	unsigned line;
+};
+
+static inline void srccode_state_init(struct srccode_state *state)
+{
+	state->srcfile = NULL;
+	state->line    = 0;
+}
+
+void srccode_state_free(struct srccode_state *state);
+
 /* Result is not 0 terminated */
 char *find_sourceline(char *fn, unsigned line, int *lenp);
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index dca7dfae69ad2..4ad106a5f2c06 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,8 @@
 #include <unistd.h>
 #include <inttypes.h>
 
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
 #include "demangle-java.h"
 #include "demangle-rust.h"
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index bcbcbd6104602..758bf5f74e6ee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -17,6 +17,7 @@
 #include "util.h"
 #include "debug.h"
 #include "machine.h"
+#include "map.h"
 #include "symbol.h"
 #include "strlist.h"
 #include "intlist.h"
@@ -717,6 +718,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct
 		}
 
 		pos->start -= curr_map->start - curr_map->pgoff;
+		if (pos->end > curr_map->end)
+			pos->end = curr_map->end;
 		if (pos->end)
 			pos->end -= curr_map->start - curr_map->pgoff;
 		symbols__insert(&curr_map->dso->symbols, pos);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 56e2bcb907cc2..9a8fe012910a7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -8,6 +8,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
+#include "map_symbol.h"
 #include "branch.h"
 #include "path.h"
 #include "symbol_conf.h"
@@ -115,19 +116,6 @@ struct ref_reloc_sym {
 	u64		unrelocated_addr;
 };
 
-struct map_symbol {
-	struct map    *map;
-	struct symbol *sym;
-};
-
-struct addr_map_symbol {
-	struct map    *map;
-	struct symbol *sym;
-	u64	      addr;
-	u64	      al_addr;
-	u64	      phys_addr;
-};
-
 struct branch_info {
 	struct addr_map_symbol from;
 	struct addr_map_symbol to;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index d52f27f373ce5..f52c0f90915d1 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -38,6 +38,7 @@
  * @cp: call path
  * @no_call: a 'call' was not seen
  * @trace_end: a 'call' but trace ended
+ * @non_call: a branch but not a 'call' to the start of a different symbol
  */
 struct thread_stack_entry {
 	u64 ret_addr;
@@ -47,6 +48,7 @@ struct thread_stack_entry {
 	struct call_path *cp;
 	bool no_call;
 	bool trace_end;
+	bool non_call;
 };
 
 /**
@@ -268,6 +270,8 @@ static int thread_stack__call_return(struct thread *thread,
 		cr.flags |= CALL_RETURN_NO_CALL;
 	if (no_return)
 		cr.flags |= CALL_RETURN_NO_RETURN;
+	if (tse->non_call)
+		cr.flags |= CALL_RETURN_NON_CALL;
 
 	return crp->process(&cr, crp->data);
 }
@@ -493,6 +497,9 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	struct thread_stack_entry *tse;
 	int err;
 
+	if (!cp)
+		return -ENOMEM;
+
 	if (ts->cnt == ts->sz) {
 		err = thread_stack__grow(ts);
 		if (err)
@@ -507,6 +514,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->cp = cp;
 	tse->no_call = no_call;
 	tse->trace_end = trace_end;
+	tse->non_call = false;
 
 	return 0;
 }
@@ -528,14 +536,16 @@ static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
 							 timestamp, ref, false);
 	}
 
-	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr &&
+	    !ts->stack[ts->cnt - 1].non_call) {
 		return thread_stack__call_return(thread, ts, --ts->cnt,
 						 timestamp, ref, false);
 	} else {
 		size_t i = ts->cnt - 1;
 
 		while (i--) {
-			if (ts->stack[i].ret_addr != ret_addr)
+			if (ts->stack[i].ret_addr != ret_addr ||
+			    ts->stack[i].non_call)
 				continue;
 			i += 1;
 			while (ts->cnt > i) {
@@ -576,8 +586,6 @@ static int thread_stack__bottom(struct thread_stack *ts,
 
 	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
 	return thread_stack__push_cp(ts, ip, sample->time, ref, cp,
 				     true, false);
@@ -590,36 +598,36 @@ static int thread_stack__no_call_return(struct thread *thread,
 					struct addr_location *to_al, u64 ref)
 {
 	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *root = &cpr->call_path;
+	struct symbol *fsym = from_al->sym;
+	struct symbol *tsym = to_al->sym;
 	struct call_path *cp, *parent;
 	u64 ks = ts->kernel_start;
+	u64 addr = sample->addr;
+	u64 tm = sample->time;
+	u64 ip = sample->ip;
 	int err;
 
-	if (sample->ip >= ks && sample->addr < ks) {
+	if (ip >= ks && addr < ks) {
 		/* Return to userspace, so pop all kernel addresses */
 		while (thread_stack__in_kernel(ts)) {
 			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							sample->time, ref,
-							true);
+							tm, ref, true);
 			if (err)
 				return err;
 		}
 
 		/* If the stack is empty, push the userspace address */
 		if (!ts->cnt) {
-			cp = call_path__findnew(cpr, &cpr->call_path,
-						to_al->sym, sample->addr,
-						ts->kernel_start);
-			if (!cp)
-				return -ENOMEM;
-			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true, false);
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+			return thread_stack__push_cp(ts, 0, tm, ref, cp, true,
+						     false);
 		}
-	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+	} else if (thread_stack__in_kernel(ts) && ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
 		while (thread_stack__in_kernel(ts)) {
 			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							sample->time, ref,
-							true);
+							tm, ref, true);
 			if (err)
 				return err;
 		}
@@ -628,21 +636,16 @@ static int thread_stack__no_call_return(struct thread *thread,
 	if (ts->cnt)
 		parent = ts->stack[ts->cnt - 1].cp;
 	else
-		parent = &cpr->call_path;
+		parent = root;
 
 	/* This 'return' had no 'call', so push and pop top of stack */
-	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
-				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
+	cp = call_path__findnew(cpr, parent, fsym, ip, ks);
 
-	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true, false);
+	err = thread_stack__push_cp(ts, addr, tm, ref, cp, true, false);
 	if (err)
 		return err;
 
-	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
-				    to_al->sym);
+	return thread_stack__pop_cp(thread, ts, addr, tm, ref, tsym);
 }
 
 static int thread_stack__trace_begin(struct thread *thread,
@@ -680,8 +683,6 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 
 	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
 	ret_addr = sample->ip + sample->insn_len;
 
@@ -745,8 +746,6 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
 					to_al->sym, sample->addr,
 					ts->kernel_start);
-		if (!cp)
-			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
 					    cp, false, trace_end);
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
@@ -765,6 +764,25 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
 	} else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
 		err = thread_stack__trace_end(ts, sample, ref);
+	} else if (sample->flags & PERF_IP_FLAG_BRANCH &&
+		   from_al->sym != to_al->sym && to_al->sym &&
+		   to_al->addr == to_al->sym->start) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+
+		/*
+		 * The compiler might optimize a call/ret combination by making
+		 * it a jmp. Make that visible by recording on the stack a
+		 * branch to the start of a different symbol. Note, that means
+		 * when a ret pops the stack, all jmps must be popped off first.
+		 */
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		err = thread_stack__push_cp(ts, 0, sample->time, ref, cp, false,
+					    false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
 	}
 
 	return err;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 1f626f4a1c40f..b7c04e19ad417 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -35,10 +35,13 @@ struct call_path;
  *
  * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
  * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ * CALL_RETURN_NON_CALL: a branch but not a 'call' to the start of a different
+ *                       symbol
  */
 enum {
 	CALL_RETURN_NO_CALL	= 1 << 0,
 	CALL_RETURN_NO_RETURN	= 1 << 1,
+	CALL_RETURN_NON_CALL	= 1 << 2,
 };
 
 /**
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index c83372329f891..4c179fef442d6 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -12,6 +12,7 @@
 #include "debug.h"
 #include "namespaces.h"
 #include "comm.h"
+#include "symbol.h"
 #include "unwind.h"
 
 #include <api/fs/fs.h>
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index f3c939150f909..8276ffeec5565 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,14 +5,17 @@
 #include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
-#include "symbol.h"
-#include "map.h"
+#include "srccode.h"
+#include "symbol_conf.h"
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
 
+struct addr_location;
+struct map;
 struct namespaces_event;
 struct thread_stack;
 struct unwind_libunwind_ops;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5eff9bfc57583..407d0167b9420 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -8,6 +8,8 @@
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "thread.h"
 #include <linux/types.h>
 #include "event.h"
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 79f521a552cf5..f3c666a84e4d5 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -34,6 +34,7 @@
 #include "session.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "map.h"
 #include "symbol.h"
 #include "util.h"
 #include "debug.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index b029a5e9ae499..9778b3133b778 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "unwind.h"
+#include "map.h"
 #include "thread.h"
 #include "session.h"
 #include "debug.h"
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3702cba11d7dd..5031b7b22bbd8 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,6 +11,7 @@
 
 #include "vdso.h"
 #include "util.h"
+#include "map.h"
 #include "symbol.h"
 #include "machine.h"
 #include "thread.h"