Merge tag 'perf-core-for-mingo-4.16-20180117' 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:

- Fix various per event 'max-stack' and 'call-graph=dwarf' issues,
  mostly in 'perf trace', allowing to use 'perf trace --call-graph' with
  'dwarf' and 'fp' to setup the callgraph details for the syscall events
  and make that apply to other events, whilhe allowing to override that on
  a per-event basis, using '-e sched:*switch/call-graph=dwarf/' for
  instance (Arnaldo Carvalho de Melo)

- Improve the --time percent support in record/report/script (Jin Yao)

- Fix copyfile_offset update of output offset (Jiri Olsa)

- Add python script to profile and resolve physical mem type (Kan Liang)

- Add ARM Statistical Profiling Extensions (SPE) support (Kim Phillips)

- Remove trailing semicolon in the evlist code (Luis de Bethencourt)

- Fix incorrect handling of type _TERM_DRV_CFG (Mathieu Poirier)

- Use asprintf when possible in libtraceevent (Federico Vaga)

- Fix bad force_token escape sequence in libtraceevent (Michael Sartain)

- Add UL suffix to MISSING_EVENTS in libtraceevent (Michael Sartain)

- value of unknown symbolic fields in libtraceevent (Jan Kiszka)

- libtraceevent updates: (Steven Rostedt)
  o Show value of flags that have not been parsed
  o Simplify pointer print logic and fix %pF
  o Handle new pointer processing of bprint strings
  o Show contents (in hex) of data of unrecognized type records
  o Fix get_field_str() for dynamic strings

- Add missing break in FALSE case of pevent_filter_clear_trivial() (Taeung Song)

- Fix failed memory allocation for get_cpuid_str (Thomas Richter)

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

35 files changed, 1465 insertions, 130 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 7ce724fc0544..e5f2acbb70cc 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1094,7 +1094,7 @@ static enum event_type __read_token(char **tok)
 		if (strcmp(*tok, "LOCAL_PR_FMT") == 0) {
 			free(*tok);
 			*tok = NULL;
-			return force_token("\"\%s\" ", tok);
+			return force_token("\"%s\" ", tok);
 		} else if (strcmp(*tok, "STA_PR_FMT") == 0) {
 			free(*tok);
 			*tok = NULL;
@@ -3970,6 +3970,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 				val &= ~fval;
 			}
 		}
+		if (val) {
+			if (print && arg->flags.delim)
+				trace_seq_puts(s, arg->flags.delim);
+			trace_seq_printf(s, "0x%llx", val);
+		}
 		break;
 	case PRINT_SYMBOL:
 		val = eval_num_arg(data, size, event, arg->symbol.field);
@@ -3980,6 +3985,8 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 				break;
 			}
 		}
+		if (!flag)
+			trace_seq_printf(s, "0x%llx", val);
 		break;
 	case PRINT_HEX:
 	case PRINT_HEX_STR:
@@ -4293,6 +4300,26 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				goto process_again;
 			case 'p':
 				ls = 1;
+				if (isalnum(ptr[1])) {
+					ptr++;
+					/* Check for special pointers */
+					switch (*ptr) {
+					case 's':
+					case 'S':
+					case 'f':
+					case 'F':
+						break;
+					default:
+						/*
+						 * Older kernels do not process
+						 * dereferenced pointers.
+						 * Only process if the pointer
+						 * value is a printable.
+						 */
+						if (isprint(*(char *)bptr))
+							goto process_string;
+					}
+				}
 				/* fall through */
 			case 'd':
 			case 'u':
@@ -4345,6 +4372,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 
 				break;
 			case 's':
+ process_string:
 				arg = alloc_arg();
 				if (!arg) {
 					do_warning_event(event, "%s(%d): not enough memory!",
@@ -4949,21 +4977,27 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				else
 					ls = 2;
 
-				if (*(ptr+1) == 'F' || *(ptr+1) == 'f' ||
-				    *(ptr+1) == 'S' || *(ptr+1) == 's') {
+				if (isalnum(ptr[1]))
 					ptr++;
+
+				if (arg->type == PRINT_BSTRING) {
+					trace_seq_puts(s, arg->string.string);
+					break;
+				}
+
+				if (*ptr == 'F' || *ptr == 'f' ||
+				    *ptr == 'S' || *ptr == 's') {
 					show_func = *ptr;
-				} else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') {
-					print_mac_arg(s, *(ptr+1), data, size, event, arg);
-					ptr++;
+				} else if (*ptr == 'M' || *ptr == 'm') {
+					print_mac_arg(s, *ptr, data, size, event, arg);
 					arg = arg->next;
 					break;
-				} else if (*(ptr+1) == 'I' || *(ptr+1) == 'i') {
+				} else if (*ptr == 'I' || *ptr == 'i') {
 					int n;
 
-					n = print_ip_arg(s, ptr+1, data, size, event, arg);
+					n = print_ip_arg(s, ptr, data, size, event, arg);
 					if (n > 0) {
-						ptr += n;
+						ptr += n - 1;
 						arg = arg->next;
 						break;
 					}
@@ -5532,8 +5566,14 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 
 	event = pevent_find_event_by_record(pevent, record);
 	if (!event) {
-		do_warning("ug! no event found for type %d",
-			   trace_parse_common_type(pevent, record->data));
+		int i;
+		int type = trace_parse_common_type(pevent, record->data);
+
+		do_warning("ug! no event found for type %d", type);
+		trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
+		for (i = 0; i < record->size; i++)
+			trace_seq_printf(s, " %02x",
+					 ((unsigned char *)record->data)[i]);
 		return;
 	}
 
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index a16756ae3526..d542cb60ca1a 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -120,12 +120,12 @@ char **traceevent_plugin_list_options(void)
 		for (op = reg->options; op->name; op++) {
 			char *alias = op->plugin_alias ? op->plugin_alias : op->file;
 			char **temp = list;
+			int ret;
 
-			name = malloc(strlen(op->name) + strlen(alias) + 2);
-			if (!name)
+			ret = asprintf(&name, "%s:%s", alias, op->name);
+			if (ret < 0)
 				goto err;
 
-			sprintf(name, "%s:%s", alias, op->name);
 			list = realloc(list, count + 2);
 			if (!list) {
 				list = temp;
@@ -290,17 +290,14 @@ load_plugin(struct pevent *pevent, const char *path,
 	const char *alias;
 	char *plugin;
 	void *handle;
+	int ret;
 
-	plugin = malloc(strlen(path) + strlen(file) + 2);
-	if (!plugin) {
+	ret = asprintf(&plugin, "%s/%s", path, file);
+	if (ret < 0) {
 		warning("could not allocate plugin memory\n");
 		return;
 	}
 
-	strcpy(plugin, path);
-	strcat(plugin, "/");
-	strcat(plugin, file);
-
 	handle = dlopen(plugin, RTLD_NOW | RTLD_GLOBAL);
 	if (!handle) {
 		warning("could not load plugin '%s'\n%s\n",
@@ -391,6 +388,7 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	char *home;
 	char *path;
 	char *envdir;
+	int ret;
 
 	if (pevent->flags & PEVENT_DISABLE_PLUGINS)
 		return;
@@ -421,16 +419,12 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	if (!home)
 		return;
 
-	path = malloc(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
-	if (!path) {
+	ret = asprintf(&path, "%s/%s", home, LOCAL_PLUGIN_DIR);
+	if (ret < 0) {
 		warning("could not allocate plugin memory\n");
 		return;
 	}
 
-	strcpy(path, home);
-	strcat(path, "/");
-	strcat(path, LOCAL_PLUGIN_DIR);
-
 	load_plugins_dir(pevent, suffix, path, load_plugin, data);
 
 	free(path);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index c94e3641b046..ca424b157e46 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -24,8 +24,8 @@
 
 #include "kbuffer.h"
 
-#define MISSING_EVENTS (1 << 31)
-#define MISSING_STORED (1 << 30)
+#define MISSING_EVENTS (1UL << 31)
+#define MISSING_STORED (1UL << 30)
 
 #define COMMIT_MASK ((1 << 27) - 1)
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 315df0a70265..431e8b309f6e 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -287,12 +287,10 @@ find_event(struct pevent *pevent, struct event_list **events,
 		sys_name = NULL;
 	}
 
-	reg = malloc(strlen(event_name) + 3);
-	if (reg == NULL)
+	ret = asprintf(&reg, "^%s$", event_name);
+	if (ret < 0)
 		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
-	sprintf(reg, "^%s$", event_name);
-
 	ret = regcomp(&ereg, reg, REG_ICASE|REG_NOSUB);
 	free(reg);
 
@@ -300,13 +298,12 @@ find_event(struct pevent *pevent, struct event_list **events,
 		return PEVENT_ERRNO__INVALID_EVENT_NAME;
 
 	if (sys_name) {
-		reg = malloc(strlen(sys_name) + 3);
-		if (reg == NULL) {
+		ret = asprintf(&reg, "^%s$", sys_name);
+		if (ret < 0) {
 			regfree(&ereg);
 			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 		}
 
-		sprintf(reg, "^%s$", sys_name);
 		ret = regcomp(&sreg, reg, REG_ICASE|REG_NOSUB);
 		free(reg);
 		if (ret) {
@@ -1634,6 +1631,7 @@ int pevent_filter_clear_trivial(struct event_filter *filter,
 		case FILTER_TRIVIAL_FALSE:
 			if (filter_type->filter->boolean.value)
 				continue;
+			break;
 		case FILTER_TRIVIAL_TRUE:
 			if (!filter_type->filter->boolean.value)
 				continue;
@@ -1879,17 +1877,25 @@ static const char *get_field_str(struct filter_arg *arg, struct pevent_record *r
 	struct pevent *pevent;
 	unsigned long long addr;
 	const char *val = NULL;
+	unsigned int size;
 	char hex[64];
 
 	/* If the field is not a string convert it */
 	if (arg->str.field->flags & FIELD_IS_STRING) {
 		val = record->data + arg->str.field->offset;
+		size = arg->str.field->size;
+
+		if (arg->str.field->flags & FIELD_IS_DYNAMIC) {
+			addr = *(unsigned int *)val;
+			val = record->data + (addr & 0xffff);
+			size = addr >> 16;
+		}
 
 		/*
 		 * We need to copy the data since we can't be sure the field
 		 * is null terminated.
 		 */
-		if (*(val + arg->str.field->size - 1)) {
+		if (*(val + size - 1)) {
 			/* copy it */
 			memcpy(arg->str.buffer, val, arg->str.field->size);
 			/* the buffer is already NULL terminated */
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 63d0db3184c9..907e505b6309 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -403,7 +403,7 @@ OPTIONS
 	to end of file.
 
 	Also support time percent with multiple time range. Time string is
-	'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10.
+	'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
 
 	For example:
 	Select the second 10% time slice:
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 806ec6391fd6..7730c1d2b5d3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -351,19 +351,19 @@ include::itrace.txt[]
 	to end of file.
 
 	Also support time percent with multipe time range. Time string is
-	'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. The maximum number of slices is 10.
+	'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
 
 	For example:
-	Select the second 10% time slice
+	Select the second 10% time slice:
 	perf script --time 10%/2
 
-	Select from 0% to 10% time slice
+	Select from 0% to 10% time slice:
 	perf script --time 0%-10%
 
-	Select the first and second 10% time slices
+	Select the first and second 10% time slices:
 	perf script --time 10%/1,10%/2
 
-	Select from 0% to 10% and 30% to 40% slices
+	Select from 0% to 10% and 30% to 40% slices:
 	perf script --time 0%-10%,30%-40%
 
 --max-blocks::
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 8edf2cb71564..2323581b157d 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -22,6 +22,42 @@
 #include "../../util/evlist.h"
 #include "../../util/pmu.h"
 #include "cs-etm.h"
+#include "arm-spe.h"
+
+static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err)
+{
+	struct perf_pmu **arm_spe_pmus = NULL;
+	int ret, i, nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	/* arm_spe_xxxxxxxxx\0 */
+	char arm_spe_pmu_name[sizeof(ARM_SPE_PMU_NAME) + 10];
+
+	arm_spe_pmus = zalloc(sizeof(struct perf_pmu *) * nr_cpus);
+	if (!arm_spe_pmus) {
+		pr_err("spes alloc failed\n");
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	for (i = 0; i < nr_cpus; i++) {
+		ret = sprintf(arm_spe_pmu_name, "%s%d", ARM_SPE_PMU_NAME, i);
+		if (ret < 0) {
+			pr_err("sprintf failed\n");
+			*err = -ENOMEM;
+			return NULL;
+		}
+
+		arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name);
+		if (arm_spe_pmus[*nr_spes]) {
+			pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n",
+				 __func__, __LINE__, *nr_spes,
+				 arm_spe_pmus[*nr_spes]->type,
+				 arm_spe_pmus[*nr_spes]->name);
+			(*nr_spes)++;
+		}
+	}
+
+	return arm_spe_pmus;
+}
 
 struct auxtrace_record
 *auxtrace_record__init(struct perf_evlist *evlist, int *err)
@@ -29,22 +65,51 @@ struct auxtrace_record
 	struct perf_pmu	*cs_etm_pmu;
 	struct perf_evsel *evsel;
 	bool found_etm = false;
+	bool found_spe = false;
+	static struct perf_pmu **arm_spe_pmus = NULL;
+	static int nr_spes = 0;
+	int i;
+
+	if (!evlist)
+		return NULL;
 
 	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
 
-	if (evlist) {
-		evlist__for_each_entry(evlist, evsel) {
-			if (cs_etm_pmu &&
-			    evsel->attr.type == cs_etm_pmu->type)
-				found_etm = true;
+	if (!arm_spe_pmus)
+		arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (cs_etm_pmu &&
+		    evsel->attr.type == cs_etm_pmu->type)
+			found_etm = true;
+
+		if (!nr_spes)
+			continue;
+
+		for (i = 0; i < nr_spes; i++) {
+			if (evsel->attr.type == arm_spe_pmus[i]->type) {
+				found_spe = true;
+				break;
+			}
 		}
 	}
 
+	if (found_etm && found_spe) {
+		pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n");
+		*err = -EOPNOTSUPP;
+		return NULL;
+	}
+
 	if (found_etm)
 		return cs_etm_record_init(err);
 
+#if defined(__aarch64__)
+	if (found_spe)
+		return arm_spe_recording_init(err, arm_spe_pmus[i]);
+#endif
+
 	/*
-	 * Clear 'err' even if we haven't found a cs_etm event - that way perf
+	 * Clear 'err' even if we haven't found an event - that way perf
 	 * record can still be used even if tracers aren't present.  The NULL
 	 * return value will take care of telling the infrastructure HW tracing
 	 * isn't available.
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index 98d67399a0d6..ac4dffc807b8 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -20,6 +20,7 @@
 #include <linux/perf_event.h>
 
 #include "cs-etm.h"
+#include "arm-spe.h"
 #include "../../util/pmu.h"
 
 struct perf_event_attr
@@ -30,7 +31,12 @@ struct perf_event_attr
 		/* 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);
+#endif
 	}
+
 #endif
 	return NULL;
 }
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index e04f6cdd6f32..c0b8dfef98ba 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -5,4 +5,5 @@ libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 
 libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
-			      ../../arm/util/cs-etm.o
+			      ../../arm/util/cs-etm.o \
+			      arm-spe.o
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
new file mode 100644
index 000000000000..1120e39c1b00
--- /dev/null
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <time.h>
+
+#include "../../util/cpumap.h"
+#include "../../util/evsel.h"
+#include "../../util/evlist.h"
+#include "../../util/session.h"
+#include "../../util/util.h"
+#include "../../util/pmu.h"
+#include "../../util/debug.h"
+#include "../../util/auxtrace.h"
+#include "../../util/arm-spe.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+
+struct arm_spe_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*arm_spe_pmu;
+	struct perf_evlist		*evlist;
+};
+
+static size_t
+arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+	return ARM_SPE_AUXTRACE_PRIV_SIZE;
+}
+
+static int arm_spe_info_fill(struct auxtrace_record *itr,
+			     struct perf_session *session,
+			     struct auxtrace_info_event *auxtrace_info,
+			     size_t priv_size)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+
+	if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->nr_mmaps)
+		return -EINVAL;
+
+	auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
+	auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type;
+
+	return 0;
+}
+
+static int arm_spe_recording_options(struct auxtrace_record *itr,
+				     struct perf_evlist *evlist,
+				     struct record_opts *opts)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+	struct perf_evsel *evsel, *arm_spe_evsel = NULL;
+	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+	struct perf_evsel *tracking_evsel;
+	int err;
+
+	sper->evlist = evlist;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == arm_spe_pmu->type) {
+			if (arm_spe_evsel) {
+				pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n");
+				return -EINVAL;
+			}
+			evsel->attr.freq = 0;
+			evsel->attr.sample_period = 1;
+			arm_spe_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	/* We are in full trace mode but '-m,xyz' wasn't specified */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for ARM SPE: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	perf_evlist__to_front(evlist, arm_spe_evsel);
+
+	perf_evsel__set_sample_bit(arm_spe_evsel, CPU);
+	perf_evsel__set_sample_bit(arm_spe_evsel, TIME);
+	perf_evsel__set_sample_bit(arm_spe_evsel, TID);
+
+	/* Add dummy event to keep tracking */
+	err = parse_events(evlist, "dummy:u", NULL);
+	if (err)
+		return err;
+
+	tracking_evsel = perf_evlist__last(evlist);
+	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->attr.freq = 0;
+	tracking_evsel->attr.sample_period = 1;
+	perf_evsel__set_sample_bit(tracking_evsel, TIME);
+	perf_evsel__set_sample_bit(tracking_evsel, CPU);
+	perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+	return 0;
+}
+
+static u64 arm_spe_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC_RAW, &ts);
+
+	return ts.tv_sec ^ ts.tv_nsec;
+}
+
+static void arm_spe_recording_free(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+
+	free(sper);
+}
+
+static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct arm_spe_recording *sper =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(sper->evlist, evsel) {
+		if (evsel->attr.type == sper->arm_spe_pmu->type)
+			return perf_evlist__enable_event_idx(sper->evlist,
+							     evsel, idx);
+	}
+	return -EINVAL;
+}
+
+struct auxtrace_record *arm_spe_recording_init(int *err,
+					       struct perf_pmu *arm_spe_pmu)
+{
+	struct arm_spe_recording *sper;
+
+	if (!arm_spe_pmu) {
+		*err = -ENODEV;
+		return NULL;
+	}
+
+	sper = zalloc(sizeof(struct arm_spe_recording));
+	if (!sper) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.recording_options = arm_spe_recording_options;
+	sper->itr.info_priv_size = arm_spe_info_priv_size;
+	sper->itr.info_fill = arm_spe_info_fill;
+	sper->itr.free = arm_spe_recording_free;
+	sper->itr.reference = arm_spe_reference;
+	sper->itr.read_finish = arm_spe_read_finish;
+	sper->itr.alignment = 0;
+
+	return &sper->itr;
+}
+
+struct perf_event_attr
+*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu)
+{
+	struct perf_event_attr *attr;
+
+	attr = zalloc(sizeof(struct perf_event_attr));
+	if (!attr) {
+		pr_err("arm_spe default config cannot allocate a perf_event_attr\n");
+		return NULL;
+	}
+
+	/*
+	 * If kernel driver doesn't advertise a minimum,
+	 * use max allowable by PMSIDR_EL1.INTERVAL
+	 */
+	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
+				  &attr->sample_period) != 1) {
+		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
+		attr->sample_period = 4096;
+	}
+
+	arm_spe_pmu->selectable = true;
+	arm_spe_pmu->is_uncore = false;
+
+	return attr;
+}
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index b626d2bad9f1..fb0d71afee8b 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -70,7 +70,7 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
-	if (__get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
+	if (buf && __get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
 		free(buf);
 		return NULL;
 	}
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index c0debc3f79b6..c0815a37fdb5 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2390,9 +2390,10 @@ static int setup_callchain(struct perf_evlist *evlist)
 	enum perf_call_graph_mode mode = CALLCHAIN_NONE;
 
 	if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-	    (sample_type & PERF_SAMPLE_STACK_USER))
+	    (sample_type & PERF_SAMPLE_STACK_USER)) {
 		mode = CALLCHAIN_DWARF;
-	else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		dwarf_callchain_users = true;
+	} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 		mode = CALLCHAIN_LBR;
 	else if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		mode = CALLCHAIN_FP;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dd4df9a5cd06..42a52dcc41cd 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -54,8 +54,6 @@
 #include <unistd.h>
 #include <linux/mman.h>
 
-#define PTIME_RANGE_MAX	10
-
 struct report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
@@ -76,7 +74,8 @@ struct report {
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
 	const char		*time_str;
-	struct perf_time_interval ptime_range[PTIME_RANGE_MAX];
+	struct perf_time_interval *ptime_range;
+	int			range_size;
 	int			range_num;
 	float			min_percent;
 	u64			nr_entries;
@@ -338,9 +337,10 @@ static int report__setup_sample_type(struct report *rep)
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		    (sample_type & PERF_SAMPLE_STACK_USER))
+		    (sample_type & PERF_SAMPLE_STACK_USER)) {
 			callchain_param.record_mode = CALLCHAIN_DWARF;
-		else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+			dwarf_callchain_users = true;
+		} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 			callchain_param.record_mode = CALLCHAIN_LBR;
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
@@ -403,6 +403,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	if (evname != NULL)
 		ret += fprintf(fp, " of event '%s'", evname);
 
+	if (rep->time_str)
+		ret += fprintf(fp, " (time slices: %s)", rep->time_str);
+
 	if (symbol_conf.show_ref_callgraph &&
 	    strstr(evname, "call-graph=no")) {
 		ret += fprintf(fp, ", show reference callgraph");
@@ -1296,22 +1299,33 @@ repeat:
 	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
+	report.ptime_range = perf_time__range_alloc(report.time_str,
+						    &report.range_size);
+	if (!report.ptime_range) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
 	if (perf_time__parse_str(report.ptime_range, report.time_str) != 0) {
 		if (session->evlist->first_sample_time == 0 &&
 		    session->evlist->last_sample_time == 0) {
-			pr_err("No first/last sample time in perf data\n");
-			return -EINVAL;
+			pr_err("HINT: no first/last sample time found in perf data.\n"
+			       "Please use latest perf binary to execute 'perf record'\n"
+			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
+			ret = -EINVAL;
+			goto error;
 		}
 
 		report.range_num = perf_time__percent_parse_str(
-					report.ptime_range, PTIME_RANGE_MAX,
+					report.ptime_range, report.range_size,
 					report.time_str,
 					session->evlist->first_sample_time,
 					session->evlist->last_sample_time);
 
 		if (report.range_num < 0) {
 			pr_err("Invalid time string\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto error;
 		}
 	} else {
 		report.range_num = 1;
@@ -1327,6 +1341,8 @@ repeat:
 		ret = 0;
 
 error:
+	zfree(&report.ptime_range);
+
 	perf_session__delete(session);
 	return ret;
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c1cce474c0f1..3499d68e1d70 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1480,8 +1480,6 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample,
 	return 0;
 }
 
-#define PTIME_RANGE_MAX	10
-
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
@@ -1496,7 +1494,8 @@ struct perf_script {
 	struct thread_map	*threads;
 	int			name_width;
 	const char              *time_str;
-	struct perf_time_interval ptime_range[PTIME_RANGE_MAX];
+	struct perf_time_interval *ptime_range;
+	int			range_size;
 	int			range_num;
 };
 
@@ -2919,9 +2918,10 @@ static void script__setup_sample_type(struct perf_script *script)
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		    (sample_type & PERF_SAMPLE_STACK_USER))
+		    (sample_type & PERF_SAMPLE_STACK_USER)) {
 			callchain_param.record_mode = CALLCHAIN_DWARF;
-		else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+			dwarf_callchain_users = true;
+		} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 			callchain_param.record_mode = CALLCHAIN_LBR;
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
@@ -3444,17 +3444,26 @@ int cmd_script(int argc, const char **argv)
 	if (err < 0)
 		goto out_delete;
 
+	script.ptime_range = perf_time__range_alloc(script.time_str,
+						    &script.range_size);
+	if (!script.ptime_range) {
+		err = -ENOMEM;
+		goto out_delete;
+	}
+
 	/* needs to be parsed after looking up reference time */
 	if (perf_time__parse_str(script.ptime_range, script.time_str) != 0) {
 		if (session->evlist->first_sample_time == 0 &&
 		    session->evlist->last_sample_time == 0) {
-			pr_err("No first/last sample time in perf data\n");
+			pr_err("HINT: no first/last sample time found in perf data.\n"
+			       "Please use latest perf binary to execute 'perf record'\n"
+			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
 			err = -EINVAL;
 			goto out_delete;
 		}
 
 		script.range_num = perf_time__percent_parse_str(
-					script.ptime_range, PTIME_RANGE_MAX,
+					script.ptime_range, script.range_size,
 					script.time_str,
 					session->evlist->first_sample_time,
 					session->evlist->last_sample_time);
@@ -3473,6 +3482,8 @@ int cmd_script(int argc, const char **argv)
 	flush_scripting();
 
 out_delete:
+	zfree(&script.ptime_range);
+
 	perf_evlist__free_stats(session->evlist);
 	perf_session__delete(session);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 71e64bdca86f..531d43bf57e1 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1644,7 +1644,7 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 	struct addr_location al;
 
 	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack))
+	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, evsel->attr.sample_max_stack))
 		return -1;
 
 	return 0;
@@ -2222,6 +2222,9 @@ static int trace__add_syscall_newtp(struct trace *trace)
 	if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
 		goto out_delete_sys_exit;
 
+	perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
+	perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
+
 	perf_evlist__add(evlist, sys_enter);
 	perf_evlist__add(evlist, sys_exit);
 
@@ -2318,6 +2321,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
 		if (pgfault_maj == NULL)
 			goto out_error_mem;
+		perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
 		perf_evlist__add(evlist, pgfault_maj);
 	}
 
@@ -2325,6 +2329,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
 		if (pgfault_min == NULL)
 			goto out_error_mem;
+		perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
 		perf_evlist__add(evlist, pgfault_min);
 	}
 
@@ -2345,45 +2350,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config(evlist, &trace->opts, NULL);
-
-	if (callchain_param.enabled) {
-		bool use_identifier = false;
-
-		if (trace->syscalls.events.sys_exit) {
-			perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
-						     &trace->opts, &callchain_param);
-			use_identifier = true;
-		}
-
-		if (pgfault_maj) {
-			perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
-			use_identifier = true;
-		}
-
-		if (pgfault_min) {
-			perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
-			use_identifier = true;
-		}
-
-		if (use_identifier) {
-		       /*
-			* Now we have evsels with different sample_ids, use
-			* PERF_SAMPLE_IDENTIFIER to map from sample to evsel
-			* from a fixed position in each ring buffer record.
-			*
-			* As of this the changeset introducing this comment, this
-			* isn't strictly needed, as the fields that can come before
-			* PERF_SAMPLE_ID are all used, but we'll probably disable
-			* some of those for things like copying the payload of
-			* pointer syscall arguments, and for vfs_getname we don't
-			* need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this
-			* here as a warning we need to use PERF_SAMPLE_IDENTIFIER.
-			*/
-			perf_evlist__set_sample_bit(evlist, IDENTIFIER);
-			perf_evlist__reset_sample_bit(evlist, ID);
-		}
-	}
+	perf_evlist__config(evlist, &trace->opts, &callchain_param);
 
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
@@ -2456,6 +2423,18 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
 				  evlist->threads->nr > 1 ||
 				  perf_evlist__first(evlist)->attr.inherit;
+
+	/*
+	 * Now that we already used evsel->attr to ask the kernel to setup the
+	 * events, lets reuse evsel->attr.sample_max_stack as the limit in
+	 * trace__resolve_callchain(), allowing per-event max-stack settings
+	 * to override an explicitely set --max-stack global setting.
+	 */
+	evlist__for_each_entry(evlist, evsel) {
+		if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+		    evsel->attr.sample_max_stack == 0)
+			evsel->attr.sample_max_stack = trace->max_stack;
+	}
 again:
 	before = trace->nr_events;
 
@@ -3098,8 +3077,9 @@ int cmd_trace(int argc, const char **argv)
 	}
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
+	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) {
 		record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
+	}
 #endif
 
 	if (callchain_param.enabled) {
diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-record b/tools/perf/scripts/python/bin/mem-phys-addr-record
new file mode 100644
index 000000000000..5a875122a904
--- /dev/null
+++ b/tools/perf/scripts/python/bin/mem-phys-addr-record
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+#
+# Profiling physical memory by all retired load instructions/uops event
+# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS
+#
+
+load=`perf list | grep mem_inst_retired.all_loads`
+if [ -z "$load" ]; then
+	load=`perf list | grep mem_uops_retired.all_loads`
+fi
+if [ -z "$load" ]; then
+	echo "There is no event to count all retired load instructions/uops."
+	exit 1
+fi
+
+arg=$(echo $load | tr -d ' ')
+arg="$arg:P"
+perf record --phys-data -e $arg $@
diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-report b/tools/perf/scripts/python/bin/mem-phys-addr-report
new file mode 100644
index 000000000000..3f2b847e2eab
--- /dev/null
+++ b/tools/perf/scripts/python/bin/mem-phys-addr-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: resolve physical address samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py
diff --git a/tools/perf/scripts/python/mem-phys-addr.py b/tools/perf/scripts/python/mem-phys-addr.py
new file mode 100644
index 000000000000..ebee2c5ae496
--- /dev/null
+++ b/tools/perf/scripts/python/mem-phys-addr.py
@@ -0,0 +1,95 @@
+# mem-phys-addr.py: Resolve physical address samples
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018, Intel Corporation.
+
+from __future__ import division
+import os
+import sys
+import struct
+import re
+import bisect
+import collections
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+#physical address ranges for System RAM
+system_ram = []
+#physical address ranges for Persistent Memory
+pmem = []
+#file object for proc iomem
+f = None
+#Count for each type of memory
+load_mem_type_cnt = collections.Counter()
+#perf event name
+event_name = None
+
+def parse_iomem():
+	global f
+	f = open('/proc/iomem', 'r')
+	for i, j in enumerate(f):
+		m = re.split('-|:',j,2)
+		if m[2].strip() == 'System RAM':
+			system_ram.append(long(m[0], 16))
+			system_ram.append(long(m[1], 16))
+		if m[2].strip() == 'Persistent Memory':
+			pmem.append(long(m[0], 16))
+			pmem.append(long(m[1], 16))
+
+def print_memory_type():
+	print "Event: %s" % (event_name)
+	print "%-40s  %10s  %10s\n" % ("Memory type", "count", "percentage"),
+	print "%-40s  %10s  %10s\n" % ("----------------------------------------", \
+					"-----------", "-----------"),
+	total = sum(load_mem_type_cnt.values())
+	for mem_type, count in sorted(load_mem_type_cnt.most_common(), \
+					key = lambda(k, v): (v, k), reverse = True):
+		print "%-40s  %10d  %10.1f%%\n" % (mem_type, count, 100 * count / total),
+
+def trace_begin():
+	parse_iomem()
+
+def trace_end():
+	print_memory_type()
+	f.close()
+
+def is_system_ram(phys_addr):
+	#/proc/iomem is sorted
+	position = bisect.bisect(system_ram, phys_addr)
+	if position % 2 == 0:
+		return False
+	return True
+
+def is_persistent_mem(phys_addr):
+	position = bisect.bisect(pmem, phys_addr)
+	if position % 2 == 0:
+		return False
+	return True
+
+def find_memory_type(phys_addr):
+	if phys_addr == 0:
+		return "N/A"
+	if is_system_ram(phys_addr):
+		return "System RAM"
+
+	if is_persistent_mem(phys_addr):
+		return "Persistent Memory"
+
+	#slow path, search all
+	f.seek(0, 0)
+	for j in f:
+		m = re.split('-|:',j,2)
+		if long(m[0], 16) <= phys_addr <= long(m[1], 16):
+			return m[2]
+	return "N/A"
+
+def process_event(param_dict):
+	name       = param_dict["ev_name"]
+	sample     = param_dict["sample"]
+	phys_addr  = sample["phys_addr"]
+
+	global event_name
+	if event_name == None:
+		event_name = name
+	load_mem_type_cnt[find_memory_type(phys_addr)] += 1
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index ac40e05bcab4..260418969120 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -173,6 +173,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
 	}
 
 	callchain_param.record_mode = CALLCHAIN_DWARF;
+	dwarf_callchain_users = true;
 
 	if (init_live_machine(machine)) {
 		pr_err("Could not init machine\n");
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a3de7916fe63..7c6a8b461e24 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -86,6 +86,8 @@ libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
+libperf-$(CONFIG_AUXTRACE) += arm-spe.o
+libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
 libperf-y += parse-branch-options.o
 libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
diff --git a/tools/perf/util/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-pkt-decoder.c
new file mode 100644
index 000000000000..b94001b756c7
--- /dev/null
+++ b/tools/perf/util/arm-spe-pkt-decoder.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "arm-spe-pkt-decoder.h"
+
+#define BIT(n)		(1ULL << (n))
+
+#define NS_FLAG		BIT(63)
+#define EL_FLAG		(BIT(62) | BIT(61))
+
+#define SPE_HEADER0_PAD			0x0
+#define SPE_HEADER0_END			0x1
+#define SPE_HEADER0_ADDRESS		0x30 /* address packet (short) */
+#define SPE_HEADER0_ADDRESS_MASK	0x38
+#define SPE_HEADER0_COUNTER		0x18 /* counter packet (short) */
+#define SPE_HEADER0_COUNTER_MASK	0x38
+#define SPE_HEADER0_TIMESTAMP		0x71
+#define SPE_HEADER0_TIMESTAMP		0x71
+#define SPE_HEADER0_EVENTS		0x2
+#define SPE_HEADER0_EVENTS_MASK		0xf
+#define SPE_HEADER0_SOURCE		0x3
+#define SPE_HEADER0_SOURCE_MASK		0xf
+#define SPE_HEADER0_CONTEXT		0x24
+#define SPE_HEADER0_CONTEXT_MASK	0x3c
+#define SPE_HEADER0_OP_TYPE		0x8
+#define SPE_HEADER0_OP_TYPE_MASK	0x3c
+#define SPE_HEADER1_ALIGNMENT		0x0
+#define SPE_HEADER1_ADDRESS		0xb0 /* address packet (extended) */
+#define SPE_HEADER1_ADDRESS_MASK	0xf8
+#define SPE_HEADER1_COUNTER		0x98 /* counter packet (extended) */
+#define SPE_HEADER1_COUNTER_MASK	0xf8
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define memcpy_le64(d, s, n) do { \
+	memcpy((d), (s), (n));    \
+	*(d) = le64_to_cpu(*(d)); \
+} while (0)
+#else
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define memcpy_le64 memcpy
+#endif
+
+static const char * const arm_spe_packet_name[] = {
+	[ARM_SPE_PAD]		= "PAD",
+	[ARM_SPE_END]		= "END",
+	[ARM_SPE_TIMESTAMP]	= "TS",
+	[ARM_SPE_ADDRESS]	= "ADDR",
+	[ARM_SPE_COUNTER]	= "LAT",
+	[ARM_SPE_CONTEXT]	= "CONTEXT",
+	[ARM_SPE_OP_TYPE]	= "OP-TYPE",
+	[ARM_SPE_EVENTS]	= "EVENTS",
+	[ARM_SPE_DATA_SOURCE]	= "DATA-SOURCE",
+};
+
+const char *arm_spe_pkt_name(enum arm_spe_pkt_type type)
+{
+	return arm_spe_packet_name[type];
+}
+
+/* return ARM SPE payload size from its encoding,
+ * which is in bits 5:4 of the byte.
+ * 00 : byte
+ * 01 : halfword (2)
+ * 10 : word (4)
+ * 11 : doubleword (8)
+ */
+static int payloadlen(unsigned char byte)
+{
+	return 1 << ((byte & 0x30) >> 4);
+}
+
+static int arm_spe_get_payload(const unsigned char *buf, size_t len,
+			       struct arm_spe_pkt *packet)
+{
+	size_t payload_len = payloadlen(buf[0]);
+
+	if (len < 1 + payload_len)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	buf++;
+
+	switch (payload_len) {
+	case 1: packet->payload = *(uint8_t *)buf; break;
+	case 2: packet->payload = le16_to_cpu(*(uint16_t *)buf); break;
+	case 4: packet->payload = le32_to_cpu(*(uint32_t *)buf); break;
+	case 8: packet->payload = le64_to_cpu(*(uint64_t *)buf); break;
+	default: return ARM_SPE_BAD_PACKET;
+	}
+
+	return 1 + payload_len;
+}
+
+static int arm_spe_get_pad(struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_PAD;
+	return 1;
+}
+
+static int arm_spe_get_alignment(const unsigned char *buf, size_t len,
+				 struct arm_spe_pkt *packet)
+{
+	unsigned int alignment = 1 << ((buf[0] & 0xf) + 1);
+
+	if (len < alignment)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	packet->type = ARM_SPE_PAD;
+	return alignment - (((uintptr_t)buf) & (alignment - 1));
+}
+
+static int arm_spe_get_end(struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_END;
+	return 1;
+}
+
+static int arm_spe_get_timestamp(const unsigned char *buf, size_t len,
+				 struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_TIMESTAMP;
+	return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_events(const unsigned char *buf, size_t len,
+			      struct arm_spe_pkt *packet)
+{
+	int ret = arm_spe_get_payload(buf, len, packet);
+
+	packet->type = ARM_SPE_EVENTS;
+
+	/* we use index to identify Events with a less number of
+	 * comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS,
+	 * LLC-REFILL, and REMOTE-ACCESS events are identified iff
+	 * index > 1.
+	 */
+	packet->index = ret - 1;
+
+	return ret;
+}
+
+static int arm_spe_get_data_source(const unsigned char *buf, size_t len,
+				   struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_DATA_SOURCE;
+	return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_context(const unsigned char *buf, size_t len,
+			       struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_CONTEXT;
+	packet->index = buf[0] & 0x3;
+
+	return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_op_type(const unsigned char *buf, size_t len,
+			       struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_OP_TYPE;
+	packet->index = buf[0] & 0x3;
+	return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_counter(const unsigned char *buf, size_t len,
+			       const unsigned char ext_hdr, struct arm_spe_pkt *packet)
+{
+	if (len < 2)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	packet->type = ARM_SPE_COUNTER;
+	if (ext_hdr)
+		packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+	else
+		packet->index = buf[0] & 0x7;
+
+	packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+
+	return 1 + ext_hdr + 2;
+}
+
+static int arm_spe_get_addr(const unsigned char *buf, size_t len,
+			    const unsigned char ext_hdr, struct arm_spe_pkt *packet)
+{
+	if (len < 8)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	packet->type = ARM_SPE_ADDRESS;
+	if (ext_hdr)
+		packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+	else
+		packet->index = buf[0] & 0x7;
+
+	memcpy_le64(&packet->payload, buf + 1, 8);
+
+	return 1 + ext_hdr + 8;
+}
+
+static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
+				 struct arm_spe_pkt *packet)
+{
+	unsigned int byte;
+
+	memset(packet, 0, sizeof(struct arm_spe_pkt));
+
+	if (!len)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	byte = buf[0];
+	if (byte == SPE_HEADER0_PAD)
+		return arm_spe_get_pad(packet);
+	else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */
+		return arm_spe_get_end(packet);
+	else if (byte & 0xc0 /* 0y11xxxxxx */) {
+		if (byte & 0x80) {
+			if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS)
+				return arm_spe_get_addr(buf, len, 0, packet);
+			if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER)
+				return arm_spe_get_counter(buf, len, 0, packet);
+		} else
+			if (byte == SPE_HEADER0_TIMESTAMP)
+				return arm_spe_get_timestamp(buf, len, packet);
+			else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS)
+				return arm_spe_get_events(buf, len, packet);
+			else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE)
+				return arm_spe_get_data_source(buf, len, packet);
+			else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT)
+				return arm_spe_get_context(buf, len, packet);
+			else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE)
+				return arm_spe_get_op_type(buf, len, packet);
+	} else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) {
+		/* 16-bit header */
+		byte = buf[1];
+		if (byte == SPE_HEADER1_ALIGNMENT)
+			return arm_spe_get_alignment(buf, len, packet);
+		else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS)
+			return arm_spe_get_addr(buf, len, 1, packet);
+		else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER)
+			return arm_spe_get_counter(buf, len, 1, packet);
+	}
+
+	return ARM_SPE_BAD_PACKET;
+}
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+		       struct arm_spe_pkt *packet)
+{
+	int ret;
+
+	ret = arm_spe_do_get_packet(buf, len, packet);
+	/* put multiple consecutive PADs on the same line, up to
+	 * the fixed-width output format of 16 bytes per line.
+	 */
+	if (ret > 0 && packet->type == ARM_SPE_PAD) {
+		while (ret < 16 && len > (size_t)ret && !buf[ret])
+			ret += 1;
+	}
+	return ret;
+}
+
+int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf,
+		     size_t buf_len)
+{
+	int ret, ns, el, idx = packet->index;
+	unsigned long long payload = packet->payload;
+	const char *name = arm_spe_pkt_name(packet->type);
+
+	switch (packet->type) {
+	case ARM_SPE_BAD:
+	case ARM_SPE_PAD:
+	case ARM_SPE_END:
+		return snprintf(buf, buf_len, "%s", name);
+	case ARM_SPE_EVENTS: {
+		size_t blen = buf_len;
+
+		ret = 0;
+		ret = snprintf(buf, buf_len, "EV");
+		buf += ret;
+		blen -= ret;
+		if (payload & 0x1) {
+			ret = snprintf(buf, buf_len, " EXCEPTION-GEN");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x2) {
+			ret = snprintf(buf, buf_len, " RETIRED");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x4) {
+			ret = snprintf(buf, buf_len, " L1D-ACCESS");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x8) {
+			ret = snprintf(buf, buf_len, " L1D-REFILL");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x10) {
+			ret = snprintf(buf, buf_len, " TLB-ACCESS");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x20) {
+			ret = snprintf(buf, buf_len, " TLB-REFILL");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x40) {
+			ret = snprintf(buf, buf_len, " NOT-TAKEN");
+			buf += ret;
+			blen -= ret;
+		}
+		if (payload & 0x80) {
+			ret = snprintf(buf, buf_len, " MISPRED");
+			buf += ret;
+			blen -= ret;
+		}
+		if (idx > 1) {
+			if (payload & 0x100) {
+				ret = snprintf(buf, buf_len, " LLC-ACCESS");
+				buf += ret;
+				blen -= ret;
+			}
+			if (payload & 0x200) {
+				ret = snprintf(buf, buf_len, " LLC-REFILL");
+				buf += ret;
+				blen -= ret;
+			}
+			if (payload & 0x400) {
+				ret = snprintf(buf, buf_len, " REMOTE-ACCESS");
+				buf += ret;
+				blen -= ret;
+			}
+		}
+		if (ret < 0)
+			return ret;
+		blen -= ret;
+		return buf_len - blen;
+	}
+	case ARM_SPE_OP_TYPE:
+		switch (idx) {
+		case 0:	return snprintf(buf, buf_len, "%s", payload & 0x1 ?
+					"COND-SELECT" : "INSN-OTHER");
+		case 1:	{
+			size_t blen = buf_len;
+
+			if (payload & 0x1)
+				ret = snprintf(buf, buf_len, "ST");
+			else
+				ret = snprintf(buf, buf_len, "LD");
+			buf += ret;
+			blen -= ret;
+			if (payload & 0x2) {
+				if (payload & 0x4) {
+					ret = snprintf(buf, buf_len, " AT");
+					buf += ret;
+					blen -= ret;
+				}
+				if (payload & 0x8) {
+					ret = snprintf(buf, buf_len, " EXCL");
+					buf += ret;
+					blen -= ret;
+				}
+				if (payload & 0x10) {
+					ret = snprintf(buf, buf_len, " AR");
+					buf += ret;
+					blen -= ret;
+				}
+			} else if (payload & 0x4) {
+				ret = snprintf(buf, buf_len, " SIMD-FP");
+				buf += ret;
+				blen -= ret;
+			}
+			if (ret < 0)
+				return ret;
+			blen -= ret;
+			return buf_len - blen;
+		}
+		case 2:	{
+			size_t blen = buf_len;
+
+			ret = snprintf(buf, buf_len, "B");
+			buf += ret;
+			blen -= ret;
+			if (payload & 0x1) {
+				ret = snprintf(buf, buf_len, " COND");
+				buf += ret;
+				blen -= ret;
+			}
+			if (payload & 0x2) {
+				ret = snprintf(buf, buf_len, " IND");
+				buf += ret;
+				blen -= ret;
+			}
+			if (ret < 0)
+				return ret;
+			blen -= ret;
+			return buf_len - blen;
+			}
+		default: return 0;
+		}
+	case ARM_SPE_DATA_SOURCE:
+	case ARM_SPE_TIMESTAMP:
+		return snprintf(buf, buf_len, "%s %lld", name, payload);
+	case ARM_SPE_ADDRESS:
+		switch (idx) {
+		case 0:
+		case 1: ns = !!(packet->payload & NS_FLAG);
+			el = (packet->payload & EL_FLAG) >> 61;
+			payload &= ~(0xffULL << 56);
+			return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d",
+				        (idx == 1) ? "TGT" : "PC", payload, el, ns);
+		case 2:	return snprintf(buf, buf_len, "VA 0x%llx", payload);
+		case 3:	ns = !!(packet->payload & NS_FLAG);
+			payload &= ~(0xffULL << 56);
+			return snprintf(buf, buf_len, "PA 0x%llx ns=%d",
+					payload, ns);
+		default: return 0;
+		}
+	case ARM_SPE_CONTEXT:
+		return snprintf(buf, buf_len, "%s 0x%lx el%d", name,
+				(unsigned long)payload, idx + 1);
+	case ARM_SPE_COUNTER: {
+		size_t blen = buf_len;
+
+		ret = snprintf(buf, buf_len, "%s %d ", name,
+			       (unsigned short)payload);
+		buf += ret;
+		blen -= ret;
+		switch (idx) {
+		case 0:	ret = snprintf(buf, buf_len, "TOT"); break;
+		case 1:	ret = snprintf(buf, buf_len, "ISSUE"); break;
+		case 2:	ret = snprintf(buf, buf_len, "XLAT"); break;
+		default: ret = 0;
+		}
+		if (ret < 0)
+			return ret;
+		blen -= ret;
+		return buf_len - blen;
+	}
+	default:
+		break;
+	}
+
+	return snprintf(buf, buf_len, "%s 0x%llx (%d)",
+			name, payload, packet->index);
+}
diff --git a/tools/perf/util/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-pkt-decoder.h
new file mode 100644
index 000000000000..d786ef65113f
--- /dev/null
+++ b/tools/perf/util/arm-spe-pkt-decoder.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#ifndef INCLUDE__ARM_SPE_PKT_DECODER_H__
+#define INCLUDE__ARM_SPE_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define ARM_SPE_PKT_DESC_MAX		256
+
+#define ARM_SPE_NEED_MORE_BYTES		-1
+#define ARM_SPE_BAD_PACKET		-2
+
+enum arm_spe_pkt_type {
+	ARM_SPE_BAD,
+	ARM_SPE_PAD,
+	ARM_SPE_END,
+	ARM_SPE_TIMESTAMP,
+	ARM_SPE_ADDRESS,
+	ARM_SPE_COUNTER,
+	ARM_SPE_CONTEXT,
+	ARM_SPE_OP_TYPE,
+	ARM_SPE_EVENTS,
+	ARM_SPE_DATA_SOURCE,
+};
+
+struct arm_spe_pkt {
+	enum arm_spe_pkt_type	type;
+	unsigned char		index;
+	uint64_t		payload;
+};
+
+const char *arm_spe_pkt_name(enum arm_spe_pkt_type);
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+		       struct arm_spe_pkt *packet);
+
+int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf, size_t len);
+#endif
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
new file mode 100644
index 000000000000..6067267cc76c
--- /dev/null
+++ b/tools/perf/util/arm-spe.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <endian.h>
+#include <errno.h>
+#include <byteswap.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "cpumap.h"
+#include "color.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "session.h"
+#include "util.h"
+#include "thread.h"
+#include "debug.h"
+#include "auxtrace.h"
+#include "arm-spe.h"
+#include "arm-spe-pkt-decoder.h"
+
+struct arm_spe {
+	struct auxtrace			auxtrace;
+	struct auxtrace_queues		queues;
+	struct auxtrace_heap		heap;
+	u32				auxtrace_type;
+	struct perf_session		*session;
+	struct machine			*machine;
+	u32				pmu_type;
+};
+
+struct arm_spe_queue {
+	struct arm_spe		*spe;
+	unsigned int		queue_nr;
+	struct auxtrace_buffer	*buffer;
+	bool			on_heap;
+	bool			done;
+	pid_t			pid;
+	pid_t			tid;
+	int			cpu;
+};
+
+static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
+			 unsigned char *buf, size_t len)
+{
+	struct arm_spe_pkt packet;
+	size_t pos = 0;
+	int ret, pkt_len, i;
+	char desc[ARM_SPE_PKT_DESC_MAX];
+	const char *color = PERF_COLOR_BLUE;
+
+	color_fprintf(stdout, color,
+		      ". ... ARM SPE data: size %zu bytes\n",
+		      len);
+
+	while (len) {
+		ret = arm_spe_get_packet(buf, len, &packet);
+		if (ret > 0)
+			pkt_len = ret;
+		else
+			pkt_len = 1;
+		printf(".");
+		color_fprintf(stdout, color, "  %08x: ", pos);
+		for (i = 0; i < pkt_len; i++)
+			color_fprintf(stdout, color, " %02x", buf[i]);
+		for (; i < 16; i++)
+			color_fprintf(stdout, color, "   ");
+		if (ret > 0) {
+			ret = arm_spe_pkt_desc(&packet, desc,
+					       ARM_SPE_PKT_DESC_MAX);
+			if (ret > 0)
+				color_fprintf(stdout, color, " %s\n", desc);
+		} else {
+			color_fprintf(stdout, color, " Bad packet!\n");
+		}
+		pos += pkt_len;
+		buf += pkt_len;
+		len -= pkt_len;
+	}
+}
+
+static void arm_spe_dump_event(struct arm_spe *spe, unsigned char *buf,
+			       size_t len)
+{
+	printf(".\n");
+	arm_spe_dump(spe, buf, len);
+}
+
+static int arm_spe_process_event(struct perf_session *session __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_sample *sample __maybe_unused,
+				 struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static int arm_spe_process_auxtrace_event(struct perf_session *session,
+					  union perf_event *event,
+					  struct perf_tool *tool __maybe_unused)
+{
+	struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+					     auxtrace);
+	struct auxtrace_buffer *buffer;
+	off_t data_offset;
+	int fd = perf_data__fd(session->data);
+	int err;
+
+	if (perf_data__is_pipe(session->data)) {
+		data_offset = 0;
+	} else {
+		data_offset = lseek(fd, 0, SEEK_CUR);
+		if (data_offset == -1)
+			return -errno;
+	}
+
+	err = auxtrace_queues__add_event(&spe->queues, session, event,
+					 data_offset, &buffer);
+	if (err)
+		return err;
+
+	/* Dump here now we have copied a piped trace out of the pipe */
+	if (dump_trace) {
+		if (auxtrace_buffer__get_data(buffer, fd)) {
+			arm_spe_dump_event(spe, buffer->data,
+					     buffer->size);
+			auxtrace_buffer__put_data(buffer);
+		}
+	}
+
+	return 0;
+}
+
+static int arm_spe_flush(struct perf_session *session __maybe_unused,
+			 struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static void arm_spe_free_queue(void *priv)
+{
+	struct arm_spe_queue *speq = priv;
+
+	if (!speq)
+		return;
+	free(speq);
+}
+
+static void arm_spe_free_events(struct perf_session *session)
+{
+	struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+					     auxtrace);
+	struct auxtrace_queues *queues = &spe->queues;
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		arm_spe_free_queue(queues->queue_array[i].priv);
+		queues->queue_array[i].priv = NULL;
+	}
+	auxtrace_queues__free(queues);
+}
+
+static void arm_spe_free(struct perf_session *session)
+{
+	struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+					     auxtrace);
+
+	auxtrace_heap__free(&spe->heap);
+	arm_spe_free_events(session);
+	session->auxtrace = NULL;
+	free(spe);
+}
+
+static const char * const arm_spe_info_fmts[] = {
+	[ARM_SPE_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
+};
+
+static void arm_spe_print_info(u64 *arr)
+{
+	if (!dump_trace)
+		return;
+
+	fprintf(stdout, arm_spe_info_fmts[ARM_SPE_PMU_TYPE], arr[ARM_SPE_PMU_TYPE]);
+}
+
+int arm_spe_process_auxtrace_info(union perf_event *event,
+				  struct perf_session *session)
+{
+	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	size_t min_sz = sizeof(u64) * ARM_SPE_PMU_TYPE;
+	struct arm_spe *spe;
+	int err;
+
+	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+					min_sz)
+		return -EINVAL;
+
+	spe = zalloc(sizeof(struct arm_spe));
+	if (!spe)
+		return -ENOMEM;
+
+	err = auxtrace_queues__init(&spe->queues);
+	if (err)
+		goto err_free;
+
+	spe->session = session;
+	spe->machine = &session->machines.host; /* No kvm support */
+	spe->auxtrace_type = auxtrace_info->type;
+	spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
+
+	spe->auxtrace.process_event = arm_spe_process_event;
+	spe->auxtrace.process_auxtrace_event = arm_spe_process_auxtrace_event;
+	spe->auxtrace.flush_events = arm_spe_flush;
+	spe->auxtrace.free_events = arm_spe_free_events;
+	spe->auxtrace.free = arm_spe_free;
+	session->auxtrace = &spe->auxtrace;
+
+	arm_spe_print_info(&auxtrace_info->priv[0]);
+
+	return 0;
+
+err_free:
+	free(spe);
+	return err;
+}
diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h
new file mode 100644
index 000000000000..98d3235781c3
--- /dev/null
+++ b/tools/perf/util/arm-spe.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#ifndef INCLUDE__PERF_ARM_SPE_H__
+#define INCLUDE__PERF_ARM_SPE_H__
+
+#define ARM_SPE_PMU_NAME "arm_spe_"
+
+enum {
+	ARM_SPE_PMU_TYPE,
+	ARM_SPE_PER_CPU_MMAPS,
+	ARM_SPE_AUXTRACE_PRIV_MAX,
+};
+
+#define ARM_SPE_AUXTRACE_PRIV_SIZE (ARM_SPE_AUXTRACE_PRIV_MAX * sizeof(u64))
+
+union perf_event;
+struct perf_session;
+struct perf_pmu;
+
+struct auxtrace_record *arm_spe_recording_init(int *err,
+					       struct perf_pmu *arm_spe_pmu);
+
+int arm_spe_process_auxtrace_info(union perf_event *event,
+				  struct perf_session *session);
+
+struct perf_event_attr *arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu);
+#endif
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c76687e42344..3bba9947ab7f 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -54,6 +54,7 @@
 
 #include "intel-pt.h"
 #include "intel-bts.h"
+#include "arm-spe.h"
 
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
@@ -910,6 +911,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 		return intel_pt_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_INTEL_BTS:
 		return intel_bts_process_auxtrace_info(event, session);
+	case PERF_AUXTRACE_ARM_SPE:
+		return arm_spe_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_CS_ETM:
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d19e11b68de7..453c148d2158 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -43,6 +43,7 @@ enum auxtrace_type {
 	PERF_AUXTRACE_INTEL_PT,
 	PERF_AUXTRACE_INTEL_BTS,
 	PERF_AUXTRACE_CS_ETM,
+	PERF_AUXTRACE_ARM_SPE,
 };
 
 enum itrace_period_type {
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 082505d08d72..32ef7bdca1cf 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -37,6 +37,15 @@ struct callchain_param callchain_param = {
 	CALLCHAIN_PARAM_DEFAULT
 };
 
+/*
+ * Are there any events usind DWARF callchains?
+ *
+ * I.e.
+ *
+ * -e cycles/call-graph=dwarf/
+ */
+bool dwarf_callchain_users;
+
 struct callchain_param callchain_param_default = {
 	CALLCHAIN_PARAM_DEFAULT
 };
@@ -265,6 +274,7 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 			ret = 0;
 			param->record_mode = CALLCHAIN_DWARF;
 			param->dump_size = default_stack_dump_size;
+			dwarf_callchain_users = true;
 
 			tok = strtok_r(NULL, ",", &saveptr);
 			if (tok) {
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b79ef2478a57..154560b1eb65 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -89,6 +89,8 @@ enum chain_value {
 	CCVAL_COUNT,
 };
 
+extern bool dwarf_callchain_users;
+
 struct callchain_param {
 	bool			enabled;
 	enum perf_call_graph_mode record_mode;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f0a5e09c4071..120efd85f2c8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1760,7 +1760,7 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 	switch (old_state) {
 	case BKW_MMAP_NOTREADY: {
 		if (state != BKW_MMAP_RUNNING)
-			goto state_err;;
+			goto state_err;
 		break;
 	}
 	case BKW_MMAP_RUNNING: {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d934f04e3110..85eb84dfdf91 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -651,9 +651,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 	return ret;
 }
 
-void perf_evsel__config_callchain(struct perf_evsel *evsel,
-				  struct record_opts *opts,
-				  struct callchain_param *param)
+static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
+					   struct record_opts *opts,
+					   struct callchain_param *param)
 {
 	bool function = perf_evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->attr;
@@ -699,6 +699,14 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 	}
 }
 
+void perf_evsel__config_callchain(struct perf_evsel *evsel,
+				  struct record_opts *opts,
+				  struct callchain_param *param)
+{
+	if (param->enabled)
+		return __perf_evsel__config_callchain(evsel, opts, param);
+}
+
 static void
 perf_evsel__reset_callgraph(struct perf_evsel *evsel,
 			    struct callchain_param *param)
@@ -718,19 +726,19 @@ perf_evsel__reset_callgraph(struct perf_evsel *evsel,
 }
 
 static void apply_config_terms(struct perf_evsel *evsel,
-			       struct record_opts *opts)
+			       struct record_opts *opts, bool track)
 {
 	struct perf_evsel_config_term *term;
 	struct list_head *config_terms = &evsel->config_terms;
 	struct perf_event_attr *attr = &evsel->attr;
-	struct callchain_param param;
+	/* callgraph default */
+	struct callchain_param param = {
+		.record_mode = callchain_param.record_mode,
+	};
 	u32 dump_size = 0;
 	int max_stack = 0;
 	const char *callgraph_buf = NULL;
 
-	/* callgraph default */
-	param.record_mode = callchain_param.record_mode;
-
 	list_for_each_entry(term, config_terms, list) {
 		switch (term->type) {
 		case PERF_EVSEL__CONFIG_TERM_PERIOD:
@@ -781,7 +789,7 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			attr->write_backward = term->val.overwrite ? 1 : 0;
 			break;
 		case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
-			BUG_ON(1);
+			break;
 		default:
 			break;
 		}
@@ -789,6 +797,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 
 	/* User explicitly set per-event callgraph, clear the old setting and reset. */
 	if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
+		bool sample_address = false;
+
 		if (max_stack) {
 			param.max_stack = max_stack;
 			if (callgraph_buf == NULL)
@@ -808,6 +818,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 					       evsel->name);
 					return;
 				}
+				if (param.record_mode == CALLCHAIN_DWARF)
+					sample_address = true;
 			}
 		}
 		if (dump_size > 0) {
@@ -820,8 +832,14 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			perf_evsel__reset_callgraph(evsel, &callchain_param);
 
 		/* set perf-event callgraph */
-		if (param.enabled)
+		if (param.enabled) {
+			if (sample_address) {
+				perf_evsel__set_sample_bit(evsel, ADDR);
+				perf_evsel__set_sample_bit(evsel, DATA_SRC);
+				evsel->attr.mmap_data = track;
+			}
 			perf_evsel__config_callchain(evsel, opts, &param);
+		}
 	}
 }
 
@@ -1052,7 +1070,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
 	 */
-	apply_config_terms(evsel, opts);
+	apply_config_terms(evsel, opts, track);
 
 	evsel->ignore_missing_thread = opts->ignore_missing_thread;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index c1848b543f27..ea070883c593 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -499,6 +499,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->time));
 	pydict_set_item_string_decref(dict_sample, "period",
 			PyLong_FromUnsignedLongLong(sample->period));
+	pydict_set_item_string_decref(dict_sample, "phys_addr",
+			PyLong_FromUnsignedLongLong(sample->phys_addr));
 	set_sample_read_in_dict(dict_sample, sample, evsel);
 	pydict_set_item_string_decref(dict, "sample", dict_sample);
 
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 3f7f18f06982..6193b46050a5 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -116,7 +116,8 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)
 
 static int parse_percent(double *pcnt, char *str)
 {
-	char *c;
+	char *c, *endptr;
+	double d;
 
 	c = strchr(str, '%');
 	if (c)
@@ -124,8 +125,11 @@ static int parse_percent(double *pcnt, char *str)
 	else
 		return -1;
 
-	*pcnt = atof(str) / 100.0;
+	d = strtod(str, &endptr);
+	if (endptr != str + strlen(str))
+		return -1;
 
+	*pcnt = d / 100.0;
 	return 0;
 }
 
@@ -257,6 +261,37 @@ static int percent_comma_split(struct perf_time_interval *ptime_buf, int num,
 	return i;
 }
 
+static int one_percent_convert(struct perf_time_interval *ptime_buf,
+			       const char *ostr, u64 start, u64 end, char *c)
+{
+	char *str;
+	int len = strlen(ostr), ret;
+
+	/*
+	 * c points to '%'.
+	 * '%' should be the last character
+	 */
+	if (ostr + len - 1 != c)
+		return -1;
+
+	/*
+	 * Construct a string like "xx%/1"
+	 */
+	str = malloc(len + 3);
+	if (str == NULL)
+		return -ENOMEM;
+
+	memcpy(str, ostr, len);
+	strcpy(str + len, "/1");
+
+	ret = percent_slash_split(str, ptime_buf, start, end);
+	if (ret == 0)
+		ret = 1;
+
+	free(str);
+	return ret;
+}
+
 int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
 				 const char *ostr, u64 start, u64 end)
 {
@@ -266,6 +301,7 @@ int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
 	 * ostr example:
 	 * 10%/2,10%/3: select the second 10% slice and the third 10% slice
 	 * 0%-10%,30%-40%: multiple time range
+	 * 50%: just one percent
 	 */
 
 	memset(ptime_buf, 0, sizeof(*ptime_buf) * num);
@@ -282,9 +318,41 @@ int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
 					   end, percent_dash_split);
 	}
 
+	c = strchr(ostr, '%');
+	if (c)
+		return one_percent_convert(ptime_buf, ostr, start, end, c);
+
 	return -1;
 }
 
+struct perf_time_interval *perf_time__range_alloc(const char *ostr, int *size)
+{
+	const char *p1, *p2;
+	int i = 1;
+	struct perf_time_interval *ptime;
+
+	/*
+	 * At least allocate one time range.
+	 */
+	if (!ostr)
+		goto alloc;
+
+	p1 = ostr;
+	while (p1 < ostr + strlen(ostr)) {
+		p2 = strchr(p1, ',');
+		if (!p2)
+			break;
+
+		p1 = p2 + 1;
+		i++;
+	}
+
+alloc:
+	*size = i;
+	ptime = calloc(i, sizeof(*ptime));
+	return ptime;
+}
+
 bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp)
 {
 	/* if time is not set don't drop sample */
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 34d5eba26bf5..70b177d2b98c 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -16,6 +16,8 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr);
 int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
 				 const char *ostr, u64 start, u64 end);
 
+struct perf_time_interval *perf_time__range_alloc(const char *ostr, int *size);
+
 bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp);
 
 bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 7a42f703e858..af873044d33a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -631,9 +631,8 @@ static unw_accessors_t accessors = {
 
 static int _unwind__prepare_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return 0;
-
 	thread->addr_space = unw_create_addr_space(&accessors, 0);
 	if (!thread->addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
@@ -646,17 +645,15 @@ static int _unwind__prepare_access(struct thread *thread)
 
 static void _unwind__flush_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return;
-
 	unw_flush_cache(thread->addr_space, 0, 0);
 }
 
 static void _unwind__finish_access(struct thread *thread)
 {
-	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+	if (!dwarf_callchain_users)
 		return;
-
 	unw_destroy_addr_space(thread->addr_space);
 }
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index a789f952b3e9..443892dabedb 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -210,7 +210,7 @@ static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64
 
 		size -= ret;
 		off_in += ret;
-		off_out -= ret;
+		off_out += ret;
 	}
 	munmap(ptr, off_in + size);