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

Pull perf updates from Ingo Molnar:
 "Most of the changes are for tooling, the main changes in this cycle were:

   - Improve Intel-PT hardware tracing support, both on the kernel and
     on the tooling side: PTWRITE instruction support, power events for
     C-state tracing, etc. (Adrian Hunter)

   - Add support to measure SMI cost to the x86 architecture, with
     tooling support in 'perf stat' (Kan Liang)

   - Support function filtering in 'perf ftrace', plus related
     improvements (Namhyung Kim)

   - Allow adding and removing fields to the default 'perf script'
     columns, using + or - as field prefixes to do so (Andi Kleen)

   - Allow resolving the DSO name with 'perf script -F brstack{sym,off},dso'
     (Mark Santaniello)

   - Add perf tooling unwind support for PowerPC (Paolo Bonzini)

   - ... and various other improvements as well"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (84 commits)
  perf auxtrace: Add CPU filter support
  perf intel-pt: Do not use TSC packets for calculating CPU cycles to TSC
  perf intel-pt: Update documentation to include new ptwrite and power events
  perf intel-pt: Add example script for power events and PTWRITE
  perf intel-pt: Synthesize new power and "ptwrite" events
  perf intel-pt: Move code in intel_pt_synth_events() to simplify attr setting
  perf intel-pt: Factor out intel_pt_set_event_name()
  perf intel-pt: Tidy messages into called function intel_pt_synth_event()
  perf intel-pt: Tidy Intel PT evsel lookup into separate function
  perf intel-pt: Join needlessly wrapped lines
  perf intel-pt: Remove unused instructions_sample_period
  perf intel-pt: Factor out common code synthesizing event samples
  perf script: Add synthesized Intel PT power and ptwrite events
  perf/x86/intel: Constify the 'lbr_desc[]' array and make a function static
  perf script: Add 'synth' field for synthesized event payloads
  perf auxtrace: Add itrace option to output power events
  perf auxtrace: Add itrace option to output ptwrite events
  tools include: Add byte-swapping macros to kernel.h
  perf script: Add 'synth' event type for synthesized events
  x86/insn: perf tools: Add new ptwrite instruction
  ...

36 files changed, 1183 insertions, 397 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ddbd56df9187..be1caabb9290 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1379,7 +1379,9 @@ static const char *annotate__norm_arch(const char *arch_name)
 	return normalize_arch((char *)arch_name);
 }
 
-int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize)
+int symbol__disassemble(struct symbol *sym, struct map *map,
+			const char *arch_name, size_t privsize,
+			struct arch **parch)
 {
 	struct dso *dso = map->dso;
 	char command[PATH_MAX * 2];
@@ -1405,6 +1407,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	if (arch == NULL)
 		return -ENOTSUP;
 
+	if (parch)
+		*parch = arch;
+
 	if (arch->init) {
 		err = arch->init(arch);
 		if (err) {
@@ -1901,7 +1906,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	struct rb_root source_line = RB_ROOT;
 	u64 len;
 
-	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0)
+	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
+				0, NULL) < 0)
 		return -1;
 
 	len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 948aa8e6fd39..21055034aedd 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -158,7 +158,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize);
+int symbol__disassemble(struct symbol *sym, struct map *map,
+			const char *arch_name, size_t privsize,
+			struct arch **parch);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 0daf63b9ee3e..5547457566a7 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -322,6 +322,13 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
 	return auxtrace_queues__add_buffer(queues, idx, buffer);
 }
 
+static bool filter_cpu(struct perf_session *session, int cpu)
+{
+	unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
+
+	return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+}
+
 int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 			       struct perf_session *session,
 			       union perf_event *event, off_t data_offset,
@@ -331,6 +338,9 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	unsigned int idx;
 	int err;
 
+	if (filter_cpu(session, event->auxtrace.cpu))
+		return 0;
+
 	buffer = zalloc(sizeof(struct auxtrace_buffer));
 	if (!buffer)
 		return -ENOMEM;
@@ -947,6 +957,8 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
+	synth_opts->ptwrites = true;
+	synth_opts->pwr_events = true;
 	synth_opts->errors = true;
 	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
@@ -1030,6 +1042,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'x':
 			synth_opts->transactions = true;
 			break;
+		case 'w':
+			synth_opts->ptwrites = true;
+			break;
+		case 'p':
+			synth_opts->pwr_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 9f0de72d58e2..33b5e6cdf38c 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -59,6 +59,8 @@ enum itrace_period_type {
  * @instructions: whether to synthesize 'instructions' events
  * @branches: whether to synthesize 'branches' events
  * @transactions: whether to synthesize events for transactions
+ * @ptwrites: whether to synthesize events for ptwrites
+ * @pwr_events: whether to synthesize power events
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -72,6 +74,7 @@ enum itrace_period_type {
  * @period: 'instructions' events period
  * @period_type: 'instructions' events period type
  * @initial_skip: skip N events at the beginning.
+ * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all
  */
 struct itrace_synth_opts {
 	bool			set;
@@ -79,6 +82,8 @@ struct itrace_synth_opts {
 	bool			instructions;
 	bool			branches;
 	bool			transactions;
+	bool			ptwrites;
+	bool			pwr_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;
@@ -92,6 +97,7 @@ struct itrace_synth_opts {
 	unsigned long long	period;
 	enum itrace_period_type	period_type;
 	unsigned long		initial_skip;
+	unsigned long		*cpu_bitmap;
 };
 
 /**
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 0328f297a748..0175765c05b9 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -5,6 +5,7 @@
 #include <subcmd/pager.h>
 #include "../ui/ui.h"
 
+#include <linux/compiler.h>
 #include <linux/string.h>
 
 #define CMD_EXEC_PATH "--exec-path"
@@ -24,6 +25,6 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+char *mkpath(const char *fmt, ...) __printf(1, 2);
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 8d724f0fa5a8..31a7dea248d0 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -335,32 +335,42 @@ static int perf_parse_long(const char *value, long *ret)
 	return 0;
 }
 
-static void die_bad_config(const char *name)
+static void bad_config(const char *name)
 {
 	if (config_file_name)
-		die("bad config value for '%s' in %s", name, config_file_name);
-	die("bad config value for '%s'", name);
+		pr_warning("bad config value for '%s' in %s, ignoring...\n", name, config_file_name);
+	else
+		pr_warning("bad config value for '%s', ignoring...\n", name);
 }
 
-u64 perf_config_u64(const char *name, const char *value)
+int perf_config_u64(u64 *dest, const char *name, const char *value)
 {
 	long long ret = 0;
 
-	if (!perf_parse_llong(value, &ret))
-		die_bad_config(name);
-	return (u64) ret;
+	if (!perf_parse_llong(value, &ret)) {
+		bad_config(name);
+		return -1;
+	}
+
+	*dest = ret;
+	return 0;
 }
 
-int perf_config_int(const char *name, const char *value)
+int perf_config_int(int *dest, const char *name, const char *value)
 {
 	long ret = 0;
-	if (!perf_parse_long(value, &ret))
-		die_bad_config(name);
-	return ret;
+	if (!perf_parse_long(value, &ret)) {
+		bad_config(name);
+		return -1;
+	}
+	*dest = ret;
+	return 0;
 }
 
 static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
 {
+	int ret;
+
 	*is_bool = 1;
 	if (!value)
 		return 1;
@@ -371,7 +381,7 @@ static int perf_config_bool_or_int(const char *name, const char *value, int *is_
 	if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off"))
 		return 0;
 	*is_bool = 0;
-	return perf_config_int(name, value);
+	return perf_config_int(&ret, name, value) < 0 ? -1 : ret;
 }
 
 int perf_config_bool(const char *name, const char *value)
@@ -657,8 +667,7 @@ static int perf_config_set__init(struct perf_config_set *set)
 
 	user_config = strdup(mkpath("%s/.perfconfig", home));
 	if (user_config == NULL) {
-		warning("Not enough memory to process %s/.perfconfig, "
-			"ignoring it.", home);
+		pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home);
 		goto out;
 	}
 
@@ -671,8 +680,7 @@ static int perf_config_set__init(struct perf_config_set *set)
 	ret = 0;
 
 	if (st.st_uid && (st.st_uid != geteuid())) {
-		warning("File %s not owned by current user or root, "
-			"ignoring it.", user_config);
+		pr_warning("File %s not owned by current user or root, ignoring it.", user_config);
 		goto out_free;
 	}
 
@@ -795,7 +803,8 @@ void perf_config_set__delete(struct perf_config_set *set)
  */
 int config_error_nonbool(const char *var)
 {
-	return error("Missing value for '%s'", var);
+	pr_err("Missing value for '%s'", var);
+	return -1;
 }
 
 void set_buildid_dir(const char *dir)
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index 1a59a6b43f8b..b6bb11f3f165 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -27,8 +27,8 @@ extern const char *config_exclusive_filename;
 typedef int (*config_fn_t)(const char *, const char *, void *);
 int perf_default_config(const char *, const char *, void *);
 int perf_config(config_fn_t fn, void *);
-int perf_config_int(const char *, const char *);
-u64 perf_config_u64(const char *, const char *);
+int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u64(u64 *dest, const char *, const char *);
 int perf_config_bool(const char *, const char *);
 int config_error_nonbool(const char *);
 const char *perf_etc_perfconfig(void);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 89d50318833d..3149b70799fd 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1444,10 +1444,8 @@ static int convert__config(const char *var, const char *value, void *cb)
 {
 	struct convert *c = cb;
 
-	if (!strcmp(var, "convert.queue-size")) {
-		c->queue_size = perf_config_u64(var, value);
-		return 0;
-	}
+	if (!strcmp(var, "convert.queue-size"))
+		return perf_config_u64(&c->queue_size, var, value);
 
 	return 0;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8a23ea1a71c7..c818bdb1c1ab 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -4,6 +4,7 @@
 
 #include <stdbool.h>
 #include <string.h>
+#include <linux/compiler.h>
 #include "event.h"
 #include "../ui/helpline.h"
 #include "../ui/progress.h"
@@ -40,16 +41,16 @@ extern int debug_data_convert;
 
 #define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
-int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
+int dump_printf(const char *fmt, ...) __printf(1, 2);
 void trace_event(union perf_event *event);
 
-int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+int ui__error(const char *format, ...) __printf(1, 2);
+int ui__warning(const char *format, ...) __printf(1, 2);
 
 void pr_stat(const char *fmt, ...);
 
-int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
-int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
+int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4);
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5);
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7c3fa1c8cbcd..9967c87af7a6 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -252,6 +252,127 @@ enum auxtrace_error_type {
 	PERF_AUXTRACE_ERROR_MAX
 };
 
+/* Attribute type for custom synthesized events */
+#define PERF_TYPE_SYNTH		(INT_MAX + 1U)
+
+/* Attribute config for custom synthesized events */
+enum perf_synth_id {
+	PERF_SYNTH_INTEL_PTWRITE,
+	PERF_SYNTH_INTEL_MWAIT,
+	PERF_SYNTH_INTEL_PWRE,
+	PERF_SYNTH_INTEL_EXSTOP,
+	PERF_SYNTH_INTEL_PWRX,
+	PERF_SYNTH_INTEL_CBR,
+};
+
+/*
+ * Raw data formats for synthesized events. Note that 4 bytes of padding are
+ * present to match the 'size' member of PERF_SAMPLE_RAW data which is always
+ * 8-byte aligned. That means we must dereference raw_data with an offset of 4.
+ * Refer perf_sample__synth_ptr() and perf_synth__raw_data().  It also means the
+ * structure sizes are 4 bytes bigger than the raw_size, refer
+ * perf_synth__raw_size().
+ */
+
+struct perf_synth_intel_ptwrite {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+	u64	payload;
+};
+
+struct perf_synth_intel_mwait {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	hints		:  8,
+				reserved1	: 24,
+				extensions	:  2,
+				reserved2	: 30;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_pwre {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	reserved1	:  7,
+				hw		:  1,
+				subcstate	:  4,
+				cstate		:  4,
+				reserved2	: 48;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_exstop {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+};
+
+struct perf_synth_intel_pwrx {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	deepest_cstate	:  4,
+				last_cstate	:  4,
+				wake_reason	:  4,
+				reserved1	: 52;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_cbr {
+	u32 padding;
+	union {
+		struct {
+			u32	cbr		:  8,
+				reserved1	:  8,
+				max_nonturbo	:  8,
+				reserved2	:  8;
+		};
+		u32	flags;
+	};
+	u32 freq;
+	u32 reserved3;
+};
+
+/*
+ * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get
+ * 8-byte alignment.
+ */
+static inline void *perf_sample__synth_ptr(struct perf_sample *sample)
+{
+	return sample->raw_data - 4;
+}
+
+static inline void *perf_synth__raw_data(void *p)
+{
+	return p + 4;
+}
+
+#define perf_synth__raw_size(d) (sizeof(d) - 4)
+
+#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4)
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 94cea4398a13..8d601fbdd8d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/refcount.h>
 #include <linux/list.h>
@@ -34,7 +35,7 @@ struct perf_mmap {
 	refcount_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
 };
 
 static inline size_t
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cda44b0e821c..6f4882f8d61f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -11,13 +11,17 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitops.h>
+#include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/compiler.h>
 #include <linux/err.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
+#include <sys/types.h>
+#include <dirent.h>
 #include "asm/bug.h"
 #include "callchain.h"
 #include "cgroup.h"
@@ -1441,7 +1445,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 }
 
 static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
-				void *priv __attribute__((unused)))
+				void *priv __maybe_unused)
 {
 	return fprintf(fp, "  %-32s %s\n", name, val);
 }
@@ -2471,6 +2475,42 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 	return false;
 }
 
+static bool find_process(const char *name)
+{
+	size_t len = strlen(name);
+	DIR *dir;
+	struct dirent *d;
+	int ret = -1;
+
+	dir = opendir(procfs__mountpoint());
+	if (!dir)
+		return false;
+
+	/* Walk through the directory. */
+	while (ret && (d = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		char *data;
+		size_t size;
+
+		if ((d->d_type != DT_DIR) ||
+		     !strcmp(".", d->d_name) ||
+		     !strcmp("..", d->d_name))
+			continue;
+
+		scnprintf(path, sizeof(path), "%s/%s/comm",
+			  procfs__mountpoint(), d->d_name);
+
+		if (filename__read_str(path, &data, &size))
+			continue;
+
+		ret = strncmp(name, data, len);
+		free(data);
+	}
+
+	closedir(dir);
+	return ret ? false : true;
+}
+
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
index 5980f7d256b1..40789d8603d0 100644
--- a/tools/perf/util/genelf_debug.c
+++ b/tools/perf/util/genelf_debug.c
@@ -11,6 +11,7 @@
  * @remark Copyright 2007 OProfile authors
  * @author Philippe Elie
  */
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <getopt.h>
@@ -125,7 +126,7 @@ struct debug_line_header {
 	 * and filesize, last entry is followed by en empty string.
 	 */
 	/* follow the first program statement */
-} __attribute__((packed));
+} __packed;
 
 /* DWARF 2 spec talk only about one possible compilation unit header while
  * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
@@ -138,7 +139,7 @@ struct compilation_unit_header {
 	uhalf version;
 	uword debug_abbrev_offset;
 	ubyte pointer_size;
-} __attribute__((packed));
+} __packed;
 
 #define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b5baff3007bb..76ed7d03e500 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -8,6 +8,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
@@ -1274,7 +1275,7 @@ error:
 }
 
 static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val,
-				void *priv __attribute__((unused)))
+				void *priv __maybe_unused)
 {
 	return fprintf(fp, ", %s = %s", name, val);
 }
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 1c88ad6425b8..15b95300d7f3 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -12,7 +12,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value,
 				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
-		autocorrect = perf_config_int(var,value);
+		return perf_config_int(&autocorrect, var,value);
 
 	return 0;
 }
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index b2834ac7b1f5..218ee2bac9a5 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -866,8 +866,6 @@ static void intel_bts_print_info(u64 *arr, int start, int finish)
 		fprintf(stdout, intel_bts_info_fmts[i], arr[i]);
 }
 
-u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE];
-
 int intel_bts_process_auxtrace_info(union perf_event *event,
 				    struct perf_session *session)
 {
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 7cf7f7aca4d2..aa1593ce551d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -64,6 +64,25 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_FUP_NO_TIP,
 };
 
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+	switch (pkt_state) {
+	case INTEL_PT_STATE_NO_PSB:
+	case INTEL_PT_STATE_NO_IP:
+	case INTEL_PT_STATE_ERR_RESYNC:
+	case INTEL_PT_STATE_IN_SYNC:
+	case INTEL_PT_STATE_TNT:
+		return true;
+	case INTEL_PT_STATE_TIP:
+	case INTEL_PT_STATE_TIP_PGD:
+	case INTEL_PT_STATE_FUP:
+	case INTEL_PT_STATE_FUP_NO_TIP:
+		return false;
+	default:
+		return true;
+	};
+}
+
 #ifdef INTEL_PT_STRICT
 #define INTEL_PT_STATE_ERR1	INTEL_PT_STATE_NO_PSB
 #define INTEL_PT_STATE_ERR2	INTEL_PT_STATE_NO_PSB
@@ -87,11 +106,13 @@ struct intel_pt_decoder {
 	const unsigned char *buf;
 	size_t len;
 	bool return_compression;
+	bool branch_enable;
 	bool mtc_insn;
 	bool pge;
 	bool have_tma;
 	bool have_cyc;
 	bool fixup_last_mtc;
+	bool have_last_ip;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;
@@ -99,6 +120,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
 	uint64_t ctc_delta;
@@ -119,6 +141,7 @@ struct intel_pt_decoder {
 	int pkt_len;
 	int last_packet_type;
 	unsigned int cbr;
+	unsigned int cbr_seen;
 	unsigned int max_non_turbo_ratio;
 	double max_non_turbo_ratio_fp;
 	double cbr_cyc_to_tsc;
@@ -136,9 +159,18 @@ struct intel_pt_decoder {
 	bool continuous_period;
 	bool overflow;
 	bool set_fup_tx_flags;
+	bool set_fup_ptw;
+	bool set_fup_mwait;
+	bool set_fup_pwre;
+	bool set_fup_exstop;
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
+	uint64_t fup_ptw_payload;
+	uint64_t fup_mwait_payload;
+	uint64_t fup_pwre_payload;
+	uint64_t cbr_payload;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;
@@ -192,6 +224,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->pgd_ip             = params->pgd_ip;
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
+	decoder->branch_enable      = params->branch_enable;
 
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
@@ -398,6 +431,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
 	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
+	decoder->have_last_ip = true;
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -635,6 +669,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 	case INTEL_PT_PAD:
 	case INTEL_PT_VMCS:
 	case INTEL_PT_MNT:
+	case INTEL_PT_PTWRITE:
+	case INTEL_PT_PTWRITE_IP:
 		return 0;
 
 	case INTEL_PT_MTC:
@@ -675,6 +711,12 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 		break;
 
 	case INTEL_PT_TSC:
+		/*
+		 * For now, do not support using TSC packets - refer
+		 * intel_pt_calc_cyc_to_tsc().
+		 */
+		if (data->from_mtc)
+			return 1;
 		timestamp = pkt_info->packet.payload |
 			    (data->timestamp & (0xffULL << 56));
 		if (data->from_mtc && timestamp < data->timestamp &&
@@ -733,6 +775,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 
 	case INTEL_PT_TIP_PGD