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

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

   - add support for Intel's "adaptive PEBS v4" - which embedds LBS data
     in PEBS records and can thus batch up and reduce the IRQ (NMI) rate
     significantly - reducing overhead and making call-graph profiling
     less intrusive.

   - add Intel CPU core and uncore support updates for Tremont, Icelake,

   - extend the x86 PMU constraints scheduler with 'constraint ranges'
     to better support Icelake hw constraints,

   - make x86 call-chain support work better with CONFIG_FRAME_POINTER=y

   - misc other changes

  Tooling changes:

   - updates to the main tools: 'perf record', 'perf trace', 'perf
     stat'

   - updated Intel and S/390 vendor events

   - libtraceevent updates

   - misc other updates and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER
  watchdog: Fix typo in comment
  perf/x86/intel: Add Tremont core PMU support
  perf/x86/intel/uncore: Add Intel Icelake uncore support
  perf/x86/msr: Add Icelake support
  perf/x86/intel/rapl: Add Icelake support
  perf/x86/intel/cstate: Add Icelake support
  perf/x86/intel: Add Icelake support
  perf/x86: Support constraint ranges
  perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them
  perf/x86/intel: Support adaptive PEBS v4
  perf/x86/intel/ds: Extract code of event update in short period
  perf/x86/intel: Extract memory code PEBS parser for reuse
  perf/x86: Support outputting XMM registers
  perf/x86/intel: Force resched when TFA sysctl is modified
  perf/core: Add perf_pmu_resched() as global function
  perf/headers: Fix stale comment for struct perf_addr_filter
  perf/core: Make perf_swevent_init_cpu() static
  perf/x86: Add sanity checks to x86_schedule_events()
  perf/x86: Optimize x86_schedule_events()
  ...

98 files changed, 11123 insertions, 6896 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8fe4dffcadd0..58986f4cc190 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo
   node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
   cpu  - thread affinity mask is set to cpu of the processed mmap buffer
 
+--mmap-flush=number::
+
+Specify minimal number of bytes that is extracted from mmap data pages and
+processed for output. One can specify the number using B/K/M/G suffixes.
+
+The maximal allowed value is a quarter of the size of mmaped data pages.
+
+The default option value is 1 byte which means that every time that the output
+writing thread finds some new data in the mmaped buffer the data is extracted,
+possibly compressed (-z) and written to the output, perf.data or pipe.
+
+Larger data chunks are compressed more effectively in comparison to smaller
+chunks so extraction of larger chunks from the mmap data pages is preferable
+from the perspective of output size reduction.
+
+Also at some cases executing less output write syscalls with bigger data size
+can take less time than executing more output write syscalls with smaller data
+size thus lowering runtime profiling overhead.
+
 --all-kernel::
 Configure all used events to run in kernel space.
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6d65874e16c3..0c52a01dc759 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -152,6 +152,13 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
+ifdef LIBZSTD_DIR
+  LIBZSTD_CFLAGS  := -I$(LIBZSTD_DIR)/lib
+  LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
+
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -787,6 +794,19 @@ ifndef NO_LZMA
   endif
 endif
 
+ifndef NO_LIBZSTD
+  ifeq ($(feature-libzstd), 1)
+    CFLAGS += -DHAVE_ZSTD_SUPPORT
+    CFLAGS += $(LIBZSTD_CFLAGS)
+    LDFLAGS += $(LIBZSTD_LDFLAGS)
+    EXTLIBS += -lzstd
+    $(call detected,CONFIG_ZSTD)
+  else
+    msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR);
+    NO_LIBZSTD := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e8c9f77e9010..c706548d5b10 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -108,6 +108,9 @@ include ../scripts/utilities.mak
 # streaming for record mode. Currently Posix AIO trace streaming is
 # supported only when linking with glibc.
 #
+# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
+# trace compression in record mode.
+#
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fa520f4b8095..b80eee455111 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv)
 			goto out_delete;
 		}
 
-		kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
+		kmem_page_size = tep_get_page_size(evsel->tp_format->tep);
 		symbol_conf.use_callchain = true;
 	}
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index a8394b4f1167..e0312a1c4792 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv)
 			print_symbol_events(NULL, PERF_TYPE_HARDWARE,
 					event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 		else if (strcmp(argv[i], "sw") == 0 ||
-			 strcmp(argv[i], "software") == 0)
+			 strcmp(argv[i], "software") == 0) {
 			print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
-		else if (strcmp(argv[i], "cache") == 0 ||
+			print_tool_events(NULL, raw_dump);
+		} else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
@@ -113,6 +114,7 @@ int cmd_list(int argc, const char **argv)
 					    event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 			print_symbol_events(s, PERF_TYPE_SOFTWARE,
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+			print_tool_events(s, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
 						long_desc_flag,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e2d953d4bc5..c5e10552776a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -337,6 +337,41 @@ static int record__aio_enabled(struct record *rec)
 	return rec->opts.nr_cblocks > 0;
 }
 
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+				    const char *str,
+				    int unset)
+{
+	int flush_max;
+	struct record_opts *opts = (struct record_opts *)opt->value;
+	static struct parse_tag tags[] = {
+			{ .tag  = 'B', .mult = 1       },
+			{ .tag  = 'K', .mult = 1 << 10 },
+			{ .tag  = 'M', .mult = 1 << 20 },
+			{ .tag  = 'G', .mult = 1 << 30 },
+			{ .tag  = 0 },
+	};
+
+	if (unset)
+		return 0;
+
+	if (str) {
+		opts->mmap_flush = parse_tag_value(str, tags);
+		if (opts->mmap_flush == (int)-1)
+			opts->mmap_flush = strtol(str, NULL, 0);
+	}
+
+	if (!opts->mmap_flush)
+		opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+	flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+	flush_max /= 4;
+	if (opts->mmap_flush > flush_max)
+		opts->mmap_flush = flush_max;
+
+	return 0;
+}
+
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -546,7 +581,8 @@ static int record__mmap_evlist(struct record *rec,
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
-				 opts->nr_cblocks, opts->affinity) < 0) {
+				 opts->nr_cblocks, opts->affinity,
+				 opts->mmap_flush) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -736,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
 }
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-				    bool overwrite)
+				    bool overwrite, bool synch)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
@@ -759,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		off = record__aio_get_pos(trace_fd);
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		u64 flush = 0;
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
 			record__adjust_affinity(rec, map);
+			if (synch) {
+				flush = map->flush;
+				map->flush = 1;
+			}
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+					if (synch)
+						map->flush = flush;
 					rc = -1;
 					goto out;