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

Pull perf changes from Ingo Molnar:
 "Main changes:

  Kernel side changes:

   - Add SNB/IVB/HSW client uncore memory controller support (Stephane
     Eranian)

   - Fix various x86/P4 PMU driver bugs (Don Zickus)

  Tooling, user visible changes:

   - Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso)

   - Speed up thread map generation (Don Zickus)

   - Introduce 'perf kvm --list-cmds' command line option for use by
     scripts (Ramkumar Ramachandra)

   - Print the evsel name in the annotate stdio output, prep to fix
     support outputting annotation for multiple events, not just for the
     first one (Arnaldo Carvalho de Melo)

   - Allow setting preferred callchain method in .perfconfig (Jiri Olsa)

   - Show in what binaries/modules 'perf probe's are set (Masami
     Hiramatsu)

   - Support distro-style debuginfo for uprobe in 'perf probe' (Masami
     Hiramatsu)

  Tooling, internal changes and fixes:

   - Use tid in mmap/mmap2 events to find maps (Don Zickus)

   - Record the reason for filtering an address_location (Namhyung Kim)

   - Apply all filters to an addr_location (Namhyung Kim)

   - Merge al->filtered with hist_entry->filtered in report/hists
     (Namhyung Kim)

   - Fix memory leak when synthesizing thread records (Namhyung Kim)

   - Use ui__has_annotation() in 'report' (Namhyung Kim)

   - hists browser refactorings to reuse code accross UIs (Namhyung Kim)

   - Add support for the new DWARF unwinder library in elfutils (Jiri
     Olsa)

   - Fix build race in the generation of bison files (Jiri Olsa)

   - Further streamline the feature detection display, trimming it a bit
     to show just the libraries detected, using VF=1 gets a more verbose
     output, showing the less interesting feature checks as well (Jiri
     Olsa).

   - Check compatible symtab type before loading dso (Namhyung Kim)

   - Check return value of filename__read_debuglink() (Stephane Eranian)

   - Move some hashing and fs related code from tools/perf/util/ to
     tools/lib/ so that it can be used by more tools/ living utilities
     (Borislav Petkov)

   - Prepare DWARF unwinding code for using an elfutils alternative
     unwinding library (Jiri Olsa)

   - Fix DWARF unwind max_stack processing (Jiri Olsa)

   - Add dwarf unwind 'perf test' entry (Jiri Olsa)

   - 'perf probe' improvements including memory leak fixes, sharing the
     intlist class with other tools, uprobes/kprobes code sharing and
     use of ref_reloc_sym (Masami Hiramatsu)

   - Shorten sample symbol resolving by adding cpumode to struct
     addr_location (Arnaldo Carvalho de Melo)

   - Fix synthesizing mmaps for threads (Don Zickus)

   - Fix invalid output on event group stdio report (Namhyung Kim)

   - Fixup header alignment in 'perf sched latency' output (Ramkumar
     Ramachandra)

   - Fix off-by-one error in 'perf timechart record' argv handling
     (Ramkumar Ramachandra)

  Tooling, cleanups:

   - Remove unused thread__find_map function (Jiri Olsa)

   - Remove unused simple_strtoul() function (Ramkumar Ramachandra)

  Tooling, documentation updates:

   - Update function names in debug messages (Ramkumar Ramachandra)

   - Update some code references in design.txt (Ramkumar Ramachandra)

   - Clarify load-latency information in the 'perf mem' docs (Andi
     Kleen)

   - Clarify x86 register naming in 'perf probe' docs (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (96 commits)
  perf tools: Remove unused simple_strtoul() function
  perf tools: Update some code references in design.txt
  perf evsel: Update function names in debug messages
  perf tools: Remove thread__find_map function
  perf annotate: Print the evsel name in the stdio output
  perf report: Use ui__has_annotation()
  perf tools: Fix memory leak when synthesizing thread records
  perf tools: Use tid in mmap/mmap2 events to find maps
  perf report: Merge al->filtered with hist_entry->filtered
  perf symbols: Apply all filters to an addr_location
  perf symbols: Record the reason for filtering an address_location
  perf sched: Fixup header alignment in 'latency' output
  perf timechart: Fix off-by-one error in 'record' argv handling
  perf machine: Factor machine__find_thread to take tid argument
  perf tools: Speed up thread map generation
  perf kvm: introduce --list-cmds for use by scripts
  perf ui hists: Pass evsel to hpp->header/width functions explicitly
  perf symbols: Introduce thread__find_cpumode_addr_location
  perf session: Change header.misc dump from decimal to hex
  perf ui/tui: Reuse generic __hpp__fmt() code
  ...

7 files changed, 185 insertions, 21 deletions

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 1e67437fb4ca..b11bf8a08430 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,6 +115,14 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+#endif
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..c059ee81c038
--- /dev/null
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -0,0 +1,144 @@
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample __maybe_unused,
+			struct machine *machine)
+{
+	return machine__process_mmap_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+	union perf_event event;
+	pid_t pid = getpid();
+
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 6
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	unsigned long *cnt = (unsigned long *) arg;
+	char *symbol = entry->sym ? entry->sym->name : NULL;
+	static const char *funcs[MAX_STACK] = {
+		"test__arch_unwind_sample",
+		"unwind_thread",
+		"krava_3",
+		"krava_2",
+		"krava_1",
+		"test__dwarf_unwind"
+	};
+
+	if (*cnt >= MAX_STACK) {
+		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+		return -1;
+	}
+
+	if (!symbol) {
+		pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+			 entry->ip);
+		return -1;
+	}
+
+	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread, struct machine *machine)
+{
+	struct perf_sample sample;
+	unsigned long cnt = 0;
+	int err = -1;
+
+	memset(&sample, 0, sizeof(sample));
+
+	if (test__arch_unwind_sample(&sample, thread)) {
+		pr_debug("failed to get unwind sample\n");
+		goto out;
+	}
+
+	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+				  &sample, MAX_STACK);
+	if (err)
+		pr_debug("unwind failed\n");
+	else if (cnt != MAX_STACK) {
+		pr_debug("got wrong number of stack entries %lu != %d\n",
+			 cnt, MAX_STACK);
+		err = -1;
+	}
+
+ out:
+	free(sample.user_stack.data);
+	free(sample.user_regs.regs);
+	return err;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread, struct machine *machine)
+{
+	return unwind_thread(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread, struct machine *machine)
+{
+	return krava_3(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread, struct machine *machine)
+{
+	return krava_2(thread, machine);
+}
+
+int test__dwarf_unwind(void)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	int err = -1;
+
+	machines__init(&machines);
+
+	machine = machines__find(&machines, HOST_KERNEL_ID);
+	if (!machine) {
+		pr_err("Could not get machine\n");
+		return -1;
+	}
+
+	if (init_live_machine(machine)) {
+		pr_err("Could not init machine\n");
+		goto out;
+	}
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	thread = machine__find_thread(machine, getpid(), getpid());
+	if (!thread) {
+		pr_err("Could not get thread\n");
+		goto out;
+	}
+
+	err = krava_1(thread, machine);
+
+ out:
+	machine__delete_threads(machine);
+	machine__exit(machine);
+	machines__exit(&machines);
+	return err;
+}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 2b6519e0e36f..7ccbc7b6ae77 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -101,6 +101,7 @@ static struct machine *setup_fake_machine(struct machines *machines)
 			.mmap = {
 				.header = { .misc = PERF_RECORD_MISC_USER, },
 				.pid = fake_mmap_info[i].pid,
+				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
 				.len = 0x1000ULL,
 				.pgoff = 0ULL,
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 00544b8b644b..5daeae1cb4c0 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -27,6 +27,7 @@ make_no_ui          := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
 make_no_demangle    := NO_DEMANGLE=1
 make_no_libelf      := NO_LIBELF=1
 make_no_libunwind   := NO_LIBUNWIND=1
+make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1
 make_no_backtrace   := NO_BACKTRACE=1
 make_no_libnuma     := NO_LIBNUMA=1
 make_no_libaudit    := NO_LIBAUDIT=1
@@ -35,8 +36,9 @@ make_tags           := tags
 make_cscope         := cscope
 make_help           := help
 make_doc            := doc
-make_perf_o         := perf.o
-make_util_map_o     := util/map.o
+make_perf_o           := perf.o
+make_util_map_o       := util/map.o
+make_util_pmu_bison_o := util/pmu-bison.o
 make_install        := install
 make_install_bin    := install-bin
 make_install_doc    := install-doc
@@ -49,6 +51,7 @@ make_install_pdf    := install-pdf
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -65,6 +68,7 @@ run += make_no_ui
 run += make_no_demangle
 run += make_no_libelf
 run += make_no_libunwind
+run += make_no_libdw_dwarf_unwind
 run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
@@ -73,6 +77,7 @@ run += make_help
 run += make_doc
 run += make_perf_o
 run += make_util_map_o
+run += make_util_pmu_bison_o
 run += make_install
 run += make_install_bin
 # FIXME 'install-*' commented out till they're fixed
@@ -113,8 +118,9 @@ test_make_doc_O  := $(test_ok)
 
 test_make_python_perf_so := test -f $(PERF)/python/perf.so
 
-test_make_perf_o     := test -f $(PERF)/perf.o
-test_make_util_map_o := test -f $(PERF)/util/map.o
+test_make_perf_o           := test -f $(PERF)/perf.o
+test_make_util_map_o       := test -f $(PERF)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
 
 define test_dest_files
   for file in $(1); do				\
@@ -167,13 +173,10 @@ test_make_install_info_O := $(test_ok)
 test_make_install_pdf    := $(test_ok)
 test_make_install_pdf_O  := $(test_ok)
 
-# Kbuild tests only
-#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
-#test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
-#test_make_util_map_o_O     := test -f $$TMP/tools/perf/util/map.o
-
-test_make_perf_o_O     := true
-test_make_util_map_o_O := true
+test_make_python_perf_so_O    := test -f $$TMP_O/python/perf.so
+test_make_perf_o_O            := test -f $$TMP_O/perf.o
+test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
+test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
 
 test_default = test -x $(PERF)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 4db0ae617d70..8605ff5572ae 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2,7 +2,7 @@
 #include "parse-events.h"
 #include "evsel.h"
 #include "evlist.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 1b677202638d..0014d3c8c21c 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -22,8 +22,8 @@
 } while (0)
 
 static bool samples_same(const struct perf_sample *s1,
-			 const struct perf_sample *s2, u64 type, u64 regs_user,
-			 u64 read_format)
+			 const struct perf_sample *s2,
+			 u64 type, u64 read_format)
 {
 	size_t i;
 
@@ -95,8 +95,9 @@ static bool samples_same(const struct perf_sample *s1,
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
-		size_t sz = hweight_long(regs_user) * sizeof(u64);
+		size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64);
 
+		COMP(user_regs.mask);
 		COMP(user_regs.abi);
 		if (s1->user_regs.abi &&
 		    (!s1->user_regs.regs || !s2->user_regs.regs ||
@@ -174,6 +175,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs_user,
 			.regs	= user_regs,
 		},
 		.user_stack	= {
@@ -201,8 +203,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		sample.read.one.id    = 99;
 	}
 
-	sz = perf_event__sample_event_size(&sample, sample_type,
-					   sample_regs_user, read_format);
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
 	bufsz = sz + 4096; /* Add a bit for overrun checking */
 	event = malloc(bufsz);
 	if (!event) {
@@ -215,8 +216,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 	event->header.misc = 0;
 	event->header.size = sz;
 
-	err = perf_event__synthesize_sample(event, sample_type,
-					    sample_regs_user, read_format,
+	err = perf_event__synthesize_sample(event, sample_type, read_format,
 					    &sample, false);
 	if (err) {
 		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
@@ -244,8 +244,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		goto out_free;
 	}
 
-	if (!samples_same(&sample, &sample_out, sample_type,
-			  sample_regs_user, read_format)) {
+	if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
 		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
 			 sample_type);
 		goto out_free;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index e0ac713857ba..a24795ca002d 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -40,5 +40,14 @@ int test__code_reading(void);
 int test__sample_parsing(void);
 int test__keep_tracking(void);
 int test__parse_no_sample_id_all(void);
+int test__dwarf_unwind(void);
 
+#if defined(__x86_64__) || defined(__i386__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+#endif
 #endif /* TESTS_H */