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

Pull perf events update from Ingo Molnar:
 "On the kernel side there's few changes, the one that stands out is
  PEBS machine state sampling support on x86, by Stephane Eranian.

  On the tooling side:

  User visible tooling changes:

   - Don't open the DWARF info multiple times, keeping instead a dwfl
     handle in struct dso, greatly speeding up 'perf report' on powerpc.
     (Sukadev Bhattiprolu)

   - Introduce PARSE_OPT_DISABLED option flag and use it to avoid
     showing undersired options in tools that provides frontends to
     'perf record', like sched, kvm, etc (Namhyung Kim)

   - Fallback to kallsyms when using the minimal 'ELF' loader (Arnaldo
     Carvalho de Melo)

   - Fix annotation with kcore (Adrian Hunter)

   - Support source line numbers in annotate using a hotkey (Andi Kleen)

   - Callchain improvements including:
     * Enable printing the srcline in the history
     * Make get_srcline fall back to sym+offset (Andi Kleen)

   - TUI hist_entry browser fixes, including showing missing overhead
     value for first level callchain.  Detected comparing the output of
     --stdio/--gui (that matched) with --tui, that had this problem.
     (Namhyung Kim)

   - Support handling complete branch stacks as histograms (Andi Kleen)

  Tooling infrastructure changes:

   - Prep work for supporting per-pkg and snapshot counters in 'perf
     stat' (Jiri Olsa)

   - 'perf stat' refactorings, moving stuff from it to evsel.c to use in
     per-pkg/snapshot format changes (Jiri Olsa)

   - Add per-pkg format file parsing (Matt Fleming)

   - Clean up libelf feature support code (Namhyung Kim)

   - Add gzip decompression support for kernel modules (Namhyung Kim)

   - More prep patches for Intel PT, including a a thread stack and more
     stuff made available via the database export mechanism (Adrian
     Hunter)

   - More Intel PT work, including a facility to export sample data
     (comms, threads, symbol names, etc) in a database friendly way,
     with an script to use this to create a postgresql database.
     (Adrian Hunter)

   - Make sure that thread->mg->machine points to the machine where the
     thread exists (it was being set only for the kmaps kernel modules
     case, do it as well for the mmaps) and use it to shorten function
     signatures (Arnaldo Carvalho de Melo)

  ... and lots of other fixes and smaller improvements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (91 commits)
  perf report: In branch stack mode use address history sorting
  perf report: Add --branch-history option
  perf callchain: Support handling complete branch stacks as histograms
  perf stat: Add support for snapshot counters
  perf stat: Add support for per-pkg counters
  perf tools: Remove perf_evsel__read interface
  perf stat: Use read_counter in read_counter_aggr
  perf stat: Make read_counter work over the thread dimension
  perf stat: Use perf_evsel__read_cb in read_counter
  perf tools: Add snapshot format file parsing
  perf tools: Add per-pkg format file parsing
  perf evsel: Introduce perf_evsel__read_cb function
  perf evsel: Introduce perf_counts_values__scale function
  perf evsel: Introduce perf_evsel__compute_deltas function
  perf tools: Allow to force redirect pr_debug to stderr.
  perf tools: Fix segfault due to invalid kernel dso access
  perf callchain: Make get_srcline fall back to sym+offset
  perf symbols: Move bfd_demangle stubbing to its only user
  perf callchain: Enable printing the srcline in the history
  perf tools: Collapse first level callchain entry if it has sibling
  ...

6 files changed, 57 insertions, 35 deletions

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 162c978f1491..4b7d9ab0f049 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -85,7 +85,7 @@ static struct test {
 		.func = test__hists_link,
 	},
 	{
-		.desc = "Try 'use perf' in python, checking link problems",
+		.desc = "Try 'import perf' in python, checking link problems",
 		.func = test__python_use,
 	},
 	{
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 67f2d6323558..f671ec37a7c4 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -133,8 +133,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 }
 
 static int read_object_code(u64 addr, size_t len, u8 cpumode,
-			    struct thread *thread, struct machine *machine,
-			    struct state *state)
+			    struct thread *thread, struct state *state)
 {
 	struct addr_location al;
 	unsigned char buf1[BUFSZ];
@@ -145,8 +144,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
-			      &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
 	if (!al.map || !al.map->dso) {
 		pr_debug("thread__find_addr_map failed\n");
 		return -1;
@@ -170,8 +168,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		len = al.map->end - addr;
 
 	/* Read the object code using perf */
-	ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
-					len);
+	ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
+					al.addr, buf1, len);
 	if (ret_len != len) {
 		pr_debug("dso__data_read_offset failed\n");
 		return -1;
@@ -264,8 +262,7 @@ static int process_sample_event(struct machine *machine,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
-				state);
+	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index fc25e57f4a5d..ab28cca2cb97 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -59,7 +59,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 }
 
 __attribute__ ((noinline))
-static int unwind_thread(struct thread *thread, struct machine *machine)
+static int unwind_thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -72,7 +72,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 		goto out;
 	}
 
-	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+	err = unwind__get_entries(unwind_entry, &cnt, thread,
 				  &sample, MAX_STACK);
 	if (err)
 		pr_debug("unwind failed\n");
@@ -89,21 +89,21 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 }
 
 __attribute__ ((noinline))
-static int krava_3(struct thread *thread, struct machine *machine)
+static int krava_3(struct thread *thread)
 {
-	return unwind_thread(thread, machine);
+	return unwind_thread(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_2(struct thread *thread, struct machine *machine)
+static int krava_2(struct thread *thread)
 {
-	return krava_3(thread, machine);
+	return krava_3(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_1(struct thread *thread, struct machine *machine)
+static int krava_1(struct thread *thread)
 {
-	return krava_2(thread, machine);
+	return krava_2(thread);
 }
 
 int test__dwarf_unwind(void)
@@ -137,7 +137,7 @@ int test__dwarf_unwind(void)
 		goto out;
 	}
 
-	err = krava_1(thread, machine);
+	err = krava_1(thread);
 
  out:
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 5a31787cc6b9..74f257a81265 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -43,7 +43,7 @@ static struct sample fake_samples[] = {
 };
 
 static int add_hist_entries(struct perf_evlist *evlist,
-			    struct machine *machine __maybe_unused)
+			    struct machine *machine)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 4a456fef66ca..2113f1c8611f 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth)
 
 		pr_debug("looking for map %p\n", td->map);
 
-		thread__find_addr_map(thread, machine,
+		thread__find_addr_map(thread,
 				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
 				      (unsigned long) (td->map + 1), &al);
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index ca292f9a4ae2..4908c648a597 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -126,16 +126,28 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_TRANSACTION)
 		COMP(transaction);
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64);
+
+		COMP(intr_regs.mask);
+		COMP(intr_regs.abi);
+		if (s1->intr_regs.abi &&
+		    (!s1->intr_regs.regs || !s2->intr_regs.regs ||
+		     memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) {
+			pr_debug("Samples differ at 'intr_regs'\n");
+			return false;
+		}
+	}
+
 	return true;
 }
 
-static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 {
 	struct perf_evsel evsel = {
 		.needs_swap = false,
 		.attr = {
 			.sample_type = sample_type,
-			.sample_regs_user = sample_regs_user,
 			.read_format = read_format,
 		},
 	};
@@ -154,7 +166,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		/* 1 branch_entry */
 		.data = {1, 211, 212, 213},
 	};
-	u64 user_regs[64];
+	u64 regs[64];
 	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
 	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
 	struct perf_sample sample = {
@@ -176,8 +188,8 @@ 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,
+			.mask	= sample_regs,
+			.regs	= regs,
 		},
 		.user_stack	= {
 			.size	= sizeof(data),
@@ -187,14 +199,25 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 			.time_enabled = 0x030a59d664fca7deULL,
 			.time_running = 0x011b6ae553eb98edULL,
 		},
+		.intr_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs,
+			.regs	= regs,
+		},
 	};
 	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
 	struct perf_sample sample_out;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
 
-	for (i = 0; i < sizeof(user_regs); i++)
-		*(i + (u8 *)user_regs) = i & 0xfe;
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		evsel.attr.sample_regs_user = sample_regs;
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		evsel.attr.sample_regs_intr = sample_regs;
+
+	for (i = 0; i < sizeof(regs); i++)
+		*(i + (u8 *)regs) = i & 0xfe;
 
 	if (read_format & PERF_FORMAT_GROUP) {
 		sample.read.group.nr     = 4;
@@ -271,7 +294,7 @@ int test__sample_parsing(void)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;
-	u64 sample_regs_user;
+	u64 sample_regs;
 	size_t i;
 	int err;
 
@@ -280,7 +303,7 @@ int test__sample_parsing(void)
 	 * were added.  Please actually update the test rather than just change
 	 * the condition below.
 	 */
-	if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
@@ -297,22 +320,24 @@ int test__sample_parsing(void)
 			}
 			continue;
 		}
+		sample_regs = 0;
 
 		if (sample_type == PERF_SAMPLE_REGS_USER)
-			sample_regs_user = 0x3fff;
-		else
-			sample_regs_user = 0;
+			sample_regs = 0x3fff;
+
+		if (sample_type == PERF_SAMPLE_REGS_INTR)
+			sample_regs = 0xff0fff;
 
-		err = do_test(sample_type, sample_regs_user, 0);
+		err = do_test(sample_type, sample_regs, 0);
 		if (err)
 			return err;
 	}
 
 	/* Test all sample format bits together */
 	sample_type = PERF_SAMPLE_MAX - 1;
-	sample_regs_user = 0x3fff;
+	sample_regs = 0x3fff; /* shared yb intr and user regs */
 	for (i = 0; i < ARRAY_SIZE(rf); i++) {
-		err = do_test(sample_type, sample_regs_user, rf[i]);
+		err = do_test(sample_type, sample_regs, rf[i]);
 		if (err)
 			return err;
 	}