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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Intel Knights Landing support.  (Harish Chegondi)

   - Intel Broadwell-EP uncore PMU support.  (Kan Liang)

   - Core code improvements.  (Peter Zijlstra.)

   - Event filter, LBR and PEBS fixes.  (Stephane Eranian)

   - Enable cycles:pp on Intel Atom.  (Stephane Eranian)

   - Add cycles:ppp support for Skylake.  (Andi Kleen)

   - Various x86 NMI overhead optimizations.  (Andi Kleen)

   - Intel PT enhancements.  (Takao Indoh)

   - AMD cache events fix.  (Vince Weaver)

  Tons of tooling changes:

   - Show random perf tool tips in the 'perf report' bottom line
     (Namhyung Kim)

   - perf report now defaults to --group if the perf.data file has
     grouped events, try it with:

      # perf record -e '{cycles,instructions}' -a sleep 1
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
      # perf report
      # Samples: 1K of event 'anon group { cycles, instructions }'
      # Event count (approx.): 1955219195
      #
      #       Overhead  Command     Shared Object      Symbol

         2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
         1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
         1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
         0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
         0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
         0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
         0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
         0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
         0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

   - Introduce the 'perf stat record/report' workflow:

     Generate perf.data files from 'perf stat', to tap into the
     scripting capabilities perf has instead of defining a 'perf stat'
     specific scripting support to calculate event ratios, etc.

     Simple example:

        $ perf stat record -e cycles usleep 1

         Performance counter stats for 'usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $ perf stat report

         Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $

     It generates PERF_RECORD_ userspace records to store the details:

        $ perf report -D | grep PERF_RECORD
        0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
        0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
        0x12a [0x40]: PERF_RECORD_STAT_CONFIG
        0x16a [0x30]: PERF_RECORD_STAT
        -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
        0x1da [0x18]: PERF_RECORD_STAT_ROUND
        [acme@ssdandy linux]$

     An effort was made to make perf.data files generated like this to
     not generate cryptic messages when processed by older tools.

     The 'perf script' bits need rebasing, will go up later.

   - Make command line options always available, even when they depend
     on some feature being enabled, warning the user about use of such
     options (Wang Nan)

   - Support hw breakpoint events (mem:0xAddress) in the default output
     mode in 'perf script' (Wang Nan)

   - Fixes and improvements for supporting annotating ARM binaries,
     support ARM call and jump instructions, more work needed to have
     arch specific stuff separated into tools/perf/arch/*/annotate/
     (Russell King)

   - Add initial 'perf config' command, for now just with a --list
     command to the contents of the configuration file in use and a
     basic man page describing its format, commands for doing edits and
     detailed documentation are being reviewed and proof-read.  (Taeung
     Song)

   - Allows BPF scriptlets specify arguments to be fetched using DWARF
     info, using a prologue generated at compile/build time (He Kuang,
     Wang Nan)

   - Allow attaching BPF scriptlets to module symbols (Wang Nan)

   - Allow attaching BPF scriptlets to userspace code using uprobe (Wang
     Nan)

   - BPF programs now can specify 'perf probe' tunables via its section
     name, separating key=val values using semicolons (Wang Nan)

     Testing some of these new BPF features:

        Use case: get callchains when receiving SSL packets, filter then in the
                  kernel, at arbitrary place.

        # cat ssl.bpf.c
        #define SEC(NAME) __attribute__((section(NAME), used))

        struct pt_regs;

        SEC("func=__inet_lookup_established hnum")
        int func(struct pt_regs *ctx, int err, unsigned short port)
        {
                return err == 0 && port == 443;
        }

        char _license[] SEC("license") = "GPL";
        int  _version   SEC("version") = LINUX_VERSION_CODE;
        #
        # perf record -a -g -e ssl.bpf.c
        ^C[ perf record: Woken up 1 times to write data ]
        [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
        # perf script | head -30
        swapper     0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
           856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
           2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
           2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
           96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
           969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
           2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
           95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
          1163ffa start_kernel ([kernel.vmlinux].init.text)
          11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
          1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)

        qemu-system-x86  9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
           8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
             430a br_handle_frame_finish ([bridge])
             48bc br_handle_frame ([bridge])
           855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
        #

   - Use 'perf probe' various options to list functions, see what
     variables can be collected at any given point, experiment first
     collecting without a filter, then filter, use it together with
     'perf trace', 'perf top', with or without callchains, if it
     explodes, please tell us!

   - Introduce a new callchain mode: "folded", that will list per line
     representations of all callchains for a give histogram entry,
     facilitating 'perf report' output processing by other tools, such
     as Brendan Gregg's flamegraph tools (Namhyung Kim)

     E.g:

        # perf report | grep -v ^# | head
           18.37%     0.00%  swapper  [kernel.kallsyms]   [k] cpu_startup_entry
                           |
                           ---cpu_startup_entry
                              |
                              |--12.07%--start_secondary
                              |
                               --6.30%--rest_init
                                         start_kernel
                                         x86_64_start_reservations
                                         x86_64_start_kernel
         #

     Becomes, in "folded" mode:

        # perf report -g folded | grep -v ^# | head -5
            18.37%     0.00%  swapper [kernel.kallsyms]   [k] cpu_startup_entry
          12.07% cpu_startup_entry;start_secondary
           6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] call_cpuidle
          11.23% call_cpuidle;cpu_startup_entry;start_secondary
           5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter
          11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
           5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            15.12%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter_state
         #

     The user can also select one of "count", "period" or "percent" as
     the first column.

  ... and lots of infrastructure enhancements, plus fixes and other
  changes, features I failed to list - see the shortlog and the git log
  for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
  perf evlist: Add --trace-fields option to show trace fields
  perf record: Store data mmaps for dwarf unwind
  perf libdw: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Use find_map function in access_dso_mem
  perf evlist: Remove perf_evlist__(enable|disable)_event functions
  perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
  perf report: Show random usage tip on the help line
  perf hists: Export a couple of hist functions
  perf diff: Use perf_hpp__register_sort_field interface
  perf tools: Add overhead/overhead_children keys defaults via string
  perf tools: Remove list entry from struct sort_entry
  perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
  perf script: Align event name properly
  perf tools: Add missing headers in perf's MANIFEST
  perf tools: Do not show trace command if it's not compiled in
  perf report: Change default to use event group view
  perf top: Decay periods in callchains
  tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
  tools lib: Sync tools/lib/find_bit.c with the kernel
  ...

1 files changed, 308 insertions, 0 deletions

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8b10621b415c..cd61bb1f3917 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -10,6 +10,8 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "symbol/kallsyms.h"
+#include "asm/bug.h"
+#include "stat.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
@@ -37,6 +39,12 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
 	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
 	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
+	[PERF_RECORD_THREAD_MAP]		= "THREAD_MAP",
+	[PERF_RECORD_CPU_MAP]			= "CPU_MAP",
+	[PERF_RECORD_STAT_CONFIG]		= "STAT_CONFIG",
+	[PERF_RECORD_STAT]			= "STAT",
+	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
+	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -699,6 +707,274 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	union perf_event *event;
+	int i, err, size;
+
+	size  = sizeof(event->thread_map);
+	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_THREAD_MAP;
+	event->header.size = size;
+	event->thread_map.nr = threads->nr;
+
+	for (i = 0; i < threads->nr; i++) {
+		struct thread_map_event_entry *entry = &event->thread_map.entries[i];
+		char *comm = thread_map__comm(threads, i);
+
+		if (!comm)
+			comm = (char *) "";
+
+		entry->pid = thread_map__pid(threads, i);
+		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+	}
+
+	err = process(tool, event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+			    struct cpu_map *map)
+{
+	int i;
+
+	cpus->nr = map->nr;
+
+	for (i = 0; i < map->nr; i++)
+		cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct cpu_map_mask *mask,
+			    struct cpu_map *map, int max)
+{
+	int i;
+
+	mask->nr = BITS_TO_LONGS(max);
+	mask->long_size = sizeof(long);
+
+	for (i = 0; i < map->nr; i++)
+		set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct cpu_map *map)
+{
+	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct cpu_map *map, int *max)
+{
+	int i;
+
+	*max = 0;
+
+	for (i = 0; i < map->nr; i++) {
+		/* bit possition of the cpu is + 1 */
+		int bit = map->map[i] + 1;
+
+		if (bit > *max)
+			*max = bit;
+	}
+
+	return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
+{
+	size_t size_cpus, size_mask;
+	bool is_dummy = cpu_map__empty(map);
+
+	/*
+	 * Both array and mask data have variable size based
+	 * on the number of cpus and their actual values.
+	 * The size of the 'struct cpu_map_data' is:
+	 *
+	 *   array = size of 'struct cpu_map_entries' +
+	 *           number of cpus * sizeof(u64)
+	 *
+	 *   mask  = size of 'struct cpu_map_mask' +
+	 *           maximum cpu bit converted to size of longs
+	 *
+	 * and finaly + the size of 'struct cpu_map_data'.
+	 */
+	size_cpus = cpus_size(map);
+	size_mask = mask_size(map, max);
+
+	if (is_dummy || (size_cpus < size_mask)) {
+		*size += size_cpus;
+		*type  = PERF_CPU_MAP__CPUS;
+	} else {
+		*size += size_mask;
+		*type  = PERF_CPU_MAP__MASK;
+	}
+
+	*size += sizeof(struct cpu_map_data);
+	return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+			      u16 type, int max)
+{
+	data->type = type;
+
+	switch (type) {
+	case PERF_CPU_MAP__CPUS:
+		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		break;
+	case PERF_CPU_MAP__MASK:
+		synthesize_mask((struct cpu_map_mask *) data->data, map, max);
+	default:
+		break;
+	};
+}
+
+static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
+{
+	size_t size = sizeof(struct cpu_map_event);
+	struct cpu_map_event *event;
+	int max;
+	u16 type;
+
+	event = cpu_map_data__alloc(map, &size, &type, &max);
+	if (!event)
+		return NULL;
+
+	event->header.type = PERF_RECORD_CPU_MAP;
+	event->header.size = size;
+	event->data.type   = type;
+
+	cpu_map_data__synthesize(&event->data, map, type, max);
+	return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct cpu_map *map,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	struct cpu_map_event *event;
+	int err;
+
+	event = cpu_map_event__new(map);
+	if (!event)
+		return -ENOMEM;
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	struct stat_config_event *event;
+	int size, i = 0, err;
+
+	size  = sizeof(*event);
+	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_STAT_CONFIG;
+	event->header.size = size;
+	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)					\
+	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
+	event->data[i].val = __val;				\
+	i++;
+
+	ADD(AGGR_MODE,	config->aggr_mode)
+	ADD(INTERVAL,	config->interval)
+	ADD(SCALE,	config->scale)
+
+	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+		  "stat config terms unbalanced\n");
+#undef ADD
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	struct stat_event event;
+
+	event.header.type = PERF_RECORD_STAT;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.id        = id;
+	event.cpu       = cpu;
+	event.thread    = thread;
+	event.val       = count->val;
+	event.ena       = count->ena;
+	event.run       = count->run;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 evtime, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	struct stat_round_event event;
+
+	event.header.type = PERF_RECORD_STAT_ROUND;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.time = evtime;
+	event.type = type;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct stat_config_event *event)
+{
+	unsigned i;
+
+	for (i = 0; i < event->nr; i++) {
+
+		switch (event->data[i].tag) {
+#define CASE(__term, __val)					\
+		case PERF_STAT_CONFIG_TERM__##__term:		\
+			config->__val = event->data[i].val;	\
+			break;
+
+		CASE(AGGR_MODE, aggr_mode)
+		CASE(SCALE,     scale)
+		CASE(INTERVAL,  interval)
+#undef CASE
+		default:
+			pr_warning("unknown stat config term %" PRIu64 "\n",
+				   event->data[i].tag);
+		}
+	}
+}
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
 	const char *s;
@@ -783,6 +1059,38 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 		       event->mmap2.filename);
 }
 
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
+{
+	struct thread_map *threads = thread_map__new_event(&event->thread_map);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (threads)
+		ret += thread_map__fprintf(threads, fp);
+	else
+		ret += fprintf(fp, "failed to get threads from event\n");
+
+	thread_map__put(threads);
+	return ret;
+}
+
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
+{
+	struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (cpus)
+		ret += cpu_map__fprintf(cpus, fp);
+	else
+		ret += fprintf(fp, "failed to get cpumap from event\n");
+
+	cpu_map__put(cpus);
+	return ret;
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,