Merge tag 'perf-core-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

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

   - Add AMD Fam17h RAPL support

   - Introduce CAP_PERFMON to kernel and user space

   - Add Zhaoxin CPU support

   - Misc fixes and cleanups

  Tooling changes:

   - perf record:

     Introduce '--switch-output-event' to use arbitrary events to be
     setup and read from a side band thread and, when they take place a
     signal be sent to the main 'perf record' thread, reusing the core
     for '--switch-output' to take perf.data snapshots from the ring
     buffer used for '--overwrite', e.g.:

	# perf record --overwrite -e sched:* \
		      --switch-output-event syscalls:*connect* \
		      workload

     will take perf.data.YYYYMMDDHHMMSS snapshots up to around the
     connect syscalls.

     Add '--num-synthesize-threads' option to control degree of
     parallelism of the synthesize_mmap() code which is scanning
     /proc/PID/task/PID/maps and can be time consuming. This mimics
     pre-existing behaviour in 'perf top'.

   - perf bench:

     Add a multi-threaded synthesize benchmark and kallsyms parsing
     benchmark.

   - Intel PT support:

     Stitch LBR records from multiple samples to get deeper backtraces,
     there are caveats, see the csets for details.

     Allow using Intel PT to synthesize callchains for regular events.

     Add support for synthesizing branch stacks for regular events
     (cycles, instructions, etc) from Intel PT data.

  Misc changes:

   - Updated perf vendor events for power9 and Coresight.

   - Add flamegraph.py script via 'perf flamegraph'

   - Misc other changes, fixes and cleanups - see the Git log for details

  Also, since over the last couple of years perf tooling has matured and
  decoupled from the kernel perf changes to a large degree, going
  forward Arnaldo is going to send perf tooling changes via direct pull
  requests"

* tag 'perf-core-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (163 commits)
  perf/x86/rapl: Add AMD Fam17h RAPL support
  perf/x86/rapl: Make perf_probe_msr() more robust and flexible
  perf/x86/rapl: Flip logic on default events visibility
  perf/x86/rapl: Refactor to share the RAPL code between Intel and AMD CPUs
  perf/x86/rapl: Move RAPL support to common x86 code
  perf/core: Replace zero-length array with flexible-array
  perf/x86: Replace zero-length array with flexible-array
  perf/x86/intel: Add more available bits for OFFCORE_RESPONSE of Intel Tremont
  perf/x86/rapl: Add Ice Lake RAPL support
  perf flamegraph: Use /bin/bash for report and record scripts
  perf cs-etm: Move definition of 'traceid_list' global variable from header file
  libsymbols kallsyms: Move hex2u64 out of header
  libsymbols kallsyms: Parse using io api
  perf bench: Add kallsyms parsing
  perf: cs-etm: Update to build with latest opencsd version.
  perf symbol: Fix kernel symbol address display
  perf inject: Rename perf_evsel__*() operating on 'struct evsel *' to evsel__*()
  perf annotate: Rename perf_evsel__*() operating on 'struct evsel *' to evsel__*()
  perf trace: Rename perf_evsel__*() operating on 'struct evsel *' to evsel__*()
  perf script: Rename perf_evsel__*() operating on 'struct evsel *' to evsel__*()
  ...

1 files changed, 94 insertions, 2 deletions

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index a3207d900339..3742511a08d1 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -6,6 +6,9 @@
 #include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <linux/string.h>
+#include <internal/lib.h>
+#include <symbol/kallsyms.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "dso.h"
@@ -290,11 +293,82 @@ out:
 	return err ? -1 : 0;
 }
 
+struct kallsyms_parse {
+	union perf_event	*event;
+	perf_event__handler_t	 process;
+	struct machine		*machine;
+	struct perf_tool	*tool;
+};
+
+static int
+process_bpf_image(char *name, u64 addr, struct kallsyms_parse *data)
+{
+	struct machine *machine = data->machine;
+	union perf_event *event = data->event;
+	struct perf_record_ksymbol *ksymbol;
+	int len;
+
+	ksymbol = &event->ksymbol;
+
+	*ksymbol = (struct perf_record_ksymbol) {
+		.header = {
+			.type = PERF_RECORD_KSYMBOL,
+			.size = offsetof(struct perf_record_ksymbol, name),
+		},
+		.addr      = addr,
+		.len       = page_size,
+		.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+		.flags     = 0,
+	};
+
+	len = scnprintf(ksymbol->name, KSYM_NAME_LEN, "%s", name);
+	ksymbol->header.size += PERF_ALIGN(len + 1, sizeof(u64));
+	memset((void *) event + event->header.size, 0, machine->id_hdr_size);
+	event->header.size += machine->id_hdr_size;
+
+	return perf_tool__process_synth_event(data->tool, event, machine,
+					      data->process);
+}
+
+static int
+kallsyms_process_symbol(void *data, const char *_name,
+			char type __maybe_unused, u64 start)
+{
+	char disp[KSYM_NAME_LEN];
+	char *module, *name;
+	unsigned long id;
+	int err = 0;
+
+	module = strchr(_name, '\t');
+	if (!module)
+		return 0;
+
+	/* We are going after [bpf] module ... */
+	if (strcmp(module + 1, "[bpf]"))
+		return 0;
+
+	name = memdup(_name, (module - _name) + 1);
+	if (!name)
+		return -ENOMEM;
+
+	name[module - _name] = 0;
+
+	/* .. and only for trampolines and dispatchers */
+	if ((sscanf(name, "bpf_trampoline_%lu", &id) == 1) ||
+	    (sscanf(name, "bpf_dispatcher_%s", disp) == 1))
+		err = process_bpf_image(name, start, data);
+
+	free(name);
+	return err;
+}
+
 int perf_event__synthesize_bpf_events(struct perf_session *session,
 				      perf_event__handler_t process,
 				      struct machine *machine,
 				      struct record_opts *opts)
 {
+	const char *kallsyms_filename = "/proc/kallsyms";
+	struct kallsyms_parse arg;
 	union perf_event *event;
 	__u32 id = 0;
 	int err;
@@ -303,6 +377,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
+
+	/* Synthesize all the bpf programs in system. */
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
@@ -335,6 +411,23 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 			break;
 		}
 	}
+
+	/* Synthesize all the bpf images - trampolines/dispatchers. */
+	if (symbol_conf.kallsyms_name != NULL)
+		kallsyms_filename = symbol_conf.kallsyms_name;
+
+	arg = (struct kallsyms_parse) {
+		.event   = event,
+		.process = process,
+		.machine = machine,
+		.tool    = session->tool,
+	};
+
+	if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) {
+		pr_err("%s: failed to synthesize bpf images: %s\n",
+		       __func__, strerror(errno));
+	}
+
 	free(event);
 	return err;
 }
@@ -416,8 +509,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
 	return 0;
 }
 
-int bpf_event__add_sb_event(struct evlist **evlist,
-			    struct perf_env *env)
+int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 {
 	struct perf_event_attr attr = {
 		.type	          = PERF_TYPE_SOFTWARE,