Merge tag 'perf-core-for-mingo-5.4-20190816' of...

Merge tag 'perf-core-for-mingo-5.4-20190816' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

report/script/trace/top:

  Arnaldo Carvalho de Melo:

  - Allow specifying marker events demarcating when to consider the other events,
    i.e. one now can state something like:

        # perf probe kernel_function
        # perf record -e cycles,probe:kernel_function

    And then, in 'perf script' or 'perf report' say:

        # perf report --switch-on=probe:kernel_function

    And then the cycles event samples will be considered only after we
    find the first probe:kernel_function event.

    There is also --switch-off=event, to make it stop considering events
    out of some window, say to avoid some winding down of a workload.

    The same can be done with the "live mode" tools: 'perf top' and 'perf trace'.

    There are examples in the cset comments showing how to use it with
    SDT events in things like 'systemtap', that have those tracepoint-like
    events for the start/end of passes, etc.

    Another example involves selecting scheduler events + entry/exit of
    a syscall, using the syscalls tracepoints, one can then see the
    scheduler events that take place while that syscall is being processed.

    In the future this should be possible in record/top/trace via eBPF
    where the perf tools would hook into the marker events and enable events
    put in place but not enabled when the on/off conditions are the desired
    ones, reducing the amount of events sampled, but this userspace only
    solution should be good enough for many scenarios.

perf vendor events intel:

  Haiyan Song:

  - Add Tremontx event file v1.02.

unwind:

  John Keeping:

  - Fix callchain unwinding when tid != pid, that was working only for the
    thread group leader.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----

iHUEABYIAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCXVcMPgAKCRCyPKLppCJ+
J6ipAP9F5+TitM1zln/wUUP7/Ug4ZPDsdvA+Ggc8x0Ns7URJQwD/RHk43MgDC1fG
VXbpQ7byj339Wo7SpjadzLl9xPlh/Qw=
=IaYE
-----END PGP SIGNATURE-----

commit e2736219
Author: John Keeping <john@metanate.com>
Date:   Thu Aug 15 11:01:46 2019 +0100

    perf unwind: Remove unnecessary test

    If dwarf_callchain_users is false, then unwind__prepare_access() will
    not set unwind_libunwind_ops so the remaining test here is sufficient.
Signed-off-by: John Keeping <john@metanate.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
    Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
    Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
    Cc: Namhyung Kim <namhyung@kernel.org>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Cc: john keeping <john@metanate.com>
    Link: http://lkml.kernel.org/r/20190815100146.28842-3-john@metanate.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index b843f9d0a9ea..6499b22b158b 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -69,18 +69,12 @@ int unwind__prepare_access(struct map_groups *mg, struct map *map,

 void unwind__flush_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-
 	if (mg->unwind_libunwind_ops)
 		mg->unwind_libunwind_ops->flush_access(mg);
 }

 void unwind__finish_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-
 	if (mg->unwind_libunwind_ops)
 		mg->unwind_libunwind_ops->finish_access(mg);
 }

tools/perf/Documentation/perf-report.txt

@@ -438,6 +438,23 @@ OPTIONS
 
 	  perf report --time 0%-10%,30%-40%
 
+--switch-on EVENT_NAME::
+	Only consider events after this event is found.
+
+	This may be interesting to measure a workload only after some initialization
+	phase is over, i.e. insert a perf probe at that point and then using this
+	option with that probe.
+
+--switch-off EVENT_NAME::
+	Stop considering events after this event is found.
+
+--show-on-off-events::
+	Show the --switch-on/off events too. This has no effect in 'perf report' now
+	but probably we'll make the default not to show the switch-on/off events
+        on the --group mode and if there is only one event besides the off/on ones,
+	go straight to the histogram browser, just like 'perf report' with no events
+	explicitely specified does.
+
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 

tools/perf/Documentation/perf-script.txt

@@ -417,6 +417,15 @@ include::itrace.txt[]
 	For itrace only show specified functions and their callees for
 	itrace. Multiple functions can be separated by comma.
 
+--switch-on EVENT_NAME::
+	Only consider events after this event is found.
+
+--switch-off EVENT_NAME::
+	Stop considering events after this event is found.
+
+--show-on-off-events::
+	Show the --switch-on/off events too.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],

tools/perf/Documentation/perf-top.txt

@@ -266,6 +266,44 @@ Default is to monitor all CPUS.
 	Record events of type PERF_RECORD_NAMESPACES and display it with the
 	'cgroup_id' sort key.
 
+--switch-on EVENT_NAME::
+	Only consider events after this event is found.
+
+	E.g.:
+
+           Find out where broadcast packets are handled
+
+		perf probe -L icmp_rcv
+
+	   Insert a probe there:
+
+		perf probe icmp_rcv:59
+
+	   Start perf top and ask it to only consider the cycles events when a
+           broadcast packet arrives This will show a menu with two entries and
+           will start counting when a broadcast packet arrives:
+
+		perf top -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv
+
+	   Alternatively one can ask for --group and then two overhead columns
+           will appear, the first for cycles and the second for the switch-on event.
+
+		perf top --group -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv
+
+	This may be interesting to measure a workload only after some initialization
+	phase is over, i.e. insert a perf probe at that point and use the above
+	examples replacing probe:icmp_rcv with the just-after-init probe.
+
+--switch-off EVENT_NAME::
+	Stop considering events after this event is found.
+
+--show-on-off-events::
+	Show the --switch-on/off events too. This has no effect in 'perf top' now
+	but probably we'll make the default not to show the switch-on/off events
+        on the --group mode and if there is only one event besides the off/on ones,
+	go straight to the histogram browser, just like 'perf top' with no events
+	explicitely specified does.
+
 
 INTERACTIVE PROMPTING KEYS
 --------------------------

tools/perf/Documentation/perf-trace.txt

@@ -176,6 +176,15 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	only at exit time or when a syscall is interrupted, i.e. in those cases this
 	option is equivalent to the number of lines printed.
 
+--switch-on EVENT_NAME::
+	Only consider events after this event is found.
+
+--switch-off EVENT_NAME::
+	Stop considering events after this event is found.
+
+--show-on-off-events::
+	Show the --switch-on/off events too.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point

tools/perf/builtin-report.c

@@ -25,6 +25,7 @@
 #include "util/debug.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evswitch.h"
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
@@ -60,6 +61,7 @@
 struct report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
+	struct evswitch		evswitch;
 	bool			use_tui, use_gtk, use_stdio;
 	bool			show_full_info;
 	bool			show_threads;
@@ -243,6 +245,9 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 	}
 
+	if (evswitch__discard(&rep->evswitch, evsel))
+		return 0;
+
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
@@ -1189,6 +1194,7 @@ int cmd_report(int argc, const char **argv)
 	OPT_CALLBACK(0, "time-quantum", &symbol_conf.time_quantum, "time (ms|us|ns|s)",
 		     "Set time quantum for time sort key (default 100ms)",
 		     parse_time_quantum),
+	OPTS_EVSWITCH(&report.evswitch),
 	OPT_END()
 	};
 	struct perf_data data = {
@@ -1257,6 +1263,10 @@ int cmd_report(int argc, const char **argv)
 	if (session == NULL)
 		return -1;
 
+	ret = evswitch__init(&report.evswitch, session->evlist, stderr);
+	if (ret)
+		return ret;
+
 	if (zstd_init(&(session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
 

tools/perf/builtin-script.c

@@ -16,6 +16,7 @@
 #include "util/trace-event.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evswitch.h"
 #include "util/sort.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
@@ -1628,6 +1629,7 @@ struct perf_script {
 	bool			show_bpf_events;
 	bool			allocated;
 	bool			per_event_dump;
+	struct evswitch		evswitch;
 	struct perf_cpu_map	*cpus;
 	struct perf_thread_map *threads;
 	int			name_width;
@@ -1805,6 +1807,9 @@ static void process_event(struct perf_script *script,
 	if (!show_event(sample, evsel, thread, al))
 		return;
 
+	if (evswitch__discard(&script->evswitch, evsel))
+		return;
+
 	++es->samples;
 
 	perf_sample__fprintf_start(sample, thread, evsel,
@@ -3538,6 +3543,7 @@ int cmd_script(int argc, const char **argv)
 		   "file", "file saving guest os /proc/kallsyms"),
 	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
 		   "file", "file saving guest os /proc/modules"),
+	OPTS_EVSWITCH(&script.evswitch),
 	OPT_END()
 	};
 	const char * const script_subcommands[] = { "record", "report", NULL };
@@ -3862,6 +3868,10 @@ int cmd_script(int argc, const char **argv)
 						  script.range_num);
 	}
 
+	err = evswitch__init(&script.evswitch, session->evlist, stderr);
+	if (err)
+		goto out_delete;
+
 	err = __cmd_script(&script);
 
 	flush_scripting();

tools/perf/builtin-top.c

@@ -1148,8 +1148,11 @@ static int deliver_event(struct ordered_events *qe,
 	evsel = perf_evlist__id2evsel(session->evlist, sample.id);
 	assert(evsel != NULL);
 
-	if (event->header.type == PERF_RECORD_SAMPLE)
+	if (event->header.type == PERF_RECORD_SAMPLE) {
+		if (evswitch__discard(&top->evswitch, evsel))
+			return 0;
 		++top->samples;
+	}
 
 	switch (sample.cpumode) {
 	case PERF_RECORD_MISC_USER:
@@ -1534,6 +1537,7 @@ int cmd_top(int argc, const char **argv)
 			"number of thread to run event synthesize"),
 	OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
 		    "Record namespaces events"),
+	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};
 	struct evlist *sb_evlist = NULL;
@@ -1567,6 +1571,10 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+	status = evswitch__init(&top.evswitch, top.evlist, stderr);
+	if (status)
+		goto out_delete_evlist;
+
 	if (symbol_conf.report_hierarchy) {
 		/* disable incompatible options */
 		symbol_conf.event_group = false;

tools/perf/builtin-trace.c

@@ -27,6 +27,7 @@
 #include "util/env.h"
 #include "util/event.h"
 #include "util/evlist.h"
+#include "util/evswitch.h"
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
 #include "util/map.h"
@@ -106,6 +107,7 @@ struct trace {
 	unsigned long		nr_events;
 	unsigned long		nr_events_printed;
 	unsigned long		max_events;
+	struct evswitch		evswitch;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -2680,6 +2682,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		return;
 	}
 
+	if (evswitch__discard(&trace->evswitch, evsel))
+		return;
+
 	trace__set_base_time(trace, evsel, sample);
 
 	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT &&
@@ -4157,6 +4162,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
+	OPTS_EVSWITCH(&trace.evswitch),
 	OPT_END()
 	};
 	bool __maybe_unused max_stack_user_set = true;
@@ -4380,6 +4386,10 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
+	err = evswitch__init(&trace.evswitch, trace.evlist, stderr);
+	if (err)
+		goto out_close;
+
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -35,4 +35,5 @@ GenuineIntel-6-55-[01234],v1,skylakex,core
 GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core
 GenuineIntel-6-7D,v1,icelake,core
 GenuineIntel-6-7E,v1,icelake,core
+GenuineIntel-6-86,v1,tremontx,core
 AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core

tools/perf/pmu-events/arch/x86/tremontx/cache.json

+[
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts cacheable memory requests that miss in the the Last Level Cache.  Requests include Demand Loads, Reads for Ownership(RFO), Instruction fetches and L1 HW prefetches. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2.",
+        "EventCode": "0x2e",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts memory requests originating from the core that miss in the last level cache. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts cacheable memory requests that access the Last Level Cache.  Requests include Demand Loads, Reads for Ownership(RFO), Instruction fetches and L1 HW prefetches. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2.",
+        "EventCode": "0x2e",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts memory requests originating from the core that reference a cache line in the last level cache. If the platform has an L3 cache, last level cache is the L3, otherwise it is the L2."
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of load uops retired. This event is Precise Event capable",
+        "EventCode": "0xd0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x81",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired.",
+        "Data_LA": "1"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of store uops retired. This event is Precise Event capable",
+        "EventCode": "0xd0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of store uops retired.",
+        "Data_LA": "1"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xd1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired that hit the level 1 data cache",
+        "Data_LA": "1"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xd1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired that hit in the level 2 cache",
+        "Data_LA": "1"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xd1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired that miss in the level 3 cache"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xd1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired that miss in the level 1 data cache",
+        "Data_LA": "1"
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xd1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of load uops retired that miss in the level 2 cache",
+        "Data_LA": "1"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tremontx/frontend.json

+[
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache)  for one or more bytes in an ICache Line and that cache line is not in the ICache (miss).  The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS.  Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.MISSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in a cache line and they do not hit in the ICache (miss)."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line.  The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS.  Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.ACCESSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes cache Line."
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tremontx/memory.json

+[
+    {
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventCode": "0XB7",
+        "MSRValue": "0x000000003F04000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
+        "Offcore": "1"
+    },
+    {
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventCode": "0XB7",
+        "MSRValue": "0x000000003F04000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
+        "Offcore": "1"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tremontx/other.json

+[
+    {
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventCode": "0XB7",
+        "MSRValue": "0x000000000000010001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads that have any response type.",
+        "Offcore": "1"
+    },
+    {
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventCode": "0XB7",
+        "MSRValue": "0x000000000000010002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that have any response type.",
+        "Offcore": "1"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tremontx/pipeline.json

+[
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of instructions that retire. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.",
+        "Counter": "32",
+        "UMask": "0x1",
+        "PEBScounters": "32",
+        "EventName": "INST_RETIRED.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of instructions retired. (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.",
+        "Counter": "33",
+        "UMask": "0x2",
+        "PEBScounters": "33",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of unhalted core clock cycles. (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  The core frequency may change from time.  This event is not affected by core frequency changes and at a fixed frequency.  This event uses fixed counter 2.",
+        "Counter": "34",
+        "UMask": "0x3",
+        "PEBScounters": "34",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency. (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses a programmable general purpose performance counter.",
+        "EventCode": "0x3c",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of unhalted core clock cycles."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts reference cycles (at TSC frequency) when core is not halted.  This event uses a programmable general purpose perfmon counter.",
+        "EventCode": "0x3c",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency."
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers.  This is an architectural performance event.  This event uses a Programmable general purpose perfmon counter. *This event is Precise Event capable:  The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.",
+        "EventCode": "0xc0",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the number of instructions retired."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xc3",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Counts all machine clears due to, but not limited to memory ordering, memory disambiguation, SMC, page faults and FP assist."
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts branch instructions retired for all branch types. This event is Precise Event capable. This is an architectural event.",
+        "EventCode": "0xc4",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of branch instructions retired for all branch types."
+    },
+    {
+        "PEBS": "1",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired for all branch types. This event is Precise Event capable. This is an architectural event.",
+        "EventCode": "0xc5",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of mispredicted branch instructions retired."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "EventCode": "0xcd",
+        "Counter": "0,1,2,3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts cycles the floating point divider or integer divider or both are busy.  Does not imply a stall waiting for either divider."
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json

+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x04",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x0f",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x04",
+        "EventName": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x30",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x02",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x04",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x02",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x08",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Precharge due to read on page miss, write on page miss or PGT",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x02",
+        "EventName": "UNC_M_PRE_COUNT.ALL",
+        "PerPkg": "1",
+        "UMask": "0x1c",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "DRAM Precharge commands. : Precharge due to page table",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventCode": "0x02",
+        "EventName": "UNC_M_PRE_COUNT.PGT",
+        "PerPkg": "1",
+        "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel.",
+        "UMask": "0x10",
+        "Unit": "iMC"
+    }
+]

tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json

+[
+    {
+        "BriefDescription": "Clockticks of the power control unit (PCU)",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "PublicDescription": "Clockticks of the power control unit (PCU)",
+        "Unit": "PCU"
+    }
+]

tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json

+[
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 4K page."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) and new translation was filled into the ITLB.  The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
+        "EventCode": "0x81",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB.FILLS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of times there was an ITLB miss and a new translation was filled into the ITLB."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 4K page."
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page."
+    }
+]
\ No newline at end of file

tools/perf/util/Build

@@ -9,6 +9,7 @@ perf-y += event.o
 perf-y += evlist.o
 perf-y += evsel.o
 perf-y += evsel_fprintf.o
+perf-y += evswitch.o
 perf-y += find_bit.o
 perf-y += get_current_dir_name.o
 perf-y += kallsyms.o

tools/perf/util/evswitch.c

+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "evswitch.h"
+#include "evlist.h"
+
+bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel)
+{
+	if (evswitch->on && evswitch->discarding) {
+		if (evswitch->on != evsel)
+			return true;
+
+		evswitch->discarding = false;
+
+		if (!evswitch->show_on_off_events)
+			return true;
+
+		return false;
+	}
+
+	if (evswitch->off && !evswitch->discarding) {
+		if (evswitch->off != evsel)
+			return false;
+
+		evswitch->discarding = true;
+
+		if (!evswitch->show_on_off_events)
+			return true;
+	}
+
+	return false;
+}
+
+static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *evname)
+{
+	int printed = fprintf(fp, "ERROR: switch-%s event not found (%s)\n", evtype, evname);
+
+	return printed += fprintf(fp, "HINT:  use 'perf evlist' to see the available event names\n");
+}
+
+int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
+{
+	if (evswitch->on_name) {
+		evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name);
+		if (evswitch->on == NULL) {
+			evswitch__fprintf_enoent(fp, "on", evswitch->on_name);
+			return -ENOENT;
+		}
+		evswitch->discarding = true;
+	}
+
+	if (evswitch->off_name) {
+		evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name);
+		if (evswitch->off == NULL) {
+			evswitch__fprintf_enoent(fp, "off", evswitch->off_name);
+			return -ENOENT;
+		}
+	}
+
+	return 0;
+}

tools/perf/util/evswitch.h

+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+#ifndef __PERF_EVSWITCH_H
+#define __PERF_EVSWITCH_H 1
+
+#include <stdbool.h>
+#include <stdio.h>
+
+struct evsel;
+struct evlist;
+
+struct evswitch {
+	struct evsel *on, *off;
+	const char   *on_name, *off_name;
+	bool	     discarding;
+	bool	     show_on_off_events;
+};
+
+int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp);
+
+bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel);
+
+#define OPTS_EVSWITCH(evswitch)								  \
+	OPT_STRING(0, "switch-on", &(evswitch)->on_name,				  \
+		   "event", "Consider events after the ocurrence of this event"),	  \
+	OPT_STRING(0, "switch-off", &(evswitch)->off_name,				  \
+		   "event", "Stop considering events after the ocurrence of this event"), \
+	OPT_BOOLEAN(0, "show-on-off-events", &(evswitch)->show_on_off_events,		  \
+		    "Show the on/off switch events, used with --switch-on and --switch-off")
+
+#endif /* __PERF_EVSWITCH_H */

tools/perf/util/map.c

@@ -636,7 +636,7 @@ bool map_groups__empty(struct map_groups *mg)
 
 struct map_groups *map_groups__new(struct machine *machine)
 {
-	struct map_groups *mg = malloc(sizeof(*mg));
+	struct map_groups *mg = zalloc(sizeof(*mg));
 
 	if (mg != NULL)
 		map_groups__init(mg, machine);
@@ -647,6 +647,7 @@ struct map_groups *map_groups__new(struct machine *machine)
 void map_groups__delete(struct map_groups *mg)
 {
 	map_groups__exit(mg);
+	unwind__finish_access(mg);
 	free(mg);
 }
 
@@ -887,7 +888,7 @@ int map_groups__clone(struct thread *thread, struct map_groups *parent)
 		if (new == NULL)
 			goto out_unlock;
 
-		err = unwind__prepare_access(thread, new, NULL);
+		err = unwind__prepare_access(mg, new, NULL);
 		if (err)
 			goto out_unlock;
 

tools/perf/util/map_groups.h

@@ -31,6 +31,10 @@ struct map_groups {
 	struct maps	 maps;
 	struct machine	 *machine;
 	refcount_t	 refcnt;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	void				*addr_space;
+	struct unwind_libunwind_ops	*unwind_libunwind_ops;
+#endif
 };
 
 #define KMAP_NAME_LEN 256

tools/perf/util/thread.c

@@ -105,7 +105,6 @@ void thread__delete(struct thread *thread)
 	}
 	up_write(&thread->comm_lock);
 
-	unwind__finish_access(thread);
 	nsinfo__zput(thread->nsinfo);
 	srccode_state_free(&thread->srccode_state);
 
@@ -252,7 +251,7 @@ static int ____thread__set_comm(struct thread *thread, const char *str,
 		list_add(&new->list, &thread->comm_list);
 
 		if (exec)
-			unwind__flush_access(thread);
+			unwind__flush_access(thread->mg);
 	}
 
 	thread->comm_set = true;
@@ -332,7 +331,7 @@ int thread__insert_map(struct thread *thread, struct map *map)
 {
 	int ret;
 
-	ret = unwind__prepare_access(thread, map, NULL);
+	ret = unwind__prepare_access(thread->mg, map, NULL);
 	if (ret)
 		return ret;
 
@@ -352,7 +351,7 @@ static int __thread__prepare_access(struct thread *thread)
 	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
-		err = unwind__prepare_access(thread, map, &initialized);
+		err = unwind__prepare_access(thread->mg, map, &initialized);
 		if (err || initialized)
 			break;
 	}

tools/perf/util/thread.h

@@ -44,10 +44,6 @@ struct thread {
 	struct thread_stack	*ts;
 	struct nsinfo		*nsinfo;
 	struct srccode_state	srccode_state;
-#ifdef HAVE_LIBUNWIND_SUPPORT
-	void				*addr_space;
-	struct unwind_libunwind_ops	*unwind_libunwind_ops;
-#endif
 	bool			filter;
 	int			filter_entry_depth;
 };

tools/perf/util/top.h

@@ -3,6 +3,7 @@
 #define __PERF_TOP_H 1
 
 #include "tool.h"
+#include "evswitch.h"
 #include "annotate.h"
 #include <linux/types.h>
 #include <stddef.h>
@@ -18,6 +19,7 @@ struct perf_top {
 	struct evlist *evlist;
 	struct record_opts record_opts;
 	struct annotation_options annotation_opts;
+	struct evswitch	   evswitch;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.

tools/perf/util/unwind-libunwind-local.c

@@ -616,26 +616,26 @@ static unw_accessors_t accessors = {
 	.get_proc_name		= get_proc_name,
 };
 
-static int _unwind__prepare_access(struct thread *thread)
+static int _unwind__prepare_access(struct map_groups *mg)
 {
-	thread->addr_space = unw_create_addr_space(&accessors, 0);
-	if (!thread->addr_space) {
+	mg->addr_space = unw_create_addr_space(&accessors, 0);
+	if (!mg->addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
 		return -ENOMEM;
 	}
 
-	unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
+	unw_set_caching_policy(mg->addr_space, UNW_CACHE_GLOBAL);
 	return 0;
 }
 
-static void _unwind__flush_access(struct thread *thread)
+static void _unwind__flush_access(struct map_groups *mg)
 {
-	unw_flush_cache(thread->addr_space, 0, 0);
+	unw_flush_cache(mg->addr_space, 0, 0);
 }
 
-static void _unwind__finish_access(struct thread *thread)
+static void _unwind__finish_access(struct map_groups *mg)
 {
-	unw_destroy_addr_space(thread->addr_space);
+	unw_destroy_addr_space(mg->addr_space);
 }
 
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
@@ -660,7 +660,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	 */
 	if (max_stack - 1 > 0) {
 		WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
-		addr_space = ui->thread->addr_space;
+		addr_space = ui->thread->mg->addr_space;
 
 		if (addr_space == NULL)
 			return -1;

tools/perf/util/unwind-libunwind.c

@@ -11,13 +11,13 @@ struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops;
 
-static void unwind__register_ops(struct thread *thread,
+static void unwind__register_ops(struct map_groups *mg,
 			  struct unwind_libunwind_ops *ops)
 {
-	thread->unwind_libunwind_ops = ops;
+	mg->unwind_libunwind_ops = ops;
 }
 
-int unwind__prepare_access(struct thread *thread, struct map *map,
+int unwind__prepare_access(struct map_groups *mg, struct map *map,
 			   bool *initialized)
 {
 	const char *arch;
@@ -28,7 +28,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
 	if (!dwarf_callchain_users)
 		return 0;
 
-	if (thread->addr_space) {
+	if (mg->addr_space) {
 		pr_debug("unwind: thread map already set, dso=%s\n",
 			 map->dso->name);
 		if (initialized)
@@ -37,14 +37,14 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
 	}
 
 	/* env->arch is NULL for live-mode (i.e. perf top) */
-	if (!thread->mg->machine->env || !thread->mg->machine->env->arch)
+	if (!mg->machine->env || !mg->machine->env->arch)
 		goto out_register;
 
-	dso_type = dso__type(map->dso, thread->mg->machine);
+	dso_type = dso__type(map->dso, mg->machine);
 	if (dso_type == DSO__TYPE_UNKNOWN)
 		return 0;
 
-	arch = perf_env__arch(thread->mg->machine->env);
+	arch = perf_env__arch(mg->machine->env);
 
 	if (!strcmp(arch, "x86")) {
 		if (dso_type != DSO__TYPE_64BIT)
@@ -59,37 +59,31 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
 		return 0;
 	}
 out_register:
-	unwind__register_ops(thread, ops);
+	unwind__register_ops(mg, ops);
 
-	err = thread->unwind_libunwind_ops->prepare_access(thread);
+	err = mg->unwind_libunwind_ops->prepare_access(mg);
 	if (initialized)
 		*initialized = err ? false : true;
 	return err;
 }
 
-void unwind__flush_access(struct thread *thread)
+void unwind__flush_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-
-	if (thread->unwind_libunwind_ops)
-		thread->unwind_libunwind_ops->flush_access(thread);
+	if (mg->unwind_libunwind_ops)
+		mg->unwind_libunwind_ops->flush_access(mg);
 }
 
-void unwind__finish_access(struct thread *thread)
+void unwind__finish_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-
-	if (thread->unwind_libunwind_ops)
-		thread->unwind_libunwind_ops->finish_access(thread);
+	if (mg->unwind_libunwind_ops)
+		mg->unwind_libunwind_ops->finish_access(mg);
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			 struct thread *thread,
 			 struct perf_sample *data, int max_stack)
 {
-	if (thread->unwind_libunwind_ops)
-		return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+	if (thread->mg->unwind_libunwind_ops)
+		return thread->mg->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
 	return 0;
 }

tools/perf/util/unwind.h

@@ -6,6 +6,7 @@
 #include <linux/types.h>
 
 struct map;
+struct map_groups;
 struct perf_sample;
 struct symbol;
 struct thread;
@@ -19,9 +20,9 @@ struct unwind_entry {
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 struct unwind_libunwind_ops {
-	int (*prepare_access)(struct thread *thread);
-	void (*flush_access)(struct thread *thread);
-	void (*finish_access)(struct thread *thread);
+	int (*prepare_access)(struct map_groups *mg);
+	void (*flush_access)(struct map_groups *mg);
+	void (*finish_access)(struct map_groups *mg);
 	int (*get_entries)(unwind_entry_cb_t cb, void *arg,
 			   struct thread *thread,
 			   struct perf_sample *data, int max_stack);
@@ -46,20 +47,20 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #endif
 
 int LIBUNWIND__ARCH_REG_ID(int regnum);
-int unwind__prepare_access(struct thread *thread, struct map *map,
+int unwind__prepare_access(struct map_groups *mg, struct map *map,
 			   bool *initialized);
-void unwind__flush_access(struct thread *thread);
-void unwind__finish_access(struct thread *thread);
+void unwind__flush_access(struct map_groups *mg);
+void unwind__finish_access(struct map_groups *mg);
 #else
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused,
 					 struct map *map __maybe_unused,
 					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
 
-static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
-static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {}
+static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -72,14 +73,14 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 	return 0;
 }
 
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused,
 					 struct map *map __maybe_unused,
 					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
 
-static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
-static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {}
+static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */