From c42ad5d4358230be166fc36c87bae0dd1680c570 Mon Sep 17 00:00:00 2001 From: Andreas Gerstmayr Date: Fri, 19 Jun 2020 17:32:31 +0200 Subject: perf flamegraph: Explicitly set utf-8 encoding On some platforms the default encoding is not utf-8, which causes an UnicodeDecodeError when reading the flamegraph template and writing the flamegraph Signed-off-by: Andreas Gerstmayr Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200619153232.203537-1-agerstmayr@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/flamegraph.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py index 61f3be9add6b..65780013f745 100755 --- a/tools/perf/scripts/python/flamegraph.py +++ b/tools/perf/scripts/python/flamegraph.py @@ -17,6 +17,7 @@ from __future__ import print_function import sys import os +import io import argparse import json @@ -81,7 +82,7 @@ class FlameGraphCLI: if self.args.format == "html": try: - with open(self.args.template) as f: + with io.open(self.args.template, encoding="utf-8") as f: output_str = f.read().replace("/** @flamegraph_json **/", json_str) except IOError as e: @@ -93,11 +94,12 @@ class FlameGraphCLI: output_fn = self.args.output or "stacks.json" if output_fn == "-": - sys.stdout.write(output_str) + with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out: + out.write(output_str) else: print("dumping data to {}".format(output_fn)) try: - with open(output_fn, "w") as out: + with io.open(output_fn, "w", encoding="utf-8") as out: out.write(output_str) except IOError as e: print("Error writing output file: {}".format(e), file=sys.stderr) -- cgit v1.2.3 From eb25de276505c664c6ee838e60c6e5ad1837f55e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Jul 2020 08:11:16 -0300 Subject: tools arch: Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy' To bring in the change made in this cset: e3a9e681adb7 ("x86/entry: Fixup bad_iret vs noinstr") This doesn't cause any functional changes to tooling, just a rebuild. Addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index df767afc690f..45f8e1b02241 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include #include +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL -- cgit v1.2.3 From 640432e6bed08e9d5d2ba26856ba3f55008b07e3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:50 +0300 Subject: perf scripts python: export-to-postgresql.py: Fix struct.pack() int argument Python 3.8 is requiring that arguments being packed as integers are also integers. Add int() accordingly. Before: $ perf record -e intel_pt//u uname $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py perf_data_db branches calls 2020-06-25 16:09:10.547256 Creating database... 2020-06-25 16:09:10.733185 Writing to intermediate files... Traceback (most recent call last): File "/home/ahunter/libexec/perf-core/scripts/python/export-to-postgresql.py", line 1106, in synth_data cbr(id, raw_buf) File "/home/ahunter/libexec/perf-core/scripts/python/export-to-postgresql.py", line 1058, in cbr value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent) struct.error: required argument is not an integer Fatal Python error: problem in Python trace event handler Python runtime state: initialized Current thread 0x00007f35d3695780 (most recent call first): Aborted (core dumped) After: $ dropdb perf_data_db $ rm -rf perf_data_db-perf-data $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py perf_data_db branches calls 2020-06-25 16:09:40.990267 Creating database... 2020-06-25 16:09:41.207009 Writing to intermediate files... 2020-06-25 16:09:41.270915 Copying to database... 2020-06-25 16:09:41.382030 Removing intermediate files... 2020-06-25 16:09:41.384630 Adding primary keys 2020-06-25 16:09:41.541894 Adding foreign keys 2020-06-25 16:09:41.677044 Dropping unused tables 2020-06-25 16:09:41.703761 Done Fixes: aba44287a224 ("perf scripts python: export-to-postgresql.py: Export Intel PT power and ptwrite events") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/export-to-postgresql.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 7bd73a904b4e..d187e46c2683 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -1055,7 +1055,7 @@ def cbr(id, raw_buf): cbr = data[0] MHz = (data[4] + 500) / 1000 percent = ((cbr * 1000 / data[2]) + 5) / 10 - value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent) + value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent)) cbr_file.write(value) def mwait(id, raw_buf): -- cgit v1.2.3 From 442ad2254ac56b39870c0cfed96d500921fea5d5 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:51 +0300 Subject: perf record: Fix duplicated sideband events with Intel PT system wide tracing Commit 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis") reveals an issue with Intel PT system wide tracing. Specifically that Intel PT already adds a dummy tracking event, and it is not the first event. Adding another dummy tracking event causes duplicated sideband events. Fix by checking for an existing dummy tracking event first. Example showing duplicated switch events: Before: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.895 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [007] 6390.516223: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516224: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [002] 6390.516415: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 swapper 0 [002] 6390.516416: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 After: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.868 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [005] 6450.567013: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 7179/7181 perf 7181 [005] 6450.567014: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 perf 7181 [005] 6450.567028: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.567029: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 7179/7181 swapper 0 [005] 6450.571699: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.571700: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [005] 6450.571702: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.571703: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [005] 6450.579703: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.579704: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20200629091955.17090-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 18 +++++++++--------- tools/perf/util/evlist.c | 12 ++++++++++++ tools/perf/util/evlist.h | 1 + tools/perf/util/evsel.c | 8 +------- tools/perf/util/evsel.h | 6 ++++++ 5 files changed, 29 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e108d90ae2ed..a37e7910e9e9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -852,20 +852,20 @@ static int record__open(struct record *rec) * event synthesis. */ if (opts->initial_delay || target__has_cpu(&opts->target)) { - if (perf_evlist__add_dummy(evlist)) - return -ENOMEM; + pos = perf_evlist__get_tracking_event(evlist); + if (!evsel__is_dummy_event(pos)) { + /* Set up dummy event. */ + if (perf_evlist__add_dummy(evlist)) + return -ENOMEM; + pos = evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, pos); + } - /* Disable tracking of mmaps on lead event. */ - pos = evlist__first(evlist); - pos->tracking = 0; - /* Set up dummy event. */ - pos = evlist__last(evlist); - pos->tracking = 1; /* * Enable the dummy event when the process is forked for * initial_delay, immediately for system wide. */ - if (opts->initial_delay) + if (opts->initial_delay && !pos->immediate) pos->core.attr.enable_on_exec = 1; else pos->immediate = 1; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 173b4f0e0e6e..ab48be4cf258 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1566,6 +1566,18 @@ void perf_evlist__to_front(struct evlist *evlist, list_splice(&move, &evlist->core.entries); } +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->tracking) + return evsel; + } + + return evlist__first(evlist); +} + void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b6f325dfb4d2..a8081dfc19cf 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -335,6 +335,7 @@ void perf_evlist__to_front(struct evlist *evlist, evlist__cpu_iter_start(evlist); \ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist); void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 96e5171dce41..a68ac3632ae6 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -898,12 +898,6 @@ static void evsel__apply_config_terms(struct evsel *evsel, } } -static bool is_dummy_event(struct evsel *evsel) -{ - return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && - (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); -} - struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) { struct evsel_config_term *term, *found_term = NULL; @@ -1161,7 +1155,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * The software event will trigger -EOPNOTSUPP error out, * if BRANCH_STACK bit is set. */ - if (is_dummy_event(evsel)) + if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f963c2a88a5..35e3f6d66085 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -399,6 +399,12 @@ static inline bool evsel__has_br_stack(const struct evsel *evsel) evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK; } +static inline bool evsel__is_dummy_event(struct evsel *evsel) +{ + return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && + (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); +} + struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); -- cgit v1.2.3 From 3a3cf7c570a486b07d9a6e68a77548aea6a8421f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:52 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix unexpanded 'Find' result Using Python version 3.8.2 and PySide2 version 5.14.0, ctrl-F ('Find') would not expand the tree to the result. Fix by using setExpanded(). Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Context-Sensitive Call Graph or Reports -> Call Tree Press: Ctrl-F Enter: main Press: Enter Before: line showing 'main' does not display After: tree is expanded to line showing 'main' Fixes: ebd70c7dc2f5f ("perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 26d7be785288..4be7cb68c8bb 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -1050,6 +1050,7 @@ class TreeWindowBase(QMdiSubWindow): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break -- cgit v1.2.3 From 7ff520b0a71dd2db695b52ad117d81b7eaf6ff9d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:53 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix zero id in call graph 'Find' result Using ctrl-F ('Find') would not find 'unknown' because it matches id zero. Fix by excluding id zero from selection. Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Context-Sensitive Call Graph Press: Ctrl-F Enter: unknown Press: Enter Before: gets stuck After: tree is expanded to line showing 'unknown' Fixes: 254c0d820b86d ("perf scripts python: exported-sql-viewer.py: Factor out CallGraphModelBase") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 4be7cb68c8bb..e0c90aeff15e 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -768,7 +768,8 @@ class CallGraphModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " GROUP BY comm_id, thread_id, call_path_id" " ORDER BY comm_id, thread_id, call_path_id") -- cgit v1.2.3 From 031c8d5edb1ddeb6d398f7942ce2a01a1a51ada9 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:54 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix zero id in call tree 'Find' result Using ctrl-F ('Find') would not find 'unknown' because it matches id zero. Fix by excluding id zero from selection. Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Call Tree Press: Ctrl-F Enter: unknown Press: Enter Before: displays 'unknown' not found After: tree is expanded to line showing 'unknown' Fixes: ae8b887c00d3f ("perf scripts python: exported-sql-viewer.py: Add call tree") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index e0c90aeff15e..0f295055ac6b 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -964,7 +964,8 @@ class CallTreeModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " ORDER BY comm_id, thread_id, call_time, calls.id") def FindPath(self, query): -- cgit v1.2.3 From f18d5cf86cdb58eb50cafb5a5e20943ec7a61b1f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 29 Jun 2020 12:19:55 +0300 Subject: perf scripts python: exported-sql-viewer.py: Fix time chart call tree Using Python version 3.8.2 and PySide2 version 5.14.0, time chart call tree would not expand the tree to the result. Fix by using setExpanded(). Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Charts -> Time chart by CPU Move mouse over middle of chart Right-click and select Show Call Tree Before: displays Call Tree but not expanded to selected time After: displays Call Tree expanded to selected time Fixes: e69d5df75d74d ("perf scripts python: exported-sql-viewer.py: Add ability for Call tree to open at a specified task and time") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-7-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 0f295055ac6b..7daa8bb70a5a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -1130,6 +1130,7 @@ class CallTreeWindow(TreeWindowBase): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break @@ -1142,6 +1143,7 @@ class CallTreeWindow(TreeWindowBase): return last_child = None for row in xrange(n): + self.view.setExpanded(parent, True) child = self.model.index(row, 0, parent) child_call_time = child.internalPointer().call_time if child_call_time < time: @@ -1154,9 +1156,11 @@ class CallTreeWindow(TreeWindowBase): if not last_child: if not found: child = self.model.index(0, 0, parent) + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) return found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(last_child) parent = last_child -- cgit v1.2.3 From 374855c5e4a76f7cc7f9aeb613c54929510eff18 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 2 Jul 2020 14:53:45 -0400 Subject: tools lib traceevent: Add API to read time information from kbuffer Add the functions kbuffer_subbuf_timestamp() and kbuffer_ptr_delta() to get the timing data stored in the ring buffer that is used to produced the time stamps of the records. This is useful for tools like trace-cmd to be able to display the content of the read data to understand why the records show the time stamps that they do. Link: http://lore.kernel.org/linux-trace-devel/20200625100516.365338-2-tz.stoyanov@gmail.com Signed-off-by: Steven Rostedt (VMware) [ Ported from trace-cmd.git ] Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20200702185703.619656282@goodmis.org Signed-off-by: Tzvetomir Stoyanov (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/kbuffer-parse.c | 28 ++++++++++++++++++++++++++++ tools/lib/traceevent/kbuffer.h | 2 ++ 2 files changed, 30 insertions(+) (limited to 'tools') diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 27f3b07fdae8..583db99aee94 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -546,6 +546,34 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer) return 0; } +/** + * kbuffer_subbuf_timestamp - read the timestamp from a sub buffer + * @kbuf: The kbuffer to load + * @subbuf: The subbuffer to read from. + * + * Return the timestamp from a subbuffer. + */ +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf) +{ + return kbuf->read_8(subbuf); +} + +/** + * kbuffer_ptr_delta - read the delta field from a record + * @kbuf: The kbuffer to load + * @ptr: The record in the buffe. + * + * Return the timestamp delta from a record + */ +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr) +{ + unsigned int type_len_ts; + + type_len_ts = read_4(kbuf, ptr); + return ts4host(kbuf, type_len_ts); +} + + /** * kbuffer_read_event - read the next event in the kbuffer subbuffer * @kbuf: The kbuffer to read from diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h index ed4d697fc137..5fa8292e341b 100644 --- a/tools/lib/traceevent/kbuffer.h +++ b/tools/lib/traceevent/kbuffer.h @@ -49,6 +49,8 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer); void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts); void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts); unsigned long long kbuffer_timestamp(struct kbuffer *kbuf); +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf); +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr); void *kbuffer_translate_data(int swap, void *data, unsigned int *size); -- cgit v1.2.3 From 2160d6c8a13e685b7b2bacbe9cd1e9600506a05f Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 2 Jul 2020 14:53:46 -0400 Subject: tools lib traceevent: Add proper KBUFFER_TYPE_TIME_STAMP handling Kernel commit dc4e2801d400 (ring-buffer: Redefine the unimplemented RINGBUF_TYPE_TIME_STAMP) changed the way the ring buffer timestamps work - after that commit the previously unimplemented RINGBUF_TYPE_TIME_STAMP type causes the time delta to be used as a timestamp rather than a delta to be added to the timestamp. The trace-cmd code didn't get updated to handle this, so misinterprets the event data for this case, which causes a cascade of errors, including trace-report not being able to identify synthetic (or any other) events generated by the histogram code (which uses TIME_STAMP mode). For example, the following triggers along with the trace-cmd shown cause an UNKNOWN_EVENT error and trace-cmd report crash: # echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > /sys/kernel/debug/tracing/synthetic_events # echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).trace(wakeup_latency,$wakeup_lat,next_pid,next_comm) if next_comm=="ping"' > /sys/kernel/debug/tracing/events/sched/sched_switch/trigger # echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger # trace-cmd record -e wakeup_latency -e sched_wakeup -f comm==\"ping\" ping localhost -c 5 # trace-cmd report CPU 0 is empty CPU 1 is empty CPU 2 is empty CPU 3 is empty CPU 5 is empty CPU 6 is empty CPU 7 is empty cpus=8 ug! no event found for type 0 [UNKNOWN TYPE 0] ug! no event found for type 11520 Segmentation fault (core dumped) After this patch we get the correct interpretation and the events are shown properly: # trace-cmd report CPU 0 is empty CPU 1 is empty CPU 2 is empty CPU 3 is empty CPU 5 is empty CPU 6 is empty CPU 7 is empty cpus=8 -0 [004] 23284.341392: sched_wakeup: ping:12031 [120] success=1 CPU:004 -0 [004] 23284.341464: wakeup_latency: lat=58, pid=12031, comm=ping -0 [004] 23285.365303: sched_wakeup: ping:12031 [120] success=1 CPU:004 -0 [004] 23285.365382: wakeup_latency: lat=64, pid=12031, comm=ping -0 [004] 23286.389290: sched_wakeup: ping:12031 [120] success=1 CPU:004 -0 [004] 23286.389378: wakeup_latency: lat=72, pid=12031, comm=ping -0 [004] 23287.413213: sched_wakeup: ping:12031 [120] success=1 CPU:004 -0 [004] 23287.413291: wakeup_latency: lat=64, pid=12031, comm=ping Link: http://lkml.kernel.org/r/1567628224.13841.4.camel@kernel.org Link: http://lore.kernel.org/linux-trace-devel/20200625100516.365338-3-tz.stoyanov@gmail.com Signed-off-by: Tom Zanussi [ Ported from trace-cmd.git ] Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20200702185703.785094515@goodmis.org Signed-off-by: Tzvetomir Stoyanov (VMware) Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/kbuffer-parse.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 583db99aee94..f1640d651c8a 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -361,6 +361,7 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, break; case KBUFFER_TYPE_TIME_EXTEND: + case KBUFFER_TYPE_TIME_STAMP: extend = read_4(kbuf, data); data += 4; extend <<= TS_SHIFT; @@ -369,10 +370,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, *length = 0; break; - case KBUFFER_TYPE_TIME_STAMP: - data += 12; - *length = 0; - break; case 0: *length = read_4(kbuf, data) - 4; *length = (*length + 3) & ~3; @@ -397,7 +394,11 @@ static unsigned int update_pointers(struct kbuffer *kbuf) type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); - kbuf->timestamp += delta; + if (type_len == KBUFFER_TYPE_TIME_STAMP) + kbuf->timestamp = delta; + else + kbuf->timestamp += delta; + kbuf->index = calc_index(kbuf, ptr); kbuf->next = kbuf->index + length; @@ -454,7 +455,9 @@ static int __next_event(struct kbuffer *kbuf) if (kbuf->next >= kbuf->size) return -1; type = update_pointers(kbuf); - } while (type == KBUFFER_TYPE_TIME_EXTEND || type == KBUFFER_TYPE_PADDING); + } while (type == KBUFFER_TYPE_TIME_EXTEND || + type == KBUFFER_TYPE_TIME_STAMP || + type == KBUFFER_TYPE_PADDING); return 0; } -- cgit v1.2.3 From d61cbb859b45fdb6b4997f2d51834fae41af0e94 Mon Sep 17 00:00:00 2001 From: Wei Li Date: Fri, 12 Jun 2020 17:43:22 +0800 Subject: perf report TUI: Fix segmentation fault in perf_evsel__hists_browse() The segmentation fault can be reproduced as following steps: 1) Executing perf report in tui. 2) Typing '/xxxxx' to filter the symbol to get nothing matched. 3) Pressing enter with no entry selected. Then it will report a segmentation fault. It is caused by the lack of check of browser->he_selection when accessing it's member res_samples in perf_evsel__hists_browse(). These processes are meaningful for specified samples, so we can skip these when nothing is selected. Fixes: 4968ac8fb7c3 ("perf report: Implement browsing of individual samples") Signed-off-by: Wei Li Acked-by: Jiri Olsa Acked-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Hanjun Guo Cc: Jin Yao Cc: Mark Rutland Link: http://lore.kernel.org/lkml/20200612094322.39565-1-liwei391@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index f98a118dfc49..4cd556c1276f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2288,6 +2288,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } +static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->res_samples : NULL; +} + /* Check whether the browser is for 'top' or 'report' */ static inline bool is_report_browser(void *timer) { @@ -3357,16 +3362,16 @@ skip_annotation: &options[nr_options], NULL, NULL, evsel); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_NORMAL); + hist_browser__selected_res_sample(browser), + evsel, A_NORMAL); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_ASM); + hist_browser__selected_res_sample(browser), + evsel, A_ASM); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_SOURCE); + hist_browser__selected_res_sample(browser), + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: -- cgit v1.2.3 From 75bcb8776dc987538f267ba4ba05ca43fc2b1676 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 30 Jun 2020 16:39:33 +0300 Subject: perf intel-pt: Fix recording PEBS-via-PT with registers When recording PEBS-via-PT, the kernel will not accept the intel_pt event with register sampling e.g. # perf record --kcore -c 10000 -e '{intel_pt/branch=0/,branch-loads/aux-output/ppp}' -I -- ls -l Error: intel_pt/branch=0/: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' Fix by suppressing register sampling on the intel_pt evsel. Committer notes: Adrian informed that this is only available from Tremont onwards, so on older processors the error continues the same as before. Fixes: 9e64cefe4335b ("perf intel-pt: Process options for PEBS event synthesis") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: Luwei Kang Link: http://lore.kernel.org/lkml/20200630133935.11150-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/intel-pt.c | 1 + tools/perf/util/evsel.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 839ef52c1ac2..6ce451293634 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -641,6 +641,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq = 0; evsel->core.attr.sample_period = 1; + evsel->no_aux_samples = true; intel_pt_evsel = evsel; opts->full_auxtrace = true; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a68ac3632ae6..ef802f6d40c1 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1014,12 +1014,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (callchain && callchain->enabled && !evsel->no_aux_samples) evsel__config_callchain(evsel, opts, callchain); - if (opts->sample_intr_regs) { + if (opts->sample_intr_regs && !evsel->no_aux_samples) { attr->sample_regs_intr = opts->sample_intr_regs; evsel__set_sample_bit(evsel, REGS_INTR); } - if (opts->sample_user_regs) { + if (opts->sample_user_regs && !evsel->no_aux_samples) { attr->sample_regs_user |= opts->sample_user_regs; evsel__set_sample_bit(evsel, REGS_USER); } -- cgit v1.2.3 From add07ccd9222ba0944df2a6d39c6e38de90cd0c5 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 30 Jun 2020 16:39:34 +0300 Subject: perf intel-pt: Fix displaying PEBS-via-PT with registers After recording PEBS-via-PT, perf script will not accept 'iregs' field e.g. # perf record -c 10000 -e '{intel_pt/branch=0/,branch-loads/aux-output/ppp}' -I -- ls -l ... [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data ] # ./perf script --itrace=eop -F+iregs Samples for 'dummy:u' event do not have IREGS attribute set. Cannot print 'iregs' field. Fix by using allow_user_set, which is true when recording AUX area data. Fixes: 9e64cefe4335b ("perf intel-pt: Process options for PEBS event synthesis") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: Luwei Kang Link: http://lore.kernel.org/lkml/20200630133935.11150-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 181d65e5a450..447457786362 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -462,7 +462,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *sess return -EINVAL; if (PRINT_FIELD(IREGS) && - evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS)) + evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set)) return -EINVAL; if (PRINT_FIELD(UREGS) && -- cgit v1.2.3 From 4c95ad261cfac120dd66238fcae222766754c219 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 30 Jun 2020 16:39:35 +0300 Subject: perf intel-pt: Fix PEBS sample for XMM registers The condition to add XMM registers was missing, the regs array needed to be in the outer scope, and the size of the regs array was too small. Fixes: 143d34a6b387b ("perf intel-pt: Add XMM registers to synthesized PEBS sample") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: Luwei Kang Link: http://lore.kernel.org/lkml/20200630133935.11150-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index e4dd8bf610ce..cb3c1e569a2d 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1735,6 +1735,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) u64 sample_type = evsel->core.attr.sample_type; u64 id = evsel->core.id[0]; u8 cpumode; + u64 regs[8 * sizeof(sample.intr_regs.mask)]; if (intel_pt_skip_event(pt)) return 0; @@ -1784,8 +1785,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) } if (sample_type & PERF_SAMPLE_REGS_INTR && - items->mask[INTEL_PT_GP_REGS_POS]) { - u64 regs[sizeof(sample.intr_regs.mask)]; + (items->mask[INTEL_PT_GP_REGS_POS] || + items->mask[INTEL_PT_XMM_POS])) { u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; -- cgit v1.2.3 From bee9ca1c8a237ca178f281062bf162637071ab04 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Jul 2020 09:29:57 -0300 Subject: perf report TUI: Remove needless 'dummy' event from menu Fixing the common case of: perf record perf report And getting just the cycles events. We now have a 'dummy' event to get perf metadata events that take place while we synthesize metadata records for pre-existing processes by traversing procfs, so we always have this extra 'dummy' evsel, but we don't have to offer it as there will be no samples on it, remove this distraction. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/20200706115452.GA2772@redhat.com/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 4cd556c1276f..be9c4c0549bc 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3603,6 +3603,23 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist, hbt, warn_lost_event); } +static bool perf_evlist__single_entry(struct evlist *evlist) +{ + int nr_entries = evlist->core.nr_entries; + + if (nr_entries == 1) + return true; + + if (nr_entries == 2) { + struct evsel *last = evlist__last(evlist); + + if (evsel__is_dummy_event(last)) + return true; + } + + return false; +} + int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, @@ -3613,7 +3630,7 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, int nr_entries = evlist->core.nr_entries; single_entry: - if (nr_entries == 1) { + if (perf_evlist__single_entry(evlist)) { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, -- cgit v1.2.3