summaryrefslogtreecommitdiffstats
path: root/tools/perf
Commit message (Collapse)AuthorAgeFilesLines
* perf script: Support total cycles countAndi Kleen2018-10-241-4/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | For 'perf script' brstackinsn also print a running cycles count. This makes it easier to calculate cycle deltas for code sections measured with LBRs. % perf record -b -a sleep 1 % perf script -F +brstackinsn ... 00007f73ecc41083 insn: 74 06 # PRED 9 cycles [17] 1.11 IPC 00007f73ecc4108b insn: a8 10 00007f73ecc4108d insn: 74 71 # PRED 1 cycles [18] 1.00 IPC 00007f73ecc41100 insn: 48 8b 46 10 00007f73ecc41104 insn: 4c 8b 38 00007f73ecc41107 insn: 4d 85 ff 00007f73ecc4110a insn: 0f 84 b0 00 00 00 00007f73ecc41110 insn: 83 43 58 01 00007f73ecc41114 insn: 48 89 df 00007f73ecc41117 insn: e8 94 73 04 00 # PRED 6 cycles [24] 1.00 IPC Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf script: Implement --graph-functionAndi Kleen2018-10-244-19/+86
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a ftrace style --graph-function argument to 'perf script' that allows to print itrace function calls only below a given function. This makes it easier to find the code of interest in a large trace. % perf record -e intel_pt//k -a sleep 1 % perf script --graph-function group_sched_in --call-trace perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage perf 900 [000] 194167.205652203: ([kernel.kallsyms]) calc_timer_values perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_cpu perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) arch_perf_update_userpage perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __fentry__ perf 900 [000] 194167.205652203: ([kernel.kallsyms]) using_native_sched_clock perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_stable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) group_sched_in swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) event_sched_in.isra.107 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_set_state.part.71 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_time swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_pmu_disable swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_log_itrace_start swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) calc_timer_values swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_cpu swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) arch_perf_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __fentry__ swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) using_native_sched_clock swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_stable Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Leo Yan <leo.yan@linaro.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Link: http://lkml.kernel.org/r/20180920180540.14039-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* tools script: Add --call-trace and --call-ret-traceAndi Kleen2018-10-242-0/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add short cut options to print PT call trace and call-ret-trace, for calls and call and returns. Roughly corresponds to ftrace function tracer and function graph tracer. Just makes these common use cases nicer to use. % perf record -a -e intel_pt// sleep 1 % perf script --call-trace perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_filter_match perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage % perf script --call-ret-trace perf 900 [000] 194167.205652203: tr strt ([unknown]) pt_config perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_config perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_event_add perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_pmu_enable perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_void perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_sched_in.isra.107 perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_int perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) group_sched_in perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_filter_match perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_filter_match perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) group_sched_in perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_txn perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_sched_in.isra.107 perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_event_set_state.part.71 Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Leo Yan <leo.yan@linaro.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Link: http://lkml.kernel.org/r/20180920180540.14039-4-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf script: Make itrace script default to all callsAndi Kleen2018-10-247-13/+30
| | | | | | | | | | | | | | | | | | | | | | | By default 'perf script' for itrace outputs sampled instructions or branches. In my experience this is confusing to users because it's hard to correlate with real program behavior. The sampling makes sense for tools like 'perf report' that actually sample to reduce the run time, but run time is normally not a problem for 'perf script'. It's better to give an accurate representation of the program flow. Default 'perf script' to output all calls for itrace. That's a much saner default. The old behavior can be still requested with 'perf script' --itrace=ibxwpe100000 v2: Fix ETM build failure v3: Really fix ETM build failure (Kim Phillips) Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Leo Yan <leo.yan@linaro.org> Link: http://lkml.kernel.org/r/20180920180540.14039-3-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf script: Add --insn-trace for instruction decodingAndi Kleen2018-10-243-0/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a --insn-trace short hand option for decoding and disassembling instruction streams for intel_pt. This automatically pipes the output into the xed disassembler to generate disassembled instructions. This just makes this use model much nicer to use. Before % perf record -e intel_pt// ... % perf script --itrace=i0ns --ns -F +insn,-event,-period | xed -F insn: -A -64 swapper 0 [000] 17276.429606186: ffffffff81010486 pt_config ([kernel.kallsyms]) nopl %eax, (%rax,%rax,1) swapper 0 [000] 17276.429606186: ffffffff8101048b pt_config ([kernel.kallsyms]) add $0x10, %rsp swapper 0 [000] 17276.429606186: ffffffff8101048f pt_config ([kernel.kallsyms]) popq %rbx swapper 0 [000] 17276.429606186: ffffffff81010490 pt_config ([kernel.kallsyms]) popq %rbp swapper 0 [000] 17276.429606186: ffffffff81010491 pt_config ([kernel.kallsyms]) popq %r12 swapper 0 [000] 17276.429606186: ffffffff81010493 pt_config ([kernel.kallsyms]) popq %r13 swapper 0 [000] 17276.429606186: ffffffff81010495 pt_config ([kernel.kallsyms]) popq %r14 swapper 0 [000] 17276.429606186: ffffffff81010497 pt_config ([kernel.kallsyms]) popq %r15 swapper 0 [000] 17276.429606186: ffffffff81010499 pt_config ([kernel.kallsyms]) retq swapper 0 [000] 17276.429606186: ffffffff8101063e pt_event_add ([kernel.kallsyms]) cmpl $0x1, 0x1b0(%rbx) swapper 0 [000] 17276.429606186: ffffffff81010645 pt_event_add ([kernel.kallsyms]) mov $0xffffffea, %eax swapper 0 [000] 17276.429606186: ffffffff8101064a pt_event_add ([kernel.kallsyms]) mov $0x0, %edx swapper 0 [000] 17276.429606186: ffffffff8101064f pt_event_add ([kernel.kallsyms]) popq %rbx swapper 0 [000] 17276.429606186: ffffffff81010650 pt_event_add ([kernel.kallsyms]) cmovnz %edx, %eax swapper 0 [000] 17276.429606186: ffffffff81010653 pt_event_add ([kernel.kallsyms]) jmp 0xffffffff81010635 swapper 0 [000] 17276.429606186: ffffffff81010635 pt_event_add ([kernel.kallsyms]) retq swapper 0 [000] 17276.429606186: ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms]) test %eax, %eax Now: % perf record -e intel_pt// ... % perf script --insn-trace --xed ... same output ... XED needs to be installed with: $ git clone https://github.com/intelxed/mbuild.git mbuild $ git clone https://github.com/intelxed/xed $ cd xed $ ./mfile.py $ ./mfile.py examples $ sudo ./mfile.py --prefix=/usr/local install $ sudo cp obj/examples/xed /usr/local/bin $ xed | head -3 ERROR: required argument(s) were missing Copyright (C) 2017, Intel Corporation. All rights reserved. XED version: [v10.0-328-g7d62c8c49b7b] $ Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20180920180540.14039-2-andi@firstfloor.org [ Fixed up whitespace damage, added the 'mfile.py examples + cp obj/examples/xed ... ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: exported-sql-viewer.py: Add All branches reportAdrian Hunter2018-10-231-0/+547
| | | | | | | | | | | | | | | | | | | | | | Add a report to display branches in a similar fashion to perf script. The main purpose of this report is to display disassembly, however, presently, the only supported disassembler is Intel XED, and additionally the object code must be present in perf build ID cache. To use Intel XED, libxed.so must be present. To build and install libxed.so: git clone https://github.com/intelxed/mbuild.git mbuild git clone https://github.com/intelxed/xed cd xed ./mfile.py --share sudo ./mfile.py --prefix=/usr/local install sudo ldconfig Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181023075949.18920-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: exported-sql-viewer.py: Add ability to display all the ↵Adrian Hunter2018-10-231-0/+694
| | | | | | | | | | | | | | | | | | | | | | | | | database tables Displaying all the database tables can help make the database easier to understand. Committer testing: Opened all the tables, even the sqlite master table, which I selected everything and used control+C, lets see if it works... CREATE VIEW threads_view AS SELECT id,machine_id,(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,process_id,pid,tid FROM threads Humm, nope, just one of the cells got copied, even with everything selected :-) Anyway, works as advertised, useful for perusing the data. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-17-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: exported-sql-viewer.py: Add ability to shrink / enlarge ↵Adrian Hunter2018-10-231-0/+24
| | | | | | | | | | | | | | | | | | | font Shrinking the font allows more information to display. Committer testing: Works, tested with the convenient Control+Shift+'+' and Control+'-' as well with the more cumbersome top menu "Edit" + "Enlarge/Shrink font" options. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-16-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: exported-sql-viewer.py: Add ability to find symbols in ↵Adrian Hunter2018-10-231-1/+305
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | the call-graph Add a Find bar that appears at the bottom of the call-graph window. Committer testing: Using: python tools/perf/scripts/python/exported-sql-viewer.py pt_example branches calls Using the database built in the first "Committer Testing" section in this patch series I was able to: "Reports" "Context-Sensitive Call Graphs" Control+F or select "Edit" in the top menu then "Find" __poll<ENTER> and find the first place where the "__poll" function appears, then press the down arrow in the lower right corner and go to the next, etc. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-15-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: exported-sql-viewer.py: Add support for multiple ↵Adrian Hunter2018-10-231-9/+173
| | | | | | | | | | | | | | | | | | | | | | sub-windows Use Qt MDI (multiple document interface) to support multiple sub-windows. Put the data model in a cache so that each sub-window can share the same data. This allows mutiple views of the call-graph at the same time and paves the way to add more reports. Committer testing: Starts with a "File Reports Windows" main menu, from the "Reports" I can get what was available up to now, the "Context-Sensitivi Call Graph" option. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-14-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Rename to exported-sql-viewer.pyAdrian Hunter2018-10-234-6/+6
| | | | | | | | | | | Additional reports will be added to the script so rename to reflect the more general purpose. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-13-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Refactor TreeItem classAdrian Hunter2018-10-231-140/+133
| | | | | | | | | | | | | | class TreeItem represents items at all levels of the call-graph tree. However, not all the levels represent the same data i.e. the top-level is comms, the next level is threads, and subsequent levels are functions. Consequently it is simpler to have separate classes for different levels with commonality in a base class. Refactor TreeItem class accordingly. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-12-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Add data helper functionsAdrian Hunter2018-10-231-25/+29
| | | | | | | | | | Add helper functions for a few common cases. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-11-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Factor out CallGraphModel from ↵Adrian Hunter2018-10-231-29/+61
| | | | | | | | | | | | | TreeModel Factor out CallGraphModel from TreeModel, which paves the way to reuse TreeModel in future reports. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-10-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Remove use of setObjectName()Adrian Hunter2018-10-231-1/+0
| | | | | | | | | | The object name is never used, so don't bother setting it. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-9-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Add a class for global dataAdrian Hunter2018-10-231-5/+21
| | | | | | | | | | | Keep global data in a single object that is easy to pass around as needed, without polluting the global namespace. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-8-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Separate the database details ↵Adrian Hunter2018-10-231-25/+38
| | | | | | | | | | | | | | into a class Separate the database details into a class that can provide different connections using the same connection information. That paves the way for sub-processes that require their own connection. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-7-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Make a "Main" functionAdrian Hunter2018-10-231-1/+6
| | | | | | | | | | | Make a "Main" function so that the variables used do not pollute the global namespace. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Change iconAdrian Hunter2018-10-231-3/+1
| | | | | | | | | | | | | | | | | There are not many standard icons, but the computer icon looks slightly better than the information icon. Committer testing: Noticed the change on the icon on the gnome menu right next to the "Activities" menu, looks nicer indeed. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Set a minimum window sizeAdrian Hunter2018-10-231-0/+1
| | | | | | | | | | | | | | | | | | | | | | Prevent weirdly small window size. Committer testing: Seems to work, but even before this patch, on my system, it always started with: xwininfo: Window id: 0x1e00002 "Call Graph: pt_example" <SNIP> Width: 800 Height: 600 <SNIP> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Provide better default column sizesAdrian Hunter2018-10-231-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Set initial column sizes to improve initial display. Committer testing: Extended instructions on testing this, using the sqlite variant: Make sure you have the SQLite glue for python+Qt installed, on fedora 27 I used: # dnf install python-pyside Collect some PT samples, say 5-secs worth, system wide: # perf record -r 10 -e intel_pt//u -a sleep 5 [ perf record: Woken up 49 times to write data ] [ perf record: Captured and wrote 96.131 MB perf.data ] This results in this perf.data file: # ls -larth perf.data -rw-------. 1 root root 97M Oct 23 10:11 perf.data With the following attributes: # perf evlist -v intel_pt//u: type: 8, size: 112, config: 0x300e601, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 1, exclude_hv: 1, sample_id_all: 1 dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1, context_switch: 1 # Then generate the "pt_example" tables using: # perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls 2018-10-23 10:56:59.177711 Creating database... 2018-10-23 10:56:59.195842 Writing records... instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x263984516750 code 5: Failed to get instruction instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e116fd20 code 6: Trace doesn't match instruction instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e162c9ee code 6: Trace doesn't match instruction instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e9ce831a code 6: Trace doesn't match instruction <SNIP> instruction trace error type 1 cpu 0 pid 1644 tid 1644 ip 0x7f26e13d07b4 code 6: Trace doesn't match instruction Warning: 132 instruction trace errors 2018-10-23 11:25:25.015717 Adding indexes 2018-10-23 11:25:28.788061 Done # In my example, that perf.data file generated this db: # file pt_example pt_example: SQLite 3.x database, last written using SQLite version 3020001 [root@seventh perf]# ls -lah pt_example -rw-r--r--. 1 root root 6.6G Oct 23 11:25 pt_example # Then use this python script to use that db and provide a GUI: $ python tools/perf/scripts/python/call-graph-from-sql.py pt_example branches calls I compared the column widths before this patch and after applying it, the visual results match the patch intent. The following patches will refer to this set of instructions in the "Committer Testing" section. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf scripts python: call-graph-from-sql.py: Use SPDX license identifierAdrian Hunter2018-10-221-11/+3
| | | | | | | | | | Use SPDX license identifier in call-graph-from-sql.py. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20181001062853.28285-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf trace: Introduce per-event maximum number of events propertyArnaldo Carvalho de Melo2018-10-223-2/+38
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Call it 'nr', as in this context it should be expressive enough, i.e.: # perf trace -e sched:*waking/nr=8,call-graph=fp/ 0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001 try_to_wake_up ([kernel.kallsyms]) sched_clock ([kernel.kallsyms]) 3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001 try_to_wake_up ([kernel.kallsyms]) sched_clock ([kernel.kallsyms]) 3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003 try_to_wake_up ([kernel.kallsyms]) __libc_write (/usr/lib64/libpthread-2.26.so) 20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003 try_to_wake_up ([kernel.kallsyms]) __libc_write (/usr/lib64/libpthread-2.26.so) 37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003 try_to_wake_up ([kernel.kallsyms]) __libc_write (/usr/lib64/libpthread-2.26.so) 53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003 try_to_wake_up ([kernel.kallsyms]) __libc_write (/usr/lib64/libpthread-2.26.so) 70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003 try_to_wake_up ([kernel.kallsyms]) __libc_write (/usr/lib64/libpthread-2.26.so) 75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000 try_to_wake_up ([kernel.kallsyms]) try_to_wake_up ([kernel.kallsyms]) wake_up_q ([kernel.kallsyms]) futex_wake ([kernel.kallsyms]) do_futex ([kernel.kallsyms]) __x64_sys_futex ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64_after_hwframe ([kernel.kallsyms]) pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so) # # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/ 0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120] 0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120] 570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66 __dev_queue_xmit ([kernel.kallsyms]) 1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8] 1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1 1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30] 1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52 __dev_queue_xmit ([kernel.kallsyms]) 3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52 __dev_queue_xmit ([kernel.kallsyms]) 4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8] 4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8] # The global --max-events has precendence: # trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/ 0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120] 0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120] 58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84 __dev_queue_xmit ([kernel.kallsyms]) __libc_send (/usr/lib64/libpthread-2.26.so) # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf script: Flush output stream after events in verbose modeMilian Wolff2018-10-221-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the perf script output is written to a terminal stream, the normal output of `perf script` would get buffered, but its debug output would be written directly. This made it quite hard to figure out where a given debug output is coming from. We can improve on this by flushing the output buffer after processing an event. To see the value, compare the following output for a `perf script -v` run: Before this patch: ``` unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 ... lots and lots of verbose debug output cpp-inlining 24617 90229.122036534: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) cpp-inlining 24617 90229.122043974: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) ... ``` After this patch: ``` ... unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) cpp-inlining 24617 90229.122036534: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) cpp-inlining 24617 90229.122043974: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) ... ``` This new output format makes it much easier to use perf script output for debugging purposes, e.g. to investigate broken dwarf unwinding. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20181021191424.16183-2-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf script: Allow extended console debug outputMilian Wolff2018-10-221-1/+3
| | | | | | | | | | | | | | | | | | | | | The script tool isn't using a browser, yet use_browser wasn't set explicitly to zero. This in turn lead to confusing output such as: ``` $ perf script -vvv ... ... overlapping maps in /home/milian/foobar (disable tui for more info) ... ``` Explicitly set use_browser to 0 now, which gives us the extended debug information now in perf script as expected. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lkml.kernel.org/r/20181021191424.16183-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Poll for monitored tasks being aliveJiri Olsa2018-10-221-0/+24
| | | | | | | | | | | | | | | Adding the check for tasks we monitor via -p/-t options, and finish stat if there's no longer task to monitor. Requested-by: Stephane Eranian <eranian@google.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lkml.kernel.org/r/20181022093015.9106-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf trace: Drop thread refcount in trace__event_handler()Arnaldo Carvalho de Melo2018-10-221-1/+1
| | | | | | | | | | | | | | | | | We must pair: thread = machine__findnew_thread(); with thread__put(thread). Fix it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Fixes: c4191e55b874 ("perf trace: Show comm and tid for tracepoint events") Link: https://lkml.kernel.org/n/tip-dkxsb8cwg87rmkrzrbns1o4z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf trace: Drop addr_location refcountsArnaldo Carvalho de Melo2018-10-221-3/+5
| | | | | | | | | | | | | | | | When we use machine__resolve() we grab a reference to addr_location.thread (and in the future to other elements there) via machine__findnew_thread(), so we must pair that with addr_location__put(), else we'll never drop that thread when it exits and no other remaining data structures have pointers to it. Fix it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-ivg9hifzeuokb1f5jxc2wob4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Mark a evsel as disabled when asking the kernel do disable itArnaldo Carvalho de Melo2018-10-223-7/+19
| | | | | | | | | | | | | | | | Because there may be more such events in the ring buffer that should be discarded when an app decides to stop considering them. At some point we'll do this with eBPF, this way we stop them at origin, before they are placed in the ring buffer. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-uzufuxws4hufigx07ue1dpv6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Introduce per event max_events propertyArnaldo Carvalho de Melo2018-10-195-0/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This simply adds the field to 'struct perf_evsel' and allows setting it via the event parser, to test it lets trace trace: First look at where in a function that receives an evsel we can put a probe to read how evsel->max_events was setup: # perf probe -x ~/bin/perf -L trace__event_handler <trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0> 0 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) 3 { 4 struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); 5 int callchain_ret = 0; 7 if (sample->callchain) { 8 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); 9 if (callchain_ret == 0) { 10 if (callchain_cursor.nr < trace->min_stack) 11 goto out; 12 callchain_ret = 1; } } See what variables we can probe at line 7: # perf probe -x ~/bin/perf -V trace__event_handler:7 Available variables at trace__event_handler:7 @<trace__event_handler+89> int callchain_ret struct perf_evsel* evsel struct perf_sample* sample struct thread* thread struct trace* trace union perf_event* event Add a probe at that line asking for evsel->max_events to be collected and named as "max_events": # perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events' Added new event: probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events) You can now use it in all perf tools, such as: perf record -e probe_perf:trace__event_handler -aR sleep 1 Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e. the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event, while the traced trace is tracing all scheduler tracepoints, will stop at two events (--max-events 2) and will just set evsel->max_events for all the sched tracepoints to 9, we will see the output of both traces intermixed: # trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/ 0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now, if the traced trace sends its output to /dev/null, we'll see just what the first level trace outputs: that evsel->max_events is indeed being set to 9: # trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/ 0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now that we can set evsel->max_events, we can go to the next step, honour that per-event property in 'perf trace'. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf trace: Introduce --max-eventsArnaldo Carvalho de Melo2018-10-192-0/+68
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Allow stopping tracing after a number of events take place, considering strace-like syscalls formatting as one event per enter/exit pair or when in a multi-process tracing session a syscall is interrupted and printed ending with '...'. Examples included in the documentation: Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here): $ perf trace -e open* --max-events 4 [root@jouet perf]# trace -e open* --max-events 4 2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31 2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65 3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65 4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3 $ Trace the first minor page fault when running a workload: # perf trace -F min --max-stack=7 --max-events 1 sleep 1 0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k) __clear_user ([kernel.kallsyms]) load_elf_binary ([kernel.kallsyms]) search_binary_handler ([kernel.kallsyms]) __do_execve_file.isra.33 ([kernel.kallsyms]) __x64_sys_execve ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64 ([kernel.kallsyms]) # Trace the next min page page fault to take place on the first CPU: # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0 0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.) js::gc::FreeSpan::initAsEmpty (inlined) js::gc::Arena::setAsNotAllocated (inlined) js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so) js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so) js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so) js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so) js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined) js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so) js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined) JSThinInlineString::new_<(js::AllowGC)1> (inlined) AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined) js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so) [0x18b26e6bc2bd] (/tmp/perf-17136.map) Tracing the next four ext4 operations on a specific CPU: # perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3 0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0 ext4_es_lookup_extent ([kernel.kallsyms]) read (/usr/lib64/libc-2.26.so) 0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0 ext4_es_lookup_extent ([kernel.kallsyms]) read (/usr/lib64/libc-2.26.so) 0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags ext4_ext_map_blocks ([kernel.kallsyms]) read (/usr/lib64/libc-2.26.so) 0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657 __read_extent_tree_block ([kernel.kallsyms]) __read_extent_tree_block ([kernel.kallsyms]) ext4_find_extent ([kernel.kallsyms]) ext4_ext_map_blocks ([kernel.kallsyms]) ext4_map_blocks ([kernel.kallsyms]) ext4_mpage_readpages ([kernel.kallsyms]) read_pages ([kernel.kallsyms]) __do_page_cache_readahead ([kernel.kallsyms]) ondemand_readahead ([kernel.kallsyms]) generic_file_read_iter ([kernel.kallsyms]) __vfs_read ([kernel.kallsyms]) vfs_read ([kernel.kallsyms]) ksys_read ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64 ([kernel.kallsyms]) read (/usr/lib64/libc-2.26.so) # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Rudá Moura <ruda.moura@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf arm64: Fix generate system call table failed with /tmp mounted with noexecHongxu Jia2018-10-191-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | When /tmp is mounted with noexec, mksyscalltbl fails. [snip] |perf-1.0/tools/perf/arch/arm64/entry/syscalls//mksyscalltbl: /tmp/create-table-6VGPSt: Permission denied [snip] Add variable TMPDIR as prefix dir of the temporary file, if it is set, replace default /tmp. Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Sébastien Boisvert <sboisvert@gydle.com> Cc: Thomas Richter <tmricht@linux.vnet.ibm.com> Fixes: 2b5882435606 ("perf arm64: Generate system call table from asm/unistd.h") LPU-Reference: 1539851173-14959-1-git-send-email-hongxu.jia@windriver.com Link: https://lkml.kernel.org/n/tip-1qrgq840ci0c5cy4oww957ge@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf symbols: Set PLT entry/header sizes properly on SparcDavid Miller2018-10-181-1/+11
| | | | | | | | | | | | | | | | | | | | | | | | | Using the sh_entsize for both values isn't correct. It happens to be correct on x86... For both 32-bit and 64-bit sparc, there are four PLT entries in the PLT section. Signed-off-by: David S. Miller <davem@davemloft.net> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexis Berlemont <alexis.berlemont@gmail.com> Cc: David Tolnay <dtolnay@gmail.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: zhangmengting@huawei.com Fixes: b2f7605076d6 ("perf symbols: Fix plt entry calculation for ARM and AARCH64") Link: http://lkml.kernel.org/r/20181017.120859.2268840244308635255.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf jitdump: Add Sparc support.David Miller2018-10-182-0/+8
| | | | | | Signed-off-by: David S. Miller <davem@davemloft.net> Link: http://lkml.kernel.org/r/20181016.211545.1487970139012324624.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf annotate: Add Sparc supportDavid Miller2018-10-182-0/+177
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | E.g.: $ perf annotate --stdio2 Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887 __gettimeofday /lib32/libc-2.27.so [Percent: local period] Percent│ │ │ │ Disassembly of section .text: │ │ 000a6fa0 <__gettimeofday@@GLIBC_2.0>: 0.47 │ save %sp, -96, %sp 0.73 │ sethi %hi(0xe9000), %l7 │ → call __frame_state_for@@GLIBC_2.0+0x480 0.30 │ add %l7, 0x58, %l7 ! e9058 <nftw64@@GLIBC_2.3.3+0x818> 1.33 │ mov %i0, %o0 │ mov %i1, %o1 0.43 │ mov 0x74, %g1 │ ta 0x10 88.92 │ ↓ bcc 30 2.95 │ clr %g1 │ neg %o0 │ mov 1, %g1 0.31 │30: cmp %g1, 0 │ bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44> │ mov %o0, %i0 1.96 │ ← return %i7 + 8 2.62 │ nop │ sethi %hi(0), %g1 │ neg %o0, %g2 │ add %g1, 0x160, %g1 │ ld [ %l7 + %g1 ], %g1 │ st %g2, [ %g7 + %g1 ] │ ← return %i7 + 8 │ mov -1, %o0 Signed-off-by: David S. Miller <davem@davemloft.net> Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf record: Encode -k clockid frequency into Perf traceAlexey Budankov2018-10-185-2/+48
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Store -k clockid frequency into Perf trace to enable timestamps derived metrics conversion into wall clock time on reporting stage. Below is the example of perf report output: tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc ... [ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ] tools/perf/perf report --header # ======== ... # event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4 ... # clockid frequency: 1000 MHz ... # ======== Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/23a4a1dc-b160-85a0-347d-40a2ed6d007b@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* Merge remote-tracking branch 'tip/perf/urgent' into perf/coreArnaldo Carvalho de Melo2018-10-189-43/+35
|\ | | | | | | | | | | To pick up fixes. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf tools: Stop fallbacking to kallsyms for vdso symbols lookupArnaldo Carvalho de Melo2018-10-171-19/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | David reports that: <quote> Perf has this hack where it uses the kernel symbol map as a backup when a symbol can't be found in the user's symbol table(s). This causes problems because the tests driving this code path use machine__kernel_ip(), and that is completely meaningless on Sparc. On sparc64 the kernel and user live in physically separate virtual address spaces, rather than a shared one. And the kernel lives at a virtual address that overlaps common userspace addresses. So this test passes almost all the time when a user symbol lookup fails. The consequence of this is that, if the unfound user virtual address in the sample doesn't match up to a kernel symbol either, we trigger things like this code in builtin-top.c: if (al.sym == NULL && al.map != NULL) { const char *msg = "Kernel samples will not be resolved.\n"; /* * As we do lazy loading of symtabs we only will know if the * specified vmlinux file is invalid when we actually have a * hit in kernel space and then try to load it. So if we get * here and there are _no_ symbols in the DSO backing the * kernel map, bail out. * * We may never get here, for instance, if we use -K/ * --hide-kernel-symbols, even if the user specifies an * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; dso__strerror_load(al.map->dso, serr, sizeof(serr)); ui__warning("The %s file can't be used: %s\n%s", symbol_conf.vmlinux_name, serr, msg); } else { ui__warning("A vmlinux file was not found.\n%s", msg); } if (use_browser <= 0) sleep(5); top->vmlinux_warned = true; } } When I fire up a compilation on sparc, this triggers immediately. I'm trying to figure out what the "backup to kernel map" code is accomplishing. I see some language in the current code and in the changes that have happened in this area talking about vdso. Does that really happen? The vdso is mapped into userspace virtual addresses, not kernel ones. More history. This didn't cause problems on sparc some time ago, because the kernel IP check used to be "ip < 0" :-) Sparc kernel addresses are not negative. But now with machine__kernel_ip(), which works using the symbol table determined kernel address range, it does trigger. What it all boils down to is that on architectures like sparc, machine__kernel_ip() should always return false in this scenerio, and therefore this kind of logic: if (cpumode == PERF_RECORD_MISC_USER && machine && mg != &machine->kmaps && machine__kernel_ip(machine, al->addr)) { is basically invalid. PERF_RECORD_MISC_USER implies no kernel address can possibly match for the sample/event in question (no matter how hard you try!) :-) </> So, I thought something had changed and in the past we would somehow find that address in the kallsyms, but I couldn't find anything to back that up, the patch introducing this is over a decade old, lots of things changed, so I was just thinking I was missing something. I tried a gtod busy loop to generate vdso activity and added a 'perf probe' at that branch, on x86_64 to see if it ever gets hit: Made thread__find_map() noinline, as 'perf probe' in lines of inline functions seems to not be working, only at function start. (Masami?) # perf probe -x ~/bin/perf -L thread__find_map:57 <thread__find_map@/home/acme/git/perf/tools/perf/util/event.c:57> 57 if (cpumode == PERF_RECORD_MISC_USER && machine && 58 mg != &machine->kmaps && 59 machine__kernel_ip(machine, al->addr)) { 60 mg = &machine->kmaps; 61 load_map = true; 62 goto try_again; } } else { /* * Kernel maps might be changed when loading * symbols so loading * must be done prior to using kernel maps. */ 69 if (load_map) 70 map__load(al->map); 71 al->addr = al->map->map_ip(al->map, al->addr); # perf probe -x ~/bin/perf thread__find_map:60 Added new event: probe_perf:thread__find_map (on thread__find_map:60 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:thread__find_map -aR sleep 1 # Then used this to see if, system wide, those probe points were being hit: # perf trace -e *perf:thread*/max-stack=8/ ^C[root@jouet ~]# No hits when running 'perf top' and: # cat gtod.c #include <sys/time.h> int main(void) { struct timeval tv; while (1) gettimeofday(&tv, 0); return 0; } [root@jouet c]# ./gtod ^C Pressed 'P' in 'perf top' and the [vdso] samples are there: 62.84% [vdso] [.] __vdso_gettimeofday 8.13% gtod [.] main 7.51% [vdso] [.] 0x0000000000000914 5.78% [vdso] [.] 0x0000000000000917 5.43% gtod [.] _init 2.71% [vdso] [.] 0x000000000000092d 0.35% [kernel] [k] native_io_delay 0.33% libc-2.26.so [.] __memmove_avx_unaligned_erms 0.20% [vdso] [.] 0x000000000000091d 0.17% [i2c_i801] [k] i801_access 0.06% firefox [.] free 0.06% libglib-2.0.so.0.5400.3 [.] g_source_iter_next 0.05% [vdso] [.] 0x0000000000000919 0.05% libpthread-2.26.so [.] __pthread_mutex_lock 0.05% libpixman-1.so.0.34.0 [.] 0x000000000006d3a7 0.04% [kernel] [k] entry_SYSCALL_64_trampoline 0.04% libxul.so [.] style::dom_apis::query_selector_slow 0.04% [kernel] [k] module_get_kallsym 0.04% firefox [.] malloc 0.04% [vdso] [.] 0x0000000000000910 I added a 'perf probe' to thread__find_map:69, and that surely got tons of hits, i.e. for every map found, just to make sure the 'perf probe' command was really working. In the process I noticed a bug, we're only have records for '[vdso]' for pre-existing commands, i.e. ones that are running when we start 'perf top', when we will generate the PERF_RECORD_MMAP by looking at /perf/PID/maps. I.e. like this, for preexisting processes with a vdso map, again, tracing for all the system, only pre-existing processes get a [vdso] map (when having one): [root@jouet ~]# perf probe -x ~/bin/perf __machine__addnew_vdso Added new event: probe_perf:__machine__addnew_vdso (on __machine__addnew_vdso in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:__machine__addnew_vdso -aR sleep 1 [root@jouet ~]# perf trace -e probe_perf:__machine__addnew_vdso/max-stack=8/ 0.000 probe_perf:__machine__addnew_vdso:(568eb3) __machine__addnew_vdso (/home/acme/bin/perf) map__new (/home/acme/bin/perf) machine__process_mmap2_event (/home/acme/bin/perf) machine__process_event (/home/acme/bin/perf) perf_event__process (/home/acme/bin/perf) perf_tool__process_synth_event (/home/acme/bin/perf) perf_event__synthesize_mmap_events (/home/acme/bin/perf) __event__synthesize_thread (/home/acme/bin/perf) The kernel is generating a PERF_RECORD_MMAP for vDSOs, but somehow 'perf top' is not getting those records while 'perf record' is: # perf record ~acme/c/gtod ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.076 MB perf.data (1499 samples) ] # perf report -D | grep PERF_RECORD_MMAP2 71293612401913 0x11b48 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x400000(0x1000) @ 0 fd:02 1137 541179306]: r-xp /home/acme/c/gtod 71293612419012 0x11be0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a2783000(0x227000) @ 0 fd:00 3146370 854107250]: r-xp /usr/lib64/ld-2.26.so 71293612432110 0x11c50 [0x60]: PERF_RECORD_MMAP2 25484/25484: [0x7ffcdb53a000(0x2000) @ 0 00:00 0 0]: r-xp [vdso] 71293612509944 0x11cb0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a23cd000(0x3b6000) @ 0 fd:00 3149723 262067164]: r-xp /usr/lib64/libc-2.26.so # # perf script | grep vdso | head gtod 25484 71293.612768: 2485554 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso]) gtod 25484 71293.613576: 2149343 cycles:ppp: 7ffcdb53a917 [unknown] ([vdso]) gtod 25484 71293.614274: 1814652 cycles:ppp: 7ffcdb53aca8 __vdso_gettimeofday+0x98 ([vdso]) gtod 25484 71293.614862: 1669070 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso]) gtod 25484 71293.615404: 1451589 cycles:ppp: 7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso]) gtod 25484 71293.615999: 1269941 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) gtod 25484 71293.616405: 1177946 cycles:ppp: 7ffcdb53a914 [unknown] ([vdso]) gtod 25484 71293.616775: 1121290 cycles:ppp: 7ffcdb53ac47 __vdso_gettimeofday+0x37 ([vdso]) gtod 25484 71293.617150: 1037721 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) gtod 25484 71293.617478: 994526 cycles:ppp: 7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso]) # The patch is the obvious one and with it we also continue to resolve vdso symbols for pre-existing processes in 'perf top' and for all processes in 'perf record' + 'perf report/script'. Suggested-by: David Miller <davem@davemloft.net> Acked-by: David Miller <davem@davemloft.net> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-cs7skq9pp0kjypiju6o7trse@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf tools: Pass build flags to traceevent buildJiri Olsa2018-10-161-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | So the extra user build flags are propagated to libtraceevent. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: "Herton R. Krzesinski" <herton@redhat.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com> Cc: Yordan Karadzhov (VMware) <y.karadz@gmail.com> Link: http://lkml.kernel.org/r/20181016150614.21260-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf report: Don't crash on invalid inline debug informationMilian Wolff2018-10-161-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the function name for an inline frame is invalid, we must not try to demangle this symbol, otherwise we crash with: #0 0x0000555555895c01 in bfd_demangle () #1 0x0000555555823262 in demangle_sym (dso=0x555555d92b90, elf_name=0x0, kmodule=0) at util/symbol-elf.c:215 #2 dso__demangle_sym (dso=dso@entry=0x555555d92b90, kmodule=<optimized out>, kmodule@entry=0, elf_name=elf_name@entry=0x0) at util/symbol-elf.c:400 #3 0x00005555557fef4b in new_inline_sym (funcname=0x0, base_sym=0x555555d92b90, dso=0x555555d92b90) at util/srcline.c:89 #4 inline_list__append_dso_a2l (dso=dso@entry=0x555555c7bb00, node=node@entry=0x555555e31810, sym=sym@entry=0x555555d92b90) at util/srcline.c:264 #5 0x00005555557ff27f in addr2line (dso_name=dso_name@entry=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf", addr=addr@entry=2888, file=file@entry=0x0, line=line@entry=0x0, dso=dso@entry=0x555555c7bb00, unwind_inlines=unwind_inlines@entry=true, node=0x555555e31810, sym=0x555555d92b90) at util/srcline.c:313 #6 0x00005555557ffe7c in addr2inlines (sym=0x555555d92b90, dso=0x555555c7bb00, addr=2888, dso_name=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf") at util/srcline.c:358 So instead handle the case where we get invalid function names for inlined frames and use a fallback '??' function name instead. While this crash was originally reported by Hadrien for rust code, I can now also reproduce it with trivial C++ code. Indeed, it seems like libbfd fails to interpret the debug information for the inline frame symbol name: $ addr2line -e /home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf -if b48 main /usr/include/c++/8.2.1/complex:610 ?? /usr/include/c++/8.2.1/complex:618 ?? /usr/include/c++/8.2.1/complex:675 ?? /usr/include/c++/8.2.1/complex:685 main /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 I've reported this bug upstream and also attached a patch there which should fix this issue: https://sourceware.org/bugzilla/show_bug.cgi?id=23715 Reported-by: Hadrien Grasland <grasland@lal.in2p3.fr> Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Fixes: a64489c56c30 ("perf report: Find the inline stack for a given address") [ The above 'Fixes:' cset is where originally the problem was introduced, i.e. using a2l->funcname without checking if it is NULL, but this current patch fixes the current codebase, i.e. multiple csets were applied after a64489c56c30 before the problem was reported by Hadrien ] Link: http://lkml.kernel.org/r/20180926135207.30263-3-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf cpu_map: Align cpu map synthesized events properly.David Miller2018-10-161-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | The size of the resulting cpu map can be smaller than a multiple of sizeof(u64), resulting in SIGBUS on cpus like Sparc as the next event will not be aligned properly. Signed-off-by: David S. Miller <davem@davemloft.net> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Fixes: 6c872901af07 ("perf cpu_map: Add cpu_map event synthesize function") Link: http://lkml.kernel.org/r/20181011.224655.716771175766946817.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf tools: Fix use of alternatives to find JDIRJarod Wilson2018-10-161-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When a build is run from something like a cron job, the user's $PATH is rather minimal, of note, not including /usr/sbin in my own case. Because of that, an automated rpm package build ultimately fails to find libperf-jvmti.so, because somewhere within the build, this happens... /bin/sh: alternatives: command not found /bin/sh: alternatives: command not found Makefile.config:849: No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel ...and while the build continues, libperf-jvmti.so isn't built, and things fall down when rpm tries to find all the %files specified. Exact same system builds everything just fine when the job is launched from a login shell instead of a cron job, since alternatives is in $PATH, so openjdk is actually found. The test required to get into this section of code actually specifies the full path, as does a block just above it, so let's do that here too. Signed-off-by: Jarod Wilson <jarod@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: William Cohen <wcohen@redhat.com> Fixes: d4dfdf00d43e ("perf jvmti: Plug compilation into perf build") Link: http://lkml.kernel.org/r/20180906221812.11167-1-jarod@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf evsel: Store ids for events with their own cpus ↵Jiri Olsa2018-10-162-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | perf_event__synthesize_event_update_cpus John reported crash when recording on an event under PMU with cpumask defined: root@localhost:~# ./perf_debug_ record -e armv8_pmuv3_0/br_mis_pred/ sleep 1 perf: Segmentation fault Obtained 9 stack frames. ./perf_debug_() [0x4c5ef8] [0xffff82ba267c] ./perf_debug_() [0x4bc5a8] ./perf_debug_() [0x419550] ./perf_debug_() [0x41a928] ./perf_debug_() [0x472f58] ./perf_debug_() [0x473210] ./perf_debug_() [0x4070f4] /lib/aarch64-linux-gnu/libc.so.6(__libc_start_main+0xe0) [0xffff8294c8a0] Segmentation fault (core dumped) We synthesize an update event that needs to touch the evsel id array, which is not defined at that time. Fixing this by forcing the id allocation for events with their own cpus. Reported-by: John Garry <john.garry@huawei.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: John Garry <john.garry@huawei.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Fixes: bfd8f72c2778 ("perf record: Synthesize unit/scale/... in event update") Link: http://lkml.kernel.org/r/20181003212052.GA32371@krava Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf vendor events intel: Fix wrong filter_band* values for uncore eventsJiri Olsa2018-10-112-16/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Michael reported that he could not stat following event: $ perf stat -e unc_p_freq_ge_1200mhz_cycles -a -- ls event syntax error: '..e_1200mhz_cycles' \___ value too big for format, maximum is 255 Run 'perf list' for a list of valid events The event is unwrapped into: uncore_pcu/event=0xb,filter_band0=1200/ where filter_band0 format says it's one byte only: # cat uncore_pcu/format/filter_band0 config1:0-7 while JSON files specifies bigger number: "Filter": "filter_band0=1200", all the filter_band* formats show 1 byte width: # cat uncore_pcu/format/filter_band1 config1:8-15 # cat uncore_pcu/format/filter_band2 config1:16-23 # cat uncore_pcu/format/filter_band3 config1:24-31 The reason of the issue is that filter_band* values are supposed to be in 100Mhz units.. it's stated in the JSON help for the events, like: filter_band3=XXX, with XXX in 100Mhz units This patch divides the filter_band* values by 100, plus there's couple of changes that actually change the number completely, like: - "Filter": "edge=1,filter_band2=4000", + "Filter": "edge=1,filter_band2=30", Reported-by: Michael Petlan <mpetlan@redhat.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20181010080339.GB15790@krava Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * Revert "perf tools: Fix PMU term format max value calculation"Jiri Olsa2018-10-091-6/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit ac0e2cd555373ae6f8f3a3ad3fbbf5b6d1e7aaaa. Michael reported an issue with oversized terms values assignment and I noticed there was actually a misunderstanding of the max value check in the past. The above commit's changelog says: If bit 21 is set, there is parsing issues as below. $ perf stat -a -e uncore_qpi_0/event=0x200002,umask=0x8/ event syntax error: '..pi_0/event=0x200002,umask=0x8/' \___ value too big for format, maximum is 511 But there's no issue there, because the event value is distributed along the value defined by the format. Even if the format defines separated bit, the value is treated as a continual number, which should follow the format definition. In above case it's 9-bit value with last bit separated: $ cat uncore_qpi_0/format/event config:0-7,21 Hence the value 0x200002 is correctly reported as format violation, because it exceeds 9 bits. It should have been 0x102 instead, which sets the 9th bit - the bit 21 of the format. $ perf stat -vv -a -e uncore_qpi_0/event=0x102,umask=0x8/ Using CPUID GenuineIntel-6-2D ... ------------------------------------------------------------ perf_event_attr: type 10 size 112 config 0x200802 sample_type IDENTIFIER ... Reported-by: Michael Petlan <mpetlan@redhat.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: ac0e2cd55537 ("perf tools: Fix PMU term format max value calculation") Link: http://lkml.kernel.org/r/20181003072046.29276-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* | Merge tag 'perf-core-for-mingo-4.20-20181008' of ↵Ingo Molnar2018-10-0910-24/+57
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: - Fix building the python bindings with python3, which fixes some problems with building with clang on Clear Linux (Eduardo Habkost) - Fix coverity warnings, fixing up some error paths and plugging some temporary small buffer leaks (Sanskriti Sharma) - Adopt a wrapper for strerror_r() for the same reasons as recently for libbpf (Steven Rostedt) - S390 does not support watchpoints in perf test 22', check if that test is supported by the arch. (Thomas Richter) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
| * | tools lib traceevent, perf tools: Move struct tep_handler definition in a ↵Tzvetomir Stoyanov2018-10-082-11/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | local header file As traceevent is going to be transferred into a proper library, its local data should be protected from the library users. This patch encapsulates struct tep_handler into a local header, not visible outside of the library. It implements also a bunch of new APIs, which library users can use to access tep_handler members. Signed-off-by: Tzvetomir Stoyanov <tstoyanov@vmware.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: linux trace devel <linux-trace-devel@vger.kernel.org> Cc: tzvetomir stoyanov <tstoyanov@vmware.com> Link: http://lkml.kernel.org/r/20181005122225.522155df@gandalf.local.home Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf python: More portable way to make CFLAGS work with clangEduardo Habkost2018-10-081-6/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The existing code that tries to make CFLAGS compatible with clang doesn't work with Python 3. Instead of trying to touch _sysconfigdata.build_time_vars directly, change the dictionary returned by disutils.sysconfig.get_config_vars(). This works on both Python 2 and Python 3. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20181005204058.7966-3-ehabkost@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf python: Make clang_has_option() work on Python 3Eduardo Habkost2018-10-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use a bytes literal so it works with Python 3's version of Popen(). Note that the b"..." syntax requires Python 2.6+. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20181005204058.7966-2-ehabkost@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf tools: Free temporary 'sys' string in read_event_files()Sanskriti Sharma2018-10-081-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For each system in a given pevent, read_event_files() reads in a temporary 'sys' string. Be sure to free this string before moving onto to the next system and/or leaving read_event_files(). Fixes the following coverity complaints: Error: RESOURCE_LEAK (CWE-772): tools/perf/util/trace-event-read.c:343: overwrite_var: Overwriting "sys" in "sys = read_string()" leaks the storage that "sys" points to. tools/perf/util/trace-event-read.c:353: leaked_storage: Variable "sys" going out of scope leaks the storage it points to. Signed-off-by: Sanskriti Sharma <sansharm@redhat.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Joe Lawrence <joe.lawrence@redhat.com> Link: http://lkml.kernel.org/r/1538490554-8161-6-git-send-email-sansharm@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
OpenPOWER on IntegriCloud