Changes in Build

8a54784e - perf build: Add pylint build tests

Tue, 11 Mar 2025 21:36:26 +0000

perf build: Add pylint build testsIf PYLINT=1 is passed to the build then run pylint over python code inperf. Unlike shellcheck this isn't default on as there are currentlytoo many errors.An example of an error:```************* Module setuputil/setup.py:19:0: C0301: Line too long (127/100) (line-too-long)util/setup.py:20:0: C0301: Line too long (138/100) (line-too-long)util/setup.py:63:0: C0301: Line too long (106/100) (line-too-long)util/setup.py:1:0: C0114: Missing module docstring (missing-module-docstring)util/setup.py:24:4: W0622: Redefining built-in 'vars' (redefined-builtin)util/setup.py:11:4: C0103: Constant name "cc_options" doesn't conform to UPPER_CASE naming style (invalid-name)util/setup.py:13:4: C0103: Constant name "cc_options" doesn't conform to UPPER_CASE naming style (invalid-name)util/setup.py:15:34: R1732: Consider using 'with' for resource-allocating operations (consider-using-with)util/setup.py:18:0: C0116: Missing function or method docstring (missing-function-docstring)util/setup.py:19:16: R1732: Consider using 'with' for resource-allocating operations (consider-using-with)util/setup.py:44:0: C0413: Import "from setuptools import setup, Extension" should be placed at the top of the module (wrong-import-position)util/setup.py:46:0: C0413: Import "from setuptools.command.build_ext import build_ext as _build_ext" should be placed at the top of the module (wrong-import-position)util/setup.py:47:0: C0413: Import "from setuptools.command.install_lib import install_lib as _install_lib" should be placed at the top of the module (wrong-import-position)util/setup.py:49:0: C0115: Missing class docstring (missing-class-docstring)util/setup.py:49:0: C0103: Class name "build_ext" doesn't conform to PascalCase naming style (invalid-name)util/setup.py:52:8: W0201: Attribute 'build_lib' defined outside __init__ (attribute-defined-outside-init)util/setup.py:53:8: W0201: Attribute 'build_temp' defined outside __init__ (attribute-defined-outside-init)util/setup.py:55:0: C0115: Missing class docstring (missing-class-docstring)util/setup.py:55:0: C0103: Class name "install_lib" doesn't conform to PascalCase naming style (invalid-name)util/setup.py:58:8: W0201: Attribute 'build_dir' defined outside __init__ (attribute-defined-outside-init)*-----------------------------------------------------------------Your code has been rated at 6.67/10 (previous run: 6.51/10, +0.16)make[4]: *** [util/Build:442: util/setup.py.pylint_log] Error 1```Reviewed-by: James Clark Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250311213628.569562-5-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

168910d0 - perf build: Add mypy build tests

Tue, 11 Mar 2025 21:36:25 +0000

perf build: Add mypy build testsIf MYPY=1 is passed to the build then run mypy over python code inperf. Unlike shellcheck this isn't default on as there are currentlytoo many errors.An example of an error:```util/setup.py:8: error: Item "None" of "str | None" has no attribute "split" [union-attr]util/setup.py:15: error: Item "None" of "IO[bytes] | None" has no attribute "readline" [union-attr]util/setup.py:15: error: List item 0 has incompatible type "str | None"; expected "str | bytes | PathLike[str] | PathLike[bytes]" [list-item]util/setup.py:16: error: Unsupported left operand type for + ("None") [operator]util/setup.py:16: note: Left operand is of type "str | None"util/setup.py:74: error: Unsupported left operand type for + ("None") [operator]util/setup.py:74: note: Left operand is of type "str | None"Found 5 errors in 1 file (checked 1 source file)make[4]: *** [util/Build:430: util/setup.py.mypy_log] Error 1```Reviewed-by: James Clark Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250311213628.569562-4-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

ef238109 - perf build: Rename TEST_LOGS to SHELL_TEST_LOGS

Tue, 11 Mar 2025 21:36:24 +0000

perf build: Rename TEST_LOGS to SHELL_TEST_LOGSRename TEST_LOGS to SHELL_TEST_LOGS as later changes will add morekinds of test logs.Minor comment tweak in Makefile.perf as more than just test shelltests are checked.Reviewed-by: James Clark Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250311213628.569562-3-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

dc6d2bc2 - perf sample: Make user_regs and intr_regs optional

Mon, 13 Jan 2025 19:43:45 +0000

perf sample: Make user_regs and intr_regs optionalThe struct dump_regs contains 512 bytes of cache_regs, meaning the twovalues in perf_sample contribute 1088 bytes of its total 1384 bytessize. Initializing this much memory has a cost reported by TavianBarnes as about 2.5% when running `perfscript --itrace=i0`:https://lore.kernel.org/lkml/d841b97b3ad2ca8bcab07e4293375fb7c32dfce7.1736618095.git.tavianator@tavianator.com/Adrian Hunter replied that the zeroinitialization was necessary and couldn't simply be removed.This patch aims to strike a middle ground of still zeroing theperf_sample, but removing 79% of its size by make user_regs andintr_regs optional pointers to zalloc-ed memory. To support theallocation accessors are created for user_regs and intr_regs. Tosupport correct cleanup perf_sample__init and perf_sample__exitfunctions are created and added throughout the code base.Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250113194345.1537821-1-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

1a12ed09 - perf lock: Move common lock contention code to new file

Tue, 19 Nov 2024 01:16:37 +0000

perf lock: Move common lock contention code to new fileAvoid references from util code to builtin-lock that require pythonstubs. Move the functions and related variables toutil/lock-contention.c. Add max_stack_depth parameter tomatch_callstack_filter to avoid sharing a global variable.Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Acked-by: Arnaldo Carvalho de Melo Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Colin Ian King Cc: Dapeng Mi Cc: Howard Chu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Kan Liang Cc: Mark Rutland Cc: Michael Petlan Cc: Peter Zijlstra Cc: Thomas Richter Cc: Veronika Molnarova Cc: Weilin Wang Link: https://lore.kernel.org/r/20241119011644.971342-16-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

e7bb49e3 - perf x86: Define arch_fetch_insn in NO_AUXTRACE builds

Tue, 19 Nov 2024 01:16:34 +0000

perf x86: Define arch_fetch_insn in NO_AUXTRACE buildsarchinsn.c containing arch_fetch_insn was only enabled withCONFIG_AUXTRACE, but this meant that a NO_AUXTRACE build on x86 woulduse the empty weak version of arch_fetch_insn - weak symbols are afrequent source of errors like this and are outside of the Cspecification. Change it so that archinsn.c is always built on x86 andmake the weak symbol empty version of arch_fetch_insn a strong oneguarded by ifdefs.arch_fetch_insn on x86 depends on insn_decode which is a functionincluded then built into intel-pt-insn-decoder.c.intel-pt-insn-decoder.c isn't built in a NO_AUXTRACE=1 build. Separatethe insn_decode function from intel-pt-insn-decoder.c by just directlycompiling the relevant file. Guard this compilation to be for eitheralways on x86 (because of the use in arch_fetch_insn) or when auxtraceis enabled. Apply the CFLAGS overrides as necessary, reducing the amountof code where warnings are disabled.Signed-off-by: Ian Rogers Tested-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Colin Ian King Cc: Dapeng Mi Cc: Howard Chu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Kan Liang Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Cc: Veronika Molnarova Cc: Weilin Wang Link: https://lore.kernel.org/r/20241119011644.971342-13-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

3f188942 - perf kvm: Move functions used in util out of builtin

Tue, 19 Nov 2024 01:16:27 +0000

perf kvm: Move functions used in util out of builtinThe util library code is used by the python module but doesn't haveaccess to the builtin files. Make a util/kvm-stat.c to match thekvm-stat.h file that declares the functions and move the functionsthere.Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Acked-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Colin Ian King Cc: Dapeng Mi Cc: Howard Chu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Kan Liang Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Cc: Veronika Molnarova Cc: Weilin Wang Link: https://lore.kernel.org/r/20241119011644.971342-6-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

800c93ff - perf trace-event: Always build trace-event-info.c

Mon, 18 Nov 2024 22:53:42 +0000

perf trace-event: Always build trace-event-info.ctrace-event-info.c has no libtraceevent dependencies, always build itand use it in builtin-record and perf_event_attr printing.Reviewed-by: Namhyung Kim Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Ben Gainey Cc: Colin Ian King Cc: Dominique Martinet Cc: Ilkka Koskinen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Oliver Upton Cc: Paran Lee Cc: Peter Zijlstra Cc: Steinar H. Gunderson Cc: Steven Rostedt (VMware) Cc: Thomas Falcon Cc: Weilin Wang Cc: Yang Jihong Cc: Yang Li Cc: Ze Gao Cc: Zixian Cai Cc: zhaimingbing Link: https://lore.kernel.org/r/20241118225345.889810-5-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

dcf90042 - perf btf: Make the sigtrap test helper to find a member by name widely available

Mon, 09 Dec 2024 19:00:39 +0000

perf btf: Make the sigtrap test helper to find a member by name widely availableBy introducing a tools/perf/util/btf.c to collect utilities not yetavailable via libbpf, the first being a way to find a member by nameonce we get the type_id for the struct.Cc: Adrian Hunter Cc: Ian Rogers Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

285b523c - perf dwarf-regs: Move powerpc dwarf-regs out of arch

Fri, 08 Nov 2024 23:45:58 +0000

perf dwarf-regs: Move powerpc dwarf-regs out of archMove arch/powerpc/util/dwarf-regs.c to util/dwarf-regs-powerpc.c andcompile in unconditionally. get_arch_regstr is redundant when EM_NONEis treated as EM_HOST so remove and update dwarf-regs.c conditions.Make get_powerpc_regs unconditionally available whwn libdw is.Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Ian Rogers Cc: Anup Patel Cc: Yang Jihong Cc: Palmer Dabbelt Cc: David S. Miller Cc: Albert Ou Cc: Shenlin Liang Cc: Nick Terrell Cc: Guilherme Amadio Cc: Steinar H. Gunderson Cc: Changbin Du Cc: Alexander Lobakin Cc: Przemek Kitszel Cc: Huacai Chen Cc: Guo Ren Cc: Masahiro Yamada Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Chen Pei Cc: Leo Yan Cc: Oliver Upton Cc: Aditya Gupta Cc: Kajol Jain Cc: Athira Rajeev Cc: linux-arm-kernel@lists.infradead.orgCc: linux-riscv@lists.infradead.orgCc: Bibo Mao Cc: John Garry Cc: Atish Patra Cc: Dima Kogan Cc: Paul Walmsley Cc: Dr. David Alan Gilbert Cc: linux-csky@vger.kernel.orgLink: https://lore.kernel.org/r/20241108234606.429459-14-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

d4a0c4f2 - perf dwarf-regs: Move csky dwarf-regs out of arch

Fri, 08 Nov 2024 23:45:55 +0000

perf dwarf-regs: Move csky dwarf-regs out of archMove arch/csky/util/dwarf-regs.c to util/dwarf-regs-csky.c and compilein unconditionally. To avoid get_arch_regstr being duplicated, renameto get_csky_regstr and add to get_dwarf_regstr switch.Update #ifdefs to allow ABI V1 and V2 tables at the sametime. Determine the table from the ELF flags.Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Ian Rogers Cc: Anup Patel Cc: Yang Jihong Cc: Palmer Dabbelt Cc: David S. Miller Cc: Albert Ou Cc: Shenlin Liang Cc: Nick Terrell Cc: Guilherme Amadio Cc: Steinar H. Gunderson Cc: Changbin Du Cc: Alexander Lobakin Cc: Przemek Kitszel Cc: Huacai Chen Cc: Guo Ren Cc: Masahiro Yamada Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Chen Pei Cc: Leo Yan Cc: Oliver Upton Cc: Aditya Gupta Cc: Kajol Jain Cc: Athira Rajeev Cc: linux-arm-kernel@lists.infradead.orgCc: linux-riscv@lists.infradead.orgCc: Bibo Mao Cc: John Garry Cc: Atish Patra Cc: Dima Kogan Cc: Paul Walmsley Cc: Dr. David Alan Gilbert Cc: linux-csky@vger.kernel.orgLink: https://lore.kernel.org/r/20241108234606.429459-11-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

bf4e799a - perf dwarf-regs: Move x86 dwarf-regs out of arch

Fri, 08 Nov 2024 23:45:52 +0000

perf dwarf-regs: Move x86 dwarf-regs out of archMove arch/x86/util/dwarf-regs.c to util/dwarf-regs-x86.c and compilein unconditionally. To avoid get_arch_regnum being duplicated, renameto get_x86_regnum and add to get_dwarf_regnum switch.For get_arch_regstr, this was unused on x86 unless the machine typewas EM_NONE. Map that case to EM_HOST and remove get_arch_regstr fromdwarf-regs-x86.c.Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Ian Rogers Cc: Anup Patel Cc: Yang Jihong Cc: Palmer Dabbelt Cc: David S. Miller Cc: Albert Ou Cc: Shenlin Liang Cc: Nick Terrell Cc: Guilherme Amadio Cc: Steinar H. Gunderson Cc: Changbin Du Cc: Alexander Lobakin Cc: Przemek Kitszel Cc: Huacai Chen Cc: Guo Ren Cc: Masahiro Yamada Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Chen Pei Cc: Leo Yan Cc: Oliver Upton Cc: Aditya Gupta Cc: Kajol Jain Cc: Athira Rajeev Cc: linux-arm-kernel@lists.infradead.orgCc: linux-riscv@lists.infradead.orgCc: Bibo Mao Cc: John Garry Cc: Atish Patra Cc: Dima Kogan Cc: Paul Walmsley Cc: Dr. David Alan Gilbert Cc: linux-csky@vger.kernel.orgLink: https://lore.kernel.org/r/20241108234606.429459-8-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

4810b761 - perf hwmon_pmu: Add hwmon filename parser

Sat, 09 Nov 2024 00:37:54 +0000

perf hwmon_pmu: Add hwmon filename parserhwmon filenames have a specific encoding that will be used to give aconfig value. The encoding is described in:Documentation/hwmon/sysfs-interface.rstAdd a function to parse the filename into consituent enums/ints thatwill then be amenable to config encoding.Note, things are done this way to allow mapping names to config andback without the use of hash/dynamic lookup tables.Signed-off-by: Ian Rogers Cc: Ravi Bangoria Cc: Yoshihiro Furudera Cc: Howard Chu Cc: Ze Gao Cc: Changbin Du Cc: Junhao He Cc: Weilin Wang Cc: James Clark Cc: Oliver Upton Cc: Athira Jajeev [namhyung: add #include for strlcpy()]Link: https://lore.kernel.org/r/20241109003759.473460-3-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

5455d89b - perf build: Rename CONFIG_DWARF to CONFIG_LIBDW

Thu, 17 Oct 2024 00:13:54 +0000

perf build: Rename CONFIG_DWARF to CONFIG_LIBDWIn Makefile.config for unwinding the name dwarf implies eitherlibunwind or libdw. Make it clearer that CONFIG_DWARF is really justdefined when libdw is present by renaming to CONFIG_LIBDW.Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Tested-by: Leo Yan Cc: Anup Patel Cc: Yang Jihong Cc: Palmer Dabbelt Cc: David S. Miller Cc: Albert Ou Cc: Shenlin Liang Cc: Nick Terrell Cc: Guilherme Amadio Cc: Steinar H. Gunderson Cc: Changbin Du Cc: Alexander Lobakin Cc: Przemek Kitszel Cc: Huacai Chen Cc: Guo Ren Cc: Masahiro Yamada Cc: Masami Hiramatsu (Google) Cc: Will Deacon Cc: James Clark Cc: Mike Leach Cc: Chen Pei Cc: Leo Yan Cc: Oliver Upton Cc: Aditya Gupta Cc: Kajol Jain Cc: Athira Rajeev Cc: linux-arm-kernel@lists.infradead.orgCc: linux-riscv@lists.infradead.orgCc: Bibo Mao Cc: John Garry Cc: Atish Patra Cc: Dima Kogan Cc: Paul Walmsley Cc: Dr. David Alan Gilbert Cc: linux-csky@vger.kernel.orgLink: https://lore.kernel.org/r/20241017001354.56973-12-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

240505b2 - perf tool_pmu: Factor tool events into their own PMU

Wed, 02 Oct 2024 03:20:07 +0000

perf tool_pmu: Factor tool events into their own PMURather than treat tool events as a special kind of event, create atool only PMU where the events/aliases match the existingduration_time, user_time and system_time events. Remove specialparsing and printing support for the tool events, but add functioncalls for when PMU functions are called on a tool_pmu.Move the tool PMU code in evsel into tool_pmu.c to better encapsulatethe tool event behavior in that file.Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Link: https://lore.kernel.org/r/20241002032016.333748-5-irogers@google.comSigned-off-by: Namhyung Kim List of files: /linux-6.15/tools/perf/util/Build

c3f8644c - perf report: Support LLVM for addr2line()

Sat, 03 Aug 2024 15:20:06 +0000

perf report: Support LLVM for addr2line()In addition to the existing support for libbfd and calling out toan external addr2line command, add support for using libllvm directly.This is both faster than libbfd, and can be enabled in distro builds(the LLVM license has an explicit provision for GPLv2 compatibility).Thus, it is set as the primary choice if available.As an example, running 'perf report' on a medium-size profile withDWARF-based backtraces took 58 seconds with LLVM, 78 seconds withlibbfd, 153 seconds with external llvm-addr2line, and I got tired andaborted the test after waiting for 55 minutes with external bfdaddr2line (which is the default for perf as compiled by distributionstoday).Evidently, for this case, the bfd addr2line process needs 18 seconds (ona 5.2 GHz Zen 3) to load the .debug ELF in question, hits the 1-secondtimeout and gets killed during initialization, getting restarted anewevery time. Having an in-process addr2line makes this much more robust.As future extensions, libllvm can be used in many other places wherewe currently use libbfd or other libraries: - Symbol enumeration (in particular, for PE binaries). - Demangling (including non-Itanium demangling, e.g. Microsoft or Rust). - Disassembling (perf annotate).However, these are much less pressing; most people don't profile PEbinaries, and perf has non-bfd paths for ELF. The same with demangling;the default _cxa_demangle path works fine for most users, and while bfdobjdump can be slow on large binaries, it is possible to use--objdump=llvm-objdump to get the speed benefits. (It appearsLLVM-based demangling is very simple, should we want that.)Tested with LLVM 14, 15, 16, 18 and 19. For some reason, LLVM 12 was notcorrectly detected using feature_check, and thus was not tested.Committer notes: Added the name and a __maybe_unused to address: 1 13.50 almalinux:8 : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-22) (GCC) util/srcline.c: In function 'dso__free_a2l': util/srcline.c:184:20: error: parameter name omitted void dso__free_a2l(struct dso *) ^~~~~~~~~~~~ make[3]: *** [/git/perf-6.11.0-rc3/tools/build/Makefile.build:158: util] Error 2Signed-off-by: Steinar H. Gunderson Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Link: https://lore.kernel.org/r/20240803152008.2818485-1-sesse@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

591156f2 - perf bpf-filter: Add build dependency to header files

Mon, 26 Aug 2024 22:10:43 +0000

perf bpf-filter: Add build dependency to header filesThe flex and bison files need to be recompiled when one of these headerfilters are changed. * util/bpf-filter.h * util/bpf_skel/sample-filter.hSigned-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/r/20240826221045.1202305-3-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

e25ebda7 - perf cap: Tidy up and improve capability testing

Tue, 06 Aug 2024 22:06:14 +0000

perf cap: Tidy up and improve capability testingRemove dependence on libcap. libcap is only used to query whether acapability is supported, which is just 1 capget system call.If the capget system call fails, fall back on root permissionchecking. Previously if libcap fails then the permission is assumednot present which may be pessimistic/wrong.Add a used_root out argument to perf_cap__capable to say whether thefall back root check was used. This allows the correct error message,"root" vs "users with the CAP_PERFMON or CAP_SYS_ADMIN capability", tobe selected.Tidy uses of perf_cap__capable so that tests aren't repeated if capgetisn't supported.Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Changbin Du Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Oliver Upton Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240806220614.831914-1-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

8db5cabc - perf stat: Fork and launch 'perf record' when 'perf stat' needs to get retire latency value for a metric.

Sat, 20 Jul 2024 06:20:56 +0000

perf stat: Fork and launch 'perf record' when 'perf stat' needs to get retire latency value for a metric.When retire_latency value is used in a metric formula, evsel would forka 'perf record' process with "-e" and "-W" options. 'perf record' willcollect required retire_latency values in parallel while 'perf stat' iscollecting counting values.At the point of time that 'perf stat' stops counting, evsel would stop'perf record' by sending sigterm signal to 'perf record' process.Sampled data will be processed to get retire latency value. Anotherthread is required to synchronize between 'perf stat' and 'perf record'when we pass data through pipe.Retire_latency evsel is not opened for 'perf stat' so that there is nocounter wasted on it. This commit includes code suggested by Namhyung toadjust reading size for groups that include retire_latency evsels.In current :R parsing implementation, the parser would recognize eventswith retire_latency modifier and insert them into the evlist like anormal event. Ideally, we need to avoid counting these events.In this commit, at the time when a retire_latency evsel is read, set theretire latency value processed from the sampled data to count value.This sampled retire latency value will be used for metric calculationand final event count print out. No special metric calculation and eventprint out code required for retire_latency events.Reviewed-by: Namhyung Kim Signed-off-by: Weilin Wang Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Link: https://lore.kernel.org/r/20240720062102.444578-4-weilin.wang@intel.com[ Squashed the 3rd and 4th commit in the series to keep it building patch by patch ][ Constified the 'struct perf_tool' pointer in process_sample_event() ][ Use perf_tool__init(&tool, false) to address a segfault I reported and Ian/Weilin diagnosed ]Signed-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build

564e5cbc - perf tool: Move fill defaults into tool.c

Mon, 12 Aug 2024 20:46:56 +0000

perf tool: Move fill defaults into tool.cThe aim here is to eventually make perf_tool__fill_defaults() an initfunction so that the tools struct is more const.Create a tool.c to go along with tool.h. Move perf_tool__fill_defaults()out of session.c into tool.c along with the default stub values. Addperf_tool__compressed_is_stub() for a test inperf_session__process_user_event().perf_session__process_compressed_event() is only used from being defaultinitialized so migrate into tool.c.Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Athira Rajeev Cc: Huacai Chen Cc: Ilkka Koskinen Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Jonathan Cameron Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Nick Terrell Cc: Oliver Upton Cc: Peter Zijlstra Cc: Song Liu Cc: Sun Haiyong Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yanteng Si Cc: Yicong Yang Cc: linux-arm-kernel@lists.infradead.orgLink: https://lore.kernel.org/r/20240812204720.631678-5-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo List of files: /linux-6.15/tools/perf/util/Build