kernel/linux.git/tools/perf/util/Build, branch v6.6.131

perf parse-regs: Refactor arch register parsing functions

2023-08-16T11:37:52+00:00

Every architecture has a specific register parsing function for returning register name based on register index, to support cross analysis (e.g. we use perf x86 binary to parse Arm64's perf data), we build all these register parsing functions into the tool, this is why we place all related functions into util/perf_regs.c. Unfortunately, since util/perf_regs.c needs to include every arch's perf_regs.h, this easily introduces duplicated definitions coming from multiple headers, finally it's fragile for building and difficult for maintenance. We cannot simply move these register parsing functions into the corresponding 'arch' folder, the folder is only conditionally built based on the target architecture. Therefore, this commit creates a new folder util/perf-regs-arch/ and uses a dedicated source file to keep every architecture's register parsing function to avoid definition conflicts. This is only a refactoring, no functionality change is expected. Committer notes: Had to add util/perf-regs-arch/*.c to tools/perf/util/python-ext-sources to keep 'perf test python' passing. Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Eric Lin Cc: Fangrui Song Cc: Guo Ren Cc: Huacai Chen Cc: Ingo Molnar Cc: Ivan Babrou Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Mark Rutland Cc: Mike Leach Cc: Ming Wang Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Sandipan Das Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-csky@vger.kernel.org Cc: linux-riscv@lists.infradead.org Link: https://lore.kernel.org/r/20230606014559.21783-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo

perf parse-events: Remove BPF event support

2023-08-15T19:41:48+00:00

New features like the BPF --filter support in perf record have made the BPF event functionality somewhat redundant. As shown by commit fcb027c1a4f6 ("perf tools: Revert enable indices setting syntax for BPF map") and commit 14e4b9f4289a ("perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility") the BPF event support hasn't been well maintained and it adds considerable complexity in areas like event parsing, not least as '/' is a separator for event modifiers as well as in paths. This patch removes support in the event parser for BPF events and then the associated functions are removed. This leads to the removal of whole source files like bpf-loader.c. Removing support means that augmented syscalls in perf trace is broken, this will be fixed in a later commit adding support using BPF skeletons. The removal of BPF events causes an unused label warning from flex generated code, so update build to ignore it: ``` util/parse-events-flex.c:2704:1: error: label ‘find_rule’ defined but not used [-Werror=unused-label] 2704 | find_rule: /* we branch to this label when backing up */ ``` Committer notes: Extracted from a larger patch that was also removing the support for linking with libllvm and libclang, that were an alternative to using an external clang execution to compile the .c event source code into BPF bytecode. Testing it: # perf trace -e /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c' \___ Bad event or PMU Unabled to find PMU or event on a PMU of 'home' Initial error: event syntax error: '/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c' \___ Cannot find PMU `home'. Missing kernel support? Run 'perf list' for a list of valid events Usage: perf trace [] [] or: perf trace [] -- [] or: perf trace record [] [] or: perf trace record [] -- [] -e, --event event/syscall selector. use 'perf list' to list available events # Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andrii Nakryiko Cc: Anshuman Khandual Cc: Athira Rajeev Cc: Brendan Gregg Cc: Carsten Haitzler Cc: Eduard Zingerman Cc: Fangrui Song Cc: He Kuang Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Naveen N. Rao Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Tiezhu Yang Cc: Tom Rix Cc: Wang Nan Cc: Wang ShaoBo Cc: Yang Jihong Cc: Yonghong Song Cc: YueHaibing Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230810184853.2860737-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Arnaldo Carvalho de Melo

perf bpf: Remove support for embedding clang for compiling BPF events (-e foo.c)

2023-08-15T19:41:48+00:00

This never was in the default build for perf, is difficult to maintain as it uses clang/llvm internals so ditch it, keeping, for now, the external compilation of .c BPF into .o bytecode and its subsequent loading, that is also going to be removed, do it separately to help bisection and to properly document what is being removed and why. Committer notes: Extracted from a larger patch and removed some leftovers, namely deleting these now unused feature tests: tools/build/feature/test-clang.cpp tools/build/feature/test-cxx.cpp tools/build/feature/test-llvm-version.cpp tools/build/feature/test-llvm.cpp Testing the use of BPF events after applying this patch: To use the external clang/llvm toolchain to compile a .c event and then use libbpf to load it, to get the syscalls:sys_enter_open* tracepoints and read the filename pointer, putting it into the ring buffer right after the usual tracepoint payload for 'perf trace' to then print it: [root@quaco ~]# perf trace -e /home/acme/git/perf-tools-next/tools/perf/examples/bpf/augmented_raw_syscalls.c,open* --max-events=10 0.000 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12 0.083 abrt-dump-jour/1453 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 0.063 abrt-dump-jour/1454 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 0.082 abrt-dump-jour/1455 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 250.124 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12 250.521 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.pressure", flags: RDONLY|CLOEXEC) = 12 251.047 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.current", flags: RDONLY|CLOEXEC) = 12 251.162 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.min", flags: RDONLY|CLOEXEC) = 12 251.242 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.low", flags: RDONLY|CLOEXEC) = 12 251.353 systemd-oomd/959 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/app.slice/memory.swap.current", flags: RDONLY|CLOEXEC) = 12 [root@quaco ~]# Same thing, but with a prebuilt .o BPF bytecode: [root@quaco ~]# perf trace -e /home/acme/git/perf-tools-next/tools/perf/examples/bpf/augmented_raw_syscalls.o,open* --max-events=10 0.000 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12 0.083 abrt-dump-jour/1453 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 0.083 abrt-dump-jour/1455 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 0.062 abrt-dump-jour/1454 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 4 249.985 systemd-oomd/959 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12 466.763 thermald/1234 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/intel-rapl:0:2/energy_uj") = 13 467.145 thermald/1234 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/energy_uj") = 13 467.311 thermald/1234 openat(dfd: CWD, filename: "/sys/class/thermal/thermal_zone2/temp") = 13 500.040 cgroupify/24006 openat(dfd: 4, filename: ".", flags: RDONLY|CLOEXEC|DIRECTORY|NONBLOCK) = 5 500.295 cgroupify/24006 openat(dfd: 4, filename: "24616/cgroup.procs") = 5 [root@quaco ~]# Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andrii Nakryiko Cc: Anshuman Khandual Cc: Athira Rajeev Cc: Brendan Gregg Cc: Carsten Haitzler Cc: Eduard Zingerman Cc: Fangrui Song Cc: He Kuang Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: "Naveen N. Rao" Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Tiezhu Yang Cc: Tom Rix Cc: Wang Nan Cc: Wang ShaoBo Cc: Yang Jihong Cc: Yonghong Song Cc: YueHaibing Link: https://lore.kernel.org/lkml/ZNZWsAXg2px1sm2h@kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf build: Remove -Wno-unused-but-set-variable from the flex flags when building with clang < 13.0.0

2023-08-11T13:27:21+00:00

clang < 13.0.0 doesn't grok -Wno-unused-but-set-variable, so just remove it to avoid: error: unknown warning option '-Wno-unused-but-set-variable'; did you mean '-Wno-unused-const-variable'? [-Werror,-Wunknown-warning-option] make[4]: *** [/git/perf-6.5.0-rc4/tools/build/Makefile.build:128: /tmp/build/perf/util/pmu-flex.o] Error 1 make[4]: *** Waiting for unfinished jobs.... Fixes: ddc8e4c966923ad1 ("perf build: Disable fewer bison warnings") Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZNUSWr52jUnVaaa%2F@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo

perf build: Remove -Wno-redundant-decls in 2 cases

2023-08-03T20:01:24+00:00

Properly fix a warning and remove the -Wno-redundant-decls C flag. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Eduard Zingerman Cc: Gaosheng Cui Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Rob Herring Cc: Tom Rix Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230728064917.767761-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf build: Disable fewer bison warnings

2023-08-03T20:01:24+00:00

If bison is version 3.8.2, reduce the number of bison C warnings disabled. Earlier bison versions have all C warnings disabled. Avoid implicit declarations of yylex by adding the declaration in the C file. A header can't be included as a circular dependency would occur due to the lexer using the bison defined tokens. Committer notes: Some recent versions of gcc and clang (noticed on Alpine Linux 3.17, edge, clearlinux, fedora 37, etc. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Eduard Zingerman Cc: Gaosheng Cui Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Rob Herring Cc: Tom Rix Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230728064917.767761-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf build: Disable fewer flex warnings

2023-08-03T20:01:24+00:00

If flex is version 2.6.4, reduce the number of flex C warnings disabled. Earlier flex versions have all C warnings disabled. Committer notes: Added this to the list of ignored warnings to get it building on a Fedora 36 machine with flex 2.6.4: -Wno-misleading-indentation Noticed when building with: $ make LLVM=1 -C tools/perf NO_BPF_SKEL=1 DEBUG=1 Take two: We can't just try to canonicalize flex versions by just removing the dots, as we end up with: 2.6.4 >= 2.5.37 becoming: 264 >= 2537 Failing the build on flex 2.5.37, so instead use the back to the past added $(call version_ge3,$(FLEX_VERSION),2.6.4) variant to check for that. Making sure $(FLEX_VERSION) keeps the dots as we may want to use 'sort -V' or something nicer when available everywhere. Some other tweaks for other flex versions and combinations with gcc and clang versions were added, notes on the patch. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Eduard Zingerman Cc: Gaosheng Cui Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Rob Herring Cc: Tom Rix Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230728064917.767761-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf parse-event: Add memory allocation test for name terms

2023-07-28T22:01:16+00:00

If the name memory allocation fails then propagate to the parser. Committer notes: Use $(BISON_FALLBACK_FLAGS) on the bison call so that we continue building with older bison versions, before 3.81, where YYNOMEM isn't present. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230627181030.95608-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf build: Define YYNOMEM as YYNOABORT for bison < 3.81

2023-07-28T22:01:14+00:00

YYNOMEM was introduced in bison 3.81, so define it as YYABORT for older versions, which should provide the previous perf behaviour. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo

perf sharded_mutex: Introduce sharded_mutex

2023-06-21T00:03:43+00:00

Per object mutexes may come with significant memory cost while a global mutex can suffer from unnecessary contention. A sharded mutex is a compromise where objects are hashed and then a particular mutex for the hash of the object used. Contention can be controlled by the number of shards. v2. Use hashmap.h's hash_bits in case of contention from alignment of objects. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Andres Freund Cc: Mark Rutland Cc: Yuan Can Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Huacai Chen Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Alexander Shishkin Cc: Kan Liang Cc: Ingo Molnar Link: https://lore.kernel.org/r/20230615040715.2064350-1-irogers@google.com Signed-off-by: Namhyung Kim