2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 12:14:01 +08:00
linux-next/tools/perf/util/Build

185 lines
5.6 KiB
Plaintext
Raw Normal View History

libperf-y += alias.o
libperf-y += annotate.o
libperf-y += build-id.o
libperf-y += config.o
libperf-y += ctype.o
libperf-y += db-export.o
libperf-y += env.o
libperf-y += event.o
libperf-y += evlist.o
libperf-y += evsel.o
libperf-y += evsel_fprintf.o
libperf-y += find_bit.o
libperf-y += kallsyms.o
libperf-y += levenshtein.o
perf tools: Introduce llvm config options This patch introduces [llvm] config section with 5 options. Following patches will use then to config llvm dynamica compiling. 'llvm-utils.[ch]' is introduced in this patch for holding all llvm/clang related stuffs. Example: [llvm] # Path to clang. If omit, search it from $PATH. clang-path = "/path/to/clang" # Cmdline template. Following line shows its default value. # Environment variable is used to passing options. # # *NOTE*: -D__KERNEL__ MUST appears before $CLANG_OPTIONS, # so user have a chance to use -U__KERNEL__ in $CLANG_OPTIONS # to cancel it. clang-bpf-cmd-template = "$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS \ $KERNEL_INC_OPTIONS -Wno-unused-value \ -Wno-pointer-sign -working-directory \ $WORKING_DIR -c $CLANG_SOURCE -target \ bpf -O2 -o -" # Options passed to clang, will be passed to cmdline by # $CLANG_OPTIONS. clang-opt = "-Wno-unused-value -Wno-pointer-sign" # kbuild directory. If not set, use /lib/modules/`uname -r`/build. # If set to "" deliberately, skip kernel header auto-detector. kbuild-dir = "/path/to/kernel/build" # Options passed to 'make' when detecting kernel header options. kbuild-opts = "ARCH=x86_64" Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1437477214-149684-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-21 19:13:34 +08:00
libperf-y += llvm-utils.o
libperf-y += parse-events.o
libperf-y += perf_regs.o
libperf-y += path.o
libperf-y += rbtree.o
libperf-y += libstring.o
libperf-y += bitmap.o
libperf-y += hweight.o
libperf-y += quote.o
libperf-y += strbuf.o
libperf-y += string.o
libperf-y += strlist.o
libperf-y += strfilter.o
libperf-y += top.o
libperf-y += usage.o
libperf-y += dso.o
libperf-y += symbol.o
libperf-y += symbol_fprintf.o
libperf-y += color.o
libperf-y += header.o
libperf-y += callchain.o
libperf-y += values.o
libperf-y += debug.o
libperf-y += machine.o
libperf-y += map.o
libperf-y += pstack.o
libperf-y += session.o
libperf-$(CONFIG_AUDIT) += syscalltbl.o
libperf-y += ordered-events.o
libperf-y += comm.o
libperf-y += thread.o
libperf-y += thread_map.o
libperf-y += trace-event-parse.o
libperf-y += parse-events-flex.o
libperf-y += parse-events-bison.o
libperf-y += pmu.o
libperf-y += pmu-flex.o
libperf-y += pmu-bison.o
libperf-y += trace-event-read.o
libperf-y += trace-event-info.o
libperf-y += trace-event-scripting.o
libperf-y += trace-event.o
libperf-y += svghelper.o
libperf-y += sort.o
libperf-y += hist.o
libperf-y += util.o
libperf-y += xyarray.o
libperf-y += cpumap.o
libperf-y += cgroup.o
libperf-y += target.o
libperf-y += rblist.o
libperf-y += intlist.o
libperf-y += vdso.o
libperf-y += counts.o
libperf-y += stat.o
libperf-y += stat-shadow.o
libperf-y += record.o
libperf-y += srcline.o
libperf-y += data.o
libperf-y += tsc.o
libperf-y += cloexec.o
libperf-y += call-path.o
libperf-y += thread-stack.o
libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
libperf-$(CONFIG_AUXTRACE) += intel-pt.o
perf tools: Add Intel BTS support Intel BTS support fits within the new auxtrace infrastructure. Recording is supporting by identifying the Intel BTS PMU, parsing options and setting up events. Decoding is supported by queuing up trace data by thread and then decoding synchronously delivering synthesized event samples into the session processing for tools to consume. Committer note: E.g: [root@felicio ~]# perf record --per-thread -e intel_bts// ls anaconda-ks.cfg apctest.output bin kernel-rt-3.10.0-298.rt56.171.el7.x86_64.rpm libexec lock_page.bpf.c perf.data perf.data.old [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 4.367 MB perf.data ] [root@felicio ~]# perf evlist -v intel_bts//: type: 6, size: 112, { sample_period, sample_freq }: 1, sample_type: IP|TID|IDENTIFIER, read_format: ID, disabled: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1 dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|IDENTIFIER, read_format: ID, disabled: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1 [root@felicio ~]# perf script # the navigate in the pager to some interesting place: ls 1843 1 branches: ffffffff810a60cb flush_signal_handlers ([kernel.kallsyms]) => ffffffff8121a522 setup_new_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8121a529 setup_new_exec ([kernel.kallsyms]) => ffffffff8122fa30 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa5d do_close_on_exec ([kernel.kallsyms]) => ffffffff81767ae0 _raw_spin_lock ([kernel.kallsyms]) ls 1843 1 branches: ffffffff81767af4 _raw_spin_lock ([kernel.kallsyms]) => ffffffff8122fa62 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fac9 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fad2 do_close_on_exec ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8122fadd do_close_on_exec ([kernel.kallsyms]) => ffffffff8120fc80 filp_close ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8120fcaf filp_close ([kernel.kallsyms]) => ffffffff8120fcb6 filp_close ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8120fcc2 filp_close ([kernel.kallsyms]) => ffffffff812547f0 dnotify_flush ([kernel.kallsyms]) ls 1843 1 branches: ffffffff81254823 dnotify_flush ([kernel.kallsyms]) => ffffffff8120fcc7 filp_close ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8120fccd filp_close ([kernel.kallsyms]) => ffffffff81261790 locks_remove_posix ([kernel.kallsyms]) ls 1843 1 branches: ffffffff812617a3 locks_remove_posix ([kernel.kallsyms]) => ffffffff812617b9 locks_remove_posix ([kernel.kallsyms]) ls 1843 1 branches: ffffffff812617b9 locks_remove_posix ([kernel.kallsyms]) => ffffffff8120fcd2 filp_close ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8120fcd5 filp_close ([kernel.kallsyms]) => ffffffff812142c0 fput ([kernel.kallsyms]) ls 1843 1 branches: ffffffff812142d6 fput ([kernel.kallsyms]) => ffffffff812142df fput ([kernel.kallsyms]) ls 1843 1 branches: ffffffff8121430c fput ([kernel.kallsyms]) => ffffffff810b6580 task_work_add ([kernel.kallsyms]) ls 1843 1 branches: ffffffff810b65ad task_work_add ([kernel.kallsyms]) => ffffffff810b65b1 task_work_add ([kernel.kallsyms]) ls 1843 1 branches: ffffffff810b65c1 task_work_add ([kernel.kallsyms]) => ffffffff810bc710 kick_process ([kernel.kallsyms]) ls 1843 1 branches: ffffffff810bc725 kick_process ([kernel.kallsyms]) => ffffffff810bc742 kick_process ([kernel.kallsyms]) ls 1843 1 branches: ffffffff810bc742 kick_process ([kernel.kallsyms]) => ffffffff810b65c6 task_work_add ([kernel.kallsyms]) ls 1843 1 branches: ffffffff810b65c9 task_work_add ([kernel.kallsyms]) => ffffffff81214311 fput ([kernel.kallsyms]) Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1437150840-31811-9-git-send-email-adrian.hunter@intel.com [ Merged sample->time fix for bug found after first round of testing on slightly older kernel ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-18 00:33:43 +08:00
libperf-$(CONFIG_AUXTRACE) += intel-bts.o
libperf-y += parse-branch-options.o
perf record: Add ability to name registers to record This patch modifies the -I/--int-regs option to enablepassing the name of the registers to sample on interrupt. Registers can be specified by their symbolic names. For instance on x86, --intr-regs=ax,si. The motivation is to reduce the size of the perf.data file and the overhead of sampling by only collecting the registers useful to a specific analysis. For instance, for value profiling, sampling only the registers used to passed arguements to functions. With no parameter, the --intr-regs still records all possible registers based on the architecture. To name registers, it is necessary to use the long form of the option, i.e., --intr-regs: $ perf record --intr-regs=si,di,r8,r9 ..... To record any possible registers: $ perf record -I ..... $ perf report --intr-regs ... To display the register, one can use perf report -D To list the available registers: $ perf record --intr-regs=\? available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15 Signed-off-by: Stephane Eranian <eranian@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1441039273-16260-4-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-09-01 00:41:12 +08:00
libperf-y += parse-regs-options.o
libperf-y += term.o
libperf-y += help-unknown-cmd.o
libperf-y += mem-events.o
libperf-y += vsprintf.o
perf tools: Enable passing bpf object file to --event By introducing new rules in tools/perf/util/parse-events.[ly], this patch enables 'perf record --event bpf_file.o' to select events by an eBPF object file. It calls parse_events_load_bpf() to load that file, which uses bpf__prepare_load() and finally calls bpf_object__open() for the object files. After applying this patch, commands like: # perf record --event foo.o sleep become possible. However, at this point it is unable to link any useful things onto the evsel list because the creating of probe points and BPF program attaching have not been implemented. Before real events are possible to be extracted, to avoid perf report error because of empty evsel list, this patch link a dummy evsel. The dummy event related code will be removed when probing and extracting code is ready. Commiter notes: Using it: $ ls -la foo.o ls: cannot access foo.o: No such file or directory $ perf record --event foo.o sleep libbpf: failed to open foo.o: No such file or directory event syntax error: 'foo.o' \___ BPF object file 'foo.o' is invalid (add -v to see detail) Run 'perf list' for a list of valid events Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -e, --event <event> event selector. use 'perf list' to list available events $ $ file /tmp/build/perf/perf.o /tmp/build/perf/perf.o: ELF 64-bit LSB relocatable, x86-64, version 1 (SYSV), not stripped $ perf record --event /tmp/build/perf/perf.o sleep libbpf: /tmp/build/perf/perf.o is not an eBPF object file event syntax error: '/tmp/build/perf/perf.o' \___ BPF object file '/tmp/build/perf/perf.o' is invalid (add -v to see detail) Run 'perf list' for a list of valid events Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -e, --event <event> event selector. use 'perf list' to list available events $ $ file /tmp/foo.o /tmp/foo.o: ELF 64-bit LSB relocatable, no machine, version 1 (SYSV), not stripped $ perf record --event /tmp/foo.o sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.013 MB perf.data ] $ perf evlist /tmp/foo.o $ perf evlist -v /tmp/foo.o: type: 1, size: 112, config: 0x9, { 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, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ So, type 1 is PERF_TYPE_SOFTWARE, config 0x9 is PERF_COUNT_SW_DUMMY, ok. $ perf report --stdio Error: The perf.data file has no samples! # To display the perf.data header info, please use --header/--header-only options. # $ Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-4-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 20:41:14 +08:00
libperf-$(CONFIG_LIBBPF) += bpf-loader.o
perf bpf: Add prologue for BPF programs for fetching arguments This patch generates a prologue for a BPF program which fetches arguments for it. With this patch, the program can have arguments as follow: SEC("lock_page=__lock_page page->flags") int lock_page(struct pt_regs *ctx, int err, unsigned long flags) { return 1; } This patch passes at most 3 arguments from r3, r4 and r5. r1 is still the ctx pointer. r2 is used to indicate if dereferencing was done successfully. This patch uses r6 to hold ctx (struct pt_regs) and r7 to hold stack pointer for result. Result of each arguments first store on stack: low address BPF_REG_FP - 24 ARG3 BPF_REG_FP - 16 ARG2 BPF_REG_FP - 8 ARG1 BPF_REG_FP high address Then loaded into r3, r4 and r5. The output prologue for offn(...off2(off1(reg)))) should be: r6 <- r1 // save ctx into a callee saved register r7 <- fp r7 <- r7 - stack_offset // pointer to result slot /* load r3 with the offset in pt_regs of 'reg' */ (r7) <- r3 // make slot valid r3 <- r3 + off1 // prepare to read unsafe pointer r2 <- 8 r1 <- r7 // result put onto stack call probe_read // read unsafe pointer jnei r0, 0, err // error checking r3 <- (r7) // read result r3 <- r3 + off2 // prepare to read unsafe pointer r2 <- 8 r1 <- r7 call probe_read jnei r0, 0, err ... /* load r2, r3, r4 from stack */ goto success err: r2 <- 1 /* load r3, r4, r5 with 0 */ goto usercode success: r2 <- 0 usercode: r1 <- r6 // restore ctx // original user code If all of arguments reside in register (dereferencing is not required), gen_prologue_fastpath() will be used to create fast prologue: r3 <- (r1 + offset of reg1) r4 <- (r1 + offset of reg2) r5 <- (r1 + offset of reg3) r2 <- 0 P.S. eBPF calling convention is defined as: * r0 - return value from in-kernel function, and exit value for eBPF program * r1 - r5 - arguments from eBPF program to in-kernel function * r6 - r9 - callee saved registers that in-kernel function will preserve * r10 - read-only frame pointer to access stack Committer note: At least testing if it builds and loads: # cat test_probe_arg.c struct pt_regs; __attribute__((section("lock_page=__lock_page page->flags"), used)) int func(struct pt_regs *ctx, int err, unsigned long flags) { return 1; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; # perf record -e ./test_probe_arg.c usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data ] # perf evlist perf_bpf_probe:lock_page # Signed-off-by: He Kuang <hekuang@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-11-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-16 20:10:12 +08:00
libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-file.o
libperf-$(CONFIG_LIBELF) += probe-event.o
ifndef CONFIG_LIBELF
libperf-y += symbol-minimal.o
endif
libperf-$(CONFIG_DWARF) += probe-finder.o
libperf-$(CONFIG_DWARF) += dwarf-aux.o
libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o
libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
libperf-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o
libperf-$(CONFIG_LIBUNWIND_AARCH64) += libunwind/arm64.o
perf data: Add perf data to CTF conversion support Adding 'perf data convert' to convert perf data file into different format. This patch adds support for CTF format conversion. To convert perf.data into CTF run: $ perf data convert --to-ctf=./ctf-data/ [ perf data convert: Converted 'perf.data' into CTF data './ctf-data/' ] [ perf data convert: Converted and wrote 11.268 MB (100230 samples) ] The command will create CTF metadata out of perf.data file (or one specified via -i option) and then convert all sample events into single CTF stream. Each sample_type bit is translated into separated CTF event field apart from following exceptions: PERF_SAMPLE_RAW - added in next patch PERF_SAMPLE_READ - TODO PERF_SAMPLE_CALLCHAIN - TODO PERF_SAMPLE_BRANCH_STACK - TODO PERF_SAMPLE_REGS_USER - TODO PERF_SAMPLE_STACK_USER - TODO $ perf --debug=data-convert=2 data convert ... The converted CTF data could be analyzed by CTF tools, like babletrace or tracecompass [1]. $ babeltrace ./ctf-data/ [03:19:13.962125533] (+?.?????????) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 1 } [03:19:13.962130001] (+0.000004468) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 1 } [03:19:13.962131936] (+0.000001935) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 8 } [03:19:13.962133732] (+0.000001796) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 114 } [03:19:13.962135557] (+0.000001825) cycles: { }, { ip = 0xFFFFFFFF8105443A, tid = 20714, pid = 20714, period = 2087 } [03:19:13.962137627] (+0.000002070) cycles: { }, { ip = 0xFFFFFFFF81361938, tid = 20714, pid = 20714, period = 37582 } [03:19:13.962161091] (+0.000023464) cycles: { }, { ip = 0xFFFFFFFF8124218F, tid = 20714, pid = 20714, period = 600246 } [03:19:13.962517569] (+0.000356478) cycles: { }, { ip = 0xFFFFFFFF811A75DB, tid = 20714, pid = 20714, period = 1325731 } [03:19:13.969518008] (+0.007000439) cycles: { }, { ip = 0x34080917B2, tid = 20714, pid = 20714, period = 1144298 } The following members to the ctf-environment were decided to be added to distinguish and specify perf CTF data: - domain It says "kernel" because it contains a kernel trace (not to be confused with a user space like lttng-ust does) - tracer_name It says perf. This can be used to distinguish between lttng and perf CTF based trace. - version The kernel version from stream. In addition to release, this is what it looks like on a Debian kernel: release = "3.14-1-amd64"; version = "3.14.0"; [1] http://projects.eclipse.org/projects/tools.tracecompass Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jeremie Galarneau <jgalar@efficios.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1424470628-5969-4-git-send-email-jolsa@kernel.org Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-21 06:17:00 +08:00
libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
libperf-y += scripting-engines/
libperf-$(CONFIG_ZLIB) += zlib.o
libperf-$(CONFIG_LZMA) += lzma.o
libperf-y += demangle-java.o
perf symbols: Add Rust demangling Rust demangling is another step after bfd demangling. Add a diagnosis to identify mangled Rust symbols based on the hash that the Rust mangler appends as the last path component, as well as other characteristics. Add a demangler to reconstruct the original symbol. Committer notes: How I tested it: Enabled COPR on Fedora 24 and then installed the 'rust-binary' package, with it: $ cat src/main.rs fn main() { println!("Hello, world!"); } $ cat Cargo.toml [package] name = "hello_world" version = "0.0.1" authors = [ "Arnaldo Carvalho de Melo <acme@kernel.org>" ] $ perf record cargo bench Compiling hello_world v0.0.1 (file:///home/acme/projects/hello_world) Running target/release/hello_world-d4b9dab4b2a47d75 running 0 tests test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.096 MB perf.data (1457 samples) ] $ Before this patch: $ perf report --stdio --dsos librbml-e8edd0fd.so # dso: librbml-e8edd0fd.so # # Total Lost Samples: 0 # # Samples: 1K of event 'cycles:u' # Event count (approx.): 979599126 # # Overhead Command Symbol # ........ ....... ............................................................................................................. # 1.78% rustc [.] rbml::reader::maybe_get_doc::hb9d387df6024b15b 1.50% rustc [.] _$LT$reader..DocsIterator$LT$$u27$a$GT$$u20$as$u20$std..iter..Iterator$GT$::next::hd9af9e60d79a35c8 1.20% rustc [.] rbml::reader::doc_at::hc88107fba445af31 0.46% rustc [.] _$LT$reader..TaggedDocsIterator$LT$$u27$a$GT$$u20$as$u20$std..iter..Iterator$GT$::next::h0cb40e696e4bb489 0.35% rustc [.] rbml::reader::Decoder::_next_int::h66eef7825a398bc3 0.29% rustc [.] rbml::reader::Decoder::_next_sub::h8e5266005580b836 0.15% rustc [.] rbml::reader::get_doc::h094521c645459139 0.14% rustc [.] _$LT$reader..Decoder$LT$$u27$doc$GT$$u20$as$u20$serialize..Decoder$GT$::read_u32::h0acea2fff9669327 0.07% rustc [.] rbml::reader::Decoder::next_doc::h6714d469c9dfaf91 0.07% rustc [.] _ZN4rbml6reader10doc_as_u6417h930b740aa94f1d3aE@plt 0.06% rustc [.] _fini $ After: $ perf report --stdio --dsos librbml-e8edd0fd.so # dso: librbml-e8edd0fd.so # # Total Lost Samples: 0 # # Samples: 1K of event 'cycles:u' # Event count (approx.): 979599126 # # Overhead Command Symbol # ........ ....... ................................................................. # 1.78% rustc [.] rbml::reader::maybe_get_doc 1.50% rustc [.] <reader::DocsIterator<'a> as std::iter::Iterator>::next 1.20% rustc [.] rbml::reader::doc_at 0.46% rustc [.] <reader::TaggedDocsIterator<'a> as std::iter::Iterator>::next 0.35% rustc [.] rbml::reader::Decoder::_next_int 0.29% rustc [.] rbml::reader::Decoder::_next_sub 0.15% rustc [.] rbml::reader::get_doc 0.14% rustc [.] <reader::Decoder<'doc> as serialize::Decoder>::read_u32 0.07% rustc [.] rbml::reader::Decoder::next_doc 0.07% rustc [.] _ZN4rbml6reader10doc_as_u6417h930b740aa94f1d3aE@plt 0.06% rustc [.] _fini $ Signed-off-by: David Tolnay <dtolnay@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/5780B7FA.3030602@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-09 15:20:00 +08:00
libperf-y += demangle-rust.o
ifdef CONFIG_JITDUMP
perf inject: Add jitdump mmap injection support This patch adds a --jit/-j option to perf inject. This options injects MMAP records into the perf.data file to cover the jitted code mmaps. It also emits ELF images for each function in the jidump file. Those images are created where the jitdump file is. The MMAP records point to that location as well. Typical flow: $ perf record -k mono -- java -agentpath:libpjvmti.so java_class $ perf inject --jit -i perf.data -o perf.data.jitted $ perf report -i perf.data.jitted Note that jitdump.h support is not limited to Java, it works with any jitted environment modified to emit the jitdump file format, include those where code can be jitted multiple times and moved around. The jitdump.h format is adapted from the Oprofile project. The genelf.c (ELF binary generation) depends on MD5 hash encoding for the buildid. To enable this, libssl-dev must be installed. If not, then genelf.c defaults to using urandom to generate the buildid, which is not ideal. The Makefile auto-detects the presence on libssl-dev. This version mmaps the jitdump file to create a marker MMAP record in the perf.data file. The marker is used to detect jitdump and cause perf inject to inject the jitted mmaps and generate ELF images for jitted functions. In V8, the following fixes and changes were made among other things: - the jidump header format include a new flags field to be used to carry information about the configuration of the runtime agent. Contributed by: Adrian Hunter <adrian.hunter@intel.com> - Fix mmap pgoff: MMAP event pgoff must be the offset within the ELF file at which the code resides. Contributed by: Adrian Hunter <adrian.hunter@intel.com> - Fix ELF virtual addresses: perf tools expect the ELF virtual addresses of dynamic objects to match the file offset. Contributed by: Adrian Hunter <adrian.hunter@intel.com> - JIT MMAP injection does not obey finished_round semantics. JIT MMAP injection injects all MMAP events in one go, so it does not obey finished_round semantics, so drop the finished_round events from the output perf.data file. Contributed by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Carl Love <cel@us.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John McCutchan <johnmccutchan@google.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Pawel Moll <pawel.moll@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sonny Rao <sonnyrao@chromium.org> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1448874143-7269-3-git-send-email-eranian@google.com [ Moved inject.build_ids ordering bits to a separate patch, fixed the NO_LIBELF=1 build ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-30 17:02:21 +08:00
libperf-$(CONFIG_LIBELF) += jitdump.o
libperf-$(CONFIG_LIBELF) += genelf.o
libperf-$(CONFIG_LIBELF) += genelf_debug.o
endif
CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
# avoid compiler warnings in 32-bit mode
CFLAGS_genelf_debug.o += -Wno-packed
$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
$(OUTPUT)util/pmu-bison.c: util/pmu.y
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
CFLAGS_parse-events-flex.o += -w
CFLAGS_pmu-flex.o += -w
CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)