From 729a78417a7b5c1f59e15d21a1900758375c4647 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 29 Oct 2015 11:48:18 -0300 Subject: perf trace: Add cmd string table to decode sys_bpf first arg # perf trace -e bpf perf record -e /tmp/foo.o -a 362.779 (0.130 ms): perf/3451 bpf(cmd: PROG_LOAD, uattr: 0x7ffe9a6825d0, size: 48) = 3 Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-2b0nknu53baz9e0wj4thcdd8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 93b80f1..c783d8f 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -585,6 +585,12 @@ static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct sysc #define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op +static const char *bpf_cmd[] = { + "MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM", + "MAP_GET_NEXT_KEY", "PROG_LOAD", +}; +static DEFINE_STRARRAY(bpf_cmd); + static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", }; static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1); @@ -1011,6 +1017,7 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ [1] = SCA_ACCMODE, /* mode */ }, }, { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, + { .name = "bpf", .errmsg = true, STRARRAY(0, cmd, bpf_cmd), }, { .name = "brk", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, { .name = "chdir", .errmsg = true, -- cgit v0.10.2 From dc323ce8e72d6d1beb9af9bbd29c4d55ce3d7fb0 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 31 Aug 2015 18:41:13 +0200 Subject: perf script: Enable printing of branch stack This patch improves perf script by enabling printing of the branch stack via the 'brstack' and 'brstacksym' arguments to the field selection option -F. The option is off by default and operates only if the perf.data file has branch stack content. The branches are printed in to/from pairs. The most recent branch is printed first. The number of branch entries vary based on the underlying hardware and filtering used. The brstack prints FROM/TO addresses in raw hexadecimal format. The brstacksym prints FROM/TO addresses in symbolic form wherever possible. $ perf script -F ip,brstack 5d3000 0x401aa0/0x5d2000/M/-/-/-/0 ... $ perf script -F ip,brstacksym 4011e0 noploop+0x0/noploop+0x0/P/-/-/0 The notation F/T/M/X/A/C describes the attributes of the branch. F=from, T=to, M/P=misprediction/prediction, X=TSX, A=TSX abort, C=cycles (SKL) Signed-off-by: Stephane Eranian Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Yuanfang Chen Link: http://lkml.kernel.org/r/1441039273-16260-5-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index b3b42f9..382ddfb 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -112,11 +112,11 @@ OPTIONS --debug-mode:: Do various checks like samples ordering and lost events. --f:: +-F:: --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, flags. + srcline, period, iregs, brstack, brstacksym, flags. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace @@ -175,6 +175,16 @@ OPTIONS Finally, a user may not set fields to none for all event types. i.e., -f "" is not allowed. + The brstack output includes branch related information with raw addresses using the + /v/v/v/v/ syntax in the following order: + FROM: branch source instruction + TO : branch target instruction + M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported + X/- : X=branch inside a transactional region, -=not in transaction region or not supported + A/- : A=TSX abort entry, -=not aborted region or not supported + + The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible. + -k:: --vmlinux=:: vmlinux pathname diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 278acb2..72b5deb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -51,6 +51,8 @@ enum perf_output_field { PERF_OUTPUT_SRCLINE = 1U << 12, PERF_OUTPUT_PERIOD = 1U << 13, PERF_OUTPUT_IREGS = 1U << 14, + PERF_OUTPUT_BRSTACK = 1U << 15, + PERF_OUTPUT_BRSTACKSYM = 1U << 16, }; struct output_option { @@ -72,6 +74,8 @@ struct output_option { {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, {.str = "period", .field = PERF_OUTPUT_PERIOD}, {.str = "iregs", .field = PERF_OUTPUT_IREGS}, + {.str = "brstack", .field = PERF_OUTPUT_BRSTACK}, + {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM}, }; /* default set to maintain compatibility with current format */ @@ -425,6 +429,77 @@ static void print_sample_start(struct perf_sample *sample, } } +static inline char +mispred_str(struct branch_entry *br) +{ + if (!(br->flags.mispred || br->flags.predicted)) + return '-'; + + return br->flags.predicted ? 'P' : 'M'; +} + +static void print_sample_brstack(union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct thread *thread __maybe_unused, + struct perf_event_attr *attr __maybe_unused) +{ + struct branch_stack *br = sample->branch_stack; + u64 i; + + if (!(br && br->nr)) + return; + + for (i = 0; i < br->nr; i++) { + printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ", + br->entries[i].from, + br->entries[i].to, + mispred_str( br->entries + i), + br->entries[i].flags.in_tx? 'X' : '-', + br->entries[i].flags.abort? 'A' : '-', + br->entries[i].flags.cycles); + } +} + +static void print_sample_brstacksym(union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct thread *thread __maybe_unused, + struct perf_event_attr *attr __maybe_unused) +{ + struct branch_stack *br = sample->branch_stack; + struct addr_location alf, alt; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + u64 i, from, to; + + if (!(br && br->nr)) + return; + + for (i = 0; i < br->nr; i++) { + + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + from = br->entries[i].from; + to = br->entries[i].to; + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, from, &alf); + if (alf.map) + alf.sym = map__find_symbol(alf.map, alf.addr, NULL); + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, to, &alt); + if (alt.map) + alt.sym = map__find_symbol(alt.map, alt.addr, NULL); + + symbol__fprintf_symname_offs(alf.sym, &alf, stdout); + putchar('/'); + symbol__fprintf_symname_offs(alt.sym, &alt, stdout); + printf("/%c/%c/%c/%d ", + mispred_str( br->entries + i), + br->entries[i].flags.in_tx? 'X' : '-', + br->entries[i].flags.abort? 'A' : '-', + br->entries[i].flags.cycles); + } +} + + static void print_sample_addr(union perf_event *event, struct perf_sample *sample, struct thread *thread, @@ -560,6 +635,11 @@ static void process_event(union perf_event *event, struct perf_sample *sample, if (PRINT_FIELD(IREGS)) print_sample_iregs(event, sample, thread, attr); + if (PRINT_FIELD(BRSTACK)) + print_sample_brstack(event, sample, thread, attr); + else if (PRINT_FIELD(BRSTACKSYM)) + print_sample_brstacksym(event, sample, thread, attr); + printf("\n"); } @@ -1681,7 +1761,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "comma separated output fields prepend with 'type:'. " "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff,period,iregs,flags", parse_output_fields), + "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", -- cgit v0.10.2 From 50f1e6d0431d3343cb506037c43ce623bd15581f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 28 Oct 2015 21:44:50 +0100 Subject: perf tools: Make sure fixdep is built before libbpf While doing 'make -C tools/perf build-test': LD fixdep-in.o LINK fixdep /bin/sh: /home/acme/git/linux/tools/build/fixdep: Permission denied make[6]: *** [bpf.o] Error 1 make[5]: *** [libbpf-in.o] Error 2 make[4]: *** [/home/acme/git/linux/tools/lib/bpf/libbpf.a] Error 2 make[4]: *** Waiting for unfinished jobs.... The fixdep tool needs to be built as the first binary. Libraries are built in paralel, so each of them needs to depend on fixdep target. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Jiri Olsa Cc: Wang Nan Link: http://lkml.kernel.org/r/20151028204450.GA25553@krava.redhat.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1e2e2d1..0d19d54 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -430,7 +430,7 @@ $(LIBAPI)-clean: $(call QUIET_CLEAN, libapi) $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null -$(LIBBPF): FORCE +$(LIBBPF): fixdep FORCE $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a $(LIBBPF)-clean: -- cgit v0.10.2 From 1f45b1d49073541947193bd7dac9e904142576aa Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 14 Oct 2015 12:41:18 +0000 Subject: perf bpf: Attach eBPF filter to perf event This is the final patch which makes basic BPF filter work. After applying this patch, users are allowed to use BPF filter like: # perf record --event ./hello_world.o ls A bpf_fd field is appended to 'struct evsel', and setup during the callback function add_bpf_event() for each 'probe_trace_event'. PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd. It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error. Committer note: The bpf proggie used so far: __attribute__((section("fork=_do_fork"), used)) int fork(void *ctx) { return 0; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; failed to produce any samples, even with forks happening and it being running in system wide mode. That is because now the filter is being associated, and the code above always returns zero, meaning that all forks will be probed but filtered away ;-/ Change it to 'return 1;' instead and after that: # trace --no-syscalls --event /tmp/foo.o 0.000 perf_bpf_probe:fork:(ffffffff8109be30)) 2.333 perf_bpf_probe:fork:(ffffffff8109be30)) 3.725 perf_bpf_probe:fork:(ffffffff8109be30)) 4.550 perf_bpf_probe:fork:(ffffffff8109be30)) ^C# And it works with all tools, including 'perf trace'. Signed-off-by: Wang Nan Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: David Ahern Cc: He Kuang Cc: Jiri Olsa Cc: Kaixu Xia Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3ac4ee9c..397fb4e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -208,6 +208,7 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->unit = ""; evsel->scale = 1.0; evsel->evlist = NULL; + evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->node); INIT_LIST_HEAD(&evsel->config_terms); perf_evsel__object.init(evsel); @@ -1356,6 +1357,22 @@ retry_open: err); goto try_fallback; } + + if (evsel->bpf_fd >= 0) { + int evt_fd = FD(evsel, cpu, thread); + int bpf_fd = evsel->bpf_fd; + + err = ioctl(evt_fd, + PERF_EVENT_IOC_SET_BPF, + bpf_fd); + if (err && errno != EEXIST) { + pr_err("failed to attach bpf fd %d: %s\n", + bpf_fd, strerror(errno)); + err = -EINVAL; + goto out_close; + } + } + set_rlimit = NO_CHANGE; /* diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 1e8ff19..0e49bd7 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -123,6 +123,7 @@ struct perf_evsel { char *group_name; bool cmdline_group_boundary; struct list_head config_terms; + int bpf_fd; }; union u64_swap { diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d97b037..cee8c61 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -542,6 +542,7 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd, struct __add_bpf_event_param *param = _param; struct parse_events_evlist *evlist = param->data; struct list_head *list = param->list; + struct perf_evsel *pos; int err; pr_debug("add bpf event %s:%s and attach bpf program %d\n", @@ -562,6 +563,11 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd, } pr_debug("adding %s:%s\n", tev->group, tev->event); + list_for_each_entry(pos, &new_evsels, node) { + pr_debug("adding %s:%s to %p\n", + tev->group, tev->event, pos); + pos->bpf_fd = fd; + } list_splice(&new_evsels, list); return 0; } -- cgit v0.10.2 From 71dc2326252ff1bcdddc05db03c0f831d16c9447 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 14 Oct 2015 12:41:19 +0000 Subject: perf record: Add clang options for compiling BPF scripts Although previous patch allows setting BPF compiler related options in perfconfig, on some ad-hoc situation it still requires passing options through cmdline. This patch introduces 2 options to 'perf record' for this propose: --clang-path and --clang-opt. Signed-off-by: Wang Nan Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: David Ahern Cc: He Kuang Cc: Jiri Olsa Cc: Kaixu Xia Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-9-git-send-email-wangnan0@huawei.com [ Add the new options to the 'record' man page ] Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 7ff6a9d..e630a7d 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -314,6 +314,12 @@ This option sets the time out limit. The default value is 500 ms. Record context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. +--clang-path:: +Path to clang binary to use for compiling BPF scriptlets. + +--clang-opt:: +Options passed to clang when compiling BPF scriptlets. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index de02267..199fc31 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -31,6 +31,7 @@ #include "util/auxtrace.h" #include "util/parse-branch-options.h" #include "util/parse-regs-options.h" +#include "util/llvm-utils.h" #include #include @@ -1112,6 +1113,12 @@ struct option __record_options[] = { "per thread proc mmap processing timeout in ms"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), +#ifdef HAVE_LIBBPF_SUPPORT + OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path", + "clang binary to use for compiling BPF scriptlets"), + OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options", + "options passed to clang when compiling BPF scriptlets"), +#endif OPT_END() }; -- cgit v0.10.2 From d509db0473e40134286271b1d1adadccf42ac467 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 14 Oct 2015 12:41:20 +0000 Subject: perf tools: Compile scriptlets to BPF objects when passing '.c' to --event This patch provides infrastructure for passing source files to --event directly using: # perf record --event bpf-file.c command This patch does following works: 1) Allow passing '.c' file to '--event'. parse_events_load_bpf() is expanded to allow caller tell it whether the passed file is source file or object. 2) llvm__compile_bpf() is called to compile the '.c' file, the result is saved into memory. Use bpf_object__open_buffer() to load the in-memory object. Introduces a bpf-script-example.c so we can manually test it: # perf record --clang-opt "-DLINUX_VERSION_CODE=0x40200" --event ./bpf-script-example.c sleep 1 Note that '--clang-opt' must put before '--event'. Futher patches will merge it into a testcase so can be tested automatically. Signed-off-by: Wang Nan Acked-by: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: David Ahern Cc: He Kuang Cc: Jiri Olsa Cc: Kaixu Xia Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-10-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c new file mode 100644 index 0000000..410a70b --- /dev/null +++ b/tools/perf/tests/bpf-script-example.c @@ -0,0 +1,44 @@ +#ifndef LINUX_VERSION_CODE +# error Need LINUX_VERSION_CODE +# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' +#endif +#define BPF_ANY 0 +#define BPF_MAP_TYPE_ARRAY 2 +#define BPF_FUNC_map_lookup_elem 1 +#define BPF_FUNC_map_update_elem 2 + +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_lookup_elem; +static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = + (void *) BPF_FUNC_map_update_elem; + +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; +}; + +#define SEC(NAME) __attribute__((section(NAME), used)) +struct bpf_map_def SEC("maps") flip_table = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, +}; + +SEC("func=sys_epoll_pwait") +int bpf_func__sys_epoll_pwait(void *ctx) +{ + int ind =0; + int *flag = bpf_map_lookup_elem(&flip_table, &ind); + int new_flag; + if (!flag) + return 0; + /* flip flag and store back */ + new_flag = !*flag; + bpf_map_update_elem(&flip_table, &ind, &new_flag, BPF_ANY); + return new_flag; +} +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index aa784a4..ba6f752 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -12,6 +12,7 @@ #include "bpf-loader.h" #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES +#include "llvm-utils.h" #define DEFINE_PRINT_FN(name, level) \ static int libbpf_##name(const char *fmt, ...) \ @@ -33,7 +34,7 @@ struct bpf_prog_priv { struct perf_probe_event pev; }; -struct bpf_object *bpf__prepare_load(const char *filename) +struct bpf_object *bpf__prepare_load(const char *filename, bool source) { struct bpf_object *obj; static bool libbpf_initialized; @@ -45,7 +46,19 @@ struct bpf_object *bpf__prepare_load(const char *filename) libbpf_initialized = true; } - obj = bpf_object__open(filename); + if (source) { + int err; + void *obj_buf; + size_t obj_buf_sz; + + err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz); + if (err) + return ERR_PTR(err); + obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); + free(obj_buf); + } else + obj = bpf_object__open(filename); + if (!obj) { pr_debug("bpf: failed to load %s\n", filename); return ERR_PTR(-EINVAL); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index a8f25ee..ccd8d7f 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -18,7 +18,7 @@ typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev, int fd, void *arg); #ifdef HAVE_LIBBPF_SUPPORT -struct bpf_object *bpf__prepare_load(const char *filename); +struct bpf_object *bpf__prepare_load(const char *filename, bool source); void bpf__clear(void); @@ -34,7 +34,8 @@ int bpf__foreach_tev(struct bpf_object *obj, bpf_prog_iter_callback_t func, void *arg); #else static inline struct bpf_object * -bpf__prepare_load(const char *filename __maybe_unused) +bpf__prepare_load(const char *filename __maybe_unused, + bool source __maybe_unused) { pr_debug("ERROR: eBPF object loading is disabled during compiling.\n"); return ERR_PTR(-ENOTSUP); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index cee8c61..bee6058 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -626,11 +626,12 @@ errout: int parse_events_load_bpf(struct parse_events_evlist *data, struct list_head *list, - char *bpf_file_name) + char *bpf_file_name, + bool source) { struct bpf_object *obj; - obj = bpf__prepare_load(bpf_file_name); + obj = bpf__prepare_load(bpf_file_name, source); if (IS_ERR(obj) || !obj) { char errbuf[BUFSIZ]; int err; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 765018a..f1a6db1 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -125,7 +125,8 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, struct list_head *head_config); int parse_events_load_bpf(struct parse_events_evlist *data, struct list_head *list, - char *bpf_file_name); + char *bpf_file_name, + bool source); /* Provide this function for perf test */ struct bpf_object; int parse_events_load_bpf_obj(struct parse_events_evlist *data, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index cf330eb..58c5831 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -116,6 +116,7 @@ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ bpf_object .*\.(o|bpf) +bpf_source .*\.c num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ @@ -161,6 +162,7 @@ modifier_bp [rwx]{1,3} {event_pmu} | {bpf_object} | +{bpf_source} | {event} { BEGIN(INITIAL); REWIND(1); @@ -269,6 +271,7 @@ r{num_raw_hex} { return raw(yyscanner); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {bpf_object} { return str(yyscanner, PE_BPF_OBJECT); } +{bpf_source} { return str(yyscanner, PE_BPF_SOURCE); } {name} { return pmu_str_check(yyscanner); } "/" { BEGIN(config); return '/'; } - { return '-'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 497f19b..ad37996 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -42,7 +42,7 @@ static inc_group_count(struct list_head *list, %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM %token PE_EVENT_NAME %token PE_NAME -%token PE_BPF_OBJECT +%token PE_BPF_OBJECT PE_BPF_SOURCE %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP @@ -55,6 +55,7 @@ static inc_group_count(struct list_head *list, %type PE_TERM %type PE_NAME %type PE_BPF_OBJECT +%type PE_BPF_SOURCE %type PE_NAME_CACHE_TYPE %type PE_NAME_CACHE_OP_RESULT %type PE_MODIFIER_EVENT @@ -461,7 +462,17 @@ PE_BPF_OBJECT struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1)); + ABORT_ON(parse_events_load_bpf(data, list, $1, false)); + $$ = list; +} +| +PE_BPF_SOURCE +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_load_bpf(data, list, $1, true)); $$ = list; } -- cgit v0.10.2 From 3af6ed84eb43c587beb5f3252222e39e65d08c61 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 29 Oct 2015 08:49:37 +0100 Subject: tools build: Fix libiberty feature detection Any CFLAGS or LDFLAGS set by the user need to be passed to the feature build command. This many include for example -I or -L to point to libraries and include files in custom paths. In most of the test-*.bin rules in build/feature/Makefile, we use the BUILD macro which always sends in CFLAGS and LDFLAGS. The libiberty build line however doesn't use the BUILD macro and thus needs to send in CFLAGS and LDFLAGS explicitly. Without this, when using custom CFLAGS/LDFLAGS, libiberty fails to be detected and the perf link fails with something like: LINK perf libbfd.a(bfd.o): In function `bfd_errmsg': bfd.c:(.text+0x168): undefined reference to `xstrerror' bbfd.a(opncls.o): In function `_bfd_new_bfd': opncls.c:(.text+0xe8): undefined reference to `objalloc_create' ... Signed-off-by: Rabin Vincent Acked-by: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rabin Vincent Link: http://lkml.kernel.org/r/1446104978-26429-2-git-send-email-rabin.vincent@axis.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index e43a297..cea04ce9 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -132,10 +132,10 @@ test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl test-liberty.bin: - $(CC) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty + $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty test-liberty-z.bin: - $(CC) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz + $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz test-cplus-demangle.bin: $(BUILD) -liberty -- cgit v0.10.2 From 7ed4915ad60788d6b846e2cd034f49ee15698143 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 29 Oct 2015 08:49:36 +0100 Subject: perf unwind: Pass symbol source to libunwind Even if --symfs is used to point to the debug binaries, we send in the non-debug filenames to libunwind, which leads to libunwind not finding the debug frame. Fix this by preferring the file in --symfs, if it is available. Signed-off-by: Rabin Vincent Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rabin Vincent Link: http://lkml.kernel.org/r/1446104978-26429-1-git-send-email-rabin.vincent@axis.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index f729f9e..c83832b 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -360,12 +360,15 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, int fd = dso__data_get_fd(map->dso, ui->machine); int is_exec = elf_is_exec(fd, map->dso->name); unw_word_t base = is_exec ? 0 : map->start; + const char *symfile; if (fd >= 0) dso__data_put_fd(map->dso); + symfile = map->dso->symsrc_filename ?: map->dso->name; + memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name, + if (dwarf_find_debug_frame(0, &di, ip, base, symfile, map->start, map->end)) return dwarf_search_unwind_table(as, ip, &di, pi, need_unwind_info, arg); -- cgit v0.10.2