From 9396c9cb0d9534ca67bda8a34b2413a2ca1c67e9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 22 Dec 2016 15:03:50 +0900 Subject: perf sched timehist: Show total scheduling time Show length of analyzed sample time and rate of idle task running. This also takes care of time range given by --time option. $ perf sched timehist -sI | tail Samples do not have callchains. Idle stats: CPU 0 idle for 930.316 msec ( 92.93%) CPU 1 idle for 963.614 msec ( 96.25%) CPU 2 idle for 885.482 msec ( 88.45%) CPU 3 idle for 938.635 msec ( 93.76%) Total number of unique tasks: 118 Total number of context switches: 2337 Total run time (msec): 3718.048 Total scheduling time (msec): 1001.131 (x 4) Suggested-by: David Ahern Signed-off-by: Namhyung Kim Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20161222060350.17655-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index d53e706a6f17..5b134b0d1ff3 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -209,6 +209,7 @@ struct perf_sched { u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; + struct perf_time_interval hist_time; }; /* per thread run time data */ @@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool, timehist_print_sample(sched, sample, &al, thread, t); out: + if (sched->hist_time.start == 0 && t >= ptime->start) + sched->hist_time.start = t; + if (ptime->end == 0 || t <= ptime->end) + sched->hist_time.end = t; + if (tr) { /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; @@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched, struct thread *t; struct thread_runtime *r; int i; + u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); @@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched, totals.sched_count += r->run_stats.n; printf(" CPU %2d idle for ", i); print_sched_time(r->total_run_time, 6); - printf(" msec\n"); + printf(" msec (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time); } else printf(" CPU %2d idle entire time window\n", i); } @@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched, printf("\n" " Total number of unique tasks: %" PRIu64 "\n" - "Total number of context switches: %" PRIu64 "\n" - " Total run time (msec): ", + "Total number of context switches: %" PRIu64 "\n", totals.task_count, totals.sched_count); + printf(" Total run time (msec): "); print_sched_time(totals.total_run_time, 2); printf("\n"); + + printf(" Total scheduling time (msec): "); + print_sched_time(hist_time, 2); + printf(" (x %d)\n", sched->max_cpu); } typedef int (*sched_handler)(struct perf_tool *tool, -- cgit From 1f2ed153b916c95a49a1ca9d7107738664224b7f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 3 Jan 2017 00:20:49 +0900 Subject: perf probe: Fix to get correct modname from elf header Since 'perf probe' supports cross-arch probes, it is possible to analyze different arch kernel image which has different bits-per-long. In that case, it fails to get the module name because it uses the MOD_NAME_OFFSET macro based on the host machine bits-per-long, instead of the target arch bits-per-long. This fixes above issue by changing modname-offset based on the target archs bit width. This is ok because linux kernel uses LP64 model on 64bit arch. E.g. without this (on x86_64, and target module is arm32): $ perf probe -m build-arm/fs/configfs/configfs.ko -D configfs_lookup p:probe/configfs_lookup :configfs_lookup+0 ^-Here is an empty module name. With this fix, you can see correct module name: $ perf probe -m build-arm/fs/configfs/configfs.ko -D configfs_lookup p:probe/configfs_lookup configfs:configfs_lookup+0 Signed-off-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/148337043836.6752.383495516397005695.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d281ae2b54e8..8f810961ec78 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -267,21 +267,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address) return true; } -/* - * NOTE: - * '.gnu.linkonce.this_module' section of kernel module elf directly - * maps to 'struct module' from linux/module.h. This section contains - * actual module name which will be used by kernel after loading it. - * But, we cannot use 'struct module' here since linux/module.h is not - * exposed to user-space. Offset of 'name' has remained same from long - * time, so hardcoding it here. - */ -#ifdef __LP64__ -#define MOD_NAME_OFFSET 24 -#else -#define MOD_NAME_OFFSET 12 -#endif - /* * @module can be module name of module file path. In case of path, * inspect elf and find out what is actual module name. @@ -296,6 +281,7 @@ static char *find_module_name(const char *module) Elf_Data *data; Elf_Scn *sec; char *mod_name = NULL; + int name_offset; fd = open(module, O_RDONLY); if (fd < 0) @@ -317,7 +303,21 @@ static char *find_module_name(const char *module) if (!data || !data->d_buf) goto ret_err; - mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET); + /* + * NOTE: + * '.gnu.linkonce.this_module' section of kernel module elf directly + * maps to 'struct module' from linux/module.h. This section contains + * actual module name which will be used by kernel after loading it. + * But, we cannot use 'struct module' here since linux/module.h is not + * exposed to user-space. Offset of 'name' has remained same from long + * time, so hardcoding it here. + */ + if (ehdr.e_ident[EI_CLASS] == ELFCLASS32) + name_offset = 12; + else /* expect ELFCLASS64 by default */ + name_offset = 24; + + mod_name = strdup((char *)data->d_buf + name_offset); ret_err: elf_end(elf); -- cgit From b66fb1da5a8cac3f5c3cdbe41937c91efc4e76a4 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 3 Jan 2017 09:19:54 +0100 Subject: tools lib subcmd: Add OPT_STRING_OPTARG_SET option To allow string options with a default argument and variable set when the option is used. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1483431600-19887-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/subcmd/parse-options.c | 3 +++ tools/lib/subcmd/parse-options.h | 5 +++++ 2 files changed, 8 insertions(+) (limited to 'tools') diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 3284bb14ae78..8aad81151d50 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p, else err = get_arg(p, opt, flags, (const char **)opt->value); + if (opt->set) + *(bool *)opt->set = true; + /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */ if (opt->flags & PARSE_OPT_NOEMPTY) { const char *val = *(const char **)opt->value; diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 8866ac438b34..11c3be3bcce7 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -137,6 +137,11 @@ struct option { { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ .value = check_vtype(v, const char **), (a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } +#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \ + { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, const char **), (a), .help = (h), \ + .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \ + .set = check_vtype(os, bool *)} #define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } -- cgit From efd21307119d5a23ac83ae8fd5a39a5c7aeb8493 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 3 Jan 2017 09:19:55 +0100 Subject: perf record: Make __record_options static There's no need for this one to be global. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1483431600-19887-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 74d6a035133a..31cf0ce12a65 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1405,7 +1405,7 @@ static bool dry_run; * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ -struct option __record_options[] = { +static struct option __record_options[] = { OPT_CALLBACK('e', "event", &record.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), -- cgit From 60437ac02f398e0ee0927748d4798dd5534ac90d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 3 Jan 2017 09:19:56 +0100 Subject: perf record: Fix --switch-output documentation and comment There's no --signal-trigger option, also adding the code comment into record man page. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1483431600-19887-4-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++++ tools/perf/builtin-record.c | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 27fc3617c6a4..5054d9147f0f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that particular perf.data snapshot should be kept or not. Implies --timestamp-filename, --no-buildid and --no-buildid-cache. +The reason for the latter two is to reduce the data file switching +overhead. You can still switch them on with: + + --switch-output --no-no-buildid --no-no-buildid-cache --dry-run:: Parse options then exit. --dry-run can be used to detect errors in cmdline diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 31cf0ce12a65..4ec10e9427d9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) * overhead. Still generate buildid if they are required * explicitly using * - * perf record --signal-trigger --no-no-buildid \ + * perf record --switch-output --no-no-buildid \ * --no-no-buildid-cache * * Following code equals to: -- cgit From 074859184d770824f4437dca716bdeb625ae8b1c Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 3 Jan 2017 12:42:42 +0100 Subject: tools lib traceevent: Fix prev/next_prio for deadline tasks Currently, the sched:sched_switch tracepoint reports deadline tasks with priority -1. But when reading the trace via perf script I've got the following output: # ./d & # (d is a deadline task, see [1]) # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 2146.962441: sched:sched_switch: swapper/0:0 [120] R ==> d:2593 [4294967295] d 2593 [000] 2146.972472: sched:sched_switch: d:2593 [4294967295] R ==> g:2590 [4294967295] The task d reports the wrong priority [4294967295]. This happens because the "int prio" is stored in an unsigned long long val. Although it is set as a %lld, as int is shorter than unsigned long long, trace_seq_printf prints it as a positive number. The fix is just to cast the val as an int, and print it as a %d, as in the sched:sched_switch tracepoint's "format". The output with the fix is: # ./d & # perf record -e sched:sched_switch -a sleep 1 # perf script ... swapper 0 [000] 4306.374037: sched:sched_switch: swapper/0:0 [120] R ==> d:10941 [-1] d 10941 [000] 4306.383823: sched:sched_switch: d:10941 [-1] R ==> swapper/0:0 [120] [1] d.c --- #include #include #include #include #include struct sched_attr { __u32 size, sched_policy; __u64 sched_flags; __s32 sched_nice; __u32 sched_priority; __u64 sched_runtime, sched_deadline, sched_period; }; int sched_setattr(pid_t pid, const struct sched_attr *attr, unsigned int flags) { return syscall(__NR_sched_setattr, pid, attr, flags); } int main(void) { struct sched_attr attr = { .size = sizeof(attr), .sched_policy = SCHED_DEADLINE, /* This creates a 10ms/30ms reservation */ .sched_runtime = 10 * 1000 * 1000, .sched_period = attr.sched_deadline = 30 * 1000 * 1000, }; if (sched_setattr(0, &attr, 0) < 0) { perror("sched_setattr"); return -1; } for(;;); } --- Committer notes: Got the program from the provided URL, http://bristot.me/lkml/d.c, trimmed it and included in the cset log above, so that we have everything needed to test it in one place. Signed-off-by: Daniel Bristot de Oliveira Acked-by: Steven Rostedt Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Daniel Bristot de Oliveira Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/866ef75bcebf670ae91c6a96daa63597ba981f0d.1483443552.git.bristot@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/plugin_sched_switch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c index f1ce60065258..ec30c2fcbac0 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugin_sched_switch.c @@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld ", val); if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0) - trace_seq_printf(s, "[%lld] ", val); + trace_seq_printf(s, "[%d] ", (int) val); if (pevent_get_field_val(s, event, "prev_state", record, &val, 0) == 0) write_state(s, val); @@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s, trace_seq_printf(s, "%lld", val); if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0) - trace_seq_printf(s, " [%lld]", val); + trace_seq_printf(s, " [%d]", (int) val); return 0; } -- cgit From 30a9c6444810429aa2b7cbfbd453ce339baaadbf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Jan 2017 12:03:59 -0300 Subject: perf tools: Install tools/lib/traceevent plugins with install-bin Those are binaries as well, so should be installed by: make -C tools/perf install-bin' too. Cc: Alexander Shishkin Cc: Daniel Bristot de Oliveira Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Steven Rostedt Link: http://lkml.kernel.org/n/tip-3841b37u05evxrs1igkyu6ks@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e9ec531131ca..4db68aec9913 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -704,9 +704,9 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' -install-bin: install-tools install-tests +install-bin: install-tools install-tests install-traceevent-plugins -install: install-bin try-install-man install-traceevent-plugins +install: install-bin try-install-man install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' -- cgit From 7934c98a6e04028eb34c1293bfb5a6b0ab630b66 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Jan 2017 15:19:21 -0300 Subject: perf symbols: Robustify reading of build-id from sysfs Markus reported that perf segfaults when reading /sys/kernel/notes from a kernel linked with GNU gold, due to what looks like a gold bug, so do some bounds checking to avoid crashing in that case. Reported-by: Markus Trippelsdorf Report-Link: http://lkml.kernel.org/r/20161219161821.GA294@x4 Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-ryhgs6a6jxvz207j2636w31c@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 99400b0e8f2a..adbc6c02c3aa 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) break; } else { int n = namesz + descsz; + + if (n > (int)sizeof(bf)) { + n = sizeof(bf); + pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n", + __func__, filename, nhdr.n_namesz, nhdr.n_descsz); + } if (read(fd, bf, n) != n) break; } -- cgit From eebc509b20881b92d62e317b2c073e57c5f200f0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 4 Jan 2017 12:29:05 +0900 Subject: perf probe: Fix --funcs to show correct symbols for offline module Fix --funcs (-F) option to show correct symbols for offline module. Since previous perf-probe uses machine__findnew_module_map() for offline module, even if user passes a module file (with full path) which is for other architecture, perf-probe always tries to load symbol map for current kernel module. This fix uses dso__new_map() to load the map from given binary as same as a map for user applications. Signed-off-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/148350053478.19001.15435255244512631545.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 25 ++++++------------------- 1 file changed, 6 insertions(+), 19 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 8f810961ec78..542e6472c4d7 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module) /* A file path -- this is an offline module */ if (module && strchr(module, '/')) - return machine__findnew_module_map(host_machine, 0, module); + return dso__new_map(module); if (!module) module = "kernel"; @@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module) if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && module[pos->dso->short_name_len - 2] == '\0') { + map__get(pos); return pos; } } @@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user) return kernel_get_module_map(target); } -static void put_target_map(struct map *map, bool user) -{ - if (map && user) { - /* Only the user map needs to be released */ - map__put(map); - } -} - - static int convert_exec_to_group(const char *exec, char **result) { char *ptr1, *ptr2, *exec_copy; @@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, } out: - put_target_map(map, uprobes); + map__put(map); return ret; } @@ -2869,7 +2861,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } out: - put_target_map(map, pev->uprobes); + map__put(map); free(syms); return ret; @@ -3362,10 +3354,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return ret; /* Get a symbol map */ - if (user) - map = dso__new_map(target); - else - map = kernel_get_module_map(target); + map = get_target_map(target, user); if (!map) { pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; @@ -3397,9 +3386,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, } end: - if (user) { - map__put(map); - } + map__put(map); exit_probe_symbol_maps(); return ret; -- cgit From 8a937a25a7e3c19d5fb3f9d92f605cf5fda219d8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 4 Jan 2017 12:30:19 +0900 Subject: perf probe: Fix to probe on gcc generated symbols for offline kernel Fix perf-probe to show probe definition on gcc generated symbols for offline kernel (including cross-arch kernel image). gcc sometimes optimizes functions and generate new symbols with suffixes such as ".constprop.N" or ".isra.N" etc. Since those symbol names are not recorded in DWARF, we have to find correct generated symbols from offline ELF binary to probe on it (kallsyms doesn't correct it). For online kernel or uprobes we don't need it because those are rebased on _text, or a section relative address. E.g. Without this: $ perf probe -k build-arm/vmlinux -F __slab_alloc* __slab_alloc.constprop.9 $ perf probe -k build-arm/vmlinux -D __slab_alloc p:probe/__slab_alloc __slab_alloc+0 If you put above definition on target machine, it should fail because there is no __slab_alloc in kallsyms. With this fix, perf probe shows correct probe definition on __slab_alloc.constprop.9: $ perf probe -k build-arm/vmlinux -D __slab_alloc p:probe/__slab_alloc __slab_alloc.constprop.9+0 Signed-off-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/148350060434.19001.11864836288580083501.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 48 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 542e6472c4d7..4a57c8a60bd9 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -610,6 +610,51 @@ error: return ret ? : -ENOENT; } +/* + * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions + * and generate new symbols with suffixes such as .constprop.N or .isra.N + * etc. Since those symbols are not recorded in DWARF, we have to find + * correct generated symbols from offline ELF binary. + * For online kernel or uprobes we don't need this because those are + * rebased on _text, or already a section relative address. + */ +static int +post_process_offline_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *pathname) +{ + struct symbol *sym; + struct map *map; + unsigned long stext = 0; + u64 addr; + int i; + + /* Prepare a map for offline binary */ + map = dso__new_map(pathname); + if (!map || get_text_start_address(pathname, &stext) < 0) { + pr_warning("Failed to get ELF symbols for %s\n", pathname); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + addr = tevs[i].point.address + tevs[i].point.offset - stext; + sym = map__find_symbol(map, addr); + if (!sym) + continue; + if (!strcmp(sym->name, tevs[i].point.symbol)) + continue; + /* If we have no realname, use symbol for it */ + if (!tevs[i].point.realname) + tevs[i].point.realname = tevs[i].point.symbol; + else + free(tevs[i].point.symbol); + tevs[i].point.symbol = strdup(sym->name); + tevs[i].point.offset = addr - sym->start; + } + map__put(map); + + return 0; +} + static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *exec) { @@ -671,7 +716,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, /* Skip post process if the target is an offline kernel */ if (symbol_conf.ignore_vmlinux_buildid) - return 0; + return post_process_offline_probe_trace_events(tevs, ntevs, + symbol_conf.vmlinux_name); reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { -- cgit From a2b1e8a20c992b01eeb76de00d4f534cbe9f3822 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Wed, 14 Dec 2016 11:59:34 +0100 Subject: selftests: do not require bash for the generated test Nothing in this minimal script seems to require bash. We often run these tests on embedded devices where the only shell available is the busybox ash. Use sh instead. Signed-off-by: Rolf Eike Beer Cc: stable@vger.kernel.org Signed-off-by: Shuah Khan --- tools/testing/selftests/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 71b05891a6a1..831022b12848 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -90,7 +90,7 @@ ifdef INSTALL_PATH done; @# Ask all targets to emit their test scripts - echo "#!/bin/bash" > $(ALL_SCRIPT) + echo "#!/bin/sh" > $(ALL_SCRIPT) echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT) echo "ROOT=\$$PWD" >> $(ALL_SCRIPT) -- cgit From d979e13a3fa9067c8cd46e292ed859626d443996 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Wed, 14 Dec 2016 11:58:20 +0100 Subject: selftests: do not require bash to run bpf tests Nothing in this minimal script seems to require bash. We often run these tests on embedded devices where the only shell available is the busybox ash. Use sh instead. Signed-off-by: Rolf Eike Beer Cc: stable@vger.kernel.org Acked-by: Daniel Borkmann Signed-off-by: Shuah Khan --- tools/testing/selftests/bpf/test_kmod.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 92e627adf354..6d58cca8e235 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh SRC_TREE=../../../../ -- cgit From 3659f98b5375d195f1870c3e508fe51e52206839 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Wed, 14 Dec 2016 11:59:57 +0100 Subject: selftests: do not require bash to run netsocktests testcase Nothing in this minimal script seems to require bash. We often run these tests on embedded devices where the only shell available is the busybox ash. Use sh instead. Signed-off-by: Rolf Eike Beer Cc: stable@vger.kernel.org Signed-off-by: Shuah Khan --- tools/testing/selftests/net/run_netsocktests | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index c09a682df56a..16058bbea7a8 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh echo "--------------------" echo "running socket test" -- cgit From 7738789fba09108a28a5fb4739595d9a0a2f85fe Mon Sep 17 00:00:00 2001 From: Colin King Date: Tue, 27 Dec 2016 16:17:21 +0000 Subject: selftests: x86/pkeys: fix spelling mistake: "itertation" -> "iteration" Fix spelling mistake in print test pass message. Signed-off-by: Colin Ian King Signed-off-by: Shuah Khan --- tools/testing/selftests/x86/protection_keys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index bdd58c78902e..df9e0a0cdf29 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -1367,7 +1367,7 @@ void run_tests_once(void) tracing_off(); close_test_fds(); - printf("test %2d PASSED (itertation %d)\n", test_nr, iteration_nr); + printf("test %2d PASSED (iteration %d)\n", test_nr, iteration_nr); dprintf1("======================\n\n"); } iteration_nr++; -- cgit From 41b6167e8f746b475668f1da78599fc4284f18db Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 10 Jan 2017 16:57:42 -0800 Subject: mm: get rid of __GFP_OTHER_NODE The flag was introduced by commit 78afd5612deb ("mm: add __GFP_OTHER_NODE flag") to allow proper accounting of remote node allocations done by kernel daemons on behalf of a process - e.g. khugepaged. After "mm: fix remote numa hits statistics" we do not need and actually use the flag so we can safely remove it because all allocations which are satisfied from their "home" node are accounted properly. [mhocko@suse.com: fix build] Link: http://lkml.kernel.org/r/20170106122225.GK5556@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170102153057.9451-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Taku Izumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 13 +++---------- include/trace/events/mmflags.h | 3 +-- mm/huge_memory.c | 3 +-- mm/khugepaged.c | 5 ++--- mm/page_alloc.c | 5 ++--- tools/perf/builtin-kmem.c | 1 - 6 files changed, 9 insertions(+), 21 deletions(-) (limited to 'tools') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4175dca4ac39..7806a8f80abc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -38,9 +38,8 @@ struct vm_area_struct; #define ___GFP_ACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u -#define ___GFP_OTHER_NODE 0x800000u -#define ___GFP_WRITE 0x1000000u -#define ___GFP_KSWAPD_RECLAIM 0x2000000u +#define ___GFP_WRITE 0x800000u +#define ___GFP_KSWAPD_RECLAIM 0x1000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -172,11 +171,6 @@ struct vm_area_struct; * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of * distinguishing in the source between false positives and allocations that * cannot be supported (e.g. page tables). - * - * __GFP_OTHER_NODE is for allocations that are on a remote node but that - * should not be accounted for as a remote allocation in vmstat. A - * typical user would be khugepaged collapsing a huge page on a remote - * node. */ #define __GFP_COLD ((__force gfp_t)___GFP_COLD) #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) @@ -184,10 +178,9 @@ struct vm_area_struct; #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT 26 +#define __GFP_BITS_SHIFT 25 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 9e687ca9a307..15bf875d0e4a 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -47,8 +47,7 @@ {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_OTHER_NODE, "__GFP_OTHER_NODE"} \ + {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"}\ #define show_gfp_flags(flags) \ (flags) ? __print_flags(flags, "|", \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf14421..72339a646fb1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -919,8 +919,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, } for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, vma, + pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma, vmf->address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_try_charge(pages[i], vma->vm_mm, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b0924a68cc36..77ae3239c3de 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -943,7 +943,7 @@ static void collapse_huge_page(struct mm_struct *mm, VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE; + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; /* * Before allocating the hugepage, release the mmap_sem read lock. @@ -1309,8 +1309,7 @@ static void collapse_shmem(struct mm_struct *mm, VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | - __GFP_OTHER_NODE | __GFP_THISNODE; + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cba2a64792e6..872caae544ef 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2584,8 +2584,7 @@ int __isolate_free_page(struct page *page, unsigned int order) * * Must be called with interrupts disabled. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, - gfp_t flags) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) { #ifdef CONFIG_NUMA enum zone_stat_item local_stat = NUMA_LOCAL; @@ -2667,7 +2666,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, } __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone, gfp_flags); + zone_statistics(preferred_zone, zone); local_irq_restore(flags); VM_BUG_ON_PAGE(bad_range(zone, page), page); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 35a02f8e5a4a..915869e00d86 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -655,7 +655,6 @@ static const struct { { "__GFP_RECLAIM", "R" }, { "__GFP_DIRECT_RECLAIM", "DR" }, { "__GFP_KSWAPD_RECLAIM", "KR" }, - { "__GFP_OTHER_NODE", "ON" }, }; static size_t max_gfp_len; -- cgit