From bc0622302f344551050995491b7d14176f39c628 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 1 Jul 2016 17:03:12 +0900 Subject: [PATCH 01/16] perf probe: Use cache entry if possible Before analyzing debuginfo, try to find a corresponding entry from probe cache always. This does not depend on --cache, the --cache enables to store/update cache, but looking up the cache is always enabled. Signed-off-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736019226.27797.16366402884098398857.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 65 +++++++++++++++++++++++++++++++++-- tools/perf/util/probe-file.c | 20 ++++++++++- tools/perf/util/probe-file.h | 5 ++- 3 files changed, 86 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 55f41d5e20d1..47b6b8b7206e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2474,17 +2474,24 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, char buf[64]; int ret; + /* If probe_event or trace_event already have the name, reuse it */ if (pev->event) event = pev->event; - else + else if (tev->event) + event = tev->event; + else { + /* Or generate new one from probe point */ if (pev->point.function && (strncmp(pev->point.function, "0x", 2) != 0) && !strisglob(pev->point.function)) event = pev->point.function; else event = tev->point.realname; + } if (pev->group) group = pev->group; + else if (tev->group) + group = tev->group; else group = PERFPROBE_GROUP; @@ -2531,7 +2538,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, for (i = 0; i < ntevs; i++) { tev = &tevs[i]; /* Skip if the symbol is out of .text or blacklisted */ - if (!tev->point.symbol) + if (!tev->point.symbol && !pev->uprobes) continue; /* Set new name for tev (and update namelist) */ @@ -2844,6 +2851,55 @@ errout: bool __weak arch__prefers_symtab(void) { return false; } +static int find_probe_trace_events_from_cache(struct perf_probe_event *pev, + struct probe_trace_event **tevs) +{ + struct probe_cache *cache; + struct probe_cache_entry *entry; + struct probe_trace_event *tev; + struct str_node *node; + int ret, i; + + cache = probe_cache__new(pev->target); + if (!cache) + return 0; + + entry = probe_cache__find(cache, pev); + if (!entry) { + ret = 0; + goto out; + } + + ret = strlist__nr_entries(entry->tevlist); + if (ret > probe_conf.max_probes) { + pr_debug("Too many entries matched in the cache of %s\n", + pev->target ? : "kernel"); + ret = -E2BIG; + goto out; + } + + *tevs = zalloc(ret * sizeof(*tev)); + if (!*tevs) { + ret = -ENOMEM; + goto out; + } + + i = 0; + strlist__for_each_entry(node, entry->tevlist) { + tev = &(*tevs)[i++]; + ret = parse_probe_trace_command(node->s, tev); + if (ret < 0) + goto out; + /* Set the uprobes attribute as same as original */ + tev->uprobes = pev->uprobes; + } + ret = i; + +out: + probe_cache__delete(cache); + return ret; +} + static int convert_to_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) { @@ -2866,6 +2922,11 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0) return ret; + /* At first, we need to lookup cache entry */ + ret = find_probe_trace_events_from_cache(pev, tevs); + if (ret > 0) + return ret; /* Found in probe cache */ + if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { ret = find_probe_trace_events_from_map(pev, tevs); if (ret > 0) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 1c12c1ab19c9..a94ee478178d 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -524,7 +524,7 @@ static bool streql(const char *a, const char *b) return !strcmp(a, b); } -static struct probe_cache_entry * +struct probe_cache_entry * probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev) { struct probe_cache_entry *entry = NULL; @@ -548,6 +548,24 @@ found: return entry; } +struct probe_cache_entry * +probe_cache__find_by_name(struct probe_cache *pcache, + const char *group, const char *event) +{ + struct probe_cache_entry *entry = NULL; + + list_for_each_entry(entry, &pcache->entries, node) { + /* Hit if same event name or same command-string */ + if (streql(entry->pev.group, group) && + streql(entry->pev.event, event)) + goto found; + } + entry = NULL; + +found: + return entry; +} + int probe_cache__add_entry(struct probe_cache *pcache, struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs) diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index d872e3df7e59..910aa74953e9 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -38,5 +38,8 @@ int probe_cache__add_entry(struct probe_cache *pcache, int probe_cache__commit(struct probe_cache *pcache); void probe_cache__purge(struct probe_cache *pcache); void probe_cache__delete(struct probe_cache *pcache); - +struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache, + struct perf_probe_event *pev); +struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, + const char *group, const char *event); #endif From 1f3736c9c833e40ac4d3a8dc6d661e341df8a259 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 1 Jul 2016 17:03:26 +0900 Subject: [PATCH 02/16] perf probe: Show all cached probes perf probe --list shows all cached probes when --cache is given. Each caches are shown with on which binary that probed. E.g.: ----- # perf probe --cache vfs_read \$params # perf probe --cache -x /lib64/libc-2.17.so getaddrinfo \$params # perf probe --cache --list [kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1): vfs_read $params /usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc): getaddrinfo $params ----- Note that $params requires debuginfo. Signed-off-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736020674.27797.13488316780383460180.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-probe.txt | 8 +- tools/perf/builtin-probe.c | 2 +- tools/perf/util/build-id.c | 108 +++++++++++++++++++++++- tools/perf/util/build-id.h | 3 + tools/perf/util/probe-event.c | 3 + tools/perf/util/probe-file.c | 66 ++++++++++++++- tools/perf/util/probe-file.h | 1 + 7 files changed, 184 insertions(+), 7 deletions(-) diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 947db6fe512c..5a70d45015ea 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -67,7 +67,10 @@ OPTIONS -l:: --list[=[GROUP:]EVENT]:: - List up current probe events. This can also accept filtering patterns of event names. + List up current probe events. This can also accept filtering patterns of + event names. + When this is used with --cache, perf shows all cached probes instead of + the live probes. -L:: --line=:: @@ -110,8 +113,9 @@ OPTIONS adding and removal operations. --cache:: - Cache the probes (with --add option). Any events which successfully added + (With --add) Cache the probes. Any events which successfully added are also stored in the cache file. + (With --list) Show cached probes. --max-probes=NUM:: Set the maximum number of probe points for an event. Default is 128. diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 34262329f405..0bb9084bf6cf 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -44,7 +44,7 @@ #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*" #define DEFAULT_FUNC_FILTER "!_*" -#define DEFAULT_LIST_FILTER "*:*" +#define DEFAULT_LIST_FILTER "*" /* Session management structure */ static struct { diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 62b147366d01..1c49620e98b2 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -165,8 +165,7 @@ retry: return NULL; } -static char *build_id_cache__linkname(const char *sbuild_id, char *bf, - size_t size) +char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size) { char *tmp = bf; int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir, @@ -176,6 +175,36 @@ static char *build_id_cache__linkname(const char *sbuild_id, char *bf, return bf; } +char *build_id_cache__origname(const char *sbuild_id) +{ + char *linkname; + char buf[PATH_MAX]; + char *ret = NULL, *p; + size_t offs = 5; /* == strlen("../..") */ + + linkname = build_id_cache__linkname(sbuild_id, NULL, 0); + if (!linkname) + return NULL; + + if (readlink(linkname, buf, PATH_MAX) < 0) + goto out; + /* The link should be "../../" */ + p = strrchr(buf, '/'); /* Cut off the "/" */ + if (p && (p > buf + offs)) { + *p = '\0'; + if (buf[offs + 1] == '[') + offs++; /* + * This is a DSO name, like [kernel.kallsyms]. + * Skip the first '/', since this is not the + * cache of a regular file. + */ + ret = strdup(buf + offs); /* Skip "../..[/]" */ + } +out: + free(linkname); + return ret; +} + static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso) { return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf"); @@ -387,6 +416,81 @@ void disable_buildid_cache(void) no_buildid_cache = true; } +static bool lsdir_bid_head_filter(const char *name __maybe_unused, + struct dirent *d __maybe_unused) +{ + return (strlen(d->d_name) == 2) && + isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]); +} + +static bool lsdir_bid_tail_filter(const char *name __maybe_unused, + struct dirent *d __maybe_unused) +{ + int i = 0; + while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3) + i++; + return (i == SBUILD_ID_SIZE - 3) && (d->d_name[i] == '\0'); +} + +struct strlist *build_id_cache__list_all(void) +{ + struct strlist *toplist, *linklist = NULL, *bidlist; + struct str_node *nd, *nd2; + char *topdir, *linkdir = NULL; + char sbuild_id[SBUILD_ID_SIZE]; + + /* Open the top-level directory */ + if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0) + return NULL; + + bidlist = strlist__new(NULL, NULL); + if (!bidlist) + goto out; + + toplist = lsdir(topdir, lsdir_bid_head_filter); + if (!toplist) { + pr_debug("Error in lsdir(%s): %d\n", topdir, errno); + /* If there is no buildid cache, return an empty list */ + if (errno == ENOENT) + goto out; + goto err_out; + } + + strlist__for_each_entry(nd, toplist) { + if (asprintf(&linkdir, "%s/%s", topdir, nd->s) < 0) + goto err_out; + /* Open the lower-level directory */ + linklist = lsdir(linkdir, lsdir_bid_tail_filter); + if (!linklist) { + pr_debug("Error in lsdir(%s): %d\n", linkdir, errno); + goto err_out; + } + strlist__for_each_entry(nd2, linklist) { + if (snprintf(sbuild_id, SBUILD_ID_SIZE, "%s%s", + nd->s, nd2->s) != SBUILD_ID_SIZE - 1) + goto err_out; + if (strlist__add(bidlist, sbuild_id) < 0) + goto err_out; + } + strlist__delete(linklist); + zfree(&linkdir); + } + +out_free: + strlist__delete(toplist); +out: + free(topdir); + + return bidlist; + +err_out: + strlist__delete(linklist); + zfree(&linkdir); + strlist__delete(bidlist); + bidlist = NULL; + goto out_free; +} + char *build_id_cache__cachedir(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso) { diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index d8c7f2fc6a87..b742e271ea2c 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -30,8 +30,11 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); +char *build_id_cache__origname(const char *sbuild_id); +char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); char *build_id_cache__cachedir(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); +struct strlist *build_id_cache__list_all(void); int build_id_cache__list_build_ids(const char *pathname, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 47b6b8b7206e..f81b5dd7f1b1 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2366,6 +2366,9 @@ int show_perf_probe_events(struct strfilter *filter) setup_pager(); + if (probe_conf.cache) + return probe_cache__show_all_caches(filter); + ret = init_probe_symbol_maps(false); if (ret < 0) return ret; diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index a94ee478178d..156e3d883965 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -367,10 +367,17 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) { char cpath[PATH_MAX]; char sbuildid[SBUILD_ID_SIZE]; - char *dir_name; + char *dir_name = NULL; bool is_kallsyms = !target; int ret, fd; + if (target && build_id_cache__cached(target)) { + /* This is a cached buildid */ + strncpy(sbuildid, target, SBUILD_ID_SIZE); + dir_name = build_id_cache__linkname(sbuildid, NULL, 0); + goto found; + } + if (target) ret = filename__sprintf_build_id(target, sbuildid); else { @@ -394,8 +401,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms, false); - if (!dir_name) +found: + if (!dir_name) { + pr_debug("Failed to get cache from %s\n", target); return -ENOMEM; + } snprintf(cpath, PATH_MAX, "%s/probes", dir_name); fd = open(cpath, O_CREAT | O_RDWR, 0644); @@ -673,3 +683,55 @@ int probe_cache__commit(struct probe_cache *pcache) out: return ret; } + +static int probe_cache__show_entries(struct probe_cache *pcache, + struct strfilter *filter) +{ + struct probe_cache_entry *entry; + char buf[128], *ptr; + + list_for_each_entry(entry, &pcache->entries, node) { + if (entry->pev.event) { + ptr = buf; + snprintf(buf, 128, "%s:%s", + entry->pev.group, entry->pev.event); + } else + ptr = entry->spev; + if (strfilter__compare(filter, ptr)) + printf("%s\n", entry->spev); + } + return 0; +} + +/* Show all cached probes */ +int probe_cache__show_all_caches(struct strfilter *filter) +{ + struct probe_cache *pcache; + struct strlist *bidlist; + struct str_node *nd; + char *buf = strfilter__string(filter); + + pr_debug("list cache with filter: %s\n", buf); + free(buf); + + bidlist = build_id_cache__list_all(); + if (!bidlist) { + pr_debug("Failed to get buildids: %d\n", errno); + return -EINVAL; + } + strlist__for_each_entry(nd, bidlist) { + pcache = probe_cache__new(nd->s); + if (!pcache) + continue; + if (!list_empty(&pcache->entries)) { + buf = build_id_cache__origname(nd->s); + printf("%s (%s):\n", buf, nd->s); + free(buf); + probe_cache__show_entries(pcache, filter); + } + probe_cache__delete(pcache); + } + strlist__delete(bidlist); + + return 0; +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 910aa74953e9..0009b8a65a5c 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -42,4 +42,5 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev); struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, const char *group, const char *event); +int probe_cache__show_all_caches(struct strfilter *filter); #endif From 4a0f65c102ec3a718b4a0b90981232b6cb019477 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 1 Jul 2016 17:03:36 +0900 Subject: [PATCH 03/16] perf probe: Remove caches when --cache is given 'perf probe --del' removes caches when '--cache' is given. Note that the delete pattern is not the same as for normal events. If you cached probes with event name, --del "eventname" works as expected. However, if you skipped it, the cached probes doesn't have actual event name. In that case --del "probe-desc" is required (wildcard is acceptable). For example a cache entry has the probe-desc "vfs_read $params", you can remove it with --del 'vfs_read*'. ----- # perf probe --cache --list /[kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1): vfs_read $params /usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc): getaddrinfo $params # perf probe --cache --del vfs_read\* Removed cached event: probe:vfs_read # perf probe --cache --list /[kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1): /usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc): getaddrinfo $params ----- Signed-off-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736021651.27797.10250879847070772920.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-probe.txt | 1 + tools/perf/builtin-probe.c | 29 ++++++++++++++++++++ tools/perf/util/probe-file.c | 36 +++++++++++++++++++------ tools/perf/util/probe-file.h | 2 ++ 4 files changed, 60 insertions(+), 8 deletions(-) diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 5a70d45015ea..8d091734d02c 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -116,6 +116,7 @@ OPTIONS (With --add) Cache the probes. Any events which successfully added are also stored in the cache file. (With --list) Show cached probes. + (With --del) Remove cached probes. --max-probes=NUM:: Set the maximum number of probe points for an event. Default is 128. diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 0bb9084bf6cf..a1a5cd1b8d60 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -363,6 +363,32 @@ out_cleanup: return ret; } +static int del_perf_probe_caches(struct strfilter *filter) +{ + struct probe_cache *cache; + struct strlist *bidlist; + struct str_node *nd; + int ret; + + bidlist = build_id_cache__list_all(); + if (!bidlist) { + ret = -errno; + pr_debug("Failed to get buildids: %d\n", ret); + return ret ?: -ENOMEM; + } + + strlist__for_each_entry(nd, bidlist) { + cache = probe_cache__new(nd->s); + if (!cache) + continue; + if (probe_cache__filter_purge(cache, filter) < 0 || + probe_cache__commit(cache) < 0) + pr_warning("Failed to remove entries for %s\n", nd->s); + probe_cache__delete(cache); + } + return 0; +} + static int perf_del_probe_events(struct strfilter *filter) { int ret, ret2, ufd = -1, kfd = -1; @@ -375,6 +401,9 @@ static int perf_del_probe_events(struct strfilter *filter) pr_debug("Delete filter: \'%s\'\n", str); + if (probe_conf.cache) + return del_perf_probe_caches(filter); + /* Get current event names */ ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW); if (ret < 0) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 156e3d883965..6cb6ec03c1fe 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -684,20 +684,40 @@ out: return ret; } +static bool probe_cache_entry__compare(struct probe_cache_entry *entry, + struct strfilter *filter) +{ + char buf[128], *ptr = entry->spev; + + if (entry->pev.event) { + snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event); + ptr = buf; + } + return strfilter__compare(filter, ptr); +} + +int probe_cache__filter_purge(struct probe_cache *pcache, + struct strfilter *filter) +{ + struct probe_cache_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &pcache->entries, node) { + if (probe_cache_entry__compare(entry, filter)) { + pr_info("Removed cached event: %s\n", entry->spev); + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } + } + return 0; +} + static int probe_cache__show_entries(struct probe_cache *pcache, struct strfilter *filter) { struct probe_cache_entry *entry; - char buf[128], *ptr; list_for_each_entry(entry, &pcache->entries, node) { - if (entry->pev.event) { - ptr = buf; - snprintf(buf, 128, "%s:%s", - entry->pev.group, entry->pev.event); - } else - ptr = entry->spev; - if (strfilter__compare(filter, ptr)) + if (probe_cache_entry__compare(entry, filter)) printf("%s\n", entry->spev); } return 0; diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 0009b8a65a5c..0ed1fc563b77 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -38,6 +38,8 @@ int probe_cache__add_entry(struct probe_cache *pcache, int probe_cache__commit(struct probe_cache *pcache); void probe_cache__purge(struct probe_cache *pcache); void probe_cache__delete(struct probe_cache *pcache); +int probe_cache__filter_purge(struct probe_cache *pcache, + struct strfilter *filter); struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev); struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, From 2492c465ad3ae6860ebfff1c9032865017835e70 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Jul 2016 19:35:47 -0300 Subject: [PATCH 04/16] perf build: Add feature detection for libelf's elf_getshdrstrndx() That appeared after 0.140, and will be used in the SDT code, so, to avoid bisection break on older systems, add a feature detection and provide a stub with a pr_debug() to keep it building. Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-80y0eldgweorqnwha9rvfxjr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-all.c | 5 +++++ tools/build/feature/test-libelf-getshdrstrndx.c | 8 ++++++++ tools/perf/config/Makefile | 4 ++++ tools/perf/util/symbol-elf.c | 8 ++++++++ 6 files changed, 30 insertions(+) create mode 100644 tools/build/feature/test-libelf-getshdrstrndx.c diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 57c8f98874e8..3dd529bb0604 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -40,6 +40,7 @@ FEATURE_TESTS_BASIC := \ libbfd \ libelf \ libelf-getphdrnum \ + libelf-getshdrstrndx \ libelf-mmap \ libnuma \ numa_num_possible_cpus \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 3d88f09e188b..674711629ef0 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -17,6 +17,7 @@ FILES= \ test-cplus-demangle.bin \ test-libelf.bin \ test-libelf-getphdrnum.bin \ + test-libelf-getshdrstrndx.bin \ test-libelf-mmap.bin \ test-libnuma.bin \ test-numa_num_possible_cpus.bin \ @@ -98,6 +99,9 @@ $(OUTPUT)test-libelf-mmap.bin: $(OUTPUT)test-libelf-getphdrnum.bin: $(BUILD) -lelf +$(OUTPUT)test-libelf-getshdrstrndx.bin: + $(BUILD) -lelf + $(OUTPUT)test-libnuma.bin: $(BUILD) -lnuma diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index a282e8cb84f3..7433cca33306 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -49,6 +49,10 @@ # include "test-libelf-getphdrnum.c" #undef main +#define main main_test_libelf_getshdrstrndx +# include "test-libelf-getshdrstrndx.c" +#undef main + #define main main_test_libunwind # include "test-libunwind.c" #undef main @@ -149,6 +153,7 @@ int main(int argc, char *argv[]) main_test_dwarf(); main_test_dwarf_getlocations(); main_test_libelf_getphdrnum(); + main_test_libelf_getshdrstrndx(); main_test_libunwind(); main_test_libaudit(); main_test_libslang(); diff --git a/tools/build/feature/test-libelf-getshdrstrndx.c b/tools/build/feature/test-libelf-getshdrstrndx.c new file mode 100644 index 000000000000..f0c3b47cce28 --- /dev/null +++ b/tools/build/feature/test-libelf-getshdrstrndx.c @@ -0,0 +1,8 @@ +#include + +int main(void) +{ + size_t dst; + + return elf_getshdrstrndx(0, &dst); +} diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index bf1a0a0dd0ad..c7e269a7ca37 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -309,6 +309,10 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT endif + ifeq ($(feature-libelf-getshdrstrndx), 1) + CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT + endif + ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 87a297dd8901..b222552c7159 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -54,6 +54,14 @@ static int elf_getphdrnum(Elf *elf, size_t *dst) } #endif +#ifndef HAVE_ELF_GETSHDRSTRNDX_SUPPORT +static int elf_getshdrstrndx(Elf *elf __maybe_unused, size_t *dst __maybe_unused) +{ + pr_err("%s: update your libelf to > 0.140, this one lacks elf_getshdrstrndx().\n", __func__); + return -1; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif From 060fa0c7a3e0bb4f1426ee79dfd38e2a4c80067a Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Fri, 1 Jul 2016 17:03:46 +0900 Subject: [PATCH 05/16] perf sdt: ELF support for SDT This patch serves the initial support to identify and list SDT events in binaries. When programs containing SDT markers are compiled, gcc with the help of assembler directives identifies them and places them in the section ".note.stapsdt". To find these markers from the binaries, one needs to traverse through this section and parse the relevant details like the name, type and location of the marker. Also, the original location could be skewed due to the effect of prelinking. If that is the case, the locations need to be adjusted. The functions in this patch open a given ELF, find out the SDT section, parse the relevant details, adjust the location (if necessary) and populate them in a list. A typical note entry in ".note.stapsdt" section is as follows : |--nhdr.n_namesz--| ------------------------------------ | nhdr | "stapsdt" | ----- |----------------------------------| | | | | | | nhdr.n_descsize | "provider_name" "note_name" | | | | ----- |----------------------------------| | nhdr | "stapsdt" | |... The above shows an excerpt from the section ".note.stapsdt". 'nhdr' is a structure which has the note name size (n_namesz), note description size (n_desc_sz) and note type (n_type). So, in order to parse the note note info, we need nhdr to tell us where to start from. As can be seen from , the name of the SDT notes given is "stapsdt". But this is not the identifier of the note. After that, we go to description of the note to find out its location, the address of the ".stapsdt.base" section and the semaphore address. Then, we find the provider name and the SDT marker name and then follow the arguments. Signed-off-by: Hemant Kumar Reviewed-by: Masami Hiramatsu Acked-by: Namhyung Kim Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736022628.27797.1201368329092908163.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 252 +++++++++++++++++++++++++++++++++++ tools/perf/util/symbol.h | 22 +++ 2 files changed, 274 insertions(+) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b222552c7159..6f15b92cbf70 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1789,6 +1789,258 @@ void kcore_extract__delete(struct kcore_extract *kce) unlink(kce->extract_filename); } +/** + * populate_sdt_note : Parse raw data and identify SDT note + * @elf: elf of the opened file + * @data: raw data of a section with description offset applied + * @len: note description size + * @type: type of the note + * @sdt_notes: List to add the SDT note + * + * Responsible for parsing the @data in section .note.stapsdt in @elf and + * if its an SDT note, it appends to @sdt_notes list. + */ +static int populate_sdt_note(Elf **elf, const char *data, size_t len, + struct list_head *sdt_notes) +{ + const char *provider, *name; + struct sdt_note *tmp = NULL; + GElf_Ehdr ehdr; + GElf_Addr base_off = 0; + GElf_Shdr shdr; + int ret = -EINVAL; + + union { + Elf64_Addr a64[NR_ADDR]; + Elf32_Addr a32[NR_ADDR]; + } buf; + + Elf_Data dst = { + .d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT, + .d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT), + .d_off = 0, .d_align = 0 + }; + Elf_Data src = { + .d_buf = (void *) data, .d_type = ELF_T_ADDR, + .d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0, + .d_align = 0 + }; + + tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note)); + if (!tmp) { + ret = -ENOMEM; + goto out_err; + } + + INIT_LIST_HEAD(&tmp->note_list); + + if (len < dst.d_size + 3) + goto out_free_note; + + /* Translation from file representation to memory representation */ + if (gelf_xlatetom(*elf, &dst, &src, + elf_getident(*elf, NULL)[EI_DATA]) == NULL) { + pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1)); + goto out_free_note; + } + + /* Populate the fields of sdt_note */ + provider = data + dst.d_size; + + name = (const char *)memchr(provider, '\0', data + len - provider); + if (name++ == NULL) + goto out_free_note; + + tmp->provider = strdup(provider); + if (!tmp->provider) { + ret = -ENOMEM; + goto out_free_note; + } + tmp->name = strdup(name); + if (!tmp->name) { + ret = -ENOMEM; + goto out_free_prov; + } + + if (gelf_getclass(*elf) == ELFCLASS32) { + memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr)); + tmp->bit32 = true; + } else { + memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr)); + tmp->bit32 = false; + } + + if (!gelf_getehdr(*elf, &ehdr)) { + pr_debug("%s : cannot get elf header.\n", __func__); + ret = -EBADF; + goto out_free_name; + } + + /* Adjust the prelink effect : + * Find out the .stapsdt.base section. + * This scn will help us to handle prelinking (if present). + * Compare the retrieved file offset of the base section with the + * base address in the description of the SDT note. If its different, + * then accordingly, adjust the note location. + */ + if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) { + base_off = shdr.sh_offset; + if (base_off) { + if (tmp->bit32) + tmp->addr.a32[0] = tmp->addr.a32[0] + base_off - + tmp->addr.a32[1]; + else + tmp->addr.a64[0] = tmp->addr.a64[0] + base_off - + tmp->addr.a64[1]; + } + } + + list_add_tail(&tmp->note_list, sdt_notes); + return 0; + +out_free_name: + free(tmp->name); +out_free_prov: + free(tmp->provider); +out_free_note: + free(tmp); +out_err: + return ret; +} + +/** + * construct_sdt_notes_list : constructs a list of SDT notes + * @elf : elf to look into + * @sdt_notes : empty list_head + * + * Scans the sections in 'elf' for the section + * .note.stapsdt. It, then calls populate_sdt_note to find + * out the SDT events and populates the 'sdt_notes'. + */ +static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes) +{ + GElf_Ehdr ehdr; + Elf_Scn *scn = NULL; + Elf_Data *data; + GElf_Shdr shdr; + size_t shstrndx, next; + GElf_Nhdr nhdr; + size_t name_off, desc_off, offset; + int ret = 0; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + ret = -EBADF; + goto out_ret; + } + if (elf_getshdrstrndx(elf, &shstrndx) != 0) { + ret = -EBADF; + goto out_ret; + } + + /* Look for the required section */ + scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL); + if (!scn) { + ret = -ENOENT; + goto out_ret; + } + + if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) { + ret = -ENOENT; + goto out_ret; + } + + data = elf_getdata(scn, NULL); + + /* Get the SDT notes */ + for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off, + &desc_off)) > 0; offset = next) { + if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) && + !memcmp(data->d_buf + name_off, SDT_NOTE_NAME, + sizeof(SDT_NOTE_NAME))) { + /* Check the type of the note */ + if (nhdr.n_type != SDT_NOTE_TYPE) + goto out_ret; + + ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off), + nhdr.n_descsz, sdt_notes); + if (ret < 0) + goto out_ret; + } + } + if (list_empty(sdt_notes)) + ret = -ENOENT; + +out_ret: + return ret; +} + +/** + * get_sdt_note_list : Wrapper to construct a list of sdt notes + * @head : empty list_head + * @target : file to find SDT notes from + * + * This opens the file, initializes + * the ELF and then calls construct_sdt_notes_list. + */ +int get_sdt_note_list(struct list_head *head, const char *target) +{ + Elf *elf; + int fd, ret; + + fd = open(target, O_RDONLY); + if (fd < 0) + return -EBADF; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (!elf) { + ret = -EBADF; + goto out_close; + } + ret = construct_sdt_notes_list(elf, head); + elf_end(elf); +out_close: + close(fd); + return ret; +} + +/** + * cleanup_sdt_note_list : free the sdt notes' list + * @sdt_notes: sdt notes' list + * + * Free up the SDT notes in @sdt_notes. + * Returns the number of SDT notes free'd. + */ +int cleanup_sdt_note_list(struct list_head *sdt_notes) +{ + struct sdt_note *tmp, *pos; + int nr_free = 0; + + list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) { + list_del(&pos->note_list); + free(pos->name); + free(pos->provider); + free(pos); + nr_free++; + } + return nr_free; +} + +/** + * sdt_notes__get_count: Counts the number of sdt events + * @start: list_head to sdt_notes list + * + * Returns the number of SDT notes in a list + */ +int sdt_notes__get_count(struct list_head *start) +{ + struct sdt_note *sdt_ptr; + int count = 0; + + list_for_each_entry(sdt_ptr, start, note_list) + count++; + return count; +} + void symbol__elf_init(void) { elf_version(EV_CURRENT); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index b10d558a8803..699f7cbcfe72 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -342,4 +342,26 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym); int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb); +/* structure containing an SDT note's info */ +struct sdt_note { + char *name; /* name of the note*/ + char *provider; /* provider name */ + bool bit32; /* whether the location is 32 bits? */ + union { /* location, base and semaphore addrs */ + Elf64_Addr a64[3]; + Elf32_Addr a32[3]; + } addr; + struct list_head note_list; /* SDT notes' list */ +}; + +int get_sdt_note_list(struct list_head *head, const char *target); +int cleanup_sdt_note_list(struct list_head *sdt_notes); +int sdt_notes__get_count(struct list_head *start); + +#define SDT_BASE_SCN ".stapsdt.base" +#define SDT_NOTE_SCN ".note.stapsdt" +#define SDT_NOTE_TYPE 3 +#define SDT_NOTE_NAME "stapsdt" +#define NR_ADDR 3 + #endif /* __PERF_SYMBOL */ From 8d993d96901f55d26e083390aae80fd02cbff7aa Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 1 Jul 2016 17:04:01 +0900 Subject: [PATCH 06/16] perf probe: Add group name support Allow user to set group name for adding new event. Note that user must ensure that the group name doesn't conflict with existing group name carefully. E.g. Existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide kernel embedded events when loading modules. Signed-off-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736024091.27797.9471545190066268995.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-probe.txt | 10 ++++++---- tools/perf/util/probe-event.c | 23 ++++++++++++++--------- 2 files changed, 20 insertions(+), 13 deletions(-) diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 8d091734d02c..7a258e953252 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -143,16 +143,18 @@ PROBE SYNTAX Probe points are defined by following syntax. 1) Define event based on function name - [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...] + [[GROUP:]EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...] 2) Define event based on source file with line number - [EVENT=]SRC:ALN [ARG ...] + [[GROUP:]EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern - [EVENT=]SRC;PTN [ARG ...] + [[GROUP:]EVENT=]SRC;PTN [ARG ...] -'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'. +'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_' is used for uprobe. +Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the +modules. 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function. It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern. 'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT). diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index f81b5dd7f1b1..0201f661ccb8 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1206,10 +1206,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) bool file_spec = false; /* * - * perf probe [EVENT=]SRC[:LN|;PTN] - * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT] - * - * TODO:Group name support + * perf probe [GRP:][EVENT=]SRC[:LN|;PTN] + * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT] */ if (!arg) return -EINVAL; @@ -1218,11 +1216,19 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) if (ptr && *ptr == '=') { /* Event name */ *ptr = '\0'; tmp = ptr + 1; - if (strchr(arg, ':')) { - semantic_error("Group name is not supported yet.\n"); - return -ENOTSUP; - } + ptr = strchr(arg, ':'); + if (ptr) { + *ptr = '\0'; + if (!is_c_func_name(arg)) + goto not_fname; + pev->group = strdup(arg); + if (!pev->group) + return -ENOMEM; + arg = ptr + 1; + } else + pev->group = NULL; if (!is_c_func_name(arg)) { +not_fname: semantic_error("%s is bad for event name -it must " "follow C symbol-naming rule.\n", arg); return -EINVAL; @@ -1230,7 +1236,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) pev->event = strdup(arg); if (pev->event == NULL) return -ENOMEM; - pev->group = NULL; arg = tmp; } From 6430a94ead2a4c8f350441351a735303eb6d1c8a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 1 Jul 2016 17:04:10 +0900 Subject: [PATCH 07/16] perf buildid-cache: Scan and import user SDT events to probe cache perf buildid-cache --add scans given binary and add the SDT events to probe cache. "sdt_" prefix is appended for all SDT providers to avoid event-name clash with other pre-defined events. It is possible to use the cached SDT events as other cached events, via perf probe --add "sdt_:=". e.g. ---- # perf buildid-cache --add /lib/libc-2.17.so # perf probe --cache --list | head -n 5 /usr/lib/libc-2.17.so (a6fb821bdf53660eb2c29f778757aef294d3d392): sdt_libc:setjmp=setjmp sdt_libc:longjmp=longjmp sdt_libc:longjmp_target=longjmp_target sdt_libc:memory_heap_new=memory_heap_new # perf probe -x /usr/lib/libc-2.17.so \ -a sdt_libc:memory_heap_new=memory_heap_new Added new event: sdt_libc:memory_heap_new (on memory_heap_new in /usr/lib/libc-2.17.so) You can now use it in all perf tools, such as: perf record -e sdt_libc:memory_heap_new -aR sleep 1 # perf probe -l sdt_libc:memory_heap_new (on new_heap+183 in /usr/lib/libc-2.17.so) ---- Note that SDT event entries in probe-cache file is somewhat different from normal cached events. Normal one starts with "#", but SDTs are starting with "%". Signed-off-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/146736025058.27797.13043265488541434502.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/Documentation/perf-buildid-cache.txt | 3 + tools/perf/util/build-id.c | 30 ++++++++ tools/perf/util/probe-file.c | 69 ++++++++++++++++++- tools/perf/util/probe-file.h | 2 + 4 files changed, 101 insertions(+), 3 deletions(-) diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index dd07b55f58d8..058064db39d2 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -15,6 +15,9 @@ DESCRIPTION This command manages the build-id cache. It can add, remove, update and purge files to/from the cache. In the future it should as well set upper limits for the space used by the cache, etc. +This also scans the target binary for SDT (Statically Defined Tracing) and +record it along with the buildid-cache, which will be used by perf-probe. +For more details, see linkperf:perf-probe[1]. OPTIONS ------- diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 1c49620e98b2..e1a16408da9c 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -17,6 +17,7 @@ #include "tool.h" #include "header.h" #include "vdso.h" +#include "probe-file.h" static bool no_buildid_cache; @@ -532,6 +533,30 @@ int build_id_cache__list_build_ids(const char *pathname, return ret; } +#ifdef HAVE_LIBELF_SUPPORT +static int build_id_cache__add_sdt_cache(const char *sbuild_id, + const char *realname) +{ + struct probe_cache *cache; + int ret; + + cache = probe_cache__new(sbuild_id); + if (!cache) + return -1; + + ret = probe_cache__scan_sdt(cache, realname); + if (ret >= 0) { + pr_debug("Found %d SDTs in %s\n", ret, realname); + if (probe_cache__commit(cache) < 0) + ret = -1; + } + probe_cache__delete(cache); + return ret; +} +#else +#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0) +#endif + int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso) { @@ -589,6 +614,11 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, if (symlink(tmp, linkname) == 0) err = 0; + + /* Update SDT cache : error is just warned */ + if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + pr_debug("Failed to update/scan SDT cache for %s\n", realname); + out_free: if (!is_kallsyms) free(realname); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 6cb6ec03c1fe..5b563b2e8b1d 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -434,12 +434,15 @@ static int probe_cache__load(struct probe_cache *pcache) p = strchr(buf, '\n'); if (p) *p = '\0'; - if (buf[0] == '#') { /* #perf_probe_event */ + /* #perf_probe_event or %sdt_event */ + if (buf[0] == '#' || buf[0] == '%') { entry = probe_cache_entry__new(NULL); if (!entry) { ret = -ENOMEM; goto out; } + if (buf[0] == '%') + entry->sdt = true; entry->spev = strdup(buf + 1); if (entry->spev) ret = parse_perf_probe_command(buf + 1, @@ -621,19 +624,79 @@ out_err: return ret; } +static unsigned long long sdt_note__get_addr(struct sdt_note *note) +{ + return note->bit32 ? (unsigned long long)note->addr.a32[0] + : (unsigned long long)note->addr.a64[0]; +} + +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) +{ + struct probe_cache_entry *entry = NULL; + struct list_head sdtlist; + struct sdt_note *note; + char *buf; + char sdtgrp[64]; + int ret; + + INIT_LIST_HEAD(&sdtlist); + ret = get_sdt_note_list(&sdtlist, pathname); + if (ret < 0) { + pr_debug("Failed to get sdt note: %d\n", ret); + return ret; + } + list_for_each_entry(note, &sdtlist, note_list) { + ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider); + if (ret < 0) + break; + /* Try to find same-name entry */ + entry = probe_cache__find_by_name(pcache, sdtgrp, note->name); + if (!entry) { + entry = probe_cache_entry__new(NULL); + if (!entry) { + ret = -ENOMEM; + break; + } + entry->sdt = true; + ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp, + note->name, note->name); + if (ret < 0) + break; + entry->pev.event = strdup(note->name); + entry->pev.group = strdup(sdtgrp); + list_add_tail(&entry->node, &pcache->entries); + } + ret = asprintf(&buf, "p:%s/%s %s:0x%llx", + sdtgrp, note->name, pathname, + sdt_note__get_addr(note)); + if (ret < 0) + break; + strlist__add(entry->tevlist, buf); + free(buf); + entry = NULL; + } + if (entry) { + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } + cleanup_sdt_note_list(&sdtlist); + return ret; +} + static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd) { struct str_node *snode; struct stat st; struct iovec iov[3]; + const char *prefix = entry->sdt ? "%" : "#"; int ret; /* Save stat for rollback */ ret = fstat(fd, &st); if (ret < 0) return ret; - pr_debug("Writing cache: #%s\n", entry->spev); - iov[0].iov_base = (void *)"#"; iov[0].iov_len = 1; + pr_debug("Writing cache: %s%s\n", prefix, entry->spev); + iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1; iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev); iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1; ret = writev(fd, iov, 3); diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 0ed1fc563b77..ddf5ae212c2f 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -8,6 +8,7 @@ /* Cache of probe definitions */ struct probe_cache_entry { struct list_head node; + bool sdt; struct perf_probe_event pev; char *spev; struct strlist *tevlist; @@ -35,6 +36,7 @@ struct probe_cache *probe_cache__new(const char *target); int probe_cache__add_entry(struct probe_cache *pcache, struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs); +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname); int probe_cache__commit(struct probe_cache *pcache); void probe_cache__purge(struct probe_cache *pcache); void probe_cache__delete(struct probe_cache *pcache); From c60da22aca8755b77b7f4d4caf57ada8654db939 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Jul 2016 14:16:20 +0200 Subject: [PATCH 08/16] perf header: Transform nodes string info to struct Storing NUMA info within struct numa_node instead of strings. This way it's usable in future patches. Also it turned out it's slightly less code involved than using strings. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467634583-29147-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 5 ++- tools/perf/util/env.h | 10 +++++- tools/perf/util/header.c | 76 ++++++++++++++-------------------------- 3 files changed, 39 insertions(+), 52 deletions(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 49a11d9d8b8f..bb964e86b09d 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -18,10 +18,13 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cmdline_argv); zfree(&env->sibling_cores); zfree(&env->sibling_threads); - zfree(&env->numa_nodes); zfree(&env->pmu_mappings); zfree(&env->cpu); + for (i = 0; i < env->nr_numa_nodes; i++) + cpu_map__put(env->numa_nodes[i].map); + zfree(&env->numa_nodes); + for (i = 0; i < env->caches_cnt; i++) cpu_cache_level__free(&env->caches[i]); zfree(&env->caches); diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 56cffb60a0b4..b164dfd2dcbf 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -2,6 +2,7 @@ #define __PERF_ENV_H #include +#include "cpumap.h" struct cpu_topology_map { int socket_id; @@ -18,6 +19,13 @@ struct cpu_cache_level { char *map; }; +struct numa_node { + u32 node; + u64 mem_total; + u64 mem_free; + struct cpu_map *map; +}; + struct perf_env { char *hostname; char *os_release; @@ -40,11 +48,11 @@ struct perf_env { const char **cmdline_argv; char *sibling_cores; char *sibling_threads; - char *numa_nodes; char *pmu_mappings; struct cpu_topology_map *cpu; struct cpu_cache_level *caches; int caches_cnt; + struct numa_node *numa_nodes; }; extern struct perf_env perf_env; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index c5cd2698281f..8f0db4007282 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1306,42 +1306,19 @@ static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { - u32 nr, c, i; - char *str, *tmp; - uint64_t mem_total, mem_free; + int i; + struct numa_node *n; - /* nr nodes */ - nr = ph->env.nr_numa_nodes; - str = ph->env.numa_nodes; - - for (i = 0; i < nr; i++) { - /* node number */ - c = strtoul(str, &tmp, 0); - if (*tmp != ':') - goto error; - - str = tmp + 1; - mem_total = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; - - str = tmp + 1; - mem_free = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; + for (i = 0; i < ph->env.nr_numa_nodes; i++) { + n = &ph->env.numa_nodes[i]; fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," " free = %"PRIu64" kB\n", - c, mem_total, mem_free); + n->node, n->mem_total, n->mem_free); - str = tmp + 1; - fprintf(fp, "# node%u cpu list : %s\n", c, str); - - str += strlen(str) + 1; + fprintf(fp, "# node%u cpu list : ", n->node); + cpu_map__fprintf(n->map, fp); } - return; -error: - fprintf(fp, "# numa topology : not available\n"); } static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) @@ -1906,11 +1883,10 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse struct perf_header *ph, int fd, void *data __maybe_unused) { + struct numa_node *nodes, *n; ssize_t ret; - u32 nr, node, i; + u32 nr, i; char *str; - uint64_t mem_total, mem_free; - struct strbuf sb; /* nr nodes */ ret = readn(fd, &nr, sizeof(nr)); @@ -1921,47 +1897,47 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse nr = bswap_32(nr); ph->env.nr_numa_nodes = nr; - if (strbuf_init(&sb, 256) < 0) - return -1; + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -ENOMEM; for (i = 0; i < nr; i++) { + n = &nodes[i]; + /* node number */ - ret = readn(fd, &node, sizeof(node)); - if (ret != sizeof(node)) + ret = readn(fd, &n->node, sizeof(u32)); + if (ret != sizeof(n->node)) goto error; - ret = readn(fd, &mem_total, sizeof(u64)); + ret = readn(fd, &n->mem_total, sizeof(u64)); if (ret != sizeof(u64)) goto error; - ret = readn(fd, &mem_free, sizeof(u64)); + ret = readn(fd, &n->mem_free, sizeof(u64)); if (ret != sizeof(u64)) goto error; if (ph->needs_swap) { - node = bswap_32(node); - mem_total = bswap_64(mem_total); - mem_free = bswap_64(mem_free); + n->node = bswap_32(n->node); + n->mem_total = bswap_64(n->mem_total); + n->mem_free = bswap_64(n->mem_free); } - if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", - node, mem_total, mem_free) < 0) - goto error; - str = do_read_string(fd, ph); if (!str) goto error; - /* include a NULL character at the end */ - if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + n->map = cpu_map__new(str); + if (!n->map) goto error; + free(str); } - ph->env.numa_nodes = strbuf_detach(&sb, NULL); + ph->env.numa_nodes = nodes; return 0; error: - strbuf_release(&sb); + free(nodes); return -1; } From 347ca878062d5fb0e16db1fae81b0994f2457efd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Jul 2016 14:16:21 +0200 Subject: [PATCH 09/16] perf tests: Fix hist accumulation test User's values from .perfconfig could overload the default callchain setup and cause this test to fail. Making sure the test is using default callchain_param values. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467634583-29147-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/hists_cumulate.c | 4 ++++ tools/perf/util/callchain.h | 1 + tools/perf/util/util.c | 19 +++++++++++++------ 3 files changed, 18 insertions(+), 6 deletions(-) diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index a9e3db3afac4..9fd54b79a788 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -216,6 +216,8 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec /* check callchain entries */ root = &he->callchain->node.rb_root; + + TEST_ASSERT_VAL("callchains expected", !RB_EMPTY_ROOT(root)); cnode = rb_entry(rb_first(root), struct callchain_node, rb_node); c = 0; @@ -666,6 +668,8 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) perf_evsel__set_sample_bit(evsel, CALLCHAIN); setup_sorting(NULL); + + callchain_param = callchain_param_default; callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index a70f6b54eb92..13e75549c440 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -106,6 +106,7 @@ struct callchain_param { }; extern struct callchain_param callchain_param; +extern struct callchain_param callchain_param_default; struct callchain_list { u64 ip; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index e08b9a092a23..5f44a21955cd 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -19,12 +19,19 @@ #include "callchain.h" #include "strlist.h" -struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_ABS, - .min_percent = 0.5, - .order = ORDER_CALLEE, - .key = CCKEY_FUNCTION, - .value = CCVAL_PERCENT, +#define CALLCHAIN_PARAM_DEFAULT \ + .mode = CHAIN_GRAPH_ABS, \ + .min_percent = 0.5, \ + .order = ORDER_CALLEE, \ + .key = CCKEY_FUNCTION, \ + .value = CCVAL_PERCENT, \ + +struct callchain_param callchain_param = { + CALLCHAIN_PARAM_DEFAULT +}; + +struct callchain_param callchain_param_default = { + CALLCHAIN_PARAM_DEFAULT }; /* From a2873325ffb21cecca8032673eb698cb4d778dc6 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Jul 2016 14:16:22 +0200 Subject: [PATCH 10/16] perf unwind: Add initialized arg into unwind__prepare_access Adding initialized arg into unwind__prepare_access to get feedback about the initialization state. It's not possible to get it from error code, because we return 0 even in case we don't recognize dso, which is valid. The 'initialized' value is used in following patch to speedup unwind__prepare_access calls logic in fork path. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: He Kuang Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467634583-29147-4-git-send-email-jolsa@kernel.org [ Remove ; after static inline function signatures, fixes build break ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 2 +- tools/perf/util/unwind-libunwind.c | 11 +++++++++-- tools/perf/util/unwind.h | 9 ++++++--- 3 files changed, 16 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index f30f9566fddc..2439b122a4e4 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -202,7 +202,7 @@ int thread__insert_map(struct thread *thread, struct map *map) { int ret; - ret = unwind__prepare_access(thread, map); + ret = unwind__prepare_access(thread, map, NULL); if (ret) return ret; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 854711966cad..6d542a4e0648 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -14,15 +14,19 @@ static void unwind__register_ops(struct thread *thread, thread->unwind_libunwind_ops = ops; } -int unwind__prepare_access(struct thread *thread, struct map *map) +int unwind__prepare_access(struct thread *thread, struct map *map, + bool *initialized) { const char *arch; enum dso_type dso_type; struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; + int err; if (thread->addr_space) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); + if (initialized) + *initialized = true; return 0; } @@ -51,7 +55,10 @@ int unwind__prepare_access(struct thread *thread, struct map *map) out_register: unwind__register_ops(thread, ops); - return thread->unwind_libunwind_ops->prepare_access(thread); + err = thread->unwind_libunwind_ops->prepare_access(thread); + if (initialized) + *initialized = err ? false : true; + return err; } void unwind__flush_access(struct thread *thread) diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 84c6d44d52f9..61fb1e90ff51 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -42,12 +42,14 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, #endif int LIBUNWIND__ARCH_REG_ID(int regnum); -int unwind__prepare_access(struct thread *thread, struct map *map); +int unwind__prepare_access(struct thread *thread, struct map *map, + bool *initialized); void unwind__flush_access(struct thread *thread); void unwind__finish_access(struct thread *thread); #else static inline int unwind__prepare_access(struct thread *thread __maybe_unused, - struct map *map __maybe_unused) + struct map *map __maybe_unused, + bool *initialized __maybe_unused) { return 0; } @@ -67,7 +69,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, } static inline int unwind__prepare_access(struct thread *thread __maybe_unused, - struct map *map __maybe_unused) + struct map *map __maybe_unused, + bool *initialized __maybe_unused) { return 0; } From 6c502584438bda63fc1a67606854fb0b300465cd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Jul 2016 14:16:23 +0200 Subject: [PATCH 11/16] perf unwind: Call unwind__prepare_access for forked thread Currently we call unwind__prepare_access for map event. In case we report fork event the thread inherits its parent's maps and unwind__prepare_access is never called for the thread. This causes unwind__get_entries seeing uninitialized unwind_libunwind_ops and thus returning no callchain. Adding unwind__prepare_access calls for fork even processing. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: He Kuang Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467634583-29147-5-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 9 ++++++++- tools/perf/util/map.h | 2 +- tools/perf/util/thread.c | 37 +++++++++++++++++++++++++++++++++++-- 3 files changed, 44 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index b19bcd3b7128..b39b12a1208d 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -15,6 +15,7 @@ #include "debug.h" #include "machine.h" #include +#include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -744,9 +745,10 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct map_groups *mg, +int map_groups__clone(struct thread *thread, struct map_groups *parent, enum map_type type) { + struct map_groups *mg = thread->mg; int err = -ENOMEM; struct map *map; struct maps *maps = &parent->maps[type]; @@ -757,6 +759,11 @@ int map_groups__clone(struct map_groups *mg, struct map *new = map__clone(map); if (new == NULL) goto out_unlock; + + err = unwind__prepare_access(thread, new, NULL); + if (err) + goto out_unlock; + map_groups__insert(mg, new); map__put(new); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 7309d64ce39e..d83396ceecba 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -194,7 +194,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp, symbol_filter_t filter); void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); -int map_groups__clone(struct map_groups *mg, +int map_groups__clone(struct thread *thread, struct map_groups *parent, enum map_type type); size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 2439b122a4e4..8b10a55410a2 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -212,6 +212,39 @@ int thread__insert_map(struct thread *thread, struct map *map) return 0; } +static int __thread__prepare_access(struct thread *thread) +{ + bool initialized = false; + int i, err = 0; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + struct maps *maps = &thread->mg->maps[i]; + struct map *map; + + pthread_rwlock_rdlock(&maps->lock); + + for (map = maps__first(maps); map; map = map__next(map)) { + err = unwind__prepare_access(thread, map, &initialized); + if (err || initialized) + break; + } + + pthread_rwlock_unlock(&maps->lock); + } + + return err; +} + +static int thread__prepare_access(struct thread *thread) +{ + int err = 0; + + if (symbol_conf.use_callchain) + err = __thread__prepare_access(thread); + + return err; +} + static int thread__clone_map_groups(struct thread *thread, struct thread *parent) { @@ -219,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread, /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) - return 0; + return thread__prepare_access(thread); if (thread->mg == parent->mg) { pr_debug("broken map groups on thread %d/%d parent %d/%d\n", @@ -229,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread, /* But this one is new process, copy maps. */ for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(thread->mg, parent->mg, i) < 0) + if (map_groups__clone(thread, parent->mg, i) < 0) return -ENOMEM; return 0; From 203d1cacaddfc1e320f1e2625502fd1e0de465bd Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 4 Jul 2016 11:02:42 +0000 Subject: [PATCH 12/16] tools lib bpf: Add license header Adding a missing license descriptopn header to files in libbpf, make it LGPL-2.1. Signed-off-by: Wang Nan Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Eric Leblond Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1467630162-193121-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/bpf.c | 13 +++++++++++++ tools/lib/bpf/bpf.h | 13 +++++++++++++ tools/lib/bpf/libbpf.c | 13 +++++++++++++ tools/lib/bpf/libbpf.h | 13 +++++++++++++ 4 files changed, 52 insertions(+) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 1f91cc941b7c..4212ed62235b 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -4,6 +4,19 @@ * Copyright (C) 2013-2015 Alexei Starovoitov * Copyright (C) 2015 Wang Nan * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see */ #include diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a76465541292..e8ba54087497 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -4,6 +4,19 @@ * Copyright (C) 2013-2015 Alexei Starovoitov * Copyright (C) 2015 Wang Nan * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see */ #ifndef __BPF_BPF_H #define __BPF_BPF_H diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a7cb40abe634..3dcda9e215b0 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4,6 +4,19 @@ * Copyright (C) 2013-2015 Alexei Starovoitov * Copyright (C) 2015 Wang Nan * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see */ #include diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 148df3640ba0..f392c5e04cc1 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -4,6 +4,19 @@ * Copyright (C) 2013-2015 Alexei Starovoitov * Copyright (C) 2015 Wang Nan * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see */ #ifndef __BPF_LIBBPF_H #define __BPF_LIBBPF_H From b983d54473344a9ef524a231943478047a779796 Mon Sep 17 00:00:00 2001 From: Chris Phlipot Date: Thu, 30 Jun 2016 22:12:32 -0700 Subject: [PATCH 13/16] tools lib api: Respect WERROR=0 for build This enables the workaround for compilers that generate warnings when compiling libapi. Signed-off-by: Chris Phlipot Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467349955-1135-2-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/api/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index 67ff93ec1515..c7ceea6dd6cb 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS += -Werror +endif + CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 CFLAGS += -I$(srctree)/tools/lib/api From fd01d06ae33be63cff7d133e650cd1eb32f1d548 Mon Sep 17 00:00:00 2001 From: Chris Phlipot Date: Thu, 30 Jun 2016 22:12:33 -0700 Subject: [PATCH 14/16] tools lib subcmd: Respect WERROR=0 for build this enables the workaround for compilers that generate warnings when compiling libsubcmd. Signed-off-by: Chris Phlipot Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467349955-1135-3-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/subcmd/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index a8103700c172..ce4b7e527566 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libsubcmd.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS += -Werror +endif + CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE CFLAGS += -I$(srctree)/tools/include/ From 3d0376113ed9cf92b86885bf5102944b61523f5b Mon Sep 17 00:00:00 2001 From: Chris Phlipot Date: Thu, 30 Jun 2016 22:12:35 -0700 Subject: [PATCH 15/16] perf tools: Update android build documentation Update the android build documentation according to recent android build fixes. The instructions for step 1a and step 2 were updated to work with NDK version 11(oldest supported version) and NDK version 12(current version). Signed-off-by: Chris Phlipot Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1467349955-1135-5-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/android.txt | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt index 8484c3a04a6a..24a59998fc91 100644 --- a/tools/perf/Documentation/android.txt +++ b/tools/perf/Documentation/android.txt @@ -12,14 +12,14 @@ Set the NDK variable to point to the path where you installed the NDK: 2. Set cross-compiling environment variables for NDK toolchain and sysroot. For arm: - export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi- - export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm + export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.9/prebuilt/linux-x86_64/bin/arm-linux-androideabi- + export NDK_SYSROOT=${NDK}/platforms/android-24/arch-arm For x86: - export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android- - export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86 + export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.9/prebuilt/linux-x86_64/bin/i686-linux-android- + export NDK_SYSROOT=${NDK}/platforms/android-24/arch-x86 -This method is not working for Android NDK versions up to Revision 8b. -perf uses some bionic enhancements that are not included in these NDK versions. +This method is only tested for Android NDK versions Revision 11b and later. +perf uses some bionic enhancements that are not included in prior NDK versions. You can use method (b) described below instead. (b). Use the Android source tree @@ -49,9 +49,9 @@ II. Compile perf for Android ------------------------------------------------ You need to run make with the NDK toolchain and sysroot defined above: For arm: - make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}" + make WERROR=0 ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}" For x86: - make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}" + make WERROR=0 ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}" III. Install perf ----------------------------------------------- From f3d082ceabe53177c98bfa4580a294c2844966e8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Jul 2016 20:29:40 -0300 Subject: [PATCH 16/16] perf tools: Sync copy of syscall_64.tbl with the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed by the build system, that emitted this warning: Warning: x86_64's syscall_64.tbl differs from kernel This was due to the wiring up of the recently added preadv2 & pwritev2 syscalls to the compat code, which hadn't been done by the patch introducing those syscalls: 4babf2c5efb7 ("x86: wire up preadv2 and pwritev2"). The patch doing the compat wiring was: 482dd2ef1244 ("x86/syscalls: Wire up compat readv2/writev2 syscalls") This just silences the perf build warning, as compat syscalls still can't be supported in 'perf trace´ due to limitations in the raw_syscalls:sys_{enter,exit} tracepoints it relies on. Reported-by: Ingo Molnar Cc: Adrian Hunter Cc: Christoph Hellwig Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-4dm8eoy0wslgtwqdhz64ods0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index cac6d17ce5db..555263e385c9 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -374,3 +374,5 @@ 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit 545 x32 execveat compat_sys_execveat/ptregs +534 x32 preadv2 compat_sys_preadv2 +535 x32 pwritev2 compat_sys_pwritev2