From 48536c9195ae8c2a00fd8f400bac72ab613feaab Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 24 Feb 2015 13:20:59 +0200 Subject: perf tools: Fix probing for PERF_FLAG_FD_CLOEXEC flag Commit f6edb53c4993ffe92ce521fb449d1c146cea6ec2 converted the probe to a CPU wide event first (pid == -1). For kernels that do not support the PERF_FLAG_FD_CLOEXEC flag the probe fails with EINVAL. Since this errno is not handled pid is not reset to 0 and the subsequent use of pid = -1 as an argument brings in an additional failure path if perf_event_paranoid > 0: $ perf record -- sleep 1 perf_event_open(..., 0) failed unexpectedly with error 13 (Permission denied) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.007 MB /tmp/perf.data (11 samples) ] Also, ensure the fd of the confirmation check is closed and comment why pid = -1 is used. Needs to go to 3.18 stable tree as well. Signed-off-by: Adrian Hunter Based-on-patch-by: David Ahern Acked-by: David Ahern Cc: David Ahern Link: http://lkml.kernel.org/r/54EC610C.8000403@intel.com Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cloexec.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 47b78b3f0325..6da965bdbc2c 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -25,6 +25,10 @@ static int perf_flag_probe(void) if (cpu < 0) cpu = 0; + /* + * Using -1 for the pid is a workaround to avoid gratuitous jump label + * changes. + */ while (1) { /* check cloexec flag */ fd = sys_perf_event_open(&attr, pid, cpu, -1, @@ -47,16 +51,24 @@ static int perf_flag_probe(void) err, strerror_r(err, sbuf, sizeof(sbuf))); /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ - fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + while (1) { + fd = sys_perf_event_open(&attr, pid, cpu, -1, 0); + if (fd < 0 && pid == -1 && errno == EACCES) { + pid = 0; + continue; + } + break; + } err = errno; + if (fd >= 0) + close(fd); + if (WARN_ONCE(fd < 0 && err != EBUSY, "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", err, strerror_r(err, sbuf, sizeof(sbuf)))) return -1; - close(fd); - return 0; } -- cgit v1.2.3 From a73b6c199a663d64a38198f547d5c5be42163193 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 18 Feb 2015 19:03:18 -0500 Subject: perf top: Fix SIGBUS on sparc64 perf-top is terminating due to SIGBUS on sparc64. git bisect points to: commit 82396986032915c1572bfb74b224fcc2e4e8ba7c Author: Arnaldo Carvalho de Melo Date: Mon Sep 8 13:26:35 2014 -0300 perf evlist: Refcount mmaps We need to know how many fds are using a perf mmap via PERF_EVENT_IOC_SET_OUTPUT, so that we can know when to ditch an mmap, refcount it. This commit added 'int refcnt' to struct perf_mmap and the addition makes the event_copy element no longer 8-byte aligned. Fix by adding __attribute__((aligned(8))) to the event_copy struct member. Signed-off-by: David Ahern Link: http://lkml.kernel.org/r/1424304198-92028-1-git-send-email-david.ahern@oracle.com [ Switched from 'int pad;' to using __attribute__, David tested/acked that ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c94a9e03ecf1..e99a67632831 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -28,7 +28,7 @@ struct perf_mmap { int mask; int refcnt; unsigned int prev; - char event_copy[PERF_SAMPLE_MAX_SIZE]; + char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); }; struct perf_evlist { -- cgit v1.2.3 From e370a3d57664cd5e39c0b95d157ebc841b568409 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 18 Feb 2015 19:33:37 -0500 Subject: perf symbols: Define EM_AARCH64 for older OSes 4886f2ca19f6f added an arm-64 check, but the EM_AARCH64 macro is not defined in older releases (e.g., RHEL6). Define if it is not defined. Signed-off-by: David Ahern Cc: Victor Kamensky Link: http://lkml.kernel.org/r/1424306017-96797-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b24f9d8727a8..33b7a2aef713 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -11,6 +11,11 @@ #include #include "debug.h" +#ifndef EM_AARCH64 +#define EM_AARCH64 183 /* ARM 64 bit */ +#endif + + #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); -- cgit v1.2.3 From ecefde629fadd3fcca2ea4c6a799d6e6aab8781f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 19 Feb 2015 13:22:33 -0500 Subject: perf tools: Only include tsc file for x86 The perf_time_to_tsc and tsc_to_perf_time functions are only used for x86. Make inclusion of tsc.c dependent on x86 as well. Signed-off-by: David Ahern Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1424370153-128274-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/Build b/tools/perf/util/Build index a2c8047d25f7..972a6e0da7ad 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -71,7 +71,7 @@ libperf-y += stat.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o -libperf-y += tsc.o +libperf-$(CONFIG_X86) += tsc.o libperf-y += cloexec.o libperf-y += thread-stack.o -- cgit v1.2.3 From 4aa5f4f7bb8bc41cba15bcd0d80c4fb085027d6b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 27 Feb 2015 19:52:10 -0300 Subject: perf tools: Fix FORK after COMM when synthesizing records for pre-existing threads In this commit: commit 363b785f3805a2632eb09a8b430842461c21a640 Author: Don Zickus Date: Fri Mar 14 10:43:44 2014 -0400 perf tools: Speed up thread map generation We ended up emitting PERF_RECORD_FORK events after their corresponding PERF_RECORD_COMM, so the code below will remove the "existing thread" and then recreates it, unnecessarily: [root@ssdandy ~]# perf probe -x ~/bin/perf -L machine__process_fork_event 0 int machine__process_fork_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) 2 { 3 struct thread *thread = machine__find_thread(machine, event->fork.pid, event->fork.tid); 6 struct thread *parent = machine__findnew_thread(machine, event->fork.ppid, event->fork.ptid); /* if a thread currently exists for the thread id remove it */ if (thread != NULL) 12 machine__remove_thread(machine, thread); 14 thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); 16 if (dump_trace) 17 perf_event__fprintf_task(event, stdout); 19 if (thread == NULL || parent == NULL || 20 thread__fork(thread, parent, sample->time) < 0) { 21 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); 22 return -1; } 25 return 0; 26 } [root@ssdandy ~]# perf probe -x ~/bin/perf fork_after_comm=machine__process_fork_event:12 Added new event: probe_perf:fork_after_comm (on machine__process_fork_event:12 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:fork_after_comm -aR sleep 1 [root@ssdandy ~]# [root@ssdandy ~]# perf record -g -e probe_perf:* trace -o /tmp/bla ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.021 MB perf.data (30 samples) ] Terminated [root@ssdandy ~]# [root@ssdandy ~]# perf report --no-children --show-total-period --stdio # To display the perf.data header info, please use --header/--header-only options. # # Samples: 30 of event 'probe_perf:fork_after_comm' # Event count (approx.): 30 # # Overhead Period Command Shared Object Symbol # ........ ............ ....... ............. ............................... # 100.00% 30 trace trace [.] machine__process_fork_event | ---machine__process_fork_event __event__synthesize_thread.part.2 perf_event__synthesize_threads cmd_trace main __libc_start_main [root@ssdandy ~]# And Looking at 'perf report -D' output we see it: 0 0 0x8698 [0x30]: PERF_RECORD_COMM: auditd:703/707 0 0 0x86c8 [0x38]: PERF_RECORD_FORK(703:707):(703:703) Fix it by more closely mimicking how the kernel generates those records when a new fork happens, i.e. first a PERF_RECORD_FORK, then a PERF_RECORD_COMM. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-h0emvymi2t3mw8dlqd6d6z73@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9e806d855b04..d5efa5092ce6 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -95,9 +95,7 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) return tgid; } -static pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, +static pid_t perf_event__prepare_comm(union perf_event *event, pid_t pid, struct machine *machine) { size_t size; @@ -124,6 +122,19 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, (sizeof(event->comm.comm) - size) + machine->id_hdr_size); event->comm.tid = pid; +out: + return tgid; +} + +static pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + pid_t tgid = perf_event__prepare_comm(event, pid, machine); + + if (tgid == -1) + goto out; if (process(tool, event, &synth_sample, machine) != 0) return -1; @@ -139,7 +150,6 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, { memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - /* this is really a clone event but we use fork to synthesize it */ event->fork.ppid = tgid; event->fork.ptid = tgid; event->fork.pid = tgid; @@ -368,19 +378,23 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (*end) continue; - tgid = perf_event__synthesize_comm(tool, comm_event, _pid, - process, machine); + tgid = perf_event__prepare_comm(comm_event, _pid, machine); if (tgid == -1) return -1; + if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + process, machine) < 0) + return -1; + /* + * Send the prepared comm event + */ + if (process(tool, comm_event, &synth_sample, machine) != 0) + return -1; + if (_pid == pid) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); - } else { - /* only fork the tid's map, to save time */ - rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - process, machine); } if (rc) -- cgit v1.2.3 From 79702f614187f652a814061e8f5875ddcc9e732d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 28 Feb 2015 11:53:29 +0900 Subject: perf probe: Warn if given uprobe event accesses memory on older kernel Warn if given uprobe event accesses memory on older kernel. Until 3.14, uprobe event only supports accessing registers so this warns to upgrade kernel if uprobe-event returns -EINVAL and an argument of the event accesses memory ($stack, @+offset, and +|-offs() symtax). With this patch (on 3.10.0-123.13.2.el7.x86_64); ----- # ./perf probe -x ./perf warn_uprobe_event_compat stack=-0\(%sp\) Added new event: Failed to write event: Invalid argument Please upgrade your kernel to at least 3.14 to have access to feature -0(%sp) Error: Failed to add events. ----- Suggested-by: Arnaldo Carvalho de Melo Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20150228025329.32106.70581.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 7c0e765fa2e3..1c570c2fa7cc 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2199,6 +2199,27 @@ static int get_new_event_name(char *buf, size_t len, const char *base, return ret; } +/* Warn if the current kernel's uprobe implementation is old */ +static void warn_uprobe_event_compat(struct probe_trace_event *tev) +{ + int i; + char *buf = synthesize_probe_trace_command(tev); + + /* Old uprobe event doesn't support memory dereference */ + if (!tev->uprobes || tev->nargs == 0 || !buf) + goto out; + + for (i = 0; i < tev->nargs; i++) + if (strglobmatch(tev->args[i].value, "[$@+-]*")) { + pr_warning("Please upgrade your kernel to at least " + "3.14 to have access to feature %s\n", + tev->args[i].value); + break; + } +out: + free(buf); +} + static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs, bool allow_suffix) @@ -2295,6 +2316,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, */ allow_suffix = true; } + if (ret == -EINVAL && pev->uprobes) + warn_uprobe_event_compat(tev); /* Note that it is possible to skip all events because of blacklist */ if (ret >= 0 && tev->event) { -- cgit v1.2.3 From 0104fe69e0287cf3635657b4c6b26a18e0091697 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 2 Mar 2015 21:49:46 +0900 Subject: perf probe: Remove bias offset to find probe point by address Remove bias offset to find probe point by address. Without this patch, probe points on kernel and executables are shown correctly, but do not work with libraries: # ./perf probe -l probe:do_fork (on do_fork@kernel/fork.c) probe_libc:malloc (on malloc in /usr/lib64/libc-2.17.so) probe_perf:strlist__new (on strlist__new@util/strlist.c in /home/mhiramat/ksrc/linux-3/tools/perf/perf) Removing bias allows it to show it as real place: # ./perf probe -l probe:do_fork (on do_fork@kernel/fork.c) probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.17.so) probe_perf:strlist__new (on strlist__new@util/strlist.c in /home/mhiramat/ksrc/linux-3/tools/perf/perf) Signed-off-by: Masami Hiramatsu Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Naohiro Aota Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20150302124946.9191.64085.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-finder.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index d14193518e4d..46f009aa486c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1345,11 +1345,8 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; - /* Adjust address with bias */ - addr += dbg->bias; - /* Find cu die */ - if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) { + if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; -- cgit v1.2.3 From f3b623b8490af7a9b819cbcf2d99ab4597ece94b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2015 22:21:35 -0300 Subject: perf tools: Reference count struct thread We need to do that to stop accumulating entries in the dead_threads linked list, i.e. we were keeping references to threads in struct hists that continue to exist even after a thread exited and was removed from the machine threads rbtree. We still keep the dead_threads list, but just for debugging, allowing us to iterate at any given point over the threads that still are referenced by things like struct hist_entry. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-3ejvfyed0r7ue61dkurzjux4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 2 +- tools/perf/builtin-trace.c | 7 ++++++- tools/perf/ui/browsers/hists.c | 6 +++--- tools/perf/util/build-id.c | 5 +++-- tools/perf/util/hist.c | 2 ++ tools/perf/util/hist.h | 2 +- tools/perf/util/machine.c | 44 ++++++++++++++++++++++-------------------- tools/perf/util/machine.h | 1 - tools/perf/util/session.c | 6 ------ tools/perf/util/thread.c | 14 ++++++++++++++ tools/perf/util/thread.h | 13 +++++++++++++ 11 files changed, 66 insertions(+), 36 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 7ce296618717..e00e2eaf89da 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -831,7 +831,7 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) return -1; } - atoms->thread = thread; + atoms->thread = thread__get(thread); INIT_LIST_HEAD(&atoms->work_list); __thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid); return 0; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d95a8f4d988c..211614fba217 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1741,7 +1741,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, } else ttrace->entry_pending = true; - trace->current = thread; + if (trace->current != thread) { + thread__put(trace->current); + trace->current = thread__get(thread); + } return 0; } @@ -2274,6 +2277,8 @@ next_event: } out_disable: + thread__zput(trace->current); + perf_evlist__disable(evlist); if (!err) { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 788506eef567..ad312d91caed 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1467,7 +1467,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, perf_hpp__set_user_width(symbol_conf.col_width_list_str); while (1) { - const struct thread *thread = NULL; + struct thread *thread = NULL; const struct dso *dso = NULL; int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, @@ -1754,13 +1754,13 @@ zoom_thread: pstack__remove(fstack, &browser->hists->thread_filter); zoom_out_thread: ui_helpline__pop(); - browser->hists->thread_filter = NULL; + thread__zput(browser->hists->thread_filter); perf_hpp__set_elide(HISTC_THREAD, false); } else { ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", thread->comm_set ? thread__comm_str(thread) : "", thread->tid); - browser->hists->thread_filter = thread; + browser->hists->thread_filter = thread__get(thread); perf_hpp__set_elide(HISTC_THREAD, false); pstack__push(fstack, &browser->hists->thread_filter); } diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index ffdc338df925..a19674666b4e 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -61,8 +61,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, if (thread) { rb_erase(&thread->rb_node, &machine->threads); - machine->last_match = NULL; - thread__delete(thread); + if (machine->last_match == thread) + thread__zput(machine->last_match); + thread__put(thread); } return 0; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 70b48a65064c..95f5ab707b74 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -355,6 +355,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, callchain_init(he->callchain); INIT_LIST_HEAD(&he->pairs.node); + thread__get(he->thread); } return he; @@ -941,6 +942,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__delete(struct hist_entry *he) { + thread__zput(he->thread); zfree(&he->branch_info); zfree(&he->mem_info); zfree(&he->stat_acc); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2b690d028907..e988c9fcd1bc 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -60,7 +60,7 @@ struct hists { struct rb_root entries_collapsed; u64 nr_entries; u64 nr_non_filtered_entries; - const struct thread *thread_filter; + struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9e0f60a7e7b3..24f8c978cfd4 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -14,6 +14,8 @@ #include "unwind.h" #include "linux/hash.h" +static void machine__remove_thread(struct machine *machine, struct thread *th); + static void dsos__init(struct dsos *dsos) { INIT_LIST_HEAD(&dsos->head); @@ -89,16 +91,6 @@ static void dsos__delete(struct dsos *dsos) } } -void machine__delete_dead_threads(struct machine *machine) -{ - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &machine->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } -} - void machine__delete_threads(struct machine *machine) { struct rb_node *nd = rb_first(&machine->threads); @@ -106,9 +98,8 @@ void machine__delete_threads(struct machine *machine) while (nd) { struct thread *t = rb_entry(nd, struct thread, rb_node); - rb_erase(&t->rb_node, &machine->threads); nd = rb_next(nd); - thread__delete(t); + machine__remove_thread(machine, t); } } @@ -361,9 +352,13 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * the full rbtree: */ th = machine->last_match; - if (th && th->tid == tid) { - machine__update_thread_pid(machine, th, pid); - return th; + if (th != NULL) { + if (th->tid == tid) { + machine__update_thread_pid(machine, th, pid); + return th; + } + + thread__zput(machine->last_match); } while (*p != NULL) { @@ -371,7 +366,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - machine->last_match = th; + machine->last_match = thread__get(th); machine__update_thread_pid(machine, th, pid); return th; } @@ -403,8 +398,11 @@ static struct thread *__machine__findnew_thread(struct machine *machine, thread__delete(th); return NULL; } - - machine->last_match = th; + /* + * It is now in the rbtree, get a ref + */ + thread__get(th); + machine->last_match = thread__get(th); } return th; @@ -1238,13 +1236,17 @@ out_problem: static void machine__remove_thread(struct machine *machine, struct thread *th) { - machine->last_match = NULL; + if (machine->last_match == th) + thread__zput(machine->last_match); + rb_erase(&th->rb_node, &machine->threads); /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. + * Move it first to the dead_threads list, then drop the reference, + * if this is the last reference, then the thread__delete destructor + * will be called and we will remove it from the dead_threads list. */ list_add_tail(&th->node, &machine->dead_threads); + thread__put(th); } int machine__process_fork_event(struct machine *machine, union perf_event *event, diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index e8b7779a0a3f..e2faf3b47e7b 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -118,7 +118,6 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); -void machine__delete_dead_threads(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e4f166981ff0..ed4e5cf2bd9d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -138,11 +138,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file, return NULL; } -static void perf_session__delete_dead_threads(struct perf_session *session) -{ - machine__delete_dead_threads(&session->machines.host); -} - static void perf_session__delete_threads(struct perf_session *session) { machine__delete_threads(&session->machines.host); @@ -167,7 +162,6 @@ static void perf_session_env__delete(struct perf_session_env *env) void perf_session__delete(struct perf_session *session) { perf_session__destroy_kernel_maps(session); - perf_session__delete_dead_threads(session); perf_session__delete_threads(session); perf_session_env__delete(&session->header.env); machines__exit(&session->machines); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 9ebc8b1f9be5..a5dbba95107f 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -82,6 +82,20 @@ void thread__delete(struct thread *thread) free(thread); } +struct thread *thread__get(struct thread *thread) +{ + ++thread->refcnt; + return thread; +} + +void thread__put(struct thread *thread) +{ + if (thread && --thread->refcnt == 0) { + list_del_init(&thread->node); + thread__delete(thread); + } +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 160fd066a7d1..783b6688d2f7 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -20,6 +20,7 @@ struct thread { pid_t tid; pid_t ppid; int cpu; + int refcnt; char shortname[3]; bool comm_set; bool dead; /* if set thread has exited */ @@ -37,6 +38,18 @@ struct comm; struct thread *thread__new(pid_t pid, pid_t tid); int thread__init_map_groups(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); + +struct thread *thread__get(struct thread *thread); +void thread__put(struct thread *thread); + +static inline void __thread__zput(struct thread **thread) +{ + thread__put(*thread); + *thread = NULL; +} + +#define thread__zput(thread) __thread__zput(&thread) + static inline void thread__exited(struct thread *thread) { thread->dead = true; -- cgit v1.2.3