| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20150330145805.GC32560@kernel.org>
Date: Mon, 30 Mar 2015 11:58:05 -0300
From: Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
To: Namhyung Kim <namhyung@...nel.org>
Cc: Jiri Olsa <jolsa@...hat.com>, David Ahern <dsahern@...il.com>,
Jiri Olsa <jolsa@...nel.org>,
Stephane Eranian <eranian@...gle.com>,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [BUG] segfault in perf-top -- thread refcnt
Em Mon, Mar 30, 2015 at 09:48:52PM +0900, Namhyung Kim escreveu:
> Hi Jiri,
>
> On Mon, Mar 30, 2015 at 01:49:07PM +0200, Jiri Olsa wrote:
> > On Mon, Mar 30, 2015 at 01:21:08PM +0200, Jiri Olsa wrote:
> > > On Mon, Mar 30, 2015 at 12:22:20PM +0200, Jiri Olsa wrote:
> > > > On Mon, Mar 30, 2015 at 10:07:37AM +0200, Jiri Olsa wrote:
> > > >
> > > > SNIP
> > > >
> > > > > >
> > > > > > 2 things:
> > > > > > 1. let run for a long time. go about using the server. do lots of builds,
> > > > > > etc. it takes time
> > > > > >
> > > > > > 2. use a box with a LOT of cpus (1024 in my case)
> > > > > >
> > > > > > Make sure ulimit is set to get the core.
> > > > >
> > > > > reproduced under 24 cpu box with kernel build (make -j25)
> > > > > running on background.. will try to look closer
> > > > >
> > > > > perf: Segmentation fault
> > > > > -------- backtrace --------
> > > > > ./perf[0x4fd79b]
> > > > > /lib64/libc.so.6(+0x358f0)[0x7f9cbff528f0]
> > > > > ./perf(thread__put+0x5b)[0x4b1a7b]
> > > > > ./perf(hists__delete_entries+0x70)[0x4c8670]
> > > > > ./perf[0x436a88]
> > > > > ./perf[0x4fa73d]
> > > > > ./perf(perf_evlist__tui_browse_hists+0x97)[0x4fc437]
> > > > > ./perf[0x4381d0]
> > > > > /lib64/libpthread.so.0(+0x7ee5)[0x7f9cc1ff2ee5]
> > > > > /lib64/libc.so.6(clone+0x6d)[0x7f9cc0011b8d]
> > > > > [0x0]
> > > >
> > > > looks like race among __machine__findnew_thread and thread__put
> > > > over the machine->threads rb_tree insert/removal
> > > >
> > > > is there a reason why thread__put does not erase itself from machine->threads?
> >
> > that was the reason.. we do this separately.. not in thread__put..
> > is there a reason for this? ;-)
> >
> > testing attached patch..
> >
> > jirka
> >
> >
> > ---
> > diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
> > index f7fb258..966564a 100644
> > --- a/tools/perf/util/build-id.c
> > +++ b/tools/perf/util/build-id.c
> > @@ -60,7 +60,6 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
> > event->fork.ppid, event->fork.ptid);
> >
> > if (thread) {
> > - rb_erase(&thread->rb_node, &machine->threads);
> > if (machine->last_match == thread)
> > thread__zput(machine->last_match);
> > thread__put(thread);
> > diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> > index e335330..a8443ef 100644
> > --- a/tools/perf/util/machine.c
> > +++ b/tools/perf/util/machine.c
> > @@ -30,6 +30,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
> > dsos__init(&machine->kernel_dsos);
> >
> > machine->threads = RB_ROOT;
> > + pthread_mutex_init(&machine->threads_lock, NULL);
> > INIT_LIST_HEAD(&machine->dead_threads);
> > machine->last_match = NULL;
> >
> > @@ -380,10 +381,13 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
> > if (!create)
> > return NULL;
> >
> > - th = thread__new(pid, tid);
> > + th = thread__new(machine, pid, tid);
> > if (th != NULL) {
> > +
> > + pthread_mutex_lock(&machine->threads_lock);
> > rb_link_node(&th->rb_node, parent, p);
> > rb_insert_color(&th->rb_node, &machine->threads);
> > + pthread_mutex_unlock(&machine->threads_lock);
>
> I think you also need to protect the rb tree traversal above.
>
> But this makes every sample processing grabs and releases the lock so
> might cause high overhead. It can be a problem if such processing is
> done parallelly like my multi-thread work. :-/
Still untested, using rw lock, next step is auditing the
machine__findnew_thread users that really should be using
machine__find_thread, i.e. grabbing just the reader lock, and measuring
the overhead of using a pthread rw lock instead of pthread_mutex_t as
Jiri is doing.
- Arnaldo
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index f7fb2587df69..e3c80bab47a3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -60,7 +60,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
event->fork.ppid, event->fork.ptid);
if (thread) {
+ pthread_rwlock_wrlock(&machine->threads_lock);
rb_erase(&thread->rb_node, &machine->threads);
+ pthread_rwlock_unlock(&machine->threads_lock);
if (machine->last_match == thread)
thread__zput(machine->last_match);
thread__put(thread);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e45c8f33a8fd..b901ed27a793 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -30,6 +30,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
dsos__init(&machine->kernel_dsos);
machine->threads = RB_ROOT;
+ pthread_rwlock_init(&machine->threads_lock, NULL);
INIT_LIST_HEAD(&machine->dead_threads);
machine->last_match = NULL;
@@ -111,6 +112,7 @@ void machine__exit(struct machine *machine)
vdso__exit(machine);
zfree(&machine->root_dir);
zfree(&machine->current_tid);
+ pthread_rwlock_destroy(&machines->threads_lock);
}
void machine__delete(struct machine *machine)
@@ -411,13 +413,22 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, true);
+ struct thread *th;
+
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ th = __machine__findnew_thread(machine, pid, tid, true);
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct thread *machine__find_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, false);
+ struct thread *th;
+ pthread_rwlock_rdlock(&machine->threads_lock);
+ th = __machine__findnew_thread(machine, pid, tid, false);
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -1258,7 +1269,9 @@ static void machine__remove_thread(struct machine *machine, struct thread *th)
if (machine->last_match == th)
thread__zput(machine->last_match);
+ pthread_rwlock_wrlock(&machine->threads_lock);
rb_erase(&th->rb_node, &machine->threads);
+ pthread_rwlock_unlock(&machine->threads_lock);
/*
* Move it first to the dead_threads list, then drop the reference,
* if this is the last reference, then the thread__delete destructor
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e2faf3b47e7b..c2b9402921fc 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -30,6 +30,7 @@ struct machine {
bool comm_exec;
char *root_dir;
struct rb_root threads;
+ pthread_rwlock_t threads_lock;
struct list_head dead_threads;
struct thread *last_match;
struct vdso_info *vdso_info;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists