From: Olivier Matz <olivier.matz@6wind.com>
To: lucp.at.work@gmail.com
Cc: dev@dpdk.org, jianfeng.tan@intel.com, david.marchand@redhat.com,
stable@dpdk.org
Subject: [dpdk-dev] [PATCH v2] eal: fix race in ctrl thread creation
Date: Thu, 25 Mar 2021 12:27:31 +0100 [thread overview]
Message-ID: <20210325112731.16324-1-olivier.matz@6wind.com> (raw)
In-Reply-To: <20210324130422.92357-1-lucp.at.work@gmail.com>
As reported by Luc, there is a race where the barrier is destroyed by
one thread, while the other thread did not yet leave
pthread_barrier_wait.
This patch fixes the race condition by adding an atomic counter to
ensure that the barrier is destroyed only it is not used by any thread.
Fixes: 3a0d465d4c53 ("eal: fix use-after-free on control thread creation")
Cc: jianfeng.tan@intel.com
Cc: stable@dpdk.org
Reported-by: Luc Pelletier <lucp.at.work@gmail.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
---
Hi Luc,
Thank you for reporting this problem and submitting the patch.
I think the issue can be fixed without any loop, like in this
patch. What do you think?
Regards,
Olivier
lib/librte_eal/common/eal_common_thread.c | 38 +++++++++++++----------
1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/lib/librte_eal/common/eal_common_thread.c b/lib/librte_eal/common/eal_common_thread.c
index 73a055902a..891f825e87 100644
--- a/lib/librte_eal/common/eal_common_thread.c
+++ b/lib/librte_eal/common/eal_common_thread.c
@@ -170,11 +170,11 @@ struct rte_thread_ctrl_params {
void *(*start_routine)(void *);
void *arg;
pthread_barrier_t configured;
+ unsigned int barrier_refcnt;
};
static void *ctrl_thread_init(void *arg)
{
- int ret;
struct internal_config *internal_conf =
eal_get_internal_configuration();
rte_cpuset_t *cpuset = &internal_conf->ctrl_cpuset;
@@ -184,8 +184,9 @@ static void *ctrl_thread_init(void *arg)
__rte_thread_init(rte_lcore_id(), cpuset);
- ret = pthread_barrier_wait(¶ms->configured);
- if (ret == PTHREAD_BARRIER_SERIAL_THREAD) {
+ pthread_barrier_wait(¶ms->configured);
+ if (__atomic_sub_fetch(¶ms->barrier_refcnt, 1,
+ __ATOMIC_ACQ_REL) == 0) {
pthread_barrier_destroy(¶ms->configured);
free(params);
}
@@ -210,15 +211,17 @@ rte_ctrl_thread_create(pthread_t *thread, const char *name,
params->start_routine = start_routine;
params->arg = arg;
-
- pthread_barrier_init(¶ms->configured, NULL, 2);
-
- ret = pthread_create(thread, attr, ctrl_thread_init, (void *)params);
+ __atomic_store_n(¶ms->barrier_refcnt, 2, __ATOMIC_RELEASE);
+ ret = pthread_barrier_init(¶ms->configured, NULL, 2);
if (ret != 0) {
free(params);
return -ret;
}
+ ret = pthread_create(thread, attr, ctrl_thread_init, (void *)params);
+ if (ret != 0)
+ goto fail;
+
if (name != NULL) {
ret = rte_thread_setname(*thread, name);
if (ret < 0)
@@ -227,25 +230,26 @@ rte_ctrl_thread_create(pthread_t *thread, const char *name,
}
ret = pthread_setaffinity_np(*thread, sizeof(*cpuset), cpuset);
- if (ret)
- goto fail;
+ if (ret != 0)
+ goto fail_cancel;
- ret = pthread_barrier_wait(¶ms->configured);
- if (ret == PTHREAD_BARRIER_SERIAL_THREAD) {
+ pthread_barrier_wait(¶ms->configured);
+ if (__atomic_sub_fetch(¶ms->barrier_refcnt, 1,
+ __ATOMIC_ACQ_REL) == 0) {
pthread_barrier_destroy(¶ms->configured);
free(params);
}
return 0;
-fail:
- if (PTHREAD_BARRIER_SERIAL_THREAD ==
- pthread_barrier_wait(¶ms->configured)) {
- pthread_barrier_destroy(¶ms->configured);
- free(params);
- }
+fail_cancel:
pthread_cancel(*thread);
pthread_join(*thread, NULL);
+
+fail:
+ pthread_barrier_destroy(¶ms->configured);
+ free(params);
+
return -ret;
}
--
2.29.2
next prev parent reply other threads:[~2021-03-25 11:28 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-24 13:04 [dpdk-dev] [PATCH] eal: fix possible UB on creation of ctrl thread Luc Pelletier
2021-03-25 11:27 ` Olivier Matz [this message]
2021-03-25 14:42 ` [dpdk-dev] [PATCH v2] eal: fix race in ctrl thread creation Luc Pelletier
2021-04-02 4:34 ` Honnappa Nagarahalli
2021-04-06 15:57 ` [dpdk-dev] [PATCH v3] eal: fix possible UB on creation of ctrl thread Luc Pelletier
2021-04-06 16:15 ` [dpdk-dev] [PATCH v3] eal: fix race in ctrl thread creation Luc Pelletier
2021-04-06 21:10 ` Honnappa Nagarahalli
2021-04-07 12:35 ` [dpdk-dev] [PATCH v4] " Luc Pelletier
2021-04-07 12:53 ` [dpdk-dev] [PATCH v5] " Luc Pelletier
2021-04-07 13:22 ` Luc Pelletier
2021-04-07 13:31 ` Olivier Matz
2021-04-07 14:42 ` [dpdk-dev] [PATCH v6] " Luc Pelletier
2021-04-07 14:57 ` Olivier Matz
2021-04-07 15:29 ` [dpdk-dev] [PATCH v7] " Luc Pelletier
2021-04-07 17:15 ` Honnappa Nagarahalli
2021-04-07 15:15 ` [dpdk-dev] [PATCH v5] " Honnappa Nagarahalli
2021-04-07 20:16 ` [dpdk-dev] [PATCH 1/2] " Luc Pelletier
2021-04-08 14:17 ` Olivier Matz
2021-04-08 17:06 ` Honnappa Nagarahalli
2021-04-07 20:16 ` [dpdk-dev] [PATCH 2/2] eal: fix hang in ctrl thread creation error logic Luc Pelletier
2021-04-08 14:20 ` Olivier Matz
2021-04-08 18:01 ` Luc Pelletier
2021-04-09 8:13 ` David Marchand
2021-04-08 17:07 ` Honnappa Nagarahalli
2021-04-09 14:34 ` [dpdk-dev] [dpdk-stable] " David Marchand
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210325112731.16324-1-olivier.matz@6wind.com \
--to=olivier.matz@6wind.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=jianfeng.tan@intel.com \
--cc=lucp.at.work@gmail.com \
--cc=stable@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).