| 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: <00202749-1b0d-91c8-9a52-cf8a66d8d340@fujitsu.com>
Date: Fri, 21 Apr 2023 01:38:10 +0000
From: "Zhijian Li (Fujitsu)" <lizhijian@...itsu.com>
To: Jinpu Wang <jinpu.wang@...os.com>
CC: Leon Romanovsky <leon@...nel.org>,
Zhu Yanjun <yanjun.zhu@...ux.dev>,
Guoqing Jiang <guoqing.jiang@...ux.dev>,
"haris.iqbal@...os.com" <haris.iqbal@...os.com>,
"jgg@...pe.ca" <jgg@...pe.ca>,
"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH for-next 2/3] RDMA/rtrs: Fix rxe_dealloc_pd warning
Jinpu
I updated the changes as below, and tested for thousand rounds.
From d441c0e2496c1795b5af2b6b8ae4672203d6af3c Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@...itsu.com>
Date: Thu, 20 Apr 2023 17:28:28 +0800
Subject: [PATCH] RDMA/rtrs: Fix rxe_dealloc_pd warning
In current design:
1. PD and clt_path->s.dev are shared among connections.
2. every con[n]'s cleanup phase will call destroy_con_cq_qp()
3. clt_path->s.dev will be always decreased in destroy_con_cq_qp(), and
when clt_path->s.dev become zero, it will destroy PD.
4. when con[1] failed to create, con[1] will not take clt_path->s.dev,
but it try to decreased clt_path->s.dev
So, in case create_cm(con[0]) succeeds but create_cm(con[1])
fails, destroy_con_cq_qp(con[1]) will be called first which will destory
the PD while this PD is still taken by con[0].
Here, we refactor the error path of create_cm() and init_conns(), so that
we do the cleanup in the order they are created.
Signed-off-by: Li Zhijian <lizhijian@...itsu.com>
---
drivers/infiniband/ulp/rtrs/rtrs-clt.c | 47 +++++++++++---------------
1 file changed, 19 insertions(+), 28 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 80abf45a197a..5faf0ecb726b 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -2040,6 +2040,7 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
return 0;
}
+/* The caller should the do the cleanup in case of error */
static int create_cm(struct rtrs_clt_con *con)
{
struct rtrs_path *s = con->c.path;
@@ -2062,14 +2063,14 @@ static int create_cm(struct rtrs_clt_con *con)
err = rdma_set_reuseaddr(cm_id, 1);
if (err != 0) {
rtrs_err(s, "Set address reuse failed, err: %d\n", err);
- goto destroy_cm;
+ return err;
}
err = rdma_resolve_addr(cm_id, (struct sockaddr *)&clt_path->s.src_addr,
(struct sockaddr *)&clt_path->s.dst_addr,
RTRS_CONNECT_TIMEOUT_MS);
if (err) {
rtrs_err(s, "Failed to resolve address, err: %d\n", err);
- goto destroy_cm;
+ return err;
}
/*
* Combine connection status and session events. This is needed
@@ -2084,29 +2085,17 @@ static int create_cm(struct rtrs_clt_con *con)
if (err == 0)
err = -ETIMEDOUT;
/* Timedout or interrupted */
- goto errr;
+ return err;
}
if (con->cm_err < 0) {
- err = con->cm_err;
- goto errr;
+ return con->cm_err;
}
if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTING) {
/* Device removal */
- err = -ECONNABORTED;
- goto errr;
+ return -ECONNABORTED;
}
return 0;
-
-errr:
- stop_cm(con);
- mutex_lock(&con->con_mutex);
- destroy_con_cq_qp(con);
- mutex_unlock(&con->con_mutex);
-destroy_cm:
- destroy_cm(con);
-
- return err;
}
static void rtrs_clt_path_up(struct rtrs_clt_path *clt_path)
@@ -2334,7 +2323,7 @@ static void rtrs_clt_close_work(struct work_struct *work)
static int init_conns(struct rtrs_clt_path *clt_path)
{
unsigned int cid;
- int err;
+ int err, i;
/*
* On every new session connections increase reconnect counter
@@ -2350,10 +2339,8 @@ static int init_conns(struct rtrs_clt_path *clt_path)
goto destroy;
err = create_cm(to_clt_con(clt_path->s.con[cid]));
- if (err) {
- destroy_con(to_clt_con(clt_path->s.con[cid]));
+ if (err)
goto destroy;
- }
}
err = alloc_path_reqs(clt_path);
if (err)
@@ -2364,15 +2351,19 @@ static int init_conns(struct rtrs_clt_path *clt_path)
return 0;
destroy:
- while (cid--) {
+ /* Make sure we do the cleanup in the order they are created */
+ for (i = 0; i <= cid; i++) {
struct rtrs_clt_con *con = to_clt_con(clt_path->s.con[cid]);
- stop_cm(con);
-
- mutex_lock(&con->con_mutex);
- destroy_con_cq_qp(con);
- mutex_unlock(&con->con_mutex);
- destroy_cm(con);
+ if (!con)
+ break;
+ if (con->c.cm_id) {
+ stop_cm(con);
+ mutex_lock(&con->con_mutex);
+ destroy_con_cq_qp(con);
+ mutex_unlock(&con->con_mutex);
+ destroy_cm(con);
+ }
destroy_con(con);
}
/*
--
2.29.2
On 20/04/2023 10:00, Li Zhijian wrote:
> On 19/04/2023 21:20, Jinpu Wang wrote:
>> On Wed, Apr 19, 2023 at 11:53 AM Zhijian Li (Fujitsu)
>> <lizhijian@...itsu.com> wrote:
>>>
>>> Leon, Guoqing
>>>
>>>
>>> On 18/04/2023 15:57, Leon Romanovsky wrote:
>>>>>>> Currently, without this patch:
>>>>>>> 1. PD and clt_path->s.dev are shared among connections.
>>>>>>> 2. every con[n]'s cleanup phase will call destroy_con_cq_qp()
>>>>>>> 3. clt_path->s.dev will be always decreased in destroy_con_cq_qp(), and when
>>>>>>> clt_path->s.dev become zero, it will destroy PD.
>>>>>>> 4. when con[1] failed to create, con[1] will not take clt_path->s.dev, but it try to decreased clt_path->s.dev <<< it's wrong to do that.
>>>>>> So please fix it by making sure that failure to create con[1] will
>>>>>> release resources which were allocated. If con[1] didn't increase
>>>>>> s.dev_ref, it shouldn't decrease it either.
>>>>> You are right, the current patch did exactly that.
>>>>> It introduced a con owning flag 'has_dev' to indicate whether this con has taken s.dev.
>>>>> so that its cleanup phase will only decrease its s.dev properly.
>>>> The has_dev is a workaround and not a solution. In proper error unwind
>>>> sequence, you won't need extra flag.
Powered by blists - more mailing lists