diff mbox

[1/2] cifs: smbd: avoid reconnect lockup

Message ID 20180330221636.32512-1-longli@linuxonhyperv.com (mailing list archive)
State New, archived
Headers show

Commit Message

Long Li March 30, 2018, 10:16 p.m. UTC
From: Long Li <longli@microsoft.com>

During transport reconnect, other processes may have registered memory
and blocked on transport. This creates a deadlock situation because the
transport resources can't be freed, and reconnect is blocked.

Fix this by returning to upper layer on timeout. Before returning,
transport status is set to reconnecting so other processes will release
memory registration resources.

Upper layer will retry the reconnect. This is not in fast I/O path so
setting the timeout to 5 seconds.

Signed-off-by: Long Li <longli@microsoft.com>
---
 fs/cifs/smbdirect.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

Comments

ronnie sahlberg March 30, 2018, 10:23 p.m. UTC | #1
Looks good to me (both patches)

Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>

On Sat, Mar 31, 2018 at 8:16 AM, Long Li <longli@linuxonhyperv.com> wrote:
> From: Long Li <longli@microsoft.com>
>
> During transport reconnect, other processes may have registered memory
> and blocked on transport. This creates a deadlock situation because the
> transport resources can't be freed, and reconnect is blocked.
>
> Fix this by returning to upper layer on timeout. Before returning,
> transport status is set to reconnecting so other processes will release
> memory registration resources.
>
> Upper layer will retry the reconnect. This is not in fast I/O path so
> setting the timeout to 5 seconds.
>
> Signed-off-by: Long Li <longli@microsoft.com>
> ---
>  fs/cifs/smbdirect.c | 12 ++++++++----
>  1 file changed, 8 insertions(+), 4 deletions(-)
>
> diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
> index 5aa0b54..3f7883e 100644
> --- a/fs/cifs/smbdirect.c
> +++ b/fs/cifs/smbdirect.c
> @@ -1498,8 +1498,8 @@ int smbd_reconnect(struct TCP_Server_Info *server)
>         log_rdma_event(INFO, "reconnecting rdma session\n");
>
>         if (!server->smbd_conn) {
> -               log_rdma_event(ERR, "rdma session already destroyed\n");
> -               return -EINVAL;
> +               log_rdma_event(INFO, "rdma session already destroyed\n");
> +               goto create_conn;
>         }
>
>         /*
> @@ -1512,15 +1512,19 @@ int smbd_reconnect(struct TCP_Server_Info *server)
>         }
>
>         /* wait until the transport is destroyed */
> -       wait_event(server->smbd_conn->wait_destroy,
> -               server->smbd_conn->transport_status == SMBD_DESTROYED);
> +       if (!wait_event_timeout(server->smbd_conn->wait_destroy,
> +               server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ))
> +               return -EAGAIN;
>
>         destroy_workqueue(server->smbd_conn->workqueue);
>         kfree(server->smbd_conn);
>
> +create_conn:
>         log_rdma_event(INFO, "creating rdma session\n");
>         server->smbd_conn = smbd_get_connection(
>                 server, (struct sockaddr *) &server->dstaddr);
> +       log_rdma_event(INFO, "created rdma session info=%p\n",
> +               server->smbd_conn);
>
>         return server->smbd_conn ? 0 : -ENOENT;
>  }
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Steve French March 31, 2018, 12:19 a.m. UTC | #2
merged into cifs-2.6.git for-next

added cc:stable

On Fri, Mar 30, 2018 at 5:23 PM, ronnie sahlberg
<ronniesahlberg@gmail.com> wrote:
> Looks good to me (both patches)
>
> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
>
> On Sat, Mar 31, 2018 at 8:16 AM, Long Li <longli@linuxonhyperv.com> wrote:
>> From: Long Li <longli@microsoft.com>
>>
>> During transport reconnect, other processes may have registered memory
>> and blocked on transport. This creates a deadlock situation because the
>> transport resources can't be freed, and reconnect is blocked.
>>
>> Fix this by returning to upper layer on timeout. Before returning,
>> transport status is set to reconnecting so other processes will release
>> memory registration resources.
>>
>> Upper layer will retry the reconnect. This is not in fast I/O path so
>> setting the timeout to 5 seconds.
>>
>> Signed-off-by: Long Li <longli@microsoft.com>
>> ---
>>  fs/cifs/smbdirect.c | 12 ++++++++----
>>  1 file changed, 8 insertions(+), 4 deletions(-)
>>
>> diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
>> index 5aa0b54..3f7883e 100644
>> --- a/fs/cifs/smbdirect.c
>> +++ b/fs/cifs/smbdirect.c
>> @@ -1498,8 +1498,8 @@ int smbd_reconnect(struct TCP_Server_Info *server)
>>         log_rdma_event(INFO, "reconnecting rdma session\n");
>>
>>         if (!server->smbd_conn) {
>> -               log_rdma_event(ERR, "rdma session already destroyed\n");
>> -               return -EINVAL;
>> +               log_rdma_event(INFO, "rdma session already destroyed\n");
>> +               goto create_conn;
>>         }
>>
>>         /*
>> @@ -1512,15 +1512,19 @@ int smbd_reconnect(struct TCP_Server_Info *server)
>>         }
>>
>>         /* wait until the transport is destroyed */
>> -       wait_event(server->smbd_conn->wait_destroy,
>> -               server->smbd_conn->transport_status == SMBD_DESTROYED);
>> +       if (!wait_event_timeout(server->smbd_conn->wait_destroy,
>> +               server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ))
>> +               return -EAGAIN;
>>
>>         destroy_workqueue(server->smbd_conn->workqueue);
>>         kfree(server->smbd_conn);
>>
>> +create_conn:
>>         log_rdma_event(INFO, "creating rdma session\n");
>>         server->smbd_conn = smbd_get_connection(
>>                 server, (struct sockaddr *) &server->dstaddr);
>> +       log_rdma_event(INFO, "created rdma session info=%p\n",
>> +               server->smbd_conn);
>>
>>         return server->smbd_conn ? 0 : -ENOENT;
>>  }
>> --
>> 2.7.4
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 5aa0b54..3f7883e 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1498,8 +1498,8 @@  int smbd_reconnect(struct TCP_Server_Info *server)
 	log_rdma_event(INFO, "reconnecting rdma session\n");
 
 	if (!server->smbd_conn) {
-		log_rdma_event(ERR, "rdma session already destroyed\n");
-		return -EINVAL;
+		log_rdma_event(INFO, "rdma session already destroyed\n");
+		goto create_conn;
 	}
 
 	/*
@@ -1512,15 +1512,19 @@  int smbd_reconnect(struct TCP_Server_Info *server)
 	}
 
 	/* wait until the transport is destroyed */
-	wait_event(server->smbd_conn->wait_destroy,
-		server->smbd_conn->transport_status == SMBD_DESTROYED);
+	if (!wait_event_timeout(server->smbd_conn->wait_destroy,
+		server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ))
+		return -EAGAIN;
 
 	destroy_workqueue(server->smbd_conn->workqueue);
 	kfree(server->smbd_conn);
 
+create_conn:
 	log_rdma_event(INFO, "creating rdma session\n");
 	server->smbd_conn = smbd_get_connection(
 		server, (struct sockaddr *) &server->dstaddr);
+	log_rdma_event(INFO, "created rdma session info=%p\n",
+		server->smbd_conn);
 
 	return server->smbd_conn ? 0 : -ENOENT;
 }