Re: [PATCH v3] iscsi: Perform connection failure entirely in kernel space

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Thu, Dec 26, 2019 at 3:48 PM Gabriel Krisman Bertazi
<krisman@xxxxxxxxxxxxx> wrote:
>
> From: Bharath Ravi <rbharath@xxxxxxxxxx>
>
> Connection failure processing depends on a daemon being present to (at
> least) stop the connection and start recovery.  This is a problem on a
> multipath scenario, where if the daemon failed for whatever reason, the
> SCSI path is never marked as down, multipath won't perform the
> failover and IO to the device will be forever waiting for that
> connection to come back.
>
> This patch performs the connection failure entirely inside the kernel.
> This way, the failover can happen and pending IO can continue even if
> the daemon is dead. Once the daemon comes alive again, it can execute
> recovery procedures if applicable.
>
> Changes since v2:
>   - Don't hold rx_mutex for too long at once
>
> Changes since v1:
>   - Remove module parameter.
>   - Always do kernel-side stop work.
>   - Block recovery timeout handler if system is dying.
>   - send a CONN_TERM stop if the system is dying.
>
> Cc: Mike Christie <mchristi@xxxxxxxxxx>
> Cc: Lee Duncan <LDuncan@xxxxxxxx>
> Cc: Bart Van Assche <bvanassche@xxxxxxx>
> Co-developed-by: Dave Clausen <dclausen@xxxxxxxxxx>
> Signed-off-by: Dave Clausen <dclausen@xxxxxxxxxx>
> Co-developed-by: Nick Black <nlb@xxxxxxxxxx>
> Signed-off-by: Nick Black <nlb@xxxxxxxxxx>
> Co-developed-by: Vaibhav Nagarnaik <vnagarnaik@xxxxxxxxxx>
> Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@xxxxxxxxxx>
> Co-developed-by: Anatol Pomazau <anatol@xxxxxxxxxx>
> Signed-off-by: Anatol Pomazau <anatol@xxxxxxxxxx>
> Co-developed-by: Tahsin Erdogan <tahsin@xxxxxxxxxx>
> Signed-off-by: Tahsin Erdogan <tahsin@xxxxxxxxxx>
> Co-developed-by: Frank Mayhar <fmayhar@xxxxxxxxxx>
> Signed-off-by: Frank Mayhar <fmayhar@xxxxxxxxxx>
> Co-developed-by: Junho Ryu <jayr@xxxxxxxxxx>
> Signed-off-by: Junho Ryu <jayr@xxxxxxxxxx>
> Co-developed-by: Khazhismel Kumykov <khazhy@xxxxxxxxxx>
> Signed-off-by: Khazhismel Kumykov <khazhy@xxxxxxxxxx>
> Signed-off-by: Bharath Ravi <rbharath@xxxxxxxxxx>
> Co-developed-by: Gabriel Krisman Bertazi <krisman@xxxxxxxxxxxxx>
> Signed-off-by: Gabriel Krisman Bertazi <krisman@xxxxxxxxxxxxx>
> ---
>  drivers/scsi/scsi_transport_iscsi.c | 63 +++++++++++++++++++++++++++++
>  include/scsi/scsi_transport_iscsi.h |  1 +
>  2 files changed, 64 insertions(+)
>
> diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
> index 271afea654e2..c6db6ded60a1 100644
> --- a/drivers/scsi/scsi_transport_iscsi.c
> +++ b/drivers/scsi/scsi_transport_iscsi.c
> @@ -86,6 +86,12 @@ struct iscsi_internal {
>         struct transport_container session_cont;
>  };
>
> +/* Worker to perform connection failure on unresponsive connections
> + * completely in kernel space.
> + */
> +static void stop_conn_work_fn(struct work_struct *work);
> +static DECLARE_WORK(stop_conn_work, stop_conn_work_fn);
> +
>  static atomic_t iscsi_session_nr; /* sysfs session id for next new session */
>  static struct workqueue_struct *iscsi_eh_timer_workq;
>
> @@ -1611,6 +1617,7 @@ static DEFINE_MUTEX(rx_queue_mutex);
>  static LIST_HEAD(sesslist);
>  static DEFINE_SPINLOCK(sesslock);
>  static LIST_HEAD(connlist);
> +static LIST_HEAD(connlist_err);
>  static DEFINE_SPINLOCK(connlock);
>
>  static uint32_t iscsi_conn_get_sid(struct iscsi_cls_conn *conn)
> @@ -2247,6 +2254,7 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid)
>
>         mutex_init(&conn->ep_mutex);
>         INIT_LIST_HEAD(&conn->conn_list);
> +       INIT_LIST_HEAD(&conn->conn_list_err);
>         conn->transport = transport;
>         conn->cid = cid;
>
> @@ -2293,6 +2301,7 @@ int iscsi_destroy_conn(struct iscsi_cls_conn *conn)
>
>         spin_lock_irqsave(&connlock, flags);
>         list_del(&conn->conn_list);
> +       list_del(&conn->conn_list_err);
>         spin_unlock_irqrestore(&connlock, flags);
>
>         transport_unregister_device(&conn->dev);
> @@ -2407,6 +2416,51 @@ int iscsi_offload_mesg(struct Scsi_Host *shost,
>  }
>  EXPORT_SYMBOL_GPL(iscsi_offload_mesg);
>
> +static void stop_conn_work_fn(struct work_struct *work)
> +{
> +       struct iscsi_cls_conn *conn, *tmp;
> +       unsigned long flags;
> +       LIST_HEAD(recovery_list);
> +
> +       spin_lock_irqsave(&connlock, flags);
> +       if (list_empty(&connlist_err)) {
> +               spin_unlock_irqrestore(&connlock, flags);
> +               return;
> +       }
> +       list_splice_init(&connlist_err, &recovery_list);
> +       spin_unlock_irqrestore(&connlock, flags);
> +
> +       list_for_each_entry_safe(conn, tmp, &recovery_list, conn_list_err) {
> +               uint32_t sid = iscsi_conn_get_sid(conn);
> +               struct iscsi_cls_session *session;
> +
> +               mutex_lock(&rx_queue_mutex);
This worried me a bit, but it seems we won't destroy_conn while it's
on the err list - cool.
> +
> +               session = iscsi_session_lookup(sid);
> +               if (session) {
> +                       if (system_state != SYSTEM_RUNNING) {
> +                               session->recovery_tmo = 0;
> +                               conn->transport->stop_conn(conn,
> +                                                          STOP_CONN_TERM);
> +                       } else {
> +                               conn->transport->stop_conn(conn,
> +                                                          STOP_CONN_RECOVER);
> +                       }
> +               }
> +
> +               list_del_init(&conn->conn_list_err);
> +
> +               mutex_unlock(&rx_queue_mutex);
> +
> +               /* we don't want to hold rx_queue_mutex for too long,
> +                * for instance if many conns failed at the same time,
> +                * since this stall other iscsi maintenance operations.
> +                * Give other users a chance to proceed.
> +                */
> +               cond_resched();
> +       }
> +}
> +
>  void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
>  {
>         struct nlmsghdr *nlh;
> @@ -2414,6 +2468,12 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
>         struct iscsi_uevent *ev;
>         struct iscsi_internal *priv;
>         int len = nlmsg_total_size(sizeof(*ev));
> +       unsigned long flags;
> +
> +       spin_lock_irqsave(&connlock, flags);
> +       list_add(&conn->conn_list_err, &connlist_err);
> +       spin_unlock_irqrestore(&connlock, flags);
> +       queue_work(system_unbound_wq, &stop_conn_work);
>
>         priv = iscsi_if_transport_lookup(conn->transport);
>         if (!priv)
> @@ -2748,6 +2808,9 @@ iscsi_if_destroy_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev
>         if (!conn)
>                 return -EINVAL;
>
> +       if (!list_empty(&conn->conn_list_err))
Does this check need to be under connlock?
> +               return -EAGAIN;
> +
>         ISCSI_DBG_TRANS_CONN(conn, "Destroying transport conn\n");
>         if (transport->destroy_conn)
>                 transport->destroy_conn(conn);
> diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
> index 325ae731d9ad..2129dc9e2dec 100644
> --- a/include/scsi/scsi_transport_iscsi.h
> +++ b/include/scsi/scsi_transport_iscsi.h
> @@ -190,6 +190,7 @@ extern void iscsi_ping_comp_event(uint32_t host_no,
>
>  struct iscsi_cls_conn {
>         struct list_head conn_list;     /* item in connlist */
> +       struct list_head conn_list_err; /* item in connlist_err */
>         void *dd_data;                  /* LLD private data */
>         struct iscsi_transport *transport;
>         uint32_t cid;                   /* connection id */
> --
> 2.24.1
>

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [SCSI Target Devel]     [Linux SCSI Target Infrastructure]     [Kernel Newbies]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Linux IIO]     [Samba]     [Device Mapper]

  Powered by Linux