From 2ce19e72f4d570c87e025ee6fca4eae699a8b712 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 21 Feb 2013 17:20:00 +0000 Subject: IB/srp: Fail I/O requests if the transport is offline If an SRP target is no longer reachable and srp_reset_host() fails to reconnect then ib_srp will invoke scsi_remove_host(). That function will invoke __scsi_remove_device() for each LUN. And that last function will change the device state from SDEV_TRANSPORT_OFFLINE into SDEV_CANCEL. Certain user space software, e.g. older versions of multipathd, continue queueing I/O to SCSI devices that are in the SDEV_CANCEL state. If these I/O requests are submitted as SG_IO that means that the REQ_PREEMPT flag will be set and hence that these requests will be passed to srp_queuecommand(). These requests will time out. If new requests are queued fast enough from user space these active requests will prevent __scsi_remove_device() to finish. Avoid this by failing I/O requests in the SDEV_CANCEL state if the transport is offline. Introduce a new variable to keep track of the transport state instead of failing requests if (!target->connected || target->qp_in_error), so that the SCSI error handler has a chance to retry commands after a transport layer failure occurred. Signed-off-by: Bart Van Assche Cc: # 3.8 Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/srp/ib_srp.c | 7 +++++++ drivers/infiniband/ulp/srp/ib_srp.h | 1 + 2 files changed, 8 insertions(+) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 8a7eb9f98a0c..7ccf3284dda3 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -734,6 +734,7 @@ static int srp_reconnect_target(struct srp_target_port *target) scsi_target_unblock(&shost->shost_gendev, ret == 0 ? SDEV_RUNNING : SDEV_TRANSPORT_OFFLINE); + target->transport_offline = !!ret; if (ret) goto err; @@ -1353,6 +1354,12 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd) unsigned long flags; int len; + if (unlikely(target->transport_offline)) { + scmnd->result = DID_NO_CONNECT << 16; + scmnd->scsi_done(scmnd); + return 0; + } + spin_lock_irqsave(&target->lock, flags); iu = __srp_get_tx_iu(target, SRP_IU_CMD); if (!iu) diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index de2d0b3c0bfe..66fbedda4571 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -140,6 +140,7 @@ struct srp_target_port { unsigned int cmd_sg_cnt; unsigned int indirect_size; bool allow_ext_sg; + bool transport_offline; /* Everything above this point is used in the hot path of * command processing. Try to keep them packed into cachelines. -- cgit v1.2.3-59-g8ed1b