From patchwork Wed Jul 8 09:06:14 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hannes Reinecke X-Patchwork-Id: 6743081 Return-Path: X-Original-To: patchwork-linux-scsi@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 444089F2F0 for ; Wed, 8 Jul 2015 09:08:46 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 947A520713 for ; Wed, 8 Jul 2015 09:08:44 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id A55F52073F for ; Wed, 8 Jul 2015 09:08:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934889AbbGHJId (ORCPT ); Wed, 8 Jul 2015 05:08:33 -0400 Received: from cantor2.suse.de ([195.135.220.15]:35940 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934508AbbGHJGc (ORCPT ); Wed, 8 Jul 2015 05:06:32 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay1.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx2.suse.de (Postfix) with ESMTP id 0286CAD88; Wed, 8 Jul 2015 09:06:25 +0000 (UTC) From: Hannes Reinecke To: James Bottomley Cc: Christoph Hellwig , linux-scsi@vger.kernel.org, "Martin K. Petersen" , Bart van Assche , Hannes Reinecke Subject: [PATCH 16/20] scsi_dh_alua: Use workqueue for RTPG Date: Wed, 8 Jul 2015 11:06:14 +0200 Message-Id: <1436346378-96518-17-git-send-email-hare@suse.de> X-Mailer: git-send-email 1.8.5.2 In-Reply-To: <1436346378-96518-1-git-send-email-hare@suse.de> References: <1436346378-96518-1-git-send-email-hare@suse.de> Sender: linux-scsi-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org X-Spam-Status: No, score=-7.6 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The current ALUA device_handler has two drawbacks: - We're sending a 'SET TARGET PORT GROUP' command to every LUN, disregarding the fact that several LUNs might be in a port group and will be automatically switched whenever _any_ LUN within that port group receives the command. - Whenever a LUN is in 'transitioning' mode we cannot block I/O to that LUN, instead the controller has to abort the command. This leads to increased traffic across the wire and heavy load on the controller during switchover. With this patch the RTPG handling is moved to a per-portgroup workqueue. This reduces the number of 'REPORT TARGET PORT GROUP' and 'SET TARGET PORT GROUPS' sent to the controller as we're sending them now per port group, and not per device as previously. It also allows us to block I/O to any LUN / port group found to be in 'transitioning' ALUA mode, as the workqueue item will be requeued until the controller moves out of transitioning. Signed-off-by: Hannes Reinecke --- drivers/scsi/device_handler/scsi_dh_alua.c | 412 ++++++++++++++++++++++++----- 1 file changed, 349 insertions(+), 63 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 88c150a..ea47d15 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include #include #include @@ -59,10 +61,15 @@ #define ALUA_RTPG_SIZE 128 #define ALUA_FAILOVER_TIMEOUT 60 #define ALUA_FAILOVER_RETRIES 5 +#define ALUA_RTPG_DELAY_MSECS 5 /* device handler flags */ -#define ALUA_OPTIMIZE_STPG 1 -#define ALUA_RTPG_EXT_HDR_UNSUPP 2 +#define ALUA_OPTIMIZE_STPG 0x01 +#define ALUA_RTPG_EXT_HDR_UNSUPP 0x02 +/* State machine flags */ +#define ALUA_PG_RUN_RTPG 0x10 +#define ALUA_PG_RUN_STPG 0x20 + static LIST_HEAD(port_group_list); static DEFINE_SPINLOCK(port_group_lock); @@ -79,13 +86,29 @@ struct alua_port_group { int pref; unsigned flags; /* used for optimizing STPG */ unsigned char transition_tmo; + unsigned long expiry; + unsigned long interval; + char work_q_name[264]; + struct workqueue_struct *work_q; + struct delayed_work rtpg_work; + struct delayed_work stpg_work; + struct delayed_work qdata_work; + spinlock_t rtpg_lock; + struct list_head rtpg_list; + struct scsi_device *rtpg_sdev; }; struct alua_dh_data { struct alua_port_group *pg; + spinlock_t pg_lock; int rel_port; int tpgs; - struct scsi_device *sdev; + int error; + struct completion init_complete; +}; + +struct alua_queue_data { + struct list_head entry; activate_complete callback_fn; void *callback_data; }; @@ -94,6 +117,10 @@ struct alua_dh_data { #define ALUA_POLICY_SWITCH_ALL 1 static char print_alua_state(int); +static void alua_rtpg_work(struct work_struct *work); +static void alua_stpg_work(struct work_struct *work); +static void alua_qdata_work(struct work_struct *work); +static void alua_check(struct scsi_device *sdev); static void release_port_group(struct kref *kref) { @@ -104,6 +131,9 @@ static void release_port_group(struct kref *kref) spin_lock(&port_group_lock); list_del(&pg->node); spin_unlock(&port_group_lock); + WARN_ON(pg->rtpg_sdev); + if (pg->work_q) + destroy_workqueue(pg->work_q); kfree(pg); } @@ -374,13 +404,17 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h) if (memcmp(tmp_pg->device_id, device_id, device_id_size)) continue; - h->pg = tmp_pg; kref_get(&tmp_pg->kref); + spin_lock(&h->pg_lock); + rcu_assign_pointer(h->pg, tmp_pg); + spin_unlock(&h->pg_lock); break; } spin_unlock(&port_group_lock); - if (h->pg) + if (h->pg) { + synchronize_rcu(); return SCSI_DH_OK; + } pg = kzalloc(sizeof(struct alua_port_group), GFP_KERNEL); if (!pg) { @@ -402,6 +436,20 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h) pg->tpgs = h->tpgs; pg->state = TPGS_STATE_OPTIMIZED; kref_init(&pg->kref); + INIT_DELAYED_WORK(&pg->rtpg_work, alua_rtpg_work); + INIT_DELAYED_WORK(&pg->stpg_work, alua_stpg_work); + INIT_DELAYED_WORK(&pg->qdata_work, alua_qdata_work); + INIT_LIST_HEAD(&pg->rtpg_list); + INIT_LIST_HEAD(&pg->node); + spin_lock_init(&pg->rtpg_lock); + snprintf(pg->work_q_name, sizeof(pg->work_q_name), + "alua_wq_%s_%d", pg->device_id_str, pg->group_id); + pg->work_q = create_singlethread_workqueue(pg->work_q_name); + if (!pg->work_q) { + kref_put(&pg->kref, release_port_group); + /* Temporary failure, bypass */ + return SCSI_DH_DEV_TEMP_BUSY; + } spin_lock(&port_group_lock); /* * Re-check list again to catch @@ -415,15 +463,19 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h) if (memcmp(tmp_pg->device_id, pg->device_id, device_id_size)) continue; - h->pg = tmp_pg; kref_get(&tmp_pg->kref); + spin_lock(&h->pg_lock); + rcu_assign_pointer(h->pg, tmp_pg); + spin_unlock(&h->pg_lock); kfree(pg); pg = NULL; break; } if (pg) { list_add(&pg->node, &port_group_list); - h->pg = pg; + spin_lock(&h->pg_lock); + rcu_assign_pointer(h->pg, pg); + spin_unlock(&h->pg_lock); } spin_unlock(&port_group_lock); @@ -457,11 +509,14 @@ static int alua_check_sense(struct scsi_device *sdev, { switch (sense_hdr->sense_key) { case NOT_READY: - if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) + if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) { /* * LUN Not Accessible - ALUA state transition + * Kickoff worker to update internal state. */ + alua_check(sdev); return ADD_TO_MLQUEUE; + } break; case UNIT_ATTENTION: if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) @@ -510,14 +565,15 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) int len, k, off, valid_states = 0, bufflen = ALUA_RTPG_SIZE; unsigned char *ucp, *buff; unsigned err, retval; - unsigned long expiry, interval = 0; unsigned int tpg_desc_tbl_off; unsigned char orig_transition_tmo; - if (!pg->transition_tmo) - expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ); - else - expiry = round_jiffies_up(jiffies + pg->transition_tmo * HZ); + if (!pg->expiry) { + if (!pg->transition_tmo) + pg->expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ); + else + pg->expiry = round_jiffies_up(jiffies + pg->transition_tmo * HZ); + } buff = kzalloc(bufflen, GFP_KERNEL); if (!buff) @@ -538,6 +594,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) else err = SCSI_DH_IO; kfree(buff); + pg->expiry = 0; return err; } @@ -564,16 +621,18 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) err = SCSI_DH_RETRY; if (sense_hdr.sense_key == UNIT_ATTENTION) err = SCSI_DH_RETRY; - if (err == SCSI_DH_RETRY && time_before(jiffies, expiry)) { + if (err == SCSI_DH_RETRY && + pg->expiry != 0 && time_before(jiffies, pg->expiry)) { sdev_printk(KERN_ERR, sdev, "%s: rtpg retry\n", ALUA_DH_NAME); scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr); - goto retry; + return err; } sdev_printk(KERN_ERR, sdev, "%s: rtpg failed\n", ALUA_DH_NAME); scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr); kfree(buff); + pg->expiry = 0; return SCSI_DH_IO; } @@ -588,6 +647,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) sdev_printk(KERN_WARNING, sdev, "%s: kmalloc buffer failed\n",__func__); /* Temporary failure, bypass */ + pg->expiry = 0; return SCSI_DH_DEV_TEMP_BUSY; } goto retry; @@ -603,7 +663,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) sdev_printk(KERN_INFO, sdev, "%s: transition timeout set to %d seconds\n", ALUA_DH_NAME, pg->transition_tmo); - expiry = jiffies + pg->transition_tmo * HZ; + pg->expiry = jiffies + pg->transition_tmo * HZ; } if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR) @@ -637,23 +697,26 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) switch (pg->state) { case TPGS_STATE_TRANSITIONING: - if (time_before(jiffies, expiry)) { + if (time_before(jiffies, pg->expiry)) { /* State transition, retry */ - interval += 2000; - msleep(interval); - goto retry; + pg->interval = 2; + err = SCSI_DH_RETRY; + } else { + /* Transitioning time exceeded, set port to standby */ + err = SCSI_DH_IO; + pg->state = TPGS_STATE_STANDBY; + pg->expiry = 0; } - /* Transitioning time exceeded, set port to standby */ - err = SCSI_DH_RETRY; - pg->state = TPGS_STATE_STANDBY; break; case TPGS_STATE_OFFLINE: /* Path unusable */ err = SCSI_DH_DEV_OFFLINED; + pg->expiry = 0; break; default: /* Useable path if active */ err = SCSI_DH_OK; + pg->expiry = 0; break; } kfree(buff); @@ -674,8 +737,8 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) struct scsi_sense_hdr sense_hdr; if (!(pg->tpgs & TPGS_MODE_EXPLICIT)) { - /* Only implicit ALUA supported, retry */ - return SCSI_DH_RETRY; + /* Only implicit ALUA supported */ + return SCSI_DH_OK; } switch (pg->state) { case TPGS_STATE_OPTIMIZED: @@ -701,8 +764,6 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) return SCSI_DH_NOSYS; break; } - /* Set state to transitioning */ - pg->state = TPGS_STATE_TRANSITIONING; retval = submit_stpg(sdev, pg->group_id, sense); if (retval) { @@ -724,6 +785,150 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) return SCSI_DH_RETRY; } +static void alua_rtpg_work(struct work_struct *work) +{ + struct alua_port_group *pg = + container_of(work, struct alua_port_group, rtpg_work.work); + struct scsi_device *sdev; + int err = SCSI_DH_OK; + unsigned long flags; + + spin_lock_irqsave(&pg->rtpg_lock, flags); + sdev = pg->rtpg_sdev; + if (!sdev) { + WARN_ON(pg->flags & ALUA_PG_RUN_RTPG || + pg->flags & ALUA_PG_RUN_STPG); + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + return; + } + if (pg->flags & ALUA_PG_RUN_RTPG) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + err = alua_rtpg(sdev, pg); + if (err == SCSI_DH_RETRY) { + queue_delayed_work(pg->work_q, &pg->rtpg_work, + pg->interval * HZ); + return; + } + spin_lock_irqsave(&pg->rtpg_lock, flags); + pg->flags &= ~ALUA_PG_RUN_RTPG; + if (err != SCSI_DH_OK) + pg->flags &= ~ALUA_PG_RUN_STPG; + } + if (pg->flags & ALUA_PG_RUN_STPG) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + queue_delayed_work(pg->work_q, &pg->stpg_work, 0); + return; + } + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + queue_delayed_work(pg->work_q, &pg->qdata_work, 0); +} + +static void alua_stpg_work(struct work_struct *work) +{ + struct alua_port_group *pg = + container_of(work, struct alua_port_group, stpg_work.work); + struct scsi_device *sdev; + int err = SCSI_DH_OK; + unsigned long flags; + + spin_lock_irqsave(&pg->rtpg_lock, flags); + sdev = pg->rtpg_sdev; + if (!sdev) { + WARN_ON(pg->flags & ALUA_PG_RUN_STPG); + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + return; + } + + if (pg->flags & ALUA_PG_RUN_STPG) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + err = alua_stpg(sdev, pg); + spin_lock_irqsave(&pg->rtpg_lock, flags); + pg->flags &= ~ALUA_PG_RUN_STPG; + if (err == SCSI_DH_RETRY) { + pg->flags |= ALUA_PG_RUN_RTPG; + pg->interval = 0; + } + } + if (pg->flags & ALUA_PG_RUN_RTPG) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + queue_delayed_work(pg->work_q, &pg->rtpg_work, + msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)); + return; + } + + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + queue_delayed_work(pg->work_q, &pg->qdata_work, 0); +} + +static void alua_qdata_work(struct work_struct *work) +{ + struct alua_port_group *pg = + container_of(work, struct alua_port_group, qdata_work.work); + struct scsi_device *sdev; + LIST_HEAD(qdata_list); + int err = SCSI_DH_OK; + struct alua_queue_data *qdata, *tmp; + unsigned long flags; + + spin_lock_irqsave(&pg->rtpg_lock, flags); + sdev = pg->rtpg_sdev; + if (WARN_ON(!sdev)) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + return; + } + if (pg->flags & ALUA_PG_RUN_RTPG) { + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + queue_delayed_work(pg->work_q, &pg->rtpg_work, + msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)); + return; + } + + list_splice_init(&pg->rtpg_list, &qdata_list); + pg->rtpg_sdev = NULL; + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + + list_for_each_entry_safe(qdata, tmp, &qdata_list, entry) { + list_del(&qdata->entry); + if (qdata->callback_fn) + qdata->callback_fn(qdata->callback_data, err); + kfree(qdata); + } + kref_put(&pg->kref, release_port_group); + scsi_device_put(sdev); +} + +static void alua_rtpg_queue(struct alua_port_group *pg, + struct scsi_device *sdev, + struct alua_queue_data *qdata) +{ + int start_queue = 0; + unsigned long flags; + + if (!pg) + return; + + kref_get(&pg->kref); + spin_lock_irqsave(&pg->rtpg_lock, flags); + if (qdata) { + list_add_tail(&qdata->entry, &pg->rtpg_list); + pg->flags |= ALUA_PG_RUN_STPG; + } + if (pg->rtpg_sdev == NULL) { + pg->interval = 0; + pg->flags |= ALUA_PG_RUN_RTPG; + kref_get(&pg->kref); + pg->rtpg_sdev = sdev; + scsi_device_get(sdev); + start_queue = 1; + } + spin_unlock_irqrestore(&pg->rtpg_lock, flags); + + if (start_queue) + queue_delayed_work(pg->work_q, &pg->rtpg_work, + msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)); + kref_put(&pg->kref, release_port_group); +} + /* * alua_initialize - Initialize ALUA state * @sdev: the device to be initialized @@ -733,22 +938,33 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) */ static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h) { - int err; - - err = alua_check_tpgs(sdev, h); - if (err != SCSI_DH_OK) - goto out; - - err = alua_check_vpd(sdev, h); - if (err != SCSI_DH_OK || !h->pg) - goto out; + struct alua_port_group *pg = NULL; - kref_get(&h->pg->kref); - err = alua_rtpg(sdev, h->pg, 0); - kref_put(&h->pg->kref, release_port_group); -out: - return err; + h->error = alua_check_tpgs(sdev, h); + if (h->error == SCSI_DH_OK) { + h->error = alua_check_vpd(sdev, h); + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg) { + rcu_read_unlock(); + h->tpgs = TPGS_MODE_NONE; + if (h->error == SCSI_DH_OK) + h->error = SCSI_DH_IO; + } else { + WARN_ON(h->error != SCSI_DH_OK); + kref_get(&pg->kref); + rcu_read_unlock(); + } + } + complete(&h->init_complete); + if (pg) { + pg->expiry = 0; + alua_rtpg_queue(pg, sdev, NULL); + kref_put(&pg->kref, release_port_group); + } + return h->error; } + /* * alua_set_params - set/unset the optimize flag * @sdev: device on the path to be activated @@ -765,6 +981,10 @@ static int alua_set_params(struct scsi_device *sdev, const char *params) unsigned int optimize = 0, argc; const char *p = params; int result = SCSI_DH_OK; + unsigned long flags; + + if (!h) + return -ENXIO; if ((sscanf(params, "%u", &argc) != 1) || (argc != 1)) return -EINVAL; @@ -782,10 +1002,12 @@ static int alua_set_params(struct scsi_device *sdev, const char *params) } rcu_read_unlock(); + spin_lock_irqsave(&pg->rtpg_lock, flags); if (optimize) pg->flags |= ALUA_OPTIMIZE_STPG; else pg->flags |= ~ALUA_OPTIMIZE_STPG; + spin_unlock_irqrestore(&pg->rtpg_lock, flags); return result; } @@ -809,24 +1031,49 @@ static int alua_activate(struct scsi_device *sdev, { struct alua_dh_data *h = sdev->handler_data; int err = SCSI_DH_OK; + struct alua_queue_data *qdata; + struct alua_port_group *pg; - if (!h->pg) + if (!h) { + err = SCSI_DH_NOSYS; goto out; + } - kref_get(&h->pg->kref); + qdata = kzalloc(sizeof(*qdata), GFP_KERNEL); + if (!qdata) { + err = SCSI_DH_RES_TEMP_UNAVAIL; + goto out; + } + qdata->callback_fn = fn; + qdata->callback_data = data; - if (optimize_stpg) - h->pg->flags |= ALUA_OPTIMIZE_STPG; + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg) { + rcu_read_unlock(); + wait_for_completion(&h->init_complete); + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg) { + rcu_read_unlock(); + kfree(qdata); + err = h->error; + goto out; + } + } + fn = NULL; + kref_get(&pg->kref); + rcu_read_unlock(); - err = alua_rtpg(sdev, h->pg, 1); - if (err != SCSI_DH_OK) { - kref_put(&h->pg->kref, release_port_group); - goto out; + if (optimize_stpg) { + unsigned long flags; + + spin_lock_irqsave(&pg->rtpg_lock, flags); + pg->flags |= ALUA_OPTIMIZE_STPG; + spin_unlock_irqrestore(&pg->rtpg_lock, flags); } - err = alua_stpg(sdev, h->pg); - if (err == SCSI_DH_RETRY) - err = alua_rtpg(sdev, h->pg, 1); - kref_put(&h->pg->kref, release_port_group); + alua_rtpg_queue(pg, sdev, qdata); + kref_put(&pg->kref, release_port_group); out: if (fn) fn(data, err); @@ -834,6 +1081,28 @@ out: } /* + * alua_check - check path status + * @sdev: device on the path to be checked + * + * Check the device status + */ +static void alua_check(struct scsi_device *sdev) +{ + struct alua_dh_data *h = sdev->handler_data; + struct alua_port_group *pg; + + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (pg) { + kref_get(&pg->kref); + rcu_read_unlock(); + alua_rtpg_queue(pg, sdev, NULL); + kref_put(&pg->kref, release_port_group); + } else + rcu_read_unlock(); +} + +/* * alua_prep_fn - request callback * * Fail I/O to all paths not in state @@ -842,14 +1111,22 @@ out: static int alua_prep_fn(struct scsi_device *sdev, struct request *req) { struct alua_dh_data *h = sdev->handler_data; - int state; + struct alua_port_group *pg; + int state = TPGS_STATE_OPTIMIZED; int ret = BLKPREP_OK; - if (!h->pg) + if (!h) return ret; - kref_get(&h->pg->kref); - state = h->pg->state; - kref_put(&h->pg->kref, release_port_group); + + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (pg) { + state = pg->state; + /* Defer I/O while rtpg_work is active */ + if (pg->rtpg_sdev) + state = TPGS_STATE_TRANSITIONING; + } + rcu_read_unlock(); if (state == TPGS_STATE_TRANSITIONING) ret = BLKPREP_DEFER; else if (state != TPGS_STATE_OPTIMIZED && @@ -874,11 +1151,13 @@ static int alua_bus_attach(struct scsi_device *sdev) h = kzalloc(sizeof(*h) , GFP_KERNEL); if (!h) return -ENOMEM; + spin_lock_init(&h->pg_lock); h->tpgs = TPGS_MODE_UNINITIALIZED; - h->pg = NULL; + rcu_assign_pointer(h->pg, NULL); h->rel_port = -1; - h->sdev = sdev; + h->error = SCSI_DH_OK; + init_completion(&h->init_complete); err = alua_initialize(sdev, h); if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED) goto failed; @@ -897,10 +1176,17 @@ failed: static void alua_bus_detach(struct scsi_device *sdev) { struct alua_dh_data *h = sdev->handler_data; + struct alua_port_group *pg; - if (h->pg) { - kref_put(&h->pg->kref, release_port_group); - h->pg = NULL; + spin_lock(&h->pg_lock); + pg = h->pg; + rcu_assign_pointer(h->pg, NULL); + spin_unlock(&h->pg_lock); + synchronize_rcu(); + if (pg) { + if (pg->rtpg_sdev) + flush_workqueue(pg->work_q); + kref_put(&pg->kref, release_port_group); } sdev->handler_data = NULL; kfree(h);