From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hannes Reinecke Subject: [PATCH 16/23] scsi_dh_alua: Recheck state on unit attention Date: Mon, 8 Feb 2016 15:34:39 +0100 Message-ID: <1454942086-128704-17-git-send-email-hare@suse.de> References: <1454942086-128704-1-git-send-email-hare@suse.de> Return-path: Received: from mx2.suse.de ([195.135.220.15]:42711 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753540AbcBHOey (ORCPT ); Mon, 8 Feb 2016 09:34:54 -0500 In-Reply-To: <1454942086-128704-1-git-send-email-hare@suse.de> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: "Martin K. Petersen" Cc: Christoph Hellwig , Bart van Assche , James Bottomley , linux-scsi@vger.kernel.org, Ewan Milne , Hannes Reinecke , Hannes Reinecke When we receive a unit attention code of 'ALUA state changed' we should recheck the state, as it might be due to an implicit ALUA state transition. This allows us to return NEEDS_RETRY instead of ADD_TO_MLQUEUE, allowing to terminate the retries after a certain time. At the same time a workqueue item might already be queued, which should be started immediately to avoid any delays. Reviewed-by: Christoph Hellwig Signed-off-by: Hannes Reinecke --- drivers/scsi/device_handler/scsi_dh_alua.c | 76 +++++++++++++++++++++++++----- 1 file changed, 64 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index f6bb1c0..8a896af 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -120,7 +120,8 @@ struct alua_queue_data { static void alua_rtpg_work(struct work_struct *work); static void alua_rtpg_queue(struct alua_port_group *pg, struct scsi_device *sdev, - struct alua_queue_data *qdata); + struct alua_queue_data *qdata, bool force); +static void alua_check(struct scsi_device *sdev, bool force); static void release_port_group(struct kref *kref) { @@ -368,7 +369,7 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h, } if (sdev->synchronous_alua) pg->flags |= ALUA_SYNC_STPG; - alua_rtpg_queue(h->pg, sdev, NULL); + alua_rtpg_queue(h->pg, sdev, NULL, true); spin_unlock(&h->pg_lock); if (old_pg) @@ -404,18 +405,24 @@ 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 */ - return ADD_TO_MLQUEUE; + alua_check(sdev, false); + return NEEDS_RETRY; + } break; case UNIT_ATTENTION: - if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) + if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) { /* - * Power On, Reset, or Bus Device Reset, just retry. + * Power On, Reset, or Bus Device Reset. + * Might have obscured a state transition, + * so schedule a recheck. */ + alua_check(sdev, true); return ADD_TO_MLQUEUE; + } if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x04) /* * Device internal reset @@ -426,16 +433,20 @@ static int alua_check_sense(struct scsi_device *sdev, * Mode Parameters Changed */ return ADD_TO_MLQUEUE; - if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06) + if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06) { /* * ALUA state changed */ + alua_check(sdev, true); return ADD_TO_MLQUEUE; - if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07) + } + if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07) { /* * Implicit ALUA state transition failed */ + alua_check(sdev, true); return ADD_TO_MLQUEUE; + } if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x03) /* * Inquiry data has changed @@ -710,7 +721,7 @@ static void alua_rtpg_work(struct work_struct *work) spin_unlock_irqrestore(&pg->lock, flags); err = alua_rtpg(sdev, pg); spin_lock_irqsave(&pg->lock, flags); - if (err == SCSI_DH_RETRY) { + if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) { pg->flags &= ~ALUA_PG_RUNNING; pg->flags |= ALUA_PG_RUN_RTPG; spin_unlock_irqrestore(&pg->lock, flags); @@ -726,7 +737,7 @@ static void alua_rtpg_work(struct work_struct *work) spin_unlock_irqrestore(&pg->lock, flags); err = alua_stpg(sdev, pg); spin_lock_irqsave(&pg->lock, flags); - if (err == SCSI_DH_RETRY) { + if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) { pg->flags |= ALUA_PG_RUN_RTPG; pg->interval = 0; pg->flags &= ~ALUA_PG_RUNNING; @@ -756,7 +767,7 @@ static void alua_rtpg_work(struct work_struct *work) static void alua_rtpg_queue(struct alua_port_group *pg, struct scsi_device *sdev, - struct alua_queue_data *qdata) + struct alua_queue_data *qdata, bool force) { int start_queue = 0; unsigned long flags; @@ -769,6 +780,7 @@ static void alua_rtpg_queue(struct alua_port_group *pg, if (qdata) { list_add_tail(&qdata->entry, &pg->rtpg_list); pg->flags |= ALUA_PG_RUN_STPG; + force = true; } if (pg->rtpg_sdev == NULL) { pg->interval = 0; @@ -777,7 +789,15 @@ static void alua_rtpg_queue(struct alua_port_group *pg, pg->rtpg_sdev = sdev; scsi_device_get(sdev); start_queue = 1; + } else if (!(pg->flags & ALUA_PG_RUN_RTPG) && force) { + pg->flags |= ALUA_PG_RUN_RTPG; + /* Do not queue if the worker is already running */ + if (!(pg->flags & ALUA_PG_RUNNING)) { + kref_get(&pg->kref); + start_queue = 1; + } } + if (pg->flags & ALUA_SYNC_STPG) alua_wq = kaluad_sync_wq; spin_unlock_irqrestore(&pg->lock, flags); @@ -892,7 +912,7 @@ static int alua_activate(struct scsi_device *sdev, rcu_read_unlock(); mutex_unlock(&h->init_mutex); - alua_rtpg_queue(pg, sdev, qdata); + alua_rtpg_queue(pg, sdev, qdata, true); kref_put(&pg->kref, release_port_group); out: if (fn) @@ -901,6 +921,38 @@ 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, bool force) +{ + struct alua_dh_data *h = sdev->handler_data; + struct alua_port_group *pg; + + /* + * This is run asynchronously, and might race with + * alua_initialize() which provides the same functionality. + * So skip it if alua_initialize() is running. + */ + if (!mutex_trylock(&h->init_mutex)) + return; + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg || !kref_get_unless_zero(&pg->kref)) { + rcu_read_unlock(); + mutex_unlock(&h->init_mutex); + return; + } + rcu_read_unlock(); + mutex_unlock(&h->init_mutex); + + alua_rtpg_queue(pg, sdev, NULL, force); + kref_put(&pg->kref, release_port_group); +} + +/* * alua_prep_fn - request callback * * Fail I/O to all paths not in state -- 1.8.5.6