diff options
author | Martin Wilck <mwilck@suse.com> | 2021-05-14 17:32:14 +0200 |
---|---|---|
committer | Martin K. Petersen <martin.petersen@oracle.com> | 2021-05-22 05:06:29 +0200 |
commit | ee8868c5c78f16fb726775741aeab8a233373332 (patch) | |
tree | 9add38ad000c99a58999a73f0cbe33ec780223b1 | |
parent | scsi: qla2xxx: Remove redundant assignment to rval (diff) | |
download | linux-ee8868c5c78f16fb726775741aeab8a233373332.tar.xz linux-ee8868c5c78f16fb726775741aeab8a233373332.zip |
scsi: scsi_dh_alua: Retry RTPG on a different path after failure
If an RTPG fails, we can't infer anything wrt. the state of the ports in
the port group except that we were unable to reach the one port on which
the RTPG had failed. "offline" is just a secondary port state, which means
that we can't infer the state of any port in the PG from the failure (in
fact, even the failed port might still be in "active/optimized" primary
port access state).
Therefore, when we encounter an RTPG failure, we should retry the RTPG on a
different port. This avoids falsely setting port states to offline for
unreachable ports. To do this, ports on which an RTPG has failed are
temporarily set to "disabled" to avoid repeating the failed I/O on the same
target port. Once the RTPG has either succeeded on one port or failed on
all ports of the PG, the ports are enabled again.
Link: https://lore.kernel.org/r/20210514153214.5626-1-mwilck@suse.com
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
-rw-r--r-- | drivers/scsi/device_handler/scsi_dh_alua.c | 70 |
1 files changed, 67 insertions, 3 deletions
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index efa8c0381476..03b7f255644f 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -88,6 +88,7 @@ struct alua_dh_data { struct scsi_device *sdev; int init_error; struct mutex init_mutex; + bool disabled; }; struct alua_queue_data { @@ -569,6 +570,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) kfree(buff); if (driver_byte(retval) == DRIVER_ERROR) return SCSI_DH_DEV_TEMP_BUSY; + if (host_byte(retval) == DID_NO_CONNECT) + return SCSI_DH_RES_TEMP_UNAVAIL; return SCSI_DH_IO; } @@ -807,6 +810,51 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) return SCSI_DH_RETRY; } +static bool alua_rtpg_select_sdev(struct alua_port_group *pg) +{ + struct alua_dh_data *h; + struct scsi_device *sdev = NULL; + + lockdep_assert_held(&pg->lock); + if (WARN_ON(!pg->rtpg_sdev)) + return false; + + /* + * RCU protection isn't necessary for dh_list here + * as we hold pg->lock, but for access to h->pg. + */ + rcu_read_lock(); + list_for_each_entry_rcu(h, &pg->dh_list, node) { + if (!h->sdev) + continue; + if (h->sdev == pg->rtpg_sdev) { + h->disabled = true; + continue; + } + if (rcu_dereference(h->pg) == pg && + !h->disabled && + !scsi_device_get(h->sdev)) { + sdev = h->sdev; + break; + } + } + rcu_read_unlock(); + + if (!sdev) { + pr_warn("%s: no device found for rtpg\n", + (pg->device_id_len ? + (char *)pg->device_id_str : "(nameless PG)")); + return false; + } + + sdev_printk(KERN_INFO, sdev, "rtpg retry on different device\n"); + + scsi_device_put(pg->rtpg_sdev); + pg->rtpg_sdev = sdev; + + return true; +} + static void alua_rtpg_work(struct work_struct *work) { struct alua_port_group *pg = @@ -815,6 +863,7 @@ static void alua_rtpg_work(struct work_struct *work) LIST_HEAD(qdata_list); int err = SCSI_DH_OK; struct alua_queue_data *qdata, *tmp; + struct alua_dh_data *h; unsigned long flags; spin_lock_irqsave(&pg->lock, flags); @@ -848,9 +897,18 @@ static void alua_rtpg_work(struct work_struct *work) } err = alua_rtpg(sdev, pg); spin_lock_irqsave(&pg->lock, flags); - if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) { + + /* If RTPG failed on the current device, try using another */ + if (err == SCSI_DH_RES_TEMP_UNAVAIL && + alua_rtpg_select_sdev(pg)) + err = SCSI_DH_IMM_RETRY; + + if (err == SCSI_DH_RETRY || err == SCSI_DH_IMM_RETRY || + pg->flags & ALUA_PG_RUN_RTPG) { pg->flags &= ~ALUA_PG_RUNNING; - if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG)) + if (err == SCSI_DH_IMM_RETRY) + pg->interval = 0; + else if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG)) pg->interval = ALUA_RTPG_RETRY_DELAY; pg->flags |= ALUA_PG_RUN_RTPG; spin_unlock_irqrestore(&pg->lock, flags); @@ -878,6 +936,12 @@ static void alua_rtpg_work(struct work_struct *work) } list_splice_init(&pg->rtpg_list, &qdata_list); + /* + * We went through an RTPG, for good or bad. + * Re-enable all devices for the next attempt. + */ + list_for_each_entry(h, &pg->dh_list, node) + h->disabled = false; pg->rtpg_sdev = NULL; spin_unlock_irqrestore(&pg->lock, flags); @@ -962,6 +1026,7 @@ static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h) int err = SCSI_DH_DEV_UNSUPP, tpgs; mutex_lock(&h->init_mutex); + h->disabled = false; tpgs = alua_check_tpgs(sdev); if (tpgs != TPGS_MODE_NONE) err = alua_check_vpd(sdev, h, tpgs); @@ -1080,7 +1145,6 @@ static void alua_check(struct scsi_device *sdev, bool force) return; } rcu_read_unlock(); - alua_rtpg_queue(pg, sdev, NULL, force); kref_put(&pg->kref, release_port_group); } |