[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230723234422.1629194-9-haowenchao2@huawei.com>
Date: Mon, 24 Jul 2023 07:44:17 +0800
From: Wenchao Hao <haowenchao2@...wei.com>
To: "James E . J . Bottomley" <jejb@...ux.ibm.com>,
"Martin K . Petersen" <martin.petersen@...cle.com>,
Hannes Reinecke <hare@...e.de>, <linux-scsi@...r.kernel.org>,
<linux-kernel@...r.kernel.org>
CC: Dan Carpenter <error27@...il.com>, <louhongxiang@...wei.com>,
Wenchao Hao <haowenchao2@...wei.com>
Subject: [PATCH 08/13] scsi:scsi_error: Add LUN based error handler based previous helper
Add LUN based error handler, drivers can call scsi_device_setup_eh() in
its slave_alloc() to setup it's LUN based error handler; call
scsi_device_clear_eh() in its slave_destroy() to clear LUN based error
handler.
Signed-off-by: Wenchao Hao <haowenchao2@...wei.com>
---
drivers/scsi/scsi_error.c | 152 ++++++++++++++++++++++++++++++++++++++
drivers/scsi/scsi_priv.h | 2 +
2 files changed, 154 insertions(+)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 00da77f3f3f8..bb6f05ba199b 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2743,3 +2743,155 @@ bool scsi_get_sense_info_fld(const u8 *sense_buffer, int sb_len,
}
}
EXPORT_SYMBOL(scsi_get_sense_info_fld);
+
+struct scsi_lun_eh {
+ spinlock_t eh_lock;
+ unsigned int eh_num;
+ struct list_head eh_cmd_q;
+ struct scsi_device *sdev;
+ struct work_struct eh_handle_work;
+};
+
+/*
+ * error handle strategy based on LUN, following steps
+ * is applied to recovery error commands in list:
+ * check sense data
+ * send start unit
+ * reset lun
+ * if there are still error commands, it would fallback to
+ * target based or host based error handle for further recovery.
+ */
+static void sdev_eh_work(struct work_struct *work)
+{
+ unsigned long flags;
+ struct scsi_lun_eh *luneh =
+ container_of(work, struct scsi_lun_eh, eh_handle_work);
+ struct scsi_device *sdev = luneh->sdev;
+ struct scsi_device_eh *eh = sdev->eh;
+ struct Scsi_Host *shost = sdev->host;
+ struct scsi_cmnd *scmd, *next;
+ LIST_HEAD(eh_work_q);
+ LIST_HEAD(eh_done_q);
+
+ spin_lock_irqsave(&luneh->eh_lock, flags);
+ list_splice_init(&luneh->eh_cmd_q, &eh_work_q);
+ spin_unlock_irqrestore(&luneh->eh_lock, flags);
+
+ if (scsi_sdev_eh(sdev, &eh_work_q, &eh_done_q))
+ goto out_flush_done;
+
+ /*
+ * fallback to target or host based error handle
+ */
+ SCSI_LOG_ERROR_RECOVERY(2, sdev_printk(KERN_INFO, sdev,
+ "%s:luneh fallback to further recovery\n", current->comm));
+ list_for_each_entry_safe(scmd, next, &eh_work_q, eh_entry) {
+ list_del_init(&scmd->eh_entry);
+
+ if (scsi_host_in_recovery(shost) ||
+ __scsi_eh_scmd_add_starget(scmd))
+ __scsi_eh_scmd_add(scmd);
+ }
+
+ eh->get_sense_done = 1;
+ eh->stu_done = 1;
+ eh->reset_done = 1;
+
+out_flush_done:
+ scsi_eh_flush_done_q(&eh_done_q);
+ spin_lock_irqsave(&luneh->eh_lock, flags);
+ luneh->eh_num = 0;
+ spin_unlock_irqrestore(&luneh->eh_lock, flags);
+}
+static void sdev_eh_add_cmnd(struct scsi_cmnd *scmd)
+{
+ unsigned long flags;
+ struct scsi_lun_eh *luneh;
+ struct scsi_device *sdev = scmd->device;
+
+ luneh = (struct scsi_lun_eh *)sdev->eh->driver_data;
+
+ spin_lock_irqsave(&luneh->eh_lock, flags);
+ list_add_tail(&scmd->eh_entry, &luneh->eh_cmd_q);
+ luneh->eh_num++;
+ spin_unlock_irqrestore(&luneh->eh_lock, flags);
+}
+static int sdev_eh_is_busy(struct scsi_device *sdev)
+{
+ int ret = 0;
+ unsigned long flags;
+ struct scsi_lun_eh *luneh;
+
+ if (!sdev->eh)
+ return 0;
+
+ luneh = (struct scsi_lun_eh *)sdev->eh->driver_data;
+
+ spin_lock_irqsave(&luneh->eh_lock, flags);
+ ret = luneh->eh_num;
+ spin_unlock_irqrestore(&luneh->eh_lock, flags);
+
+ return ret;
+}
+static int sdev_eh_wakeup(struct scsi_device *sdev)
+{
+ unsigned long flags;
+ unsigned int nr_error;
+ unsigned int nr_busy;
+ struct scsi_lun_eh *luneh;
+
+ luneh = (struct scsi_lun_eh *)sdev->eh->driver_data;
+
+ spin_lock_irqsave(&luneh->eh_lock, flags);
+ nr_error = luneh->eh_num;
+ spin_unlock_irqrestore(&luneh->eh_lock, flags);
+
+ nr_busy = scsi_device_busy(sdev);
+
+ if (!nr_error || nr_busy != nr_error) {
+ SCSI_LOG_ERROR_RECOVERY(5, sdev_printk(KERN_INFO, sdev,
+ "%s:luneh: do not wake up, busy/error: %d/%d\n",
+ current->comm, nr_busy, nr_error));
+ return 0;
+ }
+
+ SCSI_LOG_ERROR_RECOVERY(2, sdev_printk(KERN_INFO, sdev,
+ "%s:luneh: waking up, busy/error: %d/%d\n",
+ current->comm, nr_busy, nr_error));
+
+ return schedule_work(&luneh->eh_handle_work);
+}
+
+int scsi_device_setup_eh(struct scsi_device *sdev)
+{
+ struct scsi_device_eh *eh;
+ struct scsi_lun_eh *luneh;
+
+ eh = kzalloc(sizeof(struct scsi_device_eh) + sizeof(struct scsi_lun_eh),
+ GFP_KERNEL);
+ if (!eh) {
+ sdev_printk(KERN_ERR, sdev, "failed to setup error handle\n");
+ return -ENOMEM;
+ }
+ luneh = (struct scsi_lun_eh *)eh->driver_data;
+
+ eh->add_cmnd = sdev_eh_add_cmnd;
+ eh->is_busy = sdev_eh_is_busy;
+ eh->wakeup = sdev_eh_wakeup;
+
+ luneh->sdev = sdev;
+ spin_lock_init(&luneh->eh_lock);
+ INIT_LIST_HEAD(&luneh->eh_cmd_q);
+ INIT_WORK(&luneh->eh_handle_work, sdev_eh_work);
+
+ sdev->eh = eh;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(scsi_device_setup_eh);
+
+void scsi_device_clear_eh(struct scsi_device *sdev)
+{
+ kfree(sdev->eh);
+}
+EXPORT_SYMBOL_GPL(scsi_device_clear_eh);
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 484c2f61ffe7..7d7d95a6f526 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -101,6 +101,8 @@ int scsi_eh_get_sense(struct list_head *work_q,
struct list_head *done_q);
bool scsi_noretry_cmd(struct scsi_cmnd *scmd);
void scsi_eh_done(struct scsi_cmnd *scmd);
+int scsi_device_setup_eh(struct scsi_device *sdev);
+void scsi_device_clear_eh(struct scsi_device *sdev);
/* scsi_lib.c */
extern int scsi_maybe_unblock_host(struct scsi_device *sdev);
--
2.35.3
Powered by blists - more mailing lists