diff mbox series

[08/13] scsi:scsi_error: Add LUN based error handler based previous helper

Message ID 20230723234422.1629194-9-haowenchao2@huawei.com
State New
Headers show
Series scsi: Support LUN/target based error handle | expand

Commit Message

Wenchao Hao July 23, 2023, 11:44 p.m. UTC
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@huawei.com>
---
 drivers/scsi/scsi_error.c | 152 ++++++++++++++++++++++++++++++++++++++
 drivers/scsi/scsi_priv.h  |   2 +
 2 files changed, 154 insertions(+)
diff mbox series

Patch

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);