[PATCHv4 1/8] scsi_error: count medium access timeout only once per EH run

[Hannes Reinecke <hare@suse.de>]

The current medium access timeout counter will be increased for
each command, so if there are enough failed commands we'll hit
the medium access timeout for even a single device failure and
the following kernel message is displayed:

sd H:C:T:L: [sdXY] Medium access timeout failure. Offlining disk!

Fix this by making the timeout per EH run, ie the counter will
only be increased once per device and EH run.

Fixes: 18a4d0a ("[SCSI] Handle disk devices which can not process medium access commands")
Cc: Ewan Milne <emilne@redhat.com>
Cc: Lawrence Obermann <loberman@redhat.com>
Cc: Benjamin Block <bblock@linux.vnet.ibm.com>
Cc: Steffen Maier <maier@linux.vnet.ibm.com>
Signed-off-by: Hannes Reinecke <hare@suse.com>
---
 drivers/scsi/scsi_error.c  | 23 ++++++++++++++++++++++-
 drivers/scsi/sd.c          | 22 ++++++++++++++++++----
 drivers/scsi/sd.h          |  1 +
 include/scsi/scsi_driver.h |  2 +-
 4 files changed, 42 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f2cafae..390a6bc 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -221,6 +221,26 @@ static int scsi_host_eh_past_deadline(struct Scsi_Host *shost)
 }
 
 /**
+ * scsi_eh_reset - call into ->eh_action to reset internal counters
+ * @scmd:	scmd to run eh on.
+ *
+ * The scsi driver might be carrying internal state about the
+ * devices, so we need to call into the driver to reset the
+ * internal state once the error handler is started.
+ */
+static int scsi_eh_reset(struct scsi_cmnd *scmd)
+{
+	int rtn = SUCCESS;
+
+	if (!blk_rq_is_passthrough(scmd->request)) {
+		struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
+		if (sdrv->eh_action)
+			rtn = sdrv->eh_action(scmd, rtn, true);
+	}
+	return rtn;
+}
+
+/**
  * scsi_eh_scmd_add - add scsi cmd to error handling.
  * @scmd:	scmd to run eh on.
  * @eh_flag:	optional SCSI_EH flag.
@@ -249,6 +269,7 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag)
 	if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED)
 		eh_flag &= ~SCSI_EH_CANCEL_CMD;
 	scmd->eh_eflags |= eh_flag;
+	scsi_eh_reset(scmd);
 	list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q);
 	shost->host_failed++;
 	scsi_eh_wakeup(shost);
@@ -1107,7 +1128,7 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
 	if (!blk_rq_is_passthrough(scmd->request)) {
 		struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
 		if (sdrv->eh_action)
-			rtn = sdrv->eh_action(scmd, rtn);
+			rtn = sdrv->eh_action(scmd, rtn, false);
 	}
 	return rtn;
 }
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d277e86..656a32d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -115,7 +115,7 @@
 static int sd_init_command(struct scsi_cmnd *SCpnt);
 static void sd_uninit_command(struct scsi_cmnd *SCpnt);
 static int sd_done(struct scsi_cmnd *);
-static int sd_eh_action(struct scsi_cmnd *, int);
+static int sd_eh_action(struct scsi_cmnd *, int, bool);
 static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
 static void scsi_disk_release(struct device *cdev);
 static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
@@ -1689,18 +1689,29 @@ static int sd_pr_clear(struct block_device *bdev, u64 key)
  *	sd_eh_action - error handling callback
  *	@scmd:		sd-issued command that has failed
  *	@eh_disp:	The recovery disposition suggested by the midlayer
+ *	@restart:	SCSI EH has been restarted
  *
  *	This function is called by the SCSI midlayer upon completion of an
  *	error test command (currently TEST UNIT READY). The result of sending
  *	the eh command is passed in eh_disp.  We're looking for devices that
  *	fail medium access commands but are OK with non access commands like
  *	test unit ready (so wrongly see the device as having a successful
- *	recovery)
+ *	recovery).
+ *	We have to be careful to count a medium access failure only once
+ *	per device and SCSI EH run; there might be several timed out
+ *	commands which will cause the 'max_medium_access_timeouts' counter
+ *	to trigger after the first SCSI EH run already and set the device
+ *	to offline.
  **/
-static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp)
+static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp, bool restart)
 {
 	struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk);
 
+	if (restart) {
+		/* New SCSI EH run, reset gate variable */
+		sdkp->ignore_medium_access_errors = false;
+		return eh_disp;
+	}
 	if (!scsi_device_online(scmd->device) ||
 	    !scsi_medium_access_command(scmd) ||
 	    host_byte(scmd->result) != DID_TIME_OUT ||
@@ -1714,7 +1725,10 @@ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp)
 	 * process of recovering or has it suffered an internal failure
 	 * that prevents access to the storage medium.
 	 */
-	sdkp->medium_access_timed_out++;
+	if (!sdkp->ignore_medium_access_errors) {
+		sdkp->medium_access_timed_out++;
+		sdkp->ignore_medium_access_errors = true;
+	}
 
 	/*
 	 * If the device keeps failing read/write commands but TEST UNIT
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4dac35e..0cf9680 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -106,6 +106,7 @@ struct scsi_disk {
 	unsigned	rc_basis: 2;
 	unsigned	zoned: 2;
 	unsigned	urswrz : 1;
+	unsigned	ignore_medium_access_errors : 1;
 };
 #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev)
 
diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h
index 891a658..d5e0012 100644
--- a/include/scsi/scsi_driver.h
+++ b/include/scsi/scsi_driver.h
@@ -15,7 +15,7 @@ struct scsi_driver {
 	int (*init_command)(struct scsi_cmnd *);
 	void (*uninit_command)(struct scsi_cmnd *);
 	int (*done)(struct scsi_cmnd *);
-	int (*eh_action)(struct scsi_cmnd *, int);
+	int (*eh_action)(struct scsi_cmnd *, int, bool);
 };
 #define to_scsi_driver(drv) \
 	container_of((drv), struct scsi_driver, gendrv)
-- 
1.8.5.6