From: Hannes Reinecke <hare@suse.de>
Subject: multipath: Evaluate request result and sense code
References: FATE#303695,bnc#433920,bnc#442001
Patch-mainline: not yet

Currently we're updating the request result upon completion
only for BLK_PC requests. This makes it impossible for the
upper layers to reliable detect the real cause for an
I/O failure. By attaching the result and the sense to all
requests we can update multipathing to make some more elaborate
choices on how to handle I/O errors.
This also solves a potential data corruption with multipathing
and persistent reservations. When queue_if_no_path is active
multipath will queue any I/O failure (including those failed
with RESERVATION CONFLICT) until the reservation status changes.
But by then I/O might have been ongoing on the other paths,
thus the delayed submission will severely corrupt your data.

Signed-off-by: Hannes Reinecke <hare@suse.de>

---
 drivers/md/dm-mpath.c   |   51 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/scsi/scsi_lib.c |   28 +++++++++++---------------
 2 files changed, 63 insertions(+), 16 deletions(-)

--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -19,6 +19,7 @@
 #include <linux/time.h>
 #include <linux/workqueue.h>
 #include <scsi/scsi_dh.h>
+#include <scsi/scsi_eh.h>
 #include <asm/atomic.h>
 
 #define DM_MSG_PREFIX "multipath"
@@ -104,6 +105,7 @@ struct multipath {
 struct dm_mpath_io {
 	struct pgpath *pgpath;
 	size_t nr_bytes;
+	char sense[SCSI_SENSE_BUFFERSIZE];
 };
 
 typedef int (*action_fn) (struct pgpath *pgpath);
@@ -995,6 +997,9 @@ static int multipath_map(struct dm_targe
 
 	map_context->ptr = mpio;
 	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	/* Always attach a sense buffer */
+	if (!clone->sense)
+		clone->sense = mpio->sense;
 	r = map_io(m, clone, mpio, 0);
 	if (r < 0 || r == DM_MAPIO_REQUEUE)
 		mempool_free(mpio, m->mpio_pool);
@@ -1293,6 +1298,44 @@ static void activate_path(struct work_st
 }
 
 /*
+ * Evaluate scsi return code
+ */
+static int eval_scsi_error(int result, char *sense, int sense_len)
+{
+	struct scsi_sense_hdr sshdr;
+	int r = DM_ENDIO_REQUEUE;
+
+	if (host_byte(result) != DID_OK)
+		return r;
+
+	if (msg_byte(result) != COMMAND_COMPLETE)
+		return r;
+
+	if (status_byte(result) == RESERVATION_CONFLICT)
+		/* Do not retry here, possible data corruption */
+		return -EIO;
+
+#if defined(CONFIG_SCSI) || defined(CONFIG_SCSI_MODULE)
+	if (status_byte(result) == CHECK_CONDITION &&
+	    !scsi_normalize_sense(sense, sense_len, &sshdr)) {
+
+		switch (sshdr.sense_key) {
+		case MEDIUM_ERROR:
+		case DATA_PROTECT:
+		case BLANK_CHECK:
+		case COPY_ABORTED:
+		case VOLUME_OVERFLOW:
+		case MISCOMPARE:
+			r = -EIO;
+			break;
+		}
+	}
+#endif
+
+	return r;
+}
+
+/*
  * end_io handling
  */
 static int do_end_io(struct multipath *m, struct request *clone,
@@ -1318,6 +1361,10 @@ static int do_end_io(struct multipath *m
 	if (error == -EOPNOTSUPP)
 		return error;
 
+	r = eval_scsi_error(clone->errors, clone->sense, clone->sense_len);
+	if (r != DM_ENDIO_REQUEUE)
+		return r;
+
 	if (mpio->pgpath)
 		fail_path(mpio->pgpath);
 
@@ -1344,6 +1391,10 @@ static int multipath_end_io(struct dm_ta
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
+	if (clone->sense == mpio->sense) {
+		clone->sense = NULL;
+		clone->sense_len = 0;
+	}
 	mempool_free(mpio, m->mpio_pool);
 
 	return r;
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -722,23 +722,19 @@ void scsi_io_completion(struct scsi_cmnd
 			sense_deferred = scsi_sense_is_deferred(&sshdr);
 	}
 
-	if (blk_pc_request(req)) { /* SG_IO ioctl from block level */
-		req->errors = result;
-		if (result) {
-			if (sense_valid && req->sense) {
-				/*
-				 * SG_IO wants current and deferred errors
-				 */
-				int len = 8 + cmd->sense_buffer[7];
+	req->errors = result;
+	if (sense_valid && req->sense) {
+		int len = 8 + cmd->sense_buffer[7];
+
+		if (len > SCSI_SENSE_BUFFERSIZE)
+			len = SCSI_SENSE_BUFFERSIZE;
+		memcpy(req->sense, cmd->sense_buffer,  len);
+		req->sense_len = len;
+	}
 
-				if (len > SCSI_SENSE_BUFFERSIZE)
-					len = SCSI_SENSE_BUFFERSIZE;
-				memcpy(req->sense, cmd->sense_buffer,  len);
-				req->sense_len = len;
-			}
-			if (!sense_deferred)
-				error = -EIO;
-		}
+	if (blk_pc_request(req)) { /* SG_IO ioctl from block level */
+		if ((result) && (!sense_deferred))
+			error = -EIO;
 
 		req->resid_len = scsi_get_resid(cmd);