From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Benjamin Marzinski <bmarzins@redhat.com>
Date: Fri, 7 Oct 2022 12:35:44 -0500
Subject: [PATCH] libmultipath: enforce queue_mode bio for nmve:tcp paths

nvme:tcp devices set BLK_MQ_F_BLOCKING (they are the only block devices
which multipath supports that do so), meaning that block_mq expects that
they can block at certain points while servicing a request.  However,
due to the way device-mapper sets up its queue, it is not able to set
BLK_MQ_F_BLOCKING when it includes paths that set this flag.  Patches
were written to address this issue but they were rejected upstream

https://lore.kernel.org/linux-block/YcH%2FE4JNag0QYYAa@infradead.org/T/#t

The proposed solution was to have multipath use the bio queue_mode for
multipath devices that include nvme:tcp paths.

Multipath devices now automatically add the "queue_mode bio" feature if
they include nvme:tcp paths.  If a multipath devices was created with
"queue_mode rq", it will disallow the addition of nvme:tcp paths.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Reviewed-by: Martin Wilck <mwilck@suse.com>
---
 libmultipath/configure.c   | 17 ++++++++++++++++-
 libmultipath/structs_vec.c |  7 +++++++
 multipath/multipath.conf.5 |  4 +++-
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/libmultipath/configure.c b/libmultipath/configure.c
index c6803b40..193bf27d 100644
--- a/libmultipath/configure.c
+++ b/libmultipath/configure.c
@@ -296,6 +296,7 @@ static int wait_for_pending_paths(struct multipath *mpp,
 int setup_map(struct multipath *mpp, char **params, struct vectors *vecs)
 {
 	struct pathgroup * pgp;
+	struct path *pp;
 	struct config *conf;
 	int i, n_paths, marginal_pathgroups;
 	char *save_attr;
@@ -311,6 +312,14 @@ int setup_map(struct multipath *mpp, char **params, struct vectors *vecs)
 	if (mpp->disable_queueing && VECTOR_SIZE(mpp->paths) != 0)
 		mpp->disable_queueing = 0;
 
+	/* Force QUEUE_MODE_BIO for maps with nvme:tcp paths */
+	vector_foreach_slot(mpp->paths, pp, i) {
+		if (pp->bus == SYSFS_BUS_NVME &&
+		    pp->sg_id.proto_id == NVME_PROTOCOL_TCP) {
+			mpp->queue_mode = QUEUE_MODE_BIO;
+			break;
+		}
+	}
 	/*
 	 * If this map was created with add_map_without_path(),
 	 * mpp->hwe might not be set yet.
@@ -1191,6 +1200,13 @@ int coalesce_paths (struct vectors *vecs, vector mpvec, char *refwwid,
 			continue;
 		}
 
+		cmpp = find_mp_by_wwid(curmp, pp1->wwid);
+		if (cmpp && cmpp->queue_mode == QUEUE_MODE_RQ &&
+		    pp1->bus == SYSFS_BUS_NVME && pp1->sg_id.proto_id ==
+		    NVME_PROTOCOL_TCP) {
+			orphan_path(pp1, "nvme:tcp path not allowed with request queue_mode multipath device");
+			continue;
+		}
 		/*
 		 * at this point, we know we really got a new mp
 		 */
@@ -1229,7 +1245,6 @@ int coalesce_paths (struct vectors *vecs, vector mpvec, char *refwwid,
 		}
 		verify_paths(mpp);
 
-		cmpp = find_mp_by_wwid(curmp, mpp->wwid);
 		if (cmpp)
 			mpp->queue_mode = cmpp->queue_mode;
 		if (setup_map(mpp, &params, vecs)) {
diff --git a/libmultipath/structs_vec.c b/libmultipath/structs_vec.c
index 85d97ac1..4a32b405 100644
--- a/libmultipath/structs_vec.c
+++ b/libmultipath/structs_vec.c
@@ -262,6 +262,13 @@ int adopt_paths(vector pathvec, struct multipath *mpp)
 			}
 			if (pp->initialized == INIT_REMOVED)
 				continue;
+			if (mpp->queue_mode == QUEUE_MODE_RQ &&
+			    pp->bus == SYSFS_BUS_NVME &&
+			    pp->sg_id.proto_id == NVME_PROTOCOL_TCP) {
+				condlog(2, "%s: mulitpath device %s created with request queue_mode. Unable to add nvme:tcp paths",
+					pp->dev, mpp->alias);
+				continue;
+			}
 			if (!mpp->paths && !(mpp->paths = vector_alloc()))
 				goto err;
 
diff --git a/multipath/multipath.conf.5 b/multipath/multipath.conf.5
index 7af53588..01904feb 100644
--- a/multipath/multipath.conf.5
+++ b/multipath/multipath.conf.5
@@ -472,7 +472,9 @@ Before kernel 4.20 The default depends on the kernel parameter
 \fBdm_mod.use_blk_mq\fR. It is \fImq\fR if the latter is set, and \fIrq\fR
 otherwise. Since kernel 4.20, \fIrq\fR and \fImq\fR both correspond to
 block-multiqueue. Once a multipath device has been created, its queue_mode
-cannot be changed.
+cannot be changed. \fInvme:tcp\fR paths are only supported in multipath
+devices with queue_mode set to \fIbio\fR. multipath will automatically
+set this when creating a device with \fInvme:tcp\fR paths.
 .TP
 The default is: \fB<unset>\fR
 .RE