linux-hardening - [PATCH v9 3/9] nvme-fc: marginal path handling

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250813200744.17975-4-bgurney@redhat.com>
Date: Wed, 13 Aug 2025 16:07:38 -0400
From: Bryan Gurney <bgurney@...hat.com>
To: linux-nvme@...ts.infradead.org,
	kbusch@...nel.org,
	hch@....de,
	sagi@...mberg.me,
	axboe@...nel.dk
Cc: james.smart@...adcom.com,
	njavali@...vell.com,
	linux-scsi@...r.kernel.org,
	hare@...e.de,
	linux-hardening@...r.kernel.org,
	kees@...nel.org,
	gustavoars@...nel.org,
	bgurney@...hat.com,
	jmeneghi@...hat.com,
	emilne@...hat.com
Subject: [PATCH v9 3/9] nvme-fc: marginal path handling

From: Hannes Reinecke <hare@...nel.org>

FPIN LI (link integrity) messages are received when the attached
fabric detects hardware errors. In response to these messages I/O
should be directed away from the affected ports, and only used
if the 'optimized' paths are unavailable.
To handle this a new controller flag 'NVME_CTRL_MARGINAL' is added
which will cause the multipath scheduler to skip these paths when
checking for 'optimized' paths. They are, however, still eligible
for non-optimized path selected. The flag is cleared upon reset as then the
faulty hardware might be replaced.

Signed-off-by: Hannes Reinecke <hare@...nel.org>
Tested-by: Bryan Gurney <bgurney@...hat.com>
Reviewed-by: John Meneghini <jmeneghi@...hat.com>
Tested-by: Muneendra Kumar <muneendra.kumar@...adcom.com>
---
 drivers/nvme/host/fc.c        |  4 ++++
 drivers/nvme/host/multipath.c | 17 +++++++++++------
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 3e12d4683ac7..bf6188b554ce 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -786,6 +786,10 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		"Reconnect", ctrl->cnum);
 
 	set_bit(ASSOC_FAILED, &ctrl->flags);
+
+	/* clear 'marginal' flag as controller will be reset */
+	clear_bit(NVME_CTRL_MARGINAL, &ctrl->flags);
+
 	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 3da980dc60d9..c042a9a11ce3 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -324,11 +324,14 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
 
 		switch (ns->ana_state) {
 		case NVME_ANA_OPTIMIZED:
-			if (distance < found_distance) {
-				found_distance = distance;
-				found = ns;
+			if (!nvme_ctrl_is_marginal(ns->ctrl)) {
+				if (distance < found_distance) {
+					found_distance = distance;
+					found = ns;
+				}
+				break;
 			}
-			break;
+			fallthrough;
 		case NVME_ANA_NONOPTIMIZED:
 			if (distance < fallback_distance) {
 				fallback_distance = distance;
@@ -381,7 +384,8 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
 
 		if (ns->ana_state == NVME_ANA_OPTIMIZED) {
 			found = ns;
-			goto out;
+			if (!nvme_ctrl_is_marginal(ns->ctrl))
+				goto out;
 		}
 		if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
 			found = ns;
@@ -445,7 +449,8 @@ static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
 	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
-		ns->ana_state == NVME_ANA_OPTIMIZED;
+		ns->ana_state == NVME_ANA_OPTIMIZED &&
+		!nvme_ctrl_is_marginal(ns->ctrl);
 }
 
 static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
-- 
2.50.1