nvme: all namespaces in a subsystem must adhere to a common atomic write size

The first namespace configured in a subsystem sets the subsystem's
atomic write size based on its AWUPF or NAWUPF. Subsequent namespaces
must have an atomic write size (per their AWUPF or NAWUPF) less than or
equal to the subsystem's atomic write size, or their probing will be
rejected.

Signed-off-by: Alan Adamson <alan.adamson@oracle.com>
[hch: fold in review comments from John Garry]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>

1 files changed, 27 insertions, 3 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ac53629fce68..6b04473c0ab7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2059,7 +2059,21 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ns->ctrl->awupf) * bs;
+
+		/*
+		 * Set subsystem atomic bs.
+		 */
+		if (ns->ctrl->subsys->atomic_bs) {
+			if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
+				dev_err_ratelimited(ns->ctrl->device,
+					"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
+					ns->disk ? ns->disk->disk_name : "?",
+					ns->ctrl->subsys->atomic_bs,
+					atomic_bs);
+			}
+		} else
+			ns->ctrl->subsys->atomic_bs = atomic_bs;
 
 		nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
 	}
@@ -2201,6 +2215,17 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	nvme_set_chunk_sectors(ns, id, &lim);
 	if (!nvme_update_disk_info(ns, id, &lim))
 		capacity = 0;
+
+	/*
+	 * Validate the max atomic write size fits within the subsystem's
+	 * atomic write capabilities.
+	 */
+	if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
+		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
+		ret = -ENXIO;
+		goto out;
+	}
+
 	nvme_config_discard(ns, &lim);
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    ns->head->ids.csi == NVME_CSI_ZNS)
@@ -3031,7 +3056,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		kfree(subsys);
 		return -EINVAL;
 	}
-	subsys->awupf = le16_to_cpu(id->awupf);
 	nvme_mpath_default_iopolicy(subsys);
 
 	subsys->dev.class = &nvme_subsys_class;
@@ -3441,7 +3465,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
-
+	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;