Merge tag 'nvme-6.16-2025-06-26' of git://git.infradead.org/nvme into block-6.16

Pull NVMe fixes from Christoph:

" - reset delayed remove_work after reconnect (Keith Busch)
  - fix atomic write size validation (Christoph Hellwig)"

* tag 'nvme-6.16-2025-06-26' of git://git.infradead.org/nvme:
  nvme: fix atomic write size validation
  nvme: refactor the atomic write unit detection
  nvme: reset delayed remove_work after reconnect

3 files changed, 44 insertions, 48 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 92697f98c601..e533d791955d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2015,21 +2015,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
 }
 
 
-static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
-			struct nvme_id_ns *id, struct queue_limits *lim,
-			u32 bs, u32 atomic_bs)
+static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
+		struct nvme_id_ns *id, struct queue_limits *lim, u32 bs)
 {
-	unsigned int boundary = 0;
+	u32 atomic_bs, boundary = 0;
 
-	if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) {
-		if (le16_to_cpu(id->nabspf))
+	/*
+	 * We do not support an offset for the atomic boundaries.
+	 */
+	if (id->nabo)
+		return bs;
+
+	if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) {
+		/*
+		 * Use the per-namespace atomic write unit when available.
+		 */
+		atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+		if (id->nabspf)
 			boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
+	} else {
+		/*
+		 * Use the controller wide atomic write unit.  This sucks
+		 * because the limit is defined in terms of logical blocks while
+		 * namespaces can have different formats, and because there is
+		 * no clear language in the specification prohibiting different
+		 * values for different controllers in the subsystem.
+		 */
+		atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
 	}
+
 	lim->atomic_write_hw_max = atomic_bs;
 	lim->atomic_write_hw_boundary = boundary;
 	lim->atomic_write_hw_unit_min = bs;
 	lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
 	lim->features |= BLK_FEAT_ATOMIC_WRITES;
+	return atomic_bs;
 }
 
 static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
@@ -2067,34 +2087,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 		valid = false;
 	}
 
-	atomic_bs = phys_bs = bs;
-	if (id->nabo == 0) {
-		/*
-		 * Bit 1 indicates whether NAWUPF is defined for this namespace
-		 * and whether it should be used instead of AWUPF. If NAWUPF ==
-		 * 0 then AWUPF must be used instead.
-		 */
-		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
-			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
-		else
-			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);
-	}
+	phys_bs = bs;
+	atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs);
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
 		/* NPWG = Namespace Preferred Write Granularity */
@@ -2382,16 +2376,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	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)
@@ -3215,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+	subsys->awupf = le16_to_cpu(id->awupf);
 
 	/* Versions prior to 1.4 don't necessarily report a valid type */
 	if (id->cntrltype == NVME_CTRL_DISC ||
@@ -3552,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		if (ret)
 			goto out_free;
 	}
+
+	if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) {
+		dev_err_ratelimited(ctrl->device,
+			"inconsistent AWUPF, controller not added (%u/%u).\n",
+			le16_to_cpu(id->awupf), ctrl->subsys->awupf);
+		ret = -EINVAL;
+		goto out_free;
+	}
+
 	memcpy(ctrl->subsys->firmware_rev, id->fr,
 	       sizeof(ctrl->subsys->firmware_rev));
 
@@ -3647,7 +3641,6 @@ 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;
@@ -4036,6 +4029,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 	list_add_tail_rcu(&ns->siblings, &head->list);
 	ns->head = head;
 	mutex_unlock(&ctrl->subsys->lock);
+
+#ifdef CONFIG_NVME_MULTIPATH
+	cancel_delayed_work(&head->remove_work);
+#endif
 	return 0;
 
 out_put_ns_head:
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 140079ff86e6..1062467595f3 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1311,7 +1311,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 		 */
 		if (!try_module_get(THIS_MODULE))
 			goto out;
-		queue_delayed_work(nvme_wq, &head->remove_work,
+		mod_delayed_work(nvme_wq, &head->remove_work,
 				head->delayed_removal_secs * HZ);
 	} else {
 		list_del_init(&head->entry);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a468cdc5b5cb..7df2ea21851f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,7 +410,6 @@ struct nvme_ctrl {
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
-	u16 awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -443,11 +442,11 @@ struct nvme_subsystem {
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
+	u16			awupf; /* 0's based value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;
 #endif
-	u32			atomic_bs;
 };
 
 /*