[PATCH v2 0/2] fix racy access to FDP placement id array

[PATCH v2 0/2] fix racy access to FDP placement id array

[Kanchan Joshi]

Patch 1: prep to send non-admin commands from nvme_alloc_ns_head
Patch 2: avoid the race by moving fdp registration to nvme_alloc_ns_head

Changes since v1:
- Add a prep patch to unconditionally set ns->head (christoph)

Kanchan Joshi (2):
  nvme: set ns->head in nvme_alloc_ns_head
  nvme: fix racy access to FDP placement id array

 drivers/nvme/host/core.c | 39 +++++++++++++++++----------------------
 drivers/nvme/host/nvme.h |  1 +
 2 files changed, 18 insertions(+), 22 deletions(-)

-- 
2.25.1

[PATCH v2 1/2] nvme: set ns->head in nvme_alloc_ns_head

[Kanchan Joshi]

so that it becomes possible to submit non-admin commands.
This is a prep patch with no functional changes.

Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
---
 drivers/nvme/host/core.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1322c678f4eb..a2e0abf0ea8a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4001,10 +4001,11 @@ static void nvme_add_ns_cdev(struct nvme_ns *ns)
 	set_bit(NVME_NS_CDEV_LIVE, &ns->flags);
 }
 
-static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
+static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
-	__must_hold(&ctrl->subsys->lock)
+	__must_hold(&ns->ctrl->subsys->lock)
 {
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_ns_head *head;
 	size_t size = sizeof(*head);
 	int ret = -ENOMEM;
@@ -4032,6 +4033,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
 	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
 	kref_init(&head->ref);
+	ns->head = head;
 
 	if (head->ids.csi) {
 		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
@@ -4055,6 +4057,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	ida_free(&ctrl->subsys->ns_ida, head->instance);
 out_free_head:
 	kfree(head);
+	ns->head = NULL;
 out:
 	if (ret > 0)
 		ret = blk_status_to_errno(nvme_error_status(ret));
@@ -4141,7 +4144,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 				info->nsid);
 			goto out_unlock;
 		}
-		head = nvme_alloc_ns_head(ctrl, info);
+		head = nvme_alloc_ns_head(ns, info);
 		if (IS_ERR(head)) {
 			ret = PTR_ERR(head);
 			goto out_unlock;
-- 
2.25.1

[PATCH v2 2/2] nvme: fix racy access to FDP placement id array

[Kanchan Joshi]

nvme_query_fdp_info() is called per-path and therefore prone to races.

It populates head->nr_plids/head->plids for fdp registration.
But nothing protects that pair from concurrent access - two paths scanning
the same namespace can race to populate it.

Avoid the race by moving this initialization work to nvme_alloc_ns_head()
which is called once per shared namespace.

Fixes: 30b5f20bb2dd ("nvme: register fdp parameters with the block layer")
Reported-by: Hari Mishal <harimishal1@gmail.com>
Link: https://lore.kernel.org/linux-nvme/20260725135111.14041-2-harimishal1@gmail.com/
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
---
 drivers/nvme/host/core.c | 30 +++++++++++-------------------
 drivers/nvme/host/nvme.h |  1 +
 2 files changed, 12 insertions(+), 19 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a2e0abf0ea8a..aa3c3b7d5544 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2341,14 +2341,6 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 	size_t size;
 	int i, ret;
 
-	/*
-	 * The FDP configuration is static for the lifetime of the namespace,
-	 * so return immediately if we've already registered this namespace's
-	 * streams.
-	 */
-	if (head->nr_plids)
-		return 0;
-
 	ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0,
 				&fdp);
 	if (ret) {
@@ -2395,6 +2387,7 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 
 	for (i = 0; i < head->nr_plids; i++)
 		head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid);
+	head->write_stream_granularity = min(info->runs, U32_MAX);
 free:
 	kfree(ruhs);
 	return ret;
@@ -2442,12 +2435,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 			goto out;
 	}
 
-	if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) {
-		ret = nvme_query_fdp_info(ns, info);
-		if (ret < 0)
-			goto out;
-	}
-
 	if (nvme_invalid_lba_sz(le64_to_cpu(id->nsze),
 			id->lbaf[lbaf].ds - SECTOR_SHIFT, &capacity)) {
 		dev_warn_once(ns->ctrl->device,
@@ -2490,10 +2477,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		capacity = 0;
 
 	lim.max_write_streams = ns->head->nr_plids;
-	if (lim.max_write_streams)
-		lim.write_stream_granularity = min(info->runs, U32_MAX);
-	else
-		lim.write_stream_granularity = 0;
+	lim.write_stream_granularity = ns->head->write_stream_granularity;
 
 	/*
 	 * Only set the DEAC bit if the device guarantees that reads from
@@ -4042,15 +4026,23 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns,
 	} else
 		head->effects = ctrl->effects;
 
+	if (ctrl->ctratt & NVME_CTRL_ATTR_FDPS) {
+		ret = nvme_query_fdp_info(ns, info);
+		if (ret < 0)
+			goto out_cleanup_srcu;
+	}
+
 	ret = nvme_mpath_alloc_disk(ctrl, head);
 	if (ret)
-		goto out_cleanup_srcu;
+		goto out_cleanup_fdp;
 
 	list_add_tail(&head->entry, &ctrl->subsys->nsheads);
 
 	kref_get(&ctrl->subsys->ref);
 
 	return head;
+out_cleanup_fdp:
+	kfree(head->plids);
 out_cleanup_srcu:
 	cleanup_srcu_struct(&head->srcu);
 out_ida_remove:
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 75e5d5a8a77c..c20e8ef8baa0 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -571,6 +571,7 @@ struct nvme_ns_head {
 
 	u16			nr_plids;
 	u16			*plids;
+	u32			write_stream_granularity;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct bio_list		requeue_list
 		__guarded_by(&requeue_lock);
-- 
2.25.1

Re: [PATCH v2 1/2] nvme: set ns->head in nvme_alloc_ns_head

[Christoph Hellwig]

On Tue, Aug 18, 2026 at 11:32:52AM +0530, Kanchan Joshi wrote:
> so that it becomes possible to submit non-admin commands.
> This is a prep patch with no functional changes.
> 
> Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v2 2/2] nvme: fix racy access to FDP placement id array

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v2 0/2] fix racy access to FDP placement id array

[Keith Busch]

On Tue, Aug 18, 2026 at 11:32:51AM +0530, Kanchan Joshi wrote:
> Patch 1: prep to send non-admin commands from nvme_alloc_ns_head
> Patch 2: avoid the race by moving fdp registration to nvme_alloc_ns_head

Thanks, applied to nvme-7.3.