From 3fdd281e0a049a804b2512c4cb3d685e5358aee8 Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Fri, 18 Sep 2026 21:57:31 +0530 Subject: [PATCH] nvmet: don't allow I/O admission after percpu ns reference is killed nvmet_req_find_ns() uses percpu_ref_get() to obtain a reference to the namespace. However, percpu_ref_get() can acquire a reference even after the namespace reference has been killed (or marked DEAD). This is undesirable during namespace disable because nvmet_ns_disable() kills the namespace reference and then waits for all outstanding references to drain. Acquiring a new reference after the reference is killed can therefore extend the namespace drain period. Replace percpu_ref_get() in nvmet_req_find_ns() with percpu_ref_tryget_live_rcu(), which only acquires a reference while the namespace reference is still live. This handles the race where nvmet_req_find_ns() finds ns is admitting I/O (or it's live) but before it acquires the reference to ns, its reference is killed in nvmet_ns_disable(). For instance check this race: CPU0 CPU1 nvmet_req_find_ns(): nvmet_ns_disable(): xa_load() -> ns IO_LIVE == set xa_clear_mark() percpu_ref_kill() // DEAD percpu_ref_get() synchronize_rcu() | wait_for_completion() +-- succeed Replacing percpu_ref_get() with percpu_ref_tryget_live_rcu() prevents the I/O request from acquiring a namespace reference once the reference has been marked DEAD. Perform the namespace lookup and reference acquisition in nvmet_req_find_ns() within an RCU read-side critical section. nvmet_ns_disable() uses synchronize_rcu() before draining and exiting the namespace reference, ensuring that RCU readers which may be acquiring the namespace reference have completed before the reference is exited. Reviewed-by: Christoph Hellwig Signed-off-by: Nilay Shroff Signed-off-by: Keith Busch --- drivers/nvme/target/core.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 059b14da845a..8eea0a504308 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -446,21 +446,27 @@ u16 nvmet_req_find_ns(struct nvmet_req *req) { u32 nsid = le32_to_cpu(req->cmd->common.nsid); struct nvmet_subsys *subsys = nvmet_req_subsys(req); + u16 status = NVME_SC_SUCCESS; + rcu_read_lock(); req->ns = xa_load(&subsys->namespaces, nsid); if (unlikely(!req->ns) || - !test_bit(NVMET_NS_IO_LIVE, &req->ns->flags)) { + !test_bit(NVMET_NS_IO_LIVE, &req->ns->flags) || + !percpu_ref_tryget_live_rcu(&req->ns->ref)) { req->error_loc = offsetof(struct nvme_common_command, nsid); - if (!req->ns) /* ns doesn't exist! */ - return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + if (!req->ns) { /* ns doesn't exist! */ + status = NVME_SC_INVALID_NS | NVME_STATUS_DNR; + goto unlock; + } /* ns exists but it's disabled */ req->ns = NULL; - return NVME_SC_INTERNAL_PATH_ERROR; + status = NVME_SC_INTERNAL_PATH_ERROR; } +unlock: + rcu_read_unlock(); - percpu_ref_get(&req->ns->ref); - return NVME_SC_SUCCESS; + return status; } static void nvmet_destroy_namespace(struct percpu_ref *ref)