From 36ac05f7cfd59d90c597071304b14e98090d5dd1 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Thu, 16 Jul 2026 16:42:19 +0200 Subject: [PATCH] nvme-tcp: fix usage of page_frag_cache nvme uses page_frag_cache to preallocate PDU for each preallocated request of block device. Block devices are created in parallel threads, consequently page_frag_cache is used in not thread-safe manner. That leads to incorrect refcounting of backstore pages and premature free. That can be catched by !sendpage_ok inside network stack: WARNING: CPU: 7 PID: 467 at ../net/core/skbuff.c:6931 skb_splice_from_iter+0xfa/0x310. tcp_sendmsg_locked+0x782/0xce0 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x8b/0xa0 nvme_tcp_try_send_cmd_pdu+0x149/0x2a0 Then random panic may occur. Fix that by serializing the usage of page_frag_cache. Fixes: 4e893ca81170 ("nvme_core: scan namespaces asynchronously") Signed-off-by: Dmitry Bogdanov Signed-off-by: Daniel Wagner Signed-off-by: Keith Busch --- drivers/nvme/host/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 0b2ac150b675..1d303e54e13e 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -108,6 +108,7 @@ struct nvme_tcp_queue { struct mutex queue_lock; struct mutex send_mutex; + struct mutex pf_cache_lock; struct llist_head req_list; struct list_head send_list; @@ -552,9 +553,11 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx]; u8 hdgst = nvme_tcp_hdgst_len(queue); + mutex_lock(&queue->pf_cache_lock); req->pdu = page_frag_alloc(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&queue->pf_cache_lock); if (!req->pdu) return -ENOMEM; @@ -1419,9 +1422,11 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) struct nvme_tcp_request *async = &ctrl->async_req; u8 hdgst = nvme_tcp_hdgst_len(queue); + mutex_lock(&queue->pf_cache_lock); async->pdu = page_frag_alloc(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&queue->pf_cache_lock); if (!async->pdu) return -ENOMEM; @@ -1463,6 +1468,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) kfree(queue->pdu); mutex_destroy(&queue->send_mutex); mutex_destroy(&queue->queue_lock); + mutex_destroy(&queue->pf_cache_lock); #ifdef CONFIG_DEBUG_LOCK_ALLOC lockdep_unregister_key(&queue->nvme_tcp_sk_key); @@ -1790,6 +1796,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, INIT_LIST_HEAD(&queue->send_list); mutex_init(&queue->send_mutex); INIT_WORK(&queue->io_work, nvme_tcp_io_work); + mutex_init(&queue->pf_cache_lock); if (qid > 0) queue->cmnd_capsule_len = nctrl->ioccsz * 16; @@ -1930,6 +1937,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, err_destroy_mutex: mutex_destroy(&queue->send_mutex); mutex_destroy(&queue->queue_lock); + mutex_destroy(&queue->pf_cache_lock); return ret; }