nvme-tcp: fix usage of page_frag_cache
Subsystems (2)
PATCH 1/1 nvme-tcp: fix usage of page_frag_cache
From: Dmitry Bogdanov <[email protected]>
commit 36ac05f7cfd59d90c597071304b14e98090d5dd1 upstream.
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.
[carlos.bilbao: adjust context in nvme_tcp_free_queue; branch predates 19bdb70c77d3 ("nvme-tcp: lockdep: use dynamic lockdep keys per socket instance")]
---
Context conflict in nvme_tcp_free_queue due to 19bdb70c77d3; context-only adjustment, no functional change.
Build-tested: 6.18.47 (x86_64 defconfig + CONFIG_NVME_TCP=m). Also needed in 6.12.y, 7.1.y (backports submitted separately); 7.2.y takes the upstream commit cleanly.
drivers/nvme/host/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/nvme/host/tcp.c +8 -0
@@ -145,6 +145,7 @@ 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;
@@ -556,9 +557,11 @@ 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 ;
@@ -1423,9 +1426,11 @@ 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 ;
@@ -1453,6 +1458,7 @@ 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); }static int nvme_tcp_init_connection (struct nvme_tcp_queue *queue)
@@ -1775,6 +1781,7 @@ 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 ;
@@ -1906,6 +1913,7 @@ err_sock: err_destroy_mutex:mutex_destroy (&queue->send_mutex);mutex_destroy (&queue->queue_lock); +mutex_destroy (&queue->pf_cache_lock);return ret; }
Signature · 1 line
2.50.1 (Apple Git-155)
Quoted 6 lines
commit
36ac05f7cfd59d90c597071304b14e98090d5dd1upstream.nvme uses
page_frag_cacheto preallocate PDU for each preallocated request of block device. Block devices are created in parallel threads, consequentlypage_frag_cacheis used in not thread-safe manner. That leads to incorrect refcounting of backstore pages and premature free.
Queued for 6.18, thanks.
Signature · 2 lines
Thanks, Sasha