kernel/git/stable/linux.git/drivers/nvme, branch linux-5.15.y

nvmet-rdma: fix queue leak when connect backlog is exceeded

2026-09-14T11:20:54+00:00

commit fb1ed67788e21832b614c23767a088c08cfdd2f2 upstream. When pending disconnecting queues exceed the backlog limit, the connect path only drops the device reference and leaks the newly allocated queue and its IB resources. Fixes: badc53620fe8 ("nvme: target: rdma: fix ndev refcount leak on queue connect") Reviewed-by: Christoph Hellwig Signed-off-by: Xixin Liu Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman

nvme: target: rdma: fix ndev refcount leak on queue connect

2026-09-14T11:20:53+00:00

[ Upstream commit badc53620fe813b3a9f727ef9526f98567c2c898 ] nvmet_rdma_queue_connect() calls nvmet_rdma_find_get_device() which acquires a reference on the returned ndev via kref_get(). On the path where the host queue backlog is exceeded and the function returns NVME_SC_CONNECT_CTRL_BUSY, reference of ndev is not released, leaking the kref. Fix this by adding a goto to the existing put_device label before the early return. Fixes: 31deaeb11ba7 ("nvmet-rdma: avoid circular locking dependency on install_queue()") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Wentao Liang Signed-off-by: Keith Busch Signed-off-by: Sasha Levin

nvmet: fix NULL pointer dereference in nvmet_execute_identify_ns_zns()

2026-09-14T11:20:45+00:00

[ Upstream commit f594863967d87b7fcbff6e724d51135fd701a13d ] When a host issues an Identify command with CNS 05h (I/O Command Set specific Identify Namespace) and CSI 02h (ZNS) targeting a file-backed namespace, nvmet_execute_identify_ns_zns() calls bdev_is_zoned() on req->ns->bdev. A file-backed namespace has no block device, so req->ns->bdev is NULL and bdev_is_zoned() dereferences it, oopsing. The I/O command set is selected by the host-supplied CSI field and the command is routed here whenever CONFIG_BLK_DEV_ZONED is enabled, independent of the namespace backing type, so any file-backed namespace is exposed. Reject the command with Invalid Field when the namespace is not backed by a block device. Fixes: aaf2e048af27 ("nvmet: add ZBD over ZNS backend support") Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Guixin Liu Signed-off-by: Keith Busch Signed-off-by: Sasha Levin

nvme-fc: unmap cmd_iu DMA on rsp_iu mapping failure in init_request

2026-09-14T11:20:37+00:00

[ Upstream commit f49d0c3a8d56a7cda1628ae17341a4a42063563c ] __nvme_fc_init_request() maps cmd_iu and then rsp_iu for DMA. If the rsp_iu mapping fails, the original code only recorded the error and fell through: it left the already-mapped cmd_iu unmapped and still marked the op as FCPOP_STATE_IDLE before returning. Since blk-mq does not call .exit_request() when .init_request() fails, the cmd_iu mapping is leaked for every op whose rsp_iu mapping fails. Jump to an error path on rsp_iu mapping failure that unmaps cmd_iu and returns the error without marking the op idle, so it stays in the FCPOP_STATE_UNINIT state set by the initial memset(). Fixes: e399441de911 ("nvme-fabrics: Add host support for FC transport") Reviewed-by: Christoph Hellwig Signed-off-by: Guixin Liu Signed-off-by: Keith Busch Signed-off-by: Sasha Levin

nvmet-rdma: fix response resource leak on queue teardown

2026-09-14T11:20:27+00:00

[ Upstream commit 0114dd303b373522dea06053aabae34bdd33a7c4 ] When an nvme target with rdma transport is removed while I/Os are in flight, a response can be posted but its send completion is never delivered before the connection is torn down. As a result nvmet_rdma_send_done() and nvmet_rdma_release_rsp() are never called for the response, and this leaks the allocated RDMA read/write context and request SGLs. These leaks are recreated by running blktests nvme/061 with the rdma transport and the siw driver. Kernel kmemleak feature reports them as follows: unreferenced object 0xffff88812bc490c0 (size 32): comm "kworker/2:1H", pid 409, jiffies 4307744490 backtrace (crc 89afd339): __kmalloc_noprof+0x5f9/0x890 sgl_alloc_order+0x7b/0x380 nvmet_req_alloc_sgls+0x290/0x4f0 [nvmet] nvmet_rdma_map_sgl_keyed+0x241/0x12e0 [nvmet_rdma] nvmet_rdma_handle_command+0x73e/0xb80 [nvmet_rdma] __ib_process_cq+0x149/0x4c0 [ib_core] ib_cq_poll_work+0x49/0x160 [ib_core] process_one_work+0x8b2/0x1640 worker_thread+0x5fd/0xfe0 kthread+0x367/0x460 ret_from_fork+0x655/0x9d0 ret_from_fork_asm+0x1a/0x30 unreferenced object 0xffff88814bd05e80 (size 64): comm "kworker/3:1H", pid 148, jiffies 4295195428 backtrace (crc e35510cb): __kmalloc_noprof+0x5f9/0x890 rdma_rw_ctx_init+0x333/0x1fa0 [ib_core] nvmet_rdma_map_sgl_keyed+0x5c8/0x12e0 [nvmet_rdma] nvmet_rdma_handle_command+0x73e/0xb80 [nvmet_rdma] __ib_process_cq+0x149/0x4c0 [ib_core] ib_cq_poll_work+0x49/0x160 [ib_core] process_one_work+0x8b2/0x1640 worker_thread+0x5fd/0xfe0 kthread+0x367/0x460 ret_from_fork+0x655/0x9d0 ret_from_fork_asm+0x1a/0x30 To avoid the memory leaks, reclaim the memory of the in-flight responses when the queue QP is torn down. Call nvmet_rdma_free_rsp_resources() that frees up the RDMA read/write context and the request SGLs of such responses. Fixes: 8f000cac6e7a ("nvmet-rdma: add a NVMe over Fabrics RDMA target driver") Signed-off-by: Shin'ichiro Kawasaki Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin

nvmet-rdma: factor out response resource cleanup

2026-09-14T11:20:27+00:00

[ Upstream commit 90096175473f7c86e39c3f74f10343f965f5a05d ] Move the RDMA read/write context teardown and the request SGL freeing out of nvmet_rdma_release_rsp() into a new helper function nvmet_rdma_free_rsp_resources(). This is a refactoring with no functional change, in preparation for the following patch that uses nvmet_rdma_free_rsp_resources(). Signed-off-by: Shin'ichiro Kawasaki Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Stable-dep-of: 0114dd303b37 ("nvmet-rdma: fix response resource leak on queue teardown") Signed-off-by: Sasha Levin

nvmet-rdma: use sbitmap to replace rsp free list

2026-09-14T11:20:27+00:00

[ Upstream commit 40f0e5dc2f3c866bef3fccf398114b90c6136dfa ] We can use sbitmap to manage all the nvmet_rdma_rsp instead of using free lists and spinlock, and we can use an additional tag to determine whether the nvmet_rdma_rsp is extra allocated. In addition, performance has improved: 1. testing environment is local rxe rdma devie and mem-based backstore device. 2. fio command, test the average 5 times: fio -filename=/dev/nvme0n1 --ioengine=libaio -direct=1 -size=1G -name=1 -thread -runtime=60 -time_based -rw=read -numjobs=16 -iodepth=128 -bs=4k -group_reporting 3. Before: 241k IOPS, After: 256k IOPS, an increase of about 5%. Signed-off-by: Guixin Liu Reviewed-by: Jens Axboe Stable-dep-of: 0114dd303b37 ("nvmet-rdma: fix response resource leak on queue teardown") Signed-off-by: Sasha Levin

nvmet-rdma: avoid circular locking dependency on install_queue()

2026-09-14T11:20:27+00:00

[ Upstream commit 31deaeb11ba7a885116c9c30892b9f763c04d59c ] nvmet_rdma_install_queue() is driven from the ->io_work workqueue function, but will call flush_workqueue() which might trigger ->release_work() which in itself calls flush_work on ->io_work. To avoid that check for pending queue in disconnecting status, and return 'controller busy' when we reached a certain threshold. Signed-off-by: Hannes Reinecke Tested-by: Shin'ichiro Kawasaki Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Stable-dep-of: 0114dd303b37 ("nvmet-rdma: fix response resource leak on queue teardown") Signed-off-by: Sasha Levin

nvmet-tcp: reject unsolicited H2CData PDUs

2026-09-14T11:20:17+00:00

commit db62b35cbca052860c519cbcabe7650708528738 upstream. nvmet_tcp_handle_h2c_data_pdu() accepts an H2CData PDU after only checking that its TTAG is a valid in-range command index and that the command's data buffers are mapped. It never checks that the target has actually solicited that data by sending an R2T for the command. A remote host can abuse this. It submits a write command that takes the R2T path and, before the target transmits the R2T, sends an H2CData PDU for that command's tag. The data completes the command early, and when the command then fails synchronously (e.g. a length mismatch caught by nvmet_check_transfer_len()), it is completed a second time. Each completion calls nvmet_tcp_queue_response(), so the same command is added to queue->resp_list twice while it is still linked; the second llist_add() makes the node point to itself (lentry->next == lentry). nvmet_tcp_process_resp_list() then walks that self-referential node and adds the command to resp_send_list twice. With CONFIG_DEBUG_LIST this trips the "list_add double add" check (kernel BUG); without it the loop never terminates and the nvmet_tcp workqueue wedges (soft-lockup). It is remotely triggerable and needs no authentication on an allow_any_host subsystem. Track whether an R2T has been transmitted for a command and reject an H2CData PDU that arrives before it. The flag is cleared on command reuse (nvmet_tcp_get_cmd() zeroes cmd->flags) and stays set across the multiple H2CData PDUs of a single solicited transfer. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Cc: stable@vger.kernel.org Reviewed-by: Sagi Grimberg Signed-off-by: Shivam Kumar Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman

nvmet-tcp: fix out-of-bounds write when receiving an over-long PDU

2026-09-14T11:20:17+00:00

commit 14cc5a7e77731497d5bea70f3bb05df7eda982e4 upstream. nvmet_tcp_try_recv_pdu() reads a PDU header into the fixed 128-byte queue->pdu union, then computes the remaining payload length as queue->left = hdr->hlen - queue->offset + hdgst; and reads that many more bytes into &queue->pdu + queue->offset, without ever bounding the result against sizeof(queue->pdu). A struct nvme_tcp_icreq_pdu is itself 128 bytes, exactly the size of the union. Once a header digest has been negotiated (hdgst = 4), a second ICReq passes the hlen == nvmet_tcp_pdu_size() check but yields queue->left = 128 - 8 + 4 = 124, so bytes 8..132 are written into the 128-byte buffer -- 4 bytes past its end, over queue->hdr_digest and queue->data_digest. Those bytes are attacker-controlled (an ICReq carries no digest), and the duplicate ICReq is only rejected later, after the overflow. A remote unauthenticated host can thus corrupt kernel memory adjacent to the receive buffer. Reject any PDU whose declared length would read past the end of queue->pdu before the second recv. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Shivam Kumar Cc: stable@vger.kernel.org Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman