From: Martin Belanger Date: Tue, 27 Oct 2026 06:38:53 -0400 Subject: [PATCH v2 2/2] nvme-tcp: skip TLS control records while waiting for the ICResp MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Message-Id: <20261027-nvme-tcp-ctrlrec-fixes-v2-2-9656395ebcf2@gmail.com> References: <20261027-nvme-tcp-ctrlrec-fixes-v2-0-9656395ebcf2@gmail.com> In-Reply-To: <20261027-nvme-tcp-ctrlrec-fixes-v2-0-9656395ebcf2@gmail.com> To: Keith Busch , Jens Axboe , Christoph Hellwig , Sagi Grimberg , Hannes Reinecke Cc: linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org, Martin Belanger X-Mailer: b4 0.16.0 X-Developer-Signature: v=1; a=ed25519-sha256; t=1793097538; l=6992; i=martin.nvme.dev@gmail.com; s=20261014; h=from:subject:message-id; bh=6vhImiUHY3qOfKIw4v4VLuZ5CbCy/ZozsM7ByGzixOY=; b=6SS0XhMJnZGPOJUztcGQwlfnhSnykB3DMAdhB14L1EYuWo3KD4povtuxNK3ncTljSplWu2VeC QpU5Lqx3JIbAAmnJGAdqqy7ltgb3wRSoWs8ob3eOMKJJF9t2Ihpywxd X-Developer-Key: i=martin.nvme.dev@gmail.com; a=ed25519; pk=4K+XXetGK35w2LzRRddd/bbHawZU222BN+YZRuSpN+k= X-Endpoint-Received: by B4 Relay for martin.nvme.dev@gmail.com/20261014 with auth_id=1176 List-Id: B4 Relay Submissions From: Martin Belanger A peer may send a NewSessionTicket as soon as the handshake completes, ahead of the ICResp. nvme_tcp_init_connection() fails the connection on any record that is not application data, so such a target cannot be reached at all. An OpenSSL-based target does this by default. RFC 9846 section 4.7.1 requires a client that does not support session resumption to ignore a NewSessionTicket. Discard such a record and read again, up to a fixed number of records. Report an alert, and fail the connection for any other record type. The record type is now checked before the length. A control record shorter than the ICResp was reported as -ECONNRESET, which hid the real cause. Fixes: 2837966ab2a8 ("nvme-tcp: control message handling for recvmsg()") Assisted-by: LLM Reviewed-by: Hannes Reinecke Signed-off-by: Martin Belanger --- drivers/nvme/host/tcp.c | 162 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 140 insertions(+), 22 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 0231b95fe4e4..2410223b1500 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -55,6 +55,12 @@ MODULE_PARM_DESC(tls_handshake_timeout, "nvme TLS handshake timeout in seconds (default 10)"); #endif +/* read a TLS control record in chunks of this size */ +#define NVME_TCP_TLS_REC_CHUNK 256 + +/* TLS records read while waiting for the ICResp, the ICResp included */ +#define NVME_TCP_ICRESP_MAX_RECORDS 8 + static int nvme_tcp_cpu_queues[NR_CPUS]; static DEFINE_SPINLOCK(nvme_tcp_cpu_queues_lock); @@ -1547,12 +1553,143 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) mutex_destroy(&queue->pf_cache_lock); } +static int nvme_tcp_recv_tls_alert(struct nvme_tcp_queue *queue, + struct msghdr *msg, int len) +{ + struct sock *sk = queue->sock->sk; + u8 level, description; + + if (len < 2) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: truncated TLS alert\n", + nvme_tcp_queue_id(queue)); + return -ENOTCONN; + } + + /* tls_alert_recv() reads through the iterator */ + iov_iter_revert(&msg->msg_iter, len); + tls_alert_recv(sk, msg, &level, &description); + + if (level == TLS_ALERT_LEVEL_FATAL) { + dev_err(queue->ctrl->ctrl.device, + "queue %d: fatal TLS alert %u\n", + nvme_tcp_queue_id(queue), description); + return -ENOTCONN; + } + + /* a peer shutting down normally is not worth a warning */ + if (description == TLS_ALERT_DESC_CLOSE_NOTIFY) + dev_dbg(queue->ctrl->ctrl.device, + "queue %d: TLS close_notify\n", + nvme_tcp_queue_id(queue)); + else + dev_warn(queue->ctrl->ctrl.device, + "queue %d: TLS alert %u\n", + nvme_tcp_queue_id(queue), description); + + return 0; +} + +/* + * Discard a TLS record that arrived in place of the ICResp. A peer may send + * a NewSessionTicket as soon as the handshake completes. + * + * Returns 0 when the record was discarded and the ICResp can be read, or a + * negative errno if the connection cannot continue. + */ +static int nvme_tcp_skip_tls_record(struct nvme_tcp_queue *queue, + struct msghdr *msg, u8 ctype, int len) +{ + u8 buf[NVME_TCP_TLS_REC_CHUNK]; + int ret; + + switch (ctype) { + case TLS_RECORD_TYPE_HANDSHAKE: + break; + case TLS_RECORD_TYPE_ALERT: + ret = nvme_tcp_recv_tls_alert(queue, msg, len); + return ret ? : -ENOTCONN; + default: + pr_err("queue %d: unhandled TLS record %u\n", + nvme_tcp_queue_id(queue), ctype); + return -ENOTCONN; + } + + /* the ICResp is in a later record, drain this one first */ + while (!(msg->msg_flags & MSG_EOR)) { + struct kvec iov = { + .iov_base = buf, + .iov_len = sizeof(buf), + }; + char cbuf[CMSG_LEN(sizeof(char))] = {}; + /* kTLS fails a control record read without a cmsg buffer */ + struct msghdr drain = { + .msg_control = cbuf, + .msg_controllen = sizeof(cbuf), + }; + + ret = kernel_recvmsg(queue->sock, &drain, &iov, 1, sizeof(buf), + 0); + if (ret <= 0) { + pr_warn("queue %d: failed to drain TLS record: %d\n", + nvme_tcp_queue_id(queue), ret); + return ret ? : -ECONNRESET; + } + msg->msg_flags = drain.msg_flags; + } + + return 0; +} + +/* + * Receive the ICResp. Over TLS, skip the records that a peer may send + * ahead of it. + * + * Returns the length received, or a negative errno. + */ +static int nvme_tcp_recv_icresp(struct nvme_tcp_queue *queue, + struct nvme_tcp_icresp_pdu *icresp) +{ + char cbuf[CMSG_LEN(sizeof(char))]; + struct msghdr msg; + struct kvec iov; + u8 ctype; + int i, ret; + + for (i = 0; i < NVME_TCP_ICRESP_MAX_RECORDS; i++) { + memset(&msg, 0, sizeof(msg)); + memset(cbuf, 0, sizeof(cbuf)); + iov.iov_base = icresp; + iov.iov_len = sizeof(*icresp); + if (nvme_tcp_queue_tls(queue)) { + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + } + msg.msg_flags = MSG_WAITALL; + ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (ret <= 0 || !nvme_tcp_queue_tls(queue)) + return ret; + + ctype = tls_get_record_type(queue->sock->sk, + (struct cmsghdr *)cbuf); + if (ctype == TLS_RECORD_TYPE_DATA) + return ret; + + ret = nvme_tcp_skip_tls_record(queue, &msg, ctype, ret); + if (ret < 0) + return ret; + } + + pr_err("queue %d: too many TLS records before the ICResp\n", + nvme_tcp_queue_id(queue)); + return -EPROTO; +} + static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) { struct nvme_tcp_icreq_pdu *icreq; struct nvme_tcp_icresp_pdu *icresp; - char cbuf[CMSG_LEN(sizeof(char))] = {}; - u8 ctype; struct msghdr msg = {}; struct kvec iov; bool ctrl_hdgst, ctrl_ddgst; @@ -1590,16 +1727,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) goto free_icresp; } - memset(&msg, 0, sizeof(msg)); - iov.iov_base = icresp; - iov.iov_len = sizeof(*icresp); - if (nvme_tcp_queue_tls(queue)) { - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - } - msg.msg_flags = MSG_WAITALL; - ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, - iov.iov_len, msg.msg_flags); + ret = nvme_tcp_recv_icresp(queue, icresp); if (ret >= 0 && ret < sizeof(*icresp)) ret = -ECONNRESET; if (ret < 0) { @@ -1607,16 +1735,6 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) nvme_tcp_queue_id(queue), ret); goto free_icresp; } - ret = -ENOTCONN; - if (nvme_tcp_queue_tls(queue)) { - ctype = tls_get_record_type(queue->sock->sk, - (struct cmsghdr *)cbuf); - if (ctype != TLS_RECORD_TYPE_DATA) { - pr_err("queue %d: unhandled TLS record %d\n", - nvme_tcp_queue_id(queue), ctype); - goto free_icresp; - } - } ret = -EINVAL; if (icresp->hdr.type != nvme_tcp_icresp) { pr_err("queue %d: bad type returned %d\n", -- 2.53.0