Merge tag 'nvme-6.6-2023-10-18' of git://git.infradead.org/nvme into block-6.6

Pull NVMe fixes from Keith:

"nvme fixes for Linux 6.6

 - nvme-rdma queue fix (Maurizio)
 - nvmet-auth double free fix (Maurizio)
 - nvme-tcp use-after-free fix (Sagi)
 - nvme-auth data direction fix (Martin)
 - nvme passthrough metadata sanitization (Keith)
 - nvme bogus identifiers for multi-controller ssd (Keith)"

* tag 'nvme-6.6-2023-10-18' of git://git.infradead.org/nvme:
  nvme-pci: add BOGUS_NID for Intel 0a54 device
  nvmet-auth: complete a request only after freeing the dhchap pointers
  nvme: sanitize metadata bounce buffer for reads
  nvme-auth: use chap->s2 to indicate bidirectional authentication
  nvmet-tcp: Fix a possible UAF in queue intialization setup
  nvme-rdma: do not try to stop unallocated queues

Author: axboe

drivers/nvme/host/auth.c

@@ -341,7 +341,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl,
 	struct nvmf_auth_dhchap_success1_data *data = chap->buf;
 	size_t size = sizeof(*data);
 
-	if (chap->ctrl_key)
+	if (chap->s2)
 		size += chap->hash_len;
 
 	if (size > CHAP_BUF_SIZE) {
@@ -825,7 +825,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
 		goto fail2;
 	}
 
-	if (chap->ctrl_key) {
+	if (chap->s2) {
 		/* DH-HMAC-CHAP Step 5: send success2 */
 		dev_dbg(ctrl->device, "%s: qid %d send success2\n",
 			__func__, chap->qid);

drivers/nvme/host/ioctl.c

@@ -108,9 +108,13 @@ static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
 	if (!buf)
 		goto out;
 
-	ret = -EFAULT;
-	if ((req_op(req) == REQ_OP_DRV_OUT) && copy_from_user(buf, ubuf, len))
-		goto out_free_meta;
+	if (req_op(req) == REQ_OP_DRV_OUT) {
+		ret = -EFAULT;
+		if (copy_from_user(buf, ubuf, len))
+			goto out_free_meta;
+	} else {
+		memset(buf, 0, len);
+	}
 
 	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
 	if (IS_ERR(bip)) {

drivers/nvme/host/pci.c

@@ -3329,7 +3329,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES |
-				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+				NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },

drivers/nvme/host/rdma.c

@@ -638,6 +638,9 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 
 static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 {
+	if (!test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
+		return;
+
 	mutex_lock(&queue->queue_lock);
 	if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
 		__nvme_rdma_stop_queue(queue);

drivers/nvme/target/fabrics-cmd-auth.c

@@ -333,19 +333,21 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
 			 __func__, ctrl->cntlid, req->sq->qid,
 			 status, req->error_loc);
 	req->cqe->result.u64 = 0;
-	nvmet_req_complete(req, status);
 	if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 &&
 	    req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) {
 		unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120;
 
 		mod_delayed_work(system_wq, &req->sq->auth_expired_work,
 				 auth_expire_secs * HZ);
-		return;
+		goto complete;
 	}
 	/* Final states, clear up variables */
 	nvmet_auth_sq_free(req->sq);
 	if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2)
 		nvmet_ctrl_fatal_error(ctrl);
+
+complete:
+	nvmet_req_complete(req, status);
 }
 
 static int nvmet_auth_challenge(struct nvmet_req *req, void *d, int al)
@@ -514,11 +516,12 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
 	kfree(d);
 done:
 	req->cqe->result.u64 = 0;
-	nvmet_req_complete(req, status);
+
 	if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2)
 		nvmet_auth_sq_free(req->sq);
 	else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) {
 		nvmet_auth_sq_free(req->sq);
 		nvmet_ctrl_fatal_error(ctrl);
 	}
+	nvmet_req_complete(req, status);
 }

drivers/nvme/target/tcp.c

@@ -372,6 +372,7 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue)
 
 static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status)
 {
+	queue->rcv_state = NVMET_TCP_RECV_ERR;
 	if (status == -EPIPE || status == -ECONNRESET)
 		kernel_sock_shutdown(queue->sock, SHUT_RDWR);
 	else
@@ -910,15 +911,11 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	iov.iov_len = sizeof(*icresp);
 	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
 	if (ret < 0)
-		goto free_crypto;
+		return ret; /* queue removal will cleanup */
 
 	queue->state = NVMET_TCP_Q_LIVE;
 	nvmet_prepare_receive_pdu(queue);
 	return 0;
-free_crypto:
-	if (queue->hdr_digest || queue->data_digest)
-		nvmet_tcp_free_crypto(queue);
-	return ret;
 }
 
 static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,