Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 3a67e24..ee81d94 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -369,6 +369,9 @@
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
@@ -378,6 +381,9 @@
 
 static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
 
 	cancel_delayed_work_sync(&ctrl->ka_work);
@@ -555,7 +561,8 @@
 	} else {
 		struct nvmet_ns *old;
 
-		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link) {
+		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link,
+					lockdep_is_held(&subsys->lock)) {
 			BUG_ON(ns->nsid == old->nsid);
 			if (ns->nsid < old->nsid)
 				break;
@@ -871,8 +878,6 @@
 	req->error_loc = NVMET_NO_ERROR_LOC;
 	req->error_slba = 0;
 
-	trace_nvmet_req_init(req, req->cmd);
-
 	/* no support for fused commands yet */
 	if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
 		req->error_loc = offsetof(struct nvme_common_command, flags);
@@ -906,6 +911,8 @@
 	if (status)
 		goto fail;
 
+	trace_nvmet_req_init(req, req->cmd);
+
 	if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
@@ -1024,9 +1031,20 @@
 {
 	lockdep_assert_held(&ctrl->lock);
 
-	if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
-	    nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
-	    nvmet_cc_mps(ctrl->cc) != 0 ||
+	/*
+	 * Only I/O controllers should verify iosqes,iocqes.
+	 * Strictly speaking, the spec says a discovery controller
+	 * should verify iosqes,iocqes are zeroed, however that
+	 * would break backwards compatibility, so don't enforce it.
+	 */
+	if (ctrl->subsys->type != NVME_NQN_DISC &&
+	    (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
+	     nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
+		ctrl->csts = NVME_CSTS_CFS;
+		return;
+	}
+
+	if (nvmet_cc_mps(ctrl->cc) != 0 ||
 	    nvmet_cc_ams(ctrl->cc) != 0 ||
 	    nvmet_cc_css(ctrl->cc) != 0) {
 		ctrl->csts = NVME_CSTS_CFS;
@@ -1041,7 +1059,8 @@
 	 * in case a host died before it enabled the controller.  Hence, simply
 	 * reset the keep alive timer when the controller is enabled.
 	 */
-	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	if (ctrl->kato)
+		mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
@@ -1174,7 +1193,8 @@
 
 	ctrl->p2p_client = get_device(req->p2p_client);
 
-	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link,
+				lockdep_is_held(&ctrl->subsys->lock))
 		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
 }
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d16b55f..5e47395 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -105,6 +105,7 @@
 	u16 qid = le16_to_cpu(c->qid);
 	u16 sqsize = le16_to_cpu(c->sqsize);
 	struct nvmet_ctrl *old;
+	u16 ret;
 
 	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
 	if (old) {
@@ -115,7 +116,9 @@
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
-		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
+		ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		goto err;
 	}
 
 	/* note: convert queue size from 0's-based value to 1's-based value */
@@ -128,16 +131,19 @@
 	}
 
 	if (ctrl->ops->install_queue) {
-		u16 ret = ctrl->ops->install_queue(req->sq);
-
+		ret = ctrl->ops->install_queue(req->sq);
 		if (ret) {
 			pr_err("failed to install queue %d cntlid %d ret %x\n",
-				qid, ret, ctrl->cntlid);
-			return ret;
+				qid, ctrl->cntlid, ret);
+			goto err;
 		}
 	}
 
 	return 0;
+
+err:
+	req->sq->ctrl = NULL;
+	return ret;
 }
 
 static void nvmet_execute_admin_connect(struct nvmet_req *req)
@@ -245,11 +251,11 @@
 	}
 
 	status = nvmet_install_queue(ctrl, req);
-	if (status) {
-		/* pass back cntlid that had the issue of installing queue */
-		req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
+	if (status)
 		goto out_ctrl_put;
-	}
+
+	/* pass back cntlid for successful completion */
+	req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
 
 	pr_debug("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
 
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index ce8d819..9b07e8c 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1994,9 +1994,9 @@
 			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
-			spin_lock(&fod->flock);
+			spin_lock_irqsave(&fod->flock, flags);
 			fod->abort = true;
-			spin_unlock(&fod->flock);
+			spin_unlock_irqrestore(&fod->flock, flags);
 
 			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;
@@ -2152,13 +2152,6 @@
 	int ret;
 
 	/*
-	 * if there is no nvmet mapping to the targetport there
-	 * shouldn't be requests. just terminate them.
-	 */
-	if (!tgtport->pe)
-		goto transport_error;
-
-	/*
 	 * Fused commands are currently not supported in the linux
 	 * implementation.
 	 *
@@ -2185,7 +2178,8 @@
 
 	fod->req.cmd = &fod->cmdiubuf.sqe;
 	fod->req.cqe = &fod->rspiubuf.cqe;
-	fod->req.port = tgtport->pe->port;
+	if (tgtport->pe)
+		fod->req.port = tgtport->pe->port;
 
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 05453f5..6ca17a0 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -38,9 +38,11 @@
 
 	ns->file = filp_open(ns->device_path, flags, 0);
 	if (IS_ERR(ns->file)) {
-		pr_err("failed to open file %s: (%ld)\n",
-				ns->device_path, PTR_ERR(ns->file));
-		return PTR_ERR(ns->file);
+		ret = PTR_ERR(ns->file);
+		pr_err("failed to open file %s: (%d)\n",
+			ns->device_path, ret);
+		ns->file = NULL;
+		return ret;
 	}
 
 	ret = vfs_getattr(&ns->file->f_path,
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 11f5aea..f657a12 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -252,7 +252,8 @@
 
 static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
-	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
+	if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags))
+		return;
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
 	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
@@ -288,6 +289,7 @@
 		clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
 		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
 	}
+	ctrl->ctrl.queue_count = 1;
 }
 
 static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -394,6 +396,7 @@
 	return 0;
 
 out_cleanup_queue:
+	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
 out_cleanup_fabrics_q:
 	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
@@ -619,8 +622,6 @@
 	dev_info(ctrl->ctrl.device,
 		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
@@ -638,6 +639,7 @@
 	kfree(ctrl->queues);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 36d906a..50e2007 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -75,6 +75,7 @@
 
 struct nvmet_rdma_queue {
 	struct rdma_cm_id	*cm_id;
+	struct ib_qp		*qp;
 	struct nvmet_port	*port;
 	struct ib_cq		*cq;
 	atomic_t		sq_wr_avail;
@@ -464,7 +465,7 @@
 	if (ndev->srq)
 		ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL);
 	else
-		ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL);
+		ret = ib_post_recv(cmd->queue->qp, &cmd->wr, NULL);
 
 	if (unlikely(ret))
 		pr_err("post_recv cmd failed\n");
@@ -503,7 +504,7 @@
 	atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);
 
 	if (rsp->n_rdma) {
-		rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
+		rdma_rw_ctx_destroy(&rsp->rw, queue->qp,
 				queue->cm_id->port_num, rsp->req.sg,
 				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	}
@@ -587,7 +588,7 @@
 
 	WARN_ON(rsp->n_rdma <= 0);
 	atomic_add(rsp->n_rdma, &queue->sq_wr_avail);
-	rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp,
+	rdma_rw_ctx_destroy(&rsp->rw, queue->qp,
 			queue->cm_id->port_num, rsp->req.sg,
 			rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	rsp->n_rdma = 0;
@@ -742,7 +743,7 @@
 	}
 
 	if (nvmet_rdma_need_data_in(rsp)) {
-		if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp,
+		if (rdma_rw_ctx_post(&rsp->rw, queue->qp,
 				queue->cm_id->port_num, &rsp->read_cqe, NULL))
 			nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
 	} else {
@@ -1025,6 +1026,7 @@
 		pr_err("failed to create_qp ret= %d\n", ret);
 		goto err_destroy_cq;
 	}
+	queue->qp = queue->cm_id->qp;
 
 	atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr);
 
@@ -1053,11 +1055,10 @@
 
 static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue)
 {
-	struct ib_qp *qp = queue->cm_id->qp;
-
-	ib_drain_qp(qp);
-	rdma_destroy_id(queue->cm_id);
-	ib_destroy_qp(qp);
+	ib_drain_qp(queue->qp);
+	if (queue->cm_id)
+		rdma_destroy_id(queue->cm_id);
+	ib_destroy_qp(queue->qp);
 	ib_free_cq(queue->cq);
 }
 
@@ -1291,9 +1292,12 @@
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
 	if (ret) {
-		schedule_work(&queue->release_work);
-		/* Destroying rdma_cm id is not needed here */
-		return 0;
+		/*
+		 * Don't destroy the cm_id in free path, as we implicitly
+		 * destroy the cm_id here with non-zero ret code.
+		 */
+		queue->cm_id = NULL;
+		goto free_queue;
 	}
 
 	mutex_lock(&nvmet_rdma_queue_mutex);
@@ -1302,6 +1306,8 @@
 
 	return 0;
 
+free_queue:
+	nvmet_rdma_free_queue(queue);
 put_device:
 	kref_put(&ndev->ref, nvmet_rdma_free_dev);
 
@@ -1345,6 +1351,16 @@
 	spin_lock_irqsave(&queue->state_lock, flags);
 	switch (queue->state) {
 	case NVMET_RDMA_Q_CONNECTING:
+		while (!list_empty(&queue->rsp_wait_list)) {
+			struct nvmet_rdma_rsp *rsp;
+
+			rsp = list_first_entry(&queue->rsp_wait_list,
+					       struct nvmet_rdma_rsp,
+					       wait_list);
+			list_del(&rsp->wait_list);
+			nvmet_rdma_put_rsp(rsp);
+		}
+		fallthrough;
 	case NVMET_RDMA_Q_LIVE:
 		queue->state = NVMET_RDMA_Q_DISCONNECTING;
 		disconnect = true;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index d535080..2ae8462 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -150,6 +150,11 @@
 static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
 		struct nvmet_tcp_cmd *cmd)
 {
+	if (unlikely(!queue->nr_cmds)) {
+		/* We didn't allocate cmds yet, send 0xffff */
+		return USHRT_MAX;
+	}
+
 	return cmd - queue->cmds;
 }
 
@@ -287,7 +292,7 @@
 	length = cmd->pdu_len;
 	cmd->nr_mapped = DIV_ROUND_UP(length, PAGE_SIZE);
 	offset = cmd->rbytes_done;
-	cmd->sg_idx = DIV_ROUND_UP(offset, PAGE_SIZE);
+	cmd->sg_idx = offset / PAGE_SIZE;
 	sg_offset = offset % PAGE_SIZE;
 	sg = &cmd->req.sg[cmd->sg_idx];
 
@@ -300,6 +305,7 @@
 		length -= iov_len;
 		sg = sg_next(sg);
 		iov++;
+		sg_offset = 0;
 	}
 
 	iov_iter_kvec(&cmd->recv_msg.msg_iter, READ, cmd->iov,
@@ -515,7 +521,7 @@
 	return 1;
 }
 
-static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
 	int ret;
@@ -523,9 +529,15 @@
 	while (cmd->cur_sg) {
 		struct page *page = sg_page(cmd->cur_sg);
 		u32 left = cmd->cur_sg->length - cmd->offset;
+		int flags = MSG_DONTWAIT;
+
+		if ((!last_in_batch && cmd->queue->send_list_len) ||
+		    cmd->wbytes_done + left < cmd->req.transfer_len ||
+		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
+			flags |= MSG_MORE;
 
 		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
-					left, MSG_DONTWAIT | MSG_MORE);
+					left, flags);
 		if (ret <= 0)
 			return ret;
 
@@ -660,7 +672,7 @@
 	}
 
 	if (cmd->state == NVMET_TCP_SEND_DATA) {
-		ret = nvmet_try_send_data(cmd);
+		ret = nvmet_try_send_data(cmd, last_in_batch);
 		if (ret <= 0)
 			goto done_send;
 	}
@@ -788,7 +800,7 @@
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
+	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -841,7 +853,10 @@
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
 
-	cmd = &queue->cmds[data->ttag];
+	if (likely(queue->nr_cmds))
+		cmd = &queue->cmds[data->ttag];
+	else
+		cmd = &queue->connect;
 
 	if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) {
 		pr_err("ttag %u unexpected data offset %u (expected %u)\n",
@@ -1387,7 +1402,7 @@
 {
 	struct nvmet_tcp_queue *queue;
 
-	write_lock_bh(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (!queue)
 		goto done;
@@ -1397,7 +1412,6 @@
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSE:
 		/* FALLTHRU */
-		sk->sk_user_data = NULL;
 		nvmet_tcp_schedule_release_queue(queue);
 		break;
 	default:
@@ -1405,7 +1419,7 @@
 			queue->idx, sk->sk_state);
 	}
 done:
-	write_unlock_bh(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index e645caa..3f61b66 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -46,19 +46,12 @@
 	return req->sq->ctrl;
 }
 
-static inline void __assign_disk_name(char *name, struct nvmet_req *req,
-		bool init)
+static inline void __assign_req_name(char *name, struct nvmet_req *req)
 {
-	struct nvmet_ctrl *ctrl = nvmet_req_to_ctrl(req);
-	struct nvmet_ns *ns;
-
-	if ((init && req->sq->qid) || (!init && req->cq->qid)) {
-		ns = nvmet_find_namespace(ctrl, req->cmd->rw.nsid);
-		strncpy(name, ns->device_path, DISK_NAME_LEN);
-		return;
-	}
-
-	memset(name, 0, DISK_NAME_LEN);
+	if (req->ns)
+		strncpy(name, req->ns->device_path, DISK_NAME_LEN);
+	else
+		memset(name, 0, DISK_NAME_LEN);
 }
 #endif
 
@@ -81,7 +74,7 @@
 	TP_fast_assign(
 		__entry->cmd = cmd;
 		__entry->ctrl = nvmet_req_to_ctrl(req);
-		__assign_disk_name(__entry->disk, req, true);
+		__assign_req_name(__entry->disk, req);
 		__entry->qid = req->sq->qid;
 		__entry->cid = cmd->common.command_id;
 		__entry->opcode = cmd->common.opcode;
@@ -121,7 +114,7 @@
 		__entry->cid = req->cqe->command_id;
 		__entry->result = le64_to_cpu(req->cqe->result.u64);
 		__entry->status = le16_to_cpu(req->cqe->status) >> 1;
-		__assign_disk_name(__entry->disk, req, false);
+		__assign_req_name(__entry->disk, req);
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
 		__print_ctrl_name(__entry->ctrl),