6.18.11-rc1 review

@@ -34,6 +34,7 @@ enum {
 
 enum {
 	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
+	IO_WQ_BIT_EXIT_ON_IDLE	= 1,	/* allow all workers to exit on idle */
 };
 
 enum {

@@ -706,9 +707,13 @@ static int io_wq_worker(void *data)
 		raw_spin_lock(&acct->workers_lock);
 		/*
 		 * Last sleep timed out. Exit if we're not the last worker,
-		 * or if someone modified our affinity.
+		 * or if someone modified our affinity. If wq is marked
+		 * idle-exit, drop the worker as well. This is used to avoid
+		 * keeping io-wq workers around for tasks that no longer have
+		 * any active io_uring instances.
 		 */
-		if (last_timeout && (exit_mask || acct->nr_workers > 1)) {
+		if ((last_timeout && (exit_mask || acct->nr_workers > 1)) ||
+		    test_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) {
 			acct->nr_workers--;
 			raw_spin_unlock(&acct->workers_lock);
 			__set_current_state(TASK_RUNNING);

@@ -965,6 +970,24 @@ static bool io_wq_worker_wake(struct io_
 	return false;
 }
 
+void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable)
+{
+	if (!wq->task)
+		return;
+
+	if (!enable) {
+		clear_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state);
+		return;
+	}
+
+	if (test_and_set_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state))
+		return;
+
+	rcu_read_lock();
+	io_wq_for_each_worker(wq, io_wq_worker_wake, NULL);
+	rcu_read_unlock();
+}
+
 static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq)
 {
 	do {

@@ -41,6 +41,7 @@ struct io_wq_data {
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
 void io_wq_exit_start(struct io_wq *wq);
 void io_wq_put_and_exit(struct io_wq *wq);
+void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
 void io_wq_hash_work(struct io_wq_work *work, void *val);

@@ -122,6 +122,14 @@ int __io_uring_add_tctx_node(struct io_r
 				return ret;
 		}
 	}
+
+	/*
+	 * Re-activate io-wq keepalive on any new io_uring usage. The wq may have
+	 * been marked for idle-exit when the task temporarily had no active
+	 * io_uring instances.
+	 */
+	if (tctx->io_wq)
+		io_wq_set_exit_on_idle(tctx->io_wq, false);
 	if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
 		node = kmalloc(sizeof(*node), GFP_KERNEL);
 		if (!node)

@@ -183,6 +191,9 @@ __cold void io_uring_del_tctx_node(unsig
 	if (tctx->last == node->ctx)
 		tctx->last = NULL;
 	kfree(node);
+
+	if (xa_empty(&tctx->xa) && tctx->io_wq)
+		io_wq_set_exit_on_idle(tctx->io_wq, true);
 }
 
 __cold void io_uring_clean_tctx(struct io_uring_task *tctx)

@@ -36,10 +36,10 @@ struct cached_fid {
 	struct list_head entry;
 	struct cached_fids *cfids;
 	const char *path;
-	bool has_lease:1;
-	bool is_open:1;
-	bool on_list:1;
-	bool file_all_info_is_valid:1;
+	bool has_lease;
+	bool is_open;
+	bool on_list;
+	bool file_all_info_is_valid;
 	unsigned long time; /* jiffies of when lease was taken */
 	unsigned long last_access_time; /* jiffies of when last accessed */
 	struct kref refcount;

@@ -126,21 +126,21 @@ static int __process_request(struct ksmb
 andx_again:
 	if (command >= conn->max_cmds) {
 		conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER);
-		return SERVER_HANDLER_CONTINUE;
+		return SERVER_HANDLER_ABORT;
 	}
 
 	cmds = &conn->cmds[command];
 	if (!cmds->proc) {
 		ksmbd_debug(SMB, "*** not implemented yet cmd = %x\n", command);
 		conn->ops->set_rsp_status(work, STATUS_NOT_IMPLEMENTED);
-		return SERVER_HANDLER_CONTINUE;
+		return SERVER_HANDLER_ABORT;
 	}
 
 	if (work->sess && conn->ops->is_sign_req(work, command)) {
 		ret = conn->ops->check_sign_req(work);
 		if (!ret) {
 			conn->ops->set_rsp_status(work, STATUS_ACCESS_DENIED);
-			return SERVER_HANDLER_CONTINUE;
+			return SERVER_HANDLER_ABORT;
 		}
 	}
 

@@ -32,12 +32,14 @@ static void free_channel_list(struct ksm
 	struct channel *chann;
 	unsigned long index;
 
+	down_write(&sess->chann_lock);
 	xa_for_each(&sess->ksmbd_chann_list, index, chann) {
 		xa_erase(&sess->ksmbd_chann_list, index);
 		kfree(chann);
 	}
 
 	xa_destroy(&sess->ksmbd_chann_list);
+	up_write(&sess->chann_lock);
 }
 
 static void __session_rpc_close(struct ksmbd_session *sess,

@@ -220,7 +222,9 @@ static int ksmbd_chann_del(struct ksmbd_
 {
 	struct channel *chann;
 
+	down_write(&sess->chann_lock);
 	chann = xa_erase(&sess->ksmbd_chann_list, (long)conn);
+	up_write(&sess->chann_lock);
 	if (!chann)
 		return -ENOENT;
 

@@ -454,6 +458,7 @@ static struct ksmbd_session *__session_c
 	rwlock_init(&sess->tree_conns_lock);
 	atomic_set(&sess->refcnt, 2);
 	init_rwsem(&sess->rpc_lock);
+	init_rwsem(&sess->chann_lock);
 
 	ret = __init_smb2_session(sess);
 	if (ret)

@@ -49,6 +49,7 @@ struct ksmbd_session {
 	char				sess_key[CIFS_KEY_SIZE];
 
 	struct hlist_node		hlist;
+	struct rw_semaphore		chann_lock;
 	struct xarray			ksmbd_chann_list;
 	struct xarray			tree_conns;
 	struct ida			tree_conn_ida;

@@ -79,7 +79,13 @@ static inline bool check_session_id(stru
 
 struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn)
 {
-	return xa_load(&sess->ksmbd_chann_list, (long)conn);
+	struct channel *chann;
+
+	down_read(&sess->chann_lock);
+	chann = xa_load(&sess->ksmbd_chann_list, (long)conn);
+	up_read(&sess->chann_lock);
+
+	return chann;
 }
 
 /**

@@ -1563,8 +1569,10 @@ binding_session:
 				return -ENOMEM;
 
 			chann->conn = conn;
+			down_write(&sess->chann_lock);
 			old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann,
 					KSMBD_DEFAULT_GFP);
+			up_write(&sess->chann_lock);
 			if (xa_is_err(old)) {
 				kfree(chann);
 				return xa_err(old);

@@ -1661,8 +1669,10 @@ binding_session:
 				return -ENOMEM;
 
 			chann->conn = conn;
+			down_write(&sess->chann_lock);
 			old = xa_store(&sess->ksmbd_chann_list, (long)conn,
 					chann, KSMBD_DEFAULT_GFP);
+			up_write(&sess->chann_lock);
 			if (xa_is_err(old)) {
 				kfree(chann);
 				return xa_err(old);

@@ -41,6 +41,7 @@ static const struct ksmbd_transport_ops
 
 static void tcp_stop_kthread(struct task_struct *kthread);
 static struct interface *alloc_iface(char *ifname);
+static void ksmbd_tcp_disconnect(struct ksmbd_transport *t);
 
 #define KSMBD_TRANS(t)	(&(t)->transport)
 #define TCP_TRANS(t)	((struct tcp_transport *)container_of(t, \

@@ -216,7 +217,7 @@ static int ksmbd_tcp_new_connection(stru
 	if (IS_ERR(handler)) {
 		pr_err("cannot start conn thread\n");
 		rc = PTR_ERR(handler);
-		free_transport(t);
+		ksmbd_tcp_disconnect(KSMBD_TRANS(t));
 	}
 	return rc;
 }

@@ -231,6 +231,7 @@ struct smbdirect_socket {
 		 */
 		struct {
 			u16 target;
+			atomic_t available;
 			atomic_t count;
 		} credits;
 

@@ -375,6 +376,7 @@ static __always_inline void smbdirect_so
 	INIT_WORK(&sc->recv_io.posted.refill_work, __smbdirect_socket_disabled_work);
 	disable_work_sync(&sc->recv_io.posted.refill_work);
 
+	atomic_set(&sc->recv_io.credits.available, 0);
 	atomic_set(&sc->recv_io.credits.count, 0);
 
 	INIT_LIST_HEAD(&sc->recv_io.reassembly.list);

@@ -155,6 +155,17 @@ struct smbdirect_socket {
 		} mem;
 
 		/*
+		 * This is a coordination for smbdirect_send_batch.
+		 *
+		 * There's only one possible credit, which means
+		 * only one instance is running at a time.
+		 */
+		struct {
+			atomic_t count;
+			wait_queue_head_t wait_queue;
+		} bcredits;
+
+		/*
 		 * The local credit state for ib_post_send()
 		 */
 		struct {

@@ -359,6 +370,9 @@ static __always_inline void smbdirect_so
 	INIT_DELAYED_WORK(&sc->idle.timer_work, __smbdirect_socket_disabled_work);
 	disable_delayed_work_sync(&sc->idle.timer_work);
 
+	atomic_set(&sc->send_io.bcredits.count, 0);
+	init_waitqueue_head(&sc->send_io.bcredits.wait_queue);
+
 	atomic_set(&sc->send_io.lcredits.count, 0);
 	init_waitqueue_head(&sc->send_io.lcredits.wait_queue);
 

@@ -473,6 +487,8 @@ struct smbdirect_send_batch {
 	 */
 	bool need_invalidate_rkey;
 	u32 remote_key;
+
+	int credit;
 };
 
 struct smbdirect_recv_io {

@@ -926,6 +926,8 @@ static void smb_direct_post_recv_credits
 		}
 	}
 
+	atomic_add(credits, &sc->recv_io.credits.available);
+
 	if (credits)
 		queue_work(sc->workqueue, &sc->idle.immediate_work);
 }

@@ -972,19 +974,37 @@ static void send_done(struct ib_cq *cq,
 
 static int manage_credits_prior_sending(struct smbdirect_socket *sc)
 {
+	int missing;
+	int available;
 	int new_credits;
 
 	if (atomic_read(&sc->recv_io.credits.count) >= sc->recv_io.credits.target)
 		return 0;
 
-	new_credits = atomic_read(&sc->recv_io.posted.count);
-	if (new_credits == 0)
+	missing = (int)sc->recv_io.credits.target - atomic_read(&sc->recv_io.credits.count);
+	available = atomic_xchg(&sc->recv_io.credits.available, 0);
+	new_credits = (u16)min3(U16_MAX, missing, available);
+	if (new_credits <= 0) {
+		/*
+		 * If credits are available, but not granted
+		 * we need to re-add them again.
+		 */
+		if (available)
+			atomic_add(available, &sc->recv_io.credits.available);
 		return 0;
+	}
 
-	new_credits -= atomic_read(&sc->recv_io.credits.count);
-	if (new_credits <= 0)
-		return 0;
+	if (new_credits < available) {
+		/*
+		 * Readd the remaining available again.
+		 */
+		available -= new_credits;
+		atomic_add(available, &sc->recv_io.credits.available);
+	}
 
+	/*
+	 * Remember we granted the credits
+	 */
 	atomic_add(new_credits, &sc->recv_io.credits.count);
 	return new_credits;
 }

@@ -661,6 +661,7 @@ static void recv_done(struct ib_cq *cq,
 		struct smbdirect_data_transfer *data_transfer =
 			(struct smbdirect_data_transfer *)recvmsg->packet;
 		u32 remaining_data_length, data_offset, data_length;
+		int current_recv_credits;
 		u16 old_recv_credit_target;
 
 		if (wc->byte_len <

@@ -699,7 +700,7 @@ static void recv_done(struct ib_cq *cq,
 		}
 
 		atomic_dec(&sc->recv_io.posted.count);
-		atomic_dec(&sc->recv_io.credits.count);
+		current_recv_credits = atomic_dec_return(&sc->recv_io.credits.count);
 
 		old_recv_credit_target = sc->recv_io.credits.target;
 		sc->recv_io.credits.target =

@@ -719,7 +720,8 @@ static void recv_done(struct ib_cq *cq,
 			wake_up(&sc->send_io.credits.wait_queue);
 
 		if (data_length) {
-			if (sc->recv_io.credits.target > old_recv_credit_target)
+			if (current_recv_credits <= (sc->recv_io.credits.target / 4) ||
+			    sc->recv_io.credits.target > old_recv_credit_target)
 				queue_work(sc->workqueue, &sc->recv_io.posted.refill_work);
 
 			enqueue_reassembly(sc, recvmsg, (int)data_length);

@@ -221,6 +221,7 @@ static void smb_direct_disconnect_wake_u
 	 * in order to notice the broken connection.
 	 */
 	wake_up_all(&sc->status_wait);
+	wake_up_all(&sc->send_io.bcredits.wait_queue);
 	wake_up_all(&sc->send_io.lcredits.wait_queue);
 	wake_up_all(&sc->send_io.credits.wait_queue);
 	wake_up_all(&sc->send_io.pending.zero_wait_queue);

@@ -1050,6 +1051,7 @@ static void smb_direct_send_ctx_init(str
 	send_ctx->wr_cnt = 0;
 	send_ctx->need_invalidate_rkey = need_invalidate_rkey;
 	send_ctx->remote_key = remote_key;
+	send_ctx->credit = 0;
 }
 
 static int smb_direct_flush_send_list(struct smbdirect_socket *sc,

@@ -1057,10 +1059,10 @@ static int smb_direct_flush_send_list(st
 				      bool is_last)
 {
 	struct smbdirect_send_io *first, *last;
-	int ret;
+	int ret = 0;
 
 	if (list_empty(&send_ctx->msg_list))
-		return 0;
+		goto release_credit;
 
 	first = list_first_entry(&send_ctx->msg_list,
 				 struct smbdirect_send_io,

@@ -1102,6 +1104,13 @@ static int smb_direct_flush_send_list(st
 		smb_direct_free_sendmsg(sc, last);
 	}
 
+release_credit:
+	if (is_last && !ret && send_ctx->credit) {
+		atomic_add(send_ctx->credit, &sc->send_io.bcredits.count);
+		send_ctx->credit = 0;
+		wake_up(&sc->send_io.bcredits.wait_queue);
+	}
+
 	return ret;
 }
 

@@ -1127,6 +1136,25 @@ static int wait_for_credits(struct smbdi
 	} while (true);
 }
 
+static int wait_for_send_bcredit(struct smbdirect_socket *sc,
+				 struct smbdirect_send_batch *send_ctx)
+{
+	int ret;
+
+	if (send_ctx->credit)
+		return 0;
+
+	ret = wait_for_credits(sc,
+			       &sc->send_io.bcredits.wait_queue,
+			       &sc->send_io.bcredits.count,
+			       1);
+	if (ret)
+		return ret;
+
+	send_ctx->credit = 1;
+	return 0;
+}
+
 static int wait_for_send_lcredit(struct smbdirect_socket *sc,
 				 struct smbdirect_send_batch *send_ctx)
 {

@@ -1328,6 +1356,16 @@ static int smb_direct_post_send_data(str
 	struct smbdirect_send_io *msg;
 	int data_length;
 	struct scatterlist sg[SMBDIRECT_SEND_IO_MAX_SGE - 1];
+	struct smbdirect_send_batch _send_ctx;
+
+	if (!send_ctx) {
+		smb_direct_send_ctx_init(&_send_ctx, false, 0);
+		send_ctx = &_send_ctx;
+	}
+
+	ret = wait_for_send_bcredit(sc, send_ctx);
+	if (ret)
+		goto bcredit_failed;
 
 	ret = wait_for_send_lcredit(sc, send_ctx);
 	if (ret)

@@ -1380,6 +1418,13 @@ static int smb_direct_post_send_data(str
 	ret = post_sendmsg(sc, send_ctx, msg);
 	if (ret)
 		goto err;
+
+	if (send_ctx == &_send_ctx) {
+		ret = smb_direct_flush_send_list(sc, send_ctx, true);
+		if (ret)
+			goto err;
+	}
+
 	return 0;
 err:
 	smb_direct_free_sendmsg(sc, msg);

@@ -1388,6 +1433,9 @@ header_failed:
 credit_failed:
 	atomic_inc(&sc->send_io.lcredits.count);
 lcredit_failed:
+	atomic_add(send_ctx->credit, &sc->send_io.bcredits.count);
+	send_ctx->credit = 0;
+bcredit_failed:
 	return ret;
 }
 

@@ -1849,6 +1897,7 @@ static int smb_direct_send_negotiate_res
 		resp->max_fragmented_size =
 				cpu_to_le32(sp->max_fragmented_recv_size);
 
+		atomic_set(&sc->send_io.bcredits.count, 1);
 		sc->recv_io.expected = SMBDIRECT_EXPECT_DATA_TRANSFER;
 		sc->status = SMBDIRECT_SOCKET_CONNECTED;
 	}

@@ -931,6 +931,15 @@ static void smb_direct_post_recv_credits
 
 	atomic_add(credits, &sc->recv_io.credits.available);
 
+	/*
+	 * If the last send credit is waiting for credits
+	 * it can grant we need to wake it up
+	 */
+	if (credits &&
+	    atomic_read(&sc->send_io.bcredits.count) == 0 &&
+	    atomic_read(&sc->send_io.credits.count) == 0)
+		wake_up(&sc->send_io.credits.wait_queue);
+
 	if (credits)
 		queue_work(sc->workqueue, &sc->idle.immediate_work);
 }

@@ -1204,6 +1213,7 @@ static int calc_rw_credits(struct smbdir
 
 static int smb_direct_create_header(struct smbdirect_socket *sc,
 				    int size, int remaining_data_length,
+				    int new_credits,
 				    struct smbdirect_send_io **sendmsg_out)
 {
 	struct smbdirect_socket_parameters *sp = &sc->parameters;

@@ -1219,7 +1229,7 @@ static int smb_direct_create_header(stru
 	/* Fill in the packet header */
 	packet = (struct smbdirect_data_transfer *)sendmsg->packet;
 	packet->credits_requested = cpu_to_le16(sp->send_credit_target);
-	packet->credits_granted = cpu_to_le16(manage_credits_prior_sending(sc));
+	packet->credits_granted = cpu_to_le16(new_credits);
 
 	packet->flags = 0;
 	if (manage_keep_alive_before_sending(sc))

@@ -1357,6 +1367,7 @@ static int smb_direct_post_send_data(str
 	int data_length;
 	struct scatterlist sg[SMBDIRECT_SEND_IO_MAX_SGE - 1];
 	struct smbdirect_send_batch _send_ctx;
+	int new_credits;
 
 	if (!send_ctx) {
 		smb_direct_send_ctx_init(&_send_ctx, false, 0);

@@ -1375,12 +1386,29 @@ static int smb_direct_post_send_data(str
 	if (ret)
 		goto credit_failed;
 
+	new_credits = manage_credits_prior_sending(sc);
+	if (new_credits == 0 &&
+	    atomic_read(&sc->send_io.credits.count) == 0 &&
+	    atomic_read(&sc->recv_io.credits.count) == 0) {
+		queue_work(sc->workqueue, &sc->recv_io.posted.refill_work);
+		ret = wait_event_interruptible(sc->send_io.credits.wait_queue,
+					       atomic_read(&sc->send_io.credits.count) >= 1 ||
+					       atomic_read(&sc->recv_io.credits.available) >= 1 ||
+					       sc->status != SMBDIRECT_SOCKET_CONNECTED);
+		if (sc->status != SMBDIRECT_SOCKET_CONNECTED)
+			ret = -ENOTCONN;
+		if (ret < 0)
+			goto credit_failed;
+
+		new_credits = manage_credits_prior_sending(sc);
+	}
+
 	data_length = 0;
 	for (i = 0; i < niov; i++)
 		data_length += iov[i].iov_len;
 
 	ret = smb_direct_create_header(sc, data_length, remaining_data_length,
-				       &msg);
+				       new_credits, &msg);
 	if (ret)
 		goto header_failed;
 

@@ -957,6 +957,31 @@ static void send_done(struct ib_cq *cq,
 		    ib_wc_status_msg(wc->status), wc->status,
 		    wc->opcode);
 
+	if (unlikely(!(sendmsg->wr.send_flags & IB_SEND_SIGNALED))) {
+		/*
+		 * This happens when smbdirect_send_io is a sibling
+		 * before the final message, it is signaled on
+		 * error anyway, so we need to skip
+		 * smbdirect_connection_free_send_io here,
+		 * otherwise is will destroy the memory
+		 * of the siblings too, which will cause
+		 * use after free problems for the others
+		 * triggered from ib_drain_qp().
+		 */
+		if (wc->status != IB_WC_SUCCESS)
+			goto skip_free;
+
+		/*
+		 * This should not happen!
+		 * But we better just close the
+		 * connection...
+		 */
+		pr_err("unexpected send completion wc->status=%s (%d) wc->opcode=%d\n",
+		       ib_wc_status_msg(wc->status), wc->status, wc->opcode);
+		smb_direct_disconnect_rdma_connection(sc);
+		return;
+	}
+
 	/*
 	 * Free possible siblings and then the main send_io
 	 */

@@ -970,6 +995,7 @@ static void send_done(struct ib_cq *cq,
 	lcredits += 1;
 
 	if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) {
+skip_free:
 		pr_err("Send error. status='%s (%d)', opcode=%d\n",
 		       ib_wc_status_msg(wc->status), wc->status,
 		       wc->opcode);

@@ -618,6 +618,7 @@ static void smbd_post_send_credits(struc
 	struct smbdirect_recv_io *response;
 	struct smbdirect_socket *sc =
 		container_of(work, struct smbdirect_socket, recv_io.posted.refill_work);
+	int posted = 0;
 
 	if (sc->status != SMBDIRECT_SOCKET_CONNECTED) {
 		return;

@@ -640,9 +641,12 @@ static void smbd_post_send_credits(struc
 			}
 
 			atomic_inc(&sc->recv_io.posted.count);
+			posted += 1;
 		}
 	}
 
+	atomic_add(posted, &sc->recv_io.credits.available);
+
 	/* Promptly send an immediate packet as defined in [MS-SMBD] 3.1.1.1 */
 	if (atomic_read(&sc->recv_io.credits.count) <
 		sc->recv_io.credits.target - 1) {

@@ -1033,19 +1037,38 @@ dma_mapping_failed:
  */
 static int manage_credits_prior_sending(struct smbdirect_socket *sc)
 {
+	int missing;
+	int available;
 	int new_credits;
 
 	if (atomic_read(&sc->recv_io.credits.count) >= sc->recv_io.credits.target)
 		return 0;
 
-	new_credits = atomic_read(&sc->recv_io.posted.count);
-	if (new_credits == 0)
+	missing = (int)sc->recv_io.credits.target - atomic_read(&sc->recv_io.credits.count);
+	available = atomic_xchg(&sc->recv_io.credits.available, 0);
+	new_credits = (u16)min3(U16_MAX, missing, available);
+	if (new_credits <= 0) {
+		/*
+		 * If credits are available, but not granted
+		 * we need to re-add them again.
+		 */
+		if (available)
+			atomic_add(available, &sc->recv_io.credits.available);
 		return 0;
+	}
 
-	new_credits -= atomic_read(&sc->recv_io.credits.count);
-	if (new_credits <= 0)
-		return 0;
+	if (new_credits < available) {
+		/*
+		 * Readd the remaining available again.
+		 */
+		available -= new_credits;
+		atomic_add(available, &sc->recv_io.credits.available);
+	}
 
+	/*
+	 * Remember we granted the credits
+	 */
+	atomic_add(new_credits, &sc->recv_io.credits.count);
 	return new_credits;
 }
 

@@ -1217,7 +1240,6 @@ wait_credit:
 	packet->credits_requested = cpu_to_le16(sp->send_credit_target);
 
 	new_credits = manage_credits_prior_sending(sc);
-	atomic_add(new_credits, &sc->recv_io.credits.count);
 	packet->credits_granted = cpu_to_le16(new_credits);
 
 	packet->flags = 0;

@@ -663,6 +663,7 @@ static void recv_done(struct ib_cq *cq,
 		container_of(wc->wr_cqe, struct smbdirect_recv_io, cqe);
 	struct smbdirect_socket *sc = response->socket;
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
+	int current_recv_credits;
 	u16 old_recv_credit_target;
 	u32 data_offset = 0;
 	u32 data_length = 0;

@@ -747,7 +748,8 @@ static void recv_done(struct ib_cq *cq,
 		}
 
 		atomic_dec(&sc->recv_io.posted.count);
-		atomic_dec(&sc->recv_io.credits.count);
+		current_recv_credits = atomic_dec_return(&sc->recv_io.credits.count);
+
 		old_recv_credit_target = sc->recv_io.credits.target;
 		sc->recv_io.credits.target =
 			le16_to_cpu(data_transfer->credits_requested);

@@ -783,7 +785,8 @@ static void recv_done(struct ib_cq *cq,
 		 * reassembly queue and wake up the reading thread
 		 */
 		if (data_length) {
-			if (sc->recv_io.credits.target > old_recv_credit_target)
+			if (current_recv_credits <= (sc->recv_io.credits.target / 4) ||
+			    sc->recv_io.credits.target > old_recv_credit_target)
 				queue_work(sc->workqueue, &sc->recv_io.posted.refill_work);
 
 			enqueue_reassembly(sc, response, data_length);

index 61693b4a83fc..f2ae35a9f047 100644
@@ -1105,7 +1105,6 @@ static int manage_keep_alive_before_sending(struct smbdirect_socket *sc)
 static int smbd_post_send(struct smbdirect_socket *sc,
 		struct smbdirect_send_io *request)
 {
-	struct ib_send_wr send_wr;
 	int rc, i;
 
 	for (i = 0; i < request->num_sge; i++) {

@@ -1121,14 +1120,14 @@ static int smbd_post_send(struct smbdirect_socket *sc,
 
 	request->cqe.done = send_done;
 
-	send_wr.next = NULL;
-	send_wr.wr_cqe = &request->cqe;
-	send_wr.sg_list = request->sge;
-	send_wr.num_sge = request->num_sge;
-	send_wr.opcode = IB_WR_SEND;
-	send_wr.send_flags = IB_SEND_SIGNALED;
+	request->wr.next = NULL;
+	request->wr.wr_cqe = &request->cqe;
+	request->wr.sg_list = request->sge;
+	request->wr.num_sge = request->num_sge;
+	request->wr.opcode = IB_WR_SEND;
+	request->wr.send_flags = IB_SEND_SIGNALED;
 
-	rc = ib_post_send(sc->ib.qp, &send_wr, NULL);
+	rc = ib_post_send(sc->ib.qp, &request->wr, NULL);
 	if (rc) {
 		log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
 		smbd_disconnect_rdma_connection(sc);

index f2ae35a9f047..c9fcd35e0c77 100644
@@ -1288,9 +1288,6 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 					    DMA_TO_DEVICE);
 	mempool_free(request, sc->send_io.mem.pool);
 
-	/* roll back the granted receive credits */
-	atomic_sub(new_credits, &sc->recv_io.credits.count);
-
 err_alloc:
 	atomic_inc(&sc->send_io.credits.count);
 	wake_up(&sc->send_io.credits.wait_queue);

index c9fcd35e0c77..cfbe8ce0db42 100644
@@ -1274,11 +1274,6 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 	if (!rc)
 		return 0;
 
-	if (atomic_dec_and_test(&sc->send_io.pending.count))
-		wake_up(&sc->send_io.pending.zero_wait_queue);
-
-	wake_up(&sc->send_io.pending.dec_wait_queue);
-
 err_dma:
 	for (i = 0; i < request->num_sge; i++)
 		if (request->sge[i].addr)

index cfbe8ce0db42..405931ce3978 100644
@@ -1137,6 +1137,44 @@ static int smbd_post_send(struct smbdirect_socket *sc,
 	return rc;
 }
 
+static int wait_for_credits(struct smbdirect_socket *sc,
+			    wait_queue_head_t *waitq, atomic_t *total_credits,
+			    int needed)
+{
+	int ret;
+
+	do {
+		if (atomic_sub_return(needed, total_credits) >= 0)
+			return 0;
+
+		atomic_add(needed, total_credits);
+		ret = wait_event_interruptible(*waitq,
+					       atomic_read(total_credits) >= needed ||
+					       sc->status != SMBDIRECT_SOCKET_CONNECTED);
+
+		if (sc->status != SMBDIRECT_SOCKET_CONNECTED)
+			return -ENOTCONN;
+		else if (ret < 0)
+			return ret;
+	} while (true);
+}
+
+static int wait_for_send_lcredit(struct smbdirect_socket *sc)
+{
+	return wait_for_credits(sc,
+				&sc->send_io.lcredits.wait_queue,
+				&sc->send_io.lcredits.count,
+				1);
+}
+
+static int wait_for_send_credits(struct smbdirect_socket *sc)
+{
+	return wait_for_credits(sc,
+				&sc->send_io.credits.wait_queue,
+				&sc->send_io.credits.count,
+				1);
+}
+
 static int smbd_post_send_iter(struct smbdirect_socket *sc,
 			       struct iov_iter *iter,
 			       int *_remaining_data_length)

@@ -1149,41 +1187,19 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 	struct smbdirect_data_transfer *packet;
 	int new_credits = 0;
 
-wait_lcredit:
-	/* Wait for local send credits */
-	rc = wait_event_interruptible(sc->send_io.lcredits.wait_queue,
-		atomic_read(&sc->send_io.lcredits.count) > 0 ||
-		sc->status != SMBDIRECT_SOCKET_CONNECTED);
-	if (rc)
-		goto err_wait_lcredit;
-
-	if (sc->status != SMBDIRECT_SOCKET_CONNECTED) {
-		log_outgoing(ERR, "disconnected not sending on wait_credit\n");
+	rc = wait_for_send_lcredit(sc);
+	if (rc) {
+		log_outgoing(ERR, "disconnected not sending on wait_lcredit\n");
 		rc = -EAGAIN;
 		goto err_wait_lcredit;
 	}
-	if (unlikely(atomic_dec_return(&sc->send_io.lcredits.count) < 0)) {
-		atomic_inc(&sc->send_io.lcredits.count);
-		goto wait_lcredit;
-	}
 
-wait_credit:
-	/* Wait for send credits. A SMBD packet needs one credit */
-	rc = wait_event_interruptible(sc->send_io.credits.wait_queue,
-		atomic_read(&sc->send_io.credits.count) > 0 ||
-		sc->status != SMBDIRECT_SOCKET_CONNECTED);
-	if (rc)
-		goto err_wait_credit;
-
-	if (sc->status != SMBDIRECT_SOCKET_CONNECTED) {
+	rc = wait_for_send_credits(sc);
+	if (rc) {
 		log_outgoing(ERR, "disconnected not sending on wait_credit\n");
 		rc = -EAGAIN;
 		goto err_wait_credit;
 	}
-	if (unlikely(atomic_dec_return(&sc->send_io.credits.count) < 0)) {
-		atomic_inc(&sc->send_io.credits.count);
-		goto wait_credit;
-	}
 
 	request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL);
 	if (!request) {

@@ -1101,11 +1101,26 @@ static int manage_keep_alive_before_send
 	return 0;
 }
 
+static int smbd_ib_post_send(struct smbdirect_socket *sc,
+			     struct ib_send_wr *wr)
+{
+	int ret;
+
+	atomic_inc(&sc->send_io.pending.count);
+	ret = ib_post_send(sc->ib.qp, wr, NULL);
+	if (ret) {
+		pr_err("failed to post send: %d\n", ret);
+		smbd_disconnect_rdma_connection(sc);
+		ret = -EAGAIN;
+	}
+	return ret;
+}
+
 /* Post the send request */
 static int smbd_post_send(struct smbdirect_socket *sc,
 		struct smbdirect_send_io *request)
 {
-	int rc, i;
+	int i;
 
 	for (i = 0; i < request->num_sge; i++) {
 		log_rdma_send(INFO,

@@ -1126,15 +1141,7 @@ static int smbd_post_send(struct smbdire
 	request->wr.num_sge = request->num_sge;
 	request->wr.opcode = IB_WR_SEND;
 	request->wr.send_flags = IB_SEND_SIGNALED;
-
-	rc = ib_post_send(sc->ib.qp, &request->wr, NULL);
-	if (rc) {
-		log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
-		smbd_disconnect_rdma_connection(sc);
-		rc = -EAGAIN;
-	}
-
-	return rc;
+	return smbd_ib_post_send(sc, &request->wr);
 }
 
 static int wait_for_credits(struct smbdirect_socket *sc,

@@ -1280,12 +1287,6 @@ static int smbd_post_send_iter(struct sm
 		     le32_to_cpu(packet->data_length),
 		     le32_to_cpu(packet->remaining_data_length));
 
-	/*
-	 * Now that we got a local and a remote credit
-	 * we add us as pending
-	 */
-	atomic_inc(&sc->send_io.pending.count);
-
 	rc = smbd_post_send(sc, request);
 	if (!rc)
 		return 0;

index 75c0ac9cc65c..6cb40da7e589 100644
@@ -493,10 +493,54 @@ static inline void *smbdirect_recv_io_payload(struct smbdirect_recv_io *response
 	return (void *)response->packet;
 }
 
+static struct smbdirect_send_io *smbd_alloc_send_io(struct smbdirect_socket *sc)
+{
+	struct smbdirect_send_io *msg;
+
+	msg = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+	msg->socket = sc;
+	INIT_LIST_HEAD(&msg->sibling_list);
+	msg->num_sge = 0;
+
+	return msg;
+}
+
+static void smbd_free_send_io(struct smbdirect_send_io *msg)
+{
+	struct smbdirect_socket *sc = msg->socket;
+	size_t i;
+
+	/*
+	 * The list needs to be empty!
+	 * The caller should take care of it.
+	 */
+	WARN_ON_ONCE(!list_empty(&msg->sibling_list));
+
+	/*
+	 * Note we call ib_dma_unmap_page(), even if some sges are mapped using
+	 * ib_dma_map_single().
+	 *
+	 * The difference between _single() and _page() only matters for the
+	 * ib_dma_map_*() case.
+	 *
+	 * For the ib_dma_unmap_*() case it does not matter as both take the
+	 * dma_addr_t and dma_unmap_single_attrs() is just an alias to
+	 * dma_unmap_page_attrs().
+	 */
+	for (i = 0; i < msg->num_sge; i++)
+		ib_dma_unmap_page(sc->ib.dev,
+				  msg->sge[i].addr,
+				  msg->sge[i].length,
+				  DMA_TO_DEVICE);
+
+	mempool_free(msg, sc->send_io.mem.pool);
+}
+
 /* Called when a RDMA send is done */
 static void send_done(struct ib_cq *cq, struct ib_wc *wc)
 {
-	int i;
 	struct smbdirect_send_io *request =
 		container_of(wc->wr_cqe, struct smbdirect_send_io, cqe);
 	struct smbdirect_socket *sc = request->socket;

@@ -505,12 +549,8 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc)
 	log_rdma_send(INFO, "smbdirect_send_io 0x%p completed wc->status=%s\n",
 		request, ib_wc_status_msg(wc->status));
 
-	for (i = 0; i < request->num_sge; i++)
-		ib_dma_unmap_single(sc->ib.dev,
-			request->sge[i].addr,
-			request->sge[i].length,
-			DMA_TO_DEVICE);
-	mempool_free(request, sc->send_io.mem.pool);
+	/* Note this frees wc->wr_cqe, but not wc */
+	smbd_free_send_io(request);
 	lcredits += 1;
 
 	if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) {

@@ -963,15 +1003,13 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 {
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
 	struct ib_send_wr send_wr;
-	int rc = -ENOMEM;
+	int rc;
 	struct smbdirect_send_io *request;
 	struct smbdirect_negotiate_req *packet;
 
-	request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL);
-	if (!request)
-		return rc;
-
-	request->socket = sc;
+	request = smbd_alloc_send_io(sc);
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	packet = smbdirect_send_io_payload(request);
 	packet->min_version = cpu_to_le16(SMBDIRECT_V1);

@@ -983,7 +1021,6 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 	packet->max_fragmented_size =
 		cpu_to_le32(sp->max_fragmented_recv_size);
 
-	request->num_sge = 1;
 	request->sge[0].addr = ib_dma_map_single(
 				sc->ib.dev, (void *)packet,
 				sizeof(*packet), DMA_TO_DEVICE);

@@ -991,6 +1028,7 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 		rc = -EIO;
 		goto dma_mapping_failed;
 	}
+	request->num_sge = 1;
 
 	request->sge[0].length = sizeof(*packet);
 	request->sge[0].lkey = sc->ib.pd->local_dma_lkey;

@@ -1020,13 +1058,11 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 	/* if we reach here, post send failed */
 	log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
 	atomic_dec(&sc->send_io.pending.count);
-	ib_dma_unmap_single(sc->ib.dev, request->sge[0].addr,
-		request->sge[0].length, DMA_TO_DEVICE);
 
 	smbd_disconnect_rdma_connection(sc);
 
 dma_mapping_failed:
-	mempool_free(request, sc->send_io.mem.pool);
+	smbd_free_send_io(request);
 	return rc;
 }
 

@@ -1187,7 +1223,7 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 			       int *_remaining_data_length)
 {
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
-	int i, rc;
+	int rc;
 	int header_length;
 	int data_length;
 	struct smbdirect_send_io *request;

@@ -1208,13 +1244,12 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 		goto err_wait_credit;
 	}
 
-	request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL);
-	if (!request) {
-		rc = -ENOMEM;
+	request = smbd_alloc_send_io(sc);
+	if (IS_ERR(request)) {
+		rc = PTR_ERR(request);
 		goto err_alloc;
 	}
 
-	request->socket = sc;
 	memset(request->sge, 0, sizeof(request->sge));
 
 	/* Map the packet to DMA */

@@ -1292,13 +1327,7 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 		return 0;
 
 err_dma:
-	for (i = 0; i < request->num_sge; i++)
-		if (request->sge[i].addr)
-			ib_dma_unmap_single(sc->ib.dev,
-					    request->sge[i].addr,
-					    request->sge[i].length,
-					    DMA_TO_DEVICE);
-	mempool_free(request, sc->send_io.mem.pool);
+	smbd_free_send_io(request);
 
 err_alloc:
 	atomic_inc(&sc->send_io.credits.count);

index 6cb40da7e589..ef3b237bccc1 100644
@@ -544,11 +544,20 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct smbdirect_send_io *request =
 		container_of(wc->wr_cqe, struct smbdirect_send_io, cqe);
 	struct smbdirect_socket *sc = request->socket;
+	struct smbdirect_send_io *sibling, *next;
 	int lcredits = 0;
 
 	log_rdma_send(INFO, "smbdirect_send_io 0x%p completed wc->status=%s\n",
 		request, ib_wc_status_msg(wc->status));
 
+	/*
+	 * Free possible siblings and then the main send_io
+	 */
+	list_for_each_entry_safe(sibling, next, &request->sibling_list, sibling_list) {
+		list_del_init(&sibling->sibling_list);
+		smbd_free_send_io(sibling);
+		lcredits += 1;
+	}
 	/* Note this frees wc->wr_cqe, but not wc */
 	smbd_free_send_io(request);
 	lcredits += 1;

@@ -1154,7 +1163,8 @@ static int smbd_ib_post_send(struct smbdirect_socket *sc,
 
 /* Post the send request */
 static int smbd_post_send(struct smbdirect_socket *sc,
-		struct smbdirect_send_io *request)
+			  struct smbdirect_send_batch *batch,
+			  struct smbdirect_send_io *request)
 {
 	int i;
 

@@ -1170,16 +1180,95 @@ static int smbd_post_send(struct smbdirect_socket *sc,
 	}
 
 	request->cqe.done = send_done;
-
 	request->wr.next = NULL;
-	request->wr.wr_cqe = &request->cqe;
 	request->wr.sg_list = request->sge;
 	request->wr.num_sge = request->num_sge;
 	request->wr.opcode = IB_WR_SEND;
+
+	if (batch) {
+		request->wr.wr_cqe = NULL;
+		request->wr.send_flags = 0;
+		if (!list_empty(&batch->msg_list)) {
+			struct smbdirect_send_io *last;
+
+			last = list_last_entry(&batch->msg_list,
+					       struct smbdirect_send_io,
+					       sibling_list);
+			last->wr.next = &request->wr;
+		}
+		list_add_tail(&request->sibling_list, &batch->msg_list);
+		batch->wr_cnt++;
+		return 0;
+	}
+
+	request->wr.wr_cqe = &request->cqe;
 	request->wr.send_flags = IB_SEND_SIGNALED;
 	return smbd_ib_post_send(sc, &request->wr);
 }
 
+static void smbd_send_batch_init(struct smbdirect_send_batch *batch,
+				 bool need_invalidate_rkey,
+				 unsigned int remote_key)
+{
+	INIT_LIST_HEAD(&batch->msg_list);
+	batch->wr_cnt = 0;
+	batch->need_invalidate_rkey = need_invalidate_rkey;
+	batch->remote_key = remote_key;
+}
+
+static int smbd_send_batch_flush(struct smbdirect_socket *sc,
+				 struct smbdirect_send_batch *batch,
+				 bool is_last)
+{
+	struct smbdirect_send_io *first, *last;
+	int ret = 0;
+
+	if (list_empty(&batch->msg_list))
+		return 0;
+
+	first = list_first_entry(&batch->msg_list,
+				 struct smbdirect_send_io,
+				 sibling_list);
+	last = list_last_entry(&batch->msg_list,
+			       struct smbdirect_send_io,
+			       sibling_list);
+
+	if (batch->need_invalidate_rkey) {
+		first->wr.opcode = IB_WR_SEND_WITH_INV;
+		first->wr.ex.invalidate_rkey = batch->remote_key;
+		batch->need_invalidate_rkey = false;
+		batch->remote_key = 0;
+	}
+
+	last->wr.send_flags = IB_SEND_SIGNALED;
+	last->wr.wr_cqe = &last->cqe;
+
+	/*
+	 * Remove last from batch->msg_list
+	 * and splice the rest of batch->msg_list
+	 * to last->sibling_list.
+	 *
+	 * batch->msg_list is a valid empty list
+	 * at the end.
+	 */
+	list_del_init(&last->sibling_list);
+	list_splice_tail_init(&batch->msg_list, &last->sibling_list);
+	batch->wr_cnt = 0;
+
+	ret = smbd_ib_post_send(sc, &first->wr);
+	if (ret) {
+		struct smbdirect_send_io *sibling, *next;
+
+		list_for_each_entry_safe(sibling, next, &last->sibling_list, sibling_list) {
+			list_del_init(&sibling->sibling_list);
+			smbd_free_send_io(sibling);
+		}
+		smbd_free_send_io(last);
+	}
+
+	return ret;
+}
+
 static int wait_for_credits(struct smbdirect_socket *sc,
 			    wait_queue_head_t *waitq, atomic_t *total_credits,
 			    int needed)

@@ -1202,16 +1291,35 @@ static int wait_for_credits(struct smbdirect_socket *sc,
 	} while (true);
 }
 
-static int wait_for_send_lcredit(struct smbdirect_socket *sc)
+static int wait_for_send_lcredit(struct smbdirect_socket *sc,
+				 struct smbdirect_send_batch *batch)
 {
+	if (batch && (atomic_read(&sc->send_io.lcredits.count) <= 1)) {
+		int ret;
+
+		ret = smbd_send_batch_flush(sc, batch, false);
+		if (ret)
+			return ret;
+	}
+
 	return wait_for_credits(sc,
 				&sc->send_io.lcredits.wait_queue,
 				&sc->send_io.lcredits.count,
 				1);
 }
 
-static int wait_for_send_credits(struct smbdirect_socket *sc)
+static int wait_for_send_credits(struct smbdirect_socket *sc,
+				 struct smbdirect_send_batch *batch)
 {
+	if (batch &&
+	    (batch->wr_cnt >= 16 || atomic_read(&sc->send_io.credits.count) <= 1)) {
+		int ret;
+
+		ret = smbd_send_batch_flush(sc, batch, false);
+		if (ret)
+			return ret;
+	}
+
 	return wait_for_credits(sc,
 				&sc->send_io.credits.wait_queue,
 				&sc->send_io.credits.count,

@@ -1219,6 +1327,7 @@ static int wait_for_send_credits(struct smbdirect_socket *sc)
 }
 
 static int smbd_post_send_iter(struct smbdirect_socket *sc,
+			       struct smbdirect_send_batch *batch,
 			       struct iov_iter *iter,
 			       int *_remaining_data_length)
 {

@@ -1230,14 +1339,14 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 	struct smbdirect_data_transfer *packet;
 	int new_credits = 0;
 
-	rc = wait_for_send_lcredit(sc);
+	rc = wait_for_send_lcredit(sc, batch);
 	if (rc) {
 		log_outgoing(ERR, "disconnected not sending on wait_lcredit\n");
 		rc = -EAGAIN;
 		goto err_wait_lcredit;
 	}
 
-	rc = wait_for_send_credits(sc);
+	rc = wait_for_send_credits(sc, batch);
 	if (rc) {
 		log_outgoing(ERR, "disconnected not sending on wait_credit\n");
 		rc = -EAGAIN;

@@ -1322,7 +1431,7 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 		     le32_to_cpu(packet->data_length),
 		     le32_to_cpu(packet->remaining_data_length));
 
-	rc = smbd_post_send(sc, request);
+	rc = smbd_post_send(sc, batch, request);
 	if (!rc)
 		return 0;
 

@@ -1351,10 +1460,11 @@ static int smbd_post_send_empty(struct smbdirect_socket *sc)
 	int remaining_data_length = 0;
 
 	sc->statistics.send_empty++;
-	return smbd_post_send_iter(sc, NULL, &remaining_data_length);
+	return smbd_post_send_iter(sc, NULL, NULL, &remaining_data_length);
 }
 
 static int smbd_post_send_full_iter(struct smbdirect_socket *sc,
+				    struct smbdirect_send_batch *batch,
 				    struct iov_iter *iter,
 				    int *_remaining_data_length)
 {

@@ -1367,7 +1477,7 @@ static int smbd_post_send_full_iter(struct smbdirect_socket *sc,
 	 */
 
 	while (iov_iter_count(iter) > 0) {
-		rc = smbd_post_send_iter(sc, iter, _remaining_data_length);
+		rc = smbd_post_send_iter(sc, batch, iter, _remaining_data_length);
 		if (rc < 0)
 			break;
 	}

@@ -2289,8 +2399,10 @@ int smbd_send(struct TCP_Server_Info *server,
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
 	struct smb_rqst *rqst;
 	struct iov_iter iter;
+	struct smbdirect_send_batch batch;
 	unsigned int remaining_data_length, klen;
 	int rc, i, rqst_idx;
+	int error = 0;
 
 	if (sc->status != SMBDIRECT_SOCKET_CONNECTED)
 		return -EAGAIN;

@@ -2315,6 +2427,7 @@ int smbd_send(struct TCP_Server_Info *server,
 			num_rqst, remaining_data_length);
 
 	rqst_idx = 0;
+	smbd_send_batch_init(&batch, false, 0);
 	do {
 		rqst = &rqst_array[rqst_idx];
 

@@ -2333,20 +2446,28 @@ int smbd_send(struct TCP_Server_Info *server,
 			klen += rqst->rq_iov[i].iov_len;
 		iov_iter_kvec(&iter, ITER_SOURCE, rqst->rq_iov, rqst->rq_nvec, klen);
 
-		rc = smbd_post_send_full_iter(sc, &iter, &remaining_data_length);
-		if (rc < 0)
+		rc = smbd_post_send_full_iter(sc, &batch, &iter, &remaining_data_length);
+		if (rc < 0) {
+			error = rc;
 			break;
+		}
 
 		if (iov_iter_count(&rqst->rq_iter) > 0) {
 			/* And then the data pages if there are any */
-			rc = smbd_post_send_full_iter(sc, &rqst->rq_iter,
+			rc = smbd_post_send_full_iter(sc, &batch, &rqst->rq_iter,
 						      &remaining_data_length);
-			if (rc < 0)
+			if (rc < 0) {
+				error = rc;
 				break;
+			}
 		}
 
 	} while (++rqst_idx < num_rqst);
 
+	rc = smbd_send_batch_flush(sc, &batch, true);
+	if (unlikely(!rc && error))
+		rc = error;
+
 	/*
 	 * As an optimization, we don't wait for individual I/O to finish
 	 * before sending the next one.

index ef3b237bccc1..dbb2d939bc44 100644
@@ -657,6 +657,7 @@ static bool process_negotiation_response(
 			sp->max_frmr_depth * PAGE_SIZE);
 	sp->max_frmr_depth = sp->max_read_write_size / PAGE_SIZE;
 
+	atomic_set(&sc->send_io.bcredits.count, 1);
 	sc->recv_io.expected = SMBDIRECT_EXPECT_DATA_TRANSFER;
 	return true;
 }

@@ -1214,6 +1215,7 @@ static void smbd_send_batch_init(struct smbdirect_send_batch *batch,
 	batch->wr_cnt = 0;
 	batch->need_invalidate_rkey = need_invalidate_rkey;
 	batch->remote_key = remote_key;
+	batch->credit = 0;
 }
 
 static int smbd_send_batch_flush(struct smbdirect_socket *sc,

@@ -1224,7 +1226,7 @@ static int smbd_send_batch_flush(struct smbdirect_socket *sc,
 	int ret = 0;
 
 	if (list_empty(&batch->msg_list))
-		return 0;
+		goto release_credit;
 
 	first = list_first_entry(&batch->msg_list,
 				 struct smbdirect_send_io,

@@ -1266,6 +1268,13 @@ static int smbd_send_batch_flush(struct smbdirect_socket *sc,
 		smbd_free_send_io(last);
 	}
 
+release_credit:
+	if (is_last && !ret && batch->credit) {
+		atomic_add(batch->credit, &sc->send_io.bcredits.count);
+		batch->credit = 0;
+		wake_up(&sc->send_io.bcredits.wait_queue);
+	}
+
 	return ret;
 }
 

@@ -1291,6 +1300,25 @@ static int wait_for_credits(struct smbdirect_socket *sc,
 	} while (true);
 }
 
+static int wait_for_send_bcredit(struct smbdirect_socket *sc,
+				 struct smbdirect_send_batch *batch)
+{
+	int ret;
+
+	if (batch->credit)
+		return 0;
+
+	ret = wait_for_credits(sc,
+			       &sc->send_io.bcredits.wait_queue,
+			       &sc->send_io.bcredits.count,
+			       1);
+	if (ret)
+		return ret;
+
+	batch->credit = 1;
+	return 0;
+}
+
 static int wait_for_send_lcredit(struct smbdirect_socket *sc,
 				 struct smbdirect_send_batch *batch)
 {

@@ -1338,6 +1366,19 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 	struct smbdirect_send_io *request;
 	struct smbdirect_data_transfer *packet;
 	int new_credits = 0;
+	struct smbdirect_send_batch _batch;
+
+	if (!batch) {
+		smbd_send_batch_init(&_batch, false, 0);
+		batch = &_batch;
+	}
+
+	rc = wait_for_send_bcredit(sc, batch);
+	if (rc) {
+		log_outgoing(ERR, "disconnected not sending on wait_bcredit\n");
+		rc = -EAGAIN;
+		goto err_wait_bcredit;
+	}
 
 	rc = wait_for_send_lcredit(sc, batch);
 	if (rc) {

@@ -1432,8 +1473,14 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 		     le32_to_cpu(packet->remaining_data_length));
 
 	rc = smbd_post_send(sc, batch, request);
-	if (!rc)
-		return 0;
+	if (!rc) {
+		if (batch != &_batch)
+			return 0;
+
+		rc = smbd_send_batch_flush(sc, batch, true);
+		if (!rc)
+			return 0;
+	}
 
 err_dma:
 	smbd_free_send_io(request);

@@ -1447,6 +1494,11 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 	wake_up(&sc->send_io.lcredits.wait_queue);
 
 err_wait_lcredit:
+	atomic_add(batch->credit, &sc->send_io.bcredits.count);
+	batch->credit = 0;
+	wake_up(&sc->send_io.bcredits.wait_queue);
+
+err_wait_bcredit:
 	return rc;
 }
 

index dbb2d939bc44..20faa6d7f514 100644
@@ -697,6 +697,15 @@ static void smbd_post_send_credits(struct work_struct *work)
 
 	atomic_add(posted, &sc->recv_io.credits.available);
 
+	/*
+	 * If the last send credit is waiting for credits
+	 * it can grant we need to wake it up
+	 */
+	if (posted &&
+	    atomic_read(&sc->send_io.bcredits.count) == 0 &&
+	    atomic_read(&sc->send_io.credits.count) == 0)
+		wake_up(&sc->send_io.credits.wait_queue);
+
 	/* Promptly send an immediate packet as defined in [MS-SMBD] 3.1.1.1 */
 	if (atomic_read(&sc->recv_io.credits.count) <
 		sc->recv_io.credits.target - 1) {

@@ -1394,6 +1403,26 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 		goto err_wait_credit;
 	}
 
+	new_credits = manage_credits_prior_sending(sc);
+	if (new_credits == 0 &&
+	    atomic_read(&sc->send_io.credits.count) == 0 &&
+	    atomic_read(&sc->recv_io.credits.count) == 0) {
+		queue_work(sc->workqueue, &sc->recv_io.posted.refill_work);
+		rc = wait_event_interruptible(sc->send_io.credits.wait_queue,
+					      atomic_read(&sc->send_io.credits.count) >= 1 ||
+					      atomic_read(&sc->recv_io.credits.available) >= 1 ||
+					      sc->status != SMBDIRECT_SOCKET_CONNECTED);
+		if (sc->status != SMBDIRECT_SOCKET_CONNECTED)
+			rc = -ENOTCONN;
+		if (rc < 0) {
+			log_outgoing(ERR, "disconnected not sending on last credit\n");
+			rc = -EAGAIN;
+			goto err_wait_credit;
+		}
+
+		new_credits = manage_credits_prior_sending(sc);
+	}
+
 	request = smbd_alloc_send_io(sc);
 	if (IS_ERR(request)) {
 		rc = PTR_ERR(request);

@@ -1448,8 +1477,6 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc,
 
 	/* Fill in the packet header */
 	packet->credits_requested = cpu_to_le16(sp->send_credit_target);
-
-	new_credits = manage_credits_prior_sending(sc);
 	packet->credits_granted = cpu_to_le16(new_credits);
 
 	packet->flags = 0;

index 20faa6d7f514..88fefb901c27 100644
@@ -35,6 +35,10 @@ static void enqueue_reassembly(
 static struct smbdirect_recv_io *_get_first_reassembly(
 		struct smbdirect_socket *sc);
 
+static int smbd_post_send(struct smbdirect_socket *sc,
+			  struct smbdirect_send_batch *batch,
+			  struct smbdirect_send_io *request);
+
 static int smbd_post_recv(
 		struct smbdirect_socket *sc,
 		struct smbdirect_recv_io *response);

@@ -1021,7 +1025,6 @@ static int smbd_ia_open(
 static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 {
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
-	struct ib_send_wr send_wr;
 	int rc;
 	struct smbdirect_send_io *request;
 	struct smbdirect_negotiate_req *packet;

@@ -1052,33 +1055,12 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc)
 	request->sge[0].length = sizeof(*packet);
 	request->sge[0].lkey = sc->ib.pd->local_dma_lkey;
 
-	ib_dma_sync_single_for_device(
-		sc->ib.dev, request->sge[0].addr,
-		request->sge[0].length, DMA_TO_DEVICE);
-
-	request->cqe.done = send_done;
-
-	send_wr.next = NULL;
-	send_wr.wr_cqe = &request->cqe;
-	send_wr.sg_list = request->sge;
-	send_wr.num_sge = request->num_sge;
-	send_wr.opcode = IB_WR_SEND;
-	send_wr.send_flags = IB_SEND_SIGNALED;
-
-	log_rdma_send(INFO, "sge addr=0x%llx length=%u lkey=0x%x\n",
-		request->sge[0].addr,
-		request->sge[0].length, request->sge[0].lkey);
-
-	atomic_inc(&sc->send_io.pending.count);
-	rc = ib_post_send(sc->ib.qp, &send_wr, NULL);
+	rc = smbd_post_send(sc, NULL, request);
 	if (!rc)
 		return 0;
 
-	/* if we reach here, post send failed */
-	log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
-	atomic_dec(&sc->send_io.pending.count);
-
-	smbd_disconnect_rdma_connection(sc);
+	if (rc == -EAGAIN)
+		rc = -EIO;
 
 dma_mapping_failed:
 	smbd_free_send_io(request);

index 88fefb901c27..01d55bcc6d0f 100644
@@ -554,6 +554,32 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc)
 	log_rdma_send(INFO, "smbdirect_send_io 0x%p completed wc->status=%s\n",
 		request, ib_wc_status_msg(wc->status));
 
+	if (unlikely(!(request->wr.send_flags & IB_SEND_SIGNALED))) {
+		/*
+		 * This happens when smbdirect_send_io is a sibling
+		 * before the final message, it is signaled on
+		 * error anyway, so we need to skip
+		 * smbdirect_connection_free_send_io here,
+		 * otherwise is will destroy the memory
+		 * of the siblings too, which will cause
+		 * use after free problems for the others
+		 * triggered from ib_drain_qp().
+		 */
+		if (wc->status != IB_WC_SUCCESS)
+			goto skip_free;
+
+		/*
+		 * This should not happen!
+		 * But we better just close the
+		 * connection...
+		 */
+		log_rdma_send(ERR,
+			"unexpected send completion wc->status=%s (%d) wc->opcode=%d\n",
+			ib_wc_status_msg(wc->status), wc->status, wc->opcode);
+		smbd_disconnect_rdma_connection(sc);
+		return;
+	}
+
 	/*
 	 * Free possible siblings and then the main send_io
 	 */

@@ -567,6 +593,7 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc)
 	lcredits += 1;
 
 	if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) {
+skip_free:
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
 			log_rdma_send(ERR, "wc->status=%s wc->opcode=%d\n",
 				ib_wc_status_msg(wc->status), wc->opcode);

@@ -166,9 +166,18 @@ void device_set_deferred_probe_reason(co
 static inline int driver_match_device(const struct device_driver *drv,
 				      struct device *dev)
 {
+	device_lock_assert(dev);
+
 	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
 }
 
+static inline int driver_match_device_locked(const struct device_driver *drv,
+					     struct device *dev)
+{
+	guard(device)(dev);
+	return driver_match_device(drv, dev);
+}
+
 static inline void dev_sync_state(struct device *dev)
 {
 	if (dev->bus->sync_state)

@@ -263,7 +263,7 @@ static ssize_t bind_store(struct device_
 	int err = -ENODEV;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
-	if (dev && driver_match_device(drv, dev)) {
+	if (dev && driver_match_device_locked(drv, dev)) {
 		err = device_driver_attach(drv, dev);
 		if (!err) {
 			/* success */

@@ -1170,7 +1170,7 @@ static int __driver_attach(struct device
 	 * is an error.
 	 */
 
-	ret = driver_match_device(drv, dev);
+	ret = driver_match_device_locked(drv, dev);
 	if (ret == 0) {
 		/* no match */
 		return 0;

@@ -527,6 +527,8 @@ static const struct usb_device_id quirks
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x2001, 0x332a), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x7392, 0xe611), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Realtek 8852AE Bluetooth devices */
 	{ USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK |

@@ -1081,6 +1081,7 @@ static const struct hda_quirk cxt5066_fi
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8231, "HP ProBook 450 G4", CXT_FIXUP_MUTE_LED_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x826b, "HP ZBook Studio G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),

@@ -221,15 +221,13 @@ static struct iaa_compression_mode *iaa_
 
 static int find_empty_iaa_compression_mode(void)
 {
-	int i = -EINVAL;
+	int i;
 
-	for (i = 0; i < IAA_COMP_MODES_MAX; i++) {
-		if (iaa_compression_modes[i])
-			continue;
-		break;
-	}
+	for (i = 0; i < IAA_COMP_MODES_MAX; i++)
+		if (!iaa_compression_modes[i])
+			return i;
 
-	return i;
+	return -EINVAL;
 }
 
 static struct iaa_compression_mode *find_iaa_compression_mode(const char *name, int *idx)

@@ -1326,7 +1326,7 @@ static ssize_t ucode_load_store(struct d
 	int del_grp_idx = -1;
 	int ucode_idx = 0;
 
-	if (strlen(buf) > OTX_CPT_UCODE_NAME_LENGTH)
+	if (count >= OTX_CPT_UCODE_NAME_LENGTH)
 		return -EINVAL;
 
 	eng_grps = container_of(attr, struct otx_cpt_eng_grps, ucode_load_attr);

@@ -21,7 +21,7 @@ static int omap_crypto_copy_sg_lists(int
 	struct scatterlist *tmp;
 
 	if (!(flags & OMAP_CRYPTO_FORCE_SINGLE_ENTRY)) {
-		new_sg = kmalloc_array(n, sizeof(*sg), GFP_KERNEL);
+		new_sg = kmalloc_array(n, sizeof(*new_sg), GFP_KERNEL);
 		if (!new_sg)
 			return -ENOMEM;
 

@@ -75,15 +75,20 @@ static void virtcrypto_done_task(unsigne
 	struct data_queue *data_vq = (struct data_queue *)data;
 	struct virtqueue *vq = data_vq->vq;
 	struct virtio_crypto_request *vc_req;
+	unsigned long flags;
 	unsigned int len;
 
+	spin_lock_irqsave(&data_vq->lock, flags);
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) {
+			spin_unlock_irqrestore(&data_vq->lock, flags);
 			if (vc_req->alg_cb)
 				vc_req->alg_cb(vc_req, len);
+			spin_lock_irqsave(&data_vq->lock, flags);
 		}
 	} while (!virtqueue_enable_cb(vq));
+	spin_unlock_irqrestore(&data_vq->lock, flags);
 }
 
 static void virtcrypto_dataq_callback(struct virtqueue *vq)

@@ -541,8 +541,6 @@ int virtio_crypto_skcipher_crypt_req(
 	if (ret < 0)
 		return ret;
 
-	virtqueue_kick(data_vq->vq);
-
 	return 0;
 }
 

@@ -1093,6 +1093,9 @@ int nilfs_sufile_trim_fs(struct inode *s
 	else
 		end_block = start_block + len - 1;
 
+	if (end_block < nilfs->ns_first_data_block)
+		goto out;
+
 	segnum = nilfs_get_segnum_of_block(nilfs, start_block);
 	segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
 

@@ -1191,6 +1194,7 @@ int nilfs_sufile_trim_fs(struct inode *s
 out_sem:
 	up_read(&NILFS_MDT(sufile)->mi_sem);
 
+out:
 	range->len = ndiscarded << nilfs->ns_blocksize_bits;
 	return ret;
 }

@@ -92,7 +92,7 @@ int hfs_mdb_get(struct super_block *sb)
 		/* See if this is an HFS filesystem */
 		bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb);
 		if (!bh)
-			goto out;
+			return -EIO;
 
 		if (mdb->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC))
 			break;

@@ -102,13 +102,14 @@ int hfs_mdb_get(struct super_block *sb)
 		 * (should do this only for cdrom/loop though)
 		 */
 		if (hfs_part_find(sb, &part_start, &part_size))
-			goto out;
+			return -EIO;
 	}
 
 	HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz);
 	if (!size || (size & (HFS_SECTOR_SIZE - 1))) {
 		pr_err("bad allocation block size %d\n", size);
-		goto out_bh;
+		brelse(bh);
+		return -EIO;
 	}
 
 	size = min(HFS_SB(sb)->alloc_blksz, (u32)PAGE_SIZE);

@@ -125,14 +126,16 @@ int hfs_mdb_get(struct super_block *sb)
 	brelse(bh);
 	if (!sb_set_blocksize(sb, size)) {
 		pr_err("unable to set blocksize to %u\n", size);
-		goto out;
+		return -EIO;
 	}
 
 	bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb);
 	if (!bh)
-		goto out;
-	if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC))
-		goto out_bh;
+		return -EIO;
+	if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) {
+		brelse(bh);
+		return -EIO;
+	}
 
 	HFS_SB(sb)->mdb_bh = bh;
 	HFS_SB(sb)->mdb = mdb;

@@ -174,7 +177,7 @@ int hfs_mdb_get(struct super_block *sb)
 
 	HFS_SB(sb)->bitmap = kzalloc(8192, GFP_KERNEL);
 	if (!HFS_SB(sb)->bitmap)
-		goto out;
+		return -EIO;
 
 	/* read in the bitmap */
 	block = be16_to_cpu(mdb->drVBMSt) + part_start;

@@ -185,7 +188,7 @@ int hfs_mdb_get(struct super_block *sb)
 		bh = sb_bread(sb, off >> sb->s_blocksize_bits);
 		if (!bh) {
 			pr_err("unable to read volume bitmap\n");
-			goto out;
+			return -EIO;
 		}
 		off2 = off & (sb->s_blocksize - 1);
 		len = min((int)sb->s_blocksize - off2, size);

@@ -199,12 +202,12 @@ int hfs_mdb_get(struct super_block *sb)
 	HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp);
 	if (!HFS_SB(sb)->ext_tree) {
 		pr_err("unable to open extent tree\n");
-		goto out;
+		return -EIO;
 	}
 	HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp);
 	if (!HFS_SB(sb)->cat_tree) {
 		pr_err("unable to open catalog tree\n");
-		goto out;
+		return -EIO;
 	}
 
 	attrib = mdb->drAtrb;

@@ -229,12 +232,6 @@ int hfs_mdb_get(struct super_block *sb)
 	}
 
 	return 0;
-
-out_bh:
-	brelse(bh);
-out:
-	hfs_mdb_put(sb);
-	return -EIO;
 }
 
 /*

@@ -359,8 +356,6 @@ void hfs_mdb_close(struct super_block *s
  * Release the resources associated with the in-core MDB.  */
 void hfs_mdb_put(struct super_block *sb)
 {
-	if (!HFS_SB(sb))
-		return;
 	/* free the B-trees */
 	hfs_btree_close(HFS_SB(sb)->ext_tree);
 	hfs_btree_close(HFS_SB(sb)->cat_tree);

@@ -373,6 +368,4 @@ void hfs_mdb_put(struct super_block *sb)
 	unload_nls(HFS_SB(sb)->nls_disk);
 
 	kfree(HFS_SB(sb)->bitmap);
-	kfree(HFS_SB(sb));
-	sb->s_fs_info = NULL;
 }

@@ -431,10 +431,18 @@ static int hfs_init_fs_context(struct fs
 	return 0;
 }
 
+static void hfs_kill_super(struct super_block *sb)
+{
+	struct hfs_sb_info *hsb = HFS_SB(sb);
+
+	kill_block_super(sb);
+	kfree(hsb);
+}
+
 static struct file_system_type hfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "hfs",
-	.kill_sb	= kill_block_super,
+	.kill_sb	= hfs_kill_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 	.init_fs_context = hfs_init_fs_context,
 };

@@ -2444,10 +2444,10 @@ void rtw_core_enable_beacon(struct rtw_d
 
 	if (enable) {
 		rtw_write32_set(rtwdev, REG_BCN_CTRL, BIT_EN_BCN_FUNCTION);
-		rtw_write32_clr(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE);
+		rtw_write8_clr(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE);
 	} else {
 		rtw_write32_clr(rtwdev, REG_BCN_CTRL, BIT_EN_BCN_FUNCTION);
-		rtw_write32_set(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE);
+		rtw_write8_set(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE);
 	}
 }
 

@@ -3701,23 +3701,25 @@ int qla_fab_async_scan(scsi_qla_host_t *
 	return rval;
 
 done_free_sp:
-	if (sp->u.iocb_cmd.u.ctarg.req) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-		    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
-		    sp->u.iocb_cmd.u.ctarg.req,
-		    sp->u.iocb_cmd.u.ctarg.req_dma);
-		sp->u.iocb_cmd.u.ctarg.req = NULL;
-	}
-	if (sp->u.iocb_cmd.u.ctarg.rsp) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-		    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
-		    sp->u.iocb_cmd.u.ctarg.rsp,
-		    sp->u.iocb_cmd.u.ctarg.rsp_dma);
-		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
-	}
+	if (sp) {
+		if (sp->u.iocb_cmd.u.ctarg.req) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.req,
+			    sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
+		if (sp->u.iocb_cmd.u.ctarg.rsp) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.rsp,
+			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
 
-	/* ref: INIT */
-	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+		/* ref: INIT */
+		kref_put(&sp->cmd_kref, qla2x00_sp_release);
+	}
 
 	spin_lock_irqsave(&vha->work_lock, flags);
 	vha->scan.scan_flags &= ~SF_SCANNING;

@@ -3266,9 +3266,6 @@ login_logout:
 			    atomic_read(&fcport->state) == FCS_ONLINE) ||
 				do_delete) {
 				if (fcport->loop_id != FC_NO_LOOP_ID) {
-					if (fcport->flags & FCF_FCP2_DEVICE)
-						continue;
-
 					ql_log(ql_log_warn, vha, 0x20f0,
 					       "%s %d %8phC post del sess\n",
 					       __func__, __LINE__,

@@ -1859,15 +1859,6 @@ void qla2x00_handle_rscn(scsi_qla_host_t
 	case RSCN_PORT_ADDR:
 		fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1);
 		if (fcport) {
-			if (ql2xfc2target &&
-			    fcport->flags & FCF_FCP2_DEVICE &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
-				ql_dbg(ql_dbg_disc, vha, 0x2115,
-				       "Delaying session delete for FCP2 portid=%06x %8phC ",
-					fcport->d_id.b24, fcport->port_name);
-				return;
-			}
-
 			if (vha->hw->flags.edif_enabled && DBELL_ACTIVE(vha)) {
 				/*
 				 * On ipsec start by remote port, Target port

@@ -1182,7 +1182,8 @@ qla2x00_wait_for_hba_ready(scsi_qla_host
 	while ((qla2x00_reset_active(vha) || ha->dpc_active ||
 		ha->flags.mbox_busy) ||
 	       test_bit(FX00_RESET_RECOVERY, &vha->dpc_flags) ||
-	       test_bit(FX00_TARGET_SCAN, &vha->dpc_flags)) {
+	       test_bit(FX00_TARGET_SCAN, &vha->dpc_flags) ||
+	       (vha->scan.scan_flags & SF_SCANNING)) {
 		if (test_bit(UNLOADING, &base_vha->dpc_flags))
 			break;
 		msleep(1000);

@@ -3532,8 +3532,8 @@ int qla_fab_async_scan(scsi_qla_host_t *
 	if (vha->scan.scan_flags & SF_SCANNING) {
 		spin_unlock_irqrestore(&vha->work_lock, flags);
 		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2012,
-		    "%s: scan active\n", __func__);
-		return rval;
+		    "%s: scan active for sp:%p\n", __func__, sp);
+		goto done_free_sp;
 	}
 	vha->scan.scan_flags |= SF_SCANNING;
 	if (!sp)

@@ -2462,8 +2462,23 @@ qla24xx_handle_plogi_done_event(struct s
 	    ea->sp->gen1, fcport->rscn_gen,
 	    ea->data[0], ea->data[1], ea->iop[0], ea->iop[1]);
 
-	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
-	    (fcport->fw_login_state == DSC_LS_PRLI_PEND)) {
+	if (fcport->fw_login_state == DSC_LS_PLOGI_PEND) {
+		ql_dbg(ql_dbg_disc, vha, 0x20ea,
+		    "%s %d %8phC Remote is trying to login\n",
+		    __func__, __LINE__, fcport->port_name);
+		/*
+		 * If we get here, there is port thats already logged in,
+		 * but it's state has not moved ahead. Recheck with FW on
+		 * what state it is in and proceed ahead
+		 */
+		if (!N2N_TOPO(vha->hw)) {
+			fcport->fw_login_state = DSC_LS_PRLI_COMP;
+			qla24xx_post_gpdb_work(vha, fcport, 0);
+		}
+		return;
+	}
+
+	if (fcport->fw_login_state == DSC_LS_PRLI_PEND) {
 		ql_dbg(ql_dbg_disc, vha, 0x20ea,
 		    "%s %d %8phC Remote is trying to login\n",
 		    __func__, __LINE__, fcport->port_name);

@@ -1676,13 +1676,28 @@ skip_rio:
 
 			/* Port logout */
 			fcport = qla2x00_find_fcport_by_loopid(vha, mb[1]);
-			if (!fcport)
+			if (!fcport) {
+				ql_dbg(ql_dbg_async, vha, 0x5011,
+					"Could not find fcport:%04x %04x %04x\n",
+					mb[1], mb[2], mb[3]);
 				break;
-			if (atomic_read(&fcport->state) != FCS_ONLINE)
+			}
+
+			if (atomic_read(&fcport->state) != FCS_ONLINE) {
+				ql_dbg(ql_dbg_async, vha, 0x5012,
+					"Port state is not online State:0x%x \n",
+					atomic_read(&fcport->state));
+				ql_dbg(ql_dbg_async, vha, 0x5012,
+					"Scheduling session for deletion \n");
+				fcport->logout_on_delete = 0;
+				qlt_schedule_sess_for_deletion(fcport);
 				break;
+			}
+
 			ql_dbg(ql_dbg_async, vha, 0x508a,
 			    "Marking port lost loopid=%04x portid=%06x.\n",
 			    fcport->loop_id, fcport->d_id.b24);
+
 			if (qla_ini_mode_enabled(vha)) {
 				fcport->logout_on_delete = 0;
 				qlt_schedule_sess_for_deletion(fcport);

@@ -202,8 +202,12 @@ static ssize_t driver_override_show(stru
 				    struct device_attribute *attr, char *buf)
 {
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	ssize_t len;
 
-	return sysfs_emit(buf, "%s\n", mc_dev->driver_override);
+	device_lock(dev);
+	len = sysfs_emit(buf, "%s\n", mc_dev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);