Merge tag 'v7.0-rc-part1-ksmbd-and-smbdirect-fixes' of git://git.samba.org/ksmbd

Pull smb server and smbdirect updates from Steve French:

 - Fix tcp connection leak

 - Fix potential use after free when freeing multichannel

 - Fix locking problem in showing channel list

 - Locking improvement for tree connection

 - Fix infinite loop when signing errors

 - Add /proc interface for monitoring server state

 - Fixes to avoid mixing iWarp and InfiniBand/RoCEv1/RoCEv2
   port ranges used for smbdirect

 - Fixes for smbdirect credit handling problems, these make
   the connections more reliable

* tag 'v7.0-rc-part1-ksmbd-and-smbdirect-fixes' of git://git.samba.org/ksmbd: (32 commits)
  ksmbd: fix non-IPv6 build
  ksmbd: convert tree_conns_lock to rw_semaphore
  ksmbd: fix missing chann_lock while iterating session channel list
  ksmbd: add chann_lock to protect ksmbd_chann_list xarray
  smb: server: correct value for smb_direct_max_fragmented_recv_size
  smb: client: correct value for smbd_max_fragmented_recv_size
  smb: server: fix leak of active_num_conn in ksmbd_tcp_new_connection()
  ksmbd: add procfs interface for runtime monitoring and statistics
  ksmbd: fix infinite loop caused by next_smb2_rcv_hdr_off reset in error paths
  smb: server: make use of rdma_restrict_node_type()
  smb: client: make use of rdma_restrict_node_type()
  RDMA/core: introduce rdma_restrict_node_type()
  smb: client: let send_done handle a completion without IB_SEND_SIGNALED
  smb: client: let smbd_post_send_negotiate_req() use smbd_post_send()
  smb: client: fix last send credit problem causing disconnects
  smb: client: make use of smbdirect_socket.send_io.bcredits
  smb: client: use smbdirect_send_batch processing
  smb: client: introduce and use smbd_{alloc, free}_send_io()
  smb: client: split out smbd_ib_post_send()
  smb: client: port and use the wait_for_credits logic used by server
  ...

1 files changed, 440 insertions, 128 deletions

diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 788a0670c4a8..d44847c9d8fc 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -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);
@@ -97,8 +101,23 @@ int smbd_send_credit_target = 255;
 /* The maximum single message size can be sent to remote peer */
 int smbd_max_send_size = 1364;
 
-/*  The maximum fragmented upper-layer payload receive size supported */
-int smbd_max_fragmented_recv_size = 1024 * 1024;
+/*
+ * The maximum fragmented upper-layer payload receive size supported
+ *
+ * Assume max_payload_per_credit is
+ * smbd_max_receive_size - 24 = 1340
+ *
+ * The maximum number would be
+ * smbd_receive_credit_max * max_payload_per_credit
+ *
+ *                       1340 * 255 = 341700 (0x536C4)
+ *
+ * The minimum value from the spec is 131072 (0x20000)
+ *
+ * For now we use the logic we used in ksmbd before:
+ *                 (1364 * 255) / 2 = 173910 (0x2A756)
+ */
+int smbd_max_fragmented_recv_size = (1364 * 255) / 2;
 
 /*  The maximum single-message size which can be received */
 int smbd_max_receive_size = 1364;
@@ -493,27 +512,103 @@ 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;
+	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));
 
-	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);
+	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
+	 */
+	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;
 
 	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);
@@ -608,6 +703,7 @@ 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;
 }
@@ -618,6 +714,7 @@ static void smbd_post_send_credits(struct work_struct *work)
 	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 +737,21 @@ static void smbd_post_send_credits(struct work_struct *work)
 			}
 
 			atomic_inc(&sc->recv_io.posted.count);
+			posted += 1;
 		}
 	}
 
+	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) {
@@ -659,6 +768,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		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;
@@ -743,7 +853,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		}
 
 		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);
@@ -779,7 +890,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		 * 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);
@@ -810,6 +922,7 @@ static struct rdma_cm_id *smbd_create_id(
 {
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
 	struct rdma_cm_id *id;
+	u8 node_type = RDMA_NODE_UNSPECIFIED;
 	int rc;
 	__be16 *sport;
 
@@ -821,6 +934,31 @@ static struct rdma_cm_id *smbd_create_id(
 		return id;
 	}
 
+	switch (port) {
+	case SMBD_PORT:
+		/*
+		 * only allow iWarp devices
+		 * for port 5445.
+		 */
+		node_type = RDMA_NODE_RNIC;
+		break;
+	case SMB_PORT:
+		/*
+		 * only allow InfiniBand, RoCEv1 or RoCEv2
+		 * devices for port 445.
+		 *
+		 * (Basically don't allow iWarp devices)
+		 */
+		node_type = RDMA_NODE_IB_CA;
+		break;
+	}
+	rc = rdma_restrict_node_type(id, node_type);
+	if (rc) {
+		log_rdma_event(ERR, "rdma_restrict_node_type(%u) failed %i\n",
+			       node_type, rc);
+		goto out;
+	}
+
 	if (dstaddr->sa_family == AF_INET6)
 		sport = &((struct sockaddr_in6 *)dstaddr)->sin6_port;
 	else
@@ -955,16 +1093,13 @@ out1:
 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);
@@ -976,7 +1111,6 @@ 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);
@@ -984,42 +1118,20 @@ 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;
 
-	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);
-	ib_dma_unmap_single(sc->ib.dev, request->sge[0].addr,
-		request->sge[0].length, DMA_TO_DEVICE);
-
-	smbd_disconnect_rdma_connection(sc);
+	if (rc == -EAGAIN)
+		rc = -EIO;
 
 dma_mapping_failed:
-	mempool_free(request, sc->send_io.mem.pool);
+	smbd_free_send_io(request);
 	return rc;
 }
 
@@ -1033,19 +1145,38 @@ 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;
 }
 
@@ -1075,12 +1206,27 @@ static int manage_keep_alive_before_sending(struct smbdirect_socket *sc)
 	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)
+			  struct smbdirect_send_batch *batch,
+			  struct smbdirect_send_io *request)
 {
-	struct ib_send_wr send_wr;
-	int rc, i;
+	int i;
 
 	for (i = 0; i < request->num_sge; i++) {
 		log_rdma_send(INFO,
@@ -1094,79 +1240,245 @@ static int smbd_post_send(struct smbdirect_socket *sc,
 	}
 
 	request->cqe.done = send_done;
+	request->wr.next = NULL;
+	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;
+	}
 
-	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.wr_cqe = &request->cqe;
+	request->wr.send_flags = IB_SEND_SIGNALED;
+	return smbd_ib_post_send(sc, &request->wr);
+}
 
-	rc = ib_post_send(sc->ib.qp, &send_wr, NULL);
-	if (rc) {
-		log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
-		smbd_disconnect_rdma_connection(sc);
-		rc = -EAGAIN;
+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;
+	batch->credit = 0;
+}
+
+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))
+		goto release_credit;
+
+	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;
 	}
 
-	return rc;
+	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);
+	}
+
+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;
+}
+
+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_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)
+{
+	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,
+				 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,
+				1);
 }
 
 static int smbd_post_send_iter(struct smbdirect_socket *sc,
+			       struct smbdirect_send_batch *batch,
 			       struct iov_iter *iter,
 			       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;
 	struct smbdirect_data_transfer *packet;
 	int new_credits = 0;
+	struct smbdirect_send_batch _batch;
 
-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 (!batch) {
+		smbd_send_batch_init(&_batch, false, 0);
+		batch = &_batch;
+	}
 
-	if (sc->status != SMBDIRECT_SOCKET_CONNECTED) {
-		log_outgoing(ERR, "disconnected not sending on wait_credit\n");
+	rc = wait_for_send_bcredit(sc, batch);
+	if (rc) {
+		log_outgoing(ERR, "disconnected not sending on wait_bcredit\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;
+		goto err_wait_bcredit;
 	}
 
-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;
+	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;
+	}
 
-	if (sc->status != SMBDIRECT_SOCKET_CONNECTED) {
+	rc = wait_for_send_credits(sc, batch);
+	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;
+
+	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 = 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 */
@@ -1215,9 +1527,6 @@ wait_credit:
 
 	/* Fill in the packet header */
 	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;
@@ -1240,32 +1549,18 @@ wait_credit:
 		     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;
-
-	if (atomic_dec_and_test(&sc->send_io.pending.count))
-		wake_up(&sc->send_io.pending.zero_wait_queue);
+	rc = smbd_post_send(sc, batch, request);
+	if (!rc) {
+		if (batch != &_batch)
+			return 0;
 
-	wake_up(&sc->send_io.pending.dec_wait_queue);
+		rc = smbd_send_batch_flush(sc, batch, true);
+		if (!rc)
+			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);
-
-	/* roll back the granted receive credits */
-	atomic_sub(new_credits, &sc->recv_io.credits.count);
+	smbd_free_send_io(request);
 
 err_alloc:
 	atomic_inc(&sc->send_io.credits.count);
@@ -1276,6 +1571,11 @@ err_wait_credit:
 	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;
 }
 
@@ -1289,10 +1589,11 @@ 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)
 {
@@ -1305,7 +1606,7 @@ 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;
 	}
@@ -2227,8 +2528,10 @@ 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;
@@ -2253,6 +2556,7 @@ 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];
 
@@ -2271,20 +2575,28 @@ 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.