Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask into merge-rr-cpumask

Conflicts:
	arch/x86/kernel/io_apic.c
	kernel/rcuclassic.c
	kernel/sched.c
	kernel/time/tick-sched.c

Signed-off-by: Mike Travis <travis@sgi.com>
[ mingo@elte.hu: backmerged typo fix for io_apic.c ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 126 insertions, 71 deletions

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1e5b6446231..12876392516 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -119,6 +119,14 @@ error:
 	iscsi_conn_failure(conn, rc);
 }
 
+static int iscsi_iser_pdu_alloc(struct iscsi_task *task, uint8_t opcode)
+{
+	struct iscsi_iser_task *iser_task = task->dd_data;
+
+	task->hdr = (struct iscsi_hdr *)&iser_task->desc.iscsi_header;
+	task->hdr_max = sizeof(iser_task->desc.iscsi_header);
+	return 0;
+}
 
 /**
  * iscsi_iser_task_init - Initialize task
@@ -180,25 +188,26 @@ static int
 iscsi_iser_task_xmit_unsol_data(struct iscsi_conn *conn,
 				 struct iscsi_task *task)
 {
-	struct iscsi_data  hdr;
+	struct iscsi_r2t_info *r2t = &task->unsol_r2t;
+	struct iscsi_data hdr;
 	int error = 0;
 
 	/* Send data-out PDUs while there's still unsolicited data to send */
-	while (task->unsol_count > 0) {
-		iscsi_prep_unsolicit_data_pdu(task, &hdr);
+	while (iscsi_task_has_unsol_data(task)) {
+		iscsi_prep_data_out_pdu(task, r2t, &hdr);
 		debug_scsi("Sending data-out: itt 0x%x, data count %d\n",
-			   hdr.itt, task->data_count);
+			   hdr.itt, r2t->data_count);
 
 		/* the buffer description has been passed with the command */
 		/* Send the command */
 		error = iser_send_data_out(conn, task, &hdr);
 		if (error) {
-			task->unsol_datasn--;
+			r2t->datasn--;
 			goto iscsi_iser_task_xmit_unsol_data_exit;
 		}
-		task->unsol_count -= task->data_count;
+		r2t->sent += r2t->data_count;
 		debug_scsi("Need to send %d more as data-out PDUs\n",
-			   task->unsol_count);
+			   r2t->data_length - r2t->sent);
 	}
 
 iscsi_iser_task_xmit_unsol_data_exit:
@@ -220,7 +229,7 @@ iscsi_iser_task_xmit(struct iscsi_task *task)
 
 		debug_scsi("cmd [itt %x total %d imm %d unsol_data %d\n",
 			   task->itt, scsi_bufflen(task->sc),
-			   task->imm_count, task->unsol_count);
+			   task->imm_count, task->unsol_r2t.data_length);
 	}
 
 	debug_scsi("task deq [cid %d itt 0x%x]\n",
@@ -235,7 +244,7 @@ iscsi_iser_task_xmit(struct iscsi_task *task)
 	}
 
 	/* Send unsolicited data-out PDU(s) if necessary */
-	if (task->unsol_count)
+	if (iscsi_task_has_unsol_data(task))
 		error = iscsi_iser_task_xmit_unsol_data(conn, task);
 
  iscsi_iser_task_xmit_exit:
@@ -244,13 +253,15 @@ iscsi_iser_task_xmit(struct iscsi_task *task)
 	return error;
 }
 
-static void
-iscsi_iser_cleanup_task(struct iscsi_conn *conn, struct iscsi_task *task)
+static void iscsi_iser_cleanup_task(struct iscsi_task *task)
 {
 	struct iscsi_iser_task *iser_task = task->dd_data;
 
-	/* mgmt tasks do not need special cleanup */
-	if (!task->sc)
+	/*
+	 * mgmt tasks do not need special cleanup and we do not
+	 * allocate anything in the init task callout
+	 */
+	if (!task->sc || task->state == ISCSI_TASK_PENDING)
 		return;
 
 	if (iser_task->status == ISER_TASK_STATUS_STARTED) {
@@ -391,9 +402,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 	struct iscsi_cls_session *cls_session;
 	struct iscsi_session *session;
 	struct Scsi_Host *shost;
-	int i;
-	struct iscsi_task *task;
-	struct iscsi_iser_task *iser_task;
 	struct iser_conn *ib_conn;
 
 	shost = iscsi_host_alloc(&iscsi_iser_sht, 0, ISCSI_MAX_CMD_PER_LUN);
@@ -430,13 +438,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 	session = cls_session->dd_data;
 
 	shost->can_queue = session->scsi_cmds_max;
-	/* libiscsi setup itts, data and pool so just set desc fields */
-	for (i = 0; i < session->cmds_max; i++) {
-		task = session->cmds[i];
-		iser_task = task->dd_data;
-		task->hdr = (struct iscsi_cmd *)&iser_task->desc.iscsi_header;
-		task->hdr_max = sizeof(iser_task->desc.iscsi_header);
-	}
 	return cls_session;
 
 remove_host:
@@ -652,6 +653,7 @@ static struct iscsi_transport iscsi_iser_transport = {
 	.init_task		= iscsi_iser_task_init,
 	.xmit_task		= iscsi_iser_task_xmit,
 	.cleanup_task		= iscsi_iser_cleanup_task,
+	.alloc_pdu		= iscsi_iser_pdu_alloc,
 	/* recovery */
 	.session_recovery_timedout = iscsi_session_recovery_timedout,
 
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 81a82628a5f..861119593f2 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -252,6 +252,9 @@ struct iser_conn {
 	wait_queue_head_t	     wait;          /* waitq for conn/disconn  */
 	atomic_t                     post_recv_buf_count; /* posted rx count   */
 	atomic_t                     post_send_buf_count; /* posted tx count   */
+	atomic_t                     unexpected_pdu_count;/* count of received *
+							   * unexpected pdus   *
+							   * not yet retired   */
 	char 			     name[ISER_OBJECT_NAME_SIZE];
 	struct iser_page_vec         *page_vec;     /* represents SG to fmr maps*
 						     * maps serialized as tx is*/
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index cdd28318904..e209cb8dd94 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -183,14 +183,8 @@ static int iser_post_receive_control(struct iscsi_conn *conn)
 	struct iser_regd_buf *regd_data;
 	struct iser_dto      *recv_dto = NULL;
 	struct iser_device  *device = iser_conn->ib_conn->device;
-	int rx_data_size, err = 0;
-
-	rx_desc = kmem_cache_alloc(ig.desc_cache, GFP_NOIO);
-	if (rx_desc == NULL) {
-		iser_err("Failed to alloc desc for post recv\n");
-		return -ENOMEM;
-	}
-	rx_desc->type = ISCSI_RX;
+	int rx_data_size, err;
+	int posts, outstanding_unexp_pdus;
 
 	/* for the login sequence we must support rx of upto 8K; login is done
 	 * after conn create/bind (connect) and conn stop/bind (reconnect),
@@ -201,46 +195,80 @@ static int iser_post_receive_control(struct iscsi_conn *conn)
 	else /* FIXME till user space sets conn->max_recv_dlength correctly */
 		rx_data_size = 128;
 
-	rx_desc->data = kmalloc(rx_data_size, GFP_NOIO);
-	if (rx_desc->data == NULL) {
-		iser_err("Failed to alloc data buf for post recv\n");
-		err = -ENOMEM;
-		goto post_rx_kmalloc_failure;
-	}
+	outstanding_unexp_pdus =
+		atomic_xchg(&iser_conn->ib_conn->unexpected_pdu_count, 0);
 
-	recv_dto = &rx_desc->dto;
-	recv_dto->ib_conn = iser_conn->ib_conn;
-	recv_dto->regd_vector_len = 0;
+	/*
+	 * in addition to the response buffer, replace those consumed by
+	 * unexpected pdus.
+	 */
+	for (posts = 0; posts < 1 + outstanding_unexp_pdus; posts++) {
+		rx_desc = kmem_cache_alloc(ig.desc_cache, GFP_NOIO);
+		if (rx_desc == NULL) {
+			iser_err("Failed to alloc desc for post recv %d\n",
+				 posts);
+			err = -ENOMEM;
+			goto post_rx_cache_alloc_failure;
+		}
+		rx_desc->type = ISCSI_RX;
+		rx_desc->data = kmalloc(rx_data_size, GFP_NOIO);
+		if (rx_desc->data == NULL) {
+			iser_err("Failed to alloc data buf for post recv %d\n",
+				 posts);
+			err = -ENOMEM;
+			goto post_rx_kmalloc_failure;
+		}
 
-	regd_hdr = &rx_desc->hdr_regd_buf;
-	memset(regd_hdr, 0, sizeof(struct iser_regd_buf));
-	regd_hdr->device  = device;
-	regd_hdr->virt_addr  = rx_desc; /* == &rx_desc->iser_header */
-	regd_hdr->data_size  = ISER_TOTAL_HEADERS_LEN;
+		recv_dto = &rx_desc->dto;
+		recv_dto->ib_conn = iser_conn->ib_conn;
+		recv_dto->regd_vector_len = 0;
 
-	iser_reg_single(device, regd_hdr, DMA_FROM_DEVICE);
+		regd_hdr = &rx_desc->hdr_regd_buf;
+		memset(regd_hdr, 0, sizeof(struct iser_regd_buf));
+		regd_hdr->device  = device;
+		regd_hdr->virt_addr  = rx_desc; /* == &rx_desc->iser_header */
+		regd_hdr->data_size  = ISER_TOTAL_HEADERS_LEN;
 
-	iser_dto_add_regd_buff(recv_dto, regd_hdr, 0, 0);
+		iser_reg_single(device, regd_hdr, DMA_FROM_DEVICE);
 
-	regd_data = &rx_desc->data_regd_buf;
-	memset(regd_data, 0, sizeof(struct iser_regd_buf));
-	regd_data->device  = device;
-	regd_data->virt_addr  = rx_desc->data;
-	regd_data->data_size  = rx_data_size;
+		iser_dto_add_regd_buff(recv_dto, regd_hdr, 0, 0);
 
-	iser_reg_single(device, regd_data, DMA_FROM_DEVICE);
+		regd_data = &rx_desc->data_regd_buf;
+		memset(regd_data, 0, sizeof(struct iser_regd_buf));
+		regd_data->device  = device;
+		regd_data->virt_addr  = rx_desc->data;
+		regd_data->data_size  = rx_data_size;
 
-	iser_dto_add_regd_buff(recv_dto, regd_data, 0, 0);
+		iser_reg_single(device, regd_data, DMA_FROM_DEVICE);
 
-	err = iser_post_recv(rx_desc);
-	if (!err)
-		return 0;
+		iser_dto_add_regd_buff(recv_dto, regd_data, 0, 0);
+
+		err = iser_post_recv(rx_desc);
+		if (err) {
+			iser_err("Failed iser_post_recv for post %d\n", posts);
+			goto post_rx_post_recv_failure;
+		}
+	}
+	/* all posts successful */
+	return 0;
 
-	/* iser_post_recv failed */
+post_rx_post_recv_failure:
 	iser_dto_buffs_release(recv_dto);
 	kfree(rx_desc->data);
 post_rx_kmalloc_failure:
 	kmem_cache_free(ig.desc_cache, rx_desc);
+post_rx_cache_alloc_failure:
+	if (posts > 0) {
+		/*
+		 * response buffer posted, but did not replace all unexpected
+		 * pdu recv bufs. Ignore error, retry occurs next send
+		 */
+		outstanding_unexp_pdus -= (posts - 1);
+		err = 0;
+	}
+	atomic_add(outstanding_unexp_pdus,
+		   &iser_conn->ib_conn->unexpected_pdu_count);
+
 	return err;
 }
 
@@ -274,8 +302,10 @@ int iser_conn_set_full_featured_mode(struct iscsi_conn *conn)
 	struct iscsi_iser_conn *iser_conn = conn->dd_data;
 
 	int i;
-	/* no need to keep it in a var, we are after login so if this should
-	 * be negotiated, by now the result should be available here */
+	/*
+	 * FIXME this value should be declared to the target during login with
+	 * the MaxOutstandingUnexpectedPDUs key when supported
+	 */
 	int initial_post_recv_bufs_num = ISER_MAX_RX_MISC_PDUS;
 
 	iser_dbg("Initially post: %d\n", initial_post_recv_bufs_num);
@@ -323,8 +353,7 @@ int iser_send_command(struct iscsi_conn *conn,
 	unsigned long edtl;
 	int err = 0;
 	struct iser_data_buf *data_buf;
-
-	struct iscsi_cmd *hdr =  task->hdr;
+	struct iscsi_cmd *hdr =  (struct iscsi_cmd *)task->hdr;
 	struct scsi_cmnd *sc  =  task->sc;
 
 	if (!iser_conn_state_comp(iser_conn->ib_conn, ISER_CONN_UP)) {
@@ -363,7 +392,7 @@ int iser_send_command(struct iscsi_conn *conn,
 		err = iser_prepare_write_cmd(task,
 					     task->imm_count,
 				             task->imm_count +
-					     task->unsol_count,
+					     task->unsol_r2t.data_length,
 					     edtl);
 		if (err)
 			goto send_command_error;
@@ -478,6 +507,7 @@ int iser_send_control(struct iscsi_conn *conn,
 	int err = 0;
 	struct iser_regd_buf *regd_buf;
 	struct iser_device *device;
+	unsigned char opcode;
 
 	if (!iser_conn_state_comp(iser_conn->ib_conn, ISER_CONN_UP)) {
 		iser_err("Failed to send, conn: 0x%p is not up\n", iser_conn->ib_conn);
@@ -512,10 +542,15 @@ int iser_send_control(struct iscsi_conn *conn,
 				       data_seg_len);
 	}
 
-	if (iser_post_receive_control(conn) != 0) {
-		iser_err("post_rcv_buff failed!\n");
-		err = -ENOMEM;
-		goto send_control_error;
+	opcode = task->hdr->opcode & ISCSI_OPCODE_MASK;
+
+	/* post recv buffer for response if one is expected */
+	if (!(opcode == ISCSI_OP_NOOP_OUT && task->hdr->itt == RESERVED_ITT)) {
+		if (iser_post_receive_control(conn) != 0) {
+			iser_err("post_rcv_buff failed!\n");
+			err = -ENOMEM;
+			goto send_control_error;
+		}
 	}
 
 	err = iser_post_send(mdesc);
@@ -586,6 +621,20 @@ void iser_rcv_completion(struct iser_desc *rx_desc,
 	 * parallel to the execution of iser_conn_term. So the code that waits *
 	 * for the posted rx bufs refcount to become zero handles everything   */
 	atomic_dec(&conn->ib_conn->post_recv_buf_count);
+
+	/*
+	 * if an unexpected PDU was received then the recv wr consumed must
+	 * be replaced, this is done in the next send of a control-type PDU
+	 */
+	if (opcode == ISCSI_OP_NOOP_IN && hdr->itt == RESERVED_ITT) {
+		/* nop-in with itt = 0xffffffff */
+		atomic_inc(&conn->ib_conn->unexpected_pdu_count);
+	}
+	else if (opcode == ISCSI_OP_ASYNC_EVENT) {
+		/* asyncronous message */
+		atomic_inc(&conn->ib_conn->unexpected_pdu_count);
+	}
+	/* a reject PDU consumes the recv buf posted for the response */
 }
 
 void iser_snd_completion(struct iser_desc *tx_desc)
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 26ff6214a81..319b188145b 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -498,6 +498,7 @@ void iser_conn_init(struct iser_conn *ib_conn)
 	init_waitqueue_head(&ib_conn->wait);
 	atomic_set(&ib_conn->post_recv_buf_count, 0);
 	atomic_set(&ib_conn->post_send_buf_count, 0);
+	atomic_set(&ib_conn->unexpected_pdu_count, 0);
 	atomic_set(&ib_conn->refcount, 1);
 	INIT_LIST_HEAD(&ib_conn->conn_list);
 	spin_lock_init(&ib_conn->lock);
@@ -515,14 +516,14 @@ int iser_connect(struct iser_conn   *ib_conn,
 	struct sockaddr *src, *dst;
 	int err = 0;
 
-	sprintf(ib_conn->name,"%d.%d.%d.%d:%d",
-		NIPQUAD(dst_addr->sin_addr.s_addr), dst_addr->sin_port);
+	sprintf(ib_conn->name, "%pI4:%d",
+		&dst_addr->sin_addr.s_addr, dst_addr->sin_port);
 
 	/* the device is known only --after-- address resolution */
 	ib_conn->device = NULL;
 
-	iser_err("connecting to: %d.%d.%d.%d, port 0x%x\n",
-		 NIPQUAD(dst_addr->sin_addr), dst_addr->sin_port);
+	iser_err("connecting to: %pI4, port 0x%x\n",
+		 &dst_addr->sin_addr, dst_addr->sin_port);
 
 	ib_conn->state = ISER_CONN_PENDING;