IB/rdamvt, qib, hfi1: Code cleanups, bug fixes, and perf improvements

index 5ba073e..bbf0a16 100644
@@ -1540,13 +1540,13 @@ void qib_format_hwerrors(u64 hwerrs,
 			 const struct qib_hwerror_msgs *hwerrmsgs,
 			 size_t nhwerrmsgs, char *msg, size_t lmsg);
 
-void stop_send_queue(struct rvt_qp *qp);
-void quiesce_qp(struct rvt_qp *qp);
-void flush_qp_waiters(struct rvt_qp *qp);
-int mtu_to_path_mtu(u32 mtu);
-u32 mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu);
-void notify_error_qp(struct rvt_qp *qp);
-int get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-		       struct ib_qp_attr *attr);
+void qib_stop_send_queue(struct rvt_qp *qp);
+void qib_quiesce_qp(struct rvt_qp *qp);
+void qib_flush_qp_waiters(struct rvt_qp *qp);
+int qib_mtu_to_path_mtu(u32 mtu);
+u32 qib_mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu);
+void qib_notify_error_qp(struct rvt_qp *qp);
+int qib_get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			   struct ib_qp_attr *attr);
 
 #endif                          /* _QIB_KERNEL_H */

index 787116f..01d49dc 100644
@@ -127,8 +127,8 @@ static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map,
  * Allocate the next available QPN or
  * zero/one for QP type IB_QPT_SMI/IB_QPT_GSI.
  */
-int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-	      enum ib_qp_type type, u8 port, gfp_t gfp)
+int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
+		  enum ib_qp_type type, u8 port, gfp_t gfp)
 {
 	u32 i, offset, max_scan, qpn;
 	struct rvt_qpn_map *map;

@@ -232,14 +232,14 @@ unsigned qib_free_all_qps(struct rvt_dev_info *rdi)
 	return qp_inuse;
 }
 
-void notify_qp_reset(struct rvt_qp *qp)
+void qib_notify_qp_reset(struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 
 	atomic_set(&priv->s_dma_busy, 0);
 }
 
-void notify_error_qp(struct rvt_qp *qp)
+void qib_notify_error_qp(struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 	struct qib_ibdev *dev = to_idev(qp->ibqp.device);

@@ -290,8 +290,8 @@ static int mtu_to_enum(u32 mtu)
 	return enum_mtu;
 }
 
-int get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-		       struct ib_qp_attr *attr)
+int qib_get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			   struct ib_qp_attr *attr)
 {
 	int mtu, pmtu, pidx = qp->port_num - 1;
 	struct qib_ibdev *verbs_dev = container_of(rdi, struct qib_ibdev, rdi);

@@ -308,12 +308,12 @@ int get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 	return pmtu;
 }
 
-int mtu_to_path_mtu(u32 mtu)
+int qib_mtu_to_path_mtu(u32 mtu)
 {
 	return mtu_to_enum(mtu);
 }
 
-u32 mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu)
+u32 qib_mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu)
 {
 	return ib_mtu_enum_to_int(pmtu);
 }

@@ -378,7 +378,7 @@ __be32 qib_compute_aeth(struct rvt_qp *qp)
 	return cpu_to_be32(aeth);
 }
 
-void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp)
+void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp)
 {
 	struct qib_qp_priv *priv;
 

@@ -399,7 +399,7 @@ void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp)
 	return priv;
 }
 
-void qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp)
+void qib_qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 

@@ -407,7 +407,7 @@ void qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp)
 	kfree(priv);
 }
 
-void stop_send_queue(struct rvt_qp *qp)
+void qib_stop_send_queue(struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 

@@ -415,7 +415,7 @@ void stop_send_queue(struct rvt_qp *qp)
 	del_timer_sync(&qp->s_timer);
 }
 
-void quiesce_qp(struct rvt_qp *qp)
+void qib_quiesce_qp(struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 

@@ -426,7 +426,7 @@ void quiesce_qp(struct rvt_qp *qp)
 	}
 }
 
-void flush_qp_waiters(struct rvt_qp *qp)
+void qib_flush_qp_waiters(struct rvt_qp *qp)
 {
 	struct qib_qp_priv *priv = qp->priv;
 	struct qib_ibdev *dev = to_idev(qp->ibqp.device);

index 2abe31d..fa94f78 100644
@@ -1394,7 +1394,7 @@ bail:
 	return ret;
 }
 
-static int shut_down_port(struct rvt_dev_info *rdi, u8 port_num)
+static int qib_shut_down_port(struct rvt_dev_info *rdi, u8 port_num)
 {
 	struct qib_ibdev *ibdev = container_of(rdi, struct qib_ibdev, rdi);
 	struct qib_devdata *dd = dd_from_dev(ibdev);

@@ -1663,22 +1663,22 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.get_pci_dev = qib_get_pci_dev;
 	dd->verbs_dev.rdi.driver_f.check_ah = qib_check_ah;
 	dd->verbs_dev.rdi.driver_f.notify_new_ah = qib_notify_new_ah;
-	dd->verbs_dev.rdi.driver_f.alloc_qpn = alloc_qpn;
-	dd->verbs_dev.rdi.driver_f.qp_priv_alloc = qp_priv_alloc;
-	dd->verbs_dev.rdi.driver_f.qp_priv_free = qp_priv_free;
+	dd->verbs_dev.rdi.driver_f.alloc_qpn = qib_alloc_qpn;
+	dd->verbs_dev.rdi.driver_f.qp_priv_alloc = qib_qp_priv_alloc;
+	dd->verbs_dev.rdi.driver_f.qp_priv_free = qib_qp_priv_free;
 	dd->verbs_dev.rdi.driver_f.free_all_qps = qib_free_all_qps;
-	dd->verbs_dev.rdi.driver_f.notify_qp_reset = notify_qp_reset;
+	dd->verbs_dev.rdi.driver_f.notify_qp_reset = qib_notify_qp_reset;
 	dd->verbs_dev.rdi.driver_f.do_send = qib_do_send;
 	dd->verbs_dev.rdi.driver_f.schedule_send = qib_schedule_send;
-	dd->verbs_dev.rdi.driver_f.quiesce_qp = quiesce_qp;
-	dd->verbs_dev.rdi.driver_f.stop_send_queue = stop_send_queue;
-	dd->verbs_dev.rdi.driver_f.flush_qp_waiters = flush_qp_waiters;
-	dd->verbs_dev.rdi.driver_f.notify_error_qp = notify_error_qp;
-	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = mtu_to_path_mtu;
-	dd->verbs_dev.rdi.driver_f.mtu_from_qp = mtu_from_qp;
-	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = get_pmtu_from_attr;
+	dd->verbs_dev.rdi.driver_f.quiesce_qp = qib_quiesce_qp;
+	dd->verbs_dev.rdi.driver_f.stop_send_queue = qib_stop_send_queue;
+	dd->verbs_dev.rdi.driver_f.flush_qp_waiters = qib_flush_qp_waiters;
+	dd->verbs_dev.rdi.driver_f.notify_error_qp = qib_notify_error_qp;
+	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = qib_mtu_to_path_mtu;
+	dd->verbs_dev.rdi.driver_f.mtu_from_qp = qib_mtu_from_qp;
+	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = qib_get_pmtu_from_attr;
 	dd->verbs_dev.rdi.driver_f.query_port_state = qib_query_port;
-	dd->verbs_dev.rdi.driver_f.shut_down_port = shut_down_port;
+	dd->verbs_dev.rdi.driver_f.shut_down_port = qib_shut_down_port;
 	dd->verbs_dev.rdi.driver_f.cap_mask_chg = qib_cap_mask_chg;
 
 	dd->verbs_dev.rdi.dparms.max_rdma_atomic = QIB_MAX_RDMA_ATOMIC;

index cd73a97..b88e027 100644
@@ -350,11 +350,11 @@ __be32 qib_compute_aeth(struct rvt_qp *qp);
  * Functions provided by qib driver for rdmavt to use
  */
 unsigned qib_free_all_qps(struct rvt_dev_info *rdi);
-void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp);
-void qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp);
-void notify_qp_reset(struct rvt_qp *qp);
-int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
-	      enum ib_qp_type type, u8 port, gfp_t gfp);
+void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp);
+void qib_qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp);
+void qib_notify_qp_reset(struct rvt_qp *qp);
+int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
+		  enum ib_qp_type type, u8 port, gfp_t gfp);
 
 #ifdef CONFIG_DEBUG_FS
 

index 01d49dc..6ffa022 100644
@@ -474,6 +474,42 @@ void qib_get_credit(struct rvt_qp *qp, u32 aeth)
 	}
 }
 
+/**
+ * qib_check_send_wqe - validate wr/wqe
+ * @qp - The qp
+ * @wqe - The built wqe
+ *
+ * validate wr/wqe.  This is called
+ * prior to inserting the wqe into
+ * the ring but after the wqe has been
+ * setup.
+ *
+ * Returns 0 on success, -EINVAL on failure
+ */
+int qib_check_send_wqe(struct rvt_qp *qp,
+		       struct rvt_swqe *wqe)
+{
+	struct rvt_ah *ah;
+
+	switch (qp->ibqp.qp_type) {
+	case IB_QPT_RC:
+	case IB_QPT_UC:
+		if (wqe->length > 0x80000000U)
+			return -EINVAL;
+		break;
+	case IB_QPT_SMI:
+	case IB_QPT_GSI:
+	case IB_QPT_UD:
+		ah = ibah_to_rvtah(wqe->ud_wr.ah);
+		if (wqe->length > (1 << ah->log_pmtu))
+			return -EINVAL;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 #ifdef CONFIG_DEBUG_FS
 
 struct qib_qp_iter {

134 lines not on this page · raw message

index 2623684..a5f07a6 100644
@@ -391,7 +391,8 @@ static void qib_ruc_loopback(struct rvt_qp *sqp)
 	sqp->s_flags |= RVT_S_BUSY;
 
 again:
-	if (sqp->s_last == sqp->s_head)
+	smp_read_barrier_depends(); /* see post_one_send() */
+	if (sqp->s_last == ACCESS_ONCE(sqp->s_head))
 		goto clr_busy;
 	wqe = rvt_get_swqe_ptr(sqp, sqp->s_last);
 

@@ -765,22 +766,24 @@ void qib_do_send(struct rvt_qp *qp)
 
 	qp->s_flags |= RVT_S_BUSY;
 
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-
 	do {
 		/* Check for a constructed packet to be sent. */
 		if (qp->s_hdrwords != 0) {
+			spin_unlock_irqrestore(&qp->s_lock, flags);
 			/*
 			 * If the packet cannot be sent now, return and
 			 * the send tasklet will be woken up later.
 			 */
 			if (qib_verbs_send(qp, priv->s_hdr, qp->s_hdrwords,
 					   qp->s_cur_sge, qp->s_cur_size))
-				break;
+				return;
 			/* Record that s_hdr is empty. */
 			qp->s_hdrwords = 0;
+			spin_lock_irqsave(&qp->s_lock, flags);
 		}
 	} while (make_req(qp));
+
+	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 
 /*

index 1b2fc69..7bdbc79 100644
@@ -41,6 +41,8 @@
  * qib_make_uc_req - construct a request packet (SEND, RDMA write)
  * @qp: a pointer to the QP
  *
+ * Assumes the s_lock is held.
+ *
  * Return 1 if constructed; otherwise, return 0.
  */
 int qib_make_uc_req(struct rvt_qp *qp)

@@ -48,20 +50,18 @@ int qib_make_uc_req(struct rvt_qp *qp)
 	struct qib_qp_priv *priv = qp->priv;
 	struct qib_other_headers *ohdr;
 	struct rvt_swqe *wqe;
-	unsigned long flags;
 	u32 hwords;
 	u32 bth0;
 	u32 len;
 	u32 pmtu = qp->pmtu;
 	int ret = 0;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
-
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
 		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
 			goto bail;
 		/* We are in the error state, flush the work request. */
-		if (qp->s_last == qp->s_head)
+		smp_read_barrier_depends(); /* see post_one_send() */
+		if (qp->s_last == ACCESS_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_dma_busy)) {

@@ -90,13 +90,13 @@ int qib_make_uc_req(struct rvt_qp *qp)
 		    RVT_PROCESS_NEXT_SEND_OK))
 			goto bail;
 		/* Check if send work queue is empty. */
-		if (qp->s_cur == qp->s_head)
+		smp_read_barrier_depends(); /* see post_one_send() */
+		if (qp->s_cur == ACCESS_ONCE(qp->s_head))
 			goto bail;
 		/*
 		 * Start a new request.
 		 */
-		wqe->psn = qp->s_next_psn;
-		qp->s_psn = qp->s_next_psn;
+		qp->s_psn = wqe->psn;
 		qp->s_sge.sge = wqe->sg_list[0];
 		qp->s_sge.sg_list = wqe->sg_list + 1;
 		qp->s_sge.num_sge = wqe->wr.num_sge;

@@ -215,15 +215,11 @@ int qib_make_uc_req(struct rvt_qp *qp)
 	qp->s_cur_sge = &qp->s_sge;
 	qp->s_cur_size = len;
 	qib_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
-			    qp->s_next_psn++ & QIB_PSN_MASK);
+			    qp->s_psn++ & QIB_PSN_MASK);
 done:
-	ret = 1;
-	goto unlock;
-
+	return 1;
 bail:
 	qp->s_flags &= ~RVT_S_BUSY;
-unlock:
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return ret;
 }
 

index fe49172..d950213 100644
@@ -234,6 +234,8 @@ drop:
  * qib_make_ud_req - construct a UD request packet
  * @qp: the QP
  *
+ * Assumes the s_lock is held.
+ *
  * Return 1 if constructed; otherwise, return 0.
  */
 int qib_make_ud_req(struct rvt_qp *qp)

@@ -244,7 +246,6 @@ int qib_make_ud_req(struct rvt_qp *qp)
 	struct qib_pportdata *ppd;
 	struct qib_ibport *ibp;
 	struct rvt_swqe *wqe;
-	unsigned long flags;
 	u32 nwords;
 	u32 extra_bytes;
 	u32 bth0;

@@ -253,13 +254,12 @@ int qib_make_ud_req(struct rvt_qp *qp)
 	int ret = 0;
 	int next_cur;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
-
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
 		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
 			goto bail;
 		/* We are in the error state, flush the work request. */
-		if (qp->s_last == qp->s_head)
+		smp_read_barrier_depends(); /* see post_one_send */
+		if (qp->s_last == ACCESS_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_dma_busy)) {

@@ -271,7 +271,9 @@ int qib_make_ud_req(struct rvt_qp *qp)
 		goto done;
 	}
 
-	if (qp->s_cur == qp->s_head)
+	/* see post_one_send() */
+	smp_read_barrier_depends();
+	if (qp->s_cur == ACCESS_ONCE(qp->s_head))
 		goto bail;
 
 	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);

@@ -292,6 +294,7 @@ int qib_make_ud_req(struct rvt_qp *qp)
 		this_cpu_inc(ibp->pmastats->n_unicast_xmit);
 		lid = ah_attr->dlid & ~((1 << ppd->lmc) - 1);
 		if (unlikely(lid == ppd->lid)) {
+			unsigned long flags;
 			/*
 			 * If DMAs are in progress, we can't generate
 			 * a completion for the loopback packet since

@@ -304,6 +307,7 @@ int qib_make_ud_req(struct rvt_qp *qp)
 				goto bail;
 			}
 			qp->s_cur = next_cur;
+			local_irq_save(flags);
 			spin_unlock_irqrestore(&qp->s_lock, flags);
 			qib_ud_loopback(qp, wqe);
 			spin_lock_irqsave(&qp->s_lock, flags);

@@ -378,7 +382,7 @@ int qib_make_ud_req(struct rvt_qp *qp)
 		ah_attr->dlid != be16_to_cpu(IB_LID_PERMISSIVE) ?
 		cpu_to_be32(QIB_MULTICAST_QPN) :
 		cpu_to_be32(wqe->ud_wr.remote_qpn);
-	ohdr->bth[2] = cpu_to_be32(qp->s_next_psn++ & QIB_PSN_MASK);
+	ohdr->bth[2] = cpu_to_be32(wqe->psn & QIB_PSN_MASK);
 	/*
 	 * Qkeys with the high order bit set mean use the
 	 * qkey from the QP context instead of the WR (see 10.2.5).

@@ -388,13 +392,9 @@ int qib_make_ud_req(struct rvt_qp *qp)
 	ohdr->u.ud.deth[1] = cpu_to_be32(qp->ibqp.qp_num);
 
 done:
-	ret = 1;
-	goto unlock;
-
+	return 1;
 bail:
 	qp->s_flags &= ~RVT_S_BUSY;
-unlock:
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return ret;
 }
 

index fa94f78..5cf019f 100644
@@ -1662,6 +1662,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.get_card_name = qib_get_card_name;
 	dd->verbs_dev.rdi.driver_f.get_pci_dev = qib_get_pci_dev;
 	dd->verbs_dev.rdi.driver_f.check_ah = qib_check_ah;
+	dd->verbs_dev.rdi.driver_f.check_send_wqe = qib_check_send_wqe;
 	dd->verbs_dev.rdi.driver_f.notify_new_ah = qib_notify_new_ah;
 	dd->verbs_dev.rdi.driver_f.alloc_qpn = qib_alloc_qpn;
 	dd->verbs_dev.rdi.driver_f.qp_priv_alloc = qib_qp_priv_alloc;

@@ -1677,6 +1678,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = qib_mtu_to_path_mtu;
 	dd->verbs_dev.rdi.driver_f.mtu_from_qp = qib_mtu_from_qp;
 	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = qib_get_pmtu_from_attr;
+	dd->verbs_dev.rdi.driver_f.schedule_send_no_lock = _qib_schedule_send;
 	dd->verbs_dev.rdi.driver_f.query_port_state = qib_query_port;
 	dd->verbs_dev.rdi.driver_f.shut_down_port = qib_shut_down_port;
 	dd->verbs_dev.rdi.driver_f.cap_mask_chg = qib_cap_mask_chg;

@@ -1778,17 +1780,34 @@ void qib_unregister_ib_device(struct qib_devdata *dd)
 				  dev->pio_hdrs, dev->pio_hdrs_phys);
 }
 
-/*
- * This must be called with s_lock held.
+/**
+ * _qib_schedule_send - schedule progress
+ * @qp - the qp
+ *
+ * This schedules progress w/o regard to the s_flags.
+ *
+ * It is only used in post send, which doesn't hold
+ * the s_lock.
  */
-void qib_schedule_send(struct rvt_qp *qp)
+void _qib_schedule_send(struct rvt_qp *qp)
 {
+	struct qib_ibport *ibp =
+		to_iport(qp->ibqp.device, qp->port_num);
+	struct qib_pportdata *ppd = ppd_from_ibp(ibp);
 	struct qib_qp_priv *priv = qp->priv;
-	if (qib_send_ok(qp)) {
-		struct qib_ibport *ibp =
-			to_iport(qp->ibqp.device, qp->port_num);
-		struct qib_pportdata *ppd = ppd_from_ibp(ibp);
 
-		queue_work(ppd->qib_wq, &priv->s_work);
-	}
+	queue_work(ppd->qib_wq, &priv->s_work);
+}
+
+/**
+ * qib_schedule_send - schedule progress
+ * @qp - the qp
+ *
+ * This schedules qp progress.  The s_lock
+ * should be held.
+ */
+void qib_schedule_send(struct rvt_qp *qp)
+{
+	if (qib_send_ok(qp))
+		_qib_schedule_send(qp);
 }

index b88e027..d137d71 100644
@@ -298,9 +298,7 @@ static inline int qib_send_ok(struct rvt_qp *qp)
 		 !(qp->s_flags & RVT_S_ANY_WAIT_SEND));
 }
 
-/*
- * This must be called with s_lock held.
- */
+void _qib_schedule_send(struct rvt_qp *qp);
 void qib_schedule_send(struct rvt_qp *qp);
 
 static inline int qib_pkey_ok(u16 pkey1, u16 pkey2)

@@ -392,6 +390,8 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct qib_ib_header *hdr,
 
 int qib_check_ah(struct ib_device *ibdev, struct ib_ah_attr *ah_attr);
 
+int qib_check_send_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe);
+
 struct ib_ah *qib_create_qp0_ah(struct qib_ibport *ibp, u16 dlid);
 
 void qib_rc_rnr_retry(unsigned long arg);

227 lines not on this page · raw message

94 lines not on this page · raw message

index 973c14b..98827b5 100644
@@ -137,41 +137,8 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter);
  */
 void qp_comm_est(struct rvt_qp *qp);
 
-/**
- * _hfi1_schedule_send - schedule progress
- * @qp: the QP
- *
- * This schedules qp progress w/o regard to the s_flags.
- *
- * It is only used in the post send, which doesn't hold
- * the s_lock.
- */
-static inline void _hfi1_schedule_send(struct rvt_qp *qp)
-{
-	struct hfi1_qp_priv *priv = qp->priv;
-	struct hfi1_ibport *ibp =
-		to_iport(qp->ibqp.device, qp->port_num);
-	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
-
-	iowait_schedule(&priv->s_iowait, ppd->hfi1_wq,
-			priv->s_sde ?
-			priv->s_sde->cpu :
-			cpumask_first(cpumask_of_node(dd->node)));
-}
-
-/**
- * hfi1_schedule_send - schedule progress
- * @qp: the QP
- *
- * This schedules qp progress and caller should hold
- * the s_lock.
- */
-static inline void hfi1_schedule_send(struct rvt_qp *qp)
-{
-	if (hfi1_send_ok(qp))
-		_hfi1_schedule_send(qp);
-}
+void _hfi1_schedule_send(struct rvt_qp *qp);
+void hfi1_schedule_send(struct rvt_qp *qp);
 
 void hfi1_migrate_qp(struct rvt_qp *qp);
 

134 lines not on this page · raw message

index a7add3c..6114550 100644
@@ -392,7 +392,8 @@ static void ruc_loopback(struct rvt_qp *sqp)
 	sqp->s_flags |= RVT_S_BUSY;
 
 again:
-	if (sqp->s_last == sqp->s_head)
+	smp_read_barrier_depends(); /* see post_one_send() */
+	if (sqp->s_last == ACCESS_ONCE(sqp->s_head))
 		goto clr_busy;
 	wqe = rvt_get_swqe_ptr(sqp, sqp->s_last);
 

@@ -871,40 +872,43 @@ void hfi1_do_send(struct rvt_qp *qp)
 
 	qp->s_flags |= RVT_S_BUSY;
 
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-
 	timeout = jiffies + (timeout_int) / 8;
 	cpu = priv->s_sde ? priv->s_sde->cpu :
 			cpumask_first(cpumask_of_node(ps.ppd->dd->node));
 	do {
 		/* Check for a constructed packet to be sent. */
 		if (qp->s_hdrwords != 0) {
+			spin_unlock_irqrestore(&qp->s_lock, flags);
 			/*
 			 * If the packet cannot be sent now, return and
 			 * the send tasklet will be woken up later.
 			 */
 			if (hfi1_verbs_send(qp, &ps))
-				break;
+				return;
 			/* Record that s_hdr is empty. */
 			qp->s_hdrwords = 0;
-		}
-
-		/* allow other tasks to run */
-		if (unlikely(time_after(jiffies, timeout))) {
-			if (workqueue_congested(cpu, ps.ppd->hfi1_wq)) {
-				spin_lock_irqsave(&qp->s_lock, flags);
-				qp->s_flags &= ~RVT_S_BUSY;
-				hfi1_schedule_send(qp);
-				spin_unlock_irqrestore(&qp->s_lock,
-						       flags);
+			/* allow other tasks to run */
+			if (unlikely(time_after(jiffies, timeout))) {
+				if (workqueue_congested(cpu,
+							ps.ppd->hfi1_wq)) {
+					spin_lock_irqsave(&qp->s_lock, flags);
+					qp->s_flags &= ~RVT_S_BUSY;
+					hfi1_schedule_send(qp);
+					spin_unlock_irqrestore(&qp->s_lock,
+							       flags);
+					this_cpu_inc(
+						*ps.ppd->dd->send_schedule);
+					return;
+				}
+				cond_resched();
 				this_cpu_inc(*ps.ppd->dd->send_schedule);
-				return;
+				timeout = jiffies + (timeout_int) / 8;
 			}
-			cond_resched();
-			this_cpu_inc(*ps.ppd->dd->send_schedule);
-			timeout = jiffies + (timeout_int) / 8;
+			spin_lock_irqsave(&qp->s_lock, flags);
 		}
 	} while (make_req(qp));
+
+	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 
 /*

index 0aa604b..f884b5c 100644
@@ -59,6 +59,8 @@
  * hfi1_make_uc_req - construct a request packet (SEND, RDMA write)
  * @qp: a pointer to the QP
  *
+ * Assume s_lock is held.
+ *
  * Return 1 if constructed; otherwise, return 0.
  */
 int hfi1_make_uc_req(struct rvt_qp *qp)

@@ -66,7 +68,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp)
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_other_headers *ohdr;
 	struct rvt_swqe *wqe;
-	unsigned long flags;
 	u32 hwords = 5;
 	u32 bth0 = 0;
 	u32 len;

@@ -74,13 +75,12 @@ int hfi1_make_uc_req(struct rvt_qp *qp)
 	int ret = 0;
 	int middle = 0;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
-
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
 		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
 			goto bail;
 		/* We are in the error state, flush the work request. */
-		if (qp->s_last == qp->s_head)
+		smp_read_barrier_depends(); /* see post_one_send() */
+		if (qp->s_last == ACCESS_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_iowait.sdma_busy)) {

@@ -106,15 +106,15 @@ int hfi1_make_uc_req(struct rvt_qp *qp)
 		    RVT_PROCESS_NEXT_SEND_OK))
 			goto bail;
 		/* Check if send work queue is empty. */
-		if (qp->s_cur == qp->s_head) {
+		smp_read_barrier_depends(); /* see post_one_send() */
+		if (qp->s_cur == ACCESS_ONCE(qp->s_head)) {
 			clear_ahg(qp);
 			goto bail;
 		}
 		/*
 		 * Start a new request.
 		 */
-		wqe->psn = qp->s_next_psn;
-		qp->s_psn = qp->s_next_psn;
+		qp->s_psn = wqe->psn;
 		qp->s_sge.sge = wqe->sg_list[0];
 		qp->s_sge.sg_list = wqe->sg_list + 1;
 		qp->s_sge.num_sge = wqe->wr.num_sge;

@@ -235,15 +235,12 @@ int hfi1_make_uc_req(struct rvt_qp *qp)
 	qp->s_cur_sge = &qp->s_sge;
 	qp->s_cur_size = len;
 	hfi1_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24),
-			     mask_psn(qp->s_next_psn++), middle);
+			     mask_psn(qp->s_psn++), middle);
 done:
-	ret = 1;
-	goto unlock;
+	return 1;
 
 bail:
 	qp->s_flags &= ~RVT_S_BUSY;
-unlock:
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return ret;
 }
 

index fdf6e3b..ba78e2e 100644
@@ -261,6 +261,8 @@ drop:
  * hfi1_make_ud_req - construct a UD request packet
  * @qp: the QP
  *
+ * Assume s_lock is held.
+ *
  * Return 1 if constructed; otherwise, return 0.
  */
 int hfi1_make_ud_req(struct rvt_qp *qp)

@@ -271,7 +273,6 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 	struct hfi1_pportdata *ppd;
 	struct hfi1_ibport *ibp;
 	struct rvt_swqe *wqe;
-	unsigned long flags;
 	u32 nwords;
 	u32 extra_bytes;
 	u32 bth0;

@@ -281,13 +282,12 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 	int next_cur;
 	u8 sc5;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
-
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
 		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
 			goto bail;
 		/* We are in the error state, flush the work request. */
-		if (qp->s_last == qp->s_head)
+		smp_read_barrier_depends(); /* see post_one_send */
+		if (qp->s_last == ACCESS_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_iowait.sdma_busy)) {

@@ -299,7 +299,9 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 		goto done;
 	}
 
-	if (qp->s_cur == qp->s_head)
+	/* see post_one_send() */
+	smp_read_barrier_depends();
+	if (qp->s_cur == ACCESS_ONCE(qp->s_head))
 		goto bail;
 
 	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);

@@ -317,6 +319,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 		if (unlikely(!loopback && (lid == ppd->lid ||
 		    (lid == be16_to_cpu(IB_LID_PERMISSIVE) &&
 		     qp->ibqp.qp_type == IB_QPT_GSI)))) {
+			unsigned long flags;
 			/*
 			 * If DMAs are in progress, we can't generate
 			 * a completion for the loopback packet since

@@ -329,6 +332,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 				goto bail;
 			}
 			qp->s_cur = next_cur;
+			local_irq_save(flags);
 			spin_unlock_irqrestore(&qp->s_lock, flags);
 			ud_loopback(qp, wqe);
 			spin_lock_irqsave(&qp->s_lock, flags);

@@ -408,7 +412,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 		bth0 |= hfi1_get_pkey(ibp, qp->s_pkey_index);
 	ohdr->bth[0] = cpu_to_be32(bth0);
 	ohdr->bth[1] = cpu_to_be32(wqe->ud_wr.remote_qpn);
-	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->s_next_psn++));
+	ohdr->bth[2] = cpu_to_be32(mask_psn(wqe->psn));
 	/*
 	 * Qkeys with the high order bit set mean use the
 	 * qkey from the QP context instead of the WR (see 10.2.5).

@@ -423,13 +427,9 @@ int hfi1_make_ud_req(struct rvt_qp *qp)
 	priv->s_hdr->sde = NULL;
 
 done:
-	ret = 1;
-	goto unlock;
-
+	return 1;
 bail:
 	qp->s_flags &= ~RVT_S_BUSY;
-unlock:
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return ret;
 }
 

index 35f6d92..1df4648 100644
@@ -1533,6 +1533,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.notify_qp_reset = notify_qp_reset;
 	dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send;
 	dd->verbs_dev.rdi.driver_f.schedule_send = hfi1_schedule_send;
+	dd->verbs_dev.rdi.driver_f.schedule_send_no_lock = _hfi1_schedule_send;
 	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = get_pmtu_from_attr;
 	dd->verbs_dev.rdi.driver_f.notify_error_qp = notify_error_qp;
 	dd->verbs_dev.rdi.driver_f.flush_qp_waiters = flush_qp_waiters;

@@ -1543,7 +1544,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = mtu_to_path_mtu;
 	dd->verbs_dev.rdi.driver_f.check_modify_qp = hfi1_check_modify_qp;
 	dd->verbs_dev.rdi.driver_f.modify_qp = hfi1_modify_qp;
-	dd->verbs_dev.rdi.driver_f.check_send_wr = hfi1_check_send_wr;
+	dd->verbs_dev.rdi.driver_f.check_send_wqe = hfi1_check_send_wqe;
 
 	/* completeion queue */
 	snprintf(dd->verbs_dev.rdi.dparms.cq_name,

index adb63bb..d00c55d 100644
@@ -427,7 +427,7 @@ int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		    int attr_mask, struct ib_udata *udata);
 
-int hfi1_check_send_wr(struct rvt_qp *qp, struct ib_send_wr *wr);
+int hfi1_check_send_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe);
 
 int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_ib_header *hdr,
 		       int has_grh, struct rvt_qp *qp, u32 bth0);

index 5ccf683..aabd2e5 100644
@@ -220,6 +220,7 @@ struct rvt_ah {
 };
 
 struct rvt_dev_info;
+struct rvt_swqe;
 struct rvt_driver_provided {
 	/*
 	 * The work to create port files in /sys/class Infiniband is different

@@ -240,6 +241,7 @@ struct rvt_driver_provided {
 	void (*qp_priv_free)(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 	void (*notify_qp_reset)(struct rvt_qp *qp);
 	void (*schedule_send)(struct rvt_qp *qp);
+	void (*schedule_send_no_lock)(struct rvt_qp *qp);
 	void (*do_send)(struct rvt_qp *qp);
 	int (*get_pmtu_from_attr)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 				  struct ib_qp_attr *attr);

@@ -273,7 +275,7 @@ struct rvt_driver_provided {
 	void (*modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
 			  int attr_mask, struct ib_udata *udata);
 
-	int (*check_send_wr)(struct rvt_qp *qp, struct ib_send_wr *wr);
+	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
 
 	void (*notify_create_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
 	void (*notify_free_mad_agent)(struct rvt_dev_info *rdi, int port_idx);

index b3ea745..1066b5d 100644
@@ -250,11 +250,12 @@ struct rvt_qp {
 	enum ib_mtu path_mtu;
 	int srate_mbps;		/* s_srate (below) converted to Mbit/s */
 	u32 remote_qpn;
-	u32 pmtu;		/* decoded from path_mtu */
 	u32 qkey;               /* QKEY for this QP (for UD or RD) */
 	u32 s_size;             /* send work queue size */
 	u32 s_ahgpsn;           /* set to the psn in the copy of the header */
 
+	u16 pmtu;		/* decoded from path_mtu */
+	u8 log_pmtu;		/* shift for pmtu */
 	u8 state;               /* QP state */
 	u8 allowed_ops;		/* high order bits of allowed opcodes */
 	u8 qp_access_flags;

@@ -299,6 +300,13 @@ struct rvt_qp {
 	struct rvt_sge_state r_sge;     /* current receive data */
 	struct rvt_rq r_rq;             /* receive work queue */
 
+	/* post send line */
+	spinlock_t s_hlock ____cacheline_aligned_in_smp;
+	u32 s_head;             /* new entries added here */
+	u32 s_next_psn;         /* PSN for next request */
+	u32 s_avail;            /* number of entries avail */
+	u32 s_ssn;              /* SSN of tail entry */
+
 	spinlock_t s_lock ____cacheline_aligned_in_smp;
 	struct rvt_sge_state *s_cur_sge;
 	u32 s_flags;

@@ -308,19 +316,16 @@ struct rvt_qp {
 	u32 s_cur_size;         /* size of send packet in bytes */
 	u32 s_len;              /* total length of s_sge */
 	u32 s_rdma_read_len;    /* total length of s_rdma_read_sge */
-	u32 s_next_psn;         /* PSN for next request */
 	u32 s_last_psn;         /* last response PSN processed */
 	u32 s_sending_psn;      /* lowest PSN that is being sent */
 	u32 s_sending_hpsn;     /* highest PSN that is being sent */
 	u32 s_psn;              /* current packet sequence number */
 	u32 s_ack_rdma_psn;     /* PSN for sending RDMA read responses */
 	u32 s_ack_psn;          /* PSN for acking sends and RDMA writes */
-	u32 s_head;             /* new entries added here */
 	u32 s_tail;             /* next entry to process */
 	u32 s_cur;              /* current work queue entry */
 	u32 s_acked;            /* last un-ACK'ed entry */
 	u32 s_last;             /* last completed entry */
-	u32 s_ssn;              /* SSN of tail entry */
 	u32 s_lsn;              /* limit sequence number (credit) */
 	u16 s_hdrwords;         /* size of s_hdr in 32 bit words */
 	u16 s_rdma_ack_cnt;

index 522404a..d629911 100644
@@ -1441,7 +1441,12 @@ static int rvt_post_one_wr(struct rvt_qp *qp, struct ib_send_wr *wr)
 	/* check for avail */
 	if (unlikely(!qp->s_avail)) {
 		qp->s_avail = qp_get_savail(qp);
-		WARN_ON(qp->s_avail > (qp->s_size - 1));
+		if (WARN_ON(qp->s_avail > (qp->s_size - 1)))
+			rvt_pr_err(rdi,
+				   "More avail entries than QP RB size.\nQP: %u, size: %u, avail: %u\nhead: %u, tail: %u, cur: %u, acked: %u, last: %u",
+				   qp->ibqp.qp_num, qp->s_size, qp->s_avail,
+				   qp->s_head, qp->s_tail, qp->s_cur,
+				   qp->s_acked, qp->s_last);
 		if (!qp->s_avail)
 			return -ENOMEM;
 	}

@@ -1510,6 +1515,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp, struct ib_send_wr *wr)
 	wqe->lpsn = wqe->psn +
 			(wqe->length ? ((wqe->length - 1) >> log_pmtu) : 0);
 	qp->s_next_psn = wqe->lpsn + 1;
+	trace_rvt_post_one_wr(qp, wqe);
 	smp_wmb(); /* see request builders */
 	qp->s_avail--;
 	qp->s_head = next;

82 lines not on this page · raw message

index 2fcc9f3..d9efe22 100644
@@ -55,6 +55,7 @@
 #include "hfi.h"
 #include "mad.h"
 #include "trace.h"
+#include "qp.h"
 
 /* the reset value from the FM is supposed to be 0xffff, handle both */
 #define OPA_LINK_WIDTH_RESET_OLD 0x0fff

@@ -1517,14 +1518,22 @@ static int __subn_set_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	u8 *p = data;
 	int i;
+	u8 sc;
 
 	if (am) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	for (i = 0; i <  ARRAY_SIZE(ibp->sl_to_sc); i++)
-		ibp->sl_to_sc[i] = *p++;
+	for (i = 0; i <  ARRAY_SIZE(ibp->sl_to_sc); i++) {
+		sc = *p++;
+		if (ibp->sl_to_sc[i] != sc) {
+			ibp->sl_to_sc[i] = sc;
+
+			/* Put all stale qps into error state */
+			hfi1_error_port_qps(ibp, i);
+		}
+	}
 
 	return __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, resp_len);
 }

55 lines not on this page · raw message

index 98827b5..afc2b4d 100644
@@ -158,4 +158,5 @@ void stop_send_queue(struct rvt_qp *qp);
 void quiesce_qp(struct rvt_qp *qp);
 u32 mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu);
 int mtu_to_path_mtu(u32 mtu);
+void hfi1_error_port_qps(struct hfi1_ibport *ibp, u8 sl);
 #endif /* _QP_H */

index 9372c43..16c4461 100644
@@ -53,6 +53,11 @@
  * rvt_check_ah - validate the attributes of AH
  * @ibdev: the ib device
  * @ah_attr: the attributes of the AH
+ *
+ * If driver supports a more detailed check_ah function call back to it
+ * otherwise just check the basics.
+ *
+ * Return: 0 on success
  */
 int rvt_check_ah(struct ib_device *ibdev,
 		 struct ib_ah_attr *ah_attr)

@@ -95,6 +100,8 @@ EXPORT_SYMBOL(rvt_check_ah);
  * @ah_attr: the attributes of the AH
  *
  * This may be called from interrupt context.
+ *
+ * Return: newly allocated ah
  */
 struct ib_ah *rvt_create_ah(struct ib_pd *pd,
 			    struct ib_ah_attr *ah_attr)

@@ -129,6 +136,12 @@ struct ib_ah *rvt_create_ah(struct ib_pd *pd,
 	return &ah->ibah;
 }
 
+/**
+ * rvt_destory_ah - Destory an address handle
+ * @ibah: address handle
+ *
+ * Return: 0 on success
+ */
 int rvt_destroy_ah(struct ib_ah *ibah)
 {
 	struct rvt_dev_info *dev = ib_to_rvt(ibah->device);

@@ -147,6 +160,13 @@ int rvt_destroy_ah(struct ib_ah *ibah)
 	return 0;
 }
 
+/**
+ * rvt_modify_ah - modify an ah with given attrs
+ * @ibah: address handle to modify
+ * @ah_attr: attrs to apply
+ *
+ * Return: 0 on success
+ */
 int rvt_modify_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
 {
 	struct rvt_ah *ah = ibah_to_rvtah(ibah);

@@ -159,6 +179,13 @@ int rvt_modify_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
 	return 0;
 }
 
+/**
+ * rvt_query_ah - return attrs for ah
+ * @ibah: address handle to query
+ * @ah_attr: return info in this
+ *
+ * Return: always 0
+ */
 int rvt_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
 {
 	struct rvt_ah *ah = ibah_to_rvtah(ibah);

index 0e6dbe5..c69c070 100644
@@ -173,10 +173,10 @@ static void send_complete(struct kthread_work *work)
  * @context: unused by the QLogic_IB driver
  * @udata: user data for libibverbs.so
  *
- * Returns a pointer to the completion queue or negative errno values
- * for failure.
- *
  * Called by ib_create_cq() in the generic verbs code.
+ *
+ * Return: pointer to the completion queue or negative errno values
+ * for failure.
  */
 struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
 			    const struct ib_cq_init_attr *attr,

@@ -286,9 +286,9 @@ done:
  * rvt_destroy_cq - destroy a completion queue
  * @ibcq: the completion queue to destroy.
  *
- * Returns 0 for success.
- *
  * Called by ib_destroy_cq() in the generic verbs code.
+ *
+ * Return: always 0
  */
 int rvt_destroy_cq(struct ib_cq *ibcq)
 {

@@ -313,10 +313,10 @@ int rvt_destroy_cq(struct ib_cq *ibcq)
  * @ibcq: the completion queue
  * @notify_flags: the type of notification to request
  *
- * Returns 0 for success.
- *
  * This may be called from interrupt context.  Also called by
  * ib_req_notify_cq() in the generic verbs code.
+ *
+ * Return: 0 for success.
  */
 int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags)
 {

@@ -345,7 +345,7 @@ int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags)
  * rvt_resize_cq - change the size of the CQ
  * @ibcq: the completion queue
  *
- * Returns 0 for success.
+ * Return: 0 for success.
  */
 int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 {

@@ -456,10 +456,10 @@ bail_free:
  * @num_entries: the maximum number of entries to return
  * @entry: pointer to array where work completions are placed
  *
- * Returns the number of completion entries polled.
- *
  * This may be called from interrupt context.  Also called by ib_poll_cq()
  * in the generic verbs code.
+ *
+ * Return: the number of completion entries polled.
  */
 int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 {

@@ -496,6 +496,12 @@ int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 	return npolled;
 }
 
+/**
+ * rvt_driver_cq_init - Init cq resources on behalf of driver
+ * @rdi: rvt dev structure
+ *
+ * Return: 0 on success
+ */
 int rvt_driver_cq_init(struct rvt_dev_info *rdi)
 {
 	int ret = 0;

@@ -530,6 +536,10 @@ int rvt_driver_cq_init(struct rvt_dev_info *rdi)
 	return ret;
 }
 
+/**
+ * rvt_cq_exit - tear down cq reources
+ * @rdi: rvt dev structure
+ */
 void rvt_cq_exit(struct rvt_dev_info *rdi)
 {
 	struct kthread_worker *worker;

index 2feae47..f6e9977 100644
@@ -59,14 +59,13 @@
  * @in_mad: the incoming MAD
  * @out_mad: any outgoing MAD reply
  *
- * Returns IB_MAD_RESULT_SUCCESS if this is a MAD that we are not
- * interested in processing.
- *
  * Note that the verbs framework has already done the MAD sanity checks,
  * and hop count/pointer updating for IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE
  * MADs.
  *
  * This is called by the ib_mad module.
+ *
+ * Return: IB_MAD_RESULT_SUCCESS or error
  */
 int rvt_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,

@@ -75,13 +74,10 @@ int rvt_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		    u16 *out_mad_pkey_index)
 {
 	/*
-	 * Drivers will need to provide a number of things. For exmaple counters
-	 * will need to be maintained by the driver but shoud live in the rvt
-	 * structure. More study will be needed to finalize the interface
-	 * between drivers and rvt for mad packets.
-	 *
-	 *VT-DRIVER-API: ????
-	 *
+	 * MAD processing is quite different between hfi1 and qib. Therfore this
+	 * is expected to be provided by the driver. Other drivers in the future
+	 * may chose to implement this but it should not be made into a
+	 * requirement.
 	 */
 	if (ibport_num_to_idx(ibdev, port_num) < 0)
 		return -EINVAL;

@@ -95,6 +91,14 @@ static void rvt_send_mad_handler(struct ib_mad_agent *agent,
 	ib_free_send_mad(mad_send_wc->send_buf);
 }
 
+/**
+ * rvt_create_mad_agents - create mad agents
+ * @rdi: rvt dev struct
+ *
+ * If driver needs to be notified of mad agent creation then call back
+ *
+ * Return 0 on success
+ */
 int rvt_create_mad_agents(struct rvt_dev_info *rdi)
 {
 	struct ib_mad_agent *agent;

@@ -136,6 +140,12 @@ err:
 	return ret;
 }
 
+/**
+ * rvt_free_mad_agents - free up mad agents
+ * @rdi: rvt dev struct
+ *
+ * If driver needs notification of mad agent removal make the call back
+ */
 void rvt_free_mad_agents(struct rvt_dev_info *rdi)
 {
 	struct ib_mad_agent *agent;

index e06a875..983d319 100644
@@ -53,6 +53,12 @@
 
 #include "mcast.h"
 
+/**
+ * rvt_driver_mcast - init resources for multicast
+ * @rdi: rvt dev struct
+ *
+ * This is per device that registers with rdmavt
+ */
 void rvt_driver_mcast_init(struct rvt_dev_info *rdi)
 {
 	/*

@@ -130,9 +136,9 @@ static void rvt_mcast_free(struct rvt_mcast *mcast)
  * @ibp: the IB port structure
  * @mgid: the multicast GID to search for
  *
- * Returns NULL if not found.
- *
  * The caller is responsible for decrementing the reference count if found.
+ *
+ * Return: NULL if not found.
  */
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid)
 {

@@ -170,7 +176,7 @@ EXPORT_SYMBOL(rvt_mcast_find);
  * @mcast: the mcast GID table
  * @mqp: the QP to attach
  *
- * Return zero if both were added.  Return EEXIST if the GID was already in
+ * Return: zero if both were added.  Return EEXIST if the GID was already in
  * the table but the QP was added.  Return ESRCH if the QP was already
  * attached and neither structure was added.
  */

@@ -247,6 +253,14 @@ bail:
 	return ret;
 }
 
+/**
+ * rvt_attach_mcast - attach a qp to a multicast group
+ * @ibqp: Infiniband qp
+ * @igd: multicast guid
+ * @lid: multicast lid
+ *
+ * Return: 0 on success
+ */
 int rvt_attach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	struct rvt_qp *qp = ibqp_to_rvtqp(ibqp);

@@ -298,6 +312,14 @@ bail_mcast:
 	return ret;
 }
 
+/**
+ * rvt_detach_mcast - remove a qp from a multicast group
+ * @ibqp: Infiniband qp
+ * @igd: multicast guid
+ * @lid: multicast lid
+ *
+ * Return: 0 on success
+ */
 int rvt_detach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	struct rvt_qp *qp = ibqp_to_rvtqp(ibqp);

@@ -377,6 +399,12 @@ int rvt_detach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	return 0;
 }
 
+/**
+ *rvt_mast_tree_empty - determine if any qps are attached to any mcast group
+ *@rdi: rvt dev struct
+ *
+ * Return: in use count
+ */
 int rvt_mcast_tree_empty(struct rvt_dev_info *rdi)
 {
 	int i;

index 49180c4..273974f 100644
@@ -51,6 +51,10 @@
 #include <asm/pgtable.h>
 #include "mmap.h"
 
+/**
+ * rvt_mmap_init - init link list and lock for mem map
+ * @rdi: rvt dev struct
+ */
 void rvt_mmap_init(struct rvt_dev_info *rdi)
 {
 	INIT_LIST_HEAD(&rdi->pending_mmaps);

@@ -78,10 +82,6 @@ void rvt_release_mmap_info(struct kref *ref)
 }
 EXPORT_SYMBOL(rvt_release_mmap_info);
 
-/*
- * open and close keep track of how many times the CQ is mapped,
- * to avoid releasing it.
- */
 static void rvt_vma_open(struct vm_area_struct *vma)
 {
 	struct rvt_mmap_info *ip = vma->vm_private_data;

@@ -105,7 +105,8 @@ static const struct vm_operations_struct rvt_vm_ops = {
  * rvt_mmap - create a new mmap region
  * @context: the IB user context of the process making the mmap() call
  * @vma: the VMA to be initialized
- * Return zero if the mmap is OK. Otherwise, return an errno.
+ *
+ * Return: zero if the mmap is OK. Otherwise, return an errno.
  */
 int rvt_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 {

@@ -147,8 +148,14 @@ done:
 }
 EXPORT_SYMBOL(rvt_mmap);
 
-/*
- * Allocate information for hfi1_mmap
+/**
+ * rvt_create_mmap_info - allocate information for hfi1_mmap
+ * @rdi: rvt dev struct
+ * @size: size in bytes to map
+ * @context: user context
+ * @obj: opaque pointer to a cq, wq etc
+ *
+ * Return: rvt_mmap struct on success
  */
 struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
 					   u32 size,

@@ -180,6 +187,13 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
 }
 EXPORT_SYMBOL(rvt_create_mmap_info);
 
+/**
+ * rvt_update_mmap_info - update a mem map
+ * @rdi: rvt dev struct
+ * @ip: mmap info pointer
+ * @size: size to grow by
+ * @obj: opaque pointer to cq, wq, etc.
+ */
 void rvt_update_mmap_info(struct rvt_dev_info *rdi, struct rvt_mmap_info *ip,
 			  u32 size, void *obj)
 {

index 8bff6bb..8549652 100644
@@ -52,8 +52,13 @@
 #include "vt.h"
 #include "mr.h"
 
-/*
+/**
+ * rvt_driver_mr_init - Init MR resources per driver
+ * @rdi: rvt dev struct
+ *
  * Do any intilization needed when a driver registers with rdmavt.
+ *
+ * Return: 0 on success or errno on failure
  */
 int rvt_driver_mr_init(struct rvt_dev_info *rdi)
 {

@@ -98,7 +103,10 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi)
 	return 0;
 }
 
-/*
+/**
+ *rvt_mr_exit: clean up MR
+ *@rdi: rvt dev structure
+ *
  * called when drivers have unregistered or perhaps failed to register with us
  */
 void rvt_mr_exit(struct rvt_dev_info *rdi)

@@ -297,7 +305,7 @@ static void __rvt_free_mr(struct rvt_mr *mr)
  * @pd: protection domain for this memory region
  * @acc: access flags
  *
- * Returns the memory region on success, otherwise returns an errno.
+ * Return: the memory region on success, otherwise returns an errno.
  * Note that all DMA addresses should be created via the
  * struct ib_dma_mapping_ops functions (see dma.c).
  */

@@ -348,7 +356,7 @@ bail:
  * @mr_access_flags: access flags for this memory region
  * @udata: unused by the driver
  *
- * Returns the memory region on success, otherwise returns an errno.
+ * Return: the memory region on success, otherwise returns an errno.
  */
 struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			      u64 virt_addr, int mr_access_flags,

@@ -418,10 +426,11 @@ bail_umem:
  * rvt_dereg_mr - unregister and free a memory region
  * @ibmr: the memory region to free
  *
- * Returns 0 on success.
  *
  * Note that this is called to free MRs created by rvt_get_dma_mr()
  * or rvt_reg_user_mr().
+ *
+ * Returns 0 on success.
  */
 int rvt_dereg_mr(struct ib_mr *ibmr)
 {

@@ -456,7 +465,7 @@ out:
  * @mr_type: mem region type
  * @max_num_sg: Max number of segments allowed
  *
- * Return the memory region on success, otherwise return an errno.
+ * Return: the memory region on success, otherwise return an errno.
  */
 struct ib_mr *rvt_alloc_mr(struct ib_pd *pd,
 			   enum ib_mr_type mr_type,

@@ -480,7 +489,7 @@ struct ib_mr *rvt_alloc_mr(struct ib_pd *pd,
  * @mr_access_flags: access flags for this memory region
  * @fmr_attr: fast memory region attributes
  *
- * Returns the memory region on success, otherwise returns an errno.
+ * Return: the memory region on success, otherwise returns an errno.
  */
 struct ib_fmr *rvt_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
 			     struct ib_fmr_attr *fmr_attr)

@@ -537,6 +546,8 @@ bail:
  * @iova: the virtual address of the start of the fast memory region
  *
  * This may be called from interrupt context.
+ *
+ * Return: 0 on success
  */
 
 int rvt_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,

@@ -580,7 +591,7 @@ int rvt_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
  * rvt_unmap_fmr - unmap fast memory regions
  * @fmr_list: the list of fast memory regions to unmap
  *
- * Returns 0 on success.
+ * Return: 0 on success.
  */
 int rvt_unmap_fmr(struct list_head *fmr_list)
 {

@@ -605,7 +616,7 @@ int rvt_unmap_fmr(struct list_head *fmr_list)
  * rvt_dealloc_fmr - deallocate a fast memory region
  * @ibfmr: the fast memory region to deallocate
  *
- * Returns 0 on success.
+ * Return: 0 on success.
  */
 int rvt_dealloc_fmr(struct ib_fmr *ibfmr)
 {

@@ -635,12 +646,13 @@ out:
  * @sge: SGE to check
  * @acc: access flags
  *
- * Return 1 if valid and successful, otherwise returns 0.
+ * Check the IB SGE for validity and initialize our internal version
+ * of it.
+ *
+ * Return: 1 if valid and successful, otherwise returns 0.
  *
  * increments the reference count upon success
  *
- * Check the IB SGE for validity and initialize our internal version
- * of it.
  */
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 		struct rvt_sge *isge, struct ib_sge *sge, int acc)

@@ -733,7 +745,7 @@ EXPORT_SYMBOL(rvt_lkey_ok);
  * @rkey: rkey to check
  * @acc: access flags
  *
- * Return 1 if successful, otherwise 0.
+ * Return: 1 if successful, otherwise 0.
  *
  * increments the reference count upon success
  */

index 62fee44..d1292f3 100644
@@ -48,6 +48,16 @@
 #include <linux/slab.h>
 #include "pd.h"
 
+/**
+ * rvt_alloc_pd - allocate a protection domain
+ * @ibdev: ib device
+ * @context: optional user context
+ * @udata: optional user data
+ *
+ * Allocate and keep track of a PD.
+ *
+ * Return: 0 on success
+ */
 struct ib_pd *rvt_alloc_pd(struct ib_device *ibdev,
 			   struct ib_ucontext *context,
 			   struct ib_udata *udata)

@@ -88,6 +98,12 @@ bail:
 	return ret;
 }
 
+/**
+ * rvt_dealloc_pd - Free PD
+ * @ibpd: Free up PD
+ *
+ * Return: always 0
+ */
 int rvt_dealloc_pd(struct ib_pd *ibpd)
 {
 	struct rvt_pd *pd = ibpd_to_rvtpd(ibpd);

143 lines not on this page · raw message

index 4960a89..98c4927 100644
@@ -51,7 +51,10 @@
 
 #include "srq.h"
 
-/*
+/**
+ * rvt_driver_srq_init - init srq resources on a per driver basis
+ * @rdi: rvt dev structure
+ *
  * Do any initialization needed when a driver registers with rdmavt.
  */
 void rvt_driver_srq_init(struct rvt_dev_info *rdi)

@@ -65,6 +68,8 @@ void rvt_driver_srq_init(struct rvt_dev_info *rdi)
  * @ibpd: the protection domain of the SRQ to create
  * @srq_init_attr: the attributes of the SRQ
  * @udata: data from libibverbs when creating a user SRQ
+ *
+ * Return: Allocated srq object
  */
 struct ib_srq *rvt_create_srq(struct ib_pd *ibpd,
 			      struct ib_srq_init_attr *srq_init_attr,

@@ -168,6 +173,8 @@ bail_srq:
  * @attr: the new attributes of the SRQ
  * @attr_mask: indicates which attributes to modify
  * @udata: user data for libibverbs.so
+ *
+ * Return: 0 on success
  */
 int rvt_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		   enum ib_srq_attr_mask attr_mask,

@@ -305,6 +312,12 @@ bail_free:
 	return ret;
 }
 
+/** rvt_query_srq - query srq data
+ * @ibsrq: srq to query
+ * @attr: return info in attr
+ *
+ * Return: always 0
+ */
 int rvt_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
 {
 	struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);

@@ -315,6 +328,12 @@ int rvt_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
 	return 0;
 }
 
+/**
+ * rvt_destroy_srq - destory an srq
+ * @ibsrq: srq object to destroy
+ *
+ * Return always 0
+ */
 int rvt_destroy_srq(struct ib_srq *ibsrq)
 {
 	struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);

129 lines not on this page · raw message

index aabd2e5..57c708d 100644
@@ -146,21 +146,6 @@ struct rvt_ibport {
  * Things that are driver specific, module parameters in hfi1 and qib
  */
 struct rvt_driver_params {
-	/*
-	 * driver required fields:
-	 *	node_guid
-	 *	phys_port_cnt
-	 *	dma_device
-	 *	owner
-	 * driver optional fields (rvt will provide generic value if blank):
-	 *	name
-	 *	node_desc
-	 * rvt fields, driver value ignored:
-	 *	uverbs_abi_ver
-	 *	node_type
-	 *	num_comp_vectors
-	 *	uverbs_cmd_mask
-	 */
 	struct ib_device_attr props;
 
 	/*

index f5cb09b..9566a92 100644
@@ -325,12 +325,375 @@ static int rvt_get_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-/*
- * Check driver override. If driver passes a value use it, otherwise we use our
- * own value.
- */
-#define CHECK_DRIVER_OVERRIDE(rdi, x) \
-	rdi->ibdev.x = rdi->ibdev.x ? : rvt_ ##x
+enum {
+	MISC,
+	QUERY_DEVICE,
+	MODIFY_DEVICE,
+	QUERY_PORT,
+	MODIFY_PORT,
+	QUERY_PKEY,
+	QUERY_GID,
+	ALLOC_UCONTEXT,
+	DEALLOC_UCONTEXT,
+	GET_PORT_IMMUTABLE,
+	CREATE_QP,
+	MODIFY_QP,
+	DESTROY_QP,
+	QUERY_QP,
+	POST_SEND,
+	POST_RECV,
+	POST_SRQ_RECV,
+	CREATE_AH,
+	DESTROY_AH,
+	MODIFY_AH,
+	QUERY_AH,
+	CREATE_SRQ,
+	MODIFY_SRQ,
+	DESTROY_SRQ,
+	QUERY_SRQ,
+	ATTACH_MCAST,
+	DETACH_MCAST,
+	GET_DMA_MR,
+	REG_USER_MR,
+	DEREG_MR,
+	ALLOC_MR,
+	ALLOC_FMR,
+	MAP_PHYS_FMR,
+	UNMAP_FMR,
+	DEALLOC_FMR,
+	MMAP,
+	CREATE_CQ,
+	DESTROY_CQ,
+	POLL_CQ,
+	REQ_NOTFIY_CQ,
+	RESIZE_CQ,
+	ALLOC_PD,
+	DEALLOC_PD,
+	_VERB_IDX_MAX /* Must always be last! */
+};
+
+static inline int check_driver_override(struct rvt_dev_info *rdi,
+					size_t offset, void *func)
+{
+	if (!*(void **)((void *)&rdi->ibdev + offset)) {
+		*(void **)((void *)&rdi->ibdev + offset) = func;
+		return 0;
+	}
+
+	return 1;
+}
+
+static int check_support(struct rvt_dev_info *rdi, int verb)
+{
+	switch (verb) {
+	case MISC:
+		/*
+		 * These functions are not part of verbs specifically but are
+		 * required for rdmavt to function.
+		 */
+		if ((!rdi->driver_f.port_callback) ||
+		    (!rdi->driver_f.get_card_name) ||
+		    (!rdi->driver_f.get_pci_dev))
+			return -EINVAL;
+		break;
+
+	case QUERY_DEVICE:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    query_device),
+						    rvt_query_device);
+		break;
+
+	case MODIFY_DEVICE:
+		/*
+		 * rdmavt does not support modify device currently drivers must
+		 * provide.
+		 */
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 modify_device),
+					   rvt_modify_device))
+			return -EOPNOTSUPP;
+		break;
+
+	case QUERY_PORT:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 query_port),
+					   rvt_query_port))
+			if (!rdi->driver_f.query_port_state)
+				return -EINVAL;
+		break;
+
+	case MODIFY_PORT:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 modify_port),
+					   rvt_modify_port))
+			if (!rdi->driver_f.cap_mask_chg ||
+			    !rdi->driver_f.shut_down_port)
+				return -EINVAL;
+		break;
+
+	case QUERY_PKEY:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    query_pkey),
+				      rvt_query_pkey);
+		break;
+
+	case QUERY_GID:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 query_gid),
+					   rvt_query_gid))
+			if (!rdi->driver_f.get_guid_be)
+				return -EINVAL;
+		break;
+
+	case ALLOC_UCONTEXT:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    alloc_ucontext),
+				      rvt_alloc_ucontext);
+		break;
+
+	case DEALLOC_UCONTEXT:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    dealloc_ucontext),
+				      rvt_dealloc_ucontext);
+		break;
+
+	case GET_PORT_IMMUTABLE:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    get_port_immutable),
+				      rvt_get_port_immutable);
+		break;
+
+	case CREATE_QP:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 create_qp),
+					   rvt_create_qp))
+			if (!rdi->driver_f.qp_priv_alloc ||
+			    !rdi->driver_f.qp_priv_free ||
+			    !rdi->driver_f.notify_qp_reset ||
+			    !rdi->driver_f.flush_qp_waiters ||
+			    !rdi->driver_f.stop_send_queue ||
+			    !rdi->driver_f.quiesce_qp)
+				return -EINVAL;
+		break;
+
+	case MODIFY_QP:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 modify_qp),
+					   rvt_modify_qp))
+			if (!rdi->driver_f.notify_qp_reset ||
+			    !rdi->driver_f.schedule_send ||
+			    !rdi->driver_f.get_pmtu_from_attr ||
+			    !rdi->driver_f.flush_qp_waiters ||
+			    !rdi->driver_f.stop_send_queue ||
+			    !rdi->driver_f.quiesce_qp ||
+			    !rdi->driver_f.notify_error_qp ||
+			    !rdi->driver_f.mtu_from_qp ||
+			    !rdi->driver_f.mtu_to_path_mtu ||
+			    !rdi->driver_f.shut_down_port ||
+			    !rdi->driver_f.cap_mask_chg)
+				return -EINVAL;
+		break;
+
+	case DESTROY_QP:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 destroy_qp),
+					   rvt_destroy_qp))
+			if (!rdi->driver_f.qp_priv_free ||
+			    !rdi->driver_f.notify_qp_reset ||
+			    !rdi->driver_f.flush_qp_waiters ||
+			    !rdi->driver_f.stop_send_queue ||
+			    !rdi->driver_f.quiesce_qp)
+				return -EINVAL;
+		break;
+
+	case QUERY_QP:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    query_qp),
+						    rvt_query_qp);
+		break;
+
+	case POST_SEND:
+		if (!check_driver_override(rdi, offsetof(struct ib_device,
+							 post_send),
+					   rvt_post_send))
+			if (!rdi->driver_f.schedule_send ||
+			    !rdi->driver_f.do_send)
+				return -EINVAL;
+		break;
+
+	case POST_RECV:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    post_recv),
+				      rvt_post_recv);
+		break;
+	case POST_SRQ_RECV:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    post_srq_recv),
+				      rvt_post_srq_recv);
+		break;
+
+	case CREATE_AH:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    create_ah),
+				      rvt_create_ah);
+		break;
+
+	case DESTROY_AH:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    destroy_ah),
+				      rvt_destroy_ah);
+		break;
+
+	case MODIFY_AH:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    modify_ah),
+				      rvt_modify_ah);
+		break;
+
+	case QUERY_AH:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    query_ah),
+				      rvt_query_ah);
+		break;
+
+	case CREATE_SRQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    create_srq),
+				      rvt_create_srq);
+		break;
+
+	case MODIFY_SRQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    modify_srq),
+				      rvt_modify_srq);
+		break;
+
+	case DESTROY_SRQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    destroy_srq),
+				      rvt_destroy_srq);
+		break;
+
+	case QUERY_SRQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    query_srq),
+				      rvt_query_srq);
+		break;
+
+	case ATTACH_MCAST:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    attach_mcast),
+				      rvt_attach_mcast);
+		break;
+
+	case DETACH_MCAST:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    detach_mcast),
+				      rvt_detach_mcast);
+		break;
+
+	case GET_DMA_MR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    get_dma_mr),
+				      rvt_get_dma_mr);
+		break;
+
+	case REG_USER_MR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    reg_user_mr),
+				      rvt_reg_user_mr);
+		break;
+
+	case DEREG_MR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    dereg_mr),
+				      rvt_dereg_mr);
+		break;
+
+	case ALLOC_FMR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    alloc_fmr),
+				      rvt_alloc_fmr);
+		break;
+
+	case ALLOC_MR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    alloc_mr),
+				      rvt_alloc_mr);
+		break;
+
+	case MAP_PHYS_FMR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    map_phys_fmr),
+				      rvt_map_phys_fmr);
+		break;
+
+	case UNMAP_FMR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    unmap_fmr),
+				      rvt_unmap_fmr);
+		break;
+
+	case DEALLOC_FMR:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    dealloc_fmr),
+				      rvt_dealloc_fmr);
+		break;
+
+	case MMAP:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    mmap),
+				      rvt_mmap);
+		break;
+
+	case CREATE_CQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    create_cq),
+				      rvt_create_cq);
+		break;
+
+	case DESTROY_CQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    destroy_cq),
+				      rvt_destroy_cq);
+		break;
+
+	case POLL_CQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    poll_cq),
+				      rvt_poll_cq);
+		break;
+
+	case REQ_NOTFIY_CQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    req_notify_cq),
+				      rvt_req_notify_cq);
+		break;
+
+	case RESIZE_CQ:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    resize_cq),
+				      rvt_resize_cq);
+		break;
+
+	case ALLOC_PD:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    alloc_pd),
+				      rvt_alloc_pd);
+		break;
+
+	case DEALLOC_PD:
+		check_driver_override(rdi, offsetof(struct ib_device,
+						    dealloc_pd),
+				      rvt_dealloc_pd);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 /**
  * rvt_register_device - register a driver

@@ -343,35 +706,26 @@ static int rvt_get_port_immutable(struct ib_device *ibdev, u8 port_num,
  */
 int rvt_register_device(struct rvt_dev_info *rdi)
 {
-	/* Validate that drivers have provided the right information */
-	int ret = 0;
+	int ret = 0, i;
 
 	if (!rdi)
 		return -EINVAL;
 
-	if ((!rdi->driver_f.port_callback) ||
-	    (!rdi->driver_f.get_card_name) ||
-	    (!rdi->driver_f.get_pci_dev) ||
-	    (!rdi->driver_f.check_ah)) {
-		pr_err("Driver not supporting req func\n");
-		return -EINVAL;
-	}
+	/*
+	 * Check to ensure drivers have setup the required helpers for the verbs
+	 * they want rdmavt to handle
+	 */
+	for (i = 0; i < _VERB_IDX_MAX; i++)
+		if (check_support(rdi, i)) {
+			pr_err("Driver support req not met at %d\n", i);
+			return -EINVAL;
+		}
+
 
 	/* Once we get past here we can use rvt_pr macros and tracepoints */
 	trace_rvt_dbg(rdi, "Driver attempting registration");
 	rvt_mmap_init(rdi);
 
-	/* Dev Ops */
-	CHECK_DRIVER_OVERRIDE(rdi, query_device);
-	CHECK_DRIVER_OVERRIDE(rdi, modify_device);
-	CHECK_DRIVER_OVERRIDE(rdi, query_port);
-	CHECK_DRIVER_OVERRIDE(rdi, modify_port);
-	CHECK_DRIVER_OVERRIDE(rdi, query_pkey);
-	CHECK_DRIVER_OVERRIDE(rdi, query_gid);
-	CHECK_DRIVER_OVERRIDE(rdi, alloc_ucontext);
-	CHECK_DRIVER_OVERRIDE(rdi, dealloc_ucontext);
-	CHECK_DRIVER_OVERRIDE(rdi, get_port_immutable);
-
 	/* Queue Pairs */
 	ret = rvt_driver_qp_init(rdi);
 	if (ret) {

@@ -379,33 +733,15 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 		return -EINVAL;
 	}
 
-	CHECK_DRIVER_OVERRIDE(rdi, create_qp);
-	CHECK_DRIVER_OVERRIDE(rdi, modify_qp);
-	CHECK_DRIVER_OVERRIDE(rdi, destroy_qp);
-	CHECK_DRIVER_OVERRIDE(rdi, query_qp);
-	CHECK_DRIVER_OVERRIDE(rdi, post_send);
-	CHECK_DRIVER_OVERRIDE(rdi, post_recv);
-	CHECK_DRIVER_OVERRIDE(rdi, post_srq_recv);
-
 	/* Address Handle */
-	CHECK_DRIVER_OVERRIDE(rdi, create_ah);
-	CHECK_DRIVER_OVERRIDE(rdi, destroy_ah);
-	CHECK_DRIVER_OVERRIDE(rdi, modify_ah);
-	CHECK_DRIVER_OVERRIDE(rdi, query_ah);
 	spin_lock_init(&rdi->n_ahs_lock);
 	rdi->n_ahs_allocated = 0;
 
 	/* Shared Receive Queue */
-	CHECK_DRIVER_OVERRIDE(rdi, create_srq);
-	CHECK_DRIVER_OVERRIDE(rdi, modify_srq);
-	CHECK_DRIVER_OVERRIDE(rdi, destroy_srq);
-	CHECK_DRIVER_OVERRIDE(rdi, query_srq);
 	rvt_driver_srq_init(rdi);
 
 	/* Multicast */
 	rvt_driver_mcast_init(rdi);
-	CHECK_DRIVER_OVERRIDE(rdi, attach_mcast);
-	CHECK_DRIVER_OVERRIDE(rdi, detach_mcast);
 
 	/* Mem Region */
 	ret = rvt_driver_mr_init(rdi);

@@ -414,35 +750,18 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 		goto bail_no_mr;
 	}
 
-	CHECK_DRIVER_OVERRIDE(rdi, get_dma_mr);
-	CHECK_DRIVER_OVERRIDE(rdi, reg_user_mr);
-	CHECK_DRIVER_OVERRIDE(rdi, dereg_mr);
-	CHECK_DRIVER_OVERRIDE(rdi, alloc_mr);
-	CHECK_DRIVER_OVERRIDE(rdi, alloc_fmr);
-	CHECK_DRIVER_OVERRIDE(rdi, map_phys_fmr);
-	CHECK_DRIVER_OVERRIDE(rdi, unmap_fmr);
-	CHECK_DRIVER_OVERRIDE(rdi, dealloc_fmr);
-	CHECK_DRIVER_OVERRIDE(rdi, mmap);
-
 	/* Completion queues */
 	ret = rvt_driver_cq_init(rdi);
 	if (ret) {
 		pr_err("Error in driver CQ init.\n");
 		goto bail_mr;
 	}
-	CHECK_DRIVER_OVERRIDE(rdi, create_cq);
-	CHECK_DRIVER_OVERRIDE(rdi, destroy_cq);
-	CHECK_DRIVER_OVERRIDE(rdi, poll_cq);
-	CHECK_DRIVER_OVERRIDE(rdi, req_notify_cq);
-	CHECK_DRIVER_OVERRIDE(rdi, resize_cq);
 
 	/* DMA Operations */
 	rdi->ibdev.dma_ops =
 		rdi->ibdev.dma_ops ? : &rvt_default_dma_mapping_ops;
 
 	/* Protection Domain */
-	CHECK_DRIVER_OVERRIDE(rdi, alloc_pd);
-	CHECK_DRIVER_OVERRIDE(rdi, dealloc_pd);
 	spin_lock_init(&rdi->n_pds_lock);
 	rdi->n_pds_allocated = 0;
 

171 lines not on this page · raw message

index 5cf019f..cbf6200 100644
@@ -1682,6 +1682,10 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.query_port_state = qib_query_port;
 	dd->verbs_dev.rdi.driver_f.shut_down_port = qib_shut_down_port;
 	dd->verbs_dev.rdi.driver_f.cap_mask_chg = qib_cap_mask_chg;
+	dd->verbs_dev.rdi.driver_f.notify_create_mad_agent =
+						qib_notify_create_mad_agent;
+	dd->verbs_dev.rdi.driver_f.notify_free_mad_agent =
+						qib_notify_free_mad_agent;
 
 	dd->verbs_dev.rdi.dparms.max_rdma_atomic = QIB_MAX_RDMA_ATOMIC;
 	dd->verbs_dev.rdi.driver_f.get_guid_be = qib_get_guid_be;

index a159922..ca28c19 100644
@@ -2910,8 +2910,8 @@ static void qib_setup_7322_cleanup(struct qib_devdata *dd)
 			spin_unlock_irqrestore(&dd->cspec->gpio_lock, flags);
 			qib_qsfp_deinit(&dd->pport[i].cpspec->qsfp_data);
 		}
-		if (dd->pport[i].ibport_data.rvp.smi_ah)
-			ib_destroy_ah(&dd->pport[i].ibport_data.rvp.smi_ah->ibah);
+		if (dd->pport[i].ibport_data.smi_ah)
+			ib_destroy_ah(&dd->pport[i].ibport_data.smi_ah->ibah);
 	}
 }
 

@@ -5507,7 +5507,7 @@ static void try_7322_ipg(struct qib_pportdata *ppd)
 	if (IS_ERR(send_buf))
 		goto retry;
 
-	if (!ibp->rvp.smi_ah) {
+	if (!ibp->smi_ah) {
 		struct ib_ah *ah;
 
 		ah = qib_create_qp0_ah(ibp, be16_to_cpu(IB_LID_PERMISSIVE));

@@ -5515,11 +5515,11 @@ static void try_7322_ipg(struct qib_pportdata *ppd)
 			ret = PTR_ERR(ah);
 		else {
 			send_buf->ah = ah;
-			ibp->rvp.smi_ah = ibah_to_rvtah(ah);
+			ibp->smi_ah = ibah_to_rvtah(ah);
 			ret = 0;
 		}
 	} else {
-		send_buf->ah = &ibp->rvp.smi_ah->ibah;
+		send_buf->ah = &ibp->smi_ah->ibah;
 		ret = 0;
 	}
 

index d137d71..4b76a8d 100644
@@ -219,6 +219,7 @@ struct qib_pma_counters {
 
 struct qib_ibport {
 	struct rvt_ibport rvp;
+	struct rvt_ah *smi_ah;
 	__be64 guids[QIB_GUIDS_PER_PORT	- 1];	/* writable GUIDs */
 	struct qib_pma_counters __percpu *pmastats;
 	u64 z_unicast_xmit;     /* starting count for PMA */

index ec658d8..2c3a04c 100644
@@ -137,7 +137,6 @@ struct rvt_ibport {
 	u16 *pkey_table;
 
 	struct rvt_ah *sm_ah;
-	struct rvt_ah *smi_ah;
 };
 
 #define RVT_CQN_MAX 16 /* maximum length of cq name */

index c69c070..b1ffc8b 100644
@@ -508,11 +508,6 @@ int rvt_driver_cq_init(struct rvt_dev_info *rdi)
 	int cpu;
 	struct task_struct *task;
 
-	if (rdi->flags & RVT_FLAG_CQ_INIT_DRIVER) {
-		rvt_pr_info(rdi, "Driver is doing CQ init.\n");
-		return 0;
-	}
-
 	if (rdi->worker)
 		return 0;
 	rdi->worker = kzalloc(sizeof(*rdi->worker), GFP_KERNEL);

index 8549652..4d5ef73 100644
@@ -66,11 +66,6 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi)
 	unsigned lk_tab_size;
 	int i;
 
-	if (rdi->flags & RVT_FLAG_MR_INIT_DRIVER) {
-		rvt_pr_info(rdi, "Driver is doing MR init.\n");
-		return 0;
-	}
-
 	/*
 	 * The top hfi1_lkey_table_size bits are used to index the
 	 * table.  The lower 8 bits can be owned by the user (copied from

index 5809562..441e17a 100644
@@ -173,11 +173,6 @@ int rvt_driver_qp_init(struct rvt_dev_info *rdi)
 	int i;
 	int ret = -ENOMEM;
 
-	if (rdi->flags & RVT_FLAG_QP_INIT_DRIVER) {
-		rvt_pr_info(rdi, "Driver is doing QP init.\n");
-		return 0;
-	}
-
 	if (!rdi->dparms.qp_table_size)
 		return -EINVAL;
 

@@ -284,9 +279,6 @@ void rvt_qp_exit(struct rvt_dev_info *rdi)
 	if (!rdi->qp_dev)
 		return;
 
-	if (rdi->flags & RVT_FLAG_QP_INIT_DRIVER)
-		return; /* driver did the qp init so nothing else to do */
-
 	kfree(rdi->qp_dev->qp_table);
 	free_qpn_table(&rdi->qp_dev->qpn_table);
 	kfree(rdi->qp_dev);

index 2c3a04c..264c514 100644
@@ -60,16 +60,6 @@
 #include <rdma/rdmavt_mr.h>
 #include <rdma/rdmavt_qp.h>
 
-/*
- * For some of the IBTA objects there will likely be some
- * initializations required. We need flags to determine whether it is OK
- * for rdmavt to do this or not. This does not imply any functions of a
- * partiuclar IBTA object are overridden.
- */
-#define RVT_FLAG_MR_INIT_DRIVER BIT(1)
-#define RVT_FLAG_QP_INIT_DRIVER BIT(2)
-#define RVT_FLAG_CQ_INIT_DRIVER BIT(3)
-
 #define RVT_MAX_PKEY_VALUES 16
 
 struct rvt_ibport {

index 264c514..4c50bbb 100644
@@ -138,24 +138,6 @@ struct rvt_driver_params {
 	struct ib_device_attr props;
 
 	/*
-	 * Drivers will need to support a number of notifications to rvt in
-	 * accordance with certain events. This structure should contain a mask
-	 * of the supported events. Such events that the rvt may need to know
-	 * about include:
-	 * port errors
-	 * port active
-	 * lid change
-	 * sm change
-	 * client reregister
-	 * pkey change
-	 *
-	 * There may also be other events that the rvt layers needs to know
-	 * about this is not an exhaustive list. Some events though rvt does not
-	 * need to rely on the driver for such as completion queue error.
-	 */
-	 int rvt_signal_supported;
-
-	/*
 	 * Anything driver specific that is not covered by props
 	 * For instance special module parameters. Goes here.
 	 */

index 273974f..e202b81 100644
@@ -80,7 +80,6 @@ void rvt_release_mmap_info(struct kref *ref)
 	vfree(ip->obj);
 	kfree(ip);
 }
-EXPORT_SYMBOL(rvt_release_mmap_info);
 
 static void rvt_vma_open(struct vm_area_struct *vma)
 {

@@ -146,7 +145,6 @@ int rvt_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 done:
 	return ret;
 }
-EXPORT_SYMBOL(rvt_mmap);
 
 /**
  * rvt_create_mmap_info - allocate information for hfi1_mmap

@@ -185,7 +183,6 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
 
 	return ip;
 }
-EXPORT_SYMBOL(rvt_create_mmap_info);
 
 /**
  * rvt_update_mmap_info - update a mem map

@@ -209,4 +206,3 @@ void rvt_update_mmap_info(struct rvt_dev_info *rdi, struct rvt_mmap_info *ip,
 	ip->size = size;
 	ip->obj = obj;
 }
-EXPORT_SYMBOL(rvt_update_mmap_info);

index e806747..fab0e7b 100644
@@ -51,5 +51,13 @@
 #include <rdma/rdma_vt.h>
 
 void rvt_mmap_init(struct rvt_dev_info *rdi);
+void rvt_release_mmap_info(struct kref *ref);
+int rvt_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
+struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
+					   u32 size,
+					   struct ib_ucontext *context,
+					   void *obj);
+void rvt_update_mmap_info(struct rvt_dev_info *rdi, struct rvt_mmap_info *ip,
+			  u32 size, void *obj);
 
 #endif          /* DEF_RDMAVTMMAP_H */

290 lines not on this page · raw message

index 98c4927..f7c48e9 100644
@@ -50,6 +50,7 @@
 #include <linux/vmalloc.h>
 
 #include "srq.h"
+#include "vt.h"
 
 /**
  * rvt_driver_srq_init - init srq resources on a per driver basis

index e26f9e9..6b01eaa 100644
@@ -60,6 +60,7 @@
 #include "mmap.h"
 #include "cq.h"
 #include "mad.h"
+#include "mmap.h"
 
 #define rvt_pr_info(rdi, fmt, ...) \
 	__rvt_pr_info(rdi->driver_f.get_pci_dev(rdi), \

index 4c50bbb..a869655 100644
@@ -476,19 +476,6 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc);
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 		struct rvt_sge *isge, struct ib_sge *sge, int acc);
-int rvt_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
-void rvt_release_mmap_info(struct kref *ref);
-struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
-					   u32 size,
-					   struct ib_ucontext *context,
-					   void *obj);
-void rvt_update_mmap_info(struct rvt_dev_info *rdi, struct rvt_mmap_info *ip,
-			  u32 size, void *obj);
-int rvt_reg_mr(struct rvt_qp *qp, struct ib_reg_wr *wr);
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid);
 
-/* Temporary export */
-void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-		  enum ib_qp_type type);
-
 #endif          /* DEF_RDMA_VT_H */

index 1066b5d..933f14f 100644
@@ -438,10 +438,6 @@ static inline struct rvt_rwqe *rvt_get_rwqe_ptr(struct rvt_rq *rq, unsigned n)
 extern const int  ib_rvt_state_ops[];
 
 struct rvt_dev_info;
-void rvt_remove_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp);
-void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends);
 int rvt_error_qp(struct rvt_qp *qp, enum ib_wc_status err);
-void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn);
-void rvt_dec_qp_cnt(struct rvt_dev_info *rdi);
 
 #endif          /* DEF_RDMAVT_INCQP_H */

index ca28c19..82d7c4b 100644
@@ -2910,8 +2910,6 @@ static void qib_setup_7322_cleanup(struct qib_devdata *dd)
 			spin_unlock_irqrestore(&dd->cspec->gpio_lock, flags);
 			qib_qsfp_deinit(&dd->pport[i].cpspec->qsfp_data);
 		}
-		if (dd->pport[i].ibport_data.smi_ah)
-			ib_destroy_ah(&dd->pport[i].ibport_data.smi_ah->ibah);
 	}
 }
 

index 73ca2c2..0bd1837 100644
@@ -2496,4 +2496,7 @@ void qib_notify_free_mad_agent(struct rvt_dev_info *rdi, int port_idx)
 
 	if (dd->pport[port_idx].cong_stats.timer.data)
 		del_timer_sync(&dd->pport[port_idx].cong_stats.timer);
+
+	if (dd->pport[port_idx].ibport_data.smi_ah)
+		ib_destroy_ah(&dd->pport[port_idx].ibport_data.smi_ah->ibah);
 }