Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/dledford/rdma

Pull rdma fixes from Doug Ledford:
 "This is the second batch of queued up rdma patches for this rc cycle.

  There isn't anything really major in here.  It's passed 0day,
  linux-next, and local testing across a wide variety of hardware.
  There are still a few known issues to be tracked down, but this should
  amount to the vast majority of the rdma RC fixes.

  Round two of 4.7 rc fixes:

   - A couple minor fixes to the rdma core
   - Multiple minor fixes to hfi1
   - Multiple minor fixes to mlx4/mlx4
   - A few minor fixes to i40iw"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (31 commits)
  IB/srpt: Reduce QP buffer size
  i40iw: Enable level-1 PBL for fast memory registration
  i40iw: Return correct max_fast_reg_page_list_len
  i40iw: Correct status check on i40iw_get_pble
  i40iw: Correct CQ arming
  IB/rdmavt: Correct qp_priv_alloc() return value test
  IB/hfi1: Don't zero out qp->s_ack_queue in rvt_reset_qp
  IB/hfi1: Fix deadlock with txreq allocation slow path
  IB/mlx4: Prevent cross page boundary allocation
  IB/mlx4: Fix memory leak if QP creation failed
  IB/mlx4: Verify port number in flow steering create flow
  IB/mlx4: Fix error flow when sending mads under SRIOV
  IB/mlx4: Fix the SQ size of an RC QP
  IB/mlx5: Fix wrong naming of port_rcv_data counter
  IB/mlx5: Fix post send fence logic
  IB/uverbs: Initialize ib_qp_init_attr with zeros
  IB/core: Fix false search of the IB_SA_WELL_KNOWN_GUID
  IB/core: Fix RoCE v1 multicast join logic issue
  IB/core: Fix no default GIDs when netdevice reregisters
  IB/hfi1: Send a pkey change event on driver pkey update
  ...

drivers/infiniband/core/cache.c

@@ -411,7 +411,9 @@ int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
 
 	for (ix = 0; ix < table->sz; ix++)
 		if (table->data_vec[ix].attr.ndev == ndev)
-			if (!del_gid(ib_dev, port, table, ix, false))
+			if (!del_gid(ib_dev, port, table, ix,
+				     !!(table->data_vec[ix].props &
+					GID_TABLE_ENTRY_DEFAULT)))
 				deleted = true;
 
 	write_unlock_irq(&table->rwlock);

drivers/infiniband/core/cma.c

@@ -708,17 +708,6 @@ static void cma_deref_id(struct rdma_id_private *id_priv)
 		complete(&id_priv->comp);
 }
 
-static int cma_disable_callback(struct rdma_id_private *id_priv,
-				enum rdma_cm_state state)
-{
-	mutex_lock(&id_priv->handler_mutex);
-	if (id_priv->state != state) {
-		mutex_unlock(&id_priv->handler_mutex);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 struct rdma_cm_id *rdma_create_id(struct net *net,
 				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
@@ -1671,11 +1660,12 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	struct rdma_cm_event event;
 	int ret = 0;
 
+	mutex_lock(&id_priv->handler_mutex);
 	if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_CONNECT)) ||
+	     id_priv->state != RDMA_CM_CONNECT) ||
 	    (ib_event->event == IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_DISCONNECT)))
-		return 0;
+	     id_priv->state != RDMA_CM_DISCONNECT))
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -1870,7 +1860,7 @@ static int cma_check_req_qp_type(struct rdma_cm_id *id, struct ib_cm_event *ib_e
 
 static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 {
-	struct rdma_id_private *listen_id, *conn_id;
+	struct rdma_id_private *listen_id, *conn_id = NULL;
 	struct rdma_cm_event event;
 	struct net_device *net_dev;
 	int offset, ret;
@@ -1884,9 +1874,10 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 		goto net_dev_put;
 	}
 
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) {
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN) {
 		ret = -ECONNABORTED;
-		goto net_dev_put;
+		goto err1;
 	}
 
 	memset(&event, 0, sizeof event);
@@ -1976,8 +1967,9 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (iw_event->event) {
@@ -2029,6 +2021,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 		return ret;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
 }
@@ -2039,13 +2032,15 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	struct rdma_cm_id *new_cm_id;
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = -ECONNABORTED;
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
 	listen_id = cm_id->context;
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN))
-		return -ECONNABORTED;
+
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN)
+		goto out;
 
 	/* Create a new RDMA id for the new IW CM ID */
 	new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
@@ -3216,8 +3211,9 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 	struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
 	int ret = 0;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -3673,12 +3669,13 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 	struct rdma_id_private *id_priv;
 	struct cma_multicast *mc = multicast->context;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = 0;
 
 	id_priv = mc->id_priv;
-	if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) &&
-	    cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_ADDR_BOUND &&
+	    id_priv->state != RDMA_CM_ADDR_RESOLVED)
+		goto out;
 
 	if (!status)
 		status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
@@ -3720,6 +3717,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 		return 0;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return 0;
 }
@@ -3878,12 +3876,12 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
 		   rdma_start_port(id_priv->cma_dev->device)];
 	if (addr->sa_family == AF_INET) {
-		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
 			err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
 					    true);
-		if (!err) {
-			mc->igmp_joined = true;
-			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+			if (!err)
+				mc->igmp_joined = true;
 		}
 	} else {
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)

drivers/infiniband/core/uverbs_cmd.c

@@ -1747,7 +1747,7 @@ static int create_qp(struct ib_uverbs_file *file,
 	struct ib_srq			*srq = NULL;
 	struct ib_qp			*qp;
 	char				*buf;
-	struct ib_qp_init_attr		attr;
+	struct ib_qp_init_attr		attr = {};
 	struct ib_uverbs_ex_create_qp_resp resp;
 	int				ret;
 

drivers/infiniband/core/verbs.c

@@ -511,12 +511,16 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 		ah_attr->grh.dgid = sgid;
 
 		if (!rdma_cap_eth_ah(device, port_num)) {
-			ret = ib_find_cached_gid_by_port(device, &dgid,
-							 IB_GID_TYPE_IB,
-							 port_num, NULL,
-							 &gid_index);
-			if (ret)
-				return ret;
+			if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
+				ret = ib_find_cached_gid_by_port(device, &dgid,
+								 IB_GID_TYPE_IB,
+								 port_num, NULL,
+								 &gid_index);
+				if (ret)
+					return ret;
+			} else {
+				gid_index = 0;
+			}
 		}
 
 		ah_attr->grh.sgid_index = (u8) gid_index;

drivers/infiniband/hw/hfi1/chip.c

@@ -1037,7 +1037,7 @@ static void dc_shutdown(struct hfi1_devdata *);
 static void dc_start(struct hfi1_devdata *);
 static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 			   unsigned int *np);
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd);
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6962,8 +6962,6 @@ void handle_link_down(struct work_struct *work)
 	}
 
 	reset_neighbor_info(ppd);
-	if (ppd->mgmt_allowed)
-		remove_full_mgmt_pkey(ppd);
 
 	/* disable the port */
 	clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
@@ -7070,12 +7068,16 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 			    __func__, ppd->pkeys[2], FULL_MGMT_P_KEY);
 	ppd->pkeys[2] = FULL_MGMT_P_KEY;
 	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	hfi1_event_pkey_change(ppd->dd, ppd->port);
 }
 
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd)
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 {
-	ppd->pkeys[2] = 0;
-	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	if (ppd->pkeys[2] != 0) {
+		ppd->pkeys[2] = 0;
+		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+		hfi1_event_pkey_change(ppd->dd, ppd->port);
+	}
 }
 
 /*
@@ -9168,6 +9170,13 @@ int start_link(struct hfi1_pportdata *ppd)
 		return 0;
 	}
 
+	/*
+	 * FULL_MGMT_P_KEY is cleared from the pkey table, so that the
+	 * pkey table can be configured properly if the HFI unit is connected
+	 * to switch port with MgmtAllowed=NO
+	 */
+	clear_full_mgmt_pkey(ppd);
+
 	return set_link_state(ppd, HLS_DN_POLL);
 }
 
@@ -9777,7 +9786,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 	u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2)
 			      & SEND_LEN_CHECK1_LEN_VL15_MASK) <<
 		SEND_LEN_CHECK1_LEN_VL15_SHIFT;
-	int i;
+	int i, j;
 	u32 thres;
 
 	for (i = 0; i < ppd->vls_supported; i++) {
@@ -9801,7 +9810,10 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
 						dd->rcd[0]->rcvhdrqentsize));
-		sc_set_cr_threshold(dd->vld[i].sc, thres);
+		for (j = 0; j < INIT_SC_PER_VL; j++)
+			sc_set_cr_threshold(
+					pio_select_send_context_vl(dd, j, i),
+					    thres);
 	}
 	thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50),
 		    sc_mtu_to_threshold(dd->vld[15].sc,

drivers/infiniband/hw/hfi1/file_ops.c

@@ -203,6 +203,9 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 
 	switch (cmd) {
 	case HFI1_IOCTL_ASSIGN_CTXT:
+		if (uctxt)
+			return -EINVAL;
+
 		if (copy_from_user(&uinfo,
 				   (struct hfi1_user_info __user *)arg,
 				   sizeof(uinfo)))

drivers/infiniband/hw/hfi1/init.c

@@ -1383,7 +1383,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
-	struct hfi1_devdata *dd = NULL;
+	struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
 	struct hfi1_pportdata *ppd;
 
 	/* First, lock the non-writable module parameters */

drivers/infiniband/hw/hfi1/mad.c

@@ -78,6 +78,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp)
 	memset(data, 0, size);
 }
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
+{
+	struct ib_event event;
+
+	event.event = IB_EVENT_PKEY_CHANGE;
+	event.device = &dd->verbs_dev.rdi.ibdev;
+	event.element.port_num = port;
+	ib_dispatch_event(&event);
+}
+
 static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 {
 	struct ib_mad_send_buf *send_buf;
@@ -1418,15 +1428,10 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
 	}
 
 	if (changed) {
-		struct ib_event event;
-
 		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
-
-		event.event = IB_EVENT_PKEY_CHANGE;
-		event.device = &dd->verbs_dev.rdi.ibdev;
-		event.element.port_num = port;
-		ib_dispatch_event(&event);
+		hfi1_event_pkey_change(dd, port);
 	}
+
 	return 0;
 }
 

drivers/infiniband/hw/hfi1/mad.h

@@ -434,4 +434,6 @@ struct sc2vlnt {
 		    COUNTER_MASK(1, 3) | \
 		    COUNTER_MASK(1, 4))
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+
 #endif				/* _HFI1_MAD_H */

drivers/infiniband/hw/hfi1/pio.c

@@ -995,7 +995,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause)
 		/* counter is reset if occupancy count changes */
 		if (reg != reg_prev)
 			loop = 0;
-		if (loop > 500) {
+		if (loop > 50000) {
 			/* timed out - bounce the link */
 			dd_dev_err(dd,
 				   "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
@@ -1797,6 +1797,21 @@ static void pio_map_rcu_callback(struct rcu_head *list)
 	pio_map_free(m);
 }
 
+/*
+ * Set credit return threshold for the kernel send context
+ */
+static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
+{
+	u32 thres;
+
+	thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
+					    50),
+		    sc_mtu_to_threshold(dd->kernel_send_context[scontext],
+					dd->vld[i].mtu,
+					dd->rcd[0]->rcvhdrqentsize));
+	sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
+}
+
 /*
  * pio_map_init - called when #vls change
  * @dd: hfi1_devdata
@@ -1872,11 +1887,16 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts)
 			if (!newmap->map[i])
 				goto bail;
 			newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
-			/* assign send contexts */
+			/*
+			 * assign send contexts and
+			 * adjust credit return threshold
+			 */
 			for (j = 0; j < sz; j++) {
-				if (dd->kernel_send_context[scontext])
+				if (dd->kernel_send_context[scontext]) {
 					newmap->map[i]->ksc[j] =
 					dd->kernel_send_context[scontext];
+					set_threshold(dd, scontext, i);
+				}
 				if (++scontext >= first_scontext +
 						  vl_scontexts[i])
 					/* wrap back to first send context */

drivers/infiniband/hw/hfi1/qsfp.c

@@ -579,7 +579,8 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len)
 
 	if (ppd->qsfp_info.cache_valid) {
 		if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
-			sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]);
+			snprintf(lenstr, sizeof(lenstr), "%dM ",
+				 cache[QSFP_MOD_LEN_OFFS]);
 
 		power_byte = cache[QSFP_MOD_PWR_OFFS];
 		sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",