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

Pull rdma updates from Doug Ledford:
 "This is the complete update for the rdma stack for this release cycle.

  Most of it is typical driver and core updates, but there is the
  entirely new VMWare pvrdma driver. You may have noticed that there
  were changes in DaveM's pull request to the bnxt Ethernet driver to
  support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
  be pulled in this release cycle, but it simply wasn't ready in time
  and was dropped (a few review comments still to address, and some
  multi-arch build issues like prefetch() not working across all
  arches).

  Summary:

   - shared mlx5 updates with net stack (will drop out on merge if
     Dave's tree has already been merged)

   - driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe

   - debug cleanups

   - new connection rejection helpers

   - SRP updates

   - various misc fixes

   - new paravirt driver from vmware"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
  IB: Add vmw_pvrdma driver
  IB/mlx4: fix improper return value
  IB/ocrdma: fix bad initialization
  infiniband: nes: return value of skb_linearize should be handled
  MAINTAINERS: Update Intel RDMA RNIC driver maintainers
  MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
  IB/core: fix unmap_sg argument
  qede: fix general protection fault may occur on probe
  IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
  mlx5, calc_sq_size(): Make a debug message more informative
  mlx5: Remove a set-but-not-used variable
  mlx5: Use { } instead of { 0 } to init struct
  IB/srp: Make writing the add_target sysfs attr interruptible
  IB/srp: Make mapping failures easier to debug
  IB/srp: Make login failures easier to debug
  IB/srp: Introduce a local variable in srp_add_one()
  IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
  IB/multicast: Check ib_find_pkey() return value
  IPoIB: Avoid reading an uninitialized member variable
  IB/mad: Fix an array index check
  ...

drivers/infiniband/hw/hfi1/pio.c

@@ -758,6 +758,7 @@ struct send_context *sc_alloc(struct hfi1_devdata *dd, int type,
 	sc->hw_context = hw_context;
 	cr_group_addresses(sc, &dma);
 	sc->credits = sci->credits;
+	sc->size = sc->credits * PIO_BLOCK_SIZE;
 
 /* PIO Send Memory Address details */
 #define PIO_ADDR_CONTEXT_MASK 0xfful
@@ -1242,6 +1243,7 @@ int sc_enable(struct send_context *sc)
 	sc->free = 0;
 	sc->alloc_free = 0;
 	sc->fill = 0;
+	sc->fill_wrap = 0;
 	sc->sr_head = 0;
 	sc->sr_tail = 0;
 	sc->flags = 0;
@@ -1385,7 +1387,7 @@ struct pio_buf *sc_buffer_alloc(struct send_context *sc, u32 dw_len,
 	unsigned long flags;
 	unsigned long avail;
 	unsigned long blocks = dwords_to_blocks(dw_len);
-	unsigned long start_fill;
+	u32 fill_wrap;
 	int trycount = 0;
 	u32 head, next;
 
@@ -1410,9 +1412,7 @@ retry:
 			(sc->fill - sc->alloc_free);
 		if (blocks > avail) {
 			/* still no room, actively update */
-			spin_unlock_irqrestore(&sc->alloc_lock, flags);
 			sc_release_update(sc);
-			spin_lock_irqsave(&sc->alloc_lock, flags);
 			sc->alloc_free = ACCESS_ONCE(sc->free);
 			trycount++;
 			goto retry;
@@ -1428,8 +1428,11 @@ retry:
 	head = sc->sr_head;
 
 	/* "allocate" the buffer */
-	start_fill = sc->fill;
 	sc->fill += blocks;
+	fill_wrap = sc->fill_wrap;
+	sc->fill_wrap += blocks;
+	if (sc->fill_wrap >= sc->credits)
+		sc->fill_wrap = sc->fill_wrap - sc->credits;
 
 	/*
 	 * Fill the parts that the releaser looks at before moving the head.
@@ -1458,11 +1461,8 @@ retry:
 	spin_unlock_irqrestore(&sc->alloc_lock, flags);
 
 	/* finish filling in the buffer outside the lock */
-	pbuf->start = sc->base_addr + ((start_fill % sc->credits)
-							* PIO_BLOCK_SIZE);
-	pbuf->size = sc->credits * PIO_BLOCK_SIZE;
-	pbuf->end = sc->base_addr + pbuf->size;
-	pbuf->block_count = blocks;
+	pbuf->start = sc->base_addr + fill_wrap * PIO_BLOCK_SIZE;
+	pbuf->end = sc->base_addr + sc->size;
 	pbuf->qw_written = 0;
 	pbuf->carry_bytes = 0;
 	pbuf->carry.val64 = 0;
@@ -1573,6 +1573,7 @@ static void sc_piobufavail(struct send_context *sc)
 		qp = iowait_to_qp(wait);
 		priv = qp->priv;
 		list_del_init(&priv->s_iowait.list);
+		priv->s_iowait.lock = NULL;
 		/* refcount held until actual wake up */
 		qps[n++] = qp;
 	}
@@ -2028,29 +2029,17 @@ freesc15:
 int init_credit_return(struct hfi1_devdata *dd)
 {
 	int ret;
-	int num_numa;
 	int i;
 
-	num_numa = num_online_nodes();
-	/* enforce the expectation that the numas are compact */
-	for (i = 0; i < num_numa; i++) {
-		if (!node_online(i)) {
-			dd_dev_err(dd, "NUMA nodes are not compact\n");
-			ret = -EINVAL;
-			goto done;
-		}
-	}
-
 	dd->cr_base = kcalloc(
-		num_numa,
+		node_affinity.num_possible_nodes,
 		sizeof(struct credit_return_base),
 		GFP_KERNEL);
 	if (!dd->cr_base) {
-		dd_dev_err(dd, "Unable to allocate credit return base\n");
 		ret = -ENOMEM;
 		goto done;
 	}
-	for (i = 0; i < num_numa; i++) {
+	for_each_node_with_cpus(i) {
 		int bytes = TXE_NUM_CONTEXTS * sizeof(struct credit_return);
 
 		set_dev_node(&dd->pcidev->dev, i);
@@ -2077,14 +2066,11 @@ done:
 
 void free_credit_return(struct hfi1_devdata *dd)
 {
-	int num_numa;
 	int i;
 
 	if (!dd->cr_base)
 		return;
-
-	num_numa = num_online_nodes();
-	for (i = 0; i < num_numa; i++) {
+	for (i = 0; i < node_affinity.num_possible_nodes; i++) {
 		if (dd->cr_base[i].va) {
 			dma_free_coherent(&dd->pcidev->dev,
 					  TXE_NUM_CONTEXTS *