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

Pull rdma updates from Jason Gunthorpe:
 "This has been a slightly more active cycle than normal with ongoing
  core changes and quite a lot of collected driver updates.

   - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe

   - A new data transfer mode for HFI1 giving higher performance

   - Significant functional and bug fix update to the mlx5
     On-Demand-Paging MR feature

   - A chip hang reset recovery system for hns

   - Change mm->pinned_vm to an atomic64

   - Update bnxt_re to support a new 57500 chip

   - A sane netlink 'rdma link add' method for creating rxe devices and
     fixing the various unregistration race conditions in rxe's
     unregister flow

   - Allow lookup up objects by an ID over netlink

   - Various reworking of the core to driver interface:
       - drivers should not assume umem SGLs are in PAGE_SIZE chunks
       - ucontext is accessed via udata not other means
       - start to make the core code responsible for object memory
         allocation
       - drivers should convert struct device to struct ib_device via a
         helper
       - drivers have more tools to avoid use after unregister problems"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (280 commits)
  net/mlx5: ODP support for XRC transport is not enabled by default in FW
  IB/hfi1: Close race condition on user context disable and close
  RDMA/umem: Revert broken 'off by one' fix
  RDMA/umem: minor bug fix in error handling path
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  cxgb4: kfree mhp after the debug print
  IB/rdmavt: Fix concurrency panics in QP post_send and modify to error
  IB/rdmavt: Fix loopback send with invalidate ordering
  IB/iser: Fix dma_nents type definition
  IB/mlx5: Set correct write permissions for implicit ODP MR
  bnxt_re: Clean cq for kernel consumers only
  RDMA/uverbs: Don't do double free of allocated PD
  RDMA: Handle ucontext allocations by IB/core
  RDMA/core: Fix a WARN() message
  bnxt_re: fix the regression due to changes in alloc_pbl
  IB/mlx4: Increase the timeout for CM cache
  IB/core: Abort page fault handler silently during owning process exit
  IB/mlx5: Validate correct PD before prefetch MR
  IB/mlx5: Protect against prefetch of invalid MR
  RDMA/uverbs: Store PR pointer before it is overwritten
  ...

1 files changed, 28 insertions, 7 deletions

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 441b06e2a154..faaaac8fbc55 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -73,7 +73,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
 
-#define HFI1_MAX_ACTIVE_WORKQUEUE_ENTRIES 5
 /*
  * min buffers we want to have per context, after driver
  */
@@ -216,12 +215,12 @@ static void hfi1_rcd_free(struct kref *kref)
 	struct hfi1_ctxtdata *rcd =
 		container_of(kref, struct hfi1_ctxtdata, kref);
 
-	hfi1_free_ctxtdata(rcd->dd, rcd);
-
 	spin_lock_irqsave(&rcd->dd->uctxt_lock, flags);
 	rcd->dd->rcd[rcd->ctxt] = NULL;
 	spin_unlock_irqrestore(&rcd->dd->uctxt_lock, flags);
 
+	hfi1_free_ctxtdata(rcd->dd, rcd);
+
 	kfree(rcd);
 }
 
@@ -244,10 +243,13 @@ int hfi1_rcd_put(struct hfi1_ctxtdata *rcd)
  * @rcd: pointer to an initialized rcd data structure
  *
  * Use this to get a reference after the init.
+ *
+ * Return : reflect kref_get_unless_zero(), which returns non-zero on
+ * increment, otherwise 0.
  */
-void hfi1_rcd_get(struct hfi1_ctxtdata *rcd)
+int hfi1_rcd_get(struct hfi1_ctxtdata *rcd)
 {
-	kref_get(&rcd->kref);
+	return kref_get_unless_zero(&rcd->kref);
 }
 
 /**
@@ -327,7 +329,8 @@ struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt)
 	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	if (dd->rcd[ctxt]) {
 		rcd = dd->rcd[ctxt];
-		hfi1_rcd_get(rcd);
+		if (!hfi1_rcd_get(rcd))
+			rcd = NULL;
 	}
 	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 
@@ -372,6 +375,9 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 		rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
 
 		mutex_init(&rcd->exp_mutex);
+		spin_lock_init(&rcd->exp_lock);
+		INIT_LIST_HEAD(&rcd->flow_queue.queue_head);
+		INIT_LIST_HEAD(&rcd->rarr_queue.queue_head);
 
 		hfi1_cdbg(PROC, "setting up context %u\n", rcd->ctxt);
 
@@ -474,6 +480,9 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 						    GFP_KERNEL, numa);
 			if (!rcd->opstats)
 				goto bail;
+
+			/* Initialize TID flow generations for the context */
+			hfi1_kern_init_ctxt_generations(rcd);
 		}
 
 		*context = rcd;
@@ -773,6 +782,8 @@ static void enable_chip(struct hfi1_devdata *dd)
 			rcvmask |= HFI1_RCVCTRL_NO_RHQ_DROP_ENB;
 		if (HFI1_CAP_KGET_MASK(rcd->flags, NODROP_EGR_FULL))
 			rcvmask |= HFI1_RCVCTRL_NO_EGR_DROP_ENB;
+		if (HFI1_CAP_IS_KSET(TID_RDMA))
+			rcvmask |= HFI1_RCVCTRL_TIDFLOW_ENB;
 		hfi1_rcvctrl(dd, rcvmask, rcd);
 		sc_enable(rcd->sc);
 		hfi1_rcd_put(rcd);
@@ -928,6 +939,8 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 		lastfail = hfi1_create_rcvhdrq(dd, rcd);
 		if (!lastfail)
 			lastfail = hfi1_setup_eagerbufs(rcd);
+		if (!lastfail)
+			lastfail = hfi1_kern_exp_rcv_init(rcd, reinit);
 		if (lastfail) {
 			dd_dev_err(dd,
 				   "failed to allocate kernel ctxt's rcvhdrq and/or egr bufs\n");
@@ -1498,6 +1511,13 @@ static int __init hfi1_mod_init(void)
 	/* sanitize link CRC options */
 	link_crc_mask &= SUPPORTED_CRCS;
 
+	ret = opfn_init();
+	if (ret < 0) {
+		pr_err("Failed to allocate opfn_wq");
+		goto bail_dev;
+	}
+
+	hfi1_compute_tid_rdma_flow_wt();
 	/*
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.
@@ -1528,6 +1548,7 @@ module_init(hfi1_mod_init);
 static void __exit hfi1_mod_cleanup(void)
 {
 	pci_unregister_driver(&hfi1_pci_driver);
+	opfn_exit();
 	node_affinity_destroy_all();
 	hfi1_dbg_exit();
 
@@ -1582,7 +1603,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 		struct hfi1_ctxtdata *rcd = dd->rcd[ctxt];
 
 		if (rcd) {
-			hfi1_clear_tids(rcd);
+			hfi1_free_ctxt_rcv_groups(rcd);
 			hfi1_free_ctxt(rcd);
 		}
 	}