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

Pull RDMA subsystem updates from Jason Gunthorpe:
 "Overall this cycle did not have any major excitement, and did not
  require any shared branch with netdev.

  Lots of driver updates, particularly of the scale-up and performance
  variety. The largest body of core work was Parav's patches fixing and
  restructing some of the core code to make way for future RDMA
  containerization.

  Summary:

   - misc small driver fixups to
     bnxt_re/hfi1/qib/hns/ocrdma/rdmavt/vmw_pvrdma/nes

   - several major feature adds to bnxt_re driver: SRIOV VF RoCE
     support, HugePages support, extended hardware stats support, and
     SRQ support

   - a notable number of fixes to the i40iw driver from debugging scale
     up testing

   - more work to enable the new hip08 chip in the hns driver

   - misc small ULP fixups to srp/srpt//ipoib

   - preparation for srp initiator and target to support the RDMA-CM
     protocol for connections

   - add RDMA-CM support to srp initiator, srp target is still a WIP

   - fixes for a couple of places where ipoib could spam the dmesg log

   - fix encode/decode of FDR/EDR data rates in the core

   - many patches from Parav with ongoing work to clean up
     inconsistencies and bugs in RoCE support around the rdma_cm

   - mlx5 driver support for the userspace features 'thread domain',
     'wallclock timestamps' and 'DV Direct Connected transport'. Support
     for the firmware dual port rocee capability

   - core support for more than 32 rdma devices in the char dev
     allocation

   - kernel doc updates from Randy Dunlap

   - new netlink uAPI for inspecting RDMA objects similar in spirit to 'ss'

   - one minor change to the kobject code acked by Greg KH"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (259 commits)
  RDMA/nldev: Provide detailed QP information
  RDMA/nldev: Provide global resource utilization
  RDMA/core: Add resource tracking for create and destroy PDs
  RDMA/core: Add resource tracking for create and destroy CQs
  RDMA/core: Add resource tracking for create and destroy QPs
  RDMA/restrack: Add general infrastructure to track RDMA resources
  RDMA/core: Save kernel caller name when creating PD and CQ objects
  RDMA/core: Use the MODNAME instead of the function name for pd callers
  RDMA: Move enum ib_cq_creation_flags to uapi headers
  IB/rxe: Change RDMA_RXE kconfig to use select
  IB/qib: remove qib_keys.c
  IB/mthca: remove mthca_user.h
  RDMA/cm: Fix access to uninitialized variable
  RDMA/cma: Use existing netif_is_bond_master function
  IB/core: Avoid SGID attributes query while converting GID from OPA to IB
  RDMA/mlx5: Avoid memory leak in case of XRCD dealloc failure
  IB/umad: Fix use of unprotected device pointer
  IB/iser: Combine substrings for three messages
  IB/iser: Delete an unnecessary variable initialisation in iser_send_data_out()
  IB/iser: Delete an error message for a failed memory allocation in iser_send_data_out()
  ...

1 files changed, 25 insertions, 14 deletions

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index f2ae75fa3128..bc79ca8215d7 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -25,9 +25,10 @@
 #define IB_POLL_FLAGS \
 	(IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS)
 
-static int __ib_process_cq(struct ib_cq *cq, int budget)
+static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc)
 {
 	int i, n, completed = 0;
+	struct ib_wc *wcs = poll_wc ? : cq->wc;
 
 	/*
 	 * budget might be (-1) if the caller does not
@@ -35,9 +36,9 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
 	 * minimum here.
 	 */
 	while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH,
-			budget - completed), cq->wc)) > 0) {
+			budget - completed), wcs)) > 0) {
 		for (i = 0; i < n; i++) {
-			struct ib_wc *wc = &cq->wc[i];
+			struct ib_wc *wc = &wcs[i];
 
 			if (wc->wr_cqe)
 				wc->wr_cqe->done(cq, wc);
@@ -60,18 +61,20 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
  * @cq:		CQ to process
  * @budget:	number of CQEs to poll for
  *
- * This function is used to process all outstanding CQ entries on a
- * %IB_POLL_DIRECT CQ.  It does not offload CQ processing to a different
- * context and does not ask for completion interrupts from the HCA.
+ * This function is used to process all outstanding CQ entries.
+ * It does not offload CQ processing to a different context and does
+ * not ask for completion interrupts from the HCA.
+ * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger
+ * concurrent processing.
  *
  * Note: do not pass -1 as %budget unless it is guaranteed that the number
  * of completions that will be processed is small.
  */
 int ib_process_cq_direct(struct ib_cq *cq, int budget)
 {
-	WARN_ON_ONCE(cq->poll_ctx != IB_POLL_DIRECT);
+	struct ib_wc wcs[IB_POLL_BATCH];
 
-	return __ib_process_cq(cq, budget);
+	return __ib_process_cq(cq, budget, wcs);
 }
 EXPORT_SYMBOL(ib_process_cq_direct);
 
@@ -85,7 +88,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 	struct ib_cq *cq = container_of(iop, struct ib_cq, iop);
 	int completed;
 
-	completed = __ib_process_cq(cq, budget);
+	completed = __ib_process_cq(cq, budget, NULL);
 	if (completed < budget) {
 		irq_poll_complete(&cq->iop);
 		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
@@ -105,7 +108,7 @@ static void ib_cq_poll_work(struct work_struct *work)
 	struct ib_cq *cq = container_of(work, struct ib_cq, work);
 	int completed;
 
-	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE);
+	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, NULL);
 	if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
 	    ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
 		queue_work(ib_comp_wq, &cq->work);
@@ -117,20 +120,22 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 }
 
 /**
- * ib_alloc_cq - allocate a completion queue
+ * __ib_alloc_cq - allocate a completion queue
  * @dev:		device to allocate the CQ for
  * @private:		driver private data, accessible from cq->cq_context
  * @nr_cqe:		number of CQEs to allocate
  * @comp_vector:	HCA completion vectors for this CQ
  * @poll_ctx:		context to poll the CQ from.
+ * @caller:		module owner name.
  *
  * This is the proper interface to allocate a CQ for in-kernel users. A
  * CQ allocated with this interface will automatically be polled from the
  * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
  * to use this CQ abstraction.
  */
-struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
-		int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx)
+struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private,
+			    int nr_cqe, int comp_vector,
+			    enum ib_poll_context poll_ctx, const char *caller)
 {
 	struct ib_cq_init_attr cq_attr = {
 		.cqe		= nr_cqe,
@@ -154,6 +159,10 @@ struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
 	if (!cq->wc)
 		goto out_destroy_cq;
 
+	cq->res.type = RDMA_RESTRACK_CQ;
+	cq->res.kern_name = caller;
+	rdma_restrack_add(&cq->res);
+
 	switch (cq->poll_ctx) {
 	case IB_POLL_DIRECT:
 		cq->comp_handler = ib_cq_completion_direct;
@@ -178,11 +187,12 @@ struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
 
 out_free_wc:
 	kfree(cq->wc);
+	rdma_restrack_del(&cq->res);
 out_destroy_cq:
 	cq->device->destroy_cq(cq);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(ib_alloc_cq);
+EXPORT_SYMBOL(__ib_alloc_cq);
 
 /**
  * ib_free_cq - free a completion queue
@@ -209,6 +219,7 @@ void ib_free_cq(struct ib_cq *cq)
 	}
 
 	kfree(cq->wc);
+	rdma_restrack_del(&cq->res);
 	ret = cq->device->destroy_cq(cq);
 	WARN_ON_ONCE(ret);
 }