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()
  ...

21 files changed, 118 insertions, 78 deletions

diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 97d71e49c092..fb52b669bfce 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -56,7 +56,7 @@
  * rvt_cq_enter - add a new entry to the completion queue
  * @cq: completion queue
  * @entry: work completion entry to add
- * @sig: true if @entry is solicited
+ * @solicited: true if @entry is solicited
  *
  * This may be called with qp->s_lock held.
  */
@@ -101,8 +101,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].opcode = entry->opcode;
 		wc->uqueue[head].vendor_err = entry->vendor_err;
 		wc->uqueue[head].byte_len = entry->byte_len;
-		wc->uqueue[head].ex.imm_data =
-			(__u32 __force)entry->ex.imm_data;
+		wc->uqueue[head].ex.imm_data = entry->ex.imm_data;
 		wc->uqueue[head].qp_num = entry->qp->qp_num;
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
@@ -198,7 +197,7 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
 		return ERR_PTR(-EINVAL);
 
 	/* Allocate the completion queue structure. */
-	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, rdi->dparms.node);
 	if (!cq)
 		return ERR_PTR(-ENOMEM);
 
@@ -214,7 +213,9 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
 		sz += sizeof(struct ib_uverbs_wc) * (entries + 1);
 	else
 		sz += sizeof(struct ib_wc) * (entries + 1);
-	wc = vmalloc_user(sz);
+	wc = udata ?
+		vmalloc_user(sz) :
+		vzalloc_node(sz, rdi->dparms.node);
 	if (!wc) {
 		ret = ERR_PTR(-ENOMEM);
 		goto bail_cq;
@@ -369,7 +370,9 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 		sz += sizeof(struct ib_uverbs_wc) * (cqe + 1);
 	else
 		sz += sizeof(struct ib_wc) * (cqe + 1);
-	wc = vmalloc_user(sz);
+	wc = udata ?
+		vmalloc_user(sz) :
+		vzalloc_node(sz, rdi->dparms.node);
 	if (!wc)
 		return -ENOMEM;
 
diff --git a/drivers/infiniband/sw/rdmavt/mcast.c b/drivers/infiniband/sw/rdmavt/mcast.c
index b3a38c5e4cad..dd11c6fcd060 100644
--- a/drivers/infiniband/sw/rdmavt/mcast.c
+++ b/drivers/infiniband/sw/rdmavt/mcast.c
@@ -272,7 +272,7 @@ bail:
 /**
  * rvt_attach_mcast - attach a qp to a multicast group
  * @ibqp: Infiniband qp
- * @igd: multicast guid
+ * @gid: multicast guid
  * @lid: multicast lid
  *
  * Return: 0 on success
@@ -335,7 +335,7 @@ bail_mcast:
 /**
  * rvt_detach_mcast - remove a qp from a multicast group
  * @ibqp: Infiniband qp
- * @igd: multicast guid
+ * @gid: multicast guid
  * @lid: multicast lid
  *
  * Return: 0 on success
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 42713511b53b..1b2e5362a3ff 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -768,7 +768,7 @@ bail:
 
 /**
  * rvt_map_phys_fmr - set up a fast memory region
- * @ibmfr: the fast memory region to set up
+ * @ibfmr: the fast memory region to set up
  * @page_list: the list of pages to associate with the fast memory region
  * @list_len: the number of pages to associate with the fast memory region
  * @iova: the virtual address of the start of the fast memory region
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index eae84c216e2f..c82e6bb3d77c 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -269,7 +269,7 @@ no_qp_table:
 
 /**
  * free_all_qps - check for QPs still in use
- * @qpt: the QP table to empty
+ * @rdi: rvt device info structure
  *
  * There should not be any QPs still in use.
  * Free memory for table.
@@ -335,9 +335,9 @@ static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
 /**
  * alloc_qpn - Allocate the next available qpn or zero/one for QP type
  *	       IB_QPT_SMI/IB_QPT_GSI
- *@rdi:	rvt device info structure
- *@qpt: queue pair number table pointer
- *@port_num: IB port number, 1 based, comes from core
+ * @rdi: rvt device info structure
+ * @qpt: queue pair number table pointer
+ * @port_num: IB port number, 1 based, comes from core
  *
  * Return: The queue pair number
  */
@@ -1650,9 +1650,9 @@ static inline int rvt_qp_valid_operation(
 
 /**
  * rvt_qp_is_avail - determine queue capacity
- * @qp - the qp
- * @rdi - the rdmavt device
- * @reserved_op - is reserved operation
+ * @qp: the qp
+ * @rdi: the rdmavt device
+ * @reserved_op: is reserved operation
  *
  * This assumes the s_hlock is held but the s_last
  * qp variable is uncontrolled.
@@ -2074,6 +2074,7 @@ void rvt_add_rnr_timer(struct rvt_qp *qp, u32 aeth)
 	lockdep_assert_held(&qp->s_lock);
 	qp->s_flags |= RVT_S_WAIT_RNR;
 	to = rvt_aeth_to_usec(aeth);
+	trace_rvt_rnrnak_add(qp, to);
 	hrtimer_start(&qp->s_rnr_timer,
 		      ns_to_ktime(1000 * to), HRTIMER_MODE_REL);
 }
@@ -2103,17 +2104,14 @@ EXPORT_SYMBOL(rvt_stop_rc_timers);
  * stop an rnr timer and return if the timer
  * had been pending.
  */
-static int rvt_stop_rnr_timer(struct rvt_qp *qp)
+static void rvt_stop_rnr_timer(struct rvt_qp *qp)
 {
-	int rval = 0;
-
 	lockdep_assert_held(&qp->s_lock);
 	/* Remove QP from rnr timer */
 	if (qp->s_flags & RVT_S_WAIT_RNR) {
 		qp->s_flags &= ~RVT_S_WAIT_RNR;
-		rval = hrtimer_try_to_cancel(&qp->s_rnr_timer);
+		trace_rvt_rnrnak_stop(qp, 0);
 	}
-	return rval;
 }
 
 /**
@@ -2166,6 +2164,7 @@ enum hrtimer_restart rvt_rc_rnr_retry(struct hrtimer *t)
 
 	spin_lock_irqsave(&qp->s_lock, flags);
 	rvt_stop_rnr_timer(qp);
+	trace_rvt_rnrnak_timeout(qp, 0);
 	rdi->driver_f.schedule_send(qp);
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return HRTIMER_NORESTART;
@@ -2174,8 +2173,8 @@ EXPORT_SYMBOL(rvt_rc_rnr_retry);
 
 /**
  * rvt_qp_iter_init - initial for QP iteration
- * @rdi - rvt devinfo
- * @v - u64 value
+ * @rdi: rvt devinfo
+ * @v: u64 value
  *
  * This returns an iterator suitable for iterating QPs
  * in the system.
diff --git a/drivers/infiniband/sw/rdmavt/srq.c b/drivers/infiniband/sw/rdmavt/srq.c
index f7c48e9023de..3707952b4364 100644
--- a/drivers/infiniband/sw/rdmavt/srq.c
+++ b/drivers/infiniband/sw/rdmavt/srq.c
@@ -90,7 +90,7 @@ struct ib_srq *rvt_create_srq(struct ib_pd *ibpd,
 	    srq_init_attr->attr.max_wr > dev->dparms.props.max_srq_wr)
 		return ERR_PTR(-EINVAL);
 
-	srq = kmalloc(sizeof(*srq), GFP_KERNEL);
+	srq = kzalloc_node(sizeof(*srq), GFP_KERNEL, dev->dparms.node);
 	if (!srq)
 		return ERR_PTR(-ENOMEM);
 
@@ -101,7 +101,10 @@ struct ib_srq *rvt_create_srq(struct ib_pd *ibpd,
 	srq->rq.max_sge = srq_init_attr->attr.max_sge;
 	sz = sizeof(struct ib_sge) * srq->rq.max_sge +
 		sizeof(struct rvt_rwqe);
-	srq->rq.wq = vmalloc_user(sizeof(struct rvt_rwq) + srq->rq.size * sz);
+	srq->rq.wq = udata ?
+		vmalloc_user(sizeof(struct rvt_rwq) + srq->rq.size * sz) :
+		vzalloc_node(sizeof(struct rvt_rwq) + srq->rq.size * sz,
+			     dev->dparms.node);
 	if (!srq->rq.wq) {
 		ret = ERR_PTR(-ENOMEM);
 		goto bail_srq;
@@ -129,16 +132,12 @@ struct ib_srq *rvt_create_srq(struct ib_pd *ibpd,
 			ret = ERR_PTR(err);
 			goto bail_ip;
 		}
-	} else {
-		srq->ip = NULL;
 	}
 
 	/*
 	 * ib_create_srq() will initialize srq->ibsrq.
 	 */
 	spin_lock_init(&srq->rq.lock);
-	srq->rq.wq->head = 0;
-	srq->rq.wq->tail = 0;
 	srq->limit = srq_init_attr->attr.srq_limit;
 
 	spin_lock(&dev->n_srqs_lock);
@@ -200,7 +199,10 @@ int rvt_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		sz = sizeof(struct rvt_rwqe) +
 			srq->rq.max_sge * sizeof(struct ib_sge);
 		size = attr->max_wr + 1;
-		wq = vmalloc_user(sizeof(struct rvt_rwq) + size * sz);
+		wq = udata ?
+			vmalloc_user(sizeof(struct rvt_rwq) + size * sz) :
+			vzalloc_node(sizeof(struct rvt_rwq) + size * sz,
+				     dev->dparms.node);
 		if (!wq)
 			return -ENOMEM;
 
diff --git a/drivers/infiniband/sw/rdmavt/trace.h b/drivers/infiniband/sw/rdmavt/trace.h
index bb4b1e710f22..36ddbd291ee0 100644
--- a/drivers/infiniband/sw/rdmavt/trace.h
+++ b/drivers/infiniband/sw/rdmavt/trace.h
@@ -45,8 +45,8 @@
  *
  */
 
-#define RDI_DEV_ENTRY(rdi)   __string(dev, rdi->driver_f.get_card_name(rdi))
-#define RDI_DEV_ASSIGN(rdi)  __assign_str(dev, rdi->driver_f.get_card_name(rdi))
+#define RDI_DEV_ENTRY(rdi)   __string(dev, rvt_get_ibdev_name(rdi))
+#define RDI_DEV_ASSIGN(rdi)  __assign_str(dev, rvt_get_ibdev_name(rdi))
 
 #include "trace_rvt.h"
 #include "trace_qp.h"
diff --git a/drivers/infiniband/sw/rdmavt/trace_qp.h b/drivers/infiniband/sw/rdmavt/trace_qp.h
index 4c77a3119bda..efc9d814b032 100644
--- a/drivers/infiniband/sw/rdmavt/trace_qp.h
+++ b/drivers/infiniband/sw/rdmavt/trace_qp.h
@@ -85,6 +85,48 @@ DEFINE_EVENT(rvt_qphash_template, rvt_qpremove,
 	TP_PROTO(struct rvt_qp *qp, u32 bucket),
 	TP_ARGS(qp, bucket));
 
+DECLARE_EVENT_CLASS(
+	rvt_rnrnak_template,
+	TP_PROTO(struct rvt_qp *qp, u32 to),
+	TP_ARGS(qp, to),
+	TP_STRUCT__entry(
+		RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device))
+		__field(u32, qpn)
+		__field(void *, hrtimer)
+		__field(u32, s_flags)
+		__field(u32, to)
+	),
+	TP_fast_assign(
+		RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device))
+		__entry->qpn = qp->ibqp.qp_num;
+		__entry->hrtimer = &qp->s_rnr_timer;
+		__entry->s_flags = qp->s_flags;
+		__entry->to = to;
+	),
+	TP_printk(
+		"[%s] qpn 0x%x hrtimer 0x%p s_flags 0x%x timeout %u us",
+		__get_str(dev),
+		__entry->qpn,
+		__entry->hrtimer,
+		__entry->s_flags,
+		__entry->to
+	)
+);
+
+DEFINE_EVENT(
+	rvt_rnrnak_template, rvt_rnrnak_add,
+	TP_PROTO(struct rvt_qp *qp, u32 to),
+	TP_ARGS(qp, to));
+
+DEFINE_EVENT(
+	rvt_rnrnak_template, rvt_rnrnak_timeout,
+	TP_PROTO(struct rvt_qp *qp, u32 to),
+	TP_ARGS(qp, to));
+
+DEFINE_EVENT(
+	rvt_rnrnak_template, rvt_rnrnak_stop,
+	TP_PROTO(struct rvt_qp *qp, u32 to),
+	TP_ARGS(qp, to));
 
 #endif /* __RVT_TRACE_QP_H */
 
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 64bdd442078a..a4553b2b3696 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -224,7 +224,8 @@ static int rvt_modify_port(struct ib_device *ibdev, u8 port_num,
  * rvt_query_pkey - Return a pkey from the table at a given index
  * @ibdev: Verbs IB dev
  * @port_num: Port number, 1 based from ib core
- * @intex: Index into pkey table
+ * @index: Index into pkey table
+ * @pkey: returned pkey from the port pkey table
  *
  * Return: 0 on failure pkey otherwise
  */
@@ -255,7 +256,7 @@ static int rvt_query_pkey(struct ib_device *ibdev, u8 port_num, u16 index,
  * rvt_query_gid - Return a gid from the table
  * @ibdev: Verbs IB dev
  * @port_num: Port number, 1 based from ib core
- * @index: = Index in table
+ * @guid_index: Index in table
  * @gid: Gid to return
  *
  * Return: 0 on success
@@ -297,8 +298,8 @@ static inline struct rvt_ucontext *to_iucontext(struct ib_ucontext
 
 /**
  * rvt_alloc_ucontext - Allocate a user context
- * @ibdev: Vers IB dev
- * @data: User data allocated
+ * @ibdev: Verbs IB dev
+ * @udata: User data allocated
  */
 static struct ib_ucontext *rvt_alloc_ucontext(struct ib_device *ibdev,
 					      struct ib_udata *udata)
@@ -413,7 +414,6 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb)
 		 * 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;
diff --git a/drivers/infiniband/sw/rdmavt/vt.h b/drivers/infiniband/sw/rdmavt/vt.h
index f363505312be..8823b2e7aac6 100644
--- a/drivers/infiniband/sw/rdmavt/vt.h
+++ b/drivers/infiniband/sw/rdmavt/vt.h
@@ -63,19 +63,19 @@
 
 #define rvt_pr_info(rdi, fmt, ...) \
 	__rvt_pr_info(rdi->driver_f.get_pci_dev(rdi), \
-		      rdi->driver_f.get_card_name(rdi), \
+		      rvt_get_ibdev_name(rdi), \
 		      fmt, \
 		      ##__VA_ARGS__)
 
 #define rvt_pr_warn(rdi, fmt, ...) \
 	__rvt_pr_warn(rdi->driver_f.get_pci_dev(rdi), \
-		      rdi->driver_f.get_card_name(rdi), \
+		      rvt_get_ibdev_name(rdi), \
 		      fmt, \
 		      ##__VA_ARGS__)
 
 #define rvt_pr_err(rdi, fmt, ...) \
 	__rvt_pr_err(rdi->driver_f.get_pci_dev(rdi), \
-		     rdi->driver_f.get_card_name(rdi), \
+		     rvt_get_ibdev_name(rdi), \
 		     fmt, \
 		     ##__VA_ARGS__)
 
diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index 320bffc980d8..bad4a576d7cf 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -1,8 +1,8 @@
 config RDMA_RXE
 	tristate "Software RDMA over Ethernet (RoCE) driver"
 	depends on INET && PCI && INFINIBAND
-	depends on NET_UDP_TUNNEL
-	depends on CRYPTO_CRC32
+	select NET_UDP_TUNNEL
+	select CRYPTO_CRC32
 	select DMA_VIRT_OPS
 	---help---
 	This driver implements the InfiniBand RDMA transport over
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 8c3d30b3092d..b7debb6f2eac 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -77,12 +77,6 @@ void rxe_release(struct kref *kref)
 	ib_dealloc_device(&rxe->ib_dev);
 }
 
-void rxe_dev_put(struct rxe_dev *rxe)
-{
-	kref_put(&rxe->ref_cnt, rxe_release);
-}
-EXPORT_SYMBOL_GPL(rxe_dev_put);
-
 /* initialize rxe device parameters */
 static int rxe_init_device_param(struct rxe_dev *rxe)
 {
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index 6447d736d5a4..7d232611303f 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -57,6 +57,7 @@
 #include "rxe_hdr.h"
 #include "rxe_param.h"
 #include "rxe_verbs.h"
+#include "rxe_loc.h"
 
 #define RXE_UVERBS_ABI_VERSION		(1)
 
@@ -95,7 +96,10 @@ void rxe_remove_all(void);
 
 int rxe_rcv(struct sk_buff *skb);
 
-void rxe_dev_put(struct rxe_dev *rxe);
+static inline void rxe_dev_put(struct rxe_dev *rxe)
+{
+	kref_put(&rxe->ref_cnt, rxe_release);
+}
 struct rxe_dev *net_to_rxe(struct net_device *ndev);
 struct rxe_dev *get_rxe_by_name(const char *name);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index d7472a442a2c..96c3a6c5c4b5 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -237,7 +237,6 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
 
 void rxe_release(struct kref *kref);
 
-void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify);
 int rxe_completer(void *arg);
 int rxe_requester(void *arg);
 int rxe_responder(void *arg);
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 59dee10bebcb..159246b03867 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -82,7 +82,7 @@ struct rxe_dev *get_rxe_by_name(const char *name)
 }
 
 
-struct rxe_recv_sockets recv_sockets;
+static struct rxe_recv_sockets recv_sockets;
 
 struct device *rxe_dma_device(struct rxe_dev *rxe)
 {
@@ -452,31 +452,26 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb)
 
 int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
 {
-	struct sk_buff *nskb;
 	struct rxe_av *av;
 	int err;
 
 	av = rxe_get_av(pkt);
 
-	nskb = skb_clone(skb, GFP_ATOMIC);
-	if (!nskb)
-		return -ENOMEM;
-
-	nskb->destructor = rxe_skb_tx_dtor;
-	nskb->sk = pkt->qp->sk->sk;
+	skb->destructor = rxe_skb_tx_dtor;
+	skb->sk = pkt->qp->sk->sk;
 
 	rxe_add_ref(pkt->qp);
 	atomic_inc(&pkt->qp->skb_out);
 
 	if (av->network_type == RDMA_NETWORK_IPV4) {
-		err = ip_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
+		err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	} else if (av->network_type == RDMA_NETWORK_IPV6) {
-		err = ip6_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
+		err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	} else {
 		pr_err("Unknown layer 3 protocol: %d\n", av->network_type);
 		atomic_dec(&pkt->qp->skb_out);
 		rxe_drop_ref(pkt->qp);
-		kfree_skb(nskb);
+		kfree_skb(skb);
 		return -EINVAL;
 	}
 
@@ -485,7 +480,6 @@ int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
 		return -EAGAIN;
 	}
 
-	kfree_skb(skb);
 	return 0;
 }
 
diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
index 1c06b3bfe1b6..728d8c71b36a 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.h
+++ b/drivers/infiniband/sw/rxe/rxe_net.h
@@ -43,7 +43,6 @@ struct rxe_recv_sockets {
 	struct socket *sk6;
 };
 
-extern struct rxe_recv_sockets recv_sockets;
 extern struct notifier_block rxe_net_notifier;
 void rxe_release_udp_tunnel(struct socket *sk);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 4469592b839d..137d6c0c49d4 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -824,9 +824,9 @@ void rxe_qp_destroy(struct rxe_qp *qp)
 }
 
 /* called when the last reference to the qp is dropped */
-void rxe_qp_cleanup(struct rxe_pool_entry *arg)
+static void rxe_qp_do_cleanup(struct work_struct *work)
 {
-	struct rxe_qp *qp = container_of(arg, typeof(*qp), pelem);
+	struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work);
 
 	rxe_drop_all_mcast_groups(qp);
 
@@ -859,3 +859,11 @@ void rxe_qp_cleanup(struct rxe_pool_entry *arg)
 	kernel_sock_shutdown(qp->sk, SHUT_RDWR);
 	sock_release(qp->sk);
 }
+
+/* called when the last reference to the qp is dropped */
+void rxe_qp_cleanup(struct rxe_pool_entry *arg)
+{
+	struct rxe_qp *qp = container_of(arg, typeof(*qp), pelem);
+
+	execute_in_process_context(rxe_qp_do_cleanup, &qp->cleanup_work);
+}
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index fb8c83e055e1..4c3f899241d4 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -336,7 +336,6 @@ static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb)
 {
 	union ib_gid dgid;
 	union ib_gid *pdgid;
-	u16 index;
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
@@ -348,7 +347,7 @@ static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb)
 
 	return ib_find_cached_gid_by_port(&rxe->ib_dev, pdgid,
 					  IB_GID_TYPE_ROCE_UDP_ENCAP,
-					  1, rxe->ndev, &index);
+					  1, rxe->ndev, NULL);
 }
 
 /* rxe_rcv is called from the interface driver */
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 26a7f923045b..7bdaf71b8221 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -594,15 +594,8 @@ int rxe_requester(void *arg)
 	rxe_add_ref(qp);
 
 next_wqe:
-	if (unlikely(!qp->valid)) {
-		rxe_drain_req_pkts(qp, true);
+	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
 		goto exit;
-	}
-
-	if (unlikely(qp->req.state == QP_STATE_ERROR)) {
-		rxe_drain_req_pkts(qp, true);
-		goto exit;
-	}
 
 	if (unlikely(qp->req.state == QP_STATE_RESET)) {
 		qp->req.wqe_index = consumer_index(qp->sq.queue);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 4240866a5331..d37bb9b97569 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -863,8 +863,7 @@ static enum resp_states do_complete(struct rxe_qp *qp,
 
 			if (pkt->mask & RXE_IMMDT_MASK) {
 				uwc->wc_flags |= IB_WC_WITH_IMM;
-				uwc->ex.imm_data =
-					(__u32 __force)immdt_imm(pkt);
+				uwc->ex.imm_data = immdt_imm(pkt);
 			}
 
 			if (pkt->mask & RXE_IETH_MASK) {
@@ -1210,7 +1209,7 @@ static enum resp_states do_class_d1e_error(struct rxe_qp *qp)
 	}
 }
 
-void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
+static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
 {
 	struct sk_buff *skb;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index d03002b9d84d..7210a784abb4 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -814,6 +814,8 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
 			(queue_count(qp->sq.queue) > 1);
 
 	rxe_run_task(&qp->req.task, must_sched);
+	if (unlikely(qp->req.state == QP_STATE_ERROR))
+		rxe_run_task(&qp->comp.task, 1);
 
 	return err;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 0c2dbe45c729..1019f5e7dbdd 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -35,6 +35,7 @@
 #define RXE_VERBS_H
 
 #include <linux/interrupt.h>
+#include <linux/workqueue.h>
 #include <rdma/rdma_user_rxe.h>
 #include "rxe_pool.h"
 #include "rxe_task.h"
@@ -281,6 +282,8 @@ struct rxe_qp {
 	struct timer_list rnr_nak_timer;
 
 	spinlock_t		state_lock; /* guard requester and completer */
+
+	struct execute_work	cleanup_work;
 };
 
 enum rxe_mem_state {