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

Pull rdma fixes from Jason Gunthorpe:
 "Quite a few small bug fixes old and new, also Doug Ledford is retiring
  now, we thank him for his work. Details:

   - Use after free in rxe

   - mlx5 DM regression

   - hns bugs triggred by device reset

   - Two fixes for CONFIG_DEBUG_PREEMPT

   - Several longstanding corner case bugs in hfi1

   - Two irdma data path bugs in rare cases and some memory issues"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/irdma: Don't arm the CQ more than two times if no CE for this CQ
  RDMA/irdma: Report correct WC errors
  RDMA/irdma: Fix a potential memory allocation issue in 'irdma_prm_add_pble_mem()'
  RDMA/irdma: Fix a user-after-free in add_pble_prm
  IB/hfi1: Fix leak of rcvhdrtail_dummy_kvaddr
  IB/hfi1: Fix early init panic
  IB/hfi1: Insure use of smp_processor_id() is preempt disabled
  IB/hfi1: Correct guard on eager buffer deallocation
  RDMA/rtrs: Call {get,put}_cpu_ptr to silence a debug kernel warning
  RDMA/hns: Do not destroy QP resources in the hw resetting phase
  RDMA/hns: Do not halt commands during reset until later
  Remove Doug Ledford from MAINTAINERS
  RDMA/mlx5: Fix releasing unallocated memory in dereg MR flow
  RDMA: Fix use-after-free in rxe_queue_cleanup

Author: torvalds

MAINTAINERS

@@ -9329,7 +9329,6 @@ S:	Maintained
 F:	drivers/iio/pressure/dps310.c
 
 INFINIBAND SUBSYSTEM
-M:	Doug Ledford <dledford@redhat.com>
 M:	Jason Gunthorpe <jgg@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported

drivers/infiniband/hw/hfi1/chip.c

@@ -8415,6 +8415,8 @@ static void receive_interrupt_common(struct hfi1_ctxtdata *rcd)
  */
 static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
 {
+	if (!rcd->rcvhdrq)
+		return;
 	clear_recv_intr(rcd);
 	if (check_packet_present(rcd))
 		force_recv_intr(rcd);

drivers/infiniband/hw/hfi1/driver.c

@@ -1012,6 +1012,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 	struct hfi1_packet packet;
 	int skip_pkt = 0;
 
+	if (!rcd->rcvhdrq)
+		return RCV_PKT_OK;
 	/* Control context will always use the slow path interrupt handler */
 	needset = (rcd->ctxt == HFI1_CTRL_CTXT) ? 0 : 1;
 

drivers/infiniband/hw/hfi1/init.c

@@ -113,7 +113,6 @@ static int hfi1_create_kctxt(struct hfi1_devdata *dd,
 	rcd->fast_handler = get_dma_rtail_setting(rcd) ?
 				handle_receive_interrupt_dma_rtail :
 				handle_receive_interrupt_nodma_rtail;
-	rcd->slow_handler = handle_receive_interrupt;
 
 	hfi1_set_seq_cnt(rcd, 1);
 
@@ -334,6 +333,8 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 		rcd->numa_id = numa;
 		rcd->rcv_array_groups = dd->rcv_entries.ngroups;
 		rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
+		rcd->slow_handler = handle_receive_interrupt;
+		rcd->do_interrupt = rcd->slow_handler;
 		rcd->msix_intr = CCE_NUM_MSIX_VECTORS;
 
 		mutex_init(&rcd->exp_mutex);
@@ -874,18 +875,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 	if (ret)
 		goto done;
 
-	/* allocate dummy tail memory for all receive contexts */
-	dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
-							 sizeof(u64),
-							 &dd->rcvhdrtail_dummy_dma,
-							 GFP_KERNEL);
-
-	if (!dd->rcvhdrtail_dummy_kvaddr) {
-		dd_dev_err(dd, "cannot allocate dummy tail memory\n");
-		ret = -ENOMEM;
-		goto done;
-	}
-
 	/* dd->rcd can be NULL if early initialization failed */
 	for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) {
 		/*
@@ -898,8 +887,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 		if (!rcd)
 			continue;
 
-		rcd->do_interrupt = &handle_receive_interrupt;
-
 		lastfail = hfi1_create_rcvhdrq(dd, rcd);
 		if (!lastfail)
 			lastfail = hfi1_setup_eagerbufs(rcd);
@@ -1120,7 +1107,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 	rcd->egrbufs.rcvtids = NULL;
 
 	for (e = 0; e < rcd->egrbufs.alloced; e++) {
-		if (rcd->egrbufs.buffers[e].dma)
+		if (rcd->egrbufs.buffers[e].addr)
 			dma_free_coherent(&dd->pcidev->dev,
 					  rcd->egrbufs.buffers[e].len,
 					  rcd->egrbufs.buffers[e].addr,
@@ -1201,6 +1188,11 @@ void hfi1_free_devdata(struct hfi1_devdata *dd)
 	dd->tx_opstats    = NULL;
 	kfree(dd->comp_vect);
 	dd->comp_vect = NULL;
+	if (dd->rcvhdrtail_dummy_kvaddr)
+		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
+				  (void *)dd->rcvhdrtail_dummy_kvaddr,
+				  dd->rcvhdrtail_dummy_dma);
+	dd->rcvhdrtail_dummy_kvaddr = NULL;
 	sdma_clean(dd, dd->num_sdma);
 	rvt_dealloc_device(&dd->verbs_dev.rdi);
 }
@@ -1298,6 +1290,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 		goto bail;
 	}
 
+	/* allocate dummy tail memory for all receive contexts */
+	dd->rcvhdrtail_dummy_kvaddr =
+		dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64),
+				   &dd->rcvhdrtail_dummy_dma, GFP_KERNEL);
+	if (!dd->rcvhdrtail_dummy_kvaddr) {
+		ret = -ENOMEM;
+		goto bail;
+	}
+
 	atomic_set(&dd->ipoib_rsm_usr_num, 0);
 	return dd;
 
@@ -1505,13 +1506,6 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 
 	free_credit_return(dd);
 
-	if (dd->rcvhdrtail_dummy_kvaddr) {
-		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
-				  (void *)dd->rcvhdrtail_dummy_kvaddr,
-				  dd->rcvhdrtail_dummy_dma);
-		dd->rcvhdrtail_dummy_kvaddr = NULL;
-	}
-
 	/*
 	 * Free any resources still in use (usually just kernel contexts)
 	 * at unload; we do for ctxtcnt, because that's what we allocate.

drivers/infiniband/hw/hfi1/sdma.c

@@ -838,8 +838,8 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 	if (current->nr_cpus_allowed != 1)
 		goto out;
 
-	cpu_id = smp_processor_id();
 	rcu_read_lock();
+	cpu_id = smp_processor_id();
 	rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id,
 				     sdma_rht_params);
 

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -33,6 +33,7 @@
 #include <linux/acpi.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <net/addrconf.h>
@@ -1050,9 +1051,14 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev,
 					unsigned long instance_stage,
 					unsigned long reset_stage)
 {
+#define HW_RESET_TIMEOUT_US 1000000
+#define HW_RESET_SLEEP_US 1000
+
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hnae3_handle *handle = priv->handle;
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	unsigned long val;
+	int ret;
 
 	/* When hardware reset is detected, we should stop sending mailbox&cmq&
 	 * doorbell to hardware. If now in .init_instance() function, we should
@@ -1064,7 +1070,11 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev,
 	 * again.
 	 */
 	hr_dev->dis_db = true;
-	if (!ops->get_hw_reset_stat(handle))
+
+	ret = read_poll_timeout(ops->ae_dev_reset_cnt, val,
+				val > hr_dev->reset_cnt, HW_RESET_SLEEP_US,
+				HW_RESET_TIMEOUT_US, false, handle);
+	if (!ret)
 		hr_dev->is_reset = true;
 
 	if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT ||
@@ -6387,10 +6397,8 @@ static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)
 	if (!hr_dev)
 		return 0;
 
-	hr_dev->is_reset = true;
 	hr_dev->active = false;
 	hr_dev->dis_db = true;
-
 	hr_dev->state = HNS_ROCE_DEVICE_STATE_RST_DOWN;
 
 	return 0;

drivers/infiniband/hw/irdma/hw.c

@@ -60,6 +60,8 @@ static void irdma_iwarp_ce_handler(struct irdma_sc_cq *iwcq)
 {
 	struct irdma_cq *cq = iwcq->back_cq;
 
+	if (!cq->user_mode)
+		cq->armed = false;
 	if (cq->ibcq.comp_handler)
 		cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 }
@@ -146,6 +148,7 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 		qp->flush_code = FLUSH_PROT_ERR;
 		break;
 	case IRDMA_AE_AMP_BAD_QP:
+	case IRDMA_AE_WQE_UNEXPECTED_OPCODE:
 		qp->flush_code = FLUSH_LOC_QP_OP_ERR;
 		break;
 	case IRDMA_AE_AMP_BAD_STAG_KEY:
@@ -156,7 +159,6 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 	case IRDMA_AE_PRIV_OPERATION_DENIED:
 	case IRDMA_AE_IB_INVALID_REQUEST:
 	case IRDMA_AE_IB_REMOTE_ACCESS_ERROR:
-	case IRDMA_AE_IB_REMOTE_OP_ERROR:
 		qp->flush_code = FLUSH_REM_ACCESS_ERR;
 		qp->event_type = IRDMA_QP_EVENT_ACCESS_ERR;
 		break;
@@ -184,6 +186,9 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 	case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS:
 		qp->flush_code = FLUSH_MW_BIND_ERR;
 		break;
+	case IRDMA_AE_IB_REMOTE_OP_ERROR:
+		qp->flush_code = FLUSH_REM_OP_ERR;
+		break;
 	default:
 		qp->flush_code = FLUSH_FATAL_ERR;
 		break;

drivers/infiniband/hw/irdma/main.h

@@ -542,6 +542,7 @@ int irdma_ah_cqp_op(struct irdma_pci_f *rf, struct irdma_sc_ah *sc_ah, u8 cmd,
 		    void (*callback_fcn)(struct irdma_cqp_request *cqp_request),
 		    void *cb_param);
 void irdma_gsi_ud_qp_ah_cb(struct irdma_cqp_request *cqp_request);
+bool irdma_cq_empty(struct irdma_cq *iwcq);
 int irdma_inetaddr_event(struct notifier_block *notifier, unsigned long event,
 			 void *ptr);
 int irdma_inet6addr_event(struct notifier_block *notifier, unsigned long event,

drivers/infiniband/hw/irdma/pble.c

@@ -25,8 +25,7 @@ void irdma_destroy_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 		list_del(&chunk->list);
 		if (chunk->type == PBLE_SD_PAGED)
 			irdma_pble_free_paged_mem(chunk);
-		if (chunk->bitmapbuf)
-			kfree(chunk->bitmapmem.va);
+		bitmap_free(chunk->bitmapbuf);
 		kfree(chunk->chunkmem.va);
 	}
 }
@@ -283,7 +282,6 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 		  "PBLE: next_fpm_addr = %llx chunk_size[%llu] = 0x%llx\n",
 		  pble_rsrc->next_fpm_addr, chunk->size, chunk->size);
 	pble_rsrc->unallocated_pble -= (u32)(chunk->size >> 3);
-	list_add(&chunk->list, &pble_rsrc->pinfo.clist);
 	sd_reg_val = (sd_entry_type == IRDMA_SD_TYPE_PAGED) ?
 			     sd_entry->u.pd_table.pd_page_addr.pa :
 			     sd_entry->u.bp.addr.pa;
@@ -295,12 +293,12 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 			goto error;
 	}
 
+	list_add(&chunk->list, &pble_rsrc->pinfo.clist);
 	sd_entry->valid = true;
 	return 0;
 
 error:
-	if (chunk->bitmapbuf)
-		kfree(chunk->bitmapmem.va);
+	bitmap_free(chunk->bitmapbuf);
 	kfree(chunk->chunkmem.va);
 
 	return ret_code;

drivers/infiniband/hw/irdma/pble.h

@@ -78,7 +78,6 @@ struct irdma_chunk {
 	u32 pg_cnt;
 	enum irdma_alloc_type type;
 	struct irdma_sc_dev *dev;
-	struct irdma_virt_mem bitmapmem;
 	struct irdma_virt_mem chunkmem;
 };