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

…t/rdma/rdma

Pull more rdma updates from Doug Ledford:
 "Items of note:

   - two patches fix a regression in the 4.15 kernel. The 4.14 kernel
     worked fine with NVMe over Fabrics and mlx5 adapters. That broke in
     4.15. The fix is here.

   - one of the patches (the endian notation patch from Lijun) looks
     like a lot of lines of change, but it's mostly mechanical in
     nature. It amounts to the biggest chunk of change in it (it's about
     2/3rds of the overall pull request).

  Summary:

   - Clean up some function signatures in rxe for clarity

   - Tidy the RDMA netlink header to remove unimplemented constants

   - bnxt_re driver fixes, one is a regression this window.

   - Minor hns driver fixes

   - Various fixes from Dan Carpenter and his tool

   - Fix IRQ cleanup race in HFI1

   - HF1 performance optimizations and a fix to report counters in the right units

   - Fix for an IPoIB startup sequence race with the external manager

   - Oops fix for the new kabi path

   - Endian cleanups for hns

   - Fix for mlx5 related to the new automatic affinity support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (38 commits)
  net/mlx5: increase async EQ to avoid EQ overrun
  mlx5: fix mlx5_get_vector_affinity to start from completion vector 0
  RDMA/hns: Fix the endian problem for hns
  IB/uverbs: Use the standard kConfig format for experimental
  IB: Update references to libibverbs
  IB/hfi1: Add 16B rcvhdr trace support
  IB/hfi1: Convert kzalloc_node and kcalloc to use kcalloc_node
  IB/core: Avoid a potential OOPs for an unused optional parameter
  IB/core: Map iWarp AH type to undefined in rdma_ah_find_type
  IB/ipoib: Fix for potential no-carrier state
  IB/hfi1: Show fault stats in both TX and RX directions
  IB/hfi1: Remove blind constants from 16B update
  IB/hfi1: Convert PortXmitWait/PortVLXmitWait counters to flit times
  IB/hfi1: Do not override given pcie_pset value
  IB/hfi1: Optimize process_receive_ib()
  IB/hfi1: Remove unnecessary fecn and becn fields
  IB/hfi1: Look up ibport using a pointer in receive path
  IB/hfi1: Optimize packet type comparison using 9B and bypass code paths
  IB/hfi1: Compute BTH only for RDMA_WRITE_LAST/SEND_LAST packet
  IB/hfi1: Remove dependence on qp->s_hdrwords
  ...

Documentation/infiniband/user_verbs.txt

@@ -5,7 +5,7 @@ USERSPACE VERBS ACCESS
   described in chapter 11 of the InfiniBand Architecture Specification.
 
   To use the verbs, the libibverbs library, available from
-  http://www.openfabrics.org/, is required.  libibverbs contains a
+  https://github.com/linux-rdma/rdma-core, is required. libibverbs contains a
   device-independent API for using the ib_uverbs interface.
   libibverbs also requires appropriate device-dependent kernel and
   userspace driver for your InfiniBand hardware.  For example, to use

MAINTAINERS

@@ -6946,7 +6946,7 @@ INFINIBAND SUBSYSTEM
 M:	Doug Ledford <dledford@redhat.com>
 M:	Jason Gunthorpe <jgg@mellanox.com>
 L:	linux-rdma@vger.kernel.org
-W:	http://www.openfabrics.org/
+W:	https://github.com/linux-rdma/rdma-core
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git
 S:	Supported

drivers/infiniband/Kconfig

@@ -20,7 +20,8 @@ config INFINIBAND_USER_MAD
 	  Userspace InfiniBand Management Datagram (MAD) support.  This
 	  is the kernel side of the userspace MAD support, which allows
 	  userspace processes to send and receive MADs. You will also
-	  need libibumad from <http://www.openfabrics.org/downloads/management/>.
+	  need libibumad from rdma-core
+	  <https://github.com/linux-rdma/rdma-core>.
 
 config INFINIBAND_USER_ACCESS
 	tristate "InfiniBand userspace access (verbs and CM)"
@@ -32,10 +33,10 @@ config INFINIBAND_USER_ACCESS
 	  to set up connections and directly access InfiniBand
 	  hardware for fast-path operations.  You will also need
 	  libibverbs, libibcm and a hardware driver library from
-	  <http://www.openfabrics.org/git/>.
+	  rdma-core <https://github.com/linux-rdma/rdma-core>.
 
 config INFINIBAND_EXP_USER_ACCESS
-	bool "Allow experimental support for Infiniband ABI"
+	bool "Enable the full uverbs ioctl interface (EXPERIMENTAL)"
 	depends on INFINIBAND_USER_ACCESS
 	---help---
 	  IOCTL based ABI support for Infiniband. This allows userspace

drivers/infiniband/core/nldev.c

@@ -499,8 +499,10 @@ static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
+	if (!msg) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
 			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_RES_GET),

drivers/infiniband/core/uverbs_std_types.c

@@ -316,7 +316,7 @@ static int uverbs_create_cq_handler(struct ib_device *ib_dev,
 	cq->uobject       = &obj->uobject;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
-	cq->cq_context    = &ev_file->ev_queue;
+	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	obj->uobject.object = cq;
 	obj->uobject.user_handle = user_handle;
 	atomic_set(&cq->usecnt, 0);

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -1314,7 +1314,7 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq)
 		return rc;
 	}
 
-	if (srq->umem && !IS_ERR(srq->umem))
+	if (srq->umem)
 		ib_umem_release(srq->umem);
 	kfree(srq);
 	atomic_dec(&rdev->srq_count);
@@ -1430,11 +1430,8 @@ struct ib_srq *bnxt_re_create_srq(struct ib_pd *ib_pd,
 	return &srq->ib_srq;
 
 fail:
-	if (udata && srq->umem && !IS_ERR(srq->umem)) {
+	if (srq->umem)
 		ib_umem_release(srq->umem);
-		srq->umem = NULL;
-	}
-
 	kfree(srq);
 exit:
 	return ERR_PTR(rc);

drivers/infiniband/hw/bnxt_re/qplib_fp.c

@@ -557,8 +557,10 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 
 	srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq),
 			   GFP_KERNEL);
-	if (!srq->swq)
+	if (!srq->swq) {
+		rc = -ENOMEM;
 		goto fail;
+	}
 
 	RCFW_CMD_PREP(req, CREATE_SRQ, cmd_flags);
 

drivers/infiniband/hw/bnxt_re/qplib_res.c

@@ -705,31 +705,27 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res     *res,
 	dpit->max = dbr_len / PAGE_SIZE;
 
 	dpit->app_tbl = kcalloc(dpit->max, sizeof(void *), GFP_KERNEL);
-	if (!dpit->app_tbl) {
-		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
-		dev_err(&res->pdev->dev,
-			"QPLIB: DPI app tbl allocation failed");
-		return -ENOMEM;
-	}
+	if (!dpit->app_tbl)
+		goto unmap_io;
 
 	bytes = dpit->max >> 3;
 	if (!bytes)
 		bytes = 1;
 
 	dpit->tbl = kmalloc(bytes, GFP_KERNEL);
 	if (!dpit->tbl) {
-		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
 		kfree(dpit->app_tbl);
 		dpit->app_tbl = NULL;
-		dev_err(&res->pdev->dev,
-			"QPLIB: DPI tbl allocation failed for size = %d",
-			bytes);
-		return -ENOMEM;
+		goto unmap_io;
 	}
 
 	memset((u8 *)dpit->tbl, 0xFF, bytes);
 
 	return 0;
+
+unmap_io:
+	pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+	return -ENOMEM;
 }
 
 /* PKEYs */

drivers/infiniband/hw/hfi1/chip.c

@@ -1083,6 +1083,7 @@ static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 static int wait_link_transfer_active(struct hfi1_devdata *dd, int wait_ms);
 static void clear_rsm_rule(struct hfi1_devdata *dd, u8 rule_index);
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6905,6 +6906,32 @@ void handle_freeze(struct work_struct *work)
 	/* no longer frozen */
 }
 
+/**
+ * update_xmit_counters - update PortXmitWait/PortVlXmitWait
+ * counters.
+ * @ppd: info of physical Hfi port
+ * @link_width: new link width after link up or downgrade
+ *
+ * Update the PortXmitWait and PortVlXmitWait counters after
+ * a link up or downgrade event to reflect a link width change.
+ */
+static void update_xmit_counters(struct hfi1_pportdata *ppd, u16 link_width)
+{
+	int i;
+	u16 tx_width;
+	u16 link_speed;
+
+	tx_width = tx_link_width(link_width);
+	link_speed = get_link_speed(ppd->link_speed_active);
+
+	/*
+	 * There are C_VL_COUNT number of PortVLXmitWait counters.
+	 * Adding 1 to C_VL_COUNT to include the PortXmitWait counter.
+	 */
+	for (i = 0; i < C_VL_COUNT + 1; i++)
+		get_xmit_wait_counters(ppd, tx_width, link_speed, i);
+}
+
 /*
  * Handle a link up interrupt from the 8051.
  *
@@ -7526,18 +7553,29 @@ void handle_verify_cap(struct work_struct *work)
 	set_link_state(ppd, HLS_GOING_UP);
 }
 
-/*
- * Apply the link width downgrade enabled policy against the current active
- * link widths.
+/**
+ * apply_link_downgrade_policy - Apply the link width downgrade enabled
+ * policy against the current active link widths.
+ * @ppd: info of physical Hfi port
+ * @refresh_widths: True indicates link downgrade event
+ * @return: True indicates a successful link downgrade. False indicates
+ *	    link downgrade event failed and the link will bounce back to
+ *	    default link width.
  *
- * Called when the enabled policy changes or the active link widths change.
+ * Called when the enabled policy changes or the active link widths
+ * change.
+ * Refresh_widths indicates that a link downgrade occurred. The
+ * link_downgraded variable is set by refresh_widths and
+ * determines the success/failure of the policy application.
  */
-void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
+bool apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
+				 bool refresh_widths)
 {
 	int do_bounce = 0;
 	int tries;
 	u16 lwde;
 	u16 tx, rx;
+	bool link_downgraded = refresh_widths;
 
 	/* use the hls lock to avoid a race with actual link up */
 	tries = 0;
@@ -7571,6 +7609,7 @@ void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
 	    ppd->link_width_downgrade_rx_active == 0) {
 		/* the 8051 reported a dead link as a downgrade */
 		dd_dev_err(ppd->dd, "Link downgrade is really a link down, ignoring\n");
+		link_downgraded = false;
 	} else if (lwde == 0) {
 		/* downgrade is disabled */
 
@@ -7587,6 +7626,7 @@ void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
 				   ppd->link_width_downgrade_tx_active,
 				   ppd->link_width_downgrade_rx_active);
 			do_bounce = 1;
+			link_downgraded = false;
 		}
 	} else if ((lwde & ppd->link_width_downgrade_tx_active) == 0 ||
 		   (lwde & ppd->link_width_downgrade_rx_active) == 0) {
@@ -7598,6 +7638,7 @@ void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
 			   lwde, ppd->link_width_downgrade_tx_active,
 			   ppd->link_width_downgrade_rx_active);
 		do_bounce = 1;
+		link_downgraded = false;
 	}
 
 done:
@@ -7609,6 +7650,8 @@ void apply_link_downgrade_policy(struct hfi1_pportdata *ppd, int refresh_widths)
 		set_link_state(ppd, HLS_DN_OFFLINE);
 		start_link(ppd);
 	}
+
+	return link_downgraded;
 }
 
 /*
@@ -7622,7 +7665,8 @@ void handle_link_downgrade(struct work_struct *work)
 							link_downgrade_work);
 
 	dd_dev_info(ppd->dd, "8051: Link width downgrade\n");
-	apply_link_downgrade_policy(ppd, 1);
+	if (apply_link_downgrade_policy(ppd, true))
+		update_xmit_counters(ppd, ppd->link_width_downgrade_tx_active);
 }
 
 static char *dcc_err_string(char *buf, int buf_len, u64 flags)
@@ -8264,8 +8308,8 @@ static irqreturn_t sdma_interrupt(int irq, void *data)
 		/* handle the interrupt(s) */
 		sdma_engine_interrupt(sde, status);
 	} else {
-		dd_dev_err_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
-				       sde->this_idx);
+		dd_dev_info_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
+					sde->this_idx);
 	}
 	return IRQ_HANDLED;
 }
@@ -10597,6 +10641,14 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
 
 		handle_linkup_change(dd, 1);
+
+		/*
+		 * After link up, a new link width will have been set.
+		 * Update the xmit counters with regards to the new
+		 * link width.
+		 */
+		update_xmit_counters(ppd, ppd->link_width_active);
+
 		ppd->host_link_state = HLS_UP_INIT;
 		update_statusp(ppd, IB_PORT_INIT);
 		break;
@@ -12960,7 +13012,14 @@ static void disable_intx(struct pci_dev *pdev)
 	pci_intx(pdev, 0);
 }
 
-static void clean_up_interrupts(struct hfi1_devdata *dd)
+/**
+ * hfi1_clean_up_interrupts() - Free all IRQ resources
+ * @dd: valid device data data structure
+ *
+ * Free the MSI or INTx IRQs and assoicated PCI resources,
+ * if they have been allocated.
+ */
+void hfi1_clean_up_interrupts(struct hfi1_devdata *dd)
 {
 	int i;
 
@@ -13321,7 +13380,7 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
 	return 0;
 
 fail:
-	clean_up_interrupts(dd);
+	hfi1_clean_up_interrupts(dd);
 	return ret;
 }
 
@@ -14748,7 +14807,6 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd)
 	aspm_exit(dd);
 	free_cntrs(dd);
 	free_rcverr(dd);
-	clean_up_interrupts(dd);
 	finish_chip_resources(dd);
 }
 
@@ -15204,7 +15262,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 bail_free_cntrs:
 	free_cntrs(dd);
 bail_clear_intr:
-	clean_up_interrupts(dd);
+	hfi1_clean_up_interrupts(dd);
 bail_cleanup:
 	hfi1_pcie_ddcleanup(dd);
 bail_free:

drivers/infiniband/hw/hfi1/chip.h

@@ -736,8 +736,8 @@ int read_8051_config(struct hfi1_devdata *, u8, u8, u32 *);
 int start_link(struct hfi1_pportdata *ppd);
 int bringup_serdes(struct hfi1_pportdata *ppd);
 void set_intr_state(struct hfi1_devdata *dd, u32 enable);
-void apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
-				 int refresh_widths);
+bool apply_link_downgrade_policy(struct hfi1_pportdata *ppd,
+				 bool refresh_widths);
 void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd,
 		    u32 intr_adjust, u32 npkts);
 int stop_drain_data_vls(struct hfi1_devdata *dd);

drivers/infiniband/hw/hfi1/debugfs.c

@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015-2017 Intel Corporation.
+ * Copyright(c) 2015-2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -1201,6 +1201,13 @@ static int _fault_stats_seq_show(struct seq_file *s, void *v)
 		}
 		hfi1_rcd_put(rcd);
 	}
+	for_each_possible_cpu(j) {
+		struct hfi1_opcode_stats_perctx *sp =
+			per_cpu_ptr(dd->tx_opstats, j);
+
+		n_packets += sp->stats[i].n_packets;
+		n_bytes += sp->stats[i].n_bytes;
+	}
 	if (!n_packets && !n_bytes)
 		return SEQ_SKIP;
 	if (!ibd->fault_opcode->n_rxfaults[i] &&