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

Pull rdma updates from Jason Gunthorpe:
 "Many small changes across the subystem, some highlights:

   - Usual driver cleanups in qedr, siw, erdma, hfi1, mlx4/5, irdma,
     mthca, hns, and bnxt_re

   - siw now works over tunnel and other netdevs with a MAC address by
     removing assumptions about a MAC/GID from the connection manager

   - "Doorbell Pacing" for bnxt_re - this is a best effort scheme to
     allow userspace to slow down the doorbell rings if the HW gets full

   - irdma egress VLAN priority, better QP/WQ sizing

   - rxe bug fixes in queue draining and srq resizing

   - Support more ethernet speed options in the core layer

   - DMABUF support for bnxt_re

   - Multi-stage MTT support for erdma to allow much bigger MR
     registrations

   - A irdma fix with a CVE that came in too late to go to -rc, missing
     bounds checking for 0 length MRs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (87 commits)
  IB/hfi1: Reduce printing of errors during driver shut down
  RDMA/hfi1: Move user SDMA system memory pinning code to its own file
  RDMA/hfi1: Use list_for_each_entry() helper
  RDMA/mlx5: Fix trailing */ formatting in block comment
  RDMA/rxe: Fix redundant break statement in switch-case.
  RDMA/efa: Fix wrong resources deallocation order
  RDMA/siw: Call llist_reverse_order in siw_run_sq
  RDMA/siw: Correct wrong debug message
  RDMA/siw: Balance the reference of cep->kref in the error path
  Revert "IB/isert: Fix incorrect release of isert connection"
  RDMA/bnxt_re: Fix kernel doc errors
  RDMA/irdma: Prevent zero-length STAG registration
  RDMA/erdma: Implement hierarchical MTT
  RDMA/erdma: Refactor the storage structure of MTT entries
  RDMA/erdma: Renaming variable names and field names of struct erdma_mem
  RDMA/hns: Support hns HW stats
  RDMA/hns: Dump whole QP/CQ/MR resource in raw
  RDMA/irdma: Add missing kernel-doc in irdma_setup_umode_qp()
  RDMA/mlx4: Copy union directly
  RDMA/irdma: Drop unused kernel push code
  ...

Author: torvalds

drivers/infiniband/core/cache.c

@@ -1457,6 +1457,17 @@ static int config_non_roce_gid_cache(struct ib_device *device,
 				 i);
 			goto err;
 		}
+
+		if (rdma_protocol_iwarp(device, port)) {
+			struct net_device *ndev;
+
+			ndev = ib_device_get_netdev(device, port);
+			if (!ndev)
+				continue;
+			RCU_INIT_POINTER(gid_attr.ndev, ndev);
+			dev_put(ndev);
+		}
+
 		gid_attr.index = i;
 		tprops->subnet_prefix =
 			be64_to_cpu(gid_attr.gid.global.subnet_prefix);

drivers/infiniband/core/cma.c

@@ -686,30 +686,52 @@ cma_validate_port(struct ib_device *device, u32 port,
 		  struct rdma_id_private *id_priv)
 {
 	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
+	const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV);
 	int bound_if_index = dev_addr->bound_dev_if;
-	const struct ib_gid_attr *sgid_attr;
 	int dev_type = dev_addr->dev_type;
 	struct net_device *ndev = NULL;
 
 	if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net))
-		return ERR_PTR(-ENODEV);
+		goto out;
 
 	if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port))
-		return ERR_PTR(-ENODEV);
+		goto out;
 
 	if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port))
-		return ERR_PTR(-ENODEV);
+		goto out;
+
+	/*
+	 * For drivers that do not associate more than one net device with
+	 * their gid tables, such as iWARP drivers, it is sufficient to
+	 * return the first table entry.
+	 *
+	 * Other driver classes might be included in the future.
+	 */
+	if (rdma_protocol_iwarp(device, port)) {
+		sgid_attr = rdma_get_gid_attr(device, port, 0);
+		if (IS_ERR(sgid_attr))
+			goto out;
+
+		rcu_read_lock();
+		ndev = rcu_dereference(sgid_attr->ndev);
+		if (!net_eq(dev_net(ndev), dev_addr->net) ||
+		    ndev->ifindex != bound_if_index)
+			sgid_attr = ERR_PTR(-ENODEV);
+		rcu_read_unlock();
+		goto out;
+	}
 
 	if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) {
 		ndev = dev_get_by_index(dev_addr->net, bound_if_index);
 		if (!ndev)
-			return ERR_PTR(-ENODEV);
+			goto out;
 	} else {
 		gid_type = IB_GID_TYPE_IB;
 	}
 
 	sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev);
 	dev_put(ndev);
+out:
 	return sgid_attr;
 }
 

drivers/infiniband/core/iwpm_util.c

@@ -307,7 +307,7 @@ int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr,
 struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 					u8 nl_client, gfp_t gfp)
 {
-	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct iwpm_nlmsg_request *nlmsg_request;
 	unsigned long flags;
 
 	nlmsg_request = kzalloc(sizeof(struct iwpm_nlmsg_request), gfp);

drivers/infiniband/core/netlink.c

@@ -75,7 +75,7 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 	if (type >= RDMA_NL_NUM_CLIENTS)
 		return false;
 
-	return (op < max_num_ops[type]) ? true : false;
+	return op < max_num_ops[type];
 }
 
 static const struct rdma_nl_cbs *

drivers/infiniband/core/uverbs_main.c

@@ -72,12 +72,23 @@ enum {
 #define IB_UVERBS_BASE_DEV	MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR)
 
 static dev_t dynamic_uverbs_dev;
-static struct class *uverbs_class;
 
 static DEFINE_IDA(uverbs_ida);
 static int ib_uverbs_add_one(struct ib_device *device);
 static void ib_uverbs_remove_one(struct ib_device *device, void *client_data);
 
+static char *uverbs_devnode(const struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0666;
+	return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
+}
+
+static const struct class uverbs_class = {
+	.name = "infiniband_verbs",
+	.devnode = uverbs_devnode,
+};
+
 /*
  * Must be called with the ufile->device->disassociate_srcu held, and the lock
  * must be held until use of the ucontext is finished.
@@ -1117,7 +1128,7 @@ static int ib_uverbs_add_one(struct ib_device *device)
 	}
 
 	device_initialize(&uverbs_dev->dev);
-	uverbs_dev->dev.class = uverbs_class;
+	uverbs_dev->dev.class = &uverbs_class;
 	uverbs_dev->dev.parent = device->dev.parent;
 	uverbs_dev->dev.release = ib_uverbs_release_dev;
 	uverbs_dev->groups[0] = &dev_attr_group;
@@ -1235,13 +1246,6 @@ static void ib_uverbs_remove_one(struct ib_device *device, void *client_data)
 	put_device(&uverbs_dev->dev);
 }
 
-static char *uverbs_devnode(const struct device *dev, umode_t *mode)
-{
-	if (mode)
-		*mode = 0666;
-	return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
-}
-
 static int __init ib_uverbs_init(void)
 {
 	int ret;
@@ -1262,16 +1266,13 @@ static int __init ib_uverbs_init(void)
 		goto out_alloc;
 	}
 
-	uverbs_class = class_create("infiniband_verbs");
-	if (IS_ERR(uverbs_class)) {
-		ret = PTR_ERR(uverbs_class);
+	ret = class_register(&uverbs_class);
+	if (ret) {
 		pr_err("user_verbs: couldn't create class infiniband_verbs\n");
 		goto out_chrdev;
 	}
 
-	uverbs_class->devnode = uverbs_devnode;
-
-	ret = class_create_file(uverbs_class, &class_attr_abi_version.attr);
+	ret = class_create_file(&uverbs_class, &class_attr_abi_version.attr);
 	if (ret) {
 		pr_err("user_verbs: couldn't create abi_version attribute\n");
 		goto out_class;
@@ -1286,7 +1287,7 @@ static int __init ib_uverbs_init(void)
 	return 0;
 
 out_class:
-	class_destroy(uverbs_class);
+	class_unregister(&uverbs_class);
 
 out_chrdev:
 	unregister_chrdev_region(dynamic_uverbs_dev,
@@ -1303,7 +1304,7 @@ static int __init ib_uverbs_init(void)
 static void __exit ib_uverbs_cleanup(void)
 {
 	ib_unregister_client(&uverbs_client);
-	class_destroy(uverbs_class);
+	class_unregister(&uverbs_class);
 	unregister_chrdev_region(IB_UVERBS_BASE_DEV,
 				 IB_UVERBS_NUM_FIXED_MINOR);
 	unregister_chrdev_region(dynamic_uverbs_dev,

drivers/infiniband/core/uverbs_std_types_counters.c

@@ -107,6 +107,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_COUNTERS_READ)(
 		return ret;
 
 	uattr = uverbs_attr_get(attrs, UVERBS_ATTR_READ_COUNTERS_BUFF);
+	if (IS_ERR(uattr))
+		return PTR_ERR(uattr);
 	read_attr.ncounters = uattr->ptr_attr.len / sizeof(u64);
 	read_attr.counters_buff = uverbs_zalloc(
 		attrs, array_size(read_attr.ncounters, sizeof(u64)));

drivers/infiniband/core/verbs.c

@@ -1880,6 +1880,89 @@ int ib_modify_qp_with_udata(struct ib_qp *ib_qp, struct ib_qp_attr *attr,
 }
 EXPORT_SYMBOL(ib_modify_qp_with_udata);
 
+static void ib_get_width_and_speed(u32 netdev_speed, u32 lanes,
+				   u16 *speed, u8 *width)
+{
+	if (!lanes) {
+		if (netdev_speed <= SPEED_1000) {
+			*width = IB_WIDTH_1X;
+			*speed = IB_SPEED_SDR;
+		} else if (netdev_speed <= SPEED_10000) {
+			*width = IB_WIDTH_1X;
+			*speed = IB_SPEED_FDR10;
+		} else if (netdev_speed <= SPEED_20000) {
+			*width = IB_WIDTH_4X;
+			*speed = IB_SPEED_DDR;
+		} else if (netdev_speed <= SPEED_25000) {
+			*width = IB_WIDTH_1X;
+			*speed = IB_SPEED_EDR;
+		} else if (netdev_speed <= SPEED_40000) {
+			*width = IB_WIDTH_4X;
+			*speed = IB_SPEED_FDR10;
+		} else if (netdev_speed <= SPEED_50000) {
+			*width = IB_WIDTH_2X;
+			*speed = IB_SPEED_EDR;
+		} else if (netdev_speed <= SPEED_100000) {
+			*width = IB_WIDTH_4X;
+			*speed = IB_SPEED_EDR;
+		} else if (netdev_speed <= SPEED_200000) {
+			*width = IB_WIDTH_4X;
+			*speed = IB_SPEED_HDR;
+		} else {
+			*width = IB_WIDTH_4X;
+			*speed = IB_SPEED_NDR;
+		}
+
+		return;
+	}
+
+	switch (lanes) {
+	case 1:
+		*width = IB_WIDTH_1X;
+		break;
+	case 2:
+		*width = IB_WIDTH_2X;
+		break;
+	case 4:
+		*width = IB_WIDTH_4X;
+		break;
+	case 8:
+		*width = IB_WIDTH_8X;
+		break;
+	case 12:
+		*width = IB_WIDTH_12X;
+		break;
+	default:
+		*width = IB_WIDTH_1X;
+	}
+
+	switch (netdev_speed / lanes) {
+	case SPEED_2500:
+		*speed = IB_SPEED_SDR;
+		break;
+	case SPEED_5000:
+		*speed = IB_SPEED_DDR;
+		break;
+	case SPEED_10000:
+		*speed = IB_SPEED_FDR10;
+		break;
+	case SPEED_14000:
+		*speed = IB_SPEED_FDR;
+		break;
+	case SPEED_25000:
+		*speed = IB_SPEED_EDR;
+		break;
+	case SPEED_50000:
+		*speed = IB_SPEED_HDR;
+		break;
+	case SPEED_100000:
+		*speed = IB_SPEED_NDR;
+		break;
+	default:
+		*speed = IB_SPEED_SDR;
+	}
+}
+
 int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
 {
 	int rc;
@@ -1904,29 +1987,13 @@ int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
 		netdev_speed = lksettings.base.speed;
 	} else {
 		netdev_speed = SPEED_1000;
-		pr_warn("%s speed is unknown, defaulting to %u\n", netdev->name,
-			netdev_speed);
+		if (rc)
+			pr_warn("%s speed is unknown, defaulting to %u\n",
+				netdev->name, netdev_speed);
 	}
 
-	if (netdev_speed <= SPEED_1000) {
-		*width = IB_WIDTH_1X;
-		*speed = IB_SPEED_SDR;
-	} else if (netdev_speed <= SPEED_10000) {
-		*width = IB_WIDTH_1X;
-		*speed = IB_SPEED_FDR10;
-	} else if (netdev_speed <= SPEED_20000) {
-		*width = IB_WIDTH_4X;
-		*speed = IB_SPEED_DDR;
-	} else if (netdev_speed <= SPEED_25000) {
-		*width = IB_WIDTH_1X;
-		*speed = IB_SPEED_EDR;
-	} else if (netdev_speed <= SPEED_40000) {
-		*width = IB_WIDTH_4X;
-		*speed = IB_SPEED_FDR10;
-	} else {
-		*width = IB_WIDTH_4X;
-		*speed = IB_SPEED_EDR;
-	}
+	ib_get_width_and_speed(netdev_speed, lksettings.lanes,
+			       speed, width);
 
 	return 0;
 }

drivers/infiniband/hw/bnxt_re/bnxt_re.h

@@ -112,12 +112,34 @@ struct bnxt_re_gsi_context {
 #define BNXT_RE_NQ_IDX			1
 #define BNXT_RE_GEN_P5_MAX_VF		64
 
+struct bnxt_re_pacing {
+	u64 dbr_db_fifo_reg_off;
+	void *dbr_page;
+	u64 dbr_bar_addr;
+	u32 pacing_algo_th;
+	u32 do_pacing_save;
+	u32 dbq_pacing_time; /* ms */
+	u32 dbr_def_do_pacing;
+	bool dbr_pacing;
+	struct mutex dbq_lock; /* synchronize db pacing algo */
+};
+
+#define BNXT_RE_MAX_DBR_DO_PACING 0xFFFF
+#define BNXT_RE_DBR_PACING_TIME 5 /* ms */
+#define BNXT_RE_PACING_ALGO_THRESHOLD 250 /* Entries in DB FIFO */
+#define BNXT_RE_PACING_ALARM_TH_MULTIPLE 2 /* Multiple of pacing algo threshold */
+/* Default do_pacing value when there is no congestion */
+#define BNXT_RE_DBR_DO_PACING_NO_CONGESTION 0x7F /* 1 in 512 probability */
+#define BNXT_RE_DB_FIFO_ROOM_MASK 0x1FFF8000
+#define BNXT_RE_MAX_FIFO_DEPTH 0x2c00
+#define BNXT_RE_DB_FIFO_ROOM_SHIFT 15
+#define BNXT_RE_GRC_FIFO_REG_BASE 0x2000
+
 struct bnxt_re_dev {
 	struct ib_device		ibdev;
 	struct list_head		list;
 	unsigned long			flags;
 #define BNXT_RE_FLAG_NETDEV_REGISTERED		0
-#define BNXT_RE_FLAG_GOT_MSIX			2
 #define BNXT_RE_FLAG_HAVE_L2_REF		3
 #define BNXT_RE_FLAG_RCFW_CHANNEL_EN		4
 #define BNXT_RE_FLAG_QOS_WORK_REG		5
@@ -152,16 +174,9 @@ struct bnxt_re_dev {
 	struct bnxt_qplib_res		qplib_res;
 	struct bnxt_qplib_dpi		dpi_privileged;
 
-	atomic_t			qp_count;
 	struct mutex			qp_lock;	/* protect qp list */
 	struct list_head		qp_list;
 
-	atomic_t			cq_count;
-	atomic_t			srq_count;
-	atomic_t			mr_count;
-	atomic_t			mw_count;
-	atomic_t			ah_count;
-	atomic_t			pd_count;
 	/* Max of 2 lossless traffic class supported per port */
 	u16				cosq[2];
 
@@ -171,6 +186,9 @@ struct bnxt_re_dev {
 	atomic_t nq_alloc_cnt;
 	u32 is_virtfn;
 	u32 num_vfs;
+	struct bnxt_re_pacing pacing;
+	struct work_struct dbq_fifo_check_work;
+	struct delayed_work dbq_pacing_work;
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
@@ -181,6 +199,7 @@ struct bnxt_re_dev {
 #define BNXT_RE_ROCEV2_IPV6_PACKET	3
 
 #define BNXT_RE_CHECK_RC(x) ((x) && ((x) != -ETIMEDOUT))
+void bnxt_re_pacing_alert(struct bnxt_re_dev *rdev);
 
 static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev)
 {