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

…el/git/roland/infiniband

Pull InfiniBand/RDMA updates from Roland Dreier:
 - Re-enable on-demand paging changes with stable ABI
 - Fairly large set of ocrdma HW driver fixes
 - Some qib HW driver fixes
 - Other miscellaneous changes

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (43 commits)
  IB/qib: Add blank line after declaration
  IB/qib: Fix checkpatch warnings
  IB/mlx5: Enable the ODP capability query verb
  IB/core: Add on demand paging caps to ib_uverbs_ex_query_device
  IB/core: Add support for extended query device caps
  RDMA/cxgb4: Don't hang threads forever waiting on WR replies
  RDMA/ocrdma: Fix off by one in ocrdma_query_gid()
  RDMA/ocrdma: Use unsigned for bit index
  RDMA/ocrdma: Help gcc generate better code for ocrdma_srq_toggle_bit
  RDMA/ocrdma: Update the ocrdma module version string
  RDMA/ocrdma: set vlan present bit for user AH
  RDMA/ocrdma: remove reference of ocrdma_dev out of ocrdma_qp structure
  RDMA/ocrdma: Add support for interrupt moderation
  RDMA/ocrdma: Honor return value of ocrdma_resolve_dmac
  RDMA/ocrdma: Allow expansion of the SQ CQEs via buddy CQ expansion of the QP
  RDMA/ocrdma: Discontinue support of RDMA-READ-WITH-INVALIDATE
  RDMA/ocrdma: Host crash on destroying device resources
  RDMA/ocrdma: Report correct state in ibv_query_qp
  RDMA/ocrdma: Debugfs enhancments for ocrdma driver
  RDMA/ocrdma: Report correct count of interrupt vectors while registering ocrdma device
  ...

MAINTAINERS

@@ -8567,7 +8567,7 @@ S:	Maintained
 F:	drivers/scsi/sr*
 
 SCSI RDMA PROTOCOL (SRP) INITIATOR
-M:	Bart Van Assche <bvanassche@acm.org>
+M:	Bart Van Assche <bart.vanassche@sandisk.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org

drivers/infiniband/core/ucma.c

@@ -1124,6 +1124,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx,
 	if (!optlen)
 		return -EINVAL;
 
+	memset(&sa_path, 0, sizeof(sa_path));
+	sa_path.vlan_id = 0xffff;
+
 	ib_sa_unpack_path(path_data->path_rec, &sa_path);
 	ret = rdma_set_ib_paths(ctx->cm_id, &sa_path, 1);
 	if (ret)

drivers/infiniband/core/umem_odp.c

@@ -294,7 +294,8 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 	if (likely(ib_umem_start(umem) != ib_umem_end(umem)))
 		rbt_ib_umem_insert(&umem->odp_data->interval_tree,
 				   &context->umem_tree);
-	if (likely(!atomic_read(&context->notifier_count)))
+	if (likely(!atomic_read(&context->notifier_count)) ||
+	    context->odp_mrs_count == 1)
 		umem->odp_data->mn_counters_active = true;
 	else
 		list_add(&umem->odp_data->no_private_counters,

drivers/infiniband/core/uverbs.h

@@ -258,5 +258,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
+IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */

drivers/infiniband/core/uverbs_cmd.c

@@ -400,6 +400,52 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	return ret;
 }
 
+static void copy_query_dev_fields(struct ib_uverbs_file *file,
+				  struct ib_uverbs_query_device_resp *resp,
+				  struct ib_device_attr *attr)
+{
+	resp->fw_ver		= attr->fw_ver;
+	resp->node_guid		= file->device->ib_dev->node_guid;
+	resp->sys_image_guid	= attr->sys_image_guid;
+	resp->max_mr_size	= attr->max_mr_size;
+	resp->page_size_cap	= attr->page_size_cap;
+	resp->vendor_id		= attr->vendor_id;
+	resp->vendor_part_id	= attr->vendor_part_id;
+	resp->hw_ver		= attr->hw_ver;
+	resp->max_qp		= attr->max_qp;
+	resp->max_qp_wr		= attr->max_qp_wr;
+	resp->device_cap_flags	= attr->device_cap_flags;
+	resp->max_sge		= attr->max_sge;
+	resp->max_sge_rd	= attr->max_sge_rd;
+	resp->max_cq		= attr->max_cq;
+	resp->max_cqe		= attr->max_cqe;
+	resp->max_mr		= attr->max_mr;
+	resp->max_pd		= attr->max_pd;
+	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
+	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
+	resp->max_res_rd_atom	= attr->max_res_rd_atom;
+	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
+	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
+	resp->atomic_cap		= attr->atomic_cap;
+	resp->max_ee			= attr->max_ee;
+	resp->max_rdd			= attr->max_rdd;
+	resp->max_mw			= attr->max_mw;
+	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
+	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
+	resp->max_mcast_grp		= attr->max_mcast_grp;
+	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
+	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
+	resp->max_ah			= attr->max_ah;
+	resp->max_fmr			= attr->max_fmr;
+	resp->max_map_per_fmr		= attr->max_map_per_fmr;
+	resp->max_srq			= attr->max_srq;
+	resp->max_srq_wr		= attr->max_srq_wr;
+	resp->max_srq_sge		= attr->max_srq_sge;
+	resp->max_pkeys			= attr->max_pkeys;
+	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
+	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
+}
+
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -420,47 +466,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-
-	resp.fw_ver 		       = attr.fw_ver;
-	resp.node_guid 		       = file->device->ib_dev->node_guid;
-	resp.sys_image_guid 	       = attr.sys_image_guid;
-	resp.max_mr_size 	       = attr.max_mr_size;
-	resp.page_size_cap 	       = attr.page_size_cap;
-	resp.vendor_id 		       = attr.vendor_id;
-	resp.vendor_part_id 	       = attr.vendor_part_id;
-	resp.hw_ver 		       = attr.hw_ver;
-	resp.max_qp 		       = attr.max_qp;
-	resp.max_qp_wr 		       = attr.max_qp_wr;
-	resp.device_cap_flags 	       = attr.device_cap_flags;
-	resp.max_sge 		       = attr.max_sge;
-	resp.max_sge_rd 	       = attr.max_sge_rd;
-	resp.max_cq 		       = attr.max_cq;
-	resp.max_cqe 		       = attr.max_cqe;
-	resp.max_mr 		       = attr.max_mr;
-	resp.max_pd 		       = attr.max_pd;
-	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
-	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
-	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
-	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
-	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
-	resp.atomic_cap 	       = attr.atomic_cap;
-	resp.max_ee 		       = attr.max_ee;
-	resp.max_rdd 		       = attr.max_rdd;
-	resp.max_mw 		       = attr.max_mw;
-	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
-	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
-	resp.max_mcast_grp 	       = attr.max_mcast_grp;
-	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
-	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
-	resp.max_ah 		       = attr.max_ah;
-	resp.max_fmr 		       = attr.max_fmr;
-	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
-	resp.max_srq 		       = attr.max_srq;
-	resp.max_srq_wr 	       = attr.max_srq_wr;
-	resp.max_srq_sge 	       = attr.max_srq_sge;
-	resp.max_pkeys 		       = attr.max_pkeys;
-	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
-	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
+	copy_query_dev_fields(file, &resp, &attr);
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -2091,20 +2097,21 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	if (qp->real_qp == qp) {
 		ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask);
 		if (ret)
-			goto out;
+			goto release_qp;
 		ret = qp->device->modify_qp(qp, attr,
 			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
 	} else {
 		ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask));
 	}
 
-	put_qp_read(qp);
-
 	if (ret)
-		goto out;
+		goto release_qp;
 
 	ret = in_len;
 
+release_qp:
+	put_qp_read(qp);
+
 out:
 	kfree(attr);
 
@@ -3287,3 +3294,64 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 
 	return ret ? ret : in_len;
 }
+
+int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
+			      struct ib_udata *ucore,
+			      struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_query_device_resp resp;
+	struct ib_uverbs_ex_query_device  cmd;
+	struct ib_device_attr attr;
+	struct ib_device *device;
+	int err;
+
+	device = file->device->ib_dev;
+	if (ucore->inlen < sizeof(cmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	if (cmd.comp_mask)
+		return -EINVAL;
+
+	if (cmd.reserved)
+		return -EINVAL;
+
+	resp.response_length = offsetof(typeof(resp), odp_caps);
+
+	if (ucore->outlen < resp.response_length)
+		return -ENOSPC;
+
+	err = device->query_device(device, &attr);
+	if (err)
+		return err;
+
+	copy_query_dev_fields(file, &resp.base, &attr);
+	resp.comp_mask = 0;
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.odp_caps))
+		goto end;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	resp.odp_caps.general_caps = attr.odp_caps.general_caps;
+	resp.odp_caps.per_transport_caps.rc_odp_caps =
+		attr.odp_caps.per_transport_caps.rc_odp_caps;
+	resp.odp_caps.per_transport_caps.uc_odp_caps =
+		attr.odp_caps.per_transport_caps.uc_odp_caps;
+	resp.odp_caps.per_transport_caps.ud_odp_caps =
+		attr.odp_caps.per_transport_caps.ud_odp_caps;
+	resp.odp_caps.reserved = 0;
+#else
+	memset(&resp.odp_caps, 0, sizeof(resp.odp_caps));
+#endif
+	resp.response_length += sizeof(resp.odp_caps);
+
+end:
+	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
+	if (err)
+		return err;
+
+	return 0;
+}

drivers/infiniband/core/uverbs_main.c

@@ -123,6 +123,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
+	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);

drivers/infiniband/hw/cxgb4/ev.c

@@ -225,13 +225,20 @@ int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid)
 	struct c4iw_cq *chp;
 	unsigned long flag;
 
+	spin_lock_irqsave(&dev->lock, flag);
 	chp = get_chp(dev, qid);
 	if (chp) {
+		atomic_inc(&chp->refcnt);
+		spin_unlock_irqrestore(&dev->lock, flag);
 		t4_clear_cq_armed(&chp->cq);
 		spin_lock_irqsave(&chp->comp_handler_lock, flag);
 		(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
 		spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
-	} else
+		if (atomic_dec_and_test(&chp->refcnt))
+			wake_up(&chp->wait);
+	} else {
 		PDBG("%s unknown cqid 0x%x\n", __func__, qid);
+		spin_unlock_irqrestore(&dev->lock, flag);
+	}
 	return 0;
 }

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -196,7 +196,7 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev)
 	return (int)(rdev->lldi.vr->stag.size >> 5);
 }
 
-#define C4IW_WR_TO (30*HZ)
+#define C4IW_WR_TO (60*HZ)
 
 struct c4iw_wr_wait {
 	struct completion completion;
@@ -220,22 +220,21 @@ static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
 				 u32 hwtid, u32 qpid,
 				 const char *func)
 {
-	unsigned to = C4IW_WR_TO;
 	int ret;
 
-	do {
-		ret = wait_for_completion_timeout(&wr_waitp->completion, to);
-		if (!ret) {
-			printk(KERN_ERR MOD "%s - Device %s not responding - "
-			       "tid %u qpid %u\n", func,
-			       pci_name(rdev->lldi.pdev), hwtid, qpid);
-			if (c4iw_fatal_error(rdev)) {
-				wr_waitp->ret = -EIO;
-				break;
-			}
-			to = to << 2;
-		}
-	} while (!ret);
+	if (c4iw_fatal_error(rdev)) {
+		wr_waitp->ret = -EIO;
+		goto out;
+	}
+
+	ret = wait_for_completion_timeout(&wr_waitp->completion, C4IW_WR_TO);
+	if (!ret) {
+		PDBG("%s - Device %s not responding (disabling device) - tid %u qpid %u\n",
+		     func, pci_name(rdev->lldi.pdev), hwtid, qpid);
+		rdev->flags |= T4_FATAL_ERROR;
+		wr_waitp->ret = -EIO;
+	}
+out:
 	if (wr_waitp->ret)
 		PDBG("%s: FW reply %d tid %u qpid %u\n",
 		     pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);

drivers/infiniband/hw/ipath/ipath_kernel.h

@@ -908,9 +908,6 @@ void ipath_chip_cleanup(struct ipath_devdata *);
 /* clean up any chip type-specific stuff */
 void ipath_chip_done(void);
 
-/* check to see if we have to force ordering for write combining */
-int ipath_unordered_wc(void);
-
 void ipath_disarm_piobufs(struct ipath_devdata *, unsigned first,
 			  unsigned cnt);
 void ipath_cancel_sends(struct ipath_devdata *, int);

drivers/infiniband/hw/ipath/ipath_wc_ppc64.c

@@ -47,16 +47,3 @@ int ipath_enable_wc(struct ipath_devdata *dd)
 {
 	return 0;
 }
-
-/**
- * ipath_unordered_wc - indicate whether write combining is unordered
- *
- * Because our performance depends on our ability to do write
- * combining mmio writes in the most efficient way, we need to
- * know if we are on a processor that may reorder stores when
- * write combining.
- */
-int ipath_unordered_wc(void)
-{
-	return 1;
-}

drivers/infiniband/hw/ipath/ipath_wc_x86_64.c

@@ -167,18 +167,3 @@ void ipath_disable_wc(struct ipath_devdata *dd)
 		dd->ipath_wc_cookie = 0; /* even on failure */
 	}
 }
-
-/**
- * ipath_unordered_wc - indicate whether write combining is ordered
- *
- * Because our performance depends on our ability to do write combining mmio
- * writes in the most efficient way, we need to know if we are on an Intel
- * or AMD x86_64 processor.  AMD x86_64 processors flush WC buffers out in
- * the order completed, and so no special flushing is required to get
- * correct ordering.  Intel processors, however, will flush write buffers
- * out in "random" orders, and so explicit ordering is needed at times.
- */
-int ipath_unordered_wc(void)
-{
-	return boot_cpu_data.x86_vendor != X86_VENDOR_AMD;
-}

drivers/infiniband/hw/mlx4/cm.c

@@ -372,7 +372,7 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
 		*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
 		if (*slave < 0) {
 			mlx4_ib_warn(ibdev, "failed matching slave_id by gid (0x%llx)\n",
-					gid.global.interface_id);
+				     be64_to_cpu(gid.global.interface_id));
 			return -ENOENT;
 		}
 		return 0;

drivers/infiniband/hw/mlx4/cq.c

@@ -369,8 +369,7 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 	int err;
 
 	mutex_lock(&cq->resize_mutex);
-
-	if (entries < 1) {
+	if (entries < 1 || entries > dev->dev->caps.max_cqes) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -381,7 +380,7 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		goto out;
 	}
 
-	if (entries > dev->dev->caps.max_cqes) {
+	if (entries > dev->dev->caps.max_cqes + 1) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -394,7 +393,7 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		/* Can't be smaller than the number of outstanding CQEs */
 		outst_cqe = mlx4_ib_get_outstanding_cqes(cq);
 		if (entries < outst_cqe + 1) {
-			err = 0;
+			err = -EINVAL;
 			goto out;
 		}