From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 28 Jan 2018 11:17:20 +0200
Subject: RDMA/restrack: Add general infrastructure to track RDMA resources
Patch-mainline: v4.16-rc1
Git-commit: 02d8883f520ee91c4c40c0a31892eb25ea2df2c9
References: bsc#1103992 FATE#326009

The RDMA subsystem has very strict set of objects to work with, but it
completely lacks tracking facilities and has no visibility of resource
utilization.

The following patch adds such infrastructure to keep track of RDMA
resources to help with debugging of user space applications. The primary
user of this infrastructure is RDMA nldev netlink (following patches), to
be exposed to userspace via rdmatool, but it is not limited too that.

At this stage, the main three objects (PD, CQ and QP) are added, and more
will be added later.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/infiniband/core/Makefile    |    2 
 drivers/infiniband/core/core_priv.h |    1 
 drivers/infiniband/core/device.c    |    4 
 drivers/infiniband/core/restrack.c  |  164 ++++++++++++++++++++++++++++++++++++
 include/rdma/ib_verbs.h             |   19 ++++
 include/rdma/restrack.h             |  157 ++++++++++++++++++++++++++++++++++
 6 files changed, 346 insertions(+), 1 deletion(-)
 create mode 100644 drivers/infiniband/core/restrack.c
 create mode 100644 include/rdma/restrack.h

--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,7 @@ ib_core-y :=			packer.o ud_header.o verb
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
-				security.o nldev.o
+				security.o nldev.o restrack.o
 
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -40,6 +40,7 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/opa_addr.h>
 #include <rdma/ib_mad.h>
+#include <rdma/restrack.h>
 #include "mad_priv.h"
 
 /* Total number of ports combined across all struct ib_devices's */
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -263,6 +263,8 @@ struct ib_device *ib_alloc_device(size_t
 	if (!device)
 		return NULL;
 
+	rdma_restrack_init(&device->res);
+
 	device->dev.class = &ib_class;
 	device_initialize(&device->dev);
 
@@ -596,6 +598,8 @@ void ib_unregister_device(struct ib_devi
 	}
 	up_read(&lists_rwsem);
 
+	rdma_restrack_clean(&device->res);
+
 	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
 
--- /dev/null
+++ b/drivers/infiniband/core/restrack.c
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ */
+
+#include <rdma/ib_verbs.h>
+#include <rdma/restrack.h>
+#include <linux/mutex.h>
+#include <linux/sched/task.h>
+#include <linux/uaccess.h>
+#include <linux/pid_namespace.h>
+
+void rdma_restrack_init(struct rdma_restrack_root *res)
+{
+	init_rwsem(&res->rwsem);
+}
+
+void rdma_restrack_clean(struct rdma_restrack_root *res)
+{
+	WARN_ON_ONCE(!hash_empty(res->hash));
+}
+
+int rdma_restrack_count(struct rdma_restrack_root *res,
+			enum rdma_restrack_type type,
+			struct pid_namespace *ns)
+{
+	struct rdma_restrack_entry *e;
+	u32 cnt = 0;
+
+	down_read(&res->rwsem);
+	hash_for_each_possible(res->hash, e, node, type) {
+		if (ns == &init_pid_ns ||
+		    (!rdma_is_kernel_res(e) &&
+		     ns == task_active_pid_ns(e->task)))
+			cnt++;
+	}
+	up_read(&res->rwsem);
+	return cnt;
+}
+EXPORT_SYMBOL(rdma_restrack_count);
+
+static void set_kern_name(struct rdma_restrack_entry *res)
+{
+	enum rdma_restrack_type type = res->type;
+	struct ib_qp *qp;
+
+	if (type != RDMA_RESTRACK_QP)
+		/* PD and CQ types already have this name embedded in */
+		return;
+
+	qp = container_of(res, struct ib_qp, res);
+	if (!qp->pd) {
+		WARN_ONCE(true, "XRC QPs are not supported\n");
+		/* Survive, despite the programmer's error */
+		res->kern_name = " ";
+		return;
+	}
+
+	res->kern_name = qp->pd->res.kern_name;
+}
+
+static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
+{
+	enum rdma_restrack_type type = res->type;
+	struct ib_device *dev;
+	struct ib_xrcd *xrcd;
+	struct ib_pd *pd;
+	struct ib_cq *cq;
+	struct ib_qp *qp;
+
+	switch (type) {
+	case RDMA_RESTRACK_PD:
+		pd = container_of(res, struct ib_pd, res);
+		dev = pd->device;
+		break;
+	case RDMA_RESTRACK_CQ:
+		cq = container_of(res, struct ib_cq, res);
+		dev = cq->device;
+		break;
+	case RDMA_RESTRACK_QP:
+		qp = container_of(res, struct ib_qp, res);
+		dev = qp->device;
+		break;
+	case RDMA_RESTRACK_XRCD:
+		xrcd = container_of(res, struct ib_xrcd, res);
+		dev = xrcd->device;
+		break;
+	default:
+		WARN_ONCE(true, "Wrong resource tracking type %u\n", type);
+		return NULL;
+	}
+
+	return dev;
+}
+
+void rdma_restrack_add(struct rdma_restrack_entry *res)
+{
+	struct ib_device *dev = res_to_dev(res);
+
+	if (!dev)
+		return;
+
+	if (!uaccess_kernel()) {
+		get_task_struct(current);
+		res->task = current;
+		res->kern_name = NULL;
+	} else {
+		set_kern_name(res);
+		res->task = NULL;
+	}
+
+	kref_init(&res->kref);
+	init_completion(&res->comp);
+	res->valid = true;
+
+	down_write(&dev->res.rwsem);
+	hash_add(dev->res.hash, &res->node, res->type);
+	up_write(&dev->res.rwsem);
+}
+EXPORT_SYMBOL(rdma_restrack_add);
+
+int __must_check rdma_restrack_get(struct rdma_restrack_entry *res)
+{
+	return kref_get_unless_zero(&res->kref);
+}
+EXPORT_SYMBOL(rdma_restrack_get);
+
+static void restrack_release(struct kref *kref)
+{
+	struct rdma_restrack_entry *res;
+
+	res = container_of(kref, struct rdma_restrack_entry, kref);
+	complete(&res->comp);
+}
+
+int rdma_restrack_put(struct rdma_restrack_entry *res)
+{
+	return kref_put(&res->kref, restrack_release);
+}
+EXPORT_SYMBOL(rdma_restrack_put);
+
+void rdma_restrack_del(struct rdma_restrack_entry *res)
+{
+	struct ib_device *dev;
+
+	if (!res->valid)
+		return;
+
+	dev = res_to_dev(res);
+	if (!dev)
+		return;
+
+	rdma_restrack_put(res);
+
+	wait_for_completion(&res->comp);
+
+	down_write(&dev->res.rwsem);
+	hash_del(&res->node);
+	res->valid = false;
+	if (res->task)
+		put_task_struct(res->task);
+	up_write(&dev->res.rwsem);
+}
+EXPORT_SYMBOL(rdma_restrack_del);
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -63,6 +63,7 @@
 #include <linux/uaccess.h>
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
+#include <rdma/restrack.h>
 
 #define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
 
@@ -1525,6 +1526,7 @@ struct ib_pd {
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */
 	struct ib_mr	       *__internal_mr;
+	struct rdma_restrack_entry res;
 };
 
 struct ib_xrcd {
@@ -1534,6 +1536,10 @@ struct ib_xrcd {
 
 	struct mutex		tgt_qp_mutex;
 	struct list_head	tgt_qp_list;
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry res;
 };
 
 struct ib_ah {
@@ -1565,6 +1571,10 @@ struct ib_cq {
 		struct irq_poll		iop;
 		struct work_struct	work;
 	};
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry res;
 };
 
 struct ib_srq {
@@ -1741,6 +1751,11 @@ struct ib_qp {
 	struct ib_rwq_ind_table *rwq_ind_tbl;
 	struct ib_qp_security  *qp_sec;
 	u8			port;
+
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry     res;
 };
 
 struct ib_mr {
@@ -2347,6 +2362,10 @@ struct ib_device {
 #endif
 
 	u32                          index;
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers
+	 */
+	struct rdma_restrack_root     res;
 
 	/**
 	 * The following mandatory functions are used only at device
--- /dev/null
+++ b/include/rdma/restrack.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ */
+
+#ifndef _RDMA_RESTRACK_H_
+#define _RDMA_RESTRACK_H_
+
+#include <linux/typecheck.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/kref.h>
+#include <linux/completion.h>
+
+/**
+ * enum rdma_restrack_type - HW objects to track
+ */
+enum rdma_restrack_type {
+	/**
+	 * @RDMA_RESTRACK_PD: Protection domain (PD)
+	 */
+	RDMA_RESTRACK_PD,
+	/**
+	 * @RDMA_RESTRACK_CQ: Completion queue (CQ)
+	 */
+	RDMA_RESTRACK_CQ,
+	/**
+	 * @RDMA_RESTRACK_QP: Queue pair (QP)
+	 */
+	RDMA_RESTRACK_QP,
+	/**
+	 * @RDMA_RESTRACK_XRCD: XRC domain (XRCD)
+	 */
+	RDMA_RESTRACK_XRCD,
+	/**
+	 * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations
+	 */
+	RDMA_RESTRACK_MAX
+};
+
+#define RDMA_RESTRACK_HASH_BITS	8
+/**
+ * struct rdma_restrack_root - main resource tracking management
+ * entity, per-device
+ */
+struct rdma_restrack_root {
+	/*
+	 * @rwsem: Read/write lock to protect lists
+	 */
+	struct rw_semaphore	rwsem;
+	/**
+	 * @hash: global database for all resources per-device
+	 */
+	DECLARE_HASHTABLE(hash, RDMA_RESTRACK_HASH_BITS);
+};
+
+/**
+ * struct rdma_restrack_entry - metadata per-entry
+ */
+struct rdma_restrack_entry {
+	/**
+	 * @valid: validity indicator
+	 *
+	 * The entries are filled during rdma_restrack_add,
+	 * can be attempted to be free during rdma_restrack_del.
+	 *
+	 * As an example for that, see mlx5 QPs with type MLX5_IB_QPT_HW_GSI
+	 */
+	bool			valid;
+	/*
+	 * @kref: Protect destroy of the resource
+	 */
+	struct kref		kref;
+	/*
+	 * @comp: Signal that all consumers of resource are completed their work
+	 */
+	struct completion	comp;
+	/**
+	 * @task: owner of resource tracking entity
+	 *
+	 * There are two types of entities: created by user and created
+	 * by kernel.
+	 *
+	 * This is relevant for the entities created by users.
+	 * For the entities created by kernel, this pointer will be NULL.
+	 */
+	struct task_struct	*task;
+	/**
+	 * @kern_name: name of owner for the kernel created entities.
+	 */
+	const char		*kern_name;
+	/**
+	 * @node: hash table entry
+	 */
+	struct hlist_node	node;
+	/**
+	 * @type: various objects in restrack database
+	 */
+	enum rdma_restrack_type	type;
+};
+
+/**
+ * rdma_restrack_init() - initialize resource tracking
+ * @res:  resource tracking root
+ */
+void rdma_restrack_init(struct rdma_restrack_root *res);
+
+/**
+ * rdma_restrack_clean() - clean resource tracking
+ * @res:  resource tracking root
+ */
+void rdma_restrack_clean(struct rdma_restrack_root *res);
+
+/**
+ * rdma_restrack_count() - the current usage of specific object
+ * @res:  resource entry
+ * @type: actual type of object to operate
+ * @ns:   PID namespace
+ */
+int rdma_restrack_count(struct rdma_restrack_root *res,
+			enum rdma_restrack_type type,
+			struct pid_namespace *ns);
+
+/**
+ * rdma_restrack_add() - add object to the reource tracking database
+ * @res:  resource entry
+ */
+void rdma_restrack_add(struct rdma_restrack_entry *res);
+
+/**
+ * rdma_restrack_del() - delete object from the reource tracking database
+ * @res:  resource entry
+ * @type: actual type of object to operate
+ */
+void rdma_restrack_del(struct rdma_restrack_entry *res);
+
+/**
+ * rdma_is_kernel_res() - check the owner of resource
+ * @res:  resource entry
+ */
+static inline bool rdma_is_kernel_res(struct rdma_restrack_entry *res)
+{
+	return !res->task;
+}
+
+/**
+ * rdma_restrack_get() - grab to protect resource from release
+ * @res:  resource entry
+ */
+int __must_check rdma_restrack_get(struct rdma_restrack_entry *res);
+
+/**
+ * rdma_restrack_put() - relase resource
+ * @res:  resource entry
+ */
+int rdma_restrack_put(struct rdma_restrack_entry *res);
+#endif /* _RDMA_RESTRACK_H_ */