RDMA/restrack: Add general infrastructure to track RDMA resources

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>

4 files changed, 170 insertions, 1 deletions

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 504b926552c6..f69833db0a32 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -12,7 +12,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				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
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index aef9aa0ac0e6..2b1372da708a 100644
--- 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 */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2826e06311a5..e8010e73a1cf 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -263,6 +263,8 @@ struct ib_device *ib_alloc_device(size_t size)
 	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_device *device)
 	}
 	up_read(&lists_rwsem);
 
+	rdma_restrack_clean(&device->res);
+
 	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
 
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
new file mode 100644
index 000000000000..857637bf46da
--- /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);