RDMA/counter: Add set/clear per-port auto mode support

Add an API to support set/clear per-port auto mode.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/core/Makefile

@@ -11,7 +11,7 @@ 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 \
-				nldev.o restrack.o
+				nldev.o restrack.o counters.o
 
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o

drivers/infiniband/core/counters.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019 Mellanox Technologies. All rights reserved.
+ */
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_counter.h>
+
+#include "core_priv.h"
+#include "restrack.h"
+
+#define ALL_AUTO_MODE_MASKS (RDMA_COUNTER_MASK_QP_TYPE)
+
+static int __counter_set_mode(struct rdma_counter_mode *curr,
+			      enum rdma_nl_counter_mode new_mode,
+			      enum rdma_nl_counter_mask new_mask)
+{
+	if ((new_mode == RDMA_COUNTER_MODE_AUTO) &&
+	    ((new_mask & (~ALL_AUTO_MODE_MASKS)) ||
+	     (curr->mode != RDMA_COUNTER_MODE_NONE)))
+		return -EINVAL;
+
+	curr->mode = new_mode;
+	curr->mask = new_mask;
+	return 0;
+}
+
+/**
+ * rdma_counter_set_auto_mode() - Turn on/off per-port auto mode
+ *
+ * When @on is true, the @mask must be set
+ */
+int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port,
+			       bool on, enum rdma_nl_counter_mask mask)
+{
+	struct rdma_port_counter *port_counter;
+	int ret;
+
+	port_counter = &dev->port_data[port].port_counter;
+	mutex_lock(&port_counter->lock);
+	if (on) {
+		ret = __counter_set_mode(&port_counter->mode,
+					 RDMA_COUNTER_MODE_AUTO, mask);
+	} else {
+		if (port_counter->mode.mode != RDMA_COUNTER_MODE_AUTO) {
+			ret = -EINVAL;
+			goto out;
+		}
+		ret = __counter_set_mode(&port_counter->mode,
+					 RDMA_COUNTER_MODE_NONE, 0);
+	}
+
+out:
+	mutex_unlock(&port_counter->lock);
+	return ret;
+}
+
+void rdma_counter_init(struct ib_device *dev)
+{
+	struct rdma_port_counter *port_counter;
+	u32 port;
+
+	if (!dev->ops.alloc_hw_stats || !dev->port_data)
+		return;
+
+	rdma_for_each_port(dev, port) {
+		port_counter = &dev->port_data[port].port_counter;
+		port_counter->mode.mode = RDMA_COUNTER_MODE_NONE;
+		mutex_init(&port_counter->lock);
+	}
+}
+
+void rdma_counter_release(struct ib_device *dev)
+{
+}

drivers/infiniband/core/device.c

@@ -46,6 +46,7 @@
 #include <rdma/rdma_netlink.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
+#include <rdma/rdma_counter.h>
 
 #include "core_priv.h"
 #include "restrack.h"
@@ -492,10 +493,12 @@ static void ib_device_release(struct device *device)
 	if (dev->port_data) {
 		ib_cache_release_one(dev);
 		ib_security_release_port_pkey_list(dev);
+		rdma_counter_release(dev);
 		kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu,
 				       pdata[0]),
 			  rcu_head);
 	}
+
 	xa_destroy(&dev->compat_devs);
 	xa_destroy(&dev->client_data);
 	kfree_rcu(dev, rcu_head);
@@ -1316,6 +1319,8 @@ int ib_register_device(struct ib_device *device, const char *name)
 
 	ib_device_register_rdmacg(device);
 
+	rdma_counter_init(device);
+
 	/*
 	 * Ensure that ADD uevent is not fired because it
 	 * is too early amd device is not initialized yet.

include/rdma/ib_verbs.h

@@ -62,6 +62,7 @@
 #include <linux/irqflags.h>
 #include <linux/preempt.h>
 #include <uapi/rdma/ib_user_verbs.h>
+#include <rdma/rdma_counter.h>
 #include <rdma/restrack.h>
 #include <rdma/signature.h>
 #include <uapi/rdma/rdma_user_ioctl.h>
@@ -2119,6 +2120,7 @@ struct ib_port_data {
 	spinlock_t netdev_lock;
 	struct net_device __rcu *netdev;
 	struct hlist_node ndev_hash_link;
+	struct rdma_port_counter port_counter;
 };
 
 /* rdma netdev type - specifies protocol type */

include/rdma/rdma_counter.h

@@ -6,8 +6,26 @@
 #ifndef _RDMA_COUNTER_H_
 #define _RDMA_COUNTER_H_
 
+#include <linux/mutex.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/restrack.h>
+#include <rdma/rdma_netlink.h>
+
+struct auto_mode_param {
+	int qp_type;
+};
+
+struct rdma_counter_mode {
+	enum rdma_nl_counter_mode mode;
+	enum rdma_nl_counter_mask mask;
+	struct auto_mode_param param;
+};
+
+struct rdma_port_counter {
+	struct rdma_counter_mode mode;
+	struct mutex lock;
+};
 
 struct rdma_counter {
 	struct rdma_restrack_entry	res;
@@ -15,4 +33,10 @@ struct rdma_counter {
 	uint32_t			id;
 	u8				port;
 };
+
+void rdma_counter_init(struct ib_device *dev);
+void rdma_counter_release(struct ib_device *dev);
+int rdma_counter_set_auto_mode(struct ib_device *dev, u8 port,
+			       bool on, enum rdma_nl_counter_mask mask);
+
 #endif /* _RDMA_COUNTER_H_ */

include/uapi/rdma/rdma_netlink.h

@@ -507,4 +507,30 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_MAX
 };
+
+/*
+ * Supported counter bind modes. All modes are mutual-exclusive.
+ */
+enum rdma_nl_counter_mode {
+	RDMA_COUNTER_MODE_NONE,
+
+	/*
+	 * A qp is bound with a counter automatically during initialization
+	 * based on the auto mode (e.g., qp type, ...)
+	 */
+	RDMA_COUNTER_MODE_AUTO,
+
+	/*
+	 * Always the end
+	 */
+	RDMA_COUNTER_MODE_MAX,
+};
+
+/*
+ * Supported criteria in counter auto mode.
+ * Currently only "qp type" is supported
+ */
+enum rdma_nl_counter_mask {
+	RDMA_COUNTER_MASK_QP_TYPE = 1,
+};
 #endif /* _UAPI_RDMA_NETLINK_H */