From 39289bfc221423b27570e7c9157b690828e786cb Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Mon, 22 Jul 2019 17:01:30 +0000
Subject: RDMA: Make most headers compile stand alone

So that rdma can work with CONFIG_KERNEL_HEADER_TEST and
CONFIG_HEADERS_CHECK.

Link: https://lore.kernel.org/r/20190722170126.GA16453@ziepe.ca
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/Kbuild               | 6 ------
 include/rdma/ib.h            | 2 ++
 include/rdma/iw_portmap.h    | 3 +++
 include/rdma/opa_port_info.h | 2 ++
 include/rdma/rdmavt_cq.h     | 1 +
 include/rdma/signature.h     | 2 ++
 6 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/Kbuild b/include/Kbuild
index c38f0d46b267..fc2aa4e20658 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -945,12 +945,6 @@ header-test-			+= net/xdp.h
 header-test-			+= net/xdp_priv.h
 header-test-			+= pcmcia/cistpl.h
 header-test-			+= pcmcia/ds.h
-header-test-			+= rdma/ib.h
-header-test-			+= rdma/iw_portmap.h
-header-test-			+= rdma/opa_port_info.h
-header-test-			+= rdma/rdmavt_cq.h
-header-test-			+= rdma/restrack.h
-header-test-			+= rdma/signature.h
 header-test-			+= rdma/tid_rdma_defs.h
 header-test-			+= scsi/fc/fc_encaps.h
 header-test-			+= scsi/fc/fc_fc2.h
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index 4f385ec54f80..fe2fc9e91588 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -36,6 +36,8 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/cred.h>
+#include <linux/uaccess.h>
+#include <linux/fs.h>
 
 struct ib_addr {
 	union {
diff --git a/include/rdma/iw_portmap.h b/include/rdma/iw_portmap.h
index b9fee7feeeb5..c89535047c42 100644
--- a/include/rdma/iw_portmap.h
+++ b/include/rdma/iw_portmap.h
@@ -33,6 +33,9 @@
 #ifndef _IW_PORTMAP_H
 #define _IW_PORTMAP_H
 
+#include <linux/socket.h>
+#include <linux/netlink.h>
+
 #define IWPM_ULIBNAME_SIZE	32
 #define IWPM_DEVNAME_SIZE	32
 #define IWPM_IFNAME_SIZE	16
diff --git a/include/rdma/opa_port_info.h b/include/rdma/opa_port_info.h
index 7147a9263011..bdbfe25d3854 100644
--- a/include/rdma/opa_port_info.h
+++ b/include/rdma/opa_port_info.h
@@ -33,6 +33,8 @@
 #if !defined(OPA_PORT_INFO_H)
 #define OPA_PORT_INFO_H
 
+#include <rdma/opa_smi.h>
+
 #define OPA_PORT_LINK_MODE_NOP	0		/* No change */
 #define OPA_PORT_LINK_MODE_OPA	4		/* Port mode is OPA */
 
diff --git a/include/rdma/rdmavt_cq.h b/include/rdma/rdmavt_cq.h
index 04c519ef6d71..574eb7278f46 100644
--- a/include/rdma/rdmavt_cq.h
+++ b/include/rdma/rdmavt_cq.h
@@ -53,6 +53,7 @@
 
 #include <linux/kthread.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/ib_verbs.h>
 
 /*
  * Define an ib_cq_notify value that is not valid so we know when CQ
diff --git a/include/rdma/signature.h b/include/rdma/signature.h
index f24cc2a1d3c5..d16b0fcc8344 100644
--- a/include/rdma/signature.h
+++ b/include/rdma/signature.h
@@ -6,6 +6,8 @@
 #ifndef _RDMA_SIGNATURE_H_
 #define _RDMA_SIGNATURE_H_
 
+#include <linux/types.h>
+
 enum ib_signature_prot_cap {
 	IB_PROT_T10DIF_TYPE_1 = 1,
 	IB_PROT_T10DIF_TYPE_2 = 1 << 1,
-- 
cgit v1.3-14-g43fede


From 1d2fedd8561dc469a7503855ee602f4bb3eccfa7 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Tue, 23 Jul 2019 10:02:05 +0300
Subject: RDMA/core: Support netlink commands in non init_net net namespaces

Now that IB core supports RDMA device binding with specific net namespace,
enable IB core to accept netlink commands in non init_net namespaces.

This is done by having per net namespace netlink socket.

At present only netlink device handling client RDMA_NL_NLDEV supports
device handling in multiple net namespaces.  Hence do not accept netlink
messages for other clients in non init_net net namespaces.

Link: https://lore.kernel.org/r/20190723070205.6247-1-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/addr.c      |  2 +-
 drivers/infiniband/core/core_priv.h | 24 +++++++++++++-
 drivers/infiniband/core/device.c    | 38 ++++++++--------------
 drivers/infiniband/core/iwpm_msg.c  |  8 ++---
 drivers/infiniband/core/iwpm_util.c |  6 ++--
 drivers/infiniband/core/netlink.c   | 63 +++++++++++++++++++++++++------------
 drivers/infiniband/core/nldev.c     | 20 ++++++------
 drivers/infiniband/core/sa_query.c  |  2 +-
 include/rdma/rdma_netlink.h         | 10 ++++--
 9 files changed, 105 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 9b76a8fcdd24..1dd467bed8fc 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -183,7 +183,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
 
 	/* Make the request retry, so when we get the response from userspace
 	 * we will have something.
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 888d89ce81df..589ed805e0ad 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -36,6 +36,8 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/cgroup_rdma.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/opa_addr.h>
@@ -54,8 +56,26 @@ struct pkey_index_qp_list {
 	struct list_head    qp_list;
 };
 
+/**
+ * struct rdma_dev_net - rdma net namespace metadata for a net
+ * @nl_sock:	Pointer to netlink socket
+ * @net:	Pointer to owner net namespace
+ * @id:		xarray id to identify the net namespace.
+ */
+struct rdma_dev_net {
+	struct sock *nl_sock;
+	possible_net_t net;
+	u32 id;
+};
+
 extern const struct attribute_group ib_dev_attr_group;
 extern bool ib_devices_shared_netns;
+extern unsigned int rdma_dev_net_id;
+
+static inline struct rdma_dev_net *rdma_net_to_dev_net(struct net *net)
+{
+	return net_generic(net, rdma_dev_net_id);
+}
 
 int ib_device_register_sysfs(struct ib_device *device);
 void ib_device_unregister_sysfs(struct ib_device *device);
@@ -179,7 +199,6 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int rdma_nl_init(void);
 void rdma_nl_exit(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
@@ -362,4 +381,7 @@ void ib_port_unregister_module_stat(struct kobject *kobj);
 
 int ib_device_set_netns_put(struct sk_buff *skb,
 			    struct ib_device *dev, u32 ns_fd);
+
+int rdma_nl_net_init(struct rdma_dev_net *rnet);
+void rdma_nl_net_exit(struct rdma_dev_net *rnet);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 309210d2d4a8..c3576c7d2e8f 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -39,7 +39,6 @@
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <net/net_namespace.h>
-#include <net/netns/generic.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/hashtable.h>
@@ -105,17 +104,7 @@ static DECLARE_RWSEM(clients_rwsem);
  */
 #define CLIENT_DATA_REGISTERED XA_MARK_1
 
-/**
- * struct rdma_dev_net - rdma net namespace metadata for a net
- * @net:	Pointer to owner net namespace
- * @id:		xarray id to identify the net namespace.
- */
-struct rdma_dev_net {
-	possible_net_t net;
-	u32 id;
-};
-
-static unsigned int rdma_dev_net_id;
+unsigned int rdma_dev_net_id;
 
 /*
  * A list of net namespaces is maintained in an xarray. This is necessary
@@ -1050,7 +1039,7 @@ int rdma_compatdev_set(u8 enable)
 
 static void rdma_dev_exit_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	struct ib_device *dev;
 	unsigned long index;
 	int ret;
@@ -1084,25 +1073,32 @@ static void rdma_dev_exit_net(struct net *net)
 	}
 	up_read(&devices_rwsem);
 
+	rdma_nl_net_exit(rnet);
 	xa_erase(&rdma_nets, rnet->id);
 }
 
 static __net_init int rdma_dev_init_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	unsigned long index;
 	struct ib_device *dev;
 	int ret;
 
+	write_pnet(&rnet->net, net);
+
+	ret = rdma_nl_net_init(rnet);
+	if (ret)
+		return ret;
+
 	/* No need to create any compat devices in default init_net. */
 	if (net_eq(net, &init_net))
 		return 0;
 
-	write_pnet(&rnet->net, net);
-
 	ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL);
-	if (ret)
+	if (ret) {
+		rdma_nl_net_exit(rnet);
 		return ret;
+	}
 
 	down_read(&devices_rwsem);
 	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
@@ -2629,12 +2625,6 @@ static int __init ib_core_init(void)
 		goto err_comp_unbound;
 	}
 
-	ret = rdma_nl_init();
-	if (ret) {
-		pr_warn("Couldn't init IB netlink interface: err %d\n", ret);
-		goto err_sysfs;
-	}
-
 	ret = addr_init();
 	if (ret) {
 		pr_warn("Could't init IB address resolution\n");
@@ -2680,8 +2670,6 @@ err_mad:
 err_addr:
 	addr_cleanup();
 err_ibnl:
-	rdma_nl_exit();
-err_sysfs:
 	class_unregister(&ib_class);
 err_comp_unbound:
 	destroy_workqueue(ib_comp_unbound_wq);
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 2452b0ddcf0d..f1a873d4e842 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -112,7 +112,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
-	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
@@ -202,7 +202,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -297,7 +297,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";
@@ -364,7 +364,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 41929bb83739..c7ad3499228c 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -645,7 +645,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";
@@ -674,7 +674,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;
@@ -824,7 +824,7 @@ int iwpm_send_hello(u8 nl_client, int iwpm_pid, u16 abi_version)
 		goto hello_num_error;
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index eecfc0b377c9..67a76aca2dd6 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -36,20 +36,22 @@
 #include <linux/export.h>
 #include <net/netlink.h>
 #include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include <net/sock.h>
 #include <rdma/rdma_netlink.h>
 #include <linux/module.h>
 #include "core_priv.h"
 
 static DEFINE_MUTEX(rdma_nl_mutex);
-static struct sock *nls;
 static struct {
 	const struct rdma_nl_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 bool rdma_nl_chk_listeners(unsigned int group)
 {
-	return netlink_has_listeners(nls, group);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(&init_net);
+
+	return netlink_has_listeners(rnet->nl_sock, group);
 }
 EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
@@ -73,13 +75,21 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 	return (op < max_num_ops[type]) ? true : false;
 }
 
-static bool is_nl_valid(unsigned int type, unsigned int op)
+static bool
+is_nl_valid(const struct sk_buff *skb, unsigned int type, unsigned int op)
 {
 	const struct rdma_nl_cbs *cb_table;
 
 	if (!is_nl_msg_valid(type, op))
 		return false;
 
+	/*
+	 * Currently only NLDEV client is supporting netlink commands in
+	 * non init_net net namespace.
+	 */
+	if (sock_net(skb->sk) != &init_net && type != RDMA_NL_NLDEV)
+		return false;
+
 	if (!rdma_nl_types[type].cb_table) {
 		mutex_unlock(&rdma_nl_mutex);
 		request_module("rdma-netlink-subsys-%d", type);
@@ -161,7 +171,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	const struct rdma_nl_cbs *cb_table;
 
-	if (!is_nl_valid(index, op))
+	if (!is_nl_valid(skb, index, op))
 		return -EINVAL;
 
 	cb_table = rdma_nl_types[index].cb_table;
@@ -185,7 +195,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			.dump = cb_table[op].dump,
 		};
 		if (c.dump)
-			return netlink_dump_start(nls, skb, nlh, &c);
+			return netlink_dump_start(skb->sk, skb, nlh, &c);
 		return -EINVAL;
 	}
 
@@ -258,52 +268,65 @@ static void rdma_nl_rcv(struct sk_buff *skb)
 	mutex_unlock(&rdma_nl_mutex);
 }
 
-int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
+int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid)
 {
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	int err;
 
-	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
+	err = netlink_unicast(rnet->nl_sock, skb, pid, MSG_DONTWAIT);
 	return (err < 0) ? err : 0;
 }
 EXPORT_SYMBOL(rdma_nl_unicast);
 
-int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
+int rdma_nl_unicast_wait(struct net *net, struct sk_buff *skb, __u32 pid)
 {
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	int err;
 
-	err = netlink_unicast(nls, skb, pid, 0);
+	err = netlink_unicast(rnet->nl_sock, skb, pid, 0);
 	return (err < 0) ? err : 0;
 }
 EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
-int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
+int rdma_nl_multicast(struct net *net, struct sk_buff *skb,
+		      unsigned int group, gfp_t flags)
 {
-	return nlmsg_multicast(nls, skb, 0, group, flags);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
+
+	return nlmsg_multicast(rnet->nl_sock, skb, 0, group, flags);
 }
 EXPORT_SYMBOL(rdma_nl_multicast);
 
-int __init rdma_nl_init(void)
+void rdma_nl_exit(void)
+{
+	int idx;
+
+	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
+		WARN(rdma_nl_types[idx].cb_table,
+		     "Nelink client %d wasn't released prior to unloading %s\n",
+		     idx, KBUILD_MODNAME);
+}
+
+int rdma_nl_net_init(struct rdma_dev_net *rnet)
 {
+	struct net *net = read_pnet(&rnet->net);
 	struct netlink_kernel_cfg cfg = {
 		.input	= rdma_nl_rcv,
 	};
+	struct sock *nls;
 
-	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
+	nls = netlink_kernel_create(net, NETLINK_RDMA, &cfg);
 	if (!nls)
 		return -ENOMEM;
 
 	nls->sk_sndtimeo = 10 * HZ;
+	rnet->nl_sock = nls;
 	return 0;
 }
 
-void rdma_nl_exit(void)
+void rdma_nl_net_exit(struct rdma_dev_net *rnet)
 {
-	int idx;
-
-	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
-		rdma_nl_unregister(idx);
-
-	netlink_kernel_release(nls);
+	netlink_kernel_release(rnet->nl_sock);
 }
 
 MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_RDMA);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 783e465e7c41..e287b71a1cfd 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -832,7 +832,7 @@ static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlmsg_end(msg, nlh);
 
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);
@@ -972,7 +972,7 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
 
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);
@@ -1074,7 +1074,7 @@ static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);
@@ -1251,7 +1251,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);
@@ -1596,7 +1596,7 @@ static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh,
 	put_device(data.cdev);
 	if (ibdev)
 		ib_device_put(ibdev);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 out_data:
 	put_device(data.cdev);
@@ -1636,7 +1636,7 @@ static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return err;
 	}
 	nlmsg_end(msg, nlh);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 }
 
 static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1734,7 +1734,7 @@ static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_fill:
 	rdma_counter_unbind_qpn(device, port, qpn, cntn);
@@ -1802,7 +1802,7 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_fill:
 	rdma_counter_bind_qpn(device, port, qpn, cntn);
@@ -1893,7 +1893,7 @@ static int stat_get_doit_default_counter(struct sk_buff *skb,
 	mutex_unlock(&stats->lock);
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_table:
 	nla_nest_cancel(msg, table_attr);
@@ -1961,7 +1961,7 @@ static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_msg:
 	nlmsg_free(msg);
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7d8071c7e564..17fc2936c077 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -860,7 +860,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	return rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
+	return rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_mask);
 }
 
 static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 6631624e4d7c..ab22759de7ea 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -76,28 +76,32 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 /**
  * Send the supplied skb to a specific userspace PID.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
+int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid);
 
 /**
  * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
+int rdma_nl_unicast_wait(struct net *net, struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct net *net, struct sk_buff *skb,
+		      unsigned int group, gfp_t flags);
 
 /**
  * Check if there are any listeners to the netlink group
-- 
cgit v1.3-14-g43fede


From 0058eb589881056b49a4ba15dfa3f1b8db53991c Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Tue, 9 Jul 2019 17:17:33 +0300
Subject: qed*: Change dpi_addr to be denoted with __iomem

Several casts were required around dpi_addr parameter in qed_rdma_if.h
This is an address on the doorbell bar and should therefore be marked with
__iomem.

Link: https://lore.kernel.org/r/20190709141735.19193-5-michal.kalderon@marvell.com
Reported-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/qedr/main.c          | 2 +-
 drivers/infiniband/hw/qedr/qedr.h          | 2 +-
 drivers/net/ethernet/qlogic/qed/qed_rdma.c | 5 ++---
 include/linux/qed/qed_rdma_if.h            | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 533157a2a3be..ca5f6f65c929 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -820,7 +820,7 @@ static int qedr_init_hw(struct qedr_dev *dev)
 	if (rc)
 		goto out;
 
-	dev->db_addr = (void __iomem *)(uintptr_t)out_params.dpi_addr;
+	dev->db_addr = out_params.dpi_addr;
 	dev->db_phys_addr = out_params.dpi_phys_addr;
 	dev->db_size = out_params.dpi_size;
 	dev->dpi = out_params.dpi;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index a92ca22e5de1..0cfd849b13d6 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -229,7 +229,7 @@ struct qedr_ucontext {
 	struct ib_ucontext ibucontext;
 	struct qedr_dev *dev;
 	struct qedr_pd *pd;
-	u64 dpi_addr;
+	void __iomem *dpi_addr;
 	u64 dpi_phys_addr;
 	u32 dpi_size;
 	u16 dpi;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index f900fde448db..95eba277f6e2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -799,9 +799,8 @@ static int qed_rdma_add_user(void *rdma_cxt,
 	/* Calculate the corresponding DPI address */
 	dpi_start_offset = p_hwfn->dpi_start_offset;
 
-	out_params->dpi_addr = (u64)((u8 __iomem *)p_hwfn->doorbells +
-				     dpi_start_offset +
-				     ((out_params->dpi) * p_hwfn->dpi_size));
+	out_params->dpi_addr = p_hwfn->doorbells + dpi_start_offset +
+			       out_params->dpi * p_hwfn->dpi_size;
 
 	out_params->dpi_phys_addr = p_hwfn->db_phys_addr +
 				    dpi_start_offset +
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 898f595ea3d6..74efca15fde7 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -225,7 +225,7 @@ struct qed_rdma_start_in_params {
 
 struct qed_rdma_add_user_out_params {
 	u16 dpi;
-	u64 dpi_addr;
+	void __iomem *dpi_addr;
 	u64 dpi_phys_addr;
 	u32 dpi_size;
 	u16 wid_count;
-- 
cgit v1.3-14-g43fede


From 20cf4e026730104892fa1268de0371a631cee294 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 29 Jul 2019 13:22:09 -0400
Subject: rdma: Enable ib_alloc_cq to spread work over a device's comp_vectors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Send and Receive completion is handled on a single CPU selected at
the time each Completion Queue is allocated. Typically this is when
an initiator instantiates an RDMA transport, or when a target
accepts an RDMA connection.

Some ULPs cannot open a connection per CPU to spread completion
workload across available CPUs and MSI vectors. For such ULPs,
provide an API that allows the RDMA core to select a completion
vector based on the device's complement of available comp_vecs.

ULPs that invoke ib_alloc_cq() with only comp_vector 0 are converted
to use the new API so that their completion workloads interfere less
with each other.

Suggested-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Cc: <linux-cifs@vger.kernel.org>
Cc: <v9fs-developer@lists.sourceforge.net>
Link: https://lore.kernel.org/r/20190729171923.13428.52555.stgit@manet.1015granger.net
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cq.c             | 28 ++++++++++++++++++++++++++++
 drivers/infiniband/ulp/srpt/ib_srpt.c    |  4 ++--
 fs/cifs/smbdirect.c                      | 10 ++++++----
 include/rdma/ib_verbs.h                  | 19 +++++++++++++++++++
 net/9p/trans_rdma.c                      |  6 +++---
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  8 ++++----
 net/sunrpc/xprtrdma/verbs.c              | 13 ++++++-------
 7 files changed, 68 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 7c599878ccf7..bbfded6d5d3d 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -252,6 +252,34 @@ out_free_cq:
 }
 EXPORT_SYMBOL(__ib_alloc_cq_user);
 
+/**
+ * __ib_alloc_cq_any - allocate a completion queue
+ * @dev:		device to allocate the CQ for
+ * @private:		driver private data, accessible from cq->cq_context
+ * @nr_cqe:		number of CQEs to allocate
+ * @poll_ctx:		context to poll the CQ from
+ * @caller:		module owner name
+ *
+ * Attempt to spread ULP Completion Queues over each device's interrupt
+ * vectors. A simple best-effort mechanism is used.
+ */
+struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
+				int nr_cqe, enum ib_poll_context poll_ctx,
+				const char *caller)
+{
+	static atomic_t counter;
+	int comp_vector = 0;
+
+	if (dev->num_comp_vectors > 1)
+		comp_vector =
+			atomic_inc_return(&counter) %
+			min_t(int, dev->num_comp_vectors, num_online_cpus());
+
+	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
+				  caller, NULL);
+}
+EXPORT_SYMBOL(__ib_alloc_cq_any);
+
 /**
  * ib_free_cq_user - free a completion queue
  * @cq:		completion queue to free.
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 1a039f16d315..e25c70a56be6 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1767,8 +1767,8 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 		goto out;
 
 retry:
-	ch->cq = ib_alloc_cq(sdev->device, ch, ch->rq_size + sq_size,
-			0 /* XXX: spread CQs */, IB_POLL_WORKQUEUE);
+	ch->cq = ib_alloc_cq_any(sdev->device, ch, ch->rq_size + sq_size,
+				 IB_POLL_WORKQUEUE);
 	if (IS_ERR(ch->cq)) {
 		ret = PTR_ERR(ch->cq);
 		pr_err("failed to create CQ cqe= %d ret= %d\n",
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index cd07e5301d42..3c91fa97c9a8 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1654,15 +1654,17 @@ static struct smbd_connection *_smbd_get_connection(
 
 	info->send_cq = NULL;
 	info->recv_cq = NULL;
-	info->send_cq = ib_alloc_cq(info->id->device, info,
-			info->send_credit_target, 0, IB_POLL_SOFTIRQ);
+	info->send_cq =
+		ib_alloc_cq_any(info->id->device, info,
+				info->send_credit_target, IB_POLL_SOFTIRQ);
 	if (IS_ERR(info->send_cq)) {
 		info->send_cq = NULL;
 		goto alloc_cq_failed;
 	}
 
-	info->recv_cq = ib_alloc_cq(info->id->device, info,
-			info->receive_credit_max, 0, IB_POLL_SOFTIRQ);
+	info->recv_cq =
+		ib_alloc_cq_any(info->id->device, info,
+				info->receive_credit_max, IB_POLL_SOFTIRQ);
 	if (IS_ERR(info->recv_cq)) {
 		info->recv_cq = NULL;
 		goto alloc_cq_failed;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c5f8a9f17063..2a1523ccd7ab 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3711,6 +3711,25 @@ static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
 				NULL);
 }
 
+struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
+				int nr_cqe, enum ib_poll_context poll_ctx,
+				const char *caller);
+
+/**
+ * ib_alloc_cq_any: Allocate kernel CQ
+ * @dev: The IB device
+ * @private: Private data attached to the CQE
+ * @nr_cqe: Number of CQEs in the CQ
+ * @poll_ctx: Context used for polling the CQ
+ */
+static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev,
+					    void *private, int nr_cqe,
+					    enum ib_poll_context poll_ctx)
+{
+	return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx,
+				 KBUILD_MODNAME);
+}
+
 /**
  * ib_free_cq_user - Free kernel/user CQ
  * @cq: The CQ to free
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index bac8dad5dd69..b21c3c209815 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -685,9 +685,9 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 		goto error;
 
 	/* Create the Completion Queue */
-	rdma->cq = ib_alloc_cq(rdma->cm_id->device, client,
-			opts.sq_depth + opts.rq_depth + 1,
-			0, IB_POLL_SOFTIRQ);
+	rdma->cq = ib_alloc_cq_any(rdma->cm_id->device, client,
+				   opts.sq_depth + opts.rq_depth + 1,
+				   IB_POLL_SOFTIRQ);
 	if (IS_ERR(rdma->cq))
 		goto error;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3fe665152d95..4d3db6ee7f09 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -454,14 +454,14 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		dprintk("svcrdma: error creating PD for connect request\n");
 		goto errout;
 	}
-	newxprt->sc_sq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_sq_depth,
-					0, IB_POLL_WORKQUEUE);
+	newxprt->sc_sq_cq = ib_alloc_cq_any(dev, newxprt, newxprt->sc_sq_depth,
+					    IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_sq_cq)) {
 		dprintk("svcrdma: error creating SQ CQ for connect request\n");
 		goto errout;
 	}
-	newxprt->sc_rq_cq = ib_alloc_cq(dev, newxprt, rq_depth,
-					0, IB_POLL_WORKQUEUE);
+	newxprt->sc_rq_cq =
+		ib_alloc_cq_any(dev, newxprt, rq_depth, IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_rq_cq)) {
 		dprintk("svcrdma: error creating RQ CQ for connect request\n");
 		goto errout;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 805b1f35e1ca..b10aa16557f0 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -521,18 +521,17 @@ int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 	init_waitqueue_head(&ep->rep_connect_wait);
 	ep->rep_receive_count = 0;
 
-	sendcq = ib_alloc_cq(ia->ri_id->device, NULL,
-			     ep->rep_attr.cap.max_send_wr + 1,
-			     ia->ri_id->device->num_comp_vectors > 1 ? 1 : 0,
-			     IB_POLL_WORKQUEUE);
+	sendcq = ib_alloc_cq_any(ia->ri_id->device, NULL,
+				 ep->rep_attr.cap.max_send_wr + 1,
+				 IB_POLL_WORKQUEUE);
 	if (IS_ERR(sendcq)) {
 		rc = PTR_ERR(sendcq);
 		goto out1;
 	}
 
-	recvcq = ib_alloc_cq(ia->ri_id->device, NULL,
-			     ep->rep_attr.cap.max_recv_wr + 1,
-			     0, IB_POLL_WORKQUEUE);
+	recvcq = ib_alloc_cq_any(ia->ri_id->device, NULL,
+				 ep->rep_attr.cap.max_recv_wr + 1,
+				 IB_POLL_WORKQUEUE);
 	if (IS_ERR(recvcq)) {
 		rc = PTR_ERR(recvcq);
 		goto out2;
-- 
cgit v1.3-14-g43fede


From 05bb411ada9508b48044ef5d84dd8bc46cece607 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Thu, 1 Aug 2019 20:14:46 +0300
Subject: RDMA/core: Introduce ratelimited ibdev printk functions

Add ratelimited helpers to the ibdev_* printk functions.
Implementation inspired by counterpart dev_*_ratelimited functions.

Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190801171447.54440-2-galpress@amazon.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 include/rdma/ib_verbs.h | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'include')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 2a1523ccd7ab..0ecda7d15df2 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -107,6 +107,48 @@ static inline
 void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {}
 #endif
 
+#define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...)           \
+do {                                                                    \
+	static DEFINE_RATELIMIT_STATE(_rs,                              \
+				      DEFAULT_RATELIMIT_INTERVAL,       \
+				      DEFAULT_RATELIMIT_BURST);         \
+	if (__ratelimit(&_rs))                                          \
+		ibdev_level(ibdev, fmt, ##__VA_ARGS__);                 \
+} while (0)
+
+#define ibdev_emerg_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_alert_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_crit_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_err_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_warn_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_notice_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__)
+#define ibdev_info_ratelimited(ibdev, fmt, ...) \
+	ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)
+
+#if defined(CONFIG_DYNAMIC_DEBUG)
+/* descriptor check is first to prevent flooding with "callbacks suppressed" */
+#define ibdev_dbg_ratelimited(ibdev, fmt, ...)                          \
+do {                                                                    \
+	static DEFINE_RATELIMIT_STATE(_rs,                              \
+				      DEFAULT_RATELIMIT_INTERVAL,       \
+				      DEFAULT_RATELIMIT_BURST);         \
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);                 \
+	if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs))      \
+		__dynamic_ibdev_dbg(&descriptor, ibdev, fmt,            \
+				    ##__VA_ARGS__);                     \
+} while (0)
+#else
+__printf(2, 3) __cold
+static inline
+void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {}
+#endif
+
 union ib_gid {
 	u8	raw[16];
 	struct {
-- 
cgit v1.3-14-g43fede


From 72a7720fca37fec0daf295923f17ac5d88a613e1 Mon Sep 17 00:00:00 2001
From: Kamal Heib <kamalheib1@gmail.com>
Date: Wed, 7 Aug 2019 13:31:35 +0300
Subject: RDMA: Introduce ib_port_phys_state enum

In order to improve readability, add ib_port_phys_state enum to replace
the use of magic numbers.

Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Andrew Boyer <aboyer@tobark.org>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Acked-by: Bernard Metzler <bmt@zurich.ibm.com>
Link: https://lore.kernel.org/r/20190807103138.17219-2-kamalheib1@gmail.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/sysfs.c              | 30 ++++++++++++++++++----------
 drivers/infiniband/hw/bnxt_re/ib_verbs.c     |  4 ++--
 drivers/infiniband/hw/efa/efa_verbs.c        |  2 +-
 drivers/infiniband/hw/hns/hns_roce_device.h  | 10 ----------
 drivers/infiniband/hw/hns/hns_roce_main.c    |  3 ++-
 drivers/infiniband/hw/mlx4/main.c            |  3 ++-
 drivers/infiniband/hw/mlx5/main.c            |  4 ++--
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c  |  4 ++--
 drivers/infiniband/hw/qedr/verbs.c           |  4 ++--
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c |  7 ++++---
 drivers/infiniband/sw/rxe/rxe.h              |  4 ----
 drivers/infiniband/sw/rxe/rxe_param.h        |  2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c        |  6 +++---
 drivers/infiniband/sw/siw/siw_verbs.c        |  3 ++-
 include/rdma/ib_verbs.h                      | 10 ++++++++++
 15 files changed, 53 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index b477295a96c2..7a50cedcef1f 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -289,6 +289,24 @@ static ssize_t rate_show(struct ib_port *p, struct port_attribute *unused,
 		       ib_width_enum_to_int(attr.active_width), speed);
 }
 
+static const char *phys_state_to_str(enum ib_port_phys_state phys_state)
+{
+	static const char * phys_state_str[] = {
+		"<unknown>",
+		"Sleep",
+		"Polling",
+		"Disabled",
+		"PortConfigurationTraining",
+		"LinkUp",
+		"LinkErrorRecovery",
+		"Phy Test",
+	};
+
+	if (phys_state < ARRAY_SIZE(phys_state_str))
+		return phys_state_str[phys_state];
+	return "<unknown>";
+}
+
 static ssize_t phys_state_show(struct ib_port *p, struct port_attribute *unused,
 			       char *buf)
 {
@@ -300,16 +318,8 @@ static ssize_t phys_state_show(struct ib_port *p, struct port_attribute *unused,
 	if (ret)
 		return ret;
 
-	switch (attr.phys_state) {
-	case 1:  return sprintf(buf, "1: Sleep\n");
-	case 2:  return sprintf(buf, "2: Polling\n");
-	case 3:  return sprintf(buf, "3: Disabled\n");
-	case 4:  return sprintf(buf, "4: PortConfigurationTraining\n");
-	case 5:  return sprintf(buf, "5: LinkUp\n");
-	case 6:  return sprintf(buf, "6: LinkErrorRecovery\n");
-	case 7:  return sprintf(buf, "7: Phy Test\n");
-	default: return sprintf(buf, "%d: <unknown>\n", attr.phys_state);
-	}
+	return sprintf(buf, "%d: %s\n", attr.phys_state,
+		       phys_state_to_str(attr.phys_state));
 }
 
 static ssize_t link_layer_show(struct ib_port *p, struct port_attribute *unused,
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 098ab883733e..f9e97d0cc459 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -220,10 +220,10 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
 
 	if (netif_running(rdev->netdev) && netif_carrier_ok(rdev->netdev)) {
 		port_attr->state = IB_PORT_ACTIVE;
-		port_attr->phys_state = 5;
+		port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	} else {
 		port_attr->state = IB_PORT_DOWN;
-		port_attr->phys_state = 3;
+		port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	}
 	port_attr->max_mtu = IB_MTU_4096;
 	port_attr->active_mtu = iboe_get_mtu(rdev->netdev->mtu);
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 32d3b3deabce..70851bd7f801 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -333,7 +333,7 @@ int efa_query_port(struct ib_device *ibdev, u8 port,
 	props->lmc = 1;
 
 	props->state = IB_PORT_ACTIVE;
-	props->phys_state = 5;
+	props->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	props->gid_tbl_len = 1;
 	props->pkey_tbl_len = 1;
 	props->active_speed = IB_SPEED_EDR;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index b39497a13b61..12a2b8565771 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -989,16 +989,6 @@ struct hns_roce_hw {
 	const struct ib_device_ops *hns_roce_dev_srq_ops;
 };
 
-enum hns_phy_state {
-	HNS_ROCE_PHY_SLEEP		= 1,
-	HNS_ROCE_PHY_POLLING		= 2,
-	HNS_ROCE_PHY_DISABLED		= 3,
-	HNS_ROCE_PHY_TRAINING		= 4,
-	HNS_ROCE_PHY_LINKUP		= 5,
-	HNS_ROCE_PHY_LINKERR		= 6,
-	HNS_ROCE_PHY_TEST		= 7
-};
-
 struct hns_roce_dev {
 	struct ib_device	ib_dev;
 	struct platform_device  *pdev;
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 1e4ba48f5613..1b757cc924c3 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -262,7 +262,8 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u8 port_num,
 	props->state = (netif_running(net_dev) && netif_carrier_ok(net_dev)) ?
 			IB_PORT_ACTIVE : IB_PORT_DOWN;
 	props->phys_state = (props->state == IB_PORT_ACTIVE) ?
-			     HNS_ROCE_PHY_LINKUP : HNS_ROCE_PHY_DISABLED;
+			     IB_PORT_PHYS_STATE_LINK_UP :
+			     IB_PORT_PHYS_STATE_DISABLED;
 
 	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8790101facb7..8d2f1e38b891 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -734,7 +734,8 @@ out:
 
 static u8 state_to_phys_state(enum ib_port_state state)
 {
-	return state == IB_PORT_ACTIVE ? 5 : 3;
+	return state == IB_PORT_ACTIVE ?
+		IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED;
 }
 
 static int eth_link_query_port(struct ib_device *ibdev, u8 port,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4a3d700cd783..af1986b4aa7d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -535,7 +535,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	props->max_msg_sz       = 1 << MLX5_CAP_GEN(dev->mdev, log_max_msg);
 	props->pkey_tbl_len     = 1;
 	props->state            = IB_PORT_DOWN;
-	props->phys_state       = 3;
+	props->phys_state       = IB_PORT_PHYS_STATE_DISABLED;
 
 	mlx5_query_nic_vport_qkey_viol_cntr(mdev, &qkey_viol_cntr);
 	props->qkey_viol_cntr = qkey_viol_cntr;
@@ -561,7 +561,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 
 	if (netif_running(ndev) && netif_carrier_ok(ndev)) {
 		props->state      = IB_PORT_ACTIVE;
-		props->phys_state = 5;
+		props->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	}
 
 	ndev_ib_mtu = iboe_get_mtu(ndev->mtu);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index bccc11378109..e8267e590772 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -163,10 +163,10 @@ int ocrdma_query_port(struct ib_device *ibdev,
 	netdev = dev->nic_info.netdev;
 	if (netif_running(netdev) && netif_oper_up(netdev)) {
 		port_state = IB_PORT_ACTIVE;
-		props->phys_state = 5;
+		props->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	} else {
 		port_state = IB_PORT_DOWN;
-		props->phys_state = 3;
+		props->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	}
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = iboe_get_mtu(netdev->mtu);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 0c6a4bc848f5..6f3ce86019b7 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -221,10 +221,10 @@ int qedr_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *attr)
 	/* *attr being zeroed by the caller, avoid zeroing it here */
 	if (rdma_port->port_state == QED_RDMA_PORT_UP) {
 		attr->state = IB_PORT_ACTIVE;
-		attr->phys_state = 5;
+		attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	} else {
 		attr->state = IB_PORT_DOWN;
-		attr->phys_state = 3;
+		attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	}
 	attr->max_mtu = IB_MTU_4096;
 	attr->active_mtu = iboe_get_mtu(dev->ndev->mtu);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index a354c7c86547..556b8e44a51c 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -356,13 +356,14 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 
 	if (!us_ibdev->ufdev->link_up) {
 		props->state = IB_PORT_DOWN;
-		props->phys_state = 3;
+		props->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	} else if (!us_ibdev->ufdev->inaddr) {
 		props->state = IB_PORT_INIT;
-		props->phys_state = 4;
+		props->phys_state =
+			IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING;
 	} else {
 		props->state = IB_PORT_ACTIVE;
-		props->phys_state = 5;
+		props->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	}
 
 	props->port_cap_flags = 0;
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index ecf6e659c0da..fb07eed9e402 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -65,10 +65,6 @@
  */
 #define RXE_UVERBS_ABI_VERSION		2
 
-#define RDMA_LINK_PHYS_STATE_LINK_UP	(5)
-#define RDMA_LINK_PHYS_STATE_DISABLED	(3)
-#define RDMA_LINK_PHYS_STATE_POLLING	(2)
-
 #define RXE_ROCE_V2_SPORT		(0xc000)
 
 static inline u32 rxe_crc32(struct rxe_dev *rxe,
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 1abed47ca221..fe5207386700 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -154,7 +154,7 @@ enum rxe_port_param {
 	RXE_PORT_ACTIVE_WIDTH		= IB_WIDTH_1X,
 	RXE_PORT_ACTIVE_SPEED		= 1,
 	RXE_PORT_PKEY_TBL_LEN		= 64,
-	RXE_PORT_PHYS_STATE		= 2,
+	RXE_PORT_PHYS_STATE		= IB_PORT_PHYS_STATE_POLLING,
 	RXE_PORT_SUBNET_PREFIX		= 0xfe80000000000000ULL,
 };
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 4ebdfcf4d33e..623129f27f5a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -69,11 +69,11 @@ static int rxe_query_port(struct ib_device *dev,
 			      &attr->active_width);
 
 	if (attr->state == IB_PORT_ACTIVE)
-		attr->phys_state = RDMA_LINK_PHYS_STATE_LINK_UP;
+		attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
 	else if (dev_get_flags(rxe->ndev) & IFF_UP)
-		attr->phys_state = RDMA_LINK_PHYS_STATE_POLLING;
+		attr->phys_state = IB_PORT_PHYS_STATE_POLLING;
 	else
-		attr->phys_state = RDMA_LINK_PHYS_STATE_DISABLED;
+		attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 
 	mutex_unlock(&rxe->usdev_lock);
 
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 32dc79d0e898..404e7ca4b30c 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -206,7 +206,8 @@ int siw_query_port(struct ib_device *base_dev, u8 port,
 	attr->gid_tbl_len = 1;
 	attr->max_msg_sz = -1;
 	attr->max_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu);
-	attr->phys_state = sdev->state == IB_PORT_ACTIVE ? 5 : 3;
+	attr->phys_state = sdev->state == IB_PORT_ACTIVE ?
+		IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED;
 	attr->pkey_tbl_len = 1;
 	attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP;
 	attr->state = sdev->state;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0ecda7d15df2..391499008a22 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -493,6 +493,16 @@ enum ib_port_state {
 	IB_PORT_ACTIVE_DEFER	= 5
 };
 
+enum ib_port_phys_state {
+	IB_PORT_PHYS_STATE_SLEEP = 1,
+	IB_PORT_PHYS_STATE_POLLING = 2,
+	IB_PORT_PHYS_STATE_DISABLED = 3,
+	IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4,
+	IB_PORT_PHYS_STATE_LINK_UP = 5,
+	IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6,
+	IB_PORT_PHYS_STATE_PHY_TEST = 7,
+};
+
 enum ib_port_width {
 	IB_WIDTH_1X	= 1,
 	IB_WIDTH_2X	= 16,
-- 
cgit v1.3-14-g43fede


From 972d7560ee37d48a9121ca1b7796d107a16784e7 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Thu, 8 Aug 2019 11:43:57 +0300
Subject: IB/mlx5: Add legacy events to DEVX list

Add two events that were defined in the device specification but were
not exposed in the driver list.

Post this patch those events can be read over the DEVX events interface
once be reported by the firmware.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Edward Srouji <edwards@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190808084358.29517-4-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/devx.c | 8 ++++++++
 include/linux/mlx5/device.h       | 9 +++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index fd577ffd7864..3dbdfe0eb5e4 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -233,6 +233,8 @@ static bool is_legacy_obj_event_num(u16 event_num)
 	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
 	case MLX5_EVENT_TYPE_COMP:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
 		return true;
 	default:
 		return false;
@@ -315,8 +317,10 @@ static u16 get_event_obj_type(unsigned long event_type, struct mlx5_eqe *eqe)
 	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
 		return eqe->data.qp_srq.type;
 	case MLX5_EVENT_TYPE_CQ_ERROR:
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
 		return 0;
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
 		return MLX5_EVENT_QUEUE_TYPE_DCT;
 	default:
 		return MLX5_GET(affiliated_event_header, &eqe->data, obj_type);
@@ -2300,7 +2304,11 @@ static u32 devx_get_obj_id_from_event(unsigned long event_type, void *data)
 	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
 		obj_id = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
 		break;
+	case MLX5_EVENT_TYPE_XRQ_ERROR:
+		obj_id = be32_to_cpu(eqe->data.xrq_err.type_xrqn) & 0xffffff;
+		break;
 	case MLX5_EVENT_TYPE_DCT_DRAINED:
+	case MLX5_EVENT_TYPE_DCT_KEY_VIOLATION:
 		obj_id = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
 		break;
 	case MLX5_EVENT_TYPE_CQ_ERROR:
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index ce9839c8bc1a..e427af260ebe 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -328,6 +328,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_GPIO_EVENT	   = 0x15,
 	MLX5_EVENT_TYPE_PORT_MODULE_EVENT  = 0x16,
 	MLX5_EVENT_TYPE_TEMP_WARN_EVENT    = 0x17,
+	MLX5_EVENT_TYPE_XRQ_ERROR	   = 0x18,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
 	MLX5_EVENT_TYPE_GENERAL_EVENT	   = 0x22,
 	MLX5_EVENT_TYPE_MONITOR_COUNTER    = 0x24,
@@ -345,6 +346,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe,
 
 	MLX5_EVENT_TYPE_DCT_DRAINED        = 0x1c,
+	MLX5_EVENT_TYPE_DCT_KEY_VIOLATION  = 0x1d,
 
 	MLX5_EVENT_TYPE_FPGA_ERROR         = 0x20,
 	MLX5_EVENT_TYPE_FPGA_QP_ERROR      = 0x21,
@@ -584,6 +586,12 @@ struct mlx5_eqe_cq_err {
 	u8	syndrome;
 };
 
+struct mlx5_eqe_xrq_err {
+	__be32	reserved1[5];
+	__be32	type_xrqn;
+	__be32	reserved2;
+};
+
 struct mlx5_eqe_port_state {
 	u8	reserved0[8];
 	u8	port;
@@ -698,6 +706,7 @@ union ev_data {
 	struct mlx5_eqe_pps		pps;
 	struct mlx5_eqe_dct             dct;
 	struct mlx5_eqe_temp_warning	temp_warning;
+	struct mlx5_eqe_xrq_err		xrq_err;
 } __packed;
 
 struct mlx5_eqe {
-- 
cgit v1.3-14-g43fede


From b2299e83815c59ab59c4ee4fb4842b3b28e5072f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 19 Aug 2019 14:45:47 +0300
Subject: RDMA: Delete DEBUG code

There is no need to keep DEBUG defines for out-of-the tree testing.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190819114547.20704-1-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/fmr_pool.c | 13 -------------
 include/rdma/ib_verbs.h            |  3 ---
 2 files changed, 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c
index 7d841b689a1e..e08aec427027 100644
--- a/drivers/infiniband/core/fmr_pool.c
+++ b/drivers/infiniband/core/fmr_pool.c
@@ -148,13 +148,6 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
 		hlist_del_init(&fmr->cache_node);
 		fmr->remap_count = 0;
 		list_add_tail(&fmr->fmr->list, &fmr_list);
-
-#ifdef DEBUG
-		if (fmr->ref_count !=0) {
-			pr_warn(PFX "Unmapping FMR 0x%08x with ref count %d\n",
-				fmr, fmr->ref_count);
-		}
-#endif
 	}
 
 	list_splice_init(&pool->dirty_list, &unmap_list);
@@ -496,12 +489,6 @@ void ib_fmr_pool_unmap(struct ib_pool_fmr *fmr)
 		}
 	}
 
-#ifdef DEBUG
-	if (fmr->ref_count < 0)
-		pr_warn(PFX "FMR %p has ref count %d < 0\n",
-			fmr, fmr->ref_count);
-#endif
-
 	spin_unlock_irqrestore(&pool->pool_lock, flags);
 }
 EXPORT_SYMBOL(ib_fmr_pool_unmap);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 391499008a22..08e966c8081a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -98,9 +98,6 @@ void ibdev_info(const struct ib_device *ibdev, const char *format, ...);
 #if defined(CONFIG_DYNAMIC_DEBUG)
 #define ibdev_dbg(__dev, format, args...)                       \
 	dynamic_ibdev_dbg(__dev, format, ##args)
-#elif defined(DEBUG)
-#define ibdev_dbg(__dev, format, args...)                       \
-	ibdev_printk(KERN_DEBUG, __dev, format, ##args)
 #else
 __printf(2, 3) __cold
 static inline
-- 
cgit v1.3-14-g43fede


From d8abe88450beb96a66e434323eb6ab737654b840 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Mon, 19 Aug 2019 14:36:26 +0300
Subject: RDMA/mlx5: RDMA_RX flow type support for user applications

Currently user applications can only steer TCP/IP(NIC RX/RX) traffic.
This patch adds RDMA_RX as a new flow type to allow the user to insert
steering rules to control RDMA traffic.
Two destinations are supported(but not set at the same time): devx
flow table object and QP.

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190819113626.20284-4-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/mlx5/flow.c         | 13 +++++++++++--
 drivers/infiniband/hw/mlx5/main.c         |  7 +++++++
 drivers/infiniband/hw/mlx5/mlx5_ib.h      |  1 +
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |  1 +
 4 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index b8841355fcd5..571bb8539cdb 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -32,6 +32,9 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type,
 	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB:
 		*namespace = MLX5_FLOW_NAMESPACE_FDB;
 		break;
+	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX:
+		*namespace = MLX5_FLOW_NAMESPACE_RDMA_RX;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -101,6 +104,11 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB && !dest_devx)
 		return -EINVAL;
 
+	/* Allow only DEVX object or QP as dest when inserting to RDMA_RX */
+	if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) &&
+	    ((!dest_devx && !dest_qp) || (dest_devx && dest_qp)))
+		return -EINVAL;
+
 	if (dest_devx) {
 		devx_obj = uverbs_attr_get_obj(
 			attrs, MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX);
@@ -112,8 +120,9 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		 */
 		if (!mlx5_ib_devx_is_flow_dest(devx_obj, &dest_id, &dest_type))
 			return -EINVAL;
-		/* Allow only flow table as dest when inserting to FDB */
-		if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
+		/* Allow only flow table as dest when inserting to FDB or RDMA_RX */
+		if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB ||
+		     fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) &&
 		    dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
 			return -EINVAL;
 	} else if (dest_qp) {
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 1ec0e667110e..07aecba16019 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3963,6 +3963,11 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		    esw_encap)
 			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
 		priority = FDB_BYPASS_PATH;
+	} else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) {
+		max_table_size =
+			BIT(MLX5_CAP_FLOWTABLE_RDMA_RX(dev->mdev,
+						       log_max_ft_size));
+		priority = fs_matcher->priority;
 	}
 
 	max_table_size = min_t(int, max_table_size, MLX5_FS_MAX_ENTRIES);
@@ -3977,6 +3982,8 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		prio = &dev->flow_db->egress_prios[priority];
 	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB)
 		prio = &dev->flow_db->fdb;
+	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX)
+		prio = &dev->flow_db->rdma_rx[priority];
 
 	if (!prio)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index cb41a7e6255a..6abfbf3a69b7 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -200,6 +200,7 @@ struct mlx5_ib_flow_db {
 	struct mlx5_ib_flow_prio	sniffer[MLX5_IB_NUM_SNIFFER_FTS];
 	struct mlx5_ib_flow_prio	egress[MLX5_IB_NUM_EGRESS_FTS];
 	struct mlx5_ib_flow_prio	fdb;
+	struct mlx5_ib_flow_prio	rdma_rx[MLX5_IB_NUM_FLOW_FT];
 	struct mlx5_flow_table		*lag_demux_ft;
 	/* Protect flow steering bypass flow tables
 	 * when add/del flow rules.
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 7e9900b0e746..88b6ca70c2fe 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -43,6 +43,7 @@ enum mlx5_ib_uapi_flow_table_type {
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX     = 0x0,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX	= 0x1,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB	= 0x2,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX	= 0x3,
 };
 
 enum mlx5_ib_uapi_flow_action_packet_reformat_type {
-- 
cgit v1.3-14-g43fede


From 7199435414868bd656284349edc1a1f528fe3662 Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Wed, 11 Sep 2019 07:30:47 -0400
Subject: IB/{rdmavt, hfi1, qib}: Add a counter for credit waits

This patch adds a counter for credit waits to assist field debugging.

Link: https://lore.kernel.org/r/20190911113047.126040.10857.stgit@awfm-01.aw.intel.com
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/chip.c     |  2 ++
 drivers/infiniband/hw/hfi1/chip.h     |  1 +
 drivers/infiniband/hw/hfi1/rc.c       | 10 ++--------
 drivers/infiniband/hw/qib/qib_rc.c    | 10 ++--------
 drivers/infiniband/hw/qib/qib_sysfs.c |  2 ++
 include/rdma/rdma_vt.h                |  1 +
 include/rdma/rdmavt_qp.h              | 35 +++++++++++++++++++++++++++++++++++
 7 files changed, 45 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 67052dc3100c..9b1fb84a3d45 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -4101,6 +4101,7 @@ def_access_ibp_counter(rc_dupreq);
 def_access_ibp_counter(rdma_seq);
 def_access_ibp_counter(unaligned);
 def_access_ibp_counter(seq_naks);
+def_access_ibp_counter(rc_crwaits);
 
 static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 [C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
@@ -5119,6 +5120,7 @@ static struct cntr_entry port_cntrs[PORT_CNTR_LAST] = {
 [C_SW_IBP_RDMA_SEQ] = SW_IBP_CNTR(RdmaSeq, rdma_seq),
 [C_SW_IBP_UNALIGNED] = SW_IBP_CNTR(Unaligned, unaligned),
 [C_SW_IBP_SEQ_NAK] = SW_IBP_CNTR(SeqNak, seq_naks),
+[C_SW_IBP_RC_CRWAITS] = SW_IBP_CNTR(RcCrWait, rc_crwaits),
 [C_SW_CPU_RC_ACKS] = CNTR_ELEM("RcAcks", 0, 0, CNTR_NORMAL,
 			       access_sw_cpu_rc_acks),
 [C_SW_CPU_RC_QACKS] = CNTR_ELEM("RcQacks", 0, 0, CNTR_NORMAL,
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index b76cf81f927f..4ca5ac8d7e9e 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -1245,6 +1245,7 @@ enum {
 	C_SW_IBP_RDMA_SEQ,
 	C_SW_IBP_UNALIGNED,
 	C_SW_IBP_SEQ_NAK,
+	C_SW_IBP_RC_CRWAITS,
 	C_SW_CPU_RC_ACKS,
 	C_SW_CPU_RC_QACKS,
 	C_SW_CPU_RC_DELAYED_COMP,
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index eeca08d3b470..513a8aac9ccd 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -595,11 +595,8 @@ check_s_state:
 		case IB_WR_SEND_WITH_IMM:
 		case IB_WR_SEND_WITH_INV:
 			/* If no credit, return. */
-			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
-				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
+			if (!rvt_rc_credit_avail(qp, wqe))
 				goto bail;
-			}
 			if (len > pmtu) {
 				qp->s_state = OP(SEND_FIRST);
 				len = pmtu;
@@ -632,11 +629,8 @@ check_s_state:
 			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
-			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
-				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
+			if (!rvt_rc_credit_avail(qp, wqe))
 				goto bail;
-			}
 no_flow_control:
 			put_ib_reth_vaddr(
 				wqe->rdma_wr.remote_addr,
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 1d5e2d4ee257..aaf7438258fa 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -313,11 +313,8 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		case IB_WR_SEND:
 		case IB_WR_SEND_WITH_IMM:
 			/* If no credit, return. */
-			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
-				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
+			if (!rvt_rc_credit_avail(qp, wqe))
 				goto bail;
-			}
 			if (len > pmtu) {
 				qp->s_state = OP(SEND_FIRST);
 				len = pmtu;
@@ -344,11 +341,8 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
-			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
-				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
+			if (!rvt_rc_credit_avail(qp, wqe))
 				goto bail;
-			}
 no_flow_control:
 			ohdr->u.rc.reth.vaddr =
 				cpu_to_be64(wqe->rdma_wr.remote_addr);
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index 905206a0c2d5..3926be78036e 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -436,6 +436,7 @@ QIB_DIAGC_ATTR(dmawait);
 QIB_DIAGC_ATTR(unaligned);
 QIB_DIAGC_ATTR(rc_dupreq);
 QIB_DIAGC_ATTR(rc_seqnak);
+QIB_DIAGC_ATTR(rc_crwaits);
 
 static struct attribute *diagc_default_attributes[] = {
 	&qib_diagc_attr_rc_resends.attr,
@@ -453,6 +454,7 @@ static struct attribute *diagc_default_attributes[] = {
 	&qib_diagc_attr_unaligned.attr,
 	&qib_diagc_attr_rc_dupreq.attr,
 	&qib_diagc_attr_rc_seqnak.attr,
+	&qib_diagc_attr_rc_crwaits.attr,
 	NULL
 };
 
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 525848e227dc..ac5a9430abb6 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -116,6 +116,7 @@ struct rvt_ibport {
 	u64 n_unaligned;
 	u64 n_rc_dupreq;
 	u64 n_rc_seqnak;
+	u64 n_rc_crwaits;
 	u16 pkey_violations;
 	u16 qkey_violations;
 	u16 mkey_violations;
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index e06c77d76463..b550ae89bf85 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -973,6 +973,41 @@ static inline void rvt_free_rq(struct rvt_rq *rq)
 	rq->wq = NULL;
 }
 
+/**
+ * rvt_to_iport - Get the ibport pointer
+ * @qp: the qp pointer
+ *
+ * This function returns the ibport pointer from the qp pointer.
+ */
+static inline struct rvt_ibport *rvt_to_iport(struct rvt_qp *qp)
+{
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+
+	return rdi->ports[qp->port_num - 1];
+}
+
+/**
+ * rvt_rc_credit_avail - Check if there are enough RC credits for the request
+ * @qp: the qp
+ * @wqe: the request
+ *
+ * This function returns false when there are not enough credits for the given
+ * request and true otherwise.
+ */
+static inline bool rvt_rc_credit_avail(struct rvt_qp *qp, struct rvt_swqe *wqe)
+{
+	lockdep_assert_held(&qp->s_lock);
+	if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
+	    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
+		struct rvt_ibport *rvp = rvt_to_iport(qp);
+
+		qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
+		rvp->n_rc_crwaits++;
+		return false;
+	}
+	return true;
+}
+
 struct rvt_qp_iter *rvt_qp_iter_init(struct rvt_dev_info *rdi,
 				     u64 v,
 				     void (*cb)(struct rvt_qp *qp, u64 v));
-- 
cgit v1.3-14-g43fede