[PATCH rdma-next V1 00/19] RDMA Netlink Device Client

[PATCH rdma-next V1 00/19] RDMA Netlink Device Client

[Leon Romanovsky]

Hi All,

This is second version of the RDMA netlink patch set.

The following patch set is an implementation of NLDEV - RDMA netlink
device client. It is based on the already sent patch [1] and patch set [2].

This client is needed to properly integrate coming RDMAtool [3]
into iproute2 package which is based on netlink.

The following patch set can be logically divided into four parts:
 * Cleanup of RDMA netlink interface to handle dumpit/doit callbacks.
 * Implementation of static ib_device index to allow future renaming support for IB devices.
 * NLDEV initial implementation
 * Exposing device and capability masks via this interface

The supplementary user space part will follow later on.

Chagelog:
v0->v1:
 * Added Steve's Reviewed-by tags for all patches except patch #8, because it was completely rewritten.
 * Implemented static indexes for ib_device in patch #8 and dropped preview version which
   translated device name to corresponding ib_device.
 * Fixed language in commit messages as was pointed by Steve.
 * Rename TODO to be FIXME in patch #11.

Thanks

[1] "Revert "IB/core: Add flow control to the portmapper netlink calls""
     https://patchwork.kernel.org/patch/9752865/

[2] [PATCH rdma-next V2 0/5] Refactor RDMA netlink infrastructure
    https://www.spinics.net/lists/linux-rdma/msg50945.html

[3] [RFC iproute2 0/8] RDMA tool
    https://www.spinics.net/lists/linux-rdma/msg49575.html

Available in the "topic/rdma-netlink-v1" topic branch of this git repo:
git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git

Or for browsing:
https://git.kernel.org/cgit/linux/kernel/git/leon/linux-rdma.git/log/?h=topic/rdma-netlink-v1

CC: Chien Tin Tung <chien.tin.tung@intel.com>
CC: Steve Wise <swise@opengridcomputing.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Ariel Almog <ariela@mellanox.com>
CC: Linux RDMA <linux-rdma@vger.kernel.org>
CC: Linux Netdev <netdev@vger.kernel.org>


*** BLURB HERE ***

Leon Romanovsky (19):
  RDMA/netlink: Add flag to consolidate common handing
  RDMA/netlink: Simplify the put_msg and put_attr
  RDMA/netlink: Rename and remove redundant parameter from ibnl_unicast
  RDMA/netlink: Rename and remove redundant parameter from
    ibnl_multicast
  RDMA/netlink: Simplify and rename ibnl_chk_listeners
  RDMA/netlink: Rename netlink callback struct
  RDMA/core: Add iterator over ib_devices
  RDMA/core: Add and expose static device index
  RDMA/netlink: Add and implement doit netlink callback
  RDMA/netlink: Reduce indirection access to cb_table
  RDMA/netlink: Convert LS to doit callback
  RDMA/netlink: Update copyright
  RDMA/netlink: Add netlink device definitions to UAPI
  RDMA/netlink: Add nldev initialization flows
  RDMA/netlink: Implement nldev device dumpit calback
  RDMA/netlink: Add nldev device doit implementation
  RDMA/netlink: Add nldev port dumpit implementation
  RDMA/netlink: Implement nldev port doit callback
  RDMA/netlink: Expose device and port capability masks

 drivers/infiniband/core/Makefile    |   4 +-
 drivers/infiniband/core/addr.c      |  12 +-
 drivers/infiniband/core/cma.c       |   2 +-
 drivers/infiniband/core/core_priv.h |  21 ++-
 drivers/infiniband/core/device.c    |  78 ++++++++++-
 drivers/infiniband/core/iwcm.c      |   2 +-
 drivers/infiniband/core/iwpm_msg.c  |   8 +-
 drivers/infiniband/core/iwpm_util.c |   4 +-
 drivers/infiniband/core/netlink.c   |  98 ++++++-------
 drivers/infiniband/core/nldev.c     | 271 ++++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/sa_query.c  |  18 ++-
 include/rdma/ib_verbs.h             |   2 +
 include/rdma/rdma_netlink.h         |  22 +--
 include/uapi/rdma/rdma_netlink.h    |  44 +++++-
 14 files changed, 489 insertions(+), 97 deletions(-)
 create mode 100644 drivers/infiniband/core/nldev.c

[PATCH rdma-next V1 01/19] RDMA/netlink: Add flag to consolidate common handing

[Leon Romanovsky]

From: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Add ability to provide flags to control RDMA netlink callbacks
and convert addr.c and sa_query.c to be first users of such
infrastructure. It allows to move their CAP_NET_ADMIN checks
into netlink core.

Signed-off-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Reviewed-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
---
 drivers/infiniband/core/addr.c     |  3 +--
 drivers/infiniband/core/device.c   | 12 +++++++++---
 drivers/infiniband/core/netlink.c  |  4 ++++
 drivers/infiniband/core/sa_query.c |  6 ++----
 include/rdma/rdma_netlink.h        |  6 ++++++
 5 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 02971e239a18..134d8394fca5 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -134,8 +134,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	if (ib_nl_is_good_ip_resp(nlh))
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 5c70ea49d5ad..2001dabd1444 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1010,11 +1010,17 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp},
+		.dump = ib_nl_handle_resolve_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout},
+		.dump = ib_nl_handle_set_timeout,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp},
+		.dump = ib_nl_handle_ip_res_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
 static int __init ib_core_init(void)
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 4fa6746a62b1..f0d482009c69 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -171,6 +171,10 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
+	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
 	/*
 	 * For response or local service set_timeout request,
 	 * there is no need to use netlink_dump_start.
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index e335b09c022e..6e39a763b220 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1034,8 +1034,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	int ret;
 
 	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
@@ -1110,8 +1109,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	int ret;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	spin_lock_irqsave(&ib_nl_request_lock, flags);
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 761517105a36..6932b7acd3a6 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -7,6 +7,12 @@
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
+	u8 flags;
+};
+
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
 int rdma_nl_init(void);
-- 
2.13.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH rdma-next V1 02/19] RDMA/netlink: Simplify the put_msg and put_attr

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Reuse standard macros to cancel the netlink message
in case of error.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 31 +++++++++----------------------
 1 file changed, 9 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index f0d482009c69..96057e722123 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -126,36 +126,23 @@ EXPORT_SYMBOL(rdma_nl_unregister);
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 		   int len, int client, int op, int flags)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			 len, flags);
-	if (!*nlh)
-		goto out_nlmsg_trim;
-	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
+	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags);
+	if (!*nlh) {
+		nlmsg_cancel(skb, *nlh);
+		return NULL;
+	}
 	return nlmsg_data(*nlh);
-
-out_nlmsg_trim:
-	nlmsg_trim(skb, prev_tail);
-	return NULL;
 }
 EXPORT_SYMBOL(ibnl_put_msg);
 
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	if (nla_put(skb, type, len, data))
-		goto nla_put_failure;
-	nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail;
+	if (nla_put(skb, type, len, data)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
 	return 0;
-
-nla_put_failure:
-	nlmsg_trim(skb, prev_tail - nlh->nlmsg_len);
-	return -EMSGSIZE;
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-- 
2.13.1

[PATCH rdma-next V1 03/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_unicast

[Leon Romanovsky]

From: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Netlink message header is not needed for unicast reply, hence remove it.

Signed-off-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Reviewed-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
---
 drivers/infiniband/core/iwpm_msg.c  | 6 +++---
 drivers/infiniband/core/iwpm_util.c | 4 ++--
 drivers/infiniband/core/netlink.c   | 5 ++---
 include/rdma/rdma_netlink.h         | 4 +---
 4 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 1fab707b1f68..8f84557d04e3 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -172,7 +172,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -248,7 +248,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";
@@ -308,7 +308,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(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 c46442ac71a2..c81c55942626 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -597,7 +597,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
-	ret = ibnl_unicast(skb, nlh, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";
@@ -626,7 +626,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 96057e722123..cd29311078b5 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -241,12 +241,11 @@ static void rdma_nl_rcv(struct sk_buff *skb)
 	mutex_unlock(&rdma_nl_mutex);
 }
 
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid)
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
 {
 	return nlmsg_unicast(nls, skb, pid);
 }
-EXPORT_SYMBOL(ibnl_unicast);
+EXPORT_SYMBOL(rdma_nl_unicast);
 
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 6932b7acd3a6..9779cd5520d7 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -59,12 +59,10 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
-- 
2.13.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH rdma-next V1 04/19] RDMA/netlink: Rename and remove redundant parameter from ibnl_multicast

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

The pointer to netlink header was not used in the ibnl_multicast
function, so let's remove it and simplify the function
signature.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c     | 2 +-
 drivers/infiniband/core/iwpm_msg.c | 2 +-
 drivers/infiniband/core/netlink.c  | 5 ++---
 drivers/infiniband/core/sa_query.c | 2 +-
 include/rdma/rdma_netlink.h        | 4 +---
 5 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 134d8394fca5..ebd0242bab3d 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -185,7 +185,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(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/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 8f84557d04e3..561f312ea35a 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -103,7 +103,7 @@ 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 = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(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;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index cd29311078b5..89a6219b6ec8 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -247,12 +247,11 @@ int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
 }
 EXPORT_SYMBOL(rdma_nl_unicast);
 
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags)
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
 {
 	return nlmsg_multicast(nls, skb, 0, group, flags);
 }
-EXPORT_SYMBOL(ibnl_multicast);
+EXPORT_SYMBOL(rdma_nl_multicast);
 
 int __init rdma_nl_init(void)
 {
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 6e39a763b220..d890600f1e2d 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -862,7 +862,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
 	if (!ret)
 		ret = len;
 	else
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 9779cd5520d7..145283896417 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -67,13 +67,11 @@ int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
 /**
  * Check if there are any listeners to the netlink group
-- 
2.13.1

[PATCH rdma-next V1 05/19] RDMA/netlink: Simplify and rename ibnl_chk_listeners

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Make ibnl_chk_listeners function to be one line by removing
unneeded comparison.

Rename that function to be complaint to other functions in RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c     | 2 +-
 drivers/infiniband/core/netlink.c  | 8 +++-----
 drivers/infiniband/core/sa_query.c | 2 +-
 include/rdma/rdma_netlink.h        | 2 +-
 4 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index ebd0242bab3d..2cc23a26ce4f 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -324,7 +324,7 @@ static void queue_req(struct addr_req *req)
 static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 			  const void *daddr, u32 seq, u16 family)
 {
-	if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+	if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
 		return -EADDRNOTAVAIL;
 
 	/* We fill in what we can, the response will fill the rest */
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 89a6219b6ec8..1022ce6628ae 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -46,13 +46,11 @@ static struct {
 	const struct ibnl_client_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
-int ibnl_chk_listeners(unsigned int group)
+int rdma_nl_chk_listeners(unsigned int group)
 {
-	if (netlink_has_listeners(nls, group) == 0)
-		return -1;
-	return 0;
+	return (netlink_has_listeners(nls, group)) ? 0 : -1;
 }
-EXPORT_SYMBOL(ibnl_chk_listeners);
+EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
 static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index d890600f1e2d..c06b7deea4d2 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1419,7 +1419,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
 	if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
 	    (!(query->flags & IB_SA_QUERY_OPA))) {
-		if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
+		if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
 			if (!ib_nl_make_request(query, gfp_mask))
 				return id;
 		}
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 145283896417..b39e030b3a64 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -78,6 +78,6 @@ int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
  * @group: the netlink group ID
  * Returns 0 on success or a negative for no listeners.
  */
-int ibnl_chk_listeners(unsigned int group);
+int rdma_nl_chk_listeners(unsigned int group);
 
 #endif /* _RDMA_NETLINK_H */
-- 
2.13.1

[PATCH rdma-next V1 06/19] RDMA/netlink: Rename netlink callback struct

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

The RDMA netlink client infrastructure was removed and made
obsolete the old name (ibnl_client_cbs). This patch renames
to the more appropriate name (rdma_nl_cbs).

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/cma.c     | 2 +-
 drivers/infiniband/core/device.c  | 2 +-
 drivers/infiniband/core/iwcm.c    | 2 +-
 drivers/infiniband/core/netlink.c | 4 ++--
 include/rdma/rdma_netlink.h       | 4 ++--
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index a4013b0908e2..2af30a19b926 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4477,7 +4477,7 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct ibnl_client_cbs cma_cb_table[] = {
+static const struct rdma_nl_cbs cma_cb_table[] = {
 	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2001dabd1444..5326dcc6ede7 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1008,7 +1008,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
 		.dump = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 8599271d8be6..452a3115e3e6 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason)
 }
 EXPORT_SYMBOL(iwcm_reject_msg);
 
-static struct ibnl_client_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 1022ce6628ae..14b64e4d1e06 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -43,7 +43,7 @@
 static DEFINE_MUTEX(rdma_nl_mutex);
 static struct sock *nls;
 static struct {
-	const struct ibnl_client_cbs   *cb_table;
+	const struct rdma_nl_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 int rdma_nl_chk_listeners(unsigned int group)
@@ -83,7 +83,7 @@ static bool is_nl_valid(unsigned int type, unsigned int op)
 }
 
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[])
+		      const struct rdma_nl_cbs cb_table[])
 {
 	mutex_lock(&rdma_nl_mutex);
 	if (!is_nl_msg_valid(index, 0)) {
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index b39e030b3a64..8feeb899e2b2 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -5,7 +5,7 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };
@@ -24,7 +24,7 @@ void rdma_nl_exit(void);
  * @cb_table: A table for op->callback
  */
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[]);
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
-- 
2.13.1

[PATCH rdma-next V1 07/19] RDMA/core: Add iterator over ib_devices

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

The coming nldev needs to iterate over all IB devices in the system
and in order to not expose the ib_devices list outside the devices.c,
it is necessary to provide function iterator.

Current version is written explicitly for nldev callback to avoid
over-engineering at this stage, but it can be easily extended for
other types.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/core_priv.h |  8 ++++++++
 drivers/infiniband/core/device.c    | 25 +++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index cb7d372e4bdf..4a150c4be175 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -92,6 +92,14 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+typedef int (*nldev_callback)(struct ib_device *device,
+			      struct sk_buff *skb,
+			      struct netlink_callback *cb,
+			      unsigned int idx);
+
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb);
+
 enum ib_cache_gid_default_mode {
 	IB_CACHE_GID_DEFAULT_MODE_SET,
 	IB_CACHE_GID_DEFAULT_MODE_DELETE
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 5326dcc6ede7..7a799fc90348 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -815,6 +815,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 }
 
 /**
+ * ib_enum_all_devs - enumerate all ib_devices
+ * @cb: Callback to call for each found ib_device
+ *
+ * Enumerates all ib_devices and calls callback() on each device.
+ */
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb)
+{
+	struct ib_device *dev;
+	unsigned int idx = 0;
+	int ret = 0;
+
+	down_read(&lists_rwsem);
+	list_for_each_entry(dev, &device_list, core_list) {
+		ret = nldev_cb(dev, skb, cb, idx);
+		if (ret)
+			break;
+		idx++;
+	}
+
+	up_read(&lists_rwsem);
+	return ret;
+}
+
+/**
  * ib_query_pkey - Get P_Key table entry
  * @device:Device to query
  * @port_num:Port number to query
-- 
2.13.1

[PATCH rdma-next V1 08/19] RDMA/core: Add and expose static device index

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

This patch adds static device index in similar fashion to
already available in netdev world (struct net->ifindex).

In downstream patches, the RDMA nelink will use this idx-to-ib_device
conversion, so as part of this commit, we are exposing the translation
function to be visible for IB/core users.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/core_priv.h |  4 ++++
 drivers/infiniband/core/device.c    | 37 ++++++++++++++++++++++++++++++++++++-
 include/rdma/ib_verbs.h             |  2 ++
 3 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 4a150c4be175..291cae284771 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -184,4 +184,8 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 			     struct netlink_callback *cb);
 
+struct ib_device *__ib_device_get_by_index(u32 ifindex);
+/* RDMA device netlink */
+void nldev_init(void);
+void nldev_exit(void);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 7a799fc90348..7ff65d766d86 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -124,6 +124,17 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
+struct ib_device *__ib_device_get_by_index(u32 index)
+{
+	struct ib_device *device;
+
+	list_for_each_entry(device, &device_list, core_list)
+		if (device->index == index)
+			return device;
+
+	return NULL;
+}
+
 static struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;
@@ -135,7 +146,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 	return NULL;
 }
 
-
 static int alloc_name(char *name)
 {
 	unsigned long *inuse;
@@ -326,6 +336,30 @@ void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
 EXPORT_SYMBOL(ib_get_device_fw_str);
 
 /**
+ *	__dev_new_index	-	allocate an device index
+ *
+ *	Returns a suitable unique value for a new device interface
+ *	number.  It assumes that there are less than 2^32-1 ib devices
+ *	will be present in the system.
+ */
+static u32 __dev_new_index(void)
+{
+	/*
+	 * The device index to allow stable naming.
+	 * Similar to struct net -> ifindex.
+	 */
+	static u32 index;
+
+	for (;;) {
+		if (!(++index))
+			index = 1;
+
+		if (!__ib_device_get_by_index(index))
+			return index;
+	}
+}
+
+/**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register
  *
@@ -417,6 +451,7 @@ int ib_register_device(struct ib_device *device,
 		if (client->add && !add_client_context(device, client))
 			client->add(device);
 
+	device->index = __dev_new_index();
 	down_write(&lists_rwsem);
 	list_add_tail(&device->core_list, &device_list);
 	up_write(&lists_rwsem);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ba8314ec5768..b73120727d60 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2237,6 +2237,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this
-- 
2.13.1

[PATCH rdma-next V1 09/19] RDMA/netlink: Add and implement doit netlink callback

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

The .doit callback is used by netlink core to differentiate
between get and set operations. Common convention is to use
that call for command operations like (SET, ADD, e.t.c.) and/or
access without NLF_M_DUMP flag.

This commit adds proper declaration and implementation
to RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 19 ++++++++++++++-----
 include/rdma/rdma_netlink.h       |  2 ++
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 14b64e4d1e06..34f529cc9776 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -75,9 +75,13 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 
 static bool is_nl_valid(unsigned int type, unsigned int op)
 {
-	if (!is_nl_msg_valid(type, op) ||
-	    !rdma_nl_types[type].cb_table ||
-	    !rdma_nl_types[type].cb_table[op].dump)
+	const struct rdma_nl_cbs *cb_table;
+
+	if (!is_nl_msg_valid(type, op))
+		return false;
+
+	cb_table = rdma_nl_types[type].cb_table;
+	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
 		return false;
 	return true;
 }
@@ -152,6 +156,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
@@ -170,10 +175,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cb.nlh = nlh;
 		cb.dump = rdma_nl_types[index].cb_table[op].dump;
 		return cb.dump(skb, &cb);
+	} else {
+		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+	if (rdma_nl_types[index].cb_table[op].doit)
+		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	return ret;
 
-	c.dump = rdma_nl_types[index].cb_table[op].dump;
-	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
 /*
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 8feeb899e2b2..d6a481880f41 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -6,6 +6,8 @@
 #include <uapi/rdma/rdma_netlink.h>
 
 struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };
-- 
2.13.1

[PATCH rdma-next V1 10/19] RDMA/netlink: Reduce indirection access to cb_table

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Introduce intermediate variable to store access to fields
of cb_table.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 34f529cc9776..73c74d1cd2a3 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -156,12 +156,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	const struct rdma_nl_cbs *cb_table;
 	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	cb_table = rdma_nl_types[type].cb_table;
+
+	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
@@ -173,14 +176,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
 		cb.skb = skb;
 		cb.nlh = nlh;
-		cb.dump = rdma_nl_types[index].cb_table[op].dump;
+		cb.dump = cb_table[op].dump;
 		return cb.dump(skb, &cb);
 	} else {
-		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		c.dump = cb_table[op].dump;
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
-	if (rdma_nl_types[index].cb_table[op].doit)
-		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	if (cb_table[op].doit)
+		ret = cb_table[op].doit(skb, nlh, extack);
 	return ret;
 
 }
-- 
2.13.1

[PATCH rdma-next V1 11/19] RDMA/netlink: Convert LS to doit callback

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

RDMA_NL_LS protocol is actually does not dump anything,
but sets data and it should be handled by doit callback.

This patch actually converts RDMA_NL_LS to doit callback, while
preserving IWCM and RDMA_CM flows through netlink_dump_start().

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c      |  5 ++---
 drivers/infiniband/core/core_priv.h |  9 ++++++---
 drivers/infiniband/core/device.c    |  6 +++---
 drivers/infiniband/core/netlink.c   | 28 ++++++++++------------------
 drivers/infiniband/core/sa_query.c  |  8 ++++----
 5 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 2cc23a26ce4f..0b283029bc61 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -129,10 +129,9 @@ static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
-
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
 	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 291cae284771..8e17f8e71dc0 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -178,11 +178,14 @@ int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb);
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack);
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 
 struct ib_device *__ib_device_get_by_index(u32 ifindex);
 /* RDMA device netlink */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 7ff65d766d86..4aaf51db528a 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1070,15 +1070,15 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
+		.doit = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
+		.doit = ib_nl_handle_set_timeout,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp,
+		.doit = ib_nl_handle_ip_res_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 };
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 73c74d1cd2a3..103af358ce4e 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -154,38 +154,30 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int type = nlh->nlmsg_type;
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
-	struct netlink_callback cb = {};
-	struct netlink_dump_control c = {};
 	const struct rdma_nl_cbs *cb_table;
-	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	cb_table = rdma_nl_types[type].cb_table;
+	cb_table = rdma_nl_types[index].cb_table;
 
 	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	/*
-	 * For response or local service set_timeout request,
-	 * there is no need to use netlink_dump_start.
-	 */
-	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
-		cb.skb = skb;
-		cb.nlh = nlh;
-		cb.dump = cb_table[op].dump;
-		return cb.dump(skb, &cb);
-	} else {
-		c.dump = cb_table[op].dump;
+	/* FIXME: Convert IWCM to properly handle doit callbacks */
+	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM ||
+	    index == RDMA_NL_IWCM) {
+		struct netlink_dump_control c = {
+			.dump = cb_table[op].dump,
+		};
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+
 	if (cb_table[op].doit)
-		ret = cb_table[op].doit(skb, nlh, extack);
-	return ret;
+		return cb_table[op].doit(skb, nlh, extack);
 
+	return 0;
 }
 
 /*
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index c06b7deea4d2..42869d11e81e 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1022,9 +1022,9 @@ static void ib_nl_request_timeout(struct work_struct *work)
 }
 
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
 	const struct nlattr *attr;
 	unsigned long flags;
@@ -1098,9 +1098,9 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb)
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
 	struct ib_sa_query *query;
 	struct ib_mad_send_buf *send_buf;
-- 
2.13.1

[PATCH rdma-next V1 12/19] RDMA/netlink: Update copyright

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Add Mellanox to the copyright header.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 103af358ce4e..58b7ec213c59 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2017 Mellanox Technologies Inc.  All rights reserved.
  * Copyright (c) 2010 Voltaire Inc.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
-- 
2.13.1

[PATCH rdma-next V1 13/19] RDMA/netlink: Add netlink device definitions to UAPI

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Introduce new defines to rdma_netlink.h, so the RDMA configuration tool
will be able to communicate with RDMA subsystem by using the shared defines.

The addition of new client (NLDEV) revealed the fact that we exposed by
mistake the RDMA_NL_I40IW define which is not backed by any RDMA netlink
by now and it won't be exposed in the future too. So this patch reuses
the value and deletes the old defines.

The NLDEV operates with objects. The struct ib_device has two straightforward
objects: device itself and ports of that device.

This brings us to propose the following commands to work on those objects:
 * RDMA_NLDEV_CMD_{GET,SET,NEW,DEL} - works on ib_device itself
 * RDMA_NLDEV_CMD_PORT_{GET,SET,NEW,DEL} - works on ports of specific ib_device

Those commands receive/return the device index (RDMA_NLDEV_ATTR_DEV_INDEX)
and port index (RDMA_NLDEV_ATTR_PORT_INDEX). For device object accesses,
the RDMA_NLDEV_ATTR_PORT_INDEX will return the maximum number of ports
for specific ib_device and for port access the actual port index.

The port index starts from 1 to follow RDMA/core internal semantics and
the sysfs exposed knobs.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c |  2 +-
 include/uapi/rdma/rdma_netlink.h  | 39 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 39 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 58b7ec213c59..9b6b9b84f856 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -60,7 +60,7 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 				  RDMA_NL_IWPM_NUM_OPS,
 				  0,
 				  RDMA_NL_LS_NUM_OPS,
-				  0 };
+				  RDMA_NLDEV_NUM_OPS };
 
 	/*
 	 * This BUILD_BUG_ON is intended to catch addition of new
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 02fe8390c18f..1d064fedfa9a 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 
@@ -222,4 +222,41 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET comamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
2.13.1

[PATCH rdma-next V1 14/19] RDMA/netlink: Add nldev initialization flows

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Add nldev init and exit flows to the RDMA/core.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/Makefile |  4 +++-
 drivers/infiniband/core/device.c |  2 ++
 drivers/infiniband/core/nldev.c  | 45 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 1 deletion(-)
 create mode 100644 drivers/infiniband/core/nldev.c

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 6ebd9ad95010..d260c5ecf656 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -10,7 +10,9 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
-				multicast.o mad.o smi.o agent.o mad_rmpp.o
+				multicast.o mad.o smi.o agent.o mad_rmpp.o \
+				nldev.o
+
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 4aaf51db528a..646c98acc43b 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1128,6 +1128,7 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
+	nldev_init();
 	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 
@@ -1151,6 +1152,7 @@ static int __init ib_core_init(void)
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	nldev_exit();
 	rdma_nl_unregister(RDMA_NL_LS);
 	ib_sa_cleanup();
 	ib_mad_cleanup();
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
new file mode 100644
index 000000000000..1d1e4f214874
--- /dev/null
+++ b/drivers/infiniband/core/nldev.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <rdma/rdma_netlink.h>
+
+#include "core_priv.h"
+
+void __init nldev_init(void)
+{
+	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+}
+
+void __exit nldev_exit(void)
+{
+	rdma_nl_unregister(RDMA_NL_NLDEV);
+}
-- 
2.13.1

[PATCH rdma-next V1 15/19] RDMA/netlink: Implement nldev device dumpit calback

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

This patch adds the ability to return all available devices
together with their properties.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 64 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 1d1e4f214874..4b8b0f5d5344 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -30,13 +30,75 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/netlink.h>
 #include <rdma/rdma_netlink.h>
 
 #include "core_priv.h"
 
+static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
+	[RDMA_NLDEV_ATTR_DEV_INDEX]     = { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = IB_DEVICE_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+};
+
+static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int _nldev_get_dumpit(struct ib_device *device,
+			     struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     unsigned int idx)
+{
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+
+	if (idx < start)
+		return 0;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, NLM_F_MULTI);
+
+	if (fill_dev_info(skb, device)) {
+		nlmsg_cancel(skb, nlh);
+		goto out;
+	}
+
+	nlmsg_end(skb, nlh);
+
+	idx++;
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	/*
+	 * There is no need to take lock, because
+	 * we are relying on ib_core's lists_rwsem
+	 */
+	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
+}
+
+static const struct rdma_nl_cbs nldev_cb_table[] = {
+	[RDMA_NLDEV_CMD_GET] = {
+		.dump = nldev_get_dumpit,
+	},
+};
+
 void __init nldev_init(void)
 {
-	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+	rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
 }
 
 void __exit nldev_exit(void)
-- 
2.13.1

[PATCH rdma-next V1 16/19] RDMA/netlink: Add nldev device doit implementation

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Provide ability to query specific device.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 4b8b0f5d5344..666940f2b49a 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -53,6 +53,45 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_dev_info(msg, device);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int _nldev_get_dumpit(struct ib_device *device,
 			     struct sk_buff *skb,
 			     struct netlink_callback *cb,
@@ -92,6 +131,7 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
+		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
 };
-- 
2.13.1

[PATCH rdma-next V1 17/19] RDMA/netlink: Add nldev port dumpit implementation

[Leon Romanovsky]

From: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

This patch implements the query interface to get all
ports data for the specific device.

Signed-off-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Reviewed-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
---
 drivers/infiniband/core/nldev.c | 61 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 666940f2b49a..4413eda8c435 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -53,6 +53,18 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int fill_port_info(struct sk_buff *msg,
+			  struct ib_device *device, u32 port)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
+		return -EMSGSIZE;
+	return 0;
+}
+
 static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
@@ -129,11 +141,60 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+	u32 idx = 0;
+	u32 ifindex;
+	int err;
+	u32 p;
+
+	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, NULL);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(ifindex);
+	if (!device)
+		return -EINVAL;
+
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+		if (idx < start) {
+			idx++;
+			continue;
+		}
+
+		nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+				cb->nlh->nlmsg_seq,
+				RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+						 RDMA_NLDEV_CMD_PORT_GET),
+				0, NLM_F_MULTI);
+
+		if (fill_port_info(skb, device, p)) {
+			nlmsg_cancel(skb, nlh);
+			goto out;
+		}
+		idx++;
+		nlmsg_end(skb, nlh);
+	}
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
+	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.dump = nldev_port_get_dumpit,
+	},
 };
 
 void __init nldev_init(void)
-- 
2.13.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH rdma-next V1 18/19] RDMA/netlink: Implement nldev port doit callback

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

Provide ability to get specific to device and port information.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 44 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 4413eda8c435..2489ad9d9211 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -141,6 +141,49 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	u32 port;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (rdma_is_port_valid(device, port))
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_port_info(msg, device, port);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int nldev_port_get_dumpit(struct sk_buff *skb,
 				 struct netlink_callback *cb)
 {
@@ -193,6 +236,7 @@ static const struct rdma_nl_cbs nldev_cb_table[] = {
 		.dump = nldev_get_dumpit,
 	},
 	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.doit = nldev_port_get_doit,
 		.dump = nldev_port_get_dumpit,
 	},
 };
-- 
2.13.1

[PATCH rdma-next V1 19/19] RDMA/netlink: Expose device and port capability masks

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

The port capability mask is exposed to user space via sysfs interface,
while device capabilities are available for verbs only.

This patch provides those capabilities through netlink interface.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c  | 19 +++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h |  5 +++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 2489ad9d9211..75416f9f7747 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -50,18 +50,37 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
 		return -EMSGSIZE;
+
+	BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      device->attrs.device_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
 static int fill_port_info(struct sk_buff *msg,
 			  struct ib_device *device, u32 port)
 {
+	struct ib_port_attr attr;
+	int ret;
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
 		return -EMSGSIZE;
 	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
 		return -EMSGSIZE;
+
+	ret = ib_query_port(device, port, &attr);
+	if (ret)
+		return ret;
+
+	BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      (u64)attr.port_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 1d064fedfa9a..8fc5278d07d6 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -257,6 +257,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
 
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
2.13.1