1859 lines · 47.4 KB · C
RawDownload
/* * net/core/devlink.c - Network physical/parent device Netlink interface * * Heavily inspired by net/wireless/ * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #include <linux/kernel.h>#include <linux/module.h>#include <linux/types.h>#include <linux/slab.h>#include <linux/gfp.h>#include <linux/device.h>#include <linux/list.h>#include <linux/netdevice.h>#include <rdma/ib_verbs.h>#include <net/netlink.h>#include <net/genetlink.h>#include <net/rtnetlink.h>#include <net/net_namespace.h>#include <net/sock.h>#include <net/devlink.h>#define CREATE_TRACE_POINTS#include <trace/events/devlink.h> EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); static LIST_HEAD(devlink_list); /* devlink_mutex * * An overall lock guarding every operation coming from userspace. * It also guards devlink devices list and it is taken when * driver registers/unregisters it. */static DEFINE_MUTEX(devlink_mutex); /* devlink_port_mutex * * Shared lock to guard lists of ports in all devlink devices. */static DEFINE_MUTEX(devlink_port_mutex); static struct net *devlink_net(const struct devlink *devlink){	return read_pnet(&devlink->_net);} static void devlink_net_set(struct devlink *devlink, struct net *net){	write_pnet(&devlink->_net, net);} static struct devlink *devlink_get_from_attrs(struct net *net,					      struct nlattr **attrs){	struct devlink *devlink;	char *busname;	char *devname; 	if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME])		return ERR_PTR(-EINVAL); 	busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]);	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); 	list_for_each_entry(devlink, &devlink_list, list) {		if (strcmp(devlink->dev->bus->name, busname) == 0 &&		    strcmp(dev_name(devlink->dev), devname) == 0 &&		    net_eq(devlink_net(devlink), net))			return devlink;	} 	return ERR_PTR(-ENODEV);} static struct devlink *devlink_get_from_info(struct genl_info *info){	return devlink_get_from_attrs(genl_info_net(info), info->attrs);} static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,						      int port_index){	struct devlink_port *devlink_port; 	list_for_each_entry(devlink_port, &devlink->port_list, list) {		if (devlink_port->index == port_index)			return devlink_port;	}	return NULL;} static bool devlink_port_index_exists(struct devlink *devlink, int port_index){	return devlink_port_get_by_index(devlink, port_index);} static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,							struct nlattr **attrs){	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {		u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);		struct devlink_port *devlink_port; 		devlink_port = devlink_port_get_by_index(devlink, port_index);		if (!devlink_port)			return ERR_PTR(-ENODEV);		return devlink_port;	}	return ERR_PTR(-EINVAL);} static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,						       struct genl_info *info){	return devlink_port_get_from_attrs(devlink, info->attrs);} struct devlink_sb {	struct list_head list;	unsigned int index;	u32 size;	u16 ingress_pools_count;	u16 egress_pools_count;	u16 ingress_tc_count;	u16 egress_tc_count;}; static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb){	return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count;} static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink,						  unsigned int sb_index){	struct devlink_sb *devlink_sb; 	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {		if (devlink_sb->index == sb_index)			return devlink_sb;	}	return NULL;} static bool devlink_sb_index_exists(struct devlink *devlink,				    unsigned int sb_index){	return devlink_sb_get_by_index(devlink, sb_index);} static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink,						    struct nlattr **attrs){	if (attrs[DEVLINK_ATTR_SB_INDEX]) {		u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]);		struct devlink_sb *devlink_sb; 		devlink_sb = devlink_sb_get_by_index(devlink, sb_index);		if (!devlink_sb)			return ERR_PTR(-ENODEV);		return devlink_sb;	}	return ERR_PTR(-EINVAL);} static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink,						   struct genl_info *info){	return devlink_sb_get_from_attrs(devlink, info->attrs);} static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb,						struct nlattr **attrs,						u16 *p_pool_index){	u16 val; 	if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX])		return -EINVAL; 	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]);	if (val >= devlink_sb_pool_count(devlink_sb))		return -EINVAL;	*p_pool_index = val;	return 0;} static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,					       struct genl_info *info,					       u16 *p_pool_index){	return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs,						    p_pool_index);} static intdevlink_sb_pool_type_get_from_attrs(struct nlattr **attrs,				    enum devlink_sb_pool_type *p_pool_type){	u8 val; 	if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE])		return -EINVAL; 	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]);	if (val != DEVLINK_SB_POOL_TYPE_INGRESS &&	    val != DEVLINK_SB_POOL_TYPE_EGRESS)		return -EINVAL;	*p_pool_type = val;	return 0;} static intdevlink_sb_pool_type_get_from_info(struct genl_info *info,				   enum devlink_sb_pool_type *p_pool_type){	return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type);} static intdevlink_sb_th_type_get_from_attrs(struct nlattr **attrs,				  enum devlink_sb_threshold_type *p_th_type){	u8 val; 	if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])		return -EINVAL; 	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]);	if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC &&	    val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC)		return -EINVAL;	*p_th_type = val;	return 0;} static intdevlink_sb_th_type_get_from_info(struct genl_info *info,				 enum devlink_sb_threshold_type *p_th_type){	return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type);} static intdevlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,				   struct nlattr **attrs,				   enum devlink_sb_pool_type pool_type,				   u16 *p_tc_index){	u16 val; 	if (!attrs[DEVLINK_ATTR_SB_TC_INDEX])		return -EINVAL; 	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]);	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS &&	    val >= devlink_sb->ingress_tc_count)		return -EINVAL;	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS &&	    val >= devlink_sb->egress_tc_count)		return -EINVAL;	*p_tc_index = val;	return 0;} static intdevlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,				  struct genl_info *info,				  enum devlink_sb_pool_type pool_type,				  u16 *p_tc_index){	return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs,						  pool_type, p_tc_index);} #define DEVLINK_NL_FLAG_NEED_DEVLINK	BIT(0)#define DEVLINK_NL_FLAG_NEED_PORT	BIT(1)#define DEVLINK_NL_FLAG_NEED_SB		BIT(2)#define DEVLINK_NL_FLAG_LOCK_PORTS	BIT(3)	/* port is not needed but we need to ensure they don't	 * change in the middle of command	 */ static int devlink_nl_pre_doit(const struct genl_ops *ops,			       struct sk_buff *skb, struct genl_info *info){	struct devlink *devlink; 	mutex_lock(&devlink_mutex);	devlink = devlink_get_from_info(info);	if (IS_ERR(devlink)) {		mutex_unlock(&devlink_mutex);		return PTR_ERR(devlink);	}	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) {		info->user_ptr[0] = devlink;	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {		struct devlink_port *devlink_port; 		mutex_lock(&devlink_port_mutex);		devlink_port = devlink_port_get_from_info(devlink, info);		if (IS_ERR(devlink_port)) {			mutex_unlock(&devlink_port_mutex);			mutex_unlock(&devlink_mutex);			return PTR_ERR(devlink_port);		}		info->user_ptr[0] = devlink_port;	}	if (ops->internal_flags & DEVLINK_NL_FLAG_LOCK_PORTS) {		mutex_lock(&devlink_port_mutex);	}	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_SB) {		struct devlink_sb *devlink_sb; 		devlink_sb = devlink_sb_get_from_info(devlink, info);		if (IS_ERR(devlink_sb)) {			if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT)				mutex_unlock(&devlink_port_mutex);			mutex_unlock(&devlink_mutex);			return PTR_ERR(devlink_sb);		}		info->user_ptr[1] = devlink_sb;	}	return 0;} static void devlink_nl_post_doit(const struct genl_ops *ops,				 struct sk_buff *skb, struct genl_info *info){	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT ||	    ops->internal_flags & DEVLINK_NL_FLAG_LOCK_PORTS)		mutex_unlock(&devlink_port_mutex);	mutex_unlock(&devlink_mutex);} static struct genl_family devlink_nl_family = {	.id		= GENL_ID_GENERATE,	.name		= DEVLINK_GENL_NAME,	.version	= DEVLINK_GENL_VERSION,	.maxattr	= DEVLINK_ATTR_MAX,	.netnsok	= true,	.pre_doit	= devlink_nl_pre_doit,	.post_doit	= devlink_nl_post_doit,}; enum devlink_multicast_groups {	DEVLINK_MCGRP_CONFIG,}; static const struct genl_multicast_group devlink_nl_mcgrps[] = {	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },}; static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink){	if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name))		return -EMSGSIZE;	if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev)))		return -EMSGSIZE;	return 0;} static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,			   enum devlink_command cmd, u32 portid,			   u32 seq, int flags){	void *hdr; 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);	if (!hdr)		return -EMSGSIZE; 	if (devlink_nl_put_handle(msg, devlink))		goto nla_put_failure; 	genlmsg_end(msg, hdr);	return 0; nla_put_failure:	genlmsg_cancel(msg, hdr);	return -EMSGSIZE;} static void devlink_notify(struct devlink *devlink, enum devlink_command cmd){	struct sk_buff *msg;	int err; 	WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);	if (!msg)		return; 	err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0);	if (err) {		nlmsg_free(msg);		return;	} 	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);} static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,				struct devlink_port *devlink_port,				enum devlink_command cmd, u32 portid,				u32 seq, int flags){	void *hdr; 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);	if (!hdr)		return -EMSGSIZE; 	if (devlink_nl_put_handle(msg, devlink))		goto nla_put_failure;	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))		goto nla_put_failure;	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))		goto nla_put_failure;	if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&	    nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,			devlink_port->desired_type))		goto nla_put_failure;	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {		struct net_device *netdev = devlink_port->type_dev; 		if (netdev &&		    (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,				 netdev->ifindex) ||		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,				    netdev->name)))			goto nla_put_failure;	}	if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {		struct ib_device *ibdev = devlink_port->type_dev; 		if (ibdev &&		    nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,				   ibdev->name))			goto nla_put_failure;	}	if (devlink_port->split &&	    nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,			devlink_port->split_group))		goto nla_put_failure; 	genlmsg_end(msg, hdr);	return 0; nla_put_failure:	genlmsg_cancel(msg, hdr);	return -EMSGSIZE;} static void devlink_port_notify(struct devlink_port *devlink_port,				enum devlink_command cmd){	struct devlink *devlink = devlink_port->devlink;	struct sk_buff *msg;	int err; 	if (!devlink_port->registered)		return; 	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);	if (!msg)		return; 	err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0);	if (err) {		nlmsg_free(msg);		return;	} 	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);} static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info){	struct devlink *devlink = info->user_ptr[0];	struct sk_buff *msg;	int err; 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);	if (!msg)		return -ENOMEM; 

Lines 1–500 of 1859.