diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 3 | ||||
| -rw-r--r-- | net/core/dev.c | 34 | ||||
| -rw-r--r-- | net/core/devlink.c | 738 | ||||
| -rw-r--r-- | net/core/dst.c | 10 | ||||
| -rw-r--r-- | net/core/dst_cache.c | 168 | ||||
| -rw-r--r-- | net/core/ethtool.c | 638 | ||||
| -rw-r--r-- | net/core/filter.c | 254 | ||||
| -rw-r--r-- | net/core/flow_dissector.c | 58 | ||||
| -rw-r--r-- | net/core/hwbm.c | 87 | ||||
| -rw-r--r-- | net/core/lwtunnel.c | 37 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 18 | ||||
| -rw-r--r-- | net/core/netclassid_cgroup.c | 1 | ||||
| -rw-r--r-- | net/core/netprio_cgroup.c | 1 | ||||
| -rw-r--r-- | net/core/pktgen.c | 4 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 79 | ||||
| -rw-r--r-- | net/core/skbuff.c | 165 | ||||
| -rw-r--r-- | net/core/sock.c | 7 |
17 files changed, 2121 insertions, 181 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 0b835de04de3..d6508c2ddca5 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -24,3 +24,6 @@ obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o +obj-$(CONFIG_DST_CACHE) += dst_cache.o +obj-$(CONFIG_HWBM) += hwbm.o +obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/dev.c b/net/core/dev.c index 0ef061b2badc..edb7179bc051 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3829,8 +3829,14 @@ static void net_tx_action(struct softirq_action *h) trace_consume_skb(skb); else trace_kfree_skb(skb, net_tx_action); - __kfree_skb(skb); + + if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); + else + __kfree_skb_defer(skb); } + + __kfree_skb_flush(); } if (sd->output_queue) { @@ -4154,7 +4160,10 @@ ncls: ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { drop: - atomic_long_inc(&skb->dev->rx_dropped); + if (!deliver_exact) + atomic_long_inc(&skb->dev->rx_dropped); + else + atomic_long_inc(&skb->dev->rx_nohandler); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -5152,6 +5161,7 @@ static void net_rx_action(struct softirq_action *h) } } + __kfree_skb_flush(); local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); @@ -7253,24 +7263,31 @@ void netdev_run_todo(void) } } -/* Convert net_device_stats to rtnl_link_stats64. They have the same - * fields in the same order, with only the type differing. +/* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has + * all the same fields in the same order as net_device_stats, with only + * the type differing, but rtnl_link_stats64 may have additional fields + * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { #if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); + BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); memcpy(stats64, netdev_stats, sizeof(*stats64)); + /* zero out counters that only exist in rtnl_link_stats64 */ + memset((char *)stats64 + sizeof(*netdev_stats), 0, + sizeof(*stats64) - sizeof(*netdev_stats)); #else - size_t i, n = sizeof(*stats64) / sizeof(u64); + size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); const unsigned long *src = (const unsigned long *)netdev_stats; u64 *dst = (u64 *)stats64; - BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) != - sizeof(*stats64) / sizeof(u64)); + BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = src[i]; + /* zero out counters that only exist in rtnl_link_stats64 */ + memset((char *)stats64 + n * sizeof(u64), 0, + sizeof(*stats64) - n * sizeof(u64)); #endif } EXPORT_SYMBOL(netdev_stats_to_stats64); @@ -7300,6 +7317,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } storage->rx_dropped += atomic_long_read(&dev->rx_dropped); storage->tx_dropped += atomic_long_read(&dev->tx_dropped); + storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler); return storage; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/devlink.c b/net/core/devlink.c new file mode 100644 index 000000000000..590fa561cb7f --- /dev/null +++ b/net/core/devlink.c @@ -0,0 +1,738 @@ +/* + * 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> + +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); +} + +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) + +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); + } + info->user_ptr[0] = devlink; + 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[1] = devlink_port; + } + 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) + 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; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_PORT_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_port *devlink_port; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + mutex_lock(&devlink_port_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) + goto out; + idx++; + } + } +out: + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_port_type_set(struct devlink *devlink, + struct devlink_port *devlink_port, + enum devlink_port_type port_type) + +{ + int err; + + if (devlink->ops && devlink->ops->port_type_set) { + if (port_type == DEVLINK_PORT_TYPE_NOTSET) + return -EINVAL; + err = devlink->ops->port_type_set(devlink_port, port_type); + if (err) + return err; + devlink_port->desired_type = port_type; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; + } + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + int err; + + if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { + enum devlink_port_type port_type; + + port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); + err = devlink_port_type_set(devlink, devlink_port, port_type); + if (err) + return err; + } + return 0; +} + +static int devlink_port_split(struct devlink *devlink, + u32 port_index, u32 count) + +{ + if (devlink->ops && devlink->ops->port_split) + return devlink->ops->port_split(devlink, port_index, count); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + u32 count; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] || + !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); + return devlink_port_split(devlink, port_index, count); +} + +static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) + +{ + if (devlink->ops && devlink->ops->port_unsplit) + return devlink->ops->port_unsplit(devlink, port_index); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + return devlink_port_unsplit(devlink, port_index); +} + +static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, +}; + +static const struct genl_ops devlink_nl_ops[] = { + { + .cmd = DEVLINK_CMD_GET, + .doit = devlink_nl_cmd_get_doit, + .dumpit = devlink_nl_cmd_get_dumpit, + .policy = devlink_nl_policy, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_GET, + .doit = devlink_nl_cmd_port_get_doit, + .dumpit = devlink_nl_cmd_port_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_SET, + .doit = devlink_nl_cmd_port_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .doit = devlink_nl_cmd_port_split_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .doit = devlink_nl_cmd_port_unsplit_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, +}; + +/** + * devlink_alloc - Allocate new devlink instance resources + * + * @ops: ops + * @priv_size: size of user private data + * + * Allocate new devlink instance resources, including devlink index + * and name. + */ +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) +{ + struct devlink *devlink; + + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + if (!devlink) + return NULL; + devlink->ops = ops; + devlink_net_set(devlink, &init_net); + INIT_LIST_HEAD(&devlink->port_list); + return devlink; +} +EXPORT_SYMBOL_GPL(devlink_alloc); + +/** + * devlink_register - Register devlink instance + * + * @devlink: devlink + */ +int devlink_register(struct devlink *devlink, struct device *dev) +{ + mutex_lock(&devlink_mutex); + devlink->dev = dev; + list_add_tail(&devlink->list, &devlink_list); + devlink_notify(devlink, DEVLINK_CMD_NEW); + mutex_unlock(&devlink_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_register); + +/** + * devlink_unregister - Unregister devlink instance + * + * @devlink: devlink + */ +void devlink_unregister(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink_notify(devlink, DEVLINK_CMD_DEL); + list_del(&devlink->list); + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_unregister); + +/** + * devlink_free - Free devlink instance resources + * + * @devlink: devlink + */ +void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} +EXPORT_SYMBOL_GPL(devlink_free); + +/** + * devlink_port_register - Register devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * @port_index + * + * Register devlink port with provided port index. User can use + * any indexing, even hw-related one. devlink_port structure + * is convenient to be embedded inside user driver private structure. + * Note that the caller should take care of zeroing the devlink_port + * structure. + */ +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + mutex_lock(&devlink_port_mutex); + if (devlink_port_index_exists(devlink, port_index)) { + mutex_unlock(&devlink_port_mutex); + return -EEXIST; + } + devlink_port->devlink = devlink; + devlink_port->index = port_index; + devlink_port->type = DEVLINK_PORT_TYPE_NOTSET; + devlink_port->registered = true; + list_add_tail(&devlink_port->list, &devlink->port_list); + mutex_unlock(&devlink_port_mutex); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_port_register); + +/** + * devlink_port_unregister - Unregister devlink port + * + * @devlink_port: devlink port + */ +void devlink_port_unregister(struct devlink_port *devlink_port) +{ + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + mutex_lock(&devlink_port_mutex); + list_del(&devlink_port->list); + mutex_unlock(&devlink_port_mutex); +} +EXPORT_SYMBOL_GPL(devlink_port_unregister); + +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + devlink_port->type = type; + devlink_port->type_dev = type_dev; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_ETH, netdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); + +/** + * devlink_port_type_ib_set - Set port type to InfiniBand + * + * @devlink_port: devlink port + * @ibdev: related IB device + */ +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_IB, ibdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); + +/** + * devlink_port_type_clear - Clear port type + * + * @devlink_port: devlink port + */ +void devlink_port_type_clear(struct devlink_port *devlink_port) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_NOTSET, NULL); +} +EXPORT_SYMBOL_GPL(devlink_port_type_clear); + +/** + * devlink_port_split_set - Set port is split + * + * @devlink_port: devlink port + * @split_group: split group - identifies group split port is part of + */ +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ + devlink_port->split = true; + devlink_port->split_group = split_group; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_split_set); + +static int __init devlink_module_init(void) +{ + return genl_register_family_with_ops_groups(&devlink_nl_family, + devlink_nl_ops, + devlink_nl_mcgrps); +} + +static void __exit devlink_module_exit(void) +{ + genl_unregister_family(&devlink_nl_family); +} + +module_init(devlink_module_init); +module_exit(devlink_module_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); +MODULE_DESCRIPTION("Network physical device Netlink interface"); +MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME); diff --git a/net/core/dst.c b/net/core/dst.c index a1656e3b8d72..b5cbbe07f786 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -265,7 +265,7 @@ again: lwtstate_put(dst->lwtstate); if (dst->flags & DST_METADATA) - kfree(dst); + metadata_dst_free((struct metadata_dst *)dst); else kmem_cache_free(dst->ops->kmem_cachep, dst); @@ -395,6 +395,14 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) } EXPORT_SYMBOL_GPL(metadata_dst_alloc); +void metadata_dst_free(struct metadata_dst *md_dst) +{ +#ifdef CONFIG_DST_CACHE + dst_cache_destroy(&md_dst->u.tun_info.dst_cache); +#endif + kfree(md_dst); +} + struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) { int cpu; diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c new file mode 100644 index 000000000000..554d36449231 --- /dev/null +++ b/net/core/dst_cache.c @@ -0,0 +1,168 @@ +/* + * net/core/dst_cache.c - dst entry cache + * + * Copyright (c) 2016 Paolo Abeni <pabeni@redhat.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/percpu.h> +#include <net/dst_cache.h> +#include <net/route.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ip6_fib.h> +#endif +#include <uapi/linux/in.h> + +struct dst_cache_pcpu { + unsigned long refresh_ts; + struct dst_entry *dst; + u32 cookie; + union { + struct in_addr in_saddr; + struct in6_addr in6_saddr; + }; +}; + +static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, + struct dst_entry *dst, u32 cookie) +{ + dst_release(dst_cache->dst); + if (dst) + dst_hold(dst); + + dst_cache->cookie = cookie; + dst_cache->dst = dst; +} + +static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, + struct dst_cache_pcpu *idst) +{ + struct dst_entry *dst; + + dst = idst->dst; + if (!dst) + goto fail; + + /* the cache already hold a dst reference; it can't go away */ + dst_hold(dst); + + if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) || + (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { + dst_cache_per_cpu_dst_set(idst, NULL, 0); + dst_release(dst); + goto fail; + } + return dst; + +fail: + idst->refresh_ts = jiffies; + return NULL; +} + +struct dst_entry *dst_cache_get(struct dst_cache *dst_cache) +{ + if (!dst_cache->cache) + return NULL; + + return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache)); +} +EXPORT_SYMBOL_GPL(dst_cache_get); + +struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr) +{ + struct dst_cache_pcpu *idst; + struct dst_entry *dst; + + if (!dst_cache->cache) + return NULL; + + idst = this_cpu_ptr(dst_cache->cache); + dst = dst_cache_per_cpu_get(dst_cache, idst); + if (!dst) + return NULL; + + *saddr = idst->in_saddr.s_addr; + return container_of(dst, struct rtable, dst); +} +EXPORT_SYMBOL_GPL(dst_cache_get_ip4); + +void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, + __be32 saddr) +{ + struct dst_cache_pcpu *idst; + + if (!dst_cache->cache) + return; + + idst = this_cpu_ptr(dst_cache->cache); + dst_cache_per_cpu_dst_set(idst, dst, 0); + idst->in_saddr.s_addr = saddr; +} +EXPORT_SYMBOL_GPL(dst_cache_set_ip4); + +#if IS_ENABLED(CONFIG_IPV6) +void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, + const struct in6_addr *addr) +{ + struct dst_cache_pcpu *idst; + + if (!dst_cache->cache) + return; + + idst = this_cpu_ptr(dst_cache->cache); + dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, + rt6_get_cookie((struct rt6_info *)dst)); + idst->in6_saddr = *addr; +} +EXPORT_SYMBOL_GPL(dst_cache_set_ip6); + +struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, + struct in6_addr *saddr) +{ + struct dst_cache_pcpu *idst; + struct dst_entry *dst; + + if (!dst_cache->cache) + return NULL; + + idst = this_cpu_ptr(dst_cache->cache); + dst = dst_cache_per_cpu_get(dst_cache, idst); + if (!dst) + return NULL; + + *saddr = idst->in6_saddr; + return dst; +} +EXPORT_SYMBOL_GPL(dst_cache_get_ip6); +#endif + +int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp) +{ + dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu, + gfp | __GFP_ZERO); + if (!dst_cache->cache) + return -ENOMEM; + + dst_cache_reset(dst_cache); + return 0; +} +EXPORT_SYMBOL_GPL(dst_cache_init); + +void dst_cache_destroy(struct dst_cache *dst_cache) +{ + int i; + + if (!dst_cache->cache) + return; + + for_each_possible_cpu(i) + dst_release(per_cpu_ptr(dst_cache->cache, i)->dst); + + free_percpu(dst_cache->cache); +} +EXPORT_SYMBOL_GPL(dst_cache_destroy); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index daf04709dd3c..f426c5ad6149 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -98,6 +98,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_BUSY_POLL_BIT] = "busy-poll", + [NETIF_F_HW_TC_BIT] = "hw-tc-offload", }; static const char @@ -386,43 +387,461 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } -int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static void convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) { + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); + dst[0] = legacy_u32; +} + +/* return false if src had higher bits set. lower bits always updated. */ +static bool convert_link_mode_to_legacy_u32(u32 *legacy_u32, + const unsigned long *src) +{ + bool retval = true; + + /* TODO: following test will soon always be true */ + if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); + + bitmap_zero(ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_fill(ext, 32); + bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + if (bitmap_intersects(ext, src, + __ETHTOOL_LINK_MODE_MASK_NBITS)) { + /* src mask goes beyond bit 31 */ + retval = false; + } + } + *legacy_u32 = src[0]; + return retval; +} + +/* return false if legacy contained non-0 deprecated fields + * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + */ +static bool +convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings) +{ + bool retval = true; + + memset(link_ksettings, 0, sizeof(*link_ksettings)); + + /* This is used to tell users that driver is still using these + * deprecated legacy fields, and they should not use + * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS + */ + if (legacy_settings->transceiver || + legacy_settings->maxtxpkt || + legacy_settings->maxrxpkt) + retval = false; + + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.supported, + legacy_settings->supported); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.advertising, + legacy_settings->advertising); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.lp_advertising, + legacy_settings->lp_advertising); + link_ksettings->base.speed + = ethtool_cmd_speed(legacy_settings); + link_ksettings->base.duplex + = legacy_settings->duplex; + link_ksettings->base.port + = legacy_settings->port; + link_ksettings->base.phy_address + = legacy_settings->phy_address; + link_ksettings->base.autoneg + = legacy_settings->autoneg; + link_ksettings->base.mdio_support + = legacy_settings->mdio_support; + link_ksettings->base.eth_tp_mdix + = legacy_settings->eth_tp_mdix; + link_ksettings->base.eth_tp_mdix_ctrl + = legacy_settings->eth_tp_mdix_ctrl; + return retval; +} + +/* return false if ksettings link modes had higher bits + * set. legacy_settings always updated (best effort) + */ +static bool +convert_link_ksettings_to_legacy_settings( + struct ethtool_cmd *legacy_settings, + const struct ethtool_link_ksettings *link_ksettings) +{ + bool retval = true; + + memset(legacy_settings, 0, sizeof(*legacy_settings)); + /* this also clears the deprecated fields in legacy structure: + * __u8 transceiver; + * __u32 maxtxpkt; + * __u32 maxrxpkt; + */ + + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->supported, + link_ksettings->link_modes.supported); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->advertising, + link_ksettings->link_modes.advertising); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->lp_advertising, + link_ksettings->link_modes.lp_advertising); + ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed); + legacy_settings->duplex + = link_ksettings->base.duplex; + legacy_settings->port + = link_ksettings->base.port; + legacy_settings->phy_address + = link_ksettings->base.phy_address; + legacy_settings->autoneg + = link_ksettings->base.autoneg; + legacy_settings->mdio_support + = link_ksettings->base.mdio_support; + legacy_settings->eth_tp_mdix + = link_ksettings->base.eth_tp_mdix; + legacy_settings->eth_tp_mdix_ctrl + = link_ksettings->base.eth_tp_mdix_ctrl; + return retval; +} + +/* number of 32-bit words to store the user's link mode bitmaps */ +#define __ETHTOOL_LINK_MODE_MASK_NU32 \ + DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) + +/* layout of the struct passed from/to userland */ +struct ethtool_link_usettings { + struct ethtool_link_settings base; + struct { + __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + } link_modes; +}; + +/* Internal kernel helper to query a device ethtool_link_settings. + * + * Backward compatibility note: for compatibility with legacy drivers + * that implement only the ethtool_cmd API, this has to work with both + * drivers implementing get_link_ksettings API and drivers + * implementing get_settings API. When drivers implement get_settings + * and report ethtool_cmd deprecated fields + * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored + * because the resulting struct ethtool_link_settings does not report them. + */ +int __ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + int err; + struct ethtool_cmd cmd; + ASSERT_RTNL(); + if (dev->ethtool_ops->get_link_ksettings) { + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, + link_ksettings); + } + + /* driver doesn't support %ethtool_link_ksettings API. revert to + * legacy %ethtool_cmd API, unless it's not supported either. + * TODO: remove when ethtool_ops::get_settings disappears internally + */ if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; - memset(cmd, 0, sizeof(struct ethtool_cmd)); - cmd->cmd = ETHTOOL_GSET; - return dev->ethtool_ops->get_settings(dev, cmd); + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); + if (err < 0) + return err; + + /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt + */ + convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); + return err; } -EXPORT_SYMBOL(__ethtool_get_settings); +EXPORT_SYMBOL(__ethtool_get_link_ksettings); -static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +/* convert ethtool_link_usettings in user space to a kernel internal + * ethtool_link_ksettings. return 0 on success, errno on error. + */ +static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, + const void __user *from) { - int err; - struct ethtool_cmd cmd; + struct ethtool_link_usettings link_usettings; + + if (copy_from_user(&link_usettings, from, sizeof(link_usettings))) + return -EFAULT; + + memcpy(&to->base, &link_usettings.base, sizeof(to->base)); + bitmap_from_u32array(to->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + + return 0; +} + +/* convert a kernel internal ethtool_link_ksettings to + * ethtool_link_usettings in user space. return 0 on success, errno on + * error. + */ +static int +store_link_ksettings_for_user(void __user *to, + const struct ethtool_link_ksettings *from) +{ + struct ethtool_link_usettings link_usettings; + + memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + bitmap_to_u32array(link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) + return -EFAULT; + + return 0; +} + +/* Query device for its ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::get_link_ksettings, even if legacy + * ethtool_ops::get_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_GSET for + * this driver, so that they can correctly access the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_get_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err = 0; + struct ethtool_link_ksettings link_ksettings; - err = __ethtool_get_settings(dev, &cmd); + ASSERT_RTNL(); + + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; + + /* handle bitmap nbits handshake */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) { + /* wrong link mode nbits requested */ + memset(&link_ksettings, 0, sizeof(link_ksettings)); + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; + /* send back number of words required as negative val */ + compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, + "need too many bits for link modes!"); + link_ksettings.base.link_mode_masks_nwords + = -((s8)__ETHTOOL_LINK_MODE_MASK_NU32); + + /* copy the base fields back to user, not the link + * mode bitmaps + */ + if (copy_to_user(useraddr, &link_ksettings.base, + sizeof(link_ksettings.base))) + return -EFAULT; + + return 0; + } + + /* handshake successful: user/kernel agree on + * link_mode_masks_nwords + */ + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); if (err < 0) return err; + /* make sure we tell the right values to user */ + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + + return store_link_ksettings_for_user(useraddr, &link_ksettings); +} + +/* Update device ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::set_link_ksettings, even if legacy + * ethtool_ops::set_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_SSET for + * this driver, so that they can correctly update the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_set_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + /* make sure nbits field has expected value */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + /* copy the whole structure, now that we know it has expected + * format + */ + err = load_link_ksettings_from_user(&link_ksettings, useraddr); + if (err) + return err; + + /* re-check nwords field, just in case */ + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); +} + +static void +warn_incomplete_ethtool_legacy_settings_conversion(const char *details) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", + get_task_comm(name, current), details); +} + +/* Query device for its ethtool_cmd settings. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing get_link_ksettings + * API and drivers implementing get_settings API. When drivers + * implement get_link_ksettings and report higher link mode bits, a + * kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful + * (only the lower link mode bits reported back to user). + */ +static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_cmd cmd; + + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + /* First, use link_ksettings API if it is supported */ + int err; + struct ethtool_link_ksettings link_ksettings; + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, + &link_ksettings); + if (err < 0) + return err; + if (!convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings)) + warn_incomplete_ethtool_legacy_settings_conversion( + "link modes are only partially reported"); + + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; + } else { + /* driver doesn't support %ethtool_link_ksettings + * API. revert to legacy %ethtool_cmd API, unless it's + * not supported either. + */ + int err; + + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); + if (err < 0) + return err; + } + if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; + return 0; } +/* Update device link settings with given ethtool_cmd. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing set_link_ksettings + * API and drivers implementing set_settings API. When drivers + * implement set_link_ksettings and user's request updates deprecated + * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, and the request is rejected. + */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd; - if (!dev->ethtool_ops->set_settings) - return -EOPNOTSUPP; + ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + /* first, try new %ethtool_link_ksettings API. */ + if (dev->ethtool_ops->set_link_ksettings) { + struct ethtool_link_ksettings link_ksettings; + + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, + &cmd)) + return -EINVAL; + + link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, + &link_ksettings); + } + + /* legacy %ethtool_cmd API */ + + /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings + * disappears internally + */ + + if (!dev->ethtool_ops->set_settings) + return -EOPNOTSUPP; + return dev->ethtool_ops->set_settings(dev, &cmd); } @@ -632,7 +1051,7 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, return 0; } -u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; +u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len) { @@ -642,6 +1061,37 @@ void netdev_rss_key_fill(void *buffer, size_t len) } EXPORT_SYMBOL(netdev_rss_key_fill); +static int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) +{ + u32 dev_size, current_max = 0; + u32 *indir; + int ret; + + if (!dev->ethtool_ops->get_rxfh_indir_size || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (dev_size == 0) + return -EOPNOTSUPP; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); + if (!indir) + return -ENOMEM; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); + if (ret) + goto out; + + while (dev_size--) + current_max = max(current_max, indir[dev_size]); + + *max = current_max; + +out: + kfree(indir); + return ret; +} + static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { @@ -738,6 +1188,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE); + if (ret) + goto out; + + /* indicate whether rxfh was set to default */ + if (user_size == 0) + dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + else + dev->priv_flags |= IFF_RXFH_CONFIGURED; out: kfree(indir); @@ -897,6 +1355,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc); + if (ret) + goto out; + + /* indicate whether rxfh was set to default */ + if (rxfh.indir_size == 0) + dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) + dev->priv_flags |= IFF_RXFH_CONFIGURED; out: kfree(rss_config); @@ -1227,14 +1693,31 @@ static noinline_for_stack int ethtool_get_channels(struct net_device *dev, static noinline_for_stack int ethtool_set_channels(struct net_device *dev, void __user *useraddr) { - struct ethtool_channels channels; + struct ethtool_channels channels, max; + u32 max_rx_in_use = 0; - if (!dev->ethtool_ops->set_channels) + if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels) return -EOPNOTSUPP; if (copy_from_user(&channels, useraddr, sizeof(channels))) return -EFAULT; + dev->ethtool_ops->get_channels(dev, &max); + + /* ensure new counts are within the maximums */ + if ((channels.rx_count > max.max_rx) || + (channels.tx_count > max.max_tx) || + (channels.combined_count > max.max_combined) || + (channels.other_count > max.max_other)) + return -EINVAL; + + /* ensure the new Rx count fits within the configured Rx flow + * indirection table settings */ + if (netif_is_rxfh_configured(dev) && + !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && + (channels.combined_count + channels.rx_count) <= max_rx_in_use) + return -EINVAL; + return dev->ethtool_ops->set_channels(dev, &channels); } @@ -1823,13 +2306,121 @@ out: return ret; } +static int ethtool_get_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int ret; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if (!dev->ethtool_ops->get_per_queue_coalesce) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + return ret; + if (copy_to_user(useraddr, &coalesce, sizeof(coalesce))) + return -EFAULT; + useraddr += sizeof(coalesce); + } + + return 0; +} + +static int ethtool_set_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int i, ret = 0; + int n_queue; + struct ethtool_coalesce *backup = NULL, *tmp = NULL; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if ((!dev->ethtool_ops->set_per_queue_coalesce) || + (!dev->ethtool_ops->get_per_queue_coalesce)) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE); + tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL); + if (!backup) + return -ENOMEM; + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, tmp); + if (ret != 0) + goto roll_back; + + tmp++; + + if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) { + ret = -EFAULT; + goto roll_back; + } + + ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + goto roll_back; + + useraddr += sizeof(coalesce); + } + +roll_back: + if (ret != 0) { + tmp = backup; + for_each_set_bit(i, queue_mask, bit) { + dev->ethtool_ops->set_per_queue_coalesce(dev, i, tmp); + tmp++; + } + } + kfree(backup); + + return ret; +} + +static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_per_queue_op per_queue_opt; + + if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt))) + return -EFAULT; + + switch (per_queue_opt.sub_command) { + case ETHTOOL_GCOALESCE: + return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); + case ETHTOOL_SCOALESCE: + return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt); + default: + return -EOPNOTSUPP; + }; +} + /* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); void __user *useraddr = ifr->ifr_data; - u32 ethcmd; + u32 ethcmd, sub_cmd; int rc; netdev_features_t old_features; @@ -1839,8 +2430,14 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; + if (ethcmd == ETHTOOL_PERQUEUE) { + if (copy_from_user(&sub_cmd, useraddr + sizeof(ethcmd), sizeof(sub_cmd))) + return -EFAULT; + } else { + sub_cmd = ethcmd; + } /* Allow some commands to be done by anyone */ - switch (ethcmd) { + switch (sub_cmd) { case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: @@ -2070,6 +2667,15 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPHYSTATS: rc = ethtool_get_phy_stats(dev, useraddr); break; + case ETHTOOL_PERQUEUE: + rc = ethtool_set_per_queue(dev, useraddr); + break; + case ETHTOOL_GLINKSETTINGS: + rc = ethtool_get_link_ksettings(dev, useraddr); + break; + case ETHTOOL_SLINKSETTINGS: + rc = ethtool_set_link_ksettings(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/filter.c b/net/core/filter.c index bba502f7cd57..b7177d01ecb0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -530,12 +530,14 @@ do_pass: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; - /* RET_K, RET_A are remaped into 2 insns. */ + /* RET_K is remaped into 2 insns. RET_A case doesn't need an + * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. + */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: - *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ? - BPF_K : BPF_X, BPF_REG_0, - BPF_REG_A, fp->k); + if (BPF_RVAL(fp->code) == BPF_K) + *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, + 0, fp->k); *insn = BPF_EXIT_INSN(); break; @@ -1181,7 +1183,7 @@ static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk) if (bpf_prog_size(prog->len) > sysctl_optmem_max) return -ENOMEM; - if (sk_unhashed(sk)) { + if (sk_unhashed(sk) && sk->sk_reuseport) { err = reuseport_alloc(sk); if (err) return err; @@ -1333,18 +1335,25 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) return 0; } -#define BPF_LDST_LEN 16U +struct bpf_scratchpad { + union { + __be32 diff[MAX_BPF_STACK / sizeof(__be32)]; + u8 buff[MAX_BPF_STACK]; + }; +}; + +static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { + struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); struct sk_buff *skb = (struct sk_buff *) (long) r1; int offset = (int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; - char buf[BPF_LDST_LEN]; void *ptr; - if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM))) + if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; /* bpf verifier guarantees that: @@ -1355,14 +1364,12 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) * * so check for invalid 'offset' and too large 'len' */ - if (unlikely((u32) offset > 0xffff || len > sizeof(buf))) + if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + len))) + if (unlikely(skb_try_make_writable(skb, offset + len))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, len, buf); + ptr = skb_header_pointer(skb, offset, len, sp->buff); if (unlikely(!ptr)) return -EFAULT; @@ -1371,17 +1378,19 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) memcpy(ptr, from, len); - if (ptr == buf) + if (ptr == sp->buff) /* skb_store_bits cannot return -EFAULT here */ skb_store_bits(skb, offset, ptr, len); if (flags & BPF_F_RECOMPUTE_CSUM) skb_postpush_rcsum(skb, ptr, len); + if (flags & BPF_F_INVALIDATE_HASH) + skb_clear_hash(skb); return 0; } -const struct bpf_func_proto bpf_skb_store_bytes_proto = { +static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1400,7 +1409,7 @@ static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely((u32) offset > 0xffff || len > BPF_LDST_LEN)) + if (unlikely((u32) offset > 0xffff || len > MAX_BPF_STACK)) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, to); @@ -1412,7 +1421,7 @@ static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_load_bytes_proto = { +static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1432,9 +1441,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1442,6 +1449,12 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EFAULT; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + csum_replace_by_diff(ptr, to); + break; case 2: csum_replace2(ptr, from, to); break; @@ -1459,7 +1472,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l3_csum_replace_proto = { +static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1474,23 +1487,31 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; + bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; int offset = (int) r2; __sum16 sum, *ptr; - if (unlikely(flags & ~(BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) + if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | + BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); if (unlikely(!ptr)) return -EFAULT; + if (is_mmzero && !*ptr) + return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo); + break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; @@ -1501,6 +1522,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } + if (is_mmzero && !*ptr) + *ptr = CSUM_MANGLED_0; if (ptr == &sum) /* skb_store_bits guaranteed to not return -EFAULT here */ skb_store_bits(skb, offset, ptr, sizeof(sum)); @@ -1508,7 +1531,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l4_csum_replace_proto = { +static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1519,6 +1542,45 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; +static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) +{ + struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); + u64 diff_size = from_size + to_size; + __be32 *from = (__be32 *) (long) r1; + __be32 *to = (__be32 *) (long) r3; + int i, j = 0; + + /* This is quite flexible, some examples: + * + * from_size == 0, to_size > 0, seed := csum --> pushing data + * from_size > 0, to_size == 0, seed := csum --> pulling data + * from_size > 0, to_size > 0, seed := 0 --> diffing data + * + * Even for diffing, from_size and to_size don't need to be equal. + */ + if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) || + diff_size > sizeof(sp->diff))) + return -EINVAL; + + for (i = 0; i < from_size / sizeof(__be32); i++, j++) + sp->diff[j] = ~from[i]; + for (i = 0; i < to_size / sizeof(__be32); i++, j++) + sp->diff[j] = to[i]; + + return csum_partial(sp->diff, diff_size, seed); +} + +static const struct bpf_func_proto bpf_csum_diff_proto = { + .func = bpf_csum_diff, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_STACK, + .arg4_type = ARG_CONST_STACK_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, +}; + static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; @@ -1543,11 +1605,10 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) } skb2->dev = dev; - skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } -const struct bpf_func_proto bpf_clone_redirect_proto = { +static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1596,11 +1657,10 @@ int skb_do_redirect(struct sk_buff *skb) } skb->dev = dev; - skb_sender_cpu_clear(skb); return dev_queue_xmit(skb); } -const struct bpf_func_proto bpf_redirect_proto = { +static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1622,14 +1682,7 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { -#ifdef CONFIG_IP_ROUTE_CLASSID - const struct dst_entry *dst; - - dst = skb_dst((struct sk_buff *) (unsigned long) r1); - if (dst) - return dst->tclassid; -#endif - return 0; + return dst_tclassid((struct sk_buff *) (unsigned long) r1); } static const struct bpf_func_proto bpf_get_route_realm_proto = { @@ -1682,6 +1735,13 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_vlan_pop) return true; + if (func == bpf_skb_store_bytes) + return true; + if (func == bpf_l3_csum_replace) + return true; + if (func == bpf_l4_csum_replace) + return true; + return false; } @@ -1703,12 +1763,15 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EPROTO; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): + goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; +set_compat: to = (struct bpf_tunnel_key *)compat; break; default: @@ -1720,11 +1783,13 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; - if (flags & BPF_F_TUNINFO_IPV6) + if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); - else + to->tunnel_label = be32_to_cpu(info->key.label); + } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); + } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy((void *)(long) r2, to, size); @@ -1732,7 +1797,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1742,6 +1807,32 @@ const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; +static u64 bpf_skb_get_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *to = (u8 *) (long) r2; + const struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(!info || + !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) + return -ENOENT; + if (unlikely(size < info->options_len)) + return -ENOMEM; + + ip_tunnel_info_opts_get(to, info); + + return info->options_len; +} + +static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { + .func = bpf_skb_get_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + static struct metadata_dst __percpu *md_dst; static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) @@ -1752,10 +1843,12 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_DONT_FRAGMENT))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. @@ -1768,6 +1861,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EINVAL; } } + if (unlikely(!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label)) + return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); @@ -1776,7 +1871,10 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + if (flags & BPF_F_DONT_FRAGMENT) + info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; + info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1785,6 +1883,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); + info->key.label = cpu_to_be32(from->tunnel_label) & + IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); if (flags & BPF_F_ZERO_CSUM_TX) @@ -1794,7 +1894,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1804,17 +1904,53 @@ const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void) +static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *from = (u8 *) (long) r2; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + const struct metadata_dst *md = this_cpu_ptr(md_dst); + + if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) + return -EINVAL; + if (unlikely(size > IP_TUNNEL_OPTS_MAX)) + return -ENOMEM; + + ip_tunnel_info_opts_set(info, from, size); + + return 0; +} + +static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { + .func = bpf_skb_set_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto * +bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* race is not possible, since it's called from - * verifier that is holding verifier mutex + /* Race is not possible, since it's called from verifier + * that is holding verifier mutex. */ - md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL); + md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + GFP_KERNEL); if (!md_dst) return NULL; } - return &bpf_skb_set_tunnel_key_proto; + + switch (which) { + case BPF_FUNC_skb_set_tunnel_key: + return &bpf_skb_set_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return &bpf_skb_set_tunnel_opt_proto; + default: + return NULL; + } } static const struct bpf_func_proto * @@ -1851,6 +1987,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_csum_diff: + return &bpf_csum_diff_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: @@ -1866,7 +2004,11 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: - return bpf_get_skb_set_tunnel_key_proto(); + return bpf_get_skb_set_tunnel_proto(func_id); + case BPF_FUNC_skb_get_tunnel_opt: + return &bpf_skb_get_tunnel_opt_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_get_route_realm: @@ -1915,16 +2057,14 @@ static bool sk_filter_is_valid_access(int off, int size, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type) { - if (off == offsetof(struct __sk_buff, tc_classid)) - return type == BPF_WRITE ? true : false; - if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, mark): case offsetof(struct __sk_buff, tc_index): case offsetof(struct __sk_buff, priority): case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]): + case offsetof(struct __sk_buff, tc_classid): break; default: return false; @@ -2041,8 +2181,10 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, ctx_off -= offsetof(struct __sk_buff, tc_classid); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); - WARN_ON(type != BPF_WRITE); - *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + else + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, ctx_off); break; case offsetof(struct __sk_buff, tc_index): diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 12e700332010..a669dea146c6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -19,25 +19,12 @@ #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> -static bool dissector_uses_key(const struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) -{ - return flow_dissector->used_keys & (1 << key_id); -} - static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } -static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id, - void *target_container) -{ - return ((char *) target_container) + flow_dissector->offset[key_id]; -} - void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) @@ -178,15 +165,16 @@ ip: ip_proto = iph->protocol; - if (!dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS)) - break; + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + target_container); - key_addrs = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); - memcpy(&key_addrs->v4addrs, &iph->saddr, - sizeof(key_addrs->v4addrs)); - key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + memcpy(&key_addrs->v4addrs, &iph->saddr, + sizeof(key_addrs->v4addrs)); + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + } if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; @@ -219,13 +207,12 @@ ipv6: if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs; - - key_ipv6_addrs = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - target_container); + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + target_container); - memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs)); + memcpy(&key_addrs->v6addrs, &iph->saddr, + sizeof(key_addrs->v6addrs)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } @@ -339,8 +326,11 @@ mpls: } case htons(ETH_P_FCOE): - key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN); - /* fall through */ + if ((hlen - nhoff) < FCOE_HEADER_LEN) + goto out_bad; + + nhoff += FCOE_HEADER_LEN; + goto out_good; default: goto out_bad; } @@ -447,13 +437,12 @@ ip_proto_again: key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); + ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; - if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { - ip_proto = fh->nexthdr; + if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) goto ip_proto_again; - } } goto out_good; } @@ -740,6 +729,11 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data, { u32 poff = keys->control.thoff; + /* skip L4 headers for fragments after the first */ + if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && + !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) + return poff; + switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ diff --git a/net/core/hwbm.c b/net/core/hwbm.c new file mode 100644 index 000000000000..941c28486896 --- /dev/null +++ b/net/core/hwbm.c @@ -0,0 +1,87 @@ +/* Support for hardware buffer manager. + * + * Copyright (C) 2016 Marvell + * + * Gregory CLEMENT <gregory.clement@free-electrons.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/printk.h> +#include <linux/skbuff.h> +#include <net/hwbm.h> + +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) +{ + if (likely(bm_pool->frag_size <= PAGE_SIZE)) + skb_free_frag(buf); + else + kfree(buf); +} +EXPORT_SYMBOL_GPL(hwbm_buf_free); + +/* Refill processing for HW buffer management */ +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) +{ + int frag_size = bm_pool->frag_size; + void *buf; + + if (likely(frag_size <= PAGE_SIZE)) + buf = netdev_alloc_frag(frag_size); + else + buf = kmalloc(frag_size, gfp); + + if (!buf) + return -ENOMEM; + + if (bm_pool->construct) + if (bm_pool->construct(bm_pool, buf)) { + hwbm_buf_free(bm_pool, buf); + return -ENOMEM; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hwbm_pool_refill); + +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +{ + int err, i; + unsigned long flags; + + spin_lock_irqsave(&bm_pool->lock, flags); + if (bm_pool->buf_num == bm_pool->size) { + pr_warn("pool already filled\n"); + return bm_pool->buf_num; + } + + if (buf_num + bm_pool->buf_num > bm_pool->size) { + pr_warn("cannot allocate %d buffers for pool\n", + buf_num); + return 0; + } + + if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) { + pr_warn("Adding %d buffers to the %d current buffers will overflow\n", + buf_num, bm_pool->buf_num); + return 0; + } + + for (i = 0; i < buf_num; i++) { + err = hwbm_pool_refill(bm_pool, gfp); + if (err < 0) + break; + } + + /* Update BM driver with number of buffers added to pool */ + bm_pool->buf_num += i; + + pr_debug("hwpm pool: %d of %d buffers added\n", i, buf_num); + spin_unlock_irqrestore(&bm_pool->lock, flags); + + return i; +} +EXPORT_SYMBOL_GPL(hwbm_pool_add); diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 299cfc24d888..669ecc9f884e 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -27,6 +27,31 @@ #include <net/rtnetlink.h> #include <net/ip6_fib.h> +#ifdef CONFIG_MODULES + +static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) +{ + /* Only lwt encaps implemented without using an interface for + * the encap need to return a string here. + */ + switch (encap_type) { + case LWTUNNEL_ENCAP_MPLS: + return "MPLS"; + case LWTUNNEL_ENCAP_ILA: + return "ILA"; + case LWTUNNEL_ENCAP_IP6: + case LWTUNNEL_ENCAP_IP: + case LWTUNNEL_ENCAP_NONE: + case __LWTUNNEL_ENCAP_MAX: + /* should not have got here */ + WARN_ON(1); + break; + } + return NULL; +} + +#endif /* CONFIG_MODULES */ + struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) { struct lwtunnel_state *lws; @@ -85,6 +110,18 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); +#ifdef CONFIG_MODULES + if (!ops) { + const char *encap_type_str = lwtunnel_encap_str(encap_type); + + if (encap_type_str) { + rcu_read_unlock(); + request_module("rtnl-lwt-%s", encap_type_str); + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + } + } +#endif if (likely(ops && ops->build_state)) ret = ops->build_state(dev, encap, family, cfg, lws); rcu_read_unlock(); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b6c8a6629b39..2b3f76fe65f4 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -29,7 +29,6 @@ #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; -static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -199,9 +198,10 @@ static ssize_t speed_show(struct device *dev, return restart_syscall(); if (netif_running(netdev)) { - struct ethtool_cmd cmd; - if (!__ethtool_get_settings(netdev, &cmd)) - ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + struct ethtool_link_ksettings cmd; + + if (!__ethtool_get_link_ksettings(netdev, &cmd)) + ret = sprintf(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; @@ -218,10 +218,12 @@ static ssize_t duplex_show(struct device *dev, return restart_syscall(); if (netif_running(netdev)) { - struct ethtool_cmd cmd; - if (!__ethtool_get_settings(netdev, &cmd)) { + struct ethtool_link_ksettings cmd; + + if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; - switch (cmd.duplex) { + + switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; @@ -574,6 +576,7 @@ NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); +NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] = { &dev_attr_rx_packets.attr, @@ -599,6 +602,7 @@ static struct attribute *netstat_attrs[] = { &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, + &dev_attr_rx_nohandler.attr, NULL }; diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 0260c84ed83c..11fce17274f6 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -9,7 +9,6 @@ * Authors: Thomas Graf <tgraf@suug.ch> */ -#include <linux/module.h> #include <linux/slab.h> #include <linux/cgroup.h> #include <linux/fdtable.h> diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index f1efbc39ef6b..2ec86fc552df 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -11,7 +11,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1474cfd2dc1c..20999aa596dd 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2856,7 +2856,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IP); } - skb_set_mac_header(skb, 0); + skb_reset_mac_header(skb); skb_set_network_header(skb, skb->len); iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); @@ -2983,7 +2983,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IPV6); } - skb_set_mac_header(skb, 0); + skb_reset_mac_header(skb); skb_set_network_header(skb, skb->len); iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8261d95dd846..d2d9e5ebf58e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -804,6 +804,8 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->rx_compressed = b->rx_compressed; a->tx_compressed = b->tx_compressed; + + a->rx_nohandler = b->rx_nohandler; } static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) @@ -1389,15 +1391,6 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) }, }; -static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = { - [IFLA_VF_STATS_RX_PACKETS] = { .type = NLA_U64 }, - [IFLA_VF_STATS_TX_PACKETS] = { .type = NLA_U64 }, - [IFLA_VF_STATS_RX_BYTES] = { .type = NLA_U64 }, - [IFLA_VF_STATS_TX_BYTES] = { .type = NLA_U64 }, - [IFLA_VF_STATS_BROADCAST] = { .type = NLA_U64 }, - [IFLA_VF_STATS_MULTICAST] = { .type = NLA_U64 }, -}; - static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_VF] = { .type = NLA_U32 }, [IFLA_PORT_PROFILE] = { .type = NLA_STRING, @@ -1412,6 +1405,58 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, }; +static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla) +{ + const struct rtnl_link_ops *ops = NULL; + struct nlattr *linfo[IFLA_INFO_MAX + 1]; + + if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla, ifla_info_policy) < 0) + return NULL; + + if (linfo[IFLA_INFO_KIND]) { + char kind[MODULE_NAME_LEN]; + + nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind)); + ops = rtnl_link_ops_get(kind); + } + + return ops; +} + +static bool link_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + +static bool link_kind_filtered(const struct net_device *dev, + const struct rtnl_link_ops *kind_ops) +{ + if (kind_ops && dev->rtnl_link_ops != kind_ops) + return true; + + return false; +} + +static bool link_dump_filtered(struct net_device *dev, + int master_idx, + const struct rtnl_link_ops *kind_ops) +{ + if (link_master_filtered(dev, master_idx) || + link_kind_filtered(dev, kind_ops)) + return true; + + return false; +} + static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -1421,6 +1466,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + const struct rtnl_link_ops *kind_ops = NULL; + unsigned int flags = NLM_F_MULTI; + int master_idx = 0; int err; int hdrlen; @@ -1443,18 +1491,29 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + + if (tb[IFLA_MASTER]) + master_idx = nla_get_u32(tb[IFLA_MASTER]); + + if (tb[IFLA_LINKINFO]) + kind_ops = linkinfo_to_kind_ops(tb[IFLA_LINKINFO]); + + if (master_idx || kind_ops) + flags |= NLM_F_DUMP_FILTERED; } for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { + if (link_dump_filtered(dev, master_idx, kind_ops)) + continue; if (idx < s_idx) goto cont; err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, + flags, ext_filter_mask); /* If we ran out of room on the first message, * we're in trouble diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8616d1147c93..f044f970f1a6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -349,8 +349,16 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) } EXPORT_SYMBOL(build_skb); +#define NAPI_SKB_CACHE_SIZE 64 + +struct napi_alloc_cache { + struct page_frag_cache page; + size_t skb_count; + void *skb_cache[NAPI_SKB_CACHE_SIZE]; +}; + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache); +static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -380,9 +388,9 @@ EXPORT_SYMBOL(netdev_alloc_frag); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return __alloc_page_frag(nc, fragsz, gfp_mask); + return __alloc_page_frag(&nc->page, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) @@ -476,7 +484,7 @@ EXPORT_SYMBOL(__netdev_alloc_skb); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; void *data; @@ -496,7 +504,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - data = __alloc_page_frag(nc, len, gfp_mask); + data = __alloc_page_frag(&nc->page, len, gfp_mask); if (unlikely(!data)) return NULL; @@ -507,7 +515,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, } /* use OR instead of assignment to avoid clearing of bits in mask */ - if (nc->pfmemalloc) + if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -749,6 +757,73 @@ void consume_skb(struct sk_buff *skb) } EXPORT_SYMBOL(consume_skb); +void __kfree_skb_flush(void) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + /* flush skb_cache if containing objects */ + if (nc->skb_count) { + kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, + nc->skb_cache); + nc->skb_count = 0; + } +} + +static inline void _kfree_skb_defer(struct sk_buff *skb) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + /* drop skb->head and call any destructors for packet */ + skb_release_all(skb); + + /* record skb to CPU local list */ + nc->skb_cache[nc->skb_count++] = skb; + +#ifdef CONFIG_SLUB + /* SLUB writes into objects when freeing */ + prefetchw(skb); +#endif + + /* flush skb_cache if it is filled */ + if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { + kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE, + nc->skb_cache); + nc->skb_count = 0; + } +} +void __kfree_skb_defer(struct sk_buff *skb) +{ + _kfree_skb_defer(skb); +} + +void napi_consume_skb(struct sk_buff *skb, int budget) +{ + if (unlikely(!skb)) + return; + + /* Zero budget indicate non-NAPI context called us, like netpoll */ + if (unlikely(!budget)) { + dev_consume_skb_any(skb); + return; + } + + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + /* if reaching here SKB is ready to free */ + trace_consume_skb(skb); + + /* if SKB is a clone, don't handle this case */ + if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { + __kfree_skb(skb); + return; + } + + _kfree_skb_defer(skb); +} +EXPORT_SYMBOL(napi_consume_skb); + /* Make sure a field is enclosed inside headers_start/headers_end section */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) < \ @@ -1843,6 +1918,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, struct splice_pipe_desc *spd, struct sock *sk) { int seg; + struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a @@ -1869,6 +1945,19 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return true; } + skb_walk_frags(skb, iter) { + if (*offset >= iter->len) { + *offset -= iter->len; + continue; + } + /* __skb_splice_bits() only fails if the output has no room + * left, so no point in going over the frag_list for the error + * case. + */ + if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) + return true; + } + return false; } @@ -1895,9 +1984,7 @@ ssize_t skb_socket_splice(struct sock *sk, /* * Map data from the skb to a pipe. Should handle both the linear part, - * the fragments, and the frag list. It does NOT handle frag lists within - * the frag list, if such a thing exists. We'd probably need to recurse to - * handle that cleanly. + * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, @@ -1916,29 +2003,10 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; - struct sk_buff *frag_iter; int ret = 0; - /* - * __skb_splice_bits() only fails if the output has no room left, - * so no point in going over the frag_list for the error case. - */ - if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk)) - goto done; - else if (!tlen) - goto done; + __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); - /* - * now see if we have a frag_list to map - */ - skb_walk_frags(skb, frag_iter) { - if (!tlen) - break; - if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk)) - break; - } - -done: if (spd.nr_pages) ret = splice_cb(sk, pipe, &spd); @@ -3024,8 +3092,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, if (unlikely(!proto)) return ERR_PTR(-EINVAL); - csum = !head_skb->encap_hdr_csum && - !!can_checksum_protocol(features, proto); + csum = !!can_checksum_protocol(features, proto); headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); @@ -3118,13 +3185,15 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, if (nskb->len == len + doffset) goto perform_csum_check; - if (!sg && !nskb->remcsum_offload) { - nskb->ip_summed = CHECKSUM_NONE; - nskb->csum = skb_copy_and_csum_bits(head_skb, offset, - skb_put(nskb, len), - len, 0); + if (!sg) { + if (!nskb->remcsum_offload) + nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum = + skb_copy_and_csum_bits(head_skb, offset, + skb_put(nskb, len), + len, 0); SKB_GSO_CB(nskb)->csum_start = - skb_headroom(nskb) + doffset; + skb_headroom(nskb) + doffset; continue; } @@ -3190,12 +3259,19 @@ skip_fraglist: nskb->truesize += nskb->data_len; perform_csum_check: - if (!csum && !nskb->remcsum_offload) { - nskb->csum = skb_checksum(nskb, doffset, - nskb->len - doffset, 0); - nskb->ip_summed = CHECKSUM_NONE; + if (!csum) { + if (skb_has_shared_frag(nskb)) { + err = __skb_linearize(nskb); + if (err) + goto err; + } + if (!nskb->remcsum_offload) + nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum = + skb_checksum(nskb, doffset, + nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = - skb_headroom(nskb) + doffset; + skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); @@ -4237,7 +4313,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - skb_sender_cpu_clear(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); @@ -4433,9 +4508,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) skb->mac_len += VLAN_HLEN; __skb_pull(skb, offset); - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(skb->csum, csum_partial(skb->data - + (2 * ETH_ALEN), VLAN_HLEN, 0)); + skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; diff --git a/net/core/sock.c b/net/core/sock.c index 6c1c8bc93412..b67b9aedb230 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -987,6 +987,10 @@ set_rcvbuf: sk->sk_incoming_cpu = val; break; + case SO_CNX_ADVICE: + if (val == 1) + dst_negative_advice(sk); + break; default: ret = -ENOPROTOOPT; break; @@ -1531,6 +1535,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk = NULL; goto out; } + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); newsk->sk_err = 0; newsk->sk_priority = 0; @@ -1903,7 +1908,7 @@ EXPORT_SYMBOL(sock_cmsg_send); bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { - if (atomic_read(&pfrag->page->_count) == 1) { + if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } |