From 6e3e939f3b1bf8534b32ad09ff199d88800835a0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 9 Nov 2011 10:15:42 +0100 Subject: net: add wireless TX status socket option The 802.1X EAPOL handshake hostapd does requires knowing whether the frame was ack'ed by the peer. Currently, we fudge this pretty badly by not even transmitting the frame as a normal data frame but injecting it with radiotap and getting the status out of radiotap monitor as well. This is rather complex, confuses users (mon.wlan0 presence) and doesn't work with all hardware. To get rid of that hack, introduce a real wifi TX status option for data frame transmissions. This works similar to the existing TX timestamping in that it reflects the SKB back to the socket's error queue with a SCM_WIFI_STATUS cmsg that has an int indicating ACK status (0/1). Since it is possible that at some point we will want to have TX timestamping and wifi status in a single errqueue SKB (there's little point in not doing that), redefine SO_EE_ORIGIN_TIMESTAMPING to SO_EE_ORIGIN_TXSTATUS which can collect more than just the timestamp; keep the old constant as an alias of course. Currently the internal APIs don't make that possible, but it wouldn't be hard to split them up in a way that makes it possible. Thanks to Neil Horman for helping me figure out the functions that add the control messages. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/socket.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 2877647f347b..425ef4270460 100644 --- a/net/socket.c +++ b/net/socket.c @@ -538,6 +538,8 @@ int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags) *tx_flags |= SKBTX_HW_TSTAMP; if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) *tx_flags |= SKBTX_SW_TSTAMP; + if (sock_flag(sk, SOCK_WIFI_STATUS)) + *tx_flags |= SKBTX_WIFI_STATUS; return 0; } EXPORT_SYMBOL(sock_tx_timestamp); @@ -674,6 +676,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); +void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + int ack; + + if (!sock_flag(sk, SOCK_WIFI_STATUS)) + return; + if (!skb->wifi_acked_valid) + return; + + ack = skb->wifi_acked; + + put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); +} +EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); + static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { -- cgit v1.2.3-58-ga151 From 5bc1421e34ecfe0bd4b26dc3232b7d5e25179144 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 22 Nov 2011 05:10:51 +0000 Subject: net: add network priority cgroup infrastructure (v4) This patch adds in the infrastructure code to create the network priority cgroup. The cgroup, in addition to the standard processes file creates two control files: 1) prioidx - This is a read-only file that exports the index of this cgroup. This is a value that is both arbitrary and unique to a cgroup in this subsystem, and is used to index the per-device priority map 2) priomap - This is a writeable file. On read it reports a table of 2-tuples where name is the name of a network interface and priority is indicates the priority assigned to frames egresessing on the named interface and originating from a pid in this cgroup This cgroup allows for skb priority to be set prior to a root qdisc getting selected. This is benenficial for DCB enabled systems, in that it allows for any application to use dcb configured priorities so without application modification Signed-off-by: Neil Horman Signed-off-by: John Fastabend CC: Robert Love CC: "David S. Miller" Signed-off-by: David S. Miller --- include/linux/cgroup_subsys.h | 8 + include/linux/netdevice.h | 4 + include/net/netprio_cgroup.h | 65 ++++++++ include/net/sock.h | 3 + net/Kconfig | 7 + net/core/Makefile | 1 + net/core/dev.c | 14 ++ net/core/netprio_cgroup.c | 344 ++++++++++++++++++++++++++++++++++++++++++ net/core/sock.c | 22 ++- net/socket.c | 2 + 10 files changed, 469 insertions(+), 1 deletion(-) create mode 100644 include/net/netprio_cgroup.h create mode 100644 net/core/netprio_cgroup.c (limited to 'net/socket.c') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index ac663c18776c..0bd390ce98b2 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -59,8 +59,16 @@ SUBSYS(net_cls) SUBSYS(blkio) #endif +/* */ + #ifdef CONFIG_CGROUP_PERF SUBSYS(perf) #endif /* */ + +#ifdef CONFIG_NETPRIO_CGROUP +SUBSYS(net_prio) +#endif + +/* */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3eb383a9b5ed..999bb264fe27 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -50,6 +50,7 @@ #ifdef CONFIG_DCB #include #endif +#include #include @@ -1244,6 +1245,9 @@ struct net_device { #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; +#endif +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) + struct netprio_map __rcu *priomap; #endif /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h new file mode 100644 index 000000000000..c432e99942af --- /dev/null +++ b/include/net/netprio_cgroup.h @@ -0,0 +1,65 @@ +/* + * netprio_cgroup.h Control Group Priority set + * + * + * Authors: Neil Horman + * + * 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. + * + */ + +#ifndef _NETPRIO_CGROUP_H +#define _NETPRIO_CGROUP_H +#include +#include +#include +#include + +struct cgroup_netprio_state +{ + struct cgroup_subsys_state css; + u32 prioidx; +}; + +struct netprio_map { + struct rcu_head rcu; + u32 priomap_len; + u32 priomap[]; +}; + +#ifdef CONFIG_CGROUPS + +#ifndef CONFIG_NETPRIO_CGROUP +extern int net_prio_subsys_id; +#endif + +extern void sock_update_netprioidx(struct sock *sk); + +static inline struct cgroup_netprio_state + *task_netprio_state(struct task_struct *p) +{ +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) + return container_of(task_subsys_state(p, net_prio_subsys_id), + struct cgroup_netprio_state, css); +#else + return NULL; +#endif +} + +#else + +#define sock_update_netprioidx(sk) +#define skb_update_prio(skb) + +static inline struct cgroup_netprio_state + *task_netprio_state(struct task_struct *p) +{ + return NULL; +} + +#endif + +#endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 1c28f394d8ec..8ac338cb39ce 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -320,6 +320,9 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; +#ifdef CONFIG_CGROUPS + __u32 sk_cgrp_prioidx; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; diff --git a/net/Kconfig b/net/Kconfig index a07314844238..63d2c5dc36ff 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,13 @@ config XPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config NETPRIO_CGROUP + tristate "Network priority cgroup" + depends on CGROUPS + ---help--- + Cgroup subsystem for use in assigning processes to network priorities on + a per-interface basis + config HAVE_BPF_JIT bool diff --git a/net/core/Makefile b/net/core/Makefile index 0d357b1c4e57..3606d40aae62 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index f78959996148..8afb244b205f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2449,6 +2449,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference(skb->dev->priomap); + + if ((!skb->priority) && (skb->sk) && map) + skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; +} +#else +#define skb_update_prio(skb) +#endif + static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 @@ -2489,6 +2501,8 @@ int dev_queue_xmit(struct sk_buff *skb) */ rcu_read_lock_bh(); + skb_update_prio(skb); + txq = dev_pick_tx(dev, skb); q = rcu_dereference_bh(txq->qdisc); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 000000000000..72ad0bc6841e --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,344 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * 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. + * + * Authors: Neil Horman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp); +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp); + +struct cgroup_subsys net_prio_subsys = { + .name = "net_prio", + .create = cgrp_create, + .destroy = cgrp_destroy, + .populate = cgrp_populate, +#ifdef CONFIG_NETPRIO_CGROUP + .subsys_id = net_prio_subsys_id, +#endif + .module = THIS_MODULE +}; + +#define PRIOIDX_SZ 128 + +static unsigned long prioidx_map[PRIOIDX_SZ]; +static DEFINE_SPINLOCK(prioidx_map_lock); +static atomic_t max_prioidx = ATOMIC_INIT(0); + +static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id), + struct cgroup_netprio_state, css); +} + +static int get_prioidx(u32 *prio) +{ + unsigned long flags; + u32 prioidx; + + spin_lock_irqsave(&prioidx_map_lock, flags); + prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + set_bit(prioidx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) + return -ENOSPC; + + atomic_set(&max_prioidx, prioidx); + *prio = prioidx; + return 0; +} + +static void put_prioidx(u32 idx) +{ + unsigned long flags; + + spin_lock_irqsave(&prioidx_map_lock, flags); + clear_bit(idx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); +} + +static void extend_netdev_table(struct net_device *dev, u32 new_len) +{ + size_t new_size = sizeof(struct netprio_map) + + ((sizeof(u32) * new_len)); + struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL); + struct netprio_map *old_priomap; + int i; + + old_priomap = rtnl_dereference(dev->priomap); + + if (!new_priomap) { + printk(KERN_WARNING "Unable to alloc new priomap!\n"); + return; + } + + for (i = 0; + old_priomap && (i < old_priomap->priomap_len); + i++) + new_priomap->priomap[i] = old_priomap->priomap[i]; + + new_priomap->priomap_len = new_len; + + rcu_assign_pointer(dev->priomap, new_priomap); + if (old_priomap) + kfree_rcu(old_priomap, rcu); +} + +static void update_netdev_tables(void) +{ + struct net_device *dev; + u32 max_len = atomic_read(&max_prioidx); + struct netprio_map *map; + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if ((!map) || + (map->priomap_len < max_len)) + extend_netdev_table(dev, max_len); + } + rtnl_unlock(); +} + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + int ret; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { + kfree(cs); + return ERR_PTR(-EINVAL); + } + + ret = get_prioidx(&cs->prioidx); + if (ret != 0) { + printk(KERN_WARNING "No space in priority index array\n"); + kfree(cs); + return ERR_PTR(ret); + } + + return &cs->css; +} + +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + struct net_device *dev; + struct netprio_map *map; + + cs = cgrp_netprio_state(cgrp); + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if (map) + map->priomap[cs->prioidx] = 0; + } + rtnl_unlock(); + put_prioidx(cs->prioidx); + kfree(cs); +} + +static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) +{ + return (u64)cgrp_netprio_state(cgrp)->prioidx; +} + +static int read_priomap(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct net_device *dev; + u32 prioidx = cgrp_netprio_state(cont)->prioidx; + u32 priority; + struct netprio_map *map; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + map = rcu_dereference(dev->priomap); + priority = map ? map->priomap[prioidx] : 0; + cb->fill(cb, dev->name, priority); + } + rcu_read_unlock(); + return 0; +} + +static int write_priomap(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + char *devname = kstrdup(buffer, GFP_KERNEL); + int ret = -EINVAL; + u32 prioidx = cgrp_netprio_state(cgrp)->prioidx; + unsigned long priority; + char *priostr; + struct net_device *dev; + struct netprio_map *map; + + if (!devname) + return -ENOMEM; + + /* + * Minimally sized valid priomap string + */ + if (strlen(devname) < 3) + goto out_free_devname; + + priostr = strstr(devname, " "); + if (!priostr) + goto out_free_devname; + + /* + *Separate the devname from the associated priority + *and advance the priostr poitner to the priority value + */ + *priostr = '\0'; + priostr++; + + /* + * If the priostr points to NULL, we're at the end of the passed + * in string, and its not a valid write + */ + if (*priostr == '\0') + goto out_free_devname; + + ret = kstrtoul(priostr, 10, &priority); + if (ret < 0) + goto out_free_devname; + + ret = -ENODEV; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + goto out_free_devname; + + update_netdev_tables(); + ret = 0; + rcu_read_lock(); + map = rcu_dereference(dev->priomap); + if (map) + map->priomap[prioidx] = priority; + rcu_read_unlock(); + dev_put(dev); + +out_free_devname: + kfree(devname); + return ret; +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .read_map = read_priomap, + .write_string = write_priomap, + }, +}; + +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); +} + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct netprio_map *old; + u32 max_len = atomic_read(&max_prioidx); + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + + case NETDEV_REGISTER: + if (max_len) + extend_netdev_table(dev, max_len); + break; + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + rcu_assign_pointer(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + int ret; + + ret = cgroup_load_subsys(&net_prio_subsys); + if (ret) + goto out; +#ifndef CONFIG_NETPRIO_CGROUP + smp_wmb(); + net_prio_subsys_id = net_prio_subsys.subsys_id; +#endif + + register_netdevice_notifier(&netprio_device_notifier); + +out: + return ret; +} + +static void __exit exit_cgroup_netprio(void) +{ + struct netprio_map *old; + struct net_device *dev; + + unregister_netdevice_notifier(&netprio_device_notifier); + + cgroup_unload_subsys(&net_prio_subsys); + +#ifndef CONFIG_NETPRIO_CGROUP + net_prio_subsys_id = -1; + synchronize_rcu(); +#endif + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + old = rtnl_dereference(dev->priomap); + rcu_assign_pointer(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + } + rtnl_unlock(); +} + +module_init(init_cgroup_netprio); +module_exit(exit_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/sock.c b/net/core/sock.c index 9a8b3fac1401..16069139797c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -125,6 +125,7 @@ #include #include #include +#include #include @@ -221,10 +222,16 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); -#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP) +#if defined(CONFIG_CGROUPS) +#if !defined(CONFIG_NET_CLS_CGROUP) int net_cls_subsys_id = -1; EXPORT_SYMBOL_GPL(net_cls_subsys_id); #endif +#if !defined(CONFIG_NETPRIO_CGROUP) +int net_prio_subsys_id = -1; +EXPORT_SYMBOL_GPL(net_prio_subsys_id); +#endif +#endif static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -1120,6 +1127,18 @@ void sock_update_classid(struct sock *sk) sk->sk_classid = classid; } EXPORT_SYMBOL(sock_update_classid); + +void sock_update_netprioidx(struct sock *sk) +{ + struct cgroup_netprio_state *state; + if (in_interrupt()) + return; + rcu_read_lock(); + state = task_netprio_state(current); + sk->sk_cgrp_prioidx = state ? state->prioidx : 0; + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif /** @@ -1147,6 +1166,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; diff --git a/net/socket.c b/net/socket.c index 425ef4270460..e62b4f055071 100644 --- a/net/socket.c +++ b/net/socket.c @@ -551,6 +551,8 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, sock_update_classid(sock->sk); + sock_update_netprioidx(sock->sk); + si->sock = sock; si->scm = NULL; si->msg = msg; -- cgit v1.2.3-58-ga151 From 55664f324c2a1a6386dc88492c5c94aa3d336b93 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 3 Jan 2012 12:04:51 +0000 Subject: ethtool: Allow drivers to select RX NFC rule locations Define special location values for RX NFC that request the driver to select the actual rule location. This allows for implementation on devices that use hash-based filter lookup, whereas currently the API is more suited to devices with TCAM lookup or linear search. In ethtool_set_rxnfc() and the compat wrapper ethtool_ioctl(), copy the structure back to user-space after insertion so that the actual location is returned. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 26 ++++++++++++++++++++++++-- net/core/ethtool.c | 11 ++++++++++- net/socket.c | 2 +- 3 files changed, 35 insertions(+), 4 deletions(-) (limited to 'net/socket.c') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b38bf69310ee..d901714120a3 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -489,7 +489,10 @@ struct ethtool_rx_flow_spec { * on return. * * For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined - * rules on return. + * rules on return. If @data is non-zero on return then it is the + * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the + * driver supports any special location values. If that flag is not + * set in @data then special location values should not be used. * * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an * existing rule on entry and @fs contains the rule on return. @@ -501,10 +504,23 @@ struct ethtool_rx_flow_spec { * must use the second parameter to get_rxnfc() instead of @rule_locs. * * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update. - * @fs.@location specifies the location to use and must not be ignored. + * @fs.@location either specifies the location to use or is a special + * location value with %RX_CLS_LOC_SPECIAL flag set. On return, + * @fs.@location is the actual rule location. * * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an * existing rule on entry. + * + * A driver supporting the special location values for + * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused + * location, and may remove a rule at a later location (lower + * priority) that matches exactly the same set of flows. The special + * values are: %RX_CLS_LOC_ANY, selecting any location; + * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum + * priority); and %RX_CLS_LOC_LAST, selecting the last suitable + * location (minimum priority). Additional special values may be + * defined in future and drivers must return -%EINVAL for any + * unrecognised value. */ struct ethtool_rxnfc { __u32 cmd; @@ -1141,6 +1157,12 @@ struct ethtool_ops { #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL +/* Special RX classification rule insert location values */ +#define RX_CLS_LOC_SPECIAL 0x80000000 /* flag */ +#define RX_CLS_LOC_ANY 0xffffffff +#define RX_CLS_LOC_FIRST 0xfffffffe +#define RX_CLS_LOC_LAST 0xfffffffd + /* Reset flags */ /* The reset() operation must clear the flags for the components which * were actually reset. On successful return, the flags indicate the diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 597732c989ca..e88b80d41f73 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -439,6 +439,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, { struct ethtool_rxnfc info; size_t info_size = sizeof(info); + int rc; if (!dev->ethtool_ops->set_rxnfc) return -EOPNOTSUPP; @@ -454,7 +455,15 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; - return dev->ethtool_ops->set_rxnfc(dev, &info); + rc = dev->ethtool_ops->set_rxnfc(dev, &info); + if (rc) + return rc; + + if (cmd == ETHTOOL_SRXCLSRLINS && + copy_to_user(useraddr, &info, info_size)) + return -EFAULT; + + return 0; } static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, diff --git a/net/socket.c b/net/socket.c index e62b4f055071..2cad581318fe 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2758,10 +2758,10 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: + case ETHTOOL_SRXCLSRLINS: convert_out = true; /* fall through */ case ETHTOOL_SRXCLSRLDEL: - case ETHTOOL_SRXCLSRLINS: buf_size += sizeof(struct ethtool_rxnfc); convert_in = true; break; -- cgit v1.2.3-58-ga151