diff options
Diffstat (limited to 'net')
176 files changed, 4690 insertions, 1822 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e97ab824e368..9ee5787634e5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -562,8 +562,7 @@ static int vlan_dev_init(struct net_device *dev) NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; - dev->features |= real_dev->vlan_features | NETIF_F_LLTX | - NETIF_F_GSO_SOFTWARE; + dev->features |= dev->hw_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; dev->gso_max_segs = real_dev->gso_max_segs; if (dev->features & NETIF_F_VLAN_FEATURES) diff --git a/net/Makefile b/net/Makefile index 9b681550e3a3..9086ffbb5085 100644 --- a/net/Makefile +++ b/net/Makefile @@ -12,7 +12,7 @@ obj-$(CONFIG_NET) += $(tmp-y) # LLC has to be linked before the files in net/802/ obj-$(CONFIG_LLC) += llc/ -obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ +obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_XFRM) += xfrm/ diff --git a/net/atm/clip.c b/net/atm/clip.c index 53b4ac09e7b7..ec527b62f79d 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -106,7 +106,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc) entry->expires = jiffies - 1; /* force resolution or expiration */ error = neigh_update(entry->neigh, NULL, NUD_NONE, - NEIGH_UPDATE_F_ADMIN); + NEIGH_UPDATE_F_ADMIN, 0); if (error) pr_crit("neigh_update failed with %d\n", error); goto out; @@ -481,7 +481,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip) link_vcc(clip_vcc, entry); } error = neigh_update(neigh, llc_oui, NUD_PERMANENT, - NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN); + NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); return error; } diff --git a/net/atm/common.c b/net/atm/common.c index 9613381f5db0..f06422f4108d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk) write_unlock_irq(&vcc_sklist_lock); } -static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size) +static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size) { - struct sk_buff *skb; struct sock *sk = sk_atm(vcc); if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) { pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n", sk_wmem_alloc_get(sk), size, sk->sk_sndbuf); - return NULL; + return false; } - while (!(skb = alloc_skb(size, GFP_KERNEL))) - schedule(); - pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); - return skb; + return true; } static void vcc_sock_destruct(struct sock *sk) @@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) eff = (size+3) & ~3; /* align to word boundary */ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); error = 0; - while (!(skb = alloc_tx(vcc, eff))) { + while (!vcc_tx_ready(vcc, eff)) { if (m->msg_flags & MSG_DONTWAIT) { error = -EAGAIN; break; @@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) finish_wait(sk_sleep(sk), &wait); if (error) goto out; + + skb = alloc_skb(eff, GFP_KERNEL); + if (!skb) { + error = -ENOMEM; + goto out; + } + pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); + atomic_add(skb->truesize, &sk->sk_wmem_alloc); + skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { diff --git a/net/bpf/Makefile b/net/bpf/Makefile new file mode 100644 index 000000000000..27b2992a0692 --- /dev/null +++ b/net/bpf/Makefile @@ -0,0 +1 @@ +obj-y := test_run.o diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c new file mode 100644 index 000000000000..8a6d0a37c30c --- /dev/null +++ b/net/bpf/test_run.c @@ -0,0 +1,172 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/etherdevice.h> +#include <linux/filter.h> +#include <linux/sched/signal.h> + +static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx) +{ + u32 ret; + + preempt_disable(); + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, ctx); + rcu_read_unlock(); + preempt_enable(); + + return ret; +} + +static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) +{ + u64 time_start, time_spent = 0; + u32 ret = 0, i; + + if (!repeat) + repeat = 1; + time_start = ktime_get_ns(); + for (i = 0; i < repeat; i++) { + ret = bpf_test_run_one(prog, ctx); + if (need_resched()) { + if (signal_pending(current)) + break; + time_spent += ktime_get_ns() - time_start; + cond_resched(); + time_start = ktime_get_ns(); + } + } + time_spent += ktime_get_ns() - time_start; + do_div(time_spent, repeat); + *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + + return ret; +} + +static int bpf_test_finish(union bpf_attr __user *uattr, const void *data, + u32 size, u32 retval, u32 duration) +{ + void __user *data_out = u64_to_user_ptr(uattr->test.data_out); + int err = -EFAULT; + + if (data_out && copy_to_user(data_out, data, size)) + goto out; + if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) + goto out; + if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) + goto out; + if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration))) + goto out; + err = 0; +out: + return err; +} + +static void *bpf_test_init(const union bpf_attr *kattr, u32 size, + u32 headroom, u32 tailroom) +{ + void __user *data_in = u64_to_user_ptr(kattr->test.data_in); + void *data; + + if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) + return ERR_PTR(-EINVAL); + + data = kzalloc(size + headroom + tailroom, GFP_USER); + if (!data) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(data + headroom, data_in, size)) { + kfree(data); + return ERR_PTR(-EFAULT); + } + return data; +} + +int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + bool is_l2 = false, is_direct_pkt_access = false; + u32 size = kattr->test.data_size_in; + u32 repeat = kattr->test.repeat; + u32 retval, duration; + struct sk_buff *skb; + void *data; + int ret; + + data = bpf_test_init(kattr, size, NET_SKB_PAD, + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + if (IS_ERR(data)) + return PTR_ERR(data); + + switch (prog->type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + is_l2 = true; + /* fall through */ + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + is_direct_pkt_access = true; + break; + default: + break; + } + + skb = build_skb(data, 0); + if (!skb) { + kfree(data); + return -ENOMEM; + } + + skb_reserve(skb, NET_SKB_PAD); + __skb_put(skb, size); + skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev); + skb_reset_network_header(skb); + + if (is_l2) + __skb_push(skb, ETH_HLEN); + if (is_direct_pkt_access) + bpf_compute_data_end(skb); + retval = bpf_test_run(prog, skb, repeat, &duration); + if (!is_l2) + __skb_push(skb, ETH_HLEN); + size = skb->len; + /* bpf program can never convert linear skb to non-linear */ + if (WARN_ON_ONCE(skb_is_nonlinear(skb))) + size = skb_headlen(skb); + ret = bpf_test_finish(uattr, skb->data, size, retval, duration); + kfree_skb(skb); + return ret; +} + +int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + u32 size = kattr->test.data_size_in; + u32 repeat = kattr->test.repeat; + struct xdp_buff xdp = {}; + u32 retval, duration; + void *data; + int ret; + + data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM, 0); + if (IS_ERR(data)) + return PTR_ERR(data); + + xdp.data_hard_start = data; + xdp.data = data + XDP_PACKET_HEADROOM; + xdp.data_end = xdp.data + size; + + retval = bpf_test_run(prog, &xdp, repeat, &duration); + if (xdp.data != data + XDP_PACKET_HEADROOM) + size = xdp.data_end - xdp.data; + ret = bpf_test_finish(uattr, xdp.data, size, retval, duration); + kfree(data); + return ret; +} diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 6e08b7199dd7..5a40a87c4f4f 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -594,6 +594,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->updated = now; if (unlikely(added_by_user)) fdb->added_by_user = 1; + /* Take over HW learned entry */ + if (unlikely(fdb->added_by_external_learn)) + fdb->added_by_external_learn = 0; if (unlikely(fdb_modified)) fdb_notify(br, fdb, RTM_NEWNEIGH); } @@ -854,6 +857,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, br_fdb_update(br, p, addr, vid, true); rcu_read_unlock(); local_bh_enable(); + } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { + err = br_fdb_external_learn_add(br, p, addr, vid); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 8ac1770aa222..6eb52d422dd9 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -22,6 +22,7 @@ #include <linux/rtnetlink.h> #include <linux/if_ether.h> #include <linux/slab.h> +#include <net/dsa.h> #include <net/sock.h> #include <linux/if_vlan.h> #include <net/switchdev.h> diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 1f1e62095464..067cf0313449 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -997,13 +997,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, if (!elem) return okfn(net, sk, skb); - /* We may already have this, but read-locks nest anyway */ - rcu_read_lock(); nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, elem); - rcu_read_unlock(); if (ret == 1) ret = okfn(net, sk, skb); diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 98b9c8e8615e..707caea39743 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -62,10 +62,10 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset) pptr = skb_header_pointer(skb, offset, sizeof(_ports), &_ports); if (pptr == NULL) { - printk(" INCOMPLETE TCP/UDP header"); + pr_cont(" INCOMPLETE TCP/UDP header"); return; } - printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst)); + pr_cont(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst)); } } @@ -100,11 +100,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) { - printk(" INCOMPLETE IP header"); + pr_cont(" INCOMPLETE IP header"); goto out; } - printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d", - &ih->saddr, &ih->daddr, ih->tos, ih->protocol); + pr_cont(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d", + &ih->saddr, &ih->daddr, ih->tos, ih->protocol); print_ports(skb, ih->protocol, ih->ihl*4); goto out; } @@ -120,11 +120,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) { - printk(" INCOMPLETE IPv6 header"); + pr_cont(" INCOMPLETE IPv6 header"); goto out; } - printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d", - &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr); + pr_cont(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d", + &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr); nexthdr = ih->nexthdr; offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off); if (offset_ph == -1) @@ -142,12 +142,12 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { - printk(" INCOMPLETE ARP header"); + pr_cont(" INCOMPLETE ARP header"); goto out; } - printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d", - ntohs(ah->ar_hrd), ntohs(ah->ar_pro), - ntohs(ah->ar_op)); + pr_cont(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d", + ntohs(ah->ar_hrd), ntohs(ah->ar_pro), + ntohs(ah->ar_op)); /* If it's for Ethernet and the lengths are OK, * then log the ARP payload @@ -161,17 +161,17 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); if (ap == NULL) { - printk(" INCOMPLETE ARP payload"); + pr_cont(" INCOMPLETE ARP payload"); goto out; } - printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4", - ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst); + pr_cont(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4", + ap->mac_src, ap->ip_src, + ap->mac_dst, ap->ip_dst); } } out: - printk("\n"); + pr_cont("\n"); spin_unlock_bh(&ebt_log_lock); - } static unsigned int diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 206dc266ecd2..346ef6b00b8f 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -375,11 +375,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code, err; - - err = nft_reject_bridge_validate(ctx, expr, NULL); - if (err < 0) - return err; + int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/can/af_can.c b/net/can/af_can.c index 5488e4a6ccd0..abf7d854a94d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -75,9 +75,7 @@ static int stats_timer __read_mostly = 1; module_param(stats_timer, int, S_IRUGO); MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)"); -/* receive filters subscribed for 'all' CAN devices */ -struct dev_rcv_lists can_rx_alldev_list; -static DEFINE_SPINLOCK(can_rcvlists_lock); +static int can_net_id; static struct kmem_cache *rcv_cache __read_mostly; @@ -145,9 +143,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= CAN_NPROTO) return -EINVAL; - if (!net_eq(net, &init_net)) - return -EAFNOSUPPORT; - cp = can_get_proto(protocol); #ifdef CONFIG_MODULES @@ -331,10 +326,11 @@ EXPORT_SYMBOL(can_send); * af_can rx path */ -static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) +static struct dev_rcv_lists *find_dev_rcv_lists(struct net *net, + struct net_device *dev) { if (!dev) - return &can_rx_alldev_list; + return net->can.can_rx_alldev_list; else return (struct dev_rcv_lists *)dev->ml_priv; } @@ -467,9 +463,9 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, * -ENOMEM on missing cache mem to create subscription entry * -ENODEV unknown device */ -int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, - void (*func)(struct sk_buff *, void *), void *data, - char *ident, struct sock *sk) +int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, + canid_t mask, void (*func)(struct sk_buff *, void *), + void *data, char *ident, struct sock *sk) { struct receiver *r; struct hlist_head *rl; @@ -481,13 +477,16 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, if (dev && dev->type != ARPHRD_CAN) return -ENODEV; + if (dev && !net_eq(net, dev_net(dev))) + return -ENODEV; + r = kmem_cache_alloc(rcv_cache, GFP_KERNEL); if (!r) return -ENOMEM; - spin_lock(&can_rcvlists_lock); + spin_lock(&net->can.can_rcvlists_lock); - d = find_dev_rcv_lists(dev); + d = find_dev_rcv_lists(net, dev); if (d) { rl = find_rcv_list(&can_id, &mask, d); @@ -510,7 +509,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, err = -ENODEV; } - spin_unlock(&can_rcvlists_lock); + spin_unlock(&net->can.can_rcvlists_lock); return err; } @@ -540,8 +539,9 @@ static void can_rx_delete_receiver(struct rcu_head *rp) * Description: * Removes subscription entry depending on given (subscription) values. */ -void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, - void (*func)(struct sk_buff *, void *), void *data) +void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, + canid_t mask, void (*func)(struct sk_buff *, void *), + void *data) { struct receiver *r = NULL; struct hlist_head *rl; @@ -550,9 +550,12 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, if (dev && dev->type != ARPHRD_CAN) return; - spin_lock(&can_rcvlists_lock); + if (dev && !net_eq(net, dev_net(dev))) + return; - d = find_dev_rcv_lists(dev); + spin_lock(&net->can.can_rcvlists_lock); + + d = find_dev_rcv_lists(net, dev); if (!d) { pr_err("BUG: receive list not found for " "dev %s, id %03X, mask %03X\n", @@ -598,7 +601,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, } out: - spin_unlock(&can_rcvlists_lock); + spin_unlock(&net->can.can_rcvlists_lock); /* schedule the receiver item for deletion */ if (r) { @@ -696,10 +699,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); /* deliver the packet to sockets listening on all devices */ - matches = can_rcv_filter(&can_rx_alldev_list, skb); + matches = can_rcv_filter(dev_net(dev)->can.can_rx_alldev_list, skb); /* find receive list for this device */ - d = find_dev_rcv_lists(dev); + d = find_dev_rcv_lists(dev_net(dev), dev); if (d) matches += can_rcv_filter(d, skb); @@ -719,9 +722,6 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(!net_eq(dev_net(dev), &init_net))) - goto drop; - if (WARN_ONCE(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || cfd->len > CAN_MAX_DLEN, @@ -743,9 +743,6 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(!net_eq(dev_net(dev), &init_net))) - goto drop; - if (WARN_ONCE(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || cfd->len > CANFD_MAX_DLEN, @@ -835,9 +832,6 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dev_rcv_lists *d; - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; @@ -855,7 +849,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, break; case NETDEV_UNREGISTER: - spin_lock(&can_rcvlists_lock); + spin_lock(&dev_net(dev)->can.can_rcvlists_lock); d = dev->ml_priv; if (d) { @@ -869,7 +863,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, pr_err("can: notifier: receive list not found for dev " "%s\n", dev->name); - spin_unlock(&can_rcvlists_lock); + spin_unlock(&dev_net(dev)->can.can_rcvlists_lock); break; } @@ -877,6 +871,40 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; } +static int can_pernet_init(struct net *net) +{ + net->can.can_rcvlists_lock = + __SPIN_LOCK_UNLOCKED(net->can.can_rcvlists_lock); + net->can.can_rx_alldev_list = + kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL); + + if (IS_ENABLED(CONFIG_PROC_FS)) + can_init_proc(net); + + return 0; +} + +static void can_pernet_exit(struct net *net) +{ + struct net_device *dev; + + if (IS_ENABLED(CONFIG_PROC_FS)) + can_remove_proc(net); + + /* remove created dev_rcv_lists from still registered CAN devices */ + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->type == ARPHRD_CAN && dev->ml_priv) { + struct dev_rcv_lists *d = dev->ml_priv; + + BUG_ON(d->entries); + kfree(d); + dev->ml_priv = NULL; + } + } + rcu_read_unlock(); +} + /* * af_can module init/exit functions */ @@ -902,6 +930,13 @@ static struct notifier_block can_netdev_notifier __read_mostly = { .notifier_call = can_notifier, }; +static struct pernet_operations can_pernet_ops __read_mostly = { + .init = can_pernet_init, + .exit = can_pernet_exit, + .id = &can_net_id, + .size = 0, +}; + static __init int can_init(void) { /* check for correct padding to be able to use the structs similarly */ @@ -912,8 +947,6 @@ static __init int can_init(void) pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n"); - memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list)); - rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver), 0, 0, NULL); if (!rcv_cache) @@ -925,9 +958,10 @@ static __init int can_init(void) setup_timer(&can_stattimer, can_stat_update, 0); mod_timer(&can_stattimer, round_jiffies(jiffies + HZ)); } - can_init_proc(); } + register_pernet_subsys(&can_pernet_ops); + /* protocol register */ sock_register(&can_family_ops); register_netdevice_notifier(&can_netdev_notifier); @@ -939,13 +973,9 @@ static __init int can_init(void) static __exit void can_exit(void) { - struct net_device *dev; - if (IS_ENABLED(CONFIG_PROC_FS)) { if (stats_timer) del_timer_sync(&can_stattimer); - - can_remove_proc(); } /* protocol unregister */ @@ -954,19 +984,7 @@ static __exit void can_exit(void) unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); - /* remove created dev_rcv_lists from still registered CAN devices */ - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - - struct dev_rcv_lists *d = dev->ml_priv; - - BUG_ON(d->entries); - kfree(d); - dev->ml_priv = NULL; - } - } - rcu_read_unlock(); + unregister_pernet_subsys(&can_pernet_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/can/af_can.h b/net/can/af_can.h index b86f5129e838..f273c9d9b129 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -114,8 +114,8 @@ struct s_pstats { extern struct dev_rcv_lists can_rx_alldev_list; /* function prototypes for the CAN networklayer procfs (proc.c) */ -void can_init_proc(void); -void can_remove_proc(void); +void can_init_proc(struct net *net); +void can_remove_proc(struct net *net); void can_stat_update(unsigned long data); /* structures and variables from af_can.c needed in proc.c for reading */ diff --git a/net/can/bcm.c b/net/can/bcm.c index 95d13b233c65..1976629a8463 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -764,8 +764,8 @@ static void bcm_remove_op(struct bcm_op *op) static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { - can_rx_unregister(dev, op->can_id, REGMASK(op->can_id), - bcm_rx_handler, op); + can_rx_unregister(&init_net, dev, op->can_id, + REGMASK(op->can_id), bcm_rx_handler, op); /* mark as removed subscription */ op->rx_reg_dev = NULL; @@ -808,7 +808,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, } } } else - can_rx_unregister(NULL, op->can_id, + can_rx_unregister(&init_net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); @@ -1222,7 +1222,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, dev = dev_get_by_index(&init_net, ifindex); if (dev) { - err = can_rx_register(dev, op->can_id, + err = can_rx_register(&init_net, dev, + op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); @@ -1232,7 +1233,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } } else - err = can_rx_register(NULL, op->can_id, + err = can_rx_register(&init_net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); if (err) { @@ -1528,7 +1529,7 @@ static int bcm_release(struct socket *sock) } } } else - can_rx_unregister(NULL, op->can_id, + can_rx_unregister(&init_net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); diff --git a/net/can/gw.c b/net/can/gw.c index 7056a1a2bb70..3c117a33e15f 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -440,14 +440,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) static inline int cgw_register_filter(struct cgw_job *gwj) { - return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id, + return can_rx_register(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct cgw_job *gwj) { - can_rx_unregister(gwj->src.dev, gwj->ccgw.filter.can_id, + can_rx_unregister(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); } diff --git a/net/can/proc.c b/net/can/proc.c index 85ef7bb0f176..9a8d54d57b22 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -62,17 +62,6 @@ #define CAN_PROC_RCVLIST_EFF "rcvlist_eff" #define CAN_PROC_RCVLIST_ERR "rcvlist_err" -static struct proc_dir_entry *can_dir; -static struct proc_dir_entry *pde_version; -static struct proc_dir_entry *pde_stats; -static struct proc_dir_entry *pde_reset_stats; -static struct proc_dir_entry *pde_rcvlist_all; -static struct proc_dir_entry *pde_rcvlist_fil; -static struct proc_dir_entry *pde_rcvlist_inv; -static struct proc_dir_entry *pde_rcvlist_sff; -static struct proc_dir_entry *pde_rcvlist_eff; -static struct proc_dir_entry *pde_rcvlist_err; - static int user_reset; static const char rx_list_name[][8] = { @@ -351,20 +340,21 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ - int idx = (int)(long)m->private; + int idx = (int)(long)PDE_DATA(m->file->f_inode); struct net_device *dev; struct dev_rcv_lists *d; + struct net *net = m->private; seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]); rcu_read_lock(); /* receive list for 'all' CAN devices (dev == NULL) */ - d = &can_rx_alldev_list; + d = net->can.can_rx_alldev_list; can_rcvlist_proc_show_one(m, idx, NULL, d); /* receive list for registered CAN devices */ - for_each_netdev_rcu(&init_net, dev) { + for_each_netdev_rcu(net, dev) { if (dev->type == ARPHRD_CAN && dev->ml_priv) can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv); } @@ -377,7 +367,7 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v) static int can_rcvlist_proc_open(struct inode *inode, struct file *file) { - return single_open(file, can_rcvlist_proc_show, PDE_DATA(inode)); + return single_open_net(inode, file, can_rcvlist_proc_show); } static const struct file_operations can_rcvlist_proc_fops = { @@ -417,6 +407,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct dev_rcv_lists *d; + struct net *net = m->private; /* RX_SFF */ seq_puts(m, "\nreceive list 'rx_sff':\n"); @@ -424,11 +415,11 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) rcu_read_lock(); /* sff receive list for 'all' CAN devices (dev == NULL) */ - d = &can_rx_alldev_list; + d = net->can.can_rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff)); /* sff receive list for registered CAN devices */ - for_each_netdev_rcu(&init_net, dev) { + for_each_netdev_rcu(net, dev) { if (dev->type == ARPHRD_CAN && dev->ml_priv) { d = dev->ml_priv; can_rcvlist_proc_show_array(m, dev, d->rx_sff, @@ -444,7 +435,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file) { - return single_open(file, can_rcvlist_sff_proc_show, NULL); + return single_open_net(inode, file, can_rcvlist_sff_proc_show); } static const struct file_operations can_rcvlist_sff_proc_fops = { @@ -460,6 +451,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct dev_rcv_lists *d; + struct net *net = m->private; /* RX_EFF */ seq_puts(m, "\nreceive list 'rx_eff':\n"); @@ -467,11 +459,11 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) rcu_read_lock(); /* eff receive list for 'all' CAN devices (dev == NULL) */ - d = &can_rx_alldev_list; + d = net->can.can_rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff)); /* eff receive list for registered CAN devices */ - for_each_netdev_rcu(&init_net, dev) { + for_each_netdev_rcu(net, dev) { if (dev->type == ARPHRD_CAN && dev->ml_priv) { d = dev->ml_priv; can_rcvlist_proc_show_array(m, dev, d->rx_eff, @@ -487,7 +479,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file) { - return single_open(file, can_rcvlist_eff_proc_show, NULL); + return single_open_net(inode, file, can_rcvlist_eff_proc_show); } static const struct file_operations can_rcvlist_eff_proc_fops = { @@ -499,81 +491,85 @@ static const struct file_operations can_rcvlist_eff_proc_fops = { }; /* - * proc utility functions - */ - -static void can_remove_proc_readentry(const char *name) -{ - if (can_dir) - remove_proc_entry(name, can_dir); -} - -/* * can_init_proc - create main CAN proc directory and procfs entries */ -void can_init_proc(void) +void can_init_proc(struct net *net) { /* create /proc/net/can directory */ - can_dir = proc_mkdir("can", init_net.proc_net); + net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net); - if (!can_dir) { - pr_info("can: failed to create /proc/net/can.\n"); + if (!net->can.proc_dir) { + printk(KERN_INFO "can: failed to create /proc/net/can . " + "CONFIG_PROC_FS missing?\n"); return; } /* own procfs entries from the AF_CAN core */ - pde_version = proc_create(CAN_PROC_VERSION, 0644, can_dir, - &can_version_proc_fops); - pde_stats = proc_create(CAN_PROC_STATS, 0644, can_dir, - &can_stats_proc_fops); - pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, can_dir, - &can_reset_stats_proc_fops); - pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, can_dir, - &can_rcvlist_proc_fops, (void *)RX_ERR); - pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, can_dir, - &can_rcvlist_proc_fops, (void *)RX_ALL); - pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, can_dir, - &can_rcvlist_proc_fops, (void *)RX_FIL); - pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir, - &can_rcvlist_proc_fops, (void *)RX_INV); - pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir, - &can_rcvlist_eff_proc_fops); - pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir, - &can_rcvlist_sff_proc_fops); + net->can.pde_version = proc_create(CAN_PROC_VERSION, 0644, + net->can.proc_dir, + &can_version_proc_fops); + net->can.pde_stats = proc_create(CAN_PROC_STATS, 0644, + net->can.proc_dir, + &can_stats_proc_fops); + net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, + net->can.proc_dir, + &can_reset_stats_proc_fops); + net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, + net->can.proc_dir, + &can_rcvlist_proc_fops, + (void *)RX_ERR); + net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, + net->can.proc_dir, + &can_rcvlist_proc_fops, + (void *)RX_ALL); + net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, + net->can.proc_dir, + &can_rcvlist_proc_fops, + (void *)RX_FIL); + net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, + net->can.proc_dir, + &can_rcvlist_proc_fops, + (void *)RX_INV); + net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, + net->can.proc_dir, + &can_rcvlist_eff_proc_fops); + net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, + net->can.proc_dir, + &can_rcvlist_sff_proc_fops); } /* * can_remove_proc - remove procfs entries and main CAN proc directory */ -void can_remove_proc(void) +void can_remove_proc(struct net *net) { - if (pde_version) - can_remove_proc_readentry(CAN_PROC_VERSION); + if (net->can.pde_version) + remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir); - if (pde_stats) - can_remove_proc_readentry(CAN_PROC_STATS); + if (net->can.pde_stats) + remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir); - if (pde_reset_stats) - can_remove_proc_readentry(CAN_PROC_RESET_STATS); + if (net->can.pde_reset_stats) + remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir); - if (pde_rcvlist_err) - can_remove_proc_readentry(CAN_PROC_RCVLIST_ERR); + if (net->can.pde_rcvlist_err) + remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir); - if (pde_rcvlist_all) - can_remove_proc_readentry(CAN_PROC_RCVLIST_ALL); + if (net->can.pde_rcvlist_all) + remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir); - if (pde_rcvlist_fil) - can_remove_proc_readentry(CAN_PROC_RCVLIST_FIL); + if (net->can.pde_rcvlist_fil) + remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir); - if (pde_rcvlist_inv) - can_remove_proc_readentry(CAN_PROC_RCVLIST_INV); + if (net->can.pde_rcvlist_inv) + remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir); - if (pde_rcvlist_eff) - can_remove_proc_readentry(CAN_PROC_RCVLIST_EFF); + if (net->can.pde_rcvlist_eff) + remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir); - if (pde_rcvlist_sff) - can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF); + if (net->can.pde_rcvlist_sff) + remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir); - if (can_dir) - remove_proc_entry("can", init_net.proc_net); + if (net->can.proc_dir) + remove_proc_entry("can", net->proc_net); } diff --git a/net/can/raw.c b/net/can/raw.c index 6dc546a06673..864c80dbdb72 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -181,20 +181,21 @@ static void raw_rcv(struct sk_buff *oskb, void *data) kfree_skb(skb); } -static int raw_enable_filters(struct net_device *dev, struct sock *sk, - struct can_filter *filter, int count) +static int raw_enable_filters(struct net *net, struct net_device *dev, + struct sock *sk, struct can_filter *filter, + int count) { int err = 0; int i; for (i = 0; i < count; i++) { - err = can_rx_register(dev, filter[i].can_id, + err = can_rx_register(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk, "raw", sk); if (err) { /* clean up successfully registered filters */ while (--i >= 0) - can_rx_unregister(dev, filter[i].can_id, + can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); break; @@ -204,57 +205,62 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk, return err; } -static int raw_enable_errfilter(struct net_device *dev, struct sock *sk, - can_err_mask_t err_mask) +static int raw_enable_errfilter(struct net *net, struct net_device *dev, + struct sock *sk, can_err_mask_t err_mask) { int err = 0; if (err_mask) - err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG, + err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk, "raw", sk); return err; } -static void raw_disable_filters(struct net_device *dev, struct sock *sk, - struct can_filter *filter, int count) +static void raw_disable_filters(struct net *net, struct net_device *dev, + struct sock *sk, struct can_filter *filter, + int count) { int i; for (i = 0; i < count; i++) - can_rx_unregister(dev, filter[i].can_id, filter[i].can_mask, - raw_rcv, sk); + can_rx_unregister(net, dev, filter[i].can_id, + filter[i].can_mask, raw_rcv, sk); } -static inline void raw_disable_errfilter(struct net_device *dev, +static inline void raw_disable_errfilter(struct net *net, + struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { if (err_mask) - can_rx_unregister(dev, 0, err_mask | CAN_ERR_FLAG, + can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk); } -static inline void raw_disable_allfilters(struct net_device *dev, +static inline void raw_disable_allfilters(struct net *net, + struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); - raw_disable_filters(dev, sk, ro->filter, ro->count); - raw_disable_errfilter(dev, sk, ro->err_mask); + raw_disable_filters(net, dev, sk, ro->filter, ro->count); + raw_disable_errfilter(net, dev, sk, ro->err_mask); } -static int raw_enable_allfilters(struct net_device *dev, struct sock *sk) +static int raw_enable_allfilters(struct net *net, struct net_device *dev, + struct sock *sk) { struct raw_sock *ro = raw_sk(sk); int err; - err = raw_enable_filters(dev, sk, ro->filter, ro->count); + err = raw_enable_filters(net, dev, sk, ro->filter, ro->count); if (!err) { - err = raw_enable_errfilter(dev, sk, ro->err_mask); + err = raw_enable_errfilter(net, dev, sk, ro->err_mask); if (err) - raw_disable_filters(dev, sk, ro->filter, ro->count); + raw_disable_filters(net, dev, sk, ro->filter, + ro->count); } return err; @@ -267,7 +273,7 @@ static int raw_notifier(struct notifier_block *nb, struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; - if (!net_eq(dev_net(dev), &init_net)) + if (!net_eq(dev_net(dev), sock_net(sk))) return NOTIFY_DONE; if (dev->type != ARPHRD_CAN) @@ -282,7 +288,7 @@ static int raw_notifier(struct notifier_block *nb, lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) - raw_disable_allfilters(dev, sk); + raw_disable_allfilters(dev_net(dev), dev, sk); if (ro->count > 1) kfree(ro->filter); @@ -358,13 +364,13 @@ static int raw_release(struct socket *sock) if (ro->ifindex) { struct net_device *dev; - dev = dev_get_by_index(&init_net, ro->ifindex); + dev = dev_get_by_index(sock_net(sk), ro->ifindex); if (dev) { - raw_disable_allfilters(dev, sk); + raw_disable_allfilters(dev_net(dev), dev, sk); dev_put(dev); } } else - raw_disable_allfilters(NULL, sk); + raw_disable_allfilters(sock_net(sk), NULL, sk); } if (ro->count > 1) @@ -404,7 +410,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_ifindex) { struct net_device *dev; - dev = dev_get_by_index(&init_net, addr->can_ifindex); + dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; @@ -420,13 +426,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) ifindex = dev->ifindex; /* filters set by default/setsockopt */ - err = raw_enable_allfilters(dev, sk); + err = raw_enable_allfilters(sock_net(sk), dev, sk); dev_put(dev); } else { ifindex = 0; /* filters set by default/setsockopt */ - err = raw_enable_allfilters(NULL, sk); + err = raw_enable_allfilters(sock_net(sk), NULL, sk); } if (!err) { @@ -435,13 +441,15 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (ro->ifindex) { struct net_device *dev; - dev = dev_get_by_index(&init_net, ro->ifindex); + dev = dev_get_by_index(sock_net(sk), + ro->ifindex); if (dev) { - raw_disable_allfilters(dev, sk); + raw_disable_allfilters(dev_net(dev), + dev, sk); dev_put(dev); } } else - raw_disable_allfilters(NULL, sk); + raw_disable_allfilters(sock_net(sk), NULL, sk); } ro->ifindex = ifindex; ro->bound = 1; @@ -517,15 +525,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, lock_sock(sk); if (ro->bound && ro->ifindex) - dev = dev_get_by_index(&init_net, ro->ifindex); + dev = dev_get_by_index(sock_net(sk), ro->ifindex); if (ro->bound) { /* (try to) register the new filters */ if (count == 1) - err = raw_enable_filters(dev, sk, &sfilter, 1); + err = raw_enable_filters(sock_net(sk), dev, sk, + &sfilter, 1); else - err = raw_enable_filters(dev, sk, filter, - count); + err = raw_enable_filters(sock_net(sk), dev, sk, + filter, count); if (err) { if (count > 1) kfree(filter); @@ -533,7 +542,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, } /* remove old filter registrations */ - raw_disable_filters(dev, sk, ro->filter, ro->count); + raw_disable_filters(sock_net(sk), dev, sk, ro->filter, + ro->count); } /* remove old filter space */ @@ -569,18 +579,20 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, lock_sock(sk); if (ro->bound && ro->ifindex) - dev = dev_get_by_index(&init_net, ro->ifindex); + dev = dev_get_by_index(sock_net(sk), ro->ifindex); /* remove current error mask */ if (ro->bound) { /* (try to) register the new err_mask */ - err = raw_enable_errfilter(dev, sk, err_mask); + err = raw_enable_errfilter(sock_net(sk), dev, sk, + err_mask); if (err) goto out_err; /* remove old err_mask registration */ - raw_disable_errfilter(dev, sk, ro->err_mask); + raw_disable_errfilter(sock_net(sk), dev, sk, + ro->err_mask); } /* link new err_mask to the socket */ @@ -741,7 +753,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return -EINVAL; } - dev = dev_get_by_index(&init_net, ifindex); + dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENXIO; diff --git a/net/core/datagram.c b/net/core/datagram.c index ea633342ab0d..4608aa245410 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -256,8 +256,12 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, } spin_unlock_irqrestore(&queue->lock, cpu_flags); - } while (sk_can_busy_loop(sk) && - sk_busy_loop(sk, flags & MSG_DONTWAIT)); + + if (!sk_can_busy_loop(sk)) + break; + + sk_busy_loop(sk, flags & MSG_DONTWAIT); + } while (!skb_queue_empty(&sk->sk_receive_queue)); error = -EAGAIN; diff --git a/net/core/dev.c b/net/core/dev.c index 7869ae3837ca..7efb4178ffef 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5060,27 +5060,28 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) do_softirq(); } -bool sk_busy_loop(struct sock *sk, int nonblock) +void napi_busy_loop(unsigned int napi_id, + bool (*loop_end)(void *, unsigned long), + void *loop_end_arg) { - unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; + unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); void *have_poll_lock = NULL; struct napi_struct *napi; - int rc; restart: - rc = false; napi_poll = NULL; rcu_read_lock(); - napi = napi_by_id(sk->sk_napi_id); + napi = napi_by_id(napi_id); if (!napi) goto out; preempt_disable(); for (;;) { - rc = 0; + int work = 0; + local_bh_disable(); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); @@ -5098,16 +5099,15 @@ restart: have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } - rc = napi_poll(napi, BUSY_POLL_BUDGET); - trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); + work = napi_poll(napi, BUSY_POLL_BUDGET); + trace_napi_poll(napi, work, BUSY_POLL_BUDGET); count: - if (rc > 0) - __NET_ADD_STATS(sock_net(sk), - LINUX_MIB_BUSYPOLLRXPACKETS, rc); + if (work > 0) + __NET_ADD_STATS(dev_net(napi->dev), + LINUX_MIB_BUSYPOLLRXPACKETS, work); local_bh_enable(); - if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) || - busy_loop_timeout(end_time)) + if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { @@ -5116,9 +5116,8 @@ count: preempt_enable(); rcu_read_unlock(); cond_resched(); - rc = !skb_queue_empty(&sk->sk_receive_queue); - if (rc || busy_loop_timeout(end_time)) - return rc; + if (loop_end(loop_end_arg, start_time)) + return; goto restart; } cpu_relax(); @@ -5126,12 +5125,10 @@ count: if (napi_poll) busy_poll_stop(napi, have_poll_lock); preempt_enable(); - rc = !skb_queue_empty(&sk->sk_receive_queue); out: rcu_read_unlock(); - return rc; } -EXPORT_SYMBOL(sk_busy_loop); +EXPORT_SYMBOL(napi_busy_loop); #endif /* CONFIG_NET_RX_BUSY_POLL */ @@ -5143,10 +5140,10 @@ static void napi_hash_add(struct napi_struct *napi) spin_lock(&napi_hash_lock); - /* 0..NR_CPUS+1 range is reserved for sender_cpu use */ + /* 0..NR_CPUS range is reserved for sender_cpu use */ do { - if (unlikely(++napi_gen_id < NR_CPUS + 1)) - napi_gen_id = NR_CPUS + 1; + if (unlikely(++napi_gen_id < MIN_NAPI_ID)) + napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); napi->napi_id = napi_gen_id; @@ -6843,7 +6840,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL); /* diff --git a/net/core/devlink.c b/net/core/devlink.c index e9c1e6acfb6d..24b766003a61 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1493,8 +1493,686 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, if (err) return err; } + return 0; +} + +int devlink_dpipe_match_put(struct sk_buff *skb, + struct devlink_dpipe_match *match) +{ + struct devlink_dpipe_header *header = match->header; + struct devlink_dpipe_field *field = &header->fields[match->field_id]; + struct nlattr *match_attr; + + match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH); + if (!match_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + nla_nest_end(skb, match_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, match_attr); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_match_put); + +static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, + struct sk_buff *skb) +{ + struct nlattr *matches_attr; + + matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES); + if (!matches_attr) + return -EMSGSIZE; + + if (table->table_ops->matches_dump(table->priv, skb)) + goto nla_put_failure; + + nla_nest_end(skb, matches_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, matches_attr); + return -EMSGSIZE; +} + +int devlink_dpipe_action_put(struct sk_buff *skb, + struct devlink_dpipe_action *action) +{ + struct devlink_dpipe_header *header = action->header; + struct devlink_dpipe_field *field = &header->fields[action->field_id]; + struct nlattr *action_attr; + + action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION); + if (!action_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + nla_nest_end(skb, action_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, action_attr); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_action_put); + +static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, + struct sk_buff *skb) +{ + struct nlattr *actions_attr; + + actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); + if (!actions_attr) + return -EMSGSIZE; + + if (table->table_ops->actions_dump(table->priv, skb)) + goto nla_put_failure; + + nla_nest_end(skb, actions_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, actions_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_table_put(struct sk_buff *skb, + struct devlink_dpipe_table *table) +{ + struct nlattr *table_attr; + + table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE); + if (!table_attr) + return -EMSGSIZE; + + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, + table->counters_enabled)) + goto nla_put_failure; + + if (devlink_dpipe_matches_put(table, skb)) + goto nla_put_failure; + + if (devlink_dpipe_actions_put(table, skb)) + goto nla_put_failure; + + nla_nest_end(skb, table_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, table_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb, + struct genl_info *info) +{ + int err; + + if (*pskb) { + err = genlmsg_reply(*pskb, info); + if (err) + return err; + } + *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!*pskb) + return -ENOMEM; + return 0; +} + +static int devlink_dpipe_tables_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct list_head *dpipe_tables, + const char *table_name) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_dpipe_table *table; + struct nlattr *tables_attr; + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + bool incomplete; + void *hdr; + int i; + int err; + + table = list_first_entry(dpipe_tables, + struct devlink_dpipe_table, list); +start_again: + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(skb, devlink)) + goto nla_put_failure; + tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES); + if (!tables_attr) + goto nla_put_failure; + + i = 0; + incomplete = false; + list_for_each_entry_from(table, dpipe_tables, list) { + if (!table_name) { + err = devlink_dpipe_table_put(skb, table); + if (err) { + if (!i) + goto err_table_put; + incomplete = true; + break; + } + } else { + if (!strcmp(table->name, table_name)) { + err = devlink_dpipe_table_put(skb, table); + if (err) + break; + } + } + i++; + } + + nla_nest_end(skb, tables_attr); + genlmsg_end(skb, hdr); + if (incomplete) + goto start_again; + +send_done: + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + goto err_skb_send_alloc; + goto send_done; + } + + return genlmsg_reply(skb, info); + +nla_put_failure: + err = -EMSGSIZE; +err_table_put: +err_skb_send_alloc: + genlmsg_cancel(skb, hdr); + nlmsg_free(skb); + return err; +} + +static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const char *table_name = NULL; + + if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + + return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0, + &devlink->dpipe_table_list, + table_name); +} + +static int devlink_dpipe_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE, + value->value_size, value->value)) + return -EMSGSIZE; + if (value->mask) + if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK, + value->value_size, value->mask)) + return -EMSGSIZE; + if (value->mapping_valid) + if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING, + value->mapping_value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_action_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (!value->action) + return -EINVAL; + if (devlink_dpipe_action_put(skb, value->action)) + return -EMSGSIZE; + if (devlink_dpipe_value_put(skb, value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_action_values_put(struct sk_buff *skb, + struct devlink_dpipe_value *values, + unsigned int values_count) +{ + struct nlattr *action_attr; + int i; + int err; + + for (i = 0; i < values_count; i++) { + action_attr = nla_nest_start(skb, + DEVLINK_ATTR_DPIPE_ACTION_VALUE); + if (!action_attr) + return -EMSGSIZE; + err = devlink_dpipe_action_value_put(skb, &values[i]); + if (err) + goto err_action_value_put; + nla_nest_end(skb, action_attr); + } + return 0; + +err_action_value_put: + nla_nest_cancel(skb, action_attr); + return err; +} + +static int devlink_dpipe_match_value_put(struct sk_buff *skb, + struct devlink_dpipe_value *value) +{ + if (!value->match) + return -EINVAL; + if (devlink_dpipe_match_put(skb, value->match)) + return -EMSGSIZE; + if (devlink_dpipe_value_put(skb, value)) + return -EMSGSIZE; + return 0; +} + +static int devlink_dpipe_match_values_put(struct sk_buff *skb, + struct devlink_dpipe_value *values, + unsigned int values_count) +{ + struct nlattr *match_attr; + int i; + int err; + + for (i = 0; i < values_count; i++) { + match_attr = nla_nest_start(skb, + DEVLINK_ATTR_DPIPE_MATCH_VALUE); + if (!match_attr) + return -EMSGSIZE; + err = devlink_dpipe_match_value_put(skb, &values[i]); + if (err) + goto err_match_value_put; + nla_nest_end(skb, match_attr); + } + return 0; + +err_match_value_put: + nla_nest_cancel(skb, match_attr); + return err; +} + +static int devlink_dpipe_entry_put(struct sk_buff *skb, + struct devlink_dpipe_entry *entry) +{ + struct nlattr *entry_attr, *matches_attr, *actions_attr; + int err; + + entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY); + if (!entry_attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (entry->counter_valid) + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, + entry->counter, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + matches_attr = nla_nest_start(skb, + DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); + if (!matches_attr) + goto nla_put_failure; + + err = devlink_dpipe_match_values_put(skb, entry->match_values, + entry->match_values_count); + if (err) { + nla_nest_cancel(skb, matches_attr); + goto err_match_values_put; + } + nla_nest_end(skb, matches_attr); + + actions_attr = nla_nest_start(skb, + DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); + if (!actions_attr) + goto nla_put_failure; + + err = devlink_dpipe_action_values_put(skb, entry->action_values, + entry->action_values_count); + if (err) { + nla_nest_cancel(skb, actions_attr); + goto err_action_values_put; + } + nla_nest_end(skb, actions_attr); + nla_nest_end(skb, entry_attr); return 0; + +nla_put_failure: + err = -EMSGSIZE; +err_match_values_put: +err_action_values_put: + nla_nest_cancel(skb, entry_attr); + return err; +} + +static struct devlink_dpipe_table * +devlink_dpipe_table_find(struct list_head *dpipe_tables, + const char *table_name) +{ + struct devlink_dpipe_table *table; + + list_for_each_entry_rcu(table, dpipe_tables, list) { + if (!strcmp(table->name, table_name)) + return table; + } + return NULL; +} + +int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct devlink *devlink; + int err; + + err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb, + dump_ctx->info); + if (err) + return err; + + dump_ctx->hdr = genlmsg_put(dump_ctx->skb, + dump_ctx->info->snd_portid, + dump_ctx->info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, + dump_ctx->cmd); + if (!dump_ctx->hdr) + goto nla_put_failure; + + devlink = dump_ctx->info->user_ptr[0]; + if (devlink_nl_put_handle(dump_ctx->skb, devlink)) + goto nla_put_failure; + dump_ctx->nest = nla_nest_start(dump_ctx->skb, + DEVLINK_ATTR_DPIPE_ENTRIES); + if (!dump_ctx->nest) + goto nla_put_failure; + return 0; + +nla_put_failure: + genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr); + nlmsg_free(dump_ctx->skb); + return -EMSGSIZE; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare); + +int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, + struct devlink_dpipe_entry *entry) +{ + return devlink_dpipe_entry_put(dump_ctx->skb, entry); +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append); + +int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) +{ + nla_nest_end(dump_ctx->skb, dump_ctx->nest); + genlmsg_end(dump_ctx->skb, dump_ctx->hdr); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close); + +static int devlink_dpipe_entries_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_dpipe_table *table) +{ + struct devlink_dpipe_dump_ctx dump_ctx; + struct nlmsghdr *nlh; + int err; + + dump_ctx.skb = NULL; + dump_ctx.cmd = cmd; + dump_ctx.info = info; + + err = table->table_ops->entries_dump(table->priv, + table->counters_enabled, + &dump_ctx); + if (err) + goto err_entries_dump; + +send_done: + nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); + if (err) + goto err_skb_send_alloc; + goto send_done; + } + return genlmsg_reply(dump_ctx.skb, info); + +err_entries_dump: +err_skb_send_alloc: + genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); + nlmsg_free(dump_ctx.skb); + return err; +} + +static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_dpipe_table *table; + const char *table_name; + + if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) + return -EINVAL; + + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name); + if (!table) + return -EINVAL; + + if (!table->table_ops->entries_dump) + return -EINVAL; + + return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET, + 0, table); +} + +static int devlink_dpipe_fields_put(struct sk_buff *skb, + const struct devlink_dpipe_header *header) +{ + struct devlink_dpipe_field *field; + struct nlattr *field_attr; + int i; + + for (i = 0; i < header->fields_count; i++) { + field = &header->fields[i]; + field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD); + if (!field_attr) + return -EMSGSIZE; + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type)) + goto nla_put_failure; + nla_nest_end(skb, field_attr); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, field_attr); + return -EMSGSIZE; +} + +static int devlink_dpipe_header_put(struct sk_buff *skb, + struct devlink_dpipe_header *header) +{ + struct nlattr *fields_attr, *header_attr; + int err; + + header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER); + if (!header) + return -EMSGSIZE; + + if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) || + nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || + nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) + goto nla_put_failure; + + fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS); + if (!fields_attr) + goto nla_put_failure; + + err = devlink_dpipe_fields_put(skb, header); + if (err) { + nla_nest_cancel(skb, fields_attr); + goto nla_put_failure; + } + nla_nest_end(skb, fields_attr); + nla_nest_end(skb, header_attr); + return 0; + +nla_put_failure: + err = -EMSGSIZE; + nla_nest_cancel(skb, header_attr); + return err; +} + +static int devlink_dpipe_headers_fill(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_dpipe_headers * + dpipe_headers) +{ + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *headers_attr; + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + void *hdr; + int i, j; + int err; + + i = 0; +start_again: + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + return err; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(skb, devlink)) + goto nla_put_failure; + headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS); + if (!headers_attr) + goto nla_put_failure; + + j = 0; + for (; i < dpipe_headers->headers_count; i++) { + err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]); + if (err) { + if (!j) + goto err_table_put; + break; + } + j++; + } + nla_nest_end(skb, headers_attr); + genlmsg_end(skb, hdr); + if (i != dpipe_headers->headers_count) + goto start_again; + +send_done: + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = devlink_dpipe_send_and_alloc_skb(&skb, info); + if (err) + goto err_skb_send_alloc; + goto send_done; + } + return genlmsg_reply(skb, info); + +nla_put_failure: + err = -EMSGSIZE; +err_table_put: +err_skb_send_alloc: + genlmsg_cancel(skb, hdr); + nlmsg_free(skb); + return err; +} + +static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + if (!devlink->dpipe_headers) + return -EOPNOTSUPP; + return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET, + 0, devlink->dpipe_headers); +} + +static int devlink_dpipe_table_counters_set(struct devlink *devlink, + const char *table_name, + bool enable) +{ + struct devlink_dpipe_table *table; + + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name); + if (!table) + return -EINVAL; + + if (table->counter_control_extern) + return -EOPNOTSUPP; + + if (!(table->counters_enabled ^ enable)) + return 0; + + table->counters_enabled = enable; + if (table->table_ops->counters_set_update) + table->table_ops->counters_set_update(table->priv, enable); + return 0; +} + +static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const char *table_name; + bool counters_enable; + + if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] || + !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]) + return -EINVAL; + + table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); + counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]); + + return devlink_dpipe_table_counters_set(devlink, table_name, + counters_enable); } static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { @@ -1512,6 +2190,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 }, [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -1644,6 +2324,34 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, + .doit = devlink_nl_cmd_dpipe_table_get, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, + .doit = devlink_nl_cmd_dpipe_entries_get, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, + .doit = devlink_nl_cmd_dpipe_headers_get, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, + .doit = devlink_nl_cmd_dpipe_table_counters_set, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -1680,6 +2388,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->sb_list); + INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); return devlink; } EXPORT_SYMBOL_GPL(devlink_alloc); @@ -1880,6 +2589,133 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index) } EXPORT_SYMBOL_GPL(devlink_sb_unregister); +/** + * devlink_dpipe_headers_register - register dpipe headers + * + * @devlink: devlink + * @dpipe_headers: dpipe header array + * + * Register the headers supported by hardware. + */ +int devlink_dpipe_headers_register(struct devlink *devlink, + struct devlink_dpipe_headers *dpipe_headers) +{ + mutex_lock(&devlink_mutex); + devlink->dpipe_headers = dpipe_headers; + mutex_unlock(&devlink_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register); + +/** + * devlink_dpipe_headers_unregister - unregister dpipe headers + * + * @devlink: devlink + * + * Unregister the headers supported by hardware. + */ +void devlink_dpipe_headers_unregister(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->dpipe_headers = NULL; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister); + +/** + * devlink_dpipe_table_counter_enabled - check if counter allocation + * required + * @devlink: devlink + * @table_name: tables name + * + * Used by driver to check if counter allocation is required. + * After counter allocation is turned on the table entries + * are updated to include counter statistics. + * + * After that point on the driver must respect the counter + * state so that each entry added to the table is added + * with a counter. + */ +bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, + const char *table_name) +{ + struct devlink_dpipe_table *table; + bool enabled; + + rcu_read_lock(); + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name); + enabled = false; + if (table) + enabled = table->counters_enabled; + rcu_read_unlock(); + return enabled; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); + +/** + * devlink_dpipe_table_register - register dpipe table + * + * @devlink: devlink + * @table_name: table name + * @table_ops: table ops + * @priv: priv + * @size: size + * @counter_control_extern: external control for counters + */ +int devlink_dpipe_table_register(struct devlink *devlink, + const char *table_name, + struct devlink_dpipe_table_ops *table_ops, + void *priv, u64 size, + bool counter_control_extern) +{ + struct devlink_dpipe_table *table; + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) + return -EEXIST; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + table->name = table_name; + table->table_ops = table_ops; + table->priv = priv; + table->size = size; + table->counter_control_extern = counter_control_extern; + + mutex_lock(&devlink_mutex); + list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); + mutex_unlock(&devlink_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); + +/** + * devlink_dpipe_table_unregister - unregister dpipe table + * + * @devlink: devlink + * @table_name: table name + */ +void devlink_dpipe_table_unregister(struct devlink *devlink, + const char *table_name) +{ + struct devlink_dpipe_table *table; + + mutex_lock(&devlink_mutex); + table = devlink_dpipe_table_find(&devlink->dpipe_table_list, + table_name); + if (!table) + goto unlock; + list_del_rcu(&table->list); + mutex_unlock(&devlink_mutex); + kfree_rcu(table, rcu); + return; +unlock: + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index fb55327dcfea..70ccda233bd1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); INIT_WORK(&data->dm_alert_work, send_dm_alert); - init_timer(&data->send_timer); - data->send_timer.data = (unsigned long)data; - data->send_timer.function = sched_send_work; + setup_timer(&data->send_timer, sched_send_work, + (unsigned long)data); spin_lock_init(&data->lock); reset_per_cpu_data(data); } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aecb2c7241b6..905a88ad28e0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -109,6 +109,7 @@ static const char rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { [ETH_RSS_HASH_TOP_BIT] = "toeplitz", [ETH_RSS_HASH_XOR_BIT] = "xor", + [ETH_RSS_HASH_CRC32_BIT] = "crc32", }; static const char diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index b6791d94841d..816e3ccb0ec9 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(~0), }; +bool fib_rule_matchall(const struct fib_rule *rule) +{ + if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || + rule->flags) + return false; + if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) + return false; + if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || + !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib_rule_matchall); + int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { diff --git a/net/core/filter.c b/net/core/filter.c index ebaeaf2e46e8..15e9a81ffebe 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -26,6 +26,7 @@ #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> +#include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -928,7 +929,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu) */ static void sk_filter_release(struct sk_filter *fp) { - if (atomic_dec_and_test(&fp->refcnt)) + if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } @@ -943,20 +944,27 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) /* try to charge the socket memory if there is space available * return true on success */ -bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) +static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); /* same check as in sock_kmalloc() */ if (filter_size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { - atomic_inc(&fp->refcnt); atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } +bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) +{ + bool ret = __sk_filter_charge(sk, fp); + if (ret) + refcount_inc(&fp->refcnt); + return ret; +} + static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; @@ -1179,12 +1187,12 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; fp->prog = prog; - atomic_set(&fp->refcnt, 0); - if (!sk_filter_charge(sk, fp)) { + if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } + refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); @@ -2599,6 +2607,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) +{ + return skb->sk ? sock_gen_cookie(skb->sk) : 0; +} + +static const struct bpf_func_proto bpf_get_socket_cookie_proto = { + .func = bpf_get_socket_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) +{ + struct sock *sk = sk_to_full_sk(skb->sk); + kuid_t kuid; + + if (!sk || !sk_fullsock(sk)) + return overflowuid; + kuid = sock_net_uid(sock_net(sk), sk); + return from_kuid_munged(sock_net(sk)->user_ns, kuid); +} + +static const struct bpf_func_proto bpf_get_socket_uid_proto = { + .func = bpf_get_socket_uid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -2633,6 +2671,10 @@ sk_filter_func_proto(enum bpf_func_id func_id) switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_socket_uid: + return &bpf_get_socket_uid_proto; default: return bpf_base_func_proto(func_id); } @@ -2692,6 +2734,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_socket_uid: + return &bpf_get_socket_uid_proto; default: return bpf_base_func_proto(func_id); } @@ -3263,24 +3309,28 @@ static const struct bpf_verifier_ops tc_cls_act_ops = { .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, + .test_run = bpf_prog_test_run_skb, }; static const struct bpf_verifier_ops xdp_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, + .test_run = bpf_prog_test_run_xdp, }; static const struct bpf_verifier_ops cg_skb_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, + .test_run = bpf_prog_test_run_skb, }; static const struct bpf_verifier_ops lwt_inout_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, + .test_run = bpf_prog_test_run_skb, }; static const struct bpf_verifier_ops lwt_xmit_ops = { @@ -3288,6 +3338,7 @@ static const struct bpf_verifier_ops lwt_xmit_ops = { .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, + .test_run = bpf_prog_test_run_skb, }; static const struct bpf_verifier_ops cg_sock_ops = { diff --git a/net/core/flow.c b/net/core/flow.c index f765c11d8df5..f7f5d1932a27 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -47,7 +47,7 @@ struct flow_flush_info { static struct kmem_cache *flow_cachep __read_mostly; -#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) +#define flow_cache_hash_size(cache) (1U << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) static void flow_cache_new_hashrnd(unsigned long arg) @@ -99,7 +99,8 @@ static void flow_cache_gc_task(struct work_struct *work) } static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, - int deleted, struct list_head *gc_list, + unsigned int deleted, + struct list_head *gc_list, struct netns_xfrm *xfrm) { if (deleted) { @@ -114,17 +115,18 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, static void __flow_cache_shrink(struct flow_cache *fc, struct flow_cache_percpu *fcp, - int shrink_to) + unsigned int shrink_to) { struct flow_cache_entry *fle; struct hlist_node *tmp; LIST_HEAD(gc_list); - int i, deleted = 0; + unsigned int deleted = 0; struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, flow_cache_global); + unsigned int i; for (i = 0; i < flow_cache_hash_size(fc); i++) { - int saved = 0; + unsigned int saved = 0; hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { @@ -145,7 +147,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, static void flow_cache_shrink(struct flow_cache *fc, struct flow_cache_percpu *fcp) { - int shrink_to = fc->low_watermark / flow_cache_hash_size(fc); + unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc); __flow_cache_shrink(fc, fcp, shrink_to); } @@ -161,7 +163,7 @@ static void flow_new_hash_rnd(struct flow_cache *fc, static u32 flow_hash_code(struct flow_cache *fc, struct flow_cache_percpu *fcp, const struct flowi *key, - size_t keysize) + unsigned int keysize) { const u32 *k = (const u32 *) key; const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32); @@ -174,7 +176,7 @@ static u32 flow_hash_code(struct flow_cache *fc, * important assumptions that we can here, such as alignment. */ static int flow_key_compare(const struct flowi *key1, const struct flowi *key2, - size_t keysize) + unsigned int keysize) { const flow_compare_t *k1, *k1_lim, *k2; @@ -199,7 +201,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; struct flow_cache_object *flo; - size_t keysize; + unsigned int keysize; unsigned int hash; local_bh_disable(); @@ -295,9 +297,10 @@ static void flow_cache_flush_tasklet(unsigned long data) struct flow_cache_entry *fle; struct hlist_node *tmp; LIST_HEAD(gc_list); - int i, deleted = 0; + unsigned int deleted = 0; struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, flow_cache_global); + unsigned int i; fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { @@ -327,7 +330,7 @@ static void flow_cache_flush_tasklet(unsigned long data) static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp; - int i; + unsigned int i; fcp = per_cpu_ptr(fc->percpu, cpu); for (i = 0; i < flow_cache_hash_size(fc); i++) @@ -402,12 +405,12 @@ void flow_cache_flush_deferred(struct net *net) static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); - size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); + unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); if (!fcp->hash_table) { fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); if (!fcp->hash_table) { - pr_err("NET: failed to allocate flow cache sz %zu\n", sz); + pr_err("NET: failed to allocate flow cache sz %u\n", sz); return -ENOMEM; } fcp->hash_rnd_recalc = 1; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d98d4998213d..c9cf425303f8 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -113,6 +113,216 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +enum flow_dissect_ret { + FLOW_DISSECT_RET_OUT_GOOD, + FLOW_DISSECT_RET_OUT_BAD, + FLOW_DISSECT_RET_OUT_PROTO_AGAIN, +}; + +static enum flow_dissect_ret +__skb_flow_dissect_mpls(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_keyid *key_keyid; + struct mpls_label *hdr, _hdr[2]; + + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) + return FLOW_DISSECT_RET_OUT_GOOD; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> + MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY, + target_container); + key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK); + } + return FLOW_DISSECT_RET_OUT_GOOD; +} + +static enum flow_dissect_ret +__skb_flow_dissect_arp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, int hlen) +{ + struct flow_dissector_key_arp *key_arp; + struct { + unsigned char ar_sha[ETH_ALEN]; + unsigned char ar_sip[4]; + unsigned char ar_tha[ETH_ALEN]; + unsigned char ar_tip[4]; + } *arp_eth, _arp_eth; + const struct arphdr *arp; + struct arphdr _arp; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) + return FLOW_DISSECT_RET_OUT_GOOD; + + arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, + hlen, &_arp); + if (!arp) + return FLOW_DISSECT_RET_OUT_BAD; + + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_hln != ETH_ALEN || + arp->ar_pln != 4 || + (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST))) + return FLOW_DISSECT_RET_OUT_BAD; + + arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), + sizeof(_arp_eth), data, + hlen, &_arp_eth); + if (!arp_eth) + return FLOW_DISSECT_RET_OUT_BAD; + + key_arp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ARP, + target_container); + + memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); + memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); + + /* Only store the lower byte of the opcode; + * this covers ARPOP_REPLY and ARPOP_REQUEST. + */ + key_arp->op = ntohs(arp->ar_op) & 0xff; + + ether_addr_copy(key_arp->sha, arp_eth->ar_sha); + ether_addr_copy(key_arp->tha, arp_eth->ar_tha); + + return FLOW_DISSECT_RET_OUT_GOOD; +} + +static enum flow_dissect_ret +__skb_flow_dissect_gre(const struct sk_buff *skb, + struct flow_dissector_key_control *key_control, + struct flow_dissector *flow_dissector, + void *target_container, void *data, + __be16 *p_proto, int *p_nhoff, int *p_hlen, + unsigned int flags) +{ + struct flow_dissector_key_keyid *key_keyid; + struct gre_base_hdr *hdr, _hdr; + int offset = 0; + u16 gre_ver; + + hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), + data, *p_hlen, &_hdr); + if (!hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + /* Only look inside GRE without routing */ + if (hdr->flags & GRE_ROUTING) + return FLOW_DISSECT_RET_OUT_GOOD; + + /* Only look inside GRE for version 0 and 1 */ + gre_ver = ntohs(hdr->flags & GRE_VERSION); + if (gre_ver > 1) + return FLOW_DISSECT_RET_OUT_GOOD; + + *p_proto = hdr->protocol; + if (gre_ver) { + /* Version1 must be PPTP, and check the flags */ + if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) + return FLOW_DISSECT_RET_OUT_GOOD; + } + + offset += sizeof(struct gre_base_hdr); + + if (hdr->flags & GRE_CSUM) + offset += sizeof(((struct gre_full_hdr *) 0)->csum) + + sizeof(((struct gre_full_hdr *) 0)->reserved1); + + if (hdr->flags & GRE_KEY) { + const __be32 *keyid; + __be32 _keyid; + + keyid = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_keyid), + data, *p_hlen, &_keyid); + if (!keyid) + return FLOW_DISSECT_RET_OUT_BAD; + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID)) { + key_keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID, + target_container); + if (gre_ver == 0) + key_keyid->keyid = *keyid; + else + key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; + } + offset += sizeof(((struct gre_full_hdr *) 0)->key); + } + + if (hdr->flags & GRE_SEQ) + offset += sizeof(((struct pptp_gre_header *) 0)->seq); + + if (gre_ver == 0) { + if (*p_proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_eth), + data, *p_hlen, &_eth); + if (!eth) + return FLOW_DISSECT_RET_OUT_BAD; + *p_proto = eth->h_proto; + offset += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + *p_hlen = *p_nhoff + offset; + } + } else { /* version 1, must be PPTP */ + u8 _ppp_hdr[PPP_HDRLEN]; + u8 *ppp_hdr; + + if (hdr->flags & GRE_ACK) + offset += sizeof(((struct pptp_gre_header *) 0)->ack); + + ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, + sizeof(_ppp_hdr), + data, *p_hlen, _ppp_hdr); + if (!ppp_hdr) + return FLOW_DISSECT_RET_OUT_BAD; + + switch (PPP_PROTOCOL(ppp_hdr)) { + case PPP_IP: + *p_proto = htons(ETH_P_IP); + break; + case PPP_IPV6: + *p_proto = htons(ETH_P_IPV6); + break; + default: + /* Could probably catch some more like MPLS */ + break; + } + + offset += PPP_HDRLEN; + } + + *p_nhoff += offset; + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return FLOW_DISSECT_RET_OUT_GOOD; + + return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -138,12 +348,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_arp *key_arp; struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct flow_dissector_key_keyid *key_keyid; bool skip_vlan = false; u8 ip_proto = 0; bool ret; @@ -181,7 +389,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); } -again: +proto_again: switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; @@ -284,7 +492,7 @@ ipv6: proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); if (skip_vlan) - goto again; + goto proto_again; } skip_vlan = true; @@ -307,7 +515,7 @@ ipv6: } } - goto again; + goto proto_again; } case htons(ETH_P_PPP_SES): { struct { @@ -349,31 +557,17 @@ ipv6: } case htons(ETH_P_MPLS_UC): - case htons(ETH_P_MPLS_MC): { - struct mpls_label *hdr, _hdr[2]; + case htons(ETH_P_MPLS_MC): mpls: - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, - hlen, &_hdr); - if (!hdr) - goto out_bad; - - if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> - MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY, - target_container); - key_keyid->keyid = hdr[1].entry & - htonl(MPLS_LS_LABEL_MASK); - } - + switch (__skb_flow_dissect_mpls(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: + default: + goto out_bad; } - - goto out_good; - } - case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) goto out_bad; @@ -382,177 +576,33 @@ mpls: goto out_good; case htons(ETH_P_ARP): - case htons(ETH_P_RARP): { - struct { - unsigned char ar_sha[ETH_ALEN]; - unsigned char ar_sip[4]; - unsigned char ar_tha[ETH_ALEN]; - unsigned char ar_tip[4]; - } *arp_eth, _arp_eth; - const struct arphdr *arp; - struct arphdr _arp; - - arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, - hlen, &_arp); - if (!arp) - goto out_bad; - - if (arp->ar_hrd != htons(ARPHRD_ETHER) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_hln != ETH_ALEN || - arp->ar_pln != 4 || - (arp->ar_op != htons(ARPOP_REPLY) && - arp->ar_op != htons(ARPOP_REQUEST))) - goto out_bad; - - arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), - sizeof(_arp_eth), data, - hlen, - &_arp_eth); - if (!arp_eth) + case htons(ETH_P_RARP): + switch (__skb_flow_dissect_arp(skb, flow_dissector, + target_container, data, + nhoff, hlen)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: + default: goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ARP)) { - - key_arp = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_ARP, - target_container); - - memcpy(&key_arp->sip, arp_eth->ar_sip, - sizeof(key_arp->sip)); - memcpy(&key_arp->tip, arp_eth->ar_tip, - sizeof(key_arp->tip)); - - /* Only store the lower byte of the opcode; - * this covers ARPOP_REPLY and ARPOP_REQUEST. - */ - key_arp->op = ntohs(arp->ar_op) & 0xff; - - ether_addr_copy(key_arp->sha, arp_eth->ar_sha); - ether_addr_copy(key_arp->tha, arp_eth->ar_tha); } - - goto out_good; - } - default: goto out_bad; } ip_proto_again: switch (ip_proto) { - case IPPROTO_GRE: { - struct gre_base_hdr *hdr, _hdr; - u16 gre_ver; - int offset = 0; - - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); - if (!hdr) + case IPPROTO_GRE: + switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector, + target_container, data, + &proto, &nhoff, &hlen, flags)) { + case FLOW_DISSECT_RET_OUT_GOOD: + goto out_good; + case FLOW_DISSECT_RET_OUT_BAD: goto out_bad; - - /* Only look inside GRE without routing */ - if (hdr->flags & GRE_ROUTING) - break; - - /* Only look inside GRE for version 0 and 1 */ - gre_ver = ntohs(hdr->flags & GRE_VERSION); - if (gre_ver > 1) - break; - - proto = hdr->protocol; - if (gre_ver) { - /* Version1 must be PPTP, and check the flags */ - if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) - break; - } - - offset += sizeof(struct gre_base_hdr); - - if (hdr->flags & GRE_CSUM) - offset += sizeof(((struct gre_full_hdr *)0)->csum) + - sizeof(((struct gre_full_hdr *)0)->reserved1); - - if (hdr->flags & GRE_KEY) { - const __be32 *keyid; - __be32 _keyid; - - keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid), - data, hlen, &_keyid); - if (!keyid) - goto out_bad; - - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID)) { - key_keyid = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID, - target_container); - if (gre_ver == 0) - key_keyid->keyid = *keyid; - else - key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; - } - offset += sizeof(((struct gre_full_hdr *)0)->key); + case FLOW_DISSECT_RET_OUT_PROTO_AGAIN: + goto proto_again; } - - if (hdr->flags & GRE_SEQ) - offset += sizeof(((struct pptp_gre_header *)0)->seq); - - if (gre_ver == 0) { - if (proto == htons(ETH_P_TEB)) { - const struct ethhdr *eth; - struct ethhdr _eth; - - eth = __skb_header_pointer(skb, nhoff + offset, - sizeof(_eth), - data, hlen, &_eth); - if (!eth) - goto out_bad; - proto = eth->h_proto; - offset += sizeof(*eth); - - /* Cap headers that we access via pointers at the - * end of the Ethernet header as our maximum alignment - * at that point is only 2 bytes. - */ - if (NET_IP_ALIGN) - hlen = (nhoff + offset); - } - } else { /* version 1, must be PPTP */ - u8 _ppp_hdr[PPP_HDRLEN]; - u8 *ppp_hdr; - - if (hdr->flags & GRE_ACK) - offset += sizeof(((struct pptp_gre_header *)0)->ack); - - ppp_hdr = __skb_header_pointer(skb, nhoff + offset, - sizeof(_ppp_hdr), - data, hlen, _ppp_hdr); - if (!ppp_hdr) - goto out_bad; - - switch (PPP_PROTOCOL(ppp_hdr)) { - case PPP_IP: - proto = htons(ETH_P_IP); - break; - case PPP_IPV6: - proto = htons(ETH_P_IPV6); - break; - default: - /* Could probably catch some more like MPLS */ - break; - } - - offset += PPP_HDRLEN; - } - - nhoff += offset; - key_control->flags |= FLOW_DIS_ENCAPSULATION; - if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) - goto out_good; - - goto again; - } case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6df9f8fabf0c..b5888190223c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; - struct nlattr *nla; u16 encap_type; int attrlen; @@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); - nla = nla_find(attrs, attrlen, RTA_ENCAP); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 4526cbd7e28a..8ae87c591c8e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -52,8 +52,9 @@ do { \ #define PNEIGH_HASHMASK 0xF static void neigh_timer_handler(unsigned long arg); -static void __neigh_notify(struct neighbour *n, int type, int flags); -static void neigh_update_notify(struct neighbour *neigh); +static void __neigh_notify(struct neighbour *n, int type, int flags, + u32 pid); +static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); #ifdef CONFIG_PROC_FS @@ -99,7 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) if (neigh->parms->neigh_cleanup) neigh->parms->neigh_cleanup(neigh); - __neigh_notify(neigh, RTM_DELNEIGH, 0); + __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); neigh_release(neigh); } @@ -949,7 +950,7 @@ out: } if (notify) - neigh_update_notify(neigh); + neigh_update_notify(neigh, 0); neigh_release(neigh); } @@ -1073,7 +1074,7 @@ static void neigh_update_hhs(struct neighbour *neigh) */ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, - u32 flags) + u32 flags, u32 nlmsg_pid) { u8 old; int err; @@ -1230,7 +1231,7 @@ out: write_unlock_bh(&neigh->lock); if (notify) - neigh_update_notify(neigh); + neigh_update_notify(neigh, nlmsg_pid); return err; } @@ -1261,7 +1262,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, lladdr || !dev->addr_len); if (neigh) neigh_update(neigh, lladdr, NUD_STALE, - NEIGH_UPDATE_F_OVERRIDE); + NEIGH_UPDATE_F_OVERRIDE, 0); return neigh; } EXPORT_SYMBOL(neigh_event_ns); @@ -1639,7 +1640,8 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_ADMIN); + NEIGH_UPDATE_F_ADMIN, + NETLINK_CB(skb).portid); neigh_release(neigh); out: @@ -1730,7 +1732,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh) neigh_event_send(neigh, NULL); err = 0; } else - err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags, + NETLINK_CB(skb).portid); neigh_release(neigh); out: @@ -2230,10 +2233,10 @@ nla_put_failure: return -EMSGSIZE; } -static void neigh_update_notify(struct neighbour *neigh) +static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid) { call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); - __neigh_notify(neigh, RTM_NEWNEIGH, 0); + __neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid); } static bool neigh_master_filtered(struct net_device *dev, int master_idx) @@ -2831,7 +2834,8 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(4); /* NDA_PROBES */ } -static void __neigh_notify(struct neighbour *n, int type, int flags) +static void __neigh_notify(struct neighbour *n, int type, int flags, + u32 pid) { struct net *net = dev_net(n->dev); struct sk_buff *skb; @@ -2841,7 +2845,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags) if (skb == NULL) goto errout; - err = neigh_fill_info(skb, n, 0, 0, type, flags); + err = neigh_fill_info(skb, n, pid, 0, type, flags); if (err < 0) { /* -EMSGSIZE implies BUG in neigh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2857,7 +2861,7 @@ errout: void neigh_app_ns(struct neighbour *n) { - __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); + __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0); } EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 0f9275ee5595..1c4810919a0a 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/module.h> diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c4e84c558240..b2bd4c9ee860 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -944,6 +944,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size(dev) /* IFLA_XDP */ + + nla_total_size(4) /* IFLA_EVENT */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1276,9 +1277,70 @@ err_cancel: return err; } +static int rtnl_fill_link_event(struct sk_buff *skb, unsigned long event) +{ + u32 rtnl_event; + + switch (event) { + case NETDEV_REBOOT: + rtnl_event = IFLA_EVENT_REBOOT; + break; + case NETDEV_CHANGEMTU: + rtnl_event = IFLA_EVENT_CHANGE_MTU; + break; + case NETDEV_CHANGEADDR: + rtnl_event = IFLA_EVENT_CHANGE_ADDR; + break; + case NETDEV_CHANGENAME: + rtnl_event = IFLA_EVENT_CHANGE_NAME; + break; + case NETDEV_FEAT_CHANGE: + rtnl_event = IFLA_EVENT_FEAT_CHANGE; + break; + case NETDEV_BONDING_FAILOVER: + rtnl_event = IFLA_EVENT_BONDING_FAILOVER; + break; + case NETDEV_POST_TYPE_CHANGE: + rtnl_event = IFLA_EVENT_POST_TYPE_CHANGE; + break; + case NETDEV_NOTIFY_PEERS: + rtnl_event = IFLA_EVENT_NOTIFY_PEERS; + break; + case NETDEV_CHANGEUPPER: + rtnl_event = IFLA_EVENT_CHANGE_UPPER; + break; + case NETDEV_RESEND_IGMP: + rtnl_event = IFLA_EVENT_RESEND_IGMP; + break; + case NETDEV_PRECHANGEMTU: + rtnl_event = IFLA_EVENT_PRE_CHANGE_MTU; + break; + case NETDEV_CHANGEINFODATA: + rtnl_event = IFLA_EVENT_CHANGE_INFO_DATA; + break; + case NETDEV_PRECHANGEUPPER: + rtnl_event = IFLA_EVENT_PRE_CHANGE_UPPER; + break; + case NETDEV_CHANGELOWERSTATE: + rtnl_event = IFLA_EVENT_CHANGE_LOWER_STATE; + break; + case NETDEV_UDP_TUNNEL_PUSH_INFO: + rtnl_event = IFLA_EVENT_UDP_TUNNEL_PUSH_INFO; + break; + case NETDEV_CHANGE_TX_QUEUE_LEN: + rtnl_event = IFLA_EVENT_CHANGE_TX_QUEUE_LEN; + break; + default: + return 0; + } + + return nla_put_u32(skb, IFLA_EVENT, rtnl_event); +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags, u32 ext_filter_mask) + unsigned int flags, u32 ext_filter_mask, + unsigned long event) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1327,6 +1389,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; + if (rtnl_fill_link_event(skb, event)) + goto nla_put_failure; + if (rtnl_fill_link_ifmap(skb, dev)) goto nla_put_failure; @@ -1461,6 +1526,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, [IFLA_XDP] = { .type = NLA_NESTED }, + [IFLA_EVENT] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1619,7 +1685,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask); + ext_filter_mask, 0); /* If we ran out of room on the first message, * we're in trouble */ @@ -2710,7 +2776,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh) return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2782,7 +2848,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) } struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned int change, gfp_t flags) + unsigned int change, + unsigned long event, gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2793,7 +2860,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2814,18 +2881,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) +static void rtmsg_ifinfo_event(int type, struct net_device *dev, + unsigned int change, unsigned long event, + gfp_t flags) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } + +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) +{ + rtmsg_ifinfo_event(type, dev, change, 0, flags); +} EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, @@ -4116,22 +4190,25 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { - case NETDEV_UP: - case NETDEV_DOWN: - case NETDEV_PRE_UP: - case NETDEV_POST_INIT: - case NETDEV_REGISTER: - case NETDEV_CHANGE: - case NETDEV_PRE_TYPE_CHANGE: - case NETDEV_GOING_DOWN: - case NETDEV_UNREGISTER: - case NETDEV_UNREGISTER_FINAL: - case NETDEV_RELEASE: - case NETDEV_JOIN: - case NETDEV_BONDING_INFO: + case NETDEV_REBOOT: + case NETDEV_CHANGEMTU: + case NETDEV_CHANGEADDR: + case NETDEV_CHANGENAME: + case NETDEV_FEAT_CHANGE: + case NETDEV_BONDING_FAILOVER: + case NETDEV_POST_TYPE_CHANGE: + case NETDEV_NOTIFY_PEERS: + case NETDEV_CHANGEUPPER: + case NETDEV_RESEND_IGMP: + case NETDEV_PRECHANGEMTU: + case NETDEV_CHANGEINFODATA: + case NETDEV_PRECHANGEUPPER: + case NETDEV_CHANGELOWERSTATE: + case NETDEV_UDP_TUNNEL_PUSH_INFO: + case NETDEV_CHANGE_TX_QUEUE_LEN: + rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, event, GFP_KERNEL); break; default: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); break; } return NOTIFY_DONE; @@ -4185,6 +4262,7 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL); rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index d28da7d363f1..6bd2f8fb0476 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -64,8 +64,8 @@ static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) &ts_secret); } -u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport, u32 *tsoff) { const struct { struct in6_addr saddr; @@ -85,7 +85,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, *tsoff = secure_tcpv6_ts_off(saddr, daddr); return seq_scale(hash); } -EXPORT_SYMBOL(secure_tcpv6_sequence_number); +EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -116,14 +116,13 @@ static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) &ts_secret); } -/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), +/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ - -u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport, u32 *tsoff) +u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff) { u64 hash; net_secret_init(); diff --git a/net/core/sock.c b/net/core/sock.c index 2c4f574168fb..392f9b6f96e2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -247,12 +247,66 @@ static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; +static const char *const af_family_rlock_key_strings[AF_MAX+1] = { + "rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" , + "rlock-AF_AX25" , "rlock-AF_IPX" , "rlock-AF_APPLETALK", + "rlock-AF_NETROM", "rlock-AF_BRIDGE" , "rlock-AF_ATMPVC" , + "rlock-AF_X25" , "rlock-AF_INET6" , "rlock-AF_ROSE" , + "rlock-AF_DECnet", "rlock-AF_NETBEUI" , "rlock-AF_SECURITY" , + "rlock-AF_KEY" , "rlock-AF_NETLINK" , "rlock-AF_PACKET" , + "rlock-AF_ASH" , "rlock-AF_ECONET" , "rlock-AF_ATMSVC" , + "rlock-AF_RDS" , "rlock-AF_SNA" , "rlock-AF_IRDA" , + "rlock-AF_PPPOX" , "rlock-AF_WANPIPE" , "rlock-AF_LLC" , + "rlock-27" , "rlock-28" , "rlock-AF_CAN" , + "rlock-AF_TIPC" , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV" , + "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , + "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , + "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" +}; +static const char *const af_family_wlock_key_strings[AF_MAX+1] = { + "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , + "wlock-AF_AX25" , "wlock-AF_IPX" , "wlock-AF_APPLETALK", + "wlock-AF_NETROM", "wlock-AF_BRIDGE" , "wlock-AF_ATMPVC" , + "wlock-AF_X25" , "wlock-AF_INET6" , "wlock-AF_ROSE" , + "wlock-AF_DECnet", "wlock-AF_NETBEUI" , "wlock-AF_SECURITY" , + "wlock-AF_KEY" , "wlock-AF_NETLINK" , "wlock-AF_PACKET" , + "wlock-AF_ASH" , "wlock-AF_ECONET" , "wlock-AF_ATMSVC" , + "wlock-AF_RDS" , "wlock-AF_SNA" , "wlock-AF_IRDA" , + "wlock-AF_PPPOX" , "wlock-AF_WANPIPE" , "wlock-AF_LLC" , + "wlock-27" , "wlock-28" , "wlock-AF_CAN" , + "wlock-AF_TIPC" , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV" , + "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , + "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , + "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" +}; +static const char *const af_family_elock_key_strings[AF_MAX+1] = { + "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , + "elock-AF_AX25" , "elock-AF_IPX" , "elock-AF_APPLETALK", + "elock-AF_NETROM", "elock-AF_BRIDGE" , "elock-AF_ATMPVC" , + "elock-AF_X25" , "elock-AF_INET6" , "elock-AF_ROSE" , + "elock-AF_DECnet", "elock-AF_NETBEUI" , "elock-AF_SECURITY" , + "elock-AF_KEY" , "elock-AF_NETLINK" , "elock-AF_PACKET" , + "elock-AF_ASH" , "elock-AF_ECONET" , "elock-AF_ATMSVC" , + "elock-AF_RDS" , "elock-AF_SNA" , "elock-AF_IRDA" , + "elock-AF_PPPOX" , "elock-AF_WANPIPE" , "elock-AF_LLC" , + "elock-27" , "elock-28" , "elock-AF_CAN" , + "elock-AF_TIPC" , "elock-AF_BLUETOOTH", "elock-AF_IUCV" , + "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , + "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , + "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" +}; /* - * sk_callback_lock locking rules are per-address-family, + * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_rlock_keys[AF_MAX]; +static struct lock_class_key af_wlock_keys[AF_MAX]; +static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the @@ -1259,6 +1313,33 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_incoming_cpu; break; + case SO_MEMINFO: + { + u32 meminfo[SK_MEMINFO_VARS]; + + if (get_user(len, optlen)) + return -EFAULT; + + sk_get_meminfo(sk, meminfo); + + len = min_t(unsigned int, len, sizeof(meminfo)); + if (copy_to_user(optval, &meminfo, len)) + return -EFAULT; + + goto lenout; + } + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_INCOMING_NAPI_ID: + v.val = READ_ONCE(sk->sk_napi_id); + + /* aggregate non-NAPI IDs down to 0 */ + if (v.val < MIN_NAPI_ID) + v.val = 0; + + break; +#endif + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -1483,6 +1564,27 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); +static void sk_init_common(struct sock *sk) +{ + skb_queue_head_init(&sk->sk_receive_queue); + skb_queue_head_init(&sk->sk_write_queue); + skb_queue_head_init(&sk->sk_error_queue); + + rwlock_init(&sk->sk_callback_lock); + lockdep_set_class_and_name(&sk->sk_receive_queue.lock, + af_rlock_keys + sk->sk_family, + af_family_rlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_write_queue.lock, + af_wlock_keys + sk->sk_family, + af_family_wlock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_error_queue.lock, + af_elock_keys + sk->sk_family, + af_family_elock_key_strings[sk->sk_family]); + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_callback_keys + sk->sk_family, + af_family_clock_key_strings[sk->sk_family]); +} + /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1516,13 +1618,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); - skb_queue_head_init(&newsk->sk_receive_queue); - skb_queue_head_init(&newsk->sk_write_queue); - - rwlock_init(&newsk->sk_callback_lock); - lockdep_set_class_and_name(&newsk->sk_callback_lock, - af_callback_keys + newsk->sk_family, - af_family_clock_key_strings[newsk->sk_family]); + sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; @@ -1533,7 +1629,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; sock_reset_flag(newsk, SOCK_DONE); - skb_queue_head_init(&newsk->sk_error_queue); filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) @@ -2466,10 +2561,7 @@ EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) { - skb_queue_head_init(&sk->sk_receive_queue); - skb_queue_head_init(&sk->sk_write_queue); - skb_queue_head_init(&sk->sk_error_queue); - + sk_init_common(sk); sk->sk_send_head = NULL; init_timer(&sk->sk_timer); @@ -2521,7 +2613,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; - sk->sk_stamp = ktime_set(-1L, 0); + sk->sk_stamp = SK_DEFAULT_STAMP; #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; @@ -2802,6 +2894,21 @@ void sk_common_release(struct sock *sk) } EXPORT_SYMBOL(sk_common_release); +void sk_get_meminfo(const struct sock *sk, u32 *mem) +{ + memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); + + mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); + mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); + mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; + mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); +} + #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { @@ -3142,3 +3249,14 @@ static int __init proto_init(void) subsys_initcall(proto_init); #endif /* PROC_FS */ + +#ifdef CONFIG_NET_RX_BUSY_POLL +bool sk_busy_loop_end(void *p, unsigned long start_time) +{ + struct sock *sk = p; + + return !skb_queue_empty(&sk->sk_receive_queue) || + sk_busy_loop_timeout(sk, start_time); +} +EXPORT_SYMBOL(sk_busy_loop_end); +#endif /* CONFIG_NET_RX_BUSY_POLL */ diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 6b10573cc9fa..fb9d0e2fd148 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; -static u64 sock_gen_cookie(struct sock *sk) +u64 sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); @@ -59,15 +59,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; - mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); - mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; - mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); - mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; - mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; - mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; - mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; - mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); + sk_get_meminfo(sk, mem); return nla_put(skb, attrtype, sizeof(mem), &mem); } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 9a1a352fd1eb..eed1ebf7f29d 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -13,9 +13,9 @@ static DEFINE_SPINLOCK(reuseport_lock); -static struct sock_reuseport *__reuseport_alloc(u16 max_socks) +static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { - size_t size = sizeof(struct sock_reuseport) + + unsigned int size = sizeof(struct sock_reuseport) + sizeof(struct sock *) * max_socks; struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); diff --git a/net/core/utils.c b/net/core/utils.c index 6592d7bbed39..d758880c09a7 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -51,7 +51,7 @@ EXPORT_SYMBOL(net_ratelimit); __be32 in_aton(const char *str) { - unsigned long l; + unsigned int l; unsigned int val; int i; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 7de5b40a5d0d..9afa2a5030b2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -132,6 +132,7 @@ Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat #include <net/neighbour.h> #include <net/dst.h> #include <net/fib_rules.h> +#include <net/tcp.h> #include <net/dn.h> #include <net/dn_nsp.h> #include <net/dn_dev.h> @@ -1469,18 +1470,18 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 2) + if (scp->nonagle == TCP_NAGLE_CORK) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 1; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF; /* if (scp->nonagle == 1) { Push pending frames } */ break; case DSO_CORK: if (optlen != sizeof(int)) return -EINVAL; - if (scp->nonagle == 1) + if (scp->nonagle == TCP_NAGLE_OFF) return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 2; + scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK; /* if (scp->nonagle == 0) { Push pending frames } */ break; @@ -1608,14 +1609,14 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us case DSO_NODELAY: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 1); + val = (scp->nonagle == TCP_NAGLE_OFF); r_data = &val; break; case DSO_CORK: if (r_len > sizeof(int)) r_len = sizeof(int); - val = (scp->nonagle == 2); + val = (scp->nonagle == TCP_NAGLE_CORK); r_data = &val; break; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 9649238eef40..da4d64f432db 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -6,7 +6,7 @@ config HAVE_NET_DSA config NET_DSA tristate "Distributed Switch Architecture" - depends on HAVE_NET_DSA + depends on HAVE_NET_DSA && MAY_USE_DEVLINK select NET_SWITCHDEV select PHYLIB ---help--- diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index b6d4f6a23f06..95d1a756202c 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -14,15 +14,16 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/module.h> -#include <net/dsa.h> #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/of_gpio.h> +#include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/gpio/consumer.h> +#include <net/dsa.h> #include "dsa_priv.h" static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 737be6470c7f..033b3bfb63dc 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -13,16 +13,20 @@ #include <linux/device.h> #include <linux/err.h> #include <linux/list.h> +#include <linux/netdevice.h> #include <linux/slab.h> #include <linux/rtnetlink.h> -#include <net/dsa.h> #include <linux/of.h> #include <linux/of_net.h> +#include <net/dsa.h> #include "dsa_priv.h" static LIST_HEAD(dsa_switch_trees); static DEFINE_MUTEX(dsa2_mutex); +static const struct devlink_ops dsa_devlink_ops = { +}; + static struct dsa_switch_tree *dsa_get_dst(u32 tree) { struct dsa_switch_tree *dst; @@ -222,12 +226,18 @@ static int dsa_dsa_port_apply(struct dsa_port *port, u32 index, return err; } - return 0; + memset(&ds->ports[index].devlink_port, 0, + sizeof(ds->ports[index].devlink_port)); + + return devlink_port_register(ds->devlink, + &ds->ports[index].devlink_port, + index); } static void dsa_dsa_port_unapply(struct dsa_port *port, u32 index, struct dsa_switch *ds) { + devlink_port_unregister(&ds->ports[index].devlink_port); dsa_cpu_dsa_destroy(port); } @@ -245,12 +255,17 @@ static int dsa_cpu_port_apply(struct dsa_port *port, u32 index, ds->cpu_port_mask |= BIT(index); - return 0; + memset(&ds->ports[index].devlink_port, 0, + sizeof(ds->ports[index].devlink_port)); + err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port, + index); + return err; } static void dsa_cpu_port_unapply(struct dsa_port *port, u32 index, struct dsa_switch *ds) { + devlink_port_unregister(&ds->ports[index].devlink_port); dsa_cpu_dsa_destroy(port); ds->cpu_port_mask &= ~BIT(index); @@ -275,12 +290,23 @@ static int dsa_user_port_apply(struct dsa_port *port, u32 index, return err; } + memset(&ds->ports[index].devlink_port, 0, + sizeof(ds->ports[index].devlink_port)); + err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port, + index); + if (err) + return err; + + devlink_port_type_eth_set(&ds->ports[index].devlink_port, + ds->ports[index].netdev); + return 0; } static void dsa_user_port_unapply(struct dsa_port *port, u32 index, struct dsa_switch *ds) { + devlink_port_unregister(&ds->ports[index].devlink_port); if (ds->ports[index].netdev) { dsa_slave_destroy(ds->ports[index].netdev); ds->ports[index].netdev = NULL; @@ -301,6 +327,17 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) */ ds->phys_mii_mask = ds->enabled_port_mask; + /* Add the switch to devlink before calling setup, so that setup can + * add dpipe tables + */ + ds->devlink = devlink_alloc(&dsa_devlink_ops, 0); + if (!ds->devlink) + return -ENOMEM; + + err = devlink_register(ds->devlink, ds->dev); + if (err) + return err; + err = ds->ops->setup(ds); if (err < 0) return err; @@ -381,6 +418,13 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) mdiobus_unregister(ds->slave_mii_bus); dsa_switch_unregister_notifier(ds); + + if (ds->devlink) { + devlink_unregister(ds->devlink); + devlink_free(ds->devlink); + ds->devlink = NULL; + } + } static int dsa_dst_apply(struct dsa_switch_tree *dst) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c34872e1febc..7693182df81e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -17,6 +17,7 @@ #include <linux/of_mdio.h> #include <linux/mdio.h> #include <linux/list.h> +#include <net/dsa.h> #include <net/rtnetlink.h> #include <net/switchdev.h> #include <net/pkt_cls.h> @@ -419,8 +420,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev, return 0; } -static int dsa_fastest_ageing_time(struct dsa_switch *ds, - unsigned int ageing_time) +static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds, + unsigned int ageing_time) { int i; @@ -443,9 +444,13 @@ static int dsa_slave_ageing_time(struct net_device *dev, unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time); unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) + if (switchdev_trans_ph_prepare(trans)) { + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; return 0; + } /* Keep the fastest ageing time in case of multiple bridges */ p->dp->ageing_time = ageing_time; diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 6456dacf9ae9..ca6e26e514f0 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -1,7 +1,8 @@ /* * Handling of a single switch chip, part of a switch fabric * - * Copyright (c) 2017 Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * Copyright (c) 2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.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 @@ -19,9 +20,9 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, if (ds->index == info->sw_index && ds->ops->port_bridge_join) return ds->ops->port_bridge_join(ds, info->port, info->br); - if (ds->index != info->sw_index) - dev_dbg(ds->dev, "crosschip DSA port %d.%d bridged to %s\n", - info->sw_index, info->port, netdev_name(info->br)); + if (ds->index != info->sw_index && ds->ops->crosschip_bridge_join) + return ds->ops->crosschip_bridge_join(ds, info->sw_index, + info->port, info->br); return 0; } @@ -32,9 +33,9 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, if (ds->index == info->sw_index && ds->ops->port_bridge_leave) ds->ops->port_bridge_leave(ds, info->port, info->br); - if (ds->index != info->sw_index) - dev_dbg(ds->dev, "crosschip DSA port %d.%d unbridged from %s\n", - info->sw_index, info->port, netdev_name(info->br)); + if (ds->index != info->sw_index && ds->ops->crosschip_bridge_leave) + ds->ops->crosschip_bridge_leave(ds, info->sw_index, info->port, + info->br); return 0; } diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 5d925b6b2bb1..e2ed6cf68261 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -12,6 +12,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> +#include <net/dsa.h> #include "dsa_priv.h" /* This tag length is 4 bytes, older ones were 6 bytes, we do not diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 72579ceea381..e42ba906100c 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -11,6 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> +#include <net/dsa.h> #include "dsa_priv.h" #define DSA_HLEN 4 diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 648c051817a1..6a9b7a9e4e15 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -11,6 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> +#include <net/dsa.h> #include "dsa_priv.h" #define DSA_HLEN 4 diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 30240f343aea..4e0dad759d04 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -12,6 +12,7 @@ */ #include <linux/etherdevice.h> +#include <net/dsa.h> #include "dsa_priv.h" #define QCA_HDR_LEN 2 diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 26f977176978..74c948512550 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -11,6 +11,7 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> +#include <net/dsa.h> #include "dsa_priv.h" static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index c6d4238ff94a..f83de23a30e7 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_rate.o tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ - fib_frontend.o fib_semantics.o fib_trie.o \ + fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6b1fc6e4278e..d1a11707a126 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1599,8 +1599,9 @@ static const struct net_protocol igmp_protocol = { }; #endif -static const struct net_protocol tcp_protocol = { +static struct net_protocol tcp_protocol = { .early_demux = tcp_v4_early_demux, + .early_demux_handler = tcp_v4_early_demux, .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, @@ -1608,8 +1609,9 @@ static const struct net_protocol tcp_protocol = { .icmp_strict_tag_validation = 1, }; -static const struct net_protocol udp_protocol = { +static struct net_protocol udp_protocol = { .early_demux = udp_v4_early_demux, + .early_demux_handler = udp_v4_early_demux, .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, @@ -1720,6 +1722,8 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; + net->ipv4.sysctl_udp_early_demux = 1; + net->ipv4.sysctl_tcp_early_demux = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 51b27ae09fbd..0937b34c27ca 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -872,7 +872,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) skb->pkt_type != PACKET_HOST) state = NUD_STALE; neigh_update(n, sha, state, - override ? NEIGH_UPDATE_F_OVERRIDE : 0); + override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0); neigh_release(n); } @@ -1033,7 +1033,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_ADMIN); + NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); } return err; @@ -1084,7 +1084,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip) if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); + NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebedd545e5e..6d3602ec640c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1192,6 +1192,18 @@ out: return done; } +static __be32 in_dev_select_addr(const struct in_device *in_dev, + int scope) +{ + for_primary_ifa(in_dev) { + if (ifa->ifa_scope != RT_SCOPE_LINK && + ifa->ifa_scope <= scope) + return ifa->ifa_local; + } endfor_ifa(in_dev); + + return 0; +} + __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { __be32 addr = 0; @@ -1228,13 +1240,9 @@ no_in_dev: if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } /* Not loopback addresses on loopback should be preferred @@ -1249,13 +1257,9 @@ no_in_dev: if (!in_dev) continue; - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } out_unlock: rcu_read_unlock(); @@ -1798,6 +1802,9 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; + if (!devconf) + goto out; + if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF(*devconf, FORWARDING)) < 0) @@ -1819,6 +1826,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; +out: nlmsg_end(skb, nlh); return 0; @@ -1827,8 +1835,8 @@ nla_put_failure: return -EMSGSIZE; } -void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, - struct ipv4_devconf *devconf) +void inet_netconf_notify_devconf(struct net *net, int event, int type, + int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; @@ -1838,7 +1846,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, - RTM_NEWNETCONF, 0, type); + event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); @@ -2017,10 +2025,12 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); @@ -2033,7 +2043,8 @@ static void inet_forward_change(struct net *net) in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } @@ -2078,19 +2089,22 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); - inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); - inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); - inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } @@ -2125,7 +2139,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); - inet_netconf_notify_devconf(net, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); @@ -2133,7 +2147,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, rtnl_unlock(); rt_cache_flush(net); } else - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } @@ -2255,7 +2270,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, p->sysctl = t; - inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, + ifindex, p); return 0; free: @@ -2264,16 +2280,18 @@ out: return -ENOBUFS; } -static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) +static void __devinet_sysctl_unregister(struct net *net, + struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; - if (!t) - return; + if (t) { + cnf->sysctl = NULL; + unregister_net_sysctl_table(t->sysctl_header); + kfree(t); + } - cnf->sysctl = NULL; - unregister_net_sysctl_table(t->sysctl_header); - kfree(t); + inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) @@ -2295,7 +2313,9 @@ static int devinet_sysctl_register(struct in_device *idev) static void devinet_sysctl_unregister(struct in_device *idev) { - __devinet_sysctl_unregister(&idev->cnf); + struct net *net = dev_net(idev->dev); + + __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } @@ -2370,9 +2390,9 @@ static __net_init int devinet_init_net(struct net *net) #ifdef CONFIG_SYSCTL err_reg_ctl: - __devinet_sysctl_unregister(dflt); + __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: - __devinet_sysctl_unregister(all); + __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: if (tbl != ctl_forward_entry) kfree(tbl); @@ -2394,8 +2414,10 @@ static __net_exit void devinet_exit_net(struct net *net) tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); - __devinet_sysctl_unregister(net->ipv4.devconf_dflt); - __devinet_sysctl_unregister(net->ipv4.devconf_all); + __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, + NETCONFA_IFINDEX_DEFAULT); + __devinet_sysctl_unregister(net, net->ipv4.devconf_all, + NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c new file mode 100644 index 000000000000..e0714d975947 --- /dev/null +++ b/net/ipv4/fib_notifier.c @@ -0,0 +1,86 @@ +#include <linux/rtnetlink.h> +#include <linux/notifier.h> +#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <net/net_namespace.h> +#include <net/netns/ipv4.h> +#include <net/ip_fib.h> + +static ATOMIC_NOTIFIER_HEAD(fib_chain); + +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->net = net; + return nb->notifier_call(nb, event_type, info); +} + +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + net->ipv4.fib_seq++; + info->net = net; + return atomic_notifier_call_chain(&fib_chain, event_type, info); +} + +static unsigned int fib_seq_sum(void) +{ + unsigned int fib_seq = 0; + struct net *net; + + rtnl_lock(); + for_each_net(net) + fib_seq += net->ipv4.fib_seq; + rtnl_unlock(); + + return fib_seq; +} + +static bool fib_dump_is_consistent(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + unsigned int fib_seq) +{ + atomic_notifier_chain_register(&fib_chain, nb); + if (fib_seq == fib_seq_sum()) + return true; + atomic_notifier_chain_unregister(&fib_chain, nb); + if (cb) + cb(nb); + return false; +} + +#define FIB_DUMP_MAX_RETRIES 5 +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)) +{ + int retries = 0; + + do { + unsigned int fib_seq = fib_seq_sum(); + struct net *net; + + /* Mutex semantics guarantee that every change done to + * FIB tries before we read the change sequence counter + * is now visible to us. + */ + rcu_read_lock(); + for_each_net_rcu(net) { + fib_rules_notify(net, nb); + fib_notify(net, nb); + } + rcu_read_unlock(); + + if (fib_dump_is_consistent(nb, cb, fib_seq)) + return 0; + } while (++retries < FIB_DUMP_MAX_RETRIES); + + return -EBUSY; +} +EXPORT_SYMBOL(register_fib_notifier); + +int unregister_fib_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&fib_chain, nb); +} +EXPORT_SYMBOL(unregister_fib_notifier); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 2e50062f642d..778ecf977eb2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -47,6 +47,27 @@ struct fib4_rule { #endif }; +static bool fib4_rule_matchall(const struct fib_rule *rule) +{ + struct fib4_rule *r = container_of(rule, struct fib4_rule, common); + + if (r->dst_len || r->src_len || r->tos) + return false; + return fib_rule_matchall(rule); +} + +bool fib4_rule_default(const struct fib_rule *rule) +{ + if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || + rule->l3mdev) + return false; + if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN && + rule->table != RT_TABLE_DEFAULT) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib4_rule_default); + int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { @@ -164,12 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } +static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_rule *rule) +{ + struct fib_rule_notifier_info info = { + .rule = rule, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + static int call_fib_rule_notifiers(struct net *net, - enum fib_event_type event_type) + enum fib_event_type event_type, + struct fib_rule *rule) +{ + struct fib_rule_notifier_info info = { + .rule = rule, + }; + + return call_fib_notifiers(net, event_type, &info.info); +} + +/* Called with rcu_read_lock() */ +void fib_rules_notify(struct net *net, struct notifier_block *nb) { - struct fib_notifier_info info; + struct fib_rules_ops *ops = net->ipv4.rules_ops; + struct fib_rule *rule; - return call_fib_notifiers(net, event_type, &info); + list_for_each_entry_rcu(rule, &ops->rules_list, list) + call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule); } static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { @@ -228,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule); err = 0; errout: @@ -250,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule); errout: return err; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 317026a39cfa..da449ddb8cc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -57,7 +57,6 @@ static unsigned int fib_info_cnt; static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; #ifdef CONFIG_IP_ROUTE_MULTIPATH -u32 fib_multipath_secret __read_mostly; #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ @@ -576,9 +575,6 @@ static void fib_rebalance(struct fib_info *fi) atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); } endfor_nexthops(fi); - - net_get_random_once(&fib_multipath_secret, - sizeof(fib_multipath_secret)); } static inline void fib_add_weight(struct fib_info *fi, @@ -1641,7 +1637,7 @@ void fib_select_multipath(struct fib_result *res, int hash) #endif void fib_select_path(struct net *net, struct fib_result *res, - struct flowi4 *fl4, int mp_hash) + struct flowi4 *fl4, const struct sk_buff *skb) { bool oif_check; @@ -1650,10 +1646,9 @@ void fib_select_path(struct net *net, struct fib_result *res, #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi->fib_nhs > 1 && oif_check) { - if (mp_hash < 0) - mp_hash = get_hash_from_flowi4(fl4) >> 1; + int h = fib_multipath_hash(res->fi, fl4, skb); - fib_select_multipath(res, mp_hash); + fib_select_multipath(res, h); } else #endif diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2f0d8233950f..1201409ba1dc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -84,43 +84,6 @@ #include <trace/events/fib.h> #include "fib_lookup.h" -static unsigned int fib_seq_sum(void) -{ - unsigned int fib_seq = 0; - struct net *net; - - rtnl_lock(); - for_each_net(net) - fib_seq += net->ipv4.fib_seq; - rtnl_unlock(); - - return fib_seq; -} - -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -static int call_fib_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - info->net = net; - return nb->notifier_call(nb, event_type, info); -} - -static void fib_rules_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) -{ -#ifdef CONFIG_IP_MULTIPLE_TABLES - struct fib_notifier_info info; - - if (net->ipv4.fib_has_custom_rules) - call_fib_notifier(nb, net, event_type, &info); -#endif -} - -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type); - static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, return call_fib_notifier(nb, net, event_type, &info.info); } -static bool fib_dump_is_consistent(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb), - unsigned int fib_seq) -{ - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) - return true; - atomic_notifier_chain_unregister(&fib_chain, nb); - if (cb) - cb(nb); - return false; -} - -#define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) -{ - int retries = 0; - - do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - /* Mutex semantics guarantee that every change done to - * FIB tries before we read the change sequence counter - * is now visible to us. - */ - rcu_read_lock(); - for_each_net_rcu(net) { - fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD); - fib_notify(net, nb, FIB_EVENT_ENTRY_ADD); - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) - return 0; - } while (++retries < FIB_DUMP_MAX_RETRIES); - - return -EBUSY; -} -EXPORT_SYMBOL(register_fib_notifier); - -int unregister_fib_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&fib_chain, nb); -} -EXPORT_SYMBOL(unregister_fib_notifier); - -int call_fib_notifiers(struct net *net, enum fib_event_type event_type, - struct fib_notifier_info *info) -{ - net->ipv4.fib_seq++; - info->net = net; - return atomic_notifier_call_chain(&fib_chain, event_type, info); -} - static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_info *fi, @@ -1995,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb) } static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb, - enum fib_event_type event_type) + struct fib_table *tb, struct notifier_block *nb) { struct fib_alias *fa; @@ -2012,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, event_type, l->key, + call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, KEYLENGTH - fa->fa_slen, fi, fa->fa_tos, fa->fa_type, fa->tb_id); } } static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb, - enum fib_event_type event_type) + struct notifier_block *nb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb, event_type); + fib_leaf_notify(net, l, tb, nb); key = l->key + 1; /* stop in case of wrap around */ @@ -2036,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb, } } -static void fib_notify(struct net *net, struct notifier_block *nb, - enum fib_event_type event_type) +void fib_notify(struct net *net, struct notifier_block *nb) { unsigned int h; @@ -2046,7 +1950,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb, struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb, event_type); + fib_table_notify(net, tb, nb); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index fc310db2708b..43318b5f5647 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -464,22 +464,6 @@ out_bh_enable: local_bh_enable(); } -#ifdef CONFIG_IP_ROUTE_MULTIPATH - -/* Source and destination is swapped. See ip_multipath_icmp_hash */ -static int icmp_multipath_hash_skb(const struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - return fib_multipath_hash(iph->daddr, iph->saddr); -} - -#else - -#define icmp_multipath_hash_skb(skb) (-1) - -#endif - static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -505,8 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, - icmp_multipath_hash_skb(skb_in)); + rt = __ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d6feabb03516..fa2dc8f692c6 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -313,6 +313,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct net_device *dev = skb->dev; + void (*edemux)(struct sk_buff *skb); /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -329,8 +330,8 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) int protocol = iph->protocol; ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && ipprot->early_demux) { - ipprot->early_demux(skb); + if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { + edemux(skb); /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index dfb2ab2dd3c8..c3b12b1c7162 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -57,6 +57,7 @@ #include <linux/export.h> #include <net/net_namespace.h> #include <net/arp.h> +#include <net/dsa.h> #include <net/ip.h> #include <net/ipconfig.h> #include <net/route.h> diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c0317c940bcd..5bca64fc71b7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -631,7 +631,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; - inet_netconf_notify_devconf(dev_net(dev), + inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); @@ -820,8 +820,8 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; - inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex, - &in_dev->cnf); + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, + dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ @@ -1282,7 +1282,8 @@ static void mrtsock_destruct(struct sock *sk) ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); @@ -1344,7 +1345,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; - inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 6241a81fd7f5..f17dab1dee6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -562,8 +562,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } - if (ret != 0) - goto out_free; ret = -EINVAL; if (i != repl->num_entries) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 52f26459efc3..fcbdc0c49b0e 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -22,6 +22,7 @@ #include <linux/icmp.h> #include <linux/if_arp.h> #include <linux/seq_file.h> +#include <linux/refcount.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> @@ -40,8 +41,8 @@ MODULE_DESCRIPTION("Xtables: CLUSTERIP target"); struct clusterip_config { struct list_head list; /* list of all configs */ - atomic_t refcount; /* reference count */ - atomic_t entries; /* number of entries/rules + refcount_t refcount; /* reference count */ + refcount_t entries; /* number of entries/rules * referencing us */ __be32 clusterip; /* the IP address */ @@ -77,7 +78,7 @@ struct clusterip_net { static inline void clusterip_config_get(struct clusterip_config *c) { - atomic_inc(&c->refcount); + refcount_inc(&c->refcount); } @@ -89,7 +90,7 @@ static void clusterip_config_rcu_free(struct rcu_head *head) static inline void clusterip_config_put(struct clusterip_config *c) { - if (atomic_dec_and_test(&c->refcount)) + if (refcount_dec_and_test(&c->refcount)) call_rcu_bh(&c->rcu, clusterip_config_rcu_free); } @@ -103,7 +104,7 @@ clusterip_config_entry_put(struct clusterip_config *c) struct clusterip_net *cn = net_generic(net, clusterip_net_id); local_bh_disable(); - if (atomic_dec_and_lock(&c->entries, &cn->lock)) { + if (refcount_dec_and_lock(&c->entries, &cn->lock)) { list_del_rcu(&c->list); spin_unlock(&cn->lock); local_bh_enable(); @@ -149,10 +150,10 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) c = NULL; else #endif - if (unlikely(!atomic_inc_not_zero(&c->refcount))) + if (unlikely(!refcount_inc_not_zero(&c->refcount))) c = NULL; else if (entry) - atomic_inc(&c->entries); + refcount_inc(&c->entries); } rcu_read_unlock_bh(); @@ -188,8 +189,8 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, clusterip_config_init_nodelist(c, i); c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; - atomic_set(&c->refcount, 1); - atomic_set(&c->entries, 1); + refcount_set(&c->refcount, 1); + refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 53e49f5011d3..da04b9c33ef3 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -998,18 +998,6 @@ err_id_free: * *****************************************************************************/ -static void hex_dump(const unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; i++) { - if (i && !(i % 16)) - printk("\n"); - printk("%02x ", *(buf + i)); - } - printk("\n"); -} - /* * Parse and mangle SNMP message according to mapping. * (And this is the fucking 'basic' method). @@ -1026,7 +1014,8 @@ static int snmp_parse_mangle(unsigned char *msg, struct snmp_object *obj; if (debug > 1) - hex_dump(msg, len); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 1, + msg, len, 0); asn1_open(&ctx, msg, len); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 146d86105183..7cd8d0d918f8 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -104,7 +104,6 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; - const struct iphdr *oiph; struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _oth; @@ -116,8 +115,6 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; - oiph = ip_hdr(oldskb); - nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 2981291910dd..f4e4462cb5bb 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -90,7 +90,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, nft_in(pkt)->ifindex); return; } @@ -99,7 +99,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (ipv4_is_zeronet(iph->saddr)) { if (ipv4_is_lbcast(iph->daddr) || ipv4_is_local_multicast(iph->daddr)) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, get_ifindex(pkt->skb->dev)); return; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 69cf49e8356d..4ccbf464d1ac 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED), SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED), SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), - SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 4b7c0ec65251..32a691b7ce2c 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -28,7 +28,7 @@ #include <linux/spinlock.h> #include <net/protocol.h> -const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; +struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; EXPORT_SYMBOL(inet_offloads); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8471dd116771..5dda1ef81c7e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1734,45 +1734,97 @@ out: } #ifdef CONFIG_IP_ROUTE_MULTIPATH - /* To make ICMP packets follow the right flow, the multipath hash is - * calculated from the inner IP addresses in reverse order. + * calculated from the inner IP addresses. */ -static int ip_multipath_icmp_hash(struct sk_buff *skb) +static void ip_multipath_l3_keys(const struct sk_buff *skb, + struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); - struct icmphdr _icmph; + const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; - const struct iphdr *inner_iph; + struct icmphdr _icmph; + + hash_keys->addrs.v4addrs.src = outer_iph->saddr; + hash_keys->addrs.v4addrs.dst = outer_iph->daddr; + if (likely(outer_iph->protocol != IPPROTO_ICMP)) + return; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) - goto standard_hash; + return; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) - goto standard_hash; + return; if (icmph->type != ICMP_DEST_UNREACH && icmph->type != ICMP_REDIRECT && icmph->type != ICMP_TIME_EXCEEDED && - icmph->type != ICMP_PARAMETERPROB) { - goto standard_hash; - } + icmph->type != ICMP_PARAMETERPROB) + return; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) - goto standard_hash; + return; + hash_keys->addrs.v4addrs.src = inner_iph->saddr; + hash_keys->addrs.v4addrs.dst = inner_iph->daddr; +} - return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr); +/* if skb is set it will be used and fl4 can be NULL */ +int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, + const struct sk_buff *skb) +{ + struct net *net = fi->fib_net; + struct flow_keys hash_keys; + u32 mhash; -standard_hash: - return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr); -} + switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + case 0: + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (skb) { + ip_multipath_l3_keys(skb, &hash_keys); + } else { + hash_keys.addrs.v4addrs.src = fl4->saddr; + hash_keys.addrs.v4addrs.dst = fl4->daddr; + } + break; + case 1: + /* skb is currently provided only when forwarding */ + if (skb) { + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + struct flow_keys keys; + + /* short-circuit if we already have L4 hash present */ + if (skb->l4_hash) + return skb_get_hash_raw(skb) >> 1; + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, flag); + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + hash_keys.ports.src = keys.ports.src; + hash_keys.ports.dst = keys.ports.dst; + hash_keys.basic.ip_proto = keys.basic.ip_proto; + } else { + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + hash_keys.addrs.v4addrs.src = fl4->saddr; + hash_keys.addrs.v4addrs.dst = fl4->daddr; + hash_keys.ports.src = fl4->fl4_sport; + hash_keys.ports.dst = fl4->fl4_dport; + hash_keys.basic.ip_proto = fl4->flowi4_proto; + } + break; + } + mhash = flow_hash_from_keys(&hash_keys); + return mhash >> 1; +} +EXPORT_SYMBOL_GPL(fib_multipath_hash); #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, @@ -1782,12 +1834,8 @@ static int ip_mkroute_input(struct sk_buff *skb, { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) { - int h; + int h = fib_multipath_hash(res->fi, NULL, skb); - if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP)) - h = ip_multipath_icmp_hash(skb); - else - h = fib_multipath_hash(saddr, daddr); fib_select_multipath(res, h); } #endif @@ -2203,7 +2251,7 @@ add: */ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - int mp_hash) + const struct sk_buff *skb) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); @@ -2365,7 +2413,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, goto make_route; } - fib_select_path(net, &res, fl4, mp_hash); + fib_select_path(net, &res, fl4, skb); dev_out = FIB_RES_DEV(res); fl4->flowi4_oif = dev_out->ifindex; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d6880a6149ee..6fb25693c00b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -24,6 +24,7 @@ #include <net/cipso_ipv4.h> #include <net/inet_frag.h> #include <net/ping.h> +#include <net/protocol.h> static int zero; static int one = 1; @@ -294,6 +295,58 @@ bad_key: return ret; } +static void proc_configure_early_demux(int enabled, int protocol) +{ + struct net_protocol *ipprot; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_protocol *ip6prot; +#endif + + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot) + ipprot->early_demux = enabled ? ipprot->early_demux_handler : + NULL; + +#if IS_ENABLED(CONFIG_IPV6) + ip6prot = rcu_dereference(inet6_protos[protocol]); + if (ip6prot) + ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : + NULL; +#endif +} + +static int proc_tcp_early_demux(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = 0; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (write && !ret) { + int enabled = init_net.ipv4.sysctl_tcp_early_demux; + + proc_configure_early_demux(enabled, IPPROTO_TCP); + } + + return ret; +} + +static int proc_udp_early_demux(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = 0; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (write && !ret) { + int enabled = init_net.ipv4.sysctl_udp_early_demux; + + proc_configure_early_demux(enabled, IPPROTO_UDP); + } + + return ret; +} + static struct ctl_table ipv4_table[] = { { .procname = "tcp_timestamps", @@ -750,6 +803,20 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { + .procname = "udp_early_demux", + .data = &init_net.ipv4.sysctl_udp_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_udp_early_demux + }, + { + .procname = "tcp_early_demux", + .data = &init_net.ipv4.sysctl_tcp_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_tcp_early_demux + }, + { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, .maxlen = sizeof(int), @@ -981,13 +1048,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_tw_recycle", - .data = &init_net.ipv4.tcp_death_row.sysctl_tw_recycle, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), @@ -1004,6 +1064,15 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "fib_multipath_hash_policy", + .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, #endif { .procname = "ip_unprivileged_port_start", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1e319a525d51..94f0b5b50e0d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2393,7 +2393,7 @@ static int tcp_repair_options_est(struct tcp_sock *tp, u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; - if (snd_wscale > 14 || rcv_wscale > 14) + if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; @@ -2470,7 +2470,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { + if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2c1f59386a7b..31f2765ef851 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3764,11 +3764,12 @@ void tcp_parse_options(const struct sk_buff *skb, !estab && sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; - if (snd_wscale > 14) { - net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n", + if (snd_wscale > TCP_MAX_WSCALE) { + net_info_ratelimited("%s: Illegal window scaling value %d > %u received\n", __func__, - snd_wscale); - snd_wscale = 14; + snd_wscale, + TCP_MAX_WSCALE); + snd_wscale = TCP_MAX_WSCALE; } opt_rx->snd_wscale = snd_wscale; } @@ -6329,36 +6330,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (isn && tmp_opt.tstamp_ok) - af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); if (!want_cookie && !isn) { - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (net->ipv4.tcp_death_row.sysctl_tw_recycle) { - bool strict; - - dst = af_ops->route_req(sk, &fl, req, &strict); - - if (dst && strict && - !tcp_peer_is_proven(req, dst, true, - tmp_opt.saw_tstamp)) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } /* Kill the following clause, if you dislike this way. */ - else if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false, - tmp_opt.saw_tstamp)) { + if (!net->ipv4.sysctl_tcp_syncookies && + (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (net->ipv4.sysctl_max_syn_backlog >> 2)) && + !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. @@ -6371,10 +6350,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off); + isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off); } if (!dst) { - dst = af_ops->route_req(sk, &fl, req, NULL); + dst = af_ops->route_req(sk, &fl, req); if (!dst) goto drop_and_free; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 575e19dcc017..20cbd2f07f28 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcp_sequence_number(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->write_seq = 0; } - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) - tcp_fetch_timewait_stamp(sk, &rt->dst); - inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); @@ -236,11 +232,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; if (likely(!tp->repair)) { - seq = secure_tcp_sequence_number(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port, - &tp->tsoffset); + seq = secure_tcp_seq_and_tsoff(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -1217,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req, static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req); - - if (strict) { - if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr) - *strict = true; - else - *strict = false; - } - - return dst; + return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { @@ -1253,7 +1239,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_sequence, + .init_seq_tsoff = tcp_v4_init_seq_and_tsoff, .send_synack = tcp_v4_send_synack, }; @@ -1423,8 +1409,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) if (!nsk) goto discard; if (nsk != sk) { - sock_rps_save_rxhash(nsk, skb); - sk_mark_napi_id(nsk, skb); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; @@ -2466,7 +2450,6 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 0; cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_tw_recycle = 0; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0f46e5fe31ad..9d0d4f39e42b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -45,8 +45,6 @@ struct tcp_metrics_block { struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; - u32 tcpm_ts; - u32 tcpm_ts_stamp; u32 tcpm_lock; u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; @@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); - tm->tcpm_ts = 0; - tm->tcpm_ts_stamp = 0; if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; @@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, return tm; } -static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - struct inetpeer_addr saddr, daddr; - unsigned int hash; - struct net *net; - - if (tw->tw_family == AF_INET) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } -#if IS_ENABLED(CONFIG_IPV6) - else if (tw->tw_family == AF_INET6) { - if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { - inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); - inetpeer_set_addr_v4(&daddr, tw->tw_daddr); - hash = ipv4_addr_hash(tw->tw_daddr); - } else { - inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr); - inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr); - hash = ipv6_addr_hash(&tw->tw_v6_daddr); - } - } -#endif - else - return NULL; - - net = twsk_net(tw); - hash ^= net_hash_mix(net); - hash = hash_32(hash, tcp_metrics_hash_log); - - for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; - tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_saddr, &saddr) && - addr_same(&tm->tcpm_daddr, &daddr) && - net_eq(tm_net(tm), net)) - break; - } - return tm; -} - static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct dst_entry *dst, bool create) @@ -573,8 +527,7 @@ reset: tp->snd_cwnd_stamp = tcp_time_stamp; } -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, - bool paws_check, bool timestamps) +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) { struct tcp_metrics_block *tm; bool ret; @@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, rcu_read_lock(); tm = __tcp_get_metrics_req(req, dst); - if (paws_check) { - if (tm && - (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL && - ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW || - !timestamps)) - ret = false; - else - ret = true; - } else { - if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp) - ret = true; - else - ret = false; - } - rcu_read_unlock(); - - return ret; -} - -void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst) -{ - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) { - tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp; - tp->rx_opt.ts_recent = tm->tcpm_ts; - } - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp); - -/* VJ's idea. Save last timestamp seen from this destination and hold - * it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter - * synchronized state. - */ -bool tcp_remember_stamp(struct sock *sk) -{ - struct dst_entry *dst = __sk_dst_get(sk); - bool ret = false; - - if (dst) { - struct tcp_metrics_block *tm; - - rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); - if (tm) { - struct tcp_sock *tp = tcp_sk(sk); - - if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; - tm->tcpm_ts = tp->rx_opt.ts_recent; - } - ret = true; - } - rcu_read_unlock(); - } - return ret; -} - -bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) -{ - struct tcp_metrics_block *tm; - bool ret = false; - - rcu_read_lock(); - tm = __tcp_get_metrics_tw(tw); - if (tm) { - const struct tcp_timewait_sock *tcptw; - struct sock *sk = (struct sock *) tw; - - tcptw = tcp_twsk(sk); - if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL && - tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - tm->tcpm_ts = tcptw->tw_ts_recent; - } + if (tm && tcp_metric_get(tm, TCP_METRIC_RTT)) ret = true; - } + else + ret = false; rcu_read_unlock(); return ret; @@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, jiffies - tm->tcpm_stamp, TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; - if (tm->tcpm_ts_stamp) { - if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP, - (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0) - goto nla_put_failure; - if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL, - tm->tcpm_ts) < 0) - goto nla_put_failure; - } { int n = 0; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 65c0f3d13eca..8f6373b0cd77 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -26,6 +26,7 @@ #include <net/tcp.h> #include <net/inet_common.h> #include <net/xfrm.h> +#include <net/busy_poll.h> int sysctl_tcp_abort_on_overflow __read_mostly; @@ -94,7 +95,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); bool paws_reject = false; - struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row; tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { @@ -149,12 +149,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } - if (tcp_death_row->sysctl_tw_recycle && - tcptw->tw_ts_recent_stamp && - tcp_tw_remember_stamp(tw)) - inet_twsk_reschedule(tw, tw->tw_timeout); - else - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -259,12 +254,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct inet_timewait_sock *tw; - bool recycle_ok = false; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; - if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) - recycle_ok = tcp_remember_stamp(sk); - tw = inet_twsk_alloc(sk, tcp_death_row, state); if (tw) { @@ -317,13 +308,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (timeo < rto) timeo = rto; - if (recycle_ok) { - tw->tw_timeout = rto; - } else { - tw->tw_timeout = TCP_TIMEWAIT_LEN; - if (state == TCP_TIME_WAIT) - timeo = TCP_TIMEWAIT_LEN; - } + tw->tw_timeout = TCP_TIMEWAIT_LEN; + if (state == TCP_TIME_WAIT) + timeo = TCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); /* Linkage updates. */ @@ -813,6 +800,9 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + /* record NAPI ID of child */ + sk_mark_napi_id(child, skb); + tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 22548b5f05cb..0e807a83c1bc 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -212,12 +212,12 @@ void tcp_select_initial_window(int __space, __u32 mss, /* If no clamp set the clamp to the max possible scaled window */ if (*window_clamp == 0) - (*window_clamp) = (65535 << 14); + (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); space = min(*window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) - space = (space / mss) * mss; + space = rounddown(space, mss); /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us @@ -234,13 +234,11 @@ void tcp_select_initial_window(int __space, __u32 mss, (*rcv_wscale) = 0; if (wscale_ok) { - /* Set window scaling on max possible window - * See RFC1323 for an explanation of the limit to 14 - */ + /* Set window scaling on max possible window */ space = max_t(u32, space, sysctl_tcp_rmem[2]); space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); - while (space > 65535 && (*rcv_wscale) < 14) { + while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) { space >>= 1; (*rcv_wscale)++; } @@ -253,7 +251,7 @@ void tcp_select_initial_window(int __space, __u32 mss, } /* Set the clamp no higher than max representable value */ - (*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp); + (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); } EXPORT_SYMBOL(tcp_select_initial_window); @@ -2561,7 +2559,6 @@ u32 __tcp_select_window(struct sock *sk) /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ - window = tp->rcv_wnd; if (tp->rx_opt.rcv_wscale) { window = free_space; @@ -2569,10 +2566,9 @@ u32 __tcp_select_window(struct sock *sk) * Import case: prevent zero window announcement if * 1<<rcv_wscale > mss. */ - if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window) - window = (((window >> tp->rx_opt.rcv_wscale) + 1) - << tp->rx_opt.rcv_wscale); + window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale)); } else { + window = tp->rcv_wnd; /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the @@ -2582,7 +2578,7 @@ u32 __tcp_select_window(struct sock *sk) * is too small. */ if (window <= free_space - mss || window > free_space) - window = (free_space / mss) * mss; + window = rounddown(free_space, mss); else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index fed66dc0e0f5..9775453b8d17 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = 0; - info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt), - info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), + info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt); + info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min); *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index e2afe677a9d9..48c452959d2c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -307,6 +307,7 @@ config IPV6_SEG6_LWTUNNEL bool "IPv6: Segment Routing Header encapsulation support" depends on IPV6 select LWTUNNEL + select DST_CACHE ---help--- Support for encapsulation of packets within an outer IPv6 header and a Segment Routing Header using the lightweight diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 363172527e43..67ec87ea5fb6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -224,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif @@ -245,6 +246,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -276,6 +278,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif @@ -297,6 +300,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, + .disable_policy = 0, }; /* Check if a valid qdisc is available */ @@ -545,6 +549,9 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; + if (!devconf) + goto out; + if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) goto nla_put_failure; @@ -563,6 +570,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, devconf->ignore_routes_with_linkdown) < 0) goto nla_put_failure; +out: nlmsg_end(skb, nlh); return 0; @@ -571,8 +579,8 @@ nla_put_failure: return -EMSGSIZE; } -void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, - struct ipv6_devconf *devconf) +void inet6_netconf_notify_devconf(struct net *net, int event, int type, + int ifindex, struct ipv6_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; @@ -582,7 +590,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, - RTM_NEWNETCONF, 0, type); + event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); @@ -765,7 +773,8 @@ static void dev_forward_change(struct inet6_dev *idev) else addrconf_leave_anycast(ifa); } - inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING, + inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, + NETCONFA_FORWARDING, dev->ifindex, &idev->cnf); } @@ -800,7 +809,8 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_dflt->forwarding) { if ((!newf) ^ (!old)) - inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); rtnl_unlock(); @@ -812,13 +822,15 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) net->ipv6.devconf_dflt->forwarding = newf; if ((!newf) ^ (!old_dflt)) - inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); addrconf_forward_change(net, newf); if ((!newf) ^ (!old)) - inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) @@ -843,6 +855,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) idev->cnf.ignore_routes_with_linkdown = newf; if (changed) inet6_netconf_notify_devconf(dev_net(dev), + RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, dev->ifindex, &idev->cnf); @@ -865,6 +878,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, + RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); @@ -877,6 +891,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) addrconf_linkdown_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, + RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); @@ -944,6 +959,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { + struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; unsigned int hash; @@ -990,6 +1006,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } + if (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy) + rt->dst.flags |= DST_NOPOLICY; + neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *addr; @@ -4972,6 +4992,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_RTR_PROBE_INTERVAL] = jiffies_to_msecs(cnf->rtr_probe_interval); #ifdef CONFIG_IPV6_ROUTE_INFO + array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen; array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; #endif #endif @@ -5003,6 +5024,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; + array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; } static inline size_t inet6_ifla6_size(void) @@ -5664,17 +5686,20 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return restart_syscall(); if (valp == &net->ipv6.devconf_dflt->proxy_ndp) - inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); else if (valp == &net->ipv6.devconf_all->proxy_ndp) - inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); else { struct inet6_dev *idev = ctl->extra1; - inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_PROXY_NEIGH, idev->dev->ifindex, &idev->cnf); } @@ -5827,6 +5852,105 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, return ret; } +static +void addrconf_set_nopolicy(struct rt6_info *rt, int action) +{ + if (rt) { + if (action) + rt->dst.flags |= DST_NOPOLICY; + else + rt->dst.flags &= ~DST_NOPOLICY; + } +} + +static +void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) +{ + struct inet6_ifaddr *ifa; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + spin_lock(&ifa->lock); + if (ifa->rt) { + struct rt6_info *rt = ifa->rt; + struct fib6_table *table = rt->rt6i_table; + int cpu; + + read_lock(&table->tb6_lock); + addrconf_set_nopolicy(ifa->rt, val); + if (rt->rt6i_pcpu) { + for_each_possible_cpu(cpu) { + struct rt6_info **rtp; + + rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu); + addrconf_set_nopolicy(*rtp, val); + } + } + read_unlock(&table->tb6_lock); + } + spin_unlock(&ifa->lock); + } + read_unlock_bh(&idev->lock); +} + +static +int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) +{ + struct inet6_dev *idev; + struct net *net; + + if (!rtnl_trylock()) + return restart_syscall(); + + *valp = val; + + net = (struct net *)ctl->extra2; + if (valp == &net->ipv6.devconf_dflt->disable_policy) { + rtnl_unlock(); + return 0; + } + + if (valp == &net->ipv6.devconf_all->disable_policy) { + struct net_device *dev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get(dev); + if (idev) + addrconf_disable_policy_idev(idev, val); + } + } else { + idev = (struct inet6_dev *)ctl->extra1; + addrconf_disable_policy_idev(idev, val); + } + + rtnl_unlock(); + return 0; +} + +static +int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + lctl = *ctl; + lctl.data = &val; + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write && (*valp != val)) + ret = addrconf_disable_policy(ctl, valp, val); + + if (ret) + *ppos = pos; + + return ret; +} + static int minus_one = -1; static const int one = 1; static const int two_five_five = 255; @@ -6015,6 +6139,13 @@ static const struct ctl_table addrconf_sysctl[] = { }, #ifdef CONFIG_IPV6_ROUTE_INFO { + .procname = "accept_ra_rt_info_min_plen", + .data = &ipv6_devconf.accept_ra_rt_info_min_plen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), @@ -6185,6 +6316,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = addrconf_sysctl_addr_gen_mode, }, { + .procname = "disable_policy", + .data = &ipv6_devconf.disable_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_disable_policy, + }, + { /* sentinel */ } }; @@ -6224,7 +6362,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, ifindex = NETCONFA_IFINDEX_DEFAULT; else ifindex = idev->dev->ifindex; - inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, + ifindex, p); return 0; free: @@ -6233,7 +6372,8 @@ out: return -ENOBUFS; } -static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) +static void __addrconf_sysctl_unregister(struct net *net, + struct ipv6_devconf *p, int ifindex) { struct ctl_table *table; @@ -6244,6 +6384,8 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) unregister_net_sysctl_table(p->sysctl_header); p->sysctl_header = NULL; kfree(table); + + inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int addrconf_sysctl_register(struct inet6_dev *idev) @@ -6267,7 +6409,8 @@ static int addrconf_sysctl_register(struct inet6_dev *idev) static void addrconf_sysctl_unregister(struct inet6_dev *idev) { - __addrconf_sysctl_unregister(&idev->cnf); + __addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf, + idev->dev->ifindex); neigh_sysctl_unregister(idev->nd_parms); } @@ -6310,7 +6453,7 @@ static int __net_init addrconf_init_net(struct net *net) #ifdef CONFIG_SYSCTL err_reg_dflt: - __addrconf_sysctl_unregister(all); + __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); #endif @@ -6323,8 +6466,10 @@ err_alloc_all: static void __net_exit addrconf_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL - __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); - __addrconf_sysctl_unregister(net->ipv6.devconf_all); + __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt, + NETCONFA_IFINDEX_DEFAULT); + __addrconf_sysctl_unregister(net, net->ipv6.devconf_all, + NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); kfree(net->ipv6.devconf_all); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a9a9553ee63d..1635d218735e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1005,6 +1005,10 @@ static int __init inet6_init(void) if (err) goto seg6_fail; + err = igmp6_late_init(); + if (err) + goto igmp6_late_err; + #ifdef CONFIG_SYSCTL err = ipv6_sysctl_register(); if (err) @@ -1015,8 +1019,10 @@ out: #ifdef CONFIG_SYSCTL sysctl_fail: - seg6_exit(); + igmp6_late_cleanup(); #endif +igmp6_late_err: + seg6_exit(); seg6_fail: calipso_exit(); calipso_fail: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index aacfb4bce153..b04539dd4629 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -49,6 +49,8 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + void (*edemux)(struct sk_buff *skb); + /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ @@ -60,8 +62,8 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct inet6_protocol *ipprot; ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && ipprot->early_demux) - ipprot->early_demux(skb); + if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) + edemux(skb); } if (!skb_valid_dst(skb)) ip6_route_input(skb); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 6ba6c900ebcf..fb4546e80c82 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -815,7 +815,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) in6_dev = __in6_dev_get(dev); if (in6_dev) { in6_dev->cnf.mc_forwarding--; - inet6_netconf_notify_devconf(dev_net(dev), + inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } @@ -974,7 +974,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, in6_dev = __in6_dev_get(dev); if (in6_dev) { in6_dev->cnf.mc_forwarding++; - inet6_netconf_notify_devconf(dev_net(dev), + inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } @@ -1599,7 +1599,8 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) write_unlock_bh(&mrt_lock); if (!err) - inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); rtnl_unlock(); @@ -1620,7 +1621,7 @@ int ip6mr_sk_done(struct sock *sk) mrt->mroute6_sk = NULL; net->ipv6.devconf_all->mc_forwarding--; write_unlock_bh(&mrt_lock); - inet6_netconf_notify_devconf(net, + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 1bdc703cb966..07403fa164e1 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2463,7 +2463,6 @@ static void mld_ifc_event(struct inet6_dev *idev) mld_ifc_start_timer(idev, 1); } - static void igmp6_timer_handler(unsigned long data) { struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data; @@ -2599,6 +2598,44 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) write_unlock_bh(&idev->lock); } +static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) +{ + struct ifmcaddr6 *pmc; + + ASSERT_RTNL(); + + if (mld_in_v1_mode(idev)) { + read_lock_bh(&idev->lock); + for (pmc = idev->mc_list; pmc; pmc = pmc->next) + igmp6_join_group(pmc); + read_unlock_bh(&idev->lock); + } else + mld_send_report(idev, NULL); +} + +static int ipv6_mc_netdev_event(struct notifier_block *this, + unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct inet6_dev *idev = __in6_dev_get(dev); + + switch (event) { + case NETDEV_RESEND_IGMP: + if (idev) + ipv6_mc_rejoin_groups(idev); + break; + default: + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block igmp6_netdev_notifier = { + .notifier_call = ipv6_mc_netdev_event, +}; + #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; @@ -2970,7 +3007,17 @@ int __init igmp6_init(void) return register_pernet_subsys(&igmp6_net_ops); } +int __init igmp6_late_init(void) +{ + return register_netdevice_notifier(&igmp6_netdev_notifier); +} + void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); } + +void igmp6_late_cleanup(void) +{ + unregister_netdevice_notifier(&igmp6_netdev_notifier); +} diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7ebac630d3c6..b5812b3f7539 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -732,7 +732,7 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { - neigh_update(neigh, lladdr, new, flags); + neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } @@ -1418,6 +1418,8 @@ skip_linkparms: if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; + if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) + continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 765facf03d45..e8d88d82636b 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -159,7 +159,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv->result, pkt, + nft_fib_store_result(dest, priv, pkt, nft_in(pkt)->ifindex); return; } diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index e3770abe688a..b5d54d4f995c 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -26,7 +26,7 @@ #include <net/protocol.h> #if IS_ENABLED(CONFIG_IPV6) -const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; +struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; EXPORT_SYMBOL(inet6_protos); int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 85582257d3af..a644aaecdfd3 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -26,17 +26,13 @@ #include <linux/seg6_iptunnel.h> #include <net/addrconf.h> #include <net/ip6_route.h> -#ifdef CONFIG_DST_CACHE #include <net/dst_cache.h> -#endif #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif struct seg6_lwt { -#ifdef CONFIG_DST_CACHE struct dst_cache cache; -#endif struct seg6_iptunnel_encap tuninfo[0]; }; @@ -105,7 +101,7 @@ static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); - err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC); + err = skb_cow_head(skb, tot_len); if (unlikely(err)) return err; @@ -156,7 +152,7 @@ static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) hdrlen = (osrh->hdrlen + 1) << 3; - err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC); + err = skb_cow_head(skb, hdrlen); if (unlikely(err)) return err; @@ -237,6 +233,9 @@ static int seg6_do_srh(struct sk_buff *skb) static int seg6_input(struct sk_buff *skb) { + struct dst_entry *orig_dst = skb_dst(skb); + struct dst_entry *dst = NULL; + struct seg6_lwt *slwt; int err; err = seg6_do_srh(skb); @@ -245,8 +244,26 @@ static int seg6_input(struct sk_buff *skb) return err; } + slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + + preempt_disable(); + dst = dst_cache_get(&slwt->cache); + preempt_enable(); + skb_dst_drop(skb); - ip6_route_input(skb); + + if (!dst) { + ip6_route_input(skb); + dst = skb_dst(skb); + if (!dst->error) { + preempt_disable(); + dst_cache_set_ip6(&slwt->cache, dst, + &ipv6_hdr(skb)->saddr); + preempt_enable(); + } + } else { + skb_dst_set(skb, dst); + } return dst_input(skb); } @@ -264,11 +281,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); -#ifdef CONFIG_DST_CACHE preempt_disable(); dst = dst_cache_get(&slwt->cache); preempt_enable(); -#endif if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -287,11 +302,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } -#ifdef CONFIG_DST_CACHE preempt_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); preempt_enable(); -#endif } skb_dst_drop(skb); @@ -355,13 +368,11 @@ static int seg6_build_state(struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); -#ifdef CONFIG_DST_CACHE err = dst_cache_init(&slwt->cache, GFP_KERNEL); if (err) { kfree(newts); return err; } -#endif memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); @@ -375,12 +386,10 @@ static int seg6_build_state(struct nlattr *nla, return 0; } -#ifdef CONFIG_DST_CACHE static void seg6_destroy_state(struct lwtunnel_state *lwt) { dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache); } -#endif static int seg6_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) @@ -414,9 +423,7 @@ static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) static const struct lwtunnel_encap_ops seg6_iptun_ops = { .build_state = seg6_build_state, -#ifdef CONFIG_DST_CACHE .destroy_state = seg6_destroy_state, -#endif .output = seg6_output, .input = seg6_input, .fill_encap = seg6_fill_encap_info, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 49fa2e8c3fa9..8e42e8f54b70 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff) +static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff) { - return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source, tsoff); + return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source, tsoff); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, @@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); - if (tcp_death_row->sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr)) - tcp_fetch_timewait_stamp(sk, dst); - icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + @@ -287,11 +282,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { - seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport, - &tp->tsoffset); + seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport, + &tp->tsoffset); if (!tp->write_seq) tp->write_seq = seq; } @@ -727,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req, static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct flowi *fl, - const struct request_sock *req, - bool *strict) + const struct request_sock *req) { - if (strict) - *strict = true; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } @@ -757,7 +749,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_sequence, + .init_seq_tsoff = tcp_v6_init_seq_and_tsoff, .send_synack = tcp_v6_send_synack, }; @@ -1301,8 +1293,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { - sock_rps_save_rxhash(nsk, skb); - sk_mark_napi_id(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) @@ -1933,8 +1923,9 @@ struct proto tcpv6_prot = { .diag_destroy = tcp_abort, }; -static const struct inet6_protocol tcpv6_protocol = { +static struct inet6_protocol tcpv6_protocol = { .early_demux = tcp_v6_early_demux, + .early_demux_handler = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e28082f0a307..fd4b1c98a472 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -864,6 +864,64 @@ discard: return 0; } +static struct sock *__udp6_lib_demux_lookup(struct net *net, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif) +{ + struct sock *sk; + + rcu_read_lock(); + sk = __udp6_lib_lookup(net, rmt_addr, rmt_port, loc_addr, loc_port, + dif, &udp_table, NULL); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + rcu_read_unlock(); + + return sk; +} + +static void udp_v6_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct udphdr *uh; + struct sock *sk; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + + sizeof(struct udphdr))) + return; + + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_HOST) + sk = __udp6_lib_demux_lookup(net, uh->dest, + &ipv6_hdr(skb)->daddr, + uh->source, &ipv6_hdr(skb)->saddr, + dif); + else + return; + + if (!sk) + return; + + skb->sk = sk; + skb->destructor = sock_efree; + dst = READ_ONCE(sk->sk_rx_dst); + + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst) { + if (dst->flags & DST_NOCACHE) { + if (likely(atomic_inc_not_zero(&dst->__refcnt))) + skb_dst_set(skb, dst); + } else { + skb_dst_set_noref(skb, dst); + } + } +} + static __inline__ int udpv6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); @@ -1378,7 +1436,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -static const struct inet6_protocol udpv6_protocol = { +static struct inet6_protocol udpv6_protocol = { + .early_demux = udp_v6_early_demux, + .early_demux_handler = udp_v6_early_demux, .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 56ccffa3f2bf..62141dcec2d6 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -19,6 +19,7 @@ #ifndef __IEEE802154_I_H #define __IEEE802154_I_H +#include <linux/interrupt.h> #include <linux/mutex.h> #include <linux/hrtimer.h> #include <net/cfg802154.h> diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 6414079aa729..5928d22ba9c8 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -24,6 +24,9 @@ #include <net/nexthop.h> #include "internal.h" +/* max memory we will use for mpls_route */ +#define MAX_MPLS_ROUTE_MEM 4096 + /* Maximum number of labels to look ahead at when selecting a path of * a multipath route */ @@ -32,7 +35,9 @@ #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int zero = 0; +static int one = 1; static int label_limit = (1 << 20) - 1; +static int ttl_max = 255; static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, @@ -58,10 +63,7 @@ EXPORT_SYMBOL_GPL(mpls_output_possible); static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh) { - u8 *nh0_via = PTR_ALIGN((u8 *)&rt->rt_nh[rt->rt_nhn], VIA_ALEN_ALIGN); - int nh_index = nh - rt->rt_nh; - - return nh0_via + rt->rt_max_alen * nh_index; + return (u8 *)nh + rt->rt_via_offset; } static const u8 *mpls_nh_via(const struct mpls_route *rt, @@ -187,21 +189,32 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) return hash; } +static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index) +{ + return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size); +} + +/* number of alive nexthops (rt->rt_nhn_alive) and the flags for + * a next hop (nh->nh_flags) are modified by netdev event handlers. + * Since those fields can change at any moment, use READ_ONCE to + * access both. + */ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, struct sk_buff *skb) { - int alive = ACCESS_ONCE(rt->rt_nhn_alive); u32 hash = 0; int nh_index = 0; int n = 0; + u8 alive; /* No need to look further into packet if there's only * one path */ if (rt->rt_nhn == 1) - goto out; + return rt->rt_nh; - if (alive <= 0) + alive = READ_ONCE(rt->rt_nhn_alive); + if (alive == 0) return NULL; hash = mpls_multipath_hash(rt, skb); @@ -209,7 +222,9 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, if (alive == rt->rt_nhn) goto out; for_nexthops(rt) { - if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + unsigned int nh_flags = READ_ONCE(nh->nh_flags); + + if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) continue; if (n == nh_index) return nh; @@ -217,11 +232,11 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, } endfor_nexthops(rt); out: - return &rt->rt_nh[nh_index]; + return mpls_get_nexthop(rt, nh_index); } -static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, - struct mpls_entry_decoded dec) +static bool mpls_egress(struct net *net, struct mpls_route *rt, + struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; @@ -246,22 +261,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); + u8 new_ttl; skb->protocol = htons(ETH_P_IP); + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * TTL, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + new_ttl = dec.ttl; + else + new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; + csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), - htons(dec.ttl << 8)); - hdr4->ttl = dec.ttl; + htons(new_ttl << 8)); + hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); - hdr6->hop_limit = dec.ttl; + + /* If propagating TTL, take the decremented TTL from + * the incoming MPLS header, otherwise decrement the + * hop limit, but only if not 0 to avoid underflow. + */ + if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || + (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && + net->mpls.ip_ttl_propagate)) + hdr6->hop_limit = dec.ttl; + else if (hdr6->hop_limit) + hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: + /* Should have decided which protocol it is by now */ break; } @@ -361,7 +400,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ - if (!mpls_egress(rt, skb, dec)) + if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; @@ -412,6 +451,7 @@ static struct packet_type mpls_packet_type __read_mostly = { static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, + [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { @@ -421,6 +461,7 @@ struct mpls_route_config { u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; + u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; @@ -430,20 +471,27 @@ struct mpls_route_config { int rc_mp_len; }; -static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen) +/* all nexthops within a route have the same size based on max + * number of labels and max via length for a hop + */ +static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels) { - u8 max_alen_aligned = ALIGN(max_alen, VIA_ALEN_ALIGN); + u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen); struct mpls_route *rt; + size_t size; - rt = kzalloc(ALIGN(sizeof(*rt) + num_nh * sizeof(*rt->rt_nh), - VIA_ALEN_ALIGN) + - num_nh * max_alen_aligned, - GFP_KERNEL); - if (rt) { - rt->rt_nhn = num_nh; - rt->rt_nhn_alive = num_nh; - rt->rt_max_alen = max_alen_aligned; - } + size = sizeof(*rt) + num_nh * nh_size; + if (size > MAX_MPLS_ROUTE_MEM) + return ERR_PTR(-EINVAL); + + rt = kzalloc(size, GFP_KERNEL); + if (!rt) + return ERR_PTR(-ENOMEM); + + rt->rt_nhn = num_nh; + rt->rt_nhn_alive = num_nh; + rt->rt_nh_size = nh_size; + rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels); return rt; } @@ -648,9 +696,6 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, return -ENOMEM; err = -EINVAL; - /* Ensure only a supported number of labels are present */ - if (cfg->rc_output_labels > MAX_NEW_LABELS) - goto errout; nh->nh_labels = cfg->rc_output_labels; for (i = 0; i < nh->nh_labels; i++) @@ -675,7 +720,7 @@ errout: static int mpls_nh_build(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif, struct nlattr *via, - struct nlattr *newdst) + struct nlattr *newdst, u8 max_labels) { int err = -ENOMEM; @@ -683,7 +728,7 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt, goto errout; if (newdst) { - err = nla_get_labels(newdst, MAX_NEW_LABELS, + err = nla_get_labels(newdst, max_labels, &nh->nh_labels, nh->nh_label); if (err) goto errout; @@ -708,22 +753,20 @@ errout: return err; } -static int mpls_count_nexthops(struct rtnexthop *rtnh, int len, - u8 cfg_via_alen, u8 *max_via_alen) +static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, + u8 cfg_via_alen, u8 *max_via_alen, + u8 *max_labels) { - int nhs = 0; int remaining = len; - - if (!rtnh) { - *max_via_alen = cfg_via_alen; - return 1; - } + u8 nhs = 0; *max_via_alen = 0; + *max_labels = 0; while (rtnh_ok(rtnh, remaining)) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); int attrlen; + u8 n_labels = 0; attrlen = rtnh_attrlen(rtnh); nla = nla_find(attrs, attrlen, RTA_VIA); @@ -737,7 +780,20 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len, via_alen); } + nla = nla_find(attrs, attrlen, RTA_NEWDST); + if (nla && + nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0) + return 0; + + *max_labels = max_t(u8, *max_labels, n_labels); + + /* number of nexthops is tracked by a u8. + * Check for overflow. + */ + if (nhs == 255) + return 0; nhs++; + rtnh = rtnh_next(rtnh, &remaining); } @@ -746,13 +802,13 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len, } static int mpls_nh_build_multi(struct mpls_route_config *cfg, - struct mpls_route *rt) + struct mpls_route *rt, u8 max_labels) { struct rtnexthop *rtnh = cfg->rc_mp; struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; - int nhs = 0; int err = 0; + u8 nhs = 0; change_nexthops(rt) { int attrlen; @@ -779,7 +835,8 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, } err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, - rtnh->rtnh_ifindex, nla_via, nla_newdst); + rtnh->rtnh_ifindex, nla_via, nla_newdst, + max_labels); if (err) goto errout; @@ -806,7 +863,8 @@ static int mpls_route_add(struct mpls_route_config *cfg) int err = -EINVAL; u8 max_via_alen; unsigned index; - int nhs; + u8 max_labels; + u8 nhs; index = cfg->rc_label; @@ -844,21 +902,32 @@ static int mpls_route_add(struct mpls_route_config *cfg) goto errout; err = -EINVAL; - nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len, - cfg->rc_via_alen, &max_via_alen); + if (cfg->rc_mp) { + nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len, + cfg->rc_via_alen, &max_via_alen, + &max_labels); + } else { + max_via_alen = cfg->rc_via_alen; + max_labels = cfg->rc_output_labels; + nhs = 1; + } + if (nhs == 0) goto errout; err = -ENOMEM; - rt = mpls_rt_alloc(nhs, max_via_alen); - if (!rt) + rt = mpls_rt_alloc(nhs, max_via_alen, max_labels); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); goto errout; + } rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; + rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) - err = mpls_nh_build_multi(cfg, rt); + err = mpls_nh_build_multi(cfg, rt, max_labels); else err = mpls_nh_build_from_cfg(cfg, rt); if (err) @@ -1011,8 +1080,8 @@ static int mpls_netconf_msgsize_devconf(int type) return size; } -static void mpls_netconf_notify_devconf(struct net *net, int type, - struct mpls_dev *mdev) +static void mpls_netconf_notify_devconf(struct net *net, int event, + int type, struct mpls_dev *mdev) { struct sk_buff *skb; int err = -ENOBUFS; @@ -1021,8 +1090,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int type, if (!skb) goto errout; - err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, RTM_NEWNETCONF, - 0, type); + err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); @@ -1155,9 +1223,8 @@ static int mpls_conf_proc(struct ctl_table *ctl, int write, if (i == offsetof(struct mpls_dev, input_enabled) && val != oval) { - mpls_netconf_notify_devconf(net, - NETCONFA_INPUT, - mdev); + mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_INPUT, mdev); } } @@ -1198,10 +1265,11 @@ static int mpls_dev_sysctl_register(struct net_device *dev, snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); - mdev->sysctl = register_net_sysctl(dev_net(dev), path, table); + mdev->sysctl = register_net_sysctl(net, path, table); if (!mdev->sysctl) goto free; + mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev); return 0; free: @@ -1210,13 +1278,17 @@ out: return -ENOBUFS; } -static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev) +static void mpls_dev_sysctl_unregister(struct net_device *dev, + struct mpls_dev *mdev) { + struct net *net = dev_net(dev); struct ctl_table *table; table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); + + mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev); } static struct mpls_dev *mpls_add_dev(struct net_device *dev) @@ -1242,11 +1314,12 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) u64_stats_init(&mpls_stats->syncp); } + mdev->dev = dev; + err = mpls_dev_sysctl_register(dev, mdev); if (err) goto free; - mdev->dev = dev; rcu_assign_pointer(dev->mpls_ptr, mdev); return mdev; @@ -1269,8 +1342,7 @@ static void mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - unsigned int nh_flags = RTNH_F_DEAD | RTNH_F_LINKDOWN; - unsigned int alive; + u8 alive, deleted; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); @@ -1281,36 +1353,48 @@ static void mpls_ifdown(struct net_device *dev, int event) continue; alive = 0; + deleted = 0; change_nexthops(rt) { + unsigned int nh_flags = nh->nh_flags; + if (rtnl_dereference(nh->nh_dev) != dev) goto next; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: - nh->nh_flags |= RTNH_F_DEAD; + nh_flags |= RTNH_F_DEAD; /* fall through */ case NETDEV_CHANGE: - nh->nh_flags |= RTNH_F_LINKDOWN; + nh_flags |= RTNH_F_LINKDOWN; break; } if (event == NETDEV_UNREGISTER) RCU_INIT_POINTER(nh->nh_dev, NULL); + + if (nh->nh_flags != nh_flags) + WRITE_ONCE(nh->nh_flags, nh_flags); next: - if (!(nh->nh_flags & nh_flags)) + if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; + if (!rtnl_dereference(nh->nh_dev)) + deleted++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); + + /* if there are no more nexthops, delete the route */ + if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn) + mpls_route_update(net, index, NULL, NULL); } } -static void mpls_ifup(struct net_device *dev, unsigned int nh_flags) +static void mpls_ifup(struct net_device *dev, unsigned int flags) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; - int alive; + u8 alive; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { @@ -1321,20 +1405,22 @@ static void mpls_ifup(struct net_device *dev, unsigned int nh_flags) alive = 0; change_nexthops(rt) { + unsigned int nh_flags = nh->nh_flags; struct net_device *nh_dev = rtnl_dereference(nh->nh_dev); - if (!(nh->nh_flags & nh_flags)) { + if (!(nh_flags & flags)) { alive++; continue; } if (nh_dev != dev) continue; alive++; - nh->nh_flags &= ~nh_flags; + nh_flags &= ~flags; + WRITE_ONCE(nh->nh_flags, flags); } endfor_nexthops(rt); - ACCESS_ONCE(rt->rt_nhn_alive) = alive; + WRITE_ONCE(rt->rt_nhn_alive, alive); } } @@ -1385,7 +1471,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, mpls_ifdown(dev, event); mdev = mpls_dev_get(dev); if (mdev) { - mpls_dev_sysctl_unregister(mdev); + mpls_dev_sysctl_unregister(dev, mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); call_rcu(&mdev->rcu, mpls_dev_destroy_rcu); } @@ -1395,7 +1481,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, if (mdev) { int err; - mpls_dev_sysctl_unregister(mdev); + mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) return notifier_from_errno(err); @@ -1455,16 +1541,18 @@ int nla_put_labels(struct sk_buff *skb, int attrtype, EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, - u32 max_labels, u8 *labels, u32 label[]) + u8 max_labels, u8 *labels, u32 label[]) { unsigned len = nla_len(nla); - unsigned nla_labels; struct mpls_shim_hdr *nla_label; + u8 nla_labels; bool bos; int i; - /* len needs to be an even multiple of 4 (the label size) */ - if (len & 3) + /* len needs to be an even multiple of 4 (the label size). Number + * of labels is a u8 so check for overflow. + */ + if (len & 3 || len / 4 > 255) return -EINVAL; /* Limit the number of new labels allowed */ @@ -1472,6 +1560,10 @@ int nla_get_labels(const struct nlattr *nla, if (nla_labels > max_labels) return -EINVAL; + /* when label == NULL, caller wants number of labels */ + if (!label) + goto out; + nla_label = nla_data(nla); bos = true; for (i = nla_labels - 1; i >= 0; i--, bos = false) { @@ -1495,6 +1587,7 @@ int nla_get_labels(const struct nlattr *nla, label[i] = dec.label; } +out: *labels = nla_labels; return 0; } @@ -1556,7 +1649,6 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, err = -EINVAL; rtm = nlmsg_data(nlh); - memset(cfg, 0, sizeof(*cfg)); if (rtm->rtm_family != AF_MPLS) goto errout; @@ -1584,6 +1676,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; + cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; @@ -1630,6 +1723,17 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->rc_mp_len = nla_len(nla); break; } + case RTA_TTL_PROPAGATE: + { + u8 ttl_propagate = nla_get_u8(nla); + + if (ttl_propagate > 1) + goto errout; + cfg->rc_ttl_propagate = ttl_propagate ? + MPLS_TTL_PROP_ENABLED : + MPLS_TTL_PROP_DISABLED; + break; + } default: /* Unsupported attribute */ goto errout; @@ -1643,27 +1747,43 @@ errout: static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct mpls_route_config cfg; + struct mpls_route_config *cfg; int err; - err = rtm_to_route_config(skb, nlh, &cfg); + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return -ENOMEM; + + err = rtm_to_route_config(skb, nlh, cfg); if (err < 0) - return err; + goto out; + + err = mpls_route_del(cfg); +out: + kfree(cfg); - return mpls_route_del(&cfg); + return err; } static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct mpls_route_config cfg; + struct mpls_route_config *cfg; int err; - err = rtm_to_route_config(skb, nlh, &cfg); + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return -ENOMEM; + + err = rtm_to_route_config(skb, nlh, cfg); if (err < 0) - return err; + goto out; - return mpls_route_add(&cfg); + err = mpls_route_add(cfg); +out: + kfree(cfg); + + return err; } static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, @@ -1690,6 +1810,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; + + if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { + bool ttl_propagate = + rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; + + if (nla_put_u8(skb, RTA_TTL_PROPAGATE, + ttl_propagate)) + goto nla_put_failure; + } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; @@ -1711,21 +1840,23 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, } else { struct rtnexthop *rtnh; struct nlattr *mp; - int dead = 0; - int linkdown = 0; + u8 linkdown = 0; + u8 dead = 0; mp = nla_nest_start(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; for_nexthops(rt) { + dev = rtnl_dereference(nh->nh_dev); + if (!dev) + continue; + rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; - dev = rtnl_dereference(nh->nh_dev); - if (dev) - rtnh->rtnh_ifindex = dev->ifindex; + rtnh->rtnh_ifindex = dev->ifindex; if (nh->nh_flags & RTNH_F_LINKDOWN) { rtnh->rtnh_flags |= RTNH_F_LINKDOWN; linkdown++; @@ -1800,7 +1931,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) - + nla_total_size(4); /* RTA_DST */ + + nla_total_size(4) /* RTA_DST */ + + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; @@ -1816,6 +1948,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) size_t nhsize = 0; for_nexthops(rt) { + if (!rtnl_dereference(nh->nh_dev)) + continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) @@ -1878,12 +2012,13 @@ static int resize_platform_label_table(struct net *net, size_t limit) /* In case the predefined labels need to be populated */ if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; - rt0 = mpls_rt_alloc(1, lo->addr_len); - if (!rt0) + rt0 = mpls_rt_alloc(1, lo->addr_len, 0); + if (IS_ERR(rt0)) goto nort0; RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; + rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, @@ -1891,12 +2026,13 @@ static int resize_platform_label_table(struct net *net, size_t limit) } if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; - rt2 = mpls_rt_alloc(1, lo->addr_len); - if (!rt2) + rt2 = mpls_rt_alloc(1, lo->addr_len, 0); + if (IS_ERR(rt2)) goto nort2; RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; + rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, @@ -1978,6 +2114,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write, return ret; } +#define MPLS_NS_SYSCTL_OFFSET(field) \ + (&((struct net *)0)->field) + static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", @@ -1986,21 +2125,47 @@ static const struct ctl_table mpls_table[] = { .mode = 0644, .proc_handler = mpls_platform_labels, }, + { + .procname = "ip_ttl_propagate", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "default_ttl", + .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &ttl_max, + }, { } }; static int mpls_net_init(struct net *net) { struct ctl_table *table; + int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; + net->mpls.ip_ttl_propagate = 1; + net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; - table[0].data = net; + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++) + table[i].data = (char *)net + (uintptr_t)table[i].data; + net->mpls.ctl = register_net_sysctl(net, "net/mpls", table); if (net->mpls.ctl == NULL) { kfree(table); diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 76360d8b9579..4db6a5971322 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -2,6 +2,11 @@ #define MPLS_INTERNAL_H #include <net/mpls.h> +/* put a reasonable limit on the number of labels + * we will accept from userspace + */ +#define MAX_NEW_LABELS 30 + struct mpls_entry_decoded { u32 label; u8 ttl; @@ -64,7 +69,6 @@ struct mpls_dev { struct sk_buff; #define LABEL_NOT_SPECIFIED (1 << 20) -#define MAX_NEW_LABELS 2 /* This maximum ha length copied from the definition of struct neighbour */ #define VIA_ALEN_ALIGN sizeof(unsigned long) @@ -83,11 +87,35 @@ enum mpls_payload_type { struct mpls_nh { /* next hop label forwarding entry */ struct net_device __rcu *nh_dev; + + /* nh_flags is accessed under RCU in the packet path; it is + * modified handling netdev events with rtnl lock held + */ unsigned int nh_flags; - u32 nh_label[MAX_NEW_LABELS]; u8 nh_labels; u8 nh_via_alen; u8 nh_via_table; + u8 nh_reserved1; + + u32 nh_label[0]; +}; + +/* offset of via from beginning of mpls_nh */ +#define MPLS_NH_VIA_OFF(num_labels) \ + ALIGN(sizeof(struct mpls_nh) + (num_labels) * sizeof(u32), \ + VIA_ALEN_ALIGN) + +/* all nexthops within a route have the same size based on the + * max number of labels and max via length across all nexthops + */ +#define MPLS_NH_SIZE(num_labels, max_via_alen) \ + (MPLS_NH_VIA_OFF((num_labels)) + \ + ALIGN((max_via_alen), VIA_ALEN_ALIGN)) + +enum mpls_ttl_propagation { + MPLS_TTL_PROP_DEFAULT, + MPLS_TTL_PROP_ENABLED, + MPLS_TTL_PROP_DISABLED, }; /* The route, nexthops and vias are stored together in the same memory @@ -98,16 +126,16 @@ struct mpls_nh { /* next hop label forwarding entry */ * +----------------------+ * | mpls_nh 0 | * +----------------------+ - * | ... | - * +----------------------+ - * | mpls_nh n-1 | - * +----------------------+ - * | alignment padding | + * | alignment padding | 4 bytes for odd number of labels * +----------------------+ * | via[rt_max_alen] 0 | * +----------------------+ + * | alignment padding | via's aligned on sizeof(unsigned long) + * +----------------------+ * | ... | * +----------------------+ + * | mpls_nh n-1 | + * +----------------------+ * | via[rt_max_alen] n-1 | * +----------------------+ */ @@ -116,22 +144,30 @@ struct mpls_route { /* next hop label forwarding entry */ u8 rt_protocol; u8 rt_payload_type; u8 rt_max_alen; - unsigned int rt_nhn; - unsigned int rt_nhn_alive; + u8 rt_ttl_propagate; + u8 rt_nhn; + /* rt_nhn_alive is accessed under RCU in the packet path; it + * is modified handling netdev events with rtnl lock held + */ + u8 rt_nhn_alive; + u8 rt_nh_size; + u8 rt_via_offset; + u8 rt_reserved1; struct mpls_nh rt_nh[0]; }; #define for_nexthops(rt) { \ - int nhsel; struct mpls_nh *nh; \ - for (nhsel = 0, nh = (rt)->rt_nh; \ + int nhsel; struct mpls_nh *nh; u8 *__nh; \ + for (nhsel = 0, nh = (rt)->rt_nh, __nh = (u8 *)((rt)->rt_nh); \ nhsel < (rt)->rt_nhn; \ - nh++, nhsel++) + __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++) #define change_nexthops(rt) { \ - int nhsel; struct mpls_nh *nh; \ - for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh); \ + int nhsel; struct mpls_nh *nh; u8 *__nh; \ + for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh), \ + __nh = (u8 *)((rt)->rt_nh); \ nhsel < (rt)->rt_nhn; \ - nh++, nhsel++) + __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++) #define endfor_nexthops(rt) } @@ -166,7 +202,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); -int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels, +int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, u32 label[]); int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, u8 via[]); diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index e4e4424f9eb1..fe00e98667cf 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -29,6 +29,7 @@ static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, + [MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 }, }; static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) @@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb) struct rtable *rt = NULL; struct rt6_info *rt6 = NULL; struct mpls_dev *out_mdev; + struct net *net; int err = 0; bool bos; int i; @@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb) /* Find the output device */ out_dev = dst->dev; - - /* Obtain the ttl */ - if (dst->ops->family == AF_INET) { - ttl = ip_hdr(skb)->ttl; - rt = (struct rtable *)dst; - } else if (dst->ops->family == AF_INET6) { - ttl = ipv6_hdr(skb)->hop_limit; - rt6 = (struct rt6_info *)dst; - } else { - goto drop; - } + net = dev_net(out_dev); skb_orphan(skb); @@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb) tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate); + /* Obtain the ttl using the following set of rules. + * + * LWT ttl propagation setting: + * - disabled => use default TTL value from LWT + * - enabled => use TTL value from IPv4/IPv6 header + * - default => + * Global ttl propagation setting: + * - disabled => use default TTL value from global setting + * - enabled => use TTL value from IPv4/IPv6 header + */ + if (dst->ops->family == AF_INET) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + } else if (dst->ops->family == AF_INET6) { + if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) + ttl = tun_encap_info->default_ttl; + else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT && + !net->mpls.ip_ttl_propagate) + ttl = net->mpls.default_ttl; + else + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + } else { + goto drop; + } + /* Verify the destination can hold the packet */ new_header_size = mpls_encap_size(tun_encap_info); mtu = mpls_dev_mtu(out_dev); @@ -140,6 +164,7 @@ static int mpls_build_state(struct nlattr *nla, struct mpls_iptunnel_encap *tun_encap_info; struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; struct lwtunnel_state *newts; + u8 n_labels; int ret; ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, @@ -151,15 +176,32 @@ static int mpls_build_state(struct nlattr *nla, return -EINVAL; - newts = lwtunnel_state_alloc(sizeof(*tun_encap_info)); + /* determine number of labels */ + if (nla_get_labels(tb[MPLS_IPTUNNEL_DST], + MAX_NEW_LABELS, &n_labels, NULL)) + return -EINVAL; + + newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) + + n_labels * sizeof(u32)); if (!newts) return -ENOMEM; tun_encap_info = mpls_lwtunnel_encap(newts); - ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS, + ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels, &tun_encap_info->labels, tun_encap_info->label); if (ret) goto errout; + + tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT; + + if (tb[MPLS_IPTUNNEL_TTL]) { + tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]); + /* TTL 0 implies propagate from IP header */ + tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ? + MPLS_TTL_PROP_DISABLED : + MPLS_TTL_PROP_ENABLED; + } + newts->type = LWTUNNEL_ENCAP_MPLS; newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; newts->headroom = mpls_encap_size(tun_encap_info); @@ -186,6 +228,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb, tun_encap_info->label)) goto nla_put_failure; + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT && + nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -195,10 +241,16 @@ nla_put_failure: static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) { struct mpls_iptunnel_encap *tun_encap_info; + int nlsize; tun_encap_info = mpls_lwtunnel_encap(lwtstate); - return nla_total_size(tun_encap_info->labels * 4); + nlsize = nla_total_size(tun_encap_info->labels * 4); + + if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT) + nlsize += nla_total_size(1); + + return nlsize; } static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) @@ -207,10 +259,12 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); int l; - if (a_hdr->labels != b_hdr->labels) + if (a_hdr->labels != b_hdr->labels || + a_hdr->ttl_propagate != b_hdr->ttl_propagate || + a_hdr->default_ttl != b_hdr->default_ttl) return 1; - for (l = 0; l < MAX_NEW_LABELS; l++) + for (l = 0; l < a_hdr->labels; l++) if (a_hdr->label[l] != b_hdr->label[l]) return 1; return 0; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index e6a2753dff9e..3d2ac71a83ec 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -181,7 +181,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) if (!(cp->flags & IP_VS_CONN_F_HASHED)) { cp->flags |= IP_VS_CONN_F_HASHED; - atomic_inc(&cp->refcnt); + refcount_inc(&cp->refcnt); hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]); ret = 1; } else { @@ -215,7 +215,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) if (cp->flags & IP_VS_CONN_F_HASHED) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; - atomic_dec(&cp->refcnt); + refcount_dec(&cp->refcnt); ret = 1; } else ret = 0; @@ -242,13 +242,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) if (cp->flags & IP_VS_CONN_F_HASHED) { ret = false; /* Decrease refcnt and unlink conn only if we are last user */ - if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&cp->refcnt)) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; ret = true; } } else - ret = atomic_read(&cp->refcnt) ? false : true; + ret = refcount_read(&cp->refcnt) ? false : true; spin_unlock(&cp->lock); ct_write_unlock_bh(hash); @@ -475,7 +475,7 @@ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp) void ip_vs_conn_put(struct ip_vs_conn *cp) { if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && - (atomic_read(&cp->refcnt) == 1) && + (refcount_read(&cp->refcnt) == 1) && !timer_pending(&cp->timer)) /* expire connection immediately */ __ip_vs_conn_put_notimer(cp); @@ -617,8 +617,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + cp->flags, refcount_read(&cp->refcnt), + refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) { @@ -714,8 +714,8 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), ip_vs_fwd_tag(cp), cp->state, - cp->flags, atomic_read(&cp->refcnt), - atomic_read(&dest->refcnt)); + cp->flags, refcount_read(&cp->refcnt), + refcount_read(&dest->refcnt)); /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { @@ -863,10 +863,10 @@ static void ip_vs_conn_expire(unsigned long data) expire_later: IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n", - atomic_read(&cp->refcnt), + refcount_read(&cp->refcnt), atomic_read(&cp->n_control)); - atomic_inc(&cp->refcnt); + refcount_inc(&cp->refcnt); cp->timeout = 60*HZ; if (ipvs->sync_state & IP_VS_STATE_MASTER) @@ -941,7 +941,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, * it in the table, so that other thread run ip_vs_random_dropentry * but cannot drop this entry. */ - atomic_set(&cp->refcnt, 1); + refcount_set(&cp->refcnt, 1); cp->control = NULL; atomic_set(&cp->n_control, 0); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index db40050f8785..b4a746d0e39b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -542,7 +542,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), - cp->flags, atomic_read(&cp->refcnt)); + cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; @@ -1193,7 +1193,7 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), - cp->flags, atomic_read(&cp->refcnt)); + cp->flags, refcount_read(&cp->refcnt)); LeaveFunction(12); return cp; } @@ -2231,8 +2231,6 @@ static int __net_init __ip_vs_init(struct net *net) if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; - printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", - sizeof(struct netns_ipvs), ipvs->gen); return 0; /* * Error handling diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5aeb0dde6ccc..541aa7694775 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -699,7 +699,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, dest->vfwmark, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); if (dest->af == dest_af && ip_vs_addr_equal(dest_af, &dest->addr, daddr) && dest->port == dport && @@ -934,7 +934,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atomic_set(&dest->activeconns, 0); atomic_set(&dest->inactconns, 0); atomic_set(&dest->persistconns, 0); - atomic_set(&dest->refcnt, 1); + refcount_set(&dest->refcnt, 1); INIT_HLIST_NODE(&dest->d_list); spin_lock_init(&dest->dst_lock); @@ -998,7 +998,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, " "dest->refcnt=%d, service %u/%s:%u\n", IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport), - atomic_read(&dest->refcnt), + refcount_read(&dest->refcnt), dest->vfwmark, IP_VS_DBG_ADDR(svc->af, &dest->vaddr), ntohs(dest->vport)); @@ -1074,7 +1074,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); @@ -1157,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data) spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - if (atomic_read(&dest->refcnt) > 1) + if (refcount_read(&dest->refcnt) > 1) continue; if (dest->idle_start) { if (time_before(now, dest->idle_start + @@ -1545,7 +1545,7 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev) dev->name, IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), - atomic_read(&dest->refcnt)); + refcount_read(&dest->refcnt)); __ip_vs_dst_cache_reset(dest); } spin_unlock_bh(&dest->dst_lock); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 5824927cf8e0..b6aa4a970c6e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -448,7 +448,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 703f11877bee..c13ff575f9f7 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -204,7 +204,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } @@ -249,7 +249,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) __func__, IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port), atomic_read(&most->activeconns), - atomic_read(&most->refcnt), + refcount_read(&most->refcnt), atomic_read(&most->weight), moh); return most; } @@ -612,7 +612,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index a8b63401e773..7d9d4ac596ca 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -110,7 +110,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index d952d67f904d..56f8e4b204ff 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -447,7 +447,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ntohs(cp->cport), sctp_state_name(cp->state), sctp_state_name(next_state), - atomic_read(&cp->refcnt)); + refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state != IP_VS_SCTP_S_ESTABLISHED)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 5117bcb7d2f0..12dc8d5bc37d 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -557,7 +557,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ntohs(cp->cport), tcp_state_name(cp->state), tcp_state_name(new_state), - atomic_read(&cp->refcnt)); + refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c index 58bacfc461ee..ee0530d14c5f 100644 --- a/net/netfilter/ipvs/ip_vs_rr.c +++ b/net/netfilter/ipvs/ip_vs_rr.c @@ -97,7 +97,7 @@ stop: "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), atomic_read(&dest->weight)); + refcount_read(&dest->refcnt), atomic_read(&dest->weight)); return dest; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index f8e2d00f528b..ab23cf203437 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -111,7 +111,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6b366fd90554..6add39e0ec20 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -83,7 +83,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->refcnt), + refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 17e6d4406ca7..62258dd457ac 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -218,7 +218,7 @@ found: "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), - atomic_read(&dest->refcnt), + refcount_read(&dest->refcnt), atomic_read(&dest->weight)); mark->cl = dest; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ffb78e5f7b70..3d621b8d7b8a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1133,7 +1133,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ -static struct nf_conntrack_tuple_hash * +static noinline struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_l3proto *l3proto, @@ -1241,21 +1241,20 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, return &ct->tuplehash[IP_CT_DIR_ORIGINAL]; } -/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */ -static inline struct nf_conn * +/* On success, returns 0, sets skb->_nfct | ctinfo */ +static int resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, struct nf_conntrack_l3proto *l3proto, - struct nf_conntrack_l4proto *l4proto, - int *set_reply, - enum ip_conntrack_info *ctinfo) + struct nf_conntrack_l4proto *l4proto) { const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; + enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; struct nf_conn *ct; u32 hash; @@ -1264,7 +1263,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, dataoff, l3num, protonum, net, &tuple, l3proto, l4proto)) { pr_debug("Can't get tuple\n"); - return NULL; + return 0; } /* look for tuple match */ @@ -1275,33 +1274,30 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, skb, dataoff, hash); if (!h) - return NULL; + return 0; if (IS_ERR(h)) - return (void *)h; + return PTR_ERR(h); } ct = nf_ct_tuplehash_to_ctrack(h); /* It exists; we have (non-exclusive) reference. */ if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { - *ctinfo = IP_CT_ESTABLISHED_REPLY; - /* Please set reply bit if this packet OK */ - *set_reply = 1; + ctinfo = IP_CT_ESTABLISHED_REPLY; } else { /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { pr_debug("normal packet for %p\n", ct); - *ctinfo = IP_CT_ESTABLISHED; + ctinfo = IP_CT_ESTABLISHED; } else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) { pr_debug("related packet for %p\n", ct); - *ctinfo = IP_CT_RELATED; + ctinfo = IP_CT_RELATED; } else { pr_debug("new packet for %p\n", ct); - *ctinfo = IP_CT_NEW; + ctinfo = IP_CT_NEW; } - *set_reply = 0; } - nf_ct_set(skb, ct, *ctinfo); - return ct; + nf_ct_set(skb, ct, ctinfo); + return 0; } unsigned int @@ -1315,7 +1311,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, unsigned int *timeouts; unsigned int dataoff; u_int8_t protonum; - int set_reply = 0; int ret; tmpl = nf_ct_get(skb, &ctinfo); @@ -1358,23 +1353,22 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } repeat: - ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, - l3proto, l4proto, &set_reply, &ctinfo); - if (!ct) { - /* Not valid part of a connection */ - NF_CT_STAT_INC_ATOMIC(net, invalid); - ret = NF_ACCEPT; - goto out; - } - - if (IS_ERR(ct)) { + ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, + l3proto, l4proto); + if (ret < 0) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(net, drop); ret = NF_DROP; goto out; } - NF_CT_ASSERT(skb_nfct(skb)); + ct = nf_ct_get(skb, &ctinfo); + if (!ct) { + /* Not valid part of a connection */ + NF_CT_STAT_INC_ATOMIC(net, invalid); + ret = NF_ACCEPT; + goto out; + } /* Decide what timeout policy we want to apply to this flow. */ timeouts = nf_ct_timeout_lookup(net, ct, l4proto); @@ -1399,7 +1393,8 @@ repeat: goto out; } - if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) + if (ctinfo == IP_CT_ESTABLISHED_REPLY && + !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); out: if (tmpl) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4b2e1fb28bb4..cb29e598605f 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -133,7 +133,7 @@ nf_ct_expect_find_get(struct net *net, rcu_read_lock(); i = __nf_ct_expect_find(net, zone, tuple); - if (i && !atomic_inc_not_zero(&i->use)) + if (i && !refcount_inc_not_zero(&i->use)) i = NULL; rcu_read_unlock(); @@ -186,7 +186,7 @@ nf_ct_find_expectation(struct net *net, return NULL; if (exp->flags & NF_CT_EXPECT_PERMANENT) { - atomic_inc(&exp->use); + refcount_inc(&exp->use); return exp; } else if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); @@ -275,7 +275,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) return NULL; new->master = me; - atomic_set(&new->use, 1); + refcount_set(&new->use, 1); return new; } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); @@ -348,7 +348,7 @@ static void nf_ct_expect_free_rcu(struct rcu_head *head) void nf_ct_expect_put(struct nf_conntrack_expect *exp) { - if (atomic_dec_and_test(&exp->use)) + if (refcount_dec_and_test(&exp->use)) call_rcu(&exp->rcu, nf_ct_expect_free_rcu); } EXPORT_SYMBOL_GPL(nf_ct_expect_put); @@ -361,7 +361,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple); /* two references : one for hash insert, one for the timer */ - atomic_add(2, &exp->use); + refcount_add(2, &exp->use); hlist_add_head(&exp->lnode, &master_help->expectations); master_help->expecting[exp->class]++; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 908d858034e4..ecdc324c7785 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2693,7 +2693,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!atomic_inc_not_zero(&exp->use)) + if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; @@ -2739,7 +2739,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!atomic_inc_not_zero(&exp->use)) + if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 434c739dfeca..2d822d2fd830 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1772,8 +1772,19 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx, goto err1; } + if (ops->validate) { + const struct nft_data *data = NULL; + + err = ops->validate(ctx, expr, &data); + if (err < 0) + goto err2; + } + return 0; +err2: + if (ops->destroy) + ops->destroy(ctx, expr); err1: expr->ops = NULL; return err; @@ -2523,8 +2534,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, return 0; } -struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_set *set; @@ -2538,11 +2549,10 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_set_lookup); -struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla, - u8 genmask) +static struct nft_set *nf_tables_set_lookup_byid(const struct net *net, + const struct nlattr *nla, + u8 genmask) { struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); @@ -2557,7 +2567,25 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid); + +struct nft_set *nft_set_lookup(const struct net *net, + const struct nft_table *table, + const struct nlattr *nla_set_name, + const struct nlattr *nla_set_id, + u8 genmask) +{ + struct nft_set *set; + + set = nf_tables_set_lookup(table, nla_set_name, genmask); + if (IS_ERR(set)) { + if (!nla_set_id) + return set; + + set = nf_tables_set_lookup_byid(net, nla_set_id, genmask); + } + return set; +} +EXPORT_SYMBOL_GPL(nft_set_lookup); static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) @@ -4064,7 +4092,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, }; -static struct nft_object *nft_obj_init(const struct nft_object_type *type, +static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, + const struct nft_object_type *type, const struct nlattr *attr) { struct nlattr *tb[type->maxattr + 1]; @@ -4084,7 +4113,7 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type, if (obj == NULL) goto err1; - err = type->init((const struct nlattr * const *)tb, obj); + err = type->init(ctx, (const struct nlattr * const *)tb, obj); if (err < 0) goto err2; @@ -4192,7 +4221,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (IS_ERR(type)) return PTR_ERR(type); - obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]); + obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err1; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index d44d89b56127..c86da174a5fc 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/slab.h> @@ -32,7 +33,7 @@ struct nf_acct { atomic64_t bytes; unsigned long flags; struct list_head head; - atomic_t refcnt; + refcount_t refcnt; char name[NFACCT_NAME_MAX]; struct rcu_head rcu_head; char data[0]; @@ -123,7 +124,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, atomic64_set(&nfacct->pkts, be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS]))); } - atomic_set(&nfacct->refcnt, 1); + refcount_set(&nfacct->refcnt, 1); list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list); return 0; } @@ -166,7 +167,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, NFACCT_PAD) || nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes), NFACCT_PAD) || - nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)))) + nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt)))) goto nla_put_failure; if (acct->flags & NFACCT_F_QUOTA) { u64 *quota = (u64 *)acct->data; @@ -329,7 +330,7 @@ static int nfnl_acct_try_del(struct nf_acct *cur) /* We want to avoid races with nfnl_acct_put. So only when the current * refcnt is 1, we decrease it to 0. */ - if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&cur->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); @@ -413,7 +414,7 @@ struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name) if (!try_module_get(THIS_MODULE)) goto err; - if (!atomic_inc_not_zero(&cur->refcnt)) { + if (!refcount_inc_not_zero(&cur->refcnt)) { module_put(THIS_MODULE); goto err; } @@ -429,7 +430,7 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get); void nfnl_acct_put(struct nf_acct *acct) { - if (atomic_dec_and_test(&acct->refcnt)) + if (refcount_dec_and_test(&acct->refcnt)) kfree_rcu(acct, rcu_head); module_put(THIS_MODULE); @@ -502,7 +503,7 @@ static void __net_exit nfnl_acct_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) { list_del_rcu(&cur->head); - if (atomic_dec_and_test(&cur->refcnt)) + if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 47d6656c9119..57c2cdf7b691 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -138,7 +138,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME])); timeout->l3num = l3num; timeout->l4proto = l4proto; - atomic_set(&timeout->refcnt, 1); + refcount_set(&timeout->refcnt, 1); list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list); return 0; @@ -172,7 +172,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) || nla_put_be32(skb, CTA_TIMEOUT_USE, - htonl(atomic_read(&timeout->refcnt)))) + htonl(refcount_read(&timeout->refcnt)))) goto nla_put_failure; if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { @@ -339,7 +339,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) /* We want to avoid races with ctnl_timeout_put. So only when the * current refcnt is 1, we decrease it to 0. */ - if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { + if (refcount_dec_if_one(&timeout->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); @@ -536,7 +536,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) if (!try_module_get(THIS_MODULE)) goto err; - if (!atomic_inc_not_zero(&timeout->refcnt)) { + if (!refcount_inc_not_zero(&timeout->refcnt)) { module_put(THIS_MODULE); goto err; } @@ -550,7 +550,7 @@ err: static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - if (atomic_dec_and_test(&timeout->refcnt)) + if (refcount_dec_and_test(&timeout->refcnt)) kfree_rcu(timeout, rcu_head); module_put(THIS_MODULE); @@ -601,7 +601,7 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - if (atomic_dec_and_test(&cur->refcnt)) + if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 08247bf7d7b8..ecd857b75ffe 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -40,6 +40,8 @@ #include <net/netfilter/nfnetlink_log.h> #include <linux/atomic.h> +#include <linux/refcount.h> + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" @@ -57,7 +59,7 @@ struct nfulnl_instance { struct hlist_node hlist; /* global list of instances */ spinlock_t lock; - atomic_t use; /* use count */ + refcount_t use; /* use count */ unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ @@ -115,7 +117,7 @@ __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num) static inline void instance_get(struct nfulnl_instance *inst) { - atomic_inc(&inst->use); + refcount_inc(&inst->use); } static struct nfulnl_instance * @@ -125,7 +127,7 @@ instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num) rcu_read_lock_bh(); inst = __instance_lookup(log, group_num); - if (inst && !atomic_inc_not_zero(&inst->use)) + if (inst && !refcount_inc_not_zero(&inst->use)) inst = NULL; rcu_read_unlock_bh(); @@ -145,7 +147,7 @@ static void nfulnl_instance_free_rcu(struct rcu_head *head) static void instance_put(struct nfulnl_instance *inst) { - if (inst && atomic_dec_and_test(&inst->use)) + if (inst && refcount_dec_and_test(&inst->use)) call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu); } @@ -180,7 +182,7 @@ instance_create(struct net *net, u_int16_t group_num, INIT_HLIST_NODE(&inst->hlist); spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ - atomic_set(&inst->use, 2); + refcount_set(&inst->use, 2); setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst); @@ -1031,7 +1033,7 @@ static int seq_show(struct seq_file *s, void *v) inst->group_num, inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, - inst->flushtimeout, atomic_read(&inst->use)); + inst->flushtimeout, refcount_read(&inst->use)); return 0; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index c21e7eb8dce0..fab6bf3f955e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -230,10 +230,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, union nft_entry e = {}; int ret; - ret = nft_compat_chain_validate_dependency(target->table, ctx->chain); - if (ret < 0) - goto err; - target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { @@ -419,10 +415,6 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, union nft_entry e = {}; int ret; - ret = nft_compat_chain_validate_dependency(match->table, ctx->chain); - if (ret < 0) - goto err; - match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 7f8422213341..67a710ebde09 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -82,7 +82,8 @@ static int nft_counter_do_init(const struct nlattr * const tb[], return 0; } -static int nft_counter_obj_init(const struct nlattr * const tb[], +static int nft_counter_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], struct nft_object *obj) { struct nft_counter_percpu_priv *priv = nft_obj_data(obj); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 0264258c46fe..640fe5a5865e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -32,6 +32,12 @@ struct nft_ct { }; }; +struct nft_ct_helper_obj { + struct nf_conntrack_helper *helper4; + struct nf_conntrack_helper *helper6; + u8 l4proto; +}; + #ifdef CONFIG_NF_CONNTRACK_ZONES static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template); static unsigned int nft_ct_pcpu_template_refcnt __read_mostly; @@ -733,6 +739,162 @@ static struct nft_expr_type nft_notrack_type __read_mostly = { .owner = THIS_MODULE, }; +static int nft_ct_helper_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_ct_helper_obj *priv = nft_obj_data(obj); + struct nf_conntrack_helper *help4, *help6; + char name[NF_CT_HELPER_NAME_LEN]; + int family = ctx->afi->family; + + if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO]) + return -EINVAL; + + priv->l4proto = nla_get_u8(tb[NFTA_CT_HELPER_L4PROTO]); + if (!priv->l4proto) + return -ENOENT; + + nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name)); + + if (tb[NFTA_CT_HELPER_L3PROTO]) + family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO])); + + help4 = NULL; + help6 = NULL; + + switch (family) { + case NFPROTO_IPV4: + if (ctx->afi->family == NFPROTO_IPV6) + return -EINVAL; + + help4 = nf_conntrack_helper_try_module_get(name, family, + priv->l4proto); + break; + case NFPROTO_IPV6: + if (ctx->afi->family == NFPROTO_IPV4) + return -EINVAL; + + help6 = nf_conntrack_helper_try_module_get(name, family, + priv->l4proto); + break; + case NFPROTO_NETDEV: /* fallthrough */ + case NFPROTO_BRIDGE: /* same */ + case NFPROTO_INET: + help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4, + priv->l4proto); + help6 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV6, + priv->l4proto); + break; + default: + return -EAFNOSUPPORT; + } + + /* && is intentional; only error if INET found neither ipv4 or ipv6 */ + if (!help4 && !help6) + return -ENOENT; + + priv->helper4 = help4; + priv->helper6 = help6; + + return 0; +} + +static void nft_ct_helper_obj_destroy(struct nft_object *obj) +{ + struct nft_ct_helper_obj *priv = nft_obj_data(obj); + + if (priv->helper4) + module_put(priv->helper4->me); + if (priv->helper6) + module_put(priv->helper6->me); +} + +static void nft_ct_helper_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_ct_helper_obj *priv = nft_obj_data(obj); + struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); + struct nf_conntrack_helper *to_assign = NULL; + struct nf_conn_help *help; + + if (!ct || + nf_ct_is_confirmed(ct) || + nf_ct_is_template(ct) || + priv->l4proto != nf_ct_protonum(ct)) + return; + + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + to_assign = priv->helper4; + break; + case NFPROTO_IPV6: + to_assign = priv->helper6; + break; + default: + WARN_ON_ONCE(1); + return; + } + + if (!to_assign) + return; + + if (test_bit(IPS_HELPER_BIT, &ct->status)) + return; + + help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC); + if (help) { + rcu_assign_pointer(help->helper, to_assign); + set_bit(IPS_HELPER_BIT, &ct->status); + } +} + +static int nft_ct_helper_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + const struct nft_ct_helper_obj *priv = nft_obj_data(obj); + const struct nf_conntrack_helper *helper = priv->helper4; + u16 family; + + if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name)) + return -1; + + if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto)) + return -1; + + if (priv->helper4 && priv->helper6) + family = NFPROTO_INET; + else if (priv->helper6) + family = NFPROTO_IPV6; + else + family = NFPROTO_IPV4; + + if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family))) + return -1; + + return 0; +} + +static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = { + [NFTA_CT_HELPER_NAME] = { .type = NLA_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, + [NFTA_CT_HELPER_L3PROTO] = { .type = NLA_U16 }, + [NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 }, +}; + +static struct nft_object_type nft_ct_helper_obj __read_mostly = { + .type = NFT_OBJECT_CT_HELPER, + .size = sizeof(struct nft_ct_helper_obj), + .maxattr = NFTA_CT_HELPER_MAX, + .policy = nft_ct_helper_policy, + .eval = nft_ct_helper_obj_eval, + .init = nft_ct_helper_obj_init, + .destroy = nft_ct_helper_obj_destroy, + .dump = nft_ct_helper_obj_dump, + .owner = THIS_MODULE, +}; + static int __init nft_ct_module_init(void) { int err; @@ -747,7 +909,14 @@ static int __init nft_ct_module_init(void) if (err < 0) goto err1; + err = nft_register_obj(&nft_ct_helper_obj); + if (err < 0) + goto err2; + return 0; + +err2: + nft_unregister_expr(&nft_notrack_type); err1: nft_unregister_expr(&nft_ct_type); return err; @@ -755,6 +924,7 @@ err1: static void __exit nft_ct_module_exit(void) { + nft_unregister_obj(&nft_ct_helper_obj); nft_unregister_expr(&nft_notrack_type); nft_unregister_expr(&nft_ct_type); } @@ -766,3 +936,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("ct"); MODULE_ALIAS_NFT_EXPR("notrack"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 049ad2d9ee66..3948da380259 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -133,16 +133,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, priv->invert = true; } - set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME], - genmask); - if (IS_ERR(set)) { - if (tb[NFTA_DYNSET_SET_ID]) - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_DYNSET_SET_ID], - genmask); - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME], + tb[NFTA_DYNSET_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (set->ops->update == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index c308920b194c..d212a85d2f33 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -98,14 +98,21 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, goto err; offset = i + priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - memcpy(dest, opt + offset, priv->len); + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + *dest = 1; + } else { + dest[priv->len / NFT_REG32_SIZE] = 0; + memcpy(dest, opt + offset, priv->len); + } return; } err: - regs->verdict.code = NFT_BREAK; + if (priv->flags & NFT_EXTHDR_F_PRESENT) + *dest = 0; + else + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 29a4906adc27..21df8cccea65 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -24,7 +24,8 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { EXPORT_SYMBOL(nft_fib_policy); #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ - NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF) + NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \ + NFTA_FIB_F_PRESENT) int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) @@ -112,7 +113,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - return nft_fib_validate(ctx, expr, NULL); + return 0; } EXPORT_SYMBOL_GPL(nft_fib_init); @@ -133,19 +134,22 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr) } EXPORT_SYMBOL_GPL(nft_fib_dump); -void nft_fib_store_result(void *reg, enum nft_fib_result r, +void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct nft_pktinfo *pkt, int index) { struct net_device *dev; u32 *dreg = reg; - switch (r) { + switch (priv->result) { case NFT_FIB_RESULT_OIF: - *dreg = index; + *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index; break; case NFT_FIB_RESULT_OIFNAME: dev = dev_get_by_index_rcu(nft_net(pkt), index); - strncpy(reg, dev ? dev->name : "", IFNAMSIZ); + if (priv->flags & NFTA_FIB_F_PRESENT) + *dreg = !!dev; + else + strncpy(reg, dev ? dev->name : "", IFNAMSIZ); break; default: WARN_ON_ONCE(1); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index eb2721af898d..a6a4633725bb 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -17,7 +17,7 @@ #include <net/netfilter/nf_tables_core.h> #include <linux/jhash.h> -struct nft_hash { +struct nft_jhash { enum nft_registers sreg:8; enum nft_registers dreg:8; u8 len; @@ -26,11 +26,11 @@ struct nft_hash { u32 offset; }; -static void nft_hash_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_jhash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { - struct nft_hash *priv = nft_expr_priv(expr); + struct nft_jhash *priv = nft_expr_priv(expr); const void *data = ®s->data[priv->sreg]; u32 h; @@ -38,6 +38,25 @@ static void nft_hash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } +struct nft_symhash { + enum nft_registers dreg:8; + u32 modulus; + u32 offset; +}; + +static void nft_symhash_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_symhash *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + u32 h; + + h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus); + + regs->data[priv->dreg] = h + priv->offset; +} + static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, @@ -45,13 +64,14 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, + [NFTA_HASH_TYPE] = { .type = NLA_U32 }, }; -static int nft_hash_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_jhash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_expr_priv(expr); + struct nft_jhash *priv = nft_expr_priv(expr); u32 len; int err; @@ -92,10 +112,36 @@ static int nft_hash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_hash_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_symhash_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { - const struct nft_hash *priv = nft_expr_priv(expr); + struct nft_symhash *priv = nft_expr_priv(expr); + + if (!tb[NFTA_HASH_DREG] || + !tb[NFTA_HASH_MODULUS]) + return -EINVAL; + + if (tb[NFTA_HASH_OFFSET]) + priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); + + priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); + + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); + if (priv->modulus <= 1) + return -ERANGE; + + if (priv->offset + priv->modulus - 1 < priv->offset) + return -EOVERFLOW; + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); +} + +static int nft_jhash_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_jhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) goto nla_put_failure; @@ -110,6 +156,28 @@ static int nft_hash_dump(struct sk_buff *skb, if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static int nft_symhash_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_symhash *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) + goto nla_put_failure; + if (priv->offset != 0) + if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM))) + goto nla_put_failure; return 0; nla_put_failure: @@ -117,17 +185,46 @@ nla_put_failure: } static struct nft_expr_type nft_hash_type; -static const struct nft_expr_ops nft_hash_ops = { +static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)), - .eval = nft_hash_eval, - .init = nft_hash_init, - .dump = nft_hash_dump, + .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), + .eval = nft_jhash_eval, + .init = nft_jhash_init, + .dump = nft_jhash_dump, }; +static const struct nft_expr_ops nft_symhash_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), + .eval = nft_symhash_eval, + .init = nft_symhash_init, + .dump = nft_symhash_dump, +}; + +static const struct nft_expr_ops * +nft_hash_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + u32 type; + + if (!tb[NFTA_HASH_TYPE]) + return &nft_jhash_ops; + + type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); + switch (type) { + case NFT_HASH_SYM: + return &nft_symhash_ops; + case NFT_HASH_JENKINS: + return &nft_jhash_ops; + default: + break; + } + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_hash_type __read_mostly = { .name = "hash", - .ops = &nft_hash_ops, + .select_ops = &nft_hash_select_ops, .policy = nft_hash_policy, .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index c6baf412236d..18dd57a52651 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -17,9 +17,8 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -static DEFINE_SPINLOCK(limit_lock); - struct nft_limit { + spinlock_t lock; u64 last; u64 tokens; u64 tokens_max; @@ -34,7 +33,7 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) u64 now, tokens; s64 delta; - spin_lock_bh(&limit_lock); + spin_lock_bh(&limit->lock); now = ktime_get_ns(); tokens = limit->tokens + now - limit->last; if (tokens > limit->tokens_max) @@ -44,11 +43,11 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) delta = tokens - cost; if (delta >= 0) { limit->tokens = delta; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&limit->lock); return limit->invert; } limit->tokens = tokens; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&limit->lock); return !limit->invert; } @@ -86,6 +85,7 @@ static int nft_limit_init(struct nft_limit *limit, limit->invert = true; } limit->last = ktime_get_ns(); + spin_lock_init(&limit->lock); return 0; } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index e21aea7e5ec8..475570e89ede 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -71,16 +71,10 @@ static int nft_lookup_init(const struct nft_ctx *ctx, tb[NFTA_LOOKUP_SREG] == NULL) return -EINVAL; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask); - if (IS_ERR(set)) { - if (tb[NFTA_LOOKUP_SET_ID]) { - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_LOOKUP_SET_ID], - genmask); - } - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET], + tb[NFTA_LOOKUP_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (set->flags & NFT_SET_EVAL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 11ce016cd479..6ac03d4266c9 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -46,10 +46,6 @@ int nft_masq_init(const struct nft_ctx *ctx, struct nft_masq *priv = nft_expr_priv(expr); int err; - err = nft_masq_validate(ctx, expr, NULL); - if (err) - return err; - if (tb[NFTA_MASQ_FLAGS]) { priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 7b60e01f38ff..9563ce3c23aa 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -372,10 +372,6 @@ int nft_meta_set_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_meta_set_validate(ctx, expr, NULL); - if (err < 0) - return err; - priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 439e0bd152a0..ed548d06b6dd 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -138,10 +138,6 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; } - err = nft_nat_validate(ctx, expr, NULL); - if (err < 0) - return err; - if (tb[NFTA_NAT_FAMILY] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 1ae8c49ca4a1..1dd428fbaaa3 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -116,16 +116,10 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, struct nft_set *set; int err; - set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask); - if (IS_ERR(set)) { - if (tb[NFTA_OBJREF_SET_ID]) { - set = nf_tables_set_lookup_byid(ctx->net, - tb[NFTA_OBJREF_SET_ID], - genmask); - } - if (IS_ERR(set)) - return PTR_ERR(set); - } + set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME], + tb[NFTA_OBJREF_SET_ID], genmask); + if (IS_ERR(set)) + return PTR_ERR(set); if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 2d6fe3559912..25e33159be57 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -99,7 +99,8 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return 0; } -static int nft_quota_obj_init(const struct nlattr * const tb[], +static int nft_quota_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], struct nft_object *obj) { struct nft_quota *priv = nft_obj_data(obj); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 40dcd05146d5..1e66538bf0ff 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -47,10 +47,6 @@ int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - err = nft_redir_validate(ctx, expr, NULL); - if (err < 0) - return err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index c64de3f7379d..29f5bd2377b0 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -42,11 +42,6 @@ int nft_reject_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int err; - - err = nft_reject_validate(ctx, expr, NULL); - if (err < 0) - return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 9e90a02cb104..5a7fb5ff867d 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -66,11 +66,7 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code, err; - - err = nft_reject_validate(ctx, expr, NULL); - if (err < 0) - return err; + int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 78dfbf9588b3..e97e2fb53f0a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -18,9 +18,8 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -static DEFINE_SPINLOCK(nft_rbtree_lock); - struct nft_rbtree { + rwlock_t lock; struct rb_root root; }; @@ -44,14 +43,14 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this, static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { - const struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; const void *this; int d; - spin_lock_bh(&nft_rbtree_lock); + read_lock_bh(&priv->lock); parent = priv->root.rb_node; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); @@ -75,7 +74,7 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } if (nft_rbtree_interval_end(rbe)) goto out; - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); *ext = &rbe->ext; return true; @@ -85,12 +84,12 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_interval_end(interval)) { - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); *ext = &interval->ext; return true; } out: - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); return false; } @@ -140,12 +139,13 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_set_ext **ext) { + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe = elem->priv; int err; - spin_lock_bh(&nft_rbtree_lock); + write_lock_bh(&priv->lock); err = __nft_rbtree_insert(net, set, rbe, ext); - spin_unlock_bh(&nft_rbtree_lock); + write_unlock_bh(&priv->lock); return err; } @@ -157,9 +157,9 @@ static void nft_rbtree_remove(const struct net *net, struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe = elem->priv; - spin_lock_bh(&nft_rbtree_lock); + write_lock_bh(&priv->lock); rb_erase(&rbe->node, &priv->root); - spin_unlock_bh(&nft_rbtree_lock); + write_unlock_bh(&priv->lock); } static void nft_rbtree_activate(const struct net *net, @@ -224,12 +224,12 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { - const struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct nft_set_elem elem; struct rb_node *node; - spin_lock_bh(&nft_rbtree_lock); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -242,13 +242,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) { - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); return; } cont: iter->count++; } - spin_unlock_bh(&nft_rbtree_lock); + read_unlock_bh(&priv->lock); } static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) @@ -262,6 +262,7 @@ static int nft_rbtree_init(const struct nft_set *set, { struct nft_rbtree *priv = nft_set_priv(set); + rwlock_init(&priv->lock); priv->root = RB_ROOT; return 0; } diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index dab962df1787..d27b5f1ea619 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -18,6 +18,7 @@ #include <linux/netfilter/xt_limit.h> struct xt_limit_priv { + spinlock_t lock; unsigned long prev; uint32_t credit; }; @@ -32,8 +33,6 @@ MODULE_ALIAS("ip6t_limit"); * see net/sched/sch_tbf.c in the linux source tree */ -static DEFINE_SPINLOCK(limit_lock); - /* Rusty: This is my (non-mathematically-inclined) understanding of this algorithm. The `average rate' in jiffies becomes your initial amount of credit `credit' and the most credit you can ever have @@ -72,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) struct xt_limit_priv *priv = r->master; unsigned long now = jiffies; - spin_lock_bh(&limit_lock); + spin_lock_bh(&priv->lock); priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; if (priv->credit > r->credit_cap) priv->credit = r->credit_cap; @@ -80,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) if (priv->credit >= r->cost) { /* We're not limited. */ priv->credit -= r->cost; - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&priv->lock); return true; } - spin_unlock_bh(&limit_lock); + spin_unlock_bh(&priv->lock); return false; } @@ -126,6 +125,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par) r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } + spin_lock_init(&priv->lock); + return 0; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 596eaff66649..fc232441cf23 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -78,14 +78,6 @@ struct listeners { /* state bits */ #define NETLINK_S_CONGESTED 0x0 -/* flags */ -#define NETLINK_F_KERNEL_SOCKET 0x1 -#define NETLINK_F_RECV_PKTINFO 0x2 -#define NETLINK_F_BROADCAST_SEND_ERROR 0x4 -#define NETLINK_F_RECV_NO_ENOBUFS 0x8 -#define NETLINK_F_LISTEN_ALL_NSID 0x10 -#define NETLINK_F_CAP_ACK 0x20 - static inline int netlink_is_kernel(struct sock *sk) { return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 4fdb38318977..f792f8d7f982 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -6,6 +6,14 @@ #include <linux/workqueue.h> #include <net/sock.h> +/* flags */ +#define NETLINK_F_KERNEL_SOCKET 0x1 +#define NETLINK_F_RECV_PKTINFO 0x2 +#define NETLINK_F_BROADCAST_SEND_ERROR 0x4 +#define NETLINK_F_RECV_NO_ENOBUFS 0x8 +#define NETLINK_F_LISTEN_ALL_NSID 0x10 +#define NETLINK_F_CAP_ACK 0x20 + #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) #define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) diff --git a/net/netlink/diag.c b/net/netlink/diag.c index a5546249fb10..8faa20b4d457 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -19,6 +19,27 @@ static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb) nlk->groups); } +static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb) +{ + struct netlink_sock *nlk = nlk_sk(sk); + u32 flags = 0; + + if (nlk->cb_running) + flags |= NDIAG_FLAG_CB_RUNNING; + if (nlk->flags & NETLINK_F_RECV_PKTINFO) + flags |= NDIAG_FLAG_PKTINFO; + if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + flags |= NDIAG_FLAG_BROADCAST_ERROR; + if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) + flags |= NDIAG_FLAG_NO_ENOBUFS; + if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + flags |= NDIAG_FLAG_LISTEN_ALL_NSID; + if (nlk->flags & NETLINK_F_CAP_ACK) + flags |= NDIAG_FLAG_CAP_ACK; + + return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags); +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_diag_req *req, u32 portid, u32 seq, u32 flags, int sk_ino) @@ -52,6 +73,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO)) goto out_nlmsg_trim; + if ((req->ndiag_show & NDIAG_SHOW_FLAGS) && + sk_diag_put_flags(sk, skb)) + goto out_nlmsg_trim; + nlmsg_end(skb, nlh); return 0; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index c82301ce3fff..e4610676299b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2014 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -44,13 +44,10 @@ #include "conntrack.h" #include "vport.h" -static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, - struct sw_flow_key *key, - const struct nlattr *attr, int len); - struct deferred_action { struct sk_buff *skb; const struct nlattr *actions; + int actions_len; /* Store pkt_key clone when creating deferred action. */ struct sw_flow_key pkt_key; @@ -82,14 +79,31 @@ struct action_fifo { struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE]; }; -struct recirc_keys { +struct action_flow_keys { struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD]; }; static struct action_fifo __percpu *action_fifos; -static struct recirc_keys __percpu *recirc_keys; +static struct action_flow_keys __percpu *flow_keys; static DEFINE_PER_CPU(int, exec_actions_level); +/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys' + * space. Return NULL if out of key spaces. + */ +static struct sw_flow_key *clone_key(const struct sw_flow_key *key_) +{ + struct action_flow_keys *keys = this_cpu_ptr(flow_keys); + int level = this_cpu_read(exec_actions_level); + struct sw_flow_key *key = NULL; + + if (level <= OVS_DEFERRED_ACTION_THRESHOLD) { + key = &keys->key[level - 1]; + *key = *key_; + } + + return key; +} + static void action_fifo_init(struct action_fifo *fifo) { fifo->head = 0; @@ -119,8 +133,9 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo) /* Return true if fifo is not full */ static struct deferred_action *add_deferred_actions(struct sk_buff *skb, - const struct sw_flow_key *key, - const struct nlattr *attr) + const struct sw_flow_key *key, + const struct nlattr *actions, + const int actions_len) { struct action_fifo *fifo; struct deferred_action *da; @@ -129,7 +144,8 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb, da = action_fifo_put(fifo); if (da) { da->skb = skb; - da->actions = attr; + da->actions = actions; + da->actions_len = actions_len; da->pkt_key = *key; } @@ -146,6 +162,12 @@ static bool is_flow_key_valid(const struct sw_flow_key *key) return !(key->mac_proto & SW_FLOW_KEY_INVALID); } +static int clone_execute(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, + u32 recirc_id, + const struct nlattr *actions, int len, + bool last, bool clone_flow_key); + static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { @@ -908,72 +930,35 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, return ovs_dp_upcall(dp, skb, key, &upcall, cutlen); } +/* When 'last' is true, sample() should always consume the 'skb'. + * Otherwise, sample() should keep 'skb' intact regardless what + * actions are executed within sample(). + */ static int sample(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, - const struct nlattr *actions, int actions_len) + bool last) { - const struct nlattr *acts_list = NULL; - const struct nlattr *a; - int rem; - u32 cutlen = 0; - - for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { - u32 probability; - - switch (nla_type(a)) { - case OVS_SAMPLE_ATTR_PROBABILITY: - probability = nla_get_u32(a); - if (!probability || prandom_u32() > probability) - return 0; - break; - - case OVS_SAMPLE_ATTR_ACTIONS: - acts_list = a; - break; - } - } - - rem = nla_len(acts_list); - a = nla_data(acts_list); - - /* Actions list is empty, do nothing */ - if (unlikely(!rem)) + struct nlattr *actions; + struct nlattr *sample_arg; + int rem = nla_len(attr); + const struct sample_arg *arg; + bool clone_flow_key; + + /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */ + sample_arg = nla_data(attr); + arg = nla_data(sample_arg); + actions = nla_next(sample_arg, &rem); + + if ((arg->probability != U32_MAX) && + (!arg->probability || prandom_u32() > arg->probability)) { + if (last) + consume_skb(skb); return 0; - - /* The only known usage of sample action is having a single user-space - * action, or having a truncate action followed by a single user-space - * action. Treat this usage as a special case. - * The output_userspace() should clone the skb to be sent to the - * user space. This skb will be consumed by its caller. - */ - if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) { - struct ovs_action_trunc *trunc = nla_data(a); - - if (skb->len > trunc->max_len) - cutlen = skb->len - trunc->max_len; - - a = nla_next(a, &rem); } - if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE && - nla_is_last(a, rem))) - return output_userspace(dp, skb, key, a, actions, - actions_len, cutlen); - - skb = skb_clone(skb, GFP_ATOMIC); - if (!skb) - /* Skip the sample action when out of memory. */ - return 0; - - if (!add_deferred_actions(skb, key, a)) { - if (net_ratelimit()) - pr_warn("%s: deferred actions limit reached, dropping sample action\n", - ovs_dp_name(dp)); - - kfree_skb(skb); - } - return 0; + clone_flow_key = !arg->exec; + return clone_execute(dp, skb, key, 0, actions, rem, last, + clone_flow_key); } static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key, @@ -1084,10 +1069,9 @@ static int execute_masked_set_action(struct sk_buff *skb, static int execute_recirc(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, - const struct nlattr *a, int rem) + const struct nlattr *a, bool last) { - struct deferred_action *da; - int level; + u32 recirc_id; if (!is_flow_key_valid(key)) { int err; @@ -1098,43 +1082,8 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, } BUG_ON(!is_flow_key_valid(key)); - if (!nla_is_last(a, rem)) { - /* Recirc action is the not the last action - * of the action list, need to clone the skb. - */ - skb = skb_clone(skb, GFP_ATOMIC); - - /* Skip the recirc action when out of memory, but - * continue on with the rest of the action list. - */ - if (!skb) - return 0; - } - - level = this_cpu_read(exec_actions_level); - if (level <= OVS_DEFERRED_ACTION_THRESHOLD) { - struct recirc_keys *rks = this_cpu_ptr(recirc_keys); - struct sw_flow_key *recirc_key = &rks->key[level - 1]; - - *recirc_key = *key; - recirc_key->recirc_id = nla_get_u32(a); - ovs_dp_process_packet(skb, recirc_key); - - return 0; - } - - da = add_deferred_actions(skb, key, NULL); - if (da) { - da->pkt_key.recirc_id = nla_get_u32(a); - } else { - kfree_skb(skb); - - if (net_ratelimit()) - pr_warn("%s: deferred action limit reached, drop recirc action\n", - ovs_dp_name(dp)); - } - - return 0; + recirc_id = nla_get_u32(a); + return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true); } /* Execute a list of actions against 'skb'. */ @@ -1206,9 +1155,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, err = pop_vlan(skb, key); break; - case OVS_ACTION_ATTR_RECIRC: - err = execute_recirc(dp, skb, key, a, rem); - if (nla_is_last(a, rem)) { + case OVS_ACTION_ATTR_RECIRC: { + bool last = nla_is_last(a, rem); + + err = execute_recirc(dp, skb, key, a, last); + if (last) { /* If this is the last action, the skb has * been consumed or freed. * Return immediately. @@ -1216,6 +1167,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err; } break; + } case OVS_ACTION_ATTR_SET: err = execute_set_action(skb, key, nla_data(a)); @@ -1226,9 +1178,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, err = execute_masked_set_action(skb, key, nla_data(a)); break; - case OVS_ACTION_ATTR_SAMPLE: - err = sample(dp, skb, key, a, attr, len); + case OVS_ACTION_ATTR_SAMPLE: { + bool last = nla_is_last(a, rem); + + err = sample(dp, skb, key, a, last); + if (last) + return err; + break; + } case OVS_ACTION_ATTR_CT: if (!is_flow_key_valid(key)) { @@ -1264,6 +1222,79 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return 0; } +/* Execute the actions on the clone of the packet. The effect of the + * execution does not affect the original 'skb' nor the original 'key'. + * + * The execution may be deferred in case the actions can not be executed + * immediately. + */ +static int clone_execute(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, u32 recirc_id, + const struct nlattr *actions, int len, + bool last, bool clone_flow_key) +{ + struct deferred_action *da; + struct sw_flow_key *clone; + + skb = last ? skb : skb_clone(skb, GFP_ATOMIC); + if (!skb) { + /* Out of memory, skip this action. + */ + return 0; + } + + /* When clone_flow_key is false, the 'key' will not be change + * by the actions, then the 'key' can be used directly. + * Otherwise, try to clone key from the next recursion level of + * 'flow_keys'. If clone is successful, execute the actions + * without deferring. + */ + clone = clone_flow_key ? clone_key(key) : key; + if (clone) { + int err = 0; + + if (actions) { /* Sample action */ + if (clone_flow_key) + __this_cpu_inc(exec_actions_level); + + err = do_execute_actions(dp, skb, clone, + actions, len); + + if (clone_flow_key) + __this_cpu_dec(exec_actions_level); + } else { /* Recirc action */ + clone->recirc_id = recirc_id; + ovs_dp_process_packet(skb, clone); + } + return err; + } + + /* Out of 'flow_keys' space. Defer actions */ + da = add_deferred_actions(skb, key, actions, len); + if (da) { + if (!actions) { /* Recirc action */ + key = &da->pkt_key; + key->recirc_id = recirc_id; + } + } else { + /* Out of per CPU action FIFO space. Drop the 'skb' and + * log an error. + */ + kfree_skb(skb); + + if (net_ratelimit()) { + if (actions) { /* Sample action */ + pr_warn("%s: deferred action limit reached, drop sample action\n", + ovs_dp_name(dp)); + } else { /* Recirc action */ + pr_warn("%s: deferred action limit reached, drop recirc action\n", + ovs_dp_name(dp)); + } + } + } + return 0; +} + static void process_deferred_actions(struct datapath *dp) { struct action_fifo *fifo = this_cpu_ptr(action_fifos); @@ -1278,10 +1309,10 @@ static void process_deferred_actions(struct datapath *dp) struct sk_buff *skb = da->skb; struct sw_flow_key *key = &da->pkt_key; const struct nlattr *actions = da->actions; + int actions_len = da->actions_len; if (actions) - do_execute_actions(dp, skb, key, actions, - nla_len(actions)); + do_execute_actions(dp, skb, key, actions, actions_len); else ovs_dp_process_packet(skb, key); } while (!action_fifo_is_empty(fifo)); @@ -1323,8 +1354,8 @@ int action_fifos_init(void) if (!action_fifos) return -ENOMEM; - recirc_keys = alloc_percpu(struct recirc_keys); - if (!recirc_keys) { + flow_keys = alloc_percpu(struct action_flow_keys); + if (!flow_keys) { free_percpu(action_fifos); return -ENOMEM; } @@ -1335,5 +1366,5 @@ int action_fifos_init(void) void action_fifos_exit(void) { free_percpu(action_fifos); - free_percpu(recirc_keys); + free_percpu(flow_keys); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 1c6e9377436d..da931bdef8a7 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -34,8 +34,6 @@ #define DP_MAX_PORTS USHRT_MAX #define DP_VPORT_HASH_BUCKETS 1024 -#define SAMPLE_ACTION_DEPTH 3 - /** * struct dp_stats_percpu - per-cpu packet processing statistics for a given * datapath. diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 1105a838bab8..df82b81a9b35 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2014 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -59,6 +59,39 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +static bool actions_may_change_flow(const struct nlattr *actions) +{ + struct nlattr *nla; + int rem; + + nla_for_each_nested(nla, actions, rem) { + u16 action = nla_type(nla); + + switch (action) { + case OVS_ACTION_ATTR_OUTPUT: + case OVS_ACTION_ATTR_RECIRC: + case OVS_ACTION_ATTR_TRUNC: + case OVS_ACTION_ATTR_USERSPACE: + break; + + case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_HASH: + case OVS_ACTION_ATTR_POP_ETH: + case OVS_ACTION_ATTR_POP_MPLS: + case OVS_ACTION_ATTR_POP_VLAN: + case OVS_ACTION_ATTR_PUSH_ETH: + case OVS_ACTION_ATTR_PUSH_MPLS: + case OVS_ACTION_ATTR_PUSH_VLAN: + case OVS_ACTION_ATTR_SAMPLE: + case OVS_ACTION_ATTR_SET: + case OVS_ACTION_ATTR_SET_MASKED: + default: + return true; + } + } + return false; +} + static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) { @@ -2023,18 +2056,20 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa, static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, - int depth, struct sw_flow_actions **sfa, + struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, bool log); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, - const struct sw_flow_key *key, int depth, + const struct sw_flow_key *key, struct sw_flow_actions **sfa, - __be16 eth_type, __be16 vlan_tci, bool log) + __be16 eth_type, __be16 vlan_tci, + bool log, bool last) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; const struct nlattr *a; - int rem, start, err, st_acts; + int rem, start, err; + struct sample_arg arg; memset(attrs, 0, sizeof(attrs)); nla_for_each_nested(a, attr, rem) { @@ -2058,20 +2093,32 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log); if (start < 0) return start; - err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, - nla_data(probability), sizeof(u32), log); + + /* When both skb and flow may be changed, put the sample + * into a deferred fifo. On the other hand, if only skb + * may be modified, the actions can be executed in place. + * + * Do this analysis at the flow installation time. + * Set 'clone_action->exec' to true if the actions can be + * executed without being deferred. + * + * If the sample is the last action, it can always be excuted + * rather than deferred. + */ + arg.exec = last || !actions_may_change_flow(actions); + arg.probability = nla_get_u32(probability); + + err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg), + log); if (err) return err; - st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log); - if (st_acts < 0) - return st_acts; - err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa, + err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, log); + if (err) return err; - add_nested_action_end(*sfa, st_acts); add_nested_action_end(*sfa, start); return 0; @@ -2408,16 +2455,13 @@ static int copy_action(const struct nlattr *from, static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, - int depth, struct sw_flow_actions **sfa, + struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, bool log) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; - if (depth >= SAMPLE_ACTION_DEPTH) - return -EOVERFLOW; - nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -2555,13 +2599,17 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return err; break; - case OVS_ACTION_ATTR_SAMPLE: - err = validate_and_copy_sample(net, a, key, depth, sfa, - eth_type, vlan_tci, log); + case OVS_ACTION_ATTR_SAMPLE: { + bool last = nla_is_last(a, rem); + + err = validate_and_copy_sample(net, a, key, sfa, + eth_type, vlan_tci, + log, last); if (err) return err; skip_copy = true; break; + } case OVS_ACTION_ATTR_CT: err = ovs_ct_copy_action(net, a, key, sfa, log); @@ -2615,7 +2663,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return PTR_ERR(*sfa); (*sfa)->orig_len = nla_len(attr); - err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type, + err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, key->eth.vlan.tci, log); if (err) ovs_nla_free_flow_actions(*sfa); @@ -2623,39 +2671,44 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return err; } -static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) +static int sample_action_to_attr(const struct nlattr *attr, + struct sk_buff *skb) { - const struct nlattr *a; - struct nlattr *start; - int err = 0, rem; + struct nlattr *start, *ac_start = NULL, *sample_arg; + int err = 0, rem = nla_len(attr); + const struct sample_arg *arg; + struct nlattr *actions; start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE); if (!start) return -EMSGSIZE; - nla_for_each_nested(a, attr, rem) { - int type = nla_type(a); - struct nlattr *st_sample; + sample_arg = nla_data(attr); + arg = nla_data(sample_arg); + actions = nla_next(sample_arg, &rem); - switch (type) { - case OVS_SAMPLE_ATTR_PROBABILITY: - if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY, - sizeof(u32), nla_data(a))) - return -EMSGSIZE; - break; - case OVS_SAMPLE_ATTR_ACTIONS: - st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS); - if (!st_sample) - return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); - if (err) - return err; - nla_nest_end(skb, st_sample); - break; - } + if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) { + err = -EMSGSIZE; + goto out; + } + + ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS); + if (!ac_start) { + err = -EMSGSIZE; + goto out; + } + + err = ovs_nla_put_actions(actions, rem, skb); + +out: + if (err) { + nla_nest_cancel(skb, ac_start); + nla_nest_cancel(skb, start); + } else { + nla_nest_end(skb, ac_start); + nla_nest_end(skb, start); } - nla_nest_end(skb, start); return err; } diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig index b83c6807a5ae..326fd97444f5 100644 --- a/net/qrtr/Kconfig +++ b/net/qrtr/Kconfig @@ -16,7 +16,7 @@ if QRTR config QRTR_SMD tristate "SMD IPC Router channels" - depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n) + depends on RPMSG || (COMPILE_TEST && RPMSG=n) ---help--- Say Y here to support SMD based ipcrouter channels. SMD is the most common transport for IPC Router. diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c index 0d11132b3370..50615d5efac1 100644 --- a/net/qrtr/smd.c +++ b/net/qrtr/smd.c @@ -14,21 +14,21 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/soc/qcom/smd.h> +#include <linux/rpmsg.h> #include "qrtr.h" struct qrtr_smd_dev { struct qrtr_endpoint ep; - struct qcom_smd_channel *channel; + struct rpmsg_endpoint *channel; struct device *dev; }; /* from smd to qrtr */ -static int qcom_smd_qrtr_callback(struct qcom_smd_channel *channel, - const void *data, size_t len) +static int qcom_smd_qrtr_callback(struct rpmsg_device *rpdev, + void *data, int len, void *priv, u32 addr) { - struct qrtr_smd_dev *qdev = qcom_smd_get_drvdata(channel); + struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev); int rc; if (!qdev) @@ -54,7 +54,7 @@ static int qcom_smd_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) if (rc) goto out; - rc = qcom_smd_send(qdev->channel, skb->data, skb->len); + rc = rpmsg_send(qdev->channel, skb->data, skb->len); out: if (rc) @@ -64,57 +64,55 @@ out: return rc; } -static int qcom_smd_qrtr_probe(struct qcom_smd_device *sdev) +static int qcom_smd_qrtr_probe(struct rpmsg_device *rpdev) { struct qrtr_smd_dev *qdev; int rc; - qdev = devm_kzalloc(&sdev->dev, sizeof(*qdev), GFP_KERNEL); + qdev = devm_kzalloc(&rpdev->dev, sizeof(*qdev), GFP_KERNEL); if (!qdev) return -ENOMEM; - qdev->channel = sdev->channel; - qdev->dev = &sdev->dev; + qdev->channel = rpdev->ept; + qdev->dev = &rpdev->dev; qdev->ep.xmit = qcom_smd_qrtr_send; rc = qrtr_endpoint_register(&qdev->ep, QRTR_EP_NID_AUTO); if (rc) return rc; - qcom_smd_set_drvdata(sdev->channel, qdev); - dev_set_drvdata(&sdev->dev, qdev); + dev_set_drvdata(&rpdev->dev, qdev); - dev_dbg(&sdev->dev, "Qualcomm SMD QRTR driver probed\n"); + dev_dbg(&rpdev->dev, "Qualcomm SMD QRTR driver probed\n"); return 0; } -static void qcom_smd_qrtr_remove(struct qcom_smd_device *sdev) +static void qcom_smd_qrtr_remove(struct rpmsg_device *rpdev) { - struct qrtr_smd_dev *qdev = dev_get_drvdata(&sdev->dev); + struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev); qrtr_endpoint_unregister(&qdev->ep); - dev_set_drvdata(&sdev->dev, NULL); + dev_set_drvdata(&rpdev->dev, NULL); } -static const struct qcom_smd_id qcom_smd_qrtr_smd_match[] = { +static const struct rpmsg_device_id qcom_smd_qrtr_smd_match[] = { { "IPCRTR" }, {} }; -static struct qcom_smd_driver qcom_smd_qrtr_driver = { +static struct rpmsg_driver qcom_smd_qrtr_driver = { .probe = qcom_smd_qrtr_probe, .remove = qcom_smd_qrtr_remove, .callback = qcom_smd_qrtr_callback, - .smd_match_table = qcom_smd_qrtr_smd_match, - .driver = { + .id_table = qcom_smd_qrtr_smd_match, + .drv = { .name = "qcom_smd_qrtr", - .owner = THIS_MODULE, }, }; -module_qcom_smd_driver(qcom_smd_qrtr_driver); +module_rpmsg_driver(qcom_smd_qrtr_driver); MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/connection.c b/net/rds/connection.c index 1fa75ab7b733..6a5ebdea7d2e 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -333,11 +333,19 @@ void rds_conn_shutdown(struct rds_conn_path *cp) rds_conn_path_reset(cp); if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, + RDS_CONN_DOWN) && + !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { /* This can happen - eg when we're in the middle of tearing * down the connection, and someone unloads the rds module. - * Quite reproduceable with loopback connections. + * Quite reproducible with loopback connections. * Mostly harmless. + * + * Note that this also happens with rds-tcp because + * we could have triggered rds_conn_path_drop in irq + * mode from rds_tcp_state change on the receipt of + * a FIN, thus we need to recheck for RDS_CONN_ERROR + * here. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 1c38d2c7caa8..80fb6f63e768 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -702,9 +702,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, event->param.conn.initiator_depth); /* rdma_accept() calls rdma_reject() internally if it fails */ - err = rdma_accept(cm_id, &conn_param); - if (err) - rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err); + if (rdma_accept(cm_id, &conn_param)) + rds_ib_conn_error(conn, "rdma_accept failed\n"); out: if (conn) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 4fe8f4fec4ee..86ef907067bb 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -78,17 +78,15 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) return ibmr; out_no_cigar: - if (ibmr) { - if (fmr->fmr) - ib_dealloc_fmr(fmr->fmr); - kfree(ibmr); - } + kfree(ibmr); atomic_dec(&pool->item_count); + return ERR_PTR(err); } -int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, - struct scatterlist *sg, unsigned int nents) +static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, + struct rds_ib_mr *ibmr, struct scatterlist *sg, + unsigned int nents) { struct ib_device *dev = rds_ibdev->dev; struct rds_ib_fmr *fmr = &ibmr->u.fmr; @@ -114,29 +112,39 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); if (dma_addr & ~PAGE_MASK) { - if (i > 0) + if (i > 0) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } if ((dma_addr + dma_len) & ~PAGE_MASK) { - if (i < sg_dma_len - 1) + if (i < sg_dma_len - 1) { + ib_dma_unmap_sg(dev, sg, nents, + DMA_BIDIRECTIONAL); return -EINVAL; - else + } else { ++page_cnt; + } } len += dma_len; } page_cnt += len >> PAGE_SHIFT; - if (page_cnt > ibmr->pool->fmr_attr.max_pages) + if (page_cnt > ibmr->pool->fmr_attr.max_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -EINVAL; + } dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC, rdsibdev_to_node(rds_ibdev)); - if (!dma_pages) + if (!dma_pages) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -ENOMEM; + } page_cnt = 0; for (i = 0; i < sg_dma_len; ++i) { @@ -149,8 +157,10 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr, } ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr); - if (ret) + if (ret) { + ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); goto out; + } /* Success - we successfully remapped the MR, so we can * safely tear down the old mapping. diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 5d6e98a79a5e..0ea4ab017a8c 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -125,8 +125,6 @@ void rds_ib_mr_exit(void); void __rds_ib_teardown_mr(struct rds_ib_mr *); void rds_ib_teardown_mr(struct rds_ib_mr *); struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int); -int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *, - struct scatterlist *, unsigned int); struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *); int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **); struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *, diff --git a/net/rds/threads.c b/net/rds/threads.c index e36e333a0aa0..3e447d056d09 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -156,7 +156,7 @@ void rds_connect_worker(struct work_struct *work) struct rds_connection *conn = cp->cp_conn; int ret; - if (cp->cp_index > 1 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr) + if (cp->cp_index > 0 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr) return; clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index e978ccd4402c..6c319a40c1cc 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -181,6 +181,9 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl, struct tcphdr *tcph; const struct iphdr *iph; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + return 1; + tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; @@ -202,6 +205,9 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl, struct tcphdr *tcph; const struct ipv6hdr *ip6h; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + return 1; + tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; @@ -225,6 +231,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, const struct iphdr *iph; u16 ul; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + return 1; + /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, @@ -278,6 +287,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, const struct ipv6hdr *ip6h; u16 ul; + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + return 1; + /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 71e7ff22f7c9..c75ea5c9102c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -603,8 +603,8 @@ nla_put_failure: return -1; } -int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, - u16 metaid, u16 mlen, void *mdata) +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, + u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 3d6b9286c203..ca193af8634a 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -508,9 +508,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - fnew->perturb_timer.function = flow_perturbation; - fnew->perturb_timer.data = (unsigned long)fnew; - init_timer_deferrable(&fnew->perturb_timer); + setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, + (unsigned long)fnew); tcf_exts_change(tp, &fnew->exts, &e); tcf_em_tree_change(tp, &fnew->ematches, &t); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bcf49cd22786..62567bfe52c7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -274,7 +274,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) return NULL; } -void qdisc_hash_add(struct Qdisc *q) +void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { struct Qdisc *root = qdisc_dev(q)->qdisc; @@ -282,6 +282,8 @@ void qdisc_hash_add(struct Qdisc *q) WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); + if (invisible) + q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); @@ -1003,7 +1005,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, goto err_out4; } - qdisc_hash_add(sch); + qdisc_hash_add(sch, false); return sch; } @@ -1401,9 +1403,14 @@ nla_put_failure: return -1; } -static bool tc_qdisc_dump_ignore(struct Qdisc *q) +static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { - return (q->flags & TCQ_F_BUILTIN) ? true : false; + if (q->flags & TCQ_F_BUILTIN) + return true; + if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) + return true; + + return false; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, @@ -1417,12 +1424,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (old && !tc_qdisc_dump_ignore(old)) { + if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) goto err_out; } - if (new && !tc_qdisc_dump_ignore(new)) { + if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; @@ -1439,7 +1446,8 @@ err_out: static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, - int *q_idx_p, int s_q_idx, bool recur) + int *q_idx_p, int s_q_idx, bool recur, + bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; @@ -1452,7 +1460,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (q_idx < s_q_idx) { q_idx++; } else { - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1474,7 +1482,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) @@ -1496,12 +1504,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; + const struct nlmsghdr *nlh = cb->nlh; + struct tcmsg *tcm = nlmsg_data(nlh); + struct nlattr *tca[TCA_MAX + 1]; + int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); + + err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL); + if (err < 0) + return err; + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; @@ -1512,13 +1529,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) q_idx = 0; if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, - true) < 0) + true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false) < 0) + &q_idx, s_q_idx, false, + tca[TCA_DUMP_INVISIBLE]) < 0) goto done; cont: @@ -1762,7 +1780,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, { struct qdisc_dump_args arg; - if (tc_qdisc_dump_ignore(q) || + if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index d6ca18dc04c3..cf93e5ff3d63 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (!q->link.q) q->link.q = &noop_qdisc; + else + qdisc_hash_add(q->link.q, true); q->link.priority = TC_CBQ_MAXPRIO - 1; q->link.priority2 = TC_CBQ_MAXPRIO - 1; @@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!cl->q) cl->q = &noop_qdisc; + else + qdisc_hash_add(cl->q, true); + cl->common.classid = classid; cl->tparent = parent; cl->qdisc = sch; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 3b86a97bc67c..593183a5b5b5 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -58,7 +58,6 @@ struct choke_sched_data { /* Variables */ struct red_vars vars; - struct tcf_proto __rcu *filter_list; struct { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ @@ -152,11 +151,6 @@ static inline void choke_set_classid(struct sk_buff *skb, u16 classid) choke_skb_cb(skb)->classid = classid; } -static u16 choke_get_classid(const struct sk_buff *skb) -{ - return choke_skb_cb(skb)->classid; -} - /* * Compare flow of two packets * Returns true only if source and destination address and port match. @@ -188,40 +182,6 @@ static bool choke_match_flow(struct sk_buff *skb1, } /* - * Classify flow using either: - * 1. pre-existing classification result in skb - * 2. fast internal classification - * 3. use TC filter based classification - */ -static bool choke_classify(struct sk_buff *skb, - struct Qdisc *sch, int *qerr) - -{ - struct choke_sched_data *q = qdisc_priv(sch); - struct tcf_result res; - struct tcf_proto *fl; - int result; - - fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); - if (result >= 0) { -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_STOLEN: - case TC_ACT_QUEUED: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - return false; - } -#endif - choke_set_classid(skb, TC_H_MIN(res.classid)); - return true; - } - - return false; -} - -/* * Select a packet at random from queue * HACK: since queue can have holes from previous deletion; retry several * times to find a random skb but then just give up and return the head @@ -257,25 +217,15 @@ static bool choke_match_random(const struct choke_sched_data *q, return false; oskb = choke_peek_random(q, pidx); - if (rcu_access_pointer(q->filter_list)) - return choke_get_classid(nskb) == choke_get_classid(oskb); - return choke_match_flow(oskb, nskb); } static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; struct choke_sched_data *q = qdisc_priv(sch); const struct red_parms *p = &q->parms; - if (rcu_access_pointer(q->filter_list)) { - /* If using external classifiers, get result and record it. */ - if (!choke_classify(skb, sch, &ret)) - goto other_drop; /* Packet was eaten by filter */ - } - choke_skb_cb(skb)->keys_valid = 0; /* Compute average queue usage (see RED) */ q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen); @@ -339,12 +289,6 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, congestion_drop: qdisc_drop(skb, sch, to_free); return NET_XMIT_CN; - -other_drop: - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; } static struct sk_buff *choke_dequeue(struct Qdisc *sch) @@ -538,7 +482,6 @@ static void choke_destroy(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); choke_free(q->tab); } diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index bb4cbdf75004..9fe67e257dfa 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 5334e309f17f..cfa1f2cdbaf7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -374,6 +374,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (p->q == NULL) p->q = &noop_qdisc; + else + qdisc_hash_add(p->q, true); pr_debug("%s: qdisc %p\n", __func__, p->q); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9f3a884d1590..097bbe9857a5 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct fq_codel_flow *flow; struct list_head *head; u32 prev_drop_count, prev_ecn_mark; - unsigned int prev_backlog; begin: head = &q->new_flows; @@ -307,7 +306,6 @@ begin: prev_drop_count = q->cstats.drop_count; prev_ecn_mark = q->cstats.ecn_mark; - prev_backlog = sch->qstats.backlog; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b052b27a984e..3e64d23e098c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -795,7 +795,7 @@ static void attach_default_qdiscs(struct net_device *dev) } #ifdef CONFIG_NET_SCHED if (dev->qdisc) - qdisc_hash_add(dev->qdisc); + qdisc_hash_add(dev->qdisc, false); #endif } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3ffaa6fb0990..0198c6cdda49 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; + else + qdisc_hash_add(cl->qdisc, true); INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; @@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; + else + qdisc_hash_add(q->root.qdisc, true); INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4cd5fb134bc9..95867033542e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; + if (cl->un.leaf.q != &noop_qdisc) + qdisc_hash_add(cl->un.leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 20b7f1646f69..cadfdd4f1e52 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch) qdisc_destroy(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); #endif } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 922683418e53..0a4cf27ea54b 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -21,14 +21,13 @@ struct mqprio_sched { struct Qdisc **qdiscs; - int hw_owned; + int hw_offload; }; static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO}; unsigned int ntx; if (priv->qdiscs) { @@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { + struct tc_mqprio_qopt offload = { 0 }; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); - else + } else { netdev_set_num_tc(dev, 0); + } } static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) @@ -59,15 +63,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return -EINVAL; } - /* net_device does not support requested operation */ - if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) - return -EINVAL; + /* Limit qopt->hw to maximum supported offload value. Drivers have + * the option of overriding this later if they don't support the a + * given offload type. + */ + if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) + qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* if hw owned qcount and qoffset are taken from LLD so - * no reason to verify them here + /* If hardware offload is requested we will leave it to the device + * to either populate the queue counts itself or to validate the + * provided queue counts. If ndo_setup_tc is not present then + * hardware doesn't support offload and we should return an error. */ if (qopt->hw) - return 0; + return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; for (i = 0; i < qopt->num_tc; i++) { unsigned int last = qopt->offset[i] + qopt->count[i]; @@ -139,13 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO, - { .tc = qopt->num_tc }}; + struct tc_mqprio_qopt offload = *qopt; + struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, + { .mqprio = &offload } }; - priv->hw_owned = 1; err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); if (err) return err; + + priv->hw_offload = offload.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -175,7 +186,7 @@ static void mqprio_attach(struct Qdisc *sch) if (old) qdisc_destroy(old); if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc); + qdisc_hash_add(qdisc, false); } kfree(priv->qdiscs); priv->qdiscs = NULL; @@ -243,7 +254,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.num_tc = netdev_get_num_tc(dev); memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - opt.hw = priv->hw_owned; + opt.hw = priv->hw_offload; for (i = 0; i < netdev_get_num_tc(dev); i++) { opt.count[i] = dev->tc_to_txq[i].count; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e7839a0d0eaa..43a3a10b3c81 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); old = q->queues[i]; q->queues[i] = child; + if (child != &noop_qdisc) + qdisc_hash_add(child, true); if (old != &noop_qdisc) { qdisc_tree_reduce_backlog(old, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index c8bb62a1e744..94b4928ad413 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ - if (q->latency || q->jitter) + if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* @@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, now = psched_get_time(); if (q->rate) { - struct sk_buff *last; + struct netem_skb_cb *last = NULL; + + if (sch->q.tail) + last = netem_skb_cb(sch->q.tail); + if (q->t_root.rb_node) { + struct sk_buff *t_skb; + struct netem_skb_cb *t_last; + + t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_last = netem_skb_cb(t_skb); + if (!last || + t_last->time_to_send > last->time_to_send) { + last = t_last; + } + } - if (sch->q.qlen) - last = sch->q.tail; - else - last = netem_rb_to_skb(rb_last(&q->t_root)); if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ - delay -= netem_skb_cb(last)->time_to_send - now; + delay -= last->time_to_send - now; delay = max_t(psched_tdiff_t, 0, delay); - now = netem_skb_cb(last)->time_to_send; + now = last->time_to_send; } delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index d4d7db267b6e..92c2e6d448d7 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) qdisc_destroy(child); } - for (i = oldbands; i < q->bands; i++) + for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; + if (q->queues[i] != &noop_qdisc) + qdisc_hash_add(q->queues[i], true); + } sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f9e712ce2d15..6c85f3e9239b 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -494,6 +494,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, goto destroy_class; } + if (cl->qdisc != &noop_qdisc) + qdisc_hash_add(cl->qdisc, true); sch_tree_lock(sch); qdisc_class_hash_insert(&q->clhash, &cl->common); sch_tree_unlock(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 249b2a18acbd..799ea6dd69b2 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return PTR_ERR(child); } + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index fe6963d21519..ae862f172c94 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) if (IS_ERR(child)) return PTR_ERR(child); + if (child != &noop_qdisc) + qdisc_hash_add(child, true); sch_tree_lock(sch); qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 42e8c8615e65..b00e02c139de 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -714,9 +714,8 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) struct sfq_sched_data *q = qdisc_priv(sch); int i; - q->perturb_timer.function = sfq_perturbation; - q->perturb_timer.data = (unsigned long)sch; - init_timer_deferrable(&q->perturb_timer); + setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, + (unsigned long)sch); for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) { q->dep[i].next = i + SFQ_MAX_FLOWS; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 303355c449ab..9850126129a3 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; + if (child != &noop_qdisc) + qdisc_hash_add(child, true); } q->limit = qopt->limit; if (tb[TCA_TBF_PBURST]) diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index e3621cb4827f..697721a7a3f1 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -306,14 +306,24 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { - if (chunk->sent_count) + struct sctp_stream_out *streamout = + &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + + if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; - else + streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++; + } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; + streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; + } return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { + struct sctp_stream_out *streamout = + &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; + streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 8081476ed313..fe4c3d462f6e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -353,6 +353,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, struct sctp_chunk *chk, *temp; list_for_each_entry_safe(chk, temp, queue, transmitted_list) { + struct sctp_stream_out *streamout; + if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) continue; @@ -361,8 +363,10 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); + streamout = &asoc->stream->out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; + streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (!chk->tsn_gap_acked) { if (chk->transport) @@ -396,6 +400,12 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->out_qlen -= chk->skb->len; asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) { + struct sctp_stream_out *streamout = + &asoc->stream->out[chk->sinfo.sinfo_stream]; + + streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + } msg_len -= SCTP_DATA_SNDSIZE(chk) + sizeof(struct sk_buff) + diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 24c6ccce7539..4f5e6cfc7f60 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3872,9 +3872,18 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST) reply = sctp_process_strreset_inreq( (struct sctp_association *)asoc, param, &ev); - /* More handles for other types will be added here, by now it - * just ignores other types. - */ + else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST) + reply = sctp_process_strreset_tsnreq( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) + reply = sctp_process_strreset_addstrm_out( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) + reply = sctp_process_strreset_addstrm_in( + (struct sctp_association *)asoc, param, &ev); + else if (param.p->type == SCTP_PARAM_RESET_RESPONSE) + reply = sctp_process_strreset_resp( + (struct sctp_association *)asoc, param, &ev); if (ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c1401f43d40f..8e56df8d175d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3758,6 +3758,39 @@ out: return retval; } +static int sctp_setsockopt_reconfig_supported(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + asoc->reconf_enable = !!params.assoc_value; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + sp->ep->reconf_enable = !!params.assoc_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + static int sctp_setsockopt_enable_strreset(struct sock *sk, char __user *optval, unsigned int optlen) @@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, optval, optlen); break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, optval, optlen); break; @@ -6540,6 +6576,102 @@ out: return retval; } +static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_stream_out *streamout; + struct sctp_association *asoc; + struct sctp_prstatus params; + int retval = -EINVAL; + int policy; + + if (len < sizeof(params)) + goto out; + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) { + retval = -EFAULT; + goto out; + } + + policy = params.sprstat_policy; + if (policy & ~SCTP_PR_SCTP_MASK) + goto out; + + asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); + if (!asoc || params.sprstat_sid >= asoc->stream->outcnt) + goto out; + + streamout = &asoc->stream->out[params.sprstat_sid]; + if (policy == SCTP_PR_SCTP_NONE) { + params.sprstat_abandoned_unsent = 0; + params.sprstat_abandoned_sent = 0; + for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { + params.sprstat_abandoned_unsent += + streamout->abandoned_unsent[policy]; + params.sprstat_abandoned_sent += + streamout->abandoned_sent[policy]; + } + } else { + params.sprstat_abandoned_unsent = + streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)]; + params.sprstat_abandoned_sent = + streamout->abandoned_sent[__SCTP_PR_INDEX(policy)]; + } + + if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) { + retval = -EFAULT; + goto out; + } + + retval = 0; + +out: + return retval; +} + +static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->reconf_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->ep->reconf_enable; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -6748,6 +6880,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; + case SCTP_PR_STREAM_STATUS: + retval = sctp_getsockopt_pr_streamstatus(sk, len, optval, + optlen); + break; + case SCTP_RECONFIG_SUPPORTED: + retval = sctp_getsockopt_reconfig_supported(sk, len, optval, + optlen); + break; case SCTP_ENABLE_STREAM_RESET: retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); @@ -7437,9 +7577,12 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, if (sk->sk_shutdown & RCV_SHUTDOWN) break; - if (sk_can_busy_loop(sk) && - sk_busy_loop(sk, noblock)) - continue; + if (sk_can_busy_loop(sk)) { + sk_busy_loop(sk, noblock); + + if (!skb_queue_empty(&sk->sk_receive_queue)) + continue; + } /* User doesn't want to wait. */ error = -EAGAIN; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index bbed997e1c5f..eff6008a32ba 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -294,18 +294,6 @@ int sctp_send_add_streams(struct sctp_association *asoc, stream->out = streamout; } - if (in) { - struct sctp_stream_in *streamin; - - streamin = krealloc(stream->in, incnt * sizeof(*streamin), - GFP_KERNEL); - if (!streamin) - goto out; - - memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); - stream->in = streamin; - } - chunk = sctp_make_strreset_addstrm(asoc, out, in); if (!chunk) goto out; @@ -330,13 +318,14 @@ out: } static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( - struct sctp_association *asoc, __u32 resp_seq) + struct sctp_association *asoc, __u32 resp_seq, + __be16 type) { struct sctp_chunk *chunk = asoc->strreset_chunk; struct sctp_reconf_chunk *hdr; union sctp_params param; - if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk) + if (!chunk) return NULL; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; @@ -347,7 +336,8 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( */ struct sctp_strreset_tsnreq *req = param.v; - if (req->request_seq == resp_seq) + if ((!resp_seq || req->request_seq == resp_seq) && + (!type || type == req->param_hdr.type)) return param.v; } @@ -388,13 +378,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( goto out; if (asoc->strreset_chunk) { - sctp_paramhdr_t *param_hdr; - struct sctp_transport *t; - - param_hdr = sctp_chunk_lookup_strreset_param( - asoc, outreq->response_seq); - if (!param_hdr || param_hdr->type != - SCTP_PARAM_RESET_IN_REQUEST) { + if (!sctp_chunk_lookup_strreset_param( + asoc, outreq->response_seq, + SCTP_PARAM_RESET_IN_REQUEST)) { /* same process with outstanding isn't 0 */ result = SCTP_STRRESET_ERR_IN_PROGRESS; goto out; @@ -404,6 +390,8 @@ struct sctp_chunk *sctp_process_strreset_outreq( asoc->strreset_outseq++; if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + t = asoc->strreset_chunk->transport; if (del_timer(&t->reconf_timer)) sctp_transport_put(t); @@ -504,3 +492,367 @@ out: return chunk; } + +struct sctp_chunk *sctp_process_strreset_tsnreq( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; + struct sctp_strreset_tsnreq *tsnreq = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + __u32 request_seq; + __u16 i; + + request_seq = ntohl(tsnreq->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + /* G3: The same processing as though a SACK chunk with no gap report + * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were + * received MUST be performed. + */ + max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map); + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + /* G1: Compute an appropriate value for the Receiver's Next TSN -- the + * TSN that the peer should use to send the next DATA chunk. The + * value SHOULD be the smallest TSN not acknowledged by the + * receiver of the request plus 2^31. + */ + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + init_tsn, GFP_ATOMIC); + + /* G4: The same processing as though a FWD-TSN chunk (as defined in + * [RFC3758]) with all streams affected and a new cumulative TSN + * ACK of the Receiver's Next TSN minus 1 were received MUST be + * performed. + */ + sctp_outq_free(&asoc->outqueue); + + /* G2: Compute an appropriate value for the local endpoint's next TSN, + * i.e., the next TSN assigned by the receiver of the SSN/TSN reset + * chunk. The value SHOULD be the highest TSN sent by the receiver + * of the request plus 1. + */ + next_tsn = asoc->next_tsn; + asoc->ctsn_ack_point = next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + /* G5: The next expected and outgoing SSNs MUST be reset to 0 for all + * incoming and outgoing streams. + */ + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn, + next_tsn, GFP_ATOMIC); + +out: + return sctp_make_strreset_tsnresp(asoc, result, request_seq, + next_tsn, init_tsn); +} + +struct sctp_chunk *sctp_process_strreset_addstrm_out( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_in *streamin; + __u32 request_seq, incnt; + __u16 in; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_chunk) { + if (!sctp_chunk_lookup_strreset_param( + asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { + /* same process with outstanding isn't 0 */ + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + if (!asoc->strreset_outstanding) { + struct sctp_transport *t; + + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + } + + in = ntohs(addstrm->number_of_streams); + incnt = stream->incnt + in; + if (!in || incnt > SCTP_MAX_STREAM) + goto out; + + streamin = krealloc(stream->in, incnt * sizeof(*streamin), + GFP_ATOMIC); + if (!streamin) + goto out; + + memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); + stream->in = streamin; + stream->incnt = incnt; + + result = SCTP_STRRESET_PERFORMED; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC); + +out: + return sctp_make_strreset_resp(asoc, result, request_seq); +} + +struct sctp_chunk *sctp_process_strreset_addstrm_in( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_addstrm *addstrm = param.v; + struct sctp_stream *stream = asoc->stream; + __u32 result = SCTP_STRRESET_DENIED; + struct sctp_stream_out *streamout; + struct sctp_chunk *chunk = NULL; + __u32 request_seq, outcnt; + __u16 out; + + request_seq = ntohl(addstrm->request_seq); + if (request_seq > asoc->strreset_inseq) { + result = SCTP_STRRESET_ERR_BAD_SEQNO; + goto out; + } else if (request_seq == asoc->strreset_inseq) { + asoc->strreset_inseq++; + } + + if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) + goto out; + + if (asoc->strreset_outstanding) { + result = SCTP_STRRESET_ERR_IN_PROGRESS; + goto out; + } + + out = ntohs(addstrm->number_of_streams); + outcnt = stream->outcnt + out; + if (!out || outcnt > SCTP_MAX_STREAM) + goto out; + + streamout = krealloc(stream->out, outcnt * sizeof(*streamout), + GFP_ATOMIC); + if (!streamout) + goto out; + + memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); + stream->out = streamout; + + chunk = sctp_make_strreset_addstrm(asoc, out, 0); + if (!chunk) + goto out; + + asoc->strreset_chunk = chunk; + asoc->strreset_outstanding = 1; + sctp_chunk_hold(asoc->strreset_chunk); + + stream->outcnt = outcnt; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, + 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC); + +out: + if (!chunk) + chunk = sctp_make_strreset_resp(asoc, result, request_seq); + + return chunk; +} + +struct sctp_chunk *sctp_process_strreset_resp( + struct sctp_association *asoc, + union sctp_params param, + struct sctp_ulpevent **evp) +{ + struct sctp_strreset_resp *resp = param.v; + struct sctp_stream *stream = asoc->stream; + struct sctp_transport *t; + __u16 i, nums, flags = 0; + sctp_paramhdr_t *req; + __u32 result; + + req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); + if (!req) + return NULL; + + result = ntohl(resp->result); + if (result != SCTP_STRRESET_PERFORMED) { + /* if in progress, do nothing but retransmit */ + if (result == SCTP_STRRESET_IN_PROGRESS) + return NULL; + else if (result == SCTP_STRRESET_DENIED) + flags = SCTP_STREAM_RESET_DENIED; + else + flags = SCTP_STREAM_RESET_FAILED; + } + + if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) { + struct sctp_strreset_outreq *outreq; + __u16 *str_p = NULL; + + outreq = (struct sctp_strreset_outreq *)req; + nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2; + + if (result == SCTP_STRRESET_PERFORMED) { + if (nums) { + str_p = outreq->list_of_streams; + for (i = 0; i < nums; i++) + stream->out[ntohs(str_p[i])].ssn = 0; + } else { + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + } + + flags = SCTP_STREAM_RESET_OUTGOING_SSN; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) { + struct sctp_strreset_inreq *inreq; + __u16 *str_p = NULL; + + /* if the result is performed, it's impossible for inreq */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + inreq = (struct sctp_strreset_inreq *)req; + nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2; + + str_p = inreq->list_of_streams; + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, + nums, str_p, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) { + struct sctp_strreset_resptsn *resptsn; + __u32 stsn, rtsn; + + /* check for resptsn, as sctp_verify_reconf didn't do it*/ + if (ntohs(param.p->length) != sizeof(*resptsn)) + return NULL; + + resptsn = (struct sctp_strreset_resptsn *)resp; + stsn = ntohl(resptsn->senders_next_tsn); + rtsn = ntohl(resptsn->receivers_next_tsn); + + if (result == SCTP_STRRESET_PERFORMED) { + __u32 mtsn = sctp_tsnmap_get_max_tsn_seen( + &asoc->peer.tsn_map); + + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn); + sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + + sctp_tsnmap_init(&asoc->peer.tsn_map, + SCTP_TSN_MAP_INITIAL, + stsn, GFP_ATOMIC); + + sctp_outq_free(&asoc->outqueue); + + asoc->next_tsn = rtsn; + asoc->ctsn_ack_point = asoc->next_tsn - 1; + asoc->adv_peer_ack_point = asoc->ctsn_ack_point; + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].ssn = 0; + for (i = 0; i < stream->incnt; i++) + stream->in[i].ssn = 0; + } + + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + + *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags, + stsn, rtsn, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + __u16 number; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + number = stream->outcnt - nums; + + if (result == SCTP_STRRESET_PERFORMED) + for (i = number; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; + else + stream->outcnt = number; + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + 0, nums, GFP_ATOMIC); + } else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) { + struct sctp_strreset_addstrm *addstrm; + + /* if the result is performed, it's impossible for addstrm in + * request. + */ + if (result == SCTP_STRRESET_PERFORMED) + return NULL; + + addstrm = (struct sctp_strreset_addstrm *)req; + nums = ntohs(addstrm->number_of_streams); + + *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, + nums, 0, GFP_ATOMIC); + } + + asoc->strreset_outstanding--; + asoc->strreset_outseq++; + + /* remove everything for this reconf request */ + if (!asoc->strreset_outstanding) { + t = asoc->strreset_chunk->transport; + if (del_timer(&t->reconf_timer)) + sctp_transport_put(t); + + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + + return NULL; +} diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index daf8554fd42a..0e732f68c2bf 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -275,6 +275,13 @@ static struct ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "reconf_enable", + .data = &init_net.sctp.reconf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "auth_enable", .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index c8881bc542a0..ec2b3e013c2f 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -883,6 +883,62 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( return event; } +struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( + const struct sctp_association *asoc, __u16 flags, __u32 local_tsn, + __u32 remote_tsn, gfp_t gfp) +{ + struct sctp_assoc_reset_event *areset; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + areset = (struct sctp_assoc_reset_event *) + skb_put(skb, sizeof(struct sctp_assoc_reset_event)); + + areset->assocreset_type = SCTP_ASSOC_RESET_EVENT; + areset->assocreset_flags = flags; + areset->assocreset_length = sizeof(struct sctp_assoc_reset_event); + sctp_ulpevent_set_owner(event, asoc); + areset->assocreset_assoc_id = sctp_assoc2id(asoc); + areset->assocreset_local_tsn = local_tsn; + areset->assocreset_remote_tsn = remote_tsn; + + return event; +} + +struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( + const struct sctp_association *asoc, __u16 flags, + __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp) +{ + struct sctp_stream_change_event *schange; + struct sctp_ulpevent *event; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + schange = (struct sctp_stream_change_event *) + skb_put(skb, sizeof(struct sctp_stream_change_event)); + + schange->strchange_type = SCTP_STREAM_CHANGE_EVENT; + schange->strchange_flags = flags; + schange->strchange_length = sizeof(struct sctp_stream_change_event); + sctp_ulpevent_set_owner(event, asoc); + schange->strchange_assoc_id = sctp_assoc2id(asoc); + schange->strchange_instrms = strchange_instrms; + schange->strchange_outstrms = strchange_outstrms; + + return event; +} + /* Return the notification type, assuming this is a notification * event. */ diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index a95f74bb5569..7e1f0e24d177 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -11,6 +11,7 @@ #ifndef _SMC_IB_H #define _SMC_IB_H +#include <linux/interrupt.h> #include <linux/if_ether.h> #include <rdma/ib_verbs.h> diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 9be6592e4a6f..bd0aac87b41a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -416,6 +416,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns); + tipc_subscrp_get(s); list_add(&s->nameseq_list, &nseq->subscriptions); if (!sseq) @@ -787,6 +788,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) if (seq != NULL) { spin_lock_bh(&seq->lock); list_del_init(&s->nameseq_list); + tipc_subscrp_put(s); if (!seq->first_free && list_empty(&seq->subscriptions)) { hlist_del_init_rcu(&seq->ns_list); kfree(seq->sseqs); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 7130e73bd42c..15f6ce7bf868 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2511,6 +2511,28 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } } +static int tipc_socketpair(struct socket *sock1, struct socket *sock2) +{ + struct tipc_sock *tsk2 = tipc_sk(sock2->sk); + struct tipc_sock *tsk1 = tipc_sk(sock1->sk); + u32 onode = tipc_own_addr(sock_net(sock1->sk)); + + tsk1->peer.family = AF_TIPC; + tsk1->peer.addrtype = TIPC_ADDR_ID; + tsk1->peer.scope = TIPC_NODE_SCOPE; + tsk1->peer.addr.id.ref = tsk2->portid; + tsk1->peer.addr.id.node = onode; + tsk2->peer.family = AF_TIPC; + tsk2->peer.addrtype = TIPC_ADDR_ID; + tsk2->peer.scope = TIPC_NODE_SCOPE; + tsk2->peer.addr.id.ref = tsk1->portid; + tsk2->peer.addr.id.node = onode; + + tipc_sk_finish_conn(tsk1, tsk2->portid, onode); + tipc_sk_finish_conn(tsk2, tsk1->portid, onode); + return 0; +} + /* Protocol switches for the various types of TIPC sockets */ static const struct proto_ops msg_ops = { @@ -2519,7 +2541,7 @@ static const struct proto_ops msg_ops = { .release = tipc_release, .bind = tipc_bind, .connect = tipc_connect, - .socketpair = sock_no_socketpair, + .socketpair = tipc_socketpair, .accept = sock_no_accept, .getname = tipc_getname, .poll = tipc_poll, @@ -2540,7 +2562,7 @@ static const struct proto_ops packet_ops = { .release = tipc_release, .bind = tipc_bind, .connect = tipc_connect, - .socketpair = sock_no_socketpair, + .socketpair = tipc_socketpair, .accept = tipc_accept, .getname = tipc_getname, .poll = tipc_poll, @@ -2561,7 +2583,7 @@ static const struct proto_ops stream_ops = { .release = tipc_release, .bind = tipc_bind, .connect = tipc_connect, - .socketpair = sock_no_socketpair, + .socketpair = tipc_socketpair, .accept = tipc_accept, .getname = tipc_getname, .poll = tipc_poll, diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 271cd66e4b3b..0bf91cd3733c 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -54,8 +54,6 @@ struct tipc_subscriber { static void tipc_subscrp_delete(struct tipc_subscription *sub); static void tipc_subscrb_put(struct tipc_subscriber *subscriber); -static void tipc_subscrp_put(struct tipc_subscription *subscription); -static void tipc_subscrp_get(struct tipc_subscription *subscription); /** * htohl - convert value to endianness used by destination @@ -125,7 +123,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, { struct tipc_name_seq seq; - tipc_subscrp_get(sub); tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq); if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper)) return; @@ -135,7 +132,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref, node); - tipc_subscrp_put(sub); } static void tipc_subscrp_timeout(unsigned long data) @@ -145,6 +141,7 @@ static void tipc_subscrp_timeout(unsigned long data) spin_lock_bh(&subscriber->lock); tipc_nametbl_unsubscribe(sub); + list_del(&sub->subscrp_list); spin_unlock_bh(&subscriber->lock); /* Notify subscriber of timeout */ @@ -177,20 +174,17 @@ static void tipc_subscrp_kref_release(struct kref *kref) struct tipc_net *tn = net_generic(sub->net, tipc_net_id); struct tipc_subscriber *subscriber = sub->subscriber; - spin_lock_bh(&subscriber->lock); - list_del(&sub->subscrp_list); atomic_dec(&tn->subscription_count); - spin_unlock_bh(&subscriber->lock); kfree(sub); tipc_subscrb_put(subscriber); } -static void tipc_subscrp_put(struct tipc_subscription *subscription) +void tipc_subscrp_put(struct tipc_subscription *subscription) { kref_put(&subscription->kref, tipc_subscrp_kref_release); } -static void tipc_subscrp_get(struct tipc_subscription *subscription) +void tipc_subscrp_get(struct tipc_subscription *subscription) { kref_get(&subscription->kref); } @@ -210,11 +204,8 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, continue; tipc_nametbl_unsubscribe(sub); - tipc_subscrp_get(sub); - spin_unlock_bh(&subscriber->lock); + list_del(&sub->subscrp_list); tipc_subscrp_delete(sub); - tipc_subscrp_put(sub); - spin_lock_bh(&subscriber->lock); if (s) break; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index ffdc214c117a..ee52957dc952 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -78,4 +78,7 @@ u32 tipc_subscrp_convert_seq_type(u32 type, int swap); int tipc_topsrv_start(struct net *net); void tipc_topsrv_stop(struct net *net); +void tipc_subscrp_put(struct tipc_subscription *subscription); +void tipc_subscrp_get(struct tipc_subscription *subscription); + #endif diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 4be4fbbc0b50..10ae7823a19d 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -96,31 +96,23 @@ static int PROTOCOL_OVERRIDE = -1; static s32 vmci_transport_error_to_vsock_error(s32 vmci_error) { - int err; - switch (vmci_error) { case VMCI_ERROR_NO_MEM: - err = ENOMEM; - break; + return -ENOMEM; case VMCI_ERROR_DUPLICATE_ENTRY: case VMCI_ERROR_ALREADY_EXISTS: - err = EADDRINUSE; - break; + return -EADDRINUSE; case VMCI_ERROR_NO_ACCESS: - err = EPERM; - break; + return -EPERM; case VMCI_ERROR_NO_RESOURCES: - err = ENOBUFS; - break; + return -ENOBUFS; case VMCI_ERROR_INVALID_RESOURCE: - err = EHOSTUNREACH; - break; + return -EHOSTUNREACH; case VMCI_ERROR_INVALID_ARGS: default: - err = EINVAL; + break; } - - return err > 0 ? -err : err; + return -EINVAL; } static u32 vmci_transport_peer_rid(u32 peer_cid) |